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 +3267 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: cooking_sft_fail_new_mem
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# cooking_sft_fail_new_mem
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 4 |
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: cooking_sft_fail_new_mem
|
|
|
|
| 16 |
|
| 17 |
# cooking_sft_fail_new_mem
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the identity and the cooking_sft_fail_new_mem datasets.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2036
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.999983338054218,
|
| 3 |
+
"eval_loss": 0.20362387597560883,
|
| 4 |
+
"eval_runtime": 262.5946,
|
| 5 |
+
"eval_samples_per_second": 37.316,
|
| 6 |
+
"eval_steps_per_second": 4.665,
|
| 7 |
+
"total_flos": 1934604910592000.0,
|
| 8 |
+
"train_loss": 0.2527618171993302,
|
| 9 |
+
"train_runtime": 72440.3327,
|
| 10 |
+
"train_samples_per_second": 6.628,
|
| 11 |
+
"train_steps_per_second": 0.052
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.999983338054218,
|
| 3 |
+
"eval_loss": 0.20362387597560883,
|
| 4 |
+
"eval_runtime": 262.5946,
|
| 5 |
+
"eval_samples_per_second": 37.316,
|
| 6 |
+
"eval_steps_per_second": 4.665
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.999983338054218,
|
| 3 |
+
"total_flos": 1934604910592000.0,
|
| 4 |
+
"train_loss": 0.2527618171993302,
|
| 5 |
+
"train_runtime": 72440.3327,
|
| 6 |
+
"train_samples_per_second": 6.628,
|
| 7 |
+
"train_steps_per_second": 0.052
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3267 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.999983338054218,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 3751,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.002665911325124548,
|
| 13 |
+
"grad_norm": 25.460365315883454,
|
| 14 |
+
"learning_rate": 2.6595744680851066e-07,
|
| 15 |
+
"loss": 0.5957,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.005331822650249096,
|
| 20 |
+
"grad_norm": 7.786416251497864,
|
| 21 |
+
"learning_rate": 5.319148936170213e-07,
|
| 22 |
+
"loss": 0.5163,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.007997733975373645,
|
| 27 |
+
"grad_norm": 6.545796555174715,
|
| 28 |
+
"learning_rate": 7.97872340425532e-07,
|
| 29 |
+
"loss": 0.4334,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.010663645300498192,
|
| 34 |
+
"grad_norm": 5.109112355076126,
|
| 35 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 36 |
+
"loss": 0.3824,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01332955662562274,
|
| 41 |
+
"grad_norm": 5.129086050533378,
|
| 42 |
+
"learning_rate": 1.3297872340425533e-06,
|
| 43 |
+
"loss": 0.3821,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01332955662562274,
|
| 48 |
+
"eval_loss": 0.4735161364078522,
|
| 49 |
+
"eval_runtime": 263.1387,
|
| 50 |
+
"eval_samples_per_second": 37.239,
|
| 51 |
+
"eval_steps_per_second": 4.655,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.01599546795074729,
|
| 56 |
+
"grad_norm": 3.9633957758228795,
|
| 57 |
+
"learning_rate": 1.595744680851064e-06,
|
| 58 |
+
"loss": 0.3431,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.018661379275871838,
|
| 63 |
+
"grad_norm": 5.099960208152394,
|
| 64 |
+
"learning_rate": 1.8617021276595745e-06,
|
| 65 |
+
"loss": 0.3327,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.021327290600996383,
|
| 70 |
+
"grad_norm": 4.6877091477318995,
|
| 71 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 72 |
+
"loss": 0.3079,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.023993201926120932,
|
| 77 |
+
"grad_norm": 4.2158979353952,
|
| 78 |
+
"learning_rate": 2.393617021276596e-06,
|
| 79 |
+
"loss": 0.306,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02665911325124548,
|
| 84 |
+
"grad_norm": 4.111674187143645,
|
| 85 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 86 |
+
"loss": 0.302,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02665911325124548,
|
| 91 |
+
"eval_loss": 0.3177907168865204,
|
| 92 |
+
"eval_runtime": 263.1879,
|
| 93 |
+
"eval_samples_per_second": 37.232,
|
| 94 |
+
"eval_steps_per_second": 4.654,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.02932502457637003,
|
| 99 |
+
"grad_norm": 3.796268052824722,
|
| 100 |
+
"learning_rate": 2.9255319148936174e-06,
|
| 101 |
+
"loss": 0.2978,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.03199093590149458,
|
| 106 |
+
"grad_norm": 4.080365457232974,
|
| 107 |
+
"learning_rate": 3.191489361702128e-06,
|
| 108 |
+
"loss": 0.3046,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.034656847226619124,
|
| 113 |
+
"grad_norm": 3.570907286511261,
|
| 114 |
+
"learning_rate": 3.457446808510639e-06,
|
| 115 |
+
"loss": 0.3074,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.037322758551743676,
|
| 120 |
+
"grad_norm": 3.6056579252874896,
|
| 121 |
+
"learning_rate": 3.723404255319149e-06,
|
| 122 |
+
"loss": 0.3147,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.03998866987686822,
|
| 127 |
+
"grad_norm": 3.3791442973244163,
|
| 128 |
+
"learning_rate": 3.98936170212766e-06,
|
| 129 |
+
"loss": 0.2988,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.03998866987686822,
|
| 134 |
+
"eval_loss": 0.32532769441604614,
|
| 135 |
+
"eval_runtime": 263.0021,
|
| 136 |
+
"eval_samples_per_second": 37.258,
|
| 137 |
+
"eval_steps_per_second": 4.658,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.04265458120199277,
|
| 142 |
+
"grad_norm": 3.7568359111958665,
|
| 143 |
+
"learning_rate": 4.255319148936171e-06,
|
| 144 |
+
"loss": 0.3049,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.04532049252711732,
|
| 149 |
+
"grad_norm": 3.568899075332689,
|
| 150 |
+
"learning_rate": 4.521276595744681e-06,
|
| 151 |
+
"loss": 0.3077,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.047986403852241864,
|
| 156 |
+
"grad_norm": 3.446482818546644,
|
| 157 |
+
"learning_rate": 4.787234042553192e-06,
|
| 158 |
+
"loss": 0.2957,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.05065231517736641,
|
| 163 |
+
"grad_norm": 3.3569986066448223,
|
| 164 |
+
"learning_rate": 5.053191489361703e-06,
|
| 165 |
+
"loss": 0.2993,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.05331822650249096,
|
| 170 |
+
"grad_norm": 3.502984902631741,
|
| 171 |
+
"learning_rate": 5.319148936170213e-06,
|
| 172 |
+
"loss": 0.3054,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.05331822650249096,
|
| 177 |
+
"eval_loss": 0.3250272572040558,
|
| 178 |
+
"eval_runtime": 263.1161,
|
| 179 |
+
"eval_samples_per_second": 37.242,
|
| 180 |
+
"eval_steps_per_second": 4.656,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.05598413782761551,
|
| 185 |
+
"grad_norm": 2.8396576424885387,
|
| 186 |
+
"learning_rate": 5.5851063829787235e-06,
|
| 187 |
+
"loss": 0.3117,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.05865004915274006,
|
| 192 |
+
"grad_norm": 2.8315864264900372,
|
| 193 |
+
"learning_rate": 5.851063829787235e-06,
|
| 194 |
+
"loss": 0.3102,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.061315960477864605,
|
| 199 |
+
"grad_norm": 3.068071736618938,
|
| 200 |
+
"learning_rate": 6.117021276595745e-06,
|
| 201 |
+
"loss": 0.3096,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.06398187180298916,
|
| 206 |
+
"grad_norm": 3.2824497787656357,
|
| 207 |
+
"learning_rate": 6.382978723404256e-06,
|
| 208 |
+
"loss": 0.3046,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.0666477831281137,
|
| 213 |
+
"grad_norm": 2.750006857001217,
|
| 214 |
+
"learning_rate": 6.648936170212767e-06,
|
| 215 |
+
"loss": 0.2967,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.0666477831281137,
|
| 220 |
+
"eval_loss": 0.3232134282588959,
|
| 221 |
+
"eval_runtime": 263.0112,
|
| 222 |
+
"eval_samples_per_second": 37.257,
|
| 223 |
+
"eval_steps_per_second": 4.658,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.06931369445323825,
|
| 228 |
+
"grad_norm": 2.7213269114514205,
|
| 229 |
+
"learning_rate": 6.914893617021278e-06,
|
| 230 |
+
"loss": 0.3112,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.07197960577836279,
|
| 235 |
+
"grad_norm": 2.5062744105701653,
|
| 236 |
+
"learning_rate": 7.1808510638297875e-06,
|
| 237 |
+
"loss": 0.314,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.07464551710348735,
|
| 242 |
+
"grad_norm": 2.541718637398392,
|
| 243 |
+
"learning_rate": 7.446808510638298e-06,
|
| 244 |
+
"loss": 0.3041,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.0773114284286119,
|
| 249 |
+
"grad_norm": 3.203380938887303,
|
| 250 |
+
"learning_rate": 7.71276595744681e-06,
|
| 251 |
+
"loss": 0.3136,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.07997733975373644,
|
| 256 |
+
"grad_norm": 2.7982203558961016,
|
| 257 |
+
"learning_rate": 7.97872340425532e-06,
|
| 258 |
+
"loss": 0.3137,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.07997733975373644,
|
| 263 |
+
"eval_loss": 0.3207298815250397,
|
| 264 |
+
"eval_runtime": 262.9784,
|
| 265 |
+
"eval_samples_per_second": 37.262,
|
| 266 |
+
"eval_steps_per_second": 4.658,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.08264325107886099,
|
| 271 |
+
"grad_norm": 2.4586173652717216,
|
| 272 |
+
"learning_rate": 8.24468085106383e-06,
|
| 273 |
+
"loss": 0.3092,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.08530916240398553,
|
| 278 |
+
"grad_norm": 2.470341507162159,
|
| 279 |
+
"learning_rate": 8.510638297872341e-06,
|
| 280 |
+
"loss": 0.3255,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.08797507372911008,
|
| 285 |
+
"grad_norm": 2.531961920922859,
|
| 286 |
+
"learning_rate": 8.776595744680852e-06,
|
| 287 |
+
"loss": 0.3219,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.09064098505423464,
|
| 292 |
+
"grad_norm": 2.218215799424983,
|
| 293 |
+
"learning_rate": 9.042553191489362e-06,
|
| 294 |
+
"loss": 0.3093,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.09330689637935918,
|
| 299 |
+
"grad_norm": 2.5602707890452896,
|
| 300 |
+
"learning_rate": 9.308510638297872e-06,
|
| 301 |
+
"loss": 0.3221,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.09330689637935918,
|
| 306 |
+
"eval_loss": 0.3211060166358948,
|
| 307 |
+
"eval_runtime": 262.9608,
|
| 308 |
+
"eval_samples_per_second": 37.264,
|
| 309 |
+
"eval_steps_per_second": 4.658,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.09597280770448373,
|
| 314 |
+
"grad_norm": 2.4918966800165228,
|
| 315 |
+
"learning_rate": 9.574468085106385e-06,
|
| 316 |
+
"loss": 0.3209,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.09863871902960827,
|
| 321 |
+
"grad_norm": 2.7550293721808603,
|
| 322 |
+
"learning_rate": 9.840425531914895e-06,
|
| 323 |
+
"loss": 0.3188,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.10130463035473282,
|
| 328 |
+
"grad_norm": 2.086538785606296,
|
| 329 |
+
"learning_rate": 9.999965341346946e-06,
|
| 330 |
+
"loss": 0.3202,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.10397054167985738,
|
| 335 |
+
"grad_norm": 2.291915706021129,
|
| 336 |
+
"learning_rate": 9.999575437018172e-06,
|
| 337 |
+
"loss": 0.3143,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.10663645300498192,
|
| 342 |
+
"grad_norm": 2.5734029639653406,
|
| 343 |
+
"learning_rate": 9.998752338940612e-06,
|
| 344 |
+
"loss": 0.3188,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.10663645300498192,
|
| 349 |
+
"eval_loss": 0.3204084634780884,
|
| 350 |
+
"eval_runtime": 263.0611,
|
| 351 |
+
"eval_samples_per_second": 37.25,
|
| 352 |
+
"eval_steps_per_second": 4.657,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.10930236433010647,
|
| 357 |
+
"grad_norm": 1.9778855134324143,
|
| 358 |
+
"learning_rate": 9.997496118432509e-06,
|
| 359 |
+
"loss": 0.3026,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.11196827565523101,
|
| 364 |
+
"grad_norm": 2.2135770753044395,
|
| 365 |
+
"learning_rate": 9.995806884340483e-06,
|
| 366 |
+
"loss": 0.3192,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.11463418698035556,
|
| 371 |
+
"grad_norm": 2.3593510882812634,
|
| 372 |
+
"learning_rate": 9.99368478303009e-06,
|
| 373 |
+
"loss": 0.3143,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.11730009830548012,
|
| 378 |
+
"grad_norm": 2.2314058999493054,
|
| 379 |
+
"learning_rate": 9.991129998373145e-06,
|
| 380 |
+
"loss": 0.3189,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.11996600963060466,
|
| 385 |
+
"grad_norm": 2.1809009277203493,
|
| 386 |
+
"learning_rate": 9.988142751731797e-06,
|
| 387 |
