End of training
Browse files- README.md +3 -2
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +2822 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: other
|
|
| 4 |
base_model: mistralai/Ministral-8B-Instruct-2410
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: Ministral-8B-Instruct-2410-PsyCourse-fold5
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# Ministral-8B-Instruct-2410-PsyCourse-fold5
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 4 |
base_model: mistralai/Ministral-8B-Instruct-2410
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: Ministral-8B-Instruct-2410-PsyCourse-fold5
|
|
|
|
| 16 |
|
| 17 |
# Ministral-8B-Instruct-2410-PsyCourse-fold5
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on the course-train-fold1 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0312
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.994228549442093,
|
| 3 |
+
"eval_loss": 0.03119882568717003,
|
| 4 |
+
"eval_runtime": 174.417,
|
| 5 |
+
"eval_samples_per_second": 6.628,
|
| 6 |
+
"eval_steps_per_second": 6.628,
|
| 7 |
+
"total_flos": 8.169046237996646e+17,
|
| 8 |
+
"train_loss": 0.03518175135534515,
|
| 9 |
+
"train_runtime": 38986.9842,
|
| 10 |
+
"train_samples_per_second": 1.333,
|
| 11 |
+
"train_steps_per_second": 0.083
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.994228549442093,
|
| 3 |
+
"eval_loss": 0.03119882568717003,
|
| 4 |
+
"eval_runtime": 174.417,
|
| 5 |
+
"eval_samples_per_second": 6.628,
|
| 6 |
+
"eval_steps_per_second": 6.628
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.994228549442093,
|
| 3 |
+
"total_flos": 8.169046237996646e+17,
|
| 4 |
+
"train_loss": 0.03518175135534515,
|
| 5 |
+
"train_runtime": 38986.9842,
|
| 6 |
+
"train_samples_per_second": 1.333,
|
| 7 |
+
"train_steps_per_second": 0.083
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2822 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.03119882568717003,
|
| 3 |
+
"best_model_checkpoint": "saves/psy-course/Ministral-8B-Instruct-2410/train/fold5/checkpoint-1350",
|
| 4 |
+
"epoch": 4.994228549442093,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 3245,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.015390534821085032,
|
| 13 |
+
"grad_norm": 2.7206928730010986,
|
| 14 |
+
"learning_rate": 3.0769230769230774e-06,
|
| 15 |
+
"loss": 1.336,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.030781069642170065,
|
| 20 |
+
"grad_norm": 2.8094022274017334,
|
| 21 |
+
"learning_rate": 6.153846153846155e-06,
|
| 22 |
+
"loss": 1.271,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0461716044632551,
|
| 27 |
+
"grad_norm": 3.173107862472534,
|
| 28 |
+
"learning_rate": 9.230769230769232e-06,
|
| 29 |
+
"loss": 1.0347,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06156213928434013,
|
| 34 |
+
"grad_norm": 2.2601401805877686,
|
| 35 |
+
"learning_rate": 1.230769230769231e-05,
|
| 36 |
+
"loss": 0.5543,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07695267410542517,
|
| 41 |
+
"grad_norm": 1.1410682201385498,
|
| 42 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 43 |
+
"loss": 0.2581,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07695267410542517,
|
| 48 |
+
"eval_loss": 0.24166099727153778,
|
| 49 |
+
"eval_runtime": 176.1734,
|
| 50 |
+
"eval_samples_per_second": 6.562,
|
| 51 |
+
"eval_steps_per_second": 6.562,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0923432089265102,
|
| 56 |
+
"grad_norm": 1.4863005876541138,
|
| 57 |
+
"learning_rate": 1.8461538461538465e-05,
|
| 58 |
+
"loss": 0.1594,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10773374374759523,
|
| 63 |
+
"grad_norm": 1.223218321800232,
|
| 64 |
+
"learning_rate": 2.1538461538461542e-05,
|
| 65 |
+
"loss": 0.1276,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12312427856868026,
|
| 70 |
+
"grad_norm": 1.2243907451629639,
|
| 71 |
+
"learning_rate": 2.461538461538462e-05,
|
| 72 |
+
"loss": 0.1018,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1385148133897653,
|
| 77 |
+
"grad_norm": 1.4652044773101807,
|
| 78 |
+
"learning_rate": 2.7692307692307694e-05,
|
| 79 |
+
"loss": 0.118,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15390534821085033,
|
| 84 |
+
"grad_norm": 0.7412689924240112,
|
| 85 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 86 |
+
"loss": 0.0853,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.15390534821085033,
|
| 91 |
+
"eval_loss": 0.06947828084230423,
|
| 92 |
+
"eval_runtime": 176.0378,
|
| 93 |
+
"eval_samples_per_second": 6.567,
|
| 94 |
+
"eval_steps_per_second": 6.567,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.16929588303193535,
|
| 99 |
+
"grad_norm": 0.8059899806976318,
|
| 100 |
+
"learning_rate": 3.384615384615385e-05,
|
| 101 |
+
"loss": 0.0648,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.1846864178530204,
|
| 106 |
+
"grad_norm": 0.7964231371879578,
|
| 107 |
+
"learning_rate": 3.692307692307693e-05,
|
| 108 |
+
"loss": 0.0723,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2000769526741054,
|
| 113 |
+
"grad_norm": 1.1007932424545288,
|
| 114 |
+
"learning_rate": 4e-05,
|
| 115 |
+
"loss": 0.0696,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.21546748749519046,
|
| 120 |
+
"grad_norm": 0.7742824554443359,
|
| 121 |
+
"learning_rate": 4.3076923076923084e-05,
|
| 122 |
+
"loss": 0.0786,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.2308580223162755,
|
| 127 |
+
"grad_norm": 0.9034144878387451,
|
| 128 |
+
"learning_rate": 4.615384615384616e-05,
|
| 129 |
+
"loss": 0.0606,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.2308580223162755,
|
| 134 |
+
"eval_loss": 0.05840924009680748,
|
| 135 |
+
"eval_runtime": 176.2462,
|
| 136 |
+
"eval_samples_per_second": 6.559,
|
| 137 |
+
"eval_steps_per_second": 6.559,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.24624855713736052,
|
| 142 |
+
"grad_norm": 0.7853645086288452,
|
| 143 |
+
"learning_rate": 4.923076923076924e-05,
|
| 144 |
+
"loss": 0.0612,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.26163909195844554,
|
| 149 |
+
"grad_norm": 0.7825936079025269,
|
| 150 |
+
"learning_rate": 5.230769230769231e-05,
|
| 151 |
+
"loss": 0.0616,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.2770296267795306,
|
| 156 |
+
"grad_norm": 0.8186638951301575,
|
| 157 |
+
"learning_rate": 5.538461538461539e-05,
|
| 158 |
+
"loss": 0.053,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.2924201616006156,
|
| 163 |
+
"grad_norm": 0.368308961391449,
|
| 164 |
+
"learning_rate": 5.846153846153847e-05,
|
| 165 |
+
"loss": 0.0444,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.30781069642170067,
|
| 170 |
+
"grad_norm": 0.5306175351142883,
|
| 171 |
+
"learning_rate": 6.153846153846155e-05,
|
| 172 |
+
"loss": 0.0581,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.30781069642170067,
|
| 177 |
+
"eval_loss": 0.0543404258787632,
|
| 178 |
+
"eval_runtime": 176.4225,
|
| 179 |
+
"eval_samples_per_second": 6.552,
|
| 180 |
+
"eval_steps_per_second": 6.552,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.3232012312427857,
|
| 185 |
+
"grad_norm": 0.7254672050476074,
|
| 186 |
+
"learning_rate": 6.461538461538462e-05,
|
| 187 |
+
"loss": 0.0555,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.3385917660638707,
|
| 192 |
+
"grad_norm": 0.8422511219978333,
|
| 193 |
+
"learning_rate": 6.76923076923077e-05,
|
| 194 |
+
"loss": 0.0495,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.35398230088495575,
|
| 199 |
+
"grad_norm": 0.3299127519130707,
|
| 200 |
+
"learning_rate": 7.076923076923078e-05,
|
| 201 |
+
"loss": 0.0378,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.3693728357060408,
|
| 206 |
+
"grad_norm": 0.45191943645477295,
|
| 207 |
+
"learning_rate": 7.384615384615386e-05,
|
| 208 |
+
"loss": 0.046,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.38476337052712584,
|
| 213 |
+
"grad_norm": 0.4278528392314911,
|
| 214 |
+
"learning_rate": 7.692307692307693e-05,
|
| 215 |
+
"loss": 0.0439,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.38476337052712584,
|
| 220 |
+
"eval_loss": 0.04281606152653694,
|
| 221 |
+
"eval_runtime": 176.3946,
|
| 222 |
+
"eval_samples_per_second": 6.553,
|
| 223 |
+
"eval_steps_per_second": 6.553,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.4001539053482108,
|
| 228 |
+
"grad_norm": 0.5845353603363037,
|
| 229 |
+
"learning_rate": 8e-05,
|
| 230 |
+
"loss": 0.0398,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.41554444016929587,
|
| 235 |
+
"grad_norm": 0.42944037914276123,
|
| 236 |
+
"learning_rate": 8.307692307692309e-05,
|
| 237 |
+
"loss": 0.0415,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.4309349749903809,
|
| 242 |
+
"grad_norm": 0.5371568202972412,
|
| 243 |
+
"learning_rate": 8.615384615384617e-05,
|
| 244 |
+
"loss": 0.0534,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.44632550981146596,
|
| 249 |
+
"grad_norm": 0.4480336904525757,
|
| 250 |
+
"learning_rate": 8.923076923076924e-05,
|
| 251 |
+
"loss": 0.0521,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.461716044632551,
|
| 256 |
+
"grad_norm": 0.3966178894042969,
|
| 257 |
+
"learning_rate": 9.230769230769232e-05,
|
| 258 |
+
"loss": 0.0405,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.461716044632551,
|
| 263 |
+
"eval_loss": 0.046050868928432465,
|
| 264 |
+
"eval_runtime": 176.5479,
|
| 265 |
+
"eval_samples_per_second": 6.548,
|
| 266 |
+
"eval_steps_per_second": 6.548,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.477106579453636,
|
| 271 |
+
"grad_norm": 0.4799180030822754,
|
| 272 |
+
"learning_rate": 9.53846153846154e-05,
|
| 273 |
+
"loss": 0.051,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.49249711427472104,
|
| 278 |
+
"grad_norm": 0.3221646249294281,
|
| 279 |
+
"learning_rate": 9.846153846153848e-05,
|
| 280 |
+
"loss": 0.0482,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.5078876490958061,
|
| 285 |
+
"grad_norm": 0.4233333468437195,
|
| 286 |
+
"learning_rate": 9.999927654251793e-05,
|
| 287 |
+
"loss": 0.0485,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.5232781839168911,
|
| 292 |
+
"grad_norm": 0.436909019947052,
|
| 293 |
+
"learning_rate": 9.99934890082745e-05,
|
| 294 |
+
"loss": 0.0456,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.5386687187379762,
|
| 299 |
+
"grad_norm": 0.4717266261577606,
|
| 300 |
+
"learning_rate": 9.99819146097084e-05,
|
| 301 |
+
"loss": 0.0428,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.5386687187379762,
|
| 306 |
+
"eval_loss": 0.04454828426241875,
|
| 307 |
+
"eval_runtime": 176.4355,
|
| 308 |
+
"eval_samples_per_second": 6.552,
|
| 309 |
+
"eval_steps_per_second": 6.552,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5540592535590612,
