LoRA for Sentiment Analysis#
📗 You can find an interactive Colab version of this tutorial here.
Low Rank Adaptation (LoRA) is a technique used to modify and fine tune large language models in a more efficient way. Rather than modifying all of the model weights, LoRAs find two low dimensional matrices that have the lowest rank. It then multiplies the two matrices to find the fine tuned weight matrix. This fine tuned weight matrix will be the same size as the original pre trained weight matrix. Once the fine tuned matrix has been found it can then be applied to the model’s layers.
Fine tuning with a LoRA is a part of the Parameter Efficient Fine Tuning (PEFT) family because it keeps the original model unchanged and introduces a small number of layers or parameters instead. Once the fine tuned matrix has been calculated, it is applied to the last Multilayer Perceptron (MLP) layer of the model. Once the LoRA has been applied, the model is fine tuned based on a knowledge base or domain specific dataset.
Setup#
Make sure you have obtained your NDIF API key and configured your workspace for remote execution.
The following packages need to be installed for this tutorial:
!pip install nnsight
!pip install pyarrow==15.0.2
!pip install datasets
!pip install datasets torch
[ ]:
from IPython.display import clear_output
from nnsight import CONFIG
CONFIG.set_default_api_key('YOUR API KEY HERE')
!huggingface-cli login --token YOUR_HF_TOKEN_HERE # <- Copy your hugging face token here
clear_output()
The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.
Token is valid (permission: read).
Your token has been saved to /root/.cache/huggingface/token
Login successful
Here are the imports needed for this tutorial.
[ ]:
import torch
import torch.nn as nn
import pandas as pd
from nnsight import LanguageModel
from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModelForCausalLM
from transformers import TrainingArguments, Trainer
from torch.utils.data import DataLoader, Subset
from datasets import load_dataset
Prepare Data#
For this tutorial we will be using the The Stanford Sentiment Treebank (SST2). It consists of sentences from movie reviews and human annotations of their sentiment. The task is to predict the sentiment of a given sentence as being either positive or negative. In the dataset, the positive/negative labels of each phrase are represented by a 0 for each negative statement and a 1 for each positive statement.
[ ]:
# GLUE is a standard Natural Language Processing (NLP) benchmark which is commonly used for sentiment analysis tasks.
# It is responisble for assessing the effectiveness of language models across various NLP tasks.
# It serves as a standard for evaluating a model's ability to understand and process language.
dataset = load_dataset("glue", "sst2")
# 0 = neg, 1 = pos
def label_to_str(example):
example['label'] = 'positive' if example['label'] == 1 else 'negative'
return example
train_data = [(dataset['sentence'], 'positive' if dataset['label'] == 1 else 'negative') for dataset in dataset['train']]
validation_data = [(dataset['sentence'], 'positive' if dataset['label'] == 1 else 'negative') for dataset in dataset['validation']]
/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning:
The secret `HF_TOKEN` does not exist in your Colab secrets.
To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.
You will be able to reuse this secret in all of your notebooks.
Please note that authentication is recommended but still optional to access public models or datasets.
warnings.warn(
Next, we need to tokenize our data. Tokenizing involves converting text into a numerical representation. It is a popular technique in NLP because it helps the models better understand the text and output a more accurate result.
[ ]:
tokenizer = AutoTokenizer.from_pretrained('openai-community/gpt2', add_prefix_space=True)
tokenizer.pad_token = tokenizer.eos_token
# Uses the tokenizer from the model to tokenize a given sentence with padding and truncation
def tokenize_function(text):
return tokenizer(text['sentence'], padding='max_length', truncation=True, max_length=10, return_tensors='pt')
# We use .map() in order to apply the tokenization function to all the training data.
#tokenized_train = map(tokenize_function, train_data)
tokenized_train_dataset = dataset['train'].map(tokenize_function, batched=True, batch_size=10)
tokenized_train_dataset = tokenized_train_dataset.map(lambda x: {'input_ids': x['input_ids'], 'attention_mask': x['attention_mask'], 'labels': x['label']})
Prepare our Model#
For this tutorial we will be using the Llama-70B language model.
[ ]:
# Use the LanguageModel wrapper class to load in the Llama model
model_name = "meta-llama/Meta-Llama-3.1-70B"
model = LanguageModel(model_name, device_map='auto')
This is the model architechure before the LoRA has been applied. After the model has been fine tuned with the LoRA, the last MLP layer of the model will be replaced with the LoRA.
We’re going to train a very simple LORA that, when applied, will make our model determine whether a sentence is displaying a positive sentiment or a negative sentiment.
[ ]:
from nnsight.envoy import Envoy
# We will define a LORA class.
# The LORA class call method operations are simply traced like you would normally do in a .trace.
class LORA(nn.Module):
def __init__(self, module: Envoy, dim: int, r: int) -> None:
"""Init.
Args:
module (Envoy): Which model Module we are adding the LORA to.
dim (int): Dimension of the layer we are adding to (This could potentially be auto populated if the user scanned first so we know the shape)
r (int): Inner dimension of the LORA
"""
super(LORA, self).__init__()
self.r = r
self.module = module
self.WA = torch.nn.Parameter(torch.randn(dim, self.r), requires_grad=True).save()
self.WB = torch.nn.Parameter(torch.zeros(self.r, dim), requires_grad=True).save()
# The Call method defines how to actually apply the LORA.
# happens after the forward pass
def __call__(self, alpha: float = 1.0):
"""Call.
Args:
alpha (float, optional): How much to apply the LORA. Can be altered after training for inference. Defaults to 1.0.
"""
# We apply WA to the first positional arg (the hidden states)
A_x = torch.matmul(self.module.input, self.WA)
BA_x = torch.matmul(A_x, self.WB)
# LORA is additive
h = BA_x + self.module.output
# Replace the output with our new one * alpha
# Could also have been self.module.output[:] = h * alpha, for in-place
self.module.output = h * alpha
def parameters(self):
# Some way to get all the parameters.
return [self.WA, self.WB]
LLM Fine Tuning#
[ ]:
# Inner LORA dimension
lora_dim = 4
# Module to train LORA on
# Accesses the last mlp layer of the model
module = model.model.layers[-1].mlp
We can use the .scan() method to get the shape of the module without having to fully run the model.
[ ]:
with model.scan(" "):
dim = module.output.shape[-1]
print(dim)
Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32)
8192
[ ]:
# The LORA object itself isn't transmitted to the server. Only the forward / call method.
# The parameters are created remotely and never sent only retrieved
with model.session(remote=True) as session:
dataset = tokenized_train_dataset
# Smaller chunks to run faster, feel free to increase
indices = list(range(0, 5000))
subset = Subset(dataset, indices)
# Create a dataloader from it.
dataloader = DataLoader(subset, batch_size=10)
# Create our LORA on the last mlp and apply it to the model
lora = LORA(module, dim, lora_dim)
# Create an optimizer. Use the parameters from LORA
optimizer = torch.optim.AdamW(lora.parameters(), lr=3)
# Iterate over dataloader using .iter.
with session.iter(dataloader, return_context=True) as (batch, iterator):
# Accesses the phrase that contains either a positive/negative sentiment
prompt = batch['sentence']
# Determines whether the phrase is positive/negative
correct_token = batch['label']
# Run .trace with prompt
with model.trace(prompt) as tracer:
# Apply LORA to intervention graph just by calling it with .trace
# This is invoke the __call__() method of the LORA class defined above
lora()
# Get logits
# Logits are the output of the neural network before the
# activation function has been applied.
logits = model.lm_head.output
# Do cross entropy on last predicted token and correct_token
loss = torch.nn.functional.cross_entropy(logits[:, -1], batch['label'])
# Call backward
loss.backward()
# Call methods on optimizer. Graphs that arent from .trace (so in this case session and iterator both have their own graph) are executed sequentially.
# The Graph of Iterator here will be:
# 1.) Index batch at 0 for prompt
# 2.) Index batch at 1 for correct_token
# 3.) Execute the .trace using the prompt
# 4.) Call .step() on optimizer
optimizer.step()
# 5.) Call .zero_grad() in optimizer
optimizer.zero_grad()
# 6.) Print out the lora WA weights to show they are indeed changing
iterator.log(lora.WA)
Streaming output truncated to the last 5000 lines.
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4609, 0.8828, 0.3320, 0.0106],
[ 3.3281, -0.1050, 1.3281, 2.9062],
[ 1.9844, -0.1611, 0.3496, 1.0938],
...,
[-1.7109, 0.3262, -1.0625, -2.0469],
[ 1.5391, 0.9219, 0.8750, 1.9531],
[ 2.0156, 1.1953, 1.9453, 2.1562]], requires_grad=True)
2024-10-08 15:05:50,269 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4688, 0.9023, 0.3398, 0.0243],
[ 3.2969, -0.0067, 1.3750, 2.9219],
[ 1.9453, -0.1621, 0.3398, 1.0781],
...,
[-1.6562, 0.2432, -1.1016, -2.0469],
[ 1.4844, 0.9180, 0.8398, 1.9453],
[ 1.9766, 1.0859, 1.8203, 2.1406]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4688, 0.9023, 0.3398, 0.0243],
[ 3.2969, -0.0067, 1.3750, 2.9219],
[ 1.9453, -0.1621, 0.3398, 1.0781],
...,
[-1.6562, 0.2432, -1.1016, -2.0469],
[ 1.4844, 0.9180, 0.8398, 1.9453],
[ 1.9766, 1.0859, 1.8203, 2.1406]], requires_grad=True)
2024-10-08 15:05:50,423 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4766, 0.9258, 0.3555, 0.0378],
[ 3.2500, 0.0400, 1.3750, 2.9219],
[ 1.9062, -0.1650, 0.3281, 1.0625],
...,
[-1.6094, 0.1748, -1.1250, -2.0312],
[ 1.4297, 0.9180, 0.8164, 1.9375],
[ 1.9375, 0.9531, 1.6719, 2.1094]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4766, 0.9258, 0.3555, 0.0378],
[ 3.2500, 0.0400, 1.3750, 2.9219],
[ 1.9062, -0.1650, 0.3281, 1.0625],
...,
[-1.6094, 0.1748, -1.1250, -2.0312],
[ 1.4297, 0.9180, 0.8164, 1.9375],
[ 1.9375, 0.9531, 1.6719, 2.1094]], requires_grad=True)
2024-10-08 15:05:50,687 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4688, 0.9297, 0.3535, 0.0493],
[ 3.2188, 0.0359, 1.3203, 2.9062],
[ 1.8828, -0.1895, 0.2949, 1.0469],
...,
[-1.5859, 0.1699, -1.0859, -2.0156],
[ 1.4062, 0.8555, 0.7383, 1.9297],
[ 1.9219, 0.7812, 1.4922, 2.0781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4688, 0.9297, 0.3535, 0.0493],
[ 3.2188, 0.0359, 1.3203, 2.9062],
[ 1.8828, -0.1895, 0.2949, 1.0469],
...,
[-1.5859, 0.1699, -1.0859, -2.0156],
[ 1.4062, 0.8555, 0.7383, 1.9297],
[ 1.9219, 0.7812, 1.4922, 2.0781]], requires_grad=True)
2024-10-08 15:05:50,951 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4609, 0.9336, 0.3516, 0.0598],
[ 3.1719, 0.0742, 1.3125, 2.8750],
[ 1.8516, -0.2021, 0.2715, 1.0234],
...,
[-1.5547, 0.1484, -1.0703, -2.0000],
[ 1.3828, 0.8008, 0.6680, 1.9141],
[ 1.8984, 0.6836, 1.3750, 2.0469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4609, 0.9336, 0.3516, 0.0598],
[ 3.1719, 0.0742, 1.3125, 2.8750],
[ 1.8516, -0.2021, 0.2715, 1.0234],
...,
[-1.5547, 0.1484, -1.0703, -2.0000],
[ 1.3828, 0.8008, 0.6680, 1.9141],
[ 1.8984, 0.6836, 1.3750, 2.0469]], requires_grad=True)
2024-10-08 15:05:51,220 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4609, 0.9492, 0.3652, 0.0708],
[ 3.1094, 0.1582, 1.3594, 2.8438],
[ 1.8203, -0.2051, 0.2617, 1.0078],
...,
[-1.4766, 0.0583, -1.1250, -1.9688],
[ 1.3281, 0.8281, 0.6797, 1.8984],
[ 1.8750, 0.6328, 1.3125, 2.0312]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4609, 0.9492, 0.3652, 0.0708],
[ 3.1094, 0.1582, 1.3594, 2.8438],
[ 1.8203, -0.2051, 0.2617, 1.0078],
...,
[-1.4766, 0.0583, -1.1250, -1.9688],
[ 1.3281, 0.8281, 0.6797, 1.8984],
[ 1.8750, 0.6328, 1.3125, 2.0312]], requires_grad=True)
2024-10-08 15:05:51,478 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4453, 0.8867, 0.3008, 0.0605],
[ 3.0156, 0.3359, 1.5078, 2.8281],
[ 1.7734, -0.1865, 0.2695, 0.9883],
...,
[-1.3594, -0.2021, -1.3672, -1.9609],
[ 1.2500, 0.9844, 0.8164, 1.8984],
[ 1.8438, 0.6016, 1.2656, 2.0156]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4453, 0.8867, 0.3008, 0.0605],
[ 3.0156, 0.3359, 1.5078, 2.8281],
[ 1.7734, -0.1865, 0.2695, 0.9883],
...,
[-1.3594, -0.2021, -1.3672, -1.9609],
[ 1.2500, 0.9844, 0.8164, 1.8984],
[ 1.8438, 0.6016, 1.2656, 2.0156]], requires_grad=True)
2024-10-08 15:05:51,732 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4219, 0.8633, 0.2773, 0.0598],
[ 2.9219, 0.5039, 1.6406, 2.8125],
[ 1.7266, -0.1934, 0.2559, 0.9648],
...,
[-1.2734, -0.3379, -1.4844, -1.9375],
[ 1.1875, 1.0312, 0.8594, 1.8906],
[ 1.8125, 0.5078, 1.1719, 1.9844]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4219, 0.8633, 0.2773, 0.0598],
[ 2.9219, 0.5039, 1.6406, 2.8125],
[ 1.7266, -0.1934, 0.2559, 0.9648],
...,
[-1.2734, -0.3379, -1.4844, -1.9375],
[ 1.1875, 1.0312, 0.8594, 1.8906],
[ 1.8125, 0.5078, 1.1719, 1.9844]], requires_grad=True)
2024-10-08 15:05:51,890 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4062, 0.8672, 0.2793, 0.0610],
[ 2.8438, 0.5938, 1.7109, 2.7969],
[ 1.6875, -0.2178, 0.2256, 0.9453],
...,
[-1.1953, -0.4453, -1.5703, -1.9219],
[ 1.1250, 1.0234, 0.8516, 1.8750],
[ 1.7891, 0.3496, 1.0312, 1.9531]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.4062, 0.8672, 0.2793, 0.0610],
[ 2.8438, 0.5938, 1.7109, 2.7969],
[ 1.6875, -0.2178, 0.2256, 0.9453],
...,
[-1.1953, -0.4453, -1.5703, -1.9219],
[ 1.1250, 1.0234, 0.8516, 1.8750],
[ 1.7891, 0.3496, 1.0312, 1.9531]], requires_grad=True)
2024-10-08 15:05:52,142 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.3750, 0.8789, 0.2891, 0.0698],
[ 2.7812, 0.5703, 1.6719, 2.7656],
[ 1.6562, -0.2637, 0.1787, 0.9219],
...,
[-1.1172, -0.5195, -1.6250, -1.8984],
[ 1.0859, 0.9453, 0.7930, 1.8516],
[ 1.7734, 0.0913, 0.8164, 1.9062]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.3750, 0.8789, 0.2891, 0.0698],
[ 2.7812, 0.5703, 1.6719, 2.7656],
[ 1.6562, -0.2637, 0.1787, 0.9219],
...,
[-1.1172, -0.5195, -1.6250, -1.8984],
[ 1.0859, 0.9453, 0.7930, 1.8516],
[ 1.7734, 0.0913, 0.8164, 1.9062]], requires_grad=True)
2024-10-08 15:05:52,303 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.3438, 0.8711, 0.2871, 0.0762],
[ 2.7031, 0.6953, 1.7734, 2.7500],
[ 1.6172, -0.2695, 0.1660, 0.9023],
...,
[-1.0469, -0.6094, -1.6953, -1.8750],
[ 1.0312, 0.9453, 0.7969, 1.8281],
[ 1.7500, -0.0811, 0.6680, 1.8750]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.3438, 0.8711, 0.2871, 0.0762],
[ 2.7031, 0.6953, 1.7734, 2.7500],
[ 1.6172, -0.2695, 0.1660, 0.9023],
...,
[-1.0469, -0.6094, -1.6953, -1.8750],
[ 1.0312, 0.9453, 0.7969, 1.8281],
[ 1.7500, -0.0811, 0.6680, 1.8750]], requires_grad=True)
2024-10-08 15:05:52,456 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2734, 0.8281, 0.2578, 0.0884],
[ 2.5938, 0.8555, 1.8984, 2.7188],
[ 1.5703, -0.2559, 0.1699, 0.8828],
...,
[-0.9414, -0.7656, -1.8125, -1.8438],
[ 0.9492, 1.0078, 0.8477, 1.7969],
[ 1.7109, -0.1777, 0.5781, 1.8438]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2734, 0.8281, 0.2578, 0.0884],
[ 2.5938, 0.8555, 1.8984, 2.7188],
[ 1.5703, -0.2559, 0.1699, 0.8828],
...,
[-0.9414, -0.7656, -1.8125, -1.8438],
[ 0.9492, 1.0078, 0.8477, 1.7969],
[ 1.7109, -0.1777, 0.5781, 1.8438]], requires_grad=True)
2024-10-08 15:05:52,614 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2031, 0.7539, 0.2012, 0.0972],
[ 2.5156, 0.9805, 2.0000, 2.6875],
[ 1.5234, -0.2432, 0.1729, 0.8633],
...,
[-0.8555, -0.9102, -1.9219, -1.8125],
[ 0.9062, 1.0391, 0.8828, 1.7812],
[ 1.6797, -0.2500, 0.5078, 1.8125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2031, 0.7539, 0.2012, 0.0972],
[ 2.5156, 0.9805, 2.0000, 2.6875],
[ 1.5234, -0.2432, 0.1729, 0.8633],
...,
[-0.8555, -0.9102, -1.9219, -1.8125],
[ 0.9062, 1.0391, 0.8828, 1.7812],
[ 1.6797, -0.2500, 0.5078, 1.8125]], requires_grad=True)
2024-10-08 15:05:52,870 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1328, 0.6836, 0.1533, 0.1050],
[ 2.4375, 1.1016, 2.0938, 2.6562],
[ 1.4766, -0.2295, 0.1768, 0.8438],
...,
[-0.7773, -1.0469, -2.0312, -1.7812],
[ 0.8672, 1.0703, 0.9102, 1.7578],
[ 1.6562, -0.2988, 0.4531, 1.7812]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1328, 0.6836, 0.1533, 0.1050],
[ 2.4375, 1.1016, 2.0938, 2.6562],
[ 1.4766, -0.2295, 0.1768, 0.8438],
...,
[-0.7773, -1.0469, -2.0312, -1.7812],
[ 0.8672, 1.0703, 0.9102, 1.7578],
[ 1.6562, -0.2988, 0.4531, 1.7812]], requires_grad=True)
2024-10-08 15:05:53,031 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0703, 0.6406, 0.1250, 0.1152],
[ 2.3594, 1.1094, 2.0781, 2.6094],
[ 1.4375, -0.2305, 0.1689, 0.8281],
...,
[-0.7383, -1.1094, -2.0625, -1.7578],
[ 0.8398, 1.0234, 0.8750, 1.7266],
[ 1.6250, -0.4004, 0.3594, 1.7422]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0703, 0.6406, 0.1250, 0.1152],
[ 2.3594, 1.1094, 2.0781, 2.6094],
[ 1.4375, -0.2305, 0.1689, 0.8281],
...,
[-0.7383, -1.1094, -2.0625, -1.7578],
[ 0.8398, 1.0234, 0.8750, 1.7266],
[ 1.6250, -0.4004, 0.3594, 1.7422]], requires_grad=True)
2024-10-08 15:05:53,291 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0156, 0.6094, 0.1069, 0.1226],
[ 2.2812, 1.0625, 2.0156, 2.5469],
[ 1.4219, -0.2930, 0.1079, 0.8086],
...,
[-0.7109, -1.1250, -2.0625, -1.7266],
[ 0.8281, 0.9492, 0.8164, 1.6953],
[ 1.6016, -0.5156, 0.2559, 1.6953]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0156, 0.6094, 0.1069, 0.1226],
[ 2.2812, 1.0625, 2.0156, 2.5469],
[ 1.4219, -0.2930, 0.1079, 0.8086],
...,
[-0.7109, -1.1250, -2.0625, -1.7266],
[ 0.8281, 0.9492, 0.8164, 1.6953],
[ 1.6016, -0.5156, 0.2559, 1.6953]], requires_grad=True)
2024-10-08 15:05:53,538 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9570, 0.5469, 0.0649, 0.1245],
[ 2.2500, 0.9414, 1.8828, 2.4844],
[ 1.4062, -0.3457, 0.0549, 0.7852],
...,
[-0.7266, -1.0781, -2.0000, -1.7031],
[ 0.8438, 0.8398, 0.7344, 1.6641],
[ 1.5547, -0.6016, 0.1729, 1.6406]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9570, 0.5469, 0.0649, 0.1245],
[ 2.2500, 0.9414, 1.8828, 2.4844],
[ 1.4062, -0.3457, 0.0549, 0.7852],
...,
[-0.7266, -1.0781, -2.0000, -1.7031],
[ 0.8438, 0.8398, 0.7344, 1.6641],
[ 1.5547, -0.6016, 0.1729, 1.6406]], requires_grad=True)
2024-10-08 15:05:53,692 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8906, 0.4844, 0.0227, 0.1299],
[ 2.1875, 0.9648, 1.8906, 2.4375],
[ 1.3594, -0.3301, 0.0613, 0.7734],
...,
[-0.6914, -1.1875, -2.0781, -1.6953],
[ 0.8203, 0.8984, 0.7891, 1.6719],
[ 1.4688, -0.5195, 0.2139, 1.6094]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8906, 0.4844, 0.0227, 0.1299],
[ 2.1875, 0.9648, 1.8906, 2.4375],
[ 1.3594, -0.3301, 0.0613, 0.7734],
...,
[-0.6914, -1.1875, -2.0781, -1.6953],
[ 0.8203, 0.8984, 0.7891, 1.6719],
[ 1.4688, -0.5195, 0.2139, 1.6094]], requires_grad=True)
2024-10-08 15:05:53,958 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8281, 0.4004, -0.0356, 0.1216],
[ 2.0938, 1.1094, 1.9922, 2.4219],
[ 1.3203, -0.2910, 0.0859, 0.7695],
...,
[-0.6367, -1.3672, -2.2188, -1.7031],
[ 0.7695, 1.0078, 0.8828, 1.6797],
[ 1.3594, -0.3242, 0.3301, 1.6016]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8281, 0.4004, -0.0356, 0.1216],
[ 2.0938, 1.1094, 1.9922, 2.4219],
[ 1.3203, -0.2910, 0.0859, 0.7695],
...,
[-0.6367, -1.3672, -2.2188, -1.7031],
[ 0.7695, 1.0078, 0.8828, 1.6797],
[ 1.3594, -0.3242, 0.3301, 1.6016]], requires_grad=True)
2024-10-08 15:05:54,222 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7695, 0.3418, -0.0767, 0.1250],
[ 2.0312, 1.1562, 2.0156, 2.3750],
[ 1.2969, -0.2891, 0.0879, 0.7578],
...,
[-0.6094, -1.4531, -2.2969, -1.6875],
[ 0.7305, 1.0547, 0.9336, 1.6641],
[ 1.2656, -0.1729, 0.4199, 1.5781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7695, 0.3418, -0.0767, 0.1250],
[ 2.0312, 1.1562, 2.0156, 2.3750],
[ 1.2969, -0.2891, 0.0879, 0.7578],
...,
[-0.6094, -1.4531, -2.2969, -1.6875],
[ 0.7305, 1.0547, 0.9336, 1.6641],
[ 1.2656, -0.1729, 0.4199, 1.5781]], requires_grad=True)
2024-10-08 15:05:54,382 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7812, 0.3457, -0.0913, 0.1270],
[ 2.0000, 1.0703, 1.9688, 2.2969],
[ 1.3047, -0.3418, 0.0640, 0.7305],
...,
[-0.6445, -1.4531, -2.3281, -1.6797],
[ 0.7305, 1.0156, 0.9414, 1.6328],
[ 1.2109, -0.1089, 0.4727, 1.5469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7812, 0.3457, -0.0913, 0.1270],
[ 2.0000, 1.0703, 1.9688, 2.2969],
[ 1.3047, -0.3418, 0.0640, 0.7305],
...,
[-0.6445, -1.4531, -2.3281, -1.6797],
[ 0.7305, 1.0156, 0.9414, 1.6328],
[ 1.2109, -0.1089, 0.4727, 1.5469]], requires_grad=True)
2024-10-08 15:05:54,650 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8477, 0.3691, -0.0996, 0.1147],
[ 1.9922, 1.0312, 1.9531, 2.2656],
[ 1.2969, -0.3652, 0.0520, 0.7109],
...,
[-0.6172, -1.5078, -2.3750, -1.6562],
[ 0.7031, 1.0078, 0.9570, 1.5938],
[ 1.1719, 0.0067, 0.5430, 1.5469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8477, 0.3691, -0.0996, 0.1147],
[ 1.9922, 1.0312, 1.9531, 2.2656],
[ 1.2969, -0.3652, 0.0520, 0.7109],
...,
[-0.6172, -1.5078, -2.3750, -1.6562],
[ 0.7031, 1.0078, 0.9570, 1.5938],
[ 1.1719, 0.0067, 0.5430, 1.5469]], requires_grad=True)
2024-10-08 15:05:54,916 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8594, 0.3340, -0.1260, 0.0908],
[ 1.9062, 1.1953, 2.0156, 2.2656],
[ 1.2656, -0.3418, 0.0571, 0.7031],
...,
[-0.5352, -1.6328, -2.4219, -1.6406],
[ 0.6641, 1.0391, 0.9805, 1.5625],
[ 1.1094, 0.2188, 0.6406, 1.5625]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8594, 0.3340, -0.1260, 0.0908],
[ 1.9062, 1.1953, 2.0156, 2.2656],
[ 1.2656, -0.3418, 0.0571, 0.7031],
...,
[-0.5352, -1.6328, -2.4219, -1.6406],
[ 0.6641, 1.0391, 0.9805, 1.5625],
[ 1.1094, 0.2188, 0.6406, 1.5625]], requires_grad=True)
2024-10-08 15:05:55,068 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8633, 0.3008, -0.1484, 0.0752],
[ 1.8047, 1.3672, 2.0781, 2.2500],
[ 1.2188, -0.3145, 0.0635, 0.6914],
...,
[-0.4512, -1.7578, -2.4688, -1.6172],
[ 0.6172, 1.0703, 0.9961, 1.5234],
[ 1.0312, 0.4375, 0.7344, 1.5703]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8633, 0.3008, -0.1484, 0.0752],
[ 1.8047, 1.3672, 2.0781, 2.2500],
[ 1.2188, -0.3145, 0.0635, 0.6914],
...,
[-0.4512, -1.7578, -2.4688, -1.6172],
[ 0.6172, 1.0703, 0.9961, 1.5234],
[ 1.0312, 0.4375, 0.7344, 1.5703]], requires_grad=True)
2024-10-08 15:05:55,214 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8711, 0.2930, -0.1602, 0.0674],
[ 1.7109, 1.4766, 2.1094, 2.2188],
[ 1.1797, -0.3203, 0.0574, 0.6719],
...,
[-0.3848, -1.8047, -2.4844, -1.5781],
[ 0.5781, 1.0625, 0.9961, 1.4766],
[ 0.9570, 0.6016, 0.8047, 1.5625]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8711, 0.2930, -0.1602, 0.0674],
[ 1.7109, 1.4766, 2.1094, 2.2188],
[ 1.1797, -0.3203, 0.0574, 0.6719],
...,
[-0.3848, -1.8047, -2.4844, -1.5781],
[ 0.5781, 1.0625, 0.9961, 1.4766],
[ 0.9570, 0.6016, 0.8047, 1.5625]], requires_grad=True)
2024-10-08 15:05:55,373 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8789, 0.2871, -0.1709, 0.0608],
[ 1.6484, 1.4688, 2.0938, 2.1875],
[ 1.1562, -0.3613, 0.0391, 0.6445],
...,
[-0.3516, -1.7969, -2.4688, -1.5391],
[ 0.5508, 0.9805, 0.9688, 1.4141],
[ 0.8945, 0.7422, 0.8672, 1.5547]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8789, 0.2871, -0.1709, 0.0608],
[ 1.6484, 1.4688, 2.0938, 2.1875],
[ 1.1562, -0.3613, 0.0391, 0.6445],
...,
[-0.3516, -1.7969, -2.4688, -1.5391],
[ 0.5508, 0.9805, 0.9688, 1.4141],
[ 0.8945, 0.7422, 0.8672, 1.5547]], requires_grad=True)
2024-10-08 15:05:55,636 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8906, 0.2949, -0.1758, 0.0586],
[ 1.5938, 1.4609, 2.0781, 2.1406],
[ 1.1406, -0.4043, 0.0199, 0.6133],
...,
[-0.3125, -1.7891, -2.4531, -1.4922],
[ 0.5156, 0.9102, 0.9453, 1.3516],
[ 0.8359, 0.8555, 0.9141, 1.5312]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8906, 0.2949, -0.1758, 0.0586],
[ 1.5938, 1.4609, 2.0781, 2.1406],
[ 1.1406, -0.4043, 0.0199, 0.6133],
...,
[-0.3125, -1.7891, -2.4531, -1.4922],
[ 0.5156, 0.9102, 0.9453, 1.3516],
[ 0.8359, 0.8555, 0.9141, 1.5312]], requires_grad=True)
2024-10-08 15:05:55,904 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8984, 0.2344, -0.2031, 0.0383],
[ 1.5156, 1.5547, 2.0938, 2.0938],
[ 1.0859, -0.3711, 0.0262, 0.5820],
...,
[-0.1582, -1.9297, -2.4688, -1.4141],
[ 0.3867, 0.9766, 0.9570, 1.2656],
[ 0.7617, 0.9961, 0.9648, 1.5000]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8984, 0.2344, -0.2031, 0.0383],
