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 +1811 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: mistralai/Mistral-7B-v0.1
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: hp_ablations_mistral_epoch5
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_mistral_epoch5
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.3789
|
| 21 |
|
|
|
|
| 4 |
base_model: mistralai/Mistral-7B-v0.1
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: hp_ablations_mistral_epoch5
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_mistral_epoch5
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.3789
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.37886306643486023,
|
| 4 |
+
"eval_runtime": 127.9725,
|
| 5 |
+
"eval_samples_per_second": 103.96,
|
| 6 |
+
"eval_steps_per_second": 0.406,
|
| 7 |
+
"total_flos": 4136504477614080.0,
|
| 8 |
+
"train_loss": 0.39363470135430095,
|
| 9 |
+
"train_runtime": 36289.8965,
|
| 10 |
+
"train_samples_per_second": 34.825,
|
| 11 |
+
"train_steps_per_second": 0.068
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.37886306643486023,
|
| 4 |
+
"eval_runtime": 127.9725,
|
| 5 |
+
"eval_samples_per_second": 103.96,
|
| 6 |
+
"eval_steps_per_second": 0.406
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 4136504477614080.0,
|
| 4 |
+
"train_loss": 0.39363470135430095,
|
| 5 |
+
"train_runtime": 36289.8965,
|
| 6 |
+
"train_samples_per_second": 34.825,
|
| 7 |
+
"train_steps_per_second": 0.068
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1811 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2470,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.020242914979757085,
|
| 13 |
+
"grad_norm": 2.8825272538542044,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7569,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04048582995951417,
|
| 20 |
+
"grad_norm": 2.3606485385931157,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.6504,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06072874493927125,
|
| 27 |
+
"grad_norm": 1.426935919321139,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6287,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08097165991902834,
|
| 34 |
+
"grad_norm": 1.9896158325770887,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6136,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10121457489878542,
|
| 41 |
+
"grad_norm": 1.2993488018928139,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6036,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1214574898785425,
|
| 48 |
+
"grad_norm": 1.3692905065095424,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.5974,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1417004048582996,
|
| 55 |
+
"grad_norm": 1.817904836385203,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.5925,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16194331983805668,
|
| 62 |
+
"grad_norm": 1.37930069536892,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.5878,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18218623481781376,
|
| 69 |
+
"grad_norm": 1.9672481173378518,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.5869,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.20242914979757085,
|
| 76 |
+
"grad_norm": 1.5190200995442689,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.5895,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.22267206477732793,
|
| 83 |
+
"grad_norm": 1.467909545843528,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.5814,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.242914979757085,
|
| 90 |
+
"grad_norm": 1.2624328705735892,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.579,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2631578947368421,
|
| 97 |
+
"grad_norm": 2.8330967598290644,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.5783,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2834008097165992,
|
| 104 |
+
"grad_norm": 2.606189250371495,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.5692,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.30364372469635625,
|
| 111 |
+
"grad_norm": 2.0755945998925616,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.5778,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.32388663967611336,
|
| 118 |
+
"grad_norm": 2.112489158829737,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.5757,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3441295546558704,
|
| 125 |
+
"grad_norm": 1.773147820799013,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.5757,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3643724696356275,
|
| 132 |
+
"grad_norm": 1.9389286348778036,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.5699,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.38461538461538464,
|
| 139 |
+
"grad_norm": 2.0257261841165506,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.5708,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4048582995951417,
|
| 146 |
+
"grad_norm": 1.6235586407175255,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.5664,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.4251012145748988,
|
| 153 |
+
"grad_norm": 1.3600120185742202,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.5624,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.44534412955465585,
|
| 160 |
+
"grad_norm": 1.5782442409144959,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.5686,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.46558704453441296,
|
| 167 |
+
"grad_norm": 1.9084679996506322,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.5681,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.48582995951417,
|
| 174 |
+
"grad_norm": 1.562642052863713,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.5643,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5060728744939271,
|
| 181 |
+
"grad_norm": 1.9619840593224824,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.5666,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5263157894736842,
|
| 188 |
+
"grad_norm": 1.5861604962625888,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.5518,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5465587044534413,
|
| 195 |
+
"grad_norm": 1.7006302815881864,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.5605,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5668016194331984,
|
| 202 |