|
| 314 |
+
"grad_norm": 0.3741532564163208,
|
| 315 |
+
"learning_rate": 9.996455468658355e-05,
|
| 316 |
+
"loss": 0.0563,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5694497883801463,
|
| 321 |
+
"grad_norm": 0.41537120938301086,
|
| 322 |
+
"learning_rate": 9.994141124835203e-05,
|
| 323 |
+
"loss": 0.037,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5848403232012312,
|
| 328 |
+
"grad_norm": 0.6107032299041748,
|
| 329 |
+
"learning_rate": 9.991248697392142e-05,
|
| 330 |
+
"loss": 0.0391,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6002308580223162,
|
| 335 |
+
"grad_norm": 0.4859623610973358,
|
| 336 |
+
"learning_rate": 9.987778521134476e-05,
|
| 337 |
+
"loss": 0.0346,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6156213928434013,
|
| 342 |
+
"grad_norm": 0.29415926337242126,
|
| 343 |
+
"learning_rate": 9.983730997743294e-05,
|
| 344 |
+
"loss": 0.0485,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6156213928434013,
|
| 349 |
+
"eval_loss": 0.043341998010873795,
|
| 350 |
+
"eval_runtime": 176.3509,
|
| 351 |
+
"eval_samples_per_second": 6.555,
|
| 352 |
+
"eval_steps_per_second": 6.555,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6310119276644863,
|
| 357 |
+
"grad_norm": 0.3123447299003601,
|
| 358 |
+
"learning_rate": 9.979106595728978e-05,
|
| 359 |
+
"loss": 0.0404,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6464024624855714,
|
| 364 |
+
"grad_norm": 0.5193583369255066,
|
| 365 |
+
"learning_rate": 9.973905850376977e-05,
|
| 366 |
+
"loss": 0.0448,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6617929973066564,
|
| 371 |
+
"grad_norm": 0.5041560530662537,
|
| 372 |
+
"learning_rate": 9.968129363685833e-05,
|
| 373 |
+
"loss": 0.0439,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6771835321277414,
|
| 378 |
+
"grad_norm": 0.46721431612968445,
|
| 379 |
+
"learning_rate": 9.961777804297514e-05,
|
| 380 |
+
"loss": 0.0593,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6925740669488265,
|
| 385 |
+
"grad_norm": 0.49613869190216064,
|
| 386 |
+
"learning_rate": 9.954851907420009e-05,
|
| 387 |
+
"loss": 0.0286,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6925740669488265,
|
| 392 |
+
"eval_loss": 0.04055383428931236,
|
| 393 |
+
"eval_runtime": 176.5544,
|
| 394 |
+
"eval_samples_per_second": 6.548,
|
| 395 |
+
"eval_steps_per_second": 6.548,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.7079646017699115,
|
| 400 |
+
"grad_norm": 0.16034717857837677,
|
| 401 |
+
"learning_rate": 9.947352474742222e-05,
|
| 402 |
+
"loss": 0.0358,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7233551365909965,
|
| 407 |
+
"grad_norm": 0.3644324541091919,
|
| 408 |
+
"learning_rate": 9.93928037434118e-05,
|
| 409 |
+
"loss": 0.0325,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7387456714120816,
|
| 414 |
+
"grad_norm": 0.665282666683197,
|
| 415 |
+
"learning_rate": 9.930636540581556e-05,
|
| 416 |
+
"loss": 0.0424,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.7541362062331666,
|
| 421 |
+
"grad_norm": 0.22589579224586487,
|
| 422 |
+
"learning_rate": 9.921421974007506e-05,
|
| 423 |
+
"loss": 0.0458,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.7695267410542517,
|
| 428 |
+
"grad_norm": 0.28870707750320435,
|
| 429 |
+
"learning_rate": 9.911637741226849e-05,
|
| 430 |
+
"loss": 0.0287,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.7695267410542517,
|
| 435 |
+
"eval_loss": 0.03942457213997841,
|
| 436 |
+
"eval_runtime": 176.5603,
|
| 437 |
+
"eval_samples_per_second": 6.547,
|
| 438 |
+
"eval_steps_per_second": 6.547,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.7849172758753367,
|
| 443 |
+
"grad_norm": 0.43207934498786926,
|
| 444 |
+
"learning_rate": 9.90128497478762e-05,
|
| 445 |
+
"loss": 0.0307,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.8003078106964217,
|
| 450 |
+
"grad_norm": 0.29495513439178467,
|
| 451 |
+
"learning_rate": 9.890364873046965e-05,
|
| 452 |
+
"loss": 0.0427,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.8156983455175068,
|
| 457 |
+
"grad_norm": 0.40809714794158936,
|
| 458 |
+
"learning_rate": 9.878878700032427e-05,
|
| 459 |
+
"loss": 0.0535,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.8310888803385917,
|
| 464 |
+
"grad_norm": 0.3146349787712097,
|
| 465 |
+
"learning_rate": 9.866827785295638e-05,
|
| 466 |
+
"loss": 0.0423,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.8464794151596768,
|
| 471 |
+
"grad_norm": 0.24875745177268982,
|
| 472 |
+
"learning_rate": 9.854213523758413e-05,
|
| 473 |
+
"loss": 0.0426,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8464794151596768,
|
| 478 |
+
"eval_loss": 0.035120412707328796,
|
| 479 |
+
"eval_runtime": 176.5293,
|
| 480 |
+
"eval_samples_per_second": 6.548,
|
| 481 |
+
"eval_steps_per_second": 6.548,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.8618699499807618,
|
| 486 |
+
"grad_norm": 0.2829786241054535,
|
| 487 |
+
"learning_rate": 9.841037375551294e-05,
|
| 488 |
+
"loss": 0.0359,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.8772604848018468,
|
| 493 |
+
"grad_norm": 0.24912841618061066,
|
| 494 |
+
"learning_rate": 9.827300865844527e-05,
|
| 495 |
+
"loss": 0.0251,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.8926510196229319,
|
| 500 |
+
"grad_norm": 0.3470945954322815,
|
| 501 |
+
"learning_rate": 9.813005584671522e-05,
|
| 502 |
+
"loss": 0.0343,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.9080415544440169,
|
| 507 |
+
"grad_norm": 0.23871859908103943,
|
| 508 |
+
"learning_rate": 9.79815318674481e-05,
|
| 509 |
+
"loss": 0.0508,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.923432089265102,
|
| 514 |
+
"grad_norm": 0.29896286129951477,
|
| 515 |
+
"learning_rate": 9.782745391264498e-05,
|
| 516 |
+
"loss": 0.0338,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.923432089265102,
|
| 521 |
+
"eval_loss": 0.03507744148373604,
|
| 522 |
+
"eval_runtime": 176.5725,
|
| 523 |
+
"eval_samples_per_second": 6.547,
|
| 524 |
+
"eval_steps_per_second": 6.547,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.938822624086187,
|
| 529 |
+
"grad_norm": 0.41820308566093445,
|
| 530 |
+
"learning_rate": 9.76678398171927e-05,
|
| 531 |
+
"loss": 0.0309,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.954213158907272,
|
| 536 |
+
"grad_norm": 0.28623440861701965,
|
| 537 |
+
"learning_rate": 9.750270805679945e-05,
|
| 538 |
+
"loss": 0.0429,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.9696036937283571,
|
| 543 |
+
"grad_norm": 0.45469871163368225,
|
| 544 |
+
"learning_rate": 9.733207774585618e-05,
|
| 545 |
+
"loss": 0.0426,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.9849942285494421,
|
| 550 |
+
"grad_norm": 0.2690652012825012,
|
| 551 |
+
"learning_rate": 9.715596863522398e-05,
|
| 552 |
+
"loss": 0.0332,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.0003847633705272,
|
| 557 |
+
"grad_norm": 0.2812378704547882,
|
| 558 |
+
"learning_rate": 9.697440110994801e-05,
|
| 559 |
+
"loss": 0.0301,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.0003847633705272,
|
| 564 |
+
"eval_loss": 0.036583807319402695,
|
| 565 |
+
"eval_runtime": 176.5985,
|
| 566 |
+
"eval_samples_per_second": 6.546,
|
| 567 |
+
"eval_steps_per_second": 6.546,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.0157752981916122,
|
| 572 |
+
"grad_norm": 0.2946244180202484,
|
| 573 |
+
"learning_rate": 9.678739618689775e-05,
|
| 574 |
+
"loss": 0.0353,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.0311658330126972,
|
| 579 |
+
"grad_norm": 0.23367083072662354,
|
| 580 |
+
"learning_rate": 9.659497551233431e-05,
|
| 581 |
+
"loss": 0.0315,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.0465563678337821,
|
| 586 |
+
"grad_norm": 0.2701486647129059,
|
| 587 |
+
"learning_rate": 9.639716135940485e-05,
|
| 588 |
+
"loss": 0.0332,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.0619469026548674,
|
| 593 |
+
"grad_norm": 0.4597524404525757,
|
| 594 |
+
"learning_rate": 9.619397662556435e-05,
|
| 595 |
+
"loss": 0.043,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.0773374374759523,
|
| 600 |
+
"grad_norm": 0.3910011649131775,
|
| 601 |
+
"learning_rate": 9.598544482992517e-05,
|
| 602 |
+
"loss": 0.0339,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.0773374374759523,
|
| 607 |
+
"eval_loss": 0.037031788378953934,
|
| 608 |
+
"eval_runtime": 176.6917,
|
| 609 |
+
"eval_samples_per_second": 6.542,
|
| 610 |
+
"eval_steps_per_second": 6.542,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.0927279722970373,
|
| 615 |
+
"grad_norm": 0.3245735168457031,
|
| 616 |
+
"learning_rate": 9.57715901105348e-05,
|
| 617 |
+
"loss": 0.0309,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.1081185071181223,
|
| 622 |
+
"grad_norm": 0.2758731245994568,
|
| 623 |
+
"learning_rate": 9.555243722158158e-05,
|
| 624 |
+
"loss": 0.031,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.1235090419392073,
|
| 629 |
+
"grad_norm": 0.22663231194019318,
|
| 630 |
+
"learning_rate": 9.532801153052958e-05,
|
| 631 |
+
"loss": 0.0266,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.1388995767602923,
|
| 636 |
+
"grad_norm": 0.5782523155212402,
|
| 637 |
+
"learning_rate": 9.509833901518209e-05,
|
| 638 |
+
"loss": 0.0361,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.1542901115813775,
|
| 643 |
+
"grad_norm": 0.3744742274284363,
|
| 644 |
+
"learning_rate": 9.486344626067475e-05,
|
| 645 |
+
"loss": 0.0269,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.1542901115813775,
|
| 650 |
+
"eval_loss": 0.035565976053476334,
|
| 651 |
+
"eval_runtime": 176.7396,
|
| 652 |
+
"eval_samples_per_second": 6.541,
|
| 653 |
+
"eval_steps_per_second": 6.541,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1696806464024625,
|
| 658 |
+
"grad_norm": 0.24146856367588043,
|
| 659 |
+
"learning_rate": 9.462336045639815e-05,
|
| 660 |
+
"loss": 0.0351,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1850711812235475,
|
| 665 |
+
"grad_norm": 0.25894129276275635,
|
| 666 |
+
"learning_rate": 9.437810939285068e-05,
|
| 667 |
+
"loss": 0.0365,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.2004617160446325,
|
| 672 |
+
"grad_norm": 0.31034451723098755,
|
| 673 |
+
"learning_rate": 9.412772145842165e-05,
|
| 674 |
+
"loss": 0.0342,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.2158522508657175,
|
| 679 |
+
"grad_norm": 0.32283952832221985,
|
| 680 |
+
"learning_rate": 9.387222563610535e-05,
|
| 681 |
+
"loss": 0.035,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2312427856868027,
|
| 686 |
+
"grad_norm": 0.22168344259262085,
|
| 687 |
+
"learning_rate": 9.361165150014606e-05,
|
| 688 |
+
