End of training
Browse files- README.md +2 -1
- all_results.json +5 -9
- train_results.json +5 -5
- trainer_state.json +3788 -46
- 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: llama3-1_8b_4o_annotated_aops
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# llama3-1_8b_4o_annotated_aops
|
| 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: llama3-1_8b_4o_annotated_aops
|
|
|
|
| 16 |
|
| 17 |
# llama3-1_8b_4o_annotated_aops
|
| 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 mlfoundations-dev/4o_annotated_aops dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
CHANGED
|
@@ -1,12 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"train_loss": 0.7682641569305869,
|
| 9 |
-
"train_runtime": 638.061,
|
| 10 |
-
"train_samples_per_second": 39.217,
|
| 11 |
-
"train_steps_per_second": 0.08
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"total_flos": 136664820957184.0,
|
| 4 |
+
"train_loss": 0.613760003727444,
|
| 5 |
+
"train_runtime": 1147.7371,
|
| 6 |
+
"train_samples_per_second": 45.3,
|
| 7 |
+
"train_steps_per_second": 0.473
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"total_flos": 136664820957184.0,
|
| 4 |
+
"train_loss": 0.613760003727444,
|
| 5 |
+
"train_runtime": 1147.7371,
|
| 6 |
+
"train_samples_per_second": 45.3,
|
| 7 |
+
"train_steps_per_second": 0.473
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -3,82 +3,3824 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch":
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"step": 17
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch":
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 1.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"step": 34
|
| 47 |
},
|
| 48 |
{
|
| 49 |
-
"epoch":
|
| 50 |
-
"grad_norm": 0.
|
| 51 |
-
"learning_rate":
|
| 52 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
"step": 40
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch":
|
| 57 |
-
"grad_norm": 0.
|
| 58 |
-
"learning_rate":
|
| 59 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch":
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"eval_steps_per_second": 0.499,
|
| 68 |
"step": 51
|
| 69 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
{
|
| 71 |
"epoch": 3.0,
|
| 72 |
-
"step":
|
| 73 |
-
"total_flos":
|
| 74 |
-
"train_loss": 0.
|
| 75 |
-
"train_runtime":
|
| 76 |
-
"train_samples_per_second":
|
| 77 |
-
"train_steps_per_second": 0.
|
| 78 |
}
|
| 79 |
],
|
| 80 |
-
"logging_steps":
|
| 81 |
-
"max_steps":
|
| 82 |
"num_input_tokens_seen": 0,
|
| 83 |
"num_train_epochs": 3,
|
| 84 |
"save_steps": 500,
|
|
@@ -94,8 +3836,8 @@
|
|
| 94 |
"attributes": {}
|
| 95 |
}
|
| 96 |
},
|
| 97 |
-
"total_flos":
|
| 98 |
-
"train_batch_size":
|
| 99 |
"trial_name": null,
|
| 100 |
"trial_params": null
|
| 101 |
}
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 543,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.0055248618784530384,
|
| 13 |
+
"grad_norm": 4.8501728653187755,
|
| 14 |
+
"learning_rate": 1.8181818181818183e-07,
|
| 15 |
+
"loss": 0.882,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.011049723756906077,
|
| 20 |
+
"grad_norm": 5.284618547033595,
|
| 21 |
+
"learning_rate": 3.6363636363636366e-07,
|
| 22 |
+
"loss": 0.9499,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.016574585635359115,
|
| 27 |
+
"grad_norm": 4.71655301867202,
|
| 28 |
+
"learning_rate": 5.454545454545455e-07,
|
| 29 |
+
"loss": 0.8375,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.022099447513812154,
|
| 34 |
+
"grad_norm": 4.691610018967258,
|
| 35 |
+
"learning_rate": 7.272727272727273e-07,
|
| 36 |
+
"loss": 0.8694,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.027624309392265192,
|
| 41 |
+
"grad_norm": 4.525811293283286,
|
| 42 |
+
"learning_rate": 9.090909090909091e-07,
|
| 43 |
+
"loss": 0.7922,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03314917127071823,
|
| 48 |
+
"grad_norm": 4.515684677465201,
|
| 49 |
+
"learning_rate": 1.090909090909091e-06,
|
| 50 |
+
"loss": 0.8158,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03867403314917127,
|
| 55 |
+
"grad_norm": 4.521464462348852,
|
| 56 |
+
"learning_rate": 1.2727272727272728e-06,
|
| 57 |
+
"loss": 0.8463,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04419889502762431,
|
| 62 |
+
"grad_norm": 4.01317039922344,
|
| 63 |
+
"learning_rate": 1.4545454545454546e-06,
|
| 64 |
+
"loss": 0.7804,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.049723756906077346,
|
| 69 |
+
"grad_norm": 3.725743569896934,
|
| 70 |
+
"learning_rate": 1.6363636363636365e-06,
|
| 71 |
+
"loss": 0.8386,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.055248618784530384,
|
| 76 |
+
"grad_norm": 3.547034380075145,
|
| 77 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 78 |
+
"loss": 0.7804,
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.06077348066298342,
|
| 83 |
+
"grad_norm": 2.385734305081293,
|
| 84 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 85 |
+
"loss": 0.7536,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.06629834254143646,
|
| 90 |
+
"grad_norm": 2.118903283570385,
|
| 91 |
+
"learning_rate": 2.181818181818182e-06,
|
| 92 |
+
"loss": 0.8003,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0718232044198895,
|
| 97 |
+
"grad_norm": 2.071463502085266,
|
| 98 |
+
"learning_rate": 2.363636363636364e-06,
|
| 99 |
+
"loss": 0.7728,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.07734806629834254,
|
| 104 |
+
"grad_norm": 2.11975896906294,
|
| 105 |
+
"learning_rate": 2.5454545454545456e-06,
|
| 106 |
+
"loss": 0.7816,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.08287292817679558,
|
| 111 |
+
"grad_norm": 1.6109945627440467,
|
| 112 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 113 |
+
"loss": 0.7138,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08839779005524862,
|
| 118 |
+
"grad_norm": 1.946567883491615,
|
| 119 |
+
"learning_rate": 2.9090909090909093e-06,
|
| 120 |
+
"loss": 0.7254,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09392265193370165,
|
| 125 |
+
"grad_norm": 1.7266080007457147,
|
| 126 |
+
"learning_rate": 3.090909090909091e-06,
|
| 127 |
+
"loss": 0.7294,
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.09944751381215469,
|
| 132 |
+
"grad_norm": 1.6539369196579166,
|
| 133 |
+
"learning_rate": 3.272727272727273e-06,
|
| 134 |
+
"loss": 0.711,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.10497237569060773,
|
| 139 |
+
"grad_norm": 1.3760121270687458,
|
| 140 |
+
"learning_rate": 3.454545454545455e-06,
|
| 141 |
+
"loss": 0.6706,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.11049723756906077,
|
| 146 |
+
"grad_norm": 1.2322332262531337,
|
| 147 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 148 |
+
"loss": 0.714,
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.11602209944751381,
|
| 153 |
+
"grad_norm": 1.092460838605022,
|
| 154 |
+
"learning_rate": 3.818181818181819e-06,
|
| 155 |
+
"loss": 0.6221,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.12154696132596685,
|
| 160 |
+
"grad_norm": 1.3847134225952789,
|
| 161 |
+
"learning_rate": 4.000000000000001e-06,
|
| 162 |
+
"loss": 0.6874,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1270718232044199,
|
| 167 |
+
"grad_norm": 1.2895226334792846,
|
| 168 |
+
"learning_rate": 4.181818181818182e-06,
|
| 169 |
+
"loss": 0.6741,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.13259668508287292,
|
| 174 |
+
"grad_norm": 1.3973784329721743,
|
| 175 |
+
"learning_rate": 4.363636363636364e-06,
|
| 176 |
+
"loss": 0.8114,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13812154696132597,
|
| 181 |
+
"grad_norm": 1.1221564987656045,
|
| 182 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 183 |
+
"loss": 0.6904,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.143646408839779,
|
| 188 |
+
"grad_norm": 1.0813494118759077,
|
| 189 |
+
"learning_rate": 4.727272727272728e-06,
|
| 190 |
+
"loss": 0.6887,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14917127071823205,
|
| 195 |
+
"grad_norm": 1.039002428401238,
|
| 196 |
+
"learning_rate": 4.90909090909091e-06,
|
| 197 |
+
"loss": 0.7305,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.15469613259668508,
|
| 202 |
+
"grad_norm": 0.9005740059397435,
|
| 203 |
+
"learning_rate": 5.090909090909091e-06,
|
| 204 |
+
"loss": 0.7216,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.16022099447513813,
|
| 209 |
+
"grad_norm": 1.0434084181940664,
|
| 210 |
+
"learning_rate": 5.272727272727273e-06,
|
| 211 |
+
"loss": 0.7262,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.16574585635359115,
|
| 216 |
+
"grad_norm": 0.8640462038859854,
|
| 217 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 218 |
+
"loss": 0.6818,
|
| 219 |
"step": 30
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.1712707182320442,
|
| 223 |
+
"grad_norm": 0.8711602353776259,
|
| 224 |
+
"learning_rate": 5.636363636363636e-06,
|
| 225 |
+
"loss": 0.6709,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.17679558011049723,
|
| 230 |
+
"grad_norm": 0.7874062745697313,
|
| 231 |
+
"learning_rate": 5.8181818181818185e-06,
|
| 232 |
+
"loss": 0.7056,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.18232044198895028,
|
| 237 |
+
"grad_norm": 0.910787056447978,
|
| 238 |
+
"learning_rate": 6e-06,
|
| 239 |
+
"loss": 0.7321,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.1878453038674033,
|
| 244 |
+
"grad_norm": 0.8834639779382965,
|
| 245 |
+
"learning_rate": 6.181818181818182e-06,
|
| 246 |
+
"loss": 0.6943,
|
| 247 |
"step": 34
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 0.19337016574585636,
|
| 251 |
+
"grad_norm": 0.9011491907153977,
|
| 252 |
+
"learning_rate": 6.363636363636364e-06,
|
| 253 |
+
"loss": 0.7474,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.19889502762430938,
|
| 258 |
+
"grad_norm": 0.9863965225958002,
|
| 259 |
+
"learning_rate": 6.545454545454546e-06,
|
| 260 |
+
"loss": 0.7448,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.20441988950276244,
|
| 265 |
+
"grad_norm": 0.804971042531312,
|
| 266 |
+
"learning_rate": 6.7272727272727275e-06,
|
| 267 |
+
"loss": 0.6026,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.20994475138121546,
|
| 272 |
+
"grad_norm": 0.8495022527176822,
|
| 273 |
+
"learning_rate": 6.90909090909091e-06,
|
| 274 |
+
"loss": 0.686,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2154696132596685,
|
| 279 |
+
"grad_norm": 0.8536642393909392,
|
| 280 |
+
"learning_rate": 7.0909090909090916e-06,
|
| 281 |
+
"loss": 0.6863,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.22099447513812154,
|
| 286 |
+
"grad_norm": 0.7505296486129153,
|
| 287 |
+
"learning_rate": 7.272727272727273e-06,
|
| 288 |
+
"loss": 0.6495,
|
| 289 |
"step": 40
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 0.2265193370165746,
|
| 293 |
+
"grad_norm": 0.8613764113585566,
|
| 294 |
+
"learning_rate": 7.454545454545456e-06,
|
| 295 |
+
"loss": 0.6903,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.23204419889502761,
|
| 300 |
+
"grad_norm": 0.9071577576208497,
|
| 301 |
+
"learning_rate": 7.636363636363638e-06,
|
| 302 |
+
"loss": 0.6681,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23756906077348067,
|
| 307 |
+
"grad_norm": 0.7806943160679269,
|
| 308 |
+
"learning_rate": 7.81818181818182e-06,
|
| 309 |
+
"loss": 0.6454,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.2430939226519337,
|
| 314 |
+
"grad_norm": 0.8542316753334585,
|
| 315 |
+
"learning_rate": 8.000000000000001e-06,
|
| 316 |
+
"loss": 0.6943,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.24861878453038674,
|
| 321 |
+
"grad_norm": 0.8806155598957247,
|
| 322 |
+
"learning_rate": 8.181818181818183e-06,
|
| 323 |
+
"loss": 0.6376,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2541436464088398,
|
| 328 |
+
"grad_norm": 0.9140053110890461,
|
| 329 |
+
"learning_rate": 8.363636363636365e-06,
|
| 330 |
+
"loss": 0.6873,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2596685082872928,
|
| 335 |
+
"grad_norm": 0.9696816209283575,
|
| 336 |
+
"learning_rate": 8.545454545454546e-06,
|
| 337 |
+
"loss": 0.6275,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.26519337016574585,
|
| 342 |
+
"grad_norm": 0.8011554339035484,
|
| 343 |
+
"learning_rate": 8.727272727272728e-06,
|
| 344 |
+
"loss": 0.7049,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.27071823204419887,
|
| 349 |
+
"grad_norm": 0.8214450369964688,
|
| 350 |
+
"learning_rate": 8.90909090909091e-06,
|
| 351 |
+
"loss": 0.6914,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.27624309392265195,
|
| 356 |
+
"grad_norm": 0.9615553631195245,
|
| 357 |
+
"learning_rate": 9.090909090909091e-06,
|
| 358 |
+
"loss": 0.6982,
|
| 359 |
"step": 50
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 0.281767955801105,
|
| 363 |
+
"grad_norm": 0.8354942020446344,
|
| 364 |
+
"learning_rate": 9.272727272727273e-06,
|
| 365 |
+
"loss": 0.7023,
|
|
|
|
| 366 |
"step": 51
|
| 367 |
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.287292817679558,
|
| 370 |
+
"grad_norm": 0.8299384272303495,
|
| 371 |
+
"learning_rate": 9.454545454545456e-06,
|
| 372 |
+
"loss": 0.695,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.292817679558011,
|
| 377 |
+
"grad_norm": 0.919798873510162,
|
| 378 |
+
"learning_rate": 9.636363636363638e-06,
|
| 379 |
+
"loss": 0.7185,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2983425414364641,
|
| 384 |
+
"grad_norm": 0.8232925581988623,
|
| 385 |
+
"learning_rate": 9.81818181818182e-06,
|
| 386 |
+
"loss": 0.6864,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.30386740331491713,
|
| 391 |
+
"grad_norm": 0.7920084479497609,
|
| 392 |
+
"learning_rate": 1e-05,
|
| 393 |
+
"loss": 0.6191,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.30939226519337015,
|
| 398 |
+
"grad_norm": 0.8758601266592275,
|
| 399 |
+
"learning_rate": 9.999896390730872e-06,
|
| 400 |
+
"loss": 0.6469,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3149171270718232,
|
| 405 |
+
"grad_norm": 1.0142576779420058,
|
| 406 |
+
"learning_rate": 9.99958556721744e-06,
|
| 407 |
+
"loss": 0.7147,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.32044198895027626,
|
| 412 |
+
"grad_norm": 0.788012902837433,
|
| 413 |
+
"learning_rate": 9.99906754234138e-06,
|
| 414 |
+
"loss": 0.6935,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3259668508287293,
|
| 419 |
+
"grad_norm": 0.8574442174017383,
|
| 420 |
+
"learning_rate": 9.998342337571566e-06,
|
| 421 |
+
"loss": 0.6852,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.3314917127071823,
|
| 426 |
+
