End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +3262 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: ot_newparams_5epochs
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# ot_newparams_5epochs
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: ot_newparams_5epochs
|
|
|
|
| 16 |
|
| 17 |
# ot_newparams_5epochs
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the open-thoughts/OpenThoughts-114k dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.979702300405954,
|
| 3 |
+
"total_flos": 1.1837169167247606e+19,
|
| 4 |
+
"train_loss": 0.4245723386173663,
|
| 5 |
+
"train_runtime": 101661.9148,
|
| 6 |
+
"train_samples_per_second": 2.326,
|
| 7 |
+
"train_steps_per_second": 0.005
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.979702300405954,
|
| 3 |
+
"total_flos": 1.1837169167247606e+19,
|
| 4 |
+
"train_loss": 0.4245723386173663,
|
| 5 |
+
"train_runtime": 101661.9148,
|
| 6 |
+
"train_samples_per_second": 2.326,
|
| 7 |
+
"train_steps_per_second": 0.005
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.979702300405954,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 460,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.010825439783491205,
|
| 13 |
+
"grad_norm": 5.808831848901163,
|
| 14 |
+
"learning_rate": 1.7391304347826088e-06,
|
| 15 |
+
"loss": 0.8566,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02165087956698241,
|
| 20 |
+
"grad_norm": 5.8131650809808635,
|
| 21 |
+
"learning_rate": 3.4782608695652175e-06,
|
| 22 |
+
"loss": 0.8603,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03247631935047361,
|
| 27 |
+
"grad_norm": 5.758169356290023,
|
| 28 |
+
"learning_rate": 5.2173913043478265e-06,
|
| 29 |
+
"loss": 0.8631,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04330175913396482,
|
| 34 |
+
"grad_norm": 4.238914874845898,
|
| 35 |
+
"learning_rate": 6.956521739130435e-06,
|
| 36 |
+
"loss": 0.8176,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05412719891745602,
|
| 41 |
+
"grad_norm": 2.235103598722892,
|
| 42 |
+
"learning_rate": 8.695652173913044e-06,
|
| 43 |
+
"loss": 0.7658,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06495263870094722,
|
| 48 |
+
"grad_norm": 4.07899438012489,
|
| 49 |
+
"learning_rate": 1.0434782608695653e-05,
|
| 50 |
+
"loss": 0.7574,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07577807848443843,
|
| 55 |
+
"grad_norm": 4.324129456803467,
|
| 56 |
+
"learning_rate": 1.2173913043478263e-05,
|
| 57 |
+
"loss": 0.7776,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08660351826792964,
|
| 62 |
+
"grad_norm": 4.2756579015034015,
|
| 63 |
+
"learning_rate": 1.391304347826087e-05,
|
| 64 |
+
"loss": 0.7457,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09742895805142084,
|
| 69 |
+
"grad_norm": 3.6399981122437852,
|
| 70 |
+
"learning_rate": 1.565217391304348e-05,
|
| 71 |
+
"loss": 0.7141,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.10825439783491204,
|
| 76 |
+
"grad_norm": 2.114757736524999,
|
| 77 |
+
"learning_rate": 1.739130434782609e-05,
|
| 78 |
+
"loss": 0.6986,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.11907983761840325,
|
| 83 |
+
"grad_norm": 2.407779675631392,
|
| 84 |
+
"learning_rate": 1.9130434782608697e-05,
|
| 85 |
+
"loss": 0.6642,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.12990527740189445,
|
| 90 |
+
"grad_norm": 1.9690081792484082,
|
| 91 |
+
"learning_rate": 2.0869565217391306e-05,
|
| 92 |
+
"loss": 0.6566,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14073071718538566,
|
| 97 |
+
"grad_norm": 1.2791289873731233,
|
| 98 |
+
"learning_rate": 2.2608695652173914e-05,
|
| 99 |
+
"loss": 0.636,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.15155615696887687,
|
| 104 |
+
"grad_norm": 1.4272246324351143,
|
| 105 |
+
"learning_rate": 2.4347826086956526e-05,
|
| 106 |
+
"loss": 0.6427,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.16238159675236807,
|
| 111 |
+
"grad_norm": 1.1897907235661358,
|
| 112 |
+
"learning_rate": 2.608695652173913e-05,
|
| 113 |
+
"loss": 0.6195,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.17320703653585928,
|
| 118 |
+
"grad_norm": 0.9139563980188694,
|
| 119 |
+
"learning_rate": 2.782608695652174e-05,
|
| 120 |
+
"loss": 0.6092,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.18403247631935046,
|
| 125 |
+
"grad_norm": 1.0660755035768057,
|
| 126 |
+
"learning_rate": 2.956521739130435e-05,
|
| 127 |
+
"loss": 0.6006,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.19485791610284167,
|
| 132 |
+
"grad_norm": 1.1289299633501881,
|
| 133 |
+
"learning_rate": 3.130434782608696e-05,
|
| 134 |
+
"loss": 0.5868,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.20568335588633288,
|
| 139 |
+
"grad_norm": 1.005093467371569,
|
| 140 |
+
"learning_rate": 3.304347826086957e-05,
|
| 141 |
+
"loss": 0.5769,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2165087956698241,
|
| 146 |
+
"grad_norm": 1.0253086560111697,
|
| 147 |
+
"learning_rate": 3.478260869565218e-05,
|
| 148 |
+
"loss": 0.5798,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2273342354533153,
|
| 153 |
+
"grad_norm": 1.4416719038843315,
|
| 154 |
+
"learning_rate": 3.6521739130434786e-05,
|
| 155 |
+
"loss": 0.5738,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2381596752368065,
|
| 160 |
+
"grad_norm": 0.9795141368299348,
|
| 161 |
+
"learning_rate": 3.8260869565217395e-05,
|
| 162 |
+
"loss": 0.5713,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2489851150202977,
|
| 167 |
+
"grad_norm": 0.9113506379565265,
|
| 168 |
+
"learning_rate": 4e-05,
|
| 169 |
+
"loss": 0.5636,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2598105548037889,
|
| 174 |
+
"grad_norm": 1.3018876548232534,
|
| 175 |
+
"learning_rate": 4.173913043478261e-05,
|
| 176 |
+
"loss": 0.5703,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2706359945872801,
|
| 181 |
+
"grad_norm": 1.0977569575275883,
|
| 182 |
+
"learning_rate": 4.347826086956522e-05,
|
| 183 |
+
"loss": 0.5608,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2814614343707713,
|
| 188 |
+
"grad_norm": 1.3185220107226532,
|
| 189 |
+
"learning_rate": 4.521739130434783e-05,
|
| 190 |
+
"loss": 0.5383,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2922868741542625,
|
| 195 |
+
"grad_norm": 1.4506983344294453,
|
| 196 |
+
"learning_rate": 4.6956521739130444e-05,
|
| 197 |
+
"loss": 0.5481,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.30311231393775373,
|
| 202 |
+
"grad_norm": 0.7383393635142479,
|
| 203 |
+
"learning_rate": 4.869565217391305e-05,
|
| 204 |
+
"loss": 0.5463,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.31393775372124494,
|
| 209 |
+
"grad_norm": 2.4652927181675315,
|
| 210 |
+
"learning_rate": 5.043478260869566e-05,
|
| 211 |
+
"loss": 0.5542,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.32476319350473615,
|
| 216 |
+
"grad_norm": 1.1746605790954319,
|
| 217 |
+
"learning_rate": 5.217391304347826e-05,
|
| 218 |
+
"loss": 0.5401,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.33558863328822736,
|
| 223 |
+
"grad_norm": 2.892014348770916,
|
| 224 |
+
"learning_rate": 5.391304347826087e-05,
|
| 225 |
+
"loss": 0.5552,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.34641407307171856,
|
| 230 |
+
"grad_norm": 2.5911400202995685,
|
| 231 |
+
"learning_rate": 5.565217391304348e-05,
|
| 232 |
+
"loss": 0.5547,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3572395128552097,
|
| 237 |
+
"grad_norm": 1.688863282311232,
|
| 238 |
+
"learning_rate": 5.739130434782609e-05,
|
| 239 |
+
"loss": 0.5499,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3680649526387009,
|
| 244 |
+
"grad_norm": 1.8689766358229456,
|
| 245 |
+
"learning_rate": 5.91304347826087e-05,
|
| 246 |
+
"loss": 0.55,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.37889039242219213,
|
| 251 |
+
"grad_norm": 1.561406905112785,
|
| 252 |
+
"learning_rate": 6.086956521739131e-05,
|
| 253 |
+
"loss": 0.5347,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.38971583220568334,
|
| 258 |
+
"grad_norm": 1.689162114377315,
|
| 259 |
+
"learning_rate": 6.260869565217392e-05,
|
| 260 |
+
"loss": 0.5264,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.40054127198917455,
|
| 265 |
+
"grad_norm": 1.444322528581452,
|
| 266 |
+
"learning_rate": 6.434782608695653e-05,
|
| 267 |
+
"loss": 0.5362,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.41136671177266576,
|
| 272 |
+
"grad_norm": 1.2509308676002273,
|
| 273 |
+
"learning_rate": 6.608695652173914e-05,
|
| 274 |
+
"loss": 0.5238,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.42219215155615697,
|
| 279 |
+
"grad_norm": 1.88113743058469,
|
| 280 |
+
"learning_rate": 6.782608695652175e-05,
|
| 281 |
+
"loss": 0.5311,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4330175913396482,
|
| 286 |
+
"grad_norm": 1.5022638539817577,
|
| 287 |
+
"learning_rate": 6.956521739130436e-05,
|
| 288 |
+
"loss": 0.523,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4438430311231394,
|
| 293 |
+
"grad_norm": 1.205391078251559,
|
| 294 |
+
"learning_rate": 7.130434782608696e-05,
|
| 295 |
+
"loss": 0.5188,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4546684709066306,
|
| 300 |
+
"grad_norm": 1.8357524846560098,
|
| 301 |
+
"learning_rate": 7.304347826086957e-05,
|
| 302 |
+
"loss": 0.5239,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4654939106901218,
|
| 307 |
+
"grad_norm": 1.3953240643163467,
|
| 308 |
+
"learning_rate": 7.478260869565218e-05,
|
| 309 |
+
"loss": 0.5174,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.476319350473613,
|
| 314 |
+
"grad_norm": 1.2828206105300195,
|
| 315 |
+
"learning_rate": 7.652173913043479e-05,
|
| 316 |
+
"loss": 0.5147,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.4871447902571042,
|
| 321 |
+
"grad_norm": 1.53155664347226,
|
| 322 |
+
"learning_rate": 7.82608695652174e-05,
|
| 323 |
+
"loss": 0.5243,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4979702300405954,
|
| 328 |
+
"grad_norm": 2.0731025195597055,
|
| 329 |
+
"learning_rate": 8e-05,
|
| 330 |
+
"loss": 0.5176,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5087956698240866,
|
| 335 |
+
"grad_norm": 1.297417565546252,
|
| 336 |
+
"learning_rate": 7.999884833286186e-05,
|
| 337 |
+
"loss": 0.5124,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5196211096075778,
|
| 342 |
+
"grad_norm": 2.0613915660565474,
|
| 343 |
+
"learning_rate": 7.999539339776424e-05,
|
| 344 |
+
"loss": 0.5211,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.530446549391069,
|
| 349 |
+
"grad_norm": 1.9265188351114966,
|
| 350 |
+
"learning_rate": 7.998963539365397e-05,
|
| 351 |
+
"loss": 0.5144,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5412719891745602,
|
| 356 |
+
"grad_norm": 1.1654357885632856,
|
| 357 |
+
"learning_rate": 7.998157465209622e-05,
|
| 358 |
+
"loss": 0.5084,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5520974289580515,
|
| 363 |
+
"grad_norm": 3.550729874275142,
|
| 364 |
+
"learning_rate": 7.997121163725553e-05,
|
| 365 |
+
"loss": 0.52,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5629228687415426,
|
| 370 |
+
"grad_norm": 2.538469141985988,
|
| 371 |
+
"learning_rate": 7.995854694586911e-05,
|
| 372 |
+
"loss": 0.527,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5737483085250338,
|
| 377 |
+
"grad_norm": 2.3230308550181977,
|
| 378 |
+
"learning_rate": 7.994358130721238e-05,
|
| 379 |
+
"loss": 0.5125,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.584573748308525,
|
| 384 |
+
"grad_norm": 2.054696895438045,
|
| 385 |
+
"learning_rate": 7.992631558305709e-05,
|
| 386 |
+
"loss": 0.5239,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.5953991880920162,
|
| 391 |
+
"grad_norm": 1.6692562446454873,
|
| 392 |
+
"learning_rate": 7.990675076762158e-05,
|
| 393 |
+
"loss": 0.5054,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6062246278755075,
|
| 398 |
+
"grad_norm": 1.6216758113364556,
|
| 399 |
+
"learning_rate": 7.988488798751358e-05,
|
| 400 |
+
"loss": 0.5106,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6170500676589986,
|
| 405 |
+
