End of training
Browse files- README.md +5 -0
- all_results.json +10 -10
- eval_results.json +6 -6
- train_results.json +5 -5
- trainer_state.json +2256 -12
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: distilbert-base-uncased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: responsible_iddistilbert-base-uncased
|
| 8 |
results: []
|
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# responsible_iddistilbert-base-uncased
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 3 |
base_model: distilbert-base-uncased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: responsible_iddistilbert-base-uncased
|
| 10 |
results: []
|
|
|
|
| 16 |
# responsible_iddistilbert-base-uncased
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.5066
|
| 21 |
+
- Accuracy: 0.5215
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 3.
|
| 6 |
"eval_samples": 1956,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 17.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 5865,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 501.62,
|
| 3 |
+
"eval_accuracy": 0.5214723926380368,
|
| 4 |
+
"eval_loss": 2.5066423416137695,
|
| 5 |
+
"eval_runtime": 3.4808,
|
| 6 |
"eval_samples": 1956,
|
| 7 |
+
"eval_samples_per_second": 561.937,
|
| 8 |
+
"eval_steps_per_second": 17.812,
|
| 9 |
+
"train_loss": 0.10890851792161509,
|
| 10 |
+
"train_runtime": 10408.3467,
|
| 11 |
"train_samples": 5865,
|
| 12 |
+
"train_samples_per_second": 288.507,
|
| 13 |
+
"train_steps_per_second": 0.148
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 3.
|
| 6 |
"eval_samples": 1956,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 17.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 501.62,
|
| 3 |
+
"eval_accuracy": 0.5214723926380368,
|
| 4 |
+
"eval_loss": 2.5066423416137695,
|
| 5 |
+
"eval_runtime": 3.4808,
|
| 6 |
"eval_samples": 1956,
|
| 7 |
+
"eval_samples_per_second": 561.937,
|
| 8 |
+
"eval_steps_per_second": 17.812
|
| 9 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 5865,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 501.62,
|
| 3 |
+
"train_loss": 0.10890851792161509,
|
| 4 |
+
"train_runtime": 10408.3467,
|
| 5 |
"train_samples": 5865,
|
| 6 |
+
"train_samples_per_second": 288.507,
|
| 7 |
+
"train_steps_per_second": 0.148
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 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,
|
|
@@ -765,20 +765,2264 @@
|
|
| 765 |
"step": 384
|
| 766 |
},
|
| 767 |
{
|
| 768 |
-
"epoch":
|
| 769 |
-
"
|
| 770 |
-
"
|
| 771 |
-
"
|
| 772 |
-
|
| 773 |
-
|
| 774 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 775 |
}
|
| 776 |
],
|
| 777 |
"logging_steps": 500,
|
| 778 |
-
"max_steps":
|
| 779 |
-
"num_train_epochs":
|
| 780 |
"save_steps": 500,
|
| 781 |
-
"total_flos":
|
| 782 |
"trial_name": null,
|
| 783 |
"trial_params": null
|
| 784 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 501.6216216216216,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1536,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 765 |
"step": 384
|
| 766 |
},
|
| 767 |
{
|
| 768 |
+
"epoch": 128.97,
|
| 769 |
+
"learning_rate": 1.4960937500000002e-05,
|
| 770 |
+
"loss": 0.8564,
|
| 771 |
+
"step": 387
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 129.95,
|
| 775 |
+
"learning_rate": 1.4921875000000002e-05,
|
| 776 |
+
"loss": 0.8371,
|
| 777 |
+
"step": 390
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 130.92,
|
| 781 |
+
"learning_rate": 1.4882812500000002e-05,
|
| 782 |
+
"loss": 0.8192,
|
| 783 |
+
"step": 393
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 131.89,
|
| 787 |
+
"learning_rate": 1.4843750000000002e-05,
|
| 788 |
+
"loss": 0.7975,
|
| 789 |
+
"step": 396
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 132.86,
|
| 793 |
+
"learning_rate": 1.4804687500000002e-05,
|
| 794 |
+
"loss": 0.7844,
|
| 795 |
+
"step": 399
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 133.84,
|
| 799 |
+
"learning_rate": 1.4765625000000001e-05,
|
| 800 |
+
"loss": 0.7674,
|
| 801 |
+
"step": 402
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 134.81,
|
| 805 |
+
"learning_rate": 1.4726562500000001e-05,
|
| 806 |
+
"loss": 0.7525,
|
| 807 |
+
"step": 405
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 135.78,
|
| 811 |
+
"learning_rate": 1.4687500000000001e-05,
|
| 812 |
+
"loss": 0.7345,
|
| 813 |
+
"step": 408
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 136.76,
|
| 817 |
+
"learning_rate": 1.4648437500000001e-05,
|
| 818 |
+
"loss": 0.7159,
|
| 819 |
+
"step": 411
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 137.73,
|
| 823 |
+
"learning_rate": 1.4609375000000001e-05,
|
| 824 |
+
"loss": 0.7023,
|
| 825 |
+
"step": 414
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 138.7,
|
| 829 |
+
"learning_rate": 1.4570312500000001e-05,
|
| 830 |
+
"loss": 0.6946,
|
| 831 |
+
"step": 417
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 140.0,
|
| 835 |
+
"learning_rate": 1.4518229166666669e-05,
|
| 836 |
+
"loss": 0.5039,
|
| 837 |
+
"step": 421
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 140.97,
|
| 841 |
+
"learning_rate": 1.4479166666666669e-05,
|
| 842 |
+
"loss": 0.6631,
|
| 843 |
+
"step": 424
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 141.95,
|
| 847 |
+
"learning_rate": 1.4440104166666668e-05,
|
| 848 |
+
"loss": 0.6543,
|
| 849 |
+
"step": 427
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 142.92,
|
| 853 |
+
"learning_rate": 1.4401041666666668e-05,
|
| 854 |
+
"loss": 0.6378,
|
| 855 |
+
"step": 430
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 143.89,
|
| 859 |
+
"learning_rate": 1.4361979166666668e-05,
|
| 860 |
+
"loss": 0.6212,
|
| 861 |
+
"step": 433
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 144.86,
|
| 865 |
+
"learning_rate": 1.4322916666666668e-05,
|
| 866 |
+
"loss": 0.6069,
|
| 867 |
+
"step": 436
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 145.84,
|
| 871 |
+
"learning_rate": 1.4283854166666668e-05,
|
| 872 |
+
"loss": 0.5981,
|
| 873 |
+
"step": 439
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 146.81,
|
| 877 |
+
"learning_rate": 1.4244791666666668e-05,
|
| 878 |
+
"loss": 0.5923,
|
| 879 |
+
"step": 442
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 147.78,
|
| 883 |
+
"learning_rate": 1.4205729166666668e-05,
|
| 884 |
+
"loss": 0.5754,
|
| 885 |
+
"step": 445
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 148.76,
|
| 889 |
+
"learning_rate": 1.416666666666667e-05,
|
| 890 |
+
"loss": 0.5653,
|
| 891 |
+
"step": 448
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 149.73,
|
| 895 |
+
"learning_rate": 1.412760416666667e-05,
|
| 896 |
+
"loss": 0.555,
|
| 897 |
+
"step": 451
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 150.7,
|
| 901 |
+
"learning_rate": 1.408854166666667e-05,
|
| 902 |
+
"loss": 0.5408,
|
| 903 |
+
"step": 454
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 152.0,
|
| 907 |
+
"learning_rate": 1.4036458333333333e-05,
|
| 908 |
+
"loss": 0.4004,
|
| 909 |
+
"step": 458
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 152.97,
|
| 913 |
+
"learning_rate": 1.3997395833333333e-05,
|
| 914 |
+
"loss": 0.5188,
|
| 915 |
+
"step": 461
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 153.95,
|
| 919 |
+
"learning_rate": 1.3958333333333333e-05,
|
| 920 |
+
"loss": 0.5146,
|
| 921 |
+
"step": 464
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 154.92,
|
| 925 |
+
"learning_rate": 1.3919270833333333e-05,
|
| 926 |
+
"loss": 0.502,
|
| 927 |
+
"step": 467
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 155.89,
|
| 931 |
+
"learning_rate": 1.3880208333333333e-05,
|
| 932 |
+
"loss": 0.4932,
|
| 933 |
+
"step": 470
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 156.86,
|
| 937 |
+
"learning_rate": 1.3841145833333333e-05,
|
| 938 |
+
"loss": 0.4822,
|
| 939 |
+
"step": 473
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 157.84,
|
| 943 |
+
"learning_rate": 1.3802083333333335e-05,
|
| 944 |
+
"loss": 0.4804,
|
| 945 |
+
"step": 476
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 158.81,
|
| 949 |
+
"learning_rate": 1.3763020833333334e-05,
|
| 950 |
+
"loss": 0.4648,
|
| 951 |
+
"step": 479
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 159.78,
|
| 955 |
+
"learning_rate": 1.3723958333333334e-05,
