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 +1095 -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_epoch3
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_mistral_epoch3
|
| 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: 0.1461
|
| 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_epoch3
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_mistral_epoch3
|
| 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: 0.1461
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9964556962025317,
|
| 3 |
+
"eval_loss": 0.14610780775547028,
|
| 4 |
+
"eval_runtime": 253.4559,
|
| 5 |
+
"eval_samples_per_second": 52.49,
|
| 6 |
+
"eval_steps_per_second": 0.41,
|
| 7 |
+
"total_flos": 2476961326694400.0,
|
| 8 |
+
"train_loss": 0.47900067526718665,
|
| 9 |
+
"train_runtime": 42754.8995,
|
| 10 |
+
"train_samples_per_second": 17.735,
|
| 11 |
+
"train_steps_per_second": 0.035
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9964556962025317,
|
| 3 |
+
"eval_loss": 0.14610780775547028,
|
| 4 |
+
"eval_runtime": 253.4559,
|
| 5 |
+
"eval_samples_per_second": 52.49,
|
| 6 |
+
"eval_steps_per_second": 0.41
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9964556962025317,
|
| 3 |
+
"total_flos": 2476961326694400.0,
|
| 4 |
+
"train_loss": 0.47900067526718665,
|
| 5 |
+
"train_runtime": 42754.8995,
|
| 6 |
+
"train_samples_per_second": 17.735,
|
| 7 |
+
"train_steps_per_second": 0.035
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1095 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9964556962025317,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1479,
|
| 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": 2.881640763497059,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7569,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04050632911392405,
|
| 20 |
+
"grad_norm": 2.0337939479231464,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.6507,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.060759493670886074,
|
| 27 |
+
"grad_norm": 2.673785425051781,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6295,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0810126582278481,
|
| 34 |
+
"grad_norm": 3.3956320905602704,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.615,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10126582278481013,
|
| 41 |
+
"grad_norm": 2.4989053137375143,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6055,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12151898734177215,
|
| 48 |
+
"grad_norm": 1.8362600995228775,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.598,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14177215189873418,
|
| 55 |
+
"grad_norm": 1.6812600364217105,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.5919,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1620253164556962,
|
| 62 |
+
"grad_norm": 1.7204729721312917,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.5885,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18227848101265823,
|
| 69 |
+
"grad_norm": 1.5280049113720315,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.5878,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.20253164556962025,
|
| 76 |
+
"grad_norm": 2.0183706809796145,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.5912,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.22278481012658227,
|
| 83 |
+
"grad_norm": 1.3728348794112124,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.5834,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2430379746835443,
|
| 90 |
+
"grad_norm": 1.815358729258882,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.5806,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.26329113924050634,
|
| 97 |
+
"grad_norm": 1.6815731840354737,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.5793,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.28354430379746837,
|
| 104 |
+
"grad_norm": 1.225903486666645,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.5684,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3037974683544304,
|
| 111 |
+
"grad_norm": 1.5251383950821966,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.5792,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3240506329113924,
|
| 118 |
+
"grad_norm": 2.6329119810915365,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.5782,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.34430379746835443,
|
| 125 |
+
"grad_norm": 1.7167868191479003,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.5764,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.36455696202531646,
|
| 132 |
+
"grad_norm": 1.73285303403399,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.5716,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3848101265822785,
|
| 139 |
+
"grad_norm": 1.3746990652975846,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.5719,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4050632911392405,
