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: llama3
|
|
| 4 |
base_model: aaditya/Llama3-OpenBioLLM-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: Llama3-OpenBioLLM-8B-PsyCourse-fold10
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# Llama3-OpenBioLLM-8B-PsyCourse-fold10
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 4 |
base_model: aaditya/Llama3-OpenBioLLM-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: Llama3-OpenBioLLM-8B-PsyCourse-fold10
|
|
|
|
| 16 |
|
| 17 |
# Llama3-OpenBioLLM-8B-PsyCourse-fold10
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on the course-train-fold10 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0347
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.994708994708994,
|
| 3 |
+
"eval_loss": 0.03466709703207016,
|
| 4 |
+
"eval_runtime": 157.2444,
|
| 5 |
+
"eval_samples_per_second": 7.345,
|
| 6 |
+
"eval_steps_per_second": 7.345,
|
| 7 |
+
"total_flos": 8.15387262412456e+17,
|
| 8 |
+
"train_loss": 0.041617053084775736,
|
| 9 |
+
"train_runtime": 36330.2026,
|
| 10 |
+
"train_samples_per_second": 1.431,
|
| 11 |
+
"train_steps_per_second": 0.089
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.994708994708994,
|
| 3 |
+
"eval_loss": 0.03466709703207016,
|
| 4 |
+
"eval_runtime": 157.2444,
|
| 5 |
+
"eval_samples_per_second": 7.345,
|
| 6 |
+
"eval_steps_per_second": 7.345
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.994708994708994,
|
| 3 |
+
"total_flos": 8.15387262412456e+17,
|
| 4 |
+
"train_loss": 0.041617053084775736,
|
| 5 |
+
"train_runtime": 36330.2026,
|
| 6 |
+
"train_samples_per_second": 1.431,
|
| 7 |
+
"train_steps_per_second": 0.089
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2822 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.03466709703207016,
|
| 3 |
+
"best_model_checkpoint": "saves/psy-course/Llama3-OpenBioLLM-8B/train/fold10/checkpoint-1250",
|
| 4 |
+
"epoch": 4.994708994708994,
|
| 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": 0.015392015392015393,
|
| 13 |
+
"grad_norm": 5.839231491088867,
|
| 14 |
+
"learning_rate": 3.0769230769230774e-06,
|
| 15 |
+
"loss": 1.2829,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.030784030784030785,
|
| 20 |
+
"grad_norm": 5.680546283721924,
|
| 21 |
+
"learning_rate": 6.153846153846155e-06,
|
| 22 |
+
"loss": 1.35,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.046176046176046176,
|
| 27 |
+
"grad_norm": 3.828277349472046,
|
| 28 |
+
"learning_rate": 9.230769230769232e-06,
|
| 29 |
+
"loss": 1.1992,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06156806156806157,
|
| 34 |
+
"grad_norm": 2.330836296081543,
|
| 35 |
+
"learning_rate": 1.230769230769231e-05,
|
| 36 |
+
"loss": 0.8478,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07696007696007696,
|
| 41 |
+
"grad_norm": 1.7859842777252197,
|
| 42 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 43 |
+
"loss": 0.5221,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07696007696007696,
|
| 48 |
+
"eval_loss": 0.3092120289802551,
|
| 49 |
+
"eval_runtime": 192.742,
|
| 50 |
+
"eval_samples_per_second": 5.992,
|
| 51 |
+
"eval_steps_per_second": 5.992,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09235209235209235,
|
| 56 |
+
"grad_norm": 1.266290307044983,
|
| 57 |
+
"learning_rate": 1.8461538461538465e-05,
|
| 58 |
+
"loss": 0.2921,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10774410774410774,
|
| 63 |
+
"grad_norm": 2.233220338821411,
|
| 64 |
+
"learning_rate": 2.1538461538461542e-05,
|
| 65 |
+
"loss": 0.2192,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12313612313612314,
|
| 70 |
+
"grad_norm": 1.301505446434021,
|
| 71 |
+
"learning_rate": 2.461538461538462e-05,
|
| 72 |
+
"loss": 0.1696,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13852813852813853,
|
| 77 |
+
"grad_norm": 1.4332795143127441,
|
| 78 |
+
"learning_rate": 2.7692307692307694e-05,
|
| 79 |
+
"loss": 0.1291,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15392015392015393,
|
| 84 |
+
"grad_norm": 0.8287798762321472,
|
| 85 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 86 |
+
"loss": 0.0971,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.15392015392015393,
|
| 91 |
+
"eval_loss": 0.0860358327627182,
|
| 92 |
+
"eval_runtime": 201.0316,
|
| 93 |
+
"eval_samples_per_second": 5.745,
|
| 94 |
+
"eval_steps_per_second": 5.745,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.1693121693121693,
|
| 99 |
+
"grad_norm": 1.537462830543518,
|
| 100 |
+
"learning_rate": 3.384615384615385e-05,
|
| 101 |
+
"loss": 0.0958,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.1847041847041847,
|
| 106 |
+
"grad_norm": 0.8775112628936768,
|
| 107 |
+
"learning_rate": 3.692307692307693e-05,
|
| 108 |
+
"loss": 0.0727,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2000962000962001,
|
| 113 |
+
"grad_norm": 1.4552613496780396,
|
| 114 |
+
"learning_rate": 4e-05,
|
| 115 |
+
"loss": 0.0744,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.21548821548821548,
|
| 120 |
+
"grad_norm": 2.025639772415161,
|
| 121 |
+
"learning_rate": 4.3076923076923084e-05,
|
| 122 |
+
"loss": 0.0917,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.23088023088023088,
|
| 127 |
+
"grad_norm": 0.8879976868629456,
|
| 128 |
+
"learning_rate": 4.615384615384616e-05,
|
| 129 |
+
"loss": 0.0873,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.23088023088023088,
|
| 134 |
+
"eval_loss": 0.06073848158121109,
|
| 135 |
+
"eval_runtime": 200.6239,
|
| 136 |
+
"eval_samples_per_second": 5.757,
|
| 137 |
+
"eval_steps_per_second": 5.757,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.24627224627224628,
|
| 142 |
+
"grad_norm": 1.0195509195327759,
|
| 143 |
+
"learning_rate": 4.923076923076924e-05,
|
| 144 |
+
"loss": 0.0451,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.26166426166426165,
|
| 149 |
+
"grad_norm": 0.8961577415466309,
|
| 150 |
+
"learning_rate": 5.230769230769231e-05,
|
| 151 |
+
"loss": 0.0674,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.27705627705627706,
|
| 156 |
+
"grad_norm": 0.774815022945404,
|
| 157 |
+
"learning_rate": 5.538461538461539e-05,
|
| 158 |
+
"loss": 0.0593,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.29244829244829246,
|
| 163 |
+
"grad_norm": 1.6998802423477173,
|
| 164 |
+
"learning_rate": 5.846153846153847e-05,
|
| 165 |
+
"loss": 0.0692,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.30784030784030786,
|
| 170 |
+
"grad_norm": 0.5050025582313538,
|
| 171 |
+
"learning_rate": 6.153846153846155e-05,
|
| 172 |
+
"loss": 0.0616,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.30784030784030786,
|
| 177 |
+
"eval_loss": 0.056508466601371765,
|
| 178 |
+
"eval_runtime": 165.9359,
|
| 179 |
+
"eval_samples_per_second": 6.961,
|
| 180 |
+
"eval_steps_per_second": 6.961,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.32323232323232326,
|
| 185 |
+
"grad_norm": 1.1922398805618286,
|
| 186 |
+
"learning_rate": 6.461538461538462e-05,
|
| 187 |
+
"loss": 0.0634,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.3386243386243386,
|
| 192 |
+
"grad_norm": 1.0104138851165771,
|
| 193 |
+
"learning_rate": 6.76923076923077e-05,
|
| 194 |
+
"loss": 0.0744,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.354016354016354,
|
| 199 |
+
"grad_norm": 1.652618408203125,
|
| 200 |
+
"learning_rate": 7.076923076923078e-05,
|
| 201 |
+
"loss": 0.055,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.3694083694083694,
|
| 206 |
+
"grad_norm": 0.5933212041854858,
|
| 207 |
+
"learning_rate": 7.384615384615386e-05,
|
| 208 |
+
"loss": 0.0647,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.3848003848003848,
|
| 213 |
+
"grad_norm": 0.8468647003173828,
|
| 214 |
+
"learning_rate": 7.692307692307693e-05,
|
| 215 |
+
"loss": 0.071,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.3848003848003848,
|
| 220 |
+
"eval_loss": 0.05420336872339249,
|
| 221 |
+
"eval_runtime": 160.844,
|
| 222 |
+
"eval_samples_per_second": 7.181,
|
| 223 |
+
"eval_steps_per_second": 7.181,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.4001924001924002,
|
| 228 |
+
"grad_norm": 0.3505142629146576,
|
| 229 |
+
"learning_rate": 8e-05,
|
| 230 |
+
"loss": 0.0632,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.4155844155844156,
|
| 235 |
+
"grad_norm": 0.5039116144180298,
|
| 236 |
+
"learning_rate": 8.307692307692309e-05,
|
| 237 |
+
"loss": 0.0569,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.43097643097643096,
|
| 242 |
+
"grad_norm": 0.6876810193061829,
|
| 243 |
+
"learning_rate": 8.615384615384617e-05,
|
| 244 |
+
"loss": 0.0413,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.44636844636844636,
|
| 249 |
+
"grad_norm": 0.4580015242099762,
|
| 250 |
+
"learning_rate": 8.923076923076924e-05,
|
| 251 |
+
"loss": 0.0654,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.46176046176046176,
|
| 256 |
+
"grad_norm": 0.676700234413147,
|
| 257 |
+
"learning_rate": 9.230769230769232e-05,
|
| 258 |
+
"loss": 0.0615,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.46176046176046176,
|
| 263 |
+
"eval_loss": 0.049673303961753845,
|
| 264 |
+
"eval_runtime": 160.3278,
|
| 265 |
+
"eval_samples_per_second": 7.204,
|
| 266 |
+
"eval_steps_per_second": 7.204,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.47715247715247716,
|
| 271 |
+
"grad_norm": 0.5680780410766602,
|
| 272 |
+
"learning_rate": 9.53846153846154e-05,
|
| 273 |
+
"loss": 0.0497,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.49254449254449256,
|
| 278 |
+
"grad_norm": 1.1781426668167114,
|
| 279 |
+
"learning_rate": 9.846153846153848e-05,
|
| 280 |
+
"loss": 0.0625,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.5079365079365079,
|
| 285 |
+
"grad_norm": 0.5670598745346069,
|
| 286 |
+
"learning_rate": 9.999927654251793e-05,
|
| 287 |
+
"loss": 0.0691,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.5233285233285233,
|
| 292 |
+
"grad_norm": 0.393940806388855,
|
| 293 |
+
"learning_rate": 9.99934890082745e-05,
|
| 294 |
+
"loss": 0.0504,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.5387205387205387,
|
| 299 |
+
"grad_norm": 0.6476990580558777,
|
| 300 |
+
"learning_rate": 9.99819146097084e-05,
|
| 301 |
+
"loss": 0.0538,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.5387205387205387,
|
| 306 |
+
"eval_loss": 0.046799372881650925,
|
| 307 |
+
"eval_runtime": 160.4795,
|
| 308 |
+
"eval_samples_per_second": 7.197,
|
| 309 |
+
"eval_steps_per_second": 7.197,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5541125541125541,
|
| 314 |
+
"grad_norm": 0.47279223799705505,
|
| 315 |
+
"learning_rate": 9.996455468658355e-05,