"loss": 0.0276,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2312427856868027,
|
| 693 |
+
"eval_loss": 0.034503836184740067,
|
| 694 |
+
"eval_runtime": 176.7383,
|
| 695 |
+
"eval_samples_per_second": 6.541,
|
| 696 |
+
"eval_steps_per_second": 6.541,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.2466333205078877,
|
| 701 |
+
"grad_norm": 0.10351806879043579,
|
| 702 |
+
"learning_rate": 9.334602921261492e-05,
|
| 703 |
+
"loss": 0.0294,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.2620238553289727,
|
| 708 |
+
"grad_norm": 0.4381557106971741,
|
| 709 |
+
"learning_rate": 9.307538951991852e-05,
|
| 710 |
+
"loss": 0.0281,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.2774143901500576,
|
| 715 |
+
"grad_norm": 0.26532843708992004,
|
| 716 |
+
"learning_rate": 9.279976374923988e-05,
|
| 717 |
+
"loss": 0.0307,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.2928049249711426,
|
| 722 |
+
"grad_norm": 0.38265183568000793,
|
| 723 |
+
"learning_rate": 9.251918380491238e-05,
|
| 724 |
+
"loss": 0.0254,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.3081954597922278,
|
| 729 |
+
"grad_norm": 0.34733256697654724,
|
| 730 |
+
"learning_rate": 9.223368216472668e-05,
|
| 731 |
+
"loss": 0.0293,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.3081954597922278,
|
| 736 |
+
"eval_loss": 0.033552058041095734,
|
| 737 |
+
"eval_runtime": 176.7151,
|
| 738 |
+
"eval_samples_per_second": 6.542,
|
| 739 |
+
"eval_steps_per_second": 6.542,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.3235859946133128,
|
| 744 |
+
"grad_norm": 0.23357051610946655,
|
| 745 |
+
"learning_rate": 9.194329187617127e-05,
|
| 746 |
+
"loss": 0.0261,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.3389765294343978,
|
| 751 |
+
"grad_norm": 0.2974819839000702,
|
| 752 |
+
"learning_rate": 9.164804655260735e-05,
|
| 753 |
+
"loss": 0.0264,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.3543670642554828,
|
| 758 |
+
"grad_norm": 0.1959962546825409,
|
| 759 |
+
"learning_rate": 9.134798036937778e-05,
|
| 760 |
+
"loss": 0.0292,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.3697575990765678,
|
| 765 |
+
"grad_norm": 0.31932732462882996,
|
| 766 |
+
"learning_rate": 9.104312805985134e-05,
|
| 767 |
+
"loss": 0.0362,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.385148133897653,
|
| 772 |
+
"grad_norm": 0.301615446805954,
|
| 773 |
+
"learning_rate": 9.073352491140221e-05,
|
| 774 |
+
"loss": 0.0216,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.385148133897653,
|
| 779 |
+
"eval_loss": 0.033949967473745346,
|
| 780 |
+
"eval_runtime": 176.7728,
|
| 781 |
+
"eval_samples_per_second": 6.539,
|
| 782 |
+
"eval_steps_per_second": 6.539,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.400538668718738,
|
| 787 |
+
"grad_norm": 0.3114616572856903,
|
| 788 |
+
"learning_rate": 9.041920676132543e-05,
|
| 789 |
+
"loss": 0.0312,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.415929203539823,
|
| 794 |
+
"grad_norm": 0.2502421438694,
|
| 795 |
+
"learning_rate": 9.010020999268854e-05,
|
| 796 |
+
"loss": 0.0329,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.431319738360908,
|
| 801 |
+
"grad_norm": 0.2229824811220169,
|
| 802 |
+
"learning_rate": 8.977657153012027e-05,
|
| 803 |
+
"loss": 0.0283,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.446710273181993,
|
| 808 |
+
"grad_norm": 0.5619177222251892,
|
| 809 |
+
"learning_rate": 8.944832883553633e-05,
|
| 810 |
+
"loss": 0.0285,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.4621008080030782,
|
| 815 |
+
"grad_norm": 0.15374122560024261,
|
| 816 |
+
"learning_rate": 8.91155199038032e-05,
|
| 817 |
+
"loss": 0.036,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.4621008080030782,
|
| 822 |
+
"eval_loss": 0.03325812891125679,
|
| 823 |
+
"eval_runtime": 176.7292,
|
| 824 |
+
"eval_samples_per_second": 6.541,
|
| 825 |
+
"eval_steps_per_second": 6.541,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.4774913428241632,
|
| 830 |
+
"grad_norm": 0.24114222824573517,
|
| 831 |
+
"learning_rate": 8.877818325834006e-05,
|
| 832 |
+
"loss": 0.0283,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.4928818776452482,
|
| 837 |
+
"grad_norm": 0.09029097855091095,
|
| 838 |
+
"learning_rate": 8.843635794665961e-05,
|
| 839 |
+
"loss": 0.0219,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.5082724124663334,
|
| 844 |
+
"grad_norm": 0.41925254464149475,
|
| 845 |
+
"learning_rate": 8.809008353584829e-05,
|
| 846 |
+
"loss": 0.0303,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.5236629472874181,
|
| 851 |
+
"grad_norm": 0.22500939667224884,
|
| 852 |
+
"learning_rate": 8.773940010798627e-05,
|
| 853 |
+
"loss": 0.0304,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.5390534821085033,
|
| 858 |
+
"grad_norm": 0.3530929386615753,
|
| 859 |
+
"learning_rate": 8.738434825550785e-05,
|
| 860 |
+
"loss": 0.0319,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.5390534821085033,
|
| 865 |
+
"eval_loss": 0.03614142909646034,
|
| 866 |
+
"eval_runtime": 176.7074,
|
| 867 |
+
"eval_samples_per_second": 6.542,
|
| 868 |
+
"eval_steps_per_second": 6.542,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.5544440169295883,
|
| 873 |
+
"grad_norm": 0.3209225535392761,
|
| 874 |
+
"learning_rate": 8.702496907650274e-05,
|
| 875 |
+
"loss": 0.0337,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.5698345517506733,
|
| 880 |
+
"grad_norm": 0.307273805141449,
|
| 881 |
+
"learning_rate": 8.666130416995897e-05,
|
| 882 |
+
"loss": 0.0311,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.5852250865717585,
|
| 887 |
+
"grad_norm": 0.2404596507549286,
|
| 888 |
+
"learning_rate": 8.629339563094758e-05,
|
| 889 |
+
"loss": 0.0303,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.6006156213928433,
|
| 894 |
+
"grad_norm": 0.40445876121520996,
|
| 895 |
+
"learning_rate": 8.592128604575014e-05,
|
| 896 |
+
"loss": 0.0271,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.6160061562139285,
|
| 901 |
+
"grad_norm": 0.25610461831092834,
|
| 902 |
+
"learning_rate": 8.554501848692921e-05,
|
| 903 |
+
"loss": 0.0312,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.6160061562139285,
|
| 908 |
+
"eval_loss": 0.032448507845401764,
|
| 909 |
+
"eval_runtime": 176.7221,
|
| 910 |
+
"eval_samples_per_second": 6.541,
|
| 911 |
+
"eval_steps_per_second": 6.541,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.6313966910350135,
|
| 916 |
+
"grad_norm": 0.17163515090942383,
|
| 917 |
+
"learning_rate": 8.51646365083426e-05,
|
| 918 |
+
"loss": 0.0215,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.6467872258560985,
|
| 923 |
+
"grad_norm": 0.2591453194618225,
|
| 924 |
+
"learning_rate": 8.478018414010191e-05,
|
| 925 |
+
"loss": 0.0267,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.6621777606771835,
|
| 930 |
+
"grad_norm": 0.4842621088027954,
|
| 931 |
+
"learning_rate": 8.439170588347598e-05,
|
| 932 |
+
"loss": 0.0223,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.6775682954982685,
|
| 937 |
+
"grad_norm": 1.0715452432632446,
|
| 938 |
+
"learning_rate": 8.399924670573969e-05,
|
| 939 |
+
"loss": 0.0288,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.6929588303193537,
|
| 944 |
+
"grad_norm": 0.1876203417778015,
|
| 945 |
+
"learning_rate": 8.360285203496894e-05,
|
| 946 |
+
"loss": 0.0333,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.6929588303193537,
|
| 951 |
+
"eval_loss": 0.03803209587931633,
|
| 952 |
+
"eval_runtime": 176.8671,
|
| 953 |
+
"eval_samples_per_second": 6.536,
|
| 954 |
+
"eval_steps_per_second": 6.536,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.7083493651404387,
|
| 959 |
+
"grad_norm": 0.3779871165752411,
|
| 960 |
+
"learning_rate": 8.320256775478228e-05,
|
| 961 |
+
"loss": 0.0325,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7237398999615237,
|
| 966 |
+
"grad_norm": 0.2203492522239685,
|
| 967 |
+
"learning_rate": 8.279844019902968e-05,
|
| 968 |
+
"loss": 0.0237,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7391304347826086,
|
| 973 |
+
"grad_norm": 0.4551416039466858,
|
| 974 |
+
"learning_rate": 8.239051614642934e-05,
|
| 975 |
+
"loss": 0.0347,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7545209696036936,
|
| 980 |
+
"grad_norm": 0.2498016655445099,
|
| 981 |
+
"learning_rate": 8.197884281515292e-05,
|
| 982 |
+
"loss": 0.038,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7699115044247788,
|
| 987 |
+
"grad_norm": 0.16282948851585388,
|
| 988 |
+
"learning_rate": 8.156346785735997e-05,
|
| 989 |
+
"loss": 0.0228,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.7699115044247788,
|
| 994 |
+
"eval_loss": 0.03305572643876076,
|
| 995 |
+
"eval_runtime": 176.8475,
|
| 996 |
+
"eval_samples_per_second": 6.537,
|
| 997 |
+
"eval_steps_per_second": 6.537,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.7853020392458638,
|
| 1002 |
+
"grad_norm": 0.1479075402021408,
|
| 1003 |
+
"learning_rate": 8.114443935368198e-05,
|
| 1004 |
+
"loss": 0.0342,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.8006925740669488,
|
| 1009 |
+
"grad_norm": 0.2684459090232849,
|
| 1010 |
+
"learning_rate": 8.072180580765709e-05,
|
| 1011 |
+
"loss": 0.0235,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.8160831088880338,
|
| 1016 |
+
"grad_norm": 0.2641782760620117,
|
| 1017 |
+
"learning_rate": 8.02956161401155e-05,
|
| 1018 |
+
"loss": 0.0244,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.8314736437091188,
|
| 1023 |
+
"grad_norm": 0.2599339187145233,
|
| 1024 |
+
"learning_rate": 7.98659196835169e-05,
|
| 1025 |
+
"loss": 0.0295,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.846864178530204,
|
| 1030 |
+
"grad_norm": 0.12659390270709991,
|
| 1031 |
+
"learning_rate": 7.943276617624014e-05,
|
| 1032 |
+
"loss": 0.0217,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.846864178530204,
|
| 1037 |
+
"eval_loss": 0.03583278879523277,
|
| 1038 |
+
"eval_runtime": 176.7116,
|
| 1039 |
+
"eval_samples_per_second": 6.542,
|
| 1040 |
+
"eval_steps_per_second": 6.542,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.862254713351289,
|
| 1045 |
+
"grad_norm": 0.4283539056777954,
|
| 1046 |
+
"learning_rate": 7.899620575682578e-05,
|
| 1047 |
+
"loss": 0.0286,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.877645248172374,
|
| 1052 |
+
"grad_norm": 0.1819627583026886,
|
| 1053 |
+
"learning_rate": 7.85562889581725e-05,
|
| 1054 |
+
"loss": 0.0221,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.893035782993459,
|
| 1059 |
+
"grad_norm": 0.13169661164283752,
|
| 1060 |
+
"learning_rate": 7.811306670168788e-05,
|
| 1061 |
+
"loss": 0.0288,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.908426317814544,
|
| 1066 |
+
