End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +1970 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: orca-agentinstruct-1M-v1-cleaned
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# orca-agentinstruct-1M-v1-cleaned
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.4721
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: orca-agentinstruct-1M-v1-cleaned
|
|
|
|
| 16 |
|
| 17 |
# orca-agentinstruct-1M-v1-cleaned
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlabonne/orca-agentinstruct-1M-v1-cleaned dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.4721
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9983489268024215,
|
| 3 |
+
"eval_loss": 0.47213879227638245,
|
| 4 |
+
"eval_runtime": 156.8324,
|
| 5 |
+
"eval_samples_per_second": 156.033,
|
| 6 |
+
"eval_steps_per_second": 0.612,
|
| 7 |
+
"total_flos": 4561963937955840.0,
|
| 8 |
+
"train_loss": 0.44294929530652083,
|
| 9 |
+
"train_runtime": 23449.9729,
|
| 10 |
+
"train_samples_per_second": 59.48,
|
| 11 |
+
"train_steps_per_second": 0.116
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9983489268024215,
|
| 3 |
+
"eval_loss": 0.47213879227638245,
|
| 4 |
+
"eval_runtime": 156.8324,
|
| 5 |
+
"eval_samples_per_second": 156.033,
|
| 6 |
+
"eval_steps_per_second": 0.612
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9983489268024215,
|
| 3 |
+
"total_flos": 4561963937955840.0,
|
| 4 |
+
"train_loss": 0.44294929530652083,
|
| 5 |
+
"train_runtime": 23449.9729,
|
| 6 |
+
"train_samples_per_second": 59.48,
|
| 7 |
+
"train_steps_per_second": 0.116
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1970 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9983489268024215,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2724,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01100715465052284,
|
| 13 |
+
"grad_norm": 8.068985135850538,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7005,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02201430930104568,
|
| 20 |
+
"grad_norm": 1.345068090353878,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.6377,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03302146395156852,
|
| 27 |
+
"grad_norm": 0.904010640164903,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6063,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04402861860209136,
|
| 34 |
+
"grad_norm": 1.0016711496058677,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.5969,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0550357732526142,
|
| 41 |
+
"grad_norm": 0.9379200618665713,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.5714,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06604292790313704,
|
| 48 |
+
"grad_norm": 0.6938901282332245,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.5648,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07705008255365987,
|
| 55 |
+
"grad_norm": 1.2132887620233943,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.5611,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08805723720418272,
|
| 62 |
+
"grad_norm": 0.6871985890249172,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.5512,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09906439185470556,
|
| 69 |
+
"grad_norm": 0.5847039722347717,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.5485,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1100715465052284,
|
| 76 |
+
"grad_norm": 0.7554239910712166,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.5509,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.12107870115575124,
|
| 83 |
+
"grad_norm": 0.66407741684268,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.5408,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.13208585580627408,
|
| 90 |
+
"grad_norm": 0.8828744973826606,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.5454,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14309301045679693,
|
| 97 |
+
"grad_norm": 0.8332887833735565,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.547,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.15410016510731975,
|
| 104 |
+
"grad_norm": 0.589582911422936,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.5355,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1651073197578426,
|
| 111 |
+
"grad_norm": 0.5752650409924749,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.5401,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.17611447440836545,
|
| 118 |
+
"grad_norm": 0.6510988159474992,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.5382,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.18712162905888827,
|
| 125 |
+
"grad_norm": 0.6600162733921413,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.5375,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.19812878370941112,
|
| 132 |
+
"grad_norm": 0.7680493758340888,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.5293,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.20913593835993396,
|
| 139 |
+
"grad_norm": 0.5886772247201477,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.529,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2201430930104568,
|
| 146 |
+
"grad_norm": 0.9873312548126073,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.5374,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.23115024766097964,
|
| 153 |
+
"grad_norm": 0.6597424005720035,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.5244,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.24215740231150248,
|
| 160 |
+
"grad_norm": 0.6487240352856705,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.5239,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.25316455696202533,
|
| 167 |
+
"grad_norm": 0.5849183815528889,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.5208,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.26417171161254815,
|
| 174 |
+
"grad_norm": 0.7002932795368584,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.5235,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.275178866263071,
|
| 181 |
+
"grad_norm": 0.7692057600346355,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.5208,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.28618602091359385,
|
| 188 |
+
"grad_norm": 0.6479188055510907,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.5221,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2971931755641167,
|
| 195 |
+
"grad_norm": 0.5960709917895178,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.5208,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3082003302146395,
|
| 202 |
+
"grad_norm": 0.6642753446042425,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.5197,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.31920748486516237,
|
| 209 |
+
"grad_norm": 0.5612612572776104,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.5184,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3302146395156852,
|
| 216 |
+
"grad_norm": 0.6050955649607845,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.5212,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.341221794166208,
|
| 223 |
+
"grad_norm": 0.6083727153184473,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.5184,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3522289488167309,
