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 +1480 -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: dcft_orca-agentinstruct-1M-v1-cleaned-singleturn
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# dcft_orca-agentinstruct-1M-v1-cleaned-singleturn
|
| 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: 0.4835
|
| 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: dcft_orca-agentinstruct-1M-v1-cleaned-singleturn
|
|
|
|
| 16 |
|
| 17 |
# dcft_orca-agentinstruct-1M-v1-cleaned-singleturn
|
| 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 mlfoundations-dev/dcft_orca-agentinstruct-1M-v1-cleaned-singleturn dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.4835
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9977761304670127,
|
| 3 |
+
"eval_loss": 0.4834764897823334,
|
| 4 |
+
"eval_runtime": 117.4592,
|
| 5 |
+
"eval_samples_per_second": 154.718,
|
| 6 |
+
"eval_steps_per_second": 0.604,
|
| 7 |
+
"total_flos": 3386087791656960.0,
|
| 8 |
+
"train_loss": 0.4438282892800698,
|
| 9 |
+
"train_runtime": 17391.1323,
|
| 10 |
+
"train_samples_per_second": 59.561,
|
| 11 |
+
"train_steps_per_second": 0.116
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9977761304670127,
|
| 3 |
+
"eval_loss": 0.4834764897823334,
|
| 4 |
+
"eval_runtime": 117.4592,
|
| 5 |
+
"eval_samples_per_second": 154.718,
|
| 6 |
+
"eval_steps_per_second": 0.604
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9977761304670127,
|
| 3 |
+
"total_flos": 3386087791656960.0,
|
| 4 |
+
"train_loss": 0.4438282892800698,
|
| 5 |
+
"train_runtime": 17391.1323,
|
| 6 |
+
"train_samples_per_second": 59.561,
|
| 7 |
+
"train_steps_per_second": 0.116
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1480 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9977761304670127,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2022,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.014825796886582653,
|
| 13 |
+
"grad_norm": 1.3803142660082024,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.6862,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.029651593773165306,
|
| 20 |
+
"grad_norm": 1.790122423429332,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.6305,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04447739065974796,
|
| 27 |
+
"grad_norm": 0.8497603342076308,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.5946,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05930318754633061,
|
| 34 |
+
"grad_norm": 0.7732974567839591,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.5858,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07412898443291327,
|
| 41 |
+
"grad_norm": 0.8204168744024732,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.5662,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08895478131949593,
|
| 48 |
+
"grad_norm": 0.7530005874020861,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.564,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.10378057820607858,
|
| 55 |
+
"grad_norm": 0.6979206993642474,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.5536,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.11860637509266123,
|
| 62 |
+
"grad_norm": 0.9504756484437652,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.5447,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1334321719792439,
|
| 69 |
+
"grad_norm": 0.8937944128313379,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.5466,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.14825796886582654,
|
| 76 |
+
"grad_norm": 0.6670560083366487,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.5354,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.16308376575240918,
|
| 83 |
+
"grad_norm": 0.7364925811772932,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.535,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.17790956263899185,
|
| 90 |
+
"grad_norm": 0.7183776415658619,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.5338,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1927353595255745,
|
| 97 |
+
"grad_norm": 0.5967155900573925,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.5301,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.20756115641215717,
|
| 104 |
+
"grad_norm": 0.5747353912092298,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.5263,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2223869532987398,
|
| 111 |
+
"grad_norm": 0.6159997079939371,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.5248,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.23721275018532245,
|
| 118 |
+
"grad_norm": 0.5680164570830968,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.5279,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2520385470719051,
|
| 125 |
+
"grad_norm": 0.5992456838263306,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.526,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2668643439584878,
|
| 132 |
+
"grad_norm": 0.5930479122165856,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.5224,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.28169014084507044,
|
| 139 |
+
"grad_norm": 0.5912410054870685,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.52,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2965159377316531,
|
| 146 |
+