|
| 146 |
+
"grad_norm": 1.4936398849590744,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.5679,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.4253164556962025,
|
| 153 |
+
"grad_norm": 1.2921614371273473,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.5636,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.44556962025316454,
|
| 160 |
+
"grad_norm": 1.442945179409374,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.5684,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.46582278481012657,
|
| 167 |
+
"grad_norm": 1.4946631499646226,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.567,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4860759493670886,
|
| 174 |
+
"grad_norm": 1.2982882675858225,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.5633,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5063291139240507,
|
| 181 |
+
"grad_norm": 1.201139136446853,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.5672,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5265822784810127,
|
| 188 |
+
"grad_norm": 1.221681422450315,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.5541,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5468354430379747,
|
| 195 |
+
"grad_norm": 1.3764079520580204,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.5634,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5670886075949367,
|
| 202 |
+
"grad_norm": 1.2769215201401323,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.5585,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5873417721518988,
|
| 209 |
+
"grad_norm": 1.658435241290474,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.5589,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6075949367088608,
|
| 216 |
+
"grad_norm": 1.3208774206825835,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.5584,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6278481012658228,
|
| 223 |
+
"grad_norm": 1.3732535087662892,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.5641,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6481012658227848,
|
| 230 |
+
"grad_norm": 1.7757004131781444,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.5602,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6683544303797468,
|
| 237 |
+
"grad_norm": 1.4157657120348899,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.5598,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6886075949367089,
|
| 244 |
+
"grad_norm": 1.2554752448180828,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.5592,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7088607594936709,
|
| 251 |
+
"grad_norm": 1.4796331594217829,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.5606,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7291139240506329,
|
| 258 |
+
"grad_norm": 1.2444877557169038,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.5627,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7493670886075949,
|
| 265 |
+
"grad_norm": 1.3700404053887212,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.5553,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.769620253164557,
|
| 272 |
+
"grad_norm": 1.399982865718864,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.5523,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.789873417721519,
|
| 279 |
+
"grad_norm": 1.7626359294815905,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.5554,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.810126582278481,
|
| 286 |
+
"grad_norm": 1.2003485909233378,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.5554,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.830379746835443,
|
| 293 |
+
"grad_norm": 1.1749218008708648,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.5499,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.850632911392405,
|
| 300 |
+
"grad_norm": 1.1170828766358432,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.5583,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8708860759493671,
|
| 307 |
+
"grad_norm": 1.1913684385210768,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.552,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8911392405063291,
|
| 314 |
+
"grad_norm": 1.158491457002269,
|
| 315 |
+
"learning_rate": 5e-06,
|
| 316 |
+
"loss": 0.5576,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9113924050632911,
|
| 321 |
+
"grad_norm": 1.2440014645948327,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.5486,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9316455696202531,
|
| 328 |
+
"grad_norm": 1.0624082894155582,
|
| 329 |
+
"learning_rate": 5e-06,
|
| 330 |
+
"loss": 0.553,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.9518987341772152,
|
| 335 |
+
"grad_norm": 1.3891566012880086,
|
| 336 |
+
"learning_rate": 5e-06,
|
| 337 |
+
"loss": 0.5537,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.9721518987341772,
