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 +1453 -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_epoch4
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_mistral_epoch4
|
| 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: 0.1617
|
| 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_epoch4
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_mistral_epoch4
|
| 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: 0.1617
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.9954430379746837,
|
| 3 |
+
"eval_loss": 0.1617216169834137,
|
| 4 |
+
"eval_runtime": 254.457,
|
| 5 |
+
"eval_samples_per_second": 52.284,
|
| 6 |
+
"eval_steps_per_second": 0.409,
|
| 7 |
+
"total_flos": 3302754688696320.0,
|
| 8 |
+
"train_loss": 0.4368948165108176,
|
| 9 |
+
"train_runtime": 56763.579,
|
| 10 |
+
"train_samples_per_second": 17.811,
|
| 11 |
+
"train_steps_per_second": 0.035
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.9954430379746837,
|
| 3 |
+
"eval_loss": 0.1617216169834137,
|
| 4 |
+
"eval_runtime": 254.457,
|
| 5 |
+
"eval_samples_per_second": 52.284,
|
| 6 |
+
"eval_steps_per_second": 0.409
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.9954430379746837,
|
| 3 |
+
"total_flos": 3302754688696320.0,
|
| 4 |
+
"train_loss": 0.4368948165108176,
|
| 5 |
+
"train_runtime": 56763.579,
|
| 6 |
+
"train_samples_per_second": 17.811,
|
| 7 |
+
"train_steps_per_second": 0.035
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1453 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.9954430379746837,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1972,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.020253164556962026,
|
| 13 |
+
"grad_norm": 2.8833762486177865,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7568,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04050632911392405,
|
| 20 |
+
"grad_norm": 2.390286912889809,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.6504,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.060759493670886074,
|
| 27 |
+
"grad_norm": 1.489395380260759,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6287,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0810126582278481,
|
| 34 |
+
"grad_norm": 1.589470284066133,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6135,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10126582278481013,
|
| 41 |
+
"grad_norm": 1.4199327904724377,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6037,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12151898734177215,
|
| 48 |
+
"grad_norm": 1.4578167281681993,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.5974,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14177215189873418,
|
| 55 |
+
"grad_norm": 1.3411623258601368,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.5923,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1620253164556962,
|
| 62 |
+
"grad_norm": 2.0256881877625204,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.5879,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18227848101265823,
|
| 69 |
+
"grad_norm": 1.865143294695778,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.5869,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.20253164556962025,
|
| 76 |
+
"grad_norm": 2.850869507593689,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.5894,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.22278481012658227,
|
| 83 |
+
"grad_norm": 2.780764039633903,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.5825,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2430379746835443,
|
| 90 |
+
"grad_norm": 2.24595769639212,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.5792,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.26329113924050634,
|
| 97 |
+
"grad_norm": 1.898945973266495,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.5765,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.28354430379746837,
|
| 104 |
+
"grad_norm": 2.0985064075463518,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.5657,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3037974683544304,
|
| 111 |
+
"grad_norm": 2.1947025380420393,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.576,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3240506329113924,
|
| 118 |
+
"grad_norm": 1.9010440206949761,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.5748,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.34430379746835443,
|
| 125 |
+
"grad_norm": 1.5587857210363367,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.5762,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.36455696202531646,
|
| 132 |
+
"grad_norm": 1.940350997849539,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.5726,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3848101265822785,
|
| 139 |
+
"grad_norm": 1.653915136046625,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.5724,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4050632911392405,
|
| 146 |
+