"grad_norm": 0.5894696404162991,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.5179,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3113417346182357,
|
| 153 |
+
"grad_norm": 0.5643703980877148,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.5182,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.32616753150481836,
|
| 160 |
+
"grad_norm": 0.5861129018729444,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.5104,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.34099332839140106,
|
| 167 |
+
"grad_norm": 0.6236624375674511,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.5131,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3558191252779837,
|
| 174 |
+
"grad_norm": 0.5812434696304949,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.5191,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.37064492216456635,
|
| 181 |
+
"grad_norm": 0.7181156036216183,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.5093,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.385470719051149,
|
| 188 |
+
"grad_norm": 0.587369525728773,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.5161,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.40029651593773163,
|
| 195 |
+
"grad_norm": 0.5460966546871288,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.5178,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.41512231282431433,
|
| 202 |
+
"grad_norm": 0.5876447069011888,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.5142,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.429948109710897,
|
| 209 |
+
"grad_norm": 0.816294324192534,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.5125,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4447739065974796,
|
| 216 |
+
"grad_norm": 0.5492628600148616,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.5078,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.45959970348406226,
|
| 223 |
+
"grad_norm": 0.579955709352068,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.5045,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4744255003706449,
|
| 230 |
+
"grad_norm": 0.6279455964566482,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.5047,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4892512972572276,
|
| 237 |
+
"grad_norm": 0.6390417903003635,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.5067,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5040770941438102,
|
| 244 |
+
"grad_norm": 0.5816721190754486,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.5135,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5189028910303929,
|
| 251 |
+
"grad_norm": 0.6458696214772466,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.5034,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5337286879169756,
|
| 258 |
+
"grad_norm": 0.6957712465947605,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.5048,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5485544848035582,
|
| 265 |
+
"grad_norm": 0.543098433920077,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.4991,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5633802816901409,
|
| 272 |
+
"grad_norm": 0.7663819453316695,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.5025,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5782060785767235,
|
| 279 |
+
"grad_norm": 0.5194777261335899,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.5072,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5930318754633062,
|
| 286 |
+
"grad_norm": 0.8363946362832739,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.4948,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6078576723498889,
|
| 293 |
+
"grad_norm": 0.5430505650241441,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.5024,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6226834692364714,
|
| 300 |
+
"grad_norm": 0.5574129318838634,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.5034,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6375092661230541,
|
| 307 |
+
"grad_norm": 0.701668057920261,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.4912,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6523350630096367,
|
| 314 |
+
"grad_norm": 0.5952225478810055,
|
| 315 |
+
"learning_rate": 5e-06,
|
| 316 |
+
"loss": 0.4898,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6671608598962194,
|
| 321 |
+
"grad_norm": 0.585331803107272,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.5027,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6819866567828021,
|
| 328 |
+
"grad_norm": 0.5906175115867641,
|
| 329 |
+
"learning_rate": 5e-06,
|
| 330 |
+
"loss": 0.49,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6968124536693847,
|
| 335 |
+
"grad_norm": 0.5782512807193211,
|
| 336 |
+
"learning_rate": 5e-06,
|
| 337 |
+
"loss": 0.4962,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7116382505559674,
|
| 342 |
+
"grad_norm": 0.528401047427795,
|
| 343 |
+
"learning_rate": 5e-06,
|
| 344 |
+
"loss": 0.4979,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.72646404744255,
|
| 349 |
+
"grad_norm": 0.7128769222059271,
|
| 350 |
+
"learning_rate": 5e-06,
|
| 351 |
+
"loss": 0.4982,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.7412898443291327,
|
| 356 |
+
"grad_norm": 0.5767857437742224,
|