|
| 230 |
+
"grad_norm": 0.5945638816363161,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.5117,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3632361034672537,
|
| 237 |
+
"grad_norm": 0.5788925707542152,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.5168,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.37424325811777653,
|
| 244 |
+
"grad_norm": 0.5651877110220476,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.5112,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3852504127682994,
|
| 251 |
+
"grad_norm": 0.5903776050613534,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.5093,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.39625756741882223,
|
| 258 |
+
"grad_norm": 0.6395433132948327,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.5089,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.40726472206934505,
|
| 265 |
+
"grad_norm": 0.6433507142958254,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.5119,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.41827187671986793,
|
| 272 |
+
"grad_norm": 0.8112524575258614,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.5114,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.42927903137039075,
|
| 279 |
+
"grad_norm": 0.5590784475229202,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.5099,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4402861860209136,
|
| 286 |
+
"grad_norm": 0.5742385149846626,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.5052,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.45129334067143645,
|
| 293 |
+
"grad_norm": 0.5628215738544207,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.5101,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.46230049532195927,
|
| 300 |
+
"grad_norm": 0.6019602301994744,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.5052,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4733076499724821,
|
| 307 |
+
"grad_norm": 0.6953045343066634,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.5071,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.48431480462300497,
|
| 314 |
+
"grad_norm": 0.5819593216177834,
|
| 315 |
+
"learning_rate": 5e-06,
|
| 316 |
+
"loss": 0.5087,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.4953219592735278,
|
| 321 |
+
"grad_norm": 0.6411981453679727,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.5037,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5063291139240507,
|
| 328 |
+
"grad_norm": 0.6349579201005676,
|
| 329 |
+
"learning_rate": 5e-06,
|
| 330 |
+
"loss": 0.5017,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5173362685745735,
|
| 335 |
+
"grad_norm": 0.5646584437790421,
|
| 336 |
+
"learning_rate": 5e-06,
|
| 337 |
+
"loss": 0.5027,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5283434232250963,
|
| 342 |
+
"grad_norm": 0.674711086918845,
|
| 343 |
+
"learning_rate": 5e-06,
|
| 344 |
+
"loss": 0.4956,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5393505778756191,
|
| 349 |
+
"grad_norm": 0.5072994063381644,
|
| 350 |
+
"learning_rate": 5e-06,
|
| 351 |
+
"loss": 0.508,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.550357732526142,
|
| 356 |
+
"grad_norm": 0.585416024213119,
|
| 357 |
+
"learning_rate": 5e-06,
|
| 358 |
+
"loss": 0.5055,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5613648871766649,
|
| 363 |
+
"grad_norm": 0.5530035514034926,
|
| 364 |
+
"learning_rate": 5e-06,
|
| 365 |
+
"loss": 0.5039,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5723720418271877,
|
| 370 |
+
"grad_norm": 0.5538832120092045,
|
| 371 |
+
"learning_rate": 5e-06,
|
| 372 |
+
"loss": 0.4977,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5833791964777105,
|
| 377 |
+
"grad_norm": 0.6201922984553575,
|
| 378 |
+
"learning_rate": 5e-06,
|
| 379 |
+
"loss": 0.4998,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5943863511282333,
|
| 384 |
+
"grad_norm": 0.6430291554797398,
|
| 385 |
+
"learning_rate": 5e-06,
|
| 386 |
+
"loss": 0.5056,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6053935057787562,
|
| 391 |
+
"grad_norm": 0.6087664959789294,
|
| 392 |
+
"learning_rate": 5e-06,
|
| 393 |
+
"loss": 0.4987,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.616400660429279,
|
| 398 |
+
"grad_norm": 0.5870342890959941,
|
| 399 |
+
"learning_rate": 5e-06,
|
| 400 |
+
"loss": 0.501,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6274078150798019,
|
| 405 |
+
"grad_norm": 0.5991431157137032,
|
| 406 |
+
"learning_rate": 5e-06,
|
| 407 |
+
"loss": 0.4962,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6384149697303247,
|
| 412 |
+
"grad_norm": 0.5967606556151732,
|
| 413 |
+
"learning_rate": 5e-06,
|
| 414 |
+
"loss": 0.4999,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6494221243808476,
|
| 419 |
+
"grad_norm": 0.5729038172611738,
|
| 420 |
+
"learning_rate": 5e-06,
|
| 421 |
+
"loss": 0.5039,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6604292790313704,
|
| 426 |
+
"grad_norm": 0.5505607805830717,
|
| 427 |
+
"learning_rate": 5e-06,
|
| 428 |
+
"loss": 0.4997,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6714364336818932,
|
| 433 |
+
"grad_norm": 0.5816855812426598,
|
| 434 |
+
"learning_rate": 5e-06,
|
| 435 |
+
"loss": 0.4953,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.682443588332416,
|
| 440 |
+
"grad_norm": 0.5488625944674516,
|
| 441 |
+
"learning_rate": 5e-06,
|
| 442 |
+
"loss": 0.492,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.693450742982939,
|
| 447 |
+
"grad_norm": 0.5614761187121621,
|
| 448 |
+
"learning_rate": 5e-06,
|
| 449 |
+
"loss": 0.4953,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7044578976334618,
|
| 454 |
+
"grad_norm": 0.5349325221018545,
|
| 455 |
+
"learning_rate": 5e-06,
|
| 456 |
+
"loss": 0.4889,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7154650522839846,
|
| 461 |
+
"grad_norm": 0.6719016887422193,
|
| 462 |
+
"learning_rate": 5e-06,
|
| 463 |
+
"loss": 0.5007,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7264722069345074,
|
| 468 |
+
"grad_norm": 0.6391959462190592,
|
| 469 |
+
"learning_rate": 5e-06,
|
| 470 |
+
"loss": 0.4938,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7374793615850302,
|
| 475 |
+
"grad_norm": 0.582953953743529,
|
| 476 |
+
"learning_rate": 5e-06,
|
| 477 |
+
"loss": 0.4999,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7484865162355531,
|
| 482 |
+
"grad_norm": 0.706306920990327,
|
| 483 |
+
"learning_rate": 5e-06,
|
| 484 |
+
"loss": 0.502,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.759493670886076,
|
| 489 |
+
"grad_norm": 0.5848686111106695,
|
| 490 |
+
"learning_rate": 5e-06,
|
| 491 |
+
"loss": 0.4967,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7705008255365988,
|
| 496 |
+
"grad_norm": 0.6388534941572848,
|
| 497 |
+
"learning_rate": 5e-06,
|
| 498 |
+
"loss": 0.4927,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7815079801871216,
|
| 503 |
+
"grad_norm": 0.502841130639183,
|
| 504 |
+
"learning_rate": 5e-06,
|
| 505 |
+
"loss": 0.4896,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7925151348376445,