[ 1.5156, 1.5547, 2.0938, 2.0938],
[ 1.0859, -0.3711, 0.0262, 0.5820],
...,
[-0.1582, -1.9297, -2.4688, -1.4141],
[ 0.3867, 0.9766, 0.9570, 1.2656],
[ 0.7617, 0.9961, 0.9648, 1.5000]], requires_grad=True)
2024-10-08 15:05:56,163 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8750, 0.1328, -0.2480, 0.0193],
[ 1.3672, 1.9453, 2.2656, 2.0625],
[ 1.0156, -0.3008, 0.0510, 0.5586],
...,
[ 0.0035, -2.1562, -2.5312, -1.3594],
[ 0.2402, 1.1094, 1.0000, 1.1875],
[ 0.6641, 1.2109, 1.0469, 1.4688]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8750, 0.1328, -0.2480, 0.0193],
[ 1.3672, 1.9453, 2.2656, 2.0625],
[ 1.0156, -0.3008, 0.0510, 0.5586],
...,
[ 0.0035, -2.1562, -2.5312, -1.3594],
[ 0.2402, 1.1094, 1.0000, 1.1875],
[ 0.6641, 1.2109, 1.0469, 1.4688]], requires_grad=True)
2024-10-08 15:05:56,428 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9492, 0.1318, -0.2373, -0.0164],
[ 1.3359, 2.1719, 2.3438, 2.0625],
[ 0.9883, -0.2754, 0.0503, 0.5430],
...,
[ 0.0535, -2.2500, -2.5156, -1.3281],
[ 0.1660, 1.1797, 1.0078, 1.1328],
[ 0.5938, 1.3594, 1.0938, 1.4375]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9492, 0.1318, -0.2373, -0.0164],
[ 1.3359, 2.1719, 2.3438, 2.0625],
[ 0.9883, -0.2754, 0.0503, 0.5430],
...,
[ 0.0535, -2.2500, -2.5156, -1.3281],
[ 0.1660, 1.1797, 1.0078, 1.1328],
[ 0.5938, 1.3594, 1.0938, 1.4375]], requires_grad=True)
2024-10-08 15:05:56,685 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0234, 0.1709, -0.1973, -0.0396],
[ 1.2109, 2.4375, 2.4531, 2.0156],
[ 1.0156, -0.3164, 0.0028, 0.5312],
...,
[-0.0825, -2.2031, -2.4219, -1.3594],
[ 0.3965, 0.9336, 0.8164, 1.1797],
[ 0.6328, 1.3516, 1.0547, 1.4453]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0234, 0.1709, -0.1973, -0.0396],
[ 1.2109, 2.4375, 2.4531, 2.0156],
[ 1.0156, -0.3164, 0.0028, 0.5312],
...,
[-0.0825, -2.2031, -2.4219, -1.3594],
[ 0.3965, 0.9336, 0.8164, 1.1797],
[ 0.6328, 1.3516, 1.0547, 1.4453]], requires_grad=True)
2024-10-08 15:05:56,847 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0625, 0.2715, -0.1064, -0.0430],
[ 1.1250, 2.3438, 2.2500, 1.9688],
[ 1.0312, -0.3965, -0.0776, 0.5195],
...,
[-0.2266, -2.0156, -2.2031, -1.3906],
[ 0.5859, 0.7109, 0.6406, 1.2031],
[ 0.6992, 1.1406, 0.8672, 1.4609]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0625, 0.2715, -0.1064, -0.0430],
[ 1.1250, 2.3438, 2.2500, 1.9688],
[ 1.0312, -0.3965, -0.0776, 0.5195],
...,
[-0.2266, -2.0156, -2.2031, -1.3906],
[ 0.5859, 0.7109, 0.6406, 1.2031],
[ 0.6992, 1.1406, 0.8672, 1.4609]], requires_grad=True)
2024-10-08 15:05:57,114 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1328, 0.3125, -0.0669, -0.0574],
[ 1.1406, 2.3750, 2.1875, 1.9609],
[ 1.1172, -0.3984, -0.0820, 0.5273],
...,
[-0.4141, -1.9531, -2.1250, -1.4297],
[ 0.8242, 0.6328, 0.5898, 1.2422],
[ 0.7773, 1.0156, 0.7500, 1.4766]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1328, 0.3125, -0.0669, -0.0574],
[ 1.1406, 2.3750, 2.1875, 1.9609],
[ 1.1172, -0.3984, -0.0820, 0.5273],
...,
[-0.4141, -1.9531, -2.1250, -1.4297],
[ 0.8242, 0.6328, 0.5898, 1.2422],
[ 0.7773, 1.0156, 0.7500, 1.4766]], requires_grad=True)
2024-10-08 15:05:57,272 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1562, 0.3418, -0.0327, -0.0491],
[ 1.1172, 2.3125, 2.0625, 1.9531],
[ 1.2500, -0.3594, -0.0464, 0.5391],
...,
[-0.6641, -1.9688, -2.1406, -1.4766],
[ 1.1094, 0.6562, 0.6289, 1.2812],
[ 0.8008, 0.8789, 0.6289, 1.4609]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1562, 0.3418, -0.0327, -0.0491],
[ 1.1172, 2.3125, 2.0625, 1.9531],
[ 1.2500, -0.3594, -0.0464, 0.5391],
...,
[-0.6641, -1.9688, -2.1406, -1.4766],
[ 1.1094, 0.6562, 0.6289, 1.2812],
[ 0.8008, 0.8789, 0.6289, 1.4609]], requires_grad=True)
2024-10-08 15:05:57,534 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2812, 0.3223, -0.0369, -0.0435],
[ 1.3984, 2.4531, 2.1250, 1.9766],
[ 1.4844, -0.2734, 0.0264, 0.5625],
...,
[-1.0703, -2.0781, -2.2344, -1.5234],
[ 1.5156, 0.7656, 0.7344, 1.3281],
[ 0.9453, 0.8516, 0.5859, 1.4531]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2812, 0.3223, -0.0369, -0.0435],
[ 1.3984, 2.4531, 2.1250, 1.9766],
[ 1.4844, -0.2734, 0.0264, 0.5625],
...,
[-1.0703, -2.0781, -2.2344, -1.5234],
[ 1.5156, 0.7656, 0.7344, 1.3281],
[ 0.9453, 0.8516, 0.5859, 1.4531]], requires_grad=True)
2024-10-08 15:05:57,800 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1562, 0.3496, -0.0496, -0.1123],
[ 1.5469, 2.5312, 2.1875, 2.0312],
[ 1.6406, -0.2090, 0.0918, 0.5938],
...,
[-1.2344, -2.1250, -2.3281, -1.6250],
[ 1.7578, 0.8281, 0.8320, 1.4062],
[ 0.8867, 0.7539, 0.5625, 1.5156]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1562, 0.3496, -0.0496, -0.1123],
[ 1.5469, 2.5312, 2.1875, 2.0312],
[ 1.6406, -0.2090, 0.0918, 0.5938],
...,
[-1.2344, -2.1250, -2.3281, -1.6250],
[ 1.7578, 0.8281, 0.8320, 1.4062],
[ 0.8867, 0.7539, 0.5625, 1.5156]], requires_grad=True)
2024-10-08 15:05:58,065 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9531, 0.3867, -0.0791, -0.2119],
[ 1.4375, 2.5312, 2.3281, 2.2031],
[ 1.7188, -0.1611, 0.1621, 0.6406],
...,
[-1.2266, -2.1250, -2.4531, -1.7812],
[ 1.8672, 0.8633, 0.9453, 1.5234],
[ 0.6719, 0.6250, 0.5938, 1.6719]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9531, 0.3867, -0.0791, -0.2119],
[ 1.4375, 2.5312, 2.3281, 2.2031],
[ 1.7188, -0.1611, 0.1621, 0.6406],
...,
[-1.2266, -2.1250, -2.4531, -1.7812],
[ 1.8672, 0.8633, 0.9453, 1.5234],
[ 0.6719, 0.6250, 0.5938, 1.6719]], requires_grad=True)
2024-10-08 15:05:58,329 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7148, 0.4316, -0.1177, -0.3105],
[ 1.2031, 2.4531, 2.5156, 2.3906],
[ 1.7109, -0.1367, 0.2422, 0.6992],
...,
[-1.1562, -2.0938, -2.5625, -1.9219],
[ 1.9141, 0.8672, 1.0625, 1.6328],
[ 0.4434, 0.4902, 0.6367, 1.8203]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7148, 0.4316, -0.1177, -0.3105],
[ 1.2031, 2.4531, 2.5156, 2.3906],
[ 1.7109, -0.1367, 0.2422, 0.6992],
...,
[-1.1562, -2.0938, -2.5625, -1.9219],
[ 1.9141, 0.8672, 1.0625, 1.6328],
[ 0.4434, 0.4902, 0.6367, 1.8203]], requires_grad=True)
2024-10-08 15:05:58,488 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4961, 0.4629, -0.1494, -0.3965],
[ 0.9883, 2.3906, 2.6719, 2.5469],
[ 1.6875, -0.1064, 0.3105, 0.7539],
...,
[-1.0938, -2.0781, -2.6562, -2.0469],
[ 1.9453, 0.8828, 1.1562, 1.7344],
[ 0.2432, 0.3730, 0.6719, 1.9453]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4961, 0.4629, -0.1494, -0.3965],
[ 0.9883, 2.3906, 2.6719, 2.5469],
[ 1.6875, -0.1064, 0.3105, 0.7539],
...,
[-1.0938, -2.0781, -2.6562, -2.0469],
[ 1.9453, 0.8828, 1.1562, 1.7344],
[ 0.2432, 0.3730, 0.6719, 1.9453]], requires_grad=True)
2024-10-08 15:05:58,643 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2832, 0.4805, -0.1777, -0.4824],
[ 0.7656, 2.3594, 2.7969, 2.7031],
[ 1.6562, -0.0659, 0.3691, 0.8125],
...,
[-0.9570, -2.1094, -2.7344, -2.1875],
[ 1.9219, 0.9297, 1.2422, 1.8438],
[ 0.0254, 0.3086, 0.7070, 2.0781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2832, 0.4805, -0.1777, -0.4824],
[ 0.7656, 2.3594, 2.7969, 2.7031],
[ 1.6562, -0.0659, 0.3691, 0.8125],
...,
[-0.9570, -2.1094, -2.7344, -2.1875],
[ 1.9219, 0.9297, 1.2422, 1.8438],
[ 0.0254, 0.3086, 0.7070, 2.0781]], requires_grad=True)
2024-10-08 15:05:58,901 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0393, 0.4707, -0.2119, -0.5859],
[ 0.4453, 2.4062, 2.9375, 2.8750],
[ 1.5234, 0.0032, 0.4316, 0.8906],
...,
[-0.6523, -2.2031, -2.8281, -2.3594],
[ 1.7344, 1.0391, 1.3359, 1.9844],
[-0.2402, 0.3027, 0.7539, 2.2344]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0393, 0.4707, -0.2119, -0.5859],
[ 0.4453, 2.4062, 2.9375, 2.8750],
[ 1.5234, 0.0032, 0.4316, 0.8906],
...,
[-0.6523, -2.2031, -2.8281, -2.3594],
[ 1.7344, 1.0391, 1.3359, 1.9844],
[-0.2402, 0.3027, 0.7539, 2.2344]], requires_grad=True)
2024-10-08 15:05:59,053 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.3398, 0.4238, -0.2656, -0.6719],
[ 0.1226, 2.4531, 3.0469, 3.0000],
[ 1.3594, 0.0737, 0.4941, 0.9570],
...,
[-0.3008, -2.3125, -2.9375, -2.5000],
[ 1.4453, 1.1719, 1.4453, 2.1094],
[-0.4922, 0.3125, 0.8047, 2.3750]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.3398, 0.4238, -0.2656, -0.6719],
[ 0.1226, 2.4531, 3.0469, 3.0000],
[ 1.3594, 0.0737, 0.4941, 0.9570],
...,
[-0.3008, -2.3125, -2.9375, -2.5000],
[ 1.4453, 1.1719, 1.4453, 2.1094],
[-0.4922, 0.3125, 0.8047, 2.3750]], requires_grad=True)
2024-10-08 15:05:59,212 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.8828, 0.3145, -0.3867, -0.7500],
[-0.2139, 2.5312, 3.2031, 3.1250],
[ 1.1562, 0.1602, 0.5781, 1.0234],
...,
[ 0.0471, -2.4375, -3.0469, -2.6250],
[ 1.2188, 1.2891, 1.5391, 2.2188],
[-0.7852, 0.3652, 0.8945, 2.4844]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.8828, 0.3145, -0.3867, -0.7500],
[-0.2139, 2.5312, 3.2031, 3.1250],
[ 1.1562, 0.1602, 0.5781, 1.0234],
...,
[ 0.0471, -2.4375, -3.0469, -2.6250],
[ 1.2188, 1.2891, 1.5391, 2.2188],
[-0.7852, 0.3652, 0.8945, 2.4844]], requires_grad=True)
2024-10-08 15:05:59,371 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3359, 0.2295, -0.4727, -0.8008],
[-0.3379, 2.5000, 3.2031, 3.2344],
[ 1.0859, 0.2061, 0.6133, 1.0781],
...,
[ 0.0374, -2.4219, -2.9844, -2.7500],
[ 1.1484, 1.3281, 1.5391, 2.3125],
[-0.7656, 0.2715, 0.8008, 2.5781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3359, 0.2295, -0.4727, -0.8008],
[-0.3379, 2.5000, 3.2031, 3.2344],
[ 1.0859, 0.2061, 0.6133, 1.0781],
...,
[ 0.0374, -2.4219, -2.9844, -2.7500],
[ 1.1484, 1.3281, 1.5391, 2.3125],
[-0.7656, 0.2715, 0.8008, 2.5781]], requires_grad=True)
2024-10-08 15:05:59,622 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.8203, 0.1357, -0.5703, -0.8281],
[-0.3750, 2.4219, 3.1250, 3.3125],
[ 1.1875, 0.2080, 0.5898, 1.1562],
...,
[-0.1250, -2.3438, -2.8594, -2.8906],
[ 1.1953, 1.3281, 1.5000, 2.4062],
[-0.7852, 0.1865, 0.7109, 2.6250]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.8203, 0.1357, -0.5703, -0.8281],
[-0.3750, 2.4219, 3.1250, 3.3125],
[ 1.1875, 0.2080, 0.5898, 1.1562],
...,
[-0.1250, -2.3438, -2.8594, -2.8906],
[ 1.1953, 1.3281, 1.5000, 2.4062],
[-0.7852, 0.1865, 0.7109, 2.6250]], requires_grad=True)
2024-10-08 15:05:59,885 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.1562, 0.0845, -0.6172, -0.8477],
[-0.3887, 2.3594, 3.0781, 3.3750],
[ 1.2812, 0.2070, 0.5664, 1.2188],
...,
[-0.2695, -2.2969, -2.7812, -3.0000],
[ 1.2812, 1.2969, 1.4219, 2.4688],
[-0.8047, 0.1270, 0.6562, 2.6719]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.1562, 0.0845, -0.6172, -0.8477],
[-0.3887, 2.3594, 3.0781, 3.3750],
[ 1.2812, 0.2070, 0.5664, 1.2188],
...,
[-0.2695, -2.2969, -2.7812, -3.0000],
[ 1.2812, 1.2969, 1.4219, 2.4688],
[-0.8047, 0.1270, 0.6562, 2.6719]], requires_grad=True)
2024-10-08 15:06:00,148 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.4375, 0.0344, -0.6641, -0.8633],
[-0.3809, 2.2969, 3.0469, 3.4219],
[ 1.3906, 0.1982, 0.5391, 1.2656],
...,
[-0.4766, -2.2188, -2.6562, -3.0938],
[ 1.4141, 1.2344, 1.3281, 2.5156],
[-0.8359, 0.0894, 0.6211, 2.6875]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.4375, 0.0344, -0.6641, -0.8633],
[-0.3809, 2.2969, 3.0469, 3.4219],
[ 1.3906, 0.1982, 0.5391, 1.2656],
...,
[-0.4766, -2.2188, -2.6562, -3.0938],
[ 1.4141, 1.2344, 1.3281, 2.5156],
[-0.8359, 0.0894, 0.6211, 2.6875]], requires_grad=True)
2024-10-08 15:06:00,410 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.6875, -0.0109, -0.7070, -0.8672],
[-0.3184, 2.2188, 2.9844, 3.4531],
[ 1.5469, 0.1689, 0.4922, 1.3125],
...,
[-0.7539, -2.0938, -2.5000, -3.1875],
[ 1.5938, 1.1484, 1.2109, 2.5625],
[-0.8750, 0.0698, 0.6055, 2.6875]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.6875, -0.0109, -0.7070, -0.8672],
[-0.3184, 2.2188, 2.9844, 3.4531],
[ 1.5469, 0.1689, 0.4922, 1.3125],
...,
[-0.7539, -2.0938, -2.5000, -3.1875],
[ 1.5938, 1.1484, 1.2109, 2.5625],
[-0.8750, 0.0698, 0.6055, 2.6875]], requires_grad=True)
2024-10-08 15:06:00,682 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.9219, -0.0742, -0.7695, -0.8711],
[-0.3203, 2.2656, 3.0625, 3.4844],
[ 1.6562, 0.1729, 0.4863, 1.3594],
...,
[-0.9766, -2.0000, -2.3750, -3.2656],
[ 1.7109, 1.1094, 1.1328, 2.5938],
[-0.9492, 0.1455, 0.6875, 2.7031]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.9219, -0.0742, -0.7695, -0.8711],
[-0.3203, 2.2656, 3.0625, 3.4844],
[ 1.6562, 0.1729, 0.4863, 1.3594],
...,
[-0.9766, -2.0000, -2.3750, -3.2656],
[ 1.7109, 1.1094, 1.1328, 2.5938],
[-0.9492, 0.1455, 0.6875, 2.7031]], requires_grad=True)
2024-10-08 15:06:00,941 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.1406, -0.1768, -0.8750, -0.8828],
[-0.3438, 2.3594, 3.2188, 3.5000],
[ 1.7344, 0.1982, 0.5078, 1.3984],
...,
[-1.1484, -1.9219, -2.2656, -3.3125],
[ 1.7891, 1.1016, 1.1094, 2.6094],
[-1.0312, 0.2793, 0.8359, 2.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.1406, -0.1768, -0.8750, -0.8828],
[-0.3438, 2.3594, 3.2188, 3.5000],
[ 1.7344, 0.1982, 0.5078, 1.3984],
...,
[-1.1484, -1.9219, -2.2656, -3.3125],
[ 1.7891, 1.1016, 1.1094, 2.6094],
[-1.0312, 0.2793, 0.8359, 2.7188]], requires_grad=True)
2024-10-08 15:06:01,196 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.3125, -0.2520, -0.9492, -0.8906],
[-0.3691, 2.4375, 3.3594, 3.5000],
[ 1.7891, 0.2305, 0.5391, 1.4297],
...,
[-1.2969, -1.8672, -2.1875, -3.3438],
[ 1.8438, 1.1094, 1.1094, 2.6250],
[-1.1016, 0.4160, 0.9844, 2.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.3125, -0.2520, -0.9492, -0.8906],
[-0.3691, 2.4375, 3.3594, 3.5000],
[ 1.7891, 0.2305, 0.5391, 1.4297],
...,
[-1.2969, -1.8672, -2.1875, -3.3438],
[ 1.8438, 1.1094, 1.1094, 2.6250],
[-1.1016, 0.4160, 0.9844, 2.7188]], requires_grad=True)
2024-10-08 15:06:01,450 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.4844, -0.3398, -1.0391, -0.8867],
[-0.3945, 2.5000, 3.4844, 3.4844],
[ 1.8438, 0.2422, 0.5469, 1.4609],
...,
[-1.4531, -1.7734, -2.0625, -3.3750],
[ 1.9141, 1.0781, 1.0703, 2.6406],
[-1.1641, 0.5039, 1.0781, 2.7031]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.4844, -0.3398, -1.0391, -0.8867],
[-0.3945, 2.5000, 3.4844, 3.4844],
[ 1.8438, 0.2422, 0.5469, 1.4609],
...,
[-1.4531, -1.7734, -2.0625, -3.3750],
[ 1.9141, 1.0781, 1.0703, 2.6406],
[-1.1641, 0.5039, 1.0781, 2.7031]], requires_grad=True)
2024-10-08 15:06:01,603 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.6250, -0.3926, -1.0859, -0.8789],
[-0.4062, 2.4844, 3.4688, 3.4688],
[ 1.8828, 0.2471, 0.5469, 1.4688],
...,
[-1.6016, -1.6250, -1.8750, -3.4062],
[ 1.9844, 0.9961, 0.9609, 2.6562],
[-1.2188, 0.5586, 1.1328, 2.6875]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.6250, -0.3926, -1.0859, -0.8789],
[-0.4062, 2.4844, 3.4688, 3.4688],
[ 1.8828, 0.2471, 0.5469, 1.4688],
...,
[-1.6016, -1.6250, -1.8750, -3.4062],
[ 1.9844, 0.9961, 0.9609, 2.6562],
[-1.2188, 0.5586, 1.1328, 2.6875]], requires_grad=True)
2024-10-08 15:06:01,857 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.7344, -0.4395, -1.1250, -0.8711],
[-0.4141, 2.4531, 3.4375, 3.4531],
[ 1.9141, 0.2402, 0.5312, 1.4766],
...,
[-1.7344, -1.5000, -1.7109, -3.4062],
[ 2.0312, 0.8984, 0.8359, 2.6562],
[-1.2578, 0.6094, 1.1875, 2.6719]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.7344, -0.4395, -1.1250, -0.8711],
[-0.4141, 2.4531, 3.4375, 3.4531],
[ 1.9141, 0.2402, 0.5312, 1.4766],
...,
[-1.7344, -1.5000, -1.7109, -3.4062],
[ 2.0312, 0.8984, 0.8359, 2.6562],
[-1.2578, 0.6094, 1.1875, 2.6719]], requires_grad=True)
2024-10-08 15:06:02,116 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.8281, -0.5039, -1.1953, -0.8594],
[-0.4258, 2.4219, 3.4219, 3.4219],
[ 1.9297, 0.2441, 0.5273, 1.4766],
...,
[-1.8359, -1.4062, -1.5938, -3.3906],
[ 2.0625, 0.8477, 0.7773, 2.6406],
[-1.2891, 0.6797, 1.2578, 2.6406]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.8281, -0.5039, -1.1953, -0.8594],
[-0.4258, 2.4219, 3.4219, 3.4219],
[ 1.9297, 0.2441, 0.5273, 1.4766],
...,
[-1.8359, -1.4062, -1.5938, -3.3906],
[ 2.0625, 0.8477, 0.7773, 2.6406],
[-1.2891, 0.6797, 1.2578, 2.6406]], requires_grad=True)
2024-10-08 15:06:02,378 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9062, -0.5742, -1.2656, -0.8398],
[-0.4551, 2.4688, 3.5000, 3.3750],
[ 1.9297, 0.2656, 0.5547, 1.4609],
...,
[-1.9062, -1.3438, -1.5234, -3.3594],
[ 2.0625, 0.8242, 0.7578, 2.6094],
[-1.3281, 0.7578, 1.3438, 2.5938]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9062, -0.5742, -1.2656, -0.8398],
[-0.4551, 2.4688, 3.5000, 3.3750],
[ 1.9297, 0.2656, 0.5547, 1.4609],
...,
[-1.9062, -1.3438, -1.5234, -3.3594],
[ 2.0625, 0.8242, 0.7578, 2.6094],
[-1.3281, 0.7578, 1.3438, 2.5938]], requires_grad=True)
2024-10-08 15:06:02,536 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9531, -0.6680, -1.3750, -0.8203],
[-0.4805, 2.5312, 3.6250, 3.3281],
[ 1.9219, 0.3066, 0.6133, 1.4453],
...,
[-1.9688, -1.3281, -1.5391, -3.3281],
[ 2.0625, 0.8281, 0.7773, 2.5781],
[-1.3516, 0.8672, 1.4766, 2.5469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9531, -0.6680, -1.3750, -0.8203],
[-0.4805, 2.5312, 3.6250, 3.3281],
[ 1.9219, 0.3066, 0.6133, 1.4453],
...,
[-1.9688, -1.3281, -1.5391, -3.3281],
[ 2.0625, 0.8281, 0.7773, 2.5781],
[-1.3516, 0.8672, 1.4766, 2.5469]], requires_grad=True)
2024-10-08 15:06:02,700 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9688, -0.7539, -1.4844, -0.8008],
[-0.5117, 2.5625, 3.6875, 3.2812],
[ 1.9062, 0.3359, 0.6523, 1.4219],
...,
[-2.0000, -1.2969, -1.5234, -3.2969],
[ 2.0469, 0.8281, 0.7930, 2.5469],
[-1.3750, 0.9570, 1.5859, 2.5000]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9688, -0.7539, -1.4844, -0.8008],
[-0.5117, 2.5625, 3.6875, 3.2812],
[ 1.9062, 0.3359, 0.6523, 1.4219],
...,
[-2.0000, -1.2969, -1.5234, -3.2969],
[ 2.0469, 0.8281, 0.7930, 2.5469],
[-1.3750, 0.9570, 1.5859, 2.5000]], requires_grad=True)
2024-10-08 15:06:02,857 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9531, -0.8359, -1.5859, -0.7852],
[-0.5391, 2.5625, 3.7031, 3.2344],
[ 1.8672, 0.3398, 0.6484, 1.4062],
...,
[-1.9922, -1.2188, -1.4141, -3.2656],
[ 2.0156, 0.8047, 0.7656, 2.5156],
[-1.4062, 1.0000, 1.6250, 2.4531]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9531, -0.8359, -1.5859, -0.7852],
[-0.5391, 2.5625, 3.7031, 3.2344],
[ 1.8672, 0.3398, 0.6484, 1.4062],
...,
[-1.9922, -1.2188, -1.4141, -3.2656],
[ 2.0156, 0.8047, 0.7656, 2.5156],
[-1.4062, 1.0000, 1.6250, 2.4531]], requires_grad=True)
2024-10-08 15:06:03,114 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9219, -0.8867, -1.6406, -0.7773],
[-0.5547, 2.5625, 3.7188, 3.1875],
[ 1.8281, 0.3281, 0.6172, 1.3984],
...,
[-1.9766, -1.1094, -1.2656, -3.2344],
[ 1.9766, 0.7617, 0.7109, 2.4688],
[-1.4297, 1.0234, 1.6484, 2.4062]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.9219, -0.8867, -1.6406, -0.7773],
[-0.5547, 2.5625, 3.7188, 3.1875],
[ 1.8281, 0.3281, 0.6172, 1.3984],
...,
[-1.9766, -1.1094, -1.2656, -3.2344],
[ 1.9766, 0.7617, 0.7109, 2.4688],
[-1.4297, 1.0234, 1.6484, 2.4062]], requires_grad=True)
2024-10-08 15:06:03,377 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.8750, -0.8945, -1.6328, -0.7695],
[-0.5547, 2.5156, 3.6562, 3.1406],
[ 1.7969, 0.3027, 0.5664, 1.3906],
...,
[-1.9531, -1.0000, -1.0938, -3.1875],
[ 1.9375, 0.7031, 0.6328, 2.4219],
[-1.4375, 1.0312, 1.6406, 2.3594]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.8750, -0.8945, -1.6328, -0.7695],
[-0.5547, 2.5156, 3.6562, 3.1406],
[ 1.7969, 0.3027, 0.5664, 1.3906],
...,
[-1.9531, -1.0000, -1.0938, -3.1875],
[ 1.9375, 0.7031, 0.6328, 2.4219],
[-1.4375, 1.0312, 1.6406, 2.3594]], requires_grad=True)
2024-10-08 15:06:03,639 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.8281, -0.8984, -1.6250, -0.7617],
[-0.5586, 2.4375, 3.5312, 3.0781],
[ 1.7578, 0.2832, 0.5273, 1.3750],
...,
[-1.9219, -0.9141, -0.9766, -3.1406],
[ 1.9062, 0.6680, 0.5859, 2.3750],
[-1.4375, 1.0547, 1.6641, 2.3125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.8281, -0.8984, -1.6250, -0.7617],
[-0.5586, 2.4375, 3.5312, 3.0781],
[ 1.7578, 0.2832, 0.5273, 1.3750],
...,
[-1.9219, -0.9141, -0.9766, -3.1406],
[ 1.9062, 0.6680, 0.5859, 2.3750],
[-1.4375, 1.0547, 1.6641, 2.3125]], requires_grad=True)
2024-10-08 15:06:03,791 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.8125, -0.9102, -1.6250, -0.7461],
[-0.5664, 2.3594, 3.4219, 3.0000],
[ 1.6953, 0.2930, 0.5352, 1.3672],
...,
[-1.8594, -0.8984, -0.9766, -3.1094],
[ 1.8281, 0.6914, 0.6406, 2.3438],
[-1.4609, 1.1250, 1.7578, 2.2969]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.8125, -0.9102, -1.6250, -0.7461],
[-0.5664, 2.3594, 3.4219, 3.0000],
[ 1.6953, 0.2930, 0.5352, 1.3672],
...,
[-1.8594, -0.8984, -0.9766, -3.1094],
[ 1.8281, 0.6914, 0.6406, 2.3438],
[-1.4609, 1.1250, 1.7578, 2.2969]], requires_grad=True)
2024-10-08 15:06:03,931 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.7969, -0.9258, -1.6250, -0.7266],
[-0.5781, 2.2812, 3.2969, 2.9219],
[ 1.6250, 0.3086, 0.5508, 1.3594],
...,
[-1.7500, -0.9297, -1.0391, -3.0781],
[ 1.7188, 0.7461, 0.7305, 2.3281],
[-1.4844, 1.1875, 1.8281, 2.2656]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.7969, -0.9258, -1.6250, -0.7266],
[-0.5781, 2.2812, 3.2969, 2.9219],
[ 1.6250, 0.3086, 0.5508, 1.3594],
...,
[-1.7500, -0.9297, -1.0391, -3.0781],
[ 1.7188, 0.7461, 0.7305, 2.3281],
[-1.4844, 1.1875, 1.8281, 2.2656]], requires_grad=True)
2024-10-08 15:06:04,089 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.7656, -0.9258, -1.6172, -0.7070],
[-0.5820, 2.2188, 3.2031, 2.8438],
[ 1.5703, 0.3086, 0.5547, 1.3438],
...,
[-1.6406, -0.9570, -1.0938, -3.0312],
[ 1.6250, 0.7812, 0.7969, 2.3125],
[-1.4844, 1.2031, 1.8672, 2.2344]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.7656, -0.9258, -1.6172, -0.7070],
[-0.5820, 2.2188, 3.2031, 2.8438],
[ 1.5703, 0.3086, 0.5547, 1.3438],
...,
[-1.6406, -0.9570, -1.0938, -3.0312],
[ 1.6250, 0.7812, 0.7969, 2.3125],
[-1.4844, 1.2031, 1.8672, 2.2344]], requires_grad=True)
2024-10-08 15:06:04,354 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.7188, -0.9219, -1.6016, -0.6992],
[-0.5703, 2.1406, 3.0938, 2.7812],
[ 1.5234, 0.2910, 0.5430, 1.3281],
...,
[-1.5547, -0.9336, -1.1094, -2.9844],
[ 1.5469, 0.7734, 0.8320, 2.2812],
[-1.4766, 1.1797, 1.8750, 2.1875]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.7188, -0.9219, -1.6016, -0.6992],
[-0.5703, 2.1406, 3.0938, 2.7812],
[ 1.5234, 0.2910, 0.5430, 1.3281],
...,
[-1.5547, -0.9336, -1.1094, -2.9844],
[ 1.5469, 0.7734, 0.8320, 2.2812],
[-1.4766, 1.1797, 1.8750, 2.1875]], requires_grad=True)
2024-10-08 15:06:04,512 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.6562, -0.8633, -1.5625, -0.6797],
[-0.5391, 2.0156, 2.9688, 2.7188],
[ 1.4766, 0.2754, 0.5312, 1.3047],
...,
[-1.4766, -0.8789, -1.1016, -2.9219],
[ 1.4922, 0.7148, 0.8398, 2.2500],
[-1.4531, 1.1172, 1.8594, 2.1406]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.6562, -0.8633, -1.5625, -0.6797],
[-0.5391, 2.0156, 2.9688, 2.7188],
[ 1.4766, 0.2754, 0.5312, 1.3047],
...,
[-1.4766, -0.8789, -1.1016, -2.9219],
[ 1.4922, 0.7148, 0.8398, 2.2500],
[-1.4531, 1.1172, 1.8594, 2.1406]], requires_grad=True)
2024-10-08 15:06:04,668 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.5938, -0.8047, -1.5234, -0.6562],
[-0.5156, 1.9141, 2.8438, 2.6562],
[ 1.4297, 0.2715, 0.5234, 1.2812],
...,
[-1.3828, -0.8789, -1.1094, -2.8594],
[ 1.4297, 0.6875, 0.8516, 2.2188],
[-1.4297, 1.0703, 1.8438, 2.0938]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.5938, -0.8047, -1.5234, -0.6562],
[-0.5156, 1.9141, 2.8438, 2.6562],
[ 1.4297, 0.2715, 0.5234, 1.2812],
...,
[-1.3828, -0.8789, -1.1094, -2.8594],
[ 1.4297, 0.6875, 0.8516, 2.2188],
[-1.4297, 1.0703, 1.8438, 2.0938]], requires_grad=True)
2024-10-08 15:06:04,935 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.5312, -0.7734, -1.4844, -0.6328],
[-0.4883, 1.8594, 2.7500, 2.5938],
[ 1.3828, 0.2871, 0.5156, 1.2578],
...,
[-1.2891, -0.9297, -1.1172, -2.8125],
[ 1.3594, 0.7070, 0.8594, 2.1719],
[-1.4219, 1.0781, 1.8281, 2.0469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.5312, -0.7734, -1.4844, -0.6328],
[-0.4883, 1.8594, 2.7500, 2.5938],
[ 1.3828, 0.2871, 0.5156, 1.2578],
...,
[-1.2891, -0.9297, -1.1172, -2.8125],
[ 1.3594, 0.7070, 0.8594, 2.1719],
[-1.4219, 1.0781, 1.8281, 2.0469]], requires_grad=True)
2024-10-08 15:06:05,191 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.4688, -0.7461, -1.4453, -0.6094],
[-0.4688, 1.8125, 2.6562, 2.5312],
[ 1.3281, 0.3125, 0.5078, 1.2344],
...,
[-1.1875, -0.9883, -1.1250, -2.7500],
[ 1.2891, 0.7344, 0.8633, 2.1250],
[-1.4141, 1.0859, 1.8125, 2.0000]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.4688, -0.7461, -1.4453, -0.6094],
[-0.4688, 1.8125, 2.6562, 2.5312],
[ 1.3281, 0.3125, 0.5078, 1.2344],
...,
[-1.1875, -0.9883, -1.1250, -2.7500],