"grad_norm": 1.2978731074509846,
|
| 406 |
+
"learning_rate": 7.986072850166538e-05,
|
| 407 |
+
"loss": 0.5065,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6278755074424899,
|
| 412 |
+
"grad_norm": 1.5652885560156862,
|
| 413 |
+
"learning_rate": 7.983427370126126e-05,
|
| 414 |
+
"loss": 0.5062,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.638700947225981,
|
| 419 |
+
"grad_norm": 1.0902975831854205,
|
| 420 |
+
"learning_rate": 7.980552510965744e-05,
|
| 421 |
+
"loss": 0.4905,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6495263870094723,
|
| 426 |
+
"grad_norm": 1.7790014999967663,
|
| 427 |
+
"learning_rate": 7.977448438229435e-05,
|
| 428 |
+
"loss": 0.5013,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6603518267929634,
|
| 433 |
+
"grad_norm": 1.1023742875049254,
|
| 434 |
+
"learning_rate": 7.974115330660125e-05,
|
| 435 |
+
"loss": 0.5107,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6711772665764547,
|
| 440 |
+
"grad_norm": 1.6569283779226378,
|
| 441 |
+
"learning_rate": 7.970553380189338e-05,
|
| 442 |
+
"loss": 0.5004,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6820027063599459,
|
| 447 |
+
"grad_norm": 1.1231904813496703,
|
| 448 |
+
"learning_rate": 7.966762791926138e-05,
|
| 449 |
+
"loss": 0.5112,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6928281461434371,
|
| 454 |
+
"grad_norm": 1.3259929729824094,
|
| 455 |
+
"learning_rate": 7.962743784145323e-05,
|
| 456 |
+
"loss": 0.5033,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7036535859269283,
|
| 461 |
+
"grad_norm": 1.5905266367527235,
|
| 462 |
+
"learning_rate": 7.958496588274853e-05,
|
| 463 |
+
"loss": 0.4994,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7144790257104194,
|
| 468 |
+
"grad_norm": 1.3556731999712488,
|
| 469 |
+
"learning_rate": 7.954021448882522e-05,
|
| 470 |
+
"loss": 0.5014,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7253044654939107,
|
| 475 |
+
"grad_norm": 1.3046471245382867,
|
| 476 |
+
"learning_rate": 7.94931862366188e-05,
|
| 477 |
+
"loss": 0.4988,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7361299052774019,
|
| 482 |
+
"grad_norm": 1.1190463003547946,
|
| 483 |
+
"learning_rate": 7.944388383417388e-05,
|
| 484 |
+
"loss": 0.5078,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7469553450608931,
|
| 489 |
+
"grad_norm": 0.9403691436043241,
|
| 490 |
+
"learning_rate": 7.939231012048833e-05,
|
| 491 |
+
"loss": 0.497,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7577807848443843,
|
| 496 |
+
"grad_norm": 1.2389417771472975,
|
| 497 |
+
"learning_rate": 7.93384680653497e-05,
|
| 498 |
+
"loss": 0.4826,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7686062246278755,
|
| 503 |
+
"grad_norm": 1.4827310111058076,
|
| 504 |
+
"learning_rate": 7.928236076916423e-05,
|
| 505 |
+
"loss": 0.4856,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7794316644113667,
|
| 510 |
+
"grad_norm": 1.0266845521857724,
|
| 511 |
+
"learning_rate": 7.922399146277846e-05,
|
| 512 |
+
"loss": 0.4953,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.790257104194858,
|
| 517 |
+
"grad_norm": 1.5291553894877223,
|
| 518 |
+
"learning_rate": 7.916336350729293e-05,
|
| 519 |
+
"loss": 0.5043,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8010825439783491,
|
| 524 |
+
"grad_norm": 1.8339943841994815,
|
| 525 |
+
"learning_rate": 7.910048039386885e-05,
|
| 526 |
+
"loss": 0.4982,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.8119079837618404,
|
| 531 |
+
"grad_norm": 0.9242986864591416,
|
| 532 |
+
"learning_rate": 7.903534574352698e-05,
|
| 533 |
+
"loss": 0.4924,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8227334235453315,
|
| 538 |
+
"grad_norm": 2.1145786188124056,
|
| 539 |
+
"learning_rate": 7.896796330693917e-05,
|
| 540 |
+
"loss": 0.4941,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8335588633288228,
|
| 545 |
+
"grad_norm": 1.4704175209963846,
|
| 546 |
+
"learning_rate": 7.889833696421229e-05,
|
| 547 |
+
"loss": 0.4905,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8443843031123139,
|
| 552 |
+
"grad_norm": 1.642621714596807,
|
| 553 |
+
"learning_rate": 7.882647072466488e-05,
|
| 554 |
+
"loss": 0.4949,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8552097428958051,
|
| 559 |
+
"grad_norm": 1.6556981762458693,
|
| 560 |
+
"learning_rate": 7.875236872659626e-05,
|
| 561 |
+
"loss": 0.4956,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8660351826792964,
|
| 566 |
+
"grad_norm": 1.2644916442646428,
|
| 567 |
+
"learning_rate": 7.867603523704825e-05,
|
| 568 |
+
"loss": 0.4891,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8768606224627875,
|
| 573 |
+
"grad_norm": 1.2082452092510187,
|
| 574 |
+
"learning_rate": 7.859747465155941e-05,
|
| 575 |
+
"loss": 0.4983,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.8876860622462788,
|
| 580 |
+
"grad_norm": 1.7000626612415155,
|
| 581 |
+
"learning_rate": 7.851669149391198e-05,
|
| 582 |
+
"loss": 0.4853,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8985115020297699,
|
| 587 |
+
"grad_norm": 0.9763637711052663,
|
| 588 |
+
"learning_rate": 7.843369041587135e-05,
|
| 589 |
+
"loss": 0.4899,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9093369418132612,
|
| 594 |
+
"grad_norm": 1.8287685880691984,
|
| 595 |
+
"learning_rate": 7.834847619691823e-05,
|
| 596 |
+
"loss": 0.4921,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9201623815967523,
|
| 601 |
+
"grad_norm": 1.14896663354127,
|
| 602 |
+
"learning_rate": 7.82610537439734e-05,
|
| 603 |
+
"loss": 0.491,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9309878213802436,
|
| 608 |
+
"grad_norm": 1.3967407140368298,
|
| 609 |
+
"learning_rate": 7.817142809111516e-05,
|
| 610 |
+
"loss": 0.4927,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9418132611637348,
|
| 615 |
+
"grad_norm": 1.1259520998597332,
|
| 616 |
+
"learning_rate": 7.807960439928948e-05,
|
| 617 |
+
"loss": 0.4901,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.952638700947226,
|
| 622 |
+
"grad_norm": 1.1407620174965618,
|
| 623 |
+
"learning_rate": 7.798558795601278e-05,
|
| 624 |
+
"loss": 0.4727,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.9634641407307172,
|
| 629 |
+
"grad_norm": 1.3691640356867825,
|
| 630 |
+
"learning_rate": 7.788938417506746e-05,
|
| 631 |
+
"loss": 0.4909,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9742895805142084,
|
| 636 |
+
"grad_norm": 1.0738641081237286,
|
| 637 |
+
"learning_rate": 7.779099859619017e-05,
|
| 638 |
+
"loss": 0.486,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9851150202976996,
|
| 643 |
+
"grad_norm": 1.4806199400962288,
|
| 644 |
+
"learning_rate": 7.769043688475283e-05,
|
| 645 |
+
"loss": 0.4874,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.9959404600811907,
|
| 650 |
+
"grad_norm": 1.1066743457942432,
|
| 651 |
+
"learning_rate": 7.758770483143634e-05,
|
| 652 |
+
"loss": 0.4911,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.006765899864682,
|
| 657 |
+
"grad_norm": 1.4950362727418445,
|
| 658 |
+
"learning_rate": 7.748280835189721e-05,
|
| 659 |
+
"loss": 0.7639,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.0175913396481733,
|
| 664 |
+
"grad_norm": 1.7271457672573984,
|
| 665 |
+
"learning_rate": 7.737575348642685e-05,
|
| 666 |
+
"loss": 0.4898,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.0284167794316643,
|
| 671 |
+
"grad_norm": 1.3798243699861912,
|
| 672 |
+
"learning_rate": 7.726654639960379e-05,
|
| 673 |
+
"loss": 0.4714,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.0392422192151556,
|
| 678 |
+
"grad_norm": 1.0339630311729218,
|
| 679 |
+
"learning_rate": 7.715519337993869e-05,
|
| 680 |
+
"loss": 0.4714,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.0500676589986468,
|
| 685 |
+
"grad_norm": 1.4631122991865602,
|
| 686 |
+
"learning_rate": 7.704170083951221e-05,
|
| 687 |
+
"loss": 0.4684,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.060893098782138,
|
| 692 |
+
"grad_norm": 1.0376053642460665,
|
| 693 |
+
"learning_rate": 7.692607531360583e-05,
|
| 694 |
+
"loss": 0.4741,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.0717185385656292,
|
| 699 |
+
"grad_norm": 1.4499129358788265,
|
| 700 |
+
"learning_rate": 7.680832346032547e-05,
|
| 701 |
+
"loss": 0.4738,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.0825439783491204,
|
| 706 |
+
"grad_norm": 0.9495063833446171,
|
| 707 |
+
"learning_rate": 7.668845206021812e-05,
|
| 708 |
+
"loss": 0.4652,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.0933694181326117,
|
| 713 |
+
"grad_norm": 1.3963825686162348,
|
| 714 |
+
"learning_rate": 7.65664680158814e-05,
|
| 715 |
+
"loss": 0.4699,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.104194857916103,
|
| 720 |
+
"grad_norm": 1.1180437569666657,
|
| 721 |
+
"learning_rate": 7.644237835156608e-05,
|
| 722 |
+
"loss": 0.4684,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.115020297699594,
|
| 727 |
+
"grad_norm": 1.0782036495140483,
|
| 728 |
+
"learning_rate": 7.631619021277156e-05,
|
| 729 |
+
"loss": 0.4678,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.1258457374830853,
|
| 734 |
+
"grad_norm": 1.1233442468927228,
|
| 735 |
+
"learning_rate": 7.618791086583451e-05,
|
| 736 |
+
"loss": 0.4596,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.1366711772665765,
|
| 741 |
+
"grad_norm": 0.8610664763636607,
|
| 742 |
+
"learning_rate": 7.605754769751033e-05,
|
| 743 |
+
"loss": 0.4602,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.1474966170500678,
|
| 748 |
+
"grad_norm": 0.9718815741535982,
|
| 749 |
+
"learning_rate": 7.592510821454785e-05,
|
| 750 |
+
"loss": 0.4664,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.1583220568335588,
|
| 755 |
+
"grad_norm": 0.9229650455953634,
|
| 756 |
+
"learning_rate": 7.579060004325712e-05,
|
| 757 |
+
"loss": 0.4588,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.16914749661705,
|
| 762 |
+
"grad_norm": 1.3303689079136494,
|
| 763 |
+
"learning_rate": 7.565403092907015e-05,
|
| 764 |
+
"loss": 0.4567,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.1799729364005414,
|
| 769 |
+
"grad_norm": 0.6851116777600401,
|
| 770 |
+
"learning_rate": 7.551540873609502e-05,
|
| 771 |
+
"loss": 0.4586,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.1907983761840324,
|
| 776 |
+
"grad_norm": 0.6799287282219464,
|
| 777 |
+
"learning_rate": 7.53747414466629e-05,
|
| 778 |
+
"loss": 0.4618,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.2016238159675237,
|
| 783 |
+
"grad_norm": 0.8466498529896461,
|
| 784 |
+
"learning_rate": 7.523203716086855e-05,
|
| 785 |
+
"loss": 0.462,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.212449255751015,
|
| 790 |
+
"grad_norm": 1.117632861579111,
|
| 791 |
+
"learning_rate": 7.508730409610377e-05,
|
| 792 |
+
"loss": 0.4569,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.2232746955345062,
|
| 797 |
+
"grad_norm": 1.23247753401417,
|
| 798 |
+
"learning_rate": 7.494055058658431e-05,
|
| 799 |
+
"loss": 0.4522,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.2341001353179972,
|
| 804 |
+
"grad_norm": 0.566030648541157,
|
| 805 |
+
"learning_rate": 7.479178508286987e-05,
|
| 806 |
+
"loss": 0.4564,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.2449255751014885,
|
| 811 |
+
"grad_norm": 1.058284756916062,
|
| 812 |
+
"learning_rate": 7.464101615137756e-05,
|
| 813 |
+
"loss": 0.4638,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.2557510148849798,
|
| 818 |
+
"grad_norm": 1.1303301791005846,
|
| 819 |
+
"learning_rate": 7.448825247388854e-05,
|
| 820 |
+
"loss": 0.4564,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.266576454668471,
|
| 825 |
+
"grad_norm": 0.7983550091865995,
|
| 826 |
+
"learning_rate": 7.433350284704822e-05,
|
| 827 |
+
"loss": 0.4509,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.277401894451962,
|
| 832 |
+
"grad_norm": 0.7407469605628687,
|
| 833 |
+
"learning_rate": 7.417677618185955e-05,
|
| 834 |
+
"loss": 0.4515,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.2882273342354533,
|
| 839 |
+