"grad_norm": 0.3242426812648773,
|
| 1067 |
+
"learning_rate": 7.766659029139393e-05,
|
| 1068 |
+
"loss": 0.0332,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.9238168526356292,
|
| 1073 |
+
"grad_norm": 0.38562312722206116,
|
| 1074 |
+
"learning_rate": 7.72169114079887e-05,
|
| 1075 |
+
"loss": 0.0272,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.9238168526356292,
|
| 1080 |
+
"eval_loss": 0.03237110376358032,
|
| 1081 |
+
"eval_runtime": 176.7523,
|
| 1082 |
+
"eval_samples_per_second": 6.54,
|
| 1083 |
+
"eval_steps_per_second": 6.54,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.9392073874567142,
|
| 1088 |
+
"grad_norm": 0.8540070056915283,
|
| 1089 |
+
"learning_rate": 7.676408210286407e-05,
|
| 1090 |
+
"loss": 0.0289,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.9545979222777992,
|
| 1095 |
+
"grad_norm": 0.23134426772594452,
|
| 1096 |
+
"learning_rate": 7.630815479208066e-05,
|
| 1097 |
+
"loss": 0.0284,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.9699884570988841,
|
| 1102 |
+
"grad_norm": 0.26955580711364746,
|
| 1103 |
+
"learning_rate": 7.584918225030053e-05,
|
| 1104 |
+
"loss": 0.0243,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.9853789919199691,
|
| 1109 |
+
"grad_norm": 0.22115769982337952,
|
| 1110 |
+
"learning_rate": 7.538721760467845e-05,
|
| 1111 |
+
"loss": 0.0319,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.0007695267410543,
|
| 1116 |
+
"grad_norm": 0.20801742374897003,
|
| 1117 |
+
"learning_rate": 7.49223143287122e-05,
|
| 1118 |
+
"loss": 0.0217,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.0007695267410543,
|
| 1123 |
+
"eval_loss": 0.03183276578783989,
|
| 1124 |
+
"eval_runtime": 176.8781,
|
| 1125 |
+
"eval_samples_per_second": 6.536,
|
| 1126 |
+
"eval_steps_per_second": 6.536,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 2.016160061562139,
|
| 1131 |
+
"grad_norm": 0.33942127227783203,
|
| 1132 |
+
"learning_rate": 7.445452623605307e-05,
|
| 1133 |
+
"loss": 0.0168,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.0315505963832243,
|
| 1138 |
+
"grad_norm": 0.3799745440483093,
|
| 1139 |
+
"learning_rate": 7.398390747427662e-05,
|
| 1140 |
+
"loss": 0.02,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.0469411312043095,
|
| 1145 |
+
"grad_norm": 0.15786810219287872,
|
| 1146 |
+
"learning_rate": 7.351051251861501e-05,
|
| 1147 |
+
"loss": 0.0175,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.0623316660253943,
|
| 1152 |
+
"grad_norm": 0.0710686594247818,
|
| 1153 |
+
"learning_rate": 7.303439616565146e-05,
|
| 1154 |
+
"loss": 0.0194,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.0777222008464795,
|
| 1159 |
+
"grad_norm": 0.2171255350112915,
|
| 1160 |
+
"learning_rate": 7.255561352697732e-05,
|
| 1161 |
+
"loss": 0.0175,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.0777222008464795,
|
| 1166 |
+
"eval_loss": 0.03119882568717003,
|
| 1167 |
+
"eval_runtime": 176.8301,
|
| 1168 |
+
"eval_samples_per_second": 6.537,
|
| 1169 |
+
"eval_steps_per_second": 6.537,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.0931127356675643,
|
| 1174 |
+
"grad_norm": 0.1561356782913208,
|
| 1175 |
+
"learning_rate": 7.207422002281281e-05,
|
| 1176 |
+
"loss": 0.017,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.1085032704886495,
|
| 1181 |
+
"grad_norm": 0.2565746307373047,
|
| 1182 |
+
"learning_rate": 7.159027137559197e-05,
|
| 1183 |
+
"loss": 0.0156,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.1238938053097347,
|
| 1188 |
+
"grad_norm": 0.2514025568962097,
|
| 1189 |
+
"learning_rate": 7.110382360351267e-05,
|
| 1190 |
+
"loss": 0.0127,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.1392843401308195,
|
| 1195 |
+
"grad_norm": 0.0824156105518341,
|
| 1196 |
+
"learning_rate": 7.061493301405244e-05,
|
| 1197 |
+
"loss": 0.0136,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.1546748749519047,
|
| 1202 |
+
"grad_norm": 0.6427235007286072,
|
| 1203 |
+
"learning_rate": 7.012365619745064e-05,
|
| 1204 |
+
"loss": 0.021,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.1546748749519047,
|
| 1209 |
+
"eval_loss": 0.03412633389234543,
|
| 1210 |
+
"eval_runtime": 176.7342,
|
| 1211 |
+
"eval_samples_per_second": 6.541,
|
| 1212 |
+
"eval_steps_per_second": 6.541,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.1700654097729895,
|
| 1217 |
+
"grad_norm": 0.08514008671045303,
|
| 1218 |
+
"learning_rate": 6.963005002015808e-05,
|
| 1219 |
+
"loss": 0.0164,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.1854559445940747,
|
| 1224 |
+
"grad_norm": 0.20415261387825012,
|
| 1225 |
+
"learning_rate": 6.91341716182545e-05,
|
| 1226 |
+
"loss": 0.0213,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.20084647941516,
|
| 1231 |
+
"grad_norm": 0.2123573273420334,
|
| 1232 |
+
"learning_rate": 6.863607839083507e-05,
|
| 1233 |
+
"loss": 0.0127,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.2162370142362446,
|
| 1238 |
+
"grad_norm": 0.39403170347213745,
|
| 1239 |
+
"learning_rate": 6.813582799336624e-05,
|
| 1240 |
+
"loss": 0.0191,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.23162754905733,
|
| 1245 |
+
"grad_norm": 0.0883919969201088,
|
| 1246 |
+
"learning_rate": 6.763347833101192e-05,
|
| 1247 |
+
"loss": 0.009,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.23162754905733,
|
| 1252 |
+
"eval_loss": 0.039153777062892914,
|
| 1253 |
+
"eval_runtime": 176.7616,
|
| 1254 |
+
"eval_samples_per_second": 6.54,
|
| 1255 |
+
"eval_steps_per_second": 6.54,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.2470180838784146,
|
| 1260 |
+
"grad_norm": 0.5361382365226746,
|
| 1261 |
+
"learning_rate": 6.712908755193094e-05,
|
| 1262 |
+
"loss": 0.0191,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.2624086186995,
|
| 1267 |
+
"grad_norm": 0.14046382904052734,
|
| 1268 |
+
"learning_rate": 6.662271404054621e-05,
|
| 1269 |
+
"loss": 0.0236,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.2777991535205846,
|
| 1274 |
+
"grad_norm": 0.25211387872695923,
|
| 1275 |
+
"learning_rate": 6.611441641078657e-05,
|
| 1276 |
+
"loss": 0.0183,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.29318968834167,
|
| 1281 |
+
"grad_norm": 0.21686653792858124,
|
| 1282 |
+
"learning_rate": 6.560425349930208e-05,
|
| 1283 |
+
"loss": 0.0205,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.308580223162755,
|
| 1288 |
+
"grad_norm": 0.6495646238327026,
|
| 1289 |
+
"learning_rate": 6.509228435865357e-05,
|
| 1290 |
+
"loss": 0.0186,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.308580223162755,
|
| 1295 |
+
"eval_loss": 0.034755948930978775,
|
| 1296 |
+
"eval_runtime": 176.7081,
|
| 1297 |
+
"eval_samples_per_second": 6.542,
|
| 1298 |
+
"eval_steps_per_second": 6.542,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.32397075798384,
|
| 1303 |
+
"grad_norm": 0.21111302077770233,
|
| 1304 |
+
"learning_rate": 6.45785682504772e-05,
|
| 1305 |
+
"loss": 0.0201,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.339361292804925,
|
| 1310 |
+
"grad_norm": 0.6884567141532898,
|
| 1311 |
+
"learning_rate": 6.406316463862467e-05,
|
| 1312 |
+
"loss": 0.0177,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.3547518276260098,
|
| 1317 |
+
"grad_norm": 0.09983156621456146,
|
| 1318 |
+
"learning_rate": 6.35461331822803e-05,
|
| 1319 |
+
"loss": 0.0145,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.370142362447095,
|
| 1324 |
+
"grad_norm": 0.23539000749588013,
|
| 1325 |
+
"learning_rate": 6.302753372905515e-05,
|
| 1326 |
+
"loss": 0.0176,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.38553289726818,
|
| 1331 |
+
"grad_norm": 0.5075021982192993,
|
| 1332 |
+
"learning_rate": 6.250742630805971e-05,
|
| 1333 |
+
"loss": 0.0163,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.38553289726818,
|
| 1338 |
+
"eval_loss": 0.03947930037975311,
|
| 1339 |
+
"eval_runtime": 176.7236,
|
| 1340 |
+
"eval_samples_per_second": 6.541,
|
| 1341 |
+
"eval_steps_per_second": 6.541,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.400923432089265,
|
| 1346 |
+
"grad_norm": 0.22470280528068542,
|
| 1347 |
+
"learning_rate": 6.198587112295526e-05,
|
| 1348 |
+
"loss": 0.0146,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.41631396691035,
|
| 1353 |
+
"grad_norm": 0.3534475862979889,
|
| 1354 |
+
"learning_rate": 6.14629285449852e-05,
|
| 1355 |
+
"loss": 0.0176,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.431704501731435,
|
| 1360 |
+
"grad_norm": 0.11134660243988037,
|
| 1361 |
+
"learning_rate": 6.093865910598688e-05,
|
| 1362 |
+
"loss": 0.0198,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.44709503655252,
|
| 1367 |
+
"grad_norm": 0.19116228818893433,
|
| 1368 |
+
"learning_rate": 6.0413123491385025e-05,
|
| 1369 |
+
"loss": 0.018,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.4624855713736054,
|
| 1374 |
+
"grad_norm": 0.181107759475708,
|
| 1375 |
+
"learning_rate": 5.988638253316713e-05,
|
| 1376 |
+
"loss": 0.0123,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.4624855713736054,
|
| 1381 |
+
"eval_loss": 0.035887934267520905,
|
| 1382 |
+
"eval_runtime": 176.7823,
|
| 1383 |
+
"eval_samples_per_second": 6.539,
|
| 1384 |
+
"eval_steps_per_second": 6.539,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.47787610619469,
|
| 1389 |
+
"grad_norm": 0.34913918375968933,
|
| 1390 |
+
"learning_rate": 5.935849720284206e-05,
|
| 1391 |
+
"loss": 0.0151,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.4932666410157753,
|
| 1396 |
+
"grad_norm": 0.22570717334747314,
|
| 1397 |
+
"learning_rate": 5.8829528604382436e-05,
|
| 1398 |
+
"loss": 0.0213,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.50865717583686,
|
| 1403 |
+
"grad_norm": 0.09938590228557587,
|
| 1404 |
+
"learning_rate": 5.829953796715176e-05,
|
| 1405 |
+
"loss": 0.0142,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.5240477106579453,
|
| 1410 |
+
"grad_norm": 0.43842482566833496,
|
| 1411 |
+
"learning_rate": 5.7768586638816924e-05,
|
| 1412 |
+
"loss": 0.0209,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.5394382454790305,
|
| 1417 |
+
"grad_norm": 0.1973314881324768,
|
| 1418 |
+
"learning_rate": 5.723673607824705e-05,
|
| 1419 |
+
"loss": 0.0196,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.5394382454790305,
|
| 1424 |
+
"eval_loss": 0.034880444407463074,
|
| 1425 |
+
"eval_runtime": 176.7697,
|
| 1426 |
+
"eval_samples_per_second": 6.54,
|
| 1427 |
+
"eval_steps_per_second": 6.54,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.5548287803001153,
|
| 1432 |
+
"grad_norm": 0.3357468247413635,
|
| 1433 |
+
"learning_rate": 5.670404784839953e-05,
|
| 1434 |
+
"loss": 0.0128,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.5702193151212005,