|
| 316 |
+
"loss": 0.0478,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5695045695045695,
|
| 321 |
+
"grad_norm": 0.5177505016326904,
|
| 322 |
+
"learning_rate": 9.994141124835203e-05,
|
| 323 |
+
"loss": 0.0453,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5848965848965849,
|
| 328 |
+
"grad_norm": 0.7338818311691284,
|
| 329 |
+
"learning_rate": 9.991248697392142e-05,
|
| 330 |
+
"loss": 0.0367,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6002886002886003,
|
| 335 |
+
"grad_norm": 1.0812134742736816,
|
| 336 |
+
"learning_rate": 9.987778521134476e-05,
|
| 337 |
+
"loss": 0.0455,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6156806156806157,
|
| 342 |
+
"grad_norm": 0.37609776854515076,
|
| 343 |
+
"learning_rate": 9.983730997743294e-05,
|
| 344 |
+
"loss": 0.0532,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6156806156806157,
|
| 349 |
+
"eval_loss": 0.04624510183930397,
|
| 350 |
+
"eval_runtime": 160.4749,
|
| 351 |
+
"eval_samples_per_second": 7.197,
|
| 352 |
+
"eval_steps_per_second": 7.197,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6310726310726311,
|
| 357 |
+
"grad_norm": 0.7044768333435059,
|
| 358 |
+
"learning_rate": 9.979106595728978e-05,
|
| 359 |
+
"loss": 0.0568,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6464646464646465,
|
| 364 |
+
"grad_norm": 0.41372236609458923,
|
| 365 |
+
"learning_rate": 9.973905850376977e-05,
|
| 366 |
+
"loss": 0.0396,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6618566618566618,
|
| 371 |
+
"grad_norm": 0.4322606325149536,
|
| 372 |
+
"learning_rate": 9.968129363685833e-05,
|
| 373 |
+
"loss": 0.0419,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6772486772486772,
|
| 378 |
+
"grad_norm": 1.1119065284729004,
|
| 379 |
+
"learning_rate": 9.961777804297514e-05,
|
| 380 |
+
"loss": 0.0534,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6926406926406926,
|
| 385 |
+
"grad_norm": 0.2994139790534973,
|
| 386 |
+
"learning_rate": 9.954851907420009e-05,
|
| 387 |
+
"loss": 0.0501,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6926406926406926,
|
| 392 |
+
"eval_loss": 0.048226650804281235,
|
| 393 |
+
"eval_runtime": 160.5362,
|
| 394 |
+
"eval_samples_per_second": 7.195,
|
| 395 |
+
"eval_steps_per_second": 7.195,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.708032708032708,
|
| 400 |
+
"grad_norm": 0.6291306018829346,
|
| 401 |
+
"learning_rate": 9.947352474742222e-05,
|
| 402 |
+
"loss": 0.0511,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7234247234247234,
|
| 407 |
+
"grad_norm": 0.5497981905937195,
|
| 408 |
+
"learning_rate": 9.93928037434118e-05,
|
| 409 |
+
"loss": 0.0533,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7388167388167388,
|
| 414 |
+
"grad_norm": 0.6592866778373718,
|
| 415 |
+
"learning_rate": 9.930636540581556e-05,
|
| 416 |
+
"loss": 0.0464,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.7542087542087542,
|
| 421 |
+
"grad_norm": 0.438894122838974,
|
| 422 |
+
"learning_rate": 9.921421974007506e-05,
|
| 423 |
+
"loss": 0.0469,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.7696007696007696,
|
| 428 |
+
"grad_norm": 0.7949342727661133,
|
| 429 |
+
"learning_rate": 9.911637741226849e-05,
|
| 430 |
+
"loss": 0.0575,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.7696007696007696,
|
| 435 |
+
"eval_loss": 0.042172204703092575,
|
| 436 |
+
"eval_runtime": 160.3062,
|
| 437 |
+
"eval_samples_per_second": 7.205,
|
| 438 |
+
"eval_steps_per_second": 7.205,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.784992784992785,
|
| 443 |
+
"grad_norm": 0.3464134931564331,
|
| 444 |
+
"learning_rate": 9.90128497478762e-05,
|
| 445 |
+
"loss": 0.0484,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.8003848003848004,
|
| 450 |
+
"grad_norm": 0.37780413031578064,
|
| 451 |
+
"learning_rate": 9.890364873046965e-05,
|
| 452 |
+
"loss": 0.0445,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.8157768157768158,
|
| 457 |
+
"grad_norm": 0.3058973550796509,
|
| 458 |
+
"learning_rate": 9.878878700032427e-05,
|
| 459 |
+
"loss": 0.0338,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.8311688311688312,
|
| 464 |
+
"grad_norm": 0.5813219547271729,
|
| 465 |
+
"learning_rate": 9.866827785295638e-05,
|
| 466 |
+
"loss": 0.0481,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.8465608465608465,
|
| 471 |
+
"grad_norm": 0.25342145562171936,
|
| 472 |
+
"learning_rate": 9.854213523758413e-05,
|
| 473 |
+
"loss": 0.0418,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8465608465608465,
|
| 478 |
+
"eval_loss": 0.043983206152915955,
|
| 479 |
+
"eval_runtime": 160.2238,
|
| 480 |
+
"eval_samples_per_second": 7.209,
|
| 481 |
+
"eval_steps_per_second": 7.209,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.8619528619528619,
|
| 486 |
+
"grad_norm": 0.4131356179714203,
|
| 487 |
+
"learning_rate": 9.841037375551294e-05,
|
| 488 |
+
"loss": 0.0508,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.8773448773448773,
|
| 493 |
+
"grad_norm": 0.8691533803939819,
|
| 494 |
+
"learning_rate": 9.827300865844527e-05,
|
| 495 |
+
"loss": 0.0467,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.8927368927368927,
|
| 500 |
+
"grad_norm": 0.4405064284801483,
|
| 501 |
+
"learning_rate": 9.813005584671522e-05,
|
| 502 |
+
"loss": 0.0365,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.9081289081289081,
|
| 507 |
+
"grad_norm": 0.2739037573337555,
|
| 508 |
+
"learning_rate": 9.79815318674481e-05,
|
| 509 |
+
"loss": 0.0442,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.9235209235209235,
|
| 514 |
+
"grad_norm": 0.328683465719223,
|
| 515 |
+
"learning_rate": 9.782745391264498e-05,
|
| 516 |
+
"loss": 0.048,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.9235209235209235,
|
| 521 |
+
"eval_loss": 0.03977407515048981,
|
| 522 |
+
"eval_runtime": 160.2864,
|
| 523 |
+
"eval_samples_per_second": 7.206,
|
| 524 |
+
"eval_steps_per_second": 7.206,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.9389129389129389,
|
| 529 |
+
"grad_norm": 0.5097044706344604,
|
| 530 |
+
"learning_rate": 9.76678398171927e-05,
|
| 531 |
+
"loss": 0.0469,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.9543049543049543,
|
| 536 |
+
"grad_norm": 0.2837560772895813,
|
| 537 |
+
"learning_rate": 9.750270805679945e-05,
|
| 538 |
+
"loss": 0.0309,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.9696969696969697,
|
| 543 |
+
"grad_norm": 0.3343970775604248,
|
| 544 |
+
"learning_rate": 9.733207774585618e-05,
|
| 545 |
+
"loss": 0.062,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.9850889850889851,
|
| 550 |
+
"grad_norm": 0.39156869053840637,
|
| 551 |
+
"learning_rate": 9.715596863522398e-05,
|
| 552 |
+
"loss": 0.0386,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.0004810004810005,
|
| 557 |
+
"grad_norm": 0.332334041595459,
|
| 558 |
+
"learning_rate": 9.697440110994801e-05,
|
| 559 |
+
"loss": 0.0559,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.0004810004810005,
|
| 564 |
+
"eval_loss": 0.039704564958810806,
|
| 565 |
+
"eval_runtime": 160.3208,
|
| 566 |
+
"eval_samples_per_second": 7.204,
|
| 567 |
+
"eval_steps_per_second": 7.204,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.0158730158730158,
|
| 572 |
+
"grad_norm": 0.25134462118148804,
|
| 573 |
+
"learning_rate": 9.678739618689775e-05,
|
| 574 |
+
"loss": 0.0366,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.0312650312650313,
|
| 579 |
+
"grad_norm": 0.24178971350193024,
|
| 580 |
+
"learning_rate": 9.659497551233431e-05,
|
| 581 |
+
"loss": 0.0338,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.0466570466570466,
|
| 586 |
+
"grad_norm": 0.19782131910324097,
|
| 587 |
+
"learning_rate": 9.639716135940485e-05,
|
| 588 |
+
"loss": 0.0328,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.0620490620490621,
|
| 593 |
+
"grad_norm": 0.18410953879356384,
|
| 594 |
+
"learning_rate": 9.619397662556435e-05,
|
| 595 |
+
"loss": 0.0331,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.0774410774410774,
|
| 600 |
+
"grad_norm": 0.4528217613697052,
|
| 601 |
+
"learning_rate": 9.598544482992517e-05,
|
| 602 |
+
"loss": 0.0358,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.0774410774410774,
|
| 607 |
+
"eval_loss": 0.04308833181858063,
|
| 608 |
+
"eval_runtime": 160.413,
|
| 609 |
+
"eval_samples_per_second": 7.2,
|
| 610 |
+
"eval_steps_per_second": 7.2,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.092833092833093,
|
| 615 |
+
"grad_norm": 0.6040289998054504,
|
| 616 |
+
"learning_rate": 9.57715901105348e-05,
|
| 617 |
+
"loss": 0.037,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.1082251082251082,
|
| 622 |
+
"grad_norm": 0.5413057804107666,
|
| 623 |
+
"learning_rate": 9.555243722158158e-05,
|
| 624 |
+
"loss": 0.035,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.1236171236171235,
|
| 629 |
+
"grad_norm": 0.27406299114227295,
|
| 630 |
+
"learning_rate": 9.532801153052958e-05,
|
| 631 |
+
"loss": 0.0408,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.139009139009139,
|
| 636 |
+
"grad_norm": 0.371649831533432,
|
| 637 |
+
"learning_rate": 9.509833901518209e-05,
|
| 638 |
+
"loss": 0.0377,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.1544011544011543,
|
| 643 |
+
"grad_norm": 0.4681012034416199,
|
| 644 |
+
"learning_rate": 9.486344626067475e-05,
|
| 645 |
+
"loss": 0.0277,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.1544011544011543,
|
| 650 |
+
"eval_loss": 0.03915223106741905,
|
| 651 |
+
"eval_runtime": 160.4858,
|
| 652 |
+
"eval_samples_per_second": 7.197,
|
| 653 |
+
"eval_steps_per_second": 7.197,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1697931697931698,
|
| 658 |
+
"grad_norm": 0.13481155037879944,
|
| 659 |
+
"learning_rate": 9.462336045639815e-05,
|
| 660 |
+
"loss": 0.0355,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1851851851851851,
|
| 665 |
+
"grad_norm": 0.10173361003398895,
|
| 666 |
+
"learning_rate": 9.437810939285068e-05,
|
| 667 |
+
"loss": 0.0228,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.2005772005772006,
|
| 672 |
+
"grad_norm": 0.24143601953983307,
|
| 673 |
+
"learning_rate": 9.412772145842165e-05,
|
| 674 |
+
"loss": 0.0266,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.215969215969216,
|
| 679 |
+
"grad_norm": 0.43506941199302673,
|
| 680 |
+
"learning_rate": 9.387222563610535e-05,
|
| 681 |
+
"loss": 0.0391,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2313612313612314,
|
| 686 |
+
"grad_norm": 0.23058776557445526,
|
| 687 |
+
"learning_rate": 9.361165150014606e-05,
|
| 688 |
+
"loss": 0.029,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2313612313612314,