| 357 |
+
"learning_rate": 5e-06,
|
| 358 |
+
"loss": 0.4891,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7561156412157154,
|
| 363 |
+
"grad_norm": 0.6930280814580314,
|
| 364 |
+
"learning_rate": 5e-06,
|
| 365 |
+
"loss": 0.5006,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.770941438102298,
|
| 370 |
+
"grad_norm": 0.6530314579756452,
|
| 371 |
+
"learning_rate": 5e-06,
|
| 372 |
+
"loss": 0.4966,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7857672349888807,
|
| 377 |
+
"grad_norm": 0.6639683423874188,
|
| 378 |
+
"learning_rate": 5e-06,
|
| 379 |
+
"loss": 0.4962,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8005930318754633,
|
| 384 |
+
"grad_norm": 0.5556537170587046,
|
| 385 |
+
"learning_rate": 5e-06,
|
| 386 |
+
"loss": 0.4947,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.815418828762046,
|
| 391 |
+
"grad_norm": 0.5740824829726571,
|
| 392 |
+
"learning_rate": 5e-06,
|
| 393 |
+
"loss": 0.4919,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8302446256486287,
|
| 398 |
+
"grad_norm": 0.5307405473088794,
|
| 399 |
+
"learning_rate": 5e-06,
|
| 400 |
+
"loss": 0.4864,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.8450704225352113,
|
| 405 |
+
"grad_norm": 0.5249601710096029,
|
| 406 |
+
"learning_rate": 5e-06,
|
| 407 |
+
"loss": 0.4926,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.859896219421794,
|
| 412 |
+
"grad_norm": 0.5263542668413514,
|
| 413 |
+
"learning_rate": 5e-06,
|
| 414 |
+
"loss": 0.4877,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8747220163083765,
|
| 419 |
+
"grad_norm": 0.5027236096291062,
|
| 420 |
+
"learning_rate": 5e-06,
|
| 421 |
+
"loss": 0.4903,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8895478131949592,
|
| 426 |
+
"grad_norm": 0.687053549139694,
|
| 427 |
+
"learning_rate": 5e-06,
|
| 428 |
+
"loss": 0.4945,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9043736100815419,
|
| 433 |
+
"grad_norm": 0.6064169430923966,
|
| 434 |
+
"learning_rate": 5e-06,
|
| 435 |
+
"loss": 0.4898,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9191994069681245,
|
| 440 |
+
"grad_norm": 0.5127672913798731,
|
| 441 |
+
"learning_rate": 5e-06,
|
| 442 |
+
"loss": 0.4916,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.9340252038547072,
|
| 447 |
+
"grad_norm": 0.5911308230908845,
|
| 448 |
+
"learning_rate": 5e-06,
|
| 449 |
+
"loss": 0.4876,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9488510007412898,
|
| 454 |
+
"grad_norm": 0.5318485612638623,
|
| 455 |
+
"learning_rate": 5e-06,
|
| 456 |
+
"loss": 0.4911,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9636767976278725,
|
| 461 |
+
"grad_norm": 0.599135799828323,
|
| 462 |
+
"learning_rate": 5e-06,
|
| 463 |
+
"loss": 0.4907,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9785025945144552,
|
| 468 |
+
"grad_norm": 0.5017158299240659,
|
| 469 |
+
"learning_rate": 5e-06,
|
| 470 |
+
"loss": 0.4864,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.9933283914010378,
|
| 475 |
+
"grad_norm": 0.638905966589537,
|
| 476 |
+
"learning_rate": 5e-06,
|
| 477 |
+
"loss": 0.4886,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.9992587101556709,
|
| 482 |
+
"eval_loss": 0.489400178194046,
|
| 483 |
+
"eval_runtime": 119.2986,
|
| 484 |
+
"eval_samples_per_second": 152.332,
|
| 485 |
+
"eval_steps_per_second": 0.595,
|
| 486 |
+
"step": 674
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.0081541882876204,
|
| 490 |
+
"grad_norm": 0.8019081623682851,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.4775,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.0229799851742032,
|
| 497 |
+
"grad_norm": 0.5833948483649493,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.4344,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.0378057820607858,
|
| 504 |
+
"grad_norm": 0.5717232078953663,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.4372,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.0526315789473684,
|
| 511 |
+
"grad_norm": 0.5320074952877888,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.4376,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.0674573758339512,
|
| 518 |
+
"grad_norm": 0.5726271946361784,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.4314,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.0822831727205338,
|
| 525 |
+
"grad_norm": 0.596509516956136,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.4347,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.0971089696071163,
|
| 532 |
+
"grad_norm": 0.5390515390075241,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.434,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.111934766493699,
|
| 539 |
+
"grad_norm": 0.6129914776744078,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.4354,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.1267605633802817,
|
| 546 |
+
"grad_norm": 0.5592764678336093,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.4368,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.1415863602668643,
|
| 553 |
+
"grad_norm": 0.7060047642916599,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.443,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.156412157153447,
|
| 560 |
+