|
| 1439 |
+
"grad_norm": 0.3688250482082367,
|
| 1440 |
+
"learning_rate": 5.6170583609193984e-05,
|
| 1441 |
+
"loss": 0.0172,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 2.5856098499422853,
|
| 1446 |
+
"grad_norm": 0.3962181508541107,
|
| 1447 |
+
"learning_rate": 5.56364051103749e-05,
|
| 1448 |
+
"loss": 0.0221,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.6010003847633705,
|
| 1453 |
+
"grad_norm": 0.17332716286182404,
|
| 1454 |
+
"learning_rate": 5.5101574184364056e-05,
|
| 1455 |
+
"loss": 0.0179,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.6163909195844557,
|
| 1460 |
+
"grad_norm": 0.3918059468269348,
|
| 1461 |
+
"learning_rate": 5.4566152739103116e-05,
|
| 1462 |
+
"loss": 0.0201,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 2.6163909195844557,
|
| 1467 |
+
"eval_loss": 0.03516693413257599,
|
| 1468 |
+
"eval_runtime": 176.7671,
|
| 1469 |
+
"eval_samples_per_second": 6.54,
|
| 1470 |
+
"eval_steps_per_second": 6.54,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.6317814544055405,
|
| 1475 |
+
"grad_norm": 0.5600950717926025,
|
| 1476 |
+
"learning_rate": 5.403020275088786e-05,
|
| 1477 |
+
"loss": 0.0177,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 2.6471719892266257,
|
| 1482 |
+
"grad_norm": 0.5886516571044922,
|
| 1483 |
+
"learning_rate": 5.349378625719408e-05,
|
| 1484 |
+
"loss": 0.0247,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 2.6625625240477104,
|
| 1489 |
+
"grad_norm": 0.48264405131340027,
|
| 1490 |
+
"learning_rate": 5.2956965349496743e-05,
|
| 1491 |
+
"loss": 0.0188,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 2.6779530588687956,
|
| 1496 |
+
"grad_norm": 0.14684589207172394,
|
| 1497 |
+
"learning_rate": 5.241980216608261e-05,
|
| 1498 |
+
"loss": 0.0143,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 2.693343593689881,
|
| 1503 |
+
"grad_norm": 0.08048424124717712,
|
| 1504 |
+
"learning_rate": 5.188235888485773e-05,
|
| 1505 |
+
"loss": 0.0223,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.693343593689881,
|
| 1510 |
+
"eval_loss": 0.03291754424571991,
|
| 1511 |
+
"eval_runtime": 176.7369,
|
| 1512 |
+
"eval_samples_per_second": 6.541,
|
| 1513 |
+
"eval_steps_per_second": 6.541,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.7087341285109656,
|
| 1518 |
+
"grad_norm": 0.2262515276670456,
|
| 1519 |
+
"learning_rate": 5.13446977161501e-05,
|
| 1520 |
+
"loss": 0.0127,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.724124663332051,
|
| 1525 |
+
"grad_norm": 0.46145889163017273,
|
| 1526 |
+
"learning_rate": 5.0806880895508766e-05,
|
| 1527 |
+
"loss": 0.0179,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.7395151981531356,
|
| 1532 |
+
"grad_norm": 0.7554391622543335,
|
| 1533 |
+
"learning_rate": 5.026897067649976e-05,
|
| 1534 |
+
"loss": 0.0234,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.754905732974221,
|
| 1539 |
+
"grad_norm": 0.1861138641834259,
|
| 1540 |
+
"learning_rate": 4.973102932350026e-05,
|
| 1541 |
+
"loss": 0.0155,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.770296267795306,
|
| 1546 |
+
"grad_norm": 0.2975349724292755,
|
| 1547 |
+
"learning_rate": 4.9193119104491245e-05,
|
| 1548 |
+
"loss": 0.0192,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.770296267795306,
|
| 1553 |
+
"eval_loss": 0.03241715207695961,
|
| 1554 |
+
"eval_runtime": 176.853,
|
| 1555 |
+
"eval_samples_per_second": 6.537,
|
| 1556 |
+
"eval_steps_per_second": 6.537,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.785686802616391,
|
| 1561 |
+
"grad_norm": 0.42107677459716797,
|
| 1562 |
+
"learning_rate": 4.86553022838499e-05,
|
| 1563 |
+
"loss": 0.0181,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.801077337437476,
|
| 1568 |
+
"grad_norm": 0.351321280002594,
|
| 1569 |
+
"learning_rate": 4.8117641115142285e-05,
|
| 1570 |
+
"loss": 0.022,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.8164678722585608,
|
| 1575 |
+
"grad_norm": 0.4118291735649109,
|
| 1576 |
+
"learning_rate": 4.758019783391741e-05,
|
| 1577 |
+
"loss": 0.0191,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.831858407079646,
|
| 1582 |
+
"grad_norm": 0.30672571063041687,
|
| 1583 |
+
"learning_rate": 4.704303465050327e-05,
|
| 1584 |
+
"loss": 0.0197,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.847248941900731,
|
| 1589 |
+
"grad_norm": 0.1432432234287262,
|
| 1590 |
+
"learning_rate": 4.6506213742805924e-05,
|
| 1591 |
+
"loss": 0.0191,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.847248941900731,
|
| 1596 |
+
"eval_loss": 0.032423555850982666,
|
| 1597 |
+
"eval_runtime": 176.8384,
|
| 1598 |
+
"eval_samples_per_second": 6.537,
|
| 1599 |
+
"eval_steps_per_second": 6.537,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.862639476721816,
|
| 1604 |
+
"grad_norm": 0.28516244888305664,
|
| 1605 |
+
"learning_rate": 4.5969797249112146e-05,
|
| 1606 |
+
"loss": 0.014,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.878030011542901,
|
| 1611 |
+
"grad_norm": 0.3050757348537445,
|
| 1612 |
+
"learning_rate": 4.54338472608969e-05,
|
| 1613 |
+
"loss": 0.0225,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.893420546363986,
|
| 1618 |
+
"grad_norm": 0.15351629257202148,
|
| 1619 |
+
"learning_rate": 4.489842581563597e-05,
|
| 1620 |
+
"loss": 0.0149,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.908811081185071,
|
| 1625 |
+
"grad_norm": 0.12462982535362244,
|
| 1626 |
+
"learning_rate": 4.436359488962511e-05,
|
| 1627 |
+
"loss": 0.0163,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.9242016160061564,
|
| 1632 |
+
"grad_norm": 0.2019914984703064,
|
| 1633 |
+
"learning_rate": 4.382941639080602e-05,
|
| 1634 |
+
"loss": 0.0162,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.9242016160061564,
|
| 1639 |
+
"eval_loss": 0.03359019756317139,
|
| 1640 |
+
"eval_runtime": 176.7494,
|
| 1641 |
+
"eval_samples_per_second": 6.54,
|
| 1642 |
+
"eval_steps_per_second": 6.54,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.939592150827241,
|
| 1647 |
+
"grad_norm": 0.23269765079021454,
|
| 1648 |
+
"learning_rate": 4.3295952151600475e-05,
|
| 1649 |
+
"loss": 0.0204,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.9549826856483263,
|
| 1654 |
+
"grad_norm": 0.4043470323085785,
|
| 1655 |
+
"learning_rate": 4.276326392175296e-05,
|
| 1656 |
+
"loss": 0.0199,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.970373220469411,
|
| 1661 |
+
"grad_norm": 0.12517714500427246,
|
| 1662 |
+
"learning_rate": 4.2231413361183095e-05,
|
| 1663 |
+
"loss": 0.0145,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.9857637552904963,
|
| 1668 |
+
"grad_norm": 0.2903136610984802,
|
| 1669 |
+
"learning_rate": 4.1700462032848244e-05,
|
| 1670 |
+
"loss": 0.015,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 3.0011542901115815,
|
| 1675 |
+
"grad_norm": 0.15643754601478577,
|
| 1676 |
+
"learning_rate": 4.117047139561758e-05,
|
| 1677 |
+
"loss": 0.0238,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 3.0011542901115815,
|
| 1682 |
+
"eval_loss": 0.034210145473480225,
|
| 1683 |
+
"eval_runtime": 176.8536,
|
| 1684 |
+
"eval_samples_per_second": 6.536,
|
| 1685 |
+
"eval_steps_per_second": 6.536,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 3.0165448249326663,
|
| 1690 |
+
"grad_norm": 0.08787263184785843,
|
| 1691 |
+
"learning_rate": 4.0641502797157966e-05,
|
| 1692 |
+
"loss": 0.0064,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 3.0319353597537515,
|
| 1697 |
+
"grad_norm": 0.04949400946497917,
|
| 1698 |
+
"learning_rate": 4.011361746683288e-05,
|
| 1699 |
+
"loss": 0.0096,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 3.0473258945748363,
|
| 1704 |
+
"grad_norm": 0.4407104253768921,
|
| 1705 |
+
"learning_rate": 3.958687650861499e-05,
|
| 1706 |
+
"loss": 0.009,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 3.0627164293959215,
|
| 1711 |
+
"grad_norm": 0.28349077701568604,
|
| 1712 |
+
"learning_rate": 3.906134089401313e-05,
|
| 1713 |
+
"loss": 0.0055,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 3.0781069642170067,
|
| 1718 |
+
"grad_norm": 0.11285337805747986,
|
| 1719 |
+
"learning_rate": 3.853707145501482e-05,
|
| 1720 |
+
"loss": 0.0092,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 3.0781069642170067,
|
| 1725 |
+
"eval_loss": 0.03811664134263992,
|
| 1726 |
+
"eval_runtime": 176.7856,
|
| 1727 |
+
"eval_samples_per_second": 6.539,
|
| 1728 |
+
"eval_steps_per_second": 6.539,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 3.0934974990380915,
|
| 1733 |
+
"grad_norm": 0.40362584590911865,
|
| 1734 |
+
"learning_rate": 3.801412887704475e-05,
|
| 1735 |
+
"loss": 0.0049,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 3.1088880338591767,
|
| 1740 |
+
"grad_norm": 0.15941868722438812,
|
| 1741 |
+
"learning_rate": 3.749257369194029e-05,
|
| 1742 |
+
"loss": 0.0093,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 3.1242785686802614,
|
| 1747 |
+
"grad_norm": 0.06539350003004074,
|
| 1748 |
+
"learning_rate": 3.697246627094487e-05,
|
| 1749 |
+
"loss": 0.0082,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 3.1396691035013466,
|
| 1754 |
+
"grad_norm": 0.08355661481618881,
|
| 1755 |
+
"learning_rate": 3.6453866817719726e-05,
|
| 1756 |
+
"loss": 0.0088,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 3.155059638322432,
|
| 1761 |
+
"grad_norm": 0.5320833325386047,
|
| 1762 |
+
"learning_rate": 3.593683536137533e-05,
|
| 1763 |
+
"loss": 0.0105,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 3.155059638322432,
|
| 1768 |
+
"eval_loss": 0.040933817625045776,
|
| 1769 |
+
"eval_runtime": 176.6988,
|
| 1770 |
+
"eval_samples_per_second": 6.542,
|
| 1771 |
+
"eval_steps_per_second": 6.542,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 3.1704501731435166,
|
| 1776 |
+
"grad_norm": 0.049008555710315704,
|
| 1777 |
+
"learning_rate": 3.542143174952282e-05,
|
| 1778 |
+
"loss": 0.0043,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 3.185840707964602,
|
| 1783 |
+
"grad_norm": 0.42514464259147644,
|
| 1784 |
+
"learning_rate": 3.490771564134643e-05,
|
| 1785 |
+
"loss": 0.0092,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 3.2012312427856866,
|
| 1790 |
+
"grad_norm": 0.24654439091682434,
|
| 1791 |
+
"learning_rate": 3.4395746500697925e-05,
|
| 1792 |
+
"loss": 0.0115,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 3.216621777606772,
|
| 1797 |
+
"grad_norm": 0.408346027135849,
|
| 1798 |
+
"learning_rate": 3.388558358921343e-05,
|
| 1799 |
+
"loss": 0.0078,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 3.232012312427857,
|
| 1804 |
+
"grad_norm": 0.2585791051387787,
|
| 1805 |
+
"learning_rate": 3.337728595945378e-05,