|
| 510 |
+
"grad_norm": 0.5461802758885927,
|
| 511 |
+
"learning_rate": 5e-06,
|
| 512 |
+
"loss": 0.4897,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8035222894881673,
|
| 517 |
+
"grad_norm": 0.5337214956421172,
|
| 518 |
+
"learning_rate": 5e-06,
|
| 519 |
+
"loss": 0.488,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8145294441386901,
|
| 524 |
+
"grad_norm": 0.5479459981678669,
|
| 525 |
+
"learning_rate": 5e-06,
|
| 526 |
+
"loss": 0.4934,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.825536598789213,
|
| 531 |
+
"grad_norm": 0.518082392504643,
|
| 532 |
+
"learning_rate": 5e-06,
|
| 533 |
+
"loss": 0.4892,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8365437534397359,
|
| 538 |
+
"grad_norm": 0.5077982160853911,
|
| 539 |
+
"learning_rate": 5e-06,
|
| 540 |
+
"loss": 0.479,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8475509080902587,
|
| 545 |
+
"grad_norm": 0.55919091108616,
|
| 546 |
+
"learning_rate": 5e-06,
|
| 547 |
+
"loss": 0.4918,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8585580627407815,
|
| 552 |
+
"grad_norm": 0.5588406329671567,
|
| 553 |
+
"learning_rate": 5e-06,
|
| 554 |
+
"loss": 0.4936,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8695652173913043,
|
| 559 |
+
"grad_norm": 0.7100197464890179,
|
| 560 |
+
"learning_rate": 5e-06,
|
| 561 |
+
"loss": 0.4912,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8805723720418271,
|
| 566 |
+
"grad_norm": 0.6024300909723488,
|
| 567 |
+
"learning_rate": 5e-06,
|
| 568 |
+
"loss": 0.4874,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8915795266923501,
|
| 573 |
+
"grad_norm": 0.54622459399125,
|
| 574 |
+
"learning_rate": 5e-06,
|
| 575 |
+
"loss": 0.4898,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9025866813428729,
|
| 580 |
+
"grad_norm": 0.5233736919206922,
|
| 581 |
+
"learning_rate": 5e-06,
|
| 582 |
+
"loss": 0.4871,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9135938359933957,
|
| 587 |
+
"grad_norm": 0.5592995369334787,
|
| 588 |
+
"learning_rate": 5e-06,
|
| 589 |
+
"loss": 0.4874,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9246009906439185,
|
| 594 |
+
"grad_norm": 0.5287807518909434,
|
| 595 |
+
"learning_rate": 5e-06,
|
| 596 |
+
"loss": 0.4833,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9356081452944414,
|
| 601 |
+
"grad_norm": 0.5665869814810643,
|
| 602 |
+
"learning_rate": 5e-06,
|
| 603 |
+
"loss": 0.4854,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9466152999449642,
|
| 608 |
+
"grad_norm": 0.6023708712875594,
|
| 609 |
+
"learning_rate": 5e-06,
|
| 610 |
+
"loss": 0.4891,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9576224545954871,
|
| 615 |
+
"grad_norm": 0.6417033949225462,
|
| 616 |
+
"learning_rate": 5e-06,
|
| 617 |
+
"loss": 0.486,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.9686296092460099,
|
| 622 |
+
"grad_norm": 0.5609342094974721,
|
| 623 |
+
"learning_rate": 5e-06,
|
| 624 |
+
"loss": 0.4865,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.9796367638965328,
|
| 629 |
+
"grad_norm": 0.5141037922481443,
|
| 630 |
+
"learning_rate": 5e-06,
|
| 631 |
+
"loss": 0.487,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9906439185470556,
|
| 636 |
+
"grad_norm": 0.5249034479981126,
|
| 637 |
+
"learning_rate": 5e-06,
|
| 638 |
+
"loss": 0.4816,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9994496422674739,
|
| 643 |
+
"eval_loss": 0.4856513738632202,
|
| 644 |
+
"eval_runtime": 160.5131,
|
| 645 |
+
"eval_samples_per_second": 152.455,
|
| 646 |
+
"eval_steps_per_second": 0.598,
|
| 647 |
+
"step": 908
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.0016510731975785,
|
| 651 |
+
"grad_norm": 0.6956883866215322,
|
| 652 |
+
"learning_rate": 5e-06,
|
| 653 |
+
"loss": 0.481,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.0126582278481013,
|
| 658 |
+
"grad_norm": 0.6716400752129513,
|
| 659 |
+
"learning_rate": 5e-06,
|
| 660 |
+
"loss": 0.4391,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.0236653824986242,
|
| 665 |
+
"grad_norm": 0.6047593389115262,
|
| 666 |
+
"learning_rate": 5e-06,
|
| 667 |
+
"loss": 0.4375,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.034672537149147,
|
| 672 |
+
"grad_norm": 0.587176642351734,
|
| 673 |
+
"learning_rate": 5e-06,
|
| 674 |
+
"loss": 0.4384,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.0456796917996698,
|
| 679 |
+
"grad_norm": 0.6603546276646723,
|
| 680 |
+
"learning_rate": 5e-06,
|
| 681 |
+
"loss": 0.4369,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.0566868464501926,
|
| 686 |
+
"grad_norm": 0.6689012217240984,
|
| 687 |
+
"learning_rate": 5e-06,
|
| 688 |
+
"loss": 0.4355,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.0676940011007154,
|
| 693 |
+
"grad_norm": 0.7144569165196396,
|
| 694 |
+
"learning_rate": 5e-06,
|
| 695 |
+
"loss": 0.4355,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.0787011557512383,
|
| 700 |
+
"grad_norm": 0.599379629228571,
|
| 701 |
+
"learning_rate": 5e-06,
|
| 702 |
+
"loss": 0.438,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.089708310401761,
|
| 707 |
+
"grad_norm": 0.6661285634082297,
|
| 708 |
+
"learning_rate": 5e-06,
|
| 709 |
+
"loss": 0.4382,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.100715465052284,
|
| 714 |
+
"grad_norm": 0.5873001825359626,
|
| 715 |
+
"learning_rate": 5e-06,
|
| 716 |
+
"loss": 0.4402,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.1117226197028067,
|
| 721 |
+
"grad_norm": 0.5874126889355209,
|
| 722 |
+
"learning_rate": 5e-06,
|
| 723 |
+
"loss": 0.4369,
|
| 724 |
+
"step": 1010
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.1227297743533298,
|
| 728 |
+
"grad_norm": 0.5917778529211078,
|
| 729 |
+
"learning_rate": 5e-06,
|
| 730 |
+
"loss": 0.4343,
|
| 731 |
+
"step": 1020
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.1337369290038526,
|
| 735 |
+
"grad_norm": 0.663635902953046,
|
| 736 |
+
"learning_rate": 5e-06,
|
| 737 |
+
"loss": 0.4407,
|
| 738 |
+
"step": 1030
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.1447440836543754,
|
| 742 |
+
"grad_norm": 0.5893496665741478,
|
| 743 |
+
"learning_rate": 5e-06,
|
| 744 |
+
"loss": 0.438,
|
| 745 |
+
"step": 1040
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.1557512383048982,
|
| 749 |
+
"grad_norm": 0.5717519892394852,
|
| 750 |
+
"learning_rate": 5e-06,
|
| 751 |
+
"loss": 0.4382,
|
| 752 |
+
"step": 1050
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.166758392955421,
|
| 756 |
+
"grad_norm": 0.575957675659784,
|
| 757 |
+
"learning_rate": 5e-06,
|
| 758 |
+
"loss": 0.442,
|
| 759 |
+
"step": 1060
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.1777655476059439,
|
| 763 |
+
"grad_norm": 0.5392139913019496,
|
| 764 |
+
"learning_rate": 5e-06,
|
| 765 |
+
"loss": 0.4338,
|
| 766 |
+
"step": 1070
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.1887727022564667,
|
| 770 |
+
"grad_norm": 0.5544306944478229,
|
| 771 |
+
"learning_rate": 5e-06,
|
| 772 |
+
"loss": 0.435,
|
| 773 |
+
"step": 1080
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.1997798569069895,
|
| 777 |
+
"grad_norm": 0.5778227037188679,
|
| 778 |
+