"grad_norm": 1.2023281817243203,
|
| 840 |
+
"learning_rate": 7.401808150317005e-05,
|
| 841 |
+
"loss": 0.4594,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.2990527740189446,
|
| 846 |
+
"grad_norm": 1.189203037612418,
|
| 847 |
+
"learning_rate": 7.385742794915205e-05,
|
| 848 |
+
"loss": 0.4488,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.3098782138024356,
|
| 853 |
+
"grad_norm": 0.7803369478691763,
|
| 854 |
+
"learning_rate": 7.369482477077647e-05,
|
| 855 |
+
"loss": 0.4538,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.320703653585927,
|
| 860 |
+
"grad_norm": 0.7956495942708723,
|
| 861 |
+
"learning_rate": 7.353028133128018e-05,
|
| 862 |
+
"loss": 0.4508,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.3315290933694182,
|
| 867 |
+
"grad_norm": 0.7174722493029648,
|
| 868 |
+
"learning_rate": 7.336380710562678e-05,
|
| 869 |
+
"loss": 0.4541,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.3423545331529092,
|
| 874 |
+
"grad_norm": 1.232102677986553,
|
| 875 |
+
"learning_rate": 7.319541167996102e-05,
|
| 876 |
+
"loss": 0.4516,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.3531799729364005,
|
| 881 |
+
"grad_norm": 1.0800843680461558,
|
| 882 |
+
"learning_rate": 7.302510475105679e-05,
|
| 883 |
+
"loss": 0.4501,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.3640054127198917,
|
| 888 |
+
"grad_norm": 0.5894796400207796,
|
| 889 |
+
"learning_rate": 7.285289612575876e-05,
|
| 890 |
+
"loss": 0.4483,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.374830852503383,
|
| 895 |
+
"grad_norm": 1.1029047763873172,
|
| 896 |
+
"learning_rate": 7.267879572041768e-05,
|
| 897 |
+
"loss": 0.4419,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.3856562922868743,
|
| 902 |
+
"grad_norm": 1.0991239671136233,
|
| 903 |
+
"learning_rate": 7.250281356031932e-05,
|
| 904 |
+
"loss": 0.4444,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.3964817320703653,
|
| 909 |
+
"grad_norm": 0.6037885510659295,
|
| 910 |
+
"learning_rate": 7.232495977910722e-05,
|
| 911 |
+
"loss": 0.4429,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.4073071718538566,
|
| 916 |
+
"grad_norm": 0.8683412309547249,
|
| 917 |
+
"learning_rate": 7.214524461819913e-05,
|
| 918 |
+
"loss": 0.4474,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.4181326116373478,
|
| 923 |
+
"grad_norm": 1.0334636806232549,
|
| 924 |
+
"learning_rate": 7.196367842619732e-05,
|
| 925 |
+
"loss": 0.4488,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.4289580514208389,
|
| 930 |
+
"grad_norm": 0.6466646925111661,
|
| 931 |
+
"learning_rate": 7.178027165829259e-05,
|
| 932 |
+
"loss": 0.4491,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.4397834912043301,
|
| 937 |
+
"grad_norm": 0.5372317843885743,
|
| 938 |
+
"learning_rate": 7.159503487566236e-05,
|
| 939 |
+
"loss": 0.4429,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.4506089309878214,
|
| 944 |
+
"grad_norm": 0.8834867060322021,
|
| 945 |
+
"learning_rate": 7.140797874486237e-05,
|
| 946 |
+
"loss": 0.4452,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.4614343707713127,
|
| 951 |
+
"grad_norm": 1.2604508969646684,
|
| 952 |
+
"learning_rate": 7.121911403721254e-05,
|
| 953 |
+
"loss": 0.4468,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.472259810554804,
|
| 958 |
+
"grad_norm": 0.880677105803717,
|
| 959 |
+
"learning_rate": 7.10284516281768e-05,
|
| 960 |
+
"loss": 0.444,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.483085250338295,
|
| 965 |
+
"grad_norm": 1.3371545062212136,
|
| 966 |
+
"learning_rate": 7.083600249673665e-05,
|
| 967 |
+
"loss": 0.4433,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.4939106901217862,
|
| 972 |
+
"grad_norm": 0.7924984552860372,
|
| 973 |
+
"learning_rate": 7.064177772475912e-05,
|
| 974 |
+
"loss": 0.4475,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.5047361299052775,
|
| 979 |
+
"grad_norm": 0.9612014933614488,
|
| 980 |
+
"learning_rate": 7.04457884963586e-05,
|
| 981 |
+
"loss": 0.4468,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.5155615696887685,
|
| 986 |
+
"grad_norm": 0.9392541492862665,
|
| 987 |
+
"learning_rate": 7.024804609725275e-05,
|
| 988 |
+
"loss": 0.4464,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.5263870094722598,
|
| 993 |
+
"grad_norm": 0.9060567297197456,
|
| 994 |
+
"learning_rate": 7.004856191411271e-05,
|
| 995 |
+
"loss": 0.4432,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.537212449255751,
|
| 1000 |
+
"grad_norm": 1.1369625648430384,
|
| 1001 |
+
"learning_rate": 6.984734743390743e-05,
|
| 1002 |
+
"loss": 0.4461,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.548037889039242,
|
| 1007 |
+
"grad_norm": 0.7931097580196472,
|
| 1008 |
+
"learning_rate": 6.964441424324211e-05,
|
| 1009 |
+
"loss": 0.4498,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.5588633288227334,
|
| 1014 |
+
"grad_norm": 0.6650867960347666,
|
| 1015 |
+
"learning_rate": 6.94397740276911e-05,
|
| 1016 |
+
"loss": 0.4413,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.5696887686062246,
|
| 1021 |
+
"grad_norm": 0.6886753142567965,
|
| 1022 |
+
"learning_rate": 6.923343857112497e-05,
|
| 1023 |
+
"loss": 0.4387,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.5805142083897157,
|
| 1028 |
+
"grad_norm": 0.805662884063706,
|
| 1029 |
+
"learning_rate": 6.902541975503196e-05,
|
| 1030 |
+
"loss": 0.4397,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.5913396481732072,
|
| 1035 |
+
"grad_norm": 1.0626477516142214,
|
| 1036 |
+
"learning_rate": 6.881572955783382e-05,
|
| 1037 |
+
"loss": 0.4368,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.6021650879566982,
|
| 1042 |
+
"grad_norm": 1.5615470459694212,
|
| 1043 |
+
"learning_rate": 6.860438005419598e-05,
|
| 1044 |
+
"loss": 0.4574,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.6129905277401895,
|
| 1049 |
+
"grad_norm": 0.5178061477784288,
|
| 1050 |
+
"learning_rate": 6.839138341433236e-05,
|
| 1051 |
+
"loss": 0.4374,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.6238159675236807,
|
| 1056 |
+
"grad_norm": 1.546889550067696,
|
| 1057 |
+
"learning_rate": 6.81767519033045e-05,
|
| 1058 |
+
"loss": 0.4497,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.6346414073071718,
|
| 1063 |
+
"grad_norm": 0.9730507254509676,
|
| 1064 |
+
"learning_rate": 6.796049788031528e-05,
|
| 1065 |
+
"loss": 0.4449,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.645466847090663,
|
| 1070 |
+
"grad_norm": 0.9982813699267655,
|
| 1071 |
+
"learning_rate": 6.774263379799732e-05,
|
| 1072 |
+
"loss": 0.4432,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.6562922868741543,
|
| 1077 |
+
"grad_norm": 0.9179776054358382,
|
| 1078 |
+
"learning_rate": 6.752317220169581e-05,
|
| 1079 |
+
"loss": 0.4549,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.6671177266576453,
|
| 1084 |
+
"grad_norm": 0.7434050468751098,
|
| 1085 |
+
"learning_rate": 6.730212572874618e-05,
|
| 1086 |
+
"loss": 0.4448,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.6779431664411368,
|
| 1091 |
+
"grad_norm": 0.8630643785039801,
|
| 1092 |
+
"learning_rate": 6.707950710774636e-05,
|
| 1093 |
+
"loss": 0.4389,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.6887686062246279,
|
| 1098 |
+
"grad_norm": 0.95594617069569,
|
| 1099 |
+
"learning_rate": 6.685532915782388e-05,
|
| 1100 |
+
"loss": 0.446,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.699594046008119,
|
| 1105 |
+
"grad_norm": 0.6787389488446376,
|
| 1106 |
+
"learning_rate": 6.662960478789762e-05,
|
| 1107 |
+
"loss": 0.4308,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.7104194857916104,
|
| 1112 |
+
"grad_norm": 0.7138902871017276,
|
| 1113 |
+
"learning_rate": 6.640234699593457e-05,
|
| 1114 |
+
"loss": 0.4422,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.7212449255751014,
|
| 1119 |
+
"grad_norm": 0.8555364605092094,
|
| 1120 |
+
"learning_rate": 6.617356886820125e-05,
|
| 1121 |
+
"loss": 0.4489,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.7320703653585927,
|
| 1126 |
+
"grad_norm": 0.6416736344584283,
|
| 1127 |
+
"learning_rate": 6.594328357851024e-05,
|
| 1128 |
+
"loss": 0.4421,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.742895805142084,
|
| 1133 |
+
"grad_norm": 0.5280156168745573,
|
| 1134 |
+
"learning_rate": 6.571150438746157e-05,
|
| 1135 |
+
"loss": 0.4388,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.753721244925575,
|
| 1140 |
+
"grad_norm": 0.6725595610717778,
|
| 1141 |
+
"learning_rate": 6.547824464167913e-05,
|
| 1142 |
+
"loss": 0.4445,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.7645466847090663,
|
| 1147 |
+
"grad_norm": 0.866322013820141,
|
| 1148 |
+
"learning_rate": 6.524351777304212e-05,
|
| 1149 |
+
"loss": 0.4377,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.7753721244925575,
|
| 1154 |
+
"grad_norm": 1.0791676369113699,
|
| 1155 |
+
"learning_rate": 6.500733729791156e-05,
|
| 1156 |
+
"loss": 0.436,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.7861975642760486,
|
| 1161 |
+
"grad_norm": 0.8392320511506657,
|
| 1162 |
+
"learning_rate": 6.476971681635209e-05,
|
| 1163 |
+
"loss": 0.4422,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.79702300405954,
|
| 1168 |
+
"grad_norm": 0.9498667235195808,
|
| 1169 |
+
"learning_rate": 6.453067001134866e-05,
|
| 1170 |
+
"loss": 0.4363,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.8078484438430311,
|
| 1175 |
+
"grad_norm": 0.9454272098217824,
|
| 1176 |
+
"learning_rate": 6.429021064801879e-05,
|
| 1177 |
+
"loss": 0.4413,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.8186738836265224,
|
| 1182 |
+
"grad_norm": 1.0615616521628106,
|
| 1183 |
+
"learning_rate": 6.404835257281981e-05,
|
| 1184 |
+
"loss": 0.4381,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.8294993234100136,
|
| 1189 |
+
"grad_norm": 0.9856953495735615,
|
| 1190 |
+
"learning_rate": 6.38051097127516e-05,
|
| 1191 |
+
"loss": 0.4464,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.8403247631935047,
|
| 1196 |
+
"grad_norm": 0.753057646053996,
|
| 1197 |
+
"learning_rate": 6.356049607455456e-05,
|
| 1198 |
+
"loss": 0.4363,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.851150202976996,
|
| 1203 |
+
"grad_norm": 0.39232654080746043,
|
| 1204 |
+
"learning_rate": 6.331452574390314e-05,
|
| 1205 |
+
"loss": 0.4312,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.8619756427604872,
|
| 1210 |
+
"grad_norm": 0.4651286070389448,
|
| 1211 |
+
"learning_rate": 6.30672128845947e-05,
|
| 1212 |
+
"loss": 0.4326,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.8728010825439783,
|
| 1217 |
+
"grad_norm": 0.498700372148241,
|
| 1218 |
+
"learning_rate": 6.281857173773384e-05,
|
| 1219 |
+
"loss": 0.4266,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.8836265223274695,
|
| 1224 |
+
"grad_norm": 0.6143971888783442,
|
| 1225 |
+
"learning_rate": 6.25686166209125e-05,
|
| 1226 |
+
"loss": 0.4394,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.8944519621109608,
|
| 1231 |
+
"grad_norm": 0.5823010909272562,
|
| 1232 |
+
"learning_rate": 6.231736192738535e-05,
|
| 1233 |
+
"loss": 0.4334,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.9052774018944518,
|
| 1238 |
+
"grad_norm": 0.5433244104111088,
|
| 1239 |
+
"learning_rate": 6.206482212524109e-05,
|
| 1240 |
+
"loss": 0.4279,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.9161028416779433,
|
| 1245 |
+
"grad_norm": 0.40429580977808727,
|
| 1246 |
+
"learning_rate": 6.181101175656932e-05,
|
| 1247 |
+
"loss": 0.4294,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.9269282814614344,
|
| 1252 |
+
"grad_norm": 0.3710586154986815,
|
| 1253 |
+
"learning_rate": 6.155594543662304e-05,
|
| 1254 |
+
"loss": 0.4395,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.9377537212449256,
|
| 1259 |
+
"grad_norm": 0.3830066254564287,
|
| 1260 |
+
"learning_rate": 6.12996378529772e-05,
|
| 1261 |
+
"loss": 0.4333,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.9485791610284169,
|
| 1266 |
+
"grad_norm": 0.3863659341469274,
|
| 1267 |
+
