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 +2865 -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-fold8
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# Llama3-OpenBioLLM-8B-PsyCourse-fold8
|
| 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-fold8
|
|
|
|
| 16 |
|
| 17 |
# Llama3-OpenBioLLM-8B-PsyCourse-fold8
|
| 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-fold8 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0360
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.996682778883518,
|
| 3 |
+
"eval_loss": 0.03601429983973503,
|
| 4 |
+
"eval_runtime": 184.2008,
|
| 5 |
+
"eval_samples_per_second": 6.368,
|
| 6 |
+
"eval_steps_per_second": 6.368,
|
| 7 |
+
"total_flos": 8.269502901505229e+17,
|
| 8 |
+
"train_loss": 0.04054494600613038,
|
| 9 |
+
"train_runtime": 44308.6539,
|
| 10 |
+
"train_samples_per_second": 1.191,
|
| 11 |
+
"train_steps_per_second": 0.074
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.996682778883518,
|
| 3 |
+
"eval_loss": 0.03601429983973503,
|
| 4 |
+
"eval_runtime": 184.2008,
|
| 5 |
+
"eval_samples_per_second": 6.368,
|
| 6 |
+
"eval_steps_per_second": 6.368
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.996682778883518,
|
| 3 |
+
"total_flos": 8.269502901505229e+17,
|
| 4 |
+
"train_loss": 0.04054494600613038,
|
| 5 |
+
"train_runtime": 44308.6539,
|
| 6 |
+
"train_samples_per_second": 1.191,
|
| 7 |
+
"train_steps_per_second": 0.074
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2865 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.03601429983973503,
|
| 3 |
+
"best_model_checkpoint": "saves/psy-course/Llama3-OpenBioLLM-8B/train/fold8/checkpoint-1300",
|
| 4 |
+
"epoch": 4.996682778883518,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 3295,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.015164439389631315,
|
| 13 |
+
"grad_norm": 6.69179105758667,
|
| 14 |
+
"learning_rate": 3.0303030303030305e-06,
|
| 15 |
+
"loss": 1.3822,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03032887877926263,
|
| 20 |
+
"grad_norm": 6.022090435028076,
|
| 21 |
+
"learning_rate": 6.060606060606061e-06,
|
| 22 |
+
"loss": 1.3562,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.045493318168893945,
|
| 27 |
+
"grad_norm": 3.7154126167297363,
|
| 28 |
+
"learning_rate": 9.090909090909091e-06,
|
| 29 |
+
"loss": 1.0285,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06065775755852526,
|
| 34 |
+
"grad_norm": 2.2793216705322266,
|
| 35 |
+
"learning_rate": 1.2121212121212122e-05,
|
| 36 |
+
"loss": 0.7714,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07582219694815658,
|
| 41 |
+
"grad_norm": 1.6856296062469482,
|
| 42 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 43 |
+
"loss": 0.5651,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07582219694815658,
|
| 48 |
+
"eval_loss": 0.34537237882614136,
|
| 49 |
+
"eval_runtime": 206.8033,
|
| 50 |
+
"eval_samples_per_second": 5.672,
|
| 51 |
+
"eval_steps_per_second": 5.672,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09098663633778789,
|
| 56 |
+
"grad_norm": 1.1443841457366943,
|
| 57 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 58 |
+
"loss": 0.2852,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1061510757274192,
|
| 63 |
+
"grad_norm": 1.259319543838501,
|
| 64 |
+
"learning_rate": 2.1212121212121215e-05,
|
| 65 |
+
"loss": 0.1781,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12131551511705052,
|
| 70 |
+
"grad_norm": 1.664919376373291,
|
| 71 |
+
"learning_rate": 2.4242424242424244e-05,
|
| 72 |
+
"loss": 0.1862,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13647995450668182,
|
| 77 |
+
"grad_norm": 1.8507658243179321,
|
| 78 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 79 |
+
"loss": 0.1156,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15164439389631315,
|
| 84 |
+
"grad_norm": 1.0127924680709839,
|
| 85 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 86 |
+
"loss": 0.159,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.15164439389631315,
|
| 91 |
+
"eval_loss": 0.09158477187156677,
|
| 92 |
+
"eval_runtime": 206.5291,
|
| 93 |
+
"eval_samples_per_second": 5.68,
|
| 94 |
+
"eval_steps_per_second": 5.68,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.16680883328594445,
|
| 99 |
+
"grad_norm": 0.5882529020309448,
|
| 100 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 101 |
+
"loss": 0.0949,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.18197327267557578,
|
| 106 |
+
"grad_norm": 1.612291932106018,
|
| 107 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 108 |
+
"loss": 0.0905,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.19713771206520708,
|
| 113 |
+
"grad_norm": 1.462253212928772,
|
| 114 |
+
"learning_rate": 3.939393939393939e-05,
|
| 115 |
+
"loss": 0.0932,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2123021514548384,
|
| 120 |
+
"grad_norm": 0.7238670587539673,
|
| 121 |
+
"learning_rate": 4.242424242424243e-05,
|
| 122 |
+
"loss": 0.0719,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.2274665908444697,
|
| 127 |
+
"grad_norm": 1.0951787233352661,
|
| 128 |
+
"learning_rate": 4.545454545454546e-05,
|
| 129 |
+
"loss": 0.0775,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.2274665908444697,
|
| 134 |
+
"eval_loss": 0.06597652286291122,
|
| 135 |
+
"eval_runtime": 206.2354,
|
| 136 |
+
"eval_samples_per_second": 5.688,
|
| 137 |
+
"eval_steps_per_second": 5.688,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.24263103023410104,
|
| 142 |
+
"grad_norm": 0.9825966358184814,
|
| 143 |
+
"learning_rate": 4.848484848484849e-05,
|
| 144 |
+
"loss": 0.0688,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.25779546962373234,
|
| 149 |
+
"grad_norm": 1.0078524351119995,
|
| 150 |
+
"learning_rate": 5.151515151515152e-05,
|
| 151 |
+
"loss": 0.0726,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.27295990901336364,
|
| 156 |
+
"grad_norm": 1.0524179935455322,
|
| 157 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 158 |
+
"loss": 0.084,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.288124348402995,
|
| 163 |
+
"grad_norm": 0.7553159594535828,
|
| 164 |
+
"learning_rate": 5.757575757575758e-05,
|
| 165 |
+
"loss": 0.0741,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.3032887877926263,
|
| 170 |
+
"grad_norm": 1.2318599224090576,
|
| 171 |
+
"learning_rate": 6.060606060606061e-05,
|
| 172 |
+
"loss": 0.0565,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.3032887877926263,
|
| 177 |
+
"eval_loss": 0.05869923532009125,
|
| 178 |
+
"eval_runtime": 205.8994,
|
| 179 |
+
"eval_samples_per_second": 5.697,
|
| 180 |
+
"eval_steps_per_second": 5.697,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.3184532271822576,
|
| 185 |
+
"grad_norm": 0.7203672528266907,
|
| 186 |
+
"learning_rate": 6.363636363636364e-05,
|
| 187 |
+
"loss": 0.0557,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.3336176665718889,
|
| 192 |
+
"grad_norm": 0.9632550477981567,
|
| 193 |
+
"learning_rate": 6.666666666666667e-05,
|
| 194 |
+
"loss": 0.0588,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.34878210596152026,
|
| 199 |
+
"grad_norm": 0.7189677357673645,
|
| 200 |
+
"learning_rate": 6.96969696969697e-05,
|
| 201 |
+
"loss": 0.0813,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.36394654535115156,
|
| 206 |
+
"grad_norm": 0.7692343592643738,
|
| 207 |
+
"learning_rate": 7.272727272727273e-05,
|
| 208 |
+
"loss": 0.053,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.37911098474078286,
|
| 213 |
+
"grad_norm": 0.8544824123382568,
|
| 214 |
+
"learning_rate": 7.575757575757576e-05,
|
| 215 |
+
"loss": 0.0563,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.37911098474078286,
|
| 220 |
+
"eval_loss": 0.05937855690717697,
|
| 221 |
+
"eval_runtime": 206.5519,
|
| 222 |
+
"eval_samples_per_second": 5.679,
|
| 223 |
+
"eval_steps_per_second": 5.679,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.39427542413041416,
|
| 228 |
+
"grad_norm": 0.6232314109802246,
|
| 229 |
+
"learning_rate": 7.878787878787879e-05,
|
| 230 |
+
"loss": 0.0534,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.40943986352004547,
|
| 235 |
+
"grad_norm": 0.350496768951416,
|
| 236 |
+
"learning_rate": 8.181818181818183e-05,
|
| 237 |
+
"loss": 0.0794,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.4246043029096768,
|
| 242 |
+
"grad_norm": 0.9284454584121704,
|
| 243 |
+
"learning_rate": 8.484848484848486e-05,
|
| 244 |
+
"loss": 0.0607,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.4397687422993081,
|
| 249 |
+
"grad_norm": 0.5696659088134766,
|
| 250 |
+
"learning_rate": 8.787878787878789e-05,
|
| 251 |
+
"loss": 0.0464,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.4549331816889394,
|
| 256 |
+
"grad_norm": 0.7423091530799866,
|
| 257 |
+
"learning_rate": 9.090909090909092e-05,
|
| 258 |
+
"loss": 0.0631,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.4549331816889394,
|
| 263 |
+
"eval_loss": 0.05754981189966202,
|
| 264 |
+
"eval_runtime": 207.1337,
|
| 265 |
+
"eval_samples_per_second": 5.663,
|
| 266 |
+
"eval_steps_per_second": 5.663,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.4700976210785707,
|
| 271 |
+
"grad_norm": 0.46020084619522095,
|
| 272 |
+
"learning_rate": 9.393939393939395e-05,
|
| 273 |
+
"loss": 0.0479,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.4852620604682021,
|
| 278 |
+
"grad_norm": 0.6511795520782471,
|
| 279 |
+
"learning_rate": 9.696969696969698e-05,
|
| 280 |
+
"loss": 0.047,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.5004264998578334,
|
| 285 |
+
"grad_norm": 0.9548239707946777,
|
| 286 |
+
"learning_rate": 0.0001,
|
| 287 |
+
"loss": 0.0567,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.5155909392474647,
|
| 292 |
+
"grad_norm": 0.6067355275154114,
|
| 293 |
+
"learning_rate": 9.999719336268101e-05,
|
| 294 |
+
"loss": 0.0527,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.530755378637096,
|
| 299 |
+
"grad_norm": 0.4896825850009918,
|
| 300 |
+
"learning_rate": 9.998877376581251e-05,
|
| 301 |
+
"loss": 0.0677,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.530755378637096,
|
| 306 |
+
"eval_loss": 0.05034831538796425,
|
| 307 |
+
"eval_runtime": 205.9619,
|
| 308 |
+
"eval_samples_per_second": 5.695,
|
| 309 |
+
"eval_steps_per_second": 5.695,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5459198180267273,
|
| 314 |
+
"grad_norm": 0.5949435234069824,
|
| 315 |
+
"learning_rate": 9.997474215462472e-05,
|
| 316 |
+
"loss": 0.0531,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5610842574163586,
|
| 321 |
+
"grad_norm": 0.7067845463752747,
|
| 322 |
+
"learning_rate": 9.995510010438337e-05,
|
| 323 |
+
"loss": 0.041,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.57624869680599,
|
| 328 |
+
"grad_norm": 0.6521092057228088,
|
| 329 |
+