|
| 956 |
+
"loss": 0.4551,
|
| 957 |
+
"step": 482
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 160.76,
|
| 961 |
+
"learning_rate": 1.3684895833333334e-05,
|
| 962 |
+
"loss": 0.4473,
|
| 963 |
+
"step": 485
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 161.73,
|
| 967 |
+
"learning_rate": 1.3645833333333334e-05,
|
| 968 |
+
"loss": 0.4402,
|
| 969 |
+
"step": 488
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 162.7,
|
| 973 |
+
"learning_rate": 1.3606770833333334e-05,
|
| 974 |
+
"loss": 0.4293,
|
| 975 |
+
"step": 491
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 164.0,
|
| 979 |
+
"learning_rate": 1.3554687500000002e-05,
|
| 980 |
+
"loss": 0.3169,
|
| 981 |
+
"step": 495
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 164.97,
|
| 985 |
+
"learning_rate": 1.3515625000000002e-05,
|
| 986 |
+
"loss": 0.4116,
|
| 987 |
+
"step": 498
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 165.95,
|
| 991 |
+
"learning_rate": 1.3476562500000001e-05,
|
| 992 |
+
"loss": 0.4042,
|
| 993 |
+
"step": 501
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 166.92,
|
| 997 |
+
"learning_rate": 1.3437500000000001e-05,
|
| 998 |
+
"loss": 0.3975,
|
| 999 |
+
"step": 504
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 167.89,
|
| 1003 |
+
"learning_rate": 1.3398437500000001e-05,
|
| 1004 |
+
"loss": 0.379,
|
| 1005 |
+
"step": 507
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 168.86,
|
| 1009 |
+
"learning_rate": 1.3359375000000001e-05,
|
| 1010 |
+
"loss": 0.3789,
|
| 1011 |
+
"step": 510
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 169.84,
|
| 1015 |
+
"learning_rate": 1.3320312500000001e-05,
|
| 1016 |
+
"loss": 0.3669,
|
| 1017 |
+
"step": 513
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 170.81,
|
| 1021 |
+
"learning_rate": 1.3281250000000001e-05,
|
| 1022 |
+
"loss": 0.3595,
|
| 1023 |
+
"step": 516
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 171.78,
|
| 1027 |
+
"learning_rate": 1.3242187500000001e-05,
|
| 1028 |
+
"loss": 0.3508,
|
| 1029 |
+
"step": 519
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 172.76,
|
| 1033 |
+
"learning_rate": 1.3203125e-05,
|
| 1034 |
+
"loss": 0.3415,
|
| 1035 |
+
"step": 522
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 173.73,
|
| 1039 |
+
"learning_rate": 1.31640625e-05,
|
| 1040 |
+
"loss": 0.3297,
|
| 1041 |
+
"step": 525
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 174.7,
|
| 1045 |
+
"learning_rate": 1.3125e-05,
|
| 1046 |
+
"loss": 0.3316,
|
| 1047 |
+
"step": 528
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 176.0,
|
| 1051 |
+
"learning_rate": 1.3072916666666668e-05,
|
| 1052 |
+
"loss": 0.2403,
|
| 1053 |
+
"step": 532
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 176.97,
|
| 1057 |
+
"learning_rate": 1.3033854166666668e-05,
|
| 1058 |
+
"loss": 0.3148,
|
| 1059 |
+
"step": 535
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 177.95,
|
| 1063 |
+
"learning_rate": 1.2994791666666668e-05,
|
| 1064 |
+
"loss": 0.3119,
|
| 1065 |
+
"step": 538
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 178.92,
|
| 1069 |
+
"learning_rate": 1.2955729166666668e-05,
|
| 1070 |
+
"loss": 0.3013,
|
| 1071 |
+
"step": 541
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 179.89,
|
| 1075 |
+
"learning_rate": 1.2916666666666668e-05,
|
| 1076 |
+
"loss": 0.2972,
|
| 1077 |
+
"step": 544
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 180.86,
|
| 1081 |
+
"learning_rate": 1.2877604166666668e-05,
|
| 1082 |
+
"loss": 0.2894,
|
| 1083 |
+
"step": 547
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 181.84,
|
| 1087 |
+
"learning_rate": 1.283854166666667e-05,
|
| 1088 |
+
"loss": 0.2837,
|
| 1089 |
+
"step": 550
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 182.81,
|
| 1093 |
+
"learning_rate": 1.279947916666667e-05,
|
| 1094 |
+
"loss": 0.278,
|
| 1095 |
+
"step": 553
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 183.78,
|
| 1099 |
+
"learning_rate": 1.2760416666666669e-05,
|
| 1100 |
+
"loss": 0.2773,
|
| 1101 |
+
"step": 556
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 184.76,
|
| 1105 |
+
"learning_rate": 1.2721354166666669e-05,
|
| 1106 |
+
"loss": 0.2768,
|
| 1107 |
+
"step": 559
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 185.73,
|
| 1111 |
+
"learning_rate": 1.2682291666666669e-05,
|
| 1112 |
+
"loss": 0.2652,
|
| 1113 |
+
"step": 562
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 186.7,
|
| 1117 |
+
"learning_rate": 1.2643229166666669e-05,
|
| 1118 |
+
"loss": 0.266,
|
| 1119 |
+
"step": 565
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 188.0,
|
| 1123 |
+
"learning_rate": 1.2591145833333333e-05,
|
| 1124 |
+
"loss": 0.1962,
|
| 1125 |
+
"step": 569
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 188.97,
|
| 1129 |
+
"learning_rate": 1.2552083333333333e-05,
|
| 1130 |
+
"loss": 0.259,
|
| 1131 |
+
"step": 572
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 189.95,
|
| 1135 |
+
"learning_rate": 1.2513020833333333e-05,
|
| 1136 |
+
"loss": 0.2516,
|
| 1137 |
+
"step": 575
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 190.92,
|
| 1141 |
+
"learning_rate": 1.2473958333333334e-05,
|
| 1142 |
+
"loss": 0.2501,
|
| 1143 |
+
"step": 578
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 191.89,
|
| 1147 |
+
"learning_rate": 1.2434895833333334e-05,
|
| 1148 |
+
"loss": 0.243,
|
| 1149 |
+
"step": 581
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 192.86,
|
| 1153 |
+
"learning_rate": 1.2395833333333334e-05,
|
| 1154 |
+
"loss": 0.2399,
|
| 1155 |
+
"step": 584
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 193.84,
|
| 1159 |
+
"learning_rate": 1.2356770833333334e-05,
|
| 1160 |
+
"loss": 0.2396,
|
| 1161 |
+
"step": 587
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 194.81,
|
| 1165 |
+
"learning_rate": 1.2317708333333334e-05,
|
| 1166 |
+
"loss": 0.2332,
|
| 1167 |
+
"step": 590
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 195.78,
|
| 1171 |
+
"learning_rate": 1.2278645833333334e-05,
|
| 1172 |
+
"loss": 0.2244,
|
| 1173 |
+
"step": 593
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 196.76,
|
| 1177 |
+
"learning_rate": 1.2239583333333334e-05,
|
| 1178 |
+
"loss": 0.2224,
|
| 1179 |
+
"step": 596
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 197.73,
|
| 1183 |
+
"learning_rate": 1.2200520833333334e-05,
|
| 1184 |
+
"loss": 0.2175,
|
| 1185 |
+
"step": 599
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 198.7,
|
| 1189 |
+
"learning_rate": 1.2161458333333334e-05,
|
| 1190 |
+
"loss": 0.2191,
|
| 1191 |
+
"step": 602
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 200.0,
|
| 1195 |
+
"learning_rate": 1.2109375000000001e-05,
|
| 1196 |
+
"loss": 0.1639,
|
| 1197 |
+
"step": 606
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 200.97,
|
| 1201 |
+
"learning_rate": 1.2070312500000001e-05,
|
| 1202 |
+
"loss": 0.2124,
|
| 1203 |
+
"step": 609
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 201.95,
|
| 1207 |
+
"learning_rate": 1.2031250000000001e-05,
|
| 1208 |
+
"loss": 0.2076,
|
| 1209 |
+
"step": 612
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 202.92,
|
| 1213 |
+
"learning_rate": 1.1992187500000001e-05,
|
| 1214 |
+
"loss": 0.2042,
|
| 1215 |
+
"step": 615
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 203.89,
|
| 1219 |
+
"learning_rate": 1.1953125000000001e-05,
|
| 1220 |
+
"loss": 0.2005,
|
| 1221 |
+
"step": 618
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 204.86,
|
| 1225 |
+
"learning_rate": 1.19140625e-05,
|
| 1226 |
+
"loss": 0.1983,
|
| 1227 |
+
"step": 621
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 205.84,
|
| 1231 |
+
"learning_rate": 1.1875e-05,
|
| 1232 |
+
"loss": 0.194,
|
| 1233 |
+
"step": 624
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 206.81,
|
| 1237 |
+
"learning_rate": 1.18359375e-05,
|
| 1238 |
+
"loss": 0.1901,
|
| 1239 |
+
"step": 627
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 207.78,
|
| 1243 |
+
"learning_rate": 1.1796875e-05,
|
| 1244 |
+
"loss": 0.1886,
|
| 1245 |
+
"step": 630
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 208.76,
|
| 1249 |
+
"learning_rate": 1.17578125e-05,
|
| 1250 |
+
"loss": 0.1817,
|
| 1251 |
+
"step": 633