[ 1.2891, 0.7344, 0.8633, 2.1250],
[-1.4141, 1.0859, 1.8125, 2.0000]], requires_grad=True)
2024-10-08 15:06:05,351 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.4062, -0.7070, -1.4062, -0.5820],
[-0.4609, 1.7500, 2.5625, 2.4688],
[ 1.2734, 0.3145, 0.5000, 1.2031],
...,
[-1.0938, -1.0391, -1.1250, -2.6875],
[ 1.2109, 0.7266, 0.8672, 2.0781],
[-1.4062, 1.0625, 1.7891, 1.9453]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.4062, -0.7070, -1.4062, -0.5820],
[-0.4609, 1.7500, 2.5625, 2.4688],
[ 1.2734, 0.3145, 0.5000, 1.2031],
...,
[-1.0938, -1.0391, -1.1250, -2.6875],
[ 1.2109, 0.7266, 0.8672, 2.0781],
[-1.4062, 1.0625, 1.7891, 1.9453]], requires_grad=True)
2024-10-08 15:06:05,506 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.3281, -0.6914, -1.3672, -0.5625],
[-0.4590, 1.6953, 2.4688, 2.3906],
[ 1.2188, 0.3145, 0.4922, 1.1719],
...,
[-1.0078, -1.0781, -1.1250, -2.6250],
[ 1.1328, 0.6992, 0.8672, 2.0156],
[-1.3984, 1.0391, 1.7656, 1.8984]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.3281, -0.6914, -1.3672, -0.5625],
[-0.4590, 1.6953, 2.4688, 2.3906],
[ 1.2188, 0.3145, 0.4922, 1.1719],
...,
[-1.0078, -1.0781, -1.1250, -2.6250],
[ 1.1328, 0.6992, 0.8672, 2.0156],
[-1.3984, 1.0391, 1.7656, 1.8984]], requires_grad=True)
2024-10-08 15:06:05,760 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.2812, -0.6641, -1.3281, -0.5391],
[-0.4609, 1.6328, 2.3750, 2.3125],
[ 1.1641, 0.3184, 0.4844, 1.1484],
...,
[-0.9297, -1.1094, -1.1172, -2.5625],
[ 1.0625, 0.6875, 0.8633, 1.9531],
[-1.3750, 1.0469, 1.7344, 1.8516]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.2812, -0.6641, -1.3281, -0.5391],
[-0.4609, 1.6328, 2.3750, 2.3125],
[ 1.1641, 0.3184, 0.4844, 1.1484],
...,
[-0.9297, -1.1094, -1.1172, -2.5625],
[ 1.0625, 0.6875, 0.8633, 1.9531],
[-1.3750, 1.0469, 1.7344, 1.8516]], requires_grad=True)
2024-10-08 15:06:06,026 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.2188, -0.7070, -1.2891, -0.5195],
[-0.4648, 1.5234, 2.2812, 2.2500],
[ 1.1250, 0.3320, 0.4766, 1.1250],
...,
[-0.8711, -1.1641, -1.1094, -2.5000],
[ 1.0078, 0.6914, 0.8594, 1.8984],
[-1.3516, 1.0859, 1.7031, 1.8125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.2188, -0.7070, -1.2891, -0.5195],
[-0.4648, 1.5234, 2.2812, 2.2500],
[ 1.1250, 0.3320, 0.4766, 1.1250],
...,
[-0.8711, -1.1641, -1.1094, -2.5000],
[ 1.0078, 0.6914, 0.8594, 1.8984],
[-1.3516, 1.0859, 1.7031, 1.8125]], requires_grad=True)
2024-10-08 15:06:06,288 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.1719, -0.7461, -1.2500, -0.4961],
[-0.4648, 1.2891, 2.2031, 2.1719],
[ 1.0859, 0.3184, 0.4688, 1.0938],
...,
[-0.8125, -1.1484, -1.1016, -2.4219],
[ 0.9531, 0.6445, 0.8516, 1.8438],
[-1.3203, 1.0625, 1.6719, 1.7656]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.1719, -0.7461, -1.2500, -0.4961],
[-0.4648, 1.2891, 2.2031, 2.1719],
[ 1.0859, 0.3184, 0.4688, 1.0938],
...,
[-0.8125, -1.1484, -1.1016, -2.4219],
[ 0.9531, 0.6445, 0.8516, 1.8438],
[-1.3203, 1.0625, 1.6719, 1.7656]], requires_grad=True)
2024-10-08 15:06:06,544 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.1406, -0.8242, -1.2109, -0.4746],
[-0.4766, 1.1641, 2.1406, 2.0938],
[ 1.0391, 0.3262, 0.4609, 1.0703],
...,
[-0.7422, -1.1953, -1.0938, -2.3594],
[ 0.8945, 0.6250, 0.8438, 1.7891],
[-1.3047, 1.1094, 1.6484, 1.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.1406, -0.8242, -1.2109, -0.4746],
[-0.4766, 1.1641, 2.1406, 2.0938],
[ 1.0391, 0.3262, 0.4609, 1.0703],
...,
[-0.7422, -1.1953, -1.0938, -2.3594],
[ 0.8945, 0.6250, 0.8438, 1.7891],
[-1.3047, 1.1094, 1.6484, 1.7188]], requires_grad=True)
2024-10-08 15:06:06,803 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.1094, -0.9023, -1.1719, -0.4570],
[-0.4902, 1.0625, 2.0781, 2.0156],
[ 0.9922, 0.3320, 0.4531, 1.0391],
...,
[-0.6797, -1.2031, -1.0781, -2.2812],
[ 0.8320, 0.6133, 0.8398, 1.7344],
[-1.2891, 1.1562, 1.6172, 1.6719]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.1094, -0.9023, -1.1719, -0.4570],
[-0.4902, 1.0625, 2.0781, 2.0156],
[ 0.9922, 0.3320, 0.4531, 1.0391],
...,
[-0.6797, -1.2031, -1.0781, -2.2812],
[ 0.8320, 0.6133, 0.8398, 1.7344],
[-1.2891, 1.1562, 1.6172, 1.6719]], requires_grad=True)
2024-10-08 15:06:07,068 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0781, -0.9922, -1.1484, -0.4473],
[-0.4434, 0.9180, 2.0156, 1.9609],
[ 0.9727, 0.3320, 0.4453, 1.0156],
...,
[-0.6758, -1.1328, -1.0547, -2.2188],
[ 0.7891, 0.5859, 0.8320, 1.6797],
[-1.2500, 1.1328, 1.5781, 1.6250]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0781, -0.9922, -1.1484, -0.4473],
[-0.4434, 0.9180, 2.0156, 1.9609],
[ 0.9727, 0.3320, 0.4453, 1.0156],
...,
[-0.6758, -1.1328, -1.0547, -2.2188],
[ 0.7891, 0.5859, 0.8320, 1.6797],
[-1.2500, 1.1328, 1.5781, 1.6250]], requires_grad=True)
2024-10-08 15:06:07,340 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0469, -1.0938, -1.1250, -0.4414],
[-0.4277, 0.8789, 1.9609, 1.9141],
[ 0.9492, 0.3418, 0.4395, 0.9961],
...,
[-0.6484, -1.1250, -1.0391, -2.1719],
[ 0.7344, 0.5820, 0.8242, 1.6328],
[-1.2188, 1.1328, 1.5469, 1.5781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0469, -1.0938, -1.1250, -0.4414],
[-0.4277, 0.8789, 1.9609, 1.9141],
[ 0.9492, 0.3418, 0.4395, 0.9961],
...,
[-0.6484, -1.1250, -1.0391, -2.1719],
[ 0.7344, 0.5820, 0.8242, 1.6328],
[-1.2188, 1.1328, 1.5469, 1.5781]], requires_grad=True)
2024-10-08 15:06:07,496 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0312, -1.2109, -1.1094, -0.4434],
[-0.3594, 0.6172, 1.8594, 1.8281],
[ 0.9453, 0.3027, 0.4238, 0.9609],
...,
[-0.6797, -0.9102, -0.9805, -2.0625],
[ 0.7266, 0.4277, 0.7891, 1.5469],
[-1.1719, 1.0391, 1.5000, 1.5156]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0312, -1.2109, -1.1094, -0.4434],
[-0.3594, 0.6172, 1.8594, 1.8281],
[ 0.9453, 0.3027, 0.4238, 0.9609],
...,
[-0.6797, -0.9102, -0.9805, -2.0625],
[ 0.7266, 0.4277, 0.7891, 1.5469],
[-1.1719, 1.0391, 1.5000, 1.5156]], requires_grad=True)
2024-10-08 15:06:07,760 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0469, -1.3750, -1.1016, -0.4570],
[-0.3027, 0.6094, 1.8281, 1.8125],
[ 0.9141, 0.3516, 0.4277, 0.9570],
...,
[-0.6523, -0.8203, -0.9453, -1.9766],
[ 0.6523, 0.4434, 0.7852, 1.4922],
[-1.1953, 1.2422, 1.5078, 1.5156]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0469, -1.3750, -1.1016, -0.4570],
[-0.3027, 0.6094, 1.8281, 1.8125],
[ 0.9141, 0.3516, 0.4277, 0.9570],
...,
[-0.6523, -0.8203, -0.9453, -1.9766],
[ 0.6523, 0.4434, 0.7852, 1.4922],
[-1.1953, 1.2422, 1.5078, 1.5156]], requires_grad=True)
2024-10-08 15:06:08,023 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0625, -1.5234, -1.0938, -0.4688],
[-0.2812, 0.6406, 1.8047, 1.7969],
[ 0.8555, 0.4160, 0.4355, 0.9531],
...,
[-0.5508, -0.8203, -0.9375, -1.8906],
[ 0.5312, 0.5156, 0.7930, 1.4375],
[-1.2344, 1.4531, 1.5156, 1.5156]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 3.0625, -1.5234, -1.0938, -0.4688],
[-0.2812, 0.6406, 1.8047, 1.7969],
[ 0.8555, 0.4160, 0.4355, 0.9531],
...,
[-0.5508, -0.8203, -0.9375, -1.8906],
[ 0.5312, 0.5156, 0.7930, 1.4375],
[-1.2344, 1.4531, 1.5156, 1.5156]], requires_grad=True)
2024-10-08 15:06:08,277 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.8906, -1.5000, -1.0312, -0.4473],
[-0.0859, 0.4277, 1.6875, 1.7578],
[ 0.9141, 0.3809, 0.4062, 0.9336],
...,
[-0.6523, -0.6289, -0.8516, -1.8047],
[ 0.5859, 0.4062, 0.7344, 1.3672],
[-1.2734, 1.6484, 1.5234, 1.5078]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.8906, -1.5000, -1.0312, -0.4473],
[-0.0859, 0.4277, 1.6875, 1.7578],
[ 0.9141, 0.3809, 0.4062, 0.9336],
...,
[-0.6523, -0.6289, -0.8516, -1.8047],
[ 0.5859, 0.4062, 0.7344, 1.3672],
[-1.2734, 1.6484, 1.5234, 1.5078]], requires_grad=True)
2024-10-08 15:06:08,531 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.6250, -1.3984, -0.9414, -0.4141],
[ 0.1797, 0.1426, 1.5391, 1.7188],
[ 1.0312, 0.3105, 0.3652, 0.9141],
...,
[-0.8711, -0.3516, -0.7227, -1.7188],
[ 0.7188, 0.2285, 0.6445, 1.2969],
[-1.1250, 1.6406, 1.4609, 1.5078]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.6250, -1.3984, -0.9414, -0.4141],
[ 0.1797, 0.1426, 1.5391, 1.7188],
[ 1.0312, 0.3105, 0.3652, 0.9141],
...,
[-0.8711, -0.3516, -0.7227, -1.7188],
[ 0.7188, 0.2285, 0.6445, 1.2969],
[-1.1250, 1.6406, 1.4609, 1.5078]], requires_grad=True)
2024-10-08 15:06:08,681 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.3438, -1.2188, -0.8164, -0.3418],
[ 0.4512, 0.0220, 1.4766, 1.7578],
[ 1.0938, 0.3086, 0.3574, 0.9141],
...,
[-1.0078, -0.1807, -0.6445, -1.6484],
[ 0.7852, 0.2754, 0.6719, 1.3203],
[-1.0156, 1.6250, 1.3984, 1.4922]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.3438, -1.2188, -0.8164, -0.3418],
[ 0.4512, 0.0220, 1.4766, 1.7578],
[ 1.0938, 0.3086, 0.3574, 0.9141],
...,
[-1.0078, -0.1807, -0.6445, -1.6484],
[ 0.7852, 0.2754, 0.6719, 1.3203],
[-1.0156, 1.6250, 1.3984, 1.4922]], requires_grad=True)
2024-10-08 15:06:08,936 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.0938, -1.0469, -0.6992, -0.2734],
[ 0.5781, 0.0806, 1.5000, 1.8047],
[ 1.1797, 0.2812, 0.3398, 0.9102],
...,
[-1.0234, -0.1680, -0.6484, -1.6094],
[ 0.7891, 0.3926, 0.7305, 1.3516],
[-0.9375, 1.6328, 1.3516, 1.4688]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 2.0938, -1.0469, -0.6992, -0.2734],
[ 0.5781, 0.0806, 1.5000, 1.8047],
[ 1.1797, 0.2812, 0.3398, 0.9102],
...,
[-1.0234, -0.1680, -0.6484, -1.6094],
[ 0.7891, 0.3926, 0.7305, 1.3516],
[-0.9375, 1.6328, 1.3516, 1.4688]], requires_grad=True)
2024-10-08 15:06:09,089 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.9219, -0.9375, -0.6172, -0.2148],
[ 0.7344, 0.0894, 1.5000, 1.8438],
[ 1.4453, 0.1484, 0.2754, 0.9219],
...,
[-1.2344, 0.0088, -0.5703, -1.5859],
[ 0.8906, 0.4004, 0.7344, 1.3750],
[-0.7070, 1.4922, 1.2578, 1.4766]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.9219, -0.9375, -0.6172, -0.2148],
[ 0.7344, 0.0894, 1.5000, 1.8438],
[ 1.4453, 0.1484, 0.2754, 0.9219],
...,
[-1.2344, 0.0088, -0.5703, -1.5859],
[ 0.8906, 0.4004, 0.7344, 1.3750],
[-0.7070, 1.4922, 1.2578, 1.4766]], requires_grad=True)
2024-10-08 15:06:09,347 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.7812, -0.8633, -0.5508, -0.1699],
[ 0.9336, -0.0223, 1.4375, 1.8672],
[ 1.7109, -0.0251, 0.1904, 0.9141],
...,
[-1.5156, 0.2969, -0.4355, -1.5469],
[ 1.0156, 0.3359, 0.7031, 1.3828],
[-0.4102, 1.1797, 1.0938, 1.4531]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.7812, -0.8633, -0.5508, -0.1699],
[ 0.9336, -0.0223, 1.4375, 1.8672],
[ 1.7109, -0.0251, 0.1904, 0.9141],
...,
[-1.5156, 0.2969, -0.4355, -1.5469],
[ 1.0156, 0.3359, 0.7031, 1.3828],
[-0.4102, 1.1797, 1.0938, 1.4531]], requires_grad=True)
2024-10-08 15:06:09,501 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.6641, -0.8047, -0.4980, -0.1328],
[ 1.0547, -0.0383, 1.4141, 1.8828],
[ 1.9062, -0.1553, 0.1230, 0.9023],
...,
[-1.7109, 0.5039, -0.3320, -1.5000],
[ 1.0625, 0.3340, 0.6992, 1.3828],
[-0.1836, 0.9609, 0.9727, 1.4297]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.6641, -0.8047, -0.4980, -0.1328],
[ 1.0547, -0.0383, 1.4141, 1.8828],
[ 1.9062, -0.1553, 0.1230, 0.9023],
...,
[-1.7109, 0.5039, -0.3320, -1.5000],
[ 1.0625, 0.3340, 0.6992, 1.3828],
[-0.1836, 0.9609, 0.9727, 1.4297]], requires_grad=True)
2024-10-08 15:06:09,752 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.5859, -0.7227, -0.4336, -0.0742],
[ 1.1406, 0.0674, 1.4453, 1.9219],
[ 2.0469, -0.2090, 0.0874, 0.8984],
...,
[-1.8047, 0.5195, -0.3125, -1.4844],
[ 1.0469, 0.4531, 0.7383, 1.3984],
[-0.0236, 0.9258, 0.9180, 1.4453]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.5859, -0.7227, -0.4336, -0.0742],
[ 1.1406, 0.0674, 1.4453, 1.9219],
[ 2.0469, -0.2090, 0.0874, 0.8984],
...,
[-1.8047, 0.5195, -0.3125, -1.4844],
[ 1.0469, 0.4531, 0.7383, 1.3984],
[-0.0236, 0.9258, 0.9180, 1.4453]], requires_grad=True)
2024-10-08 15:06:10,006 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.4922, -0.6172, -0.3691, -0.0303],
[ 1.2188, 0.1494, 1.4609, 1.9531],
[ 2.1719, -0.2832, 0.0483, 0.8984],
...,
[-1.9219, 0.5742, -0.2812, -1.4766],
[ 1.0469, 0.5078, 0.7539, 1.4141],
[ 0.1406, 0.8281, 0.8516, 1.4609]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.4922, -0.6172, -0.3691, -0.0303],
[ 1.2188, 0.1494, 1.4609, 1.9531],
[ 2.1719, -0.2832, 0.0483, 0.8984],
...,
[-1.9219, 0.5742, -0.2812, -1.4766],
[ 1.0469, 0.5078, 0.7539, 1.4141],
[ 0.1406, 0.8281, 0.8516, 1.4609]], requires_grad=True)
2024-10-08 15:06:10,276 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.4219, -0.5234, -0.3105, 0.0170],
[ 1.2891, 0.1875, 1.4609, 1.9766],
[ 2.2656, -0.3555, 0.0107, 0.8984],
...,
[-2.0156, 0.6680, -0.2383, -1.4766],
[ 1.0312, 0.5195, 0.7539, 1.4297],
[ 0.2910, 0.7422, 0.7891, 1.4766]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.4219, -0.5234, -0.3105, 0.0170],
[ 1.2891, 0.1875, 1.4609, 1.9766],
[ 2.2656, -0.3555, 0.0107, 0.8984],
...,
[-2.0156, 0.6680, -0.2383, -1.4766],
[ 1.0312, 0.5195, 0.7539, 1.4297],
[ 0.2910, 0.7422, 0.7891, 1.4766]], requires_grad=True)
2024-10-08 15:06:10,432 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3906, -0.4082, -0.2480, 0.0549],
[ 1.3438, 0.1973, 1.4453, 2.0000],
[ 2.3438, -0.4453, -0.0310, 0.9023],
...,
[-2.0781, 0.7656, -0.1934, -1.4766],
[ 0.9961, 0.4980, 0.7422, 1.4453],
[ 0.4238, 0.6680, 0.7344, 1.4844]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3906, -0.4082, -0.2480, 0.0549],
[ 1.3438, 0.1973, 1.4453, 2.0000],
[ 2.3438, -0.4453, -0.0310, 0.9023],
...,
[-2.0781, 0.7656, -0.1934, -1.4766],
[ 0.9961, 0.4980, 0.7422, 1.4453],
[ 0.4238, 0.6680, 0.7344, 1.4844]], requires_grad=True)
2024-10-08 15:06:10,590 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3516, -0.3203, -0.1963, 0.0889],
[ 1.3906, 0.1885, 1.4219, 2.0156],
[ 2.4062, -0.5000, -0.0615, 0.8984],
...,
[-2.1094, 0.7539, -0.1797, -1.4453],
[ 0.9414, 0.5742, 0.7539, 1.4141],
[ 0.5391, 0.7031, 0.7070, 1.4688]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3516, -0.3203, -0.1963, 0.0889],
[ 1.3906, 0.1885, 1.4219, 2.0156],
[ 2.4062, -0.5000, -0.0615, 0.8984],
...,
[-2.1094, 0.7539, -0.1797, -1.4453],
[ 0.9414, 0.5742, 0.7539, 1.4141],
[ 0.5391, 0.7031, 0.7070, 1.4688]], requires_grad=True)
2024-10-08 15:06:10,753 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.2969, -0.2695, -0.1621, 0.1270],
[ 1.4688, 0.2305, 1.4375, 2.0312],
[ 2.4531, -0.5273, -0.0786, 0.8867],
...,
[-2.1406, 0.7188, -0.1777, -1.4062],
[ 0.8984, 0.6406, 0.7617, 1.3906],
[ 0.6523, 0.7695, 0.6992, 1.4453]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.2969, -0.2695, -0.1621, 0.1270],
[ 1.4688, 0.2305, 1.4375, 2.0312],
[ 2.4531, -0.5273, -0.0786, 0.8867],
...,
[-2.1406, 0.7188, -0.1777, -1.4062],
[ 0.8984, 0.6406, 0.7617, 1.3906],
[ 0.6523, 0.7695, 0.6992, 1.4453]], requires_grad=True)
2024-10-08 15:06:11,011 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3125, -0.1992, -0.1147, 0.1592],
[ 1.4453, 0.2090, 1.3906, 2.0312],
[ 2.4219, -0.5781, -0.1143, 0.8750],
...,
[-2.1094, 0.7148, -0.1533, -1.3750],
[ 0.8281, 0.6797, 0.7578, 1.3672],
[ 0.7383, 0.8164, 0.6875, 1.4141]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3125, -0.1992, -0.1147, 0.1592],
[ 1.4453, 0.2090, 1.3906, 2.0312],
[ 2.4219, -0.5781, -0.1143, 0.8750],
...,
[-2.1094, 0.7148, -0.1533, -1.3750],
[ 0.8281, 0.6797, 0.7578, 1.3672],
[ 0.7383, 0.8164, 0.6875, 1.4141]], requires_grad=True)
2024-10-08 15:06:11,279 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3281, -0.1387, -0.0732, 0.1914],
[ 1.3828, 0.1445, 1.3125, 2.0312],
[ 2.3281, -0.6680, -0.1777, 0.8750],
...,
[-2.0781, 0.7148, -0.1289, -1.3438],
[ 0.7461, 0.6953, 0.7383, 1.3438],
[ 0.7617, 0.7812, 0.6250, 1.4141]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3281, -0.1387, -0.0732, 0.1914],
[ 1.3828, 0.1445, 1.3125, 2.0312],
[ 2.3281, -0.6680, -0.1777, 0.8750],
...,
[-2.0781, 0.7148, -0.1289, -1.3438],
[ 0.7461, 0.6953, 0.7383, 1.3438],
[ 0.7617, 0.7812, 0.6250, 1.4141]], requires_grad=True)
2024-10-08 15:06:11,692 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3438, -0.0723, -0.0273, 0.2178],
[ 1.3438, 0.1377, 1.2812, 2.0156],
[ 2.2344, -0.7461, -0.2354, 0.8711],
...,
[-2.0469, 0.7227, -0.0996, -1.3125],
[ 0.6641, 0.6992, 0.7109, 1.3203],
[ 0.7773, 0.7500, 0.5664, 1.4062]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.3438, -0.0723, -0.0273, 0.2178],
[ 1.3438, 0.1377, 1.2812, 2.0156],
[ 2.2344, -0.7461, -0.2354, 0.8711],
...,
[-2.0469, 0.7227, -0.0996, -1.3125],
[ 0.6641, 0.6992, 0.7109, 1.3203],
[ 0.7773, 0.7500, 0.5664, 1.4062]], requires_grad=True)
2024-10-08 15:06:11,848 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.2188, 0.0293, 0.0391, 0.1787],
[ 1.3516, 0.1768, 1.3047, 2.0312],
[ 2.2031, -0.8008, -0.2715, 0.8828],
...,
[-2.0469, 0.7031, -0.0991, -1.2969],
[ 0.6133, 0.6992, 0.6875, 1.3047],
[ 0.7852, 0.7461, 0.5391, 1.3906]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.2188, 0.0293, 0.0391, 0.1787],
[ 1.3516, 0.1768, 1.3047, 2.0312],
[ 2.2031, -0.8008, -0.2715, 0.8828],
...,
[-2.0469, 0.7031, -0.0991, -1.2969],
[ 0.6133, 0.6992, 0.6875, 1.3047],
[ 0.7852, 0.7461, 0.5391, 1.3906]], requires_grad=True)
2024-10-08 15:06:12,100 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0781, 0.1289, 0.1055, 0.1348],
[ 1.3672, 0.3105, 1.4297, 2.0469],
[ 2.1562, -0.8281, -0.2812, 0.8906],
...,
[-2.0312, 0.6328, -0.1611, -1.2812],
[ 0.5508, 0.7227, 0.6914, 1.2812],
[ 0.7969, 0.8438, 0.6055, 1.3906]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0781, 0.1289, 0.1055, 0.1348],
[ 1.3672, 0.3105, 1.4297, 2.0469],
[ 2.1562, -0.8281, -0.2812, 0.8906],
...,
[-2.0312, 0.6328, -0.1611, -1.2812],
[ 0.5508, 0.7227, 0.6914, 1.2812],
[ 0.7969, 0.8438, 0.6055, 1.3906]], requires_grad=True)
2024-10-08 15:06:12,357 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0000, 0.1748, 0.1230, 0.1113],
[ 1.3906, 0.4121, 1.5234, 2.0625],
[ 2.1250, -0.8594, -0.2988, 0.8984],
...,
[-2.0000, 0.5430, -0.2402, -1.2578],
[ 0.4824, 0.7617, 0.7188, 1.2500],
[ 0.8164, 0.9219, 0.6523, 1.3906]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0000, 0.1748, 0.1230, 0.1113],
[ 1.3906, 0.4121, 1.5234, 2.0625],
[ 2.1250, -0.8594, -0.2988, 0.8984],
...,
[-2.0000, 0.5430, -0.2402, -1.2578],
[ 0.4824, 0.7617, 0.7188, 1.2500],
[ 0.8164, 0.9219, 0.6523, 1.3906]], requires_grad=True)
2024-10-08 15:06:12,617 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.8477, 0.1924, 0.1064, 0.0518],
[ 1.4531, 0.4941, 1.5938, 2.0781],
[ 2.1250, -0.8789, -0.3086, 0.9180],
...,
[-1.9766, 0.5234, -0.2363, -1.2266],
[ 0.4941, 0.7422, 0.6836, 1.2422],
[ 0.8359, 0.9219, 0.6250, 1.3750]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.8477, 0.1924, 0.1064, 0.0518],
[ 1.4531, 0.4941, 1.5938, 2.0781],
[ 2.1250, -0.8789, -0.3086, 0.9180],
...,
[-1.9766, 0.5234, -0.2363, -1.2266],
[ 0.4941, 0.7422, 0.6836, 1.2422],
[ 0.8359, 0.9219, 0.6250, 1.3750]], requires_grad=True)
2024-10-08 15:06:12,781 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.7266, 0.2051, 0.0908, 0.0060],
[ 1.4922, 0.5625, 1.6562, 2.0938],
[ 2.1094, -0.8789, -0.2949, 0.9258],
...,
[-1.9219, 0.4609, -0.2969, -1.1875],
[ 0.4824, 0.7422, 0.6836, 1.2266],
[ 0.8398, 0.9453, 0.6328, 1.3516]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.7266, 0.2051, 0.0908, 0.0060],
[ 1.4922, 0.5625, 1.6562, 2.0938],
[ 2.1094, -0.8789, -0.2949, 0.9258],
...,
[-1.9219, 0.4609, -0.2969, -1.1875],
[ 0.4824, 0.7422, 0.6836, 1.2266],
[ 0.8398, 0.9453, 0.6328, 1.3516]], requires_grad=True)
2024-10-08 15:06:13,057 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.6250, 0.2139, 0.0737, -0.0315],
[ 1.5234, 0.6523, 1.7578, 2.0938],
[ 2.0781, -0.8672, -0.2637, 0.9297],
...,
[-1.8594, 0.3750, -0.4043, -1.1406],
[ 0.4609, 0.7695, 0.7266, 1.2031],
[ 0.8320, 0.9883, 0.6719, 1.3203]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.6250, 0.2139, 0.0737, -0.0315],
[ 1.5234, 0.6523, 1.7578, 2.0938],
[ 2.0781, -0.8672, -0.2637, 0.9297],
...,
[-1.8594, 0.3750, -0.4043, -1.1406],
[ 0.4609, 0.7695, 0.7266, 1.2031],
[ 0.8320, 0.9883, 0.6719, 1.3203]], requires_grad=True)
2024-10-08 15:06:13,214 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.5625, 0.2949, 0.1973, -0.0596],
[ 1.5234, 0.6836, 1.7422, 2.0781],
[ 2.0312, -0.8750, -0.2812, 0.9297],
...,
[-1.7812, 0.3145, -0.4609, -1.1016],
[ 0.4258, 0.7148, 0.6133, 1.1719],
[ 0.8359, 0.9805, 0.6367, 1.3047]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.5625, 0.2949, 0.1973, -0.0596],
[ 1.5234, 0.6836, 1.7422, 2.0781],
[ 2.0312, -0.8750, -0.2812, 0.9297],
...,
[-1.7812, 0.3145, -0.4609, -1.1016],
[ 0.4258, 0.7148, 0.6133, 1.1719],
[ 0.8359, 0.9805, 0.6367, 1.3047]], requires_grad=True)
2024-10-08 15:06:13,634 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.4941, 0.3633, 0.2988, -0.0874],
[ 1.5391, 0.6680, 1.6328, 2.0625],
[ 1.9922, -0.8867, -0.3105, 0.9258],
...,
[-1.6875, 0.2344, -0.5664, -1.0547],
[ 0.3848, 0.6641, 0.5078, 1.1406],
[ 0.8438, 0.9414, 0.5547, 1.2891]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.4941, 0.3633, 0.2988, -0.0874],
[ 1.5391, 0.6680, 1.6328, 2.0625],
[ 1.9922, -0.8867, -0.3105, 0.9258],
...,
[-1.6875, 0.2344, -0.5664, -1.0547],
[ 0.3848, 0.6641, 0.5078, 1.1406],
[ 0.8438, 0.9414, 0.5547, 1.2891]], requires_grad=True)
2024-10-08 15:06:13,901 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.4277, 0.4219, 0.3867, -0.1128],
[ 1.4844, 0.7891, 1.8359, 2.0312],
[ 1.9297, -0.8711, -0.2871, 0.9141],
...,
[-1.5781, 0.1211, -0.7500, -0.9961],
[ 0.3164, 0.6523, 0.4844, 1.1016],
[ 0.8320, 0.9727, 0.6016, 1.2656]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.4277, 0.4219, 0.3867, -0.1128],
[ 1.4844, 0.7891, 1.8359, 2.0312],
[ 1.9297, -0.8711, -0.2871, 0.9141],
...,
[-1.5781, 0.1211, -0.7500, -0.9961],
[ 0.3164, 0.6523, 0.4844, 1.1016],
[ 0.8320, 0.9727, 0.6016, 1.2656]], requires_grad=True)
2024-10-08 15:06:14,060 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.3711, 0.4590, 0.4355, -0.1318],
[ 1.4219, 0.8906, 2.0000, 1.9844],
[ 1.8750, -0.8633, -0.2852, 0.8984],
...,
[-1.4844, 0.0693, -0.8086, -0.9453],
[ 0.2578, 0.6211, 0.4316, 1.0625],
[ 0.8164, 0.9961, 0.6328, 1.2344]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.3711, 0.4590, 0.4355, -0.1318],
[ 1.4219, 0.8906, 2.0000, 1.9844],
[ 1.8750, -0.8633, -0.2852, 0.8984],
...,
[-1.4844, 0.0693, -0.8086, -0.9453],
[ 0.2578, 0.6211, 0.4316, 1.0625],
[ 0.8164, 0.9961, 0.6328, 1.2344]], requires_grad=True)
2024-10-08 15:06:14,216 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.3203, 0.4863, 0.4727, -0.1465],
[ 1.3672, 0.8320, 1.8594, 1.9531],
[ 1.8125, -0.8945, -0.3535, 0.8867],
...,
[-1.3984, 0.1025, -0.7070, -0.9141],
[ 0.2041, 0.5508, 0.3105, 1.0312],
[ 0.8008, 0.9219, 0.5195, 1.2188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.3203, 0.4863, 0.4727, -0.1465],
[ 1.3672, 0.8320, 1.8594, 1.9531],
[ 1.8125, -0.8945, -0.3535, 0.8867],
...,
[-1.3984, 0.1025, -0.7070, -0.9141],
[ 0.2041, 0.5508, 0.3105, 1.0312],
[ 0.8008, 0.9219, 0.5195, 1.2188]], requires_grad=True)
2024-10-08 15:06:14,482 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2852, 0.5039, 0.4980, -0.1543],
[ 1.2891, 0.8516, 1.8516, 1.8984],
[ 1.7422, -0.9141, -0.4082, 0.8711],
...,
[-1.2891, 0.0388, -0.7734, -0.8516],
[ 0.1367, 0.5391, 0.2832, 0.9766],
[ 0.7930, 0.8555, 0.4199, 1.2109]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2852, 0.5039, 0.4980, -0.1543],
[ 1.2891, 0.8516, 1.8516, 1.8984],
[ 1.7422, -0.9141, -0.4082, 0.8711],
...,
[-1.2891, 0.0388, -0.7734, -0.8516],
[ 0.1367, 0.5391, 0.2832, 0.9766],
[ 0.7930, 0.8555, 0.4199, 1.2109]], requires_grad=True)
2024-10-08 15:06:14,736 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1328, 0.4648, 0.4434, -0.2070],
[ 1.1172, 0.9023, 1.8906, 1.7969],
[ 1.7266, -0.8594, -0.3535, 0.8711],
...,
[-1.1484, -0.0996, -0.9492, -0.7695],
[ 0.1138, 0.5977, 0.3555, 0.9375],
[ 0.7461, 0.8242, 0.3691, 1.1719]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1328, 0.4648, 0.4434, -0.2070],
[ 1.1172, 0.9023, 1.8906, 1.7969],
[ 1.7266, -0.8594, -0.3535, 0.8711],
...,
[-1.1484, -0.0996, -0.9492, -0.7695],
[ 0.1138, 0.5977, 0.3555, 0.9375],
[ 0.7461, 0.8242, 0.3691, 1.1719]], requires_grad=True)
2024-10-08 15:06:14,989 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0571, 0.4766, 0.4434, -0.2754],
[ 1.0625, 0.8086, 1.7578, 1.7422],
[ 1.7344, -0.8359, -0.3359, 0.8750],
...,
[-1.0547, -0.1934, -1.0703, -0.7070],
[ 0.1201, 0.6250, 0.3984, 0.9141],
[ 0.7344, 0.7266, 0.2480, 1.1562]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0571, 0.4766, 0.4434, -0.2754],
[ 1.0625, 0.8086, 1.7578, 1.7422],
[ 1.7344, -0.8359, -0.3359, 0.8750],
...,
[-1.0547, -0.1934, -1.0703, -0.7070],
[ 0.1201, 0.6250, 0.3984, 0.9141],
[ 0.7344, 0.7266, 0.2480, 1.1562]], requires_grad=True)
2024-10-08 15:06:15,243 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1699, 0.4453, 0.4082, -0.3223],