+
"grad_norm": 1.6651788716675646,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.5568,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5870445344129555,
|
| 209 |
+
"grad_norm": 2.2785089542841708,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.5565,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6072874493927125,
|
| 216 |
+
"grad_norm": 1.5770155712986973,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.5575,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6275303643724697,
|
| 223 |
+
"grad_norm": 1.3220149177446632,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.5622,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6477732793522267,
|
| 230 |
+
"grad_norm": 1.3472535369102203,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.5594,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6680161943319838,
|
| 237 |
+
"grad_norm": 1.3309997590990947,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.5601,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6882591093117408,
|
| 244 |
+
"grad_norm": 1.4273218646615096,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.5601,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.708502024291498,
|
| 251 |
+
"grad_norm": 1.2085847860457979,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.5619,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.728744939271255,
|
| 258 |
+
"grad_norm": 1.122941072415825,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.564,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7489878542510121,
|
| 265 |
+
"grad_norm": 1.3973216531402086,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.5571,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7692307692307693,
|
| 272 |
+
"grad_norm": 1.18082932151255,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.5538,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7894736842105263,
|
| 279 |
+
"grad_norm": 1.1780579152037594,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.557,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8097165991902834,
|
| 286 |
+
"grad_norm": 1.3785246959799171,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.5576,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8299595141700404,
|
| 293 |
+
"grad_norm": 1.2948034196229,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.5524,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8502024291497976,
|
| 300 |
+
"grad_norm": 1.186346298990548,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.5598,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8704453441295547,
|
| 307 |
+
"grad_norm": 1.1531795830071445,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.5532,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8906882591093117,
|
| 314 |
+
"grad_norm": 1.238207775770585,
|
| 315 |
+
"learning_rate": 5e-06,
|
| 316 |
+
"loss": 0.5587,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9109311740890689,
|
| 321 |
+
"grad_norm": 1.579785932754029,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.5499,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9311740890688259,
|
| 328 |
+
"grad_norm": 1.0932455184252672,
|
| 329 |
+
"learning_rate": 5e-06,
|
| 330 |
+
"loss": 0.5547,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.951417004048583,
|
| 335 |
+
"grad_norm": 1.1455184663362503,
|
| 336 |
+
"learning_rate": 5e-06,
|
| 337 |
+
"loss": 0.5548,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.97165991902834,
|
| 342 |
+
"grad_norm": 1.0783335686803248,
|
| 343 |
+
"learning_rate": 5e-06,
|
| 344 |
+
"loss": 0.5515,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.9919028340080972,
|
| 349 |
+
"grad_norm": 1.221913718764988,
|
| 350 |
+
"learning_rate": 5e-06,
|
| 351 |
+
"loss": 0.5486,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.0,
|
| 356 |
+
"eval_loss": 0.27600792050361633,
|
| 357 |
+
"eval_runtime": 127.9056,
|
| 358 |
+
"eval_samples_per_second": 104.014,
|
| 359 |
+
"eval_steps_per_second": 0.407,
|
| 360 |
+
"step": 494
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.0121457489878543,
|
| 364 |
+
"grad_norm": 1.946031690795471,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5099,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.0323886639676114,
|
| 371 |
+
"grad_norm": 1.9289680946263923,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.4748,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.0526315789473684,
|
| 378 |
+
"grad_norm": 1.353788705122084,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.468,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.0728744939271255,
|
| 385 |
+
"grad_norm": 1.205205720059485,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.4735,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0931174089068827,
|
| 392 |
+
"grad_norm": 1.282155131195443,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.4657,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.1133603238866396,
|
| 399 |
+
"grad_norm": 1.5080942345199266,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.4699,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.1336032388663968,
|
| 406 |
+
"grad_norm": 2.00023442913857,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.4659,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.1538461538461537,
|
| 413 |
+
"grad_norm": 1.7909520333071323,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.4715,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.174089068825911,
|
| 420 |
+
"grad_norm": 1.6662712618465199,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.4705,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.194331983805668,
|
| 427 |
+
"grad_norm": 1.3259873704215552,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.4633,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.214574898785425,
|
| 434 |
+
"grad_norm": 1.6651495485618664,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.4706,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.2348178137651822,
|
| 441 |
+
"grad_norm": 1.477115453248806,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.4674,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.2550607287449393,
|
| 448 |
+
"grad_norm": 1.263440522189552,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.4715,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.2753036437246963,
|
| 455 |
+