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 209.73,
|
| 1255 |
+
"learning_rate": 1.171875e-05,
|
| 1256 |
+
"loss": 0.1841,
|
| 1257 |
+
"step": 636
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 210.7,
|
| 1261 |
+
"learning_rate": 1.16796875e-05,
|
| 1262 |
+
"loss": 0.1769,
|
| 1263 |
+
"step": 639
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 212.0,
|
| 1267 |
+
"learning_rate": 1.1627604166666668e-05,
|
| 1268 |
+
"loss": 0.1352,
|
| 1269 |
+
"step": 643
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 212.97,
|
| 1273 |
+
"learning_rate": 1.1588541666666668e-05,
|
| 1274 |
+
"loss": 0.1765,
|
| 1275 |
+
"step": 646
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 213.95,
|
| 1279 |
+
"learning_rate": 1.1549479166666668e-05,
|
| 1280 |
+
"loss": 0.1696,
|
| 1281 |
+
"step": 649
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 214.92,
|
| 1285 |
+
"learning_rate": 1.151041666666667e-05,
|
| 1286 |
+
"loss": 0.1679,
|
| 1287 |
+
"step": 652
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 215.89,
|
| 1291 |
+
"learning_rate": 1.1471354166666669e-05,
|
| 1292 |
+
"loss": 0.1609,
|
| 1293 |
+
"step": 655
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 216.86,
|
| 1297 |
+
"learning_rate": 1.1432291666666669e-05,
|
| 1298 |
+
"loss": 0.1633,
|
| 1299 |
+
"step": 658
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 217.84,
|
| 1303 |
+
"learning_rate": 1.1393229166666669e-05,
|
| 1304 |
+
"loss": 0.1616,
|
| 1305 |
+
"step": 661
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 218.81,
|
| 1309 |
+
"learning_rate": 1.1354166666666669e-05,
|
| 1310 |
+
"loss": 0.1589,
|
| 1311 |
+
"step": 664
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 219.78,
|
| 1315 |
+
"learning_rate": 1.1315104166666669e-05,
|
| 1316 |
+
"loss": 0.158,
|
| 1317 |
+
"step": 667
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 220.76,
|
| 1321 |
+
"learning_rate": 1.1276041666666669e-05,
|
| 1322 |
+
"loss": 0.1544,
|
| 1323 |
+
"step": 670
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 221.73,
|
| 1327 |
+
"learning_rate": 1.1236979166666668e-05,
|
| 1328 |
+
"loss": 0.154,
|
| 1329 |
+
"step": 673
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 222.7,
|
| 1333 |
+
"learning_rate": 1.1197916666666668e-05,
|
| 1334 |
+
"loss": 0.1516,
|
| 1335 |
+
"step": 676
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 224.0,
|
| 1339 |
+
"learning_rate": 1.1145833333333334e-05,
|
| 1340 |
+
"loss": 0.1152,
|
| 1341 |
+
"step": 680
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 224.97,
|
| 1345 |
+
"learning_rate": 1.1106770833333334e-05,
|
| 1346 |
+
"loss": 0.1516,
|
| 1347 |
+
"step": 683
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 225.95,
|
| 1351 |
+
"learning_rate": 1.1067708333333334e-05,
|
| 1352 |
+
"loss": 0.145,
|
| 1353 |
+
"step": 686
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 226.92,
|
| 1357 |
+
"learning_rate": 1.1028645833333334e-05,
|
| 1358 |
+
"loss": 0.1455,
|
| 1359 |
+
"step": 689
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 227.89,
|
| 1363 |
+
"learning_rate": 1.0989583333333334e-05,
|
| 1364 |
+
"loss": 0.1437,
|
| 1365 |
+
"step": 692
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 228.86,
|
| 1369 |
+
"learning_rate": 1.0950520833333334e-05,
|
| 1370 |
+
"loss": 0.1409,
|
| 1371 |
+
"step": 695
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 229.84,
|
| 1375 |
+
"learning_rate": 1.0911458333333334e-05,
|
| 1376 |
+
"loss": 0.1452,
|
| 1377 |
+
"step": 698
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 230.81,
|
| 1381 |
+
"learning_rate": 1.0872395833333334e-05,
|
| 1382 |
+
"loss": 0.1366,
|
| 1383 |
+
"step": 701
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 231.78,
|
| 1387 |
+
"learning_rate": 1.0833333333333334e-05,
|
| 1388 |
+
"loss": 0.1367,
|
| 1389 |
+
"step": 704
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 232.76,
|
| 1393 |
+
"learning_rate": 1.0794270833333333e-05,
|
| 1394 |
+
"loss": 0.1357,
|
| 1395 |
+
"step": 707
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 233.73,
|
| 1399 |
+
"learning_rate": 1.0755208333333333e-05,
|
| 1400 |
+
"loss": 0.1342,
|
| 1401 |
+
"step": 710
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 234.7,
|
| 1405 |
+
"learning_rate": 1.0716145833333333e-05,
|
| 1406 |
+
"loss": 0.1276,
|
| 1407 |
+
"step": 713
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 236.0,
|
| 1411 |
+
"learning_rate": 1.0664062500000001e-05,
|
| 1412 |
+
"loss": 0.0974,
|
| 1413 |
+
"step": 717
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 236.97,
|
| 1417 |
+
"learning_rate": 1.0625e-05,
|
| 1418 |
+
"loss": 0.1325,
|
| 1419 |
+
"step": 720
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 237.95,
|
| 1423 |
+
"learning_rate": 1.05859375e-05,
|
| 1424 |
+
"loss": 0.1266,
|
| 1425 |
+
"step": 723
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 238.92,
|
| 1429 |
+
"learning_rate": 1.0546875e-05,
|
| 1430 |
+
"loss": 0.1237,
|
| 1431 |
+
"step": 726
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 239.89,
|
| 1435 |
+
"learning_rate": 1.05078125e-05,
|
| 1436 |
+
"loss": 0.1258,
|
| 1437 |
+
"step": 729
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 240.86,
|
| 1441 |
+
"learning_rate": 1.046875e-05,
|
| 1442 |
+
"loss": 0.123,
|
| 1443 |
+
"step": 732
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 241.84,
|
| 1447 |
+
"learning_rate": 1.04296875e-05,
|
| 1448 |
+
"loss": 0.1228,
|
| 1449 |
+
"step": 735
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 242.81,
|
| 1453 |
+
"learning_rate": 1.0390625e-05,
|
| 1454 |
+
"loss": 0.12,
|
| 1455 |
+
"step": 738
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 243.78,
|
| 1459 |
+
"learning_rate": 1.03515625e-05,
|
| 1460 |
+
"loss": 0.1174,
|
| 1461 |
+
"step": 741
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 244.76,
|
| 1465 |
+
"learning_rate": 1.0312500000000002e-05,
|
| 1466 |
+
"loss": 0.118,
|
| 1467 |
+
"step": 744
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 245.73,
|
| 1471 |
+
"learning_rate": 1.0273437500000002e-05,
|
| 1472 |
+
"loss": 0.1157,
|
| 1473 |
+
"step": 747
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 246.7,
|
| 1477 |
+
"learning_rate": 1.0234375000000001e-05,
|
| 1478 |
+
"loss": 0.115,
|
| 1479 |
+
"step": 750
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 248.0,
|
| 1483 |
+
"learning_rate": 1.0182291666666667e-05,
|
| 1484 |
+
"loss": 0.0826,
|
| 1485 |
+
"step": 754
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 248.97,
|
| 1489 |
+
"learning_rate": 1.0143229166666669e-05,
|
| 1490 |
+
"loss": 0.1094,
|
| 1491 |
+
"step": 757
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 249.95,
|
| 1495 |
+
"learning_rate": 1.0104166666666669e-05,
|
| 1496 |
+
"loss": 0.1094,
|
| 1497 |
+
"step": 760
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 250.92,
|
| 1501 |
+
"learning_rate": 1.0065104166666669e-05,
|
| 1502 |
+
"loss": 0.111,
|
| 1503 |
+
"step": 763
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 251.89,
|
| 1507 |
+
"learning_rate": 1.0026041666666669e-05,
|
| 1508 |
+
"loss": 0.1056,
|
| 1509 |
+
"step": 766
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 252.86,
|
| 1513 |
+
"learning_rate": 9.986979166666667e-06,
|
| 1514 |
+
"loss": 0.1076,
|
| 1515 |
+
"step": 769
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 253.84,
|
| 1519 |
+
"learning_rate": 9.947916666666667e-06,
|
| 1520 |
+
"loss": 0.1031,
|
| 1521 |
+
"step": 772
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 254.81,
|
| 1525 |
+
"learning_rate": 9.908854166666667e-06,
|
| 1526 |
+
"loss": 0.1084,
|
| 1527 |
+
"step": 775
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 255.78,
|
| 1531 |
+
"learning_rate": 9.869791666666667e-06,
|
| 1532 |
+
"loss": 0.1043,
|
| 1533 |
+
"step": 778
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 256.76,
|
| 1537 |
+
"learning_rate": 9.830729166666666e-06,
|
| 1538 |
+
"loss": 0.0984,
|
| 1539 |
+
"step": 781
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 257.73,
|
| 1543 |
+
"learning_rate": 9.791666666666666e-06,
|
| 1544 |
+
"loss": 0.098,
|
| 1545 |
+
"step": 784
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 258.7,
|
| 1549 |
+
"learning_rate": 9.752604166666666e-06,
|