[ 1.0234, 0.7266, 1.6328, 1.6953],
[ 1.7578, -0.8359, -0.3379, 0.8789],
...,
[-1.0078, -0.2432, -1.1406, -0.6641],
[ 0.1553, 0.6250, 0.4141, 0.8984],
[ 0.7148, 0.6211, 0.1299, 1.1328]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1699, 0.4453, 0.4082, -0.3223],
[ 1.0234, 0.7266, 1.6328, 1.6953],
[ 1.7578, -0.8359, -0.3379, 0.8789],
...,
[-1.0078, -0.2432, -1.1406, -0.6641],
[ 0.1553, 0.6250, 0.4141, 0.8984],
[ 0.7148, 0.6211, 0.1299, 1.1328]], requires_grad=True)
2024-10-08 15:06:15,393 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2891, 0.4473, 0.3965, -0.3574],
[ 1.0078, 0.5742, 1.4609, 1.6328],
[ 1.7812, -0.8555, -0.3535, 0.8750],
...,
[-0.9453, -0.2891, -1.2031, -0.6133],
[ 0.1797, 0.6055, 0.4160, 0.8750],
[ 0.6992, 0.5078, 0.0130, 1.1016]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2891, 0.4473, 0.3965, -0.3574],
[ 1.0078, 0.5742, 1.4609, 1.6328],
[ 1.7812, -0.8555, -0.3535, 0.8750],
...,
[-0.9453, -0.2891, -1.2031, -0.6133],
[ 0.1797, 0.6055, 0.4160, 0.8750],
[ 0.6992, 0.5078, 0.0130, 1.1016]], requires_grad=True)
2024-10-08 15:06:15,648 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3770, 0.4414, 0.3828, -0.3848],
[ 1.0000, 0.4238, 1.2969, 1.5781],
[ 1.7500, -0.8398, -0.3555, 0.8672],
...,
[-0.8242, -0.3789, -1.2734, -0.5586],
[ 0.1436, 0.6289, 0.4336, 0.8438],
[ 0.6523, 0.4414, -0.0757, 1.0703]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3770, 0.4414, 0.3828, -0.3848],
[ 1.0000, 0.4238, 1.2969, 1.5781],
[ 1.7500, -0.8398, -0.3555, 0.8672],
...,
[-0.8242, -0.3789, -1.2734, -0.5586],
[ 0.1436, 0.6289, 0.4336, 0.8438],
[ 0.6523, 0.4414, -0.0757, 1.0703]], requires_grad=True)
2024-10-08 15:06:15,902 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3340, 0.3691, 0.3555, -0.4043],
[ 0.7734, 0.5352, 1.2188, 1.5312],
[ 1.6016, -0.7539, -0.3379, 0.8555],
...,
[-0.5039, -0.6367, -1.3750, -0.5156],
[ 0.0330, 0.7031, 0.4590, 0.8086],
[ 0.5234, 0.4746, -0.1338, 1.0391]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3340, 0.3691, 0.3555, -0.4043],
[ 0.7734, 0.5352, 1.2188, 1.5312],
[ 1.6016, -0.7539, -0.3379, 0.8555],
...,
[-0.5039, -0.6367, -1.3750, -0.5156],
[ 0.0330, 0.7031, 0.4590, 0.8086],
[ 0.5234, 0.4746, -0.1338, 1.0391]], requires_grad=True)
2024-10-08 15:06:16,166 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3828, 0.3711, 0.3535, -0.4102],
[ 0.6836, 0.4473, 1.0703, 1.4531],
[ 1.4844, -0.6875, -0.3262, 0.8398],
...,
[-0.2930, -0.7656, -1.4297, -0.4590],
[ 0.0270, 0.6562, 0.4375, 0.7539],
[ 0.4121, 0.4961, -0.1865, 1.0000]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3828, 0.3711, 0.3535, -0.4102],
[ 0.6836, 0.4473, 1.0703, 1.4531],
[ 1.4844, -0.6875, -0.3262, 0.8398],
...,
[-0.2930, -0.7656, -1.4297, -0.4590],
[ 0.0270, 0.6562, 0.4375, 0.7539],
[ 0.4121, 0.4961, -0.1865, 1.0000]], requires_grad=True)
2024-10-08 15:06:16,425 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4922, 0.4824, 0.4062, -0.3730],
[ 0.6016, 0.3652, 0.9375, 1.3750],
[ 1.4297, -0.7148, -0.3613, 0.8008],
...,
[-0.1543, -0.7891, -1.4219, -0.3867],
[ 0.0562, 0.5312, 0.3750, 0.6758],
[ 0.3301, 0.4805, -0.2461, 0.9570]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4922, 0.4824, 0.4062, -0.3730],
[ 0.6016, 0.3652, 0.9375, 1.3750],
[ 1.4297, -0.7148, -0.3613, 0.8008],
...,
[-0.1543, -0.7891, -1.4219, -0.3867],
[ 0.0562, 0.5312, 0.3750, 0.6758],
[ 0.3301, 0.4805, -0.2461, 0.9570]], requires_grad=True)
2024-10-08 15:06:16,677 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5234, 0.5312, 0.4219, -0.3359],
[ 0.7227, 0.0150, 0.6211, 1.3203],
[ 1.3750, -0.7344, -0.3867, 0.7617],
...,
[-0.1113, -0.7656, -1.3828, -0.3418],
[ 0.3418, 0.1992, 0.1816, 0.6484],
[ 0.2676, 0.4062, -0.3359, 0.9023]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5234, 0.5312, 0.4219, -0.3359],
[ 0.7227, 0.0150, 0.6211, 1.3203],
[ 1.3750, -0.7344, -0.3867, 0.7617],
...,
[-0.1113, -0.7656, -1.3828, -0.3418],
[ 0.3418, 0.1992, 0.1816, 0.6484],
[ 0.2676, 0.4062, -0.3359, 0.9023]], requires_grad=True)
2024-10-08 15:06:16,942 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4922, 0.5312, 0.4043, -0.2910],
[ 0.7461, -0.1895, 0.4316, 1.2500],
[ 1.3047, -0.7344, -0.3984, 0.7227],
...,
[ 0.0737, -0.8789, -1.4688, -0.2715],
[ 0.5352, -0.0371, 0.0554, 0.6094],
[ 0.2100, 0.3496, -0.4062, 0.8555]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4922, 0.5312, 0.4043, -0.2910],
[ 0.7461, -0.1895, 0.4316, 1.2500],
[ 1.3047, -0.7344, -0.3984, 0.7227],
...,
[ 0.0737, -0.8789, -1.4688, -0.2715],
[ 0.5352, -0.0371, 0.0554, 0.6094],
[ 0.2100, 0.3496, -0.4062, 0.8555]], requires_grad=True)
2024-10-08 15:06:17,193 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1138, 0.2451, 0.1348, -0.1748],
[ 0.4004, 0.3613, 1.0156, 1.1094],
[ 1.0703, -0.5898, -0.2734, 0.6484],
...,
[ 0.4316, -1.4609, -2.0469, -0.2080],
[ 0.8008, 0.1572, 0.3535, 0.6953],
[ 0.0747, 0.8477, 0.0162, 0.8555]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1138, 0.2451, 0.1348, -0.1748],
[ 0.4004, 0.3613, 1.0156, 1.1094],
[ 1.0703, -0.5898, -0.2734, 0.6484],
...,
[ 0.4316, -1.4609, -2.0469, -0.2080],
[ 0.8008, 0.1572, 0.3535, 0.6953],
[ 0.0747, 0.8477, 0.0162, 0.8555]], requires_grad=True)
2024-10-08 15:06:17,459 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1104, -0.1924, -0.2930, -0.1187],
[ 0.2617, 0.7305, 1.4219, 1.0703],
[ 0.9414, -0.4414, -0.1377, 0.6133],
...,
[ 0.5352, -2.0625, -2.6719, -0.2432],
[ 1.1250, 0.4805, 0.7812, 0.8164],
[ 0.0242, 1.4141, 0.5234, 0.8906]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1104, -0.1924, -0.2930, -0.1187],
[ 0.2617, 0.7305, 1.4219, 1.0703],
[ 0.9414, -0.4414, -0.1377, 0.6133],
...,
[ 0.5352, -2.0625, -2.6719, -0.2432],
[ 1.1250, 0.4805, 0.7812, 0.8164],
[ 0.0242, 1.4141, 0.5234, 0.8906]], requires_grad=True)
2024-10-08 15:06:17,618 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0133, -0.4121, -0.5156, -0.2617],
[ 0.7031, 0.5391, 1.2266, 1.4375],
[ 1.0703, -0.4590, -0.1699, 0.7188],
...,
[ 0.3262, -2.3594, -2.9688, -0.4629],
[ 1.6172, 0.5586, 0.9453, 1.0859],
[ 0.2109, 1.6953, 0.7734, 1.1094]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0133, -0.4121, -0.5156, -0.2617],
[ 0.7031, 0.5391, 1.2266, 1.4375],
[ 1.0703, -0.4590, -0.1699, 0.7188],
...,
[ 0.3262, -2.3594, -2.9688, -0.4629],
[ 1.6172, 0.5586, 0.9453, 1.0859],
[ 0.2109, 1.6953, 0.7734, 1.1094]], requires_grad=True)
2024-10-08 15:06:17,886 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1260, -0.6289, -0.7148, -0.3848],
[ 1.0781, 0.3223, 1.0234, 1.7500],
[ 1.1719, -0.4863, -0.2021, 0.8086],
...,
[ 0.1436, -2.6094, -3.2188, -0.6523],
[ 2.0469, 0.6055, 1.0781, 1.3125],
[ 0.3750, 1.8906, 0.9766, 1.3047]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1260, -0.6289, -0.7148, -0.3848],
[ 1.0781, 0.3223, 1.0234, 1.7500],
[ 1.1719, -0.4863, -0.2021, 0.8086],
...,
[ 0.1436, -2.6094, -3.2188, -0.6523],
[ 2.0469, 0.6055, 1.0781, 1.3125],
[ 0.3750, 1.8906, 0.9766, 1.3047]], requires_grad=True)
2024-10-08 15:06:18,038 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2256, -0.8125, -0.8906, -0.4902],
[ 1.4062, 0.0928, 0.9141, 1.9922],
[ 1.2656, -0.5234, -0.2080, 0.8750],
...,
[-0.0070, -2.8281, -3.4219, -0.8125],
[ 2.4062, 0.6445, 1.1875, 1.5078],
[ 0.5195, 2.0625, 1.1562, 1.4688]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2256, -0.8125, -0.8906, -0.4902],
[ 1.4062, 0.0928, 0.9141, 1.9922],
[ 1.2656, -0.5234, -0.2080, 0.8750],
...,
[-0.0070, -2.8281, -3.4219, -0.8125],
[ 2.4062, 0.6445, 1.1875, 1.5078],
[ 0.5195, 2.0625, 1.1562, 1.4688]], requires_grad=True)
2024-10-08 15:06:18,288 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3418, -0.9805, -0.9805, -0.6406],
[ 1.7031, -0.0923, 0.6172, 2.2969],
[ 1.3438, -0.5469, -0.2852, 0.9766],
...,
[-0.1309, -3.0312, -3.4375, -1.0156],
[ 2.7188, 0.6914, 1.1250, 1.7656],
[ 0.6445, 2.2188, 1.1719, 1.6953]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3418, -0.9805, -0.9805, -0.6406],
[ 1.7031, -0.0923, 0.6172, 2.2969],
[ 1.3438, -0.5469, -0.2852, 0.9766],
...,
[-0.1309, -3.0312, -3.4375, -1.0156],
[ 2.7188, 0.6914, 1.1250, 1.7656],
[ 0.6445, 2.2188, 1.1719, 1.6953]], requires_grad=True)
2024-10-08 15:06:18,546 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4453, -1.1172, -1.0703, -0.7617],
[ 1.9375, -0.2305, 0.2471, 2.5938],
[ 1.4062, -0.5625, -0.3730, 1.0703],
...,
[-0.2354, -3.1875, -3.4219, -1.2031],
[ 2.9844, 0.7344, 1.0547, 1.9922],
[ 0.7500, 2.3594, 1.1641, 1.8906]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4453, -1.1172, -1.0703, -0.7617],
[ 1.9375, -0.2305, 0.2471, 2.5938],
[ 1.4062, -0.5625, -0.3730, 1.0703],
...,
[-0.2354, -3.1875, -3.4219, -1.2031],
[ 2.9844, 0.7344, 1.0547, 1.9922],
[ 0.7500, 2.3594, 1.1641, 1.8906]], requires_grad=True)
2024-10-08 15:06:18,686 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5352, -1.2344, -1.1484, -0.8672],
[ 2.1406, -0.3535, -0.0703, 2.8438],
[ 1.4766, -0.5898, -0.4180, 1.1406],
...,
[-0.3379, -3.3125, -3.4375, -1.3516],
[ 3.2188, 0.7500, 1.0234, 2.1719],
[ 0.8477, 2.4375, 1.1875, 2.0469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5352, -1.2344, -1.1484, -0.8672],
[ 2.1406, -0.3535, -0.0703, 2.8438],
[ 1.4766, -0.5898, -0.4180, 1.1406],
...,
[-0.3379, -3.3125, -3.4375, -1.3516],
[ 3.2188, 0.7500, 1.0234, 2.1719],
[ 0.8477, 2.4375, 1.1875, 2.0469]], requires_grad=True)
2024-10-08 15:06:18,847 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6016, -1.3359, -1.2031, -0.9609],
[ 2.3125, -0.4609, -0.3516, 3.0625],
[ 1.5547, -0.6250, -0.4316, 1.1953],
...,
[-0.4688, -3.3750, -3.4844, -1.4609],
[ 3.4531, 0.7305, 1.0391, 2.3125],
[ 0.9336, 2.5000, 1.2109, 2.1719]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6016, -1.3359, -1.2031, -0.9609],
[ 2.3125, -0.4609, -0.3516, 3.0625],
[ 1.5547, -0.6250, -0.4316, 1.1953],
...,
[-0.4688, -3.3750, -3.4844, -1.4609],
[ 3.4531, 0.7305, 1.0391, 2.3125],
[ 0.9336, 2.5000, 1.2109, 2.1719]], requires_grad=True)
2024-10-08 15:06:18,997 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6562, -1.4219, -1.2422, -1.0391],
[ 2.4844, -0.5703, -0.5586, 3.2031],
[ 1.6172, -0.6523, -0.4414, 1.2266],
...,
[-0.5898, -3.4219, -3.5312, -1.5391],
[ 3.6250, 0.7148, 1.0469, 2.4375],
[ 1.0156, 2.5312, 1.2344, 2.2656]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6562, -1.4219, -1.2422, -1.0391],
[ 2.4844, -0.5703, -0.5586, 3.2031],
[ 1.6172, -0.6523, -0.4414, 1.2266],
...,
[-0.5898, -3.4219, -3.5312, -1.5391],
[ 3.6250, 0.7148, 1.0469, 2.4375],
[ 1.0156, 2.5312, 1.2344, 2.2656]], requires_grad=True)
2024-10-08 15:06:19,254 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7969, -1.4766, -1.3047, -1.0625],
[ 2.5781, -0.6484, -0.7695, 3.3438],
[ 1.6250, -0.6641, -0.4668, 1.2734],
...,
[-0.5703, -3.4688, -3.5000, -1.6562],
[ 3.6562, 0.7383, 0.9922, 2.5781],
[ 1.0703, 2.5625, 1.2422, 2.3594]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7969, -1.4766, -1.3047, -1.0625],
[ 2.5781, -0.6484, -0.7695, 3.3438],
[ 1.6250, -0.6641, -0.4668, 1.2734],
...,
[-0.5703, -3.4688, -3.5000, -1.6562],
[ 3.6562, 0.7383, 0.9922, 2.5781],
[ 1.0703, 2.5625, 1.2422, 2.3594]], requires_grad=True)
2024-10-08 15:06:19,410 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8242, -1.5391, -1.3438, -1.1172],
[ 2.5938, -0.6836, -0.9727, 3.4844],
[ 1.5547, -0.6523, -0.5039, 1.3281],
...,
[-0.4043, -3.5625, -3.4062, -1.8125],
[ 3.5625, 0.8008, 0.9062, 2.7500],
[ 1.0391, 2.6250, 1.2188, 2.4531]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8242, -1.5391, -1.3438, -1.1172],
[ 2.5938, -0.6836, -0.9727, 3.4844],
[ 1.5547, -0.6523, -0.5039, 1.3281],
...,
[-0.4043, -3.5625, -3.4062, -1.8125],
[ 3.5625, 0.8008, 0.9062, 2.7500],
[ 1.0391, 2.6250, 1.2188, 2.4531]], requires_grad=True)
2024-10-08 15:06:19,667 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9648, -1.5469, -1.3750, -1.1484],
[ 2.6406, -0.7383, -1.1484, 3.5781],
[ 1.5391, -0.6641, -0.5312, 1.3672],
...,
[-0.2715, -3.6250, -3.3125, -1.9375],
[ 3.5000, 0.8281, 0.8320, 2.8750],
[ 1.0312, 2.6562, 1.1953, 2.5312]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9648, -1.5469, -1.3750, -1.1484],
[ 2.6406, -0.7383, -1.1484, 3.5781],
[ 1.5391, -0.6641, -0.5312, 1.3672],
...,
[-0.2715, -3.6250, -3.3125, -1.9375],
[ 3.5000, 0.8281, 0.8320, 2.8750],
[ 1.0312, 2.6562, 1.1953, 2.5312]], requires_grad=True)
2024-10-08 15:06:19,921 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0859, -1.5547, -1.3984, -1.1719],
[ 2.7812, -0.8438, -1.3125, 3.6406],
[ 1.5703, -0.6953, -0.5586, 1.3906],
...,
[-0.2490, -3.6250, -3.2188, -2.0312],
[ 3.4531, 0.8320, 0.7617, 2.9531],
[ 1.0781, 2.6406, 1.1641, 2.5781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0859, -1.5547, -1.3984, -1.1719],
[ 2.7812, -0.8438, -1.3125, 3.6406],
[ 1.5703, -0.6953, -0.5586, 1.3906],
...,
[-0.2490, -3.6250, -3.2188, -2.0312],
[ 3.4531, 0.8320, 0.7617, 2.9531],
[ 1.0781, 2.6406, 1.1641, 2.5781]], requires_grad=True)
2024-10-08 15:06:20,172 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2109, -1.5469, -1.4141, -1.1797],
[ 2.9375, -0.9688, -1.4609, 3.6875],
[ 1.6562, -0.7500, -0.5938, 1.3906],
...,
[-0.3223, -3.5469, -3.1094, -2.0781],
[ 3.4531, 0.8008, 0.6836, 3.0000],
[ 1.1328, 2.6094, 1.1406, 2.6094]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2109, -1.5469, -1.4141, -1.1797],
[ 2.9375, -0.9688, -1.4609, 3.6875],
[ 1.6562, -0.7500, -0.5938, 1.3906],
...,
[-0.3223, -3.5469, -3.1094, -2.0781],
[ 3.4531, 0.8008, 0.6836, 3.0000],
[ 1.1328, 2.6094, 1.1406, 2.6094]], requires_grad=True)
2024-10-08 15:06:20,422 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1875, -1.5781, -1.4453, -1.1953],
[ 2.9375, -1.0000, -1.5312, 3.7344],
[ 1.6797, -0.7773, -0.6094, 1.3906],
...,
[-0.2197, -3.5469, -3.0469, -2.1406],
[ 3.2969, 0.8398, 0.6523, 3.0625],
[ 1.0938, 2.6250, 1.1406, 2.6406]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1875, -1.5781, -1.4453, -1.1953],
[ 2.9375, -1.0000, -1.5312, 3.7344],
[ 1.6797, -0.7773, -0.6094, 1.3906],
...,
[-0.2197, -3.5469, -3.0469, -2.1406],
[ 3.2969, 0.8398, 0.6523, 3.0625],
[ 1.0938, 2.6250, 1.1406, 2.6406]], requires_grad=True)
2024-10-08 15:06:20,691 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2188, -1.5781, -1.4531, -1.1953],
[ 2.8906, -0.9961, -1.5781, 3.7812],
[ 1.6875, -0.7969, -0.6211, 1.3906],
...,
[-0.1133, -3.5469, -2.9844, -2.1875],
[ 3.1719, 0.8711, 0.6211, 3.1094],
[ 1.0312, 2.6406, 1.1406, 2.6719]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2188, -1.5781, -1.4531, -1.1953],
[ 2.8906, -0.9961, -1.5781, 3.7812],
[ 1.6875, -0.7969, -0.6211, 1.3906],
...,
[-0.1133, -3.5469, -2.9844, -2.1875],
[ 3.1719, 0.8711, 0.6211, 3.1094],
[ 1.0312, 2.6406, 1.1406, 2.6719]], requires_grad=True)
2024-10-08 15:06:20,954 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1562, -1.6094, -1.4766, -1.2031],
[ 2.6719, -0.8750, -1.5156, 3.8281],
[ 1.6562, -0.7969, -0.6172, 1.3906],
...,
[ 0.0593, -3.5781, -2.9531, -2.2344],
[ 3.0000, 0.9180, 0.6133, 3.1406],
[ 0.8828, 2.7188, 1.1875, 2.7031]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1562, -1.6094, -1.4766, -1.2031],
[ 2.6719, -0.8750, -1.5156, 3.8281],
[ 1.6562, -0.7969, -0.6172, 1.3906],
...,
[ 0.0593, -3.5781, -2.9531, -2.2344],
[ 3.0000, 0.9180, 0.6133, 3.1406],
[ 0.8828, 2.7188, 1.1875, 2.7031]], requires_grad=True)
2024-10-08 15:06:21,225 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1016, -1.6328, -1.4922, -1.2109],
[ 2.4844, -0.7656, -1.4609, 3.8594],
[ 1.6016, -0.7734, -0.5938, 1.3984],
...,
[ 0.1992, -3.5938, -2.9219, -2.2656],
[ 2.8594, 0.9492, 0.5938, 3.1719],
[ 0.7461, 2.7812, 1.2266, 2.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1016, -1.6328, -1.4922, -1.2109],
[ 2.4844, -0.7656, -1.4609, 3.8594],
[ 1.6016, -0.7734, -0.5938, 1.3984],
...,
[ 0.1992, -3.5938, -2.9219, -2.2656],
[ 2.8594, 0.9492, 0.5938, 3.1719],
[ 0.7461, 2.7812, 1.2266, 2.7188]], requires_grad=True)
2024-10-08 15:06:21,377 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0156, -1.6562, -1.5078, -1.2031],
[ 2.4375, -0.7734, -1.5000, 3.8594],
[ 1.6484, -0.7930, -0.6094, 1.3984],
...,
[ 0.1084, -3.4688, -2.7656, -2.2812],
[ 2.8438, 0.9062, 0.5195, 3.1719],
[ 0.7227, 2.7500, 1.1953, 2.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0156, -1.6562, -1.5078, -1.2031],
[ 2.4375, -0.7734, -1.5000, 3.8594],
[ 1.6484, -0.7930, -0.6094, 1.3984],
...,
[ 0.1084, -3.4688, -2.7656, -2.2812],
[ 2.8438, 0.9062, 0.5195, 3.1719],
[ 0.7227, 2.7500, 1.1953, 2.7188]], requires_grad=True)
2024-10-08 15:06:21,634 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9727, -1.6719, -1.5156, -1.2031],
[ 2.3281, -0.7109, -1.4609, 3.8750],
[ 1.7109, -0.8125, -0.6211, 1.3984],
...,
[-0.0295, -3.3125, -2.6094, -2.2812],
[ 2.8438, 0.8594, 0.4492, 3.1719],
[ 0.6875, 2.7344, 1.1719, 2.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9727, -1.6719, -1.5156, -1.2031],
[ 2.3281, -0.7109, -1.4609, 3.8750],
[ 1.7109, -0.8125, -0.6211, 1.3984],
...,
[-0.0295, -3.3125, -2.6094, -2.2812],
[ 2.8438, 0.8594, 0.4492, 3.1719],
[ 0.6875, 2.7344, 1.1719, 2.7188]], requires_grad=True)
2024-10-08 15:06:21,892 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9062, -1.6875, -1.5312, -1.2031],
[ 2.1875, -0.6211, -1.3906, 3.8750],
[ 1.7109, -0.8125, -0.6172, 1.3984],
...,
[-0.0430, -3.2344, -2.5156, -2.2969],
[ 2.7656, 0.8555, 0.4238, 3.1562],
[ 0.6211, 2.7344, 1.1797, 2.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9062, -1.6875, -1.5312, -1.2031],
[ 2.1875, -0.6211, -1.3906, 3.8750],
[ 1.7109, -0.8125, -0.6172, 1.3984],
...,
[-0.0430, -3.2344, -2.5156, -2.2969],
[ 2.7656, 0.8555, 0.4238, 3.1562],
[ 0.6211, 2.7344, 1.1797, 2.7188]], requires_grad=True)
2024-10-08 15:06:22,145 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8242, -1.7188, -1.5625, -1.2109],
[ 2.0156, -0.4824, -1.2656, 3.8906],
[ 1.6406, -0.7734, -0.5703, 1.4062],
...,
[ 0.0159, -3.2031, -2.4688, -2.3125],
[ 2.6250, 0.8984, 0.4473, 3.1562],
[ 0.4902, 2.7969, 1.2344, 2.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8242, -1.7188, -1.5625, -1.2109],
[ 2.0156, -0.4824, -1.2656, 3.8906],
[ 1.6406, -0.7734, -0.5703, 1.4062],
...,
[ 0.0159, -3.2031, -2.4688, -2.3125],
[ 2.6250, 0.8984, 0.4473, 3.1562],
[ 0.4902, 2.7969, 1.2344, 2.7188]], requires_grad=True)
2024-10-08 15:06:22,417 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8320, -1.6875, -1.5391, -1.1953],
[ 1.8828, -0.3574, -1.1406, 3.9062],
[ 1.5781, -0.7266, -0.5234, 1.4141],
...,
[ 0.0408, -3.1562, -2.4062, -2.3125],
[ 2.5000, 0.9336, 0.4688, 3.1562],
[ 0.3926, 2.8281, 1.2656, 2.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8320, -1.6875, -1.5391, -1.1953],
[ 1.8828, -0.3574, -1.1406, 3.9062],
[ 1.5781, -0.7266, -0.5234, 1.4141],
...,
[ 0.0408, -3.1562, -2.4062, -2.3125],
[ 2.5000, 0.9336, 0.4688, 3.1562],
[ 0.3926, 2.8281, 1.2656, 2.7188]], requires_grad=True)
2024-10-08 15:06:22,673 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9102, -1.6250, -1.4844, -1.1719],
[ 1.8438, -0.3184, -1.0938, 3.8906],
[ 1.5859, -0.7148, -0.5078, 1.4141],
...,
[-0.0383, -3.0469, -2.2812, -2.2969],
[ 2.4688, 0.9102, 0.4434, 3.1406],
[ 0.3594, 2.7969, 1.2500, 2.6875]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9102, -1.6250, -1.4844, -1.1719],
[ 1.8438, -0.3184, -1.0938, 3.8906],
[ 1.5859, -0.7148, -0.5078, 1.4141],
...,
[-0.0383, -3.0469, -2.2812, -2.2969],
[ 2.4688, 0.9102, 0.4434, 3.1406],
[ 0.3594, 2.7969, 1.2500, 2.6875]], requires_grad=True)
2024-10-08 15:06:22,826 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0391, -1.5391, -1.4062, -1.1484],
[ 1.8203, -0.3125, -1.0781, 3.8594],
[ 1.6172, -0.7188, -0.5039, 1.4062],
...,
[-0.1465, -2.9062, -2.1562, -2.2812],
[ 2.4844, 0.8398, 0.3809, 3.1094],
[ 0.3457, 2.7344, 1.2109, 2.6406]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0391, -1.5391, -1.4062, -1.1484],
[ 1.8203, -0.3125, -1.0781, 3.8594],
[ 1.6172, -0.7188, -0.5039, 1.4062],
...,
[-0.1465, -2.9062, -2.1562, -2.2812],
[ 2.4844, 0.8398, 0.3809, 3.1094],
[ 0.3457, 2.7344, 1.2109, 2.6406]], requires_grad=True)
2024-10-08 15:06:23,089 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1797, -1.4375, -1.3281, -1.1172],
[ 1.9766, -0.4434, -1.1797, 3.8125],
[ 1.6875, -0.7344, -0.5117, 1.3984],
...,
[-0.2578, -2.7812, -2.0469, -2.2656],
[ 2.5156, 0.7617, 0.3125, 3.0625],
[ 0.3613, 2.6562, 1.1562, 2.5938]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1797, -1.4375, -1.3281, -1.1172],
[ 1.9766, -0.4434, -1.1797, 3.8125],
[ 1.6875, -0.7344, -0.5117, 1.3984],
...,
[-0.2578, -2.7812, -2.0469, -2.2656],
[ 2.5156, 0.7617, 0.3125, 3.0625],
[ 0.3613, 2.6562, 1.1562, 2.5938]], requires_grad=True)
2024-10-08 15:06:23,355 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2969, -1.3438, -1.2578, -1.0859],
[ 2.0625, -0.5078, -1.2109, 3.7812],
[ 1.7109, -0.7227, -0.4961, 1.3984],
...,
[-0.3555, -2.6875, -1.9531, -2.2500],
[ 2.5469, 0.6914, 0.2559, 3.0156],
[ 0.3359, 2.6094, 1.1406, 2.5625]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2969, -1.3438, -1.2578, -1.0859],
[ 2.0625, -0.5078, -1.2109, 3.7812],
[ 1.7109, -0.7227, -0.4961, 1.3984],
...,
[-0.3555, -2.6875, -1.9531, -2.2500],
[ 2.5469, 0.6914, 0.2559, 3.0156],
[ 0.3359, 2.6094, 1.1406, 2.5625]], requires_grad=True)
2024-10-08 15:06:23,621 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2266, -1.3359, -1.2422, -1.0781],
[ 2.1719, -0.5938, -1.2656, 3.7344],
[ 1.6641, -0.6836, -0.4590, 1.3984],
...,
[-0.3789, -2.6250, -1.8984, -2.2500],
[ 2.4844, 0.6797, 0.2422, 2.9688],
[ 0.2715, 2.5938, 1.1484, 2.5312]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2266, -1.3359, -1.2422, -1.0781],
[ 2.1719, -0.5938, -1.2656, 3.7344],
[ 1.6641, -0.6836, -0.4590, 1.3984],
...,
[-0.3789, -2.6250, -1.8984, -2.2500],
[ 2.4844, 0.6797, 0.2422, 2.9688],
[ 0.2715, 2.5938, 1.1484, 2.5312]], requires_grad=True)
2024-10-08 15:06:23,909 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1484, -1.3359, -1.2344, -1.0703],
[ 2.3125, -0.7109, -1.3438, 3.6719],
[ 1.6328, -0.6562, -0.4316, 1.3906],
...,
[-0.4199, -2.5469, -1.8359, -2.2344],
[ 2.4375, 0.6523, 0.2197, 2.9219],
[ 0.1943, 2.5938, 1.1719, 2.5000]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1484, -1.3359, -1.2344, -1.0703],
[ 2.3125, -0.7109, -1.3438, 3.6719],
[ 1.6328, -0.6562, -0.4316, 1.3906],
...,
[-0.4199, -2.5469, -1.8359, -2.2344],
[ 2.4375, 0.6523, 0.2197, 2.9219],
[ 0.1943, 2.5938, 1.1719, 2.5000]], requires_grad=True)
2024-10-08 15:06:24,173 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0469, -1.3516, -1.2344, -1.0703],
[ 2.4375, -0.8203, -1.4141, 3.5938],
[ 1.6016, -0.6289, -0.4043, 1.3828],
...,
[-0.4453, -2.4844, -1.7812, -2.2188],
[ 2.3750, 0.6328, 0.2041, 2.8750],
[ 0.0898, 2.6250, 1.2109, 2.4688]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.0469, -1.3516, -1.2344, -1.0703],
[ 2.4375, -0.8203, -1.4141, 3.5938],
[ 1.6016, -0.6289, -0.4043, 1.3828],
...,
[-0.4453, -2.4844, -1.7812, -2.2188],
[ 2.3750, 0.6328, 0.2041, 2.8750],
[ 0.0898, 2.6250, 1.2109, 2.4688]], requires_grad=True)
2024-10-08 15:06:24,426 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9766, -1.3438, -1.2188, -1.0547],
[ 2.5312, -0.9258, -1.4844, 3.5156],
[ 1.5625, -0.6016, -0.3809, 1.3750],
...,
[-0.4512, -2.4219, -1.7344, -2.2031],
[ 2.3281, 0.5977, 0.1787, 2.8125],
[-0.0271, 2.6719, 1.2578, 2.4531]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9766, -1.3438, -1.2188, -1.0547],
[ 2.5312, -0.9258, -1.4844, 3.5156],
[ 1.5625, -0.6016, -0.3809, 1.3750],
...,
[-0.4512, -2.4219, -1.7344, -2.2031],
[ 2.3281, 0.5977, 0.1787, 2.8125],
[-0.0271, 2.6719, 1.2578, 2.4531]], requires_grad=True)
2024-10-08 15:06:24,684 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9180, -1.3281, -1.1953, -1.0391],
[ 2.6250, -1.0391, -1.5547, 3.4219],
[ 1.5312, -0.5820, -0.3633, 1.3594],
...,
[-0.4531, -2.3594, -1.6875, -2.1719],
[ 2.3125, 0.5547, 0.1494, 2.7656],
[-0.1299, 2.7188, 1.2969, 2.4219]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9180, -1.3281, -1.1953, -1.0391],
[ 2.6250, -1.0391, -1.5547, 3.4219],
[ 1.5312, -0.5820, -0.3633, 1.3594],
...,
[-0.4531, -2.3594, -1.6875, -2.1719],
[ 2.3125, 0.5547, 0.1494, 2.7656],
[-0.1299, 2.7188, 1.2969, 2.4219]], requires_grad=True)
2024-10-08 15:06:24,841 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8867, -1.2891, -1.1562, -1.0078],
[ 2.7031, -1.1328, -1.6094, 3.3281],
[ 1.5156, -0.5781, -0.3555, 1.3359],
...,
[-0.4785, -2.2656, -1.6250, -2.1250],
[ 2.3125, 0.4844, 0.0991, 2.7031],
[-0.2207, 2.7500, 1.3281, 2.3906]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8867, -1.2891, -1.1562, -1.0078],
[ 2.7031, -1.1328, -1.6094, 3.3281],
[ 1.5156, -0.5781, -0.3555, 1.3359],
...,
[-0.4785, -2.2656, -1.6250, -2.1250],
[ 2.3125, 0.4844, 0.0991, 2.7031],
[-0.2207, 2.7500, 1.3281, 2.3906]], requires_grad=True)