+
"loss": 0.308,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.11996600963060466,
|
| 392 |
+
"eval_loss": 0.31486886739730835,
|
| 393 |
+
"eval_runtime": 263.0029,
|
| 394 |
+
"eval_samples_per_second": 37.258,
|
| 395 |
+
"eval_steps_per_second": 4.658,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.12263192095572921,
|
| 400 |
+
"grad_norm": 2.009644779324099,
|
| 401 |
+
"learning_rate": 9.984723301939337e-06,
|
| 402 |
+
"loss": 0.3172,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.12529783228085375,
|
| 407 |
+
"grad_norm": 2.2024418868068314,
|
| 408 |
+
"learning_rate": 9.980871945277777e-06,
|
| 409 |
+
"loss": 0.3147,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.12796374360597831,
|
| 414 |
+
"grad_norm": 2.076529594327517,
|
| 415 |
+
"learning_rate": 9.976589015452178e-06,
|
| 416 |
+
"loss": 0.3211,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.13062965493110285,
|
| 421 |
+
"grad_norm": 1.921579954198359,
|
| 422 |
+
"learning_rate": 9.97187488356174e-06,
|
| 423 |
+
"loss": 0.3109,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.1332955662562274,
|
| 428 |
+
"grad_norm": 2.298024577351239,
|
| 429 |
+
"learning_rate": 9.966729958067638e-06,
|
| 430 |
+
"loss": 0.3123,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.1332955662562274,
|
| 435 |
+
"eval_loss": 0.3106406331062317,
|
| 436 |
+
"eval_runtime": 263.0069,
|
| 437 |
+
"eval_samples_per_second": 37.258,
|
| 438 |
+
"eval_steps_per_second": 4.658,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.13596147758135196,
|
| 443 |
+
"grad_norm": 2.169882121277794,
|
| 444 |
+
"learning_rate": 9.961154684757636e-06,
|
| 445 |
+
"loss": 0.3032,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.1386273889064765,
|
| 450 |
+
"grad_norm": 2.101861158344262,
|
| 451 |
+
"learning_rate": 9.955149546707465e-06,
|
| 452 |
+
"loss": 0.3048,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.14129330023160105,
|
| 457 |
+
"grad_norm": 2.048031635489159,
|
| 458 |
+
"learning_rate": 9.948715064238956e-06,
|
| 459 |
+
"loss": 0.2947,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.14395921155672559,
|
| 464 |
+
"grad_norm": 2.188308108036795,
|
| 465 |
+
"learning_rate": 9.941851794874969e-06,
|
| 466 |
+
"loss": 0.2998,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.14662512288185015,
|
| 471 |
+
"grad_norm": 2.0056114881626472,
|
| 472 |
+
"learning_rate": 9.934560333291077e-06,
|
| 473 |
+
"loss": 0.3138,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.14662512288185015,
|
| 478 |
+
"eval_loss": 0.3050285875797272,
|
| 479 |
+
"eval_runtime": 263.0851,
|
| 480 |
+
"eval_samples_per_second": 37.247,
|
| 481 |
+
"eval_steps_per_second": 4.656,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.1492910342069747,
|
| 486 |
+
"grad_norm": 1.9352426910596738,
|
| 487 |
+
"learning_rate": 9.926841311264037e-06,
|
| 488 |
+
"loss": 0.3014,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.15195694553209924,
|
| 493 |
+
"grad_norm": 2.2043603905292497,
|
| 494 |
+
"learning_rate": 9.918695397617064e-06,
|
| 495 |
+
"loss": 0.3076,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.1546228568572238,
|
| 500 |
+
"grad_norm": 1.896607728698459,
|
| 501 |
+
"learning_rate": 9.91012329816186e-06,
|
| 502 |
+
"loss": 0.3013,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.15728876818234833,
|
| 507 |
+
"grad_norm": 2.5158079295704776,
|
| 508 |
+
"learning_rate": 9.901125755637473e-06,
|
| 509 |
+
"loss": 0.3017,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.15995467950747289,
|
| 514 |
+
"grad_norm": 2.2139727973208747,
|
| 515 |
+
"learning_rate": 9.89170354964594e-06,
|
| 516 |
+
"loss": 0.3032,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.15995467950747289,
|
| 521 |
+
"eval_loss": 0.3046238422393799,
|
| 522 |
+
"eval_runtime": 263.0944,
|
| 523 |
+
"eval_samples_per_second": 37.245,
|
| 524 |
+
"eval_steps_per_second": 4.656,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.16262059083259742,
|
| 529 |
+
"grad_norm": 2.0311233806900666,
|
| 530 |
+
"learning_rate": 9.881857496584726e-06,
|
| 531 |
+
"loss": 0.3027,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.16528650215772198,
|
| 536 |
+
"grad_norm": 1.8044187965587122,
|
| 537 |
+
"learning_rate": 9.871588449575999e-06,
|
| 538 |
+
"loss": 0.296,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.16795241348284654,
|
| 543 |
+
"grad_norm": 1.9287672543745633,
|
| 544 |
+
"learning_rate": 9.860897298392712e-06,
|
| 545 |
+
"loss": 0.3031,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.17061832480797107,
|
| 550 |
+
"grad_norm": 1.9418604281132057,
|
| 551 |
+
"learning_rate": 9.849784969381488e-06,
|
| 552 |
+
"loss": 0.3006,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.17328423613309563,
|
| 557 |
+
"grad_norm": 1.7607874454195112,
|
| 558 |
+
"learning_rate": 9.83825242538238e-06,
|
| 559 |
+
"loss": 0.2827,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.17328423613309563,
|
| 564 |
+
"eval_loss": 0.30168309807777405,
|
| 565 |
+
"eval_runtime": 263.0754,
|
| 566 |
+
"eval_samples_per_second": 37.248,
|
| 567 |
+
"eval_steps_per_second": 4.656,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.17595014745822016,
|
| 572 |
+
"grad_norm": 1.6217183317438102,
|
| 573 |
+
"learning_rate": 9.826300665645432e-06,
|
| 574 |
+
"loss": 0.2814,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.17861605878334472,
|
| 579 |
+
"grad_norm": 1.8544819560192451,
|
| 580 |
+
"learning_rate": 9.813930725744095e-06,
|
| 581 |
+
"loss": 0.2852,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.18128197010846928,
|
| 586 |
+
"grad_norm": 1.7254305229833091,
|
| 587 |
+
"learning_rate": 9.801143677485509e-06,
|
| 588 |
+
"loss": 0.3016,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.1839478814335938,
|
| 593 |
+
"grad_norm": 1.76092048982559,
|
| 594 |
+
"learning_rate": 9.787940628817627e-06,
|
| 595 |
+
"loss": 0.3023,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.18661379275871837,
|
| 600 |
+
"grad_norm": 1.5976117922079591,
|
| 601 |
+
"learning_rate": 9.774322723733216e-06,
|
| 602 |
+
"loss": 0.2953,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.18661379275871837,
|
| 607 |
+
"eval_loss": 0.2970203757286072,
|
| 608 |
+
"eval_runtime": 263.005,
|
| 609 |
+
"eval_samples_per_second": 37.258,
|
| 610 |
+
"eval_steps_per_second": 4.658,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.1892797040838429,
|
| 615 |
+
"grad_norm": 2.0364062908857505,
|
| 616 |
+
"learning_rate": 9.760291142170739e-06,
|
| 617 |
+
"loss": 0.2819,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.19194561540896746,
|
| 622 |
+
"grad_norm": 1.7860594933309035,
|
| 623 |
+
"learning_rate": 9.745847099912116e-06,
|
| 624 |
+
"loss": 0.2922,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.19461152673409202,
|
| 629 |
+
"grad_norm": 1.724488742261424,
|
| 630 |
+
"learning_rate": 9.73099184847738e-06,
|
| 631 |
+
"loss": 0.2936,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.19727743805921655,
|
| 636 |
+
"grad_norm": 2.0236324189364763,
|
| 637 |
+
"learning_rate": 9.715726675016238e-06,
|
| 638 |
+
"loss": 0.2852,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.1999433493843411,
|
| 643 |
+
"grad_norm": 1.5757420943087048,
|
| 644 |
+
"learning_rate": 9.700052902196541e-06,
|
| 645 |
+
"loss": 0.2854,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.1999433493843411,
|
| 650 |
+
"eval_loss": 0.292442262172699,
|
| 651 |
+
"eval_runtime": 263.0027,
|
| 652 |
+
"eval_samples_per_second": 37.258,
|
| 653 |
+
"eval_steps_per_second": 4.658,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.20260926070946564,
|
| 658 |
+
"grad_norm": 1.6109796234381852,
|
| 659 |
+
"learning_rate": 9.68397188808969e-06,
|
| 660 |
+
"loss": 0.2911,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.2052751720345902,
|
| 665 |
+
"grad_norm": 1.7705435745788891,
|
| 666 |
+
"learning_rate": 9.667485026052956e-06,
|
| 667 |
+
"loss": 0.3003,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.20794108335971476,
|
| 672 |
+
"grad_norm": 1.8227445232808335,
|
| 673 |
+
"learning_rate": 9.650593744608754e-06,
|
| 674 |
+
"loss": 0.2954,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.2106069946848393,
|
| 679 |
+
"grad_norm": 1.6678622155458844,
|
| 680 |
+
"learning_rate": 9.633299507320862e-06,
|
| 681 |
+
"loss": 0.2921,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.21327290600996385,
|
| 686 |
+
"grad_norm": 1.7265641158944443,
|
| 687 |
+
"learning_rate": 9.615603812667618e-06,
|
| 688 |
+
"loss": 0.2872,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.21327290600996385,
|
| 693 |
+
"eval_loss": 0.2895732522010803,
|
| 694 |
+
"eval_runtime": 263.041,
|
| 695 |
+
"eval_samples_per_second": 37.253,
|
| 696 |
+
"eval_steps_per_second": 4.657,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.21593881733508838,
|
| 701 |
+
"grad_norm": 1.7182998913074186,
|
| 702 |
+
"learning_rate": 9.597508193912077e-06,
|
| 703 |
+
"loss": 0.2907,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.21860472866021294,
|
| 708 |
+
"grad_norm": 1.5880777723000974,
|
| 709 |
+
"learning_rate": 9.579014218969158e-06,
|
| 710 |
+
"loss": 0.2867,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.2212706399853375,
|
| 715 |
+
"grad_norm": 1.7866067793206908,
|
| 716 |
+
"learning_rate": 9.560123490269795e-06,
|
| 717 |
+
"loss": 0.2942,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.22393655131046203,
|
| 722 |
+
"grad_norm": 1.5877926190764673,
|
| 723 |
+
"learning_rate": 9.540837644622091e-06,
|
| 724 |
+
"loss": 0.2832,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.2266024626355866,
|
| 729 |
+
"grad_norm": 1.9217023055863738,
|
| 730 |
+
"learning_rate": 9.521158353069494e-06,
|
| 731 |
+
"loss": 0.2866,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.2266024626355866,
|
| 736 |
+
"eval_loss": 0.28362876176834106,
|
| 737 |
+
"eval_runtime": 263.2009,
|
| 738 |
+
"eval_samples_per_second": 37.23,
|
| 739 |
+
"eval_steps_per_second": 4.654,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.22926837396071112,
|
| 744 |
+
"grad_norm": 1.7253135194855898,
|
| 745 |
+
"learning_rate": 9.501087320746007e-06,
|
| 746 |
+
"loss": 0.2877,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.23193428528583568,
|
| 751 |
+
"grad_norm": 1.6645542489658331,
|
| 752 |
+
"learning_rate": 9.480626286728445e-06,
|
| 753 |
+
"loss": 0.2857,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.23460019661096024,
|
| 758 |
+
"grad_norm": 1.511024578102627,
|
| 759 |
+
"learning_rate": 9.459777023885754e-06,
|
| 760 |
+
"loss": 0.2839,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.23726610793608477,
|
| 765 |
+
"grad_norm": 1.4824802506716586,
|
| 766 |
+
"learning_rate": 9.438541338725397e-06,
|
| 767 |
+
"loss": 0.2833,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.23993201926120933,
|
| 772 |
+
"grad_norm": 1.564232445580215,
|
| 773 |
+
"learning_rate": 9.416921071236821e-06,
|
| 774 |
+
"loss": 0.2925,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.23993201926120933,
|
| 779 |
+
"eval_loss": 0.2794356942176819,
|
| 780 |
+
"eval_runtime": 263.1403,
|
| 781 |
+
"eval_samples_per_second": 37.239,
|
| 782 |
+
"eval_steps_per_second": 4.655,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.24259793058633386,
|
| 787 |
+
"grad_norm": 1.812013202524589,
|
| 788 |
+
"learning_rate": 9.394918094732044e-06,
|
| 789 |
+
"loss": 0.2846,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.24526384191145842,
|
| 794 |
+
"grad_norm": 1.7480374081646133,
|
| 795 |
+
"learning_rate": 9.37253431568332e-06,
|
| 796 |
+
"loss": 0.2826,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.24792975323658298,
|
| 801 |
+
"grad_norm": 1.71680256902317,
|
| 802 |
+
"learning_rate": 9.349771673557966e-06,
|
| 803 |
+
"loss": 0.2856,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.2505956645617075,
|
| 808 |
+
"grad_norm": 1.6078777895847485,
|
| 809 |
+
"learning_rate": 9.326632140650311e-06,
|
| 810 |
+
"loss": 0.2886,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.25326157588683207,
|
| 815 |
+
"grad_norm": 1.4898994133826529,
|
| 816 |
+
"learning_rate": 9.303117721910801e-06,
|
| 817 |
+
"loss": 0.2843,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.25326157588683207,
|
| 822 |
+
"eval_loss": 0.28232333064079285,
|
| 823 |
+
"eval_runtime": 262.9546,
|
| 824 |
+
"eval_samples_per_second": 37.265,
|
| 825 |
+