"learning_rate": 5e-06,
|
| 779 |
+
"loss": 0.4422,
|
| 780 |
+
"step": 1090
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.2107870115575123,
|
| 784 |
+
"grad_norm": 0.641697858461983,
|
| 785 |
+
"learning_rate": 5e-06,
|
| 786 |
+
"loss": 0.4372,
|
| 787 |
+
"step": 1100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.2217941662080352,
|
| 791 |
+
"grad_norm": 0.5569895073916331,
|
| 792 |
+
"learning_rate": 5e-06,
|
| 793 |
+
"loss": 0.4321,
|
| 794 |
+
"step": 1110
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.232801320858558,
|
| 798 |
+
"grad_norm": 0.6241092113262656,
|
| 799 |
+
"learning_rate": 5e-06,
|
| 800 |
+
"loss": 0.439,
|
| 801 |
+
"step": 1120
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.243808475509081,
|
| 805 |
+
"grad_norm": 0.5943410374097372,
|
| 806 |
+
"learning_rate": 5e-06,
|
| 807 |
+
"loss": 0.4391,
|
| 808 |
+
"step": 1130
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.2548156301596038,
|
| 812 |
+
"grad_norm": 0.5836266123327419,
|
| 813 |
+
"learning_rate": 5e-06,
|
| 814 |
+
"loss": 0.4358,
|
| 815 |
+
"step": 1140
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.2658227848101267,
|
| 819 |
+
"grad_norm": 0.5894554462945597,
|
| 820 |
+
"learning_rate": 5e-06,
|
| 821 |
+
"loss": 0.4357,
|
| 822 |
+
"step": 1150
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.2768299394606495,
|
| 826 |
+
"grad_norm": 0.6101160325711262,
|
| 827 |
+
"learning_rate": 5e-06,
|
| 828 |
+
"loss": 0.4377,
|
| 829 |
+
"step": 1160
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.2878370941111723,
|
| 833 |
+
"grad_norm": 0.5499163190785714,
|
| 834 |
+
"learning_rate": 5e-06,
|
| 835 |
+
"loss": 0.4373,
|
| 836 |
+
"step": 1170
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.2988442487616951,
|
| 840 |
+
"grad_norm": 0.6570888233134892,
|
| 841 |
+
"learning_rate": 5e-06,
|
| 842 |
+
"loss": 0.4397,
|
| 843 |
+
"step": 1180
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.309851403412218,
|
| 847 |
+
"grad_norm": 0.5781370179708198,
|
| 848 |
+
"learning_rate": 5e-06,
|
| 849 |
+
"loss": 0.4317,
|
| 850 |
+
"step": 1190
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.3208585580627408,
|
| 854 |
+
"grad_norm": 0.5960093131033088,
|
| 855 |
+
"learning_rate": 5e-06,
|
| 856 |
+
"loss": 0.4388,
|
| 857 |
+
"step": 1200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.3318657127132636,
|
| 861 |
+
"grad_norm": 0.5319356526638459,
|
| 862 |
+
"learning_rate": 5e-06,
|
| 863 |
+
"loss": 0.4296,
|
| 864 |
+
"step": 1210
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.3428728673637864,
|
| 868 |
+
"grad_norm": 0.6078975655308353,
|
| 869 |
+
"learning_rate": 5e-06,
|
| 870 |
+
"loss": 0.4399,
|
| 871 |
+
"step": 1220
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.3538800220143092,
|
| 875 |
+
"grad_norm": 0.5734565496131863,
|
| 876 |
+
"learning_rate": 5e-06,
|
| 877 |
+
"loss": 0.4364,
|
| 878 |
+
"step": 1230
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.364887176664832,
|
| 882 |
+
"grad_norm": 0.5839075048236241,
|
| 883 |
+
"learning_rate": 5e-06,
|
| 884 |
+
"loss": 0.4379,
|
| 885 |
+
"step": 1240
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.3758943313153549,
|
| 889 |
+
"grad_norm": 0.522698955157226,
|
| 890 |
+
"learning_rate": 5e-06,
|
| 891 |
+
"loss": 0.4417,
|
| 892 |
+
"step": 1250
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.3869014859658777,
|
| 896 |
+
"grad_norm": 0.535233080984122,
|
| 897 |
+
"learning_rate": 5e-06,
|
| 898 |
+
"loss": 0.44,
|
| 899 |
+
"step": 1260
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.3979086406164005,
|
| 903 |
+
"grad_norm": 0.5712349249996552,
|
| 904 |
+
"learning_rate": 5e-06,
|
| 905 |
+
"loss": 0.438,
|
| 906 |
+
"step": 1270
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.4089157952669236,
|
| 910 |
+
"grad_norm": 0.6316823548805974,
|
| 911 |
+
"learning_rate": 5e-06,
|
| 912 |
+
"loss": 0.4354,
|
| 913 |
+
"step": 1280
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.4199229499174464,
|
| 917 |
+
"grad_norm": 0.5521497995059079,
|
| 918 |
+
"learning_rate": 5e-06,
|
| 919 |
+
"loss": 0.4364,
|
| 920 |
+
"step": 1290
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.4309301045679692,
|
| 924 |
+
"grad_norm": 0.5287580252903409,
|
| 925 |
+
"learning_rate": 5e-06,
|
| 926 |
+
"loss": 0.433,
|
| 927 |
+
"step": 1300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.441937259218492,
|
| 931 |
+
"grad_norm": 0.5402910458762741,
|
| 932 |
+
"learning_rate": 5e-06,
|
| 933 |
+
"loss": 0.4305,
|
| 934 |
+
"step": 1310
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.4529444138690149,
|
| 938 |
+
"grad_norm": 0.571274228135471,
|
| 939 |
+
"learning_rate": 5e-06,
|
| 940 |
+
"loss": 0.4372,
|
| 941 |
+
"step": 1320
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.4639515685195377,
|
| 945 |
+
"grad_norm": 0.5793180531222271,
|
| 946 |
+
"learning_rate": 5e-06,
|
| 947 |
+
"loss": 0.4317,
|
| 948 |
+
"step": 1330
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.4749587231700605,
|
| 952 |
+
"grad_norm": 0.5325510509092749,
|
| 953 |
+
"learning_rate": 5e-06,
|
| 954 |
+
"loss": 0.4393,
|
| 955 |
+
"step": 1340
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.4859658778205833,
|
| 959 |
+
"grad_norm": 0.594212182934655,
|
| 960 |
+
"learning_rate": 5e-06,
|
| 961 |
+
"loss": 0.4341,
|
| 962 |
+
"step": 1350
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.4969730324711064,
|
| 966 |
+
"grad_norm": 0.5712922063753643,
|
| 967 |
+
"learning_rate": 5e-06,
|
| 968 |
+
"loss": 0.4356,
|
| 969 |
+
"step": 1360
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.5079801871216292,
|
| 973 |
+
"grad_norm": 0.5274575368185872,
|
| 974 |
+
"learning_rate": 5e-06,
|
| 975 |
+
"loss": 0.4362,
|
| 976 |
+
"step": 1370
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.518987341772152,
|
| 980 |
+
"grad_norm": 0.5748764141955885,
|
| 981 |
+
"learning_rate": 5e-06,
|
| 982 |
+
"loss": 0.4382,
|
| 983 |
+
"step": 1380
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.5299944964226748,
|
| 987 |
+
"grad_norm": 0.5317801238843131,
|
| 988 |
+
"learning_rate": 5e-06,
|
| 989 |
+
"loss": 0.4273,
|
| 990 |
+
"step": 1390
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.5410016510731976,
|
| 994 |
+
"grad_norm": 0.551025561769828,
|
| 995 |
+
"learning_rate": 5e-06,
|
| 996 |
+
"loss": 0.4299,
|
| 997 |
+
"step": 1400
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.5520088057237205,
|
| 1001 |
+
"grad_norm": 0.5944333674783141,
|
| 1002 |
+
"learning_rate": 5e-06,
|
| 1003 |
+
"loss": 0.4341,
|
| 1004 |
+
"step": 1410
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.5630159603742433,
|
| 1008 |
+
"grad_norm": 0.5788961613724642,
|
| 1009 |
+
"learning_rate": 5e-06,
|
| 1010 |
+
"loss": 0.4365,
|
| 1011 |
+
"step": 1420
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.574023115024766,
|
| 1015 |
+
"grad_norm": 0.5966888415992487,
|
| 1016 |
+
"learning_rate": 5e-06,
|
| 1017 |
+
"loss": 0.4351,
|
| 1018 |
+
"step": 1430
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.585030269675289,
|
| 1022 |
+
"grad_norm": 0.6442673539124382,