"grad_norm": 0.5940229109864722,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.4433,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.1712379540400297,
|
| 567 |
+
"grad_norm": 0.5491622519034774,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.4304,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.1860637509266123,
|
| 574 |
+
"grad_norm": 0.6079761033641661,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.438,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.200889547813195,
|
| 581 |
+
"grad_norm": 0.5693457065422755,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.4403,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.2157153446997775,
|
| 588 |
+
"grad_norm": 0.6505910795677263,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.4375,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.2305411415863603,
|
| 595 |
+
"grad_norm": 0.6268213064250889,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.4373,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.2453669384729429,
|
| 602 |
+
"grad_norm": 0.5919676508645508,
|
| 603 |
+
"learning_rate": 5e-06,
|
| 604 |
+
"loss": 0.4306,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.2601927353595257,
|
| 609 |
+
"grad_norm": 0.5398299551449609,
|
| 610 |
+
"learning_rate": 5e-06,
|
| 611 |
+
"loss": 0.4353,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.2750185322461083,
|
| 616 |
+
"grad_norm": 0.5424618353666834,
|
| 617 |
+
"learning_rate": 5e-06,
|
| 618 |
+
"loss": 0.4376,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.2898443291326909,
|
| 623 |
+
"grad_norm": 0.5634395154305121,
|
| 624 |
+
"learning_rate": 5e-06,
|
| 625 |
+
"loss": 0.4361,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.3046701260192735,
|
| 630 |
+
"grad_norm": 0.5785455634852342,
|
| 631 |
+
"learning_rate": 5e-06,
|
| 632 |
+
"loss": 0.4367,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.3194959229058563,
|
| 637 |
+
"grad_norm": 0.620601502244543,
|
| 638 |
+
"learning_rate": 5e-06,
|
| 639 |
+
"loss": 0.4367,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.3343217197924389,
|
| 644 |
+
"grad_norm": 0.530395060539937,
|
| 645 |
+
"learning_rate": 5e-06,
|
| 646 |
+
"loss": 0.4347,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.3491475166790214,
|
| 651 |
+
"grad_norm": 0.5770452107287607,
|
| 652 |
+
"learning_rate": 5e-06,
|
| 653 |
+
"loss": 0.4391,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.3639733135656043,
|
| 658 |
+
"grad_norm": 0.5858170710249173,
|
| 659 |
+
"learning_rate": 5e-06,
|
| 660 |
+
"loss": 0.4343,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.3787991104521868,
|
| 665 |
+
"grad_norm": 0.5500756623276715,
|
| 666 |
+
"learning_rate": 5e-06,
|
| 667 |
+
"loss": 0.4346,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.3936249073387694,
|
| 672 |
+
"grad_norm": 0.6255449782390206,
|
| 673 |
+
"learning_rate": 5e-06,
|
| 674 |
+
"loss": 0.4389,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.408450704225352,
|
| 679 |
+
"grad_norm": 0.5460524509865728,
|
| 680 |
+
"learning_rate": 5e-06,
|
| 681 |
+
"loss": 0.4369,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.4232765011119348,
|
| 686 |
+
"grad_norm": 0.5924885663735421,
|
| 687 |
+
"learning_rate": 5e-06,
|
| 688 |
+
"loss": 0.4338,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.4381022979985174,
|
| 693 |
+
"grad_norm": 0.5764645405905721,
|
| 694 |
+
"learning_rate": 5e-06,
|
| 695 |
+
"loss": 0.4367,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.4529280948851,
|
| 700 |
+
"grad_norm": 0.5850117598054916,
|
| 701 |
+
"learning_rate": 5e-06,
|
| 702 |
+
"loss": 0.4362,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.4677538917716828,
|
| 707 |
+
"grad_norm": 0.6081832575580323,
|
| 708 |
+
"learning_rate": 5e-06,
|
| 709 |
+
"loss": 0.4406,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.4825796886582654,
|
| 714 |
+
"grad_norm": 0.543363234220218,
|
| 715 |
+
"learning_rate": 5e-06,
|
| 716 |
+
"loss": 0.4351,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.497405485544848,
|
| 721 |
+
"grad_norm": 0.5448664659996519,
|
| 722 |
+
"learning_rate": 5e-06,
|
| 723 |
+
"loss": 0.436,
|
| 724 |
+
"step": 1010
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.5122312824314306,
|
| 728 |
+
"grad_norm": 0.65441524183388,
|
| 729 |
+
"learning_rate": 5e-06,
|
| 730 |
+
"loss": 0.4372,
|
| 731 |
+
"step": 1020
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.5270570793180134,
|
| 735 |
+
"grad_norm": 0.5280772751509661,
|
| 736 |
+
"learning_rate": 5e-06,
|
| 737 |
+
"loss": 0.4357,
|
| 738 |
+
"step": 1030
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.541882876204596,
|
| 742 |
+
"grad_norm": 0.5723443909631686,
|
| 743 |
+
"learning_rate": 5e-06,
|
| 744 |
+
"loss": 0.4318,
|
| 745 |
+
"step": 1040
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.5567086730911788,
|
| 749 |
+
"grad_norm": 0.5085846011938958,
|
| 750 |
+
"learning_rate": 5e-06,
|
| 751 |
+
"loss": 0.4323,
|
| 752 |
+
"step": 1050
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.5715344699777614,
|
| 756 |
+
"grad_norm": 0.638285906027132,
|
| 757 |
+
"learning_rate": 5e-06,
|
| 758 |
+
"loss": 0.4415,
|
| 759 |
+
"step": 1060
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.586360266864344,
|
| 763 |
+
"grad_norm": 0.571218693857694,