"grad_norm": 1.4025183176779765,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.4715,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.2955465587044535,
|
| 462 |
+
"grad_norm": 1.3060745387835275,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.473,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.3157894736842106,
|
| 469 |
+
"grad_norm": 1.2936497262200077,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.4775,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.3360323886639676,
|
| 476 |
+
"grad_norm": 1.2889809170808153,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.4671,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.3562753036437247,
|
| 483 |
+
"grad_norm": 1.3063275232148253,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.4808,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.376518218623482,
|
| 490 |
+
"grad_norm": 1.1392335054785994,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.4765,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.3967611336032388,
|
| 497 |
+
"grad_norm": 1.1028492143829693,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.4759,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.417004048582996,
|
| 504 |
+
"grad_norm": 1.1765124226702088,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.4739,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.4372469635627532,
|
| 511 |
+
"grad_norm": 1.2359278437898007,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.4799,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.45748987854251,
|
| 518 |
+
"grad_norm": 1.206361807359358,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.4792,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.4777327935222673,
|
| 525 |
+
"grad_norm": 1.2584288631713865,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.4829,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.4979757085020242,
|
| 532 |
+
"grad_norm": 1.3266851287176349,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.4757,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.5182186234817814,
|
| 539 |
+
"grad_norm": 1.174062885309594,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.4786,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.5384615384615383,
|
| 546 |
+
"grad_norm": 1.217286859959994,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.48,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.5587044534412957,
|
| 553 |
+
"grad_norm": 1.2963071104766335,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.4771,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.5789473684210527,
|
| 560 |
+
"grad_norm": 1.1301017979019057,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.4788,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.5991902834008096,
|
| 567 |
+
"grad_norm": 1.2142771905592493,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.4813,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.6194331983805668,
|
| 574 |
+
"grad_norm": 1.1156710660198195,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.478,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.639676113360324,
|
| 581 |
+
"grad_norm": 1.3426333112263065,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.4712,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.6599190283400809,
|
| 588 |
+
"grad_norm": 1.3351933873992157,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.4782,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.680161943319838,
|
| 595 |
+
"grad_norm": 1.1798934266276804,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.4759,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.7004048582995952,
|
| 602 |
+
"grad_norm": 1.0719853459322617,
|
| 603 |
+
"learning_rate": 5e-06,
|
| 604 |
+
"loss": 0.4751,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.7206477732793521,
|
| 609 |
+
"grad_norm": 1.1539682879539461,
|
| 610 |
+
"learning_rate": 5e-06,
|
| 611 |
+
"loss": 0.4787,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.7408906882591093,
|
| 616 |
+
"grad_norm": 1.1331656389881875,
|
| 617 |
+
"learning_rate": 5e-06,
|
| 618 |
+
"loss": 0.4782,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.7611336032388665,
|
| 623 |
+
"grad_norm": 1.2305656250383992,
|
| 624 |
+
"learning_rate": 5e-06,
|
| 625 |
+
"loss": 0.4808,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.7813765182186234,
|
| 630 |
+
"grad_norm": 1.484161550142479,
|
| 631 |
+
"learning_rate": 5e-06,
|
| 632 |
+
"loss": 0.4829,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.8016194331983806,
|
| 637 |
+
"grad_norm": 1.180007815990233,
|
| 638 |
+
"learning_rate": 5e-06,
|
| 639 |
+
"loss": 0.4781,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.8218623481781377,
|
| 644 |
+
"grad_norm": 1.200692474334057,
|
| 645 |
+
"learning_rate": 5e-06,
|
| 646 |
+
"loss": 0.4779,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.8421052631578947,
|
| 651 |
+
"grad_norm": 1.1652057043804007,
|
| 652 |
+
"learning_rate": 5e-06,
|
| 653 |
+
"loss": 0.48,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.8623481781376519,
|
| 658 |
+
"grad_norm": 1.2546941772227673,
|
| 659 |
+
"learning_rate": 5e-06,
|
| 660 |
+
"loss": 0.4796,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.882591093117409,
|
| 665 |
+
"grad_norm": 1.1919644772038955,
|
| 666 |
+
"learning_rate": 5e-06,
|
| 667 |
+
"loss": 0.4754,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.902834008097166,
|
| 672 |
+
"grad_norm": 1.086719187935772,
|
| 673 |
+
"learning_rate": 5e-06,
|
| 674 |
+
"loss": 0.4798,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.9230769230769231,
|
| 679 |
+
"grad_norm": 1.1603089251078402,
|
| 680 |
+
"learning_rate": 5e-06,
|
| 681 |
+
"loss": 0.4816,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.9433198380566803,
|
| 686 |
+
"grad_norm": 1.082753063279857,
|
| 687 |
+
"learning_rate": 5e-06,
|
| 688 |
+
"loss": 0.4842,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.9635627530364372,
|
| 693 |
+
"grad_norm": 1.1470965026545579,
|
| 694 |
+
"learning_rate": 5e-06,
|
| 695 |
+
"loss": 0.4826,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.9838056680161942,
|
| 700 |
+
"grad_norm": 1.317035146950926,
|
| 701 |
+
"learning_rate": 5e-06,
|
| 702 |
+
"loss": 0.4834,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.0,
|
| 707 |
+
"eval_loss": 0.2760300040245056,
|