|
| 1023 |
+
"learning_rate": 5e-06,
|
| 1024 |
+
"loss": 0.4331,
|
| 1025 |
+
"step": 1440
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.5960374243258117,
|
| 1029 |
+
"grad_norm": 0.5537070014925163,
|
| 1030 |
+
"learning_rate": 5e-06,
|
| 1031 |
+
"loss": 0.4292,
|
| 1032 |
+
"step": 1450
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.6070445789763346,
|
| 1036 |
+
"grad_norm": 0.5708459825871977,
|
| 1037 |
+
"learning_rate": 5e-06,
|
| 1038 |
+
"loss": 0.4366,
|
| 1039 |
+
"step": 1460
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.6180517336268574,
|
| 1043 |
+
"grad_norm": 0.6397589448051699,
|
| 1044 |
+
"learning_rate": 5e-06,
|
| 1045 |
+
"loss": 0.4361,
|
| 1046 |
+
"step": 1470
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.6290588882773802,
|
| 1050 |
+
"grad_norm": 0.5719729721108842,
|
| 1051 |
+
"learning_rate": 5e-06,
|
| 1052 |
+
"loss": 0.4308,
|
| 1053 |
+
"step": 1480
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.640066042927903,
|
| 1057 |
+
"grad_norm": 0.5856092164801038,
|
| 1058 |
+
"learning_rate": 5e-06,
|
| 1059 |
+
"loss": 0.4312,
|
| 1060 |
+
"step": 1490
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.6510731975784259,
|
| 1064 |
+
"grad_norm": 0.5381801632251061,
|
| 1065 |
+
"learning_rate": 5e-06,
|
| 1066 |
+
"loss": 0.4332,
|
| 1067 |
+
"step": 1500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.6620803522289487,
|
| 1071 |
+
"grad_norm": 0.5722118916397197,
|
| 1072 |
+
"learning_rate": 5e-06,
|
| 1073 |
+
"loss": 0.4329,
|
| 1074 |
+
"step": 1510
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.6730875068794715,
|
| 1078 |
+
"grad_norm": 0.522035618728827,
|
| 1079 |
+
"learning_rate": 5e-06,
|
| 1080 |
+
"loss": 0.4323,
|
| 1081 |
+
"step": 1520
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.6840946615299945,
|
| 1085 |
+
"grad_norm": 0.6205447482549835,
|
| 1086 |
+
"learning_rate": 5e-06,
|
| 1087 |
+
"loss": 0.4364,
|
| 1088 |
+
"step": 1530
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.6951018161805174,
|
| 1092 |
+
"grad_norm": 0.5443426263583215,
|
| 1093 |
+
"learning_rate": 5e-06,
|
| 1094 |
+
"loss": 0.4313,
|
| 1095 |
+
"step": 1540
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.7061089708310402,
|
| 1099 |
+
"grad_norm": 0.5386063701750604,
|
| 1100 |
+
"learning_rate": 5e-06,
|
| 1101 |
+
"loss": 0.4307,
|
| 1102 |
+
"step": 1550
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.717116125481563,
|
| 1106 |
+
"grad_norm": 0.6361585672978718,
|
| 1107 |
+
"learning_rate": 5e-06,
|
| 1108 |
+
"loss": 0.4353,
|
| 1109 |
+
"step": 1560
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.7281232801320858,
|
| 1113 |
+
"grad_norm": 0.6614840484986904,
|
| 1114 |
+
"learning_rate": 5e-06,
|
| 1115 |
+
"loss": 0.4328,
|
| 1116 |
+
"step": 1570
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.7391304347826086,
|
| 1120 |
+
"grad_norm": 0.570381119642231,
|
| 1121 |
+
"learning_rate": 5e-06,
|
| 1122 |
+
"loss": 0.4287,
|
| 1123 |
+
"step": 1580
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.7501375894331317,
|
| 1127 |
+
"grad_norm": 0.5090274244717806,
|
| 1128 |
+
"learning_rate": 5e-06,
|
| 1129 |
+
"loss": 0.4362,
|
| 1130 |
+
"step": 1590
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.7611447440836545,
|
| 1134 |
+
"grad_norm": 0.5446091771702728,
|
| 1135 |
+
"learning_rate": 5e-06,
|
| 1136 |
+
"loss": 0.4295,
|
| 1137 |
+
"step": 1600
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.7721518987341773,
|
| 1141 |
+
"grad_norm": 0.5647817172552334,
|
| 1142 |
+
"learning_rate": 5e-06,
|
| 1143 |
+
"loss": 0.4298,
|
| 1144 |
+
"step": 1610
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.7831590533847002,
|
| 1148 |
+
"grad_norm": 0.5140154798513348,
|
| 1149 |
+
"learning_rate": 5e-06,
|
| 1150 |
+
"loss": 0.4298,
|
| 1151 |
+
"step": 1620
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.794166208035223,
|
| 1155 |
+
"grad_norm": 0.5079001883970996,
|
| 1156 |
+
"learning_rate": 5e-06,
|
| 1157 |
+
"loss": 0.4317,
|
| 1158 |
+
"step": 1630
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.8051733626857458,
|
| 1162 |
+
"grad_norm": 0.5716780327717556,
|
| 1163 |
+
"learning_rate": 5e-06,
|
| 1164 |
+
"loss": 0.4335,
|
| 1165 |
+
"step": 1640
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.8161805173362686,
|
| 1169 |
+
"grad_norm": 0.5594834856156328,
|
| 1170 |
+
"learning_rate": 5e-06,
|
| 1171 |
+
"loss": 0.4369,
|
| 1172 |
+
"step": 1650
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.8271876719867914,
|
| 1176 |
+
"grad_norm": 0.5690421305195432,
|
| 1177 |
+
"learning_rate": 5e-06,
|
| 1178 |
+
"loss": 0.4372,
|
| 1179 |
+
"step": 1660
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.8381948266373143,
|
| 1183 |
+
"grad_norm": 0.5815766701653886,
|
| 1184 |
+
"learning_rate": 5e-06,
|
| 1185 |
+
"loss": 0.4268,
|
| 1186 |
+
"step": 1670
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.849201981287837,
|
| 1190 |
+
"grad_norm": 0.5370753144522138,
|
| 1191 |
+
"learning_rate": 5e-06,
|
| 1192 |
+
"loss": 0.4296,
|
| 1193 |
+
"step": 1680
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.86020913593836,
|
| 1197 |
+
"grad_norm": 0.537889959924609,
|
| 1198 |
+
"learning_rate": 5e-06,
|
| 1199 |
+
"loss": 0.4359,
|
| 1200 |
+
"step": 1690
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.8712162905888827,
|
| 1204 |
+
"grad_norm": 0.5542910246512667,
|
| 1205 |
+
"learning_rate": 5e-06,
|
| 1206 |
+
"loss": 0.438,
|
| 1207 |
+
"step": 1700
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.8822234452394055,
|
| 1211 |
+
"grad_norm": 0.5307067513174616,
|
| 1212 |
+
"learning_rate": 5e-06,
|
| 1213 |
+
"loss": 0.4312,
|
| 1214 |
+
"step": 1710
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.8932305998899284,
|
| 1218 |
+
"grad_norm": 0.6185255098388331,
|
| 1219 |
+
"learning_rate": 5e-06,
|
| 1220 |
+
"loss": 0.4336,
|
| 1221 |
+
"step": 1720
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.9042377545404512,
|
| 1225 |
+
"grad_norm": 0.6105302991591885,
|
| 1226 |
+
"learning_rate": 5e-06,
|
| 1227 |
+
"loss": 0.4296,
|
| 1228 |
+
"step": 1730
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.915244909190974,
|
| 1232 |
+
"grad_norm": 0.5505132542181409,
|
| 1233 |
+
"learning_rate": 5e-06,
|
| 1234 |
+
"loss": 0.4305,
|
| 1235 |
+
"step": 1740
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.9262520638414968,
|
| 1239 |
+
"grad_norm": 0.5987936899025984,
|
| 1240 |
+
"learning_rate": 5e-06,
|
| 1241 |
+
"loss": 0.4293,
|
| 1242 |
+
"step": 1750
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.9372592184920197,
|
| 1246 |
+
"grad_norm": 0.5243332176781547,
|
| 1247 |
+
"learning_rate": 5e-06,
|
| 1248 |
+
"loss": 0.4273,
|
| 1249 |
+
"step": 1760
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.9482663731425427,
|
| 1253 |
+
"grad_norm": 0.5649987091504026,
|
| 1254 |
+
"learning_rate": 5e-06,
|
| 1255 |
+
"loss": 0.4303,
|
| 1256 |
+
"step": 1770
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.9592735277930655,
|
| 1260 |
+
"grad_norm": 0.5698314583015734,
|
| 1261 |
+
"learning_rate": 5e-06,