"eval_steps_per_second": 4.659,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.25592748721195663,
|
| 830 |
+
"grad_norm": 1.818300085431669,
|
| 831 |
+
"learning_rate": 9.279230454772282e-06,
|
| 832 |
+
"loss": 0.2758,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.2585933985370812,
|
| 837 |
+
"grad_norm": 1.5128664817372184,
|
| 838 |
+
"learning_rate": 9.25497240897346e-06,
|
| 839 |
+
"loss": 0.2789,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.2612593098622057,
|
| 844 |
+
"grad_norm": 1.6097431612586455,
|
| 845 |
+
"learning_rate": 9.23034568637957e-06,
|
| 846 |
+
"loss": 0.2854,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.26392522118733025,
|
| 851 |
+
"grad_norm": 1.4100117130863956,
|
| 852 |
+
"learning_rate": 9.205352420800253e-06,
|
| 853 |
+
"loss": 0.2857,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.2665911325124548,
|
| 858 |
+
"grad_norm": 1.6675059930867078,
|
| 859 |
+
"learning_rate": 9.179994777804677e-06,
|
| 860 |
+
"loss": 0.292,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.2665911325124548,
|
| 865 |
+
"eval_loss": 0.27887627482414246,
|
| 866 |
+
"eval_runtime": 262.9281,
|
| 867 |
+
"eval_samples_per_second": 37.269,
|
| 868 |
+
"eval_steps_per_second": 4.659,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.26925704383757937,
|
| 873 |
+
"grad_norm": 1.644767282455157,
|
| 874 |
+
"learning_rate": 9.154274954533895e-06,
|
| 875 |
+
"loss": 0.2863,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.2719229551627039,
|
| 880 |
+
"grad_norm": 1.6790096248660116,
|
| 881 |
+
"learning_rate": 9.128195179510466e-06,
|
| 882 |
+
"loss": 0.279,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.27458886648782843,
|
| 887 |
+
"grad_norm": 1.583877941328967,
|
| 888 |
+
"learning_rate": 9.101757712445369e-06,
|
| 889 |
+
"loss": 0.2743,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.277254777812953,
|
| 894 |
+
"grad_norm": 1.626963776268032,
|
| 895 |
+
"learning_rate": 9.07496484404221e-06,
|
| 896 |
+
"loss": 0.2757,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.27992068913807755,
|
| 901 |
+
"grad_norm": 1.5034004223963462,
|
| 902 |
+
"learning_rate": 9.04781889579873e-06,
|
| 903 |
+
"loss": 0.2775,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.27992068913807755,
|
| 908 |
+
"eval_loss": 0.27627232670783997,
|
| 909 |
+
"eval_runtime": 262.9028,
|
| 910 |
+
"eval_samples_per_second": 37.272,
|
| 911 |
+
"eval_steps_per_second": 4.66,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.2825866004632021,
|
| 916 |
+
"grad_norm": 1.4195880755569912,
|
| 917 |
+
"learning_rate": 9.020322219805674e-06,
|
| 918 |
+
"loss": 0.2803,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.28525251178832667,
|
| 923 |
+
"grad_norm": 1.7563946494767981,
|
| 924 |
+
"learning_rate": 8.99247719854297e-06,
|
| 925 |
+
"loss": 0.2831,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.28791842311345117,
|
| 930 |
+
"grad_norm": 1.4975000328635686,
|
| 931 |
+
"learning_rate": 8.964286244673315e-06,
|
| 932 |
+
"loss": 0.2794,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.29058433443857573,
|
| 937 |
+
"grad_norm": 1.6808608884719483,
|
| 938 |
+
"learning_rate": 8.935751800833117e-06,
|
| 939 |
+
"loss": 0.2728,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.2932502457637003,
|
| 944 |
+
"grad_norm": 1.5692764321165331,
|
| 945 |
+
"learning_rate": 8.906876339420851e-06,
|
| 946 |
+
"loss": 0.2652,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.2932502457637003,
|
| 951 |
+
"eval_loss": 0.27173659205436707,
|
| 952 |
+
"eval_runtime": 263.0328,
|
| 953 |
+
"eval_samples_per_second": 37.254,
|
| 954 |
+
"eval_steps_per_second": 4.657,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.29591615708882485,
|
| 959 |
+
"grad_norm": 1.6549948875336085,
|
| 960 |
+
"learning_rate": 8.877662362382844e-06,
|
| 961 |
+
"loss": 0.2731,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.2985820684139494,
|
| 966 |
+
"grad_norm": 1.6301740740445887,
|
| 967 |
+
"learning_rate": 8.848112400996473e-06,
|
| 968 |
+
"loss": 0.2669,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.3012479797390739,
|
| 973 |
+
"grad_norm": 1.5648628679336365,
|
| 974 |
+
"learning_rate": 8.818229015650862e-06,
|
| 975 |
+
"loss": 0.274,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.30391389106419847,
|
| 980 |
+
"grad_norm": 1.5356188950454304,
|
| 981 |
+
"learning_rate": 8.788014795625018e-06,
|
| 982 |
+
"loss": 0.275,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.30657980238932303,
|
| 987 |
+
"grad_norm": 1.5817185861901346,
|
| 988 |
+
"learning_rate": 8.757472358863481e-06,
|
| 989 |
+
"loss": 0.27,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.30657980238932303,
|
| 994 |
+
"eval_loss": 0.2712327241897583,
|
| 995 |
+
"eval_runtime": 262.9142,
|
| 996 |
+
"eval_samples_per_second": 37.271,
|
| 997 |
+
"eval_steps_per_second": 4.659,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.3092457137144476,
|
| 1002 |
+
"grad_norm": 1.5194661669884653,
|
| 1003 |
+
"learning_rate": 8.726604351749503e-06,
|
| 1004 |
+
"loss": 0.2676,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.3119116250395721,
|
| 1009 |
+
"grad_norm": 1.7914357199240956,
|
| 1010 |
+
"learning_rate": 8.69541344887573e-06,
|
| 1011 |
+
"loss": 0.2779,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.31457753636469665,
|
| 1016 |
+
"grad_norm": 1.7310134858417519,
|
| 1017 |
+
"learning_rate": 8.66390235281248e-06,
|
| 1018 |
+
"loss": 0.2693,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.3172434476898212,
|
| 1023 |
+
"grad_norm": 1.5630957567521082,
|
| 1024 |
+
"learning_rate": 8.632073793873548e-06,
|
| 1025 |
+
"loss": 0.2709,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.31990935901494577,
|
| 1030 |
+
"grad_norm": 1.6939032554276248,
|
| 1031 |
+
"learning_rate": 8.599930529879669e-06,
|
| 1032 |
+
"loss": 0.277,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.31990935901494577,
|
| 1037 |
+
"eval_loss": 0.2749159336090088,
|
| 1038 |
+
"eval_runtime": 262.911,
|
| 1039 |
+
"eval_samples_per_second": 37.271,
|
| 1040 |
+
"eval_steps_per_second": 4.659,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.32257527034007033,
|
| 1045 |
+
"grad_norm": 1.5095047855589963,
|
| 1046 |
+
"learning_rate": 8.567475345919532e-06,
|
| 1047 |
+
"loss": 0.2629,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.32524118166519483,
|
| 1052 |
+
"grad_norm": 1.6080169624954084,
|
| 1053 |
+
"learning_rate": 8.534711054108487e-06,
|
| 1054 |
+
"loss": 0.2747,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.3279070929903194,
|
| 1059 |
+
"grad_norm": 1.3736048672777732,
|
| 1060 |
+
"learning_rate": 8.501640493344866e-06,
|
| 1061 |
+
"loss": 0.2644,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.33057300431544395,
|
| 1066 |
+
"grad_norm": 1.6744533289724879,
|
| 1067 |
+
"learning_rate": 8.468266529064025e-06,
|
| 1068 |
+
"loss": 0.263,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.3332389156405685,
|
| 1073 |
+
"grad_norm": 1.5519489984406099,
|
| 1074 |
+
"learning_rate": 8.434592052990044e-06,
|
| 1075 |
+
"loss": 0.2681,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.3332389156405685,
|
| 1080 |
+
"eval_loss": 0.2708764672279358,
|
| 1081 |
+
"eval_runtime": 262.898,
|
| 1082 |
+
"eval_samples_per_second": 37.273,
|
| 1083 |
+
"eval_steps_per_second": 4.66,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.33590482696569307,
|
| 1088 |
+
"grad_norm": 1.457281050568458,
|
| 1089 |
+
"learning_rate": 8.400619982885183e-06,
|
| 1090 |
+
"loss": 0.272,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.3385707382908176,
|
| 1095 |
+
"grad_norm": 1.5382553500774654,
|
| 1096 |
+
"learning_rate": 8.366353262297069e-06,
|
| 1097 |
+
"loss": 0.2713,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.34123664961594213,
|
| 1102 |
+
"grad_norm": 1.5058276908141497,
|
| 1103 |
+
"learning_rate": 8.331794860303644e-06,
|
| 1104 |
+
"loss": 0.2792,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.3439025609410667,
|
| 1109 |
+
"grad_norm": 1.5771918814364942,
|
| 1110 |
+
"learning_rate": 8.296947771255905e-06,
|
| 1111 |
+
"loss": 0.2628,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.34656847226619125,
|
| 1116 |
+
"grad_norm": 1.657853360665925,
|
| 1117 |
+
"learning_rate": 8.261815014518465e-06,
|
| 1118 |
+
"loss": 0.2699,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.34656847226619125,
|
| 1123 |
+
"eval_loss": 0.27181142568588257,
|
| 1124 |
+
"eval_runtime": 262.7648,
|
| 1125 |
+
"eval_samples_per_second": 37.292,
|
| 1126 |
+
"eval_steps_per_second": 4.662,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.3492343835913158,
|
| 1131 |
+
"grad_norm": 1.5883441926045438,
|
| 1132 |
+
"learning_rate": 8.226399634207929e-06,
|
| 1133 |
+
"loss": 0.2734,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.3519002949164403,
|
| 1138 |
+
"grad_norm": 1.5300996089830505,
|
| 1139 |
+
"learning_rate": 8.190704698929128e-06,
|
| 1140 |
+
"loss": 0.2638,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.3545662062415649,
|
| 1145 |
+
"grad_norm": 1.5262209102418558,
|
| 1146 |
+
"learning_rate": 8.154733301509249e-06,
|
| 1147 |
+
"loss": 0.2595,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.35723211756668943,
|
| 1152 |
+
"grad_norm": 1.6115009330913592,
|
| 1153 |
+
"learning_rate": 8.118488558729846e-06,
|
| 1154 |
+
"loss": 0.2663,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.359898028891814,
|
| 1159 |
+
"grad_norm": 1.5554372772477991,
|
| 1160 |
+
"learning_rate": 8.081973611056784e-06,
|
| 1161 |
+
"loss": 0.2682,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.359898028891814,
|
| 1166 |
+
"eval_loss": 0.267572283744812,
|
| 1167 |
+
"eval_runtime": 262.9095,
|
| 1168 |
+
"eval_samples_per_second": 37.271,
|
| 1169 |
+
"eval_steps_per_second": 4.659,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.36256394021693855,
|
| 1174 |
+
"grad_norm": 1.427915406398141,
|
| 1175 |
+
"learning_rate": 8.045191622368128e-06,
|
| 1176 |
+
"loss": 0.2593,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.36522985154206306,
|
| 1181 |
+
"grad_norm": 1.5334699622941028,
|
| 1182 |
+
"learning_rate": 8.008145779680011e-06,
|
| 1183 |
+
"loss": 0.2639,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.3678957628671876,
|
| 1188 |
+
"grad_norm": 1.4259972418658429,
|
| 1189 |
+
"learning_rate": 7.970839292870488e-06,
|
| 1190 |
+
"loss": 0.2669,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.3705616741923122,
|
| 1195 |
+
"grad_norm": 1.5749048798265741,
|
| 1196 |
+
"learning_rate": 7.933275394401407e-06,
|
| 1197 |
+
"loss": 0.2558,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 0.37322758551743673,
|
| 1202 |
+
"grad_norm": 1.4336549906080218,
|
| 1203 |
+
"learning_rate": 7.89545733903834e-06,
|
| 1204 |
+
"loss": 0.2668,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.37322758551743673,
|
| 1209 |
+
"eval_loss": 0.26621583104133606,
|
| 1210 |
+
"eval_runtime": 262.8653,
|
| 1211 |
+
"eval_samples_per_second": 37.278,
|
| 1212 |
+
"eval_steps_per_second": 4.66,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.3758934968425613,
|
| 1217 |
+
"grad_norm": 1.252003265223711,
|
| 1218 |
+
"learning_rate": 7.857388403568564e-06,
|
| 1219 |
+
"loss": 0.2562,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.3785594081676858,
|
| 1224 |
+
"grad_norm": 1.6246783307920207,
|
| 1225 |
+
"learning_rate": 7.819071886517134e-06,
|
| 1226 |
+
"loss": 0.2641,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.38122531949281036,
|
| 1231 |
+
"grad_norm": 1.4696921191370331,
|
| 1232 |
+
"learning_rate": 7.780511107861095e-06,
|
| 1233 |
+
"loss": 0.2574,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.3838912308179349,
|
| 1238 |
+
"grad_norm": 1.4689804757172065,
|
| 1239 |
+
"learning_rate": 7.741709408741804e-06,
|
| 1240 |
+
"loss": 0.2523,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.3865571421430595,
|
| 1245 |
+
"grad_norm": 1.464412667954816,
|
| 1246 |
+
"learning_rate": 7.702670151175435e-06,
|
| 1247 |
+
"loss": 0.2615,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.3865571421430595,
|
| 1252 |
+
"eval_loss": 0.26893940567970276,
|
| 1253 |
+
"eval_runtime": 262.8305,
|
| 1254 |
+
"eval_samples_per_second": 37.283,
|
| 1255 |
+
"eval_steps_per_second": 4.661,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.38922305346818403,
|
| 1260 |
+
"grad_norm": 1.4939931694247328,