"grad_norm": 0.8678503120132645,
|
| 427 |
+
"learning_rate": 9.997409982963173e-06,
|
| 428 |
+
"loss": 0.594,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3370165745856354,
|
| 433 |
+
"grad_norm": 0.7829472641187216,
|
| 434 |
+
"learning_rate": 9.996270517156431e-06,
|
| 435 |
+
"loss": 0.6359,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.3425414364640884,
|
| 440 |
+
"grad_norm": 0.9057620068251797,
|
| 441 |
+
"learning_rate": 9.994923987375029e-06,
|
| 442 |
+
"loss": 0.6948,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.34806629834254144,
|
| 447 |
+
"grad_norm": 0.865674232498531,
|
| 448 |
+
"learning_rate": 9.993370449424153e-06,
|
| 449 |
+
"loss": 0.73,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.35359116022099446,
|
| 454 |
+
"grad_norm": 0.9444683215382766,
|
| 455 |
+
"learning_rate": 9.991609967688177e-06,
|
| 456 |
+
"loss": 0.7042,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.35911602209944754,
|
| 461 |
+
"grad_norm": 0.8179346757831395,
|
| 462 |
+
"learning_rate": 9.98964261512799e-06,
|
| 463 |
+
"loss": 0.7034,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.36464088397790057,
|
| 468 |
+
"grad_norm": 0.8424333161772681,
|
| 469 |
+
"learning_rate": 9.987468473277975e-06,
|
| 470 |
+
"loss": 0.6368,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3701657458563536,
|
| 475 |
+
"grad_norm": 1.1453016585540032,
|
| 476 |
+
"learning_rate": 9.985087632242634e-06,
|
| 477 |
+
"loss": 0.7059,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3756906077348066,
|
| 482 |
+
"grad_norm": 0.8910424821188626,
|
| 483 |
+
"learning_rate": 9.982500190692846e-06,
|
| 484 |
+
"loss": 0.7011,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.3812154696132597,
|
| 489 |
+
"grad_norm": 0.8430209673516222,
|
| 490 |
+
"learning_rate": 9.97970625586178e-06,
|
| 491 |
+
"loss": 0.7038,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3867403314917127,
|
| 496 |
+
"grad_norm": 1.0961889806167662,
|
| 497 |
+
"learning_rate": 9.976705943540458e-06,
|
| 498 |
+
"loss": 0.7167,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.39226519337016574,
|
| 503 |
+
"grad_norm": 0.776673389768424,
|
| 504 |
+
"learning_rate": 9.973499378072947e-06,
|
| 505 |
+
"loss": 0.6383,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.39779005524861877,
|
| 510 |
+
"grad_norm": 0.7677036148013285,
|
| 511 |
+
"learning_rate": 9.970086692351204e-06,
|
| 512 |
+
"loss": 0.6711,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.40331491712707185,
|
| 517 |
+
"grad_norm": 0.7769311932254055,
|
| 518 |
+
"learning_rate": 9.966468027809582e-06,
|
| 519 |
+
"loss": 0.6631,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.4088397790055249,
|
| 524 |
+
"grad_norm": 1.345391434823482,
|
| 525 |
+
"learning_rate": 9.962643534418954e-06,
|
| 526 |
+
"loss": 0.7296,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.4143646408839779,
|
| 531 |
+
"grad_norm": 0.8085666056467051,
|
| 532 |
+
"learning_rate": 9.958613370680507e-06,
|
| 533 |
+
"loss": 0.6619,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4198895027624309,
|
| 538 |
+
"grad_norm": 0.726842812492243,
|
| 539 |
+
"learning_rate": 9.954377703619171e-06,
|
| 540 |
+
"loss": 0.6449,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.425414364640884,
|
| 545 |
+
"grad_norm": 1.0071149507052566,
|
| 546 |
+
"learning_rate": 9.949936708776692e-06,
|
| 547 |
+
"loss": 0.761,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.430939226519337,
|
| 552 |
+
"grad_norm": 0.8013700509400903,
|
| 553 |
+
"learning_rate": 9.945290570204361e-06,
|
| 554 |
+
"loss": 0.6456,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.43646408839779005,
|
| 559 |
+
"grad_norm": 0.7153613260752815,
|
| 560 |
+
"learning_rate": 9.940439480455386e-06,
|
| 561 |
+
"loss": 0.6883,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.4419889502762431,
|
| 566 |
+
"grad_norm": 0.8042269533559475,
|
| 567 |
+
"learning_rate": 9.935383640576915e-06,
|
| 568 |
+
"loss": 0.7192,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.44751381215469616,
|
| 573 |
+
"grad_norm": 0.8007389578297808,
|
| 574 |
+
"learning_rate": 9.930123260101697e-06,
|
| 575 |
+
"loss": 0.7022,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.4530386740331492,
|
| 580 |
+
"grad_norm": 0.7451865462622602,
|
| 581 |
+
"learning_rate": 9.9246585570394e-06,
|
| 582 |
+
"loss": 0.653,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.4585635359116022,
|
| 587 |
+
"grad_norm": 0.7629901737313624,
|
| 588 |
+
"learning_rate": 9.918989757867584e-06,
|
| 589 |
+
"loss": 0.7316,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.46408839779005523,
|
| 594 |
+
"grad_norm": 0.694181698027841,
|
| 595 |
+
"learning_rate": 9.9131170975223e-06,
|
| 596 |
+
"loss": 0.632,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.4696132596685083,
|
| 601 |
+
"grad_norm": 0.8031579121005685,
|
| 602 |
+
"learning_rate": 9.907040819388372e-06,
|
| 603 |
+
"loss": 0.7125,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.47513812154696133,
|
| 608 |
+
"grad_norm": 0.8027715808171925,
|
| 609 |
+
"learning_rate": 9.90076117528929e-06,
|
| 610 |
+
"loss": 0.7054,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.48066298342541436,
|
| 615 |
+
"grad_norm": 0.684436413306382,
|
| 616 |
+
"learning_rate": 9.89427842547679e-06,
|
| 617 |
+
"loss": 0.6908,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4861878453038674,
|
| 622 |
+
"grad_norm": 0.7492065837893762,
|
| 623 |
+
"learning_rate": 9.88759283862006e-06,
|
| 624 |
+
"loss": 0.6951,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.49171270718232046,
|
| 629 |
+
"grad_norm": 0.815556456770822,
|
| 630 |
+
"learning_rate": 9.880704691794608e-06,
|
| 631 |
+
"loss": 0.6829,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4972375690607735,
|
| 636 |
+
"grad_norm": 0.848254246152851,
|
| 637 |
+
"learning_rate": 9.873614270470778e-06,
|
| 638 |
+
"loss": 0.704,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5027624309392266,
|
| 643 |
+
"grad_norm": 0.7783965679247608,
|
| 644 |
+
"learning_rate": 9.866321868501914e-06,
|
| 645 |
+
"loss": 0.7535,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5082872928176796,
|
| 650 |
+
"grad_norm": 0.7186199448098722,
|
| 651 |
+
"learning_rate": 9.858827788112195e-06,
|
| 652 |
+
"loss": 0.6771,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5138121546961326,
|
| 657 |
+
"grad_norm": 0.8382444185720348,
|
| 658 |
+
"learning_rate": 9.851132339884097e-06,
|
| 659 |
+
"loss": 0.6821,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.5193370165745856,
|
| 664 |
+
"grad_norm": 0.7135375433267422,
|
| 665 |
+
"learning_rate": 9.843235842745527e-06,
|
| 666 |
+
"loss": 0.6985,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5248618784530387,
|
| 671 |
+
"grad_norm": 0.7467452705314399,
|
| 672 |
+
"learning_rate": 9.835138623956603e-06,
|
| 673 |
+
"loss": 0.6875,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5303867403314917,
|
| 678 |
+
"grad_norm": 0.6945947858932874,
|
| 679 |
+
"learning_rate": 9.826841019096095e-06,
|
| 680 |
+
"loss": 0.6488,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5359116022099447,
|
| 685 |
+
"grad_norm": 0.7817121402690996,
|
| 686 |
+
"learning_rate": 9.818343372047509e-06,
|
| 687 |
+
"loss": 0.6749,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.5414364640883977,
|
| 692 |
+
"grad_norm": 0.7141735093592115,
|
| 693 |
+
"learning_rate": 9.80964603498485e-06,
|
| 694 |
+
"loss": 0.6468,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.5469613259668509,
|
| 699 |
+
"grad_norm": 0.7962920109310585,
|
| 700 |
+
"learning_rate": 9.80074936835801e-06,
|
| 701 |
+
"loss": 0.7068,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.5524861878453039,
|
| 706 |
+
"grad_norm": 0.7317304477983744,
|
| 707 |
+
"learning_rate": 9.79165374087784e-06,
|
| 708 |
+
"loss": 0.7422,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.5580110497237569,
|
| 713 |
+
"grad_norm": 0.7000495326190369,
|
| 714 |
+
"learning_rate": 9.782359529500867e-06,
|
| 715 |
+
"loss": 0.6541,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.56353591160221,
|
| 720 |
+
"grad_norm": 0.669926861217796,
|
| 721 |
+
"learning_rate": 9.772867119413667e-06,
|
| 722 |
+
"loss": 0.6509,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.569060773480663,
|
| 727 |
+
"grad_norm": 0.7233355042750117,
|
| 728 |
+
"learning_rate": 9.763176904016914e-06,
|
| 729 |
+
"loss": 0.7281,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.574585635359116,
|
| 734 |
+
"grad_norm": 0.7297609103522801,
|
| 735 |
+
"learning_rate": 9.753289284909058e-06,
|
| 736 |
+
"loss": 0.6853,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.580110497237569,
|
| 741 |
+
"grad_norm": 0.7837111907679791,
|
| 742 |
+
"learning_rate": 9.743204671869694e-06,
|
| 743 |
+
"loss": 0.7378,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.585635359116022,
|
| 748 |
+
"grad_norm": 0.695348976767688,
|
| 749 |
+
"learning_rate": 9.73292348284258e-06,
|
| 750 |
+
"loss": 0.6548,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5911602209944752,
|
| 755 |
+
"grad_norm": 0.7062726297235884,
|
| 756 |
+
"learning_rate": 9.722446143918307e-06,
|
| 757 |
+
"loss": 0.7006,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5966850828729282,
|
| 762 |
+
"grad_norm": 0.6884204999018269,
|
| 763 |
+
"learning_rate": 9.711773089316645e-06,
|
| 764 |
+
"loss": 0.6197,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.6022099447513812,
|
| 769 |
+
"grad_norm": 0.7974626566246549,
|
| 770 |
+
"learning_rate": 9.70090476136855e-06,
|
| 771 |
+
"loss": 0.7452,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.6077348066298343,
|
| 776 |
+
"grad_norm": 0.7519249005086731,
|
| 777 |
+
"learning_rate": 9.689841610497828e-06,
|
| 778 |
+
"loss": 0.687,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.6132596685082873,
|
| 783 |
+
"grad_norm": 0.7530757425183137,
|
| 784 |
+
"learning_rate": 9.678584095202468e-06,
|
| 785 |
+
"loss": 0.7223,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.6187845303867403,
|
| 790 |
+
"grad_norm": 0.8292920525912827,
|
| 791 |
+
"learning_rate": 9.667132682035646e-06,
|
| 792 |
+
"loss": 0.6301,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6243093922651933,
|
| 797 |
+
"grad_norm": 0.7985728833994651,
|
| 798 |
+
"learning_rate": 9.655487845586378e-06,
|
| 799 |
+
"loss": 0.6117,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.6298342541436464,
|
| 804 |
+
"grad_norm": 0.675379570131735,
|
| 805 |
+
"learning_rate": 9.643650068459863e-06,
|
| 806 |
+
"loss": 0.5902,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.6353591160220995,
|
| 811 |
+
"grad_norm": 0.7621705816706639,
|
| 812 |
+
"learning_rate": 9.631619841257477e-06,
|
| 813 |
+
"loss": 0.6144,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.6408839779005525,
|
| 818 |
+
"grad_norm": 0.7372229704093334,
|
| 819 |
+
"learning_rate": 9.619397662556434e-06,
|
| 820 |
+
"loss": 0.6444,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.6464088397790055,
|
| 825 |
+
"grad_norm": 0.7171400121498231,
|
| 826 |
+
"learning_rate": 9.606984038889142e-06,
|
| 827 |
+
"loss": 0.6478,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.6519337016574586,
|
| 832 |
+
"grad_norm": 0.7162391776467386,
|
| 833 |
+
"learning_rate": 9.594379484722185e-06,
|
| 834 |
+
"loss": 0.6368,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.6574585635359116,
|
| 839 |
+
"grad_norm": 0.8119977538487404,
|
| 840 |
+
"learning_rate": 9.581584522435025e-06,
|
| 841 |
+
"loss": 0.6971,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6629834254143646,
|
| 846 |
+
"grad_norm": 0.7697231468364938,
|
| 847 |
+
"learning_rate": 9.568599682298337e-06,
|
| 848 |
+
"loss": 0.6323,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.6685082872928176,
|
| 853 |
+
"grad_norm": 0.7222511824646166,
|
| 854 |
+
"learning_rate": 9.555425502452038e-06,
|
| 855 |
+
"loss": 0.7068,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.6740331491712708,
|
| 860 |
+
"grad_norm": 0.7059581814243575,
|
| 861 |
+
"learning_rate": 9.542062528882989e-06,
|
| 862 |
+
"loss": 0.6758,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.6795580110497238,
|
| 867 |
+
"grad_norm": 0.7911262183983974,
|
| 868 |
+
"learning_rate": 9.528511315402358e-06,
|
| 869 |
+
"loss": 0.6844,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6850828729281768,
|
| 874 |
+
"grad_norm": 0.9567455662688182,
|
| 875 |
+
"learning_rate": 9.514772423622675e-06,
|
| 876 |
+
"loss": 0.7468,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.6906077348066298,
|
| 881 |
+
"grad_norm": 0.8075170793709282,
|
| 882 |
+
"learning_rate": 9.500846422934557e-06,
|
| 883 |
+
"loss": 0.6884,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.6961325966850829,
|
| 888 |
+
"grad_norm": 0.6617434418531425,
|
| 889 |
+
"learning_rate": 9.4867338904831e-06,
|
| 890 |
+
"loss": 0.6807,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.7016574585635359,
|
| 895 |
+
"grad_norm": 0.6852663876058741,
|
| 896 |
+
"learning_rate": 9.472435411143979e-06,
|
| 897 |
+
"loss": 0.631,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.7071823204419889,
|
| 902 |
+
"grad_norm": 0.8062476288399656,
|
| 903 |
+
"learning_rate": 9.457951577499187e-06,
|
| 904 |
+
"loss": 0.6678,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.712707182320442,
|
| 909 |
+
"grad_norm": 0.6969129316123458,
|
| 910 |
+
"learning_rate": 9.443282989812494e-06,
|
| 911 |
+
"loss": 0.6413,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.7182320441988951,
|
| 916 |
+
"grad_norm": 0.7139049384459147,
|
| 917 |
+
"learning_rate": 9.428430256004558e-06,
|
| 918 |
+
"loss": 0.6523,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.7237569060773481,
|
| 923 |
+
"grad_norm": 0.7008590174042524,
|
| 924 |
+
"learning_rate": 9.413393991627737e-06,
|
| 925 |
+
"loss": 0.6826,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.7292817679558011,
|
| 930 |
+
"grad_norm": 0.8833945053457845,
|
| 931 |
+
"learning_rate": 9.398174819840577e-06,
|
| 932 |
+
"loss": 0.6405,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7348066298342542,
|
| 937 |
+
"grad_norm": 0.7572193126349432,
|
| 938 |
+
"learning_rate": 9.382773371381986e-06,
|
| 939 |
+
"loss": 0.6689,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.7403314917127072,
|
| 944 |
+
"grad_norm": 0.7524950122671795,
|
| 945 |
+
"learning_rate": 9.367190284545087e-06,
|
| 946 |
+
"loss": 0.7109,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.7458563535911602,