|
| 693 |
+
"eval_loss": 0.03759562969207764,
|
| 694 |
+
"eval_runtime": 160.4221,
|
| 695 |
+
"eval_samples_per_second": 7.2,
|
| 696 |
+
"eval_steps_per_second": 7.2,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.2467532467532467,
|
| 701 |
+
"grad_norm": 0.5037282109260559,
|
| 702 |
+
"learning_rate": 9.334602921261492e-05,
|
| 703 |
+
"loss": 0.0461,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.2621452621452622,
|
| 708 |
+
"grad_norm": 0.2980537414550781,
|
| 709 |
+
"learning_rate": 9.307538951991852e-05,
|
| 710 |
+
"loss": 0.0364,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.2775372775372775,
|
| 715 |
+
"grad_norm": 0.203804150223732,
|
| 716 |
+
"learning_rate": 9.279976374923988e-05,
|
| 717 |
+
"loss": 0.0387,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.2929292929292928,
|
| 722 |
+
"grad_norm": 0.3414406478404999,
|
| 723 |
+
"learning_rate": 9.251918380491238e-05,
|
| 724 |
+
"loss": 0.0282,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.3083213083213083,
|
| 729 |
+
"grad_norm": 0.8123178482055664,
|
| 730 |
+
"learning_rate": 9.223368216472668e-05,
|
| 731 |
+
"loss": 0.0283,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.3083213083213083,
|
| 736 |
+
"eval_loss": 0.03833651915192604,
|
| 737 |
+
"eval_runtime": 160.4154,
|
| 738 |
+
"eval_samples_per_second": 7.2,
|
| 739 |
+
"eval_steps_per_second": 7.2,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.3237133237133238,
|
| 744 |
+
"grad_norm": 0.40936821699142456,
|
| 745 |
+
"learning_rate": 9.194329187617127e-05,
|
| 746 |
+
"loss": 0.0343,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.3391053391053391,
|
| 751 |
+
"grad_norm": 0.3399330973625183,
|
| 752 |
+
"learning_rate": 9.164804655260735e-05,
|
| 753 |
+
"loss": 0.036,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.3544973544973544,
|
| 758 |
+
"grad_norm": 0.3808479607105255,
|
| 759 |
+
"learning_rate": 9.134798036937778e-05,
|
| 760 |
+
"loss": 0.0428,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.36988936988937,
|
| 765 |
+
"grad_norm": 0.18996691703796387,
|
| 766 |
+
"learning_rate": 9.104312805985134e-05,
|
| 767 |
+
"loss": 0.0337,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.3852813852813852,
|
| 772 |
+
"grad_norm": 0.30460020899772644,
|
| 773 |
+
"learning_rate": 9.073352491140221e-05,
|
| 774 |
+
"loss": 0.035,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.3852813852813852,
|
| 779 |
+
"eval_loss": 0.03713306412100792,
|
| 780 |
+
"eval_runtime": 160.2728,
|
| 781 |
+
"eval_samples_per_second": 7.206,
|
| 782 |
+
"eval_steps_per_second": 7.206,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.4006734006734007,
|
| 787 |
+
"grad_norm": 0.5870276689529419,
|
| 788 |
+
"learning_rate": 9.041920676132543e-05,
|
| 789 |
+
"loss": 0.0424,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.416065416065416,
|
| 794 |
+
"grad_norm": 0.5088344216346741,
|
| 795 |
+
"learning_rate": 9.010020999268854e-05,
|
| 796 |
+
"loss": 0.0342,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.4314574314574315,
|
| 801 |
+
"grad_norm": 0.22709380090236664,
|
| 802 |
+
"learning_rate": 8.977657153012027e-05,
|
| 803 |
+
"loss": 0.0363,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.4468494468494468,
|
| 808 |
+
"grad_norm": 0.32548844814300537,
|
| 809 |
+
"learning_rate": 8.944832883553633e-05,
|
| 810 |
+
"loss": 0.0401,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.4622414622414621,
|
| 815 |
+
"grad_norm": 0.30676841735839844,
|
| 816 |
+
"learning_rate": 8.91155199038032e-05,
|
| 817 |
+
"loss": 0.0367,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.4622414622414621,
|
| 822 |
+
"eval_loss": 0.03731577843427658,
|
| 823 |
+
"eval_runtime": 160.4408,
|
| 824 |
+
"eval_samples_per_second": 7.199,
|
| 825 |
+
"eval_steps_per_second": 7.199,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.4776334776334776,
|
| 830 |
+
"grad_norm": 0.3863791227340698,
|
| 831 |
+
"learning_rate": 8.877818325834006e-05,
|
| 832 |
+
"loss": 0.0343,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.4930254930254931,
|
| 837 |
+
"grad_norm": 0.6713721752166748,
|
| 838 |
+
"learning_rate": 8.843635794665961e-05,
|
| 839 |
+
"loss": 0.0392,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.5084175084175084,
|
| 844 |
+
"grad_norm": 0.2896818518638611,
|
| 845 |
+
"learning_rate": 8.809008353584829e-05,
|
| 846 |
+
"loss": 0.0364,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.5238095238095237,
|
| 851 |
+
"grad_norm": 0.2636934518814087,
|
| 852 |
+
"learning_rate": 8.773940010798627e-05,
|
| 853 |
+
"loss": 0.0279,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.5392015392015392,
|
| 858 |
+
"grad_norm": 0.48908543586730957,
|
| 859 |
+
"learning_rate": 8.738434825550785e-05,
|
| 860 |
+
"loss": 0.0272,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.5392015392015392,
|
| 865 |
+
"eval_loss": 0.042762041091918945,
|
| 866 |
+
"eval_runtime": 160.4777,
|
| 867 |
+
"eval_samples_per_second": 7.197,
|
| 868 |
+
"eval_steps_per_second": 7.197,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.5545935545935547,
|
| 873 |
+
"grad_norm": 0.3237270712852478,
|
| 874 |
+
"learning_rate": 8.702496907650274e-05,
|
| 875 |
+
"loss": 0.0337,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.56998556998557,
|
| 880 |
+
"grad_norm": 0.25954726338386536,
|
| 881 |
+
"learning_rate": 8.666130416995897e-05,
|
| 882 |
+
"loss": 0.026,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.5853775853775853,
|
| 887 |
+
"grad_norm": 0.523502767086029,
|
| 888 |
+
"learning_rate": 8.629339563094758e-05,
|
| 889 |
+
"loss": 0.0229,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.6007696007696008,
|
| 894 |
+
"grad_norm": 0.6461522579193115,
|
| 895 |
+
"learning_rate": 8.592128604575014e-05,
|
| 896 |
+
"loss": 0.0384,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.6161616161616161,
|
| 901 |
+
"grad_norm": 0.2046208530664444,
|
| 902 |
+
"learning_rate": 8.554501848692921e-05,
|
| 903 |
+
"loss": 0.0435,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.6161616161616161,
|
| 908 |
+
"eval_loss": 0.036668434739112854,
|
| 909 |
+
"eval_runtime": 160.4211,
|
| 910 |
+
"eval_samples_per_second": 7.2,
|
| 911 |
+
"eval_steps_per_second": 7.2,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.6315536315536314,
|
| 916 |
+
"grad_norm": 0.311105877161026,
|
| 917 |
+
"learning_rate": 8.51646365083426e-05,
|
| 918 |
+
"loss": 0.0393,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.646945646945647,
|
| 923 |
+
"grad_norm": 0.42447835206985474,
|
| 924 |
+
"learning_rate": 8.478018414010191e-05,
|
| 925 |
+
"loss": 0.0451,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.6623376623376624,
|
| 930 |
+
"grad_norm": 0.3853769600391388,
|
| 931 |
+
"learning_rate": 8.439170588347598e-05,
|
| 932 |
+
"loss": 0.0365,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.6777296777296777,
|
| 937 |
+
"grad_norm": 0.18537352979183197,
|
| 938 |
+
"learning_rate": 8.399924670573969e-05,
|
| 939 |
+
"loss": 0.0249,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.693121693121693,
|
| 944 |
+
"grad_norm": 0.52433180809021,
|
| 945 |
+
"learning_rate": 8.360285203496894e-05,
|
| 946 |
+
"loss": 0.0379,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.693121693121693,
|
| 951 |
+
"eval_loss": 0.036822497844696045,
|
| 952 |
+
"eval_runtime": 160.5884,
|
| 953 |
+
"eval_samples_per_second": 7.192,
|
| 954 |
+
"eval_steps_per_second": 7.192,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.7085137085137085,
|
| 959 |
+
"grad_norm": 0.4827461540699005,
|
| 960 |
+
"learning_rate": 8.320256775478228e-05,
|
| 961 |
+
"loss": 0.0403,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.723905723905724,
|
| 966 |
+
"grad_norm": 0.3847942352294922,
|
| 967 |
+
"learning_rate": 8.279844019902968e-05,
|
| 968 |
+
"loss": 0.0265,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7392977392977393,
|
| 973 |
+
"grad_norm": 0.5013036131858826,
|
| 974 |
+
"learning_rate": 8.239051614642934e-05,
|
| 975 |
+
"loss": 0.0227,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7546897546897546,
|
| 980 |
+
"grad_norm": 0.2711322605609894,
|
| 981 |
+
"learning_rate": 8.197884281515292e-05,
|
| 982 |
+
"loss": 0.0299,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7700817700817701,
|
| 987 |
+
"grad_norm": 0.3275453448295593,
|
| 988 |
+
"learning_rate": 8.156346785735997e-05,
|
| 989 |
+
"loss": 0.0296,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.7700817700817701,
|
| 994 |
+
"eval_loss": 0.03776984289288521,
|
| 995 |
+
"eval_runtime": 160.4557,
|
| 996 |
+
"eval_samples_per_second": 7.198,
|
| 997 |
+
"eval_steps_per_second": 7.198,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.7854737854737854,
|
| 1002 |
+
"grad_norm": 0.40839052200317383,
|
| 1003 |
+
"learning_rate": 8.114443935368198e-05,
|
| 1004 |
+
"loss": 0.0346,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.8008658008658007,
|
| 1009 |
+
"grad_norm": 0.22129075229167938,
|
| 1010 |
+
"learning_rate": 8.072180580765709e-05,
|
| 1011 |
+
"loss": 0.029,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.8162578162578162,
|
| 1016 |
+
"grad_norm": 0.2696245014667511,
|
| 1017 |
+
"learning_rate": 8.02956161401155e-05,
|
| 1018 |
+
"loss": 0.0317,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.8316498316498318,
|
| 1023 |
+
"grad_norm": 0.3445149064064026,
|
| 1024 |
+
"learning_rate": 7.98659196835169e-05,
|
| 1025 |
+
"loss": 0.0397,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.847041847041847,
|
| 1030 |
+
"grad_norm": 0.45406243205070496,
|
| 1031 |
+
"learning_rate": 7.943276617624014e-05,
|
| 1032 |
+
"loss": 0.0423,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.847041847041847,
|
| 1037 |
+
"eval_loss": 0.037733353674411774,
|
| 1038 |
+
"eval_runtime": 160.3445,
|
| 1039 |
+
"eval_samples_per_second": 7.203,
|
| 1040 |
+
"eval_steps_per_second": 7.203,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.8624338624338623,
|
| 1045 |
+
"grad_norm": 0.37593597173690796,
|
| 1046 |
+
"learning_rate": 7.899620575682578e-05,
|
| 1047 |
+
"loss": 0.026,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.8778258778258778,
|
| 1052 |
+
"grad_norm": 0.1280842423439026,
|
| 1053 |
+
"learning_rate": 7.85562889581725e-05,
|
| 1054 |
+
"loss": 0.0318,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.8932178932178934,
|
| 1059 |
+
"grad_norm": 0.2298801690340042,
|
| 1060 |
+
"learning_rate": 7.811306670168788e-05,
|
| 1061 |
+
"loss": 0.0265,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.9086099086099086,