"learning_rate": 6.104210376468284e-05,
|
| 1268 |
+
"loss": 0.4358,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.959404600811908,
|
| 1273 |
+
"grad_norm": 0.35342627993699427,
|
| 1274 |
+
"learning_rate": 6.078335800141735e-05,
|
| 1275 |
+
"loss": 0.4341,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.9702300405953992,
|
| 1280 |
+
"grad_norm": 0.36966775051107076,
|
| 1281 |
+
"learning_rate": 6.052341546263032e-05,
|
| 1282 |
+
"loss": 0.4306,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.9810554803788905,
|
| 1287 |
+
"grad_norm": 0.4038581298736109,
|
| 1288 |
+
"learning_rate": 6.026229111668572e-05,
|
| 1289 |
+
"loss": 0.4378,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.9918809201623815,
|
| 1294 |
+
"grad_norm": 0.4488772095787638,
|
| 1295 |
+
"learning_rate": 6.000000000000001e-05,
|
| 1296 |
+
"loss": 0.4389,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.002706359945873,
|
| 1301 |
+
"grad_norm": 0.8295155001148825,
|
| 1302 |
+
"learning_rate": 5.973655721617613e-05,
|
| 1303 |
+
"loss": 0.6879,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.013531799729364,
|
| 1308 |
+
"grad_norm": 1.4737016899362347,
|
| 1309 |
+
"learning_rate": 5.947197793513394e-05,
|
| 1310 |
+
"loss": 0.407,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.024357239512855,
|
| 1315 |
+
"grad_norm": 0.5993476508246326,
|
| 1316 |
+
"learning_rate": 5.920627739223663e-05,
|
| 1317 |
+
"loss": 0.4022,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.0351826792963466,
|
| 1322 |
+
"grad_norm": 0.7123790524835452,
|
| 1323 |
+
"learning_rate": 5.8939470887413364e-05,
|
| 1324 |
+
"loss": 0.4034,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.0460081190798376,
|
| 1329 |
+
"grad_norm": 1.0489551042023235,
|
| 1330 |
+
"learning_rate": 5.867157378427835e-05,
|
| 1331 |
+
"loss": 0.398,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.0568335588633286,
|
| 1336 |
+
"grad_norm": 1.1280435275179306,
|
| 1337 |
+
"learning_rate": 5.840260150924609e-05,
|
| 1338 |
+
"loss": 0.4039,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.06765899864682,
|
| 1343 |
+
"grad_norm": 0.8086213856542805,
|
| 1344 |
+
"learning_rate": 5.81325695506431e-05,
|
| 1345 |
+
"loss": 0.4069,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.078484438430311,
|
| 1350 |
+
"grad_norm": 0.7971526749207055,
|
| 1351 |
+
"learning_rate": 5.7861493457816005e-05,
|
| 1352 |
+
"loss": 0.4108,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.089309878213802,
|
| 1357 |
+
"grad_norm": 0.6150880177459436,
|
| 1358 |
+
"learning_rate": 5.7589388840236235e-05,
|
| 1359 |
+
"loss": 0.4023,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.1001353179972937,
|
| 1364 |
+
"grad_norm": 0.6200048701618767,
|
| 1365 |
+
"learning_rate": 5.73162713666011e-05,
|
| 1366 |
+
"loss": 0.3947,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.1109607577807847,
|
| 1371 |
+
"grad_norm": 0.9512484994979096,
|
| 1372 |
+
"learning_rate": 5.704215676393154e-05,
|
| 1373 |
+
"loss": 0.4043,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.121786197564276,
|
| 1378 |
+
"grad_norm": 0.8033132486864113,
|
| 1379 |
+
"learning_rate": 5.676706081666657e-05,
|
| 1380 |
+
"loss": 0.4023,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.1326116373477673,
|
| 1385 |
+
"grad_norm": 0.6857766246265746,
|
| 1386 |
+
"learning_rate": 5.6490999365754304e-05,
|
| 1387 |
+
"loss": 0.3989,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.1434370771312583,
|
| 1392 |
+
"grad_norm": 0.7160087962374165,
|
| 1393 |
+
"learning_rate": 5.621398830773979e-05,
|
| 1394 |
+
"loss": 0.3974,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.15426251691475,
|
| 1399 |
+
"grad_norm": 0.7255913343428894,
|
| 1400 |
+
"learning_rate": 5.593604359384967e-05,
|
| 1401 |
+
"loss": 0.4046,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.165087956698241,
|
| 1406 |
+
"grad_norm": 1.0668814854383228,
|
| 1407 |
+
"learning_rate": 5.5657181229073584e-05,
|
| 1408 |
+
"loss": 0.4069,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.175913396481732,
|
| 1413 |
+
"grad_norm": 0.6695749773505052,
|
| 1414 |
+
"learning_rate": 5.5377417271242605e-05,
|
| 1415 |
+
"loss": 0.4004,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.1867388362652234,
|
| 1420 |
+
"grad_norm": 0.41018811941016275,
|
| 1421 |
+
"learning_rate": 5.5096767830104574e-05,
|
| 1422 |
+
"loss": 0.3973,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.1975642760487144,
|
| 1427 |
+
"grad_norm": 0.7331180833734219,
|
| 1428 |
+
"learning_rate": 5.481524906639645e-05,
|
| 1429 |
+
"loss": 0.4049,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.208389715832206,
|
| 1434 |
+
"grad_norm": 0.7311488343422455,
|
| 1435 |
+
"learning_rate": 5.453287719091366e-05,
|
| 1436 |
+
"loss": 0.4039,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.219215155615697,
|
| 1441 |
+
"grad_norm": 0.46217024270353824,
|
| 1442 |
+
"learning_rate": 5.424966846357668e-05,
|
| 1443 |
+
"loss": 0.4001,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.230040595399188,
|
| 1448 |
+
"grad_norm": 0.3580272770419428,
|
| 1449 |
+
"learning_rate": 5.3965639192494746e-05,
|
| 1450 |
+
"loss": 0.3995,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.2408660351826795,
|
| 1455 |
+
"grad_norm": 0.5415105544180893,
|
| 1456 |
+
"learning_rate": 5.368080573302676e-05,
|
| 1457 |
+
"loss": 0.4047,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.2516914749661705,
|
| 1462 |
+
"grad_norm": 0.5146452956341113,
|
| 1463 |
+
"learning_rate": 5.339518448683945e-05,
|
| 1464 |
+
"loss": 0.3959,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.2625169147496615,
|
| 1469 |
+
"grad_norm": 0.40046443729910486,
|
| 1470 |
+
"learning_rate": 5.3108791900963e-05,
|
| 1471 |
+
"loss": 0.3997,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.273342354533153,
|
| 1476 |
+
"grad_norm": 0.3552796868979913,
|
| 1477 |
+
"learning_rate": 5.282164446684389e-05,
|
| 1478 |
+
"loss": 0.3954,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.284167794316644,
|
| 1483 |
+
"grad_norm": 0.495387489856506,
|
| 1484 |
+
"learning_rate": 5.2533758719395294e-05,
|
| 1485 |
+
"loss": 0.3972,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.2949932341001356,
|
| 1490 |
+
"grad_norm": 0.37686968387016173,
|
| 1491 |
+
"learning_rate": 5.2245151236044974e-05,
|
| 1492 |
+
"loss": 0.3976,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.3058186738836266,
|
| 1497 |
+
"grad_norm": 0.2823917242370533,
|
| 1498 |
+
"learning_rate": 5.195583863578064e-05,
|
| 1499 |
+
"loss": 0.4049,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.3166441136671176,
|
| 1504 |
+
"grad_norm": 0.33559837716294566,
|
| 1505 |
+
"learning_rate": 5.1665837578193e-05,
|
| 1506 |
+
"loss": 0.3992,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.3274695534506087,
|
| 1511 |
+
"grad_norm": 0.2837563379510337,
|
| 1512 |
+
"learning_rate": 5.137516476251648e-05,
|
| 1513 |
+
"loss": 0.3997,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.3382949932341,
|
| 1518 |
+
"grad_norm": 0.28846039259956097,
|
| 1519 |
+
"learning_rate": 5.108383692666756e-05,
|
| 1520 |
+
"loss": 0.4054,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.349120433017591,
|
| 1525 |
+
"grad_norm": 0.3171321353936286,
|
| 1526 |
+
"learning_rate": 5.0791870846280974e-05,
|
| 1527 |
+
"loss": 0.3992,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.3599458728010827,
|
| 1532 |
+
"grad_norm": 0.2678755670767341,
|
| 1533 |
+
"learning_rate": 5.0499283333743754e-05,
|
| 1534 |
+
"loss": 0.4077,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.3707713125845737,
|
| 1539 |
+
"grad_norm": 0.2737614063807259,
|
| 1540 |
+
"learning_rate": 5.020609123722705e-05,
|
| 1541 |
+
"loss": 0.4037,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.381596752368065,
|
| 1546 |
+
"grad_norm": 0.3048714730712856,
|
| 1547 |
+
"learning_rate": 4.9912311439716e-05,
|
| 1548 |
+
"loss": 0.3911,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.3924221921515563,
|
| 1553 |
+
"grad_norm": 0.2574922530022283,
|
| 1554 |
+
"learning_rate": 4.961796085803754e-05,
|
| 1555 |
+
"loss": 0.3987,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.4032476319350473,
|
| 1560 |
+
"grad_norm": 0.32375321489222875,
|
| 1561 |
+
"learning_rate": 4.932305644188627e-05,
|
| 1562 |
+
"loss": 0.4056,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.414073071718539,
|
| 1567 |
+
"grad_norm": 0.3940310241959818,
|
| 1568 |
+
"learning_rate": 4.902761517284843e-05,
|
| 1569 |
+
"loss": 0.4041,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.42489851150203,
|
| 1574 |
+
"grad_norm": 0.30709183482329716,
|
| 1575 |
+
"learning_rate": 4.8731654063424066e-05,
|
| 1576 |
+
"loss": 0.4012,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.435723951285521,
|
| 1581 |
+
"grad_norm": 0.24828710130084936,
|
| 1582 |
+
"learning_rate": 4.843519015604739e-05,
|
| 1583 |
+
"loss": 0.3994,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.4465493910690124,
|
| 1588 |
+
"grad_norm": 0.3039622222887511,
|
| 1589 |
+
"learning_rate": 4.8138240522105365e-05,
|
| 1590 |
+
"loss": 0.4019,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.4573748308525034,
|
| 1595 |
+
"grad_norm": 0.3003924416251595,
|
| 1596 |
+
"learning_rate": 4.784082226095474e-05,
|
| 1597 |
+
"loss": 0.3962,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.4682002706359945,
|
| 1602 |
+
"grad_norm": 0.22755737327455813,
|
| 1603 |
+
"learning_rate": 4.7542952498937437e-05,
|
| 1604 |
+
"loss": 0.3983,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.479025710419486,
|
| 1609 |
+
"grad_norm": 0.25304360527606307,
|
| 1610 |
+
"learning_rate": 4.7244648388394235e-05,
|
| 1611 |
+
"loss": 0.3942,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 2.489851150202977,
|
| 1616 |
+
"grad_norm": 0.24578325368030968,
|
| 1617 |
+
"learning_rate": 4.694592710667723e-05,
|
| 1618 |
+
"loss": 0.3963,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.500676589986468,
|
| 1623 |
+
"grad_norm": 0.24077179007380192,
|
| 1624 |
+
"learning_rate": 4.664680585516057e-05,
|
| 1625 |
+
"loss": 0.4052,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.5115020297699595,
|
| 1630 |
+
"grad_norm": 0.25770064300310863,
|
| 1631 |
+
"learning_rate": 4.634730185825006e-05,
|
| 1632 |
+
"loss": 0.4023,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.5223274695534506,
|
| 1637 |
+
"grad_norm": 0.29543906900824984,
|
| 1638 |
+
"learning_rate": 4.604743236239124e-05,
|
| 1639 |
+
"loss": 0.3974,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.533152909336942,
|
| 1644 |
+
"grad_norm": 0.23991016795181042,
|
| 1645 |
+
"learning_rate": 4.574721463507633e-05,
|
| 1646 |
+
"loss": 0.3999,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.543978349120433,
|
| 1651 |
+
"grad_norm": 0.21566542112560377,
|
| 1652 |
+
"learning_rate": 4.5446665963849874e-05,
|
| 1653 |
+
"loss": 0.3931,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.554803788903924,
|
| 1658 |
+
"grad_norm": 0.26245544883616334,
|
| 1659 |
+
"learning_rate": 4.514580365531325e-05,
|
| 1660 |
+
"loss": 0.3921,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.565629228687415,
|
| 1665 |
+
"grad_norm": 0.2509466224574822,
|
| 1666 |
+
"learning_rate": 4.484464503412817e-05,
|
| 1667 |
+
"loss": 0.3989,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.5764546684709067,
|
| 1672 |
+
"grad_norm": 0.2921963850485716,
|
| 1673 |
+
"learning_rate": 4.4543207442019e-05,
|
| 1674 |
+
"loss": 0.3983,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.5872801082543977,
|
| 1679 |
+
"grad_norm": 0.21232868508333116,
|
| 1680 |
+
"learning_rate": 4.424150823677419e-05,
|
| 1681 |
+
"loss": 0.3951,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.598105548037889,
|
| 1686 |
+
"grad_norm": 0.2846484943408765,
|
| 1687 |
+
"learning_rate": 4.3939564791246744e-05,
|
| 1688 |
+
"loss": 0.4034,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.60893098782138,
|
| 1693 |
+
"grad_norm": 0.29357221150822416,