|
| 342 |
+
"grad_norm": 1.2000412125972895,
|
| 343 |
+
"learning_rate": 5e-06,
|
| 344 |
+
"loss": 0.5511,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.9924050632911392,
|
| 349 |
+
"grad_norm": 1.0973875984510393,
|
| 350 |
+
"learning_rate": 5e-06,
|
| 351 |
+
"loss": 0.5475,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9984810126582279,
|
| 356 |
+
"eval_loss": 0.13758791983127594,
|
| 357 |
+
"eval_runtime": 254.1278,
|
| 358 |
+
"eval_samples_per_second": 52.352,
|
| 359 |
+
"eval_steps_per_second": 0.409,
|
| 360 |
+
"step": 493
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.0131645569620253,
|
| 364 |
+
"grad_norm": 1.8117531834466138,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5044,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.0334177215189873,
|
| 371 |
+
"grad_norm": 1.3053921965302375,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.4698,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.0536708860759494,
|
| 378 |
+
"grad_norm": 1.1687624258615774,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.4664,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.0739240506329113,
|
| 385 |
+
"grad_norm": 1.1072989424160442,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.4678,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0941772151898734,
|
| 392 |
+
"grad_norm": 1.2175965077481026,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.4676,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.1144303797468353,
|
| 399 |
+
"grad_norm": 1.2541248804984217,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.4679,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.1346835443037975,
|
| 406 |
+
"grad_norm": 1.2263184938833407,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.4652,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.1549367088607596,
|
| 413 |
+
"grad_norm": 1.2335018260186486,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.4741,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.1751898734177215,
|
| 420 |
+
"grad_norm": 1.1651843980725467,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.4698,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.1954430379746834,
|
| 427 |
+
"grad_norm": 1.3299683670971845,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.4648,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.2156962025316456,
|
| 434 |
+
"grad_norm": 1.5406403193173543,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.4728,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.2359493670886077,
|
| 441 |
+
"grad_norm": 1.3994137841579308,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.4672,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.2562025316455696,
|
| 448 |
+
"grad_norm": 1.4687039924759018,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.4722,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.2764556962025315,
|
| 455 |
+
"grad_norm": 1.1767001591548043,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.4707,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.2967088607594937,
|
| 462 |
+
"grad_norm": 1.377209586857746,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.4703,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.3169620253164558,
|
| 469 |
+
"grad_norm": 1.3280966356632122,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.4743,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.3372151898734177,
|
| 476 |
+
"grad_norm": 1.172194594770593,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.4625,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.3574683544303796,
|
| 483 |
+
"grad_norm": 1.1815616623629874,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.4772,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.3777215189873417,
|
| 490 |
+
"grad_norm": 1.2788117947587072,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.4748,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.3979746835443039,
|
| 497 |
+
"grad_norm": 1.2120662888757698,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.4737,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.4182278481012658,
|
| 504 |
+
"grad_norm": 1.196686900725073,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.4706,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.438481012658228,
|
| 511 |
+
"grad_norm": 1.198300916867019,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.4766,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.4587341772151898,
|
| 518 |
+
"grad_norm": 1.2100463670783117,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.4764,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.478987341772152,
|
| 525 |
+
"grad_norm": 1.1505710467148873,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.4788,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.4992405063291139,
|
| 532 |
+