| 1550 |
+
"loss": 0.1013,
|
| 1551 |
+
"step": 787
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 260.0,
|
| 1555 |
+
"learning_rate": 9.700520833333334e-06,
|
| 1556 |
+
"loss": 0.0743,
|
| 1557 |
+
"step": 791
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 260.97,
|
| 1561 |
+
"learning_rate": 9.661458333333334e-06,
|
| 1562 |
+
"loss": 0.0947,
|
| 1563 |
+
"step": 794
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 261.95,
|
| 1567 |
+
"learning_rate": 9.622395833333334e-06,
|
| 1568 |
+
"loss": 0.0965,
|
| 1569 |
+
"step": 797
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 262.92,
|
| 1573 |
+
"learning_rate": 9.583333333333335e-06,
|
| 1574 |
+
"loss": 0.0947,
|
| 1575 |
+
"step": 800
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 263.89,
|
| 1579 |
+
"learning_rate": 9.544270833333335e-06,
|
| 1580 |
+
"loss": 0.0952,
|
| 1581 |
+
"step": 803
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 264.86,
|
| 1585 |
+
"learning_rate": 9.505208333333335e-06,
|
| 1586 |
+
"loss": 0.0896,
|
| 1587 |
+
"step": 806
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 265.84,
|
| 1591 |
+
"learning_rate": 9.466145833333335e-06,
|
| 1592 |
+
"loss": 0.0891,
|
| 1593 |
+
"step": 809
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 266.81,
|
| 1597 |
+
"learning_rate": 9.427083333333335e-06,
|
| 1598 |
+
"loss": 0.0939,
|
| 1599 |
+
"step": 812
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 267.78,
|
| 1603 |
+
"learning_rate": 9.388020833333335e-06,
|
| 1604 |
+
"loss": 0.0911,
|
| 1605 |
+
"step": 815
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 268.76,
|
| 1609 |
+
"learning_rate": 9.348958333333335e-06,
|
| 1610 |
+
"loss": 0.0882,
|
| 1611 |
+
"step": 818
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 269.73,
|
| 1615 |
+
"learning_rate": 9.309895833333335e-06,
|
| 1616 |
+
"loss": 0.0903,
|
| 1617 |
+
"step": 821
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 270.7,
|
| 1621 |
+
"learning_rate": 9.270833333333334e-06,
|
| 1622 |
+
"loss": 0.0869,
|
| 1623 |
+
"step": 824
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 272.0,
|
| 1627 |
+
"learning_rate": 9.21875e-06,
|
| 1628 |
+
"loss": 0.0664,
|
| 1629 |
+
"step": 828
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 272.97,
|
| 1633 |
+
"learning_rate": 9.1796875e-06,
|
| 1634 |
+
"loss": 0.0868,
|
| 1635 |
+
"step": 831
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 273.95,
|
| 1639 |
+
"learning_rate": 9.140625e-06,
|
| 1640 |
+
"loss": 0.0867,
|
| 1641 |
+
"step": 834
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 274.92,
|
| 1645 |
+
"learning_rate": 9.1015625e-06,
|
| 1646 |
+
"loss": 0.0858,
|
| 1647 |
+
"step": 837
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 275.89,
|
| 1651 |
+
"learning_rate": 9.0625e-06,
|
| 1652 |
+
"loss": 0.0842,
|
| 1653 |
+
"step": 840
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 276.86,
|
| 1657 |
+
"learning_rate": 9.0234375e-06,
|
| 1658 |
+
"loss": 0.0869,
|
| 1659 |
+
"step": 843
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 277.84,
|
| 1663 |
+
"learning_rate": 8.984375000000002e-06,
|
| 1664 |
+
"loss": 0.0803,
|
| 1665 |
+
"step": 846
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 278.81,
|
| 1669 |
+
"learning_rate": 8.945312500000001e-06,
|
| 1670 |
+
"loss": 0.0813,
|
| 1671 |
+
"step": 849
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 279.78,
|
| 1675 |
+
"learning_rate": 8.906250000000001e-06,
|
| 1676 |
+
"loss": 0.084,
|
| 1677 |
+
"step": 852
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 280.76,
|
| 1681 |
+
"learning_rate": 8.867187500000001e-06,
|
| 1682 |
+
"loss": 0.0814,
|
| 1683 |
+
"step": 855
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 281.73,
|
| 1687 |
+
"learning_rate": 8.828125000000001e-06,
|
| 1688 |
+
"loss": 0.0782,
|
| 1689 |
+
"step": 858
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 282.7,
|
| 1693 |
+
"learning_rate": 8.789062500000001e-06,
|
| 1694 |
+
"loss": 0.0803,
|
| 1695 |
+
"step": 861
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 284.0,
|
| 1699 |
+
"learning_rate": 8.736979166666667e-06,
|
| 1700 |
+
"loss": 0.0596,
|
| 1701 |
+
"step": 865
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 284.97,
|
| 1705 |
+
"learning_rate": 8.697916666666667e-06,
|
| 1706 |
+
"loss": 0.0787,
|
| 1707 |
+
"step": 868
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 285.95,
|
| 1711 |
+
"learning_rate": 8.658854166666667e-06,
|
| 1712 |
+
"loss": 0.0748,
|
| 1713 |
+
"step": 871
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 286.92,
|
| 1717 |
+
"learning_rate": 8.619791666666667e-06,
|
| 1718 |
+
"loss": 0.0816,
|
| 1719 |
+
"step": 874
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 287.89,
|
| 1723 |
+
"learning_rate": 8.580729166666667e-06,
|
| 1724 |
+
"loss": 0.0776,
|
| 1725 |
+
"step": 877
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 288.86,
|
| 1729 |
+
"learning_rate": 8.541666666666666e-06,
|
| 1730 |
+
"loss": 0.0749,
|
| 1731 |
+
"step": 880
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 289.84,
|
| 1735 |
+
"learning_rate": 8.502604166666666e-06,
|
| 1736 |
+
"loss": 0.0795,
|
| 1737 |
+
"step": 883
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 290.81,
|
| 1741 |
+
"learning_rate": 8.463541666666666e-06,
|
| 1742 |
+
"loss": 0.075,
|
| 1743 |
+
"step": 886
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 291.78,
|
| 1747 |
+
"learning_rate": 8.424479166666666e-06,
|
| 1748 |
+
"loss": 0.0756,
|
| 1749 |
+
"step": 889
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 292.76,
|
| 1753 |
+
"learning_rate": 8.385416666666668e-06,
|
| 1754 |
+
"loss": 0.0755,
|
| 1755 |
+
"step": 892
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 293.73,
|
| 1759 |
+
"learning_rate": 8.346354166666668e-06,
|
| 1760 |
+
"loss": 0.0721,
|
| 1761 |
+
"step": 895
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 294.7,
|
| 1765 |
+
"learning_rate": 8.307291666666668e-06,
|
| 1766 |
+
"loss": 0.0745,
|
| 1767 |
+
"step": 898
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 296.0,
|
| 1771 |
+
"learning_rate": 8.255208333333335e-06,
|
| 1772 |
+
"loss": 0.0535,
|
| 1773 |
+
"step": 902
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 296.97,
|
| 1777 |
+
"learning_rate": 8.216145833333335e-06,
|
| 1778 |
+
"loss": 0.0743,
|
| 1779 |
+
"step": 905
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 297.95,
|
| 1783 |
+
"learning_rate": 8.177083333333335e-06,
|
| 1784 |
+
"loss": 0.0756,
|
| 1785 |
+
"step": 908
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 298.92,
|
| 1789 |
+
"learning_rate": 8.138020833333335e-06,
|
| 1790 |
+
"loss": 0.0728,
|
| 1791 |
+
"step": 911
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 299.89,
|
| 1795 |
+
"learning_rate": 8.098958333333335e-06,
|
| 1796 |
+
"loss": 0.0744,
|
| 1797 |
+
"step": 914
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 300.86,
|
| 1801 |
+
"learning_rate": 8.059895833333335e-06,
|
| 1802 |
+
"loss": 0.0713,
|
| 1803 |
+
"step": 917
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 301.84,
|
| 1807 |
+
"learning_rate": 8.020833333333335e-06,
|
| 1808 |
+
"loss": 0.0707,
|
| 1809 |
+
"step": 920
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 302.81,
|
| 1813 |
+
"learning_rate": 7.981770833333335e-06,
|
| 1814 |
+
"loss": 0.0715,
|
| 1815 |
+
"step": 923
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 303.78,
|
| 1819 |
+
"learning_rate": 7.942708333333334e-06,
|
| 1820 |
+
"loss": 0.0686,
|
| 1821 |
+
"step": 926
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 304.76,
|
| 1825 |
+
"learning_rate": 7.903645833333334e-06,
|
| 1826 |
+
"loss": 0.0691,
|
| 1827 |
+
"step": 929
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 305.73,
|
| 1831 |
+
"learning_rate": 7.864583333333334e-06,
|
| 1832 |
+
"loss": 0.0682,
|
| 1833 |
+
"step": 932
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 306.7,
|
| 1837 |
+
"learning_rate": 7.825520833333334e-06,
|
| 1838 |
+
"loss": 0.0701,
|
| 1839 |
+
"step": 935
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 308.0,
|
| 1843 |
+
"learning_rate": 7.7734375e-06,
|
| 1844 |
+
"loss": 0.0488,
|
| 1845 |
+
"step": 939
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 308.97,