| 708 |
+
"eval_runtime": 128.3279,
|
| 709 |
+
"eval_samples_per_second": 103.672,
|
| 710 |
+
"eval_steps_per_second": 0.405,
|
| 711 |
+
"step": 988
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.0040485829959516,
|
| 715 |
+
"grad_norm": 2.423406809168664,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.4596,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.0242914979757085,
|
| 722 |
+
"grad_norm": 1.8171058614039022,
|
| 723 |
+
"learning_rate": 5e-06,
|
| 724 |
+
"loss": 0.3883,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.0445344129554655,
|
| 729 |
+
"grad_norm": 1.5419534841689435,
|
| 730 |
+
"learning_rate": 5e-06,
|
| 731 |
+
"loss": 0.3836,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.064777327935223,
|
| 736 |
+
"grad_norm": 1.476614885030913,
|
| 737 |
+
"learning_rate": 5e-06,
|
| 738 |
+
"loss": 0.3801,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.08502024291498,
|
| 743 |
+
"grad_norm": 1.379440361306421,
|
| 744 |
+
"learning_rate": 5e-06,
|
| 745 |
+
"loss": 0.3784,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.1052631578947367,
|
| 750 |
+
"grad_norm": 1.4083322026387224,
|
| 751 |
+
"learning_rate": 5e-06,
|
| 752 |
+
"loss": 0.3778,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.125506072874494,
|
| 757 |
+
"grad_norm": 1.4696113259366608,
|
| 758 |
+
"learning_rate": 5e-06,
|
| 759 |
+
"loss": 0.3879,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.145748987854251,
|
| 764 |
+
"grad_norm": 1.2713132554208233,
|
| 765 |
+
"learning_rate": 5e-06,
|
| 766 |
+
"loss": 0.3806,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.165991902834008,
|
| 771 |
+
"grad_norm": 1.3917546218353265,
|
| 772 |
+
"learning_rate": 5e-06,
|
| 773 |
+
"loss": 0.386,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.1862348178137654,
|
| 778 |
+
"grad_norm": 1.4708546369587632,
|
| 779 |
+
"learning_rate": 5e-06,
|
| 780 |
+
"loss": 0.3845,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.2064777327935223,
|
| 785 |
+
"grad_norm": 1.595163601660772,
|
| 786 |
+
"learning_rate": 5e-06,
|
| 787 |
+
"loss": 0.3828,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.2267206477732793,
|
| 792 |
+
"grad_norm": 1.4877074059133855,
|
| 793 |
+
"learning_rate": 5e-06,
|
| 794 |
+
"loss": 0.3897,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.246963562753036,
|
| 799 |
+
"grad_norm": 1.7370364288636082,
|
| 800 |
+
"learning_rate": 5e-06,
|
| 801 |
+
"loss": 0.3875,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.2672064777327936,
|
| 806 |
+
"grad_norm": 1.8541525908514815,
|
| 807 |
+
"learning_rate": 5e-06,
|
| 808 |
+
"loss": 0.3884,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.2874493927125505,
|
| 813 |
+
"grad_norm": 1.5781496384158298,
|
| 814 |
+
"learning_rate": 5e-06,
|
| 815 |
+
"loss": 0.3894,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.3076923076923075,
|
| 820 |
+
"grad_norm": 1.7708762236924664,
|
| 821 |
+
"learning_rate": 5e-06,
|
| 822 |
+
"loss": 0.3859,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.327935222672065,
|
| 827 |
+
"grad_norm": 1.4475591252123796,
|
| 828 |
+
"learning_rate": 5e-06,
|
| 829 |
+
"loss": 0.3887,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.348178137651822,
|
| 834 |
+
"grad_norm": 1.2226909125336796,
|
| 835 |
+
"learning_rate": 5e-06,
|
| 836 |
+
"loss": 0.3885,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.3684210526315788,
|
| 841 |
+
"grad_norm": 1.3657056897603896,
|
| 842 |
+
"learning_rate": 5e-06,
|
| 843 |
+
"loss": 0.392,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.388663967611336,
|
| 848 |
+
"grad_norm": 1.314590138508193,
|
| 849 |
+
"learning_rate": 5e-06,
|
| 850 |
+
"loss": 0.3926,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.408906882591093,
|
| 855 |
+
"grad_norm": 1.4093248309707875,
|
| 856 |
+
"learning_rate": 5e-06,
|
| 857 |
+
"loss": 0.3929,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.42914979757085,
|
| 862 |
+
"grad_norm": 1.3473340294150489,
|
| 863 |
+
"learning_rate": 5e-06,
|
| 864 |
+
"loss": 0.39,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.4493927125506074,
|
| 869 |
+
"grad_norm": 1.4512860257939517,
|
| 870 |
+
"learning_rate": 5e-06,
|
| 871 |
+
"loss": 0.3902,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.4696356275303644,
|
| 876 |
+
"grad_norm": 1.4529803502641332,
|
| 877 |
+
"learning_rate": 5e-06,
|
| 878 |
+
"loss": 0.3947,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.4898785425101213,
|
| 883 |
+
"grad_norm": 1.384452479045095,
|
| 884 |
+
"learning_rate": 5e-06,
|
| 885 |
+
"loss": 0.3953,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.5101214574898787,
|
| 890 |
+
"grad_norm": 1.2935497884972742,
|
| 891 |
+
"learning_rate": 5e-06,
|
| 892 |
+
"loss": 0.3986,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.5303643724696356,
|
| 897 |
+
"grad_norm": 1.190834719805313,
|
| 898 |
+
"learning_rate": 5e-06,
|
| 899 |
+
"loss": 0.3914,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.5506072874493926,
|
| 904 |
+
"grad_norm": 1.5623940633492222,
|
| 905 |
+
"learning_rate": 5e-06,
|
| 906 |
+
"loss": 0.3887,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.57085020242915,
|
| 911 |
+
"grad_norm": 1.4071250725201772,
|
| 912 |
+
"learning_rate": 5e-06,
|
| 913 |
+
"loss": 0.3941,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.591093117408907,
|
| 918 |
+
"grad_norm": 1.4686855669517231,
|
| 919 |
+
"learning_rate": 5e-06,
|
| 920 |
+
"loss": 0.3956,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.611336032388664,
|
| 925 |
+
"grad_norm": 1.29119112691104,
|
| 926 |
+
"learning_rate": 5e-06,
|
| 927 |
+
"loss": 0.3998,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.6315789473684212,
|
| 932 |
+
"grad_norm": 1.2673323070448081,
|
| 933 |
+
"learning_rate": 5e-06,
|
| 934 |
+
"loss": 0.3961,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.651821862348178,
|
| 939 |
+
"grad_norm": 1.2450186102009178,
|
| 940 |
+
"learning_rate": 5e-06,
|
| 941 |
+
"loss": 0.395,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.672064777327935,
|
| 946 |
+
"grad_norm": 1.3598218086289704,
|
| 947 |
+
"learning_rate": 5e-06,
|
| 948 |
+
"loss": 0.3969,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.6923076923076925,
|
| 953 |
+
"grad_norm": 1.476188415686639,
|
| 954 |
+