"learning_rate": 9.992984982021295e-05,
|
| 330 |
+
"loss": 0.0584,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5914131361956213,
|
| 335 |
+
"grad_norm": 0.5313027501106262,
|
| 336 |
+
"learning_rate": 9.9898994136849e-05,
|
| 337 |
+
"loss": 0.0549,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6065775755852526,
|
| 342 |
+
"grad_norm": 1.3004082441329956,
|
| 343 |
+
"learning_rate": 9.986253651832005e-05,
|
| 344 |
+
"loss": 0.0366,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6065775755852526,
|
| 349 |
+
"eval_loss": 0.04712074622511864,
|
| 350 |
+
"eval_runtime": 206.1479,
|
| 351 |
+
"eval_samples_per_second": 5.69,
|
| 352 |
+
"eval_steps_per_second": 5.69,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6217420149748839,
|
| 357 |
+
"grad_norm": 0.5177161693572998,
|
| 358 |
+
"learning_rate": 9.982048105755859e-05,
|
| 359 |
+
"loss": 0.0414,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6369064543645152,
|
| 364 |
+
"grad_norm": 0.36376678943634033,
|
| 365 |
+
"learning_rate": 9.977283247594166e-05,
|
| 366 |
+
"loss": 0.0556,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6520708937541465,
|
| 371 |
+
"grad_norm": 0.46044835448265076,
|
| 372 |
+
"learning_rate": 9.971959612276076e-05,
|
| 373 |
+
"loss": 0.0463,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6672353331437778,
|
| 378 |
+
"grad_norm": 0.5747679471969604,
|
| 379 |
+
"learning_rate": 9.966077797462129e-05,
|
| 380 |
+
"loss": 0.05,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6823997725334091,
|
| 385 |
+
"grad_norm": 0.3989450931549072,
|
| 386 |
+
"learning_rate": 9.959638463477165e-05,
|
| 387 |
+
"loss": 0.0397,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6823997725334091,
|
| 392 |
+
"eval_loss": 0.04302780702710152,
|
| 393 |
+
"eval_runtime": 207.0673,
|
| 394 |
+
"eval_samples_per_second": 5.665,
|
| 395 |
+
"eval_steps_per_second": 5.665,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.6975642119230405,
|
| 400 |
+
"grad_norm": 0.37973183393478394,
|
| 401 |
+
"learning_rate": 9.952642333236186e-05,
|
| 402 |
+
"loss": 0.0496,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.7127286513126718,
|
| 407 |
+
"grad_norm": 0.4910580515861511,
|
| 408 |
+
"learning_rate": 9.945090192163202e-05,
|
| 409 |
+
"loss": 0.0476,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7278930907023031,
|
| 414 |
+
"grad_norm": 0.44105058908462524,
|
| 415 |
+
"learning_rate": 9.936982888103051e-05,
|
| 416 |
+
"loss": 0.0394,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.7430575300919344,
|
| 421 |
+
"grad_norm": 0.519553542137146,
|
| 422 |
+
"learning_rate": 9.928321331226219e-05,
|
| 423 |
+
"loss": 0.045,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.7582219694815657,
|
| 428 |
+
"grad_norm": 0.28150394558906555,
|
| 429 |
+
"learning_rate": 9.919106493926655e-05,
|
| 430 |
+
"loss": 0.0383,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.7582219694815657,
|
| 435 |
+
"eval_loss": 0.04788108915090561,
|
| 436 |
+
"eval_runtime": 206.939,
|
| 437 |
+
"eval_samples_per_second": 5.668,
|
| 438 |
+
"eval_steps_per_second": 5.668,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.773386408871197,
|
| 443 |
+
"grad_norm": 0.28955650329589844,
|
| 444 |
+
"learning_rate": 9.909339410712612e-05,
|
| 445 |
+
"loss": 0.0482,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.7885508482608283,
|
| 450 |
+
"grad_norm": 0.6213341355323792,
|
| 451 |
+
"learning_rate": 9.8990211780905e-05,
|
| 452 |
+
"loss": 0.0394,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.8037152876504596,
|
| 457 |
+
"grad_norm": 0.44944509863853455,
|
| 458 |
+
"learning_rate": 9.888152954441785e-05,
|
| 459 |
+
"loss": 0.0454,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.8188797270400909,
|
| 464 |
+
"grad_norm": 0.3272422254085541,
|
| 465 |
+
"learning_rate": 9.876735959892953e-05,
|
| 466 |
+
"loss": 0.0392,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.8340441664297223,
|
| 471 |
+
"grad_norm": 0.7294989824295044,
|
| 472 |
+
"learning_rate": 9.864771476178522e-05,
|
| 473 |
+
"loss": 0.0508,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8340441664297223,
|
| 478 |
+
"eval_loss": 0.04269608110189438,
|
| 479 |
+
"eval_runtime": 206.1894,
|
| 480 |
+
"eval_samples_per_second": 5.689,
|
| 481 |
+
"eval_steps_per_second": 5.689,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.8492086058193536,
|
| 486 |
+
"grad_norm": 0.41436007618904114,
|
| 487 |
+
"learning_rate": 9.852260846497153e-05,
|
| 488 |
+
"loss": 0.0486,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.864373045208985,
|
| 493 |
+
"grad_norm": 0.8043579459190369,
|
| 494 |
+
"learning_rate": 9.839205475360851e-05,
|
| 495 |
+
"loss": 0.0505,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.8795374845986162,
|
| 500 |
+
"grad_norm": 0.4937809705734253,
|
| 501 |
+
"learning_rate": 9.825606828437291e-05,
|
| 502 |
+
"loss": 0.0561,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.8947019239882475,
|
| 507 |
+
"grad_norm": 0.4687022268772125,
|
| 508 |
+
"learning_rate": 9.811466432385267e-05,
|
| 509 |
+
"loss": 0.0428,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.9098663633778789,
|
| 514 |
+
"grad_norm": 0.5363739132881165,
|
| 515 |
+
"learning_rate": 9.796785874683314e-05,
|
| 516 |
+
"loss": 0.0346,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.9098663633778789,
|
| 521 |
+
"eval_loss": 0.04343252256512642,
|
| 522 |
+
"eval_runtime": 206.7862,
|
| 523 |
+
"eval_samples_per_second": 5.673,
|
| 524 |
+
"eval_steps_per_second": 5.673,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.9250308027675102,
|
| 529 |
+
"grad_norm": 0.446513295173645,
|
| 530 |
+
"learning_rate": 9.781566803451475e-05,
|
| 531 |
+
"loss": 0.0566,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.9401952421571415,
|
| 536 |
+
"grad_norm": 0.27837061882019043,
|
| 537 |
+
"learning_rate": 9.765810927266281e-05,
|
| 538 |
+
"loss": 0.0415,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.9553596815467729,
|
| 543 |
+
"grad_norm": 0.27945834398269653,
|
| 544 |
+
"learning_rate": 9.749520014968934e-05,
|
| 545 |
+
"loss": 0.0398,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.9705241209364042,
|
| 550 |
+
"grad_norm": 0.33713576197624207,
|
| 551 |
+
"learning_rate": 9.732695895466735e-05,
|
| 552 |
+
"loss": 0.0437,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.9856885603260355,
|
| 557 |
+
"grad_norm": 0.32925042510032654,
|
| 558 |
+
"learning_rate": 9.715340457527746e-05,
|
| 559 |
+
"loss": 0.0513,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.9856885603260355,
|
| 564 |
+
"eval_loss": 0.044393427670001984,
|
| 565 |
+
"eval_runtime": 207.4663,
|
| 566 |
+
"eval_samples_per_second": 5.654,
|
| 567 |
+
"eval_steps_per_second": 5.654,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.0008529997156668,
|
| 572 |
+
"grad_norm": 0.25668787956237793,
|
| 573 |
+
"learning_rate": 9.697455649568761e-05,
|
| 574 |
+
"loss": 0.0373,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.016017439105298,
|
| 579 |
+
"grad_norm": 0.575491726398468,
|
| 580 |
+
"learning_rate": 9.679043479436556e-05,
|
| 581 |
+
"loss": 0.0316,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.0311818784949294,
|
| 586 |
+
"grad_norm": 0.21307440102100372,
|
| 587 |
+
"learning_rate": 9.660106014182489e-05,
|
| 588 |
+
"loss": 0.0272,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.0463463178845607,
|
| 593 |
+
"grad_norm": 0.27312636375427246,
|
| 594 |
+
"learning_rate": 9.640645379830424e-05,
|
| 595 |
+
"loss": 0.0453,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.061510757274192,
|
| 600 |
+
"grad_norm": 0.286176860332489,
|
| 601 |
+
"learning_rate": 9.620663761138067e-05,
|
| 602 |
+
"loss": 0.0339,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.061510757274192,
|
| 607 |
+
"eval_loss": 0.04173321649432182,
|
| 608 |
+
"eval_runtime": 206.3468,
|
| 609 |
+
"eval_samples_per_second": 5.685,
|
| 610 |
+
"eval_steps_per_second": 5.685,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.0766751966638233,
|
| 615 |
+
"grad_norm": 0.1278642863035202,
|
| 616 |
+
"learning_rate": 9.600163401351688e-05,
|
| 617 |
+
"loss": 0.0254,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.0918396360534546,
|
| 622 |
+
"grad_norm": 0.23175828158855438,
|
| 623 |
+
"learning_rate": 9.579146601954276e-05,
|
| 624 |
+
"loss": 0.0494,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.1070040754430859,
|
| 629 |
+
"grad_norm": 0.10618554055690765,
|
| 630 |
+
"learning_rate": 9.557615722407177e-05,
|
| 631 |
+
"loss": 0.0378,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.1221685148327172,
|
| 636 |
+
"grad_norm": 0.11078658699989319,
|
| 637 |
+
"learning_rate": 9.535573179885191e-05,
|
| 638 |
+
"loss": 0.032,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.1373329542223485,
|
| 643 |
+
"grad_norm": 0.2334222048521042,
|
| 644 |
+
"learning_rate": 9.513021449005214e-05,
|
| 645 |
+
"loss": 0.0296,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.1373329542223485,
|
| 650 |
+
"eval_loss": 0.04424874484539032,
|
| 651 |
+
"eval_runtime": 206.976,
|
| 652 |
+
"eval_samples_per_second": 5.667,
|
| 653 |
+
"eval_steps_per_second": 5.667,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.15249739361198,
|
| 658 |
+
"grad_norm": 0.2527366578578949,
|
| 659 |
+
"learning_rate": 9.489963061548428e-05,
|
| 660 |
+
"loss": 0.0338,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1676618330016113,
|
| 665 |
+
"grad_norm": 0.23535087704658508,
|
| 666 |
+
"learning_rate": 9.466400606176062e-05,
|
| 667 |
+
"loss": 0.0226,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1828262723912426,
|
| 672 |
+
"grad_norm": 0.33640772104263306,
|
| 673 |
+
"learning_rate": 9.442336728138779e-05,
|
| 674 |
+
"loss": 0.0234,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.197990711780874,
|
| 679 |
+
"grad_norm": 0.18896321952342987,
|
| 680 |
+
"learning_rate": 9.417774128979706e-05,
|
| 681 |
+
"loss": 0.0368,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2131551511705052,
|
| 686 |
+
"grad_norm": 0.24871914088726044,
|
| 687 |
+
"learning_rate": 9.39271556623114e-05,
|
| 688 |
+
"loss": 0.0288,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2131551511705052,
|
| 693 |
+
"eval_loss": 0.039680108428001404,
|
| 694 |
+
"eval_runtime": 207.6653,
|
| 695 |
+
"eval_samples_per_second": 5.649,
|
| 696 |
+
"eval_steps_per_second": 5.649,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.2283195905601365,
|
| 701 |
+
"grad_norm": 0.40964576601982117,
|
| 702 |
+
"learning_rate": 9.367163853104975e-05,
|
| 703 |
+
"loss": 0.036,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.2434840299497678,
|
| 708 |
+
"grad_norm": 0.22146688401699066,
|
| 709 |
+
"learning_rate": 9.341121858176876e-05,
|
| 710 |
+