|
| 1849 |
+
"learning_rate": 7.734375e-06,
|
| 1850 |
+
"loss": 0.0689,
|
| 1851 |
+
"step": 942
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 309.95,
|
| 1855 |
+
"learning_rate": 7.6953125e-06,
|
| 1856 |
+
"loss": 0.0685,
|
| 1857 |
+
"step": 945
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 310.92,
|
| 1861 |
+
"learning_rate": 7.656250000000001e-06,
|
| 1862 |
+
"loss": 0.0688,
|
| 1863 |
+
"step": 948
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 311.89,
|
| 1867 |
+
"learning_rate": 7.6171875000000005e-06,
|
| 1868 |
+
"loss": 0.0685,
|
| 1869 |
+
"step": 951
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 312.86,
|
| 1873 |
+
"learning_rate": 7.578125e-06,
|
| 1874 |
+
"loss": 0.0688,
|
| 1875 |
+
"step": 954
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 313.84,
|
| 1879 |
+
"learning_rate": 7.5390625e-06,
|
| 1880 |
+
"loss": 0.0656,
|
| 1881 |
+
"step": 957
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 314.81,
|
| 1885 |
+
"learning_rate": 7.500000000000001e-06,
|
| 1886 |
+
"loss": 0.0666,
|
| 1887 |
+
"step": 960
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 315.78,
|
| 1891 |
+
"learning_rate": 7.460937500000001e-06,
|
| 1892 |
+
"loss": 0.0666,
|
| 1893 |
+
"step": 963
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 316.76,
|
| 1897 |
+
"learning_rate": 7.421875000000001e-06,
|
| 1898 |
+
"loss": 0.0681,
|
| 1899 |
+
"step": 966
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 317.73,
|
| 1903 |
+
"learning_rate": 7.382812500000001e-06,
|
| 1904 |
+
"loss": 0.0649,
|
| 1905 |
+
"step": 969
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 318.7,
|
| 1909 |
+
"learning_rate": 7.343750000000001e-06,
|
| 1910 |
+
"loss": 0.0671,
|
| 1911 |
+
"step": 972
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 320.0,
|
| 1915 |
+
"learning_rate": 7.291666666666667e-06,
|
| 1916 |
+
"loss": 0.0516,
|
| 1917 |
+
"step": 976
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 320.97,
|
| 1921 |
+
"learning_rate": 7.2526041666666665e-06,
|
| 1922 |
+
"loss": 0.0644,
|
| 1923 |
+
"step": 979
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 321.95,
|
| 1927 |
+
"learning_rate": 7.213541666666667e-06,
|
| 1928 |
+
"loss": 0.0652,
|
| 1929 |
+
"step": 982
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 322.92,
|
| 1933 |
+
"learning_rate": 7.174479166666667e-06,
|
| 1934 |
+
"loss": 0.0658,
|
| 1935 |
+
"step": 985
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 323.89,
|
| 1939 |
+
"learning_rate": 7.135416666666667e-06,
|
| 1940 |
+
"loss": 0.063,
|
| 1941 |
+
"step": 988
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 324.86,
|
| 1945 |
+
"learning_rate": 7.096354166666667e-06,
|
| 1946 |
+
"loss": 0.0616,
|
| 1947 |
+
"step": 991
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 325.84,
|
| 1951 |
+
"learning_rate": 7.057291666666667e-06,
|
| 1952 |
+
"loss": 0.0639,
|
| 1953 |
+
"step": 994
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 326.81,
|
| 1957 |
+
"learning_rate": 7.018229166666667e-06,
|
| 1958 |
+
"loss": 0.0622,
|
| 1959 |
+
"step": 997
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 327.78,
|
| 1963 |
+
"learning_rate": 6.979166666666667e-06,
|
| 1964 |
+
"loss": 0.0654,
|
| 1965 |
+
"step": 1000
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 328.76,
|
| 1969 |
+
"learning_rate": 6.9401041666666665e-06,
|
| 1970 |
+
"loss": 0.0629,
|
| 1971 |
+
"step": 1003
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 329.73,
|
| 1975 |
+
"learning_rate": 6.901041666666667e-06,
|
| 1976 |
+
"loss": 0.0625,
|
| 1977 |
+
"step": 1006
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 330.7,
|
| 1981 |
+
"learning_rate": 6.861979166666667e-06,
|
| 1982 |
+
"loss": 0.0655,
|
| 1983 |
+
"step": 1009
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 332.0,
|
| 1987 |
+
"learning_rate": 6.809895833333334e-06,
|
| 1988 |
+
"loss": 0.0468,
|
| 1989 |
+
"step": 1013
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 332.97,
|
| 1993 |
+
"learning_rate": 6.770833333333334e-06,
|
| 1994 |
+
"loss": 0.0653,
|
| 1995 |
+
"step": 1016
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 333.95,
|
| 1999 |
+
"learning_rate": 6.731770833333335e-06,
|
| 2000 |
+
"loss": 0.0632,
|
| 2001 |
+
"step": 1019
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 334.92,
|
| 2005 |
+
"learning_rate": 6.6927083333333345e-06,
|
| 2006 |
+
"loss": 0.0603,
|
| 2007 |
+
"step": 1022
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 335.89,
|
| 2011 |
+
"learning_rate": 6.653645833333334e-06,
|
| 2012 |
+
"loss": 0.0636,
|
| 2013 |
+
"step": 1025
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 336.86,
|
| 2017 |
+
"learning_rate": 6.614583333333334e-06,
|
| 2018 |
+
"loss": 0.061,
|
| 2019 |
+
"step": 1028
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 337.84,
|
| 2023 |
+
"learning_rate": 6.575520833333334e-06,
|
| 2024 |
+
"loss": 0.0626,
|
| 2025 |
+
"step": 1031
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 338.81,
|
| 2029 |
+
"learning_rate": 6.536458333333334e-06,
|
| 2030 |
+
"loss": 0.0646,
|
| 2031 |
+
"step": 1034
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 339.78,
|
| 2035 |
+
"learning_rate": 6.497395833333334e-06,
|
| 2036 |
+
"loss": 0.0613,
|
| 2037 |
+
"step": 1037
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 340.76,
|
| 2041 |
+
"learning_rate": 6.458333333333334e-06,
|
| 2042 |
+
"loss": 0.0645,
|
| 2043 |
+
"step": 1040
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 341.73,
|
| 2047 |
+
"learning_rate": 6.419270833333335e-06,
|
| 2048 |
+
"loss": 0.0607,
|
| 2049 |
+
"step": 1043
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 342.7,
|
| 2053 |
+
"learning_rate": 6.3802083333333345e-06,
|
| 2054 |
+
"loss": 0.0622,
|
| 2055 |
+
"step": 1046
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 344.0,
|
| 2059 |
+
"learning_rate": 6.3281250000000005e-06,
|
| 2060 |
+
"loss": 0.0441,
|
| 2061 |
+
"step": 1050
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 344.97,
|
| 2065 |
+
"learning_rate": 6.2890625e-06,
|
| 2066 |
+
"loss": 0.0624,
|
| 2067 |
+
"step": 1053
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 345.95,
|
| 2071 |
+
"learning_rate": 6.25e-06,
|
| 2072 |
+
"loss": 0.0641,
|
| 2073 |
+
"step": 1056
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 346.92,
|
| 2077 |
+
"learning_rate": 6.2109375e-06,
|
| 2078 |
+
"loss": 0.0574,
|
| 2079 |
+
"step": 1059
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 347.89,
|
| 2083 |
+
"learning_rate": 6.171875e-06,
|
| 2084 |
+
"loss": 0.0582,
|
| 2085 |
+
"step": 1062
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 348.86,
|
| 2089 |
+
"learning_rate": 6.132812500000001e-06,
|
| 2090 |
+
"loss": 0.0592,
|
| 2091 |
+
"step": 1065
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 349.84,
|
| 2095 |
+
"learning_rate": 6.093750000000001e-06,
|
| 2096 |
+
"loss": 0.0607,
|
| 2097 |
+
"step": 1068
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 350.81,
|
| 2101 |
+
"learning_rate": 6.054687500000001e-06,
|
| 2102 |
+
"loss": 0.0598,
|
| 2103 |
+
"step": 1071
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 351.78,
|
| 2107 |
+
"learning_rate": 6.0156250000000005e-06,
|
| 2108 |
+
"loss": 0.061,
|
| 2109 |
+
"step": 1074
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 352.76,
|
| 2113 |
+
"learning_rate": 5.9765625000000004e-06,
|
| 2114 |
+
"loss": 0.0586,
|
| 2115 |
+
"step": 1077
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 353.73,
|
| 2119 |
+
"learning_rate": 5.9375e-06,
|
| 2120 |
+
"loss": 0.059,
|
| 2121 |
+
"step": 1080
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 354.7,
|
| 2125 |
+
"learning_rate": 5.8984375e-06,
|
| 2126 |
+
"loss": 0.0601,
|
| 2127 |
+
"step": 1083
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 356.0,
|
| 2131 |
+
"learning_rate": 5.846354166666667e-06,
|
| 2132 |
+
"loss": 0.0447,
|
| 2133 |
+
"step": 1087
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 356.97,
|
| 2137 |
+
"learning_rate": 5.807291666666667e-06,
|
| 2138 |
+
"loss": 0.0611,
|
| 2139 |
+
"step": 1090
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 357.95,
|
| 2143 |
+
"learning_rate": 5.768229166666667e-06,
|
| 2144 |
+
"loss": 0.0575,
|
| 2145 |