|
| 951 |
+
"grad_norm": 0.6769451685165733,
|
| 952 |
+
"learning_rate": 9.351426205150778e-06,
|
| 953 |
+
"loss": 0.66,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.7513812154696132,
|
| 958 |
+
"grad_norm": 0.790773238492282,
|
| 959 |
+
"learning_rate": 9.335481786520955e-06,
|
| 960 |
+
"loss": 0.7216,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.7569060773480663,
|
| 965 |
+
"grad_norm": 0.7100066068783747,
|
| 966 |
+
"learning_rate": 9.319357689451444e-06,
|
| 967 |
+
"loss": 0.6562,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.7624309392265194,
|
| 972 |
+
"grad_norm": 0.7853719538210431,
|
| 973 |
+
"learning_rate": 9.30305458218461e-06,
|
| 974 |
+
"loss": 0.6882,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.7679558011049724,
|
| 979 |
+
"grad_norm": 0.6638407553470856,
|
| 980 |
+
"learning_rate": 9.286573140381663e-06,
|
| 981 |
+
"loss": 0.6541,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.7734806629834254,
|
| 986 |
+
"grad_norm": 0.6834239770243532,
|
| 987 |
+
"learning_rate": 9.26991404709466e-06,
|
| 988 |
+
"loss": 0.6289,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.7790055248618785,
|
| 993 |
+
"grad_norm": 0.8713388179210387,
|
| 994 |
+
"learning_rate": 9.253077992738193e-06,
|
| 995 |
+
"loss": 0.73,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7845303867403315,
|
| 1000 |
+
"grad_norm": 0.7629447190554447,
|
| 1001 |
+
"learning_rate": 9.236065675060775e-06,
|
| 1002 |
+
"loss": 0.693,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.7900552486187845,
|
| 1007 |
+
"grad_norm": 0.7544036306635357,
|
| 1008 |
+
"learning_rate": 9.218877799115929e-06,
|
| 1009 |
+
"loss": 0.7252,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.7955801104972375,
|
| 1014 |
+
"grad_norm": 0.6847405196212653,
|
| 1015 |
+
"learning_rate": 9.201515077232958e-06,
|
| 1016 |
+
"loss": 0.703,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.8011049723756906,
|
| 1021 |
+
"grad_norm": 0.7322209407647546,
|
| 1022 |
+
"learning_rate": 9.183978228987436e-06,
|
| 1023 |
+
"loss": 0.6511,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.8066298342541437,
|
| 1028 |
+
"grad_norm": 0.7306655102140895,
|
| 1029 |
+
"learning_rate": 9.166267981171369e-06,
|
| 1030 |
+
"loss": 0.6477,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.8121546961325967,
|
| 1035 |
+
"grad_norm": 0.7206398058794518,
|
| 1036 |
+
"learning_rate": 9.148385067763094e-06,
|
| 1037 |
+
"loss": 0.6407,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.8176795580110497,
|
| 1042 |
+
"grad_norm": 0.7036158657538799,
|
| 1043 |
+
"learning_rate": 9.130330229896846e-06,
|
| 1044 |
+
"loss": 0.6096,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.8232044198895028,
|
| 1049 |
+
"grad_norm": 0.7807874970263721,
|
| 1050 |
+
"learning_rate": 9.112104215832047e-06,
|
| 1051 |
+
"loss": 0.658,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.8287292817679558,
|
| 1056 |
+
"grad_norm": 0.6887926406142375,
|
| 1057 |
+
"learning_rate": 9.093707780922293e-06,
|
| 1058 |
+
"loss": 0.6985,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8342541436464088,
|
| 1063 |
+
"grad_norm": 0.7163709674127419,
|
| 1064 |
+
"learning_rate": 9.075141687584056e-06,
|
| 1065 |
+
"loss": 0.6801,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.8397790055248618,
|
| 1070 |
+
"grad_norm": 0.6837817476434366,
|
| 1071 |
+
"learning_rate": 9.056406705265084e-06,
|
| 1072 |
+
"loss": 0.6442,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.8453038674033149,
|
| 1077 |
+
"grad_norm": 0.6843857902663828,
|
| 1078 |
+
"learning_rate": 9.037503610412502e-06,
|
| 1079 |
+
"loss": 0.6446,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.850828729281768,
|
| 1084 |
+
"grad_norm": 0.7547759124038085,
|
| 1085 |
+
"learning_rate": 9.018433186440648e-06,
|
| 1086 |
+
"loss": 0.7106,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.856353591160221,
|
| 1091 |
+
"grad_norm": 0.6923617352622536,
|
| 1092 |
+
"learning_rate": 8.999196223698599e-06,
|
| 1093 |
+
"loss": 0.7418,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.861878453038674,
|
| 1098 |
+
"grad_norm": 0.7589388571367478,
|
| 1099 |
+
"learning_rate": 8.979793519437413e-06,
|
| 1100 |
+
"loss": 0.7064,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.8674033149171271,
|
| 1105 |
+
"grad_norm": 0.8111254921639891,
|
| 1106 |
+
"learning_rate": 8.960225877777095e-06,
|
| 1107 |
+
"loss": 0.7153,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.8729281767955801,
|
| 1112 |
+
"grad_norm": 0.6405807331541313,
|
| 1113 |
+
"learning_rate": 8.940494109673266e-06,
|
| 1114 |
+
"loss": 0.6121,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.8784530386740331,
|
| 1119 |
+
"grad_norm": 0.6742570632281877,
|
| 1120 |
+
"learning_rate": 8.920599032883553e-06,
|
| 1121 |
+
"loss": 0.6781,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.8839779005524862,
|
| 1126 |
+
"grad_norm": 0.7843439776633434,
|
| 1127 |
+
"learning_rate": 8.900541471933703e-06,
|
| 1128 |
+
"loss": 0.6979,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.8895027624309392,
|
| 1133 |
+
"grad_norm": 0.725960679493056,
|
| 1134 |
+
"learning_rate": 8.880322258083408e-06,
|
| 1135 |
+
"loss": 0.6557,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.8950276243093923,
|
| 1140 |
+
"grad_norm": 0.6898678148433862,
|
| 1141 |
+
"learning_rate": 8.859942229291856e-06,
|
| 1142 |
+
"loss": 0.662,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.9005524861878453,
|
| 1147 |
+
"grad_norm": 0.7710968128854336,
|
| 1148 |
+
"learning_rate": 8.839402230183e-06,
|
| 1149 |
+
"loss": 0.662,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.9060773480662984,
|
| 1154 |
+
"grad_norm": 0.741382073637584,
|
| 1155 |
+
"learning_rate": 8.818703112010562e-06,
|
| 1156 |
+
"loss": 0.6935,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.9116022099447514,
|
| 1161 |
+
"grad_norm": 0.6831369278396727,
|
| 1162 |
+
"learning_rate": 8.797845732622742e-06,
|
| 1163 |
+
"loss": 0.7031,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.9171270718232044,
|
| 1168 |
+
"grad_norm": 0.7492006743864014,
|
| 1169 |
+
"learning_rate": 8.776830956426674e-06,
|
| 1170 |
+
"loss": 0.708,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.9226519337016574,
|
| 1175 |
+
"grad_norm": 0.7613459925623692,
|
| 1176 |
+
"learning_rate": 8.755659654352599e-06,
|
| 1177 |
+
"loss": 0.7169,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.9281767955801105,
|
| 1182 |
+
"grad_norm": 0.6791670574304287,
|
| 1183 |
+
"learning_rate": 8.734332703817771e-06,
|
| 1184 |
+
"loss": 0.6991,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9337016574585635,
|
| 1189 |
+
"grad_norm": 0.6681861340818701,
|
| 1190 |
+
"learning_rate": 8.712850988690094e-06,
|
| 1191 |
+
"loss": 0.7032,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.9392265193370166,
|
| 1196 |
+
"grad_norm": 0.6569011217941949,
|
| 1197 |
+
"learning_rate": 8.691215399251489e-06,
|
| 1198 |
+
"loss": 0.6439,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.9447513812154696,
|
| 1203 |
+
"grad_norm": 0.7086161196938886,
|
| 1204 |
+
"learning_rate": 8.669426832160997e-06,
|
| 1205 |
+
"loss": 0.6193,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.9502762430939227,
|
| 1210 |
+
"grad_norm": 0.654556823801651,
|
| 1211 |
+
"learning_rate": 8.647486190417624e-06,
|
| 1212 |
+
"loss": 0.6929,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9558011049723757,
|
| 1217 |
+
"grad_norm": 0.7440213169432797,
|
| 1218 |
+
"learning_rate": 8.625394383322914e-06,
|
| 1219 |
+
"loss": 0.6779,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.9613259668508287,
|
| 1224 |
+
"grad_norm": 0.7345541693491946,
|
| 1225 |
+
"learning_rate": 8.603152326443262e-06,
|
| 1226 |
+
"loss": 0.6412,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.9668508287292817,
|
| 1231 |
+
"grad_norm": 0.7017136954703048,
|
| 1232 |
+
"learning_rate": 8.580760941571968e-06,
|
| 1233 |
+
"loss": 0.7249,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9723756906077348,
|
| 1238 |
+
"grad_norm": 0.7533884250226044,
|
| 1239 |
+
"learning_rate": 8.55822115669104e-06,
|
| 1240 |
+
"loss": 0.6725,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.9779005524861878,
|
| 1245 |
+
"grad_norm": 0.8635896869993843,
|
| 1246 |
+
"learning_rate": 8.535533905932739e-06,
|
| 1247 |
+
"loss": 0.6778,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.9834254143646409,
|
| 1252 |
+
"grad_norm": 0.7046176922723474,
|
| 1253 |
+
"learning_rate": 8.512700129540847e-06,
|
| 1254 |
+
"loss": 0.646,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.988950276243094,
|
| 1259 |
+
"grad_norm": 0.7469626256845687,
|
| 1260 |
+
"learning_rate": 8.489720773831717e-06,
|
| 1261 |
+
"loss": 0.6742,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.994475138121547,
|
| 1266 |
+
"grad_norm": 0.8073184194204243,
|
| 1267 |
+
"learning_rate": 8.466596791155055e-06,
|
| 1268 |
+
"loss": 0.6745,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.0,
|
| 1273 |
+
"grad_norm": 0.6469115640516496,
|
| 1274 |
+
"learning_rate": 8.443329139854434e-06,
|
| 1275 |
+
"loss": 0.635,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.0055248618784531,
|
| 1280 |
+
"grad_norm": 0.7680249419301477,
|
| 1281 |
+
"learning_rate": 8.419918784227592e-06,
|
| 1282 |
+
"loss": 0.6638,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.011049723756906,
|
| 1287 |
+
"grad_norm": 0.7714771127607805,
|
| 1288 |
+
"learning_rate": 8.396366694486466e-06,
|
| 1289 |
+
"loss": 0.6176,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.0165745856353592,
|
| 1294 |
+
"grad_norm": 0.6836633389900814,
|
| 1295 |
+
"learning_rate": 8.372673846716977e-06,
|
| 1296 |
+
"loss": 0.5742,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.022099447513812,
|
| 1301 |
+
"grad_norm": 0.671339247626321,
|
| 1302 |
+
"learning_rate": 8.348841222838579e-06,
|
| 1303 |
+
"loss": 0.5965,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.0276243093922652,
|
| 1308 |
+
"grad_norm": 0.6818502606595346,
|
| 1309 |
+
"learning_rate": 8.324869810563573e-06,
|
| 1310 |
+
"loss": 0.6031,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.0331491712707181,
|
| 1315 |
+
"grad_norm": 0.7679534342017695,
|
| 1316 |
+
"learning_rate": 8.30076060335616e-06,
|
| 1317 |
+
"loss": 0.6378,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.0386740331491713,
|
| 1322 |
+
"grad_norm": 0.6610817415773053,
|
| 1323 |
+
"learning_rate": 8.276514600391272e-06,
|
| 1324 |
+
"loss": 0.5828,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0441988950276242,
|
| 1329 |
+
"grad_norm": 0.7265666171607357,
|
| 1330 |
+
"learning_rate": 8.25213280651317e-06,
|
| 1331 |
+
"loss": 0.5991,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.0497237569060773,
|
| 1336 |
+
"grad_norm": 0.7356973203535483,
|
| 1337 |
+
"learning_rate": 8.227616232193794e-06,
|
| 1338 |
+
"loss": 0.5877,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.0552486187845305,
|
| 1343 |
+
"grad_norm": 0.7865650351374615,
|
| 1344 |
+
"learning_rate": 8.202965893490877e-06,
|
| 1345 |
+
"loss": 0.6476,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.0607734806629834,
|
| 1350 |
+
"grad_norm": 0.7194978525901626,
|
| 1351 |
+
"learning_rate": 8.178182812005853e-06,
|
| 1352 |
+
"loss": 0.5147,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.0662983425414365,
|
| 1357 |
+
"grad_norm": 0.70366807919922,
|
| 1358 |
+
"learning_rate": 8.153268014841507e-06,
|
| 1359 |
+
"loss": 0.6128,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.0718232044198894,
|
| 1364 |
+
"grad_norm": 0.6751029207263034,
|
| 1365 |
+
"learning_rate": 8.128222534559406e-06,
|
| 1366 |
+
"loss": 0.5743,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.0773480662983426,
|
| 1371 |
+
"grad_norm": 0.769584710702697,
|
| 1372 |
+
"learning_rate": 8.103047409137114e-06,
|
| 1373 |
+
"loss": 0.6736,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.0828729281767955,
|
| 1378 |
+
"grad_norm": 0.7906391664348668,
|
| 1379 |
+
"learning_rate": 8.07774368192517e-06,
|
| 1380 |
+
"loss": 0.6658,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.0883977900552486,
|
| 1385 |
+
"grad_norm": 0.6510299748322192,
|
| 1386 |
+
"learning_rate": 8.052312401603848e-06,
|
| 1387 |
+
"loss": 0.5765,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.0939226519337018,
|
| 1392 |
+
"grad_norm": 0.8547974979381732,
|
| 1393 |
+
"learning_rate": 8.026754622139691e-06,
|
| 1394 |
+
"loss": 0.5903,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.0994475138121547,
|
| 1399 |
+
"grad_norm": 0.8338835673156341,
|
| 1400 |
+
"learning_rate": 8.001071402741843e-06,
|
| 1401 |
+
"loss": 0.6027,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.1049723756906078,
|
| 1406 |
+
"grad_norm": 0.7681594836262089,
|
| 1407 |
+
"learning_rate": 7.975263807818136e-06,
|
| 1408 |
+
"loss": 0.6428,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.1104972375690607,
|
| 1413 |
+
"grad_norm": 0.7716286060753629,
|
| 1414 |
+
"learning_rate": 7.949332906930995e-06,
|
| 1415 |
+
"loss": 0.6502,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.1160220994475138,
|
| 1420 |
+
"grad_norm": 0.8404857249117871,
|
| 1421 |
+
"learning_rate": 7.923279774753092e-06,
|
| 1422 |
+
"loss": 0.5865,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.1215469613259668,
|
| 1427 |
+
"grad_norm": 0.6784714640462896,
|
| 1428 |
+
"learning_rate": 7.897105491022819e-06,
|
| 1429 |
+
"loss": 0.5737,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.12707182320442,
|
| 1434 |
+
"grad_norm": 0.6611561272377011,
|
| 1435 |
+
"learning_rate": 7.870811140499543e-06,
|
| 1436 |
+
"loss": 0.5916,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.132596685082873,
|
| 1441 |
+
"grad_norm": 0.6694407525681161,
|
| 1442 |
+
"learning_rate": 7.844397812918637e-06,
|
| 1443 |
+
"loss": 0.5629,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.138121546961326,
|
| 1448 |
+
"grad_norm": 0.6628808525691233,
|
| 1449 |
+
"learning_rate": 7.817866602946326e-06,
|
| 1450 |
+
"loss": 0.6174,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.143646408839779,
|
| 1455 |
+
"grad_norm": 0.6433613204625658,
|
| 1456 |
+
"learning_rate": 7.791218610134324e-06,
|
| 1457 |
+
"loss": 0.5891,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.149171270718232,
|
| 1462 |
+
"grad_norm": 0.7083946072498601,
|
| 1463 |
+
"learning_rate": 7.764454938874252e-06,
|
| 1464 |
+
"loss": 0.5973,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.1546961325966851,