"loss": 0.0369,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.2586484693393991,
|
| 715 |
+
"grad_norm": 0.2575783133506775,
|
| 716 |
+
"learning_rate": 9.314592505064239e-05,
|
| 717 |
+
"loss": 0.0344,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.2738129087290304,
|
| 722 |
+
"grad_norm": 0.19507430493831635,
|
| 723 |
+
"learning_rate": 9.28757877209796e-05,
|
| 724 |
+
"loss": 0.0265,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.2889773481186617,
|
| 729 |
+
"grad_norm": 0.2289421558380127,
|
| 730 |
+
"learning_rate": 9.260083691988084e-05,
|
| 731 |
+
"loss": 0.0299,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.2889773481186617,
|
| 736 |
+
"eval_loss": 0.04206722602248192,
|
| 737 |
+
"eval_runtime": 207.1881,
|
| 738 |
+
"eval_samples_per_second": 5.662,
|
| 739 |
+
"eval_steps_per_second": 5.662,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.304141787508293,
|
| 744 |
+
"grad_norm": 0.5384100675582886,
|
| 745 |
+
"learning_rate": 9.232110351483327e-05,
|
| 746 |
+
"loss": 0.0373,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.3193062268979243,
|
| 751 |
+
"grad_norm": 0.5763593912124634,
|
| 752 |
+
"learning_rate": 9.203661891024547e-05,
|
| 753 |
+
"loss": 0.0376,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.3344706662875556,
|
| 758 |
+
"grad_norm": 0.34299781918525696,
|
| 759 |
+
"learning_rate": 9.174741504392173e-05,
|
| 760 |
+
"loss": 0.0311,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.349635105677187,
|
| 765 |
+
"grad_norm": 0.254780650138855,
|
| 766 |
+
"learning_rate": 9.145352438347662e-05,
|
| 767 |
+
"loss": 0.0355,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.3647995450668184,
|
| 772 |
+
"grad_norm": 0.46846649050712585,
|
| 773 |
+
"learning_rate": 9.115497992268995e-05,
|
| 774 |
+
"loss": 0.0293,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.3647995450668184,
|
| 779 |
+
"eval_loss": 0.04009329527616501,
|
| 780 |
+
"eval_runtime": 206.6929,
|
| 781 |
+
"eval_samples_per_second": 5.675,
|
| 782 |
+
"eval_steps_per_second": 5.675,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.3799639844564497,
|
| 787 |
+
"grad_norm": 0.07255344092845917,
|
| 788 |
+
"learning_rate": 9.085181517780273e-05,
|
| 789 |
+
"loss": 0.0312,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.395128423846081,
|
| 794 |
+
"grad_norm": 0.18492460250854492,
|
| 795 |
+
"learning_rate": 9.054406418375443e-05,
|
| 796 |
+
"loss": 0.0329,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.4102928632357123,
|
| 801 |
+
"grad_norm": 0.34338879585266113,
|
| 802 |
+
"learning_rate": 9.023176149036203e-05,
|
| 803 |
+
"loss": 0.0288,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.4254573026253436,
|
| 808 |
+
"grad_norm": 0.22292286157608032,
|
| 809 |
+
"learning_rate": 8.991494215844132e-05,
|
| 810 |
+
"loss": 0.0441,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.440621742014975,
|
| 815 |
+
"grad_norm": 0.37994903326034546,
|
| 816 |
+
"learning_rate": 8.959364175587069e-05,
|
| 817 |
+
"loss": 0.0278,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.440621742014975,
|
| 822 |
+
"eval_loss": 0.03929847106337547,
|
| 823 |
+
"eval_runtime": 207.7851,
|
| 824 |
+
"eval_samples_per_second": 5.645,
|
| 825 |
+
"eval_steps_per_second": 5.645,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.4557861814046062,
|
| 830 |
+
"grad_norm": 0.24896001815795898,
|
| 831 |
+
"learning_rate": 8.926789635359817e-05,
|
| 832 |
+
"loss": 0.043,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.4709506207942376,
|
| 837 |
+
"grad_norm": 0.16315113008022308,
|
| 838 |
+
"learning_rate": 8.893774252159187e-05,
|
| 839 |
+
"loss": 0.0298,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.4861150601838689,
|
| 844 |
+
"grad_norm": 0.19432376325130463,
|
| 845 |
+
"learning_rate": 8.860321732473439e-05,
|
| 846 |
+
"loss": 0.0364,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.5012794995735002,
|
| 851 |
+
"grad_norm": 0.3546680212020874,
|
| 852 |
+
"learning_rate": 8.826435831866184e-05,
|
| 853 |
+
"loss": 0.0373,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.5164439389631315,
|
| 858 |
+
"grad_norm": 0.09447364509105682,
|
| 859 |
+
"learning_rate": 8.79212035455475e-05,
|
| 860 |
+
"loss": 0.0283,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.5164439389631315,
|
| 865 |
+
"eval_loss": 0.040457405149936676,
|
| 866 |
+
"eval_runtime": 207.9569,
|
| 867 |
+
"eval_samples_per_second": 5.641,
|
| 868 |
+
"eval_steps_per_second": 5.641,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.5316083783527628,
|
| 873 |
+
"grad_norm": 0.2906639873981476,
|
| 874 |
+
"learning_rate": 8.757379152983103e-05,
|
| 875 |
+
"loss": 0.0273,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.546772817742394,
|
| 880 |
+
"grad_norm": 0.4261516332626343,
|
| 881 |
+
"learning_rate": 8.722216127389363e-05,
|
| 882 |
+
"loss": 0.0337,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.5619372571320254,
|
| 887 |
+
"grad_norm": 0.3574506640434265,
|
| 888 |
+
"learning_rate": 8.686635225367919e-05,
|
| 889 |
+
"loss": 0.0285,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.5771016965216567,
|
| 894 |
+
"grad_norm": 0.2925097346305847,
|
| 895 |
+
"learning_rate": 8.650640441426274e-05,
|
| 896 |
+
"loss": 0.0367,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.592266135911288,
|
| 901 |
+
"grad_norm": 0.4504016935825348,
|
| 902 |
+
"learning_rate": 8.614235816536582e-05,
|
| 903 |
+
"loss": 0.0493,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.592266135911288,
|
| 908 |
+
"eval_loss": 0.039341144263744354,
|
| 909 |
+
"eval_runtime": 206.8668,
|
| 910 |
+
"eval_samples_per_second": 5.67,
|
| 911 |
+
"eval_steps_per_second": 5.67,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.6074305753009193,
|
| 916 |
+
"grad_norm": 0.28596726059913635,
|
| 917 |
+
"learning_rate": 8.577425437681994e-05,
|
| 918 |
+
"loss": 0.0352,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.6225950146905506,
|
| 923 |
+
"grad_norm": 0.12631350755691528,
|
| 924 |
+
"learning_rate": 8.540213437397833e-05,
|
| 925 |
+
"loss": 0.0317,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.6377594540801819,
|
| 930 |
+
"grad_norm": 0.1901707649230957,
|
| 931 |
+
"learning_rate": 8.502603993307647e-05,
|
| 932 |
+
"loss": 0.0271,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.6529238934698132,
|
| 937 |
+
"grad_norm": 0.34583041071891785,
|
| 938 |
+
"learning_rate": 8.464601327654207e-05,
|
| 939 |
+
"loss": 0.0261,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.6680883328594445,
|
| 944 |
+
"grad_norm": 0.35897573828697205,
|
| 945 |
+
"learning_rate": 8.4262097068255e-05,
|
| 946 |
+
"loss": 0.0287,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.6680883328594445,
|
| 951 |
+
"eval_loss": 0.03920057788491249,
|
| 952 |
+
"eval_runtime": 205.8057,
|
| 953 |
+
"eval_samples_per_second": 5.7,
|
| 954 |
+
"eval_steps_per_second": 5.7,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.6832527722490758,
|
| 959 |
+
"grad_norm": 0.5413476228713989,
|
| 960 |
+
"learning_rate": 8.387433440875758e-05,
|
| 961 |
+
"loss": 0.0332,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.698417211638707,
|
| 966 |
+
"grad_norm": 0.5442347526550293,
|
| 967 |
+
"learning_rate": 8.348276883041583e-05,
|
| 968 |
+
"loss": 0.0313,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7135816510283386,
|
| 973 |
+
"grad_norm": 0.3635435998439789,
|
| 974 |
+
"learning_rate": 8.308744429253238e-05,
|
| 975 |
+
"loss": 0.0388,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.72874609041797,
|
| 980 |
+
"grad_norm": 0.43414217233657837,
|
| 981 |
+
"learning_rate": 8.268840517641123e-05,
|
| 982 |
+
"loss": 0.0352,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7439105298076012,
|
| 987 |
+
"grad_norm": 0.571806788444519,
|
| 988 |
+
"learning_rate": 8.228569628037543e-05,
|
| 989 |
+
"loss": 0.0383,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.7439105298076012,
|
| 994 |
+
"eval_loss": 0.03788575902581215,
|
| 995 |
+
"eval_runtime": 207.4735,
|
| 996 |
+
"eval_samples_per_second": 5.654,
|
| 997 |
+
"eval_steps_per_second": 5.654,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.7590749691972325,
|
| 1002 |
+
"grad_norm": 0.30155709385871887,
|
| 1003 |
+
"learning_rate": 8.187936281473758e-05,
|
| 1004 |
+
"loss": 0.0311,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.7742394085868638,
|
| 1009 |
+
"grad_norm": 0.11790592968463898,
|
| 1010 |
+
"learning_rate": 8.146945039672446e-05,
|
| 1011 |
+
"loss": 0.0288,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.789403847976495,
|
| 1016 |
+
"grad_norm": 0.3467343747615814,
|
| 1017 |
+
"learning_rate": 8.105600504535567e-05,
|
| 1018 |
+
"loss": 0.0309,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.8045682873661264,
|
| 1023 |
+
"grad_norm": 0.4226018786430359,
|
| 1024 |
+
"learning_rate": 8.06390731762773e-05,
|
| 1025 |
+
"loss": 0.0439,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.8197327267557577,
|
| 1030 |
+
"grad_norm": 0.5903601050376892,
|
| 1031 |
+
"learning_rate": 8.021870159655109e-05,
|
| 1032 |
+
"loss": 0.0312,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.8197327267557577,
|
| 1037 |
+
"eval_loss": 0.037754252552986145,
|
| 1038 |
+
"eval_runtime": 206.9483,
|
| 1039 |
+
"eval_samples_per_second": 5.668,
|
| 1040 |
+
"eval_steps_per_second": 5.668,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.8348971661453892,
|
| 1045 |
+
"grad_norm": 0.2787196636199951,
|
| 1046 |
+
"learning_rate": 7.979493749939955e-05,
|
| 1047 |
+
"loss": 0.034,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.8500616055350205,
|
| 1052 |
+
"grad_norm": 0.23407863080501556,
|
| 1053 |
+
"learning_rate": 7.93678284589079e-05,
|
| 1054 |
+
"loss": 0.0418,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.8652260449246518,
|
| 1059 |
+
"grad_norm": 0.17310842871665955,
|
| 1060 |
+
"learning_rate": 7.893742242468301e-05,
|
| 1061 |
+
"loss": 0.0261,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.8803904843142831,
|
| 1066 |
+
"grad_norm": 0.7467524409294128,
|
| 1067 |
+
"learning_rate": 7.850376771647038e-05,
|
| 1068 |
+
"loss": 0.0406,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.8955549237039144,
|
| 1073 |
+
"grad_norm": 0.2921977639198303,
|
| 1074 |
+
"learning_rate": 7.806691301872958e-05,
|
| 1075 |
+
"loss": 0.0353,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.8955549237039144,
|
| 1080 |
+
"eval_loss": 0.03786836564540863,
|
| 1081 |
+
"eval_runtime": 208.333,
|
| 1082 |
+
"eval_samples_per_second": 5.63,
|
| 1083 |
+
"eval_steps_per_second": 5.63,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.9107193630935457,
|
| 1088 |
+
"grad_norm": 0.18109281361103058,
|
| 1089 |
+
"learning_rate": 7.762690737516846e-05,
|
| 1090 |
+