+
"step": 1093
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 358.92,
|
| 2149 |
+
"learning_rate": 5.729166666666667e-06,
|
| 2150 |
+
"loss": 0.0599,
|
| 2151 |
+
"step": 1096
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 359.89,
|
| 2155 |
+
"learning_rate": 5.690104166666667e-06,
|
| 2156 |
+
"loss": 0.0585,
|
| 2157 |
+
"step": 1099
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 360.86,
|
| 2161 |
+
"learning_rate": 5.6510416666666665e-06,
|
| 2162 |
+
"loss": 0.0571,
|
| 2163 |
+
"step": 1102
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 361.84,
|
| 2167 |
+
"learning_rate": 5.611979166666666e-06,
|
| 2168 |
+
"loss": 0.0573,
|
| 2169 |
+
"step": 1105
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 362.81,
|
| 2173 |
+
"learning_rate": 5.572916666666667e-06,
|
| 2174 |
+
"loss": 0.0588,
|
| 2175 |
+
"step": 1108
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 363.78,
|
| 2179 |
+
"learning_rate": 5.533854166666667e-06,
|
| 2180 |
+
"loss": 0.0563,
|
| 2181 |
+
"step": 1111
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 364.76,
|
| 2185 |
+
"learning_rate": 5.494791666666667e-06,
|
| 2186 |
+
"loss": 0.0567,
|
| 2187 |
+
"step": 1114
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 365.73,
|
| 2191 |
+
"learning_rate": 5.455729166666667e-06,
|
| 2192 |
+
"loss": 0.0578,
|
| 2193 |
+
"step": 1117
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 366.7,
|
| 2197 |
+
"learning_rate": 5.416666666666667e-06,
|
| 2198 |
+
"loss": 0.0579,
|
| 2199 |
+
"step": 1120
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 368.0,
|
| 2203 |
+
"learning_rate": 5.364583333333334e-06,
|
| 2204 |
+
"loss": 0.0417,
|
| 2205 |
+
"step": 1124
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 368.97,
|
| 2209 |
+
"learning_rate": 5.325520833333334e-06,
|
| 2210 |
+
"loss": 0.0563,
|
| 2211 |
+
"step": 1127
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 369.95,
|
| 2215 |
+
"learning_rate": 5.286458333333334e-06,
|
| 2216 |
+
"loss": 0.0565,
|
| 2217 |
+
"step": 1130
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 370.92,
|
| 2221 |
+
"learning_rate": 5.247395833333334e-06,
|
| 2222 |
+
"loss": 0.0558,
|
| 2223 |
+
"step": 1133
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 371.89,
|
| 2227 |
+
"learning_rate": 5.208333333333334e-06,
|
| 2228 |
+
"loss": 0.0572,
|
| 2229 |
+
"step": 1136
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 372.86,
|
| 2233 |
+
"learning_rate": 5.169270833333334e-06,
|
| 2234 |
+
"loss": 0.0553,
|
| 2235 |
+
"step": 1139
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 373.84,
|
| 2239 |
+
"learning_rate": 5.130208333333334e-06,
|
| 2240 |
+
"loss": 0.0546,
|
| 2241 |
+
"step": 1142
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 374.81,
|
| 2245 |
+
"learning_rate": 5.091145833333334e-06,
|
| 2246 |
+
"loss": 0.0582,
|
| 2247 |
+
"step": 1145
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 375.78,
|
| 2251 |
+
"learning_rate": 5.0520833333333344e-06,
|
| 2252 |
+
"loss": 0.0545,
|
| 2253 |
+
"step": 1148
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 376.76,
|
| 2257 |
+
"learning_rate": 5.013020833333334e-06,
|
| 2258 |
+
"loss": 0.0546,
|
| 2259 |
+
"step": 1151
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 377.73,
|
| 2263 |
+
"learning_rate": 4.973958333333333e-06,
|
| 2264 |
+
"loss": 0.0543,
|
| 2265 |
+
"step": 1154
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 378.7,
|
| 2269 |
+
"learning_rate": 4.934895833333333e-06,
|
| 2270 |
+
"loss": 0.0543,
|
| 2271 |
+
"step": 1157
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 380.0,
|
| 2275 |
+
"learning_rate": 4.8828125e-06,
|
| 2276 |
+
"loss": 0.0405,
|
| 2277 |
+
"step": 1161
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 380.97,
|
| 2281 |
+
"learning_rate": 4.84375e-06,
|
| 2282 |
+
"loss": 0.0553,
|
| 2283 |
+
"step": 1164
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 381.95,
|
| 2287 |
+
"learning_rate": 4.804687500000001e-06,
|
| 2288 |
+
"loss": 0.0552,
|
| 2289 |
+
"step": 1167
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 382.92,
|
| 2293 |
+
"learning_rate": 4.765625000000001e-06,
|
| 2294 |
+
"loss": 0.0567,
|
| 2295 |
+
"step": 1170
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 383.89,
|
| 2299 |
+
"learning_rate": 4.7265625000000005e-06,
|
| 2300 |
+
"loss": 0.056,
|
| 2301 |
+
"step": 1173
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 384.86,
|
| 2305 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 2306 |
+
"loss": 0.0547,
|
| 2307 |
+
"step": 1176
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 385.84,
|
| 2311 |
+
"learning_rate": 4.6484375e-06,
|
| 2312 |
+
"loss": 0.0559,
|
| 2313 |
+
"step": 1179
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 386.81,
|
| 2317 |
+
"learning_rate": 4.609375e-06,
|
| 2318 |
+
"loss": 0.0551,
|
| 2319 |
+
"step": 1182
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 387.78,
|
| 2323 |
+
"learning_rate": 4.5703125e-06,
|
| 2324 |
+
"loss": 0.0546,
|
| 2325 |
+
"step": 1185
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 388.76,
|
| 2329 |
+
"learning_rate": 4.53125e-06,
|
| 2330 |
+
"loss": 0.0529,
|
| 2331 |
+
"step": 1188
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 389.73,
|
| 2335 |
+
"learning_rate": 4.492187500000001e-06,
|
| 2336 |
+
"loss": 0.054,
|
| 2337 |
+
"step": 1191
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 390.7,
|
| 2341 |
+
"learning_rate": 4.453125000000001e-06,
|
| 2342 |
+
"loss": 0.0554,
|
| 2343 |
+
"step": 1194
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 392.0,
|
| 2347 |
+
"learning_rate": 4.4010416666666675e-06,
|
| 2348 |
+
"loss": 0.042,
|
| 2349 |
+
"step": 1198
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 392.97,
|
| 2353 |
+
"learning_rate": 4.361979166666667e-06,
|
| 2354 |
+
"loss": 0.0556,
|
| 2355 |
+
"step": 1201
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 393.95,
|
| 2359 |
+
"learning_rate": 4.322916666666667e-06,
|
| 2360 |
+
"loss": 0.0553,
|
| 2361 |
+
"step": 1204
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 394.92,
|
| 2365 |
+
"learning_rate": 4.283854166666667e-06,
|
| 2366 |
+
"loss": 0.053,
|
| 2367 |
+
"step": 1207
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 395.89,
|
| 2371 |
+
"learning_rate": 4.244791666666667e-06,
|
| 2372 |
+
"loss": 0.056,
|
| 2373 |
+
"step": 1210
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 396.86,
|
| 2377 |
+
"learning_rate": 4.205729166666667e-06,
|
| 2378 |
+
"loss": 0.054,
|
| 2379 |
+
"step": 1213
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 397.84,
|
| 2383 |
+
"learning_rate": 4.166666666666667e-06,
|
| 2384 |
+
"loss": 0.0555,
|
| 2385 |
+
"step": 1216
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 398.81,
|
| 2389 |
+
"learning_rate": 4.127604166666668e-06,
|
| 2390 |
+
"loss": 0.0555,
|
| 2391 |
+
"step": 1219
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 399.78,
|
| 2395 |
+
"learning_rate": 4.0885416666666675e-06,
|
| 2396 |
+
"loss": 0.0547,
|
| 2397 |
+
"step": 1222
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 400.76,
|
| 2401 |
+
"learning_rate": 4.049479166666667e-06,
|
| 2402 |
+
"loss": 0.052,
|
| 2403 |
+
"step": 1225
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 401.73,
|
| 2407 |
+
"learning_rate": 4.010416666666667e-06,
|
| 2408 |
+
"loss": 0.0535,
|
| 2409 |
+
"step": 1228
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 402.7,
|
| 2413 |
+
"learning_rate": 3.971354166666667e-06,
|
| 2414 |
+
"loss": 0.0544,
|
| 2415 |
+
"step": 1231
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 404.0,
|
| 2419 |
+
"learning_rate": 3.919270833333333e-06,
|
| 2420 |
+
"loss": 0.0404,
|
| 2421 |
+
"step": 1235
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 404.97,
|
| 2425 |
+
"learning_rate": 3.880208333333333e-06,
|
| 2426 |
+
"loss": 0.0525,
|
| 2427 |
+
"step": 1238
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 405.95,
|
| 2431 |
+
"learning_rate": 3.841145833333334e-06,
|
| 2432 |
+
"loss": 0.0552,
|
| 2433 |
+
"step": 1241
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 406.92,
|
| 2437 |
+
"learning_rate": 3.8020833333333333e-06,
|
| 2438 |
+
"loss": 0.0544,
|
| 2439 |
+
"step": 1244