"grad_norm": 2.4614019893025274,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.567,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.4253164556962025,
|
| 153 |
+
"grad_norm": 1.8586854938543989,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.5628,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.44556962025316454,
|
| 160 |
+
"grad_norm": 1.4449652115361937,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.5679,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.46582278481012657,
|
| 167 |
+
"grad_norm": 1.3739469268351123,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.5676,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4860759493670886,
|
| 174 |
+
"grad_norm": 1.165737020699501,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.5644,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5063291139240507,
|
| 181 |
+
"grad_norm": 1.357956082726849,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.5686,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5265822784810127,
|
| 188 |
+
"grad_norm": 1.4295099868510899,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.5554,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5468354430379747,
|
| 195 |
+
"grad_norm": 1.4688068967033727,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.5643,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5670886075949367,
|
| 202 |
+
"grad_norm": 1.3744420183733652,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.56,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5873417721518988,
|
| 209 |
+
"grad_norm": 1.4423763395622504,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.56,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6075949367088608,
|
| 216 |
+
"grad_norm": 1.4527708533649162,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.5596,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6278481012658228,
|
| 223 |
+
"grad_norm": 1.4417603290241021,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.5655,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6481012658227848,
|
| 230 |
+
"grad_norm": 1.6835798959760988,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.5611,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6683544303797468,
|
| 237 |
+
"grad_norm": 1.3523279967838302,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.5607,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6886075949367089,
|
| 244 |
+
"grad_norm": 1.2500179332984684,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.5597,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7088607594936709,
|
| 251 |
+
"grad_norm": 1.2523150009107906,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.5614,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7291139240506329,
|
| 258 |
+
"grad_norm": 1.0953008806392797,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.5638,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7493670886075949,
|
| 265 |
+
"grad_norm": 1.6446500941969269,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.5566,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.769620253164557,
|
| 272 |
+
"grad_norm": 1.4079831931594988,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.5533,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.789873417721519,
|
| 279 |
+
"grad_norm": 1.1110346875099018,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.5559,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.810126582278481,
|
| 286 |
+
"grad_norm": 1.4268171466763837,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.5566,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.830379746835443,
|
| 293 |
+
"grad_norm": 1.2447639143712546,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.5514,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.850632911392405,
|
| 300 |
+
"grad_norm": 1.195155734961536,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.5587,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8708860759493671,
|
| 307 |
+
"grad_norm": 1.1003141204515203,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.5521,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8911392405063291,
|
| 314 |
+
"grad_norm": 1.3030562652810704,
|
| 315 |
+
"learning_rate": 5e-06,
|
| 316 |
+
"loss": 0.5573,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9113924050632911,
|
| 321 |
+
"grad_norm": 1.2728739765574453,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.5488,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9316455696202531,
|
| 328 |
+
"grad_norm": 1.1393805858707695,
|
| 329 |
+
"learning_rate": 5e-06,
|
| 330 |
+
"loss": 0.5532,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.9518987341772152,
|
| 335 |
+
"grad_norm": 1.252449871115967,
|
| 336 |
+
"learning_rate": 5e-06,
|
| 337 |
+
"loss": 0.5539,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.9721518987341772,
|
| 342 |
+
"grad_norm": 1.3675922433289114,
|
| 343 |
+
"learning_rate": 5e-06,
|
| 344 |
+
"loss": 0.5515,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.9924050632911392,
|