|
| 1262 |
+
"loss": 0.4276,
|
| 1263 |
+
"step": 1780
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.9702806824435883,
|
| 1267 |
+
"grad_norm": 0.5541608664959677,
|
| 1268 |
+
"learning_rate": 5e-06,
|
| 1269 |
+
"loss": 0.43,
|
| 1270 |
+
"step": 1790
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.9812878370941112,
|
| 1274 |
+
"grad_norm": 0.530973092247837,
|
| 1275 |
+
"learning_rate": 5e-06,
|
| 1276 |
+
"loss": 0.4291,
|
| 1277 |
+
"step": 1800
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.992294991744634,
|
| 1281 |
+
"grad_norm": 0.5385780053649944,
|
| 1282 |
+
"learning_rate": 5e-06,
|
| 1283 |
+
"loss": 0.4296,
|
| 1284 |
+
"step": 1810
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.0,
|
| 1288 |
+
"eval_loss": 0.4724336564540863,
|
| 1289 |
+
"eval_runtime": 160.867,
|
| 1290 |
+
"eval_samples_per_second": 152.119,
|
| 1291 |
+
"eval_steps_per_second": 0.597,
|
| 1292 |
+
"step": 1817
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.003302146395157,
|
| 1296 |
+
"grad_norm": 0.8967320351826643,
|
| 1297 |
+
"learning_rate": 5e-06,
|
| 1298 |
+
"loss": 0.4165,
|
| 1299 |
+
"step": 1820
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.01430930104568,
|
| 1303 |
+
"grad_norm": 0.6842852006791557,
|
| 1304 |
+
"learning_rate": 5e-06,
|
| 1305 |
+
"loss": 0.379,
|
| 1306 |
+
"step": 1830
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.0253164556962027,
|
| 1310 |
+
"grad_norm": 0.6497861759455246,
|
| 1311 |
+
"learning_rate": 5e-06,
|
| 1312 |
+
"loss": 0.3769,
|
| 1313 |
+
"step": 1840
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.0363236103467255,
|
| 1317 |
+
"grad_norm": 0.5695788867941572,
|
| 1318 |
+
"learning_rate": 5e-06,
|
| 1319 |
+
"loss": 0.3732,
|
| 1320 |
+
"step": 1850
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.0473307649972483,
|
| 1324 |
+
"grad_norm": 0.6311590318430164,
|
| 1325 |
+
"learning_rate": 5e-06,
|
| 1326 |
+
"loss": 0.379,
|
| 1327 |
+
"step": 1860
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.058337919647771,
|
| 1331 |
+
"grad_norm": 0.5735473186308736,
|
| 1332 |
+
"learning_rate": 5e-06,
|
| 1333 |
+
"loss": 0.3792,
|
| 1334 |
+
"step": 1870
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.069345074298294,
|
| 1338 |
+
"grad_norm": 0.6568929190707151,
|
| 1339 |
+
"learning_rate": 5e-06,
|
| 1340 |
+
"loss": 0.379,
|
| 1341 |
+
"step": 1880
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.0803522289488168,
|
| 1345 |
+
"grad_norm": 0.6518588834467927,
|
| 1346 |
+
"learning_rate": 5e-06,
|
| 1347 |
+
"loss": 0.378,
|
| 1348 |
+
"step": 1890
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 2.0913593835993396,
|
| 1352 |
+
"grad_norm": 0.6236301216107463,
|
| 1353 |
+
"learning_rate": 5e-06,
|
| 1354 |
+
"loss": 0.3776,
|
| 1355 |
+
"step": 1900
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.1023665382498624,
|
| 1359 |
+
"grad_norm": 0.6771820085707594,
|
| 1360 |
+
"learning_rate": 5e-06,
|
| 1361 |
+
"loss": 0.3737,
|
| 1362 |
+
"step": 1910
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.1133736929003852,
|
| 1366 |
+
"grad_norm": 0.6959842658376467,
|
| 1367 |
+
"learning_rate": 5e-06,
|
| 1368 |
+
"loss": 0.3772,
|
| 1369 |
+
"step": 1920
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.124380847550908,
|
| 1373 |
+
"grad_norm": 0.5691873810072571,
|
| 1374 |
+
"learning_rate": 5e-06,
|
| 1375 |
+
"loss": 0.3701,
|
| 1376 |
+
"step": 1930
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 2.135388002201431,
|
| 1380 |
+
"grad_norm": 0.587230812890123,
|
| 1381 |
+
"learning_rate": 5e-06,
|
| 1382 |
+
"loss": 0.3757,
|
| 1383 |
+
"step": 1940
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 2.1463951568519537,
|
| 1387 |
+
"grad_norm": 0.5676645980467607,
|
| 1388 |
+
"learning_rate": 5e-06,
|
| 1389 |
+
"loss": 0.375,
|
| 1390 |
+
"step": 1950
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 2.1574023115024765,
|
| 1394 |
+
"grad_norm": 0.5674195737996316,
|
| 1395 |
+
"learning_rate": 5e-06,
|
| 1396 |
+
"loss": 0.3814,
|
| 1397 |
+
"step": 1960
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.1684094661529993,
|
| 1401 |
+
"grad_norm": 0.5803828928264857,
|
| 1402 |
+
"learning_rate": 5e-06,
|
| 1403 |
+
"loss": 0.3744,
|
| 1404 |
+
"step": 1970
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.179416620803522,
|
| 1408 |
+
"grad_norm": 0.6171592569899994,
|
| 1409 |
+
"learning_rate": 5e-06,
|
| 1410 |
+
"loss": 0.3741,
|
| 1411 |
+
"step": 1980
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 2.190423775454045,
|
| 1415 |
+
"grad_norm": 0.658582470951269,
|
| 1416 |
+
"learning_rate": 5e-06,
|
| 1417 |
+
"loss": 0.378,
|
| 1418 |
+
"step": 1990
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 2.201430930104568,
|
| 1422 |
+
"grad_norm": 0.6562283922269005,
|
| 1423 |
+
"learning_rate": 5e-06,
|
| 1424 |
+
"loss": 0.3769,
|
| 1425 |
+
"step": 2000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.2124380847550906,
|
| 1429 |
+
"grad_norm": 0.635240231582788,
|
| 1430 |
+
"learning_rate": 5e-06,
|
| 1431 |
+
"loss": 0.3775,
|
| 1432 |
+
"step": 2010
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 2.2234452394056134,
|
| 1436 |
+
"grad_norm": 0.6551353354672024,
|
| 1437 |
+
"learning_rate": 5e-06,
|
| 1438 |
+
"loss": 0.3809,
|
| 1439 |
+
"step": 2020
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 2.2344523940561363,
|
| 1443 |
+
"grad_norm": 0.5807020804645606,
|
| 1444 |
+
"learning_rate": 5e-06,
|
| 1445 |
+
"loss": 0.3741,
|
| 1446 |
+
"step": 2030
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 2.2454595487066595,
|
| 1450 |
+
"grad_norm": 0.6317711733432692,
|
| 1451 |
+
"learning_rate": 5e-06,
|
| 1452 |
+
"loss": 0.3811,
|
| 1453 |
+
"step": 2040
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 2.2564667033571824,
|
| 1457 |
+
"grad_norm": 0.5590373084758273,
|
| 1458 |
+
"learning_rate": 5e-06,
|
| 1459 |
+
"loss": 0.3759,
|
| 1460 |
+
"step": 2050
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 2.267473858007705,
|
| 1464 |
+
"grad_norm": 0.5529922073969795,
|
| 1465 |
+
"learning_rate": 5e-06,
|
| 1466 |
+
"loss": 0.3777,
|
| 1467 |
+
"step": 2060
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 2.278481012658228,
|
| 1471 |
+
"grad_norm": 0.6310391701743894,
|
| 1472 |
+
"learning_rate": 5e-06,
|
| 1473 |
+
"loss": 0.3809,
|
| 1474 |
+
"step": 2070
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 2.289488167308751,
|
| 1478 |
+
"grad_norm": 0.5608628930620043,
|
| 1479 |
+
"learning_rate": 5e-06,
|
| 1480 |
+
"loss": 0.3748,
|
| 1481 |
+
"step": 2080
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 2.3004953219592736,
|
| 1485 |
+
"grad_norm": 0.596887560066522,
|
| 1486 |
+
"learning_rate": 5e-06,
|
| 1487 |
+
"loss": 0.3774,
|
| 1488 |
+
"step": 2090
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.3115024766097965,
|
| 1492 |
+
"grad_norm": 0.7051450098820579,
|
| 1493 |
+
"learning_rate": 5e-06,
|
| 1494 |
+
"loss": 0.3802,
|
| 1495 |
+
"step": 2100
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 2.3225096312603193,
|
| 1499 |
+
"grad_norm": 0.6327972937976852,
|