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 407.89,
|
| 2443 |
+
"learning_rate": 3.7630208333333336e-06,
|
| 2444 |
+
"loss": 0.0529,
|
| 2445 |
+
"step": 1247
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 408.86,
|
| 2449 |
+
"learning_rate": 3.7239583333333335e-06,
|
| 2450 |
+
"loss": 0.0538,
|
| 2451 |
+
"step": 1250
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 409.84,
|
| 2455 |
+
"learning_rate": 3.6848958333333334e-06,
|
| 2456 |
+
"loss": 0.052,
|
| 2457 |
+
"step": 1253
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 410.81,
|
| 2461 |
+
"learning_rate": 3.6458333333333333e-06,
|
| 2462 |
+
"loss": 0.0525,
|
| 2463 |
+
"step": 1256
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"epoch": 411.78,
|
| 2467 |
+
"learning_rate": 3.6067708333333336e-06,
|
| 2468 |
+
"loss": 0.0524,
|
| 2469 |
+
"step": 1259
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 412.76,
|
| 2473 |
+
"learning_rate": 3.5677083333333335e-06,
|
| 2474 |
+
"loss": 0.0511,
|
| 2475 |
+
"step": 1262
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 413.73,
|
| 2479 |
+
"learning_rate": 3.5286458333333334e-06,
|
| 2480 |
+
"loss": 0.0539,
|
| 2481 |
+
"step": 1265
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 414.7,
|
| 2485 |
+
"learning_rate": 3.4895833333333333e-06,
|
| 2486 |
+
"loss": 0.0529,
|
| 2487 |
+
"step": 1268
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 416.0,
|
| 2491 |
+
"learning_rate": 3.4375e-06,
|
| 2492 |
+
"loss": 0.0408,
|
| 2493 |
+
"step": 1272
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 416.97,
|
| 2497 |
+
"learning_rate": 3.3984375000000004e-06,
|
| 2498 |
+
"loss": 0.0541,
|
| 2499 |
+
"step": 1275
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 417.95,
|
| 2503 |
+
"learning_rate": 3.3593750000000003e-06,
|
| 2504 |
+
"loss": 0.0511,
|
| 2505 |
+
"step": 1278
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 418.92,
|
| 2509 |
+
"learning_rate": 3.3203125000000002e-06,
|
| 2510 |
+
"loss": 0.0499,
|
| 2511 |
+
"step": 1281
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 419.89,
|
| 2515 |
+
"learning_rate": 3.28125e-06,
|
| 2516 |
+
"loss": 0.0512,
|
| 2517 |
+
"step": 1284
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 420.86,
|
| 2521 |
+
"learning_rate": 3.2421875000000005e-06,
|
| 2522 |
+
"loss": 0.0531,
|
| 2523 |
+
"step": 1287
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 421.84,
|
| 2527 |
+
"learning_rate": 3.2031250000000004e-06,
|
| 2528 |
+
"loss": 0.0532,
|
| 2529 |
+
"step": 1290
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 422.81,
|
| 2533 |
+
"learning_rate": 3.1640625000000003e-06,
|
| 2534 |
+
"loss": 0.0519,
|
| 2535 |
+
"step": 1293
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 423.78,
|
| 2539 |
+
"learning_rate": 3.125e-06,
|
| 2540 |
+
"loss": 0.0521,
|
| 2541 |
+
"step": 1296
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 424.76,
|
| 2545 |
+
"learning_rate": 3.0859375e-06,
|
| 2546 |
+
"loss": 0.0535,
|
| 2547 |
+
"step": 1299
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 425.73,
|
| 2551 |
+
"learning_rate": 3.0468750000000004e-06,
|
| 2552 |
+
"loss": 0.0506,
|
| 2553 |
+
"step": 1302
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 426.7,
|
| 2557 |
+
"learning_rate": 3.0078125000000003e-06,
|
| 2558 |
+
"loss": 0.0522,
|
| 2559 |
+
"step": 1305
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 428.0,
|
| 2563 |
+
"learning_rate": 2.955729166666667e-06,
|
| 2564 |
+
"loss": 0.0392,
|
| 2565 |
+
"step": 1309
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 428.97,
|
| 2569 |
+
"learning_rate": 2.916666666666667e-06,
|
| 2570 |
+
"loss": 0.0522,
|
| 2571 |
+
"step": 1312
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 429.95,
|
| 2575 |
+
"learning_rate": 2.8776041666666673e-06,
|
| 2576 |
+
"loss": 0.0532,
|
| 2577 |
+
"step": 1315
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 430.92,
|
| 2581 |
+
"learning_rate": 2.838541666666667e-06,
|
| 2582 |
+
"loss": 0.051,
|
| 2583 |
+
"step": 1318
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 431.89,
|
| 2587 |
+
"learning_rate": 2.799479166666667e-06,
|
| 2588 |
+
"loss": 0.0537,
|
| 2589 |
+
"step": 1321
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 432.86,
|
| 2593 |
+
"learning_rate": 2.760416666666667e-06,
|
| 2594 |
+
"loss": 0.0508,
|
| 2595 |
+
"step": 1324
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 433.84,
|
| 2599 |
+
"learning_rate": 2.721354166666667e-06,
|
| 2600 |
+
"loss": 0.0518,
|
| 2601 |
+
"step": 1327
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 434.81,
|
| 2605 |
+
"learning_rate": 2.682291666666667e-06,
|
| 2606 |
+
"loss": 0.052,
|
| 2607 |
+
"step": 1330
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 435.78,
|
| 2611 |
+
"learning_rate": 2.643229166666667e-06,
|
| 2612 |
+
"loss": 0.054,
|
| 2613 |
+
"step": 1333
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 436.76,
|
| 2617 |
+
"learning_rate": 2.604166666666667e-06,
|
| 2618 |
+
"loss": 0.0495,
|
| 2619 |
+
"step": 1336
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 437.73,
|
| 2623 |
+
"learning_rate": 2.565104166666667e-06,
|
| 2624 |
+
"loss": 0.0523,
|
| 2625 |
+
"step": 1339
|
| 2626 |
+
},
|
| 2627 |
+
{
|
| 2628 |
+
"epoch": 438.7,
|
| 2629 |
+
"learning_rate": 2.5260416666666672e-06,
|
| 2630 |
+
"loss": 0.0517,
|
| 2631 |
+
"step": 1342
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 440.0,
|
| 2635 |
+
"learning_rate": 2.4739583333333336e-06,
|
| 2636 |
+
"loss": 0.0382,
|
| 2637 |
+
"step": 1346
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 440.97,
|
| 2641 |
+
"learning_rate": 2.4348958333333335e-06,
|
| 2642 |
+
"loss": 0.0524,
|
| 2643 |
+
"step": 1349
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 441.95,
|
| 2647 |
+
"learning_rate": 2.395833333333334e-06,
|
| 2648 |
+
"loss": 0.0524,
|
| 2649 |
+
"step": 1352
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 442.92,
|
| 2653 |
+
"learning_rate": 2.3567708333333337e-06,
|
| 2654 |
+
"loss": 0.0539,
|
| 2655 |
+
"step": 1355
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 443.89,
|
| 2659 |
+
"learning_rate": 2.3177083333333336e-06,
|
| 2660 |
+
"loss": 0.05,
|
| 2661 |
+
"step": 1358
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 444.86,
|
| 2665 |
+
"learning_rate": 2.2786458333333335e-06,
|
| 2666 |
+
"loss": 0.0507,
|
| 2667 |
+
"step": 1361
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 445.84,
|
| 2671 |
+
"learning_rate": 2.2395833333333334e-06,
|
| 2672 |
+
"loss": 0.0505,
|
| 2673 |
+
"step": 1364
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"epoch": 446.81,
|
| 2677 |
+
"learning_rate": 2.2005208333333337e-06,
|
| 2678 |
+
"loss": 0.0518,
|
| 2679 |
+
"step": 1367
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 447.78,
|
| 2683 |
+
"learning_rate": 2.1614583333333336e-06,
|
| 2684 |
+
"loss": 0.0509,
|
| 2685 |
+
"step": 1370
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 448.76,
|
| 2689 |
+
"learning_rate": 2.1223958333333335e-06,
|
| 2690 |
+
"loss": 0.0504,
|
| 2691 |
+
"step": 1373
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 449.73,
|
| 2695 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 2696 |
+
"loss": 0.0498,
|
| 2697 |
+
"step": 1376
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 450.7,
|
| 2701 |
+
"learning_rate": 2.0442708333333338e-06,
|
| 2702 |
+
"loss": 0.0518,
|
| 2703 |
+
"step": 1379
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 452.0,
|
| 2707 |
+
"learning_rate": 1.9921875e-06,
|
| 2708 |
+
"loss": 0.0389,
|
| 2709 |
+
"step": 1383
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 452.97,
|
| 2713 |
+
"learning_rate": 1.953125e-06,
|
| 2714 |
+
"loss": 0.0512,
|
| 2715 |
+
"step": 1386
|
| 2716 |
+
},
|
| 2717 |
+
{
|
| 2718 |
+
"epoch": 453.95,
|
| 2719 |
+
"learning_rate": 1.9140625000000004e-06,
|
| 2720 |
+
"loss": 0.0509,
|
| 2721 |
+
"step": 1389
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 454.92,
|
| 2725 |
+
"learning_rate": 1.8750000000000003e-06,
|
| 2726 |
+
"loss": 0.0532,
|
| 2727 |
+
"step": 1392
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 455.89,
|
| 2731 |
+
"learning_rate": 1.8359375000000002e-06,
|
| 2732 |
+
"loss": 0.0498,
|
| 2733 |
+
"step": 1395