"loss": 0.0344,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.925883802483177,
|
| 1095 |
+
"grad_norm": 0.21812854707241058,
|
| 1096 |
+
"learning_rate": 7.718380018323742e-05,
|
| 1097 |
+
"loss": 0.0286,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.9410482418728083,
|
| 1102 |
+
"grad_norm": 0.3241231143474579,
|
| 1103 |
+
"learning_rate": 7.673764118858371e-05,
|
| 1104 |
+
"loss": 0.0287,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.9562126812624396,
|
| 1109 |
+
"grad_norm": 0.18561425805091858,
|
| 1110 |
+
"learning_rate": 7.628848047946675e-05,
|
| 1111 |
+
"loss": 0.0392,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.971377120652071,
|
| 1116 |
+
"grad_norm": 0.2008410096168518,
|
| 1117 |
+
"learning_rate": 7.583636848113483e-05,
|
| 1118 |
+
"loss": 0.0242,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.971377120652071,
|
| 1123 |
+
"eval_loss": 0.03601429983973503,
|
| 1124 |
+
"eval_runtime": 208.4866,
|
| 1125 |
+
"eval_samples_per_second": 5.626,
|
| 1126 |
+
"eval_steps_per_second": 5.626,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.9865415600417022,
|
| 1131 |
+
"grad_norm": 0.42017701268196106,
|
| 1132 |
+
"learning_rate": 7.538135595016423e-05,
|
| 1133 |
+
"loss": 0.0329,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.0017059994313335,
|
| 1138 |
+
"grad_norm": 0.23573864996433258,
|
| 1139 |
+
"learning_rate": 7.492349396876096e-05,
|
| 1140 |
+
"loss": 0.0248,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.016870438820965,
|
| 1145 |
+
"grad_norm": 0.12982603907585144,
|
| 1146 |
+
"learning_rate": 7.4462833939026e-05,
|
| 1147 |
+
"loss": 0.0258,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.032034878210596,
|
| 1152 |
+
"grad_norm": 0.20572739839553833,
|
| 1153 |
+
"learning_rate": 7.399942757718455e-05,
|
| 1154 |
+
"loss": 0.0179,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.0471993176002274,
|
| 1159 |
+
"grad_norm": 0.3729046881198883,
|
| 1160 |
+
"learning_rate": 7.35333269077802e-05,
|
| 1161 |
+
"loss": 0.0176,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.0471993176002274,
|
| 1166 |
+
"eval_loss": 0.04126604646444321,
|
| 1167 |
+
"eval_runtime": 207.5727,
|
| 1168 |
+
"eval_samples_per_second": 5.651,
|
| 1169 |
+
"eval_steps_per_second": 5.651,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.0623637569898587,
|
| 1174 |
+
"grad_norm": 0.27359482645988464,
|
| 1175 |
+
"learning_rate": 7.306458425783426e-05,
|
| 1176 |
+
"loss": 0.0309,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.07752819637949,
|
| 1181 |
+
"grad_norm": 0.2222670614719391,
|
| 1182 |
+
"learning_rate": 7.25932522509713e-05,
|
| 1183 |
+
"loss": 0.0191,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.0926926357691213,
|
| 1188 |
+
"grad_norm": 0.35448694229125977,
|
| 1189 |
+
"learning_rate": 7.211938380151133e-05,
|
| 1190 |
+
"loss": 0.0213,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.1078570751587526,
|
| 1195 |
+
"grad_norm": 0.29310059547424316,
|
| 1196 |
+
"learning_rate": 7.164303210852934e-05,
|
| 1197 |
+
"loss": 0.0245,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.123021514548384,
|
| 1202 |
+
"grad_norm": 0.2385050356388092,
|
| 1203 |
+
"learning_rate": 7.116425064988286e-05,
|
| 1204 |
+
"loss": 0.0132,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.123021514548384,
|
| 1209 |
+
"eval_loss": 0.038636982440948486,
|
| 1210 |
+
"eval_runtime": 208.1606,
|
| 1211 |
+
"eval_samples_per_second": 5.635,
|
| 1212 |
+
"eval_steps_per_second": 5.635,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.1381859539380152,
|
| 1217 |
+
"grad_norm": 0.2776142358779907,
|
| 1218 |
+
"learning_rate": 7.068309317620827e-05,
|
| 1219 |
+
"loss": 0.021,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.1533503933276466,
|
| 1224 |
+
"grad_norm": 0.3040802478790283,
|
| 1225 |
+
"learning_rate": 7.019961370488645e-05,
|
| 1226 |
+
"loss": 0.02,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.168514832717278,
|
| 1231 |
+
"grad_norm": 0.3864327073097229,
|
| 1232 |
+
"learning_rate": 6.971386651397849e-05,
|
| 1233 |
+
"loss": 0.0191,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.183679272106909,
|
| 1238 |
+
"grad_norm": 0.3276340663433075,
|
| 1239 |
+
"learning_rate": 6.922590613613211e-05,
|
| 1240 |
+
"loss": 0.017,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.1988437114965405,
|
| 1245 |
+
"grad_norm": 0.18806734681129456,
|
| 1246 |
+
"learning_rate": 6.873578735245961e-05,
|
| 1247 |
+
"loss": 0.0224,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.1988437114965405,
|
| 1252 |
+
"eval_loss": 0.04134543985128403,
|
| 1253 |
+
"eval_runtime": 208.1264,
|
| 1254 |
+
"eval_samples_per_second": 5.636,
|
| 1255 |
+
"eval_steps_per_second": 5.636,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.2140081508861718,
|
| 1260 |
+
"grad_norm": 0.1309497058391571,
|
| 1261 |
+
"learning_rate": 6.824356518638775e-05,
|
| 1262 |
+
"loss": 0.0188,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.229172590275803,
|
| 1267 |
+
"grad_norm": 0.2113678902387619,
|
| 1268 |
+
"learning_rate": 6.774929489748052e-05,
|
| 1269 |
+
"loss": 0.0169,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.2443370296654344,
|
| 1274 |
+
"grad_norm": 0.5515885353088379,
|
| 1275 |
+
"learning_rate": 6.725303197523548e-05,
|
| 1276 |
+
"loss": 0.0285,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.259501469055066,
|
| 1281 |
+
"grad_norm": 0.17094577848911285,
|
| 1282 |
+
"learning_rate": 6.675483213285412e-05,
|
| 1283 |
+
"loss": 0.019,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.274665908444697,
|
| 1288 |
+
"grad_norm": 0.4091382920742035,
|
| 1289 |
+
"learning_rate": 6.625475130098728e-05,
|
| 1290 |
+
"loss": 0.0198,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.274665908444697,
|
| 1295 |
+
"eval_loss": 0.042340174317359924,
|
| 1296 |
+
"eval_runtime": 207.7019,
|
| 1297 |
+
"eval_samples_per_second": 5.648,
|
| 1298 |
+
"eval_steps_per_second": 5.648,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.2898303478343287,
|
| 1303 |
+
"grad_norm": 0.26022475957870483,
|
| 1304 |
+
"learning_rate": 6.575284562145593e-05,
|
| 1305 |
+
"loss": 0.0198,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.30499478722396,
|
| 1310 |
+
"grad_norm": 0.46716049313545227,
|
| 1311 |
+
"learning_rate": 6.524917144094851e-05,
|
| 1312 |
+
"loss": 0.0213,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.3201592266135913,
|
| 1317 |
+
"grad_norm": 0.09904512763023376,
|
| 1318 |
+
"learning_rate": 6.474378530469509e-05,
|
| 1319 |
+
"loss": 0.0249,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.3353236660032226,
|
| 1324 |
+
"grad_norm": 0.35088425874710083,
|
| 1325 |
+
"learning_rate": 6.42367439501193e-05,
|
| 1326 |
+
"loss": 0.0149,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.350488105392854,
|
| 1331 |
+
"grad_norm": 0.38264918327331543,
|
| 1332 |
+
"learning_rate": 6.372810430046862e-05,
|
| 1333 |
+
"loss": 0.0191,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.350488105392854,
|
| 1338 |
+
"eval_loss": 0.04294043034315109,
|
| 1339 |
+
"eval_runtime": 206.9625,
|
| 1340 |
+
"eval_samples_per_second": 5.668,
|
| 1341 |
+
"eval_steps_per_second": 5.668,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.365652544782485,
|
| 1346 |
+
"grad_norm": 0.13157694041728973,
|
| 1347 |
+
"learning_rate": 6.321792345842402e-05,
|
| 1348 |
+
"loss": 0.0228,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.3808169841721165,
|
| 1353 |
+
"grad_norm": 0.2602044939994812,
|
| 1354 |
+
"learning_rate": 6.270625869968906e-05,
|
| 1355 |
+
"loss": 0.0264,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.395981423561748,
|
| 1360 |
+
"grad_norm": 0.20206056535243988,
|
| 1361 |
+
"learning_rate": 6.219316746656007e-05,
|
| 1362 |
+
"loss": 0.0243,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.411145862951379,
|
| 1367 |
+
"grad_norm": 0.3280366361141205,
|
| 1368 |
+
"learning_rate": 6.167870736147713e-05,
|
| 1369 |
+
"loss": 0.0233,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.4263103023410104,
|
| 1374 |
+
"grad_norm": 0.258645623922348,
|
| 1375 |
+
"learning_rate": 6.116293614055744e-05,
|
| 1376 |
+
"loss": 0.017,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.4263103023410104,
|
| 1381 |
+
"eval_loss": 0.041183970868587494,
|
| 1382 |
+
"eval_runtime": 208.1675,
|
| 1383 |
+
"eval_samples_per_second": 5.635,
|
| 1384 |
+
"eval_steps_per_second": 5.635,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.4414747417306417,
|
| 1389 |
+
"grad_norm": 0.29392683506011963,
|
| 1390 |
+
"learning_rate": 6.06459117071113e-05,
|
| 1391 |
+
"loss": 0.0177,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.456639181120273,
|
| 1396 |
+
"grad_norm": 0.24882225692272186,
|
| 1397 |
+
"learning_rate": 6.012769210514146e-05,
|
| 1398 |
+
"loss": 0.0164,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.4718036205099043,
|
| 1403 |
+
"grad_norm": 0.2122090458869934,
|
| 1404 |
+
"learning_rate": 5.9608335512826915e-05,
|
| 1405 |
+
"loss": 0.0197,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.4869680598995356,
|
| 1410 |
+
"grad_norm": 0.12246949225664139,
|
| 1411 |
+
"learning_rate": 5.908790023599144e-05,
|
| 1412 |
+
"loss": 0.0116,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.502132499289167,
|
| 1417 |
+
"grad_norm": 0.2111271470785141,
|
| 1418 |
+
"learning_rate": 5.856644470155781e-05,
|
| 1419 |
+
"loss": 0.0194,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.502132499289167,
|
| 1424 |
+
"eval_loss": 0.046471014618873596,
|
| 1425 |
+
"eval_runtime": 207.0102,
|
| 1426 |
+
"eval_samples_per_second": 5.666,
|
| 1427 |
+
"eval_steps_per_second": 5.666,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.5172969386787982,
|
| 1432 |
+
"grad_norm": 0.33697161078453064,
|
| 1433 |
+
"learning_rate": 5.8044027450988546e-05,
|
| 1434 |
+
"loss": 0.0242,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.5324613780684295,
|
| 1439 |
+
"grad_norm": 0.2361498922109604,
|
| 1440 |
+
"learning_rate": 5.752070713371371e-05,
|
| 1441 |
+
"loss": 0.0164,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 2.547625817458061,
|
| 1446 |
+
"grad_norm": 0.25567626953125,
|
| 1447 |
+
"learning_rate": 5.699654250054662e-05,
|
| 1448 |
+
"loss": 0.0153,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.562790256847692,
|
| 1453 |
+
"grad_norm": 0.24401170015335083,
|
| 1454 |
+
"learning_rate": 5.647159239708809e-05,
|
| 1455 |
+
"loss": 0.0132,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.5779546962373234,
|
| 1460 |
+
"grad_norm": 0.2683306038379669,
|
| 1461 |
+
"learning_rate": 5.5945915757120146e-05,
|
| 1462 |
+
"loss": 0.0178,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 2.5779546962373234,
|
| 1467 |
+
"eval_loss": 0.04394778236746788,
|