|
| 1469 |
+
"grad_norm": 0.6920035749512741,
|
| 1470 |
+
"learning_rate": 7.737576698351878e-06,
|
| 1471 |
+
"loss": 0.6368,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.160220994475138,
|
| 1476 |
+
"grad_norm": 0.77090065904851,
|
| 1477 |
+
"learning_rate": 7.710585002501145e-06,
|
| 1478 |
+
"loss": 0.6458,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.1657458563535912,
|
| 1483 |
+
"grad_norm": 0.7373547338916707,
|
| 1484 |
+
"learning_rate": 7.683480969958005e-06,
|
| 1485 |
+
"loss": 0.5674,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.1712707182320443,
|
| 1490 |
+
"grad_norm": 0.6775847537528304,
|
| 1491 |
+
"learning_rate": 7.656265724014054e-06,
|
| 1492 |
+
"loss": 0.6039,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.1767955801104972,
|
| 1497 |
+
"grad_norm": 0.7080491269295629,
|
| 1498 |
+
"learning_rate": 7.628940392569995e-06,
|
| 1499 |
+
"loss": 0.6395,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.1823204419889504,
|
| 1504 |
+
"grad_norm": 0.6741064097723004,
|
| 1505 |
+
"learning_rate": 7.601506108088874e-06,
|
| 1506 |
+
"loss": 0.5882,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.1878453038674033,
|
| 1511 |
+
"grad_norm": 0.657603362174331,
|
| 1512 |
+
"learning_rate": 7.5739640075491546e-06,
|
| 1513 |
+
"loss": 0.6184,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.1933701657458564,
|
| 1518 |
+
"grad_norm": 0.6791394246768295,
|
| 1519 |
+
"learning_rate": 7.546315232397601e-06,
|
| 1520 |
+
"loss": 0.6138,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.1988950276243093,
|
| 1525 |
+
"grad_norm": 0.6894132654756862,
|
| 1526 |
+
"learning_rate": 7.518560928501969e-06,
|
| 1527 |
+
"loss": 0.6252,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.2044198895027625,
|
| 1532 |
+
"grad_norm": 0.697165533998509,
|
| 1533 |
+
"learning_rate": 7.4907022461035125e-06,
|
| 1534 |
+
"loss": 0.6002,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.2099447513812154,
|
| 1539 |
+
"grad_norm": 0.6444399979671767,
|
| 1540 |
+
"learning_rate": 7.462740339769323e-06,
|
| 1541 |
+
"loss": 0.5868,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.2154696132596685,
|
| 1546 |
+
"grad_norm": 0.7259698993482928,
|
| 1547 |
+
"learning_rate": 7.434676368344469e-06,
|
| 1548 |
+
"loss": 0.655,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.2209944751381214,
|
| 1553 |
+
"grad_norm": 0.7245469567674288,
|
| 1554 |
+
"learning_rate": 7.406511494903982e-06,
|
| 1555 |
+
"loss": 0.5975,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.2265193370165746,
|
| 1560 |
+
"grad_norm": 0.6743396575371344,
|
| 1561 |
+
"learning_rate": 7.378246886704638e-06,
|
| 1562 |
+
"loss": 0.6729,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.2320441988950277,
|
| 1567 |
+
"grad_norm": 0.7206318344181539,
|
| 1568 |
+
"learning_rate": 7.349883715136601e-06,
|
| 1569 |
+
"loss": 0.6123,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.2375690607734806,
|
| 1574 |
+
"grad_norm": 0.602101018107306,
|
| 1575 |
+
"learning_rate": 7.321423155674858e-06,
|
| 1576 |
+
"loss": 0.5287,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.2430939226519337,
|
| 1581 |
+
"grad_norm": 0.6466479963244331,
|
| 1582 |
+
"learning_rate": 7.292866387830515e-06,
|
| 1583 |
+
"loss": 0.5927,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.2486187845303867,
|
| 1588 |
+
"grad_norm": 0.7693210833084159,
|
| 1589 |
+
"learning_rate": 7.264214595101913e-06,
|
| 1590 |
+
"loss": 0.6321,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.2541436464088398,
|
| 1595 |
+
"grad_norm": 0.6789133468563491,
|
| 1596 |
+
"learning_rate": 7.235468964925571e-06,
|
| 1597 |
+
"loss": 0.5794,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.2596685082872927,
|
| 1602 |
+
"grad_norm": 0.7739752082859613,
|
| 1603 |
+
"learning_rate": 7.206630688626981e-06,
|
| 1604 |
+
"loss": 0.6563,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.2651933701657458,
|
| 1609 |
+
"grad_norm": 0.7370007253011229,
|
| 1610 |
+
"learning_rate": 7.177700961371239e-06,
|
| 1611 |
+
"loss": 0.6075,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.270718232044199,
|
| 1616 |
+
"grad_norm": 0.7982040126875192,
|
| 1617 |
+
"learning_rate": 7.148680982113502e-06,
|
| 1618 |
+
"loss": 0.6422,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.276243093922652,
|
| 1623 |
+
"grad_norm": 0.6629426029965108,
|
| 1624 |
+
"learning_rate": 7.119571953549305e-06,
|
| 1625 |
+
"loss": 0.645,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.281767955801105,
|
| 1630 |
+
"grad_norm": 0.6597217484497837,
|
| 1631 |
+
"learning_rate": 7.0903750820647175e-06,
|
| 1632 |
+
"loss": 0.6046,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.287292817679558,
|
| 1637 |
+
"grad_norm": 0.6171612521609076,
|
| 1638 |
+
"learning_rate": 7.061091577686349e-06,
|
| 1639 |
+
"loss": 0.5663,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.292817679558011,
|
| 1644 |
+
"grad_norm": 0.6930974359608171,
|
| 1645 |
+
"learning_rate": 7.031722654031192e-06,
|
| 1646 |
+
"loss": 0.5901,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.298342541436464,
|
| 1651 |
+
"grad_norm": 0.6340608907226989,
|
| 1652 |
+
"learning_rate": 7.002269528256334e-06,
|
| 1653 |
+
"loss": 0.6084,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.3038674033149171,
|
| 1658 |
+
"grad_norm": 0.6695648424102065,
|
| 1659 |
+
"learning_rate": 6.972733421008505e-06,
|
| 1660 |
+
"loss": 0.5938,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.3093922651933703,
|
| 1665 |
+
"grad_norm": 0.7162730447160397,
|
| 1666 |
+
"learning_rate": 6.943115556373503e-06,
|
| 1667 |
+
"loss": 0.606,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.3149171270718232,
|
| 1672 |
+
"grad_norm": 0.7136879200055026,
|
| 1673 |
+
"learning_rate": 6.913417161825449e-06,
|
| 1674 |
+
"loss": 0.6491,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.3204419889502763,
|
| 1679 |
+
"grad_norm": 0.696786721330877,
|
| 1680 |
+
"learning_rate": 6.883639468175926e-06,
|
| 1681 |
+
"loss": 0.6072,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.3259668508287292,
|
| 1686 |
+
"grad_norm": 0.753245759137927,
|
| 1687 |
+
"learning_rate": 6.853783709522963e-06,
|
| 1688 |
+
"loss": 0.6018,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.3314917127071824,
|
| 1693 |
+
"grad_norm": 0.6968519374034413,
|
| 1694 |
+
"learning_rate": 6.823851123199894e-06,
|
| 1695 |
+
"loss": 0.6434,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.3370165745856353,
|
| 1700 |
+
"grad_norm": 0.6761342537400503,
|
| 1701 |
+
"learning_rate": 6.793842949724074e-06,
|
| 1702 |
+
"loss": 0.6225,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.3425414364640884,
|
| 1707 |
+
"grad_norm": 0.7322253178916728,
|
| 1708 |
+
"learning_rate": 6.763760432745475e-06,
|
| 1709 |
+
"loss": 0.6131,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.3480662983425415,
|
| 1714 |
+
"grad_norm": 0.7699522982913194,
|
| 1715 |
+
"learning_rate": 6.733604818995133e-06,
|
| 1716 |
+
"loss": 0.6366,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.3535911602209945,
|
| 1721 |
+
"grad_norm": 0.6196932838702959,
|
| 1722 |
+
"learning_rate": 6.703377358233489e-06,
|
| 1723 |
+
"loss": 0.595,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.3591160220994476,
|
| 1728 |
+
"grad_norm": 0.7047536218041381,
|
| 1729 |
+
"learning_rate": 6.673079303198591e-06,
|
| 1730 |
+
"loss": 0.5941,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.3646408839779005,
|
| 1735 |
+
"grad_norm": 0.8335370354195214,
|
| 1736 |
+
"learning_rate": 6.6427119095541745e-06,
|
| 1737 |
+
"loss": 0.5967,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.3701657458563536,
|
| 1742 |
+
"grad_norm": 0.7706739113368778,
|
| 1743 |
+
"learning_rate": 6.612276435837622e-06,
|
| 1744 |
+
"loss": 0.5917,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.3756906077348066,
|
| 1749 |
+
"grad_norm": 0.7446603300489363,
|
| 1750 |
+
"learning_rate": 6.58177414340781e-06,
|
| 1751 |
+
"loss": 0.6342,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.3812154696132597,
|
| 1756 |
+
"grad_norm": 0.6592546584880928,
|
| 1757 |
+
"learning_rate": 6.551206296392827e-06,
|
| 1758 |
+
"loss": 0.5791,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.3867403314917128,
|
| 1763 |
+
"grad_norm": 0.8080309844429614,
|
| 1764 |
+
"learning_rate": 6.520574161637591e-06,
|
| 1765 |
+
"loss": 0.6555,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.3922651933701657,
|
| 1770 |
+
"grad_norm": 0.6757755218068,
|
| 1771 |
+
"learning_rate": 6.4898790086513366e-06,
|
| 1772 |
+
"loss": 0.6002,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.3977900552486187,
|
| 1777 |
+
"grad_norm": 0.6540398994889906,
|
| 1778 |
+
"learning_rate": 6.459122109555011e-06,
|
| 1779 |
+
"loss": 0.5968,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.4033149171270718,
|
| 1784 |
+
"grad_norm": 0.6515476627729059,
|
| 1785 |
+
"learning_rate": 6.42830473902855e-06,
|
| 1786 |
+
"loss": 0.5915,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.408839779005525,
|
| 1791 |
+
"grad_norm": 0.768393574101539,
|
| 1792 |
+
"learning_rate": 6.397428174258048e-06,
|
| 1793 |
+
"loss": 0.6129,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.4143646408839778,
|
| 1798 |
+
"grad_norm": 0.6602226522160092,
|
| 1799 |
+
"learning_rate": 6.3664936948828296e-06,
|
| 1800 |
+
"loss": 0.618,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.419889502762431,
|
| 1805 |
+
"grad_norm": 0.7186347942888126,
|
| 1806 |
+
"learning_rate": 6.335502582942409e-06,
|
| 1807 |
+
"loss": 0.58,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.4254143646408841,
|
| 1812 |
+
"grad_norm": 0.6867146462508941,
|
| 1813 |
+
"learning_rate": 6.304456122823377e-06,
|
| 1814 |
+
"loss": 0.6284,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.430939226519337,
|
| 1819 |
+
"grad_norm": 0.6640537281896691,
|
| 1820 |
+
"learning_rate": 6.273355601206143e-06,
|
| 1821 |
+
"loss": 0.628,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.43646408839779,
|
| 1826 |
+
"grad_norm": 0.680561183563057,
|
| 1827 |
+
"learning_rate": 6.24220230701164e-06,
|
| 1828 |
+
"loss": 0.6601,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.441988950276243,
|
| 1833 |
+
"grad_norm": 0.6266987287558203,
|
| 1834 |
+
"learning_rate": 6.210997531347879e-06,
|
| 1835 |
+
"loss": 0.5342,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.4475138121546962,
|
| 1840 |
+
"grad_norm": 0.6970171405272507,
|
| 1841 |
+
"learning_rate": 6.179742567456464e-06,
|
| 1842 |
+
"loss": 0.6339,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.4530386740331491,
|
| 1847 |
+
"grad_norm": 0.6699218536254724,
|
| 1848 |
+
"learning_rate": 6.148438710658979e-06,
|
| 1849 |
+
"loss": 0.5782,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.4585635359116023,
|
| 1854 |
+
"grad_norm": 0.7406730671514048,
|
| 1855 |
+
"learning_rate": 6.117087258303314e-06,
|
| 1856 |
+
"loss": 0.6392,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.4640883977900552,
|
| 1861 |
+
"grad_norm": 0.6496784259742956,
|
| 1862 |
+
"learning_rate": 6.085689509709893e-06,
|
| 1863 |
+
"loss": 0.5848,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.4696132596685083,
|
| 1868 |
+
"grad_norm": 0.6630461769430164,
|
| 1869 |
+
"learning_rate": 6.0542467661178325e-06,
|
| 1870 |
+
"loss": 0.6243,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.4751381215469612,
|
| 1875 |
+
"grad_norm": 0.7024087077842354,
|
| 1876 |
+
"learning_rate": 6.022760330631006e-06,
|
| 1877 |
+
"loss": 0.6081,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.4806629834254144,
|
| 1882 |
+
"grad_norm": 0.644335689792361,
|
| 1883 |
+
"learning_rate": 5.991231508164037e-06,
|
| 1884 |
+
"loss": 0.6315,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.4861878453038675,
|
| 1889 |
+
"grad_norm": 0.6011260710575211,
|
| 1890 |
+
"learning_rate": 5.959661605388229e-06,
|
| 1891 |
+
"loss": 0.5479,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.4917127071823204,
|
| 1896 |
+
"grad_norm": 0.6735133008955199,
|
| 1897 |
+
"learning_rate": 5.928051930677404e-06,
|
| 1898 |
+
"loss": 0.6074,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.4972375690607735,
|
| 1903 |
+
"grad_norm": 0.724897423389795,
|
| 1904 |
+
"learning_rate": 5.896403794053679e-06,
|
| 1905 |
+
"loss": 0.6117,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.5027624309392267,
|
| 1910 |
+
"grad_norm": 0.6432683628472128,
|
| 1911 |
+
"learning_rate": 5.864718507133176e-06,
|
| 1912 |
+
"loss": 0.6015,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.5082872928176796,
|
| 1917 |
+
"grad_norm": 0.6345537221217502,
|
| 1918 |
+
"learning_rate": 5.83299738307166e-06,
|
| 1919 |
+
"loss": 0.6491,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.5138121546961325,
|
| 1924 |
+
"grad_norm": 0.6218808254180483,
|
| 1925 |
+
"learning_rate": 5.801241736510128e-06,
|
| 1926 |
+
"loss": 0.6134,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.5193370165745856,
|
| 1931 |
+
"grad_norm": 0.6782578788601987,
|
| 1932 |
+
"learning_rate": 5.76945288352031e-06,
|
| 1933 |
+
"loss": 0.6308,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.5248618784530388,
|
| 1938 |
+
"grad_norm": 0.5841892465281848,
|
| 1939 |
+
"learning_rate": 5.7376321415501356e-06,
|
| 1940 |
+
"loss": 0.5434,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.5303867403314917,
|
| 1945 |
+
"grad_norm": 0.6650299495850774,
|
| 1946 |
+
"learning_rate": 5.7057808293691305e-06,
|
| 1947 |
+
"loss": 0.6293,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.5359116022099446,
|
| 1952 |
+
"grad_norm": 0.752419119034265,
|
| 1953 |
+
"learning_rate": 5.67390026701377e-06,
|
| 1954 |
+
"loss": 0.6223,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.5414364640883977,
|
| 1959 |
+
"grad_norm": 0.8282947869336723,
|
| 1960 |
+
"learning_rate": 5.641991775732756e-06,
|
| 1961 |
+
"loss": 0.7056,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.5469613259668509,
|
| 1966 |
+
"grad_norm": 0.7173511510171976,
|
| 1967 |
+
"learning_rate": 5.610056677932274e-06,
|
| 1968 |
+
"loss": 0.6027,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.5524861878453038,
|
| 1973 |
+
"grad_norm": 0.6564750666347287,
|
| 1974 |
+
"learning_rate": 5.5780962971211795e-06,
|
| 1975 |
+
"loss": 0.6608,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.558011049723757,
|
| 1980 |
+
"grad_norm": 0.686798968992177,
|
| 1981 |
+
"learning_rate": 5.546111957856155e-06,