|
| 1261 |
+
"learning_rate": 7.663396717761687e-06,
|
| 1262 |
+
"loss": 0.2598,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.39188896479330854,
|
| 1267 |
+
"grad_norm": 1.3658418367677023,
|
| 1268 |
+
"learning_rate": 7.6238925113906715e-06,
|
| 1269 |
+
"loss": 0.2595,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.3945548761184331,
|
| 1274 |
+
"grad_norm": 1.402377150997183,
|
| 1275 |
+
"learning_rate": 7.5841609549480854e-06,
|
| 1276 |
+
"loss": 0.2706,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.39722078744355765,
|
| 1281 |
+
"grad_norm": 1.6251726176323527,
|
| 1282 |
+
"learning_rate": 7.544205491018626e-06,
|
| 1283 |
+
"loss": 0.252,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.3998866987686822,
|
| 1288 |
+
"grad_norm": 1.4760120447972431,
|
| 1289 |
+
"learning_rate": 7.5040295815877e-06,
|
| 1290 |
+
"loss": 0.2501,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.3998866987686822,
|
| 1295 |
+
"eval_loss": 0.2582685649394989,
|
| 1296 |
+
"eval_runtime": 262.8368,
|
| 1297 |
+
"eval_samples_per_second": 37.282,
|
| 1298 |
+
"eval_steps_per_second": 4.661,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.4025526100938068,
|
| 1303 |
+
"grad_norm": 1.4743205374828412,
|
| 1304 |
+
"learning_rate": 7.463636707741458e-06,
|
| 1305 |
+
"loss": 0.2604,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.4052185214189313,
|
| 1310 |
+
"grad_norm": 1.3923700543379627,
|
| 1311 |
+
"learning_rate": 7.423030369365175e-06,
|
| 1312 |
+
"loss": 0.264,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.40788443274405584,
|
| 1317 |
+
"grad_norm": 1.4356363473684057,
|
| 1318 |
+
"learning_rate": 7.382214084839993e-06,
|
| 1319 |
+
"loss": 0.2565,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.4105503440691804,
|
| 1324 |
+
"grad_norm": 1.4051425897192589,
|
| 1325 |
+
"learning_rate": 7.341191390738073e-06,
|
| 1326 |
+
"loss": 0.2638,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.41321625539430495,
|
| 1331 |
+
"grad_norm": 1.3088487920660643,
|
| 1332 |
+
"learning_rate": 7.299965841516164e-06,
|
| 1333 |
+
"loss": 0.2545,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.41321625539430495,
|
| 1338 |
+
"eval_loss": 0.25675299763679504,
|
| 1339 |
+
"eval_runtime": 262.9203,
|
| 1340 |
+
"eval_samples_per_second": 37.27,
|
| 1341 |
+
"eval_steps_per_second": 4.659,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.4158821667194295,
|
| 1346 |
+
"grad_norm": 1.5688903433049168,
|
| 1347 |
+
"learning_rate": 7.2585410092076154e-06,
|
| 1348 |
+
"loss": 0.2637,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.418548078044554,
|
| 1353 |
+
"grad_norm": 1.431976384484085,
|
| 1354 |
+
"learning_rate": 7.216920483112886e-06,
|
| 1355 |
+
"loss": 0.2489,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.4212139893696786,
|
| 1360 |
+
"grad_norm": 1.531858850303692,
|
| 1361 |
+
"learning_rate": 7.175107869488539e-06,
|
| 1362 |
+
"loss": 0.2545,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.42387990069480314,
|
| 1367 |
+
"grad_norm": 1.4865553973552155,
|
| 1368 |
+
"learning_rate": 7.133106791234771e-06,
|
| 1369 |
+
"loss": 0.2644,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.4265458120199277,
|
| 1374 |
+
"grad_norm": 1.66021566236256,
|
| 1375 |
+
"learning_rate": 7.090920887581507e-06,
|
| 1376 |
+
"loss": 0.2618,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.4265458120199277,
|
| 1381 |
+
"eval_loss": 0.25225213170051575,
|
| 1382 |
+
"eval_runtime": 262.8963,
|
| 1383 |
+
"eval_samples_per_second": 37.273,
|
| 1384 |
+
"eval_steps_per_second": 4.66,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.42921172334505225,
|
| 1389 |
+
"grad_norm": 1.6133520399654793,
|
| 1390 |
+
"learning_rate": 7.048553813773075e-06,
|
| 1391 |
+
"loss": 0.246,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.43187763467017676,
|
| 1396 |
+
"grad_norm": 1.496263689865299,
|
| 1397 |
+
"learning_rate": 7.006009240751488e-06,
|
| 1398 |
+
"loss": 0.248,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.4345435459953013,
|
| 1403 |
+
"grad_norm": 1.529592079575296,
|
| 1404 |
+
"learning_rate": 6.963290854838376e-06,
|
| 1405 |
+
"loss": 0.2592,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.4372094573204259,
|
| 1410 |
+
"grad_norm": 1.3359842663344557,
|
| 1411 |
+
"learning_rate": 6.920402357415582e-06,
|
| 1412 |
+
"loss": 0.2502,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.43987536864555044,
|
| 1417 |
+
"grad_norm": 1.5115966603020272,
|
| 1418 |
+
"learning_rate": 6.877347464604446e-06,
|
| 1419 |
+
"loss": 0.2615,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.43987536864555044,
|
| 1424 |
+
"eval_loss": 0.2549818754196167,
|
| 1425 |
+
"eval_runtime": 263.068,
|
| 1426 |
+
"eval_samples_per_second": 37.249,
|
| 1427 |
+
"eval_steps_per_second": 4.657,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.442541279970675,
|
| 1432 |
+
"grad_norm": 1.7762192007454982,
|
| 1433 |
+
"learning_rate": 6.834129906943822e-06,
|
| 1434 |
+
"loss": 0.2468,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.4452071912957995,
|
| 1439 |
+
"grad_norm": 1.510769947566683,
|
| 1440 |
+
"learning_rate": 6.790753429066838e-06,
|
| 1441 |
+
"loss": 0.2522,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.44787310262092406,
|
| 1446 |
+
"grad_norm": 1.287630606180817,
|
| 1447 |
+
"learning_rate": 6.7472217893764465e-06,
|
| 1448 |
+
"loss": 0.2468,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.4505390139460486,
|
| 1453 |
+
"grad_norm": 1.5134316444240614,
|
| 1454 |
+
"learning_rate": 6.70353875971976e-06,
|
| 1455 |
+
"loss": 0.2525,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.4532049252711732,
|
| 1460 |
+
"grad_norm": 1.4296879650147967,
|
| 1461 |
+
"learning_rate": 6.659708125061242e-06,
|
| 1462 |
+
"loss": 0.2512,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.4532049252711732,
|
| 1467 |
+
"eval_loss": 0.24882382154464722,
|
| 1468 |
+
"eval_runtime": 262.8695,
|
| 1469 |
+
"eval_samples_per_second": 37.277,
|
| 1470 |
+
"eval_steps_per_second": 4.66,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.45587083659629773,
|
| 1475 |
+
"grad_norm": 1.4884981725217645,
|
| 1476 |
+
"learning_rate": 6.615733683154762e-06,
|
| 1477 |
+
"loss": 0.2522,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 0.45853674792142224,
|
| 1482 |
+
"grad_norm": 1.4903981491956688,
|
| 1483 |
+
"learning_rate": 6.571619244214521e-06,
|
| 1484 |
+
"loss": 0.2505,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.4612026592465468,
|
| 1489 |
+
"grad_norm": 1.3786999091258259,
|
| 1490 |
+
"learning_rate": 6.527368630584919e-06,
|
| 1491 |
+
"loss": 0.2596,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.46386857057167136,
|
| 1496 |
+
"grad_norm": 1.588650909339789,
|
| 1497 |
+
"learning_rate": 6.482985676409368e-06,
|
| 1498 |
+
"loss": 0.2494,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.4665344818967959,
|
| 1503 |
+
"grad_norm": 1.4631431734629796,
|
| 1504 |
+
"learning_rate": 6.438474227298065e-06,
|
| 1505 |
+
"loss": 0.245,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.4665344818967959,
|
| 1510 |
+
"eval_loss": 0.25038692355155945,
|
| 1511 |
+
"eval_runtime": 262.8028,
|
| 1512 |
+
"eval_samples_per_second": 37.287,
|
| 1513 |
+
"eval_steps_per_second": 4.661,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.4692003932219205,
|
| 1518 |
+
"grad_norm": 1.5412537109524729,
|
| 1519 |
+
"learning_rate": 6.393838139994797e-06,
|
| 1520 |
+
"loss": 0.2595,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.471866304547045,
|
| 1525 |
+
"grad_norm": 1.5353759046724331,
|
| 1526 |
+
"learning_rate": 6.349081282042768e-06,
|
| 1527 |
+
"loss": 0.2516,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.47453221587216954,
|
| 1532 |
+
"grad_norm": 1.783528374337059,
|
| 1533 |
+
"learning_rate": 6.304207531449486e-06,
|
| 1534 |
+
"loss": 0.2469,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.4771981271972941,
|
| 1539 |
+
"grad_norm": 1.5629443542703378,
|
| 1540 |
+
"learning_rate": 6.259220776350746e-06,
|
| 1541 |
+
"loss": 0.2354,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.47986403852241866,
|
| 1546 |
+
"grad_norm": 1.5839504852392476,
|
| 1547 |
+
"learning_rate": 6.2141249146737545e-06,
|
| 1548 |
+
"loss": 0.2503,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.47986403852241866,
|
| 1553 |
+
"eval_loss": 0.24808603525161743,
|
| 1554 |
+
"eval_runtime": 262.9156,
|
| 1555 |
+
"eval_samples_per_second": 37.271,
|
| 1556 |
+
"eval_steps_per_second": 4.659,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.4825299498475432,
|
| 1561 |
+
"grad_norm": 1.2856913499546363,
|
| 1562 |
+
"learning_rate": 6.168923853799369e-06,
|
| 1563 |
+
"loss": 0.2466,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.4851958611726677,
|
| 1568 |
+
"grad_norm": 1.5335554959397042,
|
| 1569 |
+
"learning_rate": 6.123621510223552e-06,
|
| 1570 |
+
"loss": 0.2467,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.4878617724977923,
|
| 1575 |
+
"grad_norm": 1.4473834266997454,
|
| 1576 |
+
"learning_rate": 6.0782218092180164e-06,
|
| 1577 |
+
"loss": 0.2523,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.49052768382291684,
|
| 1582 |
+
"grad_norm": 1.394637034197444,
|
| 1583 |
+
"learning_rate": 6.032728684490118e-06,
|
| 1584 |
+
"loss": 0.2428,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.4931935951480414,
|
| 1589 |
+
"grad_norm": 1.468907580360217,
|
| 1590 |
+
"learning_rate": 5.987146077842015e-06,
|
| 1591 |
+
"loss": 0.2402,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.4931935951480414,
|
| 1596 |
+
"eval_loss": 0.24496783316135406,
|
| 1597 |
+
"eval_runtime": 262.8614,
|
| 1598 |
+
"eval_samples_per_second": 37.278,
|
| 1599 |
+
"eval_steps_per_second": 4.66,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.49585950647316596,
|
| 1604 |
+
"grad_norm": 1.3904834622458775,
|
| 1605 |
+
"learning_rate": 5.941477938829126e-06,
|
| 1606 |
+
"loss": 0.2526,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.49852541779829046,
|
| 1611 |
+
"grad_norm": 1.4889823952197347,
|
| 1612 |
+
"learning_rate": 5.8957282244179125e-06,
|
| 1613 |
+
"loss": 0.2462,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.501191329123415,
|
| 1618 |
+
"grad_norm": 1.5388317154311413,
|
| 1619 |
+
"learning_rate": 5.84990089864303e-06,
|
| 1620 |
+
"loss": 0.2343,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.5038572404485396,
|
| 1625 |
+
"grad_norm": 1.4480277186406976,
|
| 1626 |
+
"learning_rate": 5.803999932263859e-06,
|
| 1627 |
+
"loss": 0.2403,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.5065231517736641,
|
| 1632 |
+
"grad_norm": 1.386625092855129,
|
| 1633 |
+
"learning_rate": 5.7580293024204455e-06,
|
| 1634 |
+
"loss": 0.2346,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.5065231517736641,
|
| 1639 |
+
"eval_loss": 0.24397991597652435,
|
| 1640 |
+
"eval_runtime": 263.0578,
|
| 1641 |
+
"eval_samples_per_second": 37.25,
|
| 1642 |
+
"eval_steps_per_second": 4.657,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 0.5091890630987886,
|
| 1647 |
+
"grad_norm": 1.4313341683411982,
|
| 1648 |
+
"learning_rate": 5.7119929922889065e-06,
|
| 1649 |
+
"loss": 0.251,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 0.5118549744239133,
|
| 1654 |
+
"grad_norm": 1.4840350228738965,
|
| 1655 |
+
"learning_rate": 5.665894990736301e-06,
|
| 1656 |
+
"loss": 0.2443,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.5145208857490378,
|
| 1661 |
+
"grad_norm": 1.4825583514024858,
|
| 1662 |
+
"learning_rate": 5.6197392919750095e-06,
|
| 1663 |
+
"loss": 0.2492,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 0.5171867970741624,
|
| 1668 |
+
"grad_norm": 1.309952322214834,
|
| 1669 |
+
"learning_rate": 5.573529895216648e-06,
|
| 1670 |
+
"loss": 0.2472,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.5198527083992869,
|
| 1675 |
+
"grad_norm": 1.4272349945023302,
|
| 1676 |
+
"learning_rate": 5.5272708043255605e-06,
|
| 1677 |
+
"loss": 0.2413,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 0.5198527083992869,
|
| 1682 |
+
"eval_loss": 0.24250540137290955,
|
| 1683 |
+
"eval_runtime": 262.9015,
|
| 1684 |
+
"eval_samples_per_second": 37.273,
|
| 1685 |
+
"eval_steps_per_second": 4.66,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.5225186197244114,
|
| 1690 |
+
"grad_norm": 1.3899478056194363,
|
| 1691 |
+
"learning_rate": 5.480966027471889e-06,