|
| 1066 |
+
"grad_norm": 0.392292857170105,
|
| 1067 |
+
"learning_rate": 7.766659029139393e-05,
|
| 1068 |
+
"loss": 0.0399,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.924001924001924,
|
| 1073 |
+
"grad_norm": 0.7621856331825256,
|
| 1074 |
+
"learning_rate": 7.72169114079887e-05,
|
| 1075 |
+
"loss": 0.0389,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.924001924001924,
|
| 1080 |
+
"eval_loss": 0.03466709703207016,
|
| 1081 |
+
"eval_runtime": 160.3061,
|
| 1082 |
+
"eval_samples_per_second": 7.205,
|
| 1083 |
+
"eval_steps_per_second": 7.205,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.9393939393939394,
|
| 1088 |
+
"grad_norm": 0.1976393312215805,
|
| 1089 |
+
"learning_rate": 7.676408210286407e-05,
|
| 1090 |
+
"loss": 0.025,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.9547859547859547,
|
| 1095 |
+
"grad_norm": 0.20227721333503723,
|
| 1096 |
+
"learning_rate": 7.630815479208066e-05,
|
| 1097 |
+
"loss": 0.0315,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.97017797017797,
|
| 1102 |
+
"grad_norm": 0.22260995209217072,
|
| 1103 |
+
"learning_rate": 7.584918225030053e-05,
|
| 1104 |
+
"loss": 0.029,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.9855699855699855,
|
| 1109 |
+
"grad_norm": 0.17172077298164368,
|
| 1110 |
+
"learning_rate": 7.538721760467845e-05,
|
| 1111 |
+
"loss": 0.0401,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.000962000962001,
|
| 1116 |
+
"grad_norm": 0.2766900658607483,
|
| 1117 |
+
"learning_rate": 7.49223143287122e-05,
|
| 1118 |
+
"loss": 0.0349,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.000962000962001,
|
| 1123 |
+
"eval_loss": 0.03779321163892746,
|
| 1124 |
+
"eval_runtime": 160.4154,
|
| 1125 |
+
"eval_samples_per_second": 7.2,
|
| 1126 |
+
"eval_steps_per_second": 7.2,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 2.0163540163540166,
|
| 1131 |
+
"grad_norm": 0.2699854373931885,
|
| 1132 |
+
"learning_rate": 7.445452623605307e-05,
|
| 1133 |
+
"loss": 0.0297,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.0317460317460316,
|
| 1138 |
+
"grad_norm": 0.1711016446352005,
|
| 1139 |
+
"learning_rate": 7.398390747427662e-05,
|
| 1140 |
+
"loss": 0.022,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.047138047138047,
|
| 1145 |
+
"grad_norm": 0.24682311713695526,
|
| 1146 |
+
"learning_rate": 7.351051251861501e-05,
|
| 1147 |
+
"loss": 0.0201,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.0625300625300627,
|
| 1152 |
+
"grad_norm": 0.14136731624603271,
|
| 1153 |
+
"learning_rate": 7.303439616565146e-05,
|
| 1154 |
+
"loss": 0.0171,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.0779220779220777,
|
| 1159 |
+
"grad_norm": 0.3170979917049408,
|
| 1160 |
+
"learning_rate": 7.255561352697732e-05,
|
| 1161 |
+
"loss": 0.0191,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.0779220779220777,
|
| 1166 |
+
"eval_loss": 0.0376242995262146,
|
| 1167 |
+
"eval_runtime": 160.4017,
|
| 1168 |
+
"eval_samples_per_second": 7.201,
|
| 1169 |
+
"eval_steps_per_second": 7.201,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.0933140933140932,
|
| 1174 |
+
"grad_norm": 0.3596189618110657,
|
| 1175 |
+
"learning_rate": 7.207422002281281e-05,
|
| 1176 |
+
"loss": 0.0161,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.1087061087061088,
|
| 1181 |
+
"grad_norm": 0.2732468843460083,
|
| 1182 |
+
"learning_rate": 7.159027137559197e-05,
|
| 1183 |
+
"loss": 0.019,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.1240981240981243,
|
| 1188 |
+
"grad_norm": 0.27598610520362854,
|
| 1189 |
+
"learning_rate": 7.110382360351267e-05,
|
| 1190 |
+
"loss": 0.0213,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.1394901394901393,
|
| 1195 |
+
"grad_norm": 0.24308344721794128,
|
| 1196 |
+
"learning_rate": 7.061493301405244e-05,
|
| 1197 |
+
"loss": 0.0151,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.154882154882155,
|
| 1202 |
+
"grad_norm": 0.40665531158447266,
|
| 1203 |
+
"learning_rate": 7.012365619745064e-05,
|
| 1204 |
+
"loss": 0.0252,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.154882154882155,
|
| 1209 |
+
"eval_loss": 0.037112053483724594,
|
| 1210 |
+
"eval_runtime": 160.559,
|
| 1211 |
+
"eval_samples_per_second": 7.194,
|
| 1212 |
+
"eval_steps_per_second": 7.194,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.1702741702741704,
|
| 1217 |
+
"grad_norm": 0.23677869141101837,
|
| 1218 |
+
"learning_rate": 6.963005002015808e-05,
|
| 1219 |
+
"loss": 0.0197,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.185666185666186,
|
| 1224 |
+
"grad_norm": 0.07495041936635971,
|
| 1225 |
+
"learning_rate": 6.91341716182545e-05,
|
| 1226 |
+
"loss": 0.0147,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.201058201058201,
|
| 1231 |
+
"grad_norm": 0.27357932925224304,
|
| 1232 |
+
"learning_rate": 6.863607839083507e-05,
|
| 1233 |
+
"loss": 0.03,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.2164502164502164,
|
| 1238 |
+
"grad_norm": 0.19724859297275543,
|
| 1239 |
+
"learning_rate": 6.813582799336624e-05,
|
| 1240 |
+
"loss": 0.0163,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.231842231842232,
|
| 1245 |
+
"grad_norm": 0.21828219294548035,
|
| 1246 |
+
"learning_rate": 6.763347833101192e-05,
|
| 1247 |
+
"loss": 0.016,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.231842231842232,
|
| 1252 |
+
"eval_loss": 0.03809448331594467,
|
| 1253 |
+
"eval_runtime": 160.626,
|
| 1254 |
+
"eval_samples_per_second": 7.191,
|
| 1255 |
+
"eval_steps_per_second": 7.191,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.247234247234247,
|
| 1260 |
+
"grad_norm": 0.3522093594074249,
|
| 1261 |
+
"learning_rate": 6.712908755193094e-05,
|
| 1262 |
+
"loss": 0.0191,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.2626262626262625,
|
| 1267 |
+
"grad_norm": 0.3476664125919342,
|
| 1268 |
+
"learning_rate": 6.662271404054621e-05,
|
| 1269 |
+
"loss": 0.0229,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.278018278018278,
|
| 1274 |
+
"grad_norm": 0.5309289693832397,
|
| 1275 |
+
"learning_rate": 6.611441641078657e-05,
|
| 1276 |
+
"loss": 0.0252,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.2934102934102936,
|
| 1281 |
+
"grad_norm": 0.33545804023742676,
|
| 1282 |
+
"learning_rate": 6.560425349930208e-05,
|
| 1283 |
+
"loss": 0.0221,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.3088023088023086,
|
| 1288 |
+
"grad_norm": 0.22372335195541382,
|
| 1289 |
+
"learning_rate": 6.509228435865357e-05,
|
| 1290 |
+
"loss": 0.0211,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.3088023088023086,
|
| 1295 |
+
"eval_loss": 0.036216478794813156,
|
| 1296 |
+
"eval_runtime": 160.4231,
|
| 1297 |
+
"eval_samples_per_second": 7.2,
|
| 1298 |
+
"eval_steps_per_second": 7.2,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.324194324194324,
|
| 1303 |
+
"grad_norm": 0.20684416592121124,
|
| 1304 |
+
"learning_rate": 6.45785682504772e-05,
|
| 1305 |
+
"loss": 0.0227,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.3395863395863397,
|
| 1310 |
+
"grad_norm": 0.2306625097990036,
|
| 1311 |
+
"learning_rate": 6.406316463862467e-05,
|
| 1312 |
+
"loss": 0.0191,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.354978354978355,
|
| 1317 |
+
"grad_norm": 0.16803477704524994,
|
| 1318 |
+
"learning_rate": 6.35461331822803e-05,
|
| 1319 |
+
"loss": 0.0266,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.3703703703703702,
|
| 1324 |
+
"grad_norm": 0.24731677770614624,
|
| 1325 |
+
"learning_rate": 6.302753372905515e-05,
|
| 1326 |
+
"loss": 0.0307,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.3857623857623858,
|
| 1331 |
+
"grad_norm": 0.37987345457077026,
|
| 1332 |
+
"learning_rate": 6.250742630805971e-05,
|
| 1333 |
+
"loss": 0.0223,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.3857623857623858,
|
| 1338 |
+
"eval_loss": 0.03545283153653145,
|
| 1339 |
+
"eval_runtime": 160.3714,
|
| 1340 |
+
"eval_samples_per_second": 7.202,
|
| 1341 |
+
"eval_steps_per_second": 7.202,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.4011544011544013,
|
| 1346 |
+
"grad_norm": 0.1934383660554886,
|
| 1347 |
+
"learning_rate": 6.198587112295526e-05,
|
| 1348 |
+
"loss": 0.0223,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.4165464165464163,
|
| 1353 |
+
"grad_norm": 0.09964929521083832,
|
| 1354 |
+
"learning_rate": 6.14629285449852e-05,
|
| 1355 |
+
"loss": 0.0182,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.431938431938432,
|
| 1360 |
+
"grad_norm": 0.19195552170276642,
|
| 1361 |
+
"learning_rate": 6.093865910598688e-05,
|
| 1362 |
+
"loss": 0.0145,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.4473304473304474,
|
| 1367 |
+
"grad_norm": 0.0327489972114563,
|
| 1368 |
+
"learning_rate": 6.0413123491385025e-05,
|
| 1369 |
+
"loss": 0.0205,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.462722462722463,
|
| 1374 |
+
"grad_norm": 0.3766339421272278,
|
| 1375 |
+
"learning_rate": 5.988638253316713e-05,
|
| 1376 |
+
"loss": 0.0227,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.462722462722463,
|
| 1381 |
+
"eval_loss": 0.03853141516447067,
|
| 1382 |
+
"eval_runtime": 160.3204,
|
| 1383 |
+
"eval_samples_per_second": 7.204,
|
| 1384 |
+
"eval_steps_per_second": 7.204,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.478114478114478,
|
| 1389 |
+
"grad_norm": 0.2539356052875519,
|
| 1390 |
+
"learning_rate": 5.935849720284206e-05,
|
| 1391 |
+
"loss": 0.0182,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.4935064935064934,
|
| 1396 |
+
"grad_norm": 0.31089529395103455,
|
| 1397 |
+
"learning_rate": 5.8829528604382436e-05,
|
| 1398 |
+
"loss": 0.0201,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.508898508898509,
|
| 1403 |
+
"grad_norm": 0.5152587294578552,
|
| 1404 |
+
"learning_rate": 5.829953796715176e-05,
|
| 1405 |
+
"loss": 0.0292,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.5242905242905245,
|
| 1410 |
+
"grad_norm": 0.28368091583251953,
|
| 1411 |
+
"learning_rate": 5.7768586638816924e-05,
|
| 1412 |
+
"loss": 0.0242,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.5396825396825395,
|
| 1417 |
+
"grad_norm": 0.3478910028934479,
|
| 1418 |
+
"learning_rate": 5.723673607824705e-05,
|
| 1419 |
+
"loss": 0.0268,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.5396825396825395,
|
| 1424 |
+
"eval_loss": 0.03544799983501434,
|
| 1425 |
+
"eval_runtime": 160.3923,
|
| 1426 |
+
"eval_samples_per_second": 7.201,
|
| 1427 |
+
"eval_steps_per_second": 7.201,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.555074555074555,
|
| 1432 |
+