| 349 |
+
"grad_norm": 1.0986012485203254,
|
| 350 |
+
"learning_rate": 5e-06,
|
| 351 |
+
"loss": 0.548,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9984810126582279,
|
| 356 |
+
"eval_loss": 0.13772521913051605,
|
| 357 |
+
"eval_runtime": 252.9462,
|
| 358 |
+
"eval_samples_per_second": 52.596,
|
| 359 |
+
"eval_steps_per_second": 0.411,
|
| 360 |
+
"step": 493
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.0131645569620253,
|
| 364 |
+
"grad_norm": 1.8664570600716093,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5056,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.0334177215189873,
|
| 371 |
+
"grad_norm": 1.690550013794204,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.4717,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.0536708860759494,
|
| 378 |
+
"grad_norm": 1.7450606923145526,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.4683,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.0739240506329113,
|
| 385 |
+
"grad_norm": 1.4739241775856946,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.4682,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0941772151898734,
|
| 392 |
+
"grad_norm": 2.196710788601052,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.467,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.1144303797468353,
|
| 399 |
+
"grad_norm": 1.4622782937118193,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.4664,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.1346835443037975,
|
| 406 |
+
"grad_norm": 1.204681750576354,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.4629,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.1549367088607596,
|
| 413 |
+
"grad_norm": 1.2919169624567832,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.4723,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.1751898734177215,
|
| 420 |
+
"grad_norm": 1.1738791165204896,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.4696,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.1954430379746834,
|
| 427 |
+
"grad_norm": 1.2749973090696376,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.4655,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.2156962025316456,
|
| 434 |
+
"grad_norm": 1.3069834745764197,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.4738,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.2359493670886077,
|
| 441 |
+
"grad_norm": 1.268141928024117,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.4689,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.2562025316455696,
|
| 448 |
+
"grad_norm": 2.349539426930866,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.4738,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.2764556962025315,
|
| 455 |
+
"grad_norm": 1.3038280118636631,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.4724,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.2967088607594937,
|
| 462 |
+
"grad_norm": 1.2561549442694693,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.4717,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.3169620253164558,
|
| 469 |
+
"grad_norm": 1.2353995568966352,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.4756,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.3372151898734177,
|
| 476 |
+
"grad_norm": 1.3143696543162657,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.4653,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.3574683544303796,
|
| 483 |
+
"grad_norm": 1.8332487196614191,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.4791,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.3777215189873417,
|
| 490 |
+
"grad_norm": 1.5782907788998026,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.4743,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.3979746835443039,
|
| 497 |
+
"grad_norm": 1.43844179760011,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.4733,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.4182278481012658,
|
| 504 |
+
"grad_norm": 1.2104409020838625,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.4695,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.438481012658228,
|
| 511 |
+
"grad_norm": 1.2829692982799845,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.4756,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.4587341772151898,
|
| 518 |
+
"grad_norm": 1.2115512985925798,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.4757,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.478987341772152,
|
| 525 |
+
"grad_norm": 1.1708137297250578,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.479,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.4992405063291139,
|
| 532 |
+
"grad_norm": 1.1860297553473809,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.4737,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.5194936708860758,
|
| 539 |
+
"grad_norm": 1.159382227654447,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.4764,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.539746835443038,
|
| 546 |
+