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 456.86,
|
| 2737 |
+
"learning_rate": 1.796875e-06,
|
| 2738 |
+
"loss": 0.05,
|
| 2739 |
+
"step": 1398
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 457.84,
|
| 2743 |
+
"learning_rate": 1.7578125000000002e-06,
|
| 2744 |
+
"loss": 0.0526,
|
| 2745 |
+
"step": 1401
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 458.81,
|
| 2749 |
+
"learning_rate": 1.71875e-06,
|
| 2750 |
+
"loss": 0.0514,
|
| 2751 |
+
"step": 1404
|
| 2752 |
+
},
|
| 2753 |
+
{
|
| 2754 |
+
"epoch": 459.78,
|
| 2755 |
+
"learning_rate": 1.6796875000000002e-06,
|
| 2756 |
+
"loss": 0.0529,
|
| 2757 |
+
"step": 1407
|
| 2758 |
+
},
|
| 2759 |
+
{
|
| 2760 |
+
"epoch": 460.76,
|
| 2761 |
+
"learning_rate": 1.640625e-06,
|
| 2762 |
+
"loss": 0.0501,
|
| 2763 |
+
"step": 1410
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 461.73,
|
| 2767 |
+
"learning_rate": 1.6015625000000002e-06,
|
| 2768 |
+
"loss": 0.0508,
|
| 2769 |
+
"step": 1413
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 462.7,
|
| 2773 |
+
"learning_rate": 1.5625e-06,
|
| 2774 |
+
"loss": 0.0509,
|
| 2775 |
+
"step": 1416
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 464.0,
|
| 2779 |
+
"learning_rate": 1.5104166666666667e-06,
|
| 2780 |
+
"loss": 0.0385,
|
| 2781 |
+
"step": 1420
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 464.97,
|
| 2785 |
+
"learning_rate": 1.4713541666666668e-06,
|
| 2786 |
+
"loss": 0.0533,
|
| 2787 |
+
"step": 1423
|
| 2788 |
+
},
|
| 2789 |
+
{
|
| 2790 |
+
"epoch": 465.95,
|
| 2791 |
+
"learning_rate": 1.4322916666666667e-06,
|
| 2792 |
+
"loss": 0.0504,
|
| 2793 |
+
"step": 1426
|
| 2794 |
+
},
|
| 2795 |
+
{
|
| 2796 |
+
"epoch": 466.92,
|
| 2797 |
+
"learning_rate": 1.3932291666666668e-06,
|
| 2798 |
+
"loss": 0.0512,
|
| 2799 |
+
"step": 1429
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 467.89,
|
| 2803 |
+
"learning_rate": 1.3541666666666667e-06,
|
| 2804 |
+
"loss": 0.0517,
|
| 2805 |
+
"step": 1432
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 468.86,
|
| 2809 |
+
"learning_rate": 1.3151041666666666e-06,
|
| 2810 |
+
"loss": 0.0484,
|
| 2811 |
+
"step": 1435
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 469.84,
|
| 2815 |
+
"learning_rate": 1.2760416666666667e-06,
|
| 2816 |
+
"loss": 0.0511,
|
| 2817 |
+
"step": 1438
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 470.81,
|
| 2821 |
+
"learning_rate": 1.2369791666666668e-06,
|
| 2822 |
+
"loss": 0.0515,
|
| 2823 |
+
"step": 1441
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 471.78,
|
| 2827 |
+
"learning_rate": 1.197916666666667e-06,
|
| 2828 |
+
"loss": 0.0506,
|
| 2829 |
+
"step": 1444
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 472.76,
|
| 2833 |
+
"learning_rate": 1.1588541666666668e-06,
|
| 2834 |
+
"loss": 0.0515,
|
| 2835 |
+
"step": 1447
|
| 2836 |
+
},
|
| 2837 |
+
{
|
| 2838 |
+
"epoch": 473.73,
|
| 2839 |
+
"learning_rate": 1.1197916666666667e-06,
|
| 2840 |
+
"loss": 0.0501,
|
| 2841 |
+
"step": 1450
|
| 2842 |
+
},
|
| 2843 |
+
{
|
| 2844 |
+
"epoch": 474.7,
|
| 2845 |
+
"learning_rate": 1.0807291666666668e-06,
|
| 2846 |
+
"loss": 0.0523,
|
| 2847 |
+
"step": 1453
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 476.0,
|
| 2851 |
+
"learning_rate": 1.0286458333333334e-06,
|
| 2852 |
+
"loss": 0.0373,
|
| 2853 |
+
"step": 1457
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 476.97,
|
| 2857 |
+
"learning_rate": 9.895833333333333e-07,
|
| 2858 |
+
"loss": 0.0504,
|
| 2859 |
+
"step": 1460
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 477.95,
|
| 2863 |
+
"learning_rate": 9.505208333333333e-07,
|
| 2864 |
+
"loss": 0.0497,
|
| 2865 |
+
"step": 1463
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 478.92,
|
| 2869 |
+
"learning_rate": 9.114583333333333e-07,
|
| 2870 |
+
"loss": 0.0496,
|
| 2871 |
+
"step": 1466
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 479.89,
|
| 2875 |
+
"learning_rate": 8.723958333333333e-07,
|
| 2876 |
+
"loss": 0.0526,
|
| 2877 |
+
"step": 1469
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"epoch": 480.86,
|
| 2881 |
+
"learning_rate": 8.333333333333333e-07,
|
| 2882 |
+
"loss": 0.0491,
|
| 2883 |
+
"step": 1472
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 481.84,
|
| 2887 |
+
"learning_rate": 7.942708333333333e-07,
|
| 2888 |
+
"loss": 0.0499,
|
| 2889 |
+
"step": 1475
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 482.81,
|
| 2893 |
+
"learning_rate": 7.552083333333333e-07,
|
| 2894 |
+
"loss": 0.0519,
|
| 2895 |
+
"step": 1478
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 483.78,
|
| 2899 |
+
"learning_rate": 7.161458333333333e-07,
|
| 2900 |
+
"loss": 0.0499,
|
| 2901 |
+
"step": 1481
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 484.76,
|
| 2905 |
+
"learning_rate": 6.770833333333333e-07,
|
| 2906 |
+
"loss": 0.0516,
|
| 2907 |
+
"step": 1484
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 485.73,
|
| 2911 |
+
"learning_rate": 6.380208333333333e-07,
|
| 2912 |
+
"loss": 0.0493,
|
| 2913 |
+
"step": 1487
|
| 2914 |
+
},
|
| 2915 |
+
{
|
| 2916 |
+
"epoch": 486.7,
|
| 2917 |
+
"learning_rate": 5.989583333333335e-07,
|
| 2918 |
+
"loss": 0.0513,
|
| 2919 |
+
"step": 1490
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"epoch": 488.0,
|
| 2923 |
+
"learning_rate": 5.468750000000001e-07,
|
| 2924 |
+
"loss": 0.0381,
|
| 2925 |
+
"step": 1494
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 488.97,
|
| 2929 |
+
"learning_rate": 5.078125000000001e-07,
|
| 2930 |
+
"loss": 0.0518,
|
| 2931 |
+
"step": 1497
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 489.95,
|
| 2935 |
+
"learning_rate": 4.6875000000000006e-07,
|
| 2936 |
+
"loss": 0.0489,
|
| 2937 |
+
"step": 1500
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 490.92,
|
| 2941 |
+
"learning_rate": 4.296875e-07,
|
| 2942 |
+
"loss": 0.0497,
|
| 2943 |
+
"step": 1503
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 491.89,
|
| 2947 |
+
"learning_rate": 3.90625e-07,
|
| 2948 |
+
"loss": 0.0492,
|
| 2949 |
+
"step": 1506
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 492.86,
|
| 2953 |
+
"learning_rate": 3.515625e-07,
|
| 2954 |
+
"loss": 0.049,
|
| 2955 |
+
"step": 1509
|
| 2956 |
+
},
|
| 2957 |
+
{
|
| 2958 |
+
"epoch": 493.84,
|
| 2959 |
+
"learning_rate": 3.125e-07,
|
| 2960 |
+
"loss": 0.0487,
|
| 2961 |
+
"step": 1512
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"epoch": 494.81,
|
| 2965 |
+
"learning_rate": 2.7343750000000003e-07,
|
| 2966 |
+
"loss": 0.0495,
|
| 2967 |
+
"step": 1515
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 495.78,
|
| 2971 |
+
"learning_rate": 2.3437500000000003e-07,
|
| 2972 |
+
"loss": 0.049,
|
| 2973 |
+
"step": 1518
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 496.76,
|
| 2977 |
+
"learning_rate": 1.953125e-07,
|
| 2978 |
+
"loss": 0.0505,
|
| 2979 |
+
"step": 1521
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 497.73,
|
| 2983 |
+
"learning_rate": 1.5625e-07,
|
| 2984 |
+
"loss": 0.0518,
|
| 2985 |
+
"step": 1524
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 498.7,
|
| 2989 |
+
"learning_rate": 1.1718750000000002e-07,
|
| 2990 |
+
"loss": 0.0477,
|
| 2991 |
+
"step": 1527
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 500.0,
|
| 2995 |
+
"learning_rate": 6.510416666666667e-08,
|
| 2996 |
+
"loss": 0.039,
|
| 2997 |
+
"step": 1531
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 500.97,
|
| 3001 |
+
"learning_rate": 2.6041666666666667e-08,
|
| 3002 |
+
"loss": 0.0494,
|
| 3003 |
+
"step": 1534
|
| 3004 |
+
},
|
| 3005 |
+
{
|
| 3006 |
+
"epoch": 501.62,
|
| 3007 |
+
"learning_rate": 0.0,
|
| 3008 |
+
"loss": 0.0498,
|
| 3009 |
+
"step": 1536
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 501.62,
|
| 3013 |
+
"step": 1536,
|
| 3014 |
+
"total_flos": 1.9358620133923584e+17,
|
| 3015 |
+
"train_loss": 0.10890851792161509,
|
| 3016 |
+
"train_runtime": 10408.3467,
|
| 3017 |
+
"train_samples_per_second": 288.507,
|
| 3018 |
+
"train_steps_per_second": 0.148
|
| 3019 |
}
|
| 3020 |
],
|
| 3021 |
"logging_steps": 500,
|
| 3022 |
+
"max_steps": 1536,
|
| 3023 |
+
"num_train_epochs": 512,
|
| 3024 |
"save_steps": 500,
|
| 3025 |
+
"total_flos": 1.9358620133923584e+17,
|
| 3026 |
"trial_name": null,
|
| 3027 |
"trial_params": null
|
| 3028 |
}
|