"grad_norm": 1.1514955759509187,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.4729,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.5194936708860758,
|
| 539 |
+
"grad_norm": 1.2756859859117555,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.4752,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.539746835443038,
|
| 546 |
+
"grad_norm": 1.1669815187630872,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.4751,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.56,
|
| 553 |
+
"grad_norm": 1.1950794033571506,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.4745,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.5802531645569622,
|
| 560 |
+
"grad_norm": 1.2518137614638525,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.4744,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.600506329113924,
|
| 567 |
+
"grad_norm": 1.164886747372712,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.4778,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.620759493670886,
|
| 574 |
+
"grad_norm": 1.3963551349425976,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.4749,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.6410126582278481,
|
| 581 |
+
"grad_norm": 1.2170674697519668,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.4668,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.6612658227848103,
|
| 588 |
+
"grad_norm": 1.2362608113225955,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.4755,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.6815189873417722,
|
| 595 |
+
"grad_norm": 1.186974044583489,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.4709,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.701772151898734,
|
| 602 |
+
"grad_norm": 1.1120094436131531,
|
| 603 |
+
"learning_rate": 5e-06,
|
| 604 |
+
"loss": 0.473,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.7220253164556962,
|
| 609 |
+
"grad_norm": 1.1801749965556498,
|
| 610 |
+
"learning_rate": 5e-06,
|
| 611 |
+
"loss": 0.4759,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.7422784810126584,
|
| 616 |
+
"grad_norm": 1.1457854356860961,
|
| 617 |
+
"learning_rate": 5e-06,
|
| 618 |
+
"loss": 0.4751,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.7625316455696203,
|
| 623 |
+
"grad_norm": 1.096573157780436,
|
| 624 |
+
"learning_rate": 5e-06,
|
| 625 |
+
"loss": 0.476,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.7827848101265822,
|
| 630 |
+
"grad_norm": 1.1968883544722357,
|
| 631 |
+
"learning_rate": 5e-06,
|
| 632 |
+
"loss": 0.48,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.8030379746835443,
|
| 637 |
+
"grad_norm": 1.3462695661737496,
|
| 638 |
+
"learning_rate": 5e-06,
|
| 639 |
+
"loss": 0.477,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.8232911392405065,
|
| 644 |
+
"grad_norm": 1.2981459167417944,
|
| 645 |
+
"learning_rate": 5e-06,
|
| 646 |
+
"loss": 0.4753,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.8435443037974684,
|
| 651 |
+
"grad_norm": 1.4277375961136556,
|
| 652 |
+
"learning_rate": 5e-06,
|
| 653 |
+
"loss": 0.4771,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.8637974683544303,
|
| 658 |
+
"grad_norm": 1.4551182850778734,
|
| 659 |
+
"learning_rate": 5e-06,
|
| 660 |
+
"loss": 0.477,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.8840506329113924,
|
| 665 |
+
"grad_norm": 1.3405721129672685,
|
| 666 |
+
"learning_rate": 5e-06,
|
| 667 |
+
"loss": 0.4726,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.9043037974683545,
|
| 672 |
+
"grad_norm": 1.2634029223509275,
|
| 673 |
+
"learning_rate": 5e-06,
|
| 674 |
+
"loss": 0.4749,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.9245569620253165,
|
| 679 |
+
"grad_norm": 1.3160409770893926,
|
| 680 |
+
"learning_rate": 5e-06,
|
| 681 |
+
"loss": 0.4776,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.9448101265822784,
|
| 686 |
+
"grad_norm": 1.0750739382136794,
|
| 687 |
+
"learning_rate": 5e-06,
|
| 688 |
+
"loss": 0.4816,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.9650632911392405,
|
| 693 |
+
"grad_norm": 1.215667249435148,
|
| 694 |
+
"learning_rate": 5e-06,
|
| 695 |
+
"loss": 0.4789,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.9853164556962026,
|
| 700 |
+
"grad_norm": 1.1020704754247843,
|
| 701 |
+
"learning_rate": 5e-06,
|
| 702 |
+
"loss": 0.4805,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.999493670886076,
|
| 707 |
+
"eval_loss": 0.13782347738742828,
|
| 708 |
+
"eval_runtime": 255.1699,
|
| 709 |
+
"eval_samples_per_second": 52.138,
|
| 710 |
+
"eval_steps_per_second": 0.408,
|
| 711 |
+
"step": 987
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.0060759493670886,
|
| 715 |
+
"grad_norm": 2.2320392744750532,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.4496,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.0263291139240507,
|
| 722 |
+
"grad_norm": 1.6264522271278852,
|
| 723 |
+
"learning_rate": 5e-06,
|
| 724 |
+