"learning_rate": 5e-06,
|
| 955 |
+
"loss": 0.401,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.7125506072874495,
|
| 960 |
+
"grad_norm": 1.2772087881864984,
|
| 961 |
+
"learning_rate": 5e-06,
|
| 962 |
+
"loss": 0.3981,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.7327935222672064,
|
| 967 |
+
"grad_norm": 1.3901040643475941,
|
| 968 |
+
"learning_rate": 5e-06,
|
| 969 |
+
"loss": 0.399,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.753036437246964,
|
| 974 |
+
"grad_norm": 1.2669956962100783,
|
| 975 |
+
"learning_rate": 5e-06,
|
| 976 |
+
"loss": 0.3936,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.7732793522267207,
|
| 981 |
+
"grad_norm": 1.3605832094262316,
|
| 982 |
+
"learning_rate": 5e-06,
|
| 983 |
+
"loss": 0.3996,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.7935222672064777,
|
| 988 |
+
"grad_norm": 1.4625604256084817,
|
| 989 |
+
"learning_rate": 5e-06,
|
| 990 |
+
"loss": 0.3997,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.813765182186235,
|
| 995 |
+
"grad_norm": 1.784848571739763,
|
| 996 |
+
"learning_rate": 5e-06,
|
| 997 |
+
"loss": 0.4012,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.834008097165992,
|
| 1002 |
+
"grad_norm": 1.6211701201270445,
|
| 1003 |
+
"learning_rate": 5e-06,
|
| 1004 |
+
"loss": 0.3948,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.854251012145749,
|
| 1009 |
+
"grad_norm": 1.5362470053479813,
|
| 1010 |
+
"learning_rate": 5e-06,
|
| 1011 |
+
"loss": 0.4017,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.8744939271255063,
|
| 1016 |
+
"grad_norm": 1.4029392342160418,
|
| 1017 |
+
"learning_rate": 5e-06,
|
| 1018 |
+
"loss": 0.3992,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.8947368421052633,
|
| 1023 |
+
"grad_norm": 1.4342688190560124,
|
| 1024 |
+
"learning_rate": 5e-06,
|
| 1025 |
+
"loss": 0.395,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.91497975708502,
|
| 1030 |
+
"grad_norm": 1.2695118103828797,
|
| 1031 |
+
"learning_rate": 5e-06,
|
| 1032 |
+
"loss": 0.4008,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.9352226720647776,
|
| 1037 |
+
"grad_norm": 1.2741085284215934,
|
| 1038 |
+
"learning_rate": 5e-06,
|
| 1039 |
+
"loss": 0.4111,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.9554655870445345,
|
| 1044 |
+
"grad_norm": 1.2910941516817205,
|
| 1045 |
+
"learning_rate": 5e-06,
|
| 1046 |
+
"loss": 0.3975,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.9757085020242915,
|
| 1051 |
+
"grad_norm": 1.4853937254356013,
|
| 1052 |
+
"learning_rate": 5e-06,
|
| 1053 |
+
"loss": 0.4012,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.9959514170040484,
|
| 1058 |
+
"grad_norm": 1.4022248360408927,
|
| 1059 |
+
"learning_rate": 5e-06,
|
| 1060 |
+
"loss": 0.4034,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 3.0,
|
| 1065 |
+
"eval_loss": 0.29170867800712585,
|
| 1066 |
+
"eval_runtime": 128.4123,
|
| 1067 |
+
"eval_samples_per_second": 103.604,
|
| 1068 |
+
"eval_steps_per_second": 0.405,
|
| 1069 |
+
"step": 1482
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 3.016194331983806,
|
| 1073 |
+
"grad_norm": 2.450301362827223,
|
| 1074 |
+
"learning_rate": 5e-06,
|
| 1075 |
+
"loss": 0.3253,
|
| 1076 |
+
"step": 1490
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.0364372469635628,
|
| 1080 |
+
"grad_norm": 1.7227064520999624,
|
| 1081 |
+
"learning_rate": 5e-06,
|
| 1082 |
+
"loss": 0.2917,
|
| 1083 |
+
"step": 1500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 3.0566801619433197,
|
| 1087 |
+
"grad_norm": 1.708297211407951,
|
| 1088 |
+
"learning_rate": 5e-06,
|
| 1089 |
+
"loss": 0.2951,
|
| 1090 |
+
"step": 1510
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 3.076923076923077,
|
| 1094 |
+
"grad_norm": 1.6773762742996041,
|
| 1095 |
+
"learning_rate": 5e-06,
|
| 1096 |
+
"loss": 0.2916,
|
| 1097 |
+
"step": 1520
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.097165991902834,
|
| 1101 |
+
"grad_norm": 1.5835044005502448,
|
| 1102 |
+
"learning_rate": 5e-06,
|
| 1103 |
+
"loss": 0.2949,
|
| 1104 |
+
"step": 1530
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 3.117408906882591,
|
| 1108 |
+
"grad_norm": 1.6991756969105973,
|
| 1109 |
+
"learning_rate": 5e-06,
|
| 1110 |
+
"loss": 0.2906,
|
| 1111 |
+
"step": 1540
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 3.1376518218623484,
|
| 1115 |
+
"grad_norm": 1.6309085248071211,
|
| 1116 |
+
"learning_rate": 5e-06,
|
| 1117 |
+
"loss": 0.2887,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 3.1578947368421053,
|
| 1122 |
+
"grad_norm": 1.467082791239925,
|
| 1123 |
+
"learning_rate": 5e-06,
|
| 1124 |
+
"loss": 0.2958,
|
| 1125 |
+
"step": 1560
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 3.1781376518218623,
|
| 1129 |
+
"grad_norm": 1.5977415982902385,
|
| 1130 |
+
"learning_rate": 5e-06,
|
| 1131 |
+
"loss": 0.2958,
|
| 1132 |
+
"step": 1570
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 3.1983805668016196,
|
| 1136 |
+
"grad_norm": 1.794838585622722,
|
| 1137 |
+
"learning_rate": 5e-06,
|
| 1138 |
+
"loss": 0.2985,
|
| 1139 |
+
"step": 1580
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 3.2186234817813766,
|
| 1143 |
+
"grad_norm": 1.6188047839576813,
|
| 1144 |
+
"learning_rate": 5e-06,
|
| 1145 |
+
"loss": 0.3009,
|
| 1146 |
+
"step": 1590
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 3.2388663967611335,
|
| 1150 |
+
"grad_norm": 1.5996247856636512,
|
| 1151 |
+
"learning_rate": 5e-06,
|
| 1152 |
+
"loss": 0.2993,
|
| 1153 |
+
"step": 1600
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 3.2591093117408905,
|
| 1157 |
+
"grad_norm": 1.5799607329692924,
|
| 1158 |
+
"learning_rate": 5e-06,
|
| 1159 |
+
"loss": 0.2981,
|
| 1160 |
+
"step": 1610
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 3.279352226720648,
|
| 1164 |
+
"grad_norm": 1.6462393560491397,
|
| 1165 |
+
"learning_rate": 5e-06,
|
| 1166 |
+
"loss": 0.3014,
|
| 1167 |
+
"step": 1620
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 3.299595141700405,
|
| 1171 |
+
"grad_norm": 1.743995264000295,
|
| 1172 |
+
"learning_rate": 5e-06,
|
| 1173 |
+
"loss": 0.3034,
|
| 1174 |
+
"step": 1630
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 3.3198380566801617,
|
| 1178 |
+
"grad_norm": 1.6858202723993232,
|
| 1179 |
+
"learning_rate": 5e-06,
|
| 1180 |
+
"loss": 0.303,
|
| 1181 |
+
"step": 1640