|
| 1806 |
+
"loss": 0.0096,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 3.232012312427857,
|
| 1811 |
+
"eval_loss": 0.040773503482341766,
|
| 1812 |
+
"eval_runtime": 176.7674,
|
| 1813 |
+
"eval_samples_per_second": 6.54,
|
| 1814 |
+
"eval_steps_per_second": 6.54,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.247402847248942,
|
| 1819 |
+
"grad_norm": 0.14975428581237793,
|
| 1820 |
+
"learning_rate": 3.287091244806907e-05,
|
| 1821 |
+
"loss": 0.0088,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.262793382070027,
|
| 1826 |
+
"grad_norm": 0.47811585664749146,
|
| 1827 |
+
"learning_rate": 3.2366521668988106e-05,
|
| 1828 |
+
"loss": 0.0091,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.2781839168911118,
|
| 1833 |
+
"grad_norm": 0.4079134166240692,
|
| 1834 |
+
"learning_rate": 3.186417200663379e-05,
|
| 1835 |
+
"loss": 0.0075,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.293574451712197,
|
| 1840 |
+
"grad_norm": 0.14326900243759155,
|
| 1841 |
+
"learning_rate": 3.136392160916495e-05,
|
| 1842 |
+
"loss": 0.0072,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.308964986533282,
|
| 1847 |
+
"grad_norm": 0.4556676149368286,
|
| 1848 |
+
"learning_rate": 3.086582838174551e-05,
|
| 1849 |
+
"loss": 0.0078,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.308964986533282,
|
| 1854 |
+
"eval_loss": 0.04120837152004242,
|
| 1855 |
+
"eval_runtime": 176.7919,
|
| 1856 |
+
"eval_samples_per_second": 6.539,
|
| 1857 |
+
"eval_steps_per_second": 6.539,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 3.324355521354367,
|
| 1862 |
+
"grad_norm": 0.22372718155384064,
|
| 1863 |
+
"learning_rate": 3.036994997984194e-05,
|
| 1864 |
+
"loss": 0.0074,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.339746056175452,
|
| 1869 |
+
"grad_norm": 0.2346556931734085,
|
| 1870 |
+
"learning_rate": 2.9876343802549357e-05,
|
| 1871 |
+
"loss": 0.011,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 3.355136590996537,
|
| 1876 |
+
"grad_norm": 0.38766953349113464,
|
| 1877 |
+
"learning_rate": 2.938506698594755e-05,
|
| 1878 |
+
"loss": 0.0101,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 3.370527125817622,
|
| 1883 |
+
"grad_norm": 0.23224134743213654,
|
| 1884 |
+
"learning_rate": 2.8896176396487334e-05,
|
| 1885 |
+
"loss": 0.0062,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 3.3859176606387074,
|
| 1890 |
+
"grad_norm": 0.06096711382269859,
|
| 1891 |
+
"learning_rate": 2.8409728624408067e-05,
|
| 1892 |
+
"loss": 0.012,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 3.3859176606387074,
|
| 1897 |
+
"eval_loss": 0.04045013338327408,
|
| 1898 |
+
"eval_runtime": 176.7461,
|
| 1899 |
+
"eval_samples_per_second": 6.54,
|
| 1900 |
+
"eval_steps_per_second": 6.54,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 3.401308195459792,
|
| 1905 |
+
"grad_norm": 0.08051846921443939,
|
| 1906 |
+
"learning_rate": 2.7925779977187215e-05,
|
| 1907 |
+
"loss": 0.0073,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 3.4166987302808773,
|
| 1912 |
+
"grad_norm": 0.1640942096710205,
|
| 1913 |
+
"learning_rate": 2.7444386473022686e-05,
|
| 1914 |
+
"loss": 0.0063,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 3.432089265101962,
|
| 1919 |
+
"grad_norm": 0.11584623157978058,
|
| 1920 |
+
"learning_rate": 2.696560383434854e-05,
|
| 1921 |
+
"loss": 0.011,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 3.4474797999230473,
|
| 1926 |
+
"grad_norm": 0.2081407755613327,
|
| 1927 |
+
"learning_rate": 2.6489487481384988e-05,
|
| 1928 |
+
"loss": 0.012,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 3.4628703347441325,
|
| 1933 |
+
"grad_norm": 0.16449487209320068,
|
| 1934 |
+
"learning_rate": 2.601609252572339e-05,
|
| 1935 |
+
"loss": 0.0074,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 3.4628703347441325,
|
| 1940 |
+
"eval_loss": 0.0384063720703125,
|
| 1941 |
+
"eval_runtime": 176.7987,
|
| 1942 |
+
"eval_samples_per_second": 6.539,
|
| 1943 |
+
"eval_steps_per_second": 6.539,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 3.4782608695652173,
|
| 1948 |
+
"grad_norm": 0.04802235588431358,
|
| 1949 |
+
"learning_rate": 2.554547376394692e-05,
|
| 1950 |
+
"loss": 0.007,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 3.4936514043863025,
|
| 1955 |
+
"grad_norm": 0.23349222540855408,
|
| 1956 |
+
"learning_rate": 2.5077685671287808e-05,
|
| 1957 |
+
"loss": 0.0057,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 3.5090419392073873,
|
| 1962 |
+
"grad_norm": 0.11469706147909164,
|
| 1963 |
+
"learning_rate": 2.4612782395321593e-05,
|
| 1964 |
+
"loss": 0.0066,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 3.5244324740284725,
|
| 1969 |
+
"grad_norm": 0.21006856858730316,
|
| 1970 |
+
"learning_rate": 2.4150817749699496e-05,
|
| 1971 |
+
"loss": 0.0066,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 3.5398230088495577,
|
| 1976 |
+
"grad_norm": 0.1930118054151535,
|
| 1977 |
+
"learning_rate": 2.3691845207919357e-05,
|
| 1978 |
+
"loss": 0.0101,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 3.5398230088495577,
|
| 1983 |
+
"eval_loss": 0.04059465229511261,
|
| 1984 |
+
"eval_runtime": 176.7509,
|
| 1985 |
+
"eval_samples_per_second": 6.54,
|
| 1986 |
+
"eval_steps_per_second": 6.54,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 3.5552135436706425,
|
| 1991 |
+
"grad_norm": 0.05533791333436966,
|
| 1992 |
+
"learning_rate": 2.3235917897135934e-05,
|
| 1993 |
+
"loss": 0.0108,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 3.5706040784917277,
|
| 1998 |
+
"grad_norm": 0.6226391196250916,
|
| 1999 |
+
"learning_rate": 2.2783088592011303e-05,
|
| 2000 |
+
"loss": 0.0108,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.5859946133128124,
|
| 2005 |
+
"grad_norm": 0.2105931043624878,
|
| 2006 |
+
"learning_rate": 2.233340970860608e-05,
|
| 2007 |
+
"loss": 0.008,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.6013851481338977,
|
| 2012 |
+
"grad_norm": 0.07847414165735245,
|
| 2013 |
+
"learning_rate": 2.1886933298312125e-05,
|
| 2014 |
+
"loss": 0.0103,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 3.616775682954983,
|
| 2019 |
+
"grad_norm": 0.27414873242378235,
|
| 2020 |
+
"learning_rate": 2.1443711041827503e-05,
|
| 2021 |
+
"loss": 0.0056,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 3.616775682954983,
|
| 2026 |
+
"eval_loss": 0.03969665616750717,
|
| 2027 |
+
"eval_runtime": 176.7788,
|
| 2028 |
+
"eval_samples_per_second": 6.539,
|
| 2029 |
+
"eval_steps_per_second": 6.539,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 3.6321662177760676,
|
| 2034 |
+
"grad_norm": 0.27824512124061584,
|
| 2035 |
+
"learning_rate": 2.1003794243174252e-05,
|
| 2036 |
+
"loss": 0.0155,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 3.647556752597153,
|
| 2041 |
+
"grad_norm": 0.24925042688846588,
|
| 2042 |
+
"learning_rate": 2.0567233823759886e-05,
|
| 2043 |
+
"loss": 0.0096,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 3.6629472874182376,
|
| 2048 |
+
"grad_norm": 0.14463971555233002,
|
| 2049 |
+
"learning_rate": 2.0134080316483113e-05,
|
| 2050 |
+
"loss": 0.0091,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 3.678337822239323,
|
| 2055 |
+
"grad_norm": 0.21811449527740479,
|
| 2056 |
+
"learning_rate": 1.970438385988452e-05,
|
| 2057 |
+
"loss": 0.0117,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.693728357060408,
|
| 2062 |
+
"grad_norm": 0.18893787264823914,
|
| 2063 |
+
"learning_rate": 1.927819419234292e-05,
|
| 2064 |
+
"loss": 0.0114,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 3.693728357060408,
|
| 2069 |
+
"eval_loss": 0.03624710813164711,
|
| 2070 |
+
"eval_runtime": 176.7812,
|
| 2071 |
+
"eval_samples_per_second": 6.539,
|
| 2072 |
+
"eval_steps_per_second": 6.539,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 3.709118891881493,
|
| 2077 |
+
"grad_norm": 0.14122995734214783,
|
| 2078 |
+
"learning_rate": 1.885556064631801e-05,
|
| 2079 |
+
"loss": 0.0081,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 3.724509426702578,
|
| 2084 |
+
"grad_norm": 0.05854243040084839,
|
| 2085 |
+
"learning_rate": 1.843653214264003e-05,
|
| 2086 |
+
"loss": 0.0072,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 3.7398999615236628,
|
| 2091 |
+
"grad_norm": 0.2255101203918457,
|
| 2092 |
+
"learning_rate": 1.8021157184847087e-05,
|
| 2093 |
+
"loss": 0.0087,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 3.755290496344748,
|
| 2098 |
+
"grad_norm": 0.08764062821865082,
|
| 2099 |
+
"learning_rate": 1.7609483853570668e-05,
|
| 2100 |
+
"loss": 0.0053,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 3.770681031165833,
|
| 2105 |
+
"grad_norm": 0.02414390817284584,
|
| 2106 |
+
"learning_rate": 1.720155980097034e-05,
|
| 2107 |
+
"loss": 0.0056,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 3.770681031165833,
|
| 2112 |
+
"eval_loss": 0.03867615386843681,
|
| 2113 |
+
"eval_runtime": 176.7505,
|
| 2114 |
+
"eval_samples_per_second": 6.54,
|
| 2115 |
+
"eval_steps_per_second": 6.54,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.786071565986918,
|
| 2120 |
+
"grad_norm": 0.24228930473327637,
|
| 2121 |
+
"learning_rate": 1.6797432245217736e-05,
|
| 2122 |
+
"loss": 0.0067,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.801462100808003,
|
| 2127 |
+
"grad_norm": 0.2944065034389496,
|
| 2128 |
+
"learning_rate": 1.6397147965031072e-05,
|
| 2129 |
+
"loss": 0.0048,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.816852635629088,
|
| 2134 |
+
"grad_norm": 0.12245519459247589,
|
| 2135 |
+
"learning_rate": 1.600075329426033e-05,
|
| 2136 |
+
"loss": 0.0121,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.832243170450173,
|
| 2141 |
+
"grad_norm": 0.37902891635894775,
|
| 2142 |
+
"learning_rate": 1.560829411652403e-05,
|
| 2143 |
+
"loss": 0.0106,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.8476337052712584,
|
| 2148 |
+
"grad_norm": 0.17577596008777618,
|
| 2149 |
+
"learning_rate": 1.521981585989809e-05,
|
| 2150 |
+
"loss": 0.0074,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.8476337052712584,
|
| 2155 |
+
"eval_loss": 0.03889692202210426,
|
| 2156 |
+
"eval_runtime": 176.7082,
|
| 2157 |
+
"eval_samples_per_second": 6.542,
|
| 2158 |
+
"eval_steps_per_second": 6.542,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 3.863024240092343,
|
| 2163 |
+
"grad_norm": 0.03732967749238014,
|
| 2164 |
+
"learning_rate": 1.4835363491657412e-05,
|
| 2165 |
+
"loss": 0.0096,
|
| 2166 |
+
"step": 2510
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 3.8784147749134283,
|
| 2170 |
+
"grad_norm": 0.21517157554626465,
|
| 2171 |
+
"learning_rate": 1.4454981513070791e-05,
|
| 2172 |
+