|
| 764 |
+
"learning_rate": 5e-06,
|
| 765 |
+
"loss": 0.4346,
|
| 766 |
+
"step": 1070
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.6011860637509265,
|
| 770 |
+
"grad_norm": 0.517292661892654,
|
| 771 |
+
"learning_rate": 5e-06,
|
| 772 |
+
"loss": 0.4382,
|
| 773 |
+
"step": 1080
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.6160118606375091,
|
| 777 |
+
"grad_norm": 0.5102023179424974,
|
| 778 |
+
"learning_rate": 5e-06,
|
| 779 |
+
"loss": 0.4323,
|
| 780 |
+
"step": 1090
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.630837657524092,
|
| 784 |
+
"grad_norm": 0.5721112226520383,
|
| 785 |
+
"learning_rate": 5e-06,
|
| 786 |
+
"loss": 0.4378,
|
| 787 |
+
"step": 1100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.6456634544106745,
|
| 791 |
+
"grad_norm": 0.5551329559644929,
|
| 792 |
+
"learning_rate": 5e-06,
|
| 793 |
+
"loss": 0.4348,
|
| 794 |
+
"step": 1110
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.6604892512972573,
|
| 798 |
+
"grad_norm": 0.6119221260699137,
|
| 799 |
+
"learning_rate": 5e-06,
|
| 800 |
+
"loss": 0.4274,
|
| 801 |
+
"step": 1120
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.67531504818384,
|
| 805 |
+
"grad_norm": 0.5333241050316515,
|
| 806 |
+
"learning_rate": 5e-06,
|
| 807 |
+
"loss": 0.432,
|
| 808 |
+
"step": 1130
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.6901408450704225,
|
| 812 |
+
"grad_norm": 0.564328179152952,
|
| 813 |
+
"learning_rate": 5e-06,
|
| 814 |
+
"loss": 0.4391,
|
| 815 |
+
"step": 1140
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.704966641957005,
|
| 819 |
+
"grad_norm": 0.5254085440281446,
|
| 820 |
+
"learning_rate": 5e-06,
|
| 821 |
+
"loss": 0.4359,
|
| 822 |
+
"step": 1150
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.7197924388435877,
|
| 826 |
+
"grad_norm": 0.5996709499991413,
|
| 827 |
+
"learning_rate": 5e-06,
|
| 828 |
+
"loss": 0.4355,
|
| 829 |
+
"step": 1160
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.7346182357301705,
|
| 833 |
+
"grad_norm": 0.5493385200435505,
|
| 834 |
+
"learning_rate": 5e-06,
|
| 835 |
+
"loss": 0.432,
|
| 836 |
+
"step": 1170
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.7494440326167533,
|
| 840 |
+
"grad_norm": 0.5906833738744632,
|
| 841 |
+
"learning_rate": 5e-06,
|
| 842 |
+
"loss": 0.4367,
|
| 843 |
+
"step": 1180
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.7642698295033359,
|
| 847 |
+
"grad_norm": 0.5341688856567031,
|
| 848 |
+
"learning_rate": 5e-06,
|
| 849 |
+
"loss": 0.4298,
|
| 850 |
+
"step": 1190
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.7790956263899185,
|
| 854 |
+
"grad_norm": 0.533463029816806,
|
| 855 |
+
"learning_rate": 5e-06,
|
| 856 |
+
"loss": 0.4344,
|
| 857 |
+
"step": 1200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.793921423276501,
|
| 861 |
+
"grad_norm": 0.5606747279800302,
|
| 862 |
+
"learning_rate": 5e-06,
|
| 863 |
+
"loss": 0.4362,
|
| 864 |
+
"step": 1210
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.8087472201630836,
|
| 868 |
+
"grad_norm": 0.5183566067624092,
|
| 869 |
+
"learning_rate": 5e-06,
|
| 870 |
+
"loss": 0.4271,
|
| 871 |
+
"step": 1220
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.8235730170496665,
|
| 875 |
+
"grad_norm": 0.5326764319923035,
|
| 876 |
+
"learning_rate": 5e-06,
|
| 877 |
+
"loss": 0.4306,
|
| 878 |
+
"step": 1230
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.838398813936249,
|
| 882 |
+
"grad_norm": 0.5967407273470395,
|
| 883 |
+
"learning_rate": 5e-06,
|
| 884 |
+
"loss": 0.4344,
|
| 885 |
+
"step": 1240
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.8532246108228319,
|
| 889 |
+
"grad_norm": 0.569200724691502,
|
| 890 |
+
"learning_rate": 5e-06,
|
| 891 |
+
"loss": 0.4353,
|
| 892 |
+
"step": 1250
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.8680504077094144,
|
| 896 |
+
"grad_norm": 0.5364248806496852,
|
| 897 |
+
"learning_rate": 5e-06,
|
| 898 |
+
"loss": 0.4364,
|
| 899 |
+
"step": 1260
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.882876204595997,
|
| 903 |
+
"grad_norm": 0.5385402357985632,
|
| 904 |
+
"learning_rate": 5e-06,
|
| 905 |
+
"loss": 0.4379,
|
| 906 |
+
"step": 1270
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.8977020014825796,
|
| 910 |
+
"grad_norm": 0.5223344068630751,
|
| 911 |
+
"learning_rate": 5e-06,
|
| 912 |
+
"loss": 0.4347,
|
| 913 |
+
"step": 1280
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.9125277983691622,
|
| 917 |
+
"grad_norm": 0.5617283138858877,
|
| 918 |
+
"learning_rate": 5e-06,
|
| 919 |
+
"loss": 0.4319,
|
| 920 |
+
"step": 1290
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.927353595255745,
|
| 924 |
+
"grad_norm": 0.5893151487107228,
|
| 925 |
+
"learning_rate": 5e-06,
|
| 926 |
+
"loss": 0.4313,
|
| 927 |
+
"step": 1300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.9421793921423276,
|
| 931 |
+
"grad_norm": 0.5366729507399915,
|
| 932 |
+
"learning_rate": 5e-06,
|
| 933 |
+
"loss": 0.4399,
|
| 934 |
+
"step": 1310
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.9570051890289104,
|
| 938 |
+
"grad_norm": 0.5521187635061144,
|
| 939 |
+
"learning_rate": 5e-06,
|
| 940 |
+
"loss": 0.4346,
|
| 941 |
+
"step": 1320
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.971830985915493,