|
| 1982 |
+
"loss": 0.6637,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.56353591160221,
|
| 1987 |
+
"grad_norm": 0.8467673992557097,
|
| 1988 |
+
"learning_rate": 5.514104985686802e-06,
|
| 1989 |
+
"loss": 0.6916,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.569060773480663,
|
| 1994 |
+
"grad_norm": 0.7454256879275183,
|
| 1995 |
+
"learning_rate": 5.482076707100723e-06,
|
| 1996 |
+
"loss": 0.6741,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.5745856353591159,
|
| 2001 |
+
"grad_norm": 0.7068205882972726,
|
| 2002 |
+
"learning_rate": 5.4500284494685275e-06,
|
| 2003 |
+
"loss": 0.6049,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.580110497237569,
|
| 2008 |
+
"grad_norm": 0.6123366279350007,
|
| 2009 |
+
"learning_rate": 5.417961540988837e-06,
|
| 2010 |
+
"loss": 0.5804,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.5856353591160222,
|
| 2015 |
+
"grad_norm": 0.6753783255596223,
|
| 2016 |
+
"learning_rate": 5.385877310633233e-06,
|
| 2017 |
+
"loss": 0.6144,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.591160220994475,
|
| 2022 |
+
"grad_norm": 0.6787303073540277,
|
| 2023 |
+
"learning_rate": 5.353777088091177e-06,
|
| 2024 |
+
"loss": 0.6109,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.5966850828729282,
|
| 2029 |
+
"grad_norm": 0.6689374877161456,
|
| 2030 |
+
"learning_rate": 5.321662203714909e-06,
|
| 2031 |
+
"loss": 0.5701,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.6022099447513813,
|
| 2036 |
+
"grad_norm": 0.7341945035228687,
|
| 2037 |
+
"learning_rate": 5.289533988464307e-06,
|
| 2038 |
+
"loss": 0.6451,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.6077348066298343,
|
| 2043 |
+
"grad_norm": 0.7003036927886831,
|
| 2044 |
+
"learning_rate": 5.257393773851733e-06,
|
| 2045 |
+
"loss": 0.6009,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.6132596685082872,
|
| 2050 |
+
"grad_norm": 0.6798929226991296,
|
| 2051 |
+
"learning_rate": 5.2252428918868446e-06,
|
| 2052 |
+
"loss": 0.5811,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.6187845303867403,
|
| 2057 |
+
"grad_norm": 0.603212047810036,
|
| 2058 |
+
"learning_rate": 5.193082675021393e-06,
|
| 2059 |
+
"loss": 0.5346,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.6243093922651934,
|
| 2064 |
+
"grad_norm": 0.6908051872037912,
|
| 2065 |
+
"learning_rate": 5.160914456094005e-06,
|
| 2066 |
+
"loss": 0.6487,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.6298342541436464,
|
| 2071 |
+
"grad_norm": 0.759496464512415,
|
| 2072 |
+
"learning_rate": 5.1287395682749444e-06,
|
| 2073 |
+
"loss": 0.6885,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.6353591160220995,
|
| 2078 |
+
"grad_norm": 0.7182799104547218,
|
| 2079 |
+
"learning_rate": 5.0965593450108495e-06,
|
| 2080 |
+
"loss": 0.6172,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.6408839779005526,
|
| 2085 |
+
"grad_norm": 0.6463166442166366,
|
| 2086 |
+
"learning_rate": 5.064375119969491e-06,
|
| 2087 |
+
"loss": 0.6075,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.6464088397790055,
|
| 2092 |
+
"grad_norm": 0.7000976763577735,
|
| 2093 |
+
"learning_rate": 5.03218822698448e-06,
|
| 2094 |
+
"loss": 0.6416,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.6519337016574585,
|
| 2099 |
+
"grad_norm": 0.7020061467617188,
|
| 2100 |
+
"learning_rate": 5e-06,
|
| 2101 |
+
"loss": 0.5947,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.6574585635359116,
|
| 2106 |
+
"grad_norm": 0.7488808415617535,
|
| 2107 |
+
"learning_rate": 4.967811773015521e-06,
|
| 2108 |
+
"loss": 0.5809,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.6629834254143647,
|
| 2113 |
+
"grad_norm": 0.634571743970242,
|
| 2114 |
+
"learning_rate": 4.93562488003051e-06,
|
| 2115 |
+
"loss": 0.5944,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.6685082872928176,
|
| 2120 |
+
"grad_norm": 0.6445574283924204,
|
| 2121 |
+
"learning_rate": 4.90344065498915e-06,
|
| 2122 |
+
"loss": 0.5984,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.6740331491712708,
|
| 2127 |
+
"grad_norm": 0.7137775145837433,
|
| 2128 |
+
"learning_rate": 4.871260431725058e-06,
|
| 2129 |
+
"loss": 0.5448,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.679558011049724,
|
| 2134 |
+
"grad_norm": 0.6620727258550688,
|
| 2135 |
+
"learning_rate": 4.8390855439059955e-06,
|
| 2136 |
+
"loss": 0.5916,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.6850828729281768,
|
| 2141 |
+
"grad_norm": 0.648075981508642,
|
| 2142 |
+
"learning_rate": 4.806917324978608e-06,
|
| 2143 |
+
"loss": 0.5546,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.6906077348066297,
|
| 2148 |
+
"grad_norm": 0.7077774255913108,
|
| 2149 |
+
"learning_rate": 4.774757108113156e-06,
|
| 2150 |
+
"loss": 0.5546,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.6961325966850829,
|
| 2155 |
+
"grad_norm": 0.7237233387785816,
|
| 2156 |
+
"learning_rate": 4.742606226148268e-06,
|
| 2157 |
+
"loss": 0.6898,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.701657458563536,
|
| 2162 |
+
"grad_norm": 0.6284936804624925,
|
| 2163 |
+
"learning_rate": 4.710466011535695e-06,
|
| 2164 |
+
"loss": 0.6397,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.707182320441989,
|
| 2169 |
+
"grad_norm": 0.7927972591279655,
|
| 2170 |
+
"learning_rate": 4.678337796285093e-06,
|
| 2171 |
+
"loss": 0.6436,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.7127071823204418,
|
| 2176 |
+
"grad_norm": 0.6592299730654411,
|
| 2177 |
+
"learning_rate": 4.6462229119088234e-06,
|
| 2178 |
+
"loss": 0.5714,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.7182320441988952,
|
| 2183 |
+
"grad_norm": 0.6876331470178856,
|
| 2184 |
+
"learning_rate": 4.614122689366769e-06,
|
| 2185 |
+
"loss": 0.6147,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.723756906077348,
|
| 2190 |
+
"grad_norm": 0.6820420879873159,
|
| 2191 |
+
"learning_rate": 4.582038459011165e-06,
|
| 2192 |
+
"loss": 0.5625,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.729281767955801,
|
| 2197 |
+
"grad_norm": 0.7107222428969042,
|
| 2198 |
+
"learning_rate": 4.549971550531474e-06,
|
| 2199 |
+
"loss": 0.6362,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 1.7348066298342542,
|
| 2204 |
+
"grad_norm": 0.6991332889693773,
|
| 2205 |
+
"learning_rate": 4.51792329289928e-06,
|
| 2206 |
+
"loss": 0.6662,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 1.7403314917127073,
|
| 2211 |
+
"grad_norm": 0.6509307723816805,
|
| 2212 |
+
"learning_rate": 4.485895014313198e-06,
|
| 2213 |
+
"loss": 0.6239,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.7458563535911602,
|
| 2218 |
+
"grad_norm": 0.6475315801384613,
|
| 2219 |
+
"learning_rate": 4.453888042143847e-06,
|
| 2220 |
+
"loss": 0.6175,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 1.7513812154696131,
|
| 2225 |
+
"grad_norm": 0.6737553368323486,
|
| 2226 |
+
"learning_rate": 4.421903702878822e-06,
|
| 2227 |
+
"loss": 0.5807,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 1.7569060773480663,
|
| 2232 |
+
"grad_norm": 0.6579280198374517,
|
| 2233 |
+
"learning_rate": 4.389943322067728e-06,
|
| 2234 |
+
"loss": 0.5769,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 1.7624309392265194,
|
| 2239 |
+
"grad_norm": 0.6747867888004441,
|
| 2240 |
+
"learning_rate": 4.358008224267245e-06,
|
| 2241 |
+
"loss": 0.5521,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 1.7679558011049723,
|
| 2246 |
+
"grad_norm": 0.5916747700224341,
|
| 2247 |
+
"learning_rate": 4.326099732986231e-06,
|
| 2248 |
+
"loss": 0.533,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 1.7734806629834254,
|
| 2253 |
+
"grad_norm": 0.6766138160854878,
|
| 2254 |
+
"learning_rate": 4.29421917063087e-06,
|
| 2255 |
+
"loss": 0.6057,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 1.7790055248618786,
|
| 2260 |
+
"grad_norm": 0.6880698365575919,
|
| 2261 |
+
"learning_rate": 4.262367858449867e-06,
|
| 2262 |
+
"loss": 0.6024,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 1.7845303867403315,
|
| 2267 |
+
"grad_norm": 0.6506755980460356,
|
| 2268 |
+
"learning_rate": 4.230547116479691e-06,
|
| 2269 |
+
"loss": 0.5889,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 1.7900552486187844,
|
| 2274 |
+
"grad_norm": 0.6597664588077232,
|
| 2275 |
+
"learning_rate": 4.1987582634898724e-06,
|
| 2276 |
+
"loss": 0.5664,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 1.7955801104972375,
|
| 2281 |
+
"grad_norm": 0.6385623465686507,
|
| 2282 |
+
"learning_rate": 4.167002616928341e-06,
|
| 2283 |
+
"loss": 0.5943,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 1.8011049723756907,
|
| 2288 |
+
"grad_norm": 0.6967677614778646,
|
| 2289 |
+
"learning_rate": 4.135281492866826e-06,
|
| 2290 |
+
"loss": 0.6442,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 1.8066298342541436,
|
| 2295 |
+
"grad_norm": 0.6482473642073888,
|
| 2296 |
+
"learning_rate": 4.103596205946323e-06,
|
| 2297 |
+
"loss": 0.6201,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 1.8121546961325967,
|
| 2302 |
+
"grad_norm": 0.7193129213261211,
|
| 2303 |
+
"learning_rate": 4.0719480693225964e-06,
|
| 2304 |
+
"loss": 0.6096,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 1.8176795580110499,
|
| 2309 |
+
"grad_norm": 0.6888287876327789,
|
| 2310 |
+
"learning_rate": 4.040338394611772e-06,
|
| 2311 |
+
"loss": 0.6086,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 1.8232044198895028,
|
| 2316 |
+
"grad_norm": 0.6553298757478724,
|
| 2317 |
+
"learning_rate": 4.0087684918359646e-06,
|
| 2318 |
+
"loss": 0.6059,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 1.8287292817679557,
|
| 2323 |
+
"grad_norm": 0.6945457240360784,
|
| 2324 |
+
"learning_rate": 3.977239669368998e-06,
|
| 2325 |
+
"loss": 0.6322,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 1.8342541436464088,
|
| 2330 |
+
"grad_norm": 0.7470607646196792,
|
| 2331 |
+
"learning_rate": 3.945753233882168e-06,
|
| 2332 |
+
"loss": 0.6203,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 1.839779005524862,
|
| 2337 |
+
"grad_norm": 0.6675969015071959,
|
| 2338 |
+
"learning_rate": 3.9143104902901085e-06,
|
| 2339 |
+
"loss": 0.6047,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 1.8453038674033149,
|
| 2344 |
+
"grad_norm": 0.631838443419436,
|
| 2345 |
+
"learning_rate": 3.882912741696688e-06,
|
| 2346 |
+
"loss": 0.5619,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 1.850828729281768,
|
| 2351 |
+
"grad_norm": 0.6921273737693909,
|
| 2352 |
+
"learning_rate": 3.851561289341023e-06,
|
| 2353 |
+
"loss": 0.5852,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.8563535911602211,
|
| 2358 |
+
"grad_norm": 0.6212122428108089,
|
| 2359 |
+
"learning_rate": 3.820257432543539e-06,
|
| 2360 |
+
"loss": 0.5631,
|
| 2361 |
+
"step": 336
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 1.861878453038674,
|
| 2365 |
+
"grad_norm": 0.7555498667849819,
|
| 2366 |
+
"learning_rate": 3.789002468652121e-06,
|
| 2367 |
+
"loss": 0.6727,
|
| 2368 |
+
"step": 337
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 1.867403314917127,
|
| 2372 |
+
"grad_norm": 0.6679491834699562,
|
| 2373 |
+
"learning_rate": 3.7577976929883608e-06,
|
| 2374 |
+
"loss": 0.5829,
|
| 2375 |
+
"step": 338
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 1.87292817679558,
|
| 2379 |
+
"grad_norm": 0.7841296013368897,
|
| 2380 |
+
"learning_rate": 3.726644398793857e-06,
|
| 2381 |
+
"loss": 0.6562,
|
| 2382 |
+
"step": 339
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 1.8784530386740332,
|
| 2386 |
+
"grad_norm": 0.6836490585487593,
|
| 2387 |
+
"learning_rate": 3.695543877176626e-06,
|
| 2388 |
+
"loss": 0.6354,
|
| 2389 |
+
"step": 340
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 1.8839779005524862,
|
| 2393 |
+
"grad_norm": 0.6394642182719062,
|
| 2394 |
+
"learning_rate": 3.6644974170575907e-06,
|
| 2395 |
+
"loss": 0.6078,
|
| 2396 |
+
"step": 341
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 1.889502762430939,
|
| 2400 |
+
"grad_norm": 0.7143267899941073,
|
| 2401 |
+
"learning_rate": 3.6335063051171725e-06,
|
| 2402 |
+
"loss": 0.6029,
|
| 2403 |
+
"step": 342
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 1.8950276243093924,
|
| 2407 |
+
"grad_norm": 0.6909108022068383,
|
| 2408 |
+
"learning_rate": 3.6025718257419532e-06,
|
| 2409 |
+
"loss": 0.6233,
|
| 2410 |
+
"step": 343
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 1.9005524861878453,
|
| 2414 |
+
"grad_norm": 0.6329351448339191,
|
| 2415 |
+
"learning_rate": 3.5716952609714517e-06,
|
| 2416 |
+
"loss": 0.5878,
|
| 2417 |
+
"step": 344
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 1.9060773480662982,
|
| 2421 |
+
"grad_norm": 0.6478503333940434,
|
| 2422 |
+
"learning_rate": 3.540877890444989e-06,
|
| 2423 |
+
"loss": 0.5693,
|
| 2424 |
+
"step": 345
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 1.9116022099447514,
|
| 2428 |
+
"grad_norm": 0.676681543424856,
|
| 2429 |
+
"learning_rate": 3.5101209913486655e-06,
|
| 2430 |
+
"loss": 0.5788,
|
| 2431 |
+
"step": 346
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 1.9171270718232045,
|
| 2435 |
+
"grad_norm": 0.6431181230720638,
|
| 2436 |
+
"learning_rate": 3.4794258383624115e-06,
|
| 2437 |
+
"loss": 0.6159,
|
| 2438 |
+
"step": 347
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 1.9226519337016574,
|
| 2442 |
+
"grad_norm": 0.6037104641827318,
|
| 2443 |
+
"learning_rate": 3.448793703607175e-06,
|
| 2444 |
+
"loss": 0.5596,
|
| 2445 |
+
"step": 348
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 1.9281767955801103,
|
| 2449 |
+
"grad_norm": 0.6475020350302072,
|
| 2450 |
+
"learning_rate": 3.4182258565921933e-06,
|
| 2451 |
+
"loss": 0.6464,
|
| 2452 |
+
"step": 349
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 1.9337016574585635,
|
| 2456 |
+
"grad_norm": 0.6509624192770844,
|
| 2457 |
+
"learning_rate": 3.3877235641623797e-06,
|
| 2458 |
+
"loss": 0.5798,
|
| 2459 |
+
"step": 350
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 1.9392265193370166,
|
| 2463 |
+
"grad_norm": 0.73517544137987,
|
| 2464 |
+
"learning_rate": 3.3572880904458267e-06,
|
| 2465 |
+
"loss": 0.5513,
|
| 2466 |
+
"step": 351
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 1.9447513812154695,
|
| 2470 |
+
"grad_norm": 0.693346997717625,
|
| 2471 |
+
"learning_rate": 3.32692069680141e-06,
|
| 2472 |
+
"loss": 0.6178,
|
| 2473 |
+
"step": 352
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 1.9502762430939227,
|
| 2477 |
+
"grad_norm": 0.6108811315736592,
|
| 2478 |
+