"grad_norm": 0.1506284922361374,
|
| 1433 |
+
"learning_rate": 5.670404784839953e-05,
|
| 1434 |
+
"loss": 0.0312,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.5704665704665706,
|
| 1439 |
+
"grad_norm": 0.18113912642002106,
|
| 1440 |
+
"learning_rate": 5.6170583609193984e-05,
|
| 1441 |
+
"loss": 0.0241,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 2.5858585858585856,
|
| 1446 |
+
"grad_norm": 0.3110048770904541,
|
| 1447 |
+
"learning_rate": 5.56364051103749e-05,
|
| 1448 |
+
"loss": 0.0247,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.601250601250601,
|
| 1453 |
+
"grad_norm": 0.24057482182979584,
|
| 1454 |
+
"learning_rate": 5.5101574184364056e-05,
|
| 1455 |
+
"loss": 0.0158,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.6166426166426167,
|
| 1460 |
+
"grad_norm": 0.46047157049179077,
|
| 1461 |
+
"learning_rate": 5.4566152739103116e-05,
|
| 1462 |
+
"loss": 0.0267,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 2.6166426166426167,
|
| 1467 |
+
"eval_loss": 0.03490716964006424,
|
| 1468 |
+
"eval_runtime": 160.4306,
|
| 1469 |
+
"eval_samples_per_second": 7.199,
|
| 1470 |
+
"eval_steps_per_second": 7.199,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.632034632034632,
|
| 1475 |
+
"grad_norm": 0.11632063239812851,
|
| 1476 |
+
"learning_rate": 5.403020275088786e-05,
|
| 1477 |
+
"loss": 0.0153,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 2.6474266474266477,
|
| 1482 |
+
"grad_norm": 0.24772502481937408,
|
| 1483 |
+
"learning_rate": 5.349378625719408e-05,
|
| 1484 |
+
"loss": 0.0182,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 2.6628186628186628,
|
| 1489 |
+
"grad_norm": 0.3546585142612457,
|
| 1490 |
+
"learning_rate": 5.2956965349496743e-05,
|
| 1491 |
+
"loss": 0.0245,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 2.6782106782106783,
|
| 1496 |
+
"grad_norm": 0.1844964474439621,
|
| 1497 |
+
"learning_rate": 5.241980216608261e-05,
|
| 1498 |
+
"loss": 0.0197,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 2.6936026936026938,
|
| 1503 |
+
"grad_norm": 0.31028082966804504,
|
| 1504 |
+
"learning_rate": 5.188235888485773e-05,
|
| 1505 |
+
"loss": 0.0158,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.6936026936026938,
|
| 1510 |
+
"eval_loss": 0.0352238304913044,
|
| 1511 |
+
"eval_runtime": 160.4591,
|
| 1512 |
+
"eval_samples_per_second": 7.198,
|
| 1513 |
+
"eval_steps_per_second": 7.198,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.708994708994709,
|
| 1518 |
+
"grad_norm": 0.28572559356689453,
|
| 1519 |
+
"learning_rate": 5.13446977161501e-05,
|
| 1520 |
+
"loss": 0.0176,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.7243867243867244,
|
| 1525 |
+
"grad_norm": 0.3480417728424072,
|
| 1526 |
+
"learning_rate": 5.0806880895508766e-05,
|
| 1527 |
+
"loss": 0.0244,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.73977873977874,
|
| 1532 |
+
"grad_norm": 0.30054420232772827,
|
| 1533 |
+
"learning_rate": 5.026897067649976e-05,
|
| 1534 |
+
"loss": 0.0252,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.755170755170755,
|
| 1539 |
+
"grad_norm": 0.29019275307655334,
|
| 1540 |
+
"learning_rate": 4.973102932350026e-05,
|
| 1541 |
+
"loss": 0.0154,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.7705627705627704,
|
| 1546 |
+
"grad_norm": 0.3516891300678253,
|
| 1547 |
+
"learning_rate": 4.9193119104491245e-05,
|
| 1548 |
+
"loss": 0.0186,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.7705627705627704,
|
| 1553 |
+
"eval_loss": 0.03843548893928528,
|
| 1554 |
+
"eval_runtime": 160.6061,
|
| 1555 |
+
"eval_samples_per_second": 7.192,
|
| 1556 |
+
"eval_steps_per_second": 7.192,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.785954785954786,
|
| 1561 |
+
"grad_norm": 0.48940154910087585,
|
| 1562 |
+
"learning_rate": 4.86553022838499e-05,
|
| 1563 |
+
"loss": 0.0214,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.8013468013468015,
|
| 1568 |
+
"grad_norm": 0.21716728806495667,
|
| 1569 |
+
"learning_rate": 4.8117641115142285e-05,
|
| 1570 |
+
"loss": 0.0226,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.816738816738817,
|
| 1575 |
+
"grad_norm": 0.1930004209280014,
|
| 1576 |
+
"learning_rate": 4.758019783391741e-05,
|
| 1577 |
+
"loss": 0.0238,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.832130832130832,
|
| 1582 |
+
"grad_norm": 0.4503800868988037,
|
| 1583 |
+
"learning_rate": 4.704303465050327e-05,
|
| 1584 |
+
"loss": 0.0182,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.8475228475228476,
|
| 1589 |
+
"grad_norm": 0.28708982467651367,
|
| 1590 |
+
"learning_rate": 4.6506213742805924e-05,
|
| 1591 |
+
"loss": 0.0155,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.8475228475228476,
|
| 1596 |
+
"eval_loss": 0.04005544260144234,
|
| 1597 |
+
"eval_runtime": 160.4557,
|
| 1598 |
+
"eval_samples_per_second": 7.198,
|
| 1599 |
+
"eval_steps_per_second": 7.198,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.862914862914863,
|
| 1604 |
+
"grad_norm": 0.3030581772327423,
|
| 1605 |
+
"learning_rate": 4.5969797249112146e-05,
|
| 1606 |
+
"loss": 0.0163,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.878306878306878,
|
| 1611 |
+
"grad_norm": 0.3970169723033905,
|
| 1612 |
+
"learning_rate": 4.54338472608969e-05,
|
| 1613 |
+
"loss": 0.0283,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.8936988936988937,
|
| 1618 |
+
"grad_norm": 0.30313968658447266,
|
| 1619 |
+
"learning_rate": 4.489842581563597e-05,
|
| 1620 |
+
"loss": 0.017,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.909090909090909,
|
| 1625 |
+
"grad_norm": 0.07091408222913742,
|
| 1626 |
+
"learning_rate": 4.436359488962511e-05,
|
| 1627 |
+
"loss": 0.0162,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.9244829244829242,
|
| 1632 |
+
"grad_norm": 0.12560871243476868,
|
| 1633 |
+
"learning_rate": 4.382941639080602e-05,
|
| 1634 |
+
"loss": 0.0158,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.9244829244829242,
|
| 1639 |
+
"eval_loss": 0.03647943586111069,
|
| 1640 |
+
"eval_runtime": 160.33,
|
| 1641 |
+
"eval_samples_per_second": 7.204,
|
| 1642 |
+
"eval_steps_per_second": 7.204,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.9398749398749398,
|
| 1647 |
+
"grad_norm": 0.27986544370651245,
|
| 1648 |
+
"learning_rate": 4.3295952151600475e-05,
|
| 1649 |
+
"loss": 0.0199,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.9552669552669553,
|
| 1654 |
+
"grad_norm": 0.31035858392715454,
|
| 1655 |
+
"learning_rate": 4.276326392175296e-05,
|
| 1656 |
+
"loss": 0.0193,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.9706589706589708,
|
| 1661 |
+
"grad_norm": 0.15130609273910522,
|
| 1662 |
+
"learning_rate": 4.2231413361183095e-05,
|
| 1663 |
+
"loss": 0.026,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.9860509860509863,
|
| 1668 |
+
"grad_norm": 0.2772333025932312,
|
| 1669 |
+
"learning_rate": 4.1700462032848244e-05,
|
| 1670 |
+
"loss": 0.0216,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 3.0014430014430014,
|
| 1675 |
+
"grad_norm": 0.3355155289173126,
|
| 1676 |
+
"learning_rate": 4.117047139561758e-05,
|
| 1677 |
+
"loss": 0.0185,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 3.0014430014430014,
|
| 1682 |
+
"eval_loss": 0.03621777892112732,
|
| 1683 |
+
"eval_runtime": 160.2832,
|
| 1684 |
+
"eval_samples_per_second": 7.206,
|
| 1685 |
+
"eval_steps_per_second": 7.206,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 3.016835016835017,
|
| 1690 |
+
"grad_norm": 0.10336437821388245,
|
| 1691 |
+
"learning_rate": 4.0641502797157966e-05,
|
| 1692 |
+
"loss": 0.0123,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 3.0322270322270324,
|
| 1697 |
+
"grad_norm": 0.0928972139954567,
|
| 1698 |
+
"learning_rate": 4.011361746683288e-05,
|
| 1699 |
+
"loss": 0.01,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 3.0476190476190474,
|
| 1704 |
+
"grad_norm": 0.15533702075481415,
|
| 1705 |
+
"learning_rate": 3.958687650861499e-05,
|
| 1706 |
+
"loss": 0.0078,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 3.063011063011063,
|
| 1711 |
+
"grad_norm": 0.0917314663529396,
|
| 1712 |
+
"learning_rate": 3.906134089401313e-05,
|
| 1713 |
+
"loss": 0.0094,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 3.0784030784030785,
|
| 1718 |
+
"grad_norm": 0.14643442630767822,
|
| 1719 |
+
"learning_rate": 3.853707145501482e-05,
|
| 1720 |
+
"loss": 0.0103,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 3.0784030784030785,
|
| 1725 |
+
"eval_loss": 0.040098611265420914,
|
| 1726 |
+
"eval_runtime": 160.3706,
|
| 1727 |
+
"eval_samples_per_second": 7.202,
|
| 1728 |
+
"eval_steps_per_second": 7.202,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 3.093795093795094,
|
| 1733 |
+
"grad_norm": 0.21054565906524658,
|
| 1734 |
+
"learning_rate": 3.801412887704475e-05,
|
| 1735 |
+
"loss": 0.0098,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 3.109187109187109,
|
| 1740 |
+
"grad_norm": 0.15137901902198792,
|
| 1741 |
+
"learning_rate": 3.749257369194029e-05,
|
| 1742 |
+
"loss": 0.0092,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 3.1245791245791246,
|
| 1747 |
+
"grad_norm": 0.4027303159236908,
|
| 1748 |
+
"learning_rate": 3.697246627094487e-05,
|
| 1749 |
+
"loss": 0.0131,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 3.13997113997114,
|
| 1754 |
+
"grad_norm": 0.2530450224876404,
|
| 1755 |
+
"learning_rate": 3.6453866817719726e-05,
|
| 1756 |
+
"loss": 0.01,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 3.1553631553631556,
|
| 1761 |
+
"grad_norm": 0.16488143801689148,
|
| 1762 |
+
"learning_rate": 3.593683536137533e-05,
|
| 1763 |
+
"loss": 0.0111,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 3.1553631553631556,
|
| 1768 |
+
"eval_loss": 0.04021536186337471,
|
| 1769 |
+
"eval_runtime": 160.0952,
|
| 1770 |
+
"eval_samples_per_second": 7.214,
|
| 1771 |
+
"eval_steps_per_second": 7.214,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 3.1707551707551707,
|
| 1776 |
+
"grad_norm": 0.30931276082992554,
|
| 1777 |
+
"learning_rate": 3.542143174952282e-05,
|
| 1778 |
+
"loss": 0.0068,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 3.186147186147186,
|
| 1783 |
+
"grad_norm": 0.9578791260719299,
|
| 1784 |
+
"learning_rate": 3.490771564134643e-05,
|
| 1785 |
+
"loss": 0.0087,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 3.2015392015392017,
|
| 1790 |
+
"grad_norm": 0.24608023464679718,
|
| 1791 |
+
"learning_rate": 3.4395746500697925e-05,
|
| 1792 |
+
"loss": 0.0079,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 3.2169312169312168,
|
| 1797 |
+
"grad_norm": 0.2659907341003418,