|
| 945 |
+
"grad_norm": 0.5736814101430955,
|
| 946 |
+
"learning_rate": 5e-06,
|
| 947 |
+
"loss": 0.4344,
|
| 948 |
+
"step": 1330
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.9866567828020756,
|
| 952 |
+
"grad_norm": 0.6153323220981107,
|
| 953 |
+
"learning_rate": 5e-06,
|
| 954 |
+
"loss": 0.4288,
|
| 955 |
+
"step": 1340
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.0,
|
| 959 |
+
"eval_loss": 0.47887247800827026,
|
| 960 |
+
"eval_runtime": 117.4023,
|
| 961 |
+
"eval_samples_per_second": 154.793,
|
| 962 |
+
"eval_steps_per_second": 0.605,
|
| 963 |
+
"step": 1349
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.001482579688658,
|
| 967 |
+
"grad_norm": 0.8057512126070844,
|
| 968 |
+
"learning_rate": 5e-06,
|
| 969 |
+
"loss": 0.4465,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.0163083765752408,
|
| 974 |
+
"grad_norm": 0.6985686766657238,
|
| 975 |
+
"learning_rate": 5e-06,
|
| 976 |
+
"loss": 0.3758,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.031134173461824,
|
| 981 |
+
"grad_norm": 0.7516592382333935,
|
| 982 |
+
"learning_rate": 5e-06,
|
| 983 |
+
"loss": 0.3739,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.0459599703484064,
|
| 988 |
+
"grad_norm": 0.6560426338450871,
|
| 989 |
+
"learning_rate": 5e-06,
|
| 990 |
+
"loss": 0.3733,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.060785767234989,
|
| 995 |
+
"grad_norm": 0.6554981025712345,
|
| 996 |
+
"learning_rate": 5e-06,
|
| 997 |
+
"loss": 0.3738,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.0756115641215716,
|
| 1002 |
+
"grad_norm": 0.5777290379829684,
|
| 1003 |
+
"learning_rate": 5e-06,
|
| 1004 |
+
"loss": 0.373,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.090437361008154,
|
| 1009 |
+
"grad_norm": 0.6039864607065941,
|
| 1010 |
+
"learning_rate": 5e-06,
|
| 1011 |
+
"loss": 0.3726,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.1052631578947367,
|
| 1016 |
+
"grad_norm": 0.5737027873462299,
|
| 1017 |
+
"learning_rate": 5e-06,
|
| 1018 |
+
"loss": 0.3745,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.1200889547813193,
|
| 1023 |
+
"grad_norm": 0.5962503173170325,
|
| 1024 |
+
"learning_rate": 5e-06,
|
| 1025 |
+
"loss": 0.3793,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.1349147516679023,
|
| 1030 |
+
"grad_norm": 0.5896368959935617,
|
| 1031 |
+
"learning_rate": 5e-06,
|
| 1032 |
+
"loss": 0.3783,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.149740548554485,
|
| 1037 |
+
"grad_norm": 0.5817443097816994,
|
| 1038 |
+
"learning_rate": 5e-06,
|
| 1039 |
+
"loss": 0.3775,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.1645663454410675,
|
| 1044 |
+
"grad_norm": 0.5749673449125087,
|
| 1045 |
+
"learning_rate": 5e-06,
|
| 1046 |
+
"loss": 0.378,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.17939214232765,
|
| 1051 |
+
"grad_norm": 0.581781908254146,
|
| 1052 |
+
"learning_rate": 5e-06,
|
| 1053 |
+
"loss": 0.3694,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.1942179392142327,
|
| 1058 |
+
"grad_norm": 0.5991853455621899,
|
| 1059 |
+
"learning_rate": 5e-06,
|
| 1060 |
+
"loss": 0.3821,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.2090437361008153,
|
| 1065 |
+
"grad_norm": 0.5786028266566305,
|
| 1066 |
+
"learning_rate": 5e-06,
|
| 1067 |
+
"loss": 0.3761,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.223869532987398,
|
| 1072 |
+
"grad_norm": 0.6524631416486719,
|
| 1073 |
+
"learning_rate": 5e-06,
|
| 1074 |
+
"loss": 0.3733,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 2.238695329873981,
|
| 1079 |
+
"grad_norm": 0.66274701181455,
|
| 1080 |
+
"learning_rate": 5e-06,
|
| 1081 |
+
"loss": 0.3812,
|
| 1082 |
+
"step": 1510
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.2535211267605635,
|
| 1086 |
+
"grad_norm": 0.5890654308630106,
|
| 1087 |
+
"learning_rate": 5e-06,
|
| 1088 |
+
"loss": 0.3785,
|
| 1089 |
+
"step": 1520
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.268346923647146,
|
| 1093 |
+
"grad_norm": 0.5995580394178166,
|
| 1094 |
+
"learning_rate": 5e-06,
|
| 1095 |
+
"loss": 0.3766,
|
| 1096 |
+
"step": 1530
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.2831727205337287,
|
| 1100 |
+
"grad_norm": 0.5621523912385117,
|
| 1101 |
+
"learning_rate": 5e-06,
|
| 1102 |
+
"loss": 0.3819,
|
| 1103 |
+
"step": 1540
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.2979985174203112,
|
| 1107 |
+
"grad_norm": 0.5631391589331654,
|
| 1108 |
+
"learning_rate": 5e-06,
|
| 1109 |
+
"loss": 0.3831,
|
| 1110 |
+
"step": 1550
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.312824314306894,
|
| 1114 |
+
"grad_norm": 0.598394877682484,
|
| 1115 |
+
"learning_rate": 5e-06,
|
| 1116 |
+
"loss": 0.3776,
|
| 1117 |
+
"step": 1560
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.327650111193477,
|
| 1121 |
+
"grad_norm": 0.5751635376845493,
|
| 1122 |
+
"learning_rate": 5e-06,
|
| 1123 |
+
"loss": 0.3743,
|
| 1124 |
+
"step": 1570
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.3424759080800595,
|
| 1128 |
+
"grad_norm": 0.7431168749670549,
|
| 1129 |
+
"learning_rate": 5e-06,
|
| 1130 |
+
"loss": 0.3806,
|
| 1131 |
+
"step": 1580
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.357301704966642,