"loss": 0.3864,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.046582278481013,
|
| 729 |
+
"grad_norm": 1.4022257575865094,
|
| 730 |
+
"learning_rate": 5e-06,
|
| 731 |
+
"loss": 0.3795,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.0668354430379745,
|
| 736 |
+
"grad_norm": 1.5383595004674644,
|
| 737 |
+
"learning_rate": 5e-06,
|
| 738 |
+
"loss": 0.377,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.0870886075949366,
|
| 743 |
+
"grad_norm": 1.3513330118475093,
|
| 744 |
+
"learning_rate": 5e-06,
|
| 745 |
+
"loss": 0.3767,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.1073417721518988,
|
| 750 |
+
"grad_norm": 1.3272367266437448,
|
| 751 |
+
"learning_rate": 5e-06,
|
| 752 |
+
"loss": 0.3739,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.127594936708861,
|
| 757 |
+
"grad_norm": 1.3073032398087094,
|
| 758 |
+
"learning_rate": 5e-06,
|
| 759 |
+
"loss": 0.3846,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.1478481012658226,
|
| 764 |
+
"grad_norm": 1.5607458954840778,
|
| 765 |
+
"learning_rate": 5e-06,
|
| 766 |
+
"loss": 0.3804,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.1681012658227847,
|
| 771 |
+
"grad_norm": 1.3955276924826612,
|
| 772 |
+
"learning_rate": 5e-06,
|
| 773 |
+
"loss": 0.382,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.188354430379747,
|
| 778 |
+
"grad_norm": 1.5667776972963814,
|
| 779 |
+
"learning_rate": 5e-06,
|
| 780 |
+
"loss": 0.3815,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.208607594936709,
|
| 785 |
+
"grad_norm": 1.4260082058645476,
|
| 786 |
+
"learning_rate": 5e-06,
|
| 787 |
+
"loss": 0.3787,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.2288607594936707,
|
| 792 |
+
"grad_norm": 1.5562857213046708,
|
| 793 |
+
"learning_rate": 5e-06,
|
| 794 |
+
"loss": 0.3876,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.249113924050633,
|
| 799 |
+
"grad_norm": 1.9917004448182953,
|
| 800 |
+
"learning_rate": 5e-06,
|
| 801 |
+
"loss": 0.3856,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.269367088607595,
|
| 806 |
+
"grad_norm": 2.388764780653022,
|
| 807 |
+
"learning_rate": 5e-06,
|
| 808 |
+
"loss": 0.3843,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.289620253164557,
|
| 813 |
+
"grad_norm": 1.974750270308368,
|
| 814 |
+
"learning_rate": 5e-06,
|
| 815 |
+
"loss": 0.3873,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.309873417721519,
|
| 820 |
+
"grad_norm": 1.447456780610406,
|
| 821 |
+
"learning_rate": 5e-06,
|
| 822 |
+
"loss": 0.381,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.330126582278481,
|
| 827 |
+
"grad_norm": 1.3927022295027611,
|
| 828 |
+
"learning_rate": 5e-06,
|
| 829 |
+
"loss": 0.3869,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.350379746835443,
|
| 834 |
+
"grad_norm": 1.215373362438277,
|
| 835 |
+
"learning_rate": 5e-06,
|
| 836 |
+
"loss": 0.3871,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.370632911392405,
|
| 841 |
+
"grad_norm": 1.4491184946598725,
|
| 842 |
+
"learning_rate": 5e-06,
|
| 843 |
+
"loss": 0.3888,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.390886075949367,
|
| 848 |
+
"grad_norm": 1.4189426863567351,
|
| 849 |
+
"learning_rate": 5e-06,
|
| 850 |
+
"loss": 0.3901,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.411139240506329,
|
| 855 |
+
"grad_norm": 1.3984787319231367,
|
| 856 |
+
"learning_rate": 5e-06,
|
| 857 |
+
"loss": 0.3874,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.431392405063291,
|
| 862 |
+
"grad_norm": 1.5285728590269927,
|
| 863 |
+
"learning_rate": 5e-06,
|
| 864 |
+
"loss": 0.3885,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.4516455696202533,
|
| 869 |
+
"grad_norm": 1.6526724638756385,
|
| 870 |
+
"learning_rate": 5e-06,
|
| 871 |
+
"loss": 0.3866,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.4718987341772154,
|
| 876 |
+
"grad_norm": 1.7189706408748655,
|
| 877 |
+
"learning_rate": 5e-06,
|
| 878 |
+
"loss": 0.3892,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.492151898734177,
|
| 883 |
+
"grad_norm": 1.3142654182229083,
|
| 884 |
+
"learning_rate": 5e-06,
|
| 885 |
+
"loss": 0.3914,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.512405063291139,
|
| 890 |
+
"grad_norm": 1.735979097692375,
|
| 891 |
+
"learning_rate": 5e-06,
|
| 892 |
+
"loss": 0.3895,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.5326582278481014,
|
| 897 |
+
"grad_norm": 1.8356865092298218,
|
| 898 |
+
"learning_rate": 5e-06,
|
| 899 |
+
"loss": 0.3876,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.552911392405063,
|
| 904 |
+
"grad_norm": 1.2680188524532179,
|
| 905 |
+
"learning_rate": 5e-06,
|
| 906 |
+
"loss": 0.3808,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.573164556962025,
|
| 911 |
+
"grad_norm": 1.4512168828739789,
|
| 912 |
+
"learning_rate": 5e-06,
|
| 913 |
+
"loss": 0.3891,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.5934177215189873,
|
| 918 |
+