| 1500 |
+
"learning_rate": 5e-06,
|
| 1501 |
+
"loss": 0.3835,
|
| 1502 |
+
"step": 2110
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 2.333516785910842,
|
| 1506 |
+
"grad_norm": 0.6126330718992958,
|
| 1507 |
+
"learning_rate": 5e-06,
|
| 1508 |
+
"loss": 0.378,
|
| 1509 |
+
"step": 2120
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 2.344523940561365,
|
| 1513 |
+
"grad_norm": 0.6036183605384906,
|
| 1514 |
+
"learning_rate": 5e-06,
|
| 1515 |
+
"loss": 0.378,
|
| 1516 |
+
"step": 2130
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 2.3555310952118877,
|
| 1520 |
+
"grad_norm": 0.6690011983226686,
|
| 1521 |
+
"learning_rate": 5e-06,
|
| 1522 |
+
"loss": 0.3854,
|
| 1523 |
+
"step": 2140
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 2.3665382498624106,
|
| 1527 |
+
"grad_norm": 0.6167807719553883,
|
| 1528 |
+
"learning_rate": 5e-06,
|
| 1529 |
+
"loss": 0.3818,
|
| 1530 |
+
"step": 2150
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.3775454045129334,
|
| 1534 |
+
"grad_norm": 0.5936760728734222,
|
| 1535 |
+
"learning_rate": 5e-06,
|
| 1536 |
+
"loss": 0.3818,
|
| 1537 |
+
"step": 2160
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 2.388552559163456,
|
| 1541 |
+
"grad_norm": 0.6122872538963571,
|
| 1542 |
+
"learning_rate": 5e-06,
|
| 1543 |
+
"loss": 0.3772,
|
| 1544 |
+
"step": 2170
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 2.399559713813979,
|
| 1548 |
+
"grad_norm": 0.6544080290873076,
|
| 1549 |
+
"learning_rate": 5e-06,
|
| 1550 |
+
"loss": 0.3811,
|
| 1551 |
+
"step": 2180
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.410566868464502,
|
| 1555 |
+
"grad_norm": 0.6449188335513784,
|
| 1556 |
+
"learning_rate": 5e-06,
|
| 1557 |
+
"loss": 0.3783,
|
| 1558 |
+
"step": 2190
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 2.4215740231150247,
|
| 1562 |
+
"grad_norm": 0.7022837872059463,
|
| 1563 |
+
"learning_rate": 5e-06,
|
| 1564 |
+
"loss": 0.3793,
|
| 1565 |
+
"step": 2200
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 2.4325811777655475,
|
| 1569 |
+
"grad_norm": 0.7249310561789513,
|
| 1570 |
+
"learning_rate": 5e-06,
|
| 1571 |
+
"loss": 0.3803,
|
| 1572 |
+
"step": 2210
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 2.4435883324160703,
|
| 1576 |
+
"grad_norm": 0.6971979338410507,
|
| 1577 |
+
"learning_rate": 5e-06,
|
| 1578 |
+
"loss": 0.3788,
|
| 1579 |
+
"step": 2220
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 2.454595487066593,
|
| 1583 |
+
"grad_norm": 0.7707114044625848,
|
| 1584 |
+
"learning_rate": 5e-06,
|
| 1585 |
+
"loss": 0.3817,
|
| 1586 |
+
"step": 2230
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 2.465602641717116,
|
| 1590 |
+
"grad_norm": 0.6434741663311266,
|
| 1591 |
+
"learning_rate": 5e-06,
|
| 1592 |
+
"loss": 0.3778,
|
| 1593 |
+
"step": 2240
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.476609796367639,
|
| 1597 |
+
"grad_norm": 0.5911942930693944,
|
| 1598 |
+
"learning_rate": 5e-06,
|
| 1599 |
+
"loss": 0.3805,
|
| 1600 |
+
"step": 2250
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.487616951018162,
|
| 1604 |
+
"grad_norm": 0.570304109670699,
|
| 1605 |
+
"learning_rate": 5e-06,
|
| 1606 |
+
"loss": 0.3805,
|
| 1607 |
+
"step": 2260
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.498624105668685,
|
| 1611 |
+
"grad_norm": 0.5925907114220025,
|
| 1612 |
+
"learning_rate": 5e-06,
|
| 1613 |
+
"loss": 0.3779,
|
| 1614 |
+
"step": 2270
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.5096312603192077,
|
| 1618 |
+
"grad_norm": 0.6612757174277469,
|
| 1619 |
+
"learning_rate": 5e-06,
|
| 1620 |
+
"loss": 0.3818,
|
| 1621 |
+
"step": 2280
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.5206384149697305,
|
| 1625 |
+
"grad_norm": 0.6067689054978976,
|
| 1626 |
+
"learning_rate": 5e-06,
|
| 1627 |
+
"loss": 0.3774,
|
| 1628 |
+
"step": 2290
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.5316455696202533,
|
| 1632 |
+
"grad_norm": 0.5874728722311394,
|
| 1633 |
+
"learning_rate": 5e-06,
|
| 1634 |
+
"loss": 0.3787,
|
| 1635 |
+
"step": 2300
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.542652724270776,
|
| 1639 |
+
"grad_norm": 0.662103385837326,
|
| 1640 |
+
"learning_rate": 5e-06,
|
| 1641 |
+
"loss": 0.3826,
|
| 1642 |
+
"step": 2310
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 2.553659878921299,
|
| 1646 |
+
"grad_norm": 0.6026661354255178,
|
| 1647 |
+
"learning_rate": 5e-06,
|
| 1648 |
+
"loss": 0.3825,
|
| 1649 |
+
"step": 2320
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 2.564667033571822,
|
| 1653 |
+
"grad_norm": 0.5787785406337395,
|
| 1654 |
+
"learning_rate": 5e-06,
|
| 1655 |
+
"loss": 0.3794,
|
| 1656 |
+
"step": 2330
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 2.5756741882223446,
|
| 1660 |
+
"grad_norm": 0.5514615800252736,
|
| 1661 |
+
"learning_rate": 5e-06,
|
| 1662 |
+
"loss": 0.38,
|
| 1663 |
+
"step": 2340
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 2.5866813428728674,
|
| 1667 |
+
"grad_norm": 0.5961731505130763,
|
| 1668 |
+
"learning_rate": 5e-06,
|
| 1669 |
+
"loss": 0.3782,
|
| 1670 |
+
"step": 2350
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 2.5976884975233903,
|
| 1674 |
+
"grad_norm": 0.5893895677043864,
|
| 1675 |
+
"learning_rate": 5e-06,
|
| 1676 |
+
"loss": 0.3839,
|
| 1677 |
+
"step": 2360
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 2.608695652173913,
|
| 1681 |
+
"grad_norm": 0.5859569035794123,
|
| 1682 |
+
"learning_rate": 5e-06,
|
| 1683 |
+
"loss": 0.3834,
|
| 1684 |
+
"step": 2370
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 2.619702806824436,
|
| 1688 |
+
"grad_norm": 0.5997751859191552,
|
| 1689 |
+
"learning_rate": 5e-06,
|
| 1690 |
+
"loss": 0.3768,
|
| 1691 |
+
"step": 2380
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 2.6307099614749587,
|
| 1695 |
+
"grad_norm": 0.6368216879726575,
|
| 1696 |
+
"learning_rate": 5e-06,
|
| 1697 |
+
"loss": 0.3809,
|
| 1698 |
+
"step": 2390
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 2.6417171161254815,
|
| 1702 |
+
"grad_norm": 0.5877707286837056,
|
| 1703 |
+
"learning_rate": 5e-06,
|
| 1704 |
+
"loss": 0.379,
|
| 1705 |
+
"step": 2400
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 2.6527242707760044,
|
| 1709 |
+
"grad_norm": 0.5430913424974279,
|
| 1710 |
+
"learning_rate": 5e-06,
|
| 1711 |
+
"loss": 0.3794,
|
| 1712 |
+
"step": 2410
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 2.663731425426527,
|
| 1716 |
+
"grad_norm": 0.6318440202771097,
|
| 1717 |
+
"learning_rate": 5e-06,
|
| 1718 |
+
"loss": 0.3776,
|
| 1719 |
+
"step": 2420
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 2.67473858007705,
|
| 1723 |
+
"grad_norm": 0.659647040239042,
|
| 1724 |
+
"learning_rate": 5e-06,
|
| 1725 |
+
"loss": 0.3809,
|
| 1726 |
+
"step": 2430
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 2.685745734727573,
|
| 1730 |
+
"grad_norm": 0.6377513270884255,
|
| 1731 |
+
"learning_rate": 5e-06,
|
| 1732 |
+
"loss": 0.379,
|
| 1733 |
+
"step": 2440
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 2.6967528893780957,
|
| 1737 |
+
"grad_norm": 0.6437694613754824,
|
| 1738 |
+