|
| 1135 |
+
"grad_norm": 0.6148778429363163,
|
| 1136 |
+
"learning_rate": 5e-06,
|
| 1137 |
+
"loss": 0.3792,
|
| 1138 |
+
"step": 1590
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.3721275018532246,
|
| 1142 |
+
"grad_norm": 0.5904751763294604,
|
| 1143 |
+
"learning_rate": 5e-06,
|
| 1144 |
+
"loss": 0.3779,
|
| 1145 |
+
"step": 1600
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.386953298739807,
|
| 1149 |
+
"grad_norm": 0.6160494878206139,
|
| 1150 |
+
"learning_rate": 5e-06,
|
| 1151 |
+
"loss": 0.3795,
|
| 1152 |
+
"step": 1610
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.40177909562639,
|
| 1156 |
+
"grad_norm": 0.6601509703827891,
|
| 1157 |
+
"learning_rate": 5e-06,
|
| 1158 |
+
"loss": 0.381,
|
| 1159 |
+
"step": 1620
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.4166048925129724,
|
| 1163 |
+
"grad_norm": 0.5557483892389672,
|
| 1164 |
+
"learning_rate": 5e-06,
|
| 1165 |
+
"loss": 0.38,
|
| 1166 |
+
"step": 1630
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 2.431430689399555,
|
| 1170 |
+
"grad_norm": 0.5514157650195483,
|
| 1171 |
+
"learning_rate": 5e-06,
|
| 1172 |
+
"loss": 0.3785,
|
| 1173 |
+
"step": 1640
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.446256486286138,
|
| 1177 |
+
"grad_norm": 0.5896166088948557,
|
| 1178 |
+
"learning_rate": 5e-06,
|
| 1179 |
+
"loss": 0.3785,
|
| 1180 |
+
"step": 1650
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 2.4610822831727206,
|
| 1184 |
+
"grad_norm": 0.6187824694109818,
|
| 1185 |
+
"learning_rate": 5e-06,
|
| 1186 |
+
"loss": 0.3866,
|
| 1187 |
+
"step": 1660
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.475908080059303,
|
| 1191 |
+
"grad_norm": 0.6196885650354601,
|
| 1192 |
+
"learning_rate": 5e-06,
|
| 1193 |
+
"loss": 0.3773,
|
| 1194 |
+
"step": 1670
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.4907338769458858,
|
| 1198 |
+
"grad_norm": 0.6497541102453935,
|
| 1199 |
+
"learning_rate": 5e-06,
|
| 1200 |
+
"loss": 0.3792,
|
| 1201 |
+
"step": 1680
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.5055596738324684,
|
| 1205 |
+
"grad_norm": 0.6221830439300937,
|
| 1206 |
+
"learning_rate": 5e-06,
|
| 1207 |
+
"loss": 0.3814,
|
| 1208 |
+
"step": 1690
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.5203854707190514,
|
| 1212 |
+
"grad_norm": 0.5575748670805571,
|
| 1213 |
+
"learning_rate": 5e-06,
|
| 1214 |
+
"loss": 0.3788,
|
| 1215 |
+
"step": 1700
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.535211267605634,
|
| 1219 |
+
"grad_norm": 0.5820255267213036,
|
| 1220 |
+
"learning_rate": 5e-06,
|
| 1221 |
+
"loss": 0.3797,
|
| 1222 |
+
"step": 1710
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 2.5500370644922166,
|
| 1226 |
+
"grad_norm": 0.5778840920723647,
|
| 1227 |
+
"learning_rate": 5e-06,
|
| 1228 |
+
"loss": 0.3836,
|
| 1229 |
+
"step": 1720
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.564862861378799,
|
| 1233 |
+
"grad_norm": 0.6369372874220104,
|
| 1234 |
+
"learning_rate": 5e-06,
|
| 1235 |
+
"loss": 0.3822,
|
| 1236 |
+
"step": 1730
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.5796886582653817,
|
| 1240 |
+
"grad_norm": 0.5836272270823646,
|
| 1241 |
+
"learning_rate": 5e-06,
|
| 1242 |
+
"loss": 0.3825,
|
| 1243 |
+
"step": 1740
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 2.5945144551519643,
|
| 1247 |
+
"grad_norm": 0.5893118830611698,
|
| 1248 |
+
"learning_rate": 5e-06,
|
| 1249 |
+
"loss": 0.382,
|
| 1250 |
+
"step": 1750
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.609340252038547,
|
| 1254 |
+
"grad_norm": 0.691740548026418,
|
| 1255 |
+
"learning_rate": 5e-06,
|
| 1256 |
+
"loss": 0.3828,
|
| 1257 |
+
"step": 1760
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.6241660489251295,
|
| 1261 |
+
"grad_norm": 0.6016891230542475,
|
| 1262 |
+
"learning_rate": 5e-06,
|
| 1263 |
+
"loss": 0.3841,
|
| 1264 |
+
"step": 1770
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.6389918458117125,
|
| 1268 |
+
"grad_norm": 0.5709726000324739,
|
| 1269 |
+
"learning_rate": 5e-06,
|
| 1270 |
+
"loss": 0.38,
|
| 1271 |
+
"step": 1780
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 2.653817642698295,
|
| 1275 |
+
"grad_norm": 0.5707418370568915,
|
| 1276 |
+
"learning_rate": 5e-06,
|
| 1277 |
+
"loss": 0.3819,
|
| 1278 |
+
"step": 1790
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.6686434395848777,
|
| 1282 |
+
"grad_norm": 0.6121781418312778,
|
| 1283 |
+
"learning_rate": 5e-06,
|
| 1284 |
+
"loss": 0.3775,
|
| 1285 |
+
"step": 1800
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 2.6834692364714603,
|
| 1289 |
+
"grad_norm": 0.5845205444282813,
|
| 1290 |
+
"learning_rate": 5e-06,
|
| 1291 |
+
"loss": 0.3794,
|
| 1292 |
+
"step": 1810
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.698295033358043,
|
| 1296 |
+
"grad_norm": 0.6090204118467554,
|
| 1297 |
+
"learning_rate": 5e-06,
|
| 1298 |
+
"loss": 0.3749,
|
| 1299 |
+
"step": 1820
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.713120830244626,
|
| 1303 |
+
"grad_norm": 0.6311725348745423,
|
| 1304 |
+
"learning_rate": 5e-06,
|
| 1305 |
+
"loss": 0.3875,
|
| 1306 |
+
"step": 1830
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.7279466271312085,
|
| 1310 |
+