"learning_rate": 3.2966226417665125e-06,
|
| 2479 |
+
"loss": 0.6236,
|
| 2480 |
+
"step": 353
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 1.9558011049723758,
|
| 2484 |
+
"grad_norm": 0.629537696210223,
|
| 2485 |
+
"learning_rate": 3.2663951810048683e-06,
|
| 2486 |
+
"loss": 0.6122,
|
| 2487 |
+
"step": 354
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 1.9613259668508287,
|
| 2491 |
+
"grad_norm": 0.6789659150656049,
|
| 2492 |
+
"learning_rate": 3.236239567254526e-06,
|
| 2493 |
+
"loss": 0.6318,
|
| 2494 |
+
"step": 355
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 1.9668508287292816,
|
| 2498 |
+
"grad_norm": 0.6281193326590523,
|
| 2499 |
+
"learning_rate": 3.206157050275927e-06,
|
| 2500 |
+
"loss": 0.5859,
|
| 2501 |
+
"step": 356
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 1.9723756906077348,
|
| 2505 |
+
"grad_norm": 0.6576491463900354,
|
| 2506 |
+
"learning_rate": 3.176148876800109e-06,
|
| 2507 |
+
"loss": 0.5849,
|
| 2508 |
+
"step": 357
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 1.977900552486188,
|
| 2512 |
+
"grad_norm": 0.6853036340913029,
|
| 2513 |
+
"learning_rate": 3.1462162904770376e-06,
|
| 2514 |
+
"loss": 0.5779,
|
| 2515 |
+
"step": 358
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 1.9834254143646408,
|
| 2519 |
+
"grad_norm": 0.6363463477287988,
|
| 2520 |
+
"learning_rate": 3.116360531824074e-06,
|
| 2521 |
+
"loss": 0.5699,
|
| 2522 |
+
"step": 359
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 1.988950276243094,
|
| 2526 |
+
"grad_norm": 0.6709331445271008,
|
| 2527 |
+
"learning_rate": 3.0865828381745515e-06,
|
| 2528 |
+
"loss": 0.5765,
|
| 2529 |
+
"step": 360
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 1.994475138121547,
|
| 2533 |
+
"grad_norm": 0.6288565179176786,
|
| 2534 |
+
"learning_rate": 3.056884443626499e-06,
|
| 2535 |
+
"loss": 0.5679,
|
| 2536 |
+
"step": 361
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 2.0,
|
| 2540 |
+
"grad_norm": 0.6979469101641466,
|
| 2541 |
+
"learning_rate": 3.027266578991497e-06,
|
| 2542 |
+
"loss": 0.6038,
|
| 2543 |
+
"step": 362
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 2.005524861878453,
|
| 2547 |
+
"grad_norm": 0.6857162137141414,
|
| 2548 |
+
"learning_rate": 2.997730471743667e-06,
|
| 2549 |
+
"loss": 0.6094,
|
| 2550 |
+
"step": 363
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 2.0110497237569063,
|
| 2554 |
+
"grad_norm": 0.6086171132783301,
|
| 2555 |
+
"learning_rate": 2.9682773459688087e-06,
|
| 2556 |
+
"loss": 0.4948,
|
| 2557 |
+
"step": 364
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 2.016574585635359,
|
| 2561 |
+
"grad_norm": 0.6681480376436151,
|
| 2562 |
+
"learning_rate": 2.9389084223136523e-06,
|
| 2563 |
+
"loss": 0.5459,
|
| 2564 |
+
"step": 365
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 2.022099447513812,
|
| 2568 |
+
"grad_norm": 0.593654083071827,
|
| 2569 |
+
"learning_rate": 2.9096249179352833e-06,
|
| 2570 |
+
"loss": 0.5109,
|
| 2571 |
+
"step": 366
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 2.027624309392265,
|
| 2575 |
+
"grad_norm": 0.7007646517763502,
|
| 2576 |
+
"learning_rate": 2.880428046450697e-06,
|
| 2577 |
+
"loss": 0.5265,
|
| 2578 |
+
"step": 367
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 2.0331491712707184,
|
| 2582 |
+
"grad_norm": 0.702650158812983,
|
| 2583 |
+
"learning_rate": 2.8513190178865004e-06,
|
| 2584 |
+
"loss": 0.5257,
|
| 2585 |
+
"step": 368
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 2.0386740331491713,
|
| 2589 |
+
"grad_norm": 0.6531178861723401,
|
| 2590 |
+
"learning_rate": 2.822299038628762e-06,
|
| 2591 |
+
"loss": 0.5403,
|
| 2592 |
+
"step": 369
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 2.044198895027624,
|
| 2596 |
+
"grad_norm": 0.6472401575778369,
|
| 2597 |
+
"learning_rate": 2.793369311373021e-06,
|
| 2598 |
+
"loss": 0.5365,
|
| 2599 |
+
"step": 370
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 2.0497237569060776,
|
| 2603 |
+
"grad_norm": 0.6641615455285143,
|
| 2604 |
+
"learning_rate": 2.7645310350744296e-06,
|
| 2605 |
+
"loss": 0.5952,
|
| 2606 |
+
"step": 371
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 2.0552486187845305,
|
| 2610 |
+
"grad_norm": 0.7123204501299103,
|
| 2611 |
+
"learning_rate": 2.7357854048980893e-06,
|
| 2612 |
+
"loss": 0.5631,
|
| 2613 |
+
"step": 372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 2.0607734806629834,
|
| 2617 |
+
"grad_norm": 0.6900539716574728,
|
| 2618 |
+
"learning_rate": 2.7071336121694856e-06,
|
| 2619 |
+
"loss": 0.5452,
|
| 2620 |
+
"step": 373
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 2.0662983425414363,
|
| 2624 |
+
"grad_norm": 0.7021705227314888,
|
| 2625 |
+
"learning_rate": 2.6785768443251437e-06,
|
| 2626 |
+
"loss": 0.5436,
|
| 2627 |
+
"step": 374
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 2.0718232044198897,
|
| 2631 |
+
"grad_norm": 0.7605695654764374,
|
| 2632 |
+
"learning_rate": 2.6501162848634023e-06,
|
| 2633 |
+
"loss": 0.5488,
|
| 2634 |
+
"step": 375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 2.0773480662983426,
|
| 2638 |
+
"grad_norm": 0.683125655831491,
|
| 2639 |
+
"learning_rate": 2.621753113295361e-06,
|
| 2640 |
+
"loss": 0.5851,
|
| 2641 |
+
"step": 376
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 2.0828729281767955,
|
| 2645 |
+
"grad_norm": 0.6551843848513452,
|
| 2646 |
+
"learning_rate": 2.5934885050960183e-06,
|
| 2647 |
+
"loss": 0.5096,
|
| 2648 |
+
"step": 377
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 2.0883977900552484,
|
| 2652 |
+
"grad_norm": 0.7056721518164418,
|
| 2653 |
+
"learning_rate": 2.565323631655532e-06,
|
| 2654 |
+
"loss": 0.5273,
|
| 2655 |
+
"step": 378
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 2.0939226519337018,
|
| 2659 |
+
"grad_norm": 0.6611500614916435,
|
| 2660 |
+
"learning_rate": 2.537259660230679e-06,
|
| 2661 |
+
"loss": 0.5454,
|
| 2662 |
+
"step": 379
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 2.0994475138121547,
|
| 2666 |
+
"grad_norm": 0.7019525646170253,
|
| 2667 |
+
"learning_rate": 2.5092977538964887e-06,
|
| 2668 |
+
"loss": 0.5911,
|
| 2669 |
+
"step": 380
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 2.1049723756906076,
|
| 2673 |
+
"grad_norm": 0.6472748593975306,
|
| 2674 |
+
"learning_rate": 2.4814390714980325e-06,
|
| 2675 |
+
"loss": 0.5211,
|
| 2676 |
+
"step": 381
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 2.110497237569061,
|
| 2680 |
+
"grad_norm": 0.7243217306106386,
|
| 2681 |
+
"learning_rate": 2.4536847676023995e-06,
|
| 2682 |
+
"loss": 0.5731,
|
| 2683 |
+
"step": 382
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 2.116022099447514,
|
| 2687 |
+
"grad_norm": 0.6881568022419648,
|
| 2688 |
+
"learning_rate": 2.426035992450848e-06,
|
| 2689 |
+
"loss": 0.4937,
|
| 2690 |
+
"step": 383
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 2.1215469613259668,
|
| 2694 |
+
"grad_norm": 0.675968032373875,
|
| 2695 |
+
"learning_rate": 2.398493891911127e-06,
|
| 2696 |
+
"loss": 0.5293,
|
| 2697 |
+
"step": 384
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 2.12707182320442,
|
| 2701 |
+
"grad_norm": 0.6793280674446409,
|
| 2702 |
+
"learning_rate": 2.3710596074300045e-06,
|
| 2703 |
+
"loss": 0.5502,
|
| 2704 |
+
"step": 385
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 2.132596685082873,
|
| 2708 |
+
"grad_norm": 0.6827900429979371,
|
| 2709 |
+
"learning_rate": 2.3437342759859472e-06,
|
| 2710 |
+
"loss": 0.5774,
|
| 2711 |
+
"step": 386
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 2.138121546961326,
|
| 2715 |
+
"grad_norm": 0.6299741302424408,
|
| 2716 |
+
"learning_rate": 2.316519030041998e-06,
|
| 2717 |
+
"loss": 0.5355,
|
| 2718 |
+
"step": 387
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 2.143646408839779,
|
| 2722 |
+
"grad_norm": 0.679310688963614,
|
| 2723 |
+
"learning_rate": 2.289414997498856e-06,
|
| 2724 |
+
"loss": 0.579,
|
| 2725 |
+
"step": 388
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 2.149171270718232,
|
| 2729 |
+
"grad_norm": 0.6255767903887023,
|
| 2730 |
+
"learning_rate": 2.2624233016481224e-06,
|
| 2731 |
+
"loss": 0.5316,
|
| 2732 |
+
"step": 389
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 2.154696132596685,
|
| 2736 |
+
"grad_norm": 0.6592300712497258,
|
| 2737 |
+
"learning_rate": 2.235545061125748e-06,
|
| 2738 |
+
"loss": 0.5532,
|
| 2739 |
+
"step": 390
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.160220994475138,
|
| 2743 |
+
"grad_norm": 0.6610713391367827,
|
| 2744 |
+
"learning_rate": 2.2087813898656775e-06,
|
| 2745 |
+
"loss": 0.507,
|
| 2746 |
+
"step": 391
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.165745856353591,
|
| 2750 |
+
"grad_norm": 0.6350291188218904,
|
| 2751 |
+
"learning_rate": 2.182133397053675e-06,
|
| 2752 |
+
"loss": 0.5256,
|
| 2753 |
+
"step": 392
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 2.1712707182320443,
|
| 2757 |
+
"grad_norm": 0.7851921217380164,
|
| 2758 |
+
"learning_rate": 2.1556021870813653e-06,
|
| 2759 |
+
"loss": 0.5521,
|
| 2760 |
+
"step": 393
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 2.1767955801104972,
|
| 2764 |
+
"grad_norm": 0.6866503114131093,
|
| 2765 |
+
"learning_rate": 2.129188859500459e-06,
|
| 2766 |
+
"loss": 0.5784,
|
| 2767 |
+
"step": 394
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 2.18232044198895,
|
| 2771 |
+
"grad_norm": 0.6494728733892837,
|
| 2772 |
+
"learning_rate": 2.102894508977182e-06,
|
| 2773 |
+
"loss": 0.5601,
|
| 2774 |
+
"step": 395
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 2.1878453038674035,
|
| 2778 |
+
"grad_norm": 0.6678705573550681,
|
| 2779 |
+
"learning_rate": 2.0767202252469113e-06,
|
| 2780 |
+
"loss": 0.4986,
|
| 2781 |
+
"step": 396
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 2.1933701657458564,
|
| 2785 |
+
"grad_norm": 0.7160045418734877,
|
| 2786 |
+
"learning_rate": 2.0506670930690074e-06,
|
| 2787 |
+
"loss": 0.5683,
|
| 2788 |
+
"step": 397
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 2.1988950276243093,
|
| 2792 |
+
"grad_norm": 0.6856778789385509,
|
| 2793 |
+
"learning_rate": 2.0247361921818638e-06,
|
| 2794 |
+
"loss": 0.5593,
|
| 2795 |
+
"step": 398
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 2.2044198895027622,
|
| 2799 |
+
"grad_norm": 0.6486089048078473,
|
| 2800 |
+
"learning_rate": 1.9989285972581595e-06,
|
| 2801 |
+
"loss": 0.5482,
|
| 2802 |
+
"step": 399
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 2.2099447513812156,
|
| 2806 |
+
"grad_norm": 0.6894974735994067,
|
| 2807 |
+
"learning_rate": 1.9732453778603104e-06,
|
| 2808 |
+
"loss": 0.5486,
|
| 2809 |
+
"step": 400
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 2.2154696132596685,
|
| 2813 |
+
"grad_norm": 0.6135965995020478,
|
| 2814 |
+
"learning_rate": 1.947687598396154e-06,
|
| 2815 |
+
"loss": 0.523,
|
| 2816 |
+
"step": 401
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 2.2209944751381214,
|
| 2820 |
+
"grad_norm": 0.5824847944758283,
|
| 2821 |
+
"learning_rate": 1.92225631807483e-06,
|
| 2822 |
+
"loss": 0.4781,
|
| 2823 |
+
"step": 402
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 2.226519337016575,
|
| 2827 |
+
"grad_norm": 0.6880197469905236,
|
| 2828 |
+
"learning_rate": 1.896952590862886e-06,
|
| 2829 |
+
"loss": 0.5563,
|
| 2830 |
+
"step": 403
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 2.2320441988950277,
|
| 2834 |
+
"grad_norm": 0.6446697768546276,
|
| 2835 |
+
"learning_rate": 1.8717774654405962e-06,
|
| 2836 |
+
"loss": 0.5182,
|
| 2837 |
+
"step": 404
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 2.2375690607734806,
|
| 2841 |
+
"grad_norm": 0.6867656203180093,
|
| 2842 |
+
"learning_rate": 1.8467319851584952e-06,
|
| 2843 |
+
"loss": 0.5602,
|
| 2844 |
+
"step": 405
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 2.2430939226519335,
|
| 2848 |
+
"grad_norm": 0.6379130888342771,
|
| 2849 |
+
"learning_rate": 1.8218171879941465e-06,
|
| 2850 |
+
"loss": 0.5657,
|
| 2851 |
+
"step": 406
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 2.248618784530387,
|
| 2855 |
+
"grad_norm": 0.6345085950204016,
|
| 2856 |
+
"learning_rate": 1.7970341065091246e-06,
|
| 2857 |
+
"loss": 0.5266,
|
| 2858 |
+
"step": 407
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 2.25414364640884,
|
| 2862 |
+
"grad_norm": 0.6637996504745941,
|
| 2863 |
+
"learning_rate": 1.7723837678062083e-06,
|
| 2864 |
+
"loss": 0.5885,
|
| 2865 |
+
"step": 408
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 2.2596685082872927,
|
| 2869 |
+
"grad_norm": 0.6029850494243252,
|
| 2870 |
+
"learning_rate": 1.7478671934868302e-06,
|
| 2871 |
+
"loss": 0.4729,
|
| 2872 |
+
"step": 409
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 2.265193370165746,
|
| 2876 |
+
"grad_norm": 0.6459276687581147,
|
| 2877 |
+
"learning_rate": 1.7234853996087304e-06,
|
| 2878 |
+
"loss": 0.5752,
|
| 2879 |
+
"step": 410
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 2.270718232044199,
|
| 2883 |
+
"grad_norm": 0.6226965789608703,
|
| 2884 |
+
"learning_rate": 1.699239396643841e-06,
|
| 2885 |
+
"loss": 0.5411,
|
| 2886 |
+
"step": 411
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 2.276243093922652,
|
| 2890 |
+
"grad_norm": 0.6397669563858227,
|
| 2891 |
+
"learning_rate": 1.6751301894364274e-06,
|
| 2892 |
+
"loss": 0.5467,
|
| 2893 |
+
"step": 412
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 2.281767955801105,
|
| 2897 |
+
"grad_norm": 0.6608828543106198,
|
| 2898 |
+
"learning_rate": 1.6511587771614208e-06,
|
| 2899 |
+
"loss": 0.5103,
|
| 2900 |
+
"step": 413
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 2.287292817679558,
|
| 2904 |
+
"grad_norm": 0.6785181930874952,
|
| 2905 |
+
"learning_rate": 1.6273261532830242e-06,
|
| 2906 |
+
"loss": 0.5667,
|
| 2907 |
+
"step": 414
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 2.292817679558011,
|
| 2911 |
+
"grad_norm": 0.6387931680506953,
|
| 2912 |
+
"learning_rate": 1.6036333055135345e-06,
|
| 2913 |
+
"loss": 0.5469,
|
| 2914 |
+
"step": 415
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 2.298342541436464,
|
| 2918 |
+
"grad_norm": 0.6325771066839061,
|
| 2919 |
+
"learning_rate": 1.5800812157724084e-06,
|
| 2920 |
+
"loss": 0.4923,
|
| 2921 |
+
"step": 416
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 2.303867403314917,
|
| 2925 |
+
"grad_norm": 0.6382423549193763,
|
| 2926 |
+
"learning_rate": 1.556670860145567e-06,
|
| 2927 |
+
"loss": 0.536,
|
| 2928 |
+
"step": 417
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 2.3093922651933703,