|
| 1694 |
+
"learning_rate": 4.3637394492353886e-05,
|
| 1695 |
+
"loss": 0.4052,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.6197564276048713,
|
| 1700 |
+
"grad_norm": 0.2532347044145875,
|
| 1701 |
+
"learning_rate": 4.333501474007574e-05,
|
| 1702 |
+
"loss": 0.4045,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.6305818673883627,
|
| 1707 |
+
"grad_norm": 0.20455259571037776,
|
| 1708 |
+
"learning_rate": 4.303244294645354e-05,
|
| 1709 |
+
"loss": 0.3958,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.641407307171854,
|
| 1714 |
+
"grad_norm": 0.23989966946640798,
|
| 1715 |
+
"learning_rate": 4.272969653458685e-05,
|
| 1716 |
+
"loss": 0.394,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.6522327469553453,
|
| 1721 |
+
"grad_norm": 0.2255061069896111,
|
| 1722 |
+
"learning_rate": 4.242679293763035e-05,
|
| 1723 |
+
"loss": 0.3942,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.6630581867388363,
|
| 1728 |
+
"grad_norm": 0.23515116200339933,
|
| 1729 |
+
"learning_rate": 4.2123749597789984e-05,
|
| 1730 |
+
"loss": 0.3956,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.6738836265223274,
|
| 1735 |
+
"grad_norm": 0.2248941135472504,
|
| 1736 |
+
"learning_rate": 4.1820583965318555e-05,
|
| 1737 |
+
"loss": 0.4011,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.6847090663058184,
|
| 1742 |
+
"grad_norm": 0.24317542119733318,
|
| 1743 |
+
"learning_rate": 4.151731349751086e-05,
|
| 1744 |
+
"loss": 0.3964,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.69553450608931,
|
| 1749 |
+
"grad_norm": 0.2182498690125644,
|
| 1750 |
+
"learning_rate": 4.12139556576985e-05,
|
| 1751 |
+
"loss": 0.3924,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.706359945872801,
|
| 1756 |
+
"grad_norm": 0.19757577350714361,
|
| 1757 |
+
"learning_rate": 4.091052791424423e-05,
|
| 1758 |
+
"loss": 0.4033,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.7171853856562924,
|
| 1763 |
+
"grad_norm": 0.24674384659213253,
|
| 1764 |
+
"learning_rate": 4.060704773953611e-05,
|
| 1765 |
+
"loss": 0.3998,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 2.7280108254397835,
|
| 1770 |
+
"grad_norm": 0.25492479480718416,
|
| 1771 |
+
"learning_rate": 4.0303532608981336e-05,
|
| 1772 |
+
"loss": 0.4035,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.7388362652232745,
|
| 1777 |
+
"grad_norm": 0.2061832272126445,
|
| 1778 |
+
"learning_rate": 4e-05,
|
| 1779 |
+
"loss": 0.4019,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.749661705006766,
|
| 1784 |
+
"grad_norm": 0.20527089406948276,
|
| 1785 |
+
"learning_rate": 3.969646739101868e-05,
|
| 1786 |
+
"loss": 0.3954,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.760487144790257,
|
| 1791 |
+
"grad_norm": 0.17828129068585608,
|
| 1792 |
+
"learning_rate": 3.93929522604639e-05,
|
| 1793 |
+
"loss": 0.3921,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.7713125845737485,
|
| 1798 |
+
"grad_norm": 0.22611834558135363,
|
| 1799 |
+
"learning_rate": 3.908947208575577e-05,
|
| 1800 |
+
"loss": 0.3903,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.7821380243572396,
|
| 1805 |
+
"grad_norm": 0.2132214449799281,
|
| 1806 |
+
"learning_rate": 3.878604434230151e-05,
|
| 1807 |
+
"loss": 0.4042,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.7929634641407306,
|
| 1812 |
+
"grad_norm": 0.18422878450192567,
|
| 1813 |
+
"learning_rate": 3.848268650248915e-05,
|
| 1814 |
+
"loss": 0.3973,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.803788903924222,
|
| 1819 |
+
"grad_norm": 0.199127350255564,
|
| 1820 |
+
"learning_rate": 3.8179416034681465e-05,
|
| 1821 |
+
"loss": 0.3954,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.814614343707713,
|
| 1826 |
+
"grad_norm": 0.196931992775811,
|
| 1827 |
+
"learning_rate": 3.7876250402210036e-05,
|
| 1828 |
+
"loss": 0.4007,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.825439783491204,
|
| 1833 |
+
"grad_norm": 0.22253615210660102,
|
| 1834 |
+
"learning_rate": 3.757320706236966e-05,
|
| 1835 |
+
"loss": 0.3902,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.8362652232746957,
|
| 1840 |
+
"grad_norm": 0.21034998071613925,
|
| 1841 |
+
"learning_rate": 3.727030346541317e-05,
|
| 1842 |
+
"loss": 0.3951,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 2.8470906630581867,
|
| 1847 |
+
"grad_norm": 0.220038673465254,
|
| 1848 |
+
"learning_rate": 3.696755705354647e-05,
|
| 1849 |
+
"loss": 0.3995,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.8579161028416777,
|
| 1854 |
+
"grad_norm": 0.2376263555554069,
|
| 1855 |
+
"learning_rate": 3.6664985259924265e-05,
|
| 1856 |
+
"loss": 0.3955,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.8687415426251692,
|
| 1861 |
+
"grad_norm": 0.18498115246118843,
|
| 1862 |
+
"learning_rate": 3.636260550764613e-05,
|
| 1863 |
+
"loss": 0.3994,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.8795669824086603,
|
| 1868 |
+
"grad_norm": 0.2281213349380945,
|
| 1869 |
+
"learning_rate": 3.6060435208753256e-05,
|
| 1870 |
+
"loss": 0.3976,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.8903924221921518,
|
| 1875 |
+
"grad_norm": 0.21257471713489817,
|
| 1876 |
+
"learning_rate": 3.575849176322582e-05,
|
| 1877 |
+
"loss": 0.3935,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.901217861975643,
|
| 1882 |
+
"grad_norm": 0.17668776804131658,
|
| 1883 |
+
"learning_rate": 3.5456792557981e-05,
|
| 1884 |
+
"loss": 0.3958,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 2.912043301759134,
|
| 1889 |
+
"grad_norm": 0.23579452170282567,
|
| 1890 |
+
"learning_rate": 3.5155354965871846e-05,
|
| 1891 |
+
"loss": 0.397,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 2.9228687415426253,
|
| 1896 |
+
"grad_norm": 0.21220661458040213,
|
| 1897 |
+
"learning_rate": 3.485419634468676e-05,
|
| 1898 |
+
"loss": 0.398,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 2.9336941813261164,
|
| 1903 |
+
"grad_norm": 0.29156175148563857,
|
| 1904 |
+
"learning_rate": 3.4553334036150146e-05,
|
| 1905 |
+
"loss": 0.3954,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.944519621109608,
|
| 1910 |
+
"grad_norm": 0.21342855706614183,
|
| 1911 |
+
"learning_rate": 3.425278536492368e-05,
|
| 1912 |
+
"loss": 0.4014,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 2.955345060893099,
|
| 1917 |
+
"grad_norm": 0.19007967113000737,
|
| 1918 |
+
"learning_rate": 3.395256763760877e-05,
|
| 1919 |
+
"loss": 0.3987,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.96617050067659,
|
| 1924 |
+
"grad_norm": 0.20030092145985207,
|
| 1925 |
+
"learning_rate": 3.3652698141749946e-05,
|
| 1926 |
+
"loss": 0.3969,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.976995940460081,
|
| 1931 |
+
"grad_norm": 0.1671102845524452,
|
| 1932 |
+
"learning_rate": 3.3353194144839444e-05,
|
| 1933 |
+
"loss": 0.4047,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.9878213802435725,
|
| 1938 |
+
"grad_norm": 0.22912012233424828,
|
| 1939 |
+
"learning_rate": 3.305407289332279e-05,
|
| 1940 |
+
"loss": 0.3926,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.9986468200270635,
|
| 1945 |
+
"grad_norm": 0.2683137652561869,
|
| 1946 |
+
"learning_rate": 3.2755351611605765e-05,
|
| 1947 |
+
"loss": 0.566,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 3.009472259810555,
|
| 1952 |
+
"grad_norm": 0.2952413857194597,
|
| 1953 |
+
"learning_rate": 3.245704750106257e-05,
|
| 1954 |
+
"loss": 0.455,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 3.020297699594046,
|
| 1959 |
+
"grad_norm": 0.23270668650047643,
|
| 1960 |
+
"learning_rate": 3.215917773904528e-05,
|
| 1961 |
+
"loss": 0.3727,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 3.031123139377537,
|
| 1966 |
+
"grad_norm": 0.24171506781246388,
|
| 1967 |
+
"learning_rate": 3.1861759477894656e-05,
|
| 1968 |
+
"loss": 0.3665,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 3.0419485791610286,
|
| 1973 |
+
"grad_norm": 0.2680860291808305,
|
| 1974 |
+
"learning_rate": 3.156480984395263e-05,
|
| 1975 |
+
"loss": 0.3666,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 3.0527740189445196,
|
| 1980 |
+
"grad_norm": 0.19524723806636465,
|
| 1981 |
+
"learning_rate": 3.126834593657595e-05,
|
| 1982 |
+
"loss": 0.3574,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 3.0635994587280106,
|
| 1987 |
+
"grad_norm": 0.23365726223954875,
|
| 1988 |
+
"learning_rate": 3.097238482715158e-05,
|
| 1989 |
+
"loss": 0.3691,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 3.074424898511502,
|
| 1994 |
+
"grad_norm": 0.20482362620161818,
|
| 1995 |
+
"learning_rate": 3.0676943558113745e-05,
|
| 1996 |
+
"loss": 0.3689,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 3.085250338294993,
|
| 2001 |
+
"grad_norm": 0.21174717829037049,
|
| 2002 |
+
"learning_rate": 3.0382039141962473e-05,
|
| 2003 |
+
"loss": 0.3631,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 3.096075778078484,
|
| 2008 |
+
"grad_norm": 0.19387440535216213,
|
| 2009 |
+
"learning_rate": 3.008768856028401e-05,
|
| 2010 |
+
"loss": 0.3666,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 3.1069012178619757,
|
| 2015 |
+
"grad_norm": 0.21151253274662332,
|
| 2016 |
+
"learning_rate": 2.9793908762772954e-05,
|
| 2017 |
+
"loss": 0.3667,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 3.1177266576454667,
|
| 2022 |
+
"grad_norm": 0.19220716557476908,
|
| 2023 |
+
"learning_rate": 2.950071666625625e-05,
|
| 2024 |
+
"loss": 0.3676,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 3.1285520974289582,
|
| 2029 |
+
"grad_norm": 0.18887116061755296,
|
| 2030 |
+
"learning_rate": 2.9208129153719026e-05,
|
| 2031 |
+
"loss": 0.3712,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 3.1393775372124493,
|
| 2036 |
+
"grad_norm": 0.217906436813338,
|
| 2037 |
+
"learning_rate": 2.8916163073332462e-05,
|
| 2038 |
+
"loss": 0.368,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 3.1502029769959403,
|
| 2043 |
+
"grad_norm": 0.16785424264087018,
|
| 2044 |
+
"learning_rate": 2.8624835237483535e-05,
|
| 2045 |
+
"loss": 0.3545,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 3.161028416779432,
|
| 2050 |
+
"grad_norm": 0.21288405997782842,
|
| 2051 |
+
"learning_rate": 2.8334162421807002e-05,
|
| 2052 |
+
"loss": 0.3603,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 3.171853856562923,
|
| 2057 |
+
"grad_norm": 0.17657164097795794,
|
| 2058 |
+
"learning_rate": 2.8044161364219378e-05,
|
| 2059 |
+
"loss": 0.3636,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 3.182679296346414,
|
| 2064 |
+
"grad_norm": 0.17503579725776347,
|
| 2065 |
+
"learning_rate": 2.775484876395504e-05,
|
| 2066 |
+
"loss": 0.3669,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 3.1935047361299054,
|
| 2071 |
+
"grad_norm": 0.1661974981289015,
|
| 2072 |
+
"learning_rate": 2.7466241280604716e-05,
|
| 2073 |
+
"loss": 0.3617,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 3.2043301759133964,
|
| 2078 |
+
"grad_norm": 0.1804231214261922,
|
| 2079 |
+
"learning_rate": 2.717835553315612e-05,
|
| 2080 |
+
"loss": 0.3665,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 3.2151556156968875,
|
| 2085 |
+
"grad_norm": 0.1627404959706761,
|
| 2086 |
+
"learning_rate": 2.6891208099037006e-05,
|
| 2087 |
+
"loss": 0.3719,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 3.225981055480379,
|
| 2092 |
+
"grad_norm": 0.16858290476423804,
|
| 2093 |
+
"learning_rate": 2.6604815513160556e-05,
|
| 2094 |
+
"loss": 0.373,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 3.23680649526387,
|
| 2099 |
+
"grad_norm": 0.17315102971170435,
|
| 2100 |
+
"learning_rate": 2.6319194266973256e-05,
|
| 2101 |
+
"loss": 0.3628,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 3.2476319350473615,
|
| 2106 |
+
"grad_norm": 0.17092619054701708,
|
| 2107 |
+
"learning_rate": 2.6034360807505267e-05,
|
| 2108 |
+
"loss": 0.3583,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 3.2584573748308525,
|
| 2113 |
+
"grad_norm": 0.16860391372808461,
|
| 2114 |
+
"learning_rate": 2.575033153642334e-05,
|
| 2115 |
+