|
| 1692 |
+
"loss": 0.237,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.525184531049536,
|
| 1697 |
+
"grad_norm": 1.4329413761949321,
|
| 1698 |
+
"learning_rate": 5.434619576784288e-06,
|
| 1699 |
+
"loss": 0.2449,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.5278504423746605,
|
| 1704 |
+
"grad_norm": 1.4472221948239792,
|
| 1705 |
+
"learning_rate": 5.388235468002286e-06,
|
| 1706 |
+
"loss": 0.2237,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.5305163536997851,
|
| 1711 |
+
"grad_norm": 1.4195674353945604,
|
| 1712 |
+
"learning_rate": 5.341817720128344e-06,
|
| 1713 |
+
"loss": 0.2454,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.5331822650249096,
|
| 1718 |
+
"grad_norm": 1.3103614120039029,
|
| 1719 |
+
"learning_rate": 5.295370355079615e-06,
|
| 1720 |
+
"loss": 0.24,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.5331822650249096,
|
| 1725 |
+
"eval_loss": 0.2383483648300171,
|
| 1726 |
+
"eval_runtime": 262.9776,
|
| 1727 |
+
"eval_samples_per_second": 37.262,
|
| 1728 |
+
"eval_steps_per_second": 4.658,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.5358481763500341,
|
| 1733 |
+
"grad_norm": 1.3133683565273986,
|
| 1734 |
+
"learning_rate": 5.248897397339462e-06,
|
| 1735 |
+
"loss": 0.2373,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.5385140876751587,
|
| 1740 |
+
"grad_norm": 1.531592053829392,
|
| 1741 |
+
"learning_rate": 5.202402873608763e-06,
|
| 1742 |
+
"loss": 0.2355,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.5411799990002832,
|
| 1747 |
+
"grad_norm": 1.3614359816256922,
|
| 1748 |
+
"learning_rate": 5.155890812457e-06,
|
| 1749 |
+
"loss": 0.2415,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 0.5438459103254079,
|
| 1754 |
+
"grad_norm": 1.3385718906961956,
|
| 1755 |
+
"learning_rate": 5.1093652439732036e-06,
|
| 1756 |
+
"loss": 0.2319,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 0.5465118216505324,
|
| 1761 |
+
"grad_norm": 1.3010476401905142,
|
| 1762 |
+
"learning_rate": 5.062830199416764e-06,
|
| 1763 |
+
"loss": 0.2398,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.5465118216505324,
|
| 1768 |
+
"eval_loss": 0.24081052839756012,
|
| 1769 |
+
"eval_runtime": 262.8874,
|
| 1770 |
+
"eval_samples_per_second": 37.275,
|
| 1771 |
+
"eval_steps_per_second": 4.66,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.5491777329756569,
|
| 1776 |
+
"grad_norm": 1.364305498532448,
|
| 1777 |
+
"learning_rate": 5.0162897108681375e-06,
|
| 1778 |
+
"loss": 0.2393,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.5518436443007815,
|
| 1783 |
+
"grad_norm": 1.500947573673284,
|
| 1784 |
+
"learning_rate": 4.969747810879478e-06,
|
| 1785 |
+
"loss": 0.2447,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.554509555625906,
|
| 1790 |
+
"grad_norm": 1.320594568969342,
|
| 1791 |
+
"learning_rate": 4.923208532125235e-06,
|
| 1792 |
+
"loss": 0.2342,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 0.5571754669510306,
|
| 1797 |
+
"grad_norm": 1.5324196826217082,
|
| 1798 |
+
"learning_rate": 4.876675907052745e-06,
|
| 1799 |
+
"loss": 0.2355,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 0.5598413782761551,
|
| 1804 |
+
"grad_norm": 1.4300989151801904,
|
| 1805 |
+
"learning_rate": 4.8301539675328205e-06,
|
| 1806 |
+
"loss": 0.2473,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.5598413782761551,
|
| 1811 |
+
"eval_loss": 0.23838448524475098,
|
| 1812 |
+
"eval_runtime": 262.9492,
|
| 1813 |
+
"eval_samples_per_second": 37.266,
|
| 1814 |
+
"eval_steps_per_second": 4.659,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.5625072896012796,
|
| 1819 |
+
"grad_norm": 1.4958278476823126,
|
| 1820 |
+
"learning_rate": 4.783646744510416e-06,
|
| 1821 |
+
"loss": 0.2202,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.5651732009264042,
|
| 1826 |
+
"grad_norm": 1.4255485000398498,
|
| 1827 |
+
"learning_rate": 4.737158267655358e-06,
|
| 1828 |
+
"loss": 0.2367,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.5678391122515287,
|
| 1833 |
+
"grad_norm": 1.320727510403474,
|
| 1834 |
+
"learning_rate": 4.690692565013193e-06,
|
| 1835 |
+
"loss": 0.2355,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.5705050235766533,
|
| 1840 |
+
"grad_norm": 1.3566414156014617,
|
| 1841 |
+
"learning_rate": 4.644253662656167e-06,
|
| 1842 |
+
"loss": 0.2306,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.5731709349017778,
|
| 1847 |
+
"grad_norm": 1.3929922145408924,
|
| 1848 |
+
"learning_rate": 4.597845584334387e-06,
|
| 1849 |
+
"loss": 0.2423,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.5731709349017778,
|
| 1854 |
+
"eval_loss": 0.234757199883461,
|
| 1855 |
+
"eval_runtime": 262.9076,
|
| 1856 |
+
"eval_samples_per_second": 37.272,
|
| 1857 |
+
"eval_steps_per_second": 4.659,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.5758368462269023,
|
| 1862 |
+
"grad_norm": 1.374609479412353,
|
| 1863 |
+
"learning_rate": 4.55147235112718e-06,
|
| 1864 |
+
"loss": 0.2273,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.578502757552027,
|
| 1869 |
+
"grad_norm": 1.4785794464229693,
|
| 1870 |
+
"learning_rate": 4.505137981094675e-06,
|
| 1871 |
+
"loss": 0.2343,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.5811686688771515,
|
| 1876 |
+
"grad_norm": 1.4795260893327034,
|
| 1877 |
+
"learning_rate": 4.458846488929663e-06,
|
| 1878 |
+
"loss": 0.2324,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.5838345802022761,
|
| 1883 |
+
"grad_norm": 1.401523269373386,
|
| 1884 |
+
"learning_rate": 4.41260188560973e-06,
|
| 1885 |
+
"loss": 0.2345,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.5865004915274006,
|
| 1890 |
+
"grad_norm": 1.476962877773437,
|
| 1891 |
+
"learning_rate": 4.366408178049728e-06,
|
| 1892 |
+
"loss": 0.2294,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.5865004915274006,
|
| 1897 |
+
"eval_loss": 0.23114009201526642,
|
| 1898 |
+
"eval_runtime": 262.8457,
|
| 1899 |
+
"eval_samples_per_second": 37.28,
|
| 1900 |
+
"eval_steps_per_second": 4.661,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 0.5891664028525251,
|
| 1905 |
+
"grad_norm": 1.4302372289930234,
|
| 1906 |
+
"learning_rate": 4.32026936875459e-06,
|
| 1907 |
+
"loss": 0.2276,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 0.5918323141776497,
|
| 1912 |
+
"grad_norm": 1.4473961518449265,
|
| 1913 |
+
"learning_rate": 4.274189455472529e-06,
|
| 1914 |
+
"loss": 0.2273,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 0.5944982255027742,
|
| 1919 |
+
"grad_norm": 1.4008641287788706,
|
| 1920 |
+
"learning_rate": 4.228172430848645e-06,
|
| 1921 |
+
"loss": 0.2288,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.5971641368278988,
|
| 1926 |
+
"grad_norm": 1.4894210929250196,
|
| 1927 |
+
"learning_rate": 4.182222282078983e-06,
|
| 1928 |
+
"loss": 0.2357,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.5998300481530233,
|
| 1933 |
+
"grad_norm": 1.306703863087604,
|
| 1934 |
+
"learning_rate": 4.136342990565055e-06,
|
| 1935 |
+
"loss": 0.2403,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.5998300481530233,
|
| 1940 |
+
"eval_loss": 0.23227499425411224,
|
| 1941 |
+
"eval_runtime": 262.8907,
|
| 1942 |
+
"eval_samples_per_second": 37.274,
|
| 1943 |
+
"eval_steps_per_second": 4.66,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 0.6024959594781478,
|
| 1948 |
+
"grad_norm": 1.4013172843098054,
|
| 1949 |
+
"learning_rate": 4.090538531568867e-06,
|
| 1950 |
+
"loss": 0.2296,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 0.6051618708032724,
|
| 1955 |
+
"grad_norm": 1.3209487720250683,
|
| 1956 |
+
"learning_rate": 4.0448128738684775e-06,
|
| 1957 |
+
"loss": 0.2328,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 0.6078277821283969,
|
| 1962 |
+
"grad_norm": 1.4716940731508306,
|
| 1963 |
+
"learning_rate": 3.999169979414123e-06,
|
| 1964 |
+
"loss": 0.2325,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 0.6104936934535216,
|
| 1969 |
+
"grad_norm": 1.4656992929067083,
|
| 1970 |
+
"learning_rate": 3.9536138029849244e-06,
|
| 1971 |
+
"loss": 0.2168,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 0.6131596047786461,
|
| 1976 |
+
"grad_norm": 1.3738056017255034,
|
| 1977 |
+
"learning_rate": 3.908148291846225e-06,
|
| 1978 |
+
"loss": 0.2319,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 0.6131596047786461,
|
| 1983 |
+
"eval_loss": 0.22970426082611084,
|
| 1984 |
+
"eval_runtime": 262.999,
|
| 1985 |
+
"eval_samples_per_second": 37.259,
|
| 1986 |
+
"eval_steps_per_second": 4.658,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 0.6158255161037706,
|
| 1991 |
+
"grad_norm": 1.5466991422842942,
|
| 1992 |
+
"learning_rate": 3.862777385407569e-06,
|
| 1993 |
+
"loss": 0.2341,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 0.6184914274288952,
|
| 1998 |
+
"grad_norm": 1.3112376666812904,
|
| 1999 |
+
"learning_rate": 3.817505014881378e-06,
|
| 2000 |
+
"loss": 0.2233,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 0.6211573387540197,
|
| 2005 |
+
"grad_norm": 1.2953029619867271,
|
| 2006 |
+
"learning_rate": 3.7723351029423143e-06,
|
| 2007 |
+
"loss": 0.2267,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 0.6238232500791442,
|
| 2012 |
+
"grad_norm": 1.2975930501539998,
|
| 2013 |
+
"learning_rate": 3.72727156338741e-06,
|
| 2014 |
+
"loss": 0.2217,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 0.6264891614042688,
|
| 2019 |
+
"grad_norm": 1.450217813101867,
|
| 2020 |
+
"learning_rate": 3.6823183007969375e-06,
|
| 2021 |
+
"loss": 0.222,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 0.6264891614042688,
|
| 2026 |
+
"eval_loss": 0.22879666090011597,
|
| 2027 |
+
"eval_runtime": 262.998,
|
| 2028 |
+
"eval_samples_per_second": 37.259,
|
| 2029 |
+
"eval_steps_per_second": 4.658,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.6291550727293933,
|
| 2034 |
+
"grad_norm": 1.4772827053597228,
|
| 2035 |
+
"learning_rate": 3.637479210196102e-06,
|
| 2036 |
+
"loss": 0.224,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 0.6318209840545179,
|
| 2041 |
+
"grad_norm": 1.3820541090280336,
|
| 2042 |
+
"learning_rate": 3.59275817671755e-06,
|
| 2043 |
+
"loss": 0.2324,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 0.6344868953796424,
|
| 2048 |
+
"grad_norm": 1.6023213257482982,
|
| 2049 |
+
"learning_rate": 3.548159075264738e-06,
|
| 2050 |
+
"loss": 0.2402,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 0.6371528067047669,
|
| 2055 |
+
"grad_norm": 1.3905766577987069,
|
| 2056 |
+
"learning_rate": 3.5036857701761857e-06,
|
| 2057 |
+
"loss": 0.2296,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 0.6398187180298915,
|
| 2062 |
+
"grad_norm": 1.1561354043825967,
|
| 2063 |
+
"learning_rate": 3.4593421148906523e-06,
|
| 2064 |
+
"loss": 0.2193,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 0.6398187180298915,
|
| 2069 |
+
"eval_loss": 0.2302982062101364,
|
| 2070 |
+
"eval_runtime": 262.8211,
|
| 2071 |
+
"eval_samples_per_second": 37.284,
|
| 2072 |
+
"eval_steps_per_second": 4.661,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.642484629355016,
|
| 2077 |
+
"grad_norm": 1.597294433505113,
|
| 2078 |
+
"learning_rate": 3.4151319516132414e-06,
|
| 2079 |
+
"loss": 0.2241,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.6451505406801407,
|
| 2084 |
+
"grad_norm": 1.3695543102988872,
|
| 2085 |
+
"learning_rate": 3.3710591109824954e-06,
|
| 2086 |
+
"loss": 0.228,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 0.6478164520052652,
|
| 2091 |
+
"grad_norm": 1.4718036858879708,
|
| 2092 |
+
"learning_rate": 3.3271274117384834e-06,
|
| 2093 |
+
"loss": 0.2248,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.6504823633303897,
|
| 2098 |
+
"grad_norm": 1.4542440170222004,
|
| 2099 |
+
"learning_rate": 3.2833406603919243e-06,
|
| 2100 |
+
"loss": 0.2255,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.6531482746555143,
|
| 2105 |
+
"grad_norm": 1.4323637810184542,
|
| 2106 |
+
"learning_rate": 3.239702650894364e-06,
|
| 2107 |
+
"loss": 0.2252,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.6531482746555143,
|
| 2112 |
+
"eval_loss": 0.22466669976711273,
|
| 2113 |
+
"eval_runtime": 263.0427,
|
| 2114 |
+
"eval_samples_per_second": 37.253,
|
| 2115 |
+
"eval_steps_per_second": 4.657,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.6558141859806388,
|
| 2120 |
+
"grad_norm": 1.3508621042110618,
|
| 2121 |
+
"learning_rate": 3.1962171643094474e-06,
|
| 2122 |
+