|
| 1798 |
+
"learning_rate": 3.388558358921343e-05,
|
| 1799 |
+
"loss": 0.0095,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 3.2323232323232323,
|
| 1804 |
+
"grad_norm": 0.14139080047607422,
|
| 1805 |
+
"learning_rate": 3.337728595945378e-05,
|
| 1806 |
+
"loss": 0.0105,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 3.2323232323232323,
|
| 1811 |
+
"eval_loss": 0.04483305290341377,
|
| 1812 |
+
"eval_runtime": 159.6267,
|
| 1813 |
+
"eval_samples_per_second": 7.236,
|
| 1814 |
+
"eval_steps_per_second": 7.236,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.2477152477152478,
|
| 1819 |
+
"grad_norm": 0.18512935936450958,
|
| 1820 |
+
"learning_rate": 3.287091244806907e-05,
|
| 1821 |
+
"loss": 0.0083,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.2631072631072633,
|
| 1826 |
+
"grad_norm": 0.47649720311164856,
|
| 1827 |
+
"learning_rate": 3.2366521668988106e-05,
|
| 1828 |
+
"loss": 0.0161,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.2784992784992784,
|
| 1833 |
+
"grad_norm": 0.12076949328184128,
|
| 1834 |
+
"learning_rate": 3.186417200663379e-05,
|
| 1835 |
+
"loss": 0.0094,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.293891293891294,
|
| 1840 |
+
"grad_norm": 0.5417758822441101,
|
| 1841 |
+
"learning_rate": 3.136392160916495e-05,
|
| 1842 |
+
"loss": 0.0078,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.3092833092833094,
|
| 1847 |
+
"grad_norm": 0.24188639223575592,
|
| 1848 |
+
"learning_rate": 3.086582838174551e-05,
|
| 1849 |
+
"loss": 0.0077,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.3092833092833094,
|
| 1854 |
+
"eval_loss": 0.043526049703359604,
|
| 1855 |
+
"eval_runtime": 159.2497,
|
| 1856 |
+
"eval_samples_per_second": 7.253,
|
| 1857 |
+
"eval_steps_per_second": 7.253,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 3.324675324675325,
|
| 1862 |
+
"grad_norm": 0.07239481806755066,
|
| 1863 |
+
"learning_rate": 3.036994997984194e-05,
|
| 1864 |
+
"loss": 0.0072,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.34006734006734,
|
| 1869 |
+
"grad_norm": 0.05550282448530197,
|
| 1870 |
+
"learning_rate": 2.9876343802549357e-05,
|
| 1871 |
+
"loss": 0.0065,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 3.3554593554593555,
|
| 1876 |
+
"grad_norm": 0.30957522988319397,
|
| 1877 |
+
"learning_rate": 2.938506698594755e-05,
|
| 1878 |
+
"loss": 0.0073,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 3.370851370851371,
|
| 1883 |
+
"grad_norm": 0.12012802809476852,
|
| 1884 |
+
"learning_rate": 2.8896176396487334e-05,
|
| 1885 |
+
"loss": 0.0071,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 3.386243386243386,
|
| 1890 |
+
"grad_norm": 0.30071431398391724,
|
| 1891 |
+
"learning_rate": 2.8409728624408067e-05,
|
| 1892 |
+
"loss": 0.0078,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 3.386243386243386,
|
| 1897 |
+
"eval_loss": 0.047629620879888535,
|
| 1898 |
+
"eval_runtime": 158.7585,
|
| 1899 |
+
"eval_samples_per_second": 7.275,
|
| 1900 |
+
"eval_steps_per_second": 7.275,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 3.4016354016354016,
|
| 1905 |
+
"grad_norm": 0.12309174984693527,
|
| 1906 |
+
"learning_rate": 2.7925779977187215e-05,
|
| 1907 |
+
"loss": 0.0092,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 3.417027417027417,
|
| 1912 |
+
"grad_norm": 0.13252991437911987,
|
| 1913 |
+
"learning_rate": 2.7444386473022686e-05,
|
| 1914 |
+
"loss": 0.0082,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 3.4324194324194326,
|
| 1919 |
+
"grad_norm": 0.0676349624991417,
|
| 1920 |
+
"learning_rate": 2.696560383434854e-05,
|
| 1921 |
+
"loss": 0.0091,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 3.4478114478114477,
|
| 1926 |
+
"grad_norm": 0.10048947483301163,
|
| 1927 |
+
"learning_rate": 2.6489487481384988e-05,
|
| 1928 |
+
"loss": 0.0077,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 3.463203463203463,
|
| 1933 |
+
"grad_norm": 0.4449813961982727,
|
| 1934 |
+
"learning_rate": 2.601609252572339e-05,
|
| 1935 |
+
"loss": 0.0072,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 3.463203463203463,
|
| 1940 |
+
"eval_loss": 0.04566098749637604,
|
| 1941 |
+
"eval_runtime": 158.4312,
|
| 1942 |
+
"eval_samples_per_second": 7.29,
|
| 1943 |
+
"eval_steps_per_second": 7.29,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 3.4785954785954787,
|
| 1948 |
+
"grad_norm": 0.045422930270433426,
|
| 1949 |
+
"learning_rate": 2.554547376394692e-05,
|
| 1950 |
+
"loss": 0.0084,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 3.493987493987494,
|
| 1955 |
+
"grad_norm": 0.14082124829292297,
|
| 1956 |
+
"learning_rate": 2.5077685671287808e-05,
|
| 1957 |
+
"loss": 0.0115,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 3.5093795093795093,
|
| 1962 |
+
"grad_norm": 0.698976993560791,
|
| 1963 |
+
"learning_rate": 2.4612782395321593e-05,
|
| 1964 |
+
"loss": 0.0125,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 3.5247715247715248,
|
| 1969 |
+
"grad_norm": 0.28054505586624146,
|
| 1970 |
+
"learning_rate": 2.4150817749699496e-05,
|
| 1971 |
+
"loss": 0.0056,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 3.5401635401635403,
|
| 1976 |
+
"grad_norm": 0.6282978057861328,
|
| 1977 |
+
"learning_rate": 2.3691845207919357e-05,
|
| 1978 |
+
"loss": 0.0118,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 3.5401635401635403,
|
| 1983 |
+
"eval_loss": 0.04520741105079651,
|
| 1984 |
+
"eval_runtime": 158.2029,
|
| 1985 |
+
"eval_samples_per_second": 7.301,
|
| 1986 |
+
"eval_steps_per_second": 7.301,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 3.5555555555555554,
|
| 1991 |
+
"grad_norm": 0.07654228806495667,
|
| 1992 |
+
"learning_rate": 2.3235917897135934e-05,
|
| 1993 |
+
"loss": 0.0063,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 3.570947570947571,
|
| 1998 |
+
"grad_norm": 0.2524222731590271,
|
| 1999 |
+
"learning_rate": 2.2783088592011303e-05,
|
| 2000 |
+
"loss": 0.0079,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.5863395863395864,
|
| 2005 |
+
"grad_norm": 0.4098080098628998,
|
| 2006 |
+
"learning_rate": 2.233340970860608e-05,
|
| 2007 |
+
"loss": 0.0094,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.601731601731602,
|
| 2012 |
+
"grad_norm": 0.3212938606739044,
|
| 2013 |
+
"learning_rate": 2.1886933298312125e-05,
|
| 2014 |
+
"loss": 0.0096,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 3.617123617123617,
|
| 2019 |
+
"grad_norm": 0.1865200251340866,
|
| 2020 |
+
"learning_rate": 2.1443711041827503e-05,
|
| 2021 |
+
"loss": 0.0107,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 3.617123617123617,
|
| 2026 |
+
"eval_loss": 0.04479704424738884,
|
| 2027 |
+
"eval_runtime": 158.2191,
|
| 2028 |
+
"eval_samples_per_second": 7.3,
|
| 2029 |
+
"eval_steps_per_second": 7.3,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 3.6325156325156325,
|
| 2034 |
+
"grad_norm": 0.07322122901678085,
|
| 2035 |
+
"learning_rate": 2.1003794243174252e-05,
|
| 2036 |
+
"loss": 0.0049,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 3.647907647907648,
|
| 2041 |
+
"grad_norm": 0.03634365275502205,
|
| 2042 |
+
"learning_rate": 2.0567233823759886e-05,
|
| 2043 |
+
"loss": 0.0058,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 3.6632996632996635,
|
| 2048 |
+
"grad_norm": 0.2598310112953186,
|
| 2049 |
+
"learning_rate": 2.0134080316483113e-05,
|
| 2050 |
+
"loss": 0.0062,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 3.6786916786916786,
|
| 2055 |
+
"grad_norm": 0.44899070262908936,
|
| 2056 |
+
"learning_rate": 1.970438385988452e-05,
|
| 2057 |
+
"loss": 0.0055,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.694083694083694,
|
| 2062 |
+
"grad_norm": 1.2249691486358643,
|
| 2063 |
+
"learning_rate": 1.927819419234292e-05,
|
| 2064 |
+
"loss": 0.01,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 3.694083694083694,
|
| 2069 |
+
"eval_loss": 0.04775693640112877,
|
| 2070 |
+
"eval_runtime": 158.2614,
|
| 2071 |
+
"eval_samples_per_second": 7.298,
|
| 2072 |
+
"eval_steps_per_second": 7.298,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 3.7094757094757096,
|
| 2077 |
+
"grad_norm": 0.03975760191679001,
|
| 2078 |
+
"learning_rate": 1.885556064631801e-05,
|
| 2079 |
+
"loss": 0.012,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 3.7248677248677247,
|
| 2084 |
+
"grad_norm": 0.06989089399576187,
|
| 2085 |
+
"learning_rate": 1.843653214264003e-05,
|
| 2086 |
+
"loss": 0.0087,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 3.74025974025974,
|
| 2091 |
+
"grad_norm": 0.049630213528871536,
|
| 2092 |
+
"learning_rate": 1.8021157184847087e-05,
|
| 2093 |
+
"loss": 0.0113,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 3.7556517556517557,
|
| 2098 |
+
"grad_norm": 0.13058657944202423,
|
| 2099 |
+
"learning_rate": 1.7609483853570668e-05,
|
| 2100 |
+
"loss": 0.008,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 3.771043771043771,
|
| 2105 |
+
"grad_norm": 0.413333922624588,
|
| 2106 |
+
"learning_rate": 1.720155980097034e-05,
|
| 2107 |
+
"loss": 0.0092,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 3.771043771043771,
|
| 2112 |
+
"eval_loss": 0.04710584878921509,
|
| 2113 |
+
"eval_runtime": 158.1627,
|
| 2114 |
+
"eval_samples_per_second": 7.303,
|
| 2115 |
+
"eval_steps_per_second": 7.303,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.7864357864357867,
|
| 2120 |
+
"grad_norm": 0.03138028830289841,
|
| 2121 |
+
"learning_rate": 1.6797432245217736e-05,
|
| 2122 |
+
"loss": 0.0096,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.801827801827802,
|
| 2127 |
+
"grad_norm": 0.040889088064432144,
|
| 2128 |
+
"learning_rate": 1.6397147965031072e-05,
|
| 2129 |
+
"loss": 0.0076,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.8172198172198173,
|
| 2134 |
+
"grad_norm": 0.654095470905304,
|
| 2135 |
+
"learning_rate": 1.600075329426033e-05,
|
| 2136 |
+
"loss": 0.011,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.832611832611833,
|
| 2141 |
+
"grad_norm": 0.20909631252288818,
|
| 2142 |
+
"learning_rate": 1.560829411652403e-05,
|
| 2143 |
+
"loss": 0.0096,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.848003848003848,
|
| 2148 |
+
"grad_norm": 0.34065234661102295,
|
| 2149 |
+
"learning_rate": 1.521981585989809e-05,
|
| 2150 |
+
"loss": 0.0166,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.848003848003848,
|
| 2155 |
+
"eval_loss": 0.04371841251850128,
|
| 2156 |
+
"eval_runtime": 158.1627,
|
| 2157 |
+
"eval_samples_per_second": 7.303,
|
| 2158 |
+
"eval_steps_per_second": 7.303,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 3.8633958633958634,