2024-10-08 15:06:25,108 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8594, -1.2422, -1.1172, -0.9727],
[ 2.7344, -1.1875, -1.6328, 3.2500],
[ 1.4766, -0.5664, -0.3438, 1.3125],
...,
[-0.5078, -2.1719, -1.5547, -2.0781],
[ 2.3281, 0.3965, 0.0361, 2.6250],
[-0.3203, 2.7969, 1.3672, 2.3594]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8594, -1.2422, -1.1172, -0.9727],
[ 2.7344, -1.1875, -1.6328, 3.2500],
[ 1.4766, -0.5664, -0.3438, 1.3125],
...,
[-0.5078, -2.1719, -1.5547, -2.0781],
[ 2.3281, 0.3965, 0.0361, 2.6250],
[-0.3203, 2.7969, 1.3672, 2.3594]], requires_grad=True)
2024-10-08 15:06:25,268 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8320, -1.1953, -1.0781, -0.9414],
[ 2.7500, -1.2188, -1.6484, 3.1719],
[ 1.4531, -0.5625, -0.3379, 1.2812],
...,
[-0.5234, -2.0938, -1.4844, -2.0312],
[ 2.3281, 0.3223, -0.0166, 2.5469],
[-0.4023, 2.8281, 1.3906, 2.3281]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8320, -1.1953, -1.0781, -0.9414],
[ 2.7500, -1.2188, -1.6484, 3.1719],
[ 1.4531, -0.5625, -0.3379, 1.2812],
...,
[-0.5234, -2.0938, -1.4844, -2.0312],
[ 2.3281, 0.3223, -0.0166, 2.5469],
[-0.4023, 2.8281, 1.3906, 2.3281]], requires_grad=True)
2024-10-08 15:06:25,528 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7539, -1.1797, -1.0625, -0.9141],
[ 2.6406, -1.1328, -1.5781, 3.1094],
[ 1.3438, -0.5117, -0.3008, 1.2578],
...,
[-0.3770, -2.1250, -1.5078, -2.0000],
[ 2.2188, 0.3359, -0.0060, 2.4844],
[-0.6211, 2.9844, 1.5000, 2.3281]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7539, -1.1797, -1.0625, -0.9141],
[ 2.6406, -1.1328, -1.5781, 3.1094],
[ 1.3438, -0.5117, -0.3008, 1.2578],
...,
[-0.3770, -2.1250, -1.5078, -2.0000],
[ 2.2188, 0.3359, -0.0060, 2.4844],
[-0.6211, 2.9844, 1.5000, 2.3281]], requires_grad=True)
2024-10-08 15:06:25,689 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6602, -1.1719, -1.0547, -0.8945],
[ 2.5000, -1.0312, -1.4844, 3.0469],
[ 1.2344, -0.4590, -0.2617, 1.2344],
...,
[-0.2480, -2.1406, -1.5156, -1.9609],
[ 2.0938, 0.3652, 0.0168, 2.4219],
[-0.8281, 3.1250, 1.6016, 2.3125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6602, -1.1719, -1.0547, -0.8945],
[ 2.5000, -1.0312, -1.4844, 3.0469],
[ 1.2344, -0.4590, -0.2617, 1.2344],
...,
[-0.2480, -2.1406, -1.5156, -1.9609],
[ 2.0938, 0.3652, 0.0168, 2.4219],
[-0.8281, 3.1250, 1.6016, 2.3125]], requires_grad=True)
2024-10-08 15:06:25,935 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6211, -1.1250, -1.0078, -0.8555],
[ 2.4531, -1.0625, -1.4922, 2.9531],
[ 1.2031, -0.4707, -0.2695, 1.1953],
...,
[-0.2178, -2.0469, -1.4453, -1.8984],
[ 2.0625, 0.2676, -0.0500, 2.3281],
[-0.9453, 3.1406, 1.6250, 2.2812]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6211, -1.1250, -1.0078, -0.8555],
[ 2.4531, -1.0625, -1.4922, 2.9531],
[ 1.2031, -0.4707, -0.2695, 1.1953],
...,
[-0.2178, -2.0469, -1.4453, -1.8984],
[ 2.0625, 0.2676, -0.0500, 2.3281],
[-0.9453, 3.1406, 1.6250, 2.2812]], requires_grad=True)
2024-10-08 15:06:26,102 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5430, -1.1016, -0.9805, -0.8164],
[ 2.3750, -1.0469, -1.4609, 2.8594],
[ 1.1641, -0.4766, -0.2734, 1.1562],
...,
[-0.1631, -1.9766, -1.3906, -1.8438],
[ 1.9844, 0.2178, -0.0835, 2.2500],
[-1.0703, 3.1719, 1.6484, 2.2500]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5430, -1.1016, -0.9805, -0.8164],
[ 2.3750, -1.0469, -1.4609, 2.8594],
[ 1.1641, -0.4766, -0.2734, 1.1562],
...,
[-0.1631, -1.9766, -1.3906, -1.8438],
[ 1.9844, 0.2178, -0.0835, 2.2500],
[-1.0703, 3.1719, 1.6484, 2.2500]], requires_grad=True)
2024-10-08 15:06:26,261 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4824, -1.0703, -0.9492, -0.7812],
[ 2.2188, -0.9570, -1.3750, 2.7969],
[ 1.1016, -0.4648, -0.2656, 1.1250],
...,
[ 0.0126, -2.0156, -1.4297, -1.8125],
[ 1.7969, 0.2676, -0.0420, 2.2031],
[-1.3047, 3.3438, 1.7656, 2.2344]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4824, -1.0703, -0.9492, -0.7812],
[ 2.2188, -0.9570, -1.3750, 2.7969],
[ 1.1016, -0.4648, -0.2656, 1.1250],
...,
[ 0.0126, -2.0156, -1.4297, -1.8125],
[ 1.7969, 0.2676, -0.0420, 2.2031],
[-1.3047, 3.3438, 1.7656, 2.2344]], requires_grad=True)
2024-10-08 15:06:26,513 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4258, -1.0391, -0.9219, -0.7500],
[ 1.9844, -0.7617, -1.2031, 2.7500],
[ 0.9922, -0.4219, -0.2334, 1.1016],
...,
[ 0.2988, -2.1406, -1.5312, -1.7891],
[ 1.5000, 0.4121, 0.0654, 2.1719],
[-1.5938, 3.5938, 1.9297, 2.2500]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4258, -1.0391, -0.9219, -0.7500],
[ 1.9844, -0.7617, -1.2031, 2.7500],
[ 0.9922, -0.4219, -0.2334, 1.1016],
...,
[ 0.2988, -2.1406, -1.5312, -1.7891],
[ 1.5000, 0.4121, 0.0654, 2.1719],
[-1.5938, 3.5938, 1.9297, 2.2500]], requires_grad=True)
2024-10-08 15:06:26,774 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4785, -0.9414, -0.8516, -0.7070],
[ 1.9062, -0.7305, -1.1484, 2.7031],
[ 1.0000, -0.4414, -0.2422, 1.0781],
...,
[ 0.4023, -2.1406, -1.5391, -1.7578],
[ 1.3906, 0.4316, 0.0908, 2.1250],
[-1.7500, 3.7188, 2.0312, 2.2500]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.4785, -0.9414, -0.8516, -0.7070],
[ 1.9062, -0.7305, -1.1484, 2.7031],
[ 1.0000, -0.4414, -0.2422, 1.0781],
...,
[ 0.4023, -2.1406, -1.5391, -1.7578],
[ 1.3906, 0.4316, 0.0908, 2.1250],
[-1.7500, 3.7188, 2.0312, 2.2500]], requires_grad=True)
2024-10-08 15:06:27,045 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5703, -0.8164, -0.7578, -0.6602],
[ 1.8750, -0.7500, -1.1484, 2.6406],
[ 1.0078, -0.4570, -0.2520, 1.0547],
...,
[ 0.4551, -2.0781, -1.5000, -1.7109],
[ 1.2969, 0.4355, 0.1060, 2.0781],
[-1.8359, 3.7500, 2.0625, 2.2344]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5703, -0.8164, -0.7578, -0.6602],
[ 1.8750, -0.7500, -1.1484, 2.6406],
[ 1.0078, -0.4570, -0.2520, 1.0547],
...,
[ 0.4551, -2.0781, -1.5000, -1.7109],
[ 1.2969, 0.4355, 0.1060, 2.0781],
[-1.8359, 3.7500, 2.0625, 2.2344]], requires_grad=True)
2024-10-08 15:06:27,199 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6680, -0.6797, -0.6562, -0.6094],
[ 1.8516, -0.7930, -1.1641, 2.5781],
[ 0.9961, -0.4609, -0.2520, 1.0312],
...,
[ 0.5586, -2.1094, -1.5391, -1.6875],
[ 1.1875, 0.4746, 0.1455, 2.0312],
[-1.9453, 3.8438, 2.1406, 2.2344]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6680, -0.6797, -0.6562, -0.6094],
[ 1.8516, -0.7930, -1.1641, 2.5781],
[ 0.9961, -0.4609, -0.2520, 1.0312],
...,
[ 0.5586, -2.1094, -1.5391, -1.6875],
[ 1.1875, 0.4746, 0.1455, 2.0312],
[-1.9453, 3.8438, 2.1406, 2.2344]], requires_grad=True)
2024-10-08 15:06:27,467 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7266, -0.5195, -0.5352, -0.5312],
[ 1.7422, -0.6797, -1.0547, 2.5312],
[ 0.9453, -0.4121, -0.2129, 1.0156],
...,
[ 0.6953, -2.2031, -1.6250, -1.6797],
[ 1.0547, 0.5859, 0.2373, 2.0156],
[-2.0469, 3.9531, 2.2188, 2.2344]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7266, -0.5195, -0.5352, -0.5312],
[ 1.7422, -0.6797, -1.0547, 2.5312],
[ 0.9453, -0.4121, -0.2129, 1.0156],
...,
[ 0.6953, -2.2031, -1.6250, -1.6797],
[ 1.0547, 0.5859, 0.2373, 2.0156],
[-2.0469, 3.9531, 2.2188, 2.2344]], requires_grad=True)
2024-10-08 15:06:27,626 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6914, -0.4395, -0.4668, -0.4648],
[ 1.7812, -0.7148, -1.0391, 2.5000],
[ 1.0547, -0.4941, -0.2617, 0.9922],
...,
[ 0.4844, -1.9609, -1.4766, -1.6641],
[ 1.0625, 0.5312, 0.2178, 1.9844],
[-1.7969, 3.6719, 2.0938, 2.2500]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6914, -0.4395, -0.4668, -0.4648],
[ 1.7812, -0.7148, -1.0391, 2.5000],
[ 1.0547, -0.4941, -0.2617, 0.9922],
...,
[ 0.4844, -1.9609, -1.4766, -1.6641],
[ 1.0625, 0.5312, 0.2178, 1.9844],
[-1.7969, 3.6719, 2.0938, 2.2500]], requires_grad=True)
2024-10-08 15:06:27,895 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7227, -0.3184, -0.3770, -0.4004],
[ 1.8984, -0.8828, -1.1172, 2.4375],
[ 1.1484, -0.5586, -0.3008, 0.9727],
...,
[ 0.2793, -1.7500, -1.3516, -1.6562],
[ 1.0859, 0.4785, 0.2002, 1.9531],
[-1.5547, 3.4375, 1.9922, 2.2812]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7227, -0.3184, -0.3770, -0.4004],
[ 1.8984, -0.8828, -1.1172, 2.4375],
[ 1.1484, -0.5586, -0.3008, 0.9727],
...,
[ 0.2793, -1.7500, -1.3516, -1.6562],
[ 1.0859, 0.4785, 0.2002, 1.9531],
[-1.5547, 3.4375, 1.9922, 2.2812]], requires_grad=True)
2024-10-08 15:06:28,159 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7266, -0.2090, -0.2930, -0.3359],
[ 2.0312, -1.0391, -1.1953, 2.3906],
[ 1.2031, -0.5977, -0.3223, 0.9570],
...,
[ 0.2158, -1.7422, -1.3516, -1.6641],
[ 1.0078, 0.5742, 0.2656, 1.9375],
[-1.3594, 3.2500, 1.9141, 2.3125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7266, -0.2090, -0.2930, -0.3359],
[ 2.0312, -1.0391, -1.1953, 2.3906],
[ 1.2031, -0.5977, -0.3223, 0.9570],
...,
[ 0.2158, -1.7422, -1.3516, -1.6641],
[ 1.0078, 0.5742, 0.2656, 1.9375],
[-1.3594, 3.2500, 1.9141, 2.3125]], requires_grad=True)
2024-10-08 15:06:28,420 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7109, -0.1338, -0.2305, -0.2773],
[ 2.1250, -1.1562, -1.2422, 2.3438],
[ 1.2266, -0.6094, -0.3320, 0.9375],
...,
[ 0.1875, -1.7656, -1.3672, -1.6641],
[ 0.9180, 0.6836, 0.3359, 1.9219],
[-1.2031, 3.1250, 1.8594, 2.3281]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7109, -0.1338, -0.2305, -0.2773],
[ 2.1250, -1.1562, -1.2422, 2.3438],
[ 1.2266, -0.6094, -0.3320, 0.9375],
...,
[ 0.1875, -1.7656, -1.3672, -1.6641],
[ 0.9180, 0.6836, 0.3359, 1.9219],
[-1.2031, 3.1250, 1.8594, 2.3281]], requires_grad=True)
2024-10-08 15:06:28,691 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7188, -0.0322, -0.1602, -0.2246],
[ 2.1875, -1.2578, -1.2812, 2.2969],
[ 1.2734, -0.6602, -0.3574, 0.9180],
...,
[ 0.1084, -1.7109, -1.3438, -1.6641],
[ 0.8633, 0.7344, 0.3789, 1.9062],
[-1.0234, 2.9375, 1.7812, 2.3438]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7188, -0.0322, -0.1602, -0.2246],
[ 2.1875, -1.2578, -1.2812, 2.2969],
[ 1.2734, -0.6602, -0.3574, 0.9180],
...,
[ 0.1084, -1.7109, -1.3438, -1.6641],
[ 0.8633, 0.7344, 0.3789, 1.9062],
[-1.0234, 2.9375, 1.7812, 2.3438]], requires_grad=True)
2024-10-08 15:06:28,941 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7500, 0.1553, -0.0620, -0.1689],
[ 2.2656, -1.5078, -1.3828, 2.2344],
[ 1.3281, -0.7617, -0.4023, 0.8906],
...,
[ 0.0039, -1.5312, -1.2734, -1.6562],
[ 0.8359, 0.6445, 0.3652, 1.8750],
[-0.8398, 2.6562, 1.6719, 2.3438]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7500, 0.1553, -0.0620, -0.1689],
[ 2.2656, -1.5078, -1.3828, 2.2344],
[ 1.3281, -0.7617, -0.4023, 0.8906],
...,
[ 0.0039, -1.5312, -1.2734, -1.6562],
[ 0.8359, 0.6445, 0.3652, 1.8750],
[-0.8398, 2.6562, 1.6719, 2.3438]], requires_grad=True)
2024-10-08 15:06:29,198 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7852, 0.3164, 0.0228, -0.1230],
[ 2.2969, -1.6562, -1.4453, 2.1719],
[ 1.3203, -0.7852, -0.4180, 0.8594],
...,
[-0.0500, -1.4375, -1.2266, -1.6406],
[ 0.7539, 0.6719, 0.3887, 1.8359],
[-0.7227, 2.5000, 1.6016, 2.3281]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7852, 0.3164, 0.0228, -0.1230],
[ 2.2969, -1.6562, -1.4453, 2.1719],
[ 1.3203, -0.7852, -0.4180, 0.8594],
...,
[-0.0500, -1.4375, -1.2266, -1.6406],
[ 0.7539, 0.6719, 0.3887, 1.8359],
[-0.7227, 2.5000, 1.6016, 2.3281]], requires_grad=True)
2024-10-08 15:06:29,456 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7227, 0.4043, 0.0825, -0.0613],
[ 2.2188, -1.5156, -1.3828, 2.1094],
[ 1.2656, -0.7109, -0.3945, 0.8359],
...,
[ 0.0143, -1.5391, -1.2578, -1.6172],
[ 0.5781, 0.8711, 0.4727, 1.7891],
[-0.6914, 2.5312, 1.5938, 2.3125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7227, 0.4043, 0.0825, -0.0613],
[ 2.2188, -1.5156, -1.3828, 2.1094],
[ 1.2656, -0.7109, -0.3945, 0.8359],
...,
[ 0.0143, -1.5391, -1.2578, -1.6172],
[ 0.5781, 0.8711, 0.4727, 1.7891],
[-0.6914, 2.5312, 1.5938, 2.3125]], requires_grad=True)
2024-10-08 15:06:29,720 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6562, 0.4707, 0.1299, -0.0056],
[ 2.1406, -1.3516, -1.3125, 2.0469],
[ 1.2109, -0.6562, -0.3770, 0.8125],
...,
[ 0.0723, -1.5938, -1.2656, -1.5859],
[ 0.4219, 1.0156, 0.5352, 1.7344],
[-0.6680, 2.5156, 1.5703, 2.2812]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6562, 0.4707, 0.1299, -0.0056],
[ 2.1406, -1.3516, -1.3125, 2.0469],
[ 1.2109, -0.6562, -0.3770, 0.8125],
...,
[ 0.0723, -1.5938, -1.2656, -1.5859],
[ 0.4219, 1.0156, 0.5352, 1.7344],
[-0.6680, 2.5156, 1.5703, 2.2812]], requires_grad=True)
2024-10-08 15:06:29,978 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6211, 0.6250, 0.2168, 0.0601],
[ 2.0781, -1.3750, -1.3359, 1.9688],
[ 1.1641, -0.7148, -0.4160, 0.7656],
...,
[ 0.0408, -1.3750, -1.1328, -1.5312],
[ 0.3457, 1.0078, 0.5273, 1.6797],
[-0.6172, 2.2344, 1.4219, 2.2031]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6211, 0.6250, 0.2168, 0.0601],
[ 2.0781, -1.3750, -1.3359, 1.9688],
[ 1.1641, -0.7148, -0.4160, 0.7656],
...,
[ 0.0408, -1.3750, -1.1328, -1.5312],
[ 0.3457, 1.0078, 0.5273, 1.6797],
[-0.6172, 2.2344, 1.4219, 2.2031]], requires_grad=True)
2024-10-08 15:06:30,238 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6836, 0.8555, 0.3398, 0.1270],
[ 2.0312, -1.3828, -1.3516, 1.8906],
[ 1.1953, -0.8359, -0.4883, 0.7148],
...,
[-0.1504, -0.9727, -0.9023, -1.4688],
[ 0.4043, 0.8359, 0.4355, 1.6250],
[-0.5547, 1.9297, 1.2656, 2.1250]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6836, 0.8555, 0.3398, 0.1270],
[ 2.0312, -1.3828, -1.3516, 1.8906],
[ 1.1953, -0.8359, -0.4883, 0.7148],
...,
[-0.1504, -0.9727, -0.9023, -1.4688],
[ 0.4043, 0.8359, 0.4355, 1.6250],
[-0.5547, 1.9297, 1.2656, 2.1250]], requires_grad=True)
2024-10-08 15:06:30,494 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7422, 0.9648, 0.3926, 0.1260],
[ 1.9141, -1.2344, -1.2578, 1.8594],
[ 1.1328, -0.8438, -0.4902, 0.6992],
...,
[-0.0771, -0.8867, -0.8594, -1.4453],
[ 0.2295, 0.9102, 0.4785, 1.5938],
[-0.6367, 1.8906, 1.2422, 2.0781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7422, 0.9648, 0.3926, 0.1260],
[ 1.9141, -1.2344, -1.2578, 1.8594],
[ 1.1328, -0.8438, -0.4902, 0.6992],
...,
[-0.0771, -0.8867, -0.8594, -1.4453],
[ 0.2295, 0.9102, 0.4785, 1.5938],
[-0.6367, 1.8906, 1.2422, 2.0781]], requires_grad=True)
2024-10-08 15:06:30,760 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7500, 0.9492, 0.3652, 0.0469],
[ 1.8281, -1.0703, -1.1484, 1.8516],
[ 1.0703, -0.8320, -0.4785, 0.6914],
...,
[ 0.0583, -0.8789, -0.8633, -1.4297],
[-0.0092, 1.1094, 0.6016, 1.6172],
[-0.7188, 2.0156, 1.3125, 2.1250]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7500, 0.9492, 0.3652, 0.0469],
[ 1.8281, -1.0703, -1.1484, 1.8516],
[ 1.0703, -0.8320, -0.4785, 0.6914],
...,
[ 0.0583, -0.8789, -0.8633, -1.4297],
[-0.0092, 1.1094, 0.6016, 1.6172],
[-0.7188, 2.0156, 1.3125, 2.1250]], requires_grad=True)
2024-10-08 15:06:31,013 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7148, 0.9102, 0.3262, -0.0264],
[ 1.6484, -0.8438, -0.9961, 1.8438],
[ 0.9844, -0.8008, -0.4551, 0.6875],
...,
[ 0.2559, -0.9375, -0.9141, -1.4375],
[-0.2217, 1.2969, 0.7148, 1.6328],
[-0.7852, 2.0938, 1.3672, 2.1562]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7148, 0.9102, 0.3262, -0.0264],
[ 1.6484, -0.8438, -0.9961, 1.8438],
[ 0.9844, -0.8008, -0.4551, 0.6875],
...,
[ 0.2559, -0.9375, -0.9141, -1.4375],
[-0.2217, 1.2969, 0.7148, 1.6328],
[-0.7852, 2.0938, 1.3672, 2.1562]], requires_grad=True)
2024-10-08 15:06:31,271 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6836, 0.8828, 0.3008, -0.0742],
[ 1.9375, -0.9531, -1.0781, 1.7891],
[ 1.0312, -0.8320, -0.4766, 0.6602],
...,
[ 0.2773, -0.8945, -0.8906, -1.4062],
[-0.2266, 1.3438, 0.7422, 1.6172],
[-0.6328, 1.9844, 1.3047, 2.1250]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6836, 0.8828, 0.3008, -0.0742],
[ 1.9375, -0.9531, -1.0781, 1.7891],
[ 1.0312, -0.8320, -0.4766, 0.6602],
...,
[ 0.2773, -0.8945, -0.8906, -1.4062],
[-0.2266, 1.3438, 0.7422, 1.6172],
[-0.6328, 1.9844, 1.3047, 2.1250]], requires_grad=True)
2024-10-08 15:06:31,522 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7188, 0.8789, 0.2910, -0.1118],
[ 2.3438, -1.1406, -1.2109, 1.7188],
[ 1.2891, -0.9375, -0.5469, 0.6172],
...,
[ 0.0510, -0.7305, -0.7773, -1.3672],
[ 0.0442, 1.2500, 0.6797, 1.5859],
[-0.4160, 1.8281, 1.2109, 2.0781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7188, 0.8789, 0.2910, -0.1118],
[ 2.3438, -1.1406, -1.2109, 1.7188],
[ 1.2891, -0.9375, -0.5469, 0.6172],
...,
[ 0.0510, -0.7305, -0.7773, -1.3672],
[ 0.0442, 1.2500, 0.6797, 1.5859],
[-0.4160, 1.8281, 1.2109, 2.0781]], requires_grad=True)
2024-10-08 15:06:31,768 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5156, 0.8008, 0.2441, -0.1494],
[ 2.3906, -1.1172, -1.2109, 1.6719],
[ 1.3594, -0.9688, -0.5703, 0.5898],
...,
[ 0.2109, -0.7734, -0.7969, -1.3594],
[ 0.0630, 1.2734, 0.6914, 1.5703],
[-0.5586, 1.9062, 1.2344, 2.0625]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5156, 0.8008, 0.2441, -0.1494],
[ 2.3906, -1.1172, -1.2109, 1.6719],
[ 1.3594, -0.9688, -0.5703, 0.5898],
...,
[ 0.2109, -0.7734, -0.7969, -1.3594],
[ 0.0630, 1.2734, 0.6914, 1.5703],
[-0.5586, 1.9062, 1.2344, 2.0625]], requires_grad=True)
2024-10-08 15:06:32,028 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1396, 0.6289, 0.1436, -0.2188],
[ 2.1562, -0.8477, -1.0469, 1.6953],
[ 1.2734, -0.9219, -0.5469, 0.5820],
...,
[ 0.5352, -0.9297, -0.8906, -1.3750],
[-0.1416, 1.4219, 0.7734, 1.5703],
[-0.7500, 2.0781, 1.3125, 2.0938]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1396, 0.6289, 0.1436, -0.2188],
[ 2.1562, -0.8477, -1.0469, 1.6953],
[ 1.2734, -0.9219, -0.5469, 0.5820],
...,
[ 0.5352, -0.9297, -0.8906, -1.3750],
[-0.1416, 1.4219, 0.7734, 1.5703],
[-0.7500, 2.0781, 1.3125, 2.0938]], requires_grad=True)
2024-10-08 15:06:32,300 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1201, 0.5234, 0.0835, -0.2676],
[ 1.9844, -0.6562, -0.9375, 1.6875],
[ 1.2422, -0.9062, -0.5430, 0.5742],
...,
[ 0.6758, -0.9688, -0.9062, -1.3828],
[-0.2363, 1.4922, 0.8047, 1.5625],
[-0.8242, 2.1250, 1.3359, 2.1094]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1201, 0.5234, 0.0835, -0.2676],
[ 1.9844, -0.6562, -0.9375, 1.6875],
[ 1.2422, -0.9062, -0.5430, 0.5742],
...,
[ 0.6758, -0.9688, -0.9062, -1.3828],
[-0.2363, 1.4922, 0.8047, 1.5625],
[-0.8242, 2.1250, 1.3359, 2.1094]], requires_grad=True)
2024-10-08 15:06:32,568 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2305, 0.4863, 0.0630, -0.3262],
[ 2.0312, -0.7148, -0.9922, 1.6953],
[ 1.3203, -0.9531, -0.5820, 0.5742],
...,
[ 0.6523, -0.8789, -0.8320, -1.3984],
[-0.2178, 1.4688, 0.7852, 1.5625],
[-0.8438, 2.1094, 1.3203, 2.1250]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2305, 0.4863, 0.0630, -0.3262],
[ 2.0312, -0.7148, -0.9922, 1.6953],
[ 1.3203, -0.9531, -0.5820, 0.5742],
...,
[ 0.6523, -0.8789, -0.8320, -1.3984],
[-0.2178, 1.4688, 0.7852, 1.5625],
[-0.8438, 2.1094, 1.3203, 2.1250]], requires_grad=True)
2024-10-08 15:06:32,825 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.3340, 0.4883, 0.0688, -0.3555],
[ 2.0625, -0.7344, -1.0078, 1.6875],
[ 1.3750, -0.9766, -0.6016, 0.5703],
...,
[ 0.6445, -0.8086, -0.7773, -1.3984],
[-0.2168, 1.4766, 0.7852, 1.5625],
[-0.8633, 2.0625, 1.2891, 2.1094]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.3340, 0.4883, 0.0688, -0.3555],
[ 2.0625, -0.7344, -1.0078, 1.6875],
[ 1.3750, -0.9766, -0.6016, 0.5703],
...,
[ 0.6445, -0.8086, -0.7773, -1.3984],
[-0.2168, 1.4766, 0.7852, 1.5625],
[-0.8633, 2.0625, 1.2891, 2.1094]], requires_grad=True)
2024-10-08 15:06:32,964 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.4316, 0.4727, 0.0654, -0.3809],
[ 2.0625, -0.6992, -0.9922, 1.6797],
[ 1.4062, -0.9805, -0.6055, 0.5625],
...,
[ 0.6641, -0.7656, -0.7383, -1.3828],
[-0.2422, 1.5156, 0.8047, 1.5469],
[-0.9023, 2.0625, 1.2734, 2.0781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.4316, 0.4727, 0.0654, -0.3809],
[ 2.0625, -0.6992, -0.9922, 1.6797],
[ 1.4062, -0.9805, -0.6055, 0.5625],
...,
[ 0.6641, -0.7656, -0.7383, -1.3828],
[-0.2422, 1.5156, 0.8047, 1.5469],
[-0.9023, 2.0625, 1.2734, 2.0781]], requires_grad=True)
2024-10-08 15:06:33,228 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.5117, 0.4473, 0.0559, -0.4023],
[ 2.0469, -0.7070, -0.9961, 1.6641],
[ 1.4297, -1.0000, -0.6211, 0.5547],
...,
[ 0.6875, -0.6914, -0.6797, -1.3594],
[-0.2715, 1.5312, 0.8125, 1.5234],
[-0.9375, 2.0312, 1.2500, 2.0469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.5117, 0.4473, 0.0559, -0.4023],
[ 2.0469, -0.7070, -0.9961, 1.6641],
[ 1.4297, -1.0000, -0.6211, 0.5547],
...,
[ 0.6875, -0.6914, -0.6797, -1.3594],
[-0.2715, 1.5312, 0.8125, 1.5234],
[-0.9375, 2.0312, 1.2500, 2.0469]], requires_grad=True)
2024-10-08 15:06:33,495 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.5820, 0.4258, 0.0496, -0.4180],
[ 2.0156, -0.7070, -0.9961, 1.6406],
[ 1.4453, -1.0078, -0.6289, 0.5430],
...,
[ 0.7109, -0.6445, -0.6406, -1.3281],
[-0.3027, 1.5547, 0.8242, 1.4844],
[-0.9688, 2.0000, 1.2266, 2.0156]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.5820, 0.4258, 0.0496, -0.4180],
[ 2.0156, -0.7070, -0.9961, 1.6406],
[ 1.4453, -1.0078, -0.6289, 0.5430],
...,
[ 0.7109, -0.6445, -0.6406, -1.3281],
[-0.3027, 1.5547, 0.8242, 1.4844],
[-0.9688, 2.0000, 1.2266, 2.0156]], requires_grad=True)
2024-10-08 15:06:33,659 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.6562, 0.4453, 0.0654, -0.4492],
[ 1.9688, -0.7578, -1.0312, 1.6250],
[ 1.4375, -1.0469, -0.6523, 0.5430],
...,
[ 0.7422, -0.5664, -0.5781, -1.3047],
[-0.3340, 1.5391, 0.8125, 1.4609],
[-1.0078, 1.8828, 1.1562, 2.0000]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.6562, 0.4453, 0.0654, -0.4492],
[ 1.9688, -0.7578, -1.0312, 1.6250],
[ 1.4375, -1.0469, -0.6523, 0.5430],
...,
[ 0.7422, -0.5664, -0.5781, -1.3047],
[-0.3340, 1.5391, 0.8125, 1.4609],
[-1.0078, 1.8828, 1.1562, 2.0000]], requires_grad=True)
2024-10-08 15:06:33,919 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.7148, 0.4258, 0.0579, -0.4570],
[ 1.9844, -0.6719, -0.9688, 1.5938],
[ 1.4453, -1.0547, -0.6562, 0.5352],
...,
[ 0.7617, -0.5664, -0.5703, -1.2500],
[-0.3359, 1.6016, 0.8516, 1.4141],
[-1.0234, 1.8203, 1.1172, 1.9766]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.7148, 0.4258, 0.0579, -0.4570],
[ 1.9844, -0.6719, -0.9688, 1.5938],
[ 1.4453, -1.0547, -0.6562, 0.5352],
...,
[ 0.7617, -0.5664, -0.5703, -1.2500],
[-0.3359, 1.6016, 0.8516, 1.4141],
[-1.0234, 1.8203, 1.1172, 1.9766]], requires_grad=True)
2024-10-08 15:06:34,173 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.7969, 0.4336, 0.0654, -0.4727],
[ 1.9688, -0.6406, -0.9375, 1.5781],
[ 1.4219, -1.0703, -0.6680, 0.5312],
...,
[ 0.8047, -0.5234, -0.5391, -1.2109],
[-0.3633, 1.6172, 0.8633, 1.3828],
[-1.0625, 1.6953, 1.0547, 1.9688]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.7969, 0.4336, 0.0654, -0.4727],
[ 1.9688, -0.6406, -0.9375, 1.5781],
[ 1.4219, -1.0703, -0.6680, 0.5312],
...,
[ 0.8047, -0.5234, -0.5391, -1.2109],
[-0.3633, 1.6172, 0.8633, 1.3828],
[-1.0625, 1.6953, 1.0547, 1.9688]], requires_grad=True)
2024-10-08 15:06:34,430 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.8281, 0.4141, 0.0588, -0.4785],
[ 1.9609, -0.5820, -0.8906, 1.5469],
[ 1.4141, -1.0703, -0.6680, 0.5195],
...,
[ 0.8281, -0.5078, -0.5234, -1.1641],
[-0.3887, 1.6328, 0.8711, 1.3438],
[-1.0859, 1.6094, 1.0078, 1.9453]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.8281, 0.4141, 0.0588, -0.4785],
[ 1.9609, -0.5820, -0.8906, 1.5469],
[ 1.4141, -1.0703, -0.6680, 0.5195],
...,
[ 0.8281, -0.5078, -0.5234, -1.1641],
[-0.3887, 1.6328, 0.8711, 1.3438],
[-1.0859, 1.6094, 1.0078, 1.9453]], requires_grad=True)
2024-10-08 15:06:34,696 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.8398, 0.3809, 0.0449, -0.4766],
[ 1.9375, -0.5391, -0.8516, 1.5078],
[ 1.3984, -1.0625, -0.6641, 0.5039],
...,
[ 0.8594, -0.4922, -0.5039, -1.1172],
[-0.4219, 1.6406, 0.8750, 1.3047],
[-1.1094, 1.5391, 0.9609, 1.9219]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.8398, 0.3809, 0.0449, -0.4766],
[ 1.9375, -0.5391, -0.8516, 1.5078],
[ 1.3984, -1.0625, -0.6641, 0.5039],
...,
[ 0.8594, -0.4922, -0.5039, -1.1172],
[-0.4219, 1.6406, 0.8750, 1.3047],
[-1.1094, 1.5391, 0.9609, 1.9219]], requires_grad=True)
2024-10-08 15:06:34,961 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.9219, 0.4434, 0.0796, -0.4941],
[ 1.8672, -0.5820, -0.8594, 1.4766],
[ 1.3594, -1.0781, -0.6758, 0.4922],
...,
[ 0.9141, -0.4199, -0.4531, -1.0781],
[-0.4844, 1.5781, 0.8438, 1.2734],
[-1.1562, 1.3750, 0.8789, 1.9141]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.9219, 0.4434, 0.0796, -0.4941],
[ 1.8672, -0.5820, -0.8594, 1.4766],
[ 1.3594, -1.0781, -0.6758, 0.4922],
...,
[ 0.9141, -0.4199, -0.4531, -1.0781],
[-0.4844, 1.5781, 0.8438, 1.2734],
[-1.1562, 1.3750, 0.8789, 1.9141]], requires_grad=True)