| 1468 |
+
"eval_runtime": 199.3527,
|
| 1469 |
+
"eval_samples_per_second": 5.884,
|
| 1470 |
+
"eval_steps_per_second": 5.884,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.5931191356269547,
|
| 1475 |
+
"grad_norm": 0.54051673412323,
|
| 1476 |
+
"learning_rate": 5.5419571595989825e-05,
|
| 1477 |
+
"loss": 0.0211,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 2.608283575016586,
|
| 1482 |
+
"grad_norm": 0.23906239867210388,
|
| 1483 |
+
"learning_rate": 5.4892619003983734e-05,
|
| 1484 |
+
"loss": 0.0173,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 2.6234480144062173,
|
| 1489 |
+
"grad_norm": 0.07637752592563629,
|
| 1490 |
+
"learning_rate": 5.436511713969428e-05,
|
| 1491 |
+
"loss": 0.0127,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 2.6386124537958486,
|
| 1496 |
+
"grad_norm": 0.07885332405567169,
|
| 1497 |
+
"learning_rate": 5.383712522337817e-05,
|
| 1498 |
+
"loss": 0.02,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 2.65377689318548,
|
| 1503 |
+
"grad_norm": 0.47538188099861145,
|
| 1504 |
+
"learning_rate": 5.3308702530308076e-05,
|
| 1505 |
+
"loss": 0.0238,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.65377689318548,
|
| 1510 |
+
"eval_loss": 0.041050076484680176,
|
| 1511 |
+
"eval_runtime": 195.9057,
|
| 1512 |
+
"eval_samples_per_second": 5.988,
|
| 1513 |
+
"eval_steps_per_second": 5.988,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.6689413325751112,
|
| 1518 |
+
"grad_norm": 0.32186976075172424,
|
| 1519 |
+
"learning_rate": 5.2779908384118025e-05,
|
| 1520 |
+
"loss": 0.0208,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.6841057719647425,
|
| 1525 |
+
"grad_norm": 0.5302672982215881,
|
| 1526 |
+
"learning_rate": 5.22508021501434e-05,
|
| 1527 |
+
"loss": 0.0242,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.699270211354374,
|
| 1532 |
+
"grad_norm": 0.28542810678482056,
|
| 1533 |
+
"learning_rate": 5.1721443228756284e-05,
|
| 1534 |
+
"loss": 0.0162,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.714434650744005,
|
| 1539 |
+
"grad_norm": 0.11375605314970016,
|
| 1540 |
+
"learning_rate": 5.119189104869683e-05,
|
| 1541 |
+
"loss": 0.0176,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.729599090133637,
|
| 1546 |
+
"grad_norm": 0.24023477733135223,
|
| 1547 |
+
"learning_rate": 5.066220506040148e-05,
|
| 1548 |
+
"loss": 0.0181,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.729599090133637,
|
| 1553 |
+
"eval_loss": 0.04137849807739258,
|
| 1554 |
+
"eval_runtime": 193.9483,
|
| 1555 |
+
"eval_samples_per_second": 6.048,
|
| 1556 |
+
"eval_steps_per_second": 6.048,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.7447635295232677,
|
| 1561 |
+
"grad_norm": 0.19859518110752106,
|
| 1562 |
+
"learning_rate": 5.013244472932872e-05,
|
| 1563 |
+
"loss": 0.0223,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.7599279689128995,
|
| 1568 |
+
"grad_norm": 0.32186752557754517,
|
| 1569 |
+
"learning_rate": 4.960266952928316e-05,
|
| 1570 |
+
"loss": 0.0193,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.7750924083025303,
|
| 1575 |
+
"grad_norm": 0.4007152318954468,
|
| 1576 |
+
"learning_rate": 4.907293893573867e-05,
|
| 1577 |
+
"loss": 0.0172,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.790256847692162,
|
| 1582 |
+
"grad_norm": 0.26739656925201416,
|
| 1583 |
+
"learning_rate": 4.8543312419161396e-05,
|
| 1584 |
+
"loss": 0.0164,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.805421287081793,
|
| 1589 |
+
"grad_norm": 0.2896629571914673,
|
| 1590 |
+
"learning_rate": 4.8013849438333165e-05,
|
| 1591 |
+
"loss": 0.0128,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.805421287081793,
|
| 1596 |
+
"eval_loss": 0.04389198124408722,
|
| 1597 |
+
"eval_runtime": 192.7356,
|
| 1598 |
+
"eval_samples_per_second": 6.086,
|
| 1599 |
+
"eval_steps_per_second": 6.086,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.8205857264714247,
|
| 1604 |
+
"grad_norm": 0.5798066854476929,
|
| 1605 |
+
"learning_rate": 4.748460943367643e-05,
|
| 1606 |
+
"loss": 0.0179,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.8357501658610555,
|
| 1611 |
+
"grad_norm": 0.3237079083919525,
|
| 1612 |
+
"learning_rate": 4.695565182058113e-05,
|
| 1613 |
+
"loss": 0.0286,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.8509146052506873,
|
| 1618 |
+
"grad_norm": 0.2319541871547699,
|
| 1619 |
+
"learning_rate": 4.642703598273431e-05,
|
| 1620 |
+
"loss": 0.0186,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.8660790446403186,
|
| 1625 |
+
"grad_norm": 0.32056906819343567,
|
| 1626 |
+
"learning_rate": 4.589882126545352e-05,
|
| 1627 |
+
"loss": 0.0187,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.88124348402995,
|
| 1632 |
+
"grad_norm": 0.27325454354286194,
|
| 1633 |
+
"learning_rate": 4.537106696902425e-05,
|
| 1634 |
+
"loss": 0.0287,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.88124348402995,
|
| 1639 |
+
"eval_loss": 0.04099781811237335,
|
| 1640 |
+
"eval_runtime": 191.609,
|
| 1641 |
+
"eval_samples_per_second": 6.122,
|
| 1642 |
+
"eval_steps_per_second": 6.122,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.896407923419581,
|
| 1647 |
+
"grad_norm": 1.0726760625839233,
|
| 1648 |
+
"learning_rate": 4.484383234204266e-05,
|
| 1649 |
+
"loss": 0.0261,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.9115723628092125,
|
| 1654 |
+
"grad_norm": 0.3901512026786804,
|
| 1655 |
+
"learning_rate": 4.4317176574763935e-05,
|
| 1656 |
+
"loss": 0.0208,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.926736802198844,
|
| 1661 |
+
"grad_norm": 0.19363577663898468,
|
| 1662 |
+
"learning_rate": 4.3791158792457334e-05,
|
| 1663 |
+
"loss": 0.0219,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.941901241588475,
|
| 1668 |
+
"grad_norm": 0.21966907382011414,
|
| 1669 |
+
"learning_rate": 4.3265838048768334e-05,
|
| 1670 |
+
"loss": 0.0194,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.9570656809781064,
|
| 1675 |
+
"grad_norm": 0.31120771169662476,
|
| 1676 |
+
"learning_rate": 4.274127331908915e-05,
|
| 1677 |
+
"loss": 0.0202,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.9570656809781064,
|
| 1682 |
+
"eval_loss": 0.041776422411203384,
|
| 1683 |
+
"eval_runtime": 190.7741,
|
| 1684 |
+
"eval_samples_per_second": 6.149,
|
| 1685 |
+
"eval_steps_per_second": 6.149,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 2.9722301203677377,
|
| 1690 |
+
"grad_norm": 0.149943545460701,
|
| 1691 |
+
"learning_rate": 4.221752349393758e-05,
|
| 1692 |
+
"loss": 0.0123,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 2.987394559757369,
|
| 1697 |
+
"grad_norm": 0.24167421460151672,
|
| 1698 |
+
"learning_rate": 4.1694647372345886e-05,
|
| 1699 |
+
"loss": 0.0241,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 3.0025589991470003,
|
| 1704 |
+
"grad_norm": 0.09040270000696182,
|
| 1705 |
+
"learning_rate": 4.117270365525946e-05,
|
| 1706 |
+
"loss": 0.0157,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 3.0177234385366316,
|
| 1711 |
+
"grad_norm": 0.05640542134642601,
|
| 1712 |
+
"learning_rate": 4.065175093894694e-05,
|
| 1713 |
+
"loss": 0.0106,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 3.032887877926263,
|
| 1718 |
+
"grad_norm": 0.1316869705915451,
|
| 1719 |
+
"learning_rate": 4.013184770842167e-05,
|
| 1720 |
+
"loss": 0.011,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 3.032887877926263,
|
| 1725 |
+
"eval_loss": 0.042993590235710144,
|
| 1726 |
+
"eval_runtime": 190.4338,
|
| 1727 |
+
"eval_samples_per_second": 6.16,
|
| 1728 |
+
"eval_steps_per_second": 6.16,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 3.048052317315894,
|
| 1733 |
+
"grad_norm": 0.09240477532148361,
|
| 1734 |
+
"learning_rate": 3.9613052330876064e-05,
|
| 1735 |
+
"loss": 0.0117,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 3.0632167567055255,
|
| 1740 |
+
"grad_norm": 0.5564406514167786,
|
| 1741 |
+
"learning_rate": 3.909542304912881e-05,
|
| 1742 |
+
"loss": 0.0114,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 3.078381196095157,
|
| 1747 |
+
"grad_norm": 0.06670588254928589,
|
| 1748 |
+
"learning_rate": 3.857901797508628e-05,
|
| 1749 |
+
"loss": 0.0131,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 3.093545635484788,
|
| 1754 |
+
"grad_norm": 0.21447496116161346,
|
| 1755 |
+
"learning_rate": 3.80638950832186e-05,
|
| 1756 |
+
"loss": 0.0111,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 3.1087100748744194,
|
| 1761 |
+
"grad_norm": 0.2611368000507355,
|
| 1762 |
+
"learning_rate": 3.7550112204051014e-05,
|
| 1763 |
+
"loss": 0.005,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 3.1087100748744194,
|
| 1768 |
+
"eval_loss": 0.048680998384952545,
|
| 1769 |
+
"eval_runtime": 190.3304,
|
| 1770 |
+
"eval_samples_per_second": 6.163,
|
| 1771 |
+
"eval_steps_per_second": 6.163,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 3.1238745142640507,
|
| 1776 |
+
"grad_norm": 0.06609263271093369,
|
| 1777 |
+
"learning_rate": 3.703772701767167e-05,
|
| 1778 |
+
"loss": 0.0058,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 3.139038953653682,
|
| 1783 |
+
"grad_norm": 0.1730610877275467,
|
| 1784 |
+
"learning_rate": 3.652679704725596e-05,
|
| 1785 |
+
"loss": 0.0053,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 3.1542033930433133,
|
| 1790 |
+
"grad_norm": 0.15803933143615723,
|
| 1791 |
+
"learning_rate": 3.601737965260882e-05,
|
| 1792 |
+
"loss": 0.0093,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 3.1693678324329446,
|
| 1797 |
+
"grad_norm": 0.16534733772277832,
|
| 1798 |
+
"learning_rate": 3.550953202372503e-05,
|
| 1799 |
+
"loss": 0.0046,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 3.184532271822576,
|
| 1804 |
+
"grad_norm": 0.25180765986442566,
|
| 1805 |
+
"learning_rate": 3.500331117436895e-05,
|
| 1806 |
+
"loss": 0.0045,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 3.184532271822576,
|
| 1811 |
+
"eval_loss": 0.0501817911863327,
|
| 1812 |
+
"eval_runtime": 190.1913,
|
| 1813 |
+
"eval_samples_per_second": 6.167,
|
| 1814 |
+
"eval_steps_per_second": 6.167,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.1996967112122072,
|
| 1819 |
+
"grad_norm": 0.143573597073555,
|
| 1820 |
+
"learning_rate": 3.4498773935673626e-05,
|
| 1821 |
+
"loss": 0.0034,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 3.2148611506018385,
|
| 1826 |
+
"grad_norm": 0.1678372025489807,
|
| 1827 |
+
"learning_rate": 3.399597694976081e-05,
|
| 1828 |
+
"loss": 0.0081,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 3.23002558999147,
|
| 1833 |
+
"grad_norm": 0.46680811047554016,
|
| 1834 |
+
"learning_rate": 3.349497666338187e-05,
|
| 1835 |
+
"loss": 0.0117,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 3.245190029381101,
|
| 1840 |
+
"grad_norm": 0.32169198989868164,
|
| 1841 |
+