"grad_norm": 1.1694651947442445,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.4765,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.56,
|
| 553 |
+
"grad_norm": 1.160166128209198,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.4765,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.5802531645569622,
|
| 560 |
+
"grad_norm": 1.1966330785907486,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.4762,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.600506329113924,
|
| 567 |
+
"grad_norm": 1.2884100928471158,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.4797,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.620759493670886,
|
| 574 |
+
"grad_norm": 1.50350568469768,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.4765,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.6410126582278481,
|
| 581 |
+
"grad_norm": 1.1416454468827366,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.4685,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.6612658227848103,
|
| 588 |
+
"grad_norm": 1.3289305602168267,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.4771,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.6815189873417722,
|
| 595 |
+
"grad_norm": 1.242003954761086,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.4721,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.701772151898734,
|
| 602 |
+
"grad_norm": 1.1084079600907246,
|
| 603 |
+
"learning_rate": 5e-06,
|
| 604 |
+
"loss": 0.4731,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.7220253164556962,
|
| 609 |
+
"grad_norm": 1.268075113702087,
|
| 610 |
+
"learning_rate": 5e-06,
|
| 611 |
+
"loss": 0.4766,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.7422784810126584,
|
| 616 |
+
"grad_norm": 1.152924839399553,
|
| 617 |
+
"learning_rate": 5e-06,
|
| 618 |
+
"loss": 0.4767,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.7625316455696203,
|
| 623 |
+
"grad_norm": 1.0955649434062678,
|
| 624 |
+
"learning_rate": 5e-06,
|
| 625 |
+
"loss": 0.4776,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.7827848101265822,
|
| 630 |
+
"grad_norm": 1.3082664193765503,
|
| 631 |
+
"learning_rate": 5e-06,
|
| 632 |
+
"loss": 0.4815,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.8030379746835443,
|
| 637 |
+
"grad_norm": 1.166931921170078,
|
| 638 |
+
"learning_rate": 5e-06,
|
| 639 |
+
"loss": 0.4788,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.8232911392405065,
|
| 644 |
+
"grad_norm": 1.1423266879559995,
|
| 645 |
+
"learning_rate": 5e-06,
|
| 646 |
+
"loss": 0.477,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.8435443037974684,
|
| 651 |
+
"grad_norm": 1.3005388006776002,
|
| 652 |
+
"learning_rate": 5e-06,
|
| 653 |
+
"loss": 0.4789,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.8637974683544303,
|
| 658 |
+
"grad_norm": 1.5362991154311363,
|
| 659 |
+
"learning_rate": 5e-06,
|
| 660 |
+
"loss": 0.4791,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.8840506329113924,
|
| 665 |
+
"grad_norm": 1.0615549431669202,
|
| 666 |
+
"learning_rate": 5e-06,
|
| 667 |
+
"loss": 0.4746,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.9043037974683545,
|
| 672 |
+
"grad_norm": 1.1359371350640348,
|
| 673 |
+
"learning_rate": 5e-06,
|
| 674 |
+
"loss": 0.4774,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.9245569620253165,
|
| 679 |
+
"grad_norm": 1.338873863277151,
|
| 680 |
+
"learning_rate": 5e-06,
|
| 681 |
+
"loss": 0.4799,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.9448101265822784,
|
| 686 |
+
"grad_norm": 1.0562817698500642,
|
| 687 |
+
"learning_rate": 5e-06,
|
| 688 |
+
"loss": 0.4834,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.9650632911392405,
|
| 693 |
+
"grad_norm": 1.1976389472965596,
|
| 694 |
+
"learning_rate": 5e-06,
|
| 695 |
+
"loss": 0.481,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.9853164556962026,
|
| 700 |
+
"grad_norm": 1.1318384251326352,
|
| 701 |
+
"learning_rate": 5e-06,
|
| 702 |
+
"loss": 0.4823,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.999493670886076,
|
| 707 |
+
"eval_loss": 0.13791824877262115,
|
| 708 |
+
"eval_runtime": 252.4301,
|
| 709 |
+
"eval_samples_per_second": 52.704,
|
| 710 |
+
"eval_steps_per_second": 0.412,
|
| 711 |
+
"step": 987
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.0060759493670886,
|
| 715 |
+
"grad_norm": 2.24179568741783,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.4515,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.0263291139240507,
|
| 722 |
+
"grad_norm": 1.6981313244359,
|
| 723 |
+
"learning_rate": 5e-06,
|
| 724 |
+
"loss": 0.3891,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.046582278481013,
|
| 729 |
+
"grad_norm": 1.5796760743871119,
|
| 730 |
+
"learning_rate": 5e-06,
|
| 731 |
+
"loss": 0.3814,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.0668354430379745,
|
| 736 |
+
"grad_norm": 1.7079048311976808,
|
| 737 |
+
"learning_rate": 5e-06,
|
| 738 |
+
"loss": 0.3794,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.0870886075949366,
|
| 743 |
+
"grad_norm": 1.4027876167762106,