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 3.340080971659919,
|
| 1185 |
+
"grad_norm": 1.8191610290572566,
|
| 1186 |
+
"learning_rate": 5e-06,
|
| 1187 |
+
"loss": 0.3003,
|
| 1188 |
+
"step": 1650
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 3.360323886639676,
|
| 1192 |
+
"grad_norm": 1.601413073895001,
|
| 1193 |
+
"learning_rate": 5e-06,
|
| 1194 |
+
"loss": 0.3051,
|
| 1195 |
+
"step": 1660
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 3.380566801619433,
|
| 1199 |
+
"grad_norm": 1.7563790440673033,
|
| 1200 |
+
"learning_rate": 5e-06,
|
| 1201 |
+
"loss": 0.2999,
|
| 1202 |
+
"step": 1670
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 3.4008097165991904,
|
| 1206 |
+
"grad_norm": 1.5579994158970751,
|
| 1207 |
+
"learning_rate": 5e-06,
|
| 1208 |
+
"loss": 0.2989,
|
| 1209 |
+
"step": 1680
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.4210526315789473,
|
| 1213 |
+
"grad_norm": 1.516213960669368,
|
| 1214 |
+
"learning_rate": 5e-06,
|
| 1215 |
+
"loss": 0.3011,
|
| 1216 |
+
"step": 1690
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 3.4412955465587043,
|
| 1220 |
+
"grad_norm": 1.658051304756316,
|
| 1221 |
+
"learning_rate": 5e-06,
|
| 1222 |
+
"loss": 0.3024,
|
| 1223 |
+
"step": 1700
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 3.4615384615384617,
|
| 1227 |
+
"grad_norm": 1.5918375939252065,
|
| 1228 |
+
"learning_rate": 5e-06,
|
| 1229 |
+
"loss": 0.3056,
|
| 1230 |
+
"step": 1710
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 3.4817813765182186,
|
| 1234 |
+
"grad_norm": 1.6167160427713403,
|
| 1235 |
+
"learning_rate": 5e-06,
|
| 1236 |
+
"loss": 0.3059,
|
| 1237 |
+
"step": 1720
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 3.5020242914979756,
|
| 1241 |
+
"grad_norm": 1.633353659275257,
|
| 1242 |
+
"learning_rate": 5e-06,
|
| 1243 |
+
"loss": 0.3103,
|
| 1244 |
+
"step": 1730
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 3.522267206477733,
|
| 1248 |
+
"grad_norm": 1.6652424042294116,
|
| 1249 |
+
"learning_rate": 5e-06,
|
| 1250 |
+
"loss": 0.3047,
|
| 1251 |
+
"step": 1740
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 3.54251012145749,
|
| 1255 |
+
"grad_norm": 1.5945478465514338,
|
| 1256 |
+
"learning_rate": 5e-06,
|
| 1257 |
+
"loss": 0.3097,
|
| 1258 |
+
"step": 1750
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 3.562753036437247,
|
| 1262 |
+
"grad_norm": 1.4266070240229398,
|
| 1263 |
+
"learning_rate": 5e-06,
|
| 1264 |
+
"loss": 0.3053,
|
| 1265 |
+
"step": 1760
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 3.582995951417004,
|
| 1269 |
+
"grad_norm": 1.5417916459202972,
|
| 1270 |
+
"learning_rate": 5e-06,
|
| 1271 |
+
"loss": 0.3107,
|
| 1272 |
+
"step": 1770
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 3.603238866396761,
|
| 1276 |
+
"grad_norm": 1.6806576746631992,
|
| 1277 |
+
"learning_rate": 5e-06,
|
| 1278 |
+
"loss": 0.3077,
|
| 1279 |
+
"step": 1780
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 3.623481781376518,
|
| 1283 |
+
"grad_norm": 1.6366680075861002,
|
| 1284 |
+
"learning_rate": 5e-06,
|
| 1285 |
+
"loss": 0.3096,
|
| 1286 |
+
"step": 1790
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 3.6437246963562755,
|
| 1290 |
+
"grad_norm": 1.8008610671747132,
|
| 1291 |
+
"learning_rate": 5e-06,
|
| 1292 |
+
"loss": 0.3095,
|
| 1293 |
+
"step": 1800
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 3.6639676113360324,
|
| 1297 |
+
"grad_norm": 1.7218050046753175,
|
| 1298 |
+
"learning_rate": 5e-06,
|
| 1299 |
+
"loss": 0.3129,
|
| 1300 |
+
"step": 1810
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 3.6842105263157894,
|
| 1304 |
+
"grad_norm": 1.54966815167092,
|
| 1305 |
+
"learning_rate": 5e-06,
|
| 1306 |
+
"loss": 0.3089,
|
| 1307 |
+
"step": 1820
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 3.7044534412955468,
|
| 1311 |
+
"grad_norm": 1.5907699518804959,
|
| 1312 |
+
"learning_rate": 5e-06,
|
| 1313 |
+
"loss": 0.3115,
|
| 1314 |
+
"step": 1830
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.7246963562753037,
|
| 1318 |
+
"grad_norm": 1.5950760981279428,
|
| 1319 |
+
"learning_rate": 5e-06,
|
| 1320 |
+
"loss": 0.3132,
|
| 1321 |
+
"step": 1840
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 3.7449392712550607,
|
| 1325 |
+
"grad_norm": 1.6178462612967588,
|
| 1326 |
+
"learning_rate": 5e-06,
|
| 1327 |
+
"loss": 0.3112,
|
| 1328 |
+
"step": 1850
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 3.765182186234818,
|
| 1332 |
+
"grad_norm": 1.6595052047937346,
|
| 1333 |
+
"learning_rate": 5e-06,
|
| 1334 |
+
"loss": 0.3144,
|
| 1335 |
+
"step": 1860
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 3.785425101214575,
|
| 1339 |
+
"grad_norm": 1.5960921622659012,
|
| 1340 |
+
"learning_rate": 5e-06,
|
| 1341 |
+
"loss": 0.3181,
|
| 1342 |
+
"step": 1870
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 3.805668016194332,
|
| 1346 |
+
"grad_norm": 1.8789757609659636,
|
| 1347 |
+
"learning_rate": 5e-06,
|
| 1348 |
+
"loss": 0.3128,
|
| 1349 |
+
"step": 1880
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 3.8259109311740893,
|
| 1353 |
+
"grad_norm": 1.6017653115735,
|
| 1354 |
+
"learning_rate": 5e-06,
|
| 1355 |
+
"loss": 0.318,
|
| 1356 |
+
"step": 1890
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 3.8461538461538463,
|
| 1360 |
+
"grad_norm": 1.4883871110556444,
|
| 1361 |
+
"learning_rate": 5e-06,
|
| 1362 |
+
"loss": 0.3168,
|
| 1363 |
+
"step": 1900
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 3.866396761133603,
|
| 1367 |
+
"grad_norm": 1.7783804818718214,
|
| 1368 |
+
"learning_rate": 5e-06,
|
| 1369 |
+
"loss": 0.3114,
|
| 1370 |
+
"step": 1910
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 3.8866396761133606,
|
| 1374 |
+
"grad_norm": 1.7097670030385954,
|
| 1375 |
+
"learning_rate": 5e-06,
|
| 1376 |
+
"loss": 0.3196,
|
| 1377 |
+
"step": 1920
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 3.9068825910931175,
|
| 1381 |
+
"grad_norm": 1.519954953217676,
|
| 1382 |
+
"learning_rate": 5e-06,
|
| 1383 |
+
"loss": 0.3161,
|
| 1384 |
+
"step": 1930
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 3.9271255060728745,
|
| 1388 |
+
"grad_norm": 1.5786075983313086,
|
| 1389 |
+
"learning_rate": 5e-06,
|
| 1390 |
+
"loss": 0.3142,
|
| 1391 |
+
"step": 1940