"grad_norm": 0.5855235496792751,
|
| 1311 |
+
"learning_rate": 5e-06,
|
| 1312 |
+
"loss": 0.3798,
|
| 1313 |
+
"step": 1840
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.742772424017791,
|
| 1317 |
+
"grad_norm": 0.6360580241341309,
|
| 1318 |
+
"learning_rate": 5e-06,
|
| 1319 |
+
"loss": 0.3795,
|
| 1320 |
+
"step": 1850
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.7575982209043737,
|
| 1324 |
+
"grad_norm": 0.6949332357026632,
|
| 1325 |
+
"learning_rate": 5e-06,
|
| 1326 |
+
"loss": 0.3833,
|
| 1327 |
+
"step": 1860
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.7724240177909563,
|
| 1331 |
+
"grad_norm": 0.5661995725449918,
|
| 1332 |
+
"learning_rate": 5e-06,
|
| 1333 |
+
"loss": 0.3815,
|
| 1334 |
+
"step": 1870
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.787249814677539,
|
| 1338 |
+
"grad_norm": 0.6181579391717933,
|
| 1339 |
+
"learning_rate": 5e-06,
|
| 1340 |
+
"loss": 0.3814,
|
| 1341 |
+
"step": 1880
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.8020756115641214,
|
| 1345 |
+
"grad_norm": 0.621591189180585,
|
| 1346 |
+
"learning_rate": 5e-06,
|
| 1347 |
+
"loss": 0.3839,
|
| 1348 |
+
"step": 1890
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 2.816901408450704,
|
| 1352 |
+
"grad_norm": 0.6102808235648141,
|
| 1353 |
+
"learning_rate": 5e-06,
|
| 1354 |
+
"loss": 0.386,
|
| 1355 |
+
"step": 1900
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.8317272053372866,
|
| 1359 |
+
"grad_norm": 0.5570401466362744,
|
| 1360 |
+
"learning_rate": 5e-06,
|
| 1361 |
+
"loss": 0.3829,
|
| 1362 |
+
"step": 1910
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.8465530022238696,
|
| 1366 |
+
"grad_norm": 0.605864801280795,
|
| 1367 |
+
"learning_rate": 5e-06,
|
| 1368 |
+
"loss": 0.3791,
|
| 1369 |
+
"step": 1920
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.8613787991104522,
|
| 1373 |
+
"grad_norm": 0.5737361891170868,
|
| 1374 |
+
"learning_rate": 5e-06,
|
| 1375 |
+
"loss": 0.3831,
|
| 1376 |
+
"step": 1930
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 2.876204595997035,
|
| 1380 |
+
"grad_norm": 0.5867020788912005,
|
| 1381 |
+
"learning_rate": 5e-06,
|
| 1382 |
+
"loss": 0.38,
|
| 1383 |
+
"step": 1940
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 2.8910303928836174,
|
| 1387 |
+
"grad_norm": 0.557534237372008,
|
| 1388 |
+
"learning_rate": 5e-06,
|
| 1389 |
+
"loss": 0.3825,
|
| 1390 |
+
"step": 1950
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 2.9058561897702,
|
| 1394 |
+
"grad_norm": 0.5964701402385094,
|
| 1395 |
+
"learning_rate": 5e-06,
|
| 1396 |
+
"loss": 0.3852,
|
| 1397 |
+
"step": 1960
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.920681986656783,
|
| 1401 |
+
"grad_norm": 0.600588952238815,
|
| 1402 |
+
"learning_rate": 5e-06,
|
| 1403 |
+
"loss": 0.3876,
|
| 1404 |
+
"step": 1970
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.9355077835433656,
|
| 1408 |
+
"grad_norm": 0.5765877577022089,
|
| 1409 |
+
"learning_rate": 5e-06,
|
| 1410 |
+
"loss": 0.3851,
|
| 1411 |
+
"step": 1980
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 2.950333580429948,
|
| 1415 |
+
"grad_norm": 0.6187803453792526,
|
| 1416 |
+
"learning_rate": 5e-06,
|
| 1417 |
+
"loss": 0.3818,
|
| 1418 |
+
"step": 1990
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 2.965159377316531,
|
| 1422 |
+
"grad_norm": 0.5518073320285379,
|
| 1423 |
+
"learning_rate": 5e-06,
|
| 1424 |
+
"loss": 0.3834,
|
| 1425 |
+
"step": 2000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.9799851742031134,
|
| 1429 |
+
"grad_norm": 0.5343617840090896,
|
| 1430 |
+
"learning_rate": 5e-06,
|
| 1431 |
+
"loss": 0.3772,
|
| 1432 |
+
"step": 2010
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 2.994810971089696,
|
| 1436 |
+
"grad_norm": 0.5629835017462416,
|
| 1437 |
+
"learning_rate": 5e-06,
|
| 1438 |
+
"loss": 0.382,
|
| 1439 |
+
"step": 2020
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 2.9977761304670127,
|
| 1443 |
+
"eval_loss": 0.4834764897823334,
|
| 1444 |
+
"eval_runtime": 117.0978,
|
| 1445 |
+
"eval_samples_per_second": 155.195,
|
| 1446 |
+
"eval_steps_per_second": 0.606,
|
| 1447 |
+
"step": 2022
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 2.9977761304670127,
|
| 1451 |
+
"step": 2022,
|
| 1452 |
+
"total_flos": 3386087791656960.0,
|
| 1453 |
+
"train_loss": 0.4438282892800698,
|
| 1454 |
+
"train_runtime": 17391.1323,
|
| 1455 |
+
"train_samples_per_second": 59.561,
|
| 1456 |
+
"train_steps_per_second": 0.116
|
| 1457 |
+
}
|
| 1458 |
+
],
|
| 1459 |
+
"logging_steps": 10,
|
| 1460 |
+
"max_steps": 2022,
|
| 1461 |
+
"num_input_tokens_seen": 0,
|
| 1462 |
+
"num_train_epochs": 3,
|
| 1463 |
+
"save_steps": 500,
|
| 1464 |
+
"stateful_callbacks": {
|
| 1465 |
+
"TrainerControl": {
|
| 1466 |
+
"args": {
|
| 1467 |
+
"should_epoch_stop": false,
|
| 1468 |
+
"should_evaluate": false,
|
| 1469 |
+
"should_log": false,
|
| 1470 |
+
"should_save": true,
|
| 1471 |
+
"should_training_stop": true
|
| 1472 |
+
},
|
| 1473 |
+
"attributes": {}
|
| 1474 |
+
}
|
| 1475 |
+
},
|
| 1476 |
+
"total_flos": 3386087791656960.0,
|
| 1477 |
+
"train_batch_size": 8,
|
| 1478 |
+
"trial_name": null,
|
| 1479 |
+
"trial_params": null
|
| 1480 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|