"loss": 0.3627,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.2692828146143436,
|
| 2120 |
+
"grad_norm": 0.18423357259943915,
|
| 2121 |
+
"learning_rate": 2.5467122809086355e-05,
|
| 2122 |
+
"loss": 0.37,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.280108254397835,
|
| 2127 |
+
"grad_norm": 0.1549373166740434,
|
| 2128 |
+
"learning_rate": 2.518475093360356e-05,
|
| 2129 |
+
"loss": 0.3676,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.290933694181326,
|
| 2134 |
+
"grad_norm": 0.20520475892662024,
|
| 2135 |
+
"learning_rate": 2.490323216989543e-05,
|
| 2136 |
+
"loss": 0.3671,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.301759133964817,
|
| 2141 |
+
"grad_norm": 0.1462251183862993,
|
| 2142 |
+
"learning_rate": 2.46225827287574e-05,
|
| 2143 |
+
"loss": 0.3665,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.3125845737483086,
|
| 2148 |
+
"grad_norm": 0.2037257968520142,
|
| 2149 |
+
"learning_rate": 2.4342818770926437e-05,
|
| 2150 |
+
"loss": 0.3669,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.3234100135317997,
|
| 2155 |
+
"grad_norm": 0.15979516331505322,
|
| 2156 |
+
"learning_rate": 2.4063956406150345e-05,
|
| 2157 |
+
"loss": 0.3717,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 3.3342354533152907,
|
| 2162 |
+
"grad_norm": 0.18421360813445462,
|
| 2163 |
+
"learning_rate": 2.3786011692260216e-05,
|
| 2164 |
+
"loss": 0.3659,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 3.345060893098782,
|
| 2169 |
+
"grad_norm": 0.18353862952549732,
|
| 2170 |
+
"learning_rate": 2.35090006342457e-05,
|
| 2171 |
+
"loss": 0.3638,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 3.3558863328822732,
|
| 2176 |
+
"grad_norm": 0.16761186075113543,
|
| 2177 |
+
"learning_rate": 2.323293918333345e-05,
|
| 2178 |
+
"loss": 0.3704,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 3.3667117726657647,
|
| 2183 |
+
"grad_norm": 0.2012259488253085,
|
| 2184 |
+
"learning_rate": 2.295784323606848e-05,
|
| 2185 |
+
"loss": 0.3594,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 3.3775372124492558,
|
| 2190 |
+
"grad_norm": 0.14417434763773077,
|
| 2191 |
+
"learning_rate": 2.2683728633398926e-05,
|
| 2192 |
+
"loss": 0.3604,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 3.388362652232747,
|
| 2197 |
+
"grad_norm": 0.19765429801608228,
|
| 2198 |
+
"learning_rate": 2.2410611159763765e-05,
|
| 2199 |
+
"loss": 0.363,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 3.3991880920162383,
|
| 2204 |
+
"grad_norm": 0.14242034553646193,
|
| 2205 |
+
"learning_rate": 2.2138506542184e-05,
|
| 2206 |
+
"loss": 0.3608,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 3.4100135317997293,
|
| 2211 |
+
"grad_norm": 0.19492907121639994,
|
| 2212 |
+
"learning_rate": 2.1867430449356917e-05,
|
| 2213 |
+
"loss": 0.3672,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 3.420838971583221,
|
| 2218 |
+
"grad_norm": 0.18616307600245358,
|
| 2219 |
+
"learning_rate": 2.1597398490753917e-05,
|
| 2220 |
+
"loss": 0.3559,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 3.431664411366712,
|
| 2225 |
+
"grad_norm": 0.17108649074089605,
|
| 2226 |
+
"learning_rate": 2.1328426215721655e-05,
|
| 2227 |
+
"loss": 0.3619,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 3.442489851150203,
|
| 2232 |
+
"grad_norm": 0.1745701339642718,
|
| 2233 |
+
"learning_rate": 2.1060529112586642e-05,
|
| 2234 |
+
"loss": 0.3694,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 3.453315290933694,
|
| 2239 |
+
"grad_norm": 0.17738755753222712,
|
| 2240 |
+
"learning_rate": 2.0793722607763383e-05,
|
| 2241 |
+
"loss": 0.3655,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 3.4641407307171854,
|
| 2246 |
+
"grad_norm": 0.17061926888972667,
|
| 2247 |
+
"learning_rate": 2.0528022064866048e-05,
|
| 2248 |
+
"loss": 0.3753,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 3.4749661705006765,
|
| 2253 |
+
"grad_norm": 0.16060632755656637,
|
| 2254 |
+
"learning_rate": 2.0263442783823884e-05,
|
| 2255 |
+
"loss": 0.3582,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 3.485791610284168,
|
| 2260 |
+
"grad_norm": 0.1603561152232048,
|
| 2261 |
+
"learning_rate": 2.0000000000000012e-05,
|
| 2262 |
+
"loss": 0.3667,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 3.496617050067659,
|
| 2267 |
+
"grad_norm": 0.16661893716863155,
|
| 2268 |
+
"learning_rate": 1.9737708883314287e-05,
|
| 2269 |
+
"loss": 0.3631,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 3.50744248985115,
|
| 2274 |
+
"grad_norm": 0.16611613821795707,
|
| 2275 |
+
"learning_rate": 1.9476584537369705e-05,
|
| 2276 |
+
"loss": 0.368,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 3.5182679296346415,
|
| 2281 |
+
"grad_norm": 0.1544782537793828,
|
| 2282 |
+
"learning_rate": 1.9216641998582666e-05,
|
| 2283 |
+
"loss": 0.359,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 3.5290933694181326,
|
| 2288 |
+
"grad_norm": 0.15513098503272876,
|
| 2289 |
+
"learning_rate": 1.8957896235317153e-05,
|
| 2290 |
+
"loss": 0.3653,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 3.539918809201624,
|
| 2295 |
+
"grad_norm": 0.13881993920195754,
|
| 2296 |
+
"learning_rate": 1.8700362147022823e-05,
|
| 2297 |
+
"loss": 0.3643,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 3.550744248985115,
|
| 2302 |
+
"grad_norm": 0.16797414295499802,
|
| 2303 |
+
"learning_rate": 1.844405456337698e-05,
|
| 2304 |
+
"loss": 0.3599,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 3.561569688768606,
|
| 2309 |
+
"grad_norm": 0.1290170002098324,
|
| 2310 |
+
"learning_rate": 1.8188988243430698e-05,
|
| 2311 |
+
"loss": 0.3663,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 3.572395128552097,
|
| 2316 |
+
"grad_norm": 0.1449933017909107,
|
| 2317 |
+
"learning_rate": 1.793517787475891e-05,
|
| 2318 |
+
"loss": 0.3652,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 3.5832205683355887,
|
| 2323 |
+
"grad_norm": 0.12623373795565543,
|
| 2324 |
+
"learning_rate": 1.7682638072614667e-05,
|
| 2325 |
+
"loss": 0.3673,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 3.5940460081190797,
|
| 2330 |
+
"grad_norm": 0.13727234583503345,
|
| 2331 |
+
"learning_rate": 1.7431383379087523e-05,
|
| 2332 |
+
"loss": 0.3684,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 3.604871447902571,
|
| 2337 |
+
"grad_norm": 0.1216442976874091,
|
| 2338 |
+
"learning_rate": 1.7181428262266172e-05,
|
| 2339 |
+
"loss": 0.3663,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 3.6156968876860622,
|
| 2344 |
+
"grad_norm": 0.11801832138683788,
|
| 2345 |
+
"learning_rate": 1.6932787115405318e-05,
|
| 2346 |
+
"loss": 0.3551,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 3.6265223274695533,
|
| 2351 |
+
"grad_norm": 0.11494702663483314,
|
| 2352 |
+
"learning_rate": 1.6685474256096865e-05,
|
| 2353 |
+
"loss": 0.364,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 3.6373477672530448,
|
| 2358 |
+
"grad_norm": 0.12323916060969814,
|
| 2359 |
+
"learning_rate": 1.6439503925445453e-05,
|
| 2360 |
+
"loss": 0.3607,
|
| 2361 |
+
"step": 336
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 3.648173207036536,
|
| 2365 |
+
"grad_norm": 0.1098349302717658,
|
| 2366 |
+
"learning_rate": 1.619489028724842e-05,
|
| 2367 |
+
"loss": 0.3571,
|
| 2368 |
+
"step": 337
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 3.6589986468200273,
|
| 2372 |
+
"grad_norm": 0.1325820150308931,
|
| 2373 |
+
"learning_rate": 1.595164742718019e-05,
|
| 2374 |
+
"loss": 0.3649,
|
| 2375 |
+
"step": 338
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 3.6698240866035183,
|
| 2379 |
+
"grad_norm": 0.12739598866297566,
|
| 2380 |
+
"learning_rate": 1.5709789351981214e-05,
|
| 2381 |
+
"loss": 0.365,
|
| 2382 |
+
"step": 339
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 3.6806495263870094,
|
| 2386 |
+
"grad_norm": 0.1279574306960612,
|
| 2387 |
+
"learning_rate": 1.5469329988651344e-05,
|
| 2388 |
+
"loss": 0.3616,
|
| 2389 |
+
"step": 340
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 3.6914749661705004,
|
| 2393 |
+
"grad_norm": 0.12740756778928286,
|
| 2394 |
+
"learning_rate": 1.5230283183647938e-05,
|
| 2395 |
+
"loss": 0.3675,
|
| 2396 |
+
"step": 341
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 3.702300405953992,
|
| 2400 |
+
"grad_norm": 0.12199919817169146,
|
| 2401 |
+
"learning_rate": 1.4992662702088451e-05,
|
| 2402 |
+
"loss": 0.357,
|
| 2403 |
+
"step": 342
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 3.713125845737483,
|
| 2407 |
+
"grad_norm": 0.13290437651272327,
|
| 2408 |
+
"learning_rate": 1.47564822269579e-05,
|
| 2409 |
+
"loss": 0.3643,
|
| 2410 |
+
"step": 343
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 3.7239512855209744,
|
| 2414 |
+
"grad_norm": 0.12309727230864277,
|
| 2415 |
+
"learning_rate": 1.4521755358320868e-05,
|
| 2416 |
+
"loss": 0.3654,
|
| 2417 |
+
"step": 344
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 3.7347767253044655,
|
| 2421 |
+
"grad_norm": 0.11580584203358321,
|
| 2422 |
+
"learning_rate": 1.4288495612538427e-05,
|
| 2423 |
+
"loss": 0.3603,
|
| 2424 |
+
"step": 345
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 3.7456021650879565,
|
| 2428 |
+
"grad_norm": 0.12053339473193542,
|
| 2429 |
+
"learning_rate": 1.4056716421489762e-05,
|
| 2430 |
+
"loss": 0.3613,
|
| 2431 |
+
"step": 346
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 3.756427604871448,
|
| 2435 |
+
"grad_norm": 0.13687114857273397,
|
| 2436 |
+
"learning_rate": 1.3826431131798757e-05,
|
| 2437 |
+
"loss": 0.3657,
|
| 2438 |
+
"step": 347
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 3.767253044654939,
|
| 2442 |
+
"grad_norm": 0.10679108792867367,
|
| 2443 |
+
"learning_rate": 1.3597653004065436e-05,
|
| 2444 |
+
"loss": 0.3678,
|
| 2445 |
+
"step": 348
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 3.7780784844384305,
|
| 2449 |
+
"grad_norm": 0.13191858463972334,
|
| 2450 |
+
"learning_rate": 1.337039521210238e-05,
|
| 2451 |
+
"loss": 0.3624,
|
| 2452 |
+
"step": 349
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 3.7889039242219216,
|
| 2456 |
+
"grad_norm": 0.11520187391454531,
|
| 2457 |
+
"learning_rate": 1.3144670842176134e-05,
|
| 2458 |
+
"loss": 0.3571,
|
| 2459 |
+
"step": 350
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 3.7997293640054126,
|
| 2463 |
+
"grad_norm": 0.1072027738008208,
|
| 2464 |
+
"learning_rate": 1.2920492892253642e-05,
|
| 2465 |
+
"loss": 0.3583,
|
| 2466 |
+
"step": 351
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 3.8105548037889037,
|
| 2470 |
+
"grad_norm": 0.1348518526777805,
|
| 2471 |
+
"learning_rate": 1.2697874271253844e-05,
|
| 2472 |
+
"loss": 0.3674,
|
| 2473 |
+
"step": 352
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 3.821380243572395,
|
| 2477 |
+
"grad_norm": 0.11201420019346077,
|
| 2478 |
+
"learning_rate": 1.247682779830421e-05,
|
| 2479 |
+
"loss": 0.373,
|
| 2480 |
+
"step": 353
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 3.832205683355886,
|
| 2484 |
+
"grad_norm": 0.11768440300752973,
|
| 2485 |
+
"learning_rate": 1.2257366202002693e-05,
|
| 2486 |
+
"loss": 0.3655,
|
| 2487 |
+
"step": 354
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 3.8430311231393777,
|
| 2491 |
+
"grad_norm": 0.11313665709627198,
|
| 2492 |
+
"learning_rate": 1.2039502119684725e-05,
|
| 2493 |
+
"loss": 0.3671,
|
| 2494 |
+
"step": 355
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 3.8538565629228687,
|
| 2498 |
+
"grad_norm": 0.10418998401518839,
|
| 2499 |
+
"learning_rate": 1.1823248096695515e-05,
|
| 2500 |
+
"loss": 0.3618,
|
| 2501 |
+
"step": 356
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 3.8646820027063598,
|
| 2505 |
+
"grad_norm": 0.110112732988295,
|
| 2506 |
+
"learning_rate": 1.160861658566764e-05,
|
| 2507 |
+
"loss": 0.3611,
|
| 2508 |
+
"step": 357
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 3.8755074424898512,
|
| 2512 |
+
"grad_norm": 0.09942258198464687,
|
| 2513 |
+
"learning_rate": 1.1395619945804021e-05,
|
| 2514 |
+
"loss": 0.3586,
|
| 2515 |
+
"step": 358