"loss": 0.0052,
|
| 2173 |
+
"step": 2520
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 3.893805309734513,
|
| 2177 |
+
"grad_norm": 0.04260919243097305,
|
| 2178 |
+
"learning_rate": 1.4078713954249873e-05,
|
| 2179 |
+
"loss": 0.0065,
|
| 2180 |
+
"step": 2530
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 3.9091958445555983,
|
| 2184 |
+
"grad_norm": 0.06845144182443619,
|
| 2185 |
+
"learning_rate": 1.3706604369052434e-05,
|
| 2186 |
+
"loss": 0.0039,
|
| 2187 |
+
"step": 2540
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 3.9245863793766835,
|
| 2191 |
+
"grad_norm": 0.4723328948020935,
|
| 2192 |
+
"learning_rate": 1.3338695830041047e-05,
|
| 2193 |
+
"loss": 0.0089,
|
| 2194 |
+
"step": 2550
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 3.9245863793766835,
|
| 2198 |
+
"eval_loss": 0.040084753185510635,
|
| 2199 |
+
"eval_runtime": 176.8028,
|
| 2200 |
+
"eval_samples_per_second": 6.538,
|
| 2201 |
+
"eval_steps_per_second": 6.538,
|
| 2202 |
+
"step": 2550
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 3.9399769141977683,
|
| 2206 |
+
"grad_norm": 0.5228933095932007,
|
| 2207 |
+
"learning_rate": 1.2975030923497262e-05,
|
| 2208 |
+
"loss": 0.0088,
|
| 2209 |
+
"step": 2560
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 3.9553674490188535,
|
| 2213 |
+
"grad_norm": 0.25889304280281067,
|
| 2214 |
+
"learning_rate": 1.2615651744492151e-05,
|
| 2215 |
+
"loss": 0.0058,
|
| 2216 |
+
"step": 2570
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 3.9707579838399383,
|
| 2220 |
+
"grad_norm": 0.03479775786399841,
|
| 2221 |
+
"learning_rate": 1.2260599892013719e-05,
|
| 2222 |
+
"loss": 0.0117,
|
| 2223 |
+
"step": 2580
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 3.9861485186610235,
|
| 2227 |
+
"grad_norm": 0.2841411828994751,
|
| 2228 |
+
"learning_rate": 1.1909916464151715e-05,
|
| 2229 |
+
"loss": 0.0069,
|
| 2230 |
+
"step": 2590
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 4.001539053482109,
|
| 2234 |
+
"grad_norm": 0.017366070300340652,
|
| 2235 |
+
"learning_rate": 1.1563642053340406e-05,
|
| 2236 |
+
"loss": 0.0096,
|
| 2237 |
+
"step": 2600
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 4.001539053482109,
|
| 2241 |
+
"eval_loss": 0.04020934924483299,
|
| 2242 |
+
"eval_runtime": 176.6968,
|
| 2243 |
+
"eval_samples_per_second": 6.542,
|
| 2244 |
+
"eval_steps_per_second": 6.542,
|
| 2245 |
+
"step": 2600
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 4.016929588303194,
|
| 2249 |
+
"grad_norm": 0.031723860651254654,
|
| 2250 |
+
"learning_rate": 1.1221816741659964e-05,
|
| 2251 |
+
"loss": 0.0039,
|
| 2252 |
+
"step": 2610
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 4.032320123124278,
|
| 2256 |
+
"grad_norm": 0.12695831060409546,
|
| 2257 |
+
"learning_rate": 1.0884480096196803e-05,
|
| 2258 |
+
"loss": 0.0022,
|
| 2259 |
+
"step": 2620
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 4.047710657945363,
|
| 2263 |
+
"grad_norm": 0.12556283175945282,
|
| 2264 |
+
"learning_rate": 1.0551671164463666e-05,
|
| 2265 |
+
"loss": 0.0021,
|
| 2266 |
+
"step": 2630
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 4.063101192766449,
|
| 2270 |
+
"grad_norm": 0.020965544506907463,
|
| 2271 |
+
"learning_rate": 1.0223428469879736e-05,
|
| 2272 |
+
"loss": 0.0044,
|
| 2273 |
+
"step": 2640
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 4.078491727587534,
|
| 2277 |
+
"grad_norm": 0.03366950526833534,
|
| 2278 |
+
"learning_rate": 9.899790007311455e-06,
|
| 2279 |
+
"loss": 0.0019,
|
| 2280 |
+
"step": 2650
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 4.078491727587534,
|
| 2284 |
+
"eval_loss": 0.04220307990908623,
|
| 2285 |
+
"eval_runtime": 176.7951,
|
| 2286 |
+
"eval_samples_per_second": 6.539,
|
| 2287 |
+
"eval_steps_per_second": 6.539,
|
| 2288 |
+
"step": 2650
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 4.093882262408619,
|
| 2292 |
+
"grad_norm": 0.2073393017053604,
|
| 2293 |
+
"learning_rate": 9.580793238674573e-06,
|
| 2294 |
+
"loss": 0.0051,
|
| 2295 |
+
"step": 2660
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 4.109272797229703,
|
| 2299 |
+
"grad_norm": 0.14802664518356323,
|
| 2300 |
+
"learning_rate": 9.266475088597781e-06,
|
| 2301 |
+
"loss": 0.0025,
|
| 2302 |
+
"step": 2670
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 4.124663332050789,
|
| 2306 |
+
"grad_norm": 0.06581874936819077,
|
| 2307 |
+
"learning_rate": 8.956871940148681e-06,
|
| 2308 |
+
"loss": 0.0027,
|
| 2309 |
+
"step": 2680
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 4.140053866871874,
|
| 2313 |
+
"grad_norm": 0.057812996208667755,
|
| 2314 |
+
"learning_rate": 8.65201963062225e-06,
|
| 2315 |
+
"loss": 0.0051,
|
| 2316 |
+
"step": 2690
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 4.155444401692959,
|
| 2320 |
+
"grad_norm": 0.035848990082740784,
|
| 2321 |
+
"learning_rate": 8.351953447392674e-06,
|
| 2322 |
+
"loss": 0.0074,
|
| 2323 |
+
"step": 2700
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 4.155444401692959,
|
| 2327 |
+
"eval_loss": 0.04460546746850014,
|
| 2328 |
+
"eval_runtime": 176.7731,
|
| 2329 |
+
"eval_samples_per_second": 6.539,
|
| 2330 |
+
"eval_steps_per_second": 6.539,
|
| 2331 |
+
"step": 2700
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 4.170834936514044,
|
| 2335 |
+
"grad_norm": 0.029859701171517372,
|
| 2336 |
+
"learning_rate": 8.056708123828738e-06,
|
| 2337 |
+
"loss": 0.0038,
|
| 2338 |
+
"step": 2710
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 4.186225471335129,
|
| 2342 |
+
"grad_norm": 0.07501061260700226,
|
| 2343 |
+
"learning_rate": 7.76631783527334e-06,
|
| 2344 |
+
"loss": 0.0082,
|
| 2345 |
+
"step": 2720
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 4.201616006156214,
|
| 2349 |
+
"grad_norm": 0.04285607114434242,
|
| 2350 |
+
"learning_rate": 7.4808161950876145e-06,
|
| 2351 |
+
"loss": 0.0026,
|
| 2352 |
+
"step": 2730
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 4.217006540977299,
|
| 2356 |
+
"grad_norm": 0.06884312629699707,
|
| 2357 |
+
"learning_rate": 7.200236250760111e-06,
|
| 2358 |
+
"loss": 0.0041,
|
| 2359 |
+
"step": 2740
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 4.232397075798384,
|
| 2363 |
+
"grad_norm": 0.07443416863679886,
|
| 2364 |
+
"learning_rate": 6.924610480081478e-06,
|
| 2365 |
+
"loss": 0.0018,
|
| 2366 |
+
"step": 2750
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 4.232397075798384,
|
| 2370 |
+
"eval_loss": 0.04528596252202988,
|
| 2371 |
+
"eval_runtime": 176.7651,
|
| 2372 |
+
"eval_samples_per_second": 6.54,
|
| 2373 |
+
"eval_steps_per_second": 6.54,
|
| 2374 |
+
"step": 2750
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 4.247787610619469,
|
| 2378 |
+
"grad_norm": 0.04174703359603882,
|
| 2379 |
+
"learning_rate": 6.6539707873850774e-06,
|
| 2380 |
+
"loss": 0.0023,
|
| 2381 |
+
"step": 2760
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 4.263178145440554,
|
| 2385 |
+
"grad_norm": 0.06728123128414154,
|
| 2386 |
+
"learning_rate": 6.3883484998539525e-06,
|
| 2387 |
+
"loss": 0.0016,
|
| 2388 |
+
"step": 2770
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 4.278568680261639,
|
| 2392 |
+
"grad_norm": 0.10411453992128372,
|
| 2393 |
+
"learning_rate": 6.127774363894667e-06,
|
| 2394 |
+
"loss": 0.0021,
|
| 2395 |
+
"step": 2780
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 4.293959215082724,
|
| 2399 |
+
"grad_norm": 0.07528620958328247,
|
| 2400 |
+
"learning_rate": 5.872278541578352e-06,
|
| 2401 |
+
"loss": 0.0034,
|
| 2402 |
+
"step": 2790
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 4.309349749903809,
|
| 2406 |
+
"grad_norm": 0.07204550504684448,
|
| 2407 |
+
"learning_rate": 5.6218906071493275e-06,
|
| 2408 |
+
"loss": 0.0019,
|
| 2409 |
+
"step": 2800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 4.309349749903809,
|
| 2413 |
+
"eval_loss": 0.04676542431116104,
|
| 2414 |
+
"eval_runtime": 176.876,
|
| 2415 |
+
"eval_samples_per_second": 6.536,
|
| 2416 |
+
"eval_steps_per_second": 6.536,
|
| 2417 |
+
"step": 2800
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 4.324740284724895,
|
| 2421 |
+
"grad_norm": 0.06287376582622528,
|
| 2422 |
+
"learning_rate": 5.376639543601858e-06,
|
| 2423 |
+
"loss": 0.0026,
|
| 2424 |
+
"step": 2810
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 4.340130819545979,
|
| 2428 |
+
"grad_norm": 0.012383749708533287,
|
| 2429 |
+
"learning_rate": 5.136553739325256e-06,
|
| 2430 |
+
"loss": 0.0014,
|
| 2431 |
+
"step": 2820
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 4.355521354367064,
|
| 2435 |
+
"grad_norm": 0.05571524053812027,
|
| 2436 |
+
"learning_rate": 4.901660984817908e-06,
|
| 2437 |
+
"loss": 0.0019,
|
| 2438 |
+
"step": 2830
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 4.370911889188149,
|
| 2442 |
+
"grad_norm": 0.027088260278105736,
|
| 2443 |
+
"learning_rate": 4.671988469470434e-06,
|
| 2444 |
+
"loss": 0.0024,
|
| 2445 |
+
"step": 2840
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 4.3863024240092345,
|
| 2449 |
+
"grad_norm": 0.02969769574701786,
|
| 2450 |
+
"learning_rate": 4.447562778418435e-06,
|
| 2451 |
+
"loss": 0.002,
|
| 2452 |
+
"step": 2850
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 4.3863024240092345,
|
| 2456 |
+
"eval_loss": 0.048255208879709244,
|
| 2457 |
+
"eval_runtime": 176.7793,
|
| 2458 |
+
"eval_samples_per_second": 6.539,
|
| 2459 |
+
"eval_steps_per_second": 6.539,
|
| 2460 |
+
"step": 2850
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 4.40169295883032,
|
| 2464 |
+
"grad_norm": 0.25782549381256104,
|
| 2465 |
+
"learning_rate": 4.228409889465218e-06,
|
| 2466 |
+
"loss": 0.0022,
|
| 2467 |
+
"step": 2860
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 4.417083493651404,
|
| 2471 |
+
"grad_norm": 0.11440496146678925,
|
| 2472 |
+
"learning_rate": 4.014555170074824e-06,
|
| 2473 |
+
"loss": 0.0009,
|
| 2474 |
+
"step": 2870
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 4.432474028472489,
|
| 2478 |
+
"grad_norm": 0.02885556034743786,
|
| 2479 |
+
"learning_rate": 3.8060233744356633e-06,
|
| 2480 |
+
"loss": 0.0072,
|
| 2481 |
+
"step": 2880
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 4.4478645632935745,
|
| 2485 |
+
"grad_norm": 0.011130722239613533,
|
| 2486 |
+
"learning_rate": 3.602838640595152e-06,
|
| 2487 |
+
"loss": 0.0026,
|
| 2488 |
+
"step": 2890
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 4.46325509811466,
|
| 2492 |
+
"grad_norm": 0.424197793006897,
|
| 2493 |
+
"learning_rate": 3.4050244876656866e-06,
|
| 2494 |
+
"loss": 0.0045,
|
| 2495 |
+
"step": 2900
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 4.46325509811466,