"loss": 0.2262,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.6584800973057634,
|
| 2127 |
+
"grad_norm": 1.5246150137269523,
|
| 2128 |
+
"learning_rate": 3.152887968485303e-06,
|
| 2129 |
+
"loss": 0.2268,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.6611460086308879,
|
| 2134 |
+
"grad_norm": 1.383892905949888,
|
| 2135 |
+
"learning_rate": 3.1097188177280735e-06,
|
| 2136 |
+
"loss": 0.2307,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.6638119199560124,
|
| 2141 |
+
"grad_norm": 1.4496544374013476,
|
| 2142 |
+
"learning_rate": 3.0667134524766173e-06,
|
| 2143 |
+
"loss": 0.2306,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.666477831281137,
|
| 2148 |
+
"grad_norm": 1.3608828390672776,
|
| 2149 |
+
"learning_rate": 3.023875598978419e-06,
|
| 2150 |
+
"loss": 0.2304,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.666477831281137,
|
| 2155 |
+
"eval_loss": 0.22111880779266357,
|
| 2156 |
+
"eval_runtime": 263.0181,
|
| 2157 |
+
"eval_samples_per_second": 37.256,
|
| 2158 |
+
"eval_steps_per_second": 4.657,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.6691437426062615,
|
| 2163 |
+
"grad_norm": 1.4266456422805869,
|
| 2164 |
+
"learning_rate": 2.981208968966721e-06,
|
| 2165 |
+
"loss": 0.2308,
|
| 2166 |
+
"step": 2510
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.6718096539313861,
|
| 2170 |
+
"grad_norm": 1.4406082869964068,
|
| 2171 |
+
"learning_rate": 2.9387172593389148e-06,
|
| 2172 |
+
"loss": 0.2279,
|
| 2173 |
+
"step": 2520
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.6744755652565106,
|
| 2177 |
+
"grad_norm": 1.3971739179858862,
|
| 2178 |
+
"learning_rate": 2.896404151836227e-06,
|
| 2179 |
+
"loss": 0.2269,
|
| 2180 |
+
"step": 2530
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.6771414765816351,
|
| 2184 |
+
"grad_norm": 1.4152700853128788,
|
| 2185 |
+
"learning_rate": 2.8542733127247024e-06,
|
| 2186 |
+
"loss": 0.2302,
|
| 2187 |
+
"step": 2540
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.6798073879067598,
|
| 2191 |
+
"grad_norm": 1.6872576664694825,
|
| 2192 |
+
"learning_rate": 2.812328392477536e-06,
|
| 2193 |
+
"loss": 0.2139,
|
| 2194 |
+
"step": 2550
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.6798073879067598,
|
| 2198 |
+
"eval_loss": 0.2199471890926361,
|
| 2199 |
+
"eval_runtime": 263.0108,
|
| 2200 |
+
"eval_samples_per_second": 37.257,
|
| 2201 |
+
"eval_steps_per_second": 4.658,
|
| 2202 |
+
"step": 2550
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 0.6824732992318843,
|
| 2206 |
+
"grad_norm": 1.7126358001487447,
|
| 2207 |
+
"learning_rate": 2.7705730254587802e-06,
|
| 2208 |
+
"loss": 0.2237,
|
| 2209 |
+
"step": 2560
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 0.6851392105570089,
|
| 2213 |
+
"grad_norm": 1.3640091375946775,
|
| 2214 |
+
"learning_rate": 2.729010829608442e-06,
|
| 2215 |
+
"loss": 0.2166,
|
| 2216 |
+
"step": 2570
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 0.6878051218821334,
|
| 2220 |
+
"grad_norm": 1.3205123742802625,
|
| 2221 |
+
"learning_rate": 2.6876454061289892e-06,
|
| 2222 |
+
"loss": 0.2291,
|
| 2223 |
+
"step": 2580
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 0.6904710332072579,
|
| 2227 |
+
"grad_norm": 1.41857906965664,
|
| 2228 |
+
"learning_rate": 2.646480339173337e-06,
|
| 2229 |
+
"loss": 0.2226,
|
| 2230 |
+
"step": 2590
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 0.6931369445323825,
|
| 2234 |
+
"grad_norm": 1.4353906946512758,
|
| 2235 |
+
"learning_rate": 2.6055191955342886e-06,
|
| 2236 |
+
"loss": 0.2186,
|
| 2237 |
+
"step": 2600
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 0.6931369445323825,
|
| 2241 |
+
"eval_loss": 0.219247967004776,
|
| 2242 |
+
"eval_runtime": 262.8123,
|
| 2243 |
+
"eval_samples_per_second": 37.285,
|
| 2244 |
+
"eval_steps_per_second": 4.661,
|
| 2245 |
+
"step": 2600
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 0.695802855857507,
|
| 2249 |
+
"grad_norm": 1.509318119256484,
|
| 2250 |
+
"learning_rate": 2.564765524335478e-06,
|
| 2251 |
+
"loss": 0.2249,
|
| 2252 |
+
"step": 2610
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 0.6984687671826316,
|
| 2256 |
+
"grad_norm": 1.5006689440254304,
|
| 2257 |
+
"learning_rate": 2.524222856723869e-06,
|
| 2258 |
+
"loss": 0.2244,
|
| 2259 |
+
"step": 2620
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 0.7011346785077561,
|
| 2263 |
+
"grad_norm": 1.4381458956509503,
|
| 2264 |
+
"learning_rate": 2.483894705563778e-06,
|
| 2265 |
+
"loss": 0.2168,
|
| 2266 |
+
"step": 2630
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 0.7038005898328806,
|
| 2270 |
+
"grad_norm": 1.4917726610546065,
|
| 2271 |
+
"learning_rate": 2.4437845651325116e-06,
|
| 2272 |
+
"loss": 0.2175,
|
| 2273 |
+
"step": 2640
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 0.7064665011580052,
|
| 2277 |
+
"grad_norm": 1.3982582754588275,
|
| 2278 |
+
"learning_rate": 2.403895910817593e-06,
|
| 2279 |
+
"loss": 0.2156,
|
| 2280 |
+
"step": 2650
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 0.7064665011580052,
|
| 2284 |
+
"eval_loss": 0.21830175817012787,
|
| 2285 |
+
"eval_runtime": 262.8854,
|
| 2286 |
+
"eval_samples_per_second": 37.275,
|
| 2287 |
+
"eval_steps_per_second": 4.66,
|
| 2288 |
+
"step": 2650
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 0.7091324124831297,
|
| 2292 |
+
"grad_norm": 1.5108046870677676,
|
| 2293 |
+
"learning_rate": 2.364232198815638e-06,
|
| 2294 |
+
"loss": 0.2111,
|
| 2295 |
+
"step": 2660
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 0.7117983238082544,
|
| 2299 |
+
"grad_norm": 1.3667591912176449,
|
| 2300 |
+
"learning_rate": 2.3247968658328825e-06,
|
| 2301 |
+
"loss": 0.2224,
|
| 2302 |
+
"step": 2670
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 0.7144642351333789,
|
| 2306 |
+
"grad_norm": 1.4017600569153348,
|
| 2307 |
+
"learning_rate": 2.285593328787414e-06,
|
| 2308 |
+
"loss": 0.213,
|
| 2309 |
+
"step": 2680
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 0.7171301464585034,
|
| 2313 |
+
"grad_norm": 1.440902705270559,
|
| 2314 |
+
"learning_rate": 2.246624984513099e-06,
|
| 2315 |
+
"loss": 0.2283,
|
| 2316 |
+
"step": 2690
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 0.719796057783628,
|
| 2320 |
+
"grad_norm": 1.236716519182564,
|
| 2321 |
+
"learning_rate": 2.2078952094652705e-06,
|
| 2322 |
+
"loss": 0.2187,
|
| 2323 |
+
"step": 2700
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 0.719796057783628,
|
| 2327 |
+
"eval_loss": 0.21585261821746826,
|
| 2328 |
+
"eval_runtime": 262.7547,
|
| 2329 |
+
"eval_samples_per_second": 37.293,
|
| 2330 |
+
"eval_steps_per_second": 4.662,
|
| 2331 |
+
"step": 2700
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 0.7224619691087525,
|
| 2335 |
+
"grad_norm": 1.3538906092368184,
|
| 2336 |
+
"learning_rate": 2.1694073594281663e-06,
|
| 2337 |
+
"loss": 0.2221,
|
| 2338 |
+
"step": 2710
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 0.7251278804338771,
|
| 2342 |
+
"grad_norm": 1.5194150460697764,
|
| 2343 |
+
"learning_rate": 2.131164769224164e-06,
|
| 2344 |
+
"loss": 0.2192,
|
| 2345 |
+
"step": 2720
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 0.7277937917590016,
|
| 2349 |
+
"grad_norm": 1.3384474695172988,
|
| 2350 |
+
"learning_rate": 2.0931707524248268e-06,
|
| 2351 |
+
"loss": 0.2249,
|
| 2352 |
+
"step": 2730
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 0.7304597030841261,
|
| 2356 |
+
"grad_norm": 1.5838731189086506,
|
| 2357 |
+
"learning_rate": 2.0554286010638076e-06,
|
| 2358 |
+
"loss": 0.2112,
|
| 2359 |
+
"step": 2740
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 0.7331256144092507,
|
| 2363 |
+
"grad_norm": 1.569671558314134,
|
| 2364 |
+
"learning_rate": 2.017941585351591e-06,
|
| 2365 |
+
"loss": 0.222,
|
| 2366 |
+
"step": 2750
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 0.7331256144092507,
|
| 2370 |
+
"eval_loss": 0.21738137304782867,
|
| 2371 |
+
"eval_runtime": 262.8306,
|
| 2372 |
+
"eval_samples_per_second": 37.283,
|
| 2373 |
+
"eval_steps_per_second": 4.661,
|
| 2374 |
+
"step": 2750
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 0.7357915257343752,
|
| 2378 |
+
"grad_norm": 1.3524416472787477,
|
| 2379 |
+
"learning_rate": 1.98071295339216e-06,
|
| 2380 |
+
"loss": 0.2091,
|
| 2381 |
+
"step": 2760
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 0.7384574370594998,
|
| 2385 |
+
"grad_norm": 1.360747048278261,
|
| 2386 |
+
"learning_rate": 1.9437459309015426e-06,
|
| 2387 |
+
"loss": 0.2133,
|
| 2388 |
+
"step": 2770
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 0.7411233483846243,
|
| 2392 |
+
"grad_norm": 1.378087319514889,
|
| 2393 |
+
"learning_rate": 1.9070437209283304e-06,
|
| 2394 |
+
"loss": 0.2102,
|
| 2395 |
+
"step": 2780
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 0.7437892597097489,
|
| 2399 |
+
"grad_norm": 1.3569822983158015,
|
| 2400 |
+
"learning_rate": 1.8706095035761418e-06,
|
| 2401 |
+
"loss": 0.2138,
|
| 2402 |
+
"step": 2790
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 0.7464551710348735,
|
| 2406 |
+
"grad_norm": 1.3617876179506314,
|
| 2407 |
+
"learning_rate": 1.8344464357280722e-06,
|
| 2408 |
+
"loss": 0.2162,
|
| 2409 |
+
"step": 2800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.7464551710348735,
|
| 2413 |
+
"eval_loss": 0.21530871093273163,
|
| 2414 |
+
"eval_runtime": 262.8758,
|
| 2415 |
+
"eval_samples_per_second": 37.276,
|
| 2416 |
+
"eval_steps_per_second": 4.66,
|
| 2417 |
+
"step": 2800
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.749121082359998,
|
| 2421 |
+
"grad_norm": 1.3465206929111626,
|
| 2422 |
+
"learning_rate": 1.7985576507731744e-06,
|
| 2423 |
+
"loss": 0.2245,
|
| 2424 |
+
"step": 2810
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.7517869936851226,
|
| 2428 |
+
"grad_norm": 1.4990944824718522,
|
| 2429 |
+
"learning_rate": 1.762946258334951e-06,
|
| 2430 |
+
"loss": 0.2196,
|
| 2431 |
+
"step": 2820
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.7544529050102471,
|
| 2435 |
+
"grad_norm": 1.2637615882614495,
|
| 2436 |
+
"learning_rate": 1.727615344001926e-06,
|
| 2437 |
+
"loss": 0.2119,
|
| 2438 |
+
"step": 2830
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.7571188163353716,
|
| 2442 |
+
"grad_norm": 1.3954340785154413,
|
| 2443 |
+
"learning_rate": 1.6925679690602876e-06,
|
| 2444 |
+
"loss": 0.2106,
|
| 2445 |
+
"step": 2840
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.7597847276604962,
|
| 2449 |
+
"grad_norm": 1.390096178394802,
|
| 2450 |
+
"learning_rate": 1.6578071702286396e-06,
|
| 2451 |
+
"loss": 0.2253,
|
| 2452 |
+
"step": 2850
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.7597847276604962,
|
| 2456 |
+
"eval_loss": 0.21321707963943481,
|
| 2457 |
+
"eval_runtime": 263.0359,
|
| 2458 |
+
"eval_samples_per_second": 37.253,
|
| 2459 |
+
"eval_steps_per_second": 4.657,
|
| 2460 |
+
"step": 2850
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.7624506389856207,
|
| 2464 |
+
"grad_norm": 1.3401955453773768,
|
| 2465 |
+
"learning_rate": 1.6233359593948777e-06,
|
| 2466 |
+
"loss": 0.22,
|
| 2467 |
+
"step": 2860
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.7651165503107453,
|
| 2471 |
+
"grad_norm": 1.287854168515364,
|
| 2472 |
+
"learning_rate": 1.5891573233552315e-06,
|
| 2473 |
+
"loss": 0.2133,
|
| 2474 |
+
"step": 2870
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.7677824616358698,
|
| 2478 |
+
"grad_norm": 1.3415313412375607,
|
| 2479 |
+
"learning_rate": 1.5552742235554551e-06,
|
| 2480 |
+
"loss": 0.2161,
|
| 2481 |
+
"step": 2880
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.7704483729609943,
|
| 2485 |
+
"grad_norm": 1.4355286266779297,
|
| 2486 |
+
"learning_rate": 1.521689595834246e-06,
|
| 2487 |
+
"loss": 0.2129,
|
| 2488 |
+
"step": 2890
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.773114284286119,
|
| 2492 |
+
"grad_norm": 1.3269614788833008,
|
| 2493 |
+
"learning_rate": 1.4884063501688539e-06,
|
| 2494 |
+
"loss": 0.2066,
|
| 2495 |
+
"step": 2900
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.773114284286119,
|
| 2499 |
+
"eval_loss": 0.21342259645462036,
|
| 2500 |
+
"eval_runtime": 262.8386,
|
| 2501 |
+
"eval_samples_per_second": 37.281,
|
| 2502 |
+
"eval_steps_per_second": 4.661,
|
| 2503 |
+
"step": 2900
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 0.7757801956112435,
|
| 2507 |
+
"grad_norm": 1.4582052603751765,
|
| 2508 |
+