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 3.9473684210526314,
|
| 1395 |
+
"grad_norm": 1.8339039956017331,
|
| 1396 |
+
"learning_rate": 5e-06,
|
| 1397 |
+
"loss": 0.3156,
|
| 1398 |
+
"step": 1950
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 3.967611336032389,
|
| 1402 |
+
"grad_norm": 1.504586213513185,
|
| 1403 |
+
"learning_rate": 5e-06,
|
| 1404 |
+
"loss": 0.3173,
|
| 1405 |
+
"step": 1960
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 3.9878542510121457,
|
| 1409 |
+
"grad_norm": 1.603597507259475,
|
| 1410 |
+
"learning_rate": 5e-06,
|
| 1411 |
+
"loss": 0.3182,
|
| 1412 |
+
"step": 1970
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 4.0,
|
| 1416 |
+
"eval_loss": 0.3246242105960846,
|
| 1417 |
+
"eval_runtime": 128.1021,
|
| 1418 |
+
"eval_samples_per_second": 103.855,
|
| 1419 |
+
"eval_steps_per_second": 0.406,
|
| 1420 |
+
"step": 1976
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 4.008097165991903,
|
| 1424 |
+
"grad_norm": 5.133136743732594,
|
| 1425 |
+
"learning_rate": 5e-06,
|
| 1426 |
+
"loss": 0.2774,
|
| 1427 |
+
"step": 1980
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 4.02834008097166,
|
| 1431 |
+
"grad_norm": 2.5228879416463936,
|
| 1432 |
+
"learning_rate": 5e-06,
|
| 1433 |
+
"loss": 0.2123,
|
| 1434 |
+
"step": 1990
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 4.048582995951417,
|
| 1438 |
+
"grad_norm": 2.0169504998470833,
|
| 1439 |
+
"learning_rate": 5e-06,
|
| 1440 |
+
"loss": 0.2057,
|
| 1441 |
+
"step": 2000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 4.068825910931174,
|
| 1445 |
+
"grad_norm": 1.9085723632427691,
|
| 1446 |
+
"learning_rate": 5e-06,
|
| 1447 |
+
"loss": 0.2061,
|
| 1448 |
+
"step": 2010
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 4.089068825910931,
|
| 1452 |
+
"grad_norm": 1.8551214473550242,
|
| 1453 |
+
"learning_rate": 5e-06,
|
| 1454 |
+
"loss": 0.2058,
|
| 1455 |
+
"step": 2020
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 4.109311740890688,
|
| 1459 |
+
"grad_norm": 1.8804505495475972,
|
| 1460 |
+
"learning_rate": 5e-06,
|
| 1461 |
+
"loss": 0.2076,
|
| 1462 |
+
"step": 2030
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 4.129554655870446,
|
| 1466 |
+
"grad_norm": 1.8325377033435544,
|
| 1467 |
+
"learning_rate": 5e-06,
|
| 1468 |
+
"loss": 0.2055,
|
| 1469 |
+
"step": 2040
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 4.149797570850202,
|
| 1473 |
+
"grad_norm": 1.892921271335565,
|
| 1474 |
+
"learning_rate": 5e-06,
|
| 1475 |
+
"loss": 0.2073,
|
| 1476 |
+
"step": 2050
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 4.17004048582996,
|
| 1480 |
+
"grad_norm": 2.00985346837552,
|
| 1481 |
+
"learning_rate": 5e-06,
|
| 1482 |
+
"loss": 0.2084,
|
| 1483 |
+
"step": 2060
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 4.190283400809717,
|
| 1487 |
+
"grad_norm": 1.820158031557001,
|
| 1488 |
+
"learning_rate": 5e-06,
|
| 1489 |
+
"loss": 0.209,
|
| 1490 |
+
"step": 2070
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 4.2105263157894735,
|
| 1494 |
+
"grad_norm": 1.8327459405866524,
|
| 1495 |
+
"learning_rate": 5e-06,
|
| 1496 |
+
"loss": 0.2127,
|
| 1497 |
+
"step": 2080
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 4.230769230769231,
|
| 1501 |
+
"grad_norm": 1.9394580410768052,
|
| 1502 |
+
"learning_rate": 5e-06,
|
| 1503 |
+
"loss": 0.2123,
|
| 1504 |
+
"step": 2090
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 4.251012145748988,
|
| 1508 |
+
"grad_norm": 1.9657450113344472,
|
| 1509 |
+
"learning_rate": 5e-06,
|
| 1510 |
+
"loss": 0.2108,
|
| 1511 |
+
"step": 2100
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 4.271255060728745,
|
| 1515 |
+
"grad_norm": 1.949924211787456,
|
| 1516 |
+
"learning_rate": 5e-06,
|
| 1517 |
+
"loss": 0.2139,
|
| 1518 |
+
"step": 2110
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 4.291497975708502,
|
| 1522 |
+
"grad_norm": 1.8700037789000614,
|
| 1523 |
+
"learning_rate": 5e-06,
|
| 1524 |
+
"loss": 0.2146,
|
| 1525 |
+
"step": 2120
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 4.3117408906882595,
|
| 1529 |
+
"grad_norm": 1.8948956761363887,
|
| 1530 |
+
"learning_rate": 5e-06,
|
| 1531 |
+
"loss": 0.2145,
|
| 1532 |
+
"step": 2130
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 4.331983805668016,
|
| 1536 |
+
"grad_norm": 2.183456888675007,
|
| 1537 |
+
"learning_rate": 5e-06,
|
| 1538 |
+
"loss": 0.2168,
|
| 1539 |
+
"step": 2140
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 4.352226720647773,
|
| 1543 |
+
"grad_norm": 2.01397562728079,
|
| 1544 |
+
"learning_rate": 5e-06,
|
| 1545 |
+
"loss": 0.2151,
|
| 1546 |
+
"step": 2150
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 4.372469635627531,
|
| 1550 |
+
"grad_norm": 2.1466988238739697,
|
| 1551 |
+
"learning_rate": 5e-06,
|
| 1552 |
+
"loss": 0.2148,
|
| 1553 |
+
"step": 2160
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 4.392712550607287,
|
| 1557 |
+
"grad_norm": 1.8790514185213776,
|
| 1558 |
+
"learning_rate": 5e-06,
|
| 1559 |
+
"loss": 0.2159,
|
| 1560 |
+
"step": 2170
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 4.412955465587045,
|
| 1564 |
+
"grad_norm": 1.9845491426747,
|
| 1565 |
+
"learning_rate": 5e-06,
|
| 1566 |
+
"loss": 0.2179,
|
| 1567 |
+
"step": 2180
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 4.433198380566802,
|
| 1571 |
+
"grad_norm": 1.9657898682355717,
|
| 1572 |
+
"learning_rate": 5e-06,
|
| 1573 |
+
"loss": 0.2173,
|
| 1574 |
+
"step": 2190
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 4.4534412955465585,
|
| 1578 |
+
"grad_norm": 1.8874931048307386,
|
| 1579 |
+
"learning_rate": 5e-06,
|
| 1580 |
+
"loss": 0.2156,
|
| 1581 |
+
"step": 2200
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 4.473684210526316,
|
| 1585 |
+
"grad_norm": 1.845963836099471,
|
| 1586 |
+
"learning_rate": 5e-06,
|
| 1587 |
+
"loss": 0.2188,
|
| 1588 |
+
"step": 2210
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 4.493927125506072,
|
| 1592 |
+
"grad_norm": 1.9372215749139772,
|
| 1593 |
+
"learning_rate": 5e-06,
|
| 1594 |
+
"loss": 0.2191,
|
| 1595 |
+
"step": 2220
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 4.51417004048583,
|
| 1599 |
+
"grad_norm": 2.150693124788377,
|
| 1600 |
+
"learning_rate": 5e-06,
|
| 1601 |
+
"loss": 0.2201,
|
| 1602 |
+
"step": 2230