2024-10-08 15:06:35,218 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0078, 0.5117, 0.1196, -0.5000],
[ 1.7969, -0.5742, -0.8398, 1.4375],
[ 1.3203, -1.0781, -0.6758, 0.4785],
...,
[ 0.9766, -0.4219, -0.4473, -1.0312],
[-0.5625, 1.5938, 0.8594, 1.2266],
[-1.2188, 1.3047, 0.8398, 1.8828]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0078, 0.5117, 0.1196, -0.5000],
[ 1.7969, -0.5742, -0.8398, 1.4375],
[ 1.3203, -1.0781, -0.6758, 0.4785],
...,
[ 0.9766, -0.4219, -0.4473, -1.0312],
[-0.5625, 1.5938, 0.8594, 1.2266],
[-1.2188, 1.3047, 0.8398, 1.8828]], requires_grad=True)
2024-10-08 15:06:35,368 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0781, 0.5742, 0.1562, -0.5039],
[ 1.7188, -0.5586, -0.8164, 1.3906],
[ 1.2812, -1.0781, -0.6758, 0.4648],
...,
[ 1.0469, -0.4707, -0.4707, -0.9727],
[-0.6445, 1.6406, 0.8828, 1.1641],
[-1.2734, 1.2578, 0.8125, 1.8438]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0781, 0.5742, 0.1562, -0.5039],
[ 1.7188, -0.5586, -0.8164, 1.3906],
[ 1.2812, -1.0781, -0.6758, 0.4648],
...,
[ 1.0469, -0.4707, -0.4707, -0.9727],
[-0.6445, 1.6406, 0.8828, 1.1641],
[-1.2734, 1.2578, 0.8125, 1.8438]], requires_grad=True)
2024-10-08 15:06:35,624 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.1406, 0.6211, 0.1826, -0.5039],
[ 1.6406, -0.5547, -0.8047, 1.3516],
[ 1.2422, -1.0703, -0.6680, 0.4492],
...,
[ 1.1094, -0.5508, -0.5117, -0.9141],
[-0.7148, 1.7031, 0.9180, 1.1094],
[-1.3203, 1.2031, 0.7812, 1.7969]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.1406, 0.6211, 0.1826, -0.5039],
[ 1.6406, -0.5547, -0.8047, 1.3516],
[ 1.2422, -1.0703, -0.6680, 0.4492],
...,
[ 1.1094, -0.5508, -0.5117, -0.9141],
[-0.7148, 1.7031, 0.9180, 1.1094],
[-1.3203, 1.2031, 0.7812, 1.7969]], requires_grad=True)
2024-10-08 15:06:35,881 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.1953, 0.6719, 0.2139, -0.5078],
[ 1.5312, -0.6328, -0.8477, 1.3125],
[ 1.1641, -1.1094, -0.6953, 0.4395],
...,
[ 1.2266, -0.4570, -0.4414, -0.8711],
[-0.8164, 1.6328, 0.8789, 1.0703],
[-1.3906, 0.9609, 0.6523, 1.7891]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.1953, 0.6719, 0.2139, -0.5078],
[ 1.5312, -0.6328, -0.8477, 1.3125],
[ 1.1641, -1.1094, -0.6953, 0.4395],
...,
[ 1.2266, -0.4570, -0.4414, -0.8711],
[-0.8164, 1.6328, 0.8789, 1.0703],
[-1.3906, 0.9609, 0.6523, 1.7891]], requires_grad=True)
2024-10-08 15:06:36,140 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.2031, 0.7852, 0.2793, -0.5273],
[ 1.4375, -0.6758, -0.8594, 1.2734],
[ 1.0938, -1.1328, -0.7109, 0.4258],
...,
[ 1.3047, -0.3848, -0.3867, -0.8359],
[-0.8945, 1.5859, 0.8516, 1.0312],
[-1.4375, 0.7578, 0.5430, 1.7734]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.2031, 0.7852, 0.2793, -0.5273],
[ 1.4375, -0.6758, -0.8594, 1.2734],
[ 1.0938, -1.1328, -0.7109, 0.4258],
...,
[ 1.3047, -0.3848, -0.3867, -0.8359],
[-0.8945, 1.5859, 0.8516, 1.0312],
[-1.4375, 0.7578, 0.5430, 1.7734]], requires_grad=True)
2024-10-08 15:06:36,300 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0859, 0.7617, 0.2559, -0.5938],
[ 1.5234, -0.3203, -0.5664, 1.3203],
[ 1.1016, -1.1250, -0.6992, 0.4395],
...,
[ 1.2344, -0.3887, -0.4004, -0.8633],
[-0.8984, 1.5078, 0.8086, 1.0234],
[-1.4062, 0.6250, 0.4824, 1.7891]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0859, 0.7617, 0.2559, -0.5938],
[ 1.5234, -0.3203, -0.5664, 1.3203],
[ 1.1016, -1.1250, -0.6992, 0.4395],
...,
[ 1.2344, -0.3887, -0.4004, -0.8633],
[-0.8984, 1.5078, 0.8086, 1.0234],
[-1.4062, 0.6250, 0.4824, 1.7891]], requires_grad=True)
2024-10-08 15:06:36,445 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0703, 0.6680, 0.1895, -0.6250],
[ 1.3828, 0.4668, 0.0249, 1.3203],
[ 0.9766, -0.9453, -0.5742, 0.4316],
...,
[ 1.2422, -0.5742, -0.5430, -0.8750],
[-1.0312, 1.6797, 0.9297, 0.9922],
[-1.4453, 0.6250, 0.4941, 1.7812]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0703, 0.6680, 0.1895, -0.6250],
[ 1.3828, 0.4668, 0.0249, 1.3203],
[ 0.9766, -0.9453, -0.5742, 0.4316],
...,
[ 1.2422, -0.5742, -0.5430, -0.8750],
[-1.0312, 1.6797, 0.9297, 0.9922],
[-1.4453, 0.6250, 0.4941, 1.7812]], requires_grad=True)
2024-10-08 15:06:36,697 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0859, 0.5664, 0.1226, -0.6445],
[ 1.3047, 1.1016, 0.5078, 1.3203],
[ 0.8633, -0.7852, -0.4648, 0.4219],
...,
[ 1.1562, -0.6289, -0.5938, -0.8945],
[-1.0938, 1.7656, 0.9961, 0.9688],
[-1.4375, 0.5586, 0.4629, 1.7656]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 1.0859, 0.5664, 0.1226, -0.6445],
[ 1.3047, 1.1016, 0.5078, 1.3203],
[ 0.8633, -0.7852, -0.4648, 0.4219],
...,
[ 1.1562, -0.6289, -0.5938, -0.8945],
[-1.0938, 1.7656, 0.9961, 0.9688],
[-1.4375, 0.5586, 0.4629, 1.7656]], requires_grad=True)
2024-10-08 15:06:36,951 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.7617, 0.7109, 0.1973, -0.6953],
[ 1.5391, 1.2812, 0.6836, 1.3594],
[ 0.8438, -0.7227, -0.4180, 0.4141],
...,
[ 0.9297, -0.4883, -0.5117, -0.9180],
[-1.0234, 1.6953, 0.9648, 0.9531],
[-1.4141, 0.4414, 0.4023, 1.7422]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.7617, 0.7109, 0.1973, -0.6953],
[ 1.5391, 1.2812, 0.6836, 1.3594],
[ 0.8438, -0.7227, -0.4180, 0.4141],
...,
[ 0.9297, -0.4883, -0.5117, -0.9180],
[-1.0234, 1.6953, 0.9648, 0.9531],
[-1.4141, 0.4414, 0.4023, 1.7422]], requires_grad=True)
2024-10-08 15:06:37,215 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.4746, 0.8242, 0.2539, -0.7461],
[ 1.8047, 1.3516, 0.7891, 1.3906],
[ 0.8398, -0.6719, -0.3828, 0.4043],
...,
[ 0.7305, -0.3594, -0.4355, -0.9336],
[-0.9141, 1.5703, 0.9062, 0.9336],
[-1.3750, 0.3301, 0.3457, 1.7188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.4746, 0.8242, 0.2539, -0.7461],
[ 1.8047, 1.3516, 0.7891, 1.3906],
[ 0.8398, -0.6719, -0.3828, 0.4043],
...,
[ 0.7305, -0.3594, -0.4355, -0.9336],
[-0.9141, 1.5703, 0.9062, 0.9336],
[-1.3750, 0.3301, 0.3457, 1.7188]], requires_grad=True)
2024-10-08 15:06:37,367 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1289, 0.7617, 0.2070, -0.9180],
[ 2.0469, 1.4609, 0.9141, 1.4453],
[ 0.8398, -0.6016, -0.3320, 0.4102],
...,
[ 0.5195, -0.3887, -0.4648, -1.0234],
[-0.7812, 1.5391, 0.9023, 0.9688],
[-1.3203, 0.3555, 0.3652, 1.7578]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1289, 0.7617, 0.2070, -0.9180],
[ 2.0469, 1.4609, 0.9141, 1.4453],
[ 0.8398, -0.6016, -0.3320, 0.4102],
...,
[ 0.5195, -0.3887, -0.4648, -1.0234],
[-0.7812, 1.5391, 0.9023, 0.9688],
[-1.3203, 0.3555, 0.3652, 1.7578]], requires_grad=True)
2024-10-08 15:06:37,522 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1328, 0.6562, 0.1416, -1.0781],
[ 2.2656, 1.5234, 1.0000, 1.4766],
[ 0.8750, -0.5625, -0.2988, 0.4160],
...,
[ 0.2305, -0.3145, -0.4375, -1.0938],
[-0.5977, 1.4453, 0.8633, 0.9961],
[-1.2109, 0.3066, 0.3496, 1.7891]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1328, 0.6562, 0.1416, -1.0781],
[ 2.2656, 1.5234, 1.0000, 1.4766],
[ 0.8750, -0.5625, -0.2988, 0.4160],
...,
[ 0.2305, -0.3145, -0.4375, -1.0938],
[-0.5977, 1.4453, 0.8633, 0.9961],
[-1.2109, 0.3066, 0.3496, 1.7891]], requires_grad=True)
2024-10-08 15:06:37,679 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3203, 0.5312, 0.0728, -1.2266],
[ 2.5156, 1.5078, 1.0469, 1.4922],
[ 0.9531, -0.5664, -0.2832, 0.4141],
...,
[-0.1230, -0.1592, -0.3750, -1.1406],
[-0.3457, 1.2734, 0.7969, 1.0000],
[-1.0547, 0.2080, 0.3184, 1.8125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3203, 0.5312, 0.0728, -1.2266],
[ 2.5156, 1.5078, 1.0469, 1.4922],
[ 0.9531, -0.5664, -0.2832, 0.4141],
...,
[-0.1230, -0.1592, -0.3750, -1.1406],
[-0.3457, 1.2734, 0.7969, 1.0000],
[-1.0547, 0.2080, 0.3184, 1.8125]], requires_grad=True)
2024-10-08 15:06:37,940 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4961e-01, 3.7305e-01, 1.7700e-03, -1.3438e+00],
[ 2.6406e+00, 1.5391e+00, 1.0938e+00, 1.5000e+00],
[ 1.0000e+00, -5.6250e-01, -2.6953e-01, 4.1016e-01],
...,
[-1.5332e-01, -1.6309e-01, -3.5352e-01, -1.1797e+00],
[-3.4180e-01, 1.2344e+00, 7.6172e-01, 1.0000e+00],
[-1.0000e+00, 1.7676e-01, 3.0078e-01, 1.8203e+00]],
requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4961e-01, 3.7305e-01, 1.7700e-03, -1.3438e+00],
[ 2.6406e+00, 1.5391e+00, 1.0938e+00, 1.5000e+00],
[ 1.0000e+00, -5.6250e-01, -2.6953e-01, 4.1016e-01],
...,
[-1.5332e-01, -1.6309e-01, -3.5352e-01, -1.1797e+00],
[-3.4180e-01, 1.2344e+00, 7.6172e-01, 1.0000e+00],
[-1.0000e+00, 1.7676e-01, 3.0078e-01, 1.8203e+00]],
requires_grad=True)
2024-10-08 15:06:38,207 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2559, 0.1279, -0.0908, -1.5078],
[ 2.5625, 1.7969, 1.2109, 1.5781],
[ 0.9883, -0.5195, -0.2451, 0.4199],
...,
[-0.0154, -0.3262, -0.3848, -1.2578],
[-0.4512, 1.2969, 0.7578, 1.0312],
[-0.9883, 0.2227, 0.3027, 1.8516]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2559, 0.1279, -0.0908, -1.5078],
[ 2.5625, 1.7969, 1.2109, 1.5781],
[ 0.9883, -0.5195, -0.2451, 0.4199],
...,
[-0.0154, -0.3262, -0.3848, -1.2578],
[-0.4512, 1.2969, 0.7578, 1.0312],
[-0.9883, 0.2227, 0.3027, 1.8516]], requires_grad=True)
2024-10-08 15:06:38,460 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2080, -0.0491, -0.1602, -1.6328],
[ 2.6406, 1.9062, 1.2812, 1.6719],
[ 1.0469, -0.5000, -0.2266, 0.4395],
...,
[-0.2520, -0.2148, -0.3379, -1.3516],
[-0.4199, 1.2578, 0.7266, 1.0703],
[-0.9766, 0.2490, 0.3008, 1.8672]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2080, -0.0491, -0.1602, -1.6328],
[ 2.6406, 1.9062, 1.2812, 1.6719],
[ 1.0469, -0.5000, -0.2266, 0.4395],
...,
[-0.2520, -0.2148, -0.3379, -1.3516],
[-0.4199, 1.2578, 0.7266, 1.0703],
[-0.9766, 0.2490, 0.3008, 1.8672]], requires_grad=True)
2024-10-08 15:06:38,713 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2031, -0.1826, -0.2178, -1.7422],
[ 2.8906, 1.7656, 1.2812, 1.7422],
[ 1.1641, -0.5312, -0.2207, 0.4512],
...,
[-0.4492, -0.1309, -0.3008, -1.4375],
[-0.3320, 1.1562, 0.6836, 1.0938],
[-0.9375, 0.2412, 0.2930, 1.8750]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.2031, -0.1826, -0.2178, -1.7422],
[ 2.8906, 1.7656, 1.2812, 1.7422],
[ 1.1641, -0.5312, -0.2207, 0.4512],
...,
[-0.4492, -0.1309, -0.3008, -1.4375],
[-0.3320, 1.1562, 0.6836, 1.0938],
[-0.9375, 0.2412, 0.2930, 1.8750]], requires_grad=True)
2024-10-08 15:06:38,874 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1748, -0.3047, -0.2656, -1.8281],
[ 3.1250, 1.5859, 1.2812, 1.7734],
[ 1.2578, -0.5664, -0.2158, 0.4531],
...,
[-0.6406, -0.0374, -0.2637, -1.5000],
[-0.2314, 1.0469, 0.6445, 1.1016],
[-0.9102, 0.2305, 0.2852, 1.8750]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1748, -0.3047, -0.2656, -1.8281],
[ 3.1250, 1.5859, 1.2812, 1.7734],
[ 1.2578, -0.5664, -0.2158, 0.4531],
...,
[-0.6406, -0.0374, -0.2637, -1.5000],
[-0.2314, 1.0469, 0.6445, 1.1016],
[-0.9102, 0.2305, 0.2852, 1.8750]], requires_grad=True)
2024-10-08 15:06:39,129 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1357, -0.4180, -0.3066, -1.8984],
[ 3.2969, 1.5000, 1.2656, 1.8672],
[ 1.2656, -0.5508, -0.2188, 0.4922],
...,
[-0.7617, 0.0137, -0.2256, -1.5625],
[-0.2100, 0.9961, 0.5977, 1.1406],
[-0.9180, 0.2461, 0.2715, 1.8750]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1357, -0.4180, -0.3066, -1.8984],
[ 3.2969, 1.5000, 1.2656, 1.8672],
[ 1.2656, -0.5508, -0.2188, 0.4922],
...,
[-0.7617, 0.0137, -0.2256, -1.5625],
[-0.2100, 0.9961, 0.5977, 1.1406],
[-0.9180, 0.2461, 0.2715, 1.8750]], requires_grad=True)
2024-10-08 15:06:39,379 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1050, -0.5195, -0.3398, -1.9688],
[ 3.4219, 1.4609, 1.2266, 1.9688],
[ 1.2422, -0.5117, -0.2314, 0.5469],
...,
[-0.8203, 0.0442, -0.1816, -1.6172],
[-0.2393, 0.9766, 0.5391, 1.1875],
[-0.9570, 0.2910, 0.2441, 1.8906]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.1050, -0.5195, -0.3398, -1.9688],
[ 3.4219, 1.4609, 1.2266, 1.9688],
[ 1.2422, -0.5117, -0.2314, 0.5469],
...,
[-0.8203, 0.0442, -0.1816, -1.6172],
[-0.2393, 0.9766, 0.5391, 1.1875],
[-0.9570, 0.2910, 0.2441, 1.8906]], requires_grad=True)
2024-10-08 15:06:39,543 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0688, -0.6172, -0.3594, -2.0156],
[ 3.5156, 1.4219, 1.1875, 2.0469],
[ 1.2188, -0.4805, -0.2373, 0.5859],
...,
[-0.8711, 0.0801, -0.1514, -1.6484],
[-0.2656, 0.9648, 0.4805, 1.2266],
[-0.9766, 0.3242, 0.2246, 1.8984]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0688, -0.6172, -0.3594, -2.0156],
[ 3.5156, 1.4219, 1.1875, 2.0469],
[ 1.2188, -0.4805, -0.2373, 0.5859],
...,
[-0.8711, 0.0801, -0.1514, -1.6484],
[-0.2656, 0.9648, 0.4805, 1.2266],
[-0.9766, 0.3242, 0.2246, 1.8984]], requires_grad=True)
2024-10-08 15:06:39,796 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0238, -0.6797, -0.4023, -2.0469],
[ 3.5781, 1.3594, 1.1953, 2.1094],
[ 1.1875, -0.4590, -0.2305, 0.6211],
...,
[-0.9102, 0.1289, -0.1562, -1.6719],
[-0.2910, 0.9375, 0.4590, 1.2578],
[-0.9883, 0.3496, 0.2119, 1.8984]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0238, -0.6797, -0.4023, -2.0469],
[ 3.5781, 1.3594, 1.1953, 2.1094],
[ 1.1875, -0.4590, -0.2305, 0.6211],
...,
[-0.9102, 0.1289, -0.1562, -1.6719],
[-0.2910, 0.9375, 0.4590, 1.2578],
[-0.9883, 0.3496, 0.2119, 1.8984]], requires_grad=True)
2024-10-08 15:06:40,049 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.0244, -0.7227, -0.4609, -2.0625],
[ 3.6250, 1.2734, 1.2500, 2.1562],
[ 1.1484, -0.4473, -0.2070, 0.6406],
...,
[-0.9375, 0.1875, -0.1885, -1.6875],
[-0.3164, 0.9023, 0.4512, 1.2734],
[-0.9961, 0.3594, 0.2168, 1.8906]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.0244, -0.7227, -0.4609, -2.0625],
[ 3.6250, 1.2734, 1.2500, 2.1562],
[ 1.1484, -0.4473, -0.2070, 0.6406],
...,
[-0.9375, 0.1875, -0.1885, -1.6875],
[-0.3164, 0.9023, 0.4512, 1.2734],
[-0.9961, 0.3594, 0.2168, 1.8906]], requires_grad=True)
2024-10-08 15:06:40,313 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.0806, -0.7656, -0.5078, -2.0781],
[ 3.6094, 1.2500, 1.2656, 2.2031],
[ 1.0781, -0.4141, -0.1973, 0.6562],
...,
[-0.9102, 0.2002, -0.1943, -1.6953],
[-0.3789, 0.8984, 0.4258, 1.2891],
[-1.0391, 0.4062, 0.2012, 1.8828]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.0806, -0.7656, -0.5078, -2.0781],
[ 3.6094, 1.2500, 1.2656, 2.2031],
[ 1.0781, -0.4141, -0.1973, 0.6562],
...,
[-0.9102, 0.2002, -0.1943, -1.6953],
[-0.3789, 0.8984, 0.4258, 1.2891],
[-1.0391, 0.4062, 0.2012, 1.8828]], requires_grad=True)
2024-10-08 15:06:40,470 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1328, -0.8086, -0.5469, -2.0938],
[ 3.6094, 1.2031, 1.2656, 2.2344],
[ 1.0312, -0.3926, -0.1895, 0.6680],
...,
[-0.9141, 0.2256, -0.1963, -1.6875],
[-0.4141, 0.8867, 0.4004, 1.2969],
[-1.0625, 0.4395, 0.1865, 1.8672]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1328, -0.8086, -0.5469, -2.0938],
[ 3.6094, 1.2031, 1.2656, 2.2344],
[ 1.0312, -0.3926, -0.1895, 0.6680],
...,
[-0.9141, 0.2256, -0.1963, -1.6875],
[-0.4141, 0.8867, 0.4004, 1.2969],
[-1.0625, 0.4395, 0.1865, 1.8672]], requires_grad=True)
2024-10-08 15:06:40,727 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2051, -0.8633, -0.5898, -2.1094],
[ 3.5938, 1.1875, 1.2891, 2.2812],
[ 0.9961, -0.3691, -0.1797, 0.6797],
...,
[-0.9648, 0.2598, -0.1924, -1.6875],
[-0.4219, 0.8750, 0.3809, 1.3047],
[-1.0938, 0.4922, 0.1846, 1.8594]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2051, -0.8633, -0.5898, -2.1094],
[ 3.5938, 1.1875, 1.2891, 2.2812],
[ 0.9961, -0.3691, -0.1797, 0.6797],
...,
[-0.9648, 0.2598, -0.1924, -1.6875],
[-0.4219, 0.8750, 0.3809, 1.3047],
[-1.0938, 0.4922, 0.1846, 1.8594]], requires_grad=True)
2024-10-08 15:06:40,885 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2500, -0.8906, -0.6133, -2.1094],
[ 3.6406, 1.1406, 1.2891, 2.3125],
[ 0.9844, -0.3594, -0.1777, 0.6836],
...,
[-1.1406, 0.3828, -0.1260, -1.6484],
[-0.3242, 0.7891, 0.3184, 1.2812],
[-1.0703, 0.4844, 0.1543, 1.8281]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2500, -0.8906, -0.6133, -2.1094],
[ 3.6406, 1.1406, 1.2891, 2.3125],
[ 0.9844, -0.3594, -0.1777, 0.6836],
...,
[-1.1406, 0.3828, -0.1260, -1.6484],
[-0.3242, 0.7891, 0.3184, 1.2812],
[-1.0703, 0.4844, 0.1543, 1.8281]], requires_grad=True)
2024-10-08 15:06:41,043 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2441, -0.8906, -0.6211, -2.0781],
[ 3.6406, 1.1250, 1.2969, 2.3438],
[ 0.9453, -0.3359, -0.1670, 0.6914],
...,
[-1.1875, 0.4297, -0.1094, -1.6328],
[-0.3145, 0.7617, 0.2949, 1.2812],
[-1.0703, 0.4922, 0.1348, 1.7891]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2441, -0.8906, -0.6211, -2.0781],
[ 3.6406, 1.1250, 1.2969, 2.3438],
[ 0.9453, -0.3359, -0.1670, 0.6914],
...,
[-1.1875, 0.4297, -0.1094, -1.6328],
[-0.3145, 0.7617, 0.2949, 1.2812],
[-1.0703, 0.4922, 0.1348, 1.7891]], requires_grad=True)
2024-10-08 15:06:41,294 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2969, -0.9219, -0.6484, -2.0781],
[ 3.4844, 1.2109, 1.3828, 2.4062],
[ 0.8516, -0.2871, -0.1348, 0.7148],
...,
[-1.1641, 0.4395, -0.1177, -1.6250],
[-0.3535, 0.7656, 0.2949, 1.2891],
[-1.1250, 0.5430, 0.1494, 1.7734]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.2969, -0.9219, -0.6484, -2.0781],
[ 3.4844, 1.2109, 1.3828, 2.4062],
[ 0.8516, -0.2871, -0.1348, 0.7148],
...,
[-1.1641, 0.4395, -0.1177, -1.6250],
[-0.3535, 0.7656, 0.2949, 1.2891],
[-1.1250, 0.5430, 0.1494, 1.7734]], requires_grad=True)
2024-10-08 15:06:41,450 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1787, -0.8945, -0.6328, -2.0469],
[ 3.5469, 1.1562, 1.3516, 2.4062],
[ 0.8477, -0.2754, -0.1318, 0.7148],
...,
[-1.3438, 0.5430, -0.0408, -1.5625],
[-0.2598, 0.7031, 0.2441, 1.2656],
[-1.0312, 0.4922, 0.0933, 1.7109]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1787, -0.8945, -0.6328, -2.0469],
[ 3.5469, 1.1562, 1.3516, 2.4062],
[ 0.8477, -0.2754, -0.1318, 0.7148],
...,
[-1.3438, 0.5430, -0.0408, -1.5625],
[-0.2598, 0.7031, 0.2441, 1.2656],
[-1.0312, 0.4922, 0.0933, 1.7109]], requires_grad=True)
2024-10-08 15:06:41,612 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1045, -0.8750, -0.6211, -2.0156],
[ 3.5781, 1.1172, 1.3281, 2.3906],
[ 0.8672, -0.2754, -0.1377, 0.7031],
...,
[-1.3906, 0.5938, -0.0053, -1.5234],
[-0.2754, 0.6875, 0.2275, 1.2578],
[-0.9570, 0.4551, 0.0505, 1.6484]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.1045, -0.8750, -0.6211, -2.0156],
[ 3.5781, 1.1172, 1.3281, 2.3906],
[ 0.8672, -0.2754, -0.1377, 0.7031],
...,
[-1.3906, 0.5938, -0.0053, -1.5234],
[-0.2754, 0.6875, 0.2275, 1.2578],
[-0.9570, 0.4551, 0.0505, 1.6484]], requires_grad=True)
2024-10-08 15:06:41,869 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.0280, -0.8555, -0.6094, -1.9844],
[ 3.3750, 1.2266, 1.4141, 2.4688],
[ 0.8086, -0.2471, -0.1235, 0.7148],
...,
[-1.2422, 0.5508, -0.0342, -1.5312],
[-0.5078, 0.7773, 0.2832, 1.3203],
[-1.1328, 0.5742, 0.1064, 1.6953]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[ 0.0280, -0.8555, -0.6094, -1.9844],
[ 3.3750, 1.2266, 1.4141, 2.4688],
[ 0.8086, -0.2471, -0.1235, 0.7148],
...,
[-1.2422, 0.5508, -0.0342, -1.5312],
[-0.5078, 0.7773, 0.2832, 1.3203],
[-1.1328, 0.5742, 0.1064, 1.6953]], requires_grad=True)
2024-10-08 15:06:42,126 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0305, -0.8438, -0.6016, -1.9609],
[ 3.2344, 1.2812, 1.4688, 2.5000],
[ 0.7773, -0.2324, -0.1172, 0.7109],
...,
[-1.2031, 0.5664, -0.0277, -1.4922],
[-0.6211, 0.8008, 0.3047, 1.3281],
[-1.2812, 0.6680, 0.1504, 1.7109]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.0305, -0.8438, -0.6016, -1.9609],
[ 3.2344, 1.2812, 1.4688, 2.5000],
[ 0.7773, -0.2324, -0.1172, 0.7109],
...,
[-1.2031, 0.5664, -0.0277, -1.4922],
[-0.6211, 0.8008, 0.3047, 1.3281],
[-1.2812, 0.6680, 0.1504, 1.7109]], requires_grad=True)
2024-10-08 15:06:42,390 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3008, -0.7500, -0.5508, -1.8594],
[ 3.2812, 1.2266, 1.4531, 2.4688],
[ 0.8594, -0.2559, -0.1299, 0.6797],
...,
[-1.2891, 0.6406, 0.0115, -1.4141],
[-0.6094, 0.7617, 0.2891, 1.2891],
[-1.2734, 0.6836, 0.1621, 1.7031]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.3008, -0.7500, -0.5508, -1.8594],
[ 3.2812, 1.2266, 1.4531, 2.4688],
[ 0.8594, -0.2559, -0.1299, 0.6797],
...,
[-1.2891, 0.6406, 0.0115, -1.4141],
[-0.6094, 0.7617, 0.2891, 1.2891],
[-1.2734, 0.6836, 0.1621, 1.7031]], requires_grad=True)
2024-10-08 15:06:42,657 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5938, -0.6406, -0.4980, -1.7500],
[ 3.3594, 1.1406, 1.4141, 2.4062],
[ 0.9570, -0.2891, -0.1484, 0.6367],
...,
[-1.3750, 0.7148, 0.0527, -1.3359],
[-0.5703, 0.7070, 0.2695, 1.2344],
[-1.2734, 0.6992, 0.1729, 1.6875]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5938, -0.6406, -0.4980, -1.7500],
[ 3.3594, 1.1406, 1.4141, 2.4062],
[ 0.9570, -0.2891, -0.1484, 0.6367],
...,
[-1.3750, 0.7148, 0.0527, -1.3359],
[-0.5703, 0.7070, 0.2695, 1.2344],
[-1.2734, 0.6992, 0.1729, 1.6875]], requires_grad=True)
2024-10-08 15:06:42,812 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7422, -0.5742, -0.4629, -1.6562],
[ 3.2656, 1.1641, 1.4297, 2.3906],
[ 1.0156, -0.3086, -0.1592, 0.6016],
...,
[-1.2656, 0.6875, 0.0430, -1.3047],
[-0.6523, 0.7188, 0.2773, 1.2109],
[-1.4297, 0.8203, 0.2266, 1.7266]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7422, -0.5742, -0.4629, -1.6562],
[ 3.2656, 1.1641, 1.4297, 2.3906],
[ 1.0156, -0.3086, -0.1592, 0.6016],
...,
[-1.2656, 0.6875, 0.0430, -1.3047],
[-0.6523, 0.7188, 0.2773, 1.2109],
[-1.4297, 0.8203, 0.2266, 1.7266]], requires_grad=True)
2024-10-08 15:06:43,065 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6445, -0.5820, -0.4570, -1.5938],
[ 3.1875, 1.1641, 1.4297, 2.3594],
[ 0.9883, -0.3027, -0.1582, 0.5742],
...,
[-1.0156, 0.6016, 0.0072, -1.2812],
[-0.9570, 0.8203, 0.3242, 1.2109],
[-1.7422, 1.0156, 0.3086, 1.7656]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.6445, -0.5820, -0.4570, -1.5938],
[ 3.1875, 1.1641, 1.4297, 2.3594],
[ 0.9883, -0.3027, -0.1582, 0.5742],
...,
[-1.0156, 0.6016, 0.0072, -1.2812],
[-0.9570, 0.8203, 0.3242, 1.2109],
[-1.7422, 1.0156, 0.3086, 1.7656]], requires_grad=True)
2024-10-08 15:06:43,322 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5664, -0.5781, -0.4473, -1.5234],
[ 3.1094, 1.1562, 1.4219, 2.3281],
[ 0.9922, -0.3086, -0.1631, 0.5469],
...,
[-0.7070, 0.4707, -0.0522, -1.2812],
[-1.2266, 0.9102, 0.3652, 1.2031],
[-2.0938, 1.2422, 0.4043, 1.8125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.5664, -0.5781, -0.4473, -1.5234],
[ 3.1094, 1.1562, 1.4219, 2.3281],
[ 0.9922, -0.3086, -0.1631, 0.5469],
...,
[-0.7070, 0.4707, -0.0522, -1.2812],
[-1.2266, 0.9102, 0.3652, 1.2031],
[-2.0938, 1.2422, 0.4043, 1.8125]], requires_grad=True)
2024-10-08 15:06:43,577 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7070, -0.4980, -0.4004, -1.4297],
[ 3.4219, 0.8828, 1.2656, 2.2344],
[ 1.1719, -0.3828, -0.2051, 0.4961],
...,
[-0.6250, 0.4512, -0.0515, -1.2500],
[-1.2188, 0.8516, 0.3301, 1.1484],
[-2.1562, 1.2891, 0.4219, 1.8281]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.7070, -0.4980, -0.4004, -1.4297],
[ 3.4219, 0.8828, 1.2656, 2.2344],
[ 1.1719, -0.3828, -0.2051, 0.4961],
...,
[-0.6250, 0.4512, -0.0515, -1.2500],
[-1.2188, 0.8516, 0.3301, 1.1484],
[-2.1562, 1.2891, 0.4219, 1.8281]], requires_grad=True)
2024-10-08 15:06:43,829 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9570, -0.3613, -0.3262, -1.3203],
[ 3.9844, 0.3770, 0.9648, 2.0625],
[ 1.3672, -0.4648, -0.2520, 0.4395],
...,
[-0.5508, 0.4297, -0.0522, -1.2188],
[-1.1328, 0.7422, 0.2715, 1.0781],
[-2.0312, 1.1719, 0.3613, 1.7891]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9570, -0.3613, -0.3262, -1.3203],
[ 3.9844, 0.3770, 0.9648, 2.0625],
[ 1.3672, -0.4648, -0.2520, 0.4395],
...,
[-0.5508, 0.4297, -0.0522, -1.2188],
[-1.1328, 0.7422, 0.2715, 1.0781],
[-2.0312, 1.1719, 0.3613, 1.7891]], requires_grad=True)
2024-10-08 15:06:44,092 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1641, -0.3203, -0.3086, -1.2969],
[ 4.4062, -0.0299, 0.7227, 1.8984],
[ 1.5078, -0.5117, -0.2754, 0.4023],
...,
[-0.3965, 0.3008, -0.1226, -1.2344],
[-1.0703, 0.6992, 0.2520, 1.0469],
[-1.9375, 1.0312, 0.2812, 1.6953]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.1641, -0.3203, -0.3086, -1.2969],
[ 4.4062, -0.0299, 0.7227, 1.8984],
[ 1.5078, -0.5117, -0.2754, 0.4023],
...,
[-0.3965, 0.3008, -0.1226, -1.2344],
[-1.0703, 0.6992, 0.2520, 1.0469],
[-1.9375, 1.0312, 0.2812, 1.6953]], requires_grad=True)
2024-10-08 15:06:44,351 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.3828, -0.3438, -0.3281, -1.3359],
[ 5.0312, -0.6133, 0.3691, 1.7344],
[ 1.6797, -0.5625, -0.3027, 0.3789],
...,
[-0.1592, -0.0977, -0.3691, -1.3828],
[-1.0234, 0.7344, 0.2773, 1.0625],
[-1.8281, 1.0312, 0.2871, 1.7031]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.3828, -0.3438, -0.3281, -1.3359],
[ 5.0312, -0.6133, 0.3691, 1.7344],
[ 1.6797, -0.5625, -0.3027, 0.3789],