|
| 744 |
+
"learning_rate": 5e-06,
|
| 745 |
+
"loss": 0.3793,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.1073417721518988,
|
| 750 |
+
"grad_norm": 1.2776686544662923,
|
| 751 |
+
"learning_rate": 5e-06,
|
| 752 |
+
"loss": 0.3758,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.127594936708861,
|
| 757 |
+
"grad_norm": 1.3728804833099486,
|
| 758 |
+
"learning_rate": 5e-06,
|
| 759 |
+
"loss": 0.3868,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.1478481012658226,
|
| 764 |
+
"grad_norm": 1.4205398673755427,
|
| 765 |
+
"learning_rate": 5e-06,
|
| 766 |
+
"loss": 0.3827,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.1681012658227847,
|
| 771 |
+
"grad_norm": 1.3832130487234917,
|
| 772 |
+
"learning_rate": 5e-06,
|
| 773 |
+
"loss": 0.3852,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.188354430379747,
|
| 778 |
+
"grad_norm": 1.5929946445474668,
|
| 779 |
+
"learning_rate": 5e-06,
|
| 780 |
+
"loss": 0.3841,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.208607594936709,
|
| 785 |
+
"grad_norm": 1.4600989820317136,
|
| 786 |
+
"learning_rate": 5e-06,
|
| 787 |
+
"loss": 0.3818,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.2288607594936707,
|
| 792 |
+
"grad_norm": 1.4225880515710438,
|
| 793 |
+
"learning_rate": 5e-06,
|
| 794 |
+
"loss": 0.3909,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.249113924050633,
|
| 799 |
+
"grad_norm": 1.780076806234694,
|
| 800 |
+
"learning_rate": 5e-06,
|
| 801 |
+
"loss": 0.3884,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.269367088607595,
|
| 806 |
+
"grad_norm": 1.694668518355522,
|
| 807 |
+
"learning_rate": 5e-06,
|
| 808 |
+
"loss": 0.387,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.289620253164557,
|
| 813 |
+
"grad_norm": 1.7667024915838094,
|
| 814 |
+
"learning_rate": 5e-06,
|
| 815 |
+
"loss": 0.3894,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.309873417721519,
|
| 820 |
+
"grad_norm": 1.410793594228534,
|
| 821 |
+
"learning_rate": 5e-06,
|
| 822 |
+
"loss": 0.3842,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.330126582278481,
|
| 827 |
+
"grad_norm": 1.5234909172570381,
|
| 828 |
+
"learning_rate": 5e-06,
|
| 829 |
+
"loss": 0.3908,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.350379746835443,
|
| 834 |
+
"grad_norm": 1.2213254079078641,
|
| 835 |
+
"learning_rate": 5e-06,
|
| 836 |
+
"loss": 0.3903,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.370632911392405,
|
| 841 |
+
"grad_norm": 1.4202255106744544,
|
| 842 |
+
"learning_rate": 5e-06,
|
| 843 |
+
"loss": 0.3915,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.390886075949367,
|
| 848 |
+
"grad_norm": 1.4023194734455904,
|
| 849 |
+
"learning_rate": 5e-06,
|
| 850 |
+
"loss": 0.3924,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.411139240506329,
|
| 855 |
+
"grad_norm": 1.7343746037355243,
|
| 856 |
+
"learning_rate": 5e-06,
|
| 857 |
+
"loss": 0.3905,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.431392405063291,
|
| 862 |
+
"grad_norm": 1.4482110997116577,
|
| 863 |
+
"learning_rate": 5e-06,
|
| 864 |
+
"loss": 0.3899,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.4516455696202533,
|
| 869 |
+
"grad_norm": 1.9131070141039026,
|
| 870 |
+
"learning_rate": 5e-06,
|
| 871 |
+
"loss": 0.3878,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.4718987341772154,
|
| 876 |
+
"grad_norm": 1.3699773358857317,
|
| 877 |
+
"learning_rate": 5e-06,
|
| 878 |
+
"loss": 0.3907,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.492151898734177,
|
| 883 |
+
"grad_norm": 1.2435143983285588,
|
| 884 |
+
"learning_rate": 5e-06,
|
| 885 |
+
"loss": 0.3937,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.512405063291139,
|
| 890 |
+
"grad_norm": 1.271353869459015,
|
| 891 |
+
"learning_rate": 5e-06,
|
| 892 |
+
"loss": 0.393,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.5326582278481014,
|
| 897 |
+
"grad_norm": 1.9458404824086235,
|
| 898 |
+
"learning_rate": 5e-06,
|
| 899 |
+
"loss": 0.3921,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.552911392405063,
|
| 904 |
+
"grad_norm": 1.324983619143349,
|
| 905 |
+
"learning_rate": 5e-06,
|
| 906 |
+
"loss": 0.386,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.573164556962025,
|
| 911 |
+
"grad_norm": 1.5086572692565505,
|
| 912 |
+
"learning_rate": 5e-06,
|
| 913 |
+
"loss": 0.3929,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.5934177215189873,
|
| 918 |
+
"grad_norm": 1.2387524175778437,
|
| 919 |
+
"learning_rate": 5e-06,
|
| 920 |
+
"loss": 0.3956,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.6136708860759494,
|
| 925 |
+
"grad_norm": 1.4032957006294775,
|
| 926 |
+
"learning_rate": 5e-06,
|
| 927 |
+
"loss": 0.3985,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.6339240506329116,
|
| 932 |
+
"grad_norm": 1.4186988248363785,
|
| 933 |
+
"learning_rate": 5e-06,
|
| 934 |
+
"loss": 0.3949,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.6541772151898733,
|
| 939 |
+
"grad_norm": 1.474152675372263,
|