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 3.8863328822733423,
|
| 2519 |
+
"grad_norm": 0.10319257251599674,
|
| 2520 |
+
"learning_rate": 1.118427044216619e-05,
|
| 2521 |
+
"loss": 0.356,
|
| 2522 |
+
"step": 359
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 3.8971583220568338,
|
| 2526 |
+
"grad_norm": 0.10283087239718877,
|
| 2527 |
+
"learning_rate": 1.0974580244968039e-05,
|
| 2528 |
+
"loss": 0.3585,
|
| 2529 |
+
"step": 360
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 3.907983761840325,
|
| 2533 |
+
"grad_norm": 0.10712486173724692,
|
| 2534 |
+
"learning_rate": 1.0766561428875036e-05,
|
| 2535 |
+
"loss": 0.372,
|
| 2536 |
+
"step": 361
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 3.918809201623816,
|
| 2540 |
+
"grad_norm": 0.10477576856268758,
|
| 2541 |
+
"learning_rate": 1.0560225972308925e-05,
|
| 2542 |
+
"loss": 0.361,
|
| 2543 |
+
"step": 362
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 3.9296346414073073,
|
| 2547 |
+
"grad_norm": 0.09697172045393422,
|
| 2548 |
+
"learning_rate": 1.0355585756757907e-05,
|
| 2549 |
+
"loss": 0.3604,
|
| 2550 |
+
"step": 363
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 3.9404600811907984,
|
| 2554 |
+
"grad_norm": 0.10981365350889641,
|
| 2555 |
+
"learning_rate": 1.0152652566092582e-05,
|
| 2556 |
+
"loss": 0.3609,
|
| 2557 |
+
"step": 364
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 3.9512855209742894,
|
| 2561 |
+
"grad_norm": 0.10519785185770371,
|
| 2562 |
+
"learning_rate": 9.951438085887294e-06,
|
| 2563 |
+
"loss": 0.3631,
|
| 2564 |
+
"step": 365
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 3.962110960757781,
|
| 2568 |
+
"grad_norm": 0.10740052554928715,
|
| 2569 |
+
"learning_rate": 9.751953902747267e-06,
|
| 2570 |
+
"loss": 0.368,
|
| 2571 |
+
"step": 366
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 3.972936400541272,
|
| 2575 |
+
"grad_norm": 0.10480987894849778,
|
| 2576 |
+
"learning_rate": 9.554211503641416e-06,
|
| 2577 |
+
"loss": 0.3565,
|
| 2578 |
+
"step": 367
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 3.983761840324763,
|
| 2582 |
+
"grad_norm": 0.1040412988156162,
|
| 2583 |
+
"learning_rate": 9.358222275240884e-06,
|
| 2584 |
+
"loss": 0.3592,
|
| 2585 |
+
"step": 368
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 3.9945872801082545,
|
| 2589 |
+
"grad_norm": 0.10495487860148761,
|
| 2590 |
+
"learning_rate": 9.163997503263364e-06,
|
| 2591 |
+
"loss": 0.3707,
|
| 2592 |
+
"step": 369
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 4.005412719891746,
|
| 2596 |
+
"grad_norm": 0.1875294677786279,
|
| 2597 |
+
"learning_rate": 8.971548371823205e-06,
|
| 2598 |
+
"loss": 0.5807,
|
| 2599 |
+
"step": 370
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 4.016238159675237,
|
| 2603 |
+
"grad_norm": 0.14041995604948812,
|
| 2604 |
+
"learning_rate": 8.780885962787452e-06,
|
| 2605 |
+
"loss": 0.3404,
|
| 2606 |
+
"step": 371
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 4.027063599458728,
|
| 2610 |
+
"grad_norm": 0.1253661015397288,
|
| 2611 |
+
"learning_rate": 8.592021255137646e-06,
|
| 2612 |
+
"loss": 0.3487,
|
| 2613 |
+
"step": 372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 4.037889039242219,
|
| 2617 |
+
"grad_norm": 0.11634016776170551,
|
| 2618 |
+
"learning_rate": 8.404965124337665e-06,
|
| 2619 |
+
"loss": 0.338,
|
| 2620 |
+
"step": 373
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 4.04871447902571,
|
| 2624 |
+
"grad_norm": 0.13106693030223066,
|
| 2625 |
+
"learning_rate": 8.219728341707425e-06,
|
| 2626 |
+
"loss": 0.3418,
|
| 2627 |
+
"step": 374
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 4.059539918809202,
|
| 2631 |
+
"grad_norm": 0.1320753462354552,
|
| 2632 |
+
"learning_rate": 8.036321573802706e-06,
|
| 2633 |
+
"loss": 0.345,
|
| 2634 |
+
"step": 375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 4.070365358592693,
|
| 2638 |
+
"grad_norm": 0.1408674098165186,
|
| 2639 |
+
"learning_rate": 7.854755381800872e-06,
|
| 2640 |
+
"loss": 0.344,
|
| 2641 |
+
"step": 376
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 4.081190798376184,
|
| 2645 |
+
"grad_norm": 0.132540628100584,
|
| 2646 |
+
"learning_rate": 7.675040220892782e-06,
|
| 2647 |
+
"loss": 0.3441,
|
| 2648 |
+
"step": 377
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 4.092016238159675,
|
| 2652 |
+
"grad_norm": 0.11968734635815752,
|
| 2653 |
+
"learning_rate": 7.4971864396806795e-06,
|
| 2654 |
+
"loss": 0.3389,
|
| 2655 |
+
"step": 378
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 4.102841677943166,
|
| 2659 |
+
"grad_norm": 0.11698410253549779,
|
| 2660 |
+
"learning_rate": 7.321204279582321e-06,
|
| 2661 |
+
"loss": 0.3449,
|
| 2662 |
+
"step": 379
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 4.113667117726657,
|
| 2666 |
+
"grad_norm": 0.12255988282586658,
|
| 2667 |
+
"learning_rate": 7.147103874241246e-06,
|
| 2668 |
+
"loss": 0.3499,
|
| 2669 |
+
"step": 380
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 4.124492557510149,
|
| 2673 |
+
"grad_norm": 0.12100999680393194,
|
| 2674 |
+
"learning_rate": 6.974895248943223e-06,
|
| 2675 |
+
"loss": 0.3423,
|
| 2676 |
+
"step": 381
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 4.13531799729364,
|
| 2680 |
+
"grad_norm": 0.11527621996191134,
|
| 2681 |
+
"learning_rate": 6.804588320038998e-06,
|
| 2682 |
+
"loss": 0.3392,
|
| 2683 |
+
"step": 382
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 4.146143437077131,
|
| 2687 |
+
"grad_norm": 0.12139325805430597,
|
| 2688 |
+
"learning_rate": 6.636192894373232e-06,
|
| 2689 |
+
"loss": 0.3444,
|
| 2690 |
+
"step": 383
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 4.156968876860622,
|
| 2694 |
+
"grad_norm": 0.11122602457716502,
|
| 2695 |
+
"learning_rate": 6.4697186687198285e-06,
|
| 2696 |
+
"loss": 0.3383,
|
| 2697 |
+
"step": 384
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 4.167794316644113,
|
| 2701 |
+
"grad_norm": 0.11224637325482494,
|
| 2702 |
+
"learning_rate": 6.305175229223541e-06,
|
| 2703 |
+
"loss": 0.3319,
|
| 2704 |
+
"step": 385
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 4.178619756427604,
|
| 2708 |
+
"grad_norm": 0.10879841592643402,
|
| 2709 |
+
"learning_rate": 6.142572050847966e-06,
|
| 2710 |
+
"loss": 0.3479,
|
| 2711 |
+
"step": 386
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 4.189445196211096,
|
| 2715 |
+
"grad_norm": 0.12627793027748102,
|
| 2716 |
+
"learning_rate": 5.981918496829959e-06,
|
| 2717 |
+
"loss": 0.3464,
|
| 2718 |
+
"step": 387
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.200270635994587,
|
| 2722 |
+
"grad_norm": 0.12250577402975518,
|
| 2723 |
+
"learning_rate": 5.823223818140458e-06,
|
| 2724 |
+
"loss": 0.3444,
|
| 2725 |
+
"step": 388
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.211096075778078,
|
| 2729 |
+
"grad_norm": 0.11127210268527363,
|
| 2730 |
+
"learning_rate": 5.666497152951791e-06,
|
| 2731 |
+
"loss": 0.3438,
|
| 2732 |
+
"step": 389
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.2219215155615695,
|
| 2736 |
+
"grad_norm": 0.10375456129249835,
|
| 2737 |
+
"learning_rate": 5.511747526111459e-06,
|
| 2738 |
+
"loss": 0.343,
|
| 2739 |
+
"step": 390
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.2327469553450605,
|
| 2743 |
+
"grad_norm": 0.11020190222669736,
|
| 2744 |
+
"learning_rate": 5.358983848622452e-06,
|
| 2745 |
+
"loss": 0.3443,
|
| 2746 |
+
"step": 391
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.243572395128552,
|
| 2750 |
+
"grad_norm": 0.11547044420370078,
|
| 2751 |
+
"learning_rate": 5.208214917130132e-06,
|
| 2752 |
+
"loss": 0.3456,
|
| 2753 |
+
"step": 392
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.2543978349120435,
|
| 2757 |
+
"grad_norm": 0.11195990742206446,
|
| 2758 |
+
"learning_rate": 5.059449413415705e-06,
|
| 2759 |
+
"loss": 0.3458,
|
| 2760 |
+
"step": 393
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 4.2652232746955345,
|
| 2764 |
+
"grad_norm": 0.1044621266094549,
|
| 2765 |
+
"learning_rate": 4.91269590389623e-06,
|
| 2766 |
+
"loss": 0.3413,
|
| 2767 |
+
"step": 394
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 4.276048714479026,
|
| 2771 |
+
"grad_norm": 0.09428855278720129,
|
| 2772 |
+
"learning_rate": 4.7679628391314615e-06,
|
| 2773 |
+
"loss": 0.3387,
|
| 2774 |
+
"step": 395
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 4.286874154262517,
|
| 2778 |
+
"grad_norm": 0.1218060268682413,
|
| 2779 |
+
"learning_rate": 4.625258553337108e-06,
|
| 2780 |
+
"loss": 0.3373,
|
| 2781 |
+
"step": 396
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 4.2976995940460085,
|
| 2785 |
+
"grad_norm": 0.10192114482593552,
|
| 2786 |
+
"learning_rate": 4.484591263904992e-06,
|
| 2787 |
+
"loss": 0.3429,
|
| 2788 |
+
"step": 397
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 4.3085250338295,
|
| 2792 |
+
"grad_norm": 0.09490696955645948,
|
| 2793 |
+
"learning_rate": 4.345969070929848e-06,
|
| 2794 |
+
"loss": 0.3397,
|
| 2795 |
+
"step": 398
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 4.319350473612991,
|
| 2799 |
+
"grad_norm": 0.0943001566489396,
|
| 2800 |
+
"learning_rate": 4.20939995674289e-06,
|
| 2801 |
+
"loss": 0.3498,
|
| 2802 |
+
"step": 399
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 4.330175913396482,
|
| 2806 |
+
"grad_norm": 0.0910155289601598,
|
| 2807 |
+
"learning_rate": 4.07489178545216e-06,
|
| 2808 |
+
"loss": 0.3415,
|
| 2809 |
+
"step": 400
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 4.341001353179973,
|
| 2813 |
+
"grad_norm": 0.10041740401971753,
|
| 2814 |
+
"learning_rate": 3.942452302489686e-06,
|
| 2815 |
+
"loss": 0.3405,
|
| 2816 |
+
"step": 401
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 4.351826792963464,
|
| 2820 |
+
"grad_norm": 0.10532998834210694,
|
| 2821 |
+
"learning_rate": 3.8120891341654955e-06,
|
| 2822 |
+
"loss": 0.3431,
|
| 2823 |
+
"step": 402
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 4.362652232746956,
|
| 2827 |
+
"grad_norm": 0.09532752858531783,
|
| 2828 |
+
"learning_rate": 3.6838097872284382e-06,
|
| 2829 |
+
"loss": 0.3422,
|
| 2830 |
+
"step": 403
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 4.373477672530447,
|
| 2834 |
+
"grad_norm": 0.08806314013092435,
|
| 2835 |
+
"learning_rate": 3.5576216484339356e-06,
|
| 2836 |
+
"loss": 0.3438,
|
| 2837 |
+
"step": 404
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 4.384303112313938,
|
| 2841 |
+
"grad_norm": 0.0902671665456689,
|
| 2842 |
+
"learning_rate": 3.4335319841186077e-06,
|
| 2843 |
+
"loss": 0.3454,
|
| 2844 |
+
"step": 405
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 4.395128552097429,
|
| 2848 |
+
"grad_norm": 0.09375561638182935,
|
| 2849 |
+
"learning_rate": 3.311547939781887e-06,
|
| 2850 |
+
"loss": 0.338,
|
| 2851 |
+
"step": 406
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 4.40595399188092,
|
| 2855 |
+
"grad_norm": 0.09234688834689847,
|
| 2856 |
+
"learning_rate": 3.1916765396745288e-06,
|
| 2857 |
+
"loss": 0.3394,
|
| 2858 |
+
"step": 407
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 4.416779431664412,
|
| 2862 |
+
"grad_norm": 0.08840156590696185,
|
| 2863 |
+
"learning_rate": 3.0739246863941717e-06,
|
| 2864 |
+
"loss": 0.3472,
|
| 2865 |
+
"step": 408
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 4.427604871447903,
|
| 2869 |
+
"grad_norm": 0.08739334077231752,
|
| 2870 |
+
"learning_rate": 2.95829916048779e-06,
|
| 2871 |
+
"loss": 0.3409,
|
| 2872 |
+
"step": 409
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 4.438430311231394,
|
| 2876 |
+
"grad_norm": 0.0875172603982304,
|
| 2877 |
+
"learning_rate": 2.84480662006132e-06,
|
| 2878 |
+
"loss": 0.3477,
|
| 2879 |
+
"step": 410
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 4.449255751014885,
|
| 2883 |
+
"grad_norm": 0.094984179377533,
|
| 2884 |
+
"learning_rate": 2.7334536003962166e-06,
|
| 2885 |
+
"loss": 0.3393,
|
| 2886 |
+
"step": 411
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 4.460081190798376,
|
| 2890 |
+
"grad_norm": 0.08706812389766655,