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 4.534412955465587,
|
| 1606 |
+
"grad_norm": 2.0442818699824317,
|
| 1607 |
+
"learning_rate": 5e-06,
|
| 1608 |
+
"loss": 0.22,
|
| 1609 |
+
"step": 2240
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 4.554655870445345,
|
| 1613 |
+
"grad_norm": 1.9514620437414862,
|
| 1614 |
+
"learning_rate": 5e-06,
|
| 1615 |
+
"loss": 0.2185,
|
| 1616 |
+
"step": 2250
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 4.574898785425101,
|
| 1620 |
+
"grad_norm": 1.8963967573781124,
|
| 1621 |
+
"learning_rate": 5e-06,
|
| 1622 |
+
"loss": 0.2213,
|
| 1623 |
+
"step": 2260
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 4.5951417004048585,
|
| 1627 |
+
"grad_norm": 1.8526961706560494,
|
| 1628 |
+
"learning_rate": 5e-06,
|
| 1629 |
+
"loss": 0.2221,
|
| 1630 |
+
"step": 2270
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 4.615384615384615,
|
| 1634 |
+
"grad_norm": 1.9821664496420446,
|
| 1635 |
+
"learning_rate": 5e-06,
|
| 1636 |
+
"loss": 0.2214,
|
| 1637 |
+
"step": 2280
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 4.635627530364372,
|
| 1641 |
+
"grad_norm": 1.915513929466144,
|
| 1642 |
+
"learning_rate": 5e-06,
|
| 1643 |
+
"loss": 0.2237,
|
| 1644 |
+
"step": 2290
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 4.65587044534413,
|
| 1648 |
+
"grad_norm": 1.8762006846363004,
|
| 1649 |
+
"learning_rate": 5e-06,
|
| 1650 |
+
"loss": 0.2249,
|
| 1651 |
+
"step": 2300
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 4.676113360323887,
|
| 1655 |
+
"grad_norm": 1.9227849786208417,
|
| 1656 |
+
"learning_rate": 5e-06,
|
| 1657 |
+
"loss": 0.2265,
|
| 1658 |
+
"step": 2310
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 4.696356275303644,
|
| 1662 |
+
"grad_norm": 1.9572380827157467,
|
| 1663 |
+
"learning_rate": 5e-06,
|
| 1664 |
+
"loss": 0.2265,
|
| 1665 |
+
"step": 2320
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 4.716599190283401,
|
| 1669 |
+
"grad_norm": 1.8826393602367635,
|
| 1670 |
+
"learning_rate": 5e-06,
|
| 1671 |
+
"loss": 0.2252,
|
| 1672 |
+
"step": 2330
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 4.7368421052631575,
|
| 1676 |
+
"grad_norm": 1.825743956937918,
|
| 1677 |
+
"learning_rate": 5e-06,
|
| 1678 |
+
"loss": 0.2234,
|
| 1679 |
+
"step": 2340
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 4.757085020242915,
|
| 1683 |
+
"grad_norm": 2.194102804306542,
|
| 1684 |
+
"learning_rate": 5e-06,
|
| 1685 |
+
"loss": 0.2243,
|
| 1686 |
+
"step": 2350
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 4.777327935222672,
|
| 1690 |
+
"grad_norm": 1.8765617982862395,
|
| 1691 |
+
"learning_rate": 5e-06,
|
| 1692 |
+
"loss": 0.2246,
|
| 1693 |
+
"step": 2360
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 4.797570850202429,
|
| 1697 |
+
"grad_norm": 1.8687466226351828,
|
| 1698 |
+
"learning_rate": 5e-06,
|
| 1699 |
+
"loss": 0.2276,
|
| 1700 |
+
"step": 2370
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 4.817813765182186,
|
| 1704 |
+
"grad_norm": 1.7759017848087686,
|
| 1705 |
+
"learning_rate": 5e-06,
|
| 1706 |
+
"loss": 0.2257,
|
| 1707 |
+
"step": 2380
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 4.838056680161944,
|
| 1711 |
+
"grad_norm": 1.8906492602012772,
|
| 1712 |
+
"learning_rate": 5e-06,
|
| 1713 |
+
"loss": 0.2253,
|
| 1714 |
+
"step": 2390
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 4.8582995951417,
|
| 1718 |
+
"grad_norm": 2.050008885412097,
|
| 1719 |
+
"learning_rate": 5e-06,
|
| 1720 |
+
"loss": 0.2294,
|
| 1721 |
+
"step": 2400
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 4.8785425101214575,
|
| 1725 |
+
"grad_norm": 1.9449950754235916,
|
| 1726 |
+
"learning_rate": 5e-06,
|
| 1727 |
+
"loss": 0.2307,
|
| 1728 |
+
"step": 2410
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 4.898785425101215,
|
| 1732 |
+
"grad_norm": 1.866407529076546,
|
| 1733 |
+
"learning_rate": 5e-06,
|
| 1734 |
+
"loss": 0.2293,
|
| 1735 |
+
"step": 2420
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 4.919028340080971,
|
| 1739 |
+
"grad_norm": 1.9434490467739143,
|
| 1740 |
+
"learning_rate": 5e-06,
|
| 1741 |
+
"loss": 0.2285,
|
| 1742 |
+
"step": 2430
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 4.939271255060729,
|
| 1746 |
+
"grad_norm": 1.9646396229024239,
|
| 1747 |
+
"learning_rate": 5e-06,
|
| 1748 |
+
"loss": 0.2306,
|
| 1749 |
+
"step": 2440
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 4.959514170040486,
|
| 1753 |
+
"grad_norm": 1.8683726614276728,
|
| 1754 |
+
"learning_rate": 5e-06,
|
| 1755 |
+
"loss": 0.2277,
|
| 1756 |
+
"step": 2450
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 4.979757085020243,
|
| 1760 |
+
"grad_norm": 1.984199504770925,
|
| 1761 |
+
"learning_rate": 5e-06,
|
| 1762 |
+
"loss": 0.2312,
|
| 1763 |
+
"step": 2460
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 5.0,
|
| 1767 |
+
"grad_norm": 1.8362584513440876,
|
| 1768 |
+
"learning_rate": 5e-06,
|
| 1769 |
+
"loss": 0.2292,
|
| 1770 |
+
"step": 2470
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 5.0,
|
| 1774 |
+
"eval_loss": 0.37886306643486023,
|
| 1775 |
+
"eval_runtime": 128.1269,
|
| 1776 |
+
"eval_samples_per_second": 103.835,
|
| 1777 |
+
"eval_steps_per_second": 0.406,
|
| 1778 |
+
"step": 2470
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 5.0,
|
| 1782 |
+
"step": 2470,
|
| 1783 |
+
"total_flos": 4136504477614080.0,
|
| 1784 |
+
"train_loss": 0.39363470135430095,
|
| 1785 |
+
"train_runtime": 36289.8965,
|
| 1786 |
+
"train_samples_per_second": 34.825,
|
| 1787 |
+
"train_steps_per_second": 0.068
|
| 1788 |
+
}
|
| 1789 |
+
],
|
| 1790 |
+
"logging_steps": 10,
|
| 1791 |
+
"max_steps": 2470,
|
| 1792 |
+
"num_input_tokens_seen": 0,
|
| 1793 |
+
"num_train_epochs": 5,
|
| 1794 |
+
"save_steps": 500,
|
| 1795 |
+
"stateful_callbacks": {
|
| 1796 |
+
"TrainerControl": {
|
| 1797 |
+
"args": {
|
| 1798 |
+
"should_epoch_stop": false,
|
| 1799 |
+
"should_evaluate": false,
|
| 1800 |
+
"should_log": false,
|
| 1801 |
+
"should_save": true,
|
| 1802 |
+
"should_training_stop": true
|
| 1803 |
+
},
|
| 1804 |
+
"attributes": {}
|
| 1805 |
+
}
|
| 1806 |
+
},
|
| 1807 |
+
"total_flos": 4136504477614080.0,
|
| 1808 |
+
"train_batch_size": 8,
|
| 1809 |
+
"trial_name": null,
|
| 1810 |
+
"trial_params": null
|
| 1811 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|