| 940 |
+
"learning_rate": 5e-06,
|
| 941 |
+
"loss": 0.3949,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.6744303797468354,
|
| 946 |
+
"grad_norm": 1.388800748370683,
|
| 947 |
+
"learning_rate": 5e-06,
|
| 948 |
+
"loss": 0.3972,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.6946835443037975,
|
| 953 |
+
"grad_norm": 1.3404535288890715,
|
| 954 |
+
"learning_rate": 5e-06,
|
| 955 |
+
"loss": 0.3975,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.714936708860759,
|
| 960 |
+
"grad_norm": 1.3485784987514158,
|
| 961 |
+
"learning_rate": 5e-06,
|
| 962 |
+
"loss": 0.3998,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.7351898734177214,
|
| 967 |
+
"grad_norm": 1.3182287721338872,
|
| 968 |
+
"learning_rate": 5e-06,
|
| 969 |
+
"loss": 0.3972,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.7554430379746835,
|
| 974 |
+
"grad_norm": 1.2129071324788472,
|
| 975 |
+
"learning_rate": 5e-06,
|
| 976 |
+
"loss": 0.3932,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.7756962025316456,
|
| 981 |
+
"grad_norm": 1.4082013444619639,
|
| 982 |
+
"learning_rate": 5e-06,
|
| 983 |
+
"loss": 0.3999,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.7959493670886078,
|
| 988 |
+
"grad_norm": 1.4390382641502573,
|
| 989 |
+
"learning_rate": 5e-06,
|
| 990 |
+
"loss": 0.3974,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.81620253164557,
|
| 995 |
+
"grad_norm": 1.3463527613931228,
|
| 996 |
+
"learning_rate": 5e-06,
|
| 997 |
+
"loss": 0.4004,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.8364556962025316,
|
| 1002 |
+
"grad_norm": 1.2190952668881454,
|
| 1003 |
+
"learning_rate": 5e-06,
|
| 1004 |
+
"loss": 0.3945,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.8567088607594937,
|
| 1009 |
+
"grad_norm": 1.2959901372391192,
|
| 1010 |
+
"learning_rate": 5e-06,
|
| 1011 |
+
"loss": 0.4014,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.876962025316456,
|
| 1016 |
+
"grad_norm": 1.2846058903861945,
|
| 1017 |
+
"learning_rate": 5e-06,
|
| 1018 |
+
"loss": 0.3987,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.8972151898734175,
|
| 1023 |
+
"grad_norm": 1.340897452737586,
|
| 1024 |
+
"learning_rate": 5e-06,
|
| 1025 |
+
"loss": 0.3983,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.9174683544303797,
|
| 1030 |
+
"grad_norm": 1.3196158163944824,
|
| 1031 |
+
"learning_rate": 5e-06,
|
| 1032 |
+
"loss": 0.4016,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.937721518987342,
|
| 1037 |
+
"grad_norm": 1.275687217034204,
|
| 1038 |
+
"learning_rate": 5e-06,
|
| 1039 |
+
"loss": 0.4105,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.957974683544304,
|
| 1044 |
+
"grad_norm": 1.4052855567194664,
|
| 1045 |
+
"learning_rate": 5e-06,
|
| 1046 |
+
"loss": 0.3992,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.978227848101266,
|
| 1051 |
+
"grad_norm": 1.3721809126891413,
|
| 1052 |
+
"learning_rate": 5e-06,
|
| 1053 |
+
"loss": 0.403,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.9984810126582278,
|
| 1058 |
+
"grad_norm": 1.3733986827541713,
|
| 1059 |
+
"learning_rate": 5e-06,
|
| 1060 |
+
"loss": 0.4008,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.9984810126582278,
|
| 1065 |
+
"eval_loss": 0.1451626569032669,
|
| 1066 |
+
"eval_runtime": 252.5403,
|
| 1067 |
+
"eval_samples_per_second": 52.681,
|
| 1068 |
+
"eval_steps_per_second": 0.412,
|
| 1069 |
+
"step": 1480
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 3.019240506329114,
|
| 1073 |
+
"grad_norm": 2.1233881502453333,
|
| 1074 |
+
"learning_rate": 5e-06,
|
| 1075 |
+
"loss": 0.3123,
|
| 1076 |
+
"step": 1490
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.039493670886076,
|
| 1080 |
+
"grad_norm": 1.733976300717687,
|
| 1081 |
+
"learning_rate": 5e-06,
|
| 1082 |
+
"loss": 0.2924,
|
| 1083 |
+
"step": 1500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 3.059746835443038,
|
| 1087 |
+
"grad_norm": 1.7085808896440553,
|
| 1088 |
+
"learning_rate": 5e-06,
|
| 1089 |
+
"loss": 0.2942,
|
| 1090 |
+
"step": 1510
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 3.08,
|
| 1094 |
+
"grad_norm": 1.4544968881558145,
|
| 1095 |
+
"learning_rate": 5e-06,
|
| 1096 |
+
"loss": 0.2933,
|
| 1097 |
+
"step": 1520
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.100253164556962,
|
| 1101 |
+
"grad_norm": 1.6261331378733803,
|
| 1102 |
+
"learning_rate": 5e-06,
|
| 1103 |
+
"loss": 0.2944,
|
| 1104 |
+
"step": 1530
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 3.120506329113924,
|
| 1108 |
+
"grad_norm": 1.5609283167478611,
|
| 1109 |
+
"learning_rate": 5e-06,
|
| 1110 |
+
"loss": 0.292,
|
| 1111 |
+
"step": 1540
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 3.140759493670886,
|
| 1115 |
+
"grad_norm": 1.6902454180217539,
|
| 1116 |
+
"learning_rate": 5e-06,
|
| 1117 |
+
"loss": 0.29,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 3.161012658227848,
|
| 1122 |
+
"grad_norm": 1.47961286622397,
|
| 1123 |
+
"learning_rate": 5e-06,
|
| 1124 |
+
"loss": 0.2964,
|
| 1125 |