"learning_rate": 5e-06,
|
| 1739 |
+
"loss": 0.3777,
|
| 1740 |
+
"step": 2450
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 2.7077600440286185,
|
| 1744 |
+
"grad_norm": 0.6227150600183708,
|
| 1745 |
+
"learning_rate": 5e-06,
|
| 1746 |
+
"loss": 0.381,
|
| 1747 |
+
"step": 2460
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 2.7187671986791413,
|
| 1751 |
+
"grad_norm": 0.6074943535217816,
|
| 1752 |
+
"learning_rate": 5e-06,
|
| 1753 |
+
"loss": 0.3829,
|
| 1754 |
+
"step": 2470
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 2.729774353329664,
|
| 1758 |
+
"grad_norm": 0.6059099193970705,
|
| 1759 |
+
"learning_rate": 5e-06,
|
| 1760 |
+
"loss": 0.3798,
|
| 1761 |
+
"step": 2480
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 2.740781507980187,
|
| 1765 |
+
"grad_norm": 0.5639872940942946,
|
| 1766 |
+
"learning_rate": 5e-06,
|
| 1767 |
+
"loss": 0.3803,
|
| 1768 |
+
"step": 2490
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 2.7517886626307098,
|
| 1772 |
+
"grad_norm": 0.6138763737267989,
|
| 1773 |
+
"learning_rate": 5e-06,
|
| 1774 |
+
"loss": 0.3836,
|
| 1775 |
+
"step": 2500
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 2.7627958172812326,
|
| 1779 |
+
"grad_norm": 0.6174392484182389,
|
| 1780 |
+
"learning_rate": 5e-06,
|
| 1781 |
+
"loss": 0.3771,
|
| 1782 |
+
"step": 2510
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 2.7738029719317554,
|
| 1786 |
+
"grad_norm": 0.5813465334873451,
|
| 1787 |
+
"learning_rate": 5e-06,
|
| 1788 |
+
"loss": 0.3832,
|
| 1789 |
+
"step": 2520
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 2.7848101265822782,
|
| 1793 |
+
"grad_norm": 0.5939709459181249,
|
| 1794 |
+
"learning_rate": 5e-06,
|
| 1795 |
+
"loss": 0.3758,
|
| 1796 |
+
"step": 2530
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 2.795817281232801,
|
| 1800 |
+
"grad_norm": 0.6100879294250667,
|
| 1801 |
+
"learning_rate": 5e-06,
|
| 1802 |
+
"loss": 0.3846,
|
| 1803 |
+
"step": 2540
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 2.8068244358833243,
|
| 1807 |
+
"grad_norm": 0.5849829885439275,
|
| 1808 |
+
"learning_rate": 5e-06,
|
| 1809 |
+
"loss": 0.3805,
|
| 1810 |
+
"step": 2550
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.817831590533847,
|
| 1814 |
+
"grad_norm": 0.614871493034729,
|
| 1815 |
+
"learning_rate": 5e-06,
|
| 1816 |
+
"loss": 0.3814,
|
| 1817 |
+
"step": 2560
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.82883874518437,
|
| 1821 |
+
"grad_norm": 0.5972503634442111,
|
| 1822 |
+
"learning_rate": 5e-06,
|
| 1823 |
+
"loss": 0.3833,
|
| 1824 |
+
"step": 2570
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.8398458998348928,
|
| 1828 |
+
"grad_norm": 0.7445333487223286,
|
| 1829 |
+
"learning_rate": 5e-06,
|
| 1830 |
+
"loss": 0.3785,
|
| 1831 |
+
"step": 2580
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 2.8508530544854156,
|
| 1835 |
+
"grad_norm": 0.622730774203719,
|
| 1836 |
+
"learning_rate": 5e-06,
|
| 1837 |
+
"loss": 0.3791,
|
| 1838 |
+
"step": 2590
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 2.8618602091359384,
|
| 1842 |
+
"grad_norm": 0.6588152521106931,
|
| 1843 |
+
"learning_rate": 5e-06,
|
| 1844 |
+
"loss": 0.3771,
|
| 1845 |
+
"step": 2600
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 2.8728673637864612,
|
| 1849 |
+
"grad_norm": 0.6021676282902743,
|
| 1850 |
+
"learning_rate": 5e-06,
|
| 1851 |
+
"loss": 0.3814,
|
| 1852 |
+
"step": 2610
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 2.883874518436984,
|
| 1856 |
+
"grad_norm": 0.5852769901706747,
|
| 1857 |
+
"learning_rate": 5e-06,
|
| 1858 |
+
"loss": 0.3879,
|
| 1859 |
+
"step": 2620
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 2.894881673087507,
|
| 1863 |
+
"grad_norm": 0.6163235754681848,
|
| 1864 |
+
"learning_rate": 5e-06,
|
| 1865 |
+
"loss": 0.3756,
|
| 1866 |
+
"step": 2630
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 2.9058888277380297,
|
| 1870 |
+
"grad_norm": 0.6116839094719151,
|
| 1871 |
+
"learning_rate": 5e-06,
|
| 1872 |
+
"loss": 0.3791,
|
| 1873 |
+
"step": 2640
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 2.9168959823885525,
|
| 1877 |
+
"grad_norm": 0.5676400582470854,
|
| 1878 |
+
"learning_rate": 5e-06,
|
| 1879 |
+
"loss": 0.383,
|
| 1880 |
+
"step": 2650
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 2.9279031370390753,
|
| 1884 |
+
"grad_norm": 0.6768408000572769,
|
| 1885 |
+
"learning_rate": 5e-06,
|
| 1886 |
+
"loss": 0.3838,
|
| 1887 |
+
"step": 2660
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 2.938910291689598,
|
| 1891 |
+
"grad_norm": 0.6506353755745358,
|
| 1892 |
+
"learning_rate": 5e-06,
|
| 1893 |
+
"loss": 0.3805,
|
| 1894 |
+
"step": 2670
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 2.949917446340121,
|
| 1898 |
+
"grad_norm": 0.5611923951294836,
|
| 1899 |
+
"learning_rate": 5e-06,
|
| 1900 |
+
"loss": 0.379,
|
| 1901 |
+
"step": 2680
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 2.960924600990644,
|
| 1905 |
+
"grad_norm": 0.5857791831118236,
|
| 1906 |
+
"learning_rate": 5e-06,
|
| 1907 |
+
"loss": 0.3779,
|
| 1908 |
+
"step": 2690
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 2.9719317556411666,
|
| 1912 |
+
"grad_norm": 0.5961118998765907,
|
| 1913 |
+
"learning_rate": 5e-06,
|
| 1914 |
+
"loss": 0.3791,
|
| 1915 |
+
"step": 2700
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 2.9829389102916894,
|
| 1919 |
+
"grad_norm": 0.6132753371779015,
|
| 1920 |
+
"learning_rate": 5e-06,
|
| 1921 |
+
"loss": 0.377,
|
| 1922 |
+
"step": 2710
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 2.9939460649422127,
|
| 1926 |
+
"grad_norm": 0.5713537011568807,
|
| 1927 |
+
"learning_rate": 5e-06,
|
| 1928 |
+
"loss": 0.3803,
|
| 1929 |
+
"step": 2720
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 2.9983489268024215,
|
| 1933 |
+
"eval_loss": 0.47213879227638245,
|
| 1934 |
+
"eval_runtime": 158.6207,
|
| 1935 |
+
"eval_samples_per_second": 154.274,
|
| 1936 |
+
"eval_steps_per_second": 0.605,
|
| 1937 |
+
"step": 2724
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 2.9983489268024215,
|
| 1941 |
+
"step": 2724,
|
| 1942 |
+
"total_flos": 4561963937955840.0,
|
| 1943 |
+
"train_loss": 0.44294929530652083,
|
| 1944 |
+
"train_runtime": 23449.9729,
|
| 1945 |
+
"train_samples_per_second": 59.48,
|
| 1946 |
+
"train_steps_per_second": 0.116
|
| 1947 |
+
}
|
| 1948 |
+
],
|
| 1949 |
+
"logging_steps": 10,
|
| 1950 |
+
"max_steps": 2724,
|
| 1951 |
+
"num_input_tokens_seen": 0,
|
| 1952 |
+
"num_train_epochs": 3,
|
| 1953 |
+
"save_steps": 500,
|
| 1954 |
+
"stateful_callbacks": {
|
| 1955 |
+
"TrainerControl": {
|
| 1956 |
+
"args": {
|
| 1957 |
+
"should_epoch_stop": false,
|
| 1958 |
+
"should_evaluate": false,
|
| 1959 |
+
"should_log": false,
|
| 1960 |
+
"should_save": true,
|
| 1961 |
+
"should_training_stop": true
|
| 1962 |
+
},
|
| 1963 |
+
"attributes": {}
|
| 1964 |
+
}
|
| 1965 |
+
},
|
| 1966 |
+
"total_flos": 4561963937955840.0,
|
| 1967 |
+
"train_batch_size": 8,
|
| 1968 |
+
"trial_name": null,
|
| 1969 |
+
"trial_params": null
|
| 1970 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|