|
| 2932 |
+
"grad_norm": 0.655241299309122,
|
| 2933 |
+
"learning_rate": 1.533403208844947e-06,
|
| 2934 |
+
"loss": 0.5437,
|
| 2935 |
+
"step": 418
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 2.314917127071823,
|
| 2939 |
+
"grad_norm": 0.6805728068716513,
|
| 2940 |
+
"learning_rate": 1.5102792261682813e-06,
|
| 2941 |
+
"loss": 0.5418,
|
| 2942 |
+
"step": 419
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 2.320441988950276,
|
| 2946 |
+
"grad_norm": 0.6836442326534425,
|
| 2947 |
+
"learning_rate": 1.487299870459155e-06,
|
| 2948 |
+
"loss": 0.6096,
|
| 2949 |
+
"step": 420
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 2.3259668508287294,
|
| 2953 |
+
"grad_norm": 0.6284514006381783,
|
| 2954 |
+
"learning_rate": 1.4644660940672628e-06,
|
| 2955 |
+
"loss": 0.534,
|
| 2956 |
+
"step": 421
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 2.3314917127071824,
|
| 2960 |
+
"grad_norm": 0.6642371366553435,
|
| 2961 |
+
"learning_rate": 1.4417788433089596e-06,
|
| 2962 |
+
"loss": 0.5647,
|
| 2963 |
+
"step": 422
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 2.3370165745856353,
|
| 2967 |
+
"grad_norm": 0.6541492771250856,
|
| 2968 |
+
"learning_rate": 1.4192390584280347e-06,
|
| 2969 |
+
"loss": 0.5209,
|
| 2970 |
+
"step": 423
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 2.3425414364640886,
|
| 2974 |
+
"grad_norm": 0.67885347112545,
|
| 2975 |
+
"learning_rate": 1.3968476735567392e-06,
|
| 2976 |
+
"loss": 0.5806,
|
| 2977 |
+
"step": 424
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 2.3480662983425415,
|
| 2981 |
+
"grad_norm": 0.6716876869006629,
|
| 2982 |
+
"learning_rate": 1.3746056166770872e-06,
|
| 2983 |
+
"loss": 0.5247,
|
| 2984 |
+
"step": 425
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 2.3535911602209945,
|
| 2988 |
+
"grad_norm": 0.6934129162480718,
|
| 2989 |
+
"learning_rate": 1.352513809582377e-06,
|
| 2990 |
+
"loss": 0.5466,
|
| 2991 |
+
"step": 426
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 2.3591160220994474,
|
| 2995 |
+
"grad_norm": 0.6400098878071714,
|
| 2996 |
+
"learning_rate": 1.330573167839005e-06,
|
| 2997 |
+
"loss": 0.4947,
|
| 2998 |
+
"step": 427
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 2.3646408839779007,
|
| 3002 |
+
"grad_norm": 0.6163300040150086,
|
| 3003 |
+
"learning_rate": 1.3087846007485134e-06,
|
| 3004 |
+
"loss": 0.5675,
|
| 3005 |
+
"step": 428
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 2.3701657458563536,
|
| 3009 |
+
"grad_norm": 0.6148189692207581,
|
| 3010 |
+
"learning_rate": 1.2871490113099066e-06,
|
| 3011 |
+
"loss": 0.5162,
|
| 3012 |
+
"step": 429
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 2.3756906077348066,
|
| 3016 |
+
"grad_norm": 0.6296512007771748,
|
| 3017 |
+
"learning_rate": 1.2656672961822285e-06,
|
| 3018 |
+
"loss": 0.5354,
|
| 3019 |
+
"step": 430
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 2.3812154696132595,
|
| 3023 |
+
"grad_norm": 0.6659353506949467,
|
| 3024 |
+
"learning_rate": 1.2443403456474017e-06,
|
| 3025 |
+
"loss": 0.5558,
|
| 3026 |
+
"step": 431
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 2.386740331491713,
|
| 3030 |
+
"grad_norm": 0.6250696714712421,
|
| 3031 |
+
"learning_rate": 1.223169043573325e-06,
|
| 3032 |
+
"loss": 0.5161,
|
| 3033 |
+
"step": 432
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 2.3922651933701657,
|
| 3037 |
+
"grad_norm": 0.628285669477399,
|
| 3038 |
+
"learning_rate": 1.2021542673772584e-06,
|
| 3039 |
+
"loss": 0.5309,
|
| 3040 |
+
"step": 433
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 2.3977900552486187,
|
| 3044 |
+
"grad_norm": 0.6470067569677168,
|
| 3045 |
+
"learning_rate": 1.1812968879894387e-06,
|
| 3046 |
+
"loss": 0.5133,
|
| 3047 |
+
"step": 434
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 2.403314917127072,
|
| 3051 |
+
"grad_norm": 0.6690982254466323,
|
| 3052 |
+
"learning_rate": 1.1605977698170001e-06,
|
| 3053 |
+
"loss": 0.5498,
|
| 3054 |
+
"step": 435
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 2.408839779005525,
|
| 3058 |
+
"grad_norm": 0.6773043112171515,
|
| 3059 |
+
"learning_rate": 1.1400577707081467e-06,
|
| 3060 |
+
"loss": 0.5279,
|
| 3061 |
+
"step": 436
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 2.414364640883978,
|
| 3065 |
+
"grad_norm": 0.6465508208097143,
|
| 3066 |
+
"learning_rate": 1.1196777419165927e-06,
|
| 3067 |
+
"loss": 0.5645,
|
| 3068 |
+
"step": 437
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 2.4198895027624308,
|
| 3072 |
+
"grad_norm": 0.6754843790206556,
|
| 3073 |
+
"learning_rate": 1.0994585280662978e-06,
|
| 3074 |
+
"loss": 0.5709,
|
| 3075 |
+
"step": 438
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 2.425414364640884,
|
| 3079 |
+
"grad_norm": 0.6373867979221823,
|
| 3080 |
+
"learning_rate": 1.0794009671164484e-06,
|
| 3081 |
+
"loss": 0.5301,
|
| 3082 |
+
"step": 439
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 2.430939226519337,
|
| 3086 |
+
"grad_norm": 0.6529002066290224,
|
| 3087 |
+
"learning_rate": 1.0595058903267357e-06,
|
| 3088 |
+
"loss": 0.5283,
|
| 3089 |
+
"step": 440
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 2.43646408839779,
|
| 3093 |
+
"grad_norm": 0.6785490644572046,
|
| 3094 |
+
"learning_rate": 1.0397741222229057e-06,
|
| 3095 |
+
"loss": 0.5368,
|
| 3096 |
+
"step": 441
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 2.441988950276243,
|
| 3100 |
+
"grad_norm": 0.6906247289237696,
|
| 3101 |
+
"learning_rate": 1.0202064805625883e-06,
|
| 3102 |
+
"loss": 0.5811,
|
| 3103 |
+
"step": 442
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 2.447513812154696,
|
| 3107 |
+
"grad_norm": 0.6332990091280457,
|
| 3108 |
+
"learning_rate": 1.0008037763014033e-06,
|
| 3109 |
+
"loss": 0.5324,
|
| 3110 |
+
"step": 443
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 2.453038674033149,
|
| 3114 |
+
"grad_norm": 0.5981606081277429,
|
| 3115 |
+
"learning_rate": 9.815668135593548e-07,
|
| 3116 |
+
"loss": 0.4981,
|
| 3117 |
+
"step": 444
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 2.458563535911602,
|
| 3121 |
+
"grad_norm": 0.6658535935861339,
|
| 3122 |
+
"learning_rate": 9.624963895874995e-07,
|
| 3123 |
+
"loss": 0.5804,
|
| 3124 |
+
"step": 445
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 2.4640883977900554,
|
| 3128 |
+
"grad_norm": 0.6173994326467493,
|
| 3129 |
+
"learning_rate": 9.435932947349169e-07,
|
| 3130 |
+
"loss": 0.5223,
|
| 3131 |
+
"step": 446
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 2.4696132596685083,
|
| 3135 |
+
"grad_norm": 0.6696683287460099,
|
| 3136 |
+
"learning_rate": 9.248583124159438e-07,
|
| 3137 |
+
"loss": 0.5488,
|
| 3138 |
+
"step": 447
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 2.4751381215469612,
|
| 3142 |
+
"grad_norm": 0.681352463917548,
|
| 3143 |
+
"learning_rate": 9.062922190777079e-07,
|
| 3144 |
+
"loss": 0.5377,
|
| 3145 |
+
"step": 448
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 2.4806629834254146,
|
| 3149 |
+
"grad_norm": 0.6413299506586427,
|
| 3150 |
+
"learning_rate": 8.878957841679542e-07,
|
| 3151 |
+
"loss": 0.538,
|
| 3152 |
+
"step": 449
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 2.4861878453038675,
|
| 3156 |
+
"grad_norm": 0.5976825742538746,
|
| 3157 |
+
"learning_rate": 8.696697701031543e-07,
|
| 3158 |
+
"loss": 0.4698,
|
| 3159 |
+
"step": 450
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 2.4917127071823204,
|
| 3163 |
+
"grad_norm": 0.6586286738339465,
|
| 3164 |
+
"learning_rate": 8.516149322369055e-07,
|
| 3165 |
+
"loss": 0.5529,
|
| 3166 |
+
"step": 451
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 2.4972375690607733,
|
| 3170 |
+
"grad_norm": 0.6374084552099051,
|
| 3171 |
+
"learning_rate": 8.337320188286318e-07,
|
| 3172 |
+
"loss": 0.4934,
|
| 3173 |
+
"step": 452
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 2.5027624309392267,
|
| 3177 |
+
"grad_norm": 0.6429007341483025,
|
| 3178 |
+
"learning_rate": 8.160217710125661e-07,
|
| 3179 |
+
"loss": 0.5544,
|
| 3180 |
+
"step": 453
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 2.5082872928176796,
|
| 3184 |
+
"grad_norm": 0.6664059102374921,
|
| 3185 |
+
"learning_rate": 7.984849227670421e-07,
|
| 3186 |
+
"loss": 0.6073,
|
| 3187 |
+
"step": 454
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 2.5138121546961325,
|
| 3191 |
+
"grad_norm": 0.6392153790680253,
|
| 3192 |
+
"learning_rate": 7.811222008840719e-07,
|
| 3193 |
+
"loss": 0.5542,
|
| 3194 |
+
"step": 455
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 2.5193370165745854,
|
| 3198 |
+
"grad_norm": 0.6018857165135849,
|
| 3199 |
+
"learning_rate": 7.639343249392256e-07,
|
| 3200 |
+
"loss": 0.5285,
|
| 3201 |
+
"step": 456
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 2.5248618784530388,
|
| 3205 |
+
"grad_norm": 0.7674240660472489,
|
| 3206 |
+
"learning_rate": 7.469220072618094e-07,
|
| 3207 |
+
"loss": 0.5761,
|
| 3208 |
+
"step": 457
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 2.5303867403314917,
|
| 3212 |
+
"grad_norm": 0.6496289775570502,
|
| 3213 |
+
"learning_rate": 7.300859529053422e-07,
|
| 3214 |
+
"loss": 0.5525,
|
| 3215 |
+
"step": 458
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 2.5359116022099446,
|
| 3219 |
+
"grad_norm": 0.6547899116663247,
|
| 3220 |
+
"learning_rate": 7.13426859618338e-07,
|
| 3221 |
+
"loss": 0.4973,
|
| 3222 |
+
"step": 459
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 2.541436464088398,
|
| 3226 |
+
"grad_norm": 0.6505467220043211,
|
| 3227 |
+
"learning_rate": 6.969454178153923e-07,
|
| 3228 |
+
"loss": 0.5752,
|
| 3229 |
+
"step": 460
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 2.546961325966851,
|
| 3233 |
+
"grad_norm": 0.6735594708393216,
|
| 3234 |
+
"learning_rate": 6.806423105485576e-07,
|
| 3235 |
+
"loss": 0.5679,
|
| 3236 |
+
"step": 461
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 2.552486187845304,
|
| 3240 |
+
"grad_norm": 0.7191676631486709,
|
| 3241 |
+
"learning_rate": 6.645182134790467e-07,
|
| 3242 |
+
"loss": 0.5415,
|
| 3243 |
+
"step": 462
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 2.558011049723757,
|
| 3247 |
+
"grad_norm": 0.6766548740002727,
|
| 3248 |
+
"learning_rate": 6.485737948492237e-07,
|
| 3249 |
+
"loss": 0.5656,
|
| 3250 |
+
"step": 463
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 2.56353591160221,
|
| 3254 |
+
"grad_norm": 0.6610159478158815,
|
| 3255 |
+
"learning_rate": 6.328097154549146e-07,
|
| 3256 |
+
"loss": 0.576,
|
| 3257 |
+
"step": 464
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 2.569060773480663,
|
| 3261 |
+
"grad_norm": 0.6227047055678046,
|
| 3262 |
+
"learning_rate": 6.172266286180162e-07,
|
| 3263 |
+
"loss": 0.5068,
|
| 3264 |
+
"step": 465
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 2.574585635359116,
|
| 3268 |
+
"grad_norm": 0.6389412833805688,
|
| 3269 |
+
"learning_rate": 6.018251801594232e-07,
|
| 3270 |
+
"loss": 0.5258,
|
| 3271 |
+
"step": 466
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 2.580110497237569,
|
| 3275 |
+
"grad_norm": 0.6232609013170282,
|
| 3276 |
+
"learning_rate": 5.866060083722624e-07,
|
| 3277 |
+
"loss": 0.5355,
|
| 3278 |
+
"step": 467
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 2.585635359116022,
|
| 3282 |
+
"grad_norm": 0.6278311488371855,
|
| 3283 |
+
"learning_rate": 5.715697439954432e-07,
|
| 3284 |
+
"loss": 0.5126,
|
| 3285 |
+
"step": 468
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 2.591160220994475,
|
| 3289 |
+
"grad_norm": 0.6077201096302113,
|
| 3290 |
+
"learning_rate": 5.567170101875074e-07,
|
| 3291 |
+
"loss": 0.4949,
|
| 3292 |
+
"step": 469
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 2.596685082872928,
|
| 3296 |
+
"grad_norm": 0.6686676733895326,
|
| 3297 |
+
"learning_rate": 5.420484225008138e-07,
|
| 3298 |
+
"loss": 0.5645,
|
| 3299 |
+
"step": 470
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 2.6022099447513813,
|
| 3303 |
+
"grad_norm": 0.6427639590105313,
|
| 3304 |
+
"learning_rate": 5.275645888560233e-07,
|
| 3305 |
+
"loss": 0.5939,
|
| 3306 |
+
"step": 471
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 2.6077348066298343,
|
| 3310 |
+
"grad_norm": 0.5974938612500432,
|
| 3311 |
+
"learning_rate": 5.132661095168994e-07,
|
| 3312 |
+
"loss": 0.5061,
|
| 3313 |
+
"step": 472
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 2.613259668508287,
|
| 3317 |
+
"grad_norm": 0.6408484309671157,
|
| 3318 |
+
"learning_rate": 4.991535770654449e-07,
|
| 3319 |
+
"loss": 0.5004,
|
| 3320 |
+
"step": 473
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 2.6187845303867405,
|
| 3324 |
+
"grad_norm": 0.6464185272075329,
|
| 3325 |
+
"learning_rate": 4.852275763773251e-07,
|
| 3326 |
+
"loss": 0.5614,
|
| 3327 |
+
"step": 474
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 2.6243093922651934,
|
| 3331 |
+
"grad_norm": 0.7272955176468657,
|
| 3332 |
+
"learning_rate": 4.71488684597643e-07,
|
| 3333 |
+
"loss": 0.6543,
|
| 3334 |
+
"step": 475
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 2.6298342541436464,
|
| 3338 |
+
"grad_norm": 0.6731985657132716,
|
| 3339 |
+
"learning_rate": 4.57937471117012e-07,
|
| 3340 |
+
"loss": 0.5776,
|
| 3341 |
+
"step": 476
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 2.6353591160220997,
|
| 3345 |
+
"grad_norm": 0.6348396347822451,
|
| 3346 |
+
"learning_rate": 4.445744975479627e-07,
|
| 3347 |
+
"loss": 0.6063,
|
| 3348 |
+
"step": 477
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 2.6408839779005526,
|
| 3352 |
+
"grad_norm": 0.635930709870673,
|
| 3353 |
+
"learning_rate": 4.3140031770166457e-07,
|
| 3354 |
+
"loss": 0.5416,
|
| 3355 |
+
"step": 478
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 2.6464088397790055,
|
| 3359 |
+
"grad_norm": 0.6098205107229787,
|
| 3360 |
+
"learning_rate": 4.184154775649768e-07,
|
| 3361 |
+
"loss": 0.5063,
|
| 3362 |
+
"step": 479
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 2.6519337016574585,
|
| 3366 |
+
"grad_norm": 0.6607556626481141,
|
| 3367 |
+
"learning_rate": 4.0562051527781534e-07,
|
| 3368 |
+
"loss": 0.5875,
|
| 3369 |
+
"step": 480
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 2.6574585635359114,
|
| 3373 |
+
"grad_norm": 0.6324042696562345,
|
| 3374 |
+
"learning_rate": 3.930159611108603e-07,
|
| 3375 |
+
"loss": 0.4783,
|
| 3376 |
+
"step": 481
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 2.6629834254143647,
|
| 3380 |
+
"grad_norm": 0.6938336791108509,
|
| 3381 |
+