...,
[-0.1592, -0.0977, -0.3691, -1.3828],
[-1.0234, 0.7344, 0.2773, 1.0625],
[-1.8281, 1.0312, 0.2871, 1.7031]], requires_grad=True)
2024-10-08 15:06:44,511 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.5156, -0.4199, -0.3750, -1.3828],
[ 5.5000, -1.0625, 0.0962, 1.5859],
[ 1.7812, -0.5547, -0.2949, 0.3672],
...,
[ 0.0659, -0.4492, -0.5820, -1.5078],
[-1.0000, 0.7812, 0.3125, 1.0781],
[-1.7109, 0.9961, 0.2734, 1.6953]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.5156, -0.4199, -0.3750, -1.3828],
[ 5.5000, -1.0625, 0.0962, 1.5859],
[ 1.7812, -0.5547, -0.2949, 0.3672],
...,
[ 0.0659, -0.4492, -0.5820, -1.5078],
[-1.0000, 0.7812, 0.3125, 1.0781],
[-1.7109, 0.9961, 0.2734, 1.6953]], requires_grad=True)
2024-10-08 15:06:44,772 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.8438, -0.3418, -0.3438, -1.4297],
[ 5.9062, -1.5391, -0.1953, 1.4219],
[ 1.9297, -0.6055, -0.3184, 0.3516],
...,
[-0.0325, -0.5273, -0.6484, -1.6328],
[-0.7969, 0.6367, 0.2461, 1.0781],
[-1.4844, 0.8203, 0.1973, 1.6875]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.8438, -0.3418, -0.3438, -1.4297],
[ 5.9062, -1.5391, -0.1953, 1.4219],
[ 1.9297, -0.6055, -0.3184, 0.3516],
...,
[-0.0325, -0.5273, -0.6484, -1.6328],
[-0.7969, 0.6367, 0.2461, 1.0781],
[-1.4844, 0.8203, 0.1973, 1.6875]], requires_grad=True)
2024-10-08 15:06:45,037 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.1250, -0.1797, -0.2695, -1.4297],
[ 6.1875, -1.9453, -0.4473, 1.2656],
[ 2.1094, -0.6992, -0.3652, 0.3379],
...,
[-0.1006, -0.5586, -0.6797, -1.7266],
[-0.2871, 0.2969, 0.0913, 1.1641],
[-1.4688, 0.7539, 0.1602, 1.6094]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.1250, -0.1797, -0.2695, -1.4297],
[ 6.1875, -1.9453, -0.4473, 1.2656],
[ 2.1094, -0.6992, -0.3652, 0.3379],
...,
[-0.1006, -0.5586, -0.6797, -1.7266],
[-0.2871, 0.2969, 0.0913, 1.1641],
[-1.4688, 0.7539, 0.1602, 1.6094]], requires_grad=True)
2024-10-08 15:06:45,305 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.2812, -0.1680, -0.2637, -1.4141],
[ 6.3125, -2.1094, -0.5703, 1.0938],
[ 2.2188, -0.7383, -0.3828, 0.3223],
...,
[-0.0674, -0.6797, -0.7539, -1.7734],
[ 0.0620, 0.1328, 0.0182, 1.2109],
[-1.4609, 0.7148, 0.1367, 1.5312]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.2812, -0.1680, -0.2637, -1.4141],
[ 6.3125, -2.1094, -0.5703, 1.0938],
[ 2.2188, -0.7383, -0.3828, 0.3223],
...,
[-0.0674, -0.6797, -0.7539, -1.7734],
[ 0.0620, 0.1328, 0.0182, 1.2109],
[-1.4609, 0.7148, 0.1367, 1.5312]], requires_grad=True)
2024-10-08 15:06:45,554 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4219e+00, -2.4023e-01, -2.9492e-01, -1.4141e+00],
[ 6.4062e+00, -2.0469e+00, -5.7422e-01, 9.4922e-01],
[ 2.3125e+00, -7.1094e-01, -3.7109e-01, 3.0859e-01],
...,
[-5.4688e-02, -9.4141e-01, -8.9844e-01, -1.8281e+00],
[ 3.5938e-01, 9.1797e-02, 2.6093e-03, 1.2500e+00],
[-1.4141e+00, 8.1641e-01, 1.7676e-01, 1.4844e+00]],
requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4219e+00, -2.4023e-01, -2.9492e-01, -1.4141e+00],
[ 6.4062e+00, -2.0469e+00, -5.7422e-01, 9.4922e-01],
[ 2.3125e+00, -7.1094e-01, -3.7109e-01, 3.0859e-01],
...,
[-5.4688e-02, -9.4141e-01, -8.9844e-01, -1.8281e+00],
[ 3.5938e-01, 9.1797e-02, 2.6093e-03, 1.2500e+00],
[-1.4141e+00, 8.1641e-01, 1.7676e-01, 1.4844e+00]],
requires_grad=True)
2024-10-08 15:06:45,815 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5312, -0.3242, -0.3281, -1.4062],
[ 6.4688, -1.9688, -0.5703, 0.8125],
[ 2.3750, -0.6836, -0.3574, 0.2930],
...,
[-0.0398, -1.1875, -1.0312, -1.8672],
[ 0.6094, 0.0635, -0.0085, 1.2734],
[-1.3906, 0.9062, 0.2119, 1.4297]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5312, -0.3242, -0.3281, -1.4062],
[ 6.4688, -1.9688, -0.5703, 0.8125],
[ 2.3750, -0.6836, -0.3574, 0.2930],
...,
[-0.0398, -1.1875, -1.0312, -1.8672],
[ 0.6094, 0.0635, -0.0085, 1.2734],
[-1.3906, 0.9062, 0.2119, 1.4297]], requires_grad=True)
2024-10-08 15:06:45,975 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.3301, -0.3340, -1.3828],
[ 6.4062, -2.0156, -0.6172, 0.6680],
[ 2.3438, -0.7188, -0.3711, 0.2656],
...,
[ 0.0586, -1.2656, -1.0859, -1.8828],
[ 0.7539, -0.0776, -0.0615, 1.2812],
[-1.4062, 0.9258, 0.2217, 1.3672]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.3301, -0.3340, -1.3828],
[ 6.4062, -2.0156, -0.6172, 0.6680],
[ 2.3438, -0.7188, -0.3711, 0.2656],
...,
[ 0.0586, -1.2656, -1.0859, -1.8828],
[ 0.7539, -0.0776, -0.0615, 1.2812],
[-1.4062, 0.9258, 0.2217, 1.3672]], requires_grad=True)
2024-10-08 15:06:46,129 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5312, -0.3633, -0.3496, -1.3516],
[ 6.3750, -2.0625, -0.6562, 0.5508],
[ 2.3438, -0.6953, -0.3594, 0.2500],
...,
[ 0.1177, -1.3828, -1.1562, -1.9062],
[ 0.9062, -0.1953, -0.1035, 1.2969],
[-1.4062, 0.9141, 0.2217, 1.3125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5312, -0.3633, -0.3496, -1.3516],
[ 6.3750, -2.0625, -0.6562, 0.5508],
[ 2.3438, -0.6953, -0.3594, 0.2500],
...,
[ 0.1177, -1.3828, -1.1562, -1.9062],
[ 0.9062, -0.1953, -0.1035, 1.2969],
[-1.4062, 0.9141, 0.2217, 1.3125]], requires_grad=True)
2024-10-08 15:06:46,396 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.3711, -0.3555, -1.3281],
[ 6.5312, -2.2344, -0.7383, 0.5078],
[ 2.3750, -0.6719, -0.3438, 0.2490],
...,
[ 0.1582, -1.5156, -1.2344, -1.9375],
[ 1.1250, -0.2969, -0.1348, 1.3438],
[-1.4453, 0.9023, 0.2188, 1.2344]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.3711, -0.3555, -1.3281],
[ 6.5312, -2.2344, -0.7383, 0.5078],
[ 2.3750, -0.6719, -0.3438, 0.2490],
...,
[ 0.1582, -1.5156, -1.2344, -1.9375],
[ 1.1250, -0.2969, -0.1348, 1.3438],
[-1.4453, 0.9023, 0.2188, 1.2344]], requires_grad=True)
2024-10-08 15:06:46,645 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.3887, -0.3633, -1.3047],
[ 6.6562, -2.3438, -0.7891, 0.4824],
[ 2.3750, -0.6250, -0.3223, 0.2559],
...,
[ 0.2080, -1.7188, -1.3359, -1.9844],
[ 1.3125, -0.3223, -0.1387, 1.4062],
[-1.4531, 0.9258, 0.2275, 1.1797]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.3887, -0.3633, -1.3047],
[ 6.6562, -2.3438, -0.7891, 0.4824],
[ 2.3750, -0.6250, -0.3223, 0.2559],
...,
[ 0.2080, -1.7188, -1.3359, -1.9844],
[ 1.3125, -0.3223, -0.1387, 1.4062],
[-1.4531, 0.9258, 0.2275, 1.1797]], requires_grad=True)
2024-10-08 15:06:46,906 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.4336, -0.3750, -1.2969],
[ 6.7500, -2.4219, -0.8281, 0.4590],
[ 2.3594, -0.5859, -0.3027, 0.2578],
...,
[ 0.2715, -1.8672, -1.4141, -2.0000],
[ 1.4531, -0.3555, -0.1455, 1.4453],
[-1.4609, 0.9531, 0.2363, 1.1250]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.4336, -0.3750, -1.2969],
[ 6.7500, -2.4219, -0.8281, 0.4590],
[ 2.3594, -0.5859, -0.3027, 0.2578],
...,
[ 0.2715, -1.8672, -1.4141, -2.0000],
[ 1.4531, -0.3555, -0.1455, 1.4453],
[-1.4609, 0.9531, 0.2363, 1.1250]], requires_grad=True)
2024-10-08 15:06:47,068 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.4609, -0.3828, -1.2812],
[ 6.8438, -2.5000, -0.8633, 0.4434],
[ 2.3438, -0.5664, -0.2852, 0.2559],
...,
[ 0.3242, -1.9688, -1.4766, -2.0000],
[ 1.5781, -0.4121, -0.1553, 1.4609],
[-1.4609, 0.9648, 0.2432, 1.0781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5469, -0.4609, -0.3828, -1.2812],
[ 6.8438, -2.5000, -0.8633, 0.4434],
[ 2.3438, -0.5664, -0.2852, 0.2559],
...,
[ 0.3242, -1.9688, -1.4766, -2.0000],
[ 1.5781, -0.4121, -0.1553, 1.4609],
[-1.4609, 0.9648, 0.2432, 1.0781]], requires_grad=True)
2024-10-08 15:06:47,218 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5156, -0.4980, -0.3887, -1.2656],
[ 6.8750, -2.5781, -0.8906, 0.4180],
[ 2.3281, -0.5430, -0.2715, 0.2520],
...,
[ 0.3906, -2.0781, -1.5234, -2.0000],
[ 1.6641, -0.4355, -0.1611, 1.4766],
[-1.4609, 0.9805, 0.2480, 1.0312]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5156, -0.4980, -0.3887, -1.2656],
[ 6.8750, -2.5781, -0.8906, 0.4180],
[ 2.3281, -0.5430, -0.2715, 0.2520],
...,
[ 0.3906, -2.0781, -1.5234, -2.0000],
[ 1.6641, -0.4355, -0.1611, 1.4766],
[-1.4609, 0.9805, 0.2480, 1.0312]], requires_grad=True)
2024-10-08 15:06:47,486 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4844, -0.5195, -0.3945, -1.2422],
[ 6.9375, -2.6719, -0.9102, 0.3945],
[ 2.3281, -0.5273, -0.2578, 0.2441],
...,
[ 0.4277, -2.1250, -1.5625, -1.9688],
[ 1.7422, -0.4746, -0.1650, 1.4688],
[-1.4609, 0.9961, 0.2500, 0.9922]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4844, -0.5195, -0.3945, -1.2422],
[ 6.9375, -2.6719, -0.9102, 0.3945],
[ 2.3281, -0.5273, -0.2578, 0.2441],
...,
[ 0.4277, -2.1250, -1.5625, -1.9688],
[ 1.7422, -0.4746, -0.1650, 1.4688],
[-1.4609, 0.9961, 0.2500, 0.9922]], requires_grad=True)
2024-10-08 15:06:47,749 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4375, -0.5742, -0.3945, -1.2656],
[ 6.9688, -2.7656, -0.9219, 0.3652],
[ 2.3281, -0.5078, -0.2441, 0.2441],
...,
[ 0.5078, -2.2344, -1.5781, -2.0000],
[ 1.7578, -0.4453, -0.1777, 1.5156],
[-1.4844, 1.0703, 0.2441, 1.0000]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4375, -0.5742, -0.3945, -1.2656],
[ 6.9688, -2.7656, -0.9219, 0.3652],
[ 2.3281, -0.5078, -0.2441, 0.2441],
...,
[ 0.5078, -2.2344, -1.5781, -2.0000],
[ 1.7578, -0.4453, -0.1777, 1.5156],
[-1.4844, 1.0703, 0.2441, 1.0000]], requires_grad=True)
2024-10-08 15:06:48,014 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4062, -0.6016, -0.4082, -1.2578],
[ 7.0000, -2.9062, -0.8633, 0.2754],
[ 2.3281, -0.5000, -0.2207, 0.2305],
...,
[ 0.5586, -2.2969, -1.6172, -1.9844],
[ 1.7656, -0.4277, -0.1816, 1.5391],
[-1.4844, 1.0938, 0.2676, 0.9648]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4062, -0.6016, -0.4082, -1.2578],
[ 7.0000, -2.9062, -0.8633, 0.2754],
[ 2.3281, -0.5000, -0.2207, 0.2305],
...,
[ 0.5586, -2.2969, -1.6172, -1.9844],
[ 1.7656, -0.4277, -0.1816, 1.5391],
[-1.4844, 1.0938, 0.2676, 0.9648]], requires_grad=True)
2024-10-08 15:06:48,271 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.3750, -0.6172, -0.4238, -1.2344],
[ 7.0625, -3.0469, -0.7695, 0.1621],
[ 2.3281, -0.4922, -0.1992, 0.2168],
...,
[ 0.5859, -2.3281, -1.6719, -1.9453],
[ 1.7734, -0.4199, -0.1709, 1.5391],
[-1.4766, 1.1016, 0.2969, 0.9219]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.3750, -0.6172, -0.4238, -1.2344],
[ 7.0625, -3.0469, -0.7695, 0.1621],
[ 2.3281, -0.4922, -0.1992, 0.2168],
...,
[ 0.5859, -2.3281, -1.6719, -1.9453],
[ 1.7734, -0.4199, -0.1709, 1.5391],
[-1.4766, 1.1016, 0.2969, 0.9219]], requires_grad=True)
2024-10-08 15:06:48,523 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.1406, -0.6719, -0.3691, -1.3281],
[ 6.9688, -3.1094, -0.7773, 0.1553],
[ 2.2344, -0.4668, -0.2100, 0.2451],
...,
[ 0.9297, -2.4531, -1.5547, -2.0938],
[ 1.5859, -0.3594, -0.2471, 1.6484],
[-1.6016, 1.1641, 0.2441, 0.9844]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.1406, -0.6719, -0.3691, -1.3281],
[ 6.9688, -3.1094, -0.7773, 0.1553],
[ 2.2344, -0.4668, -0.2100, 0.2451],
...,
[ 0.9297, -2.4531, -1.5547, -2.0938],
[ 1.5859, -0.3594, -0.2471, 1.6484],
[-1.6016, 1.1641, 0.2441, 0.9844]], requires_grad=True)
2024-10-08 15:06:48,685 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.9688, -0.7109, -0.3320, -1.3906],
[ 7.0312, -3.2188, -0.6914, 0.0933],
[ 2.2188, -0.4629, -0.1924, 0.2412],
...,
[ 1.0234, -2.4688, -1.5391, -2.1250],
[ 1.4453, -0.3145, -0.2988, 1.7188],
[-1.5703, 1.1562, 0.2676, 0.9648]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.9688, -0.7109, -0.3320, -1.3906],
[ 7.0312, -3.2188, -0.6914, 0.0933],
[ 2.2188, -0.4629, -0.1924, 0.2412],
...,
[ 1.0234, -2.4688, -1.5391, -2.1250],
[ 1.4453, -0.3145, -0.2988, 1.7188],
[-1.5703, 1.1562, 0.2676, 0.9648]], requires_grad=True)
2024-10-08 15:06:48,834 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.8438, -0.7383, -0.3145, -1.4297],
[ 7.0000, -3.2969, -0.6484, 0.0593],
[ 2.2188, -0.4609, -0.1670, 0.2285],
...,
[ 1.0547, -2.4688, -1.5547, -2.1250],
[ 1.3438, -0.2832, -0.3203, 1.7500],
[-1.5078, 1.1328, 0.3223, 0.9102]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.8438, -0.7383, -0.3145, -1.4297],
[ 7.0000, -3.2969, -0.6484, 0.0593],
[ 2.2188, -0.4609, -0.1670, 0.2285],
...,
[ 1.0547, -2.4688, -1.5547, -2.1250],
[ 1.3438, -0.2832, -0.3203, 1.7500],
[-1.5078, 1.1328, 0.3223, 0.9102]], requires_grad=True)
2024-10-08 15:06:49,091 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.5938, -0.7734, -0.2393, -1.5312],
[ 6.8750, -3.3281, -0.7070, 0.1011],
[ 2.1406, -0.4512, -0.1748, 0.2412],
...,
[ 1.2891, -2.4844, -1.4297, -2.2031],
[ 1.1562, -0.2422, -0.3965, 1.8203],
[-1.5156, 1.1172, 0.3203, 0.8984]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.5938, -0.7734, -0.2393, -1.5312],
[ 6.8750, -3.3281, -0.7070, 0.1011],
[ 2.1406, -0.4512, -0.1748, 0.2412],
...,
[ 1.2891, -2.4844, -1.4297, -2.2031],
[ 1.1562, -0.2422, -0.3965, 1.8203],
[-1.5156, 1.1172, 0.3203, 0.8984]], requires_grad=True)
2024-10-08 15:06:49,249 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2344, -0.8125, -0.1055, -1.6875],
[ 6.6250, -3.3281, -0.8867, 0.2393],
[ 2.0156, -0.4355, -0.2119, 0.2812],
...,
[ 1.5234, -2.5000, -1.2969, -2.2969],
[ 0.9648, -0.2031, -0.4766, 1.8828],
[-1.6484, 1.1250, 0.2090, 0.9883]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.2344, -0.8125, -0.1055, -1.6875],
[ 6.6250, -3.3281, -0.8867, 0.2393],
[ 2.0156, -0.4355, -0.2119, 0.2812],
...,
[ 1.5234, -2.5000, -1.2969, -2.2969],
[ 0.9648, -0.2031, -0.4766, 1.8828],
[-1.6484, 1.1250, 0.2090, 0.9883]], requires_grad=True)
2024-10-08 15:06:49,513 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-8.9844e-01, -8.4375e-01, -4.2915e-04, -1.7891e+00],
[ 6.5625e+00, -3.3438e+00, -8.5547e-01, 2.4609e-01],
[ 1.9297e+00, -4.2383e-01, -2.1484e-01, 2.8711e-01],
...,
[ 1.7031e+00, -2.5000e+00, -1.1797e+00, -2.3750e+00],
[ 8.5156e-01, -1.7383e-01, -5.0391e-01, 1.8984e+00],
[-1.7109e+00, 1.1250e+00, 1.5527e-01, 1.0234e+00]],
requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-8.9844e-01, -8.4375e-01, -4.2915e-04, -1.7891e+00],
[ 6.5625e+00, -3.3438e+00, -8.5547e-01, 2.4609e-01],
[ 1.9297e+00, -4.2383e-01, -2.1484e-01, 2.8711e-01],
...,
[ 1.7031e+00, -2.5000e+00, -1.1797e+00, -2.3750e+00],
[ 8.5156e-01, -1.7383e-01, -5.0391e-01, 1.8984e+00],
[-1.7109e+00, 1.1250e+00, 1.5527e-01, 1.0234e+00]],
requires_grad=True)
2024-10-08 15:06:49,764 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8984, -0.8516, -0.0270, -1.7656],
[ 6.4688, -3.3438, -0.8438, 0.2559],
[ 2.0625, -0.4258, -0.1250, 0.2236],
...,
[ 1.5547, -2.4688, -1.2656, -2.3125],
[ 0.9531, -0.1670, -0.4043, 1.8281],
[-1.5625, 1.0938, 0.2480, 0.9531]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8984, -0.8516, -0.0270, -1.7656],
[ 6.4688, -3.3438, -0.8438, 0.2559],
[ 2.0625, -0.4258, -0.1250, 0.2236],
...,
[ 1.5547, -2.4688, -1.2656, -2.3125],
[ 0.9531, -0.1670, -0.4043, 1.8281],
[-1.5625, 1.0938, 0.2480, 0.9531]], requires_grad=True)
2024-10-08 15:06:50,017 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9648, -0.8398, -0.0747, -1.6875],
[ 6.1562, -3.2812, -0.9688, 0.4043],
[ 1.9844, -0.4043, -0.1021, 0.2422],
...,
[ 1.9922, -2.5156, -1.1094, -2.4844],
[ 0.8008, -0.1270, -0.4023, 1.8516],
[-1.7500, 1.1250, 0.1855, 1.0547]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.9648, -0.8398, -0.0747, -1.6875],
[ 6.1562, -3.2812, -0.9688, 0.4043],
[ 1.9844, -0.4043, -0.1021, 0.2422],
...,
[ 1.9922, -2.5156, -1.1094, -2.4844],
[ 0.8008, -0.1270, -0.4023, 1.8516],
[-1.7500, 1.1250, 0.1855, 1.0547]], requires_grad=True)
2024-10-08 15:06:50,264 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8711, -0.8594, -0.0981, -1.6875],
[ 5.9062, -3.2031, -1.0781, 0.6094],
[ 1.7656, -0.3574, -0.1016, 0.3203],
...,
[ 2.7031, -2.6406, -0.9062, -2.7656],
[ 0.4766, -0.0427, -0.4336, 1.9609],
[-2.0625, 1.2188, 0.0923, 1.2734]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-0.8711, -0.8594, -0.0981, -1.6875],
[ 5.9062, -3.2031, -1.0781, 0.6094],
[ 1.7656, -0.3574, -0.1016, 0.3203],
...,
[ 2.7031, -2.6406, -0.9062, -2.7656],
[ 0.4766, -0.0427, -0.4336, 1.9609],
[-2.0625, 1.2188, 0.0923, 1.2734]], requires_grad=True)
2024-10-08 15:06:50,425 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.3281, -0.7656, -0.1138, -1.5703],
[ 5.8125, -3.1875, -1.1719, 0.7266],
[ 1.7812, -0.3633, -0.1045, 0.3340],
...,
[ 3.0781, -2.6719, -0.7188, -2.9688],
[ 0.6367, -0.0854, -0.4629, 1.9531],
[-2.1719, 1.2266, 0.0072, 1.3984]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.3281, -0.7656, -0.1138, -1.5703],
[ 5.8125, -3.1875, -1.1719, 0.7266],
[ 1.7812, -0.3633, -0.1045, 0.3340],
...,
[ 3.0781, -2.6719, -0.7188, -2.9688],
[ 0.6367, -0.0854, -0.4629, 1.9531],
[-2.1719, 1.2266, 0.0072, 1.3984]], requires_grad=True)
2024-10-08 15:06:50,560 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.6953, -0.7031, -0.1377, -1.4922],
[ 5.6875, -3.1406, -1.2344, 0.8594],
[ 1.7578, -0.3457, -0.0947, 0.3730],
...,
[ 3.4375, -2.7188, -0.5703, -3.1562],
[ 0.7578, -0.1128, -0.4824, 1.9453],
[-2.2969, 1.2734, -0.0435, 1.5625]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.6953, -0.7031, -0.1377, -1.4922],
[ 5.6875, -3.1406, -1.2344, 0.8594],
[ 1.7578, -0.3457, -0.0947, 0.3730],
...,
[ 3.4375, -2.7188, -0.5703, -3.1562],
[ 0.7578, -0.1128, -0.4824, 1.9453],
[-2.2969, 1.2734, -0.0435, 1.5625]], requires_grad=True)
2024-10-08 15:06:50,815 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.0000, -0.6445, -0.1572, -1.4141],
[ 5.5625, -3.0469, -1.2422, 0.9961],
[ 1.7266, -0.3281, -0.0840, 0.4062],
...,
[ 3.7969, -2.8125, -0.4902, -3.3438],
[ 0.8359, -0.1104, -0.4766, 1.9609],
[-2.4531, 1.3516, -0.0554, 1.7266]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.0000, -0.6445, -0.1572, -1.4141],
[ 5.5625, -3.0469, -1.2422, 0.9961],
[ 1.7266, -0.3281, -0.0840, 0.4062],
...,
[ 3.7969, -2.8125, -0.4902, -3.3438],
[ 0.8359, -0.1104, -0.4766, 1.9609],
[-2.4531, 1.3516, -0.0554, 1.7266]], requires_grad=True)
2024-10-08 15:06:50,967 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.2656, -0.6016, -0.1836, -1.3516],
[ 5.5312, -3.0312, -1.3438, 1.0938],
[ 1.7188, -0.3203, -0.0835, 0.4355],
...,
[ 4.0938, -2.8750, -0.4004, -3.5156],
[ 0.9062, -0.1094, -0.4707, 1.9609],
[-2.5625, 1.4297, -0.0601, 1.8672]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.2656, -0.6016, -0.1836, -1.3516],
[ 5.5312, -3.0312, -1.3438, 1.0938],
[ 1.7188, -0.3203, -0.0835, 0.4355],
...,
[ 4.0938, -2.8750, -0.4004, -3.5156],
[ 0.9062, -0.1094, -0.4707, 1.9609],
[-2.5625, 1.4297, -0.0601, 1.8672]], requires_grad=True)
2024-10-08 15:06:51,126 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5000, -0.5625, -0.2070, -1.2969],
[ 5.4062, -2.8906, -1.2656, 1.2109],
[ 1.6953, -0.2988, -0.0684, 0.4609],
...,
[ 4.3750, -2.9531, -0.3867, -3.6562],
[ 0.9297, -0.0654, -0.4160, 1.9688],
[-2.7031, 1.5781, 0.0232, 2.0156]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5000, -0.5625, -0.2070, -1.2969],
[ 5.4062, -2.8906, -1.2656, 1.2109],
[ 1.6953, -0.2988, -0.0684, 0.4609],
...,
[ 4.3750, -2.9531, -0.3867, -3.6562],
[ 0.9297, -0.0654, -0.4160, 1.9688],
[-2.7031, 1.5781, 0.0232, 2.0156]], requires_grad=True)
2024-10-08 15:06:51,391 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.7188, -0.4453, -0.1357, -1.2109],
[ 5.3125, -2.8125, -1.2812, 1.2891],
[ 1.6641, -0.3008, -0.0806, 0.4727],
...,
[ 4.5938, -3.0000, -0.3398, -3.7500],
[ 0.9609, -0.0708, -0.4180, 1.9531],
[-2.8125, 1.6641, 0.0593, 2.1250]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.7188, -0.4453, -0.1357, -1.2109],
[ 5.3125, -2.8125, -1.2812, 1.2891],
[ 1.6641, -0.3008, -0.0806, 0.4727],
...,
[ 4.5938, -3.0000, -0.3398, -3.7500],
[ 0.9609, -0.0708, -0.4180, 1.9531],
[-2.8125, 1.6641, 0.0593, 2.1250]], requires_grad=True)
2024-10-08 15:06:51,646 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.9062, -0.3398, -0.0723, -1.1250],
[ 5.2188, -2.7656, -1.3047, 1.3594],
[ 1.6562, -0.3105, -0.1001, 0.4805],
...,
[ 4.8125, -3.0781, -0.3672, -3.8438],
[ 0.9844, -0.0540, -0.3945, 1.9375],
[-2.9219, 1.7578, 0.1128, 2.2188]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.9062, -0.3398, -0.0723, -1.1250],
[ 5.2188, -2.7656, -1.3047, 1.3594],
[ 1.6562, -0.3105, -0.1001, 0.4805],
...,
[ 4.8125, -3.0781, -0.3672, -3.8438],
[ 0.9844, -0.0540, -0.3945, 1.9375],
[-2.9219, 1.7578, 0.1128, 2.2188]], requires_grad=True)
2024-10-08 15:06:51,905 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.0781, -0.1982, 0.0282, -1.0312],
[ 5.1562, -2.7344, -1.3516, 1.4219],
[ 1.6406, -0.2949, -0.0952, 0.4961],
...,
[ 4.9688, -3.1875, -0.4336, -3.9219],
[ 1.0000, -0.0114, -0.3457, 1.9453],
[-3.0000, 1.8359, 0.1641, 2.2969]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.0781, -0.1982, 0.0282, -1.0312],
[ 5.1562, -2.7344, -1.3516, 1.4219],
[ 1.6406, -0.2949, -0.0952, 0.4961],
...,
[ 4.9688, -3.1875, -0.4336, -3.9219],
[ 1.0000, -0.0114, -0.3457, 1.9453],
[-3.0000, 1.8359, 0.1641, 2.2969]], requires_grad=True)
2024-10-08 15:06:52,164 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.2031, -0.0889, 0.1040, -0.9453],
[ 5.0938, -2.7031, -1.3828, 1.4766],
[ 1.6172, -0.2910, -0.1001, 0.5039],
...,
[ 5.0938, -3.2500, -0.4707, -3.9688],
[ 1.0078, 0.0150, -0.3125, 1.9375],
[-3.0625, 1.8516, 0.1650, 2.3438]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.2031, -0.0889, 0.1040, -0.9453],
[ 5.0938, -2.7031, -1.3828, 1.4766],
[ 1.6172, -0.2910, -0.1001, 0.5039],
...,
[ 5.0938, -3.2500, -0.4707, -3.9688],
[ 1.0078, 0.0150, -0.3125, 1.9375],
[-3.0625, 1.8516, 0.1650, 2.3438]], requires_grad=True)
2024-10-08 15:06:52,422 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3438, 0.1328, 0.2637, -0.8516],
[ 5.0312, -2.8281, -1.5469, 1.4922],
[ 1.5938, -0.3555, -0.1582, 0.4980],
...,
[ 5.2188, -3.3125, -0.5039, -4.0000],
[ 1.0234, -0.0244, -0.3301, 1.9219],
[-3.1094, 1.7734, 0.1069, 2.3750]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3438, 0.1328, 0.2637, -0.8516],
[ 5.0312, -2.8281, -1.5469, 1.4922],
[ 1.5938, -0.3555, -0.1582, 0.4980],
...,
[ 5.2188, -3.3125, -0.5039, -4.0000],
[ 1.0234, -0.0244, -0.3301, 1.9219],
[-3.1094, 1.7734, 0.1069, 2.3750]], requires_grad=True)
2024-10-08 15:06:52,690 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4531, 0.3398, 0.4121, -0.7578],
[ 4.9062, -2.7031, -1.5156, 1.5234],
[ 1.5469, -0.3691, -0.1787, 0.4961],
...,
[ 5.3750, -3.4844, -0.6250, -4.0312],
[ 1.0000, 0.0464, -0.2734, 1.9141],
[-3.1562, 1.8125, 0.1235, 2.3906]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4531, 0.3398, 0.4121, -0.7578],
[ 4.9062, -2.7031, -1.5156, 1.5234],
[ 1.5469, -0.3691, -0.1787, 0.4961],
...,
[ 5.3750, -3.4844, -0.6250, -4.0312],
[ 1.0000, 0.0464, -0.2734, 1.9141],
[-3.1562, 1.8125, 0.1235, 2.3906]], requires_grad=True)
2024-10-08 15:06:52,959 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5156, 0.4902, 0.5273, -0.6797],
[ 4.7500, -2.3594, -1.3438, 1.5938],
[ 1.5000, -0.3066, -0.1562, 0.5156],
...,
[ 5.5000, -3.7812, -0.8281, -4.0625],
[ 0.9727, 0.2109, -0.1660, 1.9297],
[-3.1719, 2.0312, 0.2373, 2.4531]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5156, 0.4902, 0.5273, -0.6797],
[ 4.7500, -2.3594, -1.3438, 1.5938],
[ 1.5000, -0.3066, -0.1562, 0.5156],
...,
[ 5.5000, -3.7812, -0.8281, -4.0625],
[ 0.9727, 0.2109, -0.1660, 1.9297],
[-3.1719, 2.0312, 0.2373, 2.4531]], requires_grad=True)
2024-10-08 15:06:53,227 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5312, 0.6250, 0.6289, -0.6016],
[ 4.5625, -2.0781, -1.2031, 1.6406],
[ 1.4297, -0.2988, -0.1572, 0.5156],
...,
[ 5.6250, -3.9688, -0.9766, -4.0625],
[ 0.9375, 0.3301, -0.0825, 1.9297],
[-3.1875, 2.1406, 0.3066, 2.4844]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5312, 0.6250, 0.6289, -0.6016],
[ 4.5625, -2.0781, -1.2031, 1.6406],
[ 1.4297, -0.2988, -0.1572, 0.5156],
...,
[ 5.6250, -3.9688, -0.9766, -4.0625],
[ 0.9375, 0.3301, -0.0825, 1.9297],
[-3.1875, 2.1406, 0.3066, 2.4844]], requires_grad=True)
2024-10-08 15:06:53,479 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5625, 0.7852, 0.7266, -0.5273],
[ 4.4688, -1.8906, -1.0938, 1.6797],
[ 1.3906, -0.3301, -0.1680, 0.5117],
...,
[ 5.6875, -4.0312, -1.0703, -4.0625],
[ 0.9141, 0.3789, -0.0234, 1.9141],
[-3.1250, 2.0312, 0.3164, 2.5000]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5625, 0.7852, 0.7266, -0.5273],
[ 4.4688, -1.8906, -1.0938, 1.6797],
[ 1.3906, -0.3301, -0.1680, 0.5117],
...,
[ 5.6875, -4.0312, -1.0703, -4.0625],
[ 0.9141, 0.3789, -0.0234, 1.9141],
[-3.1250, 2.0312, 0.3164, 2.5000]], requires_grad=True)
2024-10-08 15:06:53,731 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5938, 1.0000, 0.8125, -0.4199],
[ 4.4375, -2.0156, -1.0234, 1.6250],
[ 1.3672, -0.4102, -0.1816, 0.4805],
...,
[ 5.6875, -3.9531, -1.1484, -4.0000],
[ 0.9492, 0.3145, 0.0212, 1.8672],
[-3.0469, 1.7578, 0.3125, 2.4375]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5938, 1.0000, 0.8125, -0.4199],
[ 4.4375, -2.0156, -1.0234, 1.6250],