"learning_rate": 3.299582932158085e-05,
|
| 1842 |
+
"loss": 0.0125,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 3.260354468770733,
|
| 1847 |
+
"grad_norm": 0.20941679179668427,
|
| 1848 |
+
"learning_rate": 3.2498590961379996e-05,
|
| 1849 |
+
"loss": 0.0072,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 3.260354468770733,
|
| 1854 |
+
"eval_loss": 0.04960820451378822,
|
| 1855 |
+
"eval_runtime": 189.4256,
|
| 1856 |
+
"eval_samples_per_second": 6.192,
|
| 1857 |
+
"eval_steps_per_second": 6.192,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 3.2755189081603637,
|
| 1862 |
+
"grad_norm": 0.17324012517929077,
|
| 1863 |
+
"learning_rate": 3.200331740548887e-05,
|
| 1864 |
+
"loss": 0.0083,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.2906833475499955,
|
| 1869 |
+
"grad_norm": 0.5363154411315918,
|
| 1870 |
+
"learning_rate": 3.1510064256037274e-05,
|
| 1871 |
+
"loss": 0.0136,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 3.3058477869396263,
|
| 1876 |
+
"grad_norm": 0.03524131327867508,
|
| 1877 |
+
"learning_rate": 3.1018886888333065e-05,
|
| 1878 |
+
"loss": 0.0091,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 3.321012226329258,
|
| 1883 |
+
"grad_norm": 0.24780172109603882,
|
| 1884 |
+
"learning_rate": 3.052984044464548e-05,
|
| 1885 |
+
"loss": 0.0088,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 3.3361766657188894,
|
| 1890 |
+
"grad_norm": 0.07167384773492813,
|
| 1891 |
+
"learning_rate": 3.0042979828014496e-05,
|
| 1892 |
+
"loss": 0.0098,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 3.3361766657188894,
|
| 1897 |
+
"eval_loss": 0.04823986068367958,
|
| 1898 |
+
"eval_runtime": 188.5523,
|
| 1899 |
+
"eval_samples_per_second": 6.221,
|
| 1900 |
+
"eval_steps_per_second": 6.221,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 3.3513411051085207,
|
| 1905 |
+
"grad_norm": 0.10964875668287277,
|
| 1906 |
+
"learning_rate": 2.9558359696087152e-05,
|
| 1907 |
+
"loss": 0.0114,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 3.366505544498152,
|
| 1912 |
+
"grad_norm": 0.4698887765407562,
|
| 1913 |
+
"learning_rate": 2.9076034454981332e-05,
|
| 1914 |
+
"loss": 0.0099,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 3.3816699838877833,
|
| 1919 |
+
"grad_norm": 0.4254396855831146,
|
| 1920 |
+
"learning_rate": 2.8596058253177932e-05,
|
| 1921 |
+
"loss": 0.0073,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 3.3968344232774146,
|
| 1926 |
+
"grad_norm": 0.22847697138786316,
|
| 1927 |
+
"learning_rate": 2.811848497544175e-05,
|
| 1928 |
+
"loss": 0.0109,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 3.411998862667046,
|
| 1933 |
+
"grad_norm": 0.08946174383163452,
|
| 1934 |
+
"learning_rate": 2.764336823677216e-05,
|
| 1935 |
+
"loss": 0.0089,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 3.411998862667046,
|
| 1940 |
+
"eval_loss": 0.049223024398088455,
|
| 1941 |
+
"eval_runtime": 188.3627,
|
| 1942 |
+
"eval_samples_per_second": 6.227,
|
| 1943 |
+
"eval_steps_per_second": 6.227,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 3.427163302056677,
|
| 1948 |
+
"grad_norm": 0.2524348497390747,
|
| 1949 |
+
"learning_rate": 2.717076137638388e-05,
|
| 1950 |
+
"loss": 0.0077,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 3.4423277414463085,
|
| 1955 |
+
"grad_norm": 0.3513559401035309,
|
| 1956 |
+
"learning_rate": 2.6700717451719066e-05,
|
| 1957 |
+
"loss": 0.013,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 3.45749218083594,
|
| 1962 |
+
"grad_norm": 0.35712215304374695,
|
| 1963 |
+
"learning_rate": 2.6233289232490447e-05,
|
| 1964 |
+
"loss": 0.0095,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 3.472656620225571,
|
| 1969 |
+
"grad_norm": 0.06787083297967911,
|
| 1970 |
+
"learning_rate": 2.5768529194757474e-05,
|
| 1971 |
+
"loss": 0.006,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 3.4878210596152024,
|
| 1976 |
+
"grad_norm": 0.028745301067829132,
|
| 1977 |
+
"learning_rate": 2.5306489515034713e-05,
|
| 1978 |
+
"loss": 0.0072,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 3.4878210596152024,
|
| 1983 |
+
"eval_loss": 0.04863268509507179,
|
| 1984 |
+
"eval_runtime": 188.4036,
|
| 1985 |
+
"eval_samples_per_second": 6.226,
|
| 1986 |
+
"eval_steps_per_second": 6.226,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 3.5029854990048337,
|
| 1991 |
+
"grad_norm": 0.26812678575515747,
|
| 1992 |
+
"learning_rate": 2.484722206443455e-05,
|
| 1993 |
+
"loss": 0.0088,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 3.518149938394465,
|
| 1998 |
+
"grad_norm": 0.04494244605302811,
|
| 1999 |
+
"learning_rate": 2.4390778402843605e-05,
|
| 2000 |
+
"loss": 0.0105,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.5333143777840963,
|
| 2005 |
+
"grad_norm": 0.2933897078037262,
|
| 2006 |
+
"learning_rate": 2.3937209773134472e-05,
|
| 2007 |
+
"loss": 0.0072,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.5484788171737276,
|
| 2012 |
+
"grad_norm": 0.32120901346206665,
|
| 2013 |
+
"learning_rate": 2.3486567095412864e-05,
|
| 2014 |
+
"loss": 0.0084,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 3.563643256563359,
|
| 2019 |
+
"grad_norm": 0.6362977027893066,
|
| 2020 |
+
"learning_rate": 2.3038900961301053e-05,
|
| 2021 |
+
"loss": 0.0116,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 3.563643256563359,
|
| 2026 |
+
"eval_loss": 0.04956178739666939,
|
| 2027 |
+
"eval_runtime": 188.2167,
|
| 2028 |
+
"eval_samples_per_second": 6.232,
|
| 2029 |
+
"eval_steps_per_second": 6.232,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 3.57880769595299,
|
| 2034 |
+
"grad_norm": 0.03769369050860405,
|
| 2035 |
+
"learning_rate": 2.259426162825819e-05,
|
| 2036 |
+
"loss": 0.0068,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 3.5939721353426215,
|
| 2041 |
+
"grad_norm": 0.4940986931324005,
|
| 2042 |
+
"learning_rate": 2.215269901393805e-05,
|
| 2043 |
+
"loss": 0.0122,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 3.609136574732253,
|
| 2048 |
+
"grad_norm": 0.11686809360980988,
|
| 2049 |
+
"learning_rate": 2.1714262690585192e-05,
|
| 2050 |
+
"loss": 0.007,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 3.624301014121884,
|
| 2055 |
+
"grad_norm": 0.11242389678955078,
|
| 2056 |
+
"learning_rate": 2.1279001879469424e-05,
|
| 2057 |
+
"loss": 0.0058,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.6394654535115154,
|
| 2062 |
+
"grad_norm": 0.25813475251197815,
|
| 2063 |
+
"learning_rate": 2.084696544536025e-05,
|
| 2064 |
+
"loss": 0.0094,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 3.6394654535115154,
|
| 2069 |
+
"eval_loss": 0.0489325188100338,
|
| 2070 |
+
"eval_runtime": 188.2757,
|
| 2071 |
+
"eval_samples_per_second": 6.23,
|
| 2072 |
+
"eval_steps_per_second": 6.23,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 3.6546298929011467,
|
| 2077 |
+
"grad_norm": 0.05024724453687668,
|
| 2078 |
+
"learning_rate": 2.0418201891040778e-05,
|
| 2079 |
+
"loss": 0.0066,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 3.669794332290778,
|
| 2084 |
+
"grad_norm": 0.07094204425811768,
|
| 2085 |
+
"learning_rate": 1.9992759351862772e-05,
|
| 2086 |
+
"loss": 0.015,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 3.6849587716804093,
|
| 2091 |
+
"grad_norm": 0.21597981452941895,
|
| 2092 |
+
"learning_rate": 1.9570685590342463e-05,
|
| 2093 |
+
"loss": 0.0071,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 3.7001232110700406,
|
| 2098 |
+
"grad_norm": 0.4047929644584656,
|
| 2099 |
+
"learning_rate": 1.9152027990798748e-05,
|
| 2100 |
+
"loss": 0.0092,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 3.715287650459672,
|
| 2105 |
+
"grad_norm": 1.1898387670516968,
|
| 2106 |
+
"learning_rate": 1.8736833554033263e-05,
|
| 2107 |
+
"loss": 0.0055,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 3.715287650459672,
|
| 2112 |
+
"eval_loss": 0.050134897232055664,
|
| 2113 |
+
"eval_runtime": 187.4638,
|
| 2114 |
+
"eval_samples_per_second": 6.257,
|
| 2115 |
+
"eval_steps_per_second": 6.257,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.7304520898493037,
|
| 2120 |
+
"grad_norm": 0.17783983051776886,
|
| 2121 |
+
"learning_rate": 1.8325148892054093e-05,
|
| 2122 |
+
"loss": 0.0068,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.7456165292389345,
|
| 2127 |
+
"grad_norm": 0.0921979695558548,
|
| 2128 |
+
"learning_rate": 1.7917020222842662e-05,
|
| 2129 |
+
"loss": 0.0066,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.7607809686285663,
|
| 2134 |
+
"grad_norm": 0.07260593771934509,
|
| 2135 |
+
"learning_rate": 1.751249336516513e-05,
|
| 2136 |
+
"loss": 0.0083,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.775945408018197,
|
| 2141 |
+
"grad_norm": 0.07632392644882202,
|
| 2142 |
+
"learning_rate": 1.7111613733428522e-05,
|
| 2143 |
+
"loss": 0.0078,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.791109847407829,
|
| 2148 |
+
"grad_norm": 0.1986379325389862,
|
| 2149 |
+
"learning_rate": 1.671442633258218e-05,
|
| 2150 |
+
"loss": 0.0095,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.791109847407829,
|
| 2155 |
+
"eval_loss": 0.052877526730298996,
|
| 2156 |
+
"eval_runtime": 187.1604,
|
| 2157 |
+
"eval_samples_per_second": 6.267,
|
| 2158 |
+
"eval_steps_per_second": 6.267,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 3.8062742867974597,
|
| 2163 |
+
"grad_norm": 0.33867862820625305,
|
| 2164 |
+
"learning_rate": 1.6320975753065453e-05,
|
| 2165 |
+
"loss": 0.0084,
|
| 2166 |
+
"step": 2510
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 3.8214387261870915,
|
| 2170 |
+
"grad_norm": 0.5895967483520508,
|
| 2171 |
+
"learning_rate": 1.5931306165801452e-05,
|
| 2172 |
+
"loss": 0.0071,
|
| 2173 |
+
"step": 2520
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 3.8366031655767223,
|
| 2177 |
+
"grad_norm": 0.15865935385227203,
|
| 2178 |
+
"learning_rate": 1.554546131723848e-05,
|
| 2179 |
+
"loss": 0.0064,
|
| 2180 |
+
"step": 2530
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 3.851767604966354,
|
| 2184 |
+
"grad_norm": 0.7080567479133606,
|
| 2185 |
+
"learning_rate": 1.5163484524438516e-05,
|
| 2186 |
+
"loss": 0.0066,
|
| 2187 |
+
"step": 2540
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 3.8669320443559854,
|
| 2191 |
+
"grad_norm": 0.34300854802131653,
|
| 2192 |
+
"learning_rate": 1.4785418670214496e-05,
|
| 2193 |
+
"loss": 0.0113,
|
| 2194 |
+
"step": 2550
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 3.8669320443559854,
|
| 2198 |
+
"eval_loss": 0.05170406401157379,
|
| 2199 |
+
"eval_runtime": 187.6804,
|
| 2200 |
+
"eval_samples_per_second": 6.25,
|
| 2201 |
+
"eval_steps_per_second": 6.25,
|
| 2202 |
+
"step": 2550
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 3.8820964837456167,
|
| 2206 |
+
"grad_norm": 0.03344808518886566,
|
| 2207 |
+