"learning_rate": 1.4554273704229494e-06,
|
| 2509 |
+
"loss": 0.2244,
|
| 2510 |
+
"step": 2910
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 0.7784461069363681,
|
| 2514 |
+
"grad_norm": 1.1948855303191914,
|
| 2515 |
+
"learning_rate": 1.4227555140967402e-06,
|
| 2516 |
+
"loss": 0.2156,
|
| 2517 |
+
"step": 2920
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 0.7811120182614926,
|
| 2521 |
+
"grad_norm": 1.5589564581113802,
|
| 2522 |
+
"learning_rate": 1.3903936120793926e-06,
|
| 2523 |
+
"loss": 0.2192,
|
| 2524 |
+
"step": 2930
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 0.7837779295866171,
|
| 2528 |
+
"grad_norm": 1.3051867211369865,
|
| 2529 |
+
"learning_rate": 1.3583444684037312e-06,
|
| 2530 |
+
"loss": 0.2156,
|
| 2531 |
+
"step": 2940
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 0.7864438409117417,
|
| 2535 |
+
"grad_norm": 1.3423994247273423,
|
| 2536 |
+
"learning_rate": 1.3266108600032928e-06,
|
| 2537 |
+
"loss": 0.2113,
|
| 2538 |
+
"step": 2950
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 0.7864438409117417,
|
| 2542 |
+
"eval_loss": 0.2107125222682953,
|
| 2543 |
+
"eval_runtime": 263.0418,
|
| 2544 |
+
"eval_samples_per_second": 37.253,
|
| 2545 |
+
"eval_steps_per_second": 4.657,
|
| 2546 |
+
"step": 2950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 0.7891097522368662,
|
| 2550 |
+
"grad_norm": 1.3712137564595037,
|
| 2551 |
+
"learning_rate": 1.2951955364717116e-06,
|
| 2552 |
+
"loss": 0.2143,
|
| 2553 |
+
"step": 2960
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 0.7917756635619908,
|
| 2557 |
+
"grad_norm": 1.3657856665947792,
|
| 2558 |
+
"learning_rate": 1.2641012198244718e-06,
|
| 2559 |
+
"loss": 0.2065,
|
| 2560 |
+
"step": 2970
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 0.7944415748871153,
|
| 2564 |
+
"grad_norm": 1.21692203839909,
|
| 2565 |
+
"learning_rate": 1.2333306042630672e-06,
|
| 2566 |
+
"loss": 0.2201,
|
| 2567 |
+
"step": 2980
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 0.7971074862122398,
|
| 2571 |
+
"grad_norm": 1.4562111256731463,
|
| 2572 |
+
"learning_rate": 1.202886355941546e-06,
|
| 2573 |
+
"loss": 0.2097,
|
| 2574 |
+
"step": 2990
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 0.7997733975373644,
|
| 2578 |
+
"grad_norm": 1.42678698336257,
|
| 2579 |
+
"learning_rate": 1.1727711127355118e-06,
|
| 2580 |
+
"loss": 0.2107,
|
| 2581 |
+
"step": 3000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 0.7997733975373644,
|
| 2585 |
+
"eval_loss": 0.20849083364009857,
|
| 2586 |
+
"eval_runtime": 262.8245,
|
| 2587 |
+
"eval_samples_per_second": 37.283,
|
| 2588 |
+
"eval_steps_per_second": 4.661,
|
| 2589 |
+
"step": 3000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 0.8024393088624889,
|
| 2593 |
+
"grad_norm": 1.6939593357963476,
|
| 2594 |
+
"learning_rate": 1.1429874840135492e-06,
|
| 2595 |
+
"loss": 0.2126,
|
| 2596 |
+
"step": 3010
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 0.8051052201876135,
|
| 2600 |
+
"grad_norm": 1.365257481621389,
|
| 2601 |
+
"learning_rate": 1.1135380504111476e-06,
|
| 2602 |
+
"loss": 0.2024,
|
| 2603 |
+
"step": 3020
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 0.807771131512738,
|
| 2607 |
+
"grad_norm": 1.4085575069668772,
|
| 2608 |
+
"learning_rate": 1.0844253636070805e-06,
|
| 2609 |
+
"loss": 0.2103,
|
| 2610 |
+
"step": 3030
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 0.8104370428378626,
|
| 2614 |
+
"grad_norm": 1.4997581763477477,
|
| 2615 |
+
"learning_rate": 1.0556519461023301e-06,
|
| 2616 |
+
"loss": 0.2093,
|
| 2617 |
+
"step": 3040
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 0.8131029541629872,
|
| 2621 |
+
"grad_norm": 1.384763329857118,
|
| 2622 |
+
"learning_rate": 1.0272202910015083e-06,
|
| 2623 |
+
"loss": 0.2055,
|
| 2624 |
+
"step": 3050
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 0.8131029541629872,
|
| 2628 |
+
"eval_loss": 0.2096840888261795,
|
| 2629 |
+
"eval_runtime": 262.8819,
|
| 2630 |
+
"eval_samples_per_second": 37.275,
|
| 2631 |
+
"eval_steps_per_second": 4.66,
|
| 2632 |
+
"step": 3050
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 0.8157688654881117,
|
| 2636 |
+
"grad_norm": 1.4019463660561169,
|
| 2637 |
+
"learning_rate": 9.991328617968509e-07,
|
| 2638 |
+
"loss": 0.2084,
|
| 2639 |
+
"step": 3060
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 0.8184347768132363,
|
| 2643 |
+
"grad_norm": 1.4903762495669879,
|
| 2644 |
+
"learning_rate": 9.713920921547532e-07,
|
| 2645 |
+
"loss": 0.2076,
|
| 2646 |
+
"step": 3070
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 0.8211006881383608,
|
| 2650 |
+
"grad_norm": 1.4296247263023294,
|
| 2651 |
+
"learning_rate": 9.440003857049173e-07,
|
| 2652 |
+
"loss": 0.2072,
|
| 2653 |
+
"step": 3080
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 0.8237665994634853,
|
| 2657 |
+
"grad_norm": 1.498715554303158,
|
| 2658 |
+
"learning_rate": 9.169601158320707e-07,
|
| 2659 |
+
"loss": 0.2252,
|
| 2660 |
+
"step": 3090
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 0.8264325107886099,
|
| 2664 |
+
"grad_norm": 1.4851333098682147,
|
| 2665 |
+
"learning_rate": 8.902736254703347e-07,
|
| 2666 |
+
"loss": 0.2045,
|
| 2667 |
+
"step": 3100
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 0.8264325107886099,
|
| 2671 |
+
"eval_loss": 0.20747578144073486,
|
| 2672 |
+
"eval_runtime": 262.8395,
|
| 2673 |
+
"eval_samples_per_second": 37.281,
|
| 2674 |
+
"eval_steps_per_second": 4.661,
|
| 2675 |
+
"step": 3100
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 0.8290984221137344,
|
| 2679 |
+
"grad_norm": 1.4703270343823225,
|
| 2680 |
+
"learning_rate": 8.639432269002102e-07,
|
| 2681 |
+
"loss": 0.2038,
|
| 2682 |
+
"step": 3110
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 0.831764333438859,
|
| 2686 |
+
"grad_norm": 1.277311132392977,
|
| 2687 |
+
"learning_rate": 8.379712015482333e-07,
|
| 2688 |
+
"loss": 0.2071,
|
| 2689 |
+
"step": 3120
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 0.8344302447639835,
|
| 2693 |
+
"grad_norm": 1.3393459507656948,
|
| 2694 |
+
"learning_rate": 8.123597997892918e-07,
|
| 2695 |
+
"loss": 0.1988,
|
| 2696 |
+
"step": 3130
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 0.837096156089108,
|
| 2700 |
+
"grad_norm": 1.4461311558504941,
|
| 2701 |
+
"learning_rate": 7.871112407516474e-07,
|
| 2702 |
+
"loss": 0.2181,
|
| 2703 |
+
"step": 3140
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 0.8397620674142326,
|
| 2707 |
+
"grad_norm": 1.435791157531731,
|
| 2708 |
+
"learning_rate": 7.622277121246513e-07,
|
| 2709 |
+
"loss": 0.2172,
|
| 2710 |
+
"step": 3150
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 0.8397620674142326,
|
| 2714 |
+
"eval_loss": 0.2062389850616455,
|
| 2715 |
+
"eval_runtime": 262.9168,
|
| 2716 |
+
"eval_samples_per_second": 37.27,
|
| 2717 |
+
"eval_steps_per_second": 4.659,
|
| 2718 |
+
"step": 3150
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.8424279787393572,
|
| 2722 |
+
"grad_norm": 1.3532701657995663,
|
| 2723 |
+
"learning_rate": 7.377113699691879e-07,
|
| 2724 |
+
"loss": 0.2045,
|
| 2725 |
+
"step": 3160
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.8450938900644818,
|
| 2729 |
+
"grad_norm": 1.3493480728612797,
|
| 2730 |
+
"learning_rate": 7.135643385308677e-07,
|
| 2731 |
+
"loss": 0.2162,
|
| 2732 |
+
"step": 3170
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.8477598013896063,
|
| 2736 |
+
"grad_norm": 1.5269560977358674,
|
| 2737 |
+
"learning_rate": 6.897887100559608e-07,
|
| 2738 |
+
"loss": 0.2089,
|
| 2739 |
+
"step": 3180
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.8504257127147308,
|
| 2743 |
+
"grad_norm": 1.29264776120369,
|
| 2744 |
+
"learning_rate": 6.663865446101192e-07,
|
| 2745 |
+
"loss": 0.216,
|
| 2746 |
+
"step": 3190
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.8530916240398554,
|
| 2750 |
+
"grad_norm": 1.6285538029089162,
|
| 2751 |
+
"learning_rate": 6.433598698998766e-07,
|
| 2752 |
+
"loss": 0.2138,
|
| 2753 |
+
"step": 3200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.8530916240398554,
|
| 2757 |
+
"eval_loss": 0.2074633538722992,
|
| 2758 |
+
"eval_runtime": 262.9966,
|
| 2759 |
+
"eval_samples_per_second": 37.259,
|
| 2760 |
+
"eval_steps_per_second": 4.658,
|
| 2761 |
+
"step": 3200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.8557575353649799,
|
| 2765 |
+
"grad_norm": 1.3678851449133813,
|
| 2766 |
+
"learning_rate": 6.207106810969577e-07,
|
| 2767 |
+
"loss": 0.2121,
|
| 2768 |
+
"step": 3210
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.8584234466901045,
|
| 2772 |
+
"grad_norm": 1.535513254522266,
|
| 2773 |
+
"learning_rate": 5.98440940665399e-07,
|
| 2774 |
+
"loss": 0.2141,
|
| 2775 |
+
"step": 3220
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.861089358015229,
|
| 2779 |
+
"grad_norm": 1.4232188919597053,
|
| 2780 |
+
"learning_rate": 5.765525781915172e-07,
|
| 2781 |
+
"loss": 0.1917,
|
| 2782 |
+
"step": 3230
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.8637552693403535,
|
| 2786 |
+
"grad_norm": 1.379241907620819,
|
| 2787 |
+
"learning_rate": 5.550474902167091e-07,
|
| 2788 |
+
"loss": 0.213,
|
| 2789 |
+
"step": 3240
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.8664211806654781,
|
| 2793 |
+
"grad_norm": 1.4866740177549789,
|
| 2794 |
+
"learning_rate": 5.339275400731331e-07,
|
| 2795 |
+
"loss": 0.194,
|
| 2796 |
+
"step": 3250
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.8664211806654781,
|
| 2800 |
+
"eval_loss": 0.2050597220659256,
|
| 2801 |
+
"eval_runtime": 262.896,
|
| 2802 |
+
"eval_samples_per_second": 37.273,
|
| 2803 |
+
"eval_steps_per_second": 4.66,
|
| 2804 |
+
"step": 3250
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 0.8690870919906026,
|
| 2808 |
+
"grad_norm": 1.3230806315640078,
|
| 2809 |
+
"learning_rate": 5.131945577222485e-07,
|
| 2810 |
+
"loss": 0.2031,
|
| 2811 |
+
"step": 3260
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 0.8717530033157272,
|
| 2815 |
+
"grad_norm": 1.4976380022642137,
|
| 2816 |
+
"learning_rate": 4.92850339596268e-07,
|
| 2817 |
+
"loss": 0.2061,
|
| 2818 |
+
"step": 3270
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 0.8744189146408518,
|
| 2822 |
+
"grad_norm": 1.421070272722705,
|
| 2823 |
+
"learning_rate": 4.728966484424913e-07,
|
| 2824 |
+
"loss": 0.2148,
|
| 2825 |
+
"step": 3280
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 0.8770848259659763,
|
| 2829 |
+
"grad_norm": 1.321758338936035,
|
| 2830 |
+
"learning_rate": 4.5333521317058207e-07,
|
| 2831 |
+
"loss": 0.2181,
|
| 2832 |
+
"step": 3290
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 0.8797507372911009,
|
| 2836 |
+
"grad_norm": 1.4222679966153535,
|
| 2837 |
+
"learning_rate": 4.3416772870275295e-07,
|
| 2838 |
+
"loss": 0.2133,
|
| 2839 |
+
"step": 3300
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 0.8797507372911009,
|
| 2843 |
+
"eval_loss": 0.20511919260025024,
|
| 2844 |
+
"eval_runtime": 263.0571,
|
| 2845 |
+
"eval_samples_per_second": 37.25,
|
| 2846 |
+
"eval_steps_per_second": 4.657,
|
| 2847 |
+
"step": 3300
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 0.8824166486162254,
|
| 2851 |
+
"grad_norm": 1.4283343273273894,
|
| 2852 |
+
"learning_rate": 4.153958558269189e-07,
|
| 2853 |
+
"loss": 0.1987,
|
| 2854 |
+
"step": 3310
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 0.88508255994135,
|
| 2858 |
+
"grad_norm": 1.5675323422816119,
|
| 2859 |
+
"learning_rate": 3.9702122105278405e-07,
|
| 2860 |
+
"loss": 0.2,
|
| 2861 |
+
"step": 3320
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 0.8877484712664745,
|
| 2865 |
+
"grad_norm": 1.3013063484388072,
|
| 2866 |
+
"learning_rate": 3.7904541647092506e-07,
|
| 2867 |
+
"loss": 0.1995,
|
| 2868 |
+
"step": 3330
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 0.890414382591599,
|
| 2872 |
+
"grad_norm": 1.354917224230714,
|
| 2873 |
+
"learning_rate": 3.614699996148285e-07,
|
| 2874 |
+
"loss": 0.1988,
|
| 2875 |
+
"step": 3340
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 0.8930802939167236,
|
| 2879 |
+
"grad_norm": 1.2832901778967167,
|
| 2880 |
+
"learning_rate": 3.442964933259474e-07,
|
| 2881 |
+
"loss": 0.2025,
|
| 2882 |
+
"step": 3350
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 0.8930802939167236,
|
| 2886 |
+
"eval_loss": 0.20472171902656555,
|
| 2887 |
+
"eval_runtime": 263.0226,
|
| 2888 |
+
"eval_samples_per_second": 37.255,
|