[ 1.3672, -0.4102, -0.1816, 0.4805],
...,
[ 5.6875, -3.9531, -1.1484, -4.0000],
[ 0.9492, 0.3145, 0.0212, 1.8672],
[-3.0469, 1.7578, 0.3125, 2.4375]], requires_grad=True)
2024-10-08 15:06:53,893 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4688, 1.1094, 0.8984, -0.3613],
[ 4.0938, -1.7344, -1.0156, 1.7656],
[ 1.1172, -0.3320, -0.2148, 0.5430],
...,
[ 6.0625, -4.2188, -1.1562, -4.1250],
[ 0.7695, 0.4531, 0.0312, 1.9375],
[-3.1875, 1.7500, 0.2754, 2.4844]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4688, 1.1094, 0.8984, -0.3613],
[ 4.0938, -1.7344, -1.0156, 1.7656],
[ 1.1172, -0.3320, -0.2148, 0.5430],
...,
[ 6.0625, -4.2188, -1.1562, -4.1250],
[ 0.7695, 0.4531, 0.0312, 1.9375],
[-3.1875, 1.7500, 0.2754, 2.4844]], requires_grad=True)
2024-10-08 15:06:54,161 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3125, 1.2031, 0.9727, -0.2969],
[ 3.6562, -1.3438, -1.0391, 1.9766],
[ 0.8477, -0.2383, -0.2490, 0.6133],
...,
[ 6.4688, -4.5625, -1.1406, -4.2812],
[ 0.5938, 0.5820, 0.0378, 1.9922],
[-3.4062, 1.8359, 0.2246, 2.5781]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3125, 1.2031, 0.9727, -0.2969],
[ 3.6562, -1.3438, -1.0391, 1.9766],
[ 0.8477, -0.2383, -0.2490, 0.6133],
...,
[ 6.4688, -4.5625, -1.1406, -4.2812],
[ 0.5938, 0.5820, 0.0378, 1.9922],
[-3.4062, 1.8359, 0.2246, 2.5781]], requires_grad=True)
2024-10-08 15:06:54,420 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1562, 1.2734, 1.0391, -0.2402],
[ 3.1875, -0.9570, -1.0703, 2.1875],
[ 0.6133, -0.1611, -0.2773, 0.6641],
...,
[ 6.8438, -4.8750, -1.1094, -4.4375],
[ 0.4238, 0.6953, 0.0422, 2.0312],
[-3.5781, 1.9062, 0.1797, 2.6562]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1562, 1.2734, 1.0391, -0.2402],
[ 3.1875, -0.9570, -1.0703, 2.1875],
[ 0.6133, -0.1611, -0.2773, 0.6641],
...,
[ 6.8438, -4.8750, -1.1094, -4.4375],
[ 0.4238, 0.6953, 0.0422, 2.0312],
[-3.5781, 1.9062, 0.1797, 2.6562]], requires_grad=True)
2024-10-08 15:06:54,690 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.0469, 1.3594, 1.0859, -0.1621],
[ 3.2344, -0.8867, -1.0078, 2.1875],
[ 0.7461, -0.2080, -0.2656, 0.6133],
...,
[ 6.6250, -4.9062, -1.1562, -4.4062],
[ 0.5898, 0.6445, 0.0923, 1.9375],
[-3.3281, 1.7188, 0.2070, 2.5469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.0469, 1.3594, 1.0859, -0.1621],
[ 3.2344, -0.8867, -1.0078, 2.1875],
[ 0.7461, -0.2080, -0.2656, 0.6133],
...,
[ 6.6250, -4.9062, -1.1562, -4.4062],
[ 0.5898, 0.6445, 0.0923, 1.9375],
[-3.3281, 1.7188, 0.2070, 2.5469]], requires_grad=True)
2024-10-08 15:06:54,854 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.8906, 1.4297, 1.1250, -0.0713],
[ 3.5000, -0.9258, -0.8945, 2.1094],
[ 0.9336, -0.2432, -0.2520, 0.5977],
...,
[ 6.5312, -5.0000, -1.1641, -4.5000],
[ 0.6797, 0.6367, 0.1206, 1.9141],
[-2.9688, 1.5078, 0.2490, 2.4375]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.8906, 1.4297, 1.1250, -0.0713],
[ 3.5000, -0.9258, -0.8945, 2.1094],
[ 0.9336, -0.2432, -0.2520, 0.5977],
...,
[ 6.5312, -5.0000, -1.1641, -4.5000],
[ 0.6797, 0.6367, 0.1206, 1.9141],
[-2.9688, 1.5078, 0.2490, 2.4375]], requires_grad=True)
2024-10-08 15:06:55,266 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.7969, 1.4844, 1.1562, -0.0342],
[ 3.7188, -0.9648, -0.7930, 2.0156],
[ 1.1250, -0.2812, -0.2363, 0.5742],
...,
[ 6.7188, -5.1562, -1.1172, -4.6562],
[ 0.5039, 0.7109, 0.1079, 1.9766],
[-2.5938, 1.3125, 0.2871, 2.3438]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.7969, 1.4844, 1.1562, -0.0342],
[ 3.7188, -0.9648, -0.7930, 2.0156],
[ 1.1250, -0.2812, -0.2363, 0.5742],
...,
[ 6.7188, -5.1562, -1.1172, -4.6562],
[ 0.5039, 0.7109, 0.1079, 1.9766],
[-2.5938, 1.3125, 0.2871, 2.3438]], requires_grad=True)
2024-10-08 15:06:55,522 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5000, 1.4297, 1.2109, -0.1641],
[ 3.7969, -0.9688, -0.7148, 1.9375],
[ 1.0156, -0.2256, -0.2500, 0.6797],
...,
[ 7.0625, -5.3750, -1.0391, -4.9062],
[ 0.0635, 0.8984, 0.0574, 2.1719],
[-2.4062, 1.2031, 0.3008, 2.3125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5000, 1.4297, 1.2109, -0.1641],
[ 3.7969, -0.9688, -0.7148, 1.9375],
[ 1.0156, -0.2256, -0.2500, 0.6797],
...,
[ 7.0625, -5.3750, -1.0391, -4.9062],
[ 0.0635, 0.8984, 0.0574, 2.1719],
[-2.4062, 1.2031, 0.3008, 2.3125]], requires_grad=True)
2024-10-08 15:06:55,670 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5312, 1.4688, 1.2344, -0.1689],
[ 3.8750, -0.9844, -0.6445, 1.8516],
[ 1.1875, -0.2393, -0.2480, 0.7148],
...,
[ 7.1875, -5.5312, -0.9766, -5.0625],
[-0.0977, 0.9922, 0.0270, 2.2969],
[-2.1406, 1.0625, 0.3184, 2.2656]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.5312, 1.4688, 1.2344, -0.1689],
[ 3.8750, -0.9844, -0.6445, 1.8516],
[ 1.1875, -0.2393, -0.2480, 0.7148],
...,
[ 7.1875, -5.5312, -0.9766, -5.0625],
[-0.0977, 0.9922, 0.0270, 2.2969],
[-2.1406, 1.0625, 0.3184, 2.2656]], requires_grad=True)
2024-10-08 15:06:55,927 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.9375e+00, 1.5859e+00, 1.2500e+00, -8.4961e-02],
[ 4.2500e+00, -1.1172e+00, -5.7422e-01, 1.6953e+00],
[ 1.7422e+00, -3.5742e-01, -2.4219e-01, 6.5234e-01],
...,
[ 6.6875e+00, -5.4375e+00, -9.2578e-01, -5.0625e+00],
[ 8.8379e-02, 9.5312e-01, 4.4556e-03, 2.3125e+00],
[-1.7656e+00, 8.7891e-01, 3.3594e-01, 2.1719e+00]],
requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.9375e+00, 1.5859e+00, 1.2500e+00, -8.4961e-02],
[ 4.2500e+00, -1.1172e+00, -5.7422e-01, 1.6953e+00],
[ 1.7422e+00, -3.5742e-01, -2.4219e-01, 6.5234e-01],
...,
[ 6.6875e+00, -5.4375e+00, -9.2578e-01, -5.0625e+00],
[ 8.8379e-02, 9.5312e-01, 4.4556e-03, 2.3125e+00],
[-1.7656e+00, 8.7891e-01, 3.3594e-01, 2.1719e+00]],
requires_grad=True)
2024-10-08 15:06:56,190 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1875, 1.6562, 1.2500, -0.0435],
[ 4.6875, -1.3203, -0.5312, 1.4844],
[ 2.1719, -0.4355, -0.2314, 0.6211],
...,
[ 6.0938, -5.2812, -0.8711, -5.0000],
[ 0.3359, 0.8906, -0.0197, 2.2969],
[-1.3984, 0.6836, 0.3438, 2.0469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1875, 1.6562, 1.2500, -0.0435],
[ 4.6875, -1.3203, -0.5312, 1.4844],
[ 2.1719, -0.4355, -0.2314, 0.6211],
...,
[ 6.0938, -5.2812, -0.8711, -5.0000],
[ 0.3359, 0.8906, -0.0197, 2.2969],
[-1.3984, 0.6836, 0.3438, 2.0469]], requires_grad=True)
2024-10-08 15:06:56,441 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3750, 1.7031, 1.2422, -0.0205],
[ 4.9688, -1.4062, -0.4492, 1.3594],
[ 2.4844, -0.4727, -0.2070, 0.6172],
...,
[ 5.6250, -5.1562, -0.8320, -4.9375],
[ 0.4531, 0.8828, -0.0192, 2.3125],
[-1.1250, 0.5352, 0.3574, 1.9375]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3750, 1.7031, 1.2422, -0.0205],
[ 4.9688, -1.4062, -0.4492, 1.3594],
[ 2.4844, -0.4727, -0.2070, 0.6172],
...,
[ 5.6250, -5.1562, -0.8320, -4.9375],
[ 0.4531, 0.8828, -0.0192, 2.3125],
[-1.1250, 0.5352, 0.3574, 1.9375]], requires_grad=True)
2024-10-08 15:06:56,693 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4375, 1.6875, 1.2031, -0.0366],
[ 5.1250, -1.4375, -0.3438, 1.2734],
[ 2.7344, -0.4922, -0.1768, 0.6250],
...,
[ 5.2188, -5.0312, -0.8086, -4.8750],
[ 0.4531, 0.9453, 0.0325, 2.3750],
[-0.9297, 0.4512, 0.3984, 1.8672]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4375, 1.6875, 1.2031, -0.0366],
[ 5.1250, -1.4375, -0.3438, 1.2734],
[ 2.7344, -0.4922, -0.1768, 0.6250],
...,
[ 5.2188, -5.0312, -0.8086, -4.8750],
[ 0.4531, 0.9453, 0.0325, 2.3750],
[-0.9297, 0.4512, 0.3984, 1.8672]], requires_grad=True)
2024-10-08 15:06:56,851 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4844, 1.6875, 1.1719, -0.0422],
[ 5.2812, -1.4844, -0.2793, 1.1719],
[ 2.9531, -0.5156, -0.1572, 0.6211],
...,
[ 4.8438, -4.9062, -0.7852, -4.8125],
[ 0.4531, 0.9961, 0.0732, 2.4062],
[-0.7383, 0.3379, 0.4023, 1.7734]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4844, 1.6875, 1.1719, -0.0422],
[ 5.2812, -1.4844, -0.2793, 1.1719],
[ 2.9531, -0.5156, -0.1572, 0.6211],
...,
[ 4.8438, -4.9062, -0.7852, -4.8125],
[ 0.4531, 0.9961, 0.0732, 2.4062],
[-0.7383, 0.3379, 0.4023, 1.7734]], requires_grad=True)
2024-10-08 15:06:57,006 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5000, 1.6641, 1.1328, -0.0481],
[ 5.4062, -1.5703, -0.2754, 1.0781],
[ 3.1250, -0.5547, -0.1592, 0.6133],
...,
[ 4.4688, -4.7188, -0.6914, -4.7188],
[ 0.4629, 0.9961, 0.0698, 2.4219],
[-0.5547, 0.1924, 0.3613, 1.6797]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5000, 1.6641, 1.1328, -0.0481],
[ 5.4062, -1.5703, -0.2754, 1.0781],
[ 3.1250, -0.5547, -0.1592, 0.6133],
...,
[ 4.4688, -4.7188, -0.6914, -4.7188],
[ 0.4629, 0.9961, 0.0698, 2.4219],
[-0.5547, 0.1924, 0.3613, 1.6797]], requires_grad=True)
2024-10-08 15:06:57,166 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5000, 1.6406, 1.0859, -0.0508],
[ 5.5000, -1.6562, -0.2891, 0.9844],
[ 3.2812, -0.5859, -0.1592, 0.6016],
...,
[ 4.1562, -4.5625, -0.6211, -4.6250],
[ 0.4727, 0.9766, 0.0452, 2.4219],
[-0.3965, 0.0728, 0.3320, 1.5938]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.5000, 1.6406, 1.0859, -0.0508],
[ 5.5000, -1.6562, -0.2891, 0.9844],
[ 3.2812, -0.5859, -0.1592, 0.6016],
...,
[ 4.1562, -4.5625, -0.6211, -4.6250],
[ 0.4727, 0.9766, 0.0452, 2.4219],
[-0.3965, 0.0728, 0.3320, 1.5938]], requires_grad=True)
2024-10-08 15:06:57,324 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4844, 1.6016, 1.0312, -0.0574],
[ 5.5625, -1.6875, -0.2480, 0.9062],
[ 3.3906, -0.5938, -0.1328, 0.5938],
...,
[ 3.8750, -4.4688, -0.5977, -4.5625],
[ 0.4629, 0.9805, 0.0552, 2.4062],
[-0.2451, -0.0415, 0.2969, 1.5156]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4844, 1.6016, 1.0312, -0.0574],
[ 5.5625, -1.6875, -0.2480, 0.9062],
[ 3.3906, -0.5938, -0.1328, 0.5938],
...,
[ 3.8750, -4.4688, -0.5977, -4.5625],
[ 0.4629, 0.9805, 0.0552, 2.4062],
[-0.2451, -0.0415, 0.2969, 1.5156]], requires_grad=True)
2024-10-08 15:06:57,588 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4688, 1.5391, 0.9531, -0.0732],
[ 5.5938, -1.6484, -0.1216, 0.8516],
[ 3.4688, -0.5742, -0.0835, 0.5898],
...,
[ 3.6406, -4.4062, -0.6289, -4.5000],
[ 0.4336, 1.0156, 0.1025, 2.3906],
[-0.1099, -0.1147, 0.2930, 1.4453]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4688, 1.5391, 0.9531, -0.0732],
[ 5.5938, -1.6484, -0.1216, 0.8516],
[ 3.4688, -0.5742, -0.0835, 0.5898],
...,
[ 3.6406, -4.4062, -0.6289, -4.5000],
[ 0.4336, 1.0156, 0.1025, 2.3906],
[-0.1099, -0.1147, 0.2930, 1.4453]], requires_grad=True)
2024-10-08 15:06:57,851 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4375e+00, 1.4766e+00, 8.8672e-01, -8.5938e-02],
[ 5.5938e+00, -1.6094e+00, -1.0010e-02, 7.9297e-01],
[ 3.5156e+00, -5.6641e-01, -5.2246e-02, 5.8203e-01],
...,
[ 3.4219e+00, -4.3125e+00, -6.1719e-01, -4.4062e+00],
[ 3.9648e-01, 1.0078e+00, 1.0352e-01, 2.3594e+00],
[-5.2795e-03, -2.1875e-01, 2.4707e-01, 1.3750e+00]],
requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.4375e+00, 1.4766e+00, 8.8672e-01, -8.5938e-02],
[ 5.5938e+00, -1.6094e+00, -1.0010e-02, 7.9297e-01],
[ 3.5156e+00, -5.6641e-01, -5.2246e-02, 5.8203e-01],
...,
[ 3.4219e+00, -4.3125e+00, -6.1719e-01, -4.4062e+00],
[ 3.9648e-01, 1.0078e+00, 1.0352e-01, 2.3594e+00],
[-5.2795e-03, -2.1875e-01, 2.4707e-01, 1.3750e+00]],
requires_grad=True)
2024-10-08 15:06:58,113 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3906, 1.4297, 0.8320, -0.0928],
[ 5.5938, -1.6250, 0.0184, 0.7383],
[ 3.5469, -0.5859, -0.0554, 0.5703],
...,
[ 3.2188, -4.1562, -0.5391, -4.3125],
[ 0.3574, 0.9688, 0.0723, 2.3281],
[ 0.0806, -0.3359, 0.1777, 1.3125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3906, 1.4297, 0.8320, -0.0928],
[ 5.5938, -1.6250, 0.0184, 0.7383],
[ 3.5469, -0.5859, -0.0554, 0.5703],
...,
[ 3.2188, -4.1562, -0.5391, -4.3125],
[ 0.3574, 0.9688, 0.0723, 2.3281],
[ 0.0806, -0.3359, 0.1777, 1.3125]], requires_grad=True)
2024-10-08 15:06:58,365 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3281, 1.3750, 0.7656, -0.1055],
[ 5.5312, -1.5469, 0.1416, 0.7031],
[ 3.5625, -0.5938, -0.0508, 0.5625],
...,
[ 3.0938, -4.0625, -0.5391, -4.2188],
[ 0.2891, 0.9805, 0.0889, 2.3125],
[ 0.1226, -0.3770, 0.1719, 1.2578]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.3281, 1.3750, 0.7656, -0.1055],
[ 5.5312, -1.5469, 0.1416, 0.7031],
[ 3.5625, -0.5938, -0.0508, 0.5625],
...,
[ 3.0938, -4.0625, -0.5391, -4.2188],
[ 0.2891, 0.9805, 0.0889, 2.3125],
[ 0.1226, -0.3770, 0.1719, 1.2578]], requires_grad=True)
2024-10-08 15:06:58,623 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.2500, 1.2734, 0.6641, -0.1387],
[ 5.3750, -1.3203, 0.4023, 0.7109],
[ 3.5312, -0.5664, -0.0177, 0.5625],
...,
[ 3.0312, -4.0625, -0.6250, -4.1562],
[ 0.1865, 1.0391, 0.1543, 2.3125],
[ 0.1147, -0.3340, 0.2324, 1.2266]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.2500, 1.2734, 0.6641, -0.1387],
[ 5.3750, -1.3203, 0.4023, 0.7109],
[ 3.5312, -0.5664, -0.0177, 0.5625],
...,
[ 3.0312, -4.0625, -0.6250, -4.1562],
[ 0.1865, 1.0391, 0.1543, 2.3125],
[ 0.1147, -0.3340, 0.2324, 1.2266]], requires_grad=True)
2024-10-08 15:06:58,772 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1875, 1.2109, 0.6016, -0.1553],
[ 5.2188, -1.1562, 0.5977, 0.7031],
[ 3.5156, -0.5742, -0.0150, 0.5547],
...,
[ 2.9375, -3.9844, -0.6484, -4.0625],
[ 0.1001, 1.0625, 0.1895, 2.2969],
[ 0.1226, -0.3691, 0.2285, 1.1719]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1875, 1.2109, 0.6016, -0.1553],
[ 5.2188, -1.1562, 0.5977, 0.7031],
[ 3.5156, -0.5742, -0.0150, 0.5547],
...,
[ 2.9375, -3.9844, -0.6484, -4.0625],
[ 0.1001, 1.0625, 0.1895, 2.2969],
[ 0.1226, -0.3691, 0.2285, 1.1719]], requires_grad=True)
2024-10-08 15:06:58,936 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1406, 1.1719, 0.5586, -0.1660],
[ 5.0938, -1.0703, 0.7148, 0.6797],
[ 3.4844, -0.5898, -0.0205, 0.5391],
...,
[ 2.8125, -3.7969, -0.5820, -3.9531],
[ 0.0601, 0.9805, 0.1445, 2.2500],
[ 0.1377, -0.4629, 0.1807, 1.1094]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1406, 1.1719, 0.5586, -0.1660],
[ 5.0938, -1.0703, 0.7148, 0.6797],
[ 3.4844, -0.5898, -0.0205, 0.5391],
...,
[ 2.8125, -3.7969, -0.5820, -3.9531],
[ 0.0601, 0.9805, 0.1445, 2.2500],
[ 0.1377, -0.4629, 0.1807, 1.1094]], requires_grad=True)
2024-10-08 15:06:59,085 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1875, 1.2578, 0.5859, -0.1230],
[ 5.0000, -1.0703, 0.7656, 0.6328],
[ 3.5156, -0.6719, -0.0698, 0.4961],
...,
[ 2.6562, -3.5625, -0.4824, -3.8125],
[ 0.0420, 0.8594, 0.0801, 2.1719],
[ 0.1611, -0.5625, 0.1279, 1.0469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1875, 1.2578, 0.5859, -0.1230],
[ 5.0000, -1.0703, 0.7656, 0.6328],
[ 3.5156, -0.6719, -0.0698, 0.4961],
...,
[ 2.6562, -3.5625, -0.4824, -3.8125],
[ 0.0420, 0.8594, 0.0801, 2.1719],
[ 0.1611, -0.5625, 0.1279, 1.0469]], requires_grad=True)
2024-10-08 15:06:59,349 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.2031e+00, 1.2891e+00, 5.9375e-01, -1.1426e-01],
[ 4.8750e+00, -1.0234e+00, 8.3203e-01, 6.1328e-01],
[ 3.5469e+00, -7.4219e-01, -1.0986e-01, 4.6289e-01],
...,
[ 2.5156e+00, -3.3438e+00, -3.9062e-01, -3.6875e+00],
[ 3.5858e-03, 7.6953e-01, 3.0029e-02, 2.1094e+00],
[ 1.7969e-01, -6.3672e-01, 8.7402e-02, 9.9609e-01]],
requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.2031e+00, 1.2891e+00, 5.9375e-01, -1.1426e-01],
[ 4.8750e+00, -1.0234e+00, 8.3203e-01, 6.1328e-01],
[ 3.5469e+00, -7.4219e-01, -1.0986e-01, 4.6289e-01],
...,
[ 2.5156e+00, -3.3438e+00, -3.9062e-01, -3.6875e+00],
[ 3.5858e-03, 7.6953e-01, 3.0029e-02, 2.1094e+00],
[ 1.7969e-01, -6.3672e-01, 8.7402e-02, 9.9609e-01]],
requires_grad=True)
2024-10-08 15:06:59,608 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1250, 1.2578, 0.5742, -0.1484],
[ 4.5938, -0.7383, 0.9844, 0.7227],
[ 3.5312, -0.7578, -0.1289, 0.4648],
...,
[ 2.6406, -3.3906, -0.4004, -3.6875],
[-0.2197, 0.8828, 0.0549, 2.1562],
[ 0.1348, -0.5469, 0.1025, 1.0469]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-3.1250, 1.2578, 0.5742, -0.1484],
[ 4.5938, -0.7383, 0.9844, 0.7227],
[ 3.5312, -0.7578, -0.1289, 0.4648],
...,
[ 2.6406, -3.3906, -0.4004, -3.6875],
[-0.2197, 0.8828, 0.0549, 2.1562],
[ 0.1348, -0.5469, 0.1025, 1.0469]], requires_grad=True)
2024-10-08 15:06:59,865 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.9844, 1.1719, 0.5430, -0.2227],
[ 4.2812, -0.3809, 1.1484, 0.8750],
[ 3.4531, -0.7266, -0.1318, 0.4961],
...,
[ 2.7969, -3.4844, -0.4316, -3.7188],
[-0.4316, 0.9922, 0.0806, 2.2031],
[ 0.0654, -0.4180, 0.1289, 1.1172]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.9844, 1.1719, 0.5430, -0.2227],
[ 4.2812, -0.3809, 1.1484, 0.8750],
[ 3.4531, -0.7266, -0.1318, 0.4961],
...,
[ 2.7969, -3.4844, -0.4316, -3.7188],
[-0.4316, 0.9922, 0.0806, 2.2031],
[ 0.0654, -0.4180, 0.1289, 1.1172]], requires_grad=True)
2024-10-08 15:07:00,021 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.8750, 1.1016, 0.5156, -0.2871],
[ 4.0312, -0.1226, 1.2734, 0.9805],
[ 3.4219, -0.7266, -0.1416, 0.5039],
...,
[ 2.8750, -3.5000, -0.4453, -3.7188],
[-0.5156, 1.0000, 0.0825, 2.2031],
[ 0.0276, -0.3398, 0.1436, 1.1641]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.8750, 1.1016, 0.5156, -0.2871],
[ 4.0312, -0.1226, 1.2734, 0.9805],
[ 3.4219, -0.7266, -0.1416, 0.5039],
...,
[ 2.8750, -3.5000, -0.4453, -3.7188],
[-0.5156, 1.0000, 0.0825, 2.2031],
[ 0.0276, -0.3398, 0.1436, 1.1641]], requires_grad=True)
2024-10-08 15:07:00,272 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.6875, 1.0156, 0.4844, -0.3418],
[ 3.7969, 0.0942, 1.3750, 1.0625],
[ 3.5156, -0.8008, -0.1670, 0.4766],
...,
[ 2.6094, -3.2969, -0.4062, -3.6406],
[-0.3848, 0.8555, 0.0520, 2.1406],
[ 0.0923, -0.3457, 0.1426, 1.1797]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.6875, 1.0156, 0.4844, -0.3418],
[ 3.7969, 0.0942, 1.3750, 1.0625],
[ 3.5156, -0.8008, -0.1670, 0.4766],
...,
[ 2.6094, -3.2969, -0.4062, -3.6406],
[-0.3848, 0.8555, 0.0520, 2.1406],
[ 0.0923, -0.3457, 0.1426, 1.1797]], requires_grad=True)
2024-10-08 15:07:00,526 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4844, 0.9453, 0.4629, -0.3613],
[ 3.5469, 0.3223, 1.4688, 1.1406],
[ 3.4688, -0.7773, -0.1680, 0.4980],
...,
[ 2.6094, -3.2500, -0.4004, -3.5938],
[-0.4258, 0.8164, 0.0420, 2.0938],
[ 0.0742, -0.2236, 0.1680, 1.2500]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.4844, 0.9453, 0.4629, -0.3613],
[ 3.5469, 0.3223, 1.4688, 1.1406],
[ 3.4688, -0.7773, -0.1680, 0.4980],
...,
[ 2.6094, -3.2500, -0.4004, -3.5938],
[-0.4258, 0.8164, 0.0420, 2.0938],
[ 0.0742, -0.2236, 0.1680, 1.2500]], requires_grad=True)
2024-10-08 15:07:00,782 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.2656, 0.8008, 0.4199, -0.4473],
[ 3.2812, 0.5703, 1.5547, 1.2344],
[ 3.3594, -0.7109, -0.1582, 0.5352],
...,
[ 2.6719, -3.2500, -0.4062, -3.5469],
[-0.5234, 0.8633, 0.0530, 2.0781],
[ 0.0292, -0.0913, 0.1934, 1.3125]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-2.2656, 0.8008, 0.4199, -0.4473],
[ 3.2812, 0.5703, 1.5547, 1.2344],
[ 3.3594, -0.7109, -0.1582, 0.5352],
...,
[ 2.6719, -3.2500, -0.4062, -3.5469],
[-0.5234, 0.8633, 0.0530, 2.0781],
[ 0.0292, -0.0913, 0.1934, 1.3125]], requires_grad=True)
2024-10-08 15:07:01,043 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.9531, 0.6406, 0.3770, -0.5117],
[ 3.2031, 0.6797, 1.6016, 1.3047],
[ 3.2812, -0.6523, -0.1494, 0.5703],
...,
[ 2.3906, -3.0469, -0.3652, -3.4688],
[-0.4629, 0.8008, 0.0393, 2.0469],
[ 0.0435, -0.0342, 0.2021, 1.3516]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.9531, 0.6406, 0.3770, -0.5117],
[ 3.2031, 0.6797, 1.6016, 1.3047],
[ 3.2812, -0.6523, -0.1494, 0.5703],
...,
[ 2.3906, -3.0469, -0.3652, -3.4688],
[-0.4629, 0.8008, 0.0393, 2.0469],
[ 0.0435, -0.0342, 0.2021, 1.3516]], requires_grad=True)
2024-10-08 15:07:01,202 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.6562, 0.4961, 0.3379, -0.5625],
[ 3.1094, 0.7969, 1.6484, 1.3672],
[ 3.1875, -0.5898, -0.1387, 0.6016],
...,
[ 2.1562, -2.9062, -0.3379, -3.4062],
[-0.4199, 0.7578, 0.0297, 2.0156],
[ 0.0322, 0.0698, 0.2217, 1.3984]], requires_grad=True)
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - LOG: Parameter containing:
tensor([[-1.6562, 0.4961, 0.3379, -0.5625],
[ 3.1094, 0.7969, 1.6484, 1.3672],
[ 3.1875, -0.5898, -0.1387, 0.6016],
...,
[ 2.1562, -2.9062, -0.3379, -3.4062],
[-0.4199, 0.7578, 0.0297, 2.0156],
[ 0.0322, 0.0698, 0.2217, 1.3984]], requires_grad=True)
2024-10-08 15:07:01,392 a61583b9-75eb-4f84-b103-dd6c1b3ba32a - COMPLETED: Your job has been completed.
INFO:nnsight_remote:a61583b9-75eb-4f84-b103-dd6c1b3ba32a - COMPLETED: Your job has been completed.
Downloading result: 100%|██████████| 911k/911k [00:00<00:00, 2.31MB/s]
[ ]:
print(model)
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(128256, 8192)
(layers): ModuleList(
(0-79): 80 x LlamaDecoderLayer(
(self_attn): LlamaSdpaAttention(
(q_proj): Linear(in_features=8192, out_features=8192, bias=False)
(k_proj): Linear(in_features=8192, out_features=1024, bias=False)
(v_proj): Linear(in_features=8192, out_features=1024, bias=False)
(o_proj): Linear(in_features=8192, out_features=8192, bias=False)
(rotary_emb): LlamaRotaryEmbedding()
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=8192, out_features=28672, bias=False)
(up_proj): Linear(in_features=8192, out_features=28672, bias=False)
(down_proj): Linear(in_features=28672, out_features=8192, bias=False)
(act_fn): SiLU()
)
(input_layernorm): LlamaRMSNorm((8192,), eps=1e-05)
(post_attention_layernorm): LlamaRMSNorm((8192,), eps=1e-05)
)
)
(norm): LlamaRMSNorm((8192,), eps=1e-05)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=8192, out_features=128256, bias=False)
(generator): WrapperModule()
)
In addition to the weights changing, we know the LoRA has been applied because there is a difference in the model’s architecture. The 11th block of the model no longer has the standard MLP layer and instead contains the LoRA.
Now it is time to test out whether our fine tuned model is able to predict the sentiment of a given sentence.
[ ]:
# With lora. Will output "negative".
with model.generate("I'm upset", remote=True) as generator:
lora()
out = model.lm_head.output.save()
# The model outputs the sentiment as tokens first.
token_ids = out.argmax(dim=-1)
# Convert the tokens to either positive or negative
count_positive = (token_ids == 1).sum().item()
count_negative = (token_ids == 0).sum().item()
# Determine the overall sentiment of the entire sentence
if count_positive > count_negative:
print("\nPrediction with LoRA: Positive\n")
else:
print("\nPrediction with LoRA: Negative\n")
# Then without. It will try to complete the sentence rather than output the
# sentiment analysis.
with model.generate("I'm upset", remote=True) as generator:
out = model.lm_head.output.save()
print("\nPrediction without LoRA:", model.tokenizer.decode(out.argmax(dim=-1)[0]))
2024-10-08 15:16:19,547 1e738b58-e05d-47f9-93c4-fb9ae84602b9 - RECEIVED: Your job has been received and is waiting approval.
INFO:nnsight_remote:1e738b58-e05d-47f9-93c4-fb9ae84602b9 - RECEIVED: Your job has been received and is waiting approval.
2024-10-08 15:16:19,586 1e738b58-e05d-47f9-93c4-fb9ae84602b9 - RUNNING: Your job has started running.
INFO:nnsight_remote:1e738b58-e05d-47f9-93c4-fb9ae84602b9 - RUNNING: Your job has started running.
2024-10-08 15:16:19,598 1e738b58-e05d-47f9-93c4-fb9ae84602b9 - APPROVED: Your job was approved and is waiting to be run.
INFO:nnsight_remote:1e738b58-e05d-47f9-93c4-fb9ae84602b9 - APPROVED: Your job was approved and is waiting to be run.
2024-10-08 15:16:20,109 1e738b58-e05d-47f9-93c4-fb9ae84602b9 - COMPLETED: Your job has been completed.
INFO:nnsight_remote:1e738b58-e05d-47f9-93c4-fb9ae84602b9 - COMPLETED: Your job has been completed.
Downloading result: 100%|██████████| 1.03M/1.03M [00:00<00:00, 1.98MB/s]
Prediction with LoRA: Negative
2024-10-08 15:16:22,933 1ad601ee-b03b-4e6c-9f43-6dcd3cc9a02f - RECEIVED: Your job has been received and is waiting approval.
INFO:nnsight_remote:1ad601ee-b03b-4e6c-9f43-6dcd3cc9a02f - RECEIVED: Your job has been received and is waiting approval.
2024-10-08 15:16:25,291 1ad601ee-b03b-4e6c-9f43-6dcd3cc9a02f - APPROVED: Your job was approved and is waiting to be run.
INFO:nnsight_remote:1ad601ee-b03b-4e6c-9f43-6dcd3cc9a02f - APPROVED: Your job was approved and is waiting to be run.
2024-10-08 15:16:25,302 1ad601ee-b03b-4e6c-9f43-6dcd3cc9a02f - RUNNING: Your job has started running.
INFO:nnsight_remote:1ad601ee-b03b-4e6c-9f43-6dcd3cc9a02f - RUNNING: Your job has started running.
2024-10-08 15:16:25,478 1ad601ee-b03b-4e6c-9f43-6dcd3cc9a02f - COMPLETED: Your job has been completed.
INFO:nnsight_remote:1ad601ee-b03b-4e6c-9f43-6dcd3cc9a02f - COMPLETED: Your job has been completed.
Downloading result: 100%|██████████| 1.03M/1.03M [00:00<00:00, 2.59MB/s]
Prediction without LoRA: Question have a that