"learning_rate": 1.4411306198315777e-05,
|
| 2208 |
+
"loss": 0.0071,
|
| 2209 |
+
"step": 2560
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 3.897260923135248,
|
| 2213 |
+
"grad_norm": 0.22047798335552216,
|
| 2214 |
+
"learning_rate": 1.4041189108663421e-05,
|
| 2215 |
+
"loss": 0.0072,
|
| 2216 |
+
"step": 2570
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 3.9124253625248793,
|
| 2220 |
+
"grad_norm": 0.36693868041038513,
|
| 2221 |
+
"learning_rate": 1.3675108952634824e-05,
|
| 2222 |
+
"loss": 0.0041,
|
| 2223 |
+
"step": 2580
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 3.9275898019145106,
|
| 2227 |
+
"grad_norm": 0.6838831901550293,
|
| 2228 |
+
"learning_rate": 1.3313106828399147e-05,
|
| 2229 |
+
"loss": 0.01,
|
| 2230 |
+
"step": 2590
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 3.942754241304142,
|
| 2234 |
+
"grad_norm": 0.04084847494959831,
|
| 2235 |
+
"learning_rate": 1.2955223376303205e-05,
|
| 2236 |
+
"loss": 0.0042,
|
| 2237 |
+
"step": 2600
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 3.942754241304142,
|
| 2241 |
+
"eval_loss": 0.05176025629043579,
|
| 2242 |
+
"eval_runtime": 187.7358,
|
| 2243 |
+
"eval_samples_per_second": 6.248,
|
| 2244 |
+
"eval_steps_per_second": 6.248,
|
| 2245 |
+
"step": 2600
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 3.957918680693773,
|
| 2249 |
+
"grad_norm": 0.13362419605255127,
|
| 2250 |
+
"learning_rate": 1.2601498774309112e-05,
|
| 2251 |
+
"loss": 0.006,
|
| 2252 |
+
"step": 2610
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 3.9730831200834045,
|
| 2256 |
+
"grad_norm": 0.21809060871601105,
|
| 2257 |
+
"learning_rate": 1.2251972733483612e-05,
|
| 2258 |
+
"loss": 0.0086,
|
| 2259 |
+
"step": 2620
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 3.9882475594730358,
|
| 2263 |
+
"grad_norm": 0.6125285625457764,
|
| 2264 |
+
"learning_rate": 1.19066844935399e-05,
|
| 2265 |
+
"loss": 0.0048,
|
| 2266 |
+
"step": 2630
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 4.003411998862667,
|
| 2270 |
+
"grad_norm": 0.09248276054859161,
|
| 2271 |
+
"learning_rate": 1.156567281843241e-05,
|
| 2272 |
+
"loss": 0.0059,
|
| 2273 |
+
"step": 2640
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 4.018576438252298,
|
| 2277 |
+
"grad_norm": 0.17377474904060364,
|
| 2278 |
+
"learning_rate": 1.1228975992004842e-05,
|
| 2279 |
+
"loss": 0.0021,
|
| 2280 |
+
"step": 2650
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 4.018576438252298,
|
| 2284 |
+
"eval_loss": 0.053896982222795486,
|
| 2285 |
+
"eval_runtime": 187.5167,
|
| 2286 |
+
"eval_samples_per_second": 6.255,
|
| 2287 |
+
"eval_steps_per_second": 6.255,
|
| 2288 |
+
"step": 2650
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 4.03374087764193,
|
| 2292 |
+
"grad_norm": 0.09760443866252899,
|
| 2293 |
+
"learning_rate": 1.0896631813692377e-05,
|
| 2294 |
+
"loss": 0.0032,
|
| 2295 |
+
"step": 2660
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 4.048905317031561,
|
| 2299 |
+
"grad_norm": 0.09826330095529556,
|
| 2300 |
+
"learning_rate": 1.0568677594277899e-05,
|
| 2301 |
+
"loss": 0.0035,
|
| 2302 |
+
"step": 2670
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 4.064069756421192,
|
| 2306 |
+
"grad_norm": 0.029800906777381897,
|
| 2307 |
+
"learning_rate": 1.0245150151703509e-05,
|
| 2308 |
+
"loss": 0.0023,
|
| 2309 |
+
"step": 2680
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 4.079234195810824,
|
| 2313 |
+
"grad_norm": 0.13375523686408997,
|
| 2314 |
+
"learning_rate": 9.926085806936918e-06,
|
| 2315 |
+
"loss": 0.0029,
|
| 2316 |
+
"step": 2690
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 4.094398635200455,
|
| 2320 |
+
"grad_norm": 0.26318782567977905,
|
| 2321 |
+
"learning_rate": 9.611520379894068e-06,
|
| 2322 |
+
"loss": 0.0027,
|
| 2323 |
+
"step": 2700
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 4.094398635200455,
|
| 2327 |
+
"eval_loss": 0.0573224201798439,
|
| 2328 |
+
"eval_runtime": 187.1068,
|
| 2329 |
+
"eval_samples_per_second": 6.269,
|
| 2330 |
+
"eval_steps_per_second": 6.269,
|
| 2331 |
+
"step": 2700
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 4.109563074590087,
|
| 2335 |
+
"grad_norm": 0.11672820150852203,
|
| 2336 |
+
"learning_rate": 9.301489185417578e-06,
|
| 2337 |
+
"loss": 0.0036,
|
| 2338 |
+
"step": 2710
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 4.1247275139797175,
|
| 2342 |
+
"grad_norm": 0.06662098318338394,
|
| 2343 |
+
"learning_rate": 8.996027029312314e-06,
|
| 2344 |
+
"loss": 0.0018,
|
| 2345 |
+
"step": 2720
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 4.139891953369349,
|
| 2349 |
+
"grad_norm": 0.18935194611549377,
|
| 2350 |
+
"learning_rate": 8.695168204437721e-06,
|
| 2351 |
+
"loss": 0.0065,
|
| 2352 |
+
"step": 2730
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 4.15505639275898,
|
| 2356 |
+
"grad_norm": 0.212269127368927,
|
| 2357 |
+
"learning_rate": 8.398946486858029e-06,
|
| 2358 |
+
"loss": 0.0027,
|
| 2359 |
+
"step": 2740
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 4.170220832148612,
|
| 2363 |
+
"grad_norm": 0.0438799224793911,
|
| 2364 |
+
"learning_rate": 8.107395132050333e-06,
|
| 2365 |
+
"loss": 0.0017,
|
| 2366 |
+
"step": 2750
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 4.170220832148612,
|
| 2370 |
+
"eval_loss": 0.058968957513570786,
|
| 2371 |
+
"eval_runtime": 186.8676,
|
| 2372 |
+
"eval_samples_per_second": 6.277,
|
| 2373 |
+
"eval_steps_per_second": 6.277,
|
| 2374 |
+
"step": 2750
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 4.185385271538243,
|
| 2378 |
+
"grad_norm": 0.09194748103618622,
|
| 2379 |
+
"learning_rate": 7.820546871171142e-06,
|
| 2380 |
+
"loss": 0.0034,
|
| 2381 |
+
"step": 2760
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 4.200549710927874,
|
| 2385 |
+
"grad_norm": 0.07000330835580826,
|
| 2386 |
+
"learning_rate": 7.5384339073818145e-06,
|
| 2387 |
+
"loss": 0.0031,
|
| 2388 |
+
"step": 2770
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 4.215714150317505,
|
| 2392 |
+
"grad_norm": 0.0696445107460022,
|
| 2393 |
+
"learning_rate": 7.261087912233228e-06,
|
| 2394 |
+
"loss": 0.0047,
|
| 2395 |
+
"step": 2780
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 4.230878589707137,
|
| 2399 |
+
"grad_norm": 0.15083633363246918,
|
| 2400 |
+
"learning_rate": 6.988540022110235e-06,
|
| 2401 |
+
"loss": 0.0033,
|
| 2402 |
+
"step": 2790
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 4.246043029096768,
|
| 2406 |
+
"grad_norm": 0.18565095961093903,
|
| 2407 |
+
"learning_rate": 6.720820834735969e-06,
|
| 2408 |
+
"loss": 0.0033,
|
| 2409 |
+
"step": 2800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 4.246043029096768,
|
| 2413 |
+
"eval_loss": 0.060299091041088104,
|
| 2414 |
+
"eval_runtime": 186.5266,
|
| 2415 |
+
"eval_samples_per_second": 6.289,
|
| 2416 |
+
"eval_steps_per_second": 6.289,
|
| 2417 |
+
"step": 2800
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 4.2612074684864,
|
| 2421 |
+
"grad_norm": 0.2135116308927536,
|
| 2422 |
+
"learning_rate": 6.457960405736968e-06,
|
| 2423 |
+
"loss": 0.0052,
|
| 2424 |
+
"step": 2810
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 4.2763719078760305,
|
| 2428 |
+
"grad_norm": 0.030328113585710526,
|
| 2429 |
+
"learning_rate": 6.199988245268778e-06,
|
| 2430 |
+
"loss": 0.0019,
|
| 2431 |
+
"step": 2820
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 4.291536347265662,
|
| 2435 |
+
"grad_norm": 0.35592690110206604,
|
| 2436 |
+
"learning_rate": 5.946933314703157e-06,
|
| 2437 |
+
"loss": 0.0017,
|
| 2438 |
+
"step": 2830
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 4.306700786655293,
|
| 2442 |
+
"grad_norm": 0.027882764115929604,
|
| 2443 |
+
"learning_rate": 5.698824023376531e-06,
|
| 2444 |
+
"loss": 0.002,
|
| 2445 |
+
"step": 2840
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 4.321865226044925,
|
| 2449 |
+
"grad_norm": 0.12716230750083923,
|
| 2450 |
+
"learning_rate": 5.455688225400802e-06,
|
| 2451 |
+
"loss": 0.003,
|
| 2452 |
+
"step": 2850
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 4.321865226044925,
|
| 2456 |
+
"eval_loss": 0.06180414929986,
|
| 2457 |
+
"eval_runtime": 186.8078,
|
| 2458 |
+
"eval_samples_per_second": 6.279,
|
| 2459 |
+
"eval_steps_per_second": 6.279,
|
| 2460 |
+
"step": 2850
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 4.337029665434556,
|
| 2464 |
+
"grad_norm": 0.05450417846441269,
|
| 2465 |
+
"learning_rate": 5.217553216536098e-06,
|
| 2466 |
+
"loss": 0.0024,
|
| 2467 |
+
"step": 2860
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 4.3521941048241874,
|
| 2471 |
+
"grad_norm": 0.2045290321111679,
|
| 2472 |
+
"learning_rate": 4.984445731126542e-06,
|
| 2473 |
+
"loss": 0.0045,
|
| 2474 |
+
"step": 2870
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 4.367358544213818,
|
| 2478 |
+
"grad_norm": 0.022383777424693108,
|
| 2479 |
+
"learning_rate": 4.756391939098853e-06,
|
| 2480 |
+
"loss": 0.0013,
|
| 2481 |
+
"step": 2880
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 4.38252298360345,
|
| 2485 |
+
"grad_norm": 0.011135186068713665,
|
| 2486 |
+
"learning_rate": 4.533417443024374e-06,
|
| 2487 |
+
"loss": 0.0059,
|
| 2488 |
+
"step": 2890
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 4.397687422993081,
|
| 2492 |
+
"grad_norm": 0.04015190526843071,
|
| 2493 |
+
"learning_rate": 4.315547275244769e-06,
|
| 2494 |
+
"loss": 0.0013,
|
| 2495 |
+
"step": 2900
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 4.397687422993081,
|
| 2499 |
+
"eval_loss": 0.0623171404004097,
|
| 2500 |
+
"eval_runtime": 186.7545,
|
| 2501 |
+
"eval_samples_per_second": 6.281,
|
| 2502 |
+
"eval_steps_per_second": 6.281,
|
| 2503 |
+
"step": 2900
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 4.412851862382713,
|
| 2507 |
+
"grad_norm": 0.21536949276924133,
|
| 2508 |
+
"learning_rate": 4.10280589506179e-06,
|
| 2509 |
+
"loss": 0.0035,
|
| 2510 |
+
"step": 2910
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 4.4280163017723435,
|
| 2514 |
+
"grad_norm": 0.08297796547412872,
|
| 2515 |
+
"learning_rate": 3.895217185991312e-06,
|
| 2516 |
+
"loss": 0.0021,
|
| 2517 |
+
"step": 2920
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 4.443180741161975,
|
| 2521 |
+
"grad_norm": 0.25166183710098267,
|
| 2522 |
+
"learning_rate": 3.692804453082038e-06,
|
| 2523 |
+
"loss": 0.0056,
|
| 2524 |
+
"step": 2930
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 4.458345180551606,
|
| 2528 |
+
"grad_norm": 0.12861423194408417,
|
| 2529 |
+
"learning_rate": 3.495590420299194e-06,
|
| 2530 |
+
"loss": 0.0016,
|
| 2531 |
+
"step": 2940
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 4.473509619941238,
|
| 2535 |
+
"grad_norm": 0.8641133308410645,
|
| 2536 |
+
"learning_rate": 3.3035972279733207e-06,