|
| 2163 |
+
"grad_norm": 0.1074584573507309,
|
| 2164 |
+
"learning_rate": 1.4835363491657412e-05,
|
| 2165 |
+
"loss": 0.011,
|
| 2166 |
+
"step": 2510
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 3.878787878787879,
|
| 2170 |
+
"grad_norm": 0.14425139129161835,
|
| 2171 |
+
"learning_rate": 1.4454981513070791e-05,
|
| 2172 |
+
"loss": 0.0121,
|
| 2173 |
+
"step": 2520
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 3.894179894179894,
|
| 2177 |
+
"grad_norm": 0.2657093107700348,
|
| 2178 |
+
"learning_rate": 1.4078713954249873e-05,
|
| 2179 |
+
"loss": 0.0061,
|
| 2180 |
+
"step": 2530
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 3.9095719095719095,
|
| 2184 |
+
"grad_norm": 0.09532363712787628,
|
| 2185 |
+
"learning_rate": 1.3706604369052434e-05,
|
| 2186 |
+
"loss": 0.0059,
|
| 2187 |
+
"step": 2540
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 3.924963924963925,
|
| 2191 |
+
"grad_norm": 0.22441978752613068,
|
| 2192 |
+
"learning_rate": 1.3338695830041047e-05,
|
| 2193 |
+
"loss": 0.0048,
|
| 2194 |
+
"step": 2550
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 3.924963924963925,
|
| 2198 |
+
"eval_loss": 0.044441528618335724,
|
| 2199 |
+
"eval_runtime": 158.141,
|
| 2200 |
+
"eval_samples_per_second": 7.304,
|
| 2201 |
+
"eval_steps_per_second": 7.304,
|
| 2202 |
+
"step": 2550
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 3.9403559403559405,
|
| 2206 |
+
"grad_norm": 0.21590059995651245,
|
| 2207 |
+
"learning_rate": 1.2975030923497262e-05,
|
| 2208 |
+
"loss": 0.0052,
|
| 2209 |
+
"step": 2560
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 3.955747955747956,
|
| 2213 |
+
"grad_norm": 0.41011568903923035,
|
| 2214 |
+
"learning_rate": 1.2615651744492151e-05,
|
| 2215 |
+
"loss": 0.0098,
|
| 2216 |
+
"step": 2570
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 3.971139971139971,
|
| 2220 |
+
"grad_norm": 0.14635717868804932,
|
| 2221 |
+
"learning_rate": 1.2260599892013719e-05,
|
| 2222 |
+
"loss": 0.0059,
|
| 2223 |
+
"step": 2580
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 3.9865319865319866,
|
| 2227 |
+
"grad_norm": 0.14410582184791565,
|
| 2228 |
+
"learning_rate": 1.1909916464151715e-05,
|
| 2229 |
+
"loss": 0.0084,
|
| 2230 |
+
"step": 2590
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 4.001924001924002,
|
| 2234 |
+
"grad_norm": 0.11865393072366714,
|
| 2235 |
+
"learning_rate": 1.1563642053340406e-05,
|
| 2236 |
+
"loss": 0.0057,
|
| 2237 |
+
"step": 2600
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 4.001924001924002,
|
| 2241 |
+
"eval_loss": 0.0453677773475647,
|
| 2242 |
+
"eval_runtime": 157.9245,
|
| 2243 |
+
"eval_samples_per_second": 7.314,
|
| 2244 |
+
"eval_steps_per_second": 7.314,
|
| 2245 |
+
"step": 2600
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 4.017316017316017,
|
| 2249 |
+
"grad_norm": 0.06959637254476547,
|
| 2250 |
+
"learning_rate": 1.1221816741659964e-05,
|
| 2251 |
+
"loss": 0.0042,
|
| 2252 |
+
"step": 2610
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 4.032708032708033,
|
| 2256 |
+
"grad_norm": 0.13380874693393707,
|
| 2257 |
+
"learning_rate": 1.0884480096196803e-05,
|
| 2258 |
+
"loss": 0.0037,
|
| 2259 |
+
"step": 2620
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 4.048100048100048,
|
| 2263 |
+
"grad_norm": 0.06643780320882797,
|
| 2264 |
+
"learning_rate": 1.0551671164463666e-05,
|
| 2265 |
+
"loss": 0.0043,
|
| 2266 |
+
"step": 2630
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 4.063492063492063,
|
| 2270 |
+
"grad_norm": 0.14242886006832123,
|
| 2271 |
+
"learning_rate": 1.0223428469879736e-05,
|
| 2272 |
+
"loss": 0.0051,
|
| 2273 |
+
"step": 2640
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 4.078884078884079,
|
| 2277 |
+
"grad_norm": 0.16189664602279663,
|
| 2278 |
+
"learning_rate": 9.899790007311455e-06,
|
| 2279 |
+
"loss": 0.0033,
|
| 2280 |
+
"step": 2650
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 4.078884078884079,
|
| 2284 |
+
"eval_loss": 0.048355016857385635,
|
| 2285 |
+
"eval_runtime": 157.8991,
|
| 2286 |
+
"eval_samples_per_second": 7.315,
|
| 2287 |
+
"eval_steps_per_second": 7.315,
|
| 2288 |
+
"step": 2650
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 4.094276094276094,
|
| 2292 |
+
"grad_norm": 0.022516440600156784,
|
| 2293 |
+
"learning_rate": 9.580793238674573e-06,
|
| 2294 |
+
"loss": 0.0028,
|
| 2295 |
+
"step": 2660
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 4.109668109668109,
|
| 2299 |
+
"grad_norm": 0.24439583718776703,
|
| 2300 |
+
"learning_rate": 9.266475088597781e-06,
|
| 2301 |
+
"loss": 0.0019,
|
| 2302 |
+
"step": 2670
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 4.125060125060125,
|
| 2306 |
+
"grad_norm": 0.30291637778282166,
|
| 2307 |
+
"learning_rate": 8.956871940148681e-06,
|
| 2308 |
+
"loss": 0.0057,
|
| 2309 |
+
"step": 2680
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 4.14045214045214,
|
| 2313 |
+
"grad_norm": 0.07655764371156693,
|
| 2314 |
+
"learning_rate": 8.65201963062225e-06,
|
| 2315 |
+
"loss": 0.0044,
|
| 2316 |
+
"step": 2690
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 4.1558441558441555,
|
| 2320 |
+
"grad_norm": 0.13116689026355743,
|
| 2321 |
+
"learning_rate": 8.351953447392674e-06,
|
| 2322 |
+
"loss": 0.0032,
|
| 2323 |
+
"step": 2700
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 4.1558441558441555,
|
| 2327 |
+
"eval_loss": 0.05001786723732948,
|
| 2328 |
+
"eval_runtime": 157.9193,
|
| 2329 |
+
"eval_samples_per_second": 7.314,
|
| 2330 |
+
"eval_steps_per_second": 7.314,
|
| 2331 |
+
"step": 2700
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 4.171236171236171,
|
| 2335 |
+
"grad_norm": 0.23487193882465363,
|
| 2336 |
+
"learning_rate": 8.056708123828738e-06,
|
| 2337 |
+
"loss": 0.0025,
|
| 2338 |
+
"step": 2710
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 4.1866281866281865,
|
| 2342 |
+
"grad_norm": 0.0992528423666954,
|
| 2343 |
+
"learning_rate": 7.76631783527334e-06,
|
| 2344 |
+
"loss": 0.0021,
|
| 2345 |
+
"step": 2720
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 4.202020202020202,
|
| 2349 |
+
"grad_norm": 0.30396416783332825,
|
| 2350 |
+
"learning_rate": 7.4808161950876145e-06,
|
| 2351 |
+
"loss": 0.0046,
|
| 2352 |
+
"step": 2730
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 4.2174122174122175,
|
| 2356 |
+
"grad_norm": 0.0412018857896328,
|
| 2357 |
+
"learning_rate": 7.200236250760111e-06,
|
| 2358 |
+
"loss": 0.0026,
|
| 2359 |
+
"step": 2740
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 4.232804232804233,
|
| 2363 |
+
"grad_norm": 0.009596334770321846,
|
| 2364 |
+
"learning_rate": 6.924610480081478e-06,
|
| 2365 |
+
"loss": 0.005,
|
| 2366 |
+
"step": 2750
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 4.232804232804233,
|
| 2370 |
+
"eval_loss": 0.0526924729347229,
|
| 2371 |
+
"eval_runtime": 157.9437,
|
| 2372 |
+
"eval_samples_per_second": 7.313,
|
| 2373 |
+
"eval_steps_per_second": 7.313,
|
| 2374 |
+
"step": 2750
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 4.2481962481962485,
|
| 2378 |
+
"grad_norm": 0.038329195231199265,
|
| 2379 |
+
"learning_rate": 6.6539707873850774e-06,
|
| 2380 |
+
"loss": 0.0025,
|
| 2381 |
+
"step": 2760
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 4.263588263588264,
|
| 2385 |
+
"grad_norm": 0.0019896586891263723,
|
| 2386 |
+
"learning_rate": 6.3883484998539525e-06,
|
| 2387 |
+
"loss": 0.0029,
|
| 2388 |
+
"step": 2770
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 4.278980278980279,
|
| 2392 |
+
"grad_norm": 0.06064137443900108,
|
| 2393 |
+
"learning_rate": 6.127774363894667e-06,
|
| 2394 |
+
"loss": 0.0017,
|
| 2395 |
+
"step": 2780
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 4.294372294372295,
|
| 2399 |
+
"grad_norm": 0.07957368344068527,
|
| 2400 |
+
"learning_rate": 5.872278541578352e-06,
|
| 2401 |
+
"loss": 0.0051,
|
| 2402 |
+
"step": 2790
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 4.30976430976431,
|
| 2406 |
+
"grad_norm": 0.007363211829215288,
|
| 2407 |
+
"learning_rate": 5.6218906071493275e-06,
|
| 2408 |
+
"loss": 0.004,
|
| 2409 |
+
"step": 2800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 4.30976430976431,
|
| 2413 |
+
"eval_loss": 0.05456327274441719,
|
| 2414 |
+
"eval_runtime": 157.911,
|
| 2415 |
+
"eval_samples_per_second": 7.314,
|
| 2416 |
+
"eval_steps_per_second": 7.314,
|
| 2417 |
+
"step": 2800
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 4.325156325156325,
|
| 2421 |
+
"grad_norm": 0.2222929447889328,
|
| 2422 |
+
"learning_rate": 5.376639543601858e-06,
|
| 2423 |
+
"loss": 0.0028,
|
| 2424 |
+
"step": 2810
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 4.340548340548341,
|
| 2428 |
+
"grad_norm": 0.0447678342461586,
|
| 2429 |
+
"learning_rate": 5.136553739325256e-06,
|
| 2430 |
+
"loss": 0.0017,
|
| 2431 |
+
"step": 2820
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 4.355940355940356,
|
| 2435 |
+
"grad_norm": 0.04685351252555847,
|
| 2436 |
+
"learning_rate": 4.901660984817908e-06,
|
| 2437 |
+
"loss": 0.0027,
|
| 2438 |
+
"step": 2830
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 4.371332371332372,
|
| 2442 |
+
"grad_norm": 0.9541874527931213,
|
| 2443 |
+
"learning_rate": 4.671988469470434e-06,
|
| 2444 |
+
"loss": 0.0036,
|
| 2445 |
+
"step": 2840
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 4.386724386724387,
|
| 2449 |
+
"grad_norm": 0.08022912591695786,
|
| 2450 |
+
"learning_rate": 4.447562778418435e-06,
|
| 2451 |
+
"loss": 0.0034,
|
| 2452 |
+
"step": 2850
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 4.386724386724387,
|
| 2456 |
+
"eval_loss": 0.055369455367326736,
|
| 2457 |
+
"eval_runtime": 157.9015,
|
| 2458 |
+
"eval_samples_per_second": 7.315,
|
| 2459 |
+
"eval_steps_per_second": 7.315,
|
| 2460 |
+
"step": 2850
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 4.402116402116402,
|
| 2464 |
+
"grad_norm": 0.1095672994852066,
|
| 2465 |
+
"learning_rate": 4.228409889465218e-06,
|
| 2466 |
+
"loss": 0.0018,
|
| 2467 |
+
"step": 2860
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 4.417508417508418,
|
| 2471 |
+
"grad_norm": 0.7465848922729492,
|
| 2472 |
+
"learning_rate": 4.014555170074824e-06,
|
| 2473 |
+
"loss": 0.0041,
|
| 2474 |
+
"step": 2870
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 4.432900432900433,
|
| 2478 |
+
"grad_norm": 0.11146574467420578,
|
| 2479 |
+
"learning_rate": 3.8060233744356633e-06,
|
| 2480 |
+
"loss": 0.0018,
|
| 2481 |
+
"step": 2880
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 4.448292448292448,
|
| 2485 |
+