"learning_rate": 3.8060233744356634e-07,
|
| 3382 |
+
"loss": 0.5537,
|
| 3383 |
+
"step": 482
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 2.6685082872928176,
|
| 3387 |
+
"grad_norm": 0.6325704993286224,
|
| 3388 |
+
"learning_rate": 3.683801587425251e-07,
|
| 3389 |
+
"loss": 0.5502,
|
| 3390 |
+
"step": 483
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 2.6740331491712706,
|
| 3394 |
+
"grad_norm": 0.6934512585984158,
|
| 3395 |
+
"learning_rate": 3.563499315401386e-07,
|
| 3396 |
+
"loss": 0.5962,
|
| 3397 |
+
"step": 484
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 2.679558011049724,
|
| 3401 |
+
"grad_norm": 0.6128926230516574,
|
| 3402 |
+
"learning_rate": 3.4451215441362264e-07,
|
| 3403 |
+
"loss": 0.5282,
|
| 3404 |
+
"step": 485
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 2.685082872928177,
|
| 3408 |
+
"grad_norm": 0.6812281139244459,
|
| 3409 |
+
"learning_rate": 3.328673179643555e-07,
|
| 3410 |
+
"loss": 0.5655,
|
| 3411 |
+
"step": 486
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 2.6906077348066297,
|
| 3415 |
+
"grad_norm": 0.6773585472582779,
|
| 3416 |
+
"learning_rate": 3.214159047975324e-07,
|
| 3417 |
+
"loss": 0.5818,
|
| 3418 |
+
"step": 487
|
| 3419 |
+
},
|
| 3420 |
+
{
|
| 3421 |
+
"epoch": 2.696132596685083,
|
| 3422 |
+
"grad_norm": 0.6516795165171537,
|
| 3423 |
+
"learning_rate": 3.101583895021731e-07,
|
| 3424 |
+
"loss": 0.5326,
|
| 3425 |
+
"step": 488
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 2.701657458563536,
|
| 3429 |
+
"grad_norm": 0.6662378644824801,
|
| 3430 |
+
"learning_rate": 2.990952386314505e-07,
|
| 3431 |
+
"loss": 0.5417,
|
| 3432 |
+
"step": 489
|
| 3433 |
+
},
|
| 3434 |
+
{
|
| 3435 |
+
"epoch": 2.707182320441989,
|
| 3436 |
+
"grad_norm": 0.6210703639589708,
|
| 3437 |
+
"learning_rate": 2.8822691068335515e-07,
|
| 3438 |
+
"loss": 0.4857,
|
| 3439 |
+
"step": 490
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 2.712707182320442,
|
| 3443 |
+
"grad_norm": 0.6196505032930314,
|
| 3444 |
+
"learning_rate": 2.7755385608169374e-07,
|
| 3445 |
+
"loss": 0.4956,
|
| 3446 |
+
"step": 491
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 2.718232044198895,
|
| 3450 |
+
"grad_norm": 0.713069198760707,
|
| 3451 |
+
"learning_rate": 2.6707651715742075e-07,
|
| 3452 |
+
"loss": 0.5266,
|
| 3453 |
+
"step": 492
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 2.723756906077348,
|
| 3457 |
+
"grad_norm": 0.6649253442646119,
|
| 3458 |
+
"learning_rate": 2.567953281303059e-07,
|
| 3459 |
+
"loss": 0.5354,
|
| 3460 |
+
"step": 493
|
| 3461 |
+
},
|
| 3462 |
+
{
|
| 3463 |
+
"epoch": 2.729281767955801,
|
| 3464 |
+
"grad_norm": 0.6407239217065679,
|
| 3465 |
+
"learning_rate": 2.4671071509094367e-07,
|
| 3466 |
+
"loss": 0.5376,
|
| 3467 |
+
"step": 494
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 2.734806629834254,
|
| 3471 |
+
"grad_norm": 0.6804096600469481,
|
| 3472 |
+
"learning_rate": 2.368230959830875e-07,
|
| 3473 |
+
"loss": 0.6262,
|
| 3474 |
+
"step": 495
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"epoch": 2.7403314917127073,
|
| 3478 |
+
"grad_norm": 0.6396360467624123,
|
| 3479 |
+
"learning_rate": 2.2713288058633321e-07,
|
| 3480 |
+
"loss": 0.5281,
|
| 3481 |
+
"step": 496
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 2.74585635359116,
|
| 3485 |
+
"grad_norm": 0.6476227999392966,
|
| 3486 |
+
"learning_rate": 2.1764047049913528e-07,
|
| 3487 |
+
"loss": 0.5318,
|
| 3488 |
+
"step": 497
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 2.751381215469613,
|
| 3492 |
+
"grad_norm": 0.6122643116968306,
|
| 3493 |
+
"learning_rate": 2.0834625912216133e-07,
|
| 3494 |
+
"loss": 0.4926,
|
| 3495 |
+
"step": 498
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 2.7569060773480665,
|
| 3499 |
+
"grad_norm": 0.6528467839639731,
|
| 3500 |
+
"learning_rate": 1.992506316419912e-07,
|
| 3501 |
+
"loss": 0.546,
|
| 3502 |
+
"step": 499
|
| 3503 |
+
},
|
| 3504 |
+
{
|
| 3505 |
+
"epoch": 2.7624309392265194,
|
| 3506 |
+
"grad_norm": 0.61759278073022,
|
| 3507 |
+
"learning_rate": 1.9035396501515148e-07,
|
| 3508 |
+
"loss": 0.4984,
|
| 3509 |
+
"step": 500
|
| 3510 |
+
},
|
| 3511 |
+
{
|
| 3512 |
+
"epoch": 2.7679558011049723,
|
| 3513 |
+
"grad_norm": 0.6443700794544784,
|
| 3514 |
+
"learning_rate": 1.8165662795249172e-07,
|
| 3515 |
+
"loss": 0.5885,
|
| 3516 |
+
"step": 501
|
| 3517 |
+
},
|
| 3518 |
+
{
|
| 3519 |
+
"epoch": 2.7734806629834257,
|
| 3520 |
+
"grad_norm": 0.6316205180357609,
|
| 3521 |
+
"learning_rate": 1.7315898090390748e-07,
|
| 3522 |
+
"loss": 0.5291,
|
| 3523 |
+
"step": 502
|
| 3524 |
+
},
|
| 3525 |
+
{
|
| 3526 |
+
"epoch": 2.7790055248618786,
|
| 3527 |
+
"grad_norm": 0.6628524099587767,
|
| 3528 |
+
"learning_rate": 1.6486137604339813e-07,
|
| 3529 |
+
"loss": 0.569,
|
| 3530 |
+
"step": 503
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"epoch": 2.7845303867403315,
|
| 3534 |
+
"grad_norm": 0.6149733294537271,
|
| 3535 |
+
"learning_rate": 1.5676415725447424e-07,
|
| 3536 |
+
"loss": 0.4872,
|
| 3537 |
+
"step": 504
|
| 3538 |
+
},
|
| 3539 |
+
{
|
| 3540 |
+
"epoch": 2.7900552486187844,
|
| 3541 |
+
"grad_norm": 0.6199230062873984,
|
| 3542 |
+
"learning_rate": 1.4886766011590449e-07,
|
| 3543 |
+
"loss": 0.5333,
|
| 3544 |
+
"step": 505
|
| 3545 |
+
},
|
| 3546 |
+
{
|
| 3547 |
+
"epoch": 2.7955801104972373,
|
| 3548 |
+
"grad_norm": 0.65667152629127,
|
| 3549 |
+
"learning_rate": 1.4117221188780616e-07,
|
| 3550 |
+
"loss": 0.597,
|
| 3551 |
+
"step": 506
|
| 3552 |
+
},
|
| 3553 |
+
{
|
| 3554 |
+
"epoch": 2.8011049723756907,
|
| 3555 |
+
"grad_norm": 0.6818138783253694,
|
| 3556 |
+
"learning_rate": 1.3367813149808728e-07,
|
| 3557 |
+
"loss": 0.5724,
|
| 3558 |
+
"step": 507
|
| 3559 |
+
},
|
| 3560 |
+
{
|
| 3561 |
+
"epoch": 2.8066298342541436,
|
| 3562 |
+
"grad_norm": 0.6178280944589913,
|
| 3563 |
+
"learning_rate": 1.2638572952922478e-07,
|
| 3564 |
+
"loss": 0.5352,
|
| 3565 |
+
"step": 508
|
| 3566 |
+
},
|
| 3567 |
+
{
|
| 3568 |
+
"epoch": 2.8121546961325965,
|
| 3569 |
+
"grad_norm": 0.6134027399269469,
|
| 3570 |
+
"learning_rate": 1.192953082053927e-07,
|
| 3571 |
+
"loss": 0.5361,
|
| 3572 |
+
"step": 509
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 2.81767955801105,
|
| 3576 |
+
"grad_norm": 0.5711150946348813,
|
| 3577 |
+
"learning_rate": 1.1240716137994045e-07,
|
| 3578 |
+
"loss": 0.4995,
|
| 3579 |
+
"step": 510
|
| 3580 |
+
},
|
| 3581 |
+
{
|
| 3582 |
+
"epoch": 2.8232044198895028,
|
| 3583 |
+
"grad_norm": 0.6559442348032254,
|
| 3584 |
+
"learning_rate": 1.0572157452321097e-07,
|
| 3585 |
+
"loss": 0.5625,
|
| 3586 |
+
"step": 511
|
| 3587 |
+
},
|
| 3588 |
+
{
|
| 3589 |
+
"epoch": 2.8287292817679557,
|
| 3590 |
+
"grad_norm": 0.6552526778451414,
|
| 3591 |
+
"learning_rate": 9.923882471071123e-08,
|
| 3592 |
+
"loss": 0.5439,
|
| 3593 |
+
"step": 512
|
| 3594 |
+
},
|
| 3595 |
+
{
|
| 3596 |
+
"epoch": 2.834254143646409,
|
| 3597 |
+
"grad_norm": 0.6605300263231985,
|
| 3598 |
+
"learning_rate": 9.295918061163034e-08,
|
| 3599 |
+
"loss": 0.5461,
|
| 3600 |
+
"step": 513
|
| 3601 |
+
},
|
| 3602 |
+
{
|
| 3603 |
+
"epoch": 2.839779005524862,
|
| 3604 |
+
"grad_norm": 0.6591460854201797,
|
| 3605 |
+
"learning_rate": 8.688290247770071e-08,
|
| 3606 |
+
"loss": 0.4975,
|
| 3607 |
+
"step": 514
|
| 3608 |
+
},
|
| 3609 |
+
{
|
| 3610 |
+
"epoch": 2.845303867403315,
|
| 3611 |
+
"grad_norm": 0.6367498607019844,
|
| 3612 |
+
"learning_rate": 8.101024213241826e-08,
|
| 3613 |
+
"loss": 0.5556,
|
| 3614 |
+
"step": 515
|
| 3615 |
+
},
|
| 3616 |
+
{
|
| 3617 |
+
"epoch": 2.8508287292817682,
|
| 3618 |
+
"grad_norm": 0.654902042221914,
|
| 3619 |
+
"learning_rate": 7.534144296060142e-08,
|
| 3620 |
+
"loss": 0.5925,
|
| 3621 |
+
"step": 516
|
| 3622 |
+
},
|
| 3623 |
+
{
|
| 3624 |
+
"epoch": 2.856353591160221,
|
| 3625 |
+
"grad_norm": 0.6837595818853758,
|
| 3626 |
+
"learning_rate": 6.987673989830523e-08,
|
| 3627 |
+
"loss": 0.5811,
|
| 3628 |
+
"step": 517
|
| 3629 |
+
},
|
| 3630 |
+
{
|
| 3631 |
+
"epoch": 2.861878453038674,
|
| 3632 |
+
"grad_norm": 0.6227316374587448,
|
| 3633 |
+
"learning_rate": 6.461635942308641e-08,
|
| 3634 |
+
"loss": 0.5371,
|
| 3635 |
+
"step": 518
|
| 3636 |
+
},
|
| 3637 |
+
{
|
| 3638 |
+
"epoch": 2.867403314917127,
|
| 3639 |
+
"grad_norm": 0.6780391903150306,
|
| 3640 |
+
"learning_rate": 5.9560519544614725e-08,
|
| 3641 |
+
"loss": 0.4954,
|
| 3642 |
+
"step": 519
|
| 3643 |
+
},
|
| 3644 |
+
{
|
| 3645 |
+
"epoch": 2.87292817679558,
|
| 3646 |
+
"grad_norm": 0.6322452524518853,
|
| 3647 |
+
"learning_rate": 5.47094297956402e-08,
|
| 3648 |
+
"loss": 0.5109,
|
| 3649 |
+
"step": 520
|
| 3650 |
+
},
|
| 3651 |
+
{
|
| 3652 |
+
"epoch": 2.8784530386740332,
|
| 3653 |
+
"grad_norm": 0.6320105555650557,
|
| 3654 |
+
"learning_rate": 5.0063291223308993e-08,
|
| 3655 |
+
"loss": 0.4752,
|
| 3656 |
+
"step": 521
|
| 3657 |
+
},
|
| 3658 |
+
{
|
| 3659 |
+
"epoch": 2.883977900552486,
|
| 3660 |
+
"grad_norm": 0.6772494967739778,
|
| 3661 |
+
"learning_rate": 4.5622296380828936e-08,
|
| 3662 |
+
"loss": 0.5787,
|
| 3663 |
+
"step": 522
|
| 3664 |
+
},
|
| 3665 |
+
{
|
| 3666 |
+
"epoch": 2.889502762430939,
|
| 3667 |
+
"grad_norm": 0.6123147921965099,
|
| 3668 |
+
"learning_rate": 4.138662931949255e-08,
|
| 3669 |
+
"loss": 0.4779,
|
| 3670 |
+
"step": 523
|
| 3671 |
+
},
|
| 3672 |
+
{
|
| 3673 |
+
"epoch": 2.8950276243093924,
|
| 3674 |
+
"grad_norm": 0.6387696683129898,
|
| 3675 |
+
"learning_rate": 3.7356465581047105e-08,
|
| 3676 |
+
"loss": 0.5329,
|
| 3677 |
+
"step": 524
|
| 3678 |
+
},
|
| 3679 |
+
{
|
| 3680 |
+
"epoch": 2.9005524861878453,
|
| 3681 |
+
"grad_norm": 0.6541159566548991,
|
| 3682 |
+
"learning_rate": 3.353197219041981e-08,
|
| 3683 |
+
"loss": 0.5193,
|
| 3684 |
+
"step": 525
|
| 3685 |
+
},
|
| 3686 |
+
{
|
| 3687 |
+
"epoch": 2.9060773480662982,
|
| 3688 |
+
"grad_norm": 0.6447424767896685,
|
| 3689 |
+
"learning_rate": 2.9913307648797293e-08,
|
| 3690 |
+
"loss": 0.5528,
|
| 3691 |
+
"step": 526
|
| 3692 |
+
},
|
| 3693 |
+
{
|
| 3694 |
+
"epoch": 2.9116022099447516,
|
| 3695 |
+
"grad_norm": 0.6455122275019286,
|
| 3696 |
+
"learning_rate": 2.6500621927054716e-08,
|
| 3697 |
+
"loss": 0.5462,
|
| 3698 |
+
"step": 527
|
| 3699 |
+
},
|
| 3700 |
+
{
|
| 3701 |
+
"epoch": 2.9171270718232045,
|
| 3702 |
+
"grad_norm": 0.6329939876148144,
|
| 3703 |
+
"learning_rate": 2.3294056459541302e-08,
|
| 3704 |
+
"loss": 0.4936,
|
| 3705 |
+
"step": 528
|
| 3706 |
+
},
|
| 3707 |
+
{
|
| 3708 |
+
"epoch": 2.9226519337016574,
|
| 3709 |
+
"grad_norm": 0.6557883836151688,
|
| 3710 |
+
"learning_rate": 2.0293744138219495e-08,
|
| 3711 |
+
"loss": 0.5273,
|
| 3712 |
+
"step": 529
|
| 3713 |
+
},
|
| 3714 |
+
{
|
| 3715 |
+
"epoch": 2.9281767955801103,
|
| 3716 |
+
"grad_norm": 0.6686955747117752,
|
| 3717 |
+
"learning_rate": 1.7499809307154892e-08,
|
| 3718 |
+
"loss": 0.5506,
|
| 3719 |
+
"step": 530
|
| 3720 |
+
},
|
| 3721 |
+
{
|
| 3722 |
+
"epoch": 2.9337016574585633,
|
| 3723 |
+
"grad_norm": 0.5955974502813394,
|
| 3724 |
+
"learning_rate": 1.4912367757366485e-08,
|
| 3725 |
+
"loss": 0.487,
|
| 3726 |
+
"step": 531
|
| 3727 |
+
},
|
| 3728 |
+
{
|
| 3729 |
+
"epoch": 2.9392265193370166,
|
| 3730 |
+
"grad_norm": 0.6114812296017272,
|
| 3731 |
+
"learning_rate": 1.2531526722026067e-08,
|
| 3732 |
+
"loss": 0.4649,
|
| 3733 |
+
"step": 532
|
| 3734 |
+
},
|
| 3735 |
+
{
|
| 3736 |
+
"epoch": 2.9447513812154695,
|
| 3737 |
+
"grad_norm": 0.6612511110875763,
|
| 3738 |
+
"learning_rate": 1.0357384872011767e-08,
|
| 3739 |
+
"loss": 0.5328,
|
| 3740 |
+
"step": 533
|
| 3741 |
+
},
|
| 3742 |
+
{
|
| 3743 |
+
"epoch": 2.9502762430939224,
|
| 3744 |
+
"grad_norm": 0.6280473844471933,
|
| 3745 |
+
"learning_rate": 8.390032311824115e-09,
|
| 3746 |
+
"loss": 0.5157,
|
| 3747 |
+
"step": 534
|
| 3748 |
+
},
|
| 3749 |
+
{
|
| 3750 |
+
"epoch": 2.955801104972376,
|
| 3751 |
+
"grad_norm": 0.6485700698849401,
|
| 3752 |
+
"learning_rate": 6.629550575847355e-09,
|
| 3753 |
+
"loss": 0.5375,
|
| 3754 |
+
"step": 535
|
| 3755 |
+
},
|
| 3756 |
+
{
|
| 3757 |
+
"epoch": 2.9613259668508287,
|
| 3758 |
+
"grad_norm": 0.6621455408098162,
|
| 3759 |
+
"learning_rate": 5.0760126249715935e-09,
|
| 3760 |
+
"loss": 0.6062,
|
| 3761 |
+
"step": 536
|
| 3762 |
+
},
|
| 3763 |
+
{
|
| 3764 |
+
"epoch": 2.9668508287292816,
|
| 3765 |
+
"grad_norm": 0.6340833044767035,
|
| 3766 |
+
"learning_rate": 3.729482843569665e-09,
|
| 3767 |
+
"loss": 0.5398,
|
| 3768 |
+
"step": 537
|
| 3769 |
+
},
|
| 3770 |
+
{
|
| 3771 |
+
"epoch": 2.972375690607735,
|
| 3772 |
+
"grad_norm": 0.6235121401681177,
|
| 3773 |
+
"learning_rate": 2.5900170368281517e-09,
|
| 3774 |
+
"loss": 0.5235,
|
| 3775 |
+
"step": 538
|
| 3776 |
+
},
|
| 3777 |
+
{
|
| 3778 |
+
"epoch": 2.977900552486188,
|
| 3779 |
+
"grad_norm": 0.626406886227414,
|
| 3780 |
+
"learning_rate": 1.657662428434792e-09,
|
| 3781 |
+
"loss": 0.5245,
|
| 3782 |
+
"step": 539
|
| 3783 |
+
},
|
| 3784 |
+
{
|
| 3785 |
+
"epoch": 2.983425414364641,
|
| 3786 |
+
"grad_norm": 0.6517990473785358,
|
| 3787 |
+
"learning_rate": 9.324576586211553e-10,
|
| 3788 |
+
"loss": 0.5615,
|
| 3789 |
+
"step": 540
|
| 3790 |
+
},
|
| 3791 |
+
{
|
| 3792 |
+
"epoch": 2.988950276243094,
|
| 3793 |
+
"grad_norm": 0.6588091394692884,
|
| 3794 |
+
"learning_rate": 4.1443278256170227e-10,
|
| 3795 |
+
"loss": 0.5629,
|
| 3796 |
+
"step": 541
|
| 3797 |
+
},
|
| 3798 |
+
{
|
| 3799 |
+
"epoch": 2.994475138121547,
|
| 3800 |
+
"grad_norm": 0.6095291946882728,
|
| 3801 |
+
"learning_rate": 1.0360926912866831e-10,
|
| 3802 |
+
"loss": 0.4717,
|
| 3803 |
+
"step": 542
|
| 3804 |
+
},
|
| 3805 |
+
{
|
| 3806 |
+
"epoch": 3.0,
|
| 3807 |
+
"grad_norm": 0.6878897999106169,
|
| 3808 |
+
"learning_rate": 0.0,
|
| 3809 |
+
"loss": 0.5853,
|
| 3810 |
+
"step": 543
|
| 3811 |
+
},
|
| 3812 |
{
|
| 3813 |
"epoch": 3.0,
|
| 3814 |
+
"step": 543,
|
| 3815 |
+
"total_flos": 136664820957184.0,
|
| 3816 |
+
"train_loss": 0.613760003727444,
|
| 3817 |
+
"train_runtime": 1147.7371,
|
| 3818 |
+
"train_samples_per_second": 45.3,
|
| 3819 |
+
"train_steps_per_second": 0.473
|
| 3820 |
}
|
| 3821 |
],
|
| 3822 |
+
"logging_steps": 1,
|
| 3823 |
+
"max_steps": 543,
|
| 3824 |
"num_input_tokens_seen": 0,
|
| 3825 |
"num_train_epochs": 3,
|
| 3826 |
"save_steps": 500,
|
|
|
|
| 3836 |
"attributes": {}
|
| 3837 |
}
|
| 3838 |
},
|
| 3839 |
+
"total_flos": 136664820957184.0,
|
| 3840 |
+
"train_batch_size": 3,
|
| 3841 |
"trial_name": null,
|
| 3842 |
"trial_params": null
|
| 3843 |
}
|
training_loss.png
CHANGED
|
|