|
| 2537 |
+
"loss": 0.003,
|
| 2538 |
+
"step": 2950
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 4.473509619941238,
|
| 2542 |
+
"eval_loss": 0.06252659857273102,
|
| 2543 |
+
"eval_runtime": 186.6625,
|
| 2544 |
+
"eval_samples_per_second": 6.284,
|
| 2545 |
+
"eval_steps_per_second": 6.284,
|
| 2546 |
+
"step": 2950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 4.488674059330869,
|
| 2550 |
+
"grad_norm": 0.05727919191122055,
|
| 2551 |
+
"learning_rate": 3.116846430314796e-06,
|
| 2552 |
+
"loss": 0.0016,
|
| 2553 |
+
"step": 2960
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 4.5038384987205005,
|
| 2557 |
+
"grad_norm": 0.019385578110814095,
|
| 2558 |
+
"learning_rate": 2.9353589929939087e-06,
|
| 2559 |
+
"loss": 0.0011,
|
| 2560 |
+
"step": 2970
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 4.519002938110132,
|
| 2564 |
+
"grad_norm": 0.07699675858020782,
|
| 2565 |
+
"learning_rate": 2.7591552907872574e-06,
|
| 2566 |
+
"loss": 0.0022,
|
| 2567 |
+
"step": 2980
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 4.534167377499763,
|
| 2571 |
+
"grad_norm": 0.04615270346403122,
|
| 2572 |
+
"learning_rate": 2.5882551052902883e-06,
|
| 2573 |
+
"loss": 0.0035,
|
| 2574 |
+
"step": 2990
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 4.549331816889394,
|
| 2578 |
+
"grad_norm": 0.5508703589439392,
|
| 2579 |
+
"learning_rate": 2.4226776226965453e-06,
|
| 2580 |
+
"loss": 0.0036,
|
| 2581 |
+
"step": 3000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 4.549331816889394,
|
| 2585 |
+
"eval_loss": 0.06311533600091934,
|
| 2586 |
+
"eval_runtime": 186.2603,
|
| 2587 |
+
"eval_samples_per_second": 6.298,
|
| 2588 |
+
"eval_steps_per_second": 6.298,
|
| 2589 |
+
"step": 3000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 4.564496256279026,
|
| 2593 |
+
"grad_norm": 0.025140024721622467,
|
| 2594 |
+
"learning_rate": 2.262441431643697e-06,
|
| 2595 |
+
"loss": 0.0062,
|
| 2596 |
+
"step": 3010
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 4.579660695668657,
|
| 2600 |
+
"grad_norm": 0.018112068995833397,
|
| 2601 |
+
"learning_rate": 2.1075645211266927e-06,
|
| 2602 |
+
"loss": 0.001,
|
| 2603 |
+
"step": 3020
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 4.594825135058288,
|
| 2607 |
+
"grad_norm": 0.22902579605579376,
|
| 2608 |
+
"learning_rate": 1.9580642784782053e-06,
|
| 2609 |
+
"loss": 0.0028,
|
| 2610 |
+
"step": 3030
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 4.60998957444792,
|
| 2614 |
+
"grad_norm": 0.021765662357211113,
|
| 2615 |
+
"learning_rate": 1.813957487416651e-06,
|
| 2616 |
+
"loss": 0.0011,
|
| 2617 |
+
"step": 3040
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 4.625154013837551,
|
| 2621 |
+
"grad_norm": 0.30804678797721863,
|
| 2622 |
+
"learning_rate": 1.6752603261619315e-06,
|
| 2623 |
+
"loss": 0.0017,
|
| 2624 |
+
"step": 3050
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 4.625154013837551,
|
| 2628 |
+
"eval_loss": 0.06340394914150238,
|
| 2629 |
+
"eval_runtime": 186.2512,
|
| 2630 |
+
"eval_samples_per_second": 6.298,
|
| 2631 |
+
"eval_steps_per_second": 6.298,
|
| 2632 |
+
"step": 3050
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 4.640318453227183,
|
| 2636 |
+
"grad_norm": 0.058663006871938705,
|
| 2637 |
+
"learning_rate": 1.541988365619207e-06,
|
| 2638 |
+
"loss": 0.0043,
|
| 2639 |
+
"step": 3060
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 4.6554828926168135,
|
| 2643 |
+
"grad_norm": 0.22114038467407227,
|
| 2644 |
+
"learning_rate": 1.4141565676307865e-06,
|
| 2645 |
+
"loss": 0.0033,
|
| 2646 |
+
"step": 3070
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 4.670647332006445,
|
| 2650 |
+
"grad_norm": 0.013990496285259724,
|
| 2651 |
+
"learning_rate": 1.291779283296468e-06,
|
| 2652 |
+
"loss": 0.0018,
|
| 2653 |
+
"step": 3080
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 4.685811771396076,
|
| 2657 |
+
"grad_norm": 0.06152665242552757,
|
| 2658 |
+
"learning_rate": 1.1748702513623922e-06,
|
| 2659 |
+
"loss": 0.0027,
|
| 2660 |
+
"step": 3090
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 4.700976210785708,
|
| 2664 |
+
"grad_norm": 0.13100837171077728,
|
| 2665 |
+
"learning_rate": 1.0634425966786155e-06,
|
| 2666 |
+
"loss": 0.0023,
|
| 2667 |
+
"step": 3100
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 4.700976210785708,
|
| 2671 |
+
"eval_loss": 0.06349016726016998,
|
| 2672 |
+
"eval_runtime": 186.2271,
|
| 2673 |
+
"eval_samples_per_second": 6.299,
|
| 2674 |
+
"eval_steps_per_second": 6.299,
|
| 2675 |
+
"step": 3100
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 4.716140650175339,
|
| 2679 |
+
"grad_norm": 0.24262085556983948,
|
| 2680 |
+
"learning_rate": 9.575088287257118e-07,
|
| 2681 |
+
"loss": 0.0025,
|
| 2682 |
+
"step": 3110
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 4.73130508956497,
|
| 2686 |
+
"grad_norm": 0.5570153594017029,
|
| 2687 |
+
"learning_rate": 8.570808402103392e-07,
|
| 2688 |
+
"loss": 0.0051,
|
| 2689 |
+
"step": 3120
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 4.746469528954601,
|
| 2693 |
+
"grad_norm": 0.22754321992397308,
|
| 2694 |
+
"learning_rate": 7.62169905730109e-07,
|
| 2695 |
+
"loss": 0.0032,
|
| 2696 |
+
"step": 3130
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 4.761633968344233,
|
| 2700 |
+
"grad_norm": 0.4912855625152588,
|
| 2701 |
+
"learning_rate": 6.727866805078531e-07,
|
| 2702 |
+
"loss": 0.0021,
|
| 2703 |
+
"step": 3140
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 4.776798407733864,
|
| 2707 |
+
"grad_norm": 0.017126476392149925,
|
| 2708 |
+
"learning_rate": 5.889411991953975e-07,
|
| 2709 |
+
"loss": 0.0028,
|
| 2710 |
+
"step": 3150
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 4.776798407733864,
|
| 2714 |
+
"eval_loss": 0.06346834450960159,
|
| 2715 |
+
"eval_runtime": 186.8935,
|
| 2716 |
+
"eval_samples_per_second": 6.276,
|
| 2717 |
+
"eval_steps_per_second": 6.276,
|
| 2718 |
+
"step": 3150
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.791962847123496,
|
| 2722 |
+
"grad_norm": 0.2492581158876419,
|
| 2723 |
+
"learning_rate": 5.106428747470137e-07,
|
| 2724 |
+
"loss": 0.0021,
|
| 2725 |
+
"step": 3160
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.8071272865131265,
|
| 2729 |
+
"grad_norm": 0.10539235919713974,
|
| 2730 |
+
"learning_rate": 4.37900497362681e-07,
|
| 2731 |
+
"loss": 0.0027,
|
| 2732 |
+
"step": 3170
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.822291725902758,
|
| 2736 |
+
"grad_norm": 0.04554608091711998,
|
| 2737 |
+
"learning_rate": 3.7072223350124167e-07,
|
| 2738 |
+
"loss": 0.0021,
|
| 2739 |
+
"step": 3180
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.837456165292389,
|
| 2743 |
+
"grad_norm": 0.2119264155626297,
|
| 2744 |
+
"learning_rate": 3.0911562496358517e-07,
|
| 2745 |
+
"loss": 0.0032,
|
| 2746 |
+
"step": 3190
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.852620604682021,
|
| 2750 |
+
"grad_norm": 0.1288806051015854,
|
| 2751 |
+
"learning_rate": 2.53087588045986e-07,
|
| 2752 |
+
"loss": 0.0028,
|
| 2753 |
+
"step": 3200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.852620604682021,
|
| 2757 |
+
"eval_loss": 0.06373777985572815,
|
| 2758 |
+
"eval_runtime": 186.9337,
|
| 2759 |
+
"eval_samples_per_second": 6.275,
|
| 2760 |
+
"eval_steps_per_second": 6.275,
|
| 2761 |
+
"step": 3200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 4.867785044071652,
|
| 2765 |
+
"grad_norm": 0.12755931913852692,
|
| 2766 |
+
"learning_rate": 2.026444127636029e-07,
|
| 2767 |
+
"loss": 0.0023,
|
| 2768 |
+
"step": 3210
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 4.882949483461283,
|
| 2772 |
+
"grad_norm": 0.00676093390211463,
|
| 2773 |
+
"learning_rate": 1.577917621443825e-07,
|
| 2774 |
+
"loss": 0.0038,
|
| 2775 |
+
"step": 3220
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 4.898113922850914,
|
| 2779 |
+
"grad_norm": 0.26253750920295715,
|
| 2780 |
+
"learning_rate": 1.185346715932345e-07,
|
| 2781 |
+
"loss": 0.005,
|
| 2782 |
+
"step": 3230
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 4.913278362240546,
|
| 2786 |
+
"grad_norm": 0.42117446660995483,
|
| 2787 |
+
"learning_rate": 8.48775483267783e-08,
|
| 2788 |
+
"loss": 0.0029,
|
| 2789 |
+
"step": 3240
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 4.928442801630177,
|
| 2793 |
+
"grad_norm": 0.05510617420077324,
|
| 2794 |
+
"learning_rate": 5.6824170878544414e-08,
|
| 2795 |
+
"loss": 0.0021,
|
| 2796 |
+
"step": 3250
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 4.928442801630177,
|
| 2800 |
+
"eval_loss": 0.06360332667827606,
|
| 2801 |
+
"eval_runtime": 186.8974,
|
| 2802 |
+
"eval_samples_per_second": 6.276,
|
| 2803 |
+
"eval_steps_per_second": 6.276,
|
| 2804 |
+
"step": 3250
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 4.943607241019809,
|
| 2808 |
+
"grad_norm": 0.033535584807395935,
|
| 2809 |
+
"learning_rate": 3.4377688674774866e-08,
|
| 2810 |
+
"loss": 0.002,
|
| 2811 |
+
"step": 3260
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 4.9587716804094395,
|
| 2815 |
+
"grad_norm": 0.037935420870780945,
|
| 2816 |
+
"learning_rate": 1.7540621680850466e-08,
|
| 2817 |
+
"loss": 0.0012,
|
| 2818 |
+
"step": 3270
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 4.973936119799071,
|
| 2822 |
+
"grad_norm": 0.057161327451467514,
|
| 2823 |
+
"learning_rate": 6.314860118400434e-09,
|
| 2824 |
+
"loss": 0.0038,
|
| 2825 |
+
"step": 3280
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 4.989100559188703,
|
| 2829 |
+
"grad_norm": 0.027261769399046898,
|
| 2830 |
+
"learning_rate": 7.016642530777162e-10,
|
| 2831 |
+
"loss": 0.0017,
|
| 2832 |
+
"step": 3290
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 4.996682778883518,
|
| 2836 |
+
"step": 3295,
|
| 2837 |
+
"total_flos": 8.269502901505229e+17,
|
| 2838 |
+
"train_loss": 0.04054494600613038,
|
| 2839 |
+
"train_runtime": 44308.6539,
|
| 2840 |
+
"train_samples_per_second": 1.191,
|
| 2841 |
+
"train_steps_per_second": 0.074
|
| 2842 |
+
}
|
| 2843 |
+
],
|
| 2844 |
+
"logging_steps": 10,
|
| 2845 |
+
"max_steps": 3295,
|
| 2846 |
+
"num_input_tokens_seen": 0,
|
| 2847 |
+
"num_train_epochs": 5,
|
| 2848 |
+
"save_steps": 50,
|
| 2849 |
+
"stateful_callbacks": {
|
| 2850 |
+
"TrainerControl": {
|
| 2851 |
+
"args": {
|
| 2852 |
+
"should_epoch_stop": false,
|
| 2853 |
+
"should_evaluate": false,
|
| 2854 |
+
"should_log": false,
|
| 2855 |
+
"should_save": true,
|
| 2856 |
+
"should_training_stop": true
|
| 2857 |
+
},
|
| 2858 |
+
"attributes": {}
|
| 2859 |
+
}
|
| 2860 |
+
},
|
| 2861 |
+
"total_flos": 8.269502901505229e+17,
|
| 2862 |
+
"train_batch_size": 1,
|
| 2863 |
+
"trial_name": null,
|
| 2864 |
+
"trial_params": null
|
| 2865 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|