+
"step": 1560
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 3.1812658227848103,
|
| 1129 |
+
"grad_norm": 1.6098815338414532,
|
| 1130 |
+
"learning_rate": 5e-06,
|
| 1131 |
+
"loss": 0.2967,
|
| 1132 |
+
"step": 1570
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 3.201518987341772,
|
| 1136 |
+
"grad_norm": 1.4570975957744257,
|
| 1137 |
+
"learning_rate": 5e-06,
|
| 1138 |
+
"loss": 0.2999,
|
| 1139 |
+
"step": 1580
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 3.221772151898734,
|
| 1143 |
+
"grad_norm": 1.5616376984698326,
|
| 1144 |
+
"learning_rate": 5e-06,
|
| 1145 |
+
"loss": 0.3003,
|
| 1146 |
+
"step": 1590
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 3.2420253164556962,
|
| 1150 |
+
"grad_norm": 1.5261875412769847,
|
| 1151 |
+
"learning_rate": 5e-06,
|
| 1152 |
+
"loss": 0.3007,
|
| 1153 |
+
"step": 1600
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 3.2622784810126584,
|
| 1157 |
+
"grad_norm": 1.5927243321009188,
|
| 1158 |
+
"learning_rate": 5e-06,
|
| 1159 |
+
"loss": 0.2992,
|
| 1160 |
+
"step": 1610
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 3.28253164556962,
|
| 1164 |
+
"grad_norm": 1.4687003886067878,
|
| 1165 |
+
"learning_rate": 5e-06,
|
| 1166 |
+
"loss": 0.3016,
|
| 1167 |
+
"step": 1620
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 3.302784810126582,
|
| 1171 |
+
"grad_norm": 1.6212181828314611,
|
| 1172 |
+
"learning_rate": 5e-06,
|
| 1173 |
+
"loss": 0.3046,
|
| 1174 |
+
"step": 1630
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 3.3230379746835443,
|
| 1178 |
+
"grad_norm": 1.7006560112850782,
|
| 1179 |
+
"learning_rate": 5e-06,
|
| 1180 |
+
"loss": 0.3014,
|
| 1181 |
+
"step": 1640
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 3.3432911392405065,
|
| 1185 |
+
"grad_norm": 1.6369351197517492,
|
| 1186 |
+
"learning_rate": 5e-06,
|
| 1187 |
+
"loss": 0.3031,
|
| 1188 |
+
"step": 1650
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 3.363544303797468,
|
| 1192 |
+
"grad_norm": 1.8997824836659962,
|
| 1193 |
+
"learning_rate": 5e-06,
|
| 1194 |
+
"loss": 0.3052,
|
| 1195 |
+
"step": 1660
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 3.3837974683544303,
|
| 1199 |
+
"grad_norm": 1.7686559384037446,
|
| 1200 |
+
"learning_rate": 5e-06,
|
| 1201 |
+
"loss": 0.2994,
|
| 1202 |
+
"step": 1670
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 3.4040506329113924,
|
| 1206 |
+
"grad_norm": 1.9852860129783203,
|
| 1207 |
+
"learning_rate": 5e-06,
|
| 1208 |
+
"loss": 0.2987,
|
| 1209 |
+
"step": 1680
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.4243037974683546,
|
| 1213 |
+
"grad_norm": 1.6687727310492642,
|
| 1214 |
+
"learning_rate": 5e-06,
|
| 1215 |
+
"loss": 0.3028,
|
| 1216 |
+
"step": 1690
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 3.4445569620253167,
|
| 1220 |
+
"grad_norm": 1.555588423959256,
|
| 1221 |
+
"learning_rate": 5e-06,
|
| 1222 |
+
"loss": 0.3012,
|
| 1223 |
+
"step": 1700
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 3.4648101265822784,
|
| 1227 |
+
"grad_norm": 1.570937882764948,
|
| 1228 |
+
"learning_rate": 5e-06,
|
| 1229 |
+
"loss": 0.3033,
|
| 1230 |
+
"step": 1710
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 3.4850632911392405,
|
| 1234 |
+
"grad_norm": 1.762794823286088,
|
| 1235 |
+
"learning_rate": 5e-06,
|
| 1236 |
+
"loss": 0.3078,
|
| 1237 |
+
"step": 1720
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 3.5053164556962026,
|
| 1241 |
+
"grad_norm": 1.5085676767074419,
|
| 1242 |
+
"learning_rate": 5e-06,
|
| 1243 |
+
"loss": 0.3076,
|
| 1244 |
+
"step": 1730
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 3.5255696202531643,
|
| 1248 |
+
"grad_norm": 1.846690362471807,
|
| 1249 |
+
"learning_rate": 5e-06,
|
| 1250 |
+
"loss": 0.3058,
|
| 1251 |
+
"step": 1740
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 3.5458227848101265,
|
| 1255 |
+
"grad_norm": 1.888656474961098,
|
| 1256 |
+
"learning_rate": 5e-06,
|
| 1257 |
+
"loss": 0.3092,
|
| 1258 |
+
"step": 1750
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 3.5660759493670886,
|
| 1262 |
+
"grad_norm": 1.5522432118926228,
|
| 1263 |
+
"learning_rate": 5e-06,
|
| 1264 |
+
"loss": 0.3031,
|
| 1265 |
+
"step": 1760
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 3.5863291139240507,
|
| 1269 |
+
"grad_norm": 1.7040265273376634,
|
| 1270 |
+
"learning_rate": 5e-06,
|
| 1271 |
+
"loss": 0.3097,
|
| 1272 |
+
"step": 1770
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 3.606582278481013,
|
| 1276 |
+
"grad_norm": 1.6319175616422348,
|
| 1277 |
+
"learning_rate": 5e-06,
|
| 1278 |
+
"loss": 0.3076,
|
| 1279 |
+
"step": 1780
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 3.6268354430379746,
|
| 1283 |
+
"grad_norm": 1.6539455217449284,
|
| 1284 |
+
"learning_rate": 5e-06,
|
| 1285 |
+
"loss": 0.3054,
|
| 1286 |
+
"step": 1790
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 3.6470886075949367,
|
| 1290 |
+
"grad_norm": 1.6323498992182317,
|
| 1291 |
+
"learning_rate": 5e-06,