"grad_norm": 0.06695666164159775,
|
| 2486 |
+
"learning_rate": 3.602838640595152e-06,
|
| 2487 |
+
"loss": 0.0026,
|
| 2488 |
+
"step": 2890
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 4.463684463684464,
|
| 2492 |
+
"grad_norm": 0.15812787413597107,
|
| 2493 |
+
"learning_rate": 3.4050244876656866e-06,
|
| 2494 |
+
"loss": 0.0023,
|
| 2495 |
+
"step": 2900
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 4.463684463684464,
|
| 2499 |
+
"eval_loss": 0.05597861111164093,
|
| 2500 |
+
"eval_runtime": 158.0063,
|
| 2501 |
+
"eval_samples_per_second": 7.31,
|
| 2502 |
+
"eval_steps_per_second": 7.31,
|
| 2503 |
+
"step": 2900
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 4.479076479076479,
|
| 2507 |
+
"grad_norm": 0.028353378176689148,
|
| 2508 |
+
"learning_rate": 3.2126038131022552e-06,
|
| 2509 |
+
"loss": 0.001,
|
| 2510 |
+
"step": 2910
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 4.494468494468494,
|
| 2514 |
+
"grad_norm": 0.13058075308799744,
|
| 2515 |
+
"learning_rate": 3.025598890051995e-06,
|
| 2516 |
+
"loss": 0.0016,
|
| 2517 |
+
"step": 2920
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 4.50986050986051,
|
| 2521 |
+
"grad_norm": 0.0282717477530241,
|
| 2522 |
+
"learning_rate": 2.8440313647760288e-06,
|
| 2523 |
+
"loss": 0.0058,
|
| 2524 |
+
"step": 2930
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 4.525252525252525,
|
| 2528 |
+
"grad_norm": 0.2148657888174057,
|
| 2529 |
+
"learning_rate": 2.6679222541438397e-06,
|
| 2530 |
+
"loss": 0.0041,
|
| 2531 |
+
"step": 2940
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 4.540644540644541,
|
| 2535 |
+
"grad_norm": 0.07000631839036942,
|
| 2536 |
+
"learning_rate": 2.4972919432005582e-06,
|
| 2537 |
+
"loss": 0.0027,
|
| 2538 |
+
"step": 2950
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 4.540644540644541,
|
| 2542 |
+
"eval_loss": 0.05637305602431297,
|
| 2543 |
+
"eval_runtime": 157.8692,
|
| 2544 |
+
"eval_samples_per_second": 7.316,
|
| 2545 |
+
"eval_steps_per_second": 7.316,
|
| 2546 |
+
"step": 2950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 4.556036556036556,
|
| 2550 |
+
"grad_norm": 0.058950576931238174,
|
| 2551 |
+
"learning_rate": 2.3321601828073135e-06,
|
| 2552 |
+
"loss": 0.0054,
|
| 2553 |
+
"step": 2960
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 4.571428571428571,
|
| 2557 |
+
"grad_norm": 0.12322745472192764,
|
| 2558 |
+
"learning_rate": 2.1725460873550317e-06,
|
| 2559 |
+
"loss": 0.0022,
|
| 2560 |
+
"step": 2970
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 4.586820586820587,
|
| 2564 |
+
"grad_norm": 0.0949539840221405,
|
| 2565 |
+
"learning_rate": 2.0184681325519096e-06,
|
| 2566 |
+
"loss": 0.0043,
|
| 2567 |
+
"step": 2980
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 4.602212602212602,
|
| 2571 |
+
"grad_norm": 0.01033385656774044,
|
| 2572 |
+
"learning_rate": 1.869944153284786e-06,
|
| 2573 |
+
"loss": 0.0039,
|
| 2574 |
+
"step": 2990
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 4.617604617604617,
|
| 2578 |
+
"grad_norm": 0.09847161173820496,
|
| 2579 |
+
"learning_rate": 1.7269913415547456e-06,
|
| 2580 |
+
"loss": 0.0025,
|
| 2581 |
+
"step": 3000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 4.617604617604617,
|
| 2585 |
+
"eval_loss": 0.0562971830368042,
|
| 2586 |
+
"eval_runtime": 157.7475,
|
| 2587 |
+
"eval_samples_per_second": 7.322,
|
| 2588 |
+
"eval_steps_per_second": 7.322,
|
| 2589 |
+
"step": 3000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 4.632996632996633,
|
| 2593 |
+
"grad_norm": 0.07785726338624954,
|
| 2594 |
+
"learning_rate": 1.589626244487069e-06,
|
| 2595 |
+
"loss": 0.0029,
|
| 2596 |
+
"step": 3010
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 4.648388648388648,
|
| 2600 |
+
"grad_norm": 0.0484982393682003,
|
| 2601 |
+
"learning_rate": 1.4578647624158726e-06,
|
| 2602 |
+
"loss": 0.0041,
|
| 2603 |
+
"step": 3020
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 4.663780663780663,
|
| 2607 |
+
"grad_norm": 0.4885905086994171,
|
| 2608 |
+
"learning_rate": 1.3317221470436293e-06,
|
| 2609 |
+
"loss": 0.0034,
|
| 2610 |
+
"step": 3030
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 4.679172679172679,
|
| 2614 |
+
"grad_norm": 0.2064741998910904,
|
| 2615 |
+
"learning_rate": 1.2112129996757315e-06,
|
| 2616 |
+
"loss": 0.0036,
|
| 2617 |
+
"step": 3040
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 4.694564694564694,
|
| 2621 |
+
"grad_norm": 0.06070768088102341,
|
| 2622 |
+
"learning_rate": 1.0963512695303546e-06,
|
| 2623 |
+
"loss": 0.0054,
|
| 2624 |
+
"step": 3050
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 4.694564694564694,
|
| 2628 |
+
"eval_loss": 0.05679197236895561,
|
| 2629 |
+
"eval_runtime": 157.7617,
|
| 2630 |
+
"eval_samples_per_second": 7.321,
|
| 2631 |
+
"eval_steps_per_second": 7.321,
|
| 2632 |
+
"step": 3050
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 4.70995670995671,
|
| 2636 |
+
"grad_norm": 0.015436189249157906,
|
| 2637 |
+
"learning_rate": 9.871502521237975e-07,
|
| 2638 |
+
"loss": 0.003,
|
| 2639 |
+
"step": 3060
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 4.725348725348725,
|
| 2643 |
+
"grad_norm": 0.08534955233335495,
|
| 2644 |
+
"learning_rate": 8.83622587731514e-07,
|
| 2645 |
+
"loss": 0.0026,
|
| 2646 |
+
"step": 3070
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 4.7407407407407405,
|
| 2650 |
+
"grad_norm": 0.18290217220783234,
|
| 2651 |
+
"learning_rate": 7.857802599249564e-07,
|
| 2652 |
+
"loss": 0.0019,
|
| 2653 |
+
"step": 3080
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 4.756132756132756,
|
| 2657 |
+
"grad_norm": 0.012095090933144093,
|
| 2658 |
+
"learning_rate": 6.936345941844335e-07,
|
| 2659 |
+
"loss": 0.0039,
|
| 2660 |
+
"step": 3090
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 4.7715247715247715,
|
| 2664 |
+
"grad_norm": 0.032935187220573425,
|
| 2665 |
+
"learning_rate": 6.071962565881939e-07,
|
| 2666 |
+
"loss": 0.0016,
|
| 2667 |
+
"step": 3100
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 4.7715247715247715,
|
| 2671 |
+
"eval_loss": 0.05687952786684036,
|
| 2672 |
+
"eval_runtime": 157.7599,
|
| 2673 |
+
"eval_samples_per_second": 7.321,
|
| 2674 |
+
"eval_steps_per_second": 7.321,
|
| 2675 |
+
"step": 3100
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 4.786916786916787,
|
| 2679 |
+
"grad_norm": 0.03579120710492134,
|
| 2680 |
+
"learning_rate": 5.264752525777961e-07,
|
| 2681 |
+
"loss": 0.0014,
|
| 2682 |
+
"step": 3110
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 4.8023088023088025,
|
| 2686 |
+
"grad_norm": 0.34775373339653015,
|
| 2687 |
+
"learning_rate": 4.5148092579991863e-07,
|
| 2688 |
+
"loss": 0.0023,
|
| 2689 |
+
"step": 3120
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 4.817700817700818,
|
| 2693 |
+
"grad_norm": 0.2920624911785126,
|
| 2694 |
+
"learning_rate": 3.822219570248531e-07,
|
| 2695 |
+
"loss": 0.0033,
|
| 2696 |
+
"step": 3130
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 4.833092833092833,
|
| 2700 |
+
"grad_norm": 0.03081696853041649,
|
| 2701 |
+
"learning_rate": 3.187063631416742e-07,
|
| 2702 |
+
"loss": 0.0048,
|
| 2703 |
+
"step": 3140
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 4.848484848484849,
|
| 2707 |
+
"grad_norm": 0.07112334668636322,
|
| 2708 |
+
"learning_rate": 2.6094149623024365e-07,
|
| 2709 |
+
"loss": 0.0024,
|
| 2710 |
+
"step": 3150
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 4.848484848484849,
|
| 2714 |
+
"eval_loss": 0.056653253734111786,
|
| 2715 |
+
"eval_runtime": 157.8802,
|
| 2716 |
+
"eval_samples_per_second": 7.316,
|
| 2717 |
+
"eval_steps_per_second": 7.316,
|
| 2718 |
+
"step": 3150
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.863876863876864,
|
| 2722 |
+
"grad_norm": 0.1798284500837326,
|
| 2723 |
+
"learning_rate": 2.0893404271022376e-07,
|
| 2724 |
+
"loss": 0.002,
|
| 2725 |
+
"step": 3160
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.87926887926888,
|
| 2729 |
+
"grad_norm": 0.08457917720079422,
|
| 2730 |
+
"learning_rate": 1.626900225670691e-07,
|
| 2731 |
+
"loss": 0.0021,
|
| 2732 |
+
"step": 3170
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.894660894660895,
|
| 2736 |
+
"grad_norm": 0.057848088443279266,
|
| 2737 |
+
"learning_rate": 1.2221478865524493e-07,
|
| 2738 |
+
"loss": 0.0038,
|
| 2739 |
+
"step": 3180
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.91005291005291,
|
| 2743 |
+
"grad_norm": 0.12058410048484802,
|
| 2744 |
+
"learning_rate": 8.751302607857836e-08,
|
| 2745 |
+
"loss": 0.0022,
|
| 2746 |
+
"step": 3190
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.925444925444926,
|
| 2750 |
+
"grad_norm": 0.028752174228429794,
|
| 2751 |
+
"learning_rate": 5.8588751647975506e-08,
|
| 2752 |
+
"loss": 0.0018,
|
| 2753 |
+
"step": 3200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.925444925444926,
|
| 2757 |
+
"eval_loss": 0.056797631084918976,
|
| 2758 |
+
"eval_runtime": 157.844,
|
| 2759 |
+
"eval_samples_per_second": 7.317,
|
| 2760 |
+
"eval_steps_per_second": 7.317,
|
| 2761 |
+
"step": 3200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 4.940836940836941,
|
| 2765 |
+
"grad_norm": 0.13063248991966248,
|
| 2766 |
+
"learning_rate": 3.544531341646007e-08,
|
| 2767 |
+
"loss": 0.0062,
|
| 2768 |
+
"step": 3210
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 4.956228956228956,
|
| 2772 |
+
"grad_norm": 0.27323055267333984,
|
| 2773 |
+
"learning_rate": 1.808539029161116e-08,
|
| 2774 |
+
"loss": 0.0031,
|
| 2775 |
+
"step": 3220
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 4.971620971620972,
|
| 2779 |
+
"grad_norm": 0.03140595927834511,
|
| 2780 |
+
"learning_rate": 6.510991725500182e-09,
|
| 2781 |
+
"loss": 0.0027,
|
| 2782 |
+
"step": 3230
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 4.987012987012987,
|
| 2786 |
+
"grad_norm": 0.02295578084886074,
|
| 2787 |
+
"learning_rate": 7.234574820769169e-10,
|
| 2788 |
+
"loss": 0.0016,
|
| 2789 |
+
"step": 3240
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 4.994708994708994,
|
| 2793 |
+
"step": 3245,
|
| 2794 |
+
"total_flos": 8.15387262412456e+17,
|
| 2795 |
+
"train_loss": 0.041617053084775736,
|
| 2796 |
+
"train_runtime": 36330.2026,
|
| 2797 |
+
"train_samples_per_second": 1.431,
|
| 2798 |
+
"train_steps_per_second": 0.089
|
| 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": 8.15387262412456e+17,
|
| 2819 |
+
"train_batch_size": 1,
|
| 2820 |
+
"trial_name": null,
|
| 2821 |
+
"trial_params": null
|
| 2822 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|