"grad_norm": 1.3295995678864736,
|
| 919 |
+
"learning_rate": 5e-06,
|
| 920 |
+
"loss": 0.3921,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.6136708860759494,
|
| 925 |
+
"grad_norm": 1.3912435194150836,
|
| 926 |
+
"learning_rate": 5e-06,
|
| 927 |
+
"loss": 0.3958,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.6339240506329116,
|
| 932 |
+
"grad_norm": 1.3175096081971012,
|
| 933 |
+
"learning_rate": 5e-06,
|
| 934 |
+
"loss": 0.3915,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.6541772151898733,
|
| 939 |
+
"grad_norm": 1.5566817774133672,
|
| 940 |
+
"learning_rate": 5e-06,
|
| 941 |
+
"loss": 0.3917,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.6744303797468354,
|
| 946 |
+
"grad_norm": 1.3878720965690428,
|
| 947 |
+
"learning_rate": 5e-06,
|
| 948 |
+
"loss": 0.3945,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.6946835443037975,
|
| 953 |
+
"grad_norm": 1.3785817403015144,
|
| 954 |
+
"learning_rate": 5e-06,
|
| 955 |
+
"loss": 0.3953,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.714936708860759,
|
| 960 |
+
"grad_norm": 1.4183014258875806,
|
| 961 |
+
"learning_rate": 5e-06,
|
| 962 |
+
"loss": 0.3974,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.7351898734177214,
|
| 967 |
+
"grad_norm": 1.3491695029291941,
|
| 968 |
+
"learning_rate": 5e-06,
|
| 969 |
+
"loss": 0.3946,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.7554430379746835,
|
| 974 |
+
"grad_norm": 1.2428699126707001,
|
| 975 |
+
"learning_rate": 5e-06,
|
| 976 |
+
"loss": 0.3904,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.7756962025316456,
|
| 981 |
+
"grad_norm": 1.433548321717136,
|
| 982 |
+
"learning_rate": 5e-06,
|
| 983 |
+
"loss": 0.3973,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.7959493670886078,
|
| 988 |
+
"grad_norm": 1.5285229294068068,
|
| 989 |
+
"learning_rate": 5e-06,
|
| 990 |
+
"loss": 0.395,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.81620253164557,
|
| 995 |
+
"grad_norm": 1.3717745770912413,
|
| 996 |
+
"learning_rate": 5e-06,
|
| 997 |
+
"loss": 0.3975,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.8364556962025316,
|
| 1002 |
+
"grad_norm": 1.6107209557365296,
|
| 1003 |
+
"learning_rate": 5e-06,
|
| 1004 |
+
"loss": 0.3919,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.8567088607594937,
|
| 1009 |
+
"grad_norm": 1.4417849324011554,
|
| 1010 |
+
"learning_rate": 5e-06,
|
| 1011 |
+
"loss": 0.3977,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.876962025316456,
|
| 1016 |
+
"grad_norm": 1.3890939860087244,
|
| 1017 |
+
"learning_rate": 5e-06,
|
| 1018 |
+
"loss": 0.3945,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.8972151898734175,
|
| 1023 |
+
"grad_norm": 1.340958614241595,
|
| 1024 |
+
"learning_rate": 5e-06,
|
| 1025 |
+
"loss": 0.3944,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.9174683544303797,
|
| 1030 |
+
"grad_norm": 1.6057483136323554,
|
| 1031 |
+
"learning_rate": 5e-06,
|
| 1032 |
+
"loss": 0.3974,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.937721518987342,
|
| 1037 |
+
"grad_norm": 1.3480539514146224,
|
| 1038 |
+
"learning_rate": 5e-06,
|
| 1039 |
+
"loss": 0.4065,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.957974683544304,
|
| 1044 |
+
"grad_norm": 1.4215727797263549,
|
| 1045 |
+
"learning_rate": 5e-06,
|
| 1046 |
+
"loss": 0.3949,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.978227848101266,
|
| 1051 |
+
"grad_norm": 1.3718015666487833,
|
| 1052 |
+
"learning_rate": 5e-06,
|
| 1053 |
+
"loss": 0.3987,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.9964556962025317,
|
| 1058 |
+
"eval_loss": 0.14610780775547028,
|
| 1059 |
+
"eval_runtime": 253.7654,
|
| 1060 |
+
"eval_samples_per_second": 52.426,
|
| 1061 |
+
"eval_steps_per_second": 0.41,
|
| 1062 |
+
"step": 1479
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.9964556962025317,
|
| 1066 |
+
"step": 1479,
|
| 1067 |
+
"total_flos": 2476961326694400.0,
|
| 1068 |
+
"train_loss": 0.47900067526718665,
|
| 1069 |
+
"train_runtime": 42754.8995,
|
| 1070 |
+
"train_samples_per_second": 17.735,
|
| 1071 |
+
"train_steps_per_second": 0.035
|
| 1072 |
+
}
|
| 1073 |
+
],
|
| 1074 |
+
"logging_steps": 10,
|
| 1075 |
+
"max_steps": 1479,
|
| 1076 |
+
"num_input_tokens_seen": 0,
|
| 1077 |
+
"num_train_epochs": 3,
|
| 1078 |
+
"save_steps": 500,
|
| 1079 |
+
"stateful_callbacks": {
|
| 1080 |
+
"TrainerControl": {
|
| 1081 |
+
"args": {
|
| 1082 |
+
"should_epoch_stop": false,
|
| 1083 |
+
"should_evaluate": false,
|
| 1084 |
+
"should_log": false,
|
| 1085 |
+
"should_save": true,
|
| 1086 |
+
"should_training_stop": true
|
| 1087 |
+
},
|
| 1088 |
+
"attributes": {}
|
| 1089 |
+
}
|
| 1090 |
+
},
|
| 1091 |
+
"total_flos": 2476961326694400.0,
|
| 1092 |
+
"train_batch_size": 8,
|
| 1093 |
+
"trial_name": null,
|
| 1094 |
+
"trial_params": null
|
| 1095 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|