|
| 2499 |
+
"eval_loss": 0.04861905798316002,
|
| 2500 |
+
"eval_runtime": 176.8295,
|
| 2501 |
+
"eval_samples_per_second": 6.537,
|
| 2502 |
+
"eval_steps_per_second": 6.537,
|
| 2503 |
+
"step": 2900
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 4.478645632935745,
|
| 2507 |
+
"grad_norm": 0.1396138072013855,
|
| 2508 |
+
"learning_rate": 3.2126038131022552e-06,
|
| 2509 |
+
"loss": 0.0071,
|
| 2510 |
+
"step": 2910
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 4.494036167756829,
|
| 2514 |
+
"grad_norm": 0.06447521597146988,
|
| 2515 |
+
"learning_rate": 3.025598890051995e-06,
|
| 2516 |
+
"loss": 0.0038,
|
| 2517 |
+
"step": 2920
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 4.5094267025779144,
|
| 2521 |
+
"grad_norm": 0.0140528017655015,
|
| 2522 |
+
"learning_rate": 2.8440313647760288e-06,
|
| 2523 |
+
"loss": 0.003,
|
| 2524 |
+
"step": 2930
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 4.524817237399,
|
| 2528 |
+
"grad_norm": 0.28481969237327576,
|
| 2529 |
+
"learning_rate": 2.6679222541438397e-06,
|
| 2530 |
+
"loss": 0.0058,
|
| 2531 |
+
"step": 2940
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 4.540207772220085,
|
| 2535 |
+
"grad_norm": 0.025602344423532486,
|
| 2536 |
+
"learning_rate": 2.4972919432005582e-06,
|
| 2537 |
+
"loss": 0.002,
|
| 2538 |
+
"step": 2950
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 4.540207772220085,
|
| 2542 |
+
"eval_loss": 0.04802686348557472,
|
| 2543 |
+
"eval_runtime": 176.8568,
|
| 2544 |
+
"eval_samples_per_second": 6.536,
|
| 2545 |
+
"eval_steps_per_second": 6.536,
|
| 2546 |
+
"step": 2950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 4.555598307041169,
|
| 2550 |
+
"grad_norm": 0.13335546851158142,
|
| 2551 |
+
"learning_rate": 2.3321601828073135e-06,
|
| 2552 |
+
"loss": 0.0012,
|
| 2553 |
+
"step": 2960
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 4.570988841862254,
|
| 2557 |
+
"grad_norm": 0.0808529257774353,
|
| 2558 |
+
"learning_rate": 2.1725460873550317e-06,
|
| 2559 |
+
"loss": 0.0073,
|
| 2560 |
+
"step": 2970
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 4.58637937668334,
|
| 2564 |
+
"grad_norm": 0.041818227618932724,
|
| 2565 |
+
"learning_rate": 2.0184681325519096e-06,
|
| 2566 |
+
"loss": 0.0027,
|
| 2567 |
+
"step": 2980
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 4.601769911504425,
|
| 2571 |
+
"grad_norm": 0.020071454346179962,
|
| 2572 |
+
"learning_rate": 1.869944153284786e-06,
|
| 2573 |
+
"loss": 0.0026,
|
| 2574 |
+
"step": 2990
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 4.61716044632551,
|
| 2578 |
+
"grad_norm": 0.06694600731134415,
|
| 2579 |
+
"learning_rate": 1.7269913415547456e-06,
|
| 2580 |
+
"loss": 0.0033,
|
| 2581 |
+
"step": 3000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 4.61716044632551,
|
| 2585 |
+
"eval_loss": 0.047850143164396286,
|
| 2586 |
+
"eval_runtime": 176.7617,
|
| 2587 |
+
"eval_samples_per_second": 6.54,
|
| 2588 |
+
"eval_steps_per_second": 6.54,
|
| 2589 |
+
"step": 3000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 4.632550981146595,
|
| 2593 |
+
"grad_norm": 0.16029523313045502,
|
| 2594 |
+
"learning_rate": 1.589626244487069e-06,
|
| 2595 |
+
"loss": 0.0024,
|
| 2596 |
+
"step": 3010
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 4.64794151596768,
|
| 2600 |
+
"grad_norm": 0.3176231384277344,
|
| 2601 |
+
"learning_rate": 1.4578647624158726e-06,
|
| 2602 |
+
"loss": 0.0027,
|
| 2603 |
+
"step": 3020
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 4.663332050788765,
|
| 2607 |
+
"grad_norm": 0.13648022711277008,
|
| 2608 |
+
"learning_rate": 1.3317221470436293e-06,
|
| 2609 |
+
"loss": 0.0041,
|
| 2610 |
+
"step": 3030
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 4.67872258560985,
|
| 2614 |
+
"grad_norm": 0.5381929874420166,
|
| 2615 |
+
"learning_rate": 1.2112129996757315e-06,
|
| 2616 |
+
"loss": 0.0035,
|
| 2617 |
+
"step": 3040
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 4.694113120430935,
|
| 2621 |
+
"grad_norm": 0.010145686566829681,
|
| 2622 |
+
"learning_rate": 1.0963512695303546e-06,
|
| 2623 |
+
"loss": 0.0054,
|
| 2624 |
+
"step": 3050
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 4.694113120430935,
|
| 2628 |
+
"eval_loss": 0.04837736859917641,
|
| 2629 |
+
"eval_runtime": 176.7537,
|
| 2630 |
+
"eval_samples_per_second": 6.54,
|
| 2631 |
+
"eval_steps_per_second": 6.54,
|
| 2632 |
+
"step": 3050
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 4.7095036552520195,
|
| 2636 |
+
"grad_norm": 0.19823475182056427,
|
| 2637 |
+
"learning_rate": 9.871502521237975e-07,
|
| 2638 |
+
"loss": 0.0023,
|
| 2639 |
+
"step": 3060
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 4.724894190073105,
|
| 2643 |
+
"grad_norm": 0.2060529589653015,
|
| 2644 |
+
"learning_rate": 8.83622587731514e-07,
|
| 2645 |
+
"loss": 0.0027,
|
| 2646 |
+
"step": 3070
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 4.74028472489419,
|
| 2650 |
+
"grad_norm": 0.6080601215362549,
|
| 2651 |
+
"learning_rate": 7.857802599249564e-07,
|
| 2652 |
+
"loss": 0.0072,
|
| 2653 |
+
"step": 3080
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 4.755675259715275,
|
| 2657 |
+
"grad_norm": 0.11862636357545853,
|
| 2658 |
+
"learning_rate": 6.936345941844335e-07,
|
| 2659 |
+
"loss": 0.0028,
|
| 2660 |
+
"step": 3090
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 4.77106579453636,
|
| 2664 |
+
"grad_norm": 0.06396199017763138,
|
| 2665 |
+
"learning_rate": 6.071962565881939e-07,
|
| 2666 |
+
"loss": 0.0055,
|
| 2667 |
+
"step": 3100
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 4.77106579453636,
|
| 2671 |
+
"eval_loss": 0.04817047342658043,
|
| 2672 |
+
"eval_runtime": 176.8158,
|
| 2673 |
+
"eval_samples_per_second": 6.538,
|
| 2674 |
+
"eval_steps_per_second": 6.538,
|
| 2675 |
+
"step": 3100
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 4.786456329357446,
|
| 2679 |
+
"grad_norm": 0.14032289385795593,
|
| 2680 |
+
"learning_rate": 5.264752525777961e-07,
|
| 2681 |
+
"loss": 0.0082,
|
| 2682 |
+
"step": 3110
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 4.80184686417853,
|
| 2686 |
+
"grad_norm": 0.17890319228172302,
|
| 2687 |
+
"learning_rate": 4.5148092579991863e-07,
|
| 2688 |
+
"loss": 0.0046,
|
| 2689 |
+
"step": 3120
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 4.817237398999615,
|
| 2693 |
+
"grad_norm": 0.008984181098639965,
|
| 2694 |
+
"learning_rate": 3.822219570248531e-07,
|
| 2695 |
+
"loss": 0.0043,
|
| 2696 |
+
"step": 3130
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 4.8326279338207,
|
| 2700 |
+
"grad_norm": 0.012724678963422775,
|
| 2701 |
+
"learning_rate": 3.187063631416742e-07,
|
| 2702 |
+
"loss": 0.0015,
|
| 2703 |
+
"step": 3140
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 4.8480184686417855,
|
| 2707 |
+
"grad_norm": 0.04591573029756546,
|
| 2708 |
+
"learning_rate": 2.6094149623024365e-07,
|
| 2709 |
+
"loss": 0.0034,
|
| 2710 |
+
"step": 3150
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 4.8480184686417855,
|
| 2714 |
+
"eval_loss": 0.048183247447013855,
|
| 2715 |
+
"eval_runtime": 176.9728,
|
| 2716 |
+
"eval_samples_per_second": 6.532,
|
| 2717 |
+
"eval_steps_per_second": 6.532,
|
| 2718 |
+
"step": 3150
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.86340900346287,
|
| 2722 |
+
"grad_norm": 0.05306975543498993,
|
| 2723 |
+
"learning_rate": 2.0893404271022376e-07,
|
| 2724 |
+
"loss": 0.0032,
|
| 2725 |
+
"step": 3160
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.878799538283955,
|
| 2729 |
+
"grad_norm": 0.19906778633594513,
|
| 2730 |
+
"learning_rate": 1.626900225670691e-07,
|
| 2731 |
+
"loss": 0.0026,
|
| 2732 |
+
"step": 3170
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.89419007310504,
|
| 2736 |
+
"grad_norm": 0.055820539593696594,
|
| 2737 |
+
"learning_rate": 1.2221478865524493e-07,
|
| 2738 |
+
"loss": 0.0018,
|
| 2739 |
+
"step": 3180
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.9095806079261255,
|
| 2743 |
+
"grad_norm": 0.020210551097989082,
|
| 2744 |
+
"learning_rate": 8.751302607857836e-08,
|
| 2745 |
+
"loss": 0.0041,
|
| 2746 |
+
"step": 3190
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.924971142747211,
|
| 2750 |
+
"grad_norm": 0.02825630083680153,
|
| 2751 |
+
"learning_rate": 5.8588751647975506e-08,
|
| 2752 |
+
"loss": 0.0038,
|
| 2753 |
+
"step": 3200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.924971142747211,
|
| 2757 |
+
"eval_loss": 0.04810521379113197,
|
| 2758 |
+
"eval_runtime": 177.0651,
|
| 2759 |
+
"eval_samples_per_second": 6.529,
|
| 2760 |
+
"eval_steps_per_second": 6.529,
|
| 2761 |
+
"step": 3200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 4.940361677568296,
|
| 2765 |
+
"grad_norm": 0.028862258419394493,
|
| 2766 |
+
"learning_rate": 3.544531341646007e-08,
|
| 2767 |
+
"loss": 0.0037,
|
| 2768 |
+
"step": 3210
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 4.95575221238938,
|
| 2772 |
+
"grad_norm": 0.043836887925863266,
|
| 2773 |
+
"learning_rate": 1.808539029161116e-08,
|
| 2774 |
+
"loss": 0.0027,
|
| 2775 |
+
"step": 3220
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 4.9711427472104655,
|
| 2779 |
+
"grad_norm": 0.05687952786684036,
|
| 2780 |
+
"learning_rate": 6.510991725500182e-09,
|
| 2781 |
+
"loss": 0.0058,
|
| 2782 |
+
"step": 3230
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 4.986533282031551,
|
| 2786 |
+
"grad_norm": 0.06359147280454636,
|
| 2787 |
+
"learning_rate": 7.234574820769169e-10,
|
| 2788 |
+
"loss": 0.0032,
|
| 2789 |
+
"step": 3240
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 4.994228549442093,
|
| 2793 |
+
"step": 3245,
|
| 2794 |
+
"total_flos": 8.169046237996646e+17,
|
| 2795 |
+
"train_loss": 0.03518175135534515,
|
| 2796 |
+
"train_runtime": 38986.9842,
|
| 2797 |
+
"train_samples_per_second": 1.333,
|
| 2798 |
+
"train_steps_per_second": 0.083
|
| 2799 |
+
}
|
| 2800 |
+
],
|
| 2801 |
+
"logging_steps": 10,
|
| 2802 |
+
"max_steps": 3245,
|
| 2803 |
+
"num_input_tokens_seen": 0,
|
| 2804 |
+
"num_train_epochs": 5,
|
| 2805 |
+
"save_steps": 50,
|
| 2806 |
+
"stateful_callbacks": {
|
| 2807 |
+
"TrainerControl": {
|
| 2808 |
+
"args": {
|
| 2809 |
+
"should_epoch_stop": false,
|
| 2810 |
+
"should_evaluate": false,
|
| 2811 |
+
"should_log": false,
|
| 2812 |
+
"should_save": true,
|
| 2813 |
+
"should_training_stop": true
|
| 2814 |
+
},
|
| 2815 |
+
"attributes": {}
|
| 2816 |
+
}
|
| 2817 |
+
},
|
| 2818 |
+
"total_flos": 8.169046237996646e+17,
|
| 2819 |
+
"train_batch_size": 1,
|
| 2820 |
+
"trial_name": null,
|
| 2821 |
+
"trial_params": null
|
| 2822 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|