|
| 2891 |
+
"learning_rate": 2.6242465135731587e-06,
|
| 2892 |
+
"loss": 0.3395,
|
| 2893 |
+
"step": 412
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 4.470906630581867,
|
| 2897 |
+
"grad_norm": 0.09622976821594861,
|
| 2898 |
+
"learning_rate": 2.5171916481027968e-06,
|
| 2899 |
+
"loss": 0.3438,
|
| 2900 |
+
"step": 413
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 4.481732070365359,
|
| 2904 |
+
"grad_norm": 0.09042626515531108,
|
| 2905 |
+
"learning_rate": 2.4122951685636674e-06,
|
| 2906 |
+
"loss": 0.3397,
|
| 2907 |
+
"step": 414
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 4.49255751014885,
|
| 2911 |
+
"grad_norm": 0.08697445987862922,
|
| 2912 |
+
"learning_rate": 2.309563115247184e-06,
|
| 2913 |
+
"loss": 0.3442,
|
| 2914 |
+
"step": 415
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 4.503382949932341,
|
| 2918 |
+
"grad_norm": 0.08521377871295831,
|
| 2919 |
+
"learning_rate": 2.2090014038098364e-06,
|
| 2920 |
+
"loss": 0.343,
|
| 2921 |
+
"step": 416
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 4.514208389715832,
|
| 2925 |
+
"grad_norm": 0.08874899185726369,
|
| 2926 |
+
"learning_rate": 2.1106158249325536e-06,
|
| 2927 |
+
"loss": 0.336,
|
| 2928 |
+
"step": 417
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 4.525033829499323,
|
| 2932 |
+
"grad_norm": 0.08808087170450281,
|
| 2933 |
+
"learning_rate": 2.014412043987233e-06,
|
| 2934 |
+
"loss": 0.3428,
|
| 2935 |
+
"step": 418
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 4.535859269282815,
|
| 2939 |
+
"grad_norm": 0.08142283041322351,
|
| 2940 |
+
"learning_rate": 1.9203956007105293e-06,
|
| 2941 |
+
"loss": 0.3443,
|
| 2942 |
+
"step": 419
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 4.546684709066306,
|
| 2946 |
+
"grad_norm": 0.0851360186887014,
|
| 2947 |
+
"learning_rate": 1.8285719088848442e-06,
|
| 2948 |
+
"loss": 0.3376,
|
| 2949 |
+
"step": 420
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 4.557510148849797,
|
| 2953 |
+
"grad_norm": 0.08649957637526776,
|
| 2954 |
+
"learning_rate": 1.7389462560266102e-06,
|
| 2955 |
+
"loss": 0.3467,
|
| 2956 |
+
"step": 421
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 4.568335588633288,
|
| 2960 |
+
"grad_norm": 0.08311650620599292,
|
| 2961 |
+
"learning_rate": 1.651523803081778e-06,
|
| 2962 |
+
"loss": 0.3451,
|
| 2963 |
+
"step": 422
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 4.579161028416779,
|
| 2967 |
+
"grad_norm": 0.08116356626628798,
|
| 2968 |
+
"learning_rate": 1.5663095841286535e-06,
|
| 2969 |
+
"loss": 0.3492,
|
| 2970 |
+
"step": 423
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 4.589986468200271,
|
| 2974 |
+
"grad_norm": 0.0824392457885468,
|
| 2975 |
+
"learning_rate": 1.4833085060880349e-06,
|
| 2976 |
+
"loss": 0.3387,
|
| 2977 |
+
"step": 424
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 4.600811907983762,
|
| 2981 |
+
"grad_norm": 0.08566606903234027,
|
| 2982 |
+
"learning_rate": 1.4025253484405954e-06,
|
| 2983 |
+
"loss": 0.3459,
|
| 2984 |
+
"step": 425
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 4.611637347767253,
|
| 2988 |
+
"grad_norm": 0.08258042133215138,
|
| 2989 |
+
"learning_rate": 1.3239647629517572e-06,
|
| 2990 |
+
"loss": 0.3405,
|
| 2991 |
+
"step": 426
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 4.622462787550744,
|
| 2995 |
+
"grad_norm": 0.08262381506050841,
|
| 2996 |
+
"learning_rate": 1.2476312734037488e-06,
|
| 2997 |
+
"loss": 0.3433,
|
| 2998 |
+
"step": 427
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 4.633288227334235,
|
| 3002 |
+
"grad_norm": 0.08609860936550076,
|
| 3003 |
+
"learning_rate": 1.1735292753351346e-06,
|
| 3004 |
+
"loss": 0.3375,
|
| 3005 |
+
"step": 428
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 4.644113667117726,
|
| 3009 |
+
"grad_norm": 0.08075622135740361,
|
| 3010 |
+
"learning_rate": 1.1016630357877278e-06,
|
| 3011 |
+
"loss": 0.343,
|
| 3012 |
+
"step": 429
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 4.654939106901217,
|
| 3016 |
+
"grad_norm": 0.08233697551125709,
|
| 3017 |
+
"learning_rate": 1.0320366930608405e-06,
|
| 3018 |
+
"loss": 0.3394,
|
| 3019 |
+
"step": 430
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 4.665764546684709,
|
| 3023 |
+
"grad_norm": 0.08316101123672864,
|
| 3024 |
+
"learning_rate": 9.64654256473021e-07,
|
| 3025 |
+
"loss": 0.3437,
|
| 3026 |
+
"step": 431
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 4.6765899864682,
|
| 3030 |
+
"grad_norm": 0.09300648661066627,
|
| 3031 |
+
"learning_rate": 8.995196061311628e-07,
|
| 3032 |
+
"loss": 0.3415,
|
| 3033 |
+
"step": 432
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 4.687415426251691,
|
| 3037 |
+
"grad_norm": 0.0875268399310967,
|
| 3038 |
+
"learning_rate": 8.366364927070836e-07,
|
| 3039 |
+
"loss": 0.3545,
|
| 3040 |
+
"step": 433
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 4.698240866035182,
|
| 3044 |
+
"grad_norm": 0.08398923274446536,
|
| 3045 |
+
"learning_rate": 7.760085372215509e-07,
|
| 3046 |
+
"loss": 0.3453,
|
| 3047 |
+
"step": 434
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 4.7090663058186735,
|
| 3051 |
+
"grad_norm": 0.08167730199654379,
|
| 3052 |
+
"learning_rate": 7.176392308357649e-07,
|
| 3053 |
+
"loss": 0.3393,
|
| 3054 |
+
"step": 435
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 4.719891745602165,
|
| 3058 |
+
"grad_norm": 0.07876472278529771,
|
| 3059 |
+
"learning_rate": 6.61531934650319e-07,
|
| 3060 |
+
"loss": 0.3422,
|
| 3061 |
+
"step": 436
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 4.730717185385656,
|
| 3065 |
+
"grad_norm": 0.07955859230593923,
|
| 3066 |
+
"learning_rate": 6.076898795116792e-07,
|
| 3067 |
+
"loss": 0.3446,
|
| 3068 |
+
"step": 437
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 4.7415426251691475,
|
| 3072 |
+
"grad_norm": 0.07950730370407931,
|
| 3073 |
+
"learning_rate": 5.561161658261238e-07,
|
| 3074 |
+
"loss": 0.3497,
|
| 3075 |
+
"step": 438
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 4.7523680649526385,
|
| 3079 |
+
"grad_norm": 0.08188578916605453,
|
| 3080 |
+
"learning_rate": 5.068137633812153e-07,
|
| 3081 |
+
"loss": 0.3437,
|
| 3082 |
+
"step": 439
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 4.76319350473613,
|
| 3086 |
+
"grad_norm": 0.07643930436958575,
|
| 3087 |
+
"learning_rate": 4.5978551117479063e-07,
|
| 3088 |
+
"loss": 0.3395,
|
| 3089 |
+
"step": 440
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 4.7740189445196215,
|
| 3093 |
+
"grad_norm": 0.0792066807028224,
|
| 3094 |
+
"learning_rate": 4.1503411725147824e-07,
|
| 3095 |
+
"loss": 0.345,
|
| 3096 |
+
"step": 441
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 4.7848443843031125,
|
| 3100 |
+
"grad_norm": 0.07917452696979885,
|
| 3101 |
+
"learning_rate": 3.725621585467698e-07,
|
| 3102 |
+
"loss": 0.3349,
|
| 3103 |
+
"step": 442
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 4.795669824086604,
|
| 3107 |
+
"grad_norm": 0.0814817497437418,
|
| 3108 |
+
"learning_rate": 3.3237208073862324e-07,
|
| 3109 |
+
"loss": 0.3465,
|
| 3110 |
+
"step": 443
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 4.806495263870095,
|
| 3114 |
+
"grad_norm": 0.07978334424890356,
|
| 3115 |
+
"learning_rate": 2.9446619810662434e-07,
|
| 3116 |
+
"loss": 0.3444,
|
| 3117 |
+
"step": 444
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 4.817320703653586,
|
| 3121 |
+
"grad_norm": 0.08242514400126746,
|
| 3122 |
+
"learning_rate": 2.5884669339875546e-07,
|
| 3123 |
+
"loss": 0.3453,
|
| 3124 |
+
"step": 445
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 4.828146143437078,
|
| 3128 |
+
"grad_norm": 0.07808288606410942,
|
| 3129 |
+
"learning_rate": 2.2551561770565611e-07,
|
| 3130 |
+
"loss": 0.3485,
|
| 3131 |
+
"step": 446
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 4.838971583220569,
|
| 3135 |
+
"grad_norm": 0.07928112358547848,
|
| 3136 |
+
"learning_rate": 1.9447489034256196e-07,
|
| 3137 |
+
"loss": 0.348,
|
| 3138 |
+
"step": 447
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 4.84979702300406,
|
| 3142 |
+
"grad_norm": 0.0794259887072925,
|
| 3143 |
+
"learning_rate": 1.6572629873874869e-07,
|
| 3144 |
+
"loss": 0.3414,
|
| 3145 |
+
"step": 448
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 4.860622462787551,
|
| 3149 |
+
"grad_norm": 0.07566795403724712,
|
| 3150 |
+
"learning_rate": 1.392714983346366e-07,
|
| 3151 |
+
"loss": 0.3435,
|
| 3152 |
+
"step": 449
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 4.871447902571042,
|
| 3156 |
+
"grad_norm": 0.07843464378271181,
|
| 3157 |
+
"learning_rate": 1.1511201248643134e-07,
|
| 3158 |
+
"loss": 0.3405,
|
| 3159 |
+
"step": 450
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 4.882273342354533,
|
| 3163 |
+
"grad_norm": 0.07703599202280859,
|
| 3164 |
+
"learning_rate": 9.324923237842953e-08,
|
| 3165 |
+
"loss": 0.3426,
|
| 3166 |
+
"step": 451
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 4.893098782138025,
|
| 3170 |
+
"grad_norm": 0.07979599503404064,
|
| 3171 |
+
"learning_rate": 7.368441694290963e-08,
|
| 3172 |
+
"loss": 0.3487,
|
| 3173 |
+
"step": 452
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 4.903924221921516,
|
| 3177 |
+
"grad_norm": 0.0781513546026194,
|
| 3178 |
+
"learning_rate": 5.641869278761203e-08,
|
| 3179 |
+
"loss": 0.3463,
|
| 3180 |
+
"step": 453
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 4.914749661705007,
|
| 3184 |
+
"grad_norm": 0.07970596360712374,
|
| 3185 |
+
"learning_rate": 4.145305413089773e-08,
|
| 3186 |
+
"loss": 0.3469,
|
| 3187 |
+
"step": 454
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 4.925575101488498,
|
| 3191 |
+
"grad_norm": 0.07818127551791816,
|
| 3192 |
+
"learning_rate": 2.8788362744478492e-08,
|
| 3193 |
+
"loss": 0.336,
|
| 3194 |
+
"step": 455
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 4.936400541271989,
|
| 3198 |
+
"grad_norm": 0.07869679667959938,
|
| 3199 |
+
"learning_rate": 1.8425347903794355e-08,
|
| 3200 |
+
"loss": 0.347,
|
| 3201 |
+
"step": 456
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 4.94722598105548,
|
| 3205 |
+
"grad_norm": 0.08181150471394064,
|
| 3206 |
+
"learning_rate": 1.0364606346033867e-08,
|
| 3207 |
+
"loss": 0.3518,
|
| 3208 |
+
"step": 457
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 4.958051420838972,
|
| 3212 |
+
"grad_norm": 0.07775322978676268,
|
| 3213 |
+
"learning_rate": 4.606602235752711e-09,
|
| 3214 |
+
"loss": 0.3442,
|
| 3215 |
+
"step": 458
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 4.968876860622463,
|
| 3219 |
+
"grad_norm": 0.07656113821295778,
|
| 3220 |
+
"learning_rate": 1.1516671381528454e-09,
|
| 3221 |
+
"loss": 0.3409,
|
| 3222 |
+
"step": 459
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 4.979702300405954,
|
| 3226 |
+
"grad_norm": 0.07887018893888488,
|
| 3227 |
+
"learning_rate": 0.0,
|
| 3228 |
+
"loss": 0.345,
|
| 3229 |
+
"step": 460
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 4.979702300405954,
|
| 3233 |
+
"step": 460,
|
| 3234 |
+
"total_flos": 1.1837169167247606e+19,
|
| 3235 |
+
"train_loss": 0.4245723386173663,
|
| 3236 |
+
"train_runtime": 101661.9148,
|
| 3237 |
+
"train_samples_per_second": 2.326,
|
| 3238 |
+
"train_steps_per_second": 0.005
|
| 3239 |
+
}
|
| 3240 |
+
],
|
| 3241 |
+
"logging_steps": 1.0,
|
| 3242 |
+
"max_steps": 460,
|
| 3243 |
+
"num_input_tokens_seen": 0,
|
| 3244 |
+
"num_train_epochs": 5,
|
| 3245 |
+
"save_steps": 500,
|
| 3246 |
+
"stateful_callbacks": {
|
| 3247 |
+
"TrainerControl": {
|
| 3248 |
+
"args": {
|
| 3249 |
+
"should_epoch_stop": false,
|
| 3250 |
+
"should_evaluate": false,
|
| 3251 |
+
"should_log": false,
|
| 3252 |
+
"should_save": true,
|
| 3253 |
+
"should_training_stop": true
|
| 3254 |
+
},
|
| 3255 |
+
"attributes": {}
|
| 3256 |
+
}
|
| 3257 |
+
},
|
| 3258 |
+
"total_flos": 1.1837169167247606e+19,
|
| 3259 |
+
"train_batch_size": 1,
|
| 3260 |
+
"trial_name": null,
|
| 3261 |
+
"trial_params": null
|
| 3262 |
+
}
|
training_loss.png
ADDED
|