|
| 1292 |
+
"loss": 0.3089,
|
| 1293 |
+
"step": 1800
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 3.667341772151899,
|
| 1297 |
+
"grad_norm": 1.9811098470470307,
|
| 1298 |
+
"learning_rate": 5e-06,
|
| 1299 |
+
"loss": 0.3141,
|
| 1300 |
+
"step": 1810
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 3.6875949367088605,
|
| 1304 |
+
"grad_norm": 1.5750523511747638,
|
| 1305 |
+
"learning_rate": 5e-06,
|
| 1306 |
+
"loss": 0.3093,
|
| 1307 |
+
"step": 1820
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 3.7078481012658226,
|
| 1311 |
+
"grad_norm": 1.5810037258388918,
|
| 1312 |
+
"learning_rate": 5e-06,
|
| 1313 |
+
"loss": 0.3105,
|
| 1314 |
+
"step": 1830
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.728101265822785,
|
| 1318 |
+
"grad_norm": 1.554399518805066,
|
| 1319 |
+
"learning_rate": 5e-06,
|
| 1320 |
+
"loss": 0.3124,
|
| 1321 |
+
"step": 1840
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 3.748354430379747,
|
| 1325 |
+
"grad_norm": 1.6069072450441366,
|
| 1326 |
+
"learning_rate": 5e-06,
|
| 1327 |
+
"loss": 0.3099,
|
| 1328 |
+
"step": 1850
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 3.768607594936709,
|
| 1332 |
+
"grad_norm": 1.6769246041867307,
|
| 1333 |
+
"learning_rate": 5e-06,
|
| 1334 |
+
"loss": 0.3173,
|
| 1335 |
+
"step": 1860
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 3.7888607594936707,
|
| 1339 |
+
"grad_norm": 1.579060667933051,
|
| 1340 |
+
"learning_rate": 5e-06,
|
| 1341 |
+
"loss": 0.3145,
|
| 1342 |
+
"step": 1870
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 3.809113924050633,
|
| 1346 |
+
"grad_norm": 2.0501104971409396,
|
| 1347 |
+
"learning_rate": 5e-06,
|
| 1348 |
+
"loss": 0.3154,
|
| 1349 |
+
"step": 1880
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 3.829367088607595,
|
| 1353 |
+
"grad_norm": 2.2983760386486214,
|
| 1354 |
+
"learning_rate": 5e-06,
|
| 1355 |
+
"loss": 0.315,
|
| 1356 |
+
"step": 1890
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 3.8496202531645567,
|
| 1360 |
+
"grad_norm": 1.780585915706879,
|
| 1361 |
+
"learning_rate": 5e-06,
|
| 1362 |
+
"loss": 0.3157,
|
| 1363 |
+
"step": 1900
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 3.869873417721519,
|
| 1367 |
+
"grad_norm": 1.77785313158742,
|
| 1368 |
+
"learning_rate": 5e-06,
|
| 1369 |
+
"loss": 0.3117,
|
| 1370 |
+
"step": 1910
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 3.890126582278481,
|
| 1374 |
+
"grad_norm": 1.6198590987029773,
|
| 1375 |
+
"learning_rate": 5e-06,
|
| 1376 |
+
"loss": 0.3172,
|
| 1377 |
+
"step": 1920
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 3.910379746835443,
|
| 1381 |
+
"grad_norm": 1.64334724662568,
|
| 1382 |
+
"learning_rate": 5e-06,
|
| 1383 |
+
"loss": 0.3147,
|
| 1384 |
+
"step": 1930
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 3.9306329113924052,
|
| 1388 |
+
"grad_norm": 1.5274532742672213,
|
| 1389 |
+
"learning_rate": 5e-06,
|
| 1390 |
+
"loss": 0.312,
|
| 1391 |
+
"step": 1940
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 3.9508860759493674,
|
| 1395 |
+
"grad_norm": 1.7941457309206295,
|
| 1396 |
+
"learning_rate": 5e-06,
|
| 1397 |
+
"loss": 0.3164,
|
| 1398 |
+
"step": 1950
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 3.971139240506329,
|
| 1402 |
+
"grad_norm": 1.6138102060492845,
|
| 1403 |
+
"learning_rate": 5e-06,
|
| 1404 |
+
"loss": 0.3175,
|
| 1405 |
+
"step": 1960
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 3.991392405063291,
|
| 1409 |
+
"grad_norm": 1.7439224514084468,
|
| 1410 |
+
"learning_rate": 5e-06,
|
| 1411 |
+
"loss": 0.3172,
|
| 1412 |
+
"step": 1970
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 3.9954430379746837,
|
| 1416 |
+
"eval_loss": 0.1617216169834137,
|
| 1417 |
+
"eval_runtime": 254.4743,
|
| 1418 |
+
"eval_samples_per_second": 52.28,
|
| 1419 |
+
"eval_steps_per_second": 0.409,
|
| 1420 |
+
"step": 1972
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 3.9954430379746837,
|
| 1424 |
+
"step": 1972,
|
| 1425 |
+
"total_flos": 3302754688696320.0,
|
| 1426 |
+
"train_loss": 0.4368948165108176,
|
| 1427 |
+
"train_runtime": 56763.579,
|
| 1428 |
+
"train_samples_per_second": 17.811,
|
| 1429 |
+
"train_steps_per_second": 0.035
|
| 1430 |
+
}
|
| 1431 |
+
],
|
| 1432 |
+
"logging_steps": 10,
|
| 1433 |
+
"max_steps": 1972,
|
| 1434 |
+
"num_input_tokens_seen": 0,
|
| 1435 |
+
"num_train_epochs": 4,
|
| 1436 |
+
"save_steps": 500,
|
| 1437 |
+
"stateful_callbacks": {
|
| 1438 |
+
"TrainerControl": {
|
| 1439 |
+
"args": {
|
| 1440 |
+
"should_epoch_stop": false,
|
| 1441 |
+
"should_evaluate": false,
|
| 1442 |
+
"should_log": false,
|
| 1443 |
+
"should_save": true,
|
| 1444 |
+
"should_training_stop": true
|
| 1445 |
+
},
|
| 1446 |
+
"attributes": {}
|
| 1447 |
+
}
|
| 1448 |
+
},
|
| 1449 |
+
"total_flos": 3302754688696320.0,
|
| 1450 |
+
"train_batch_size": 8,
|
| 1451 |
+
"trial_name": null,
|
| 1452 |
+
"trial_params": null
|
| 1453 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|