| 2889 |
+
"eval_steps_per_second": 4.657,
|
| 2890 |
+
"step": 3350
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 0.8957462052418481,
|
| 2894 |
+
"grad_norm": 1.510961640653365,
|
| 2895 |
+
"learning_rate": 3.275263856217442e-07,
|
| 2896 |
+
"loss": 0.2066,
|
| 2897 |
+
"step": 3360
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 0.8984121165669727,
|
| 2901 |
+
"grad_norm": 1.4157593597386668,
|
| 2902 |
+
"learning_rate": 3.1116112956677045e-07,
|
| 2903 |
+
"loss": 0.2041,
|
| 2904 |
+
"step": 3370
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 0.9010780278920972,
|
| 2908 |
+
"grad_norm": 1.3311731607352142,
|
| 2909 |
+
"learning_rate": 2.952021431467522e-07,
|
| 2910 |
+
"loss": 0.2075,
|
| 2911 |
+
"step": 3380
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 0.9037439392172217,
|
| 2915 |
+
"grad_norm": 1.4936420011473173,
|
| 2916 |
+
"learning_rate": 2.7965080914573786e-07,
|
| 2917 |
+
"loss": 0.2102,
|
| 2918 |
+
"step": 3390
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 0.9064098505423464,
|
| 2922 |
+
"grad_norm": 1.5419179206834437,
|
| 2923 |
+
"learning_rate": 2.6450847502627883e-07,
|
| 2924 |
+
"loss": 0.2088,
|
| 2925 |
+
"step": 3400
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 0.9064098505423464,
|
| 2929 |
+
"eval_loss": 0.20498156547546387,
|
| 2930 |
+
"eval_runtime": 262.97,
|
| 2931 |
+
"eval_samples_per_second": 37.263,
|
| 2932 |
+
"eval_steps_per_second": 4.658,
|
| 2933 |
+
"step": 3400
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"epoch": 0.9090757618674709,
|
| 2937 |
+
"grad_norm": 1.4557819209662033,
|
| 2938 |
+
"learning_rate": 2.497764528126778e-07,
|
| 2939 |
+
"loss": 0.2127,
|
| 2940 |
+
"step": 3410
|
| 2941 |
+
},
|
| 2942 |
+
{
|
| 2943 |
+
"epoch": 0.9117416731925955,
|
| 2944 |
+
"grad_norm": 1.3483821589972327,
|
| 2945 |
+
"learning_rate": 2.3545601897731085e-07,
|
| 2946 |
+
"loss": 0.2087,
|
| 2947 |
+
"step": 3420
|
| 2948 |
+
},
|
| 2949 |
+
{
|
| 2950 |
+
"epoch": 0.91440758451772,
|
| 2951 |
+
"grad_norm": 1.3949209578658839,
|
| 2952 |
+
"learning_rate": 2.2154841433002062e-07,
|
| 2953 |
+
"loss": 0.208,
|
| 2954 |
+
"step": 3430
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 0.9170734958428445,
|
| 2958 |
+
"grad_norm": 1.3985557189628612,
|
| 2959 |
+
"learning_rate": 2.0805484391061003e-07,
|
| 2960 |
+
"loss": 0.197,
|
| 2961 |
+
"step": 3440
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"epoch": 0.9197394071679691,
|
| 2965 |
+
"grad_norm": 1.6011076878070405,
|
| 2966 |
+
"learning_rate": 1.9497647688442478e-07,
|
| 2967 |
+
"loss": 0.204,
|
| 2968 |
+
"step": 3450
|
| 2969 |
+
},
|
| 2970 |
+
{
|
| 2971 |
+
"epoch": 0.9197394071679691,
|
| 2972 |
+
"eval_loss": 0.20443060994148254,
|
| 2973 |
+
"eval_runtime": 262.9479,
|
| 2974 |
+
"eval_samples_per_second": 37.266,
|
| 2975 |
+
"eval_steps_per_second": 4.659,
|
| 2976 |
+
"step": 3450
|
| 2977 |
+
},
|
| 2978 |
+
{
|
| 2979 |
+
"epoch": 0.9224053184930936,
|
| 2980 |
+
"grad_norm": 1.4046196100578223,
|
| 2981 |
+
"learning_rate": 1.8231444644105755e-07,
|
| 2982 |
+
"loss": 0.2063,
|
| 2983 |
+
"step": 3460
|
| 2984 |
+
},
|
| 2985 |
+
{
|
| 2986 |
+
"epoch": 0.9250712298182182,
|
| 2987 |
+
"grad_norm": 1.41779845252418,
|
| 2988 |
+
"learning_rate": 1.7006984969615226e-07,
|
| 2989 |
+
"loss": 0.2063,
|
| 2990 |
+
"step": 3470
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 0.9277371411433427,
|
| 2994 |
+
"grad_norm": 1.3987321445452827,
|
| 2995 |
+
"learning_rate": 1.5824374759635165e-07,
|
| 2996 |
+
"loss": 0.2103,
|
| 2997 |
+
"step": 3480
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 0.9304030524684672,
|
| 3001 |
+
"grad_norm": 1.2896847102113629,
|
| 3002 |
+
"learning_rate": 1.4683716482736364e-07,
|
| 3003 |
+
"loss": 0.1999,
|
| 3004 |
+
"step": 3490
|
| 3005 |
+
},
|
| 3006 |
+
{
|
| 3007 |
+
"epoch": 0.9330689637935918,
|
| 3008 |
+
"grad_norm": 1.4530276844098788,
|
| 3009 |
+
"learning_rate": 1.358510897251808e-07,
|
| 3010 |
+
"loss": 0.2059,
|
| 3011 |
+
"step": 3500
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 0.9330689637935918,
|
| 3015 |
+
"eval_loss": 0.20389488339424133,
|
| 3016 |
+
"eval_runtime": 262.985,
|
| 3017 |
+
"eval_samples_per_second": 37.261,
|
| 3018 |
+
"eval_steps_per_second": 4.658,
|
| 3019 |
+
"step": 3500
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 0.9357348751187163,
|
| 3023 |
+
"grad_norm": 1.376435217170314,
|
| 3024 |
+
"learning_rate": 1.252864741904425e-07,
|
| 3025 |
+
"loss": 0.2041,
|
| 3026 |
+
"step": 3510
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.938400786443841,
|
| 3030 |
+
"grad_norm": 1.63745742682993,
|
| 3031 |
+
"learning_rate": 1.1514423360595939e-07,
|
| 3032 |
+
"loss": 0.2071,
|
| 3033 |
+
"step": 3520
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 0.9410666977689655,
|
| 3037 |
+
"grad_norm": 1.352875159457686,
|
| 3038 |
+
"learning_rate": 1.0542524675739407e-07,
|
| 3039 |
+
"loss": 0.197,
|
| 3040 |
+
"step": 3530
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 0.94373260909409,
|
| 3044 |
+
"grad_norm": 1.4239967793966135,
|
| 3045 |
+
"learning_rate": 9.613035575712304e-08,
|
| 3046 |
+
"loss": 0.2051,
|
| 3047 |
+
"step": 3540
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 0.9463985204192146,
|
| 3051 |
+
"grad_norm": 1.3958904189251933,
|
| 3052 |
+
"learning_rate": 8.726036597126619e-08,
|
| 3053 |
+
"loss": 0.2103,
|
| 3054 |
+
"step": 3550
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 0.9463985204192146,
|
| 3058 |
+
"eval_loss": 0.20391830801963806,
|
| 3059 |
+
"eval_runtime": 262.9962,
|
| 3060 |
+
"eval_samples_per_second": 37.259,
|
| 3061 |
+
"eval_steps_per_second": 4.658,
|
| 3062 |
+
"step": 3550
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.9490644317443391,
|
| 3066 |
+
"grad_norm": 1.3789213423803108,
|
| 3067 |
+
"learning_rate": 7.881604594990932e-08,
|
| 3068 |
+
"loss": 0.2028,
|
| 3069 |
+
"step": 3560
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 0.9517303430694637,
|
| 3073 |
+
"grad_norm": 1.4337723414549706,
|
| 3074 |
+
"learning_rate": 7.079812736050906e-08,
|
| 3075 |
+
"loss": 0.2141,
|
| 3076 |
+
"step": 3570
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 0.9543962543945882,
|
| 3080 |
+
"grad_norm": 1.2816441548148045,
|
| 3081 |
+
"learning_rate": 6.3207304924498e-08,
|
| 3082 |
+
"loss": 0.2008,
|
| 3083 |
+
"step": 3580
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 0.9570621657197127,
|
| 3087 |
+
"grad_norm": 1.3587442586245593,
|
| 3088 |
+
"learning_rate": 5.604423635709122e-08,
|
| 3089 |
+
"loss": 0.2088,
|
| 3090 |
+
"step": 3590
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 0.9597280770448373,
|
| 3094 |
+
"grad_norm": 1.398655956796932,
|
| 3095 |
+
"learning_rate": 4.93095423102935e-08,
|
| 3096 |
+
"loss": 0.2102,
|
| 3097 |
+
"step": 3600
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.9597280770448373,
|
| 3101 |
+
"eval_loss": 0.20385359227657318,
|
| 3102 |
+
"eval_runtime": 262.9737,
|
| 3103 |
+
"eval_samples_per_second": 37.262,
|
| 3104 |
+
"eval_steps_per_second": 4.658,
|
| 3105 |
+
"step": 3600
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 0.9623939883699618,
|
| 3109 |
+
"grad_norm": 1.3545794976233818,
|
| 3110 |
+
"learning_rate": 4.3003806319127376e-08,
|
| 3111 |
+
"loss": 0.1974,
|
| 3112 |
+
"step": 3610
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 0.9650598996950864,
|
| 3116 |
+
"grad_norm": 1.472940446548246,
|
| 3117 |
+
"learning_rate": 3.712757475106854e-08,
|
| 3118 |
+
"loss": 0.2038,
|
| 3119 |
+
"step": 3620
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 0.9677258110202109,
|
| 3123 |
+
"grad_norm": 1.4688819140937053,
|
| 3124 |
+
"learning_rate": 3.168135675870654e-08,
|
| 3125 |
+
"loss": 0.2033,
|
| 3126 |
+
"step": 3630
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 0.9703917223453354,
|
| 3130 |
+
"grad_norm": 1.559082216657787,
|
| 3131 |
+
"learning_rate": 2.6665624235629463e-08,
|
| 3132 |
+
"loss": 0.2066,
|
| 3133 |
+
"step": 3640
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 0.97305763367046,
|
| 3137 |
+
"grad_norm": 1.4442615348656187,
|
| 3138 |
+
"learning_rate": 2.2080811775535006e-08,
|
| 3139 |
+
"loss": 0.2051,
|
| 3140 |
+
"step": 3650
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 0.97305763367046,
|
| 3144 |
+
"eval_loss": 0.20379623770713806,
|
| 3145 |
+
"eval_runtime": 262.9438,
|
| 3146 |
+
"eval_samples_per_second": 37.267,
|
| 3147 |
+
"eval_steps_per_second": 4.659,
|
| 3148 |
+
"step": 3650
|
| 3149 |
+
},
|
| 3150 |
+
{
|
| 3151 |
+
"epoch": 0.9757235449955846,
|
| 3152 |
+
"grad_norm": 1.4302312819140066,
|
| 3153 |
+
"learning_rate": 1.7927316634573368e-08,
|
| 3154 |
+
"loss": 0.2005,
|
| 3155 |
+
"step": 3660
|
| 3156 |
+
},
|
| 3157 |
+
{
|
| 3158 |
+
"epoch": 0.9783894563207092,
|
| 3159 |
+
"grad_norm": 1.5231097086128733,
|
| 3160 |
+
"learning_rate": 1.4205498696930332e-08,
|
| 3161 |
+
"loss": 0.198,
|
| 3162 |
+
"step": 3670
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 0.9810553676458337,
|
| 3166 |
+
"grad_norm": 1.3232525431455444,
|
| 3167 |
+
"learning_rate": 1.0915680443641663e-08,
|
| 3168 |
+
"loss": 0.1995,
|
| 3169 |
+
"step": 3680
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 0.9837212789709582,
|
| 3173 |
+
"grad_norm": 1.373155468144249,
|
| 3174 |
+
"learning_rate": 8.058146924651012e-09,
|
| 3175 |
+
"loss": 0.2048,
|
| 3176 |
+
"step": 3690
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 0.9863871902960828,
|
| 3180 |
+
"grad_norm": 1.4110519682344211,
|
| 3181 |
+
"learning_rate": 5.633145734114665e-09,
|
| 3182 |
+
"loss": 0.2017,
|
| 3183 |
+
"step": 3700
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 0.9863871902960828,
|
| 3187 |
+
"eval_loss": 0.203701451420784,
|
| 3188 |
+
"eval_runtime": 263.031,
|
| 3189 |
+
"eval_samples_per_second": 37.254,
|
| 3190 |
+
"eval_steps_per_second": 4.657,
|
| 3191 |
+
"step": 3700
|
| 3192 |
+
},
|
| 3193 |
+
{
|
| 3194 |
+
"epoch": 0.9890531016212073,
|
| 3195 |
+
"grad_norm": 1.400340000512079,
|
| 3196 |
+
"learning_rate": 3.640886988945935e-09,
|
| 3197 |
+
"loss": 0.2069,
|
| 3198 |
+
"step": 3710
|
| 3199 |
+
},
|
| 3200 |
+
{
|
| 3201 |
+
"epoch": 0.9917190129463319,
|
| 3202 |
+
"grad_norm": 1.5211040678505572,
|
| 3203 |
+
"learning_rate": 2.0815433106080583e-09,
|
| 3204 |
+
"loss": 0.2021,
|
| 3205 |
+
"step": 3720
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 0.9943849242714564,
|
| 3209 |
+
"grad_norm": 1.4375248921695807,
|
| 3210 |
+
"learning_rate": 9.55249810161152e-10,
|
| 3211 |
+
"loss": 0.2134,
|
| 3212 |
+
"step": 3730
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 0.9970508355965809,
|
| 3216 |
+
"grad_norm": 1.492474671725836,
|
| 3217 |
+
"learning_rate": 2.6210407655269386e-10,
|
| 3218 |
+
"loss": 0.211,
|
| 3219 |
+
"step": 3740
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 0.9997167469217055,
|
| 3223 |
+
"grad_norm": 1.6278639410883167,
|
| 3224 |
+
"learning_rate": 2.1661681620654963e-12,
|
| 3225 |
+
"loss": 0.2088,
|
| 3226 |
+
"step": 3750
|
| 3227 |
+
},
|
| 3228 |
+
{
|
| 3229 |
+
"epoch": 0.9997167469217055,
|
| 3230 |
+
"eval_loss": 0.2036588490009308,
|
| 3231 |
+
"eval_runtime": 262.7967,
|
| 3232 |
+
"eval_samples_per_second": 37.287,
|
| 3233 |
+
"eval_steps_per_second": 4.661,
|
| 3234 |
+
"step": 3750
|
| 3235 |
+
},
|
| 3236 |
+
{
|
| 3237 |
+
"epoch": 0.999983338054218,
|
| 3238 |
+
"step": 3751,
|
| 3239 |
+
"total_flos": 1934604910592000.0,
|
| 3240 |
+
"train_loss": 0.2527618171993302,
|
| 3241 |
+
"train_runtime": 72440.3327,
|
| 3242 |
+
"train_samples_per_second": 6.628,
|
| 3243 |
+
"train_steps_per_second": 0.052
|
| 3244 |
+
}
|
| 3245 |
+
],
|
| 3246 |
+
"logging_steps": 10,
|
| 3247 |
+
"max_steps": 3751,
|
| 3248 |
+
"num_input_tokens_seen": 0,
|
| 3249 |
+
"num_train_epochs": 1,
|
| 3250 |
+
"save_steps": 500,
|
| 3251 |
+
"stateful_callbacks": {
|
| 3252 |
+
"TrainerControl": {
|
| 3253 |
+
"args": {
|
| 3254 |
+
"should_epoch_stop": false,
|
| 3255 |
+
"should_evaluate": false,
|
| 3256 |
+
"should_log": false,
|
| 3257 |
+
"should_save": true,
|
| 3258 |
+
"should_training_stop": true
|
| 3259 |
+
},
|
| 3260 |
+
"attributes": {}
|
| 3261 |
+
}
|
| 3262 |
+
},
|
| 3263 |
+
"total_flos": 1934604910592000.0,
|
| 3264 |
+
"train_batch_size": 1,
|
| 3265 |
+
"trial_name": null,
|
| 3266 |
+
"trial_params": null
|
| 3267 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|