Training in progress, epoch 65
Browse files- all_results.json +5 -10
- config.json +1 -0
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +1191 -12
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,12 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"eval_steps_per_second": 4.055,
|
| 8 |
-
"train_loss": 0.08673005339085323,
|
| 9 |
-
"train_runtime": 125919.3774,
|
| 10 |
-
"train_samples_per_second": 373.471,
|
| 11 |
-
"train_steps_per_second": 0.73
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 64.0,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 758.3182,
|
| 5 |
+
"train_samples_per_second": 53155.811,
|
| 6 |
+
"train_steps_per_second": 207.696
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
config.json
CHANGED
|
@@ -31044,6 +31044,7 @@
|
|
| 31044 |
0,
|
| 31045 |
0
|
| 31046 |
],
|
|
|
|
| 31047 |
"qkv_bias": true,
|
| 31048 |
"torch_dtype": "float32",
|
| 31049 |
"transformers_version": "4.33.3",
|
|
|
|
| 31044 |
0,
|
| 31045 |
0
|
| 31046 |
],
|
| 31047 |
+
"problem_type": "single_label_classification",
|
| 31048 |
"qkv_bias": true,
|
| 31049 |
"torch_dtype": "float32",
|
| 31050 |
"transformers_version": "4.33.3",
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 411298414
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b38174b9aa57c0f58305fc7409d9a19a0faf0f9b07e0c2e3366e75424596f69c
|
| 3 |
size 411298414
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 64.0,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 758.3182,
|
| 5 |
+
"train_samples_per_second": 53155.811,
|
| 6 |
+
"train_steps_per_second": 207.696
|
| 7 |
}
|
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,
|
|
@@ -1737,20 +1737,1199 @@
|
|
| 1737 |
"step": 91910
|
| 1738 |
},
|
| 1739 |
{
|
| 1740 |
-
"epoch":
|
| 1741 |
-
"
|
| 1742 |
-
"
|
| 1743 |
-
"
|
| 1744 |
-
|
| 1745 |
-
|
| 1746 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1747 |
}
|
| 1748 |
],
|
| 1749 |
"logging_steps": 500,
|
| 1750 |
-
"max_steps":
|
| 1751 |
-
"num_train_epochs":
|
| 1752 |
"save_steps": 500,
|
| 1753 |
-
"total_flos":
|
| 1754 |
"trial_name": null,
|
| 1755 |
"trial_params": null
|
| 1756 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 64.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 168000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1737 |
"step": 91910
|
| 1738 |
},
|
| 1739 |
{
|
| 1740 |
+
"epoch": 35.05,
|
| 1741 |
+
"learning_rate": 0.003247619047619048,
|
| 1742 |
+
"loss": 0.5379,
|
| 1743 |
+
"step": 92000
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 35.24,
|
| 1747 |
+
"learning_rate": 0.0032380952380952383,
|
| 1748 |
+
"loss": 0.6972,
|
| 1749 |
+
"step": 92500
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 35.43,
|
| 1753 |
+
"learning_rate": 0.0032285714285714283,
|
| 1754 |
+
"loss": 0.7947,
|
| 1755 |
+
"step": 93000
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 35.62,
|
| 1759 |
+
"learning_rate": 0.003219047619047619,
|
| 1760 |
+
"loss": 0.8301,
|
| 1761 |
+
"step": 93500
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 35.81,
|
| 1765 |
+
"learning_rate": 0.0032095238095238092,
|
| 1766 |
+
"loss": 0.8519,
|
| 1767 |
+
"step": 94000
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 36.0,
|
| 1771 |
+
"learning_rate": 0.0032,
|
| 1772 |
+
"loss": 0.8802,
|
| 1773 |
+
"step": 94500
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 36.0,
|
| 1777 |
+
"eval_accuracy": 0.6566997112321753,
|
| 1778 |
+
"eval_loss": 1.7587852478027344,
|
| 1779 |
+
"eval_runtime": 4381.2628,
|
| 1780 |
+
"eval_samples_per_second": 38.335,
|
| 1781 |
+
"eval_steps_per_second": 4.792,
|
| 1782 |
+
"step": 94500
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 36.19,
|
| 1786 |
+
"learning_rate": 0.00319047619047619,
|
| 1787 |
+
"loss": 0.7776,
|
| 1788 |
+
"step": 95000
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 36.38,
|
| 1792 |
+
"learning_rate": 0.003180952380952381,
|
| 1793 |
+
"loss": 0.8104,
|
| 1794 |
+
"step": 95500
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 36.57,
|
| 1798 |
+
"learning_rate": 0.003171428571428571,
|
| 1799 |
+
"loss": 0.8249,
|
| 1800 |
+
"step": 96000
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 36.76,
|
| 1804 |
+
"learning_rate": 0.003161904761904762,
|
| 1805 |
+
"loss": 0.8548,
|
| 1806 |
+
"step": 96500
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 36.95,
|
| 1810 |
+
"learning_rate": 0.0031523809523809525,
|
| 1811 |
+
"loss": 0.8772,
|
| 1812 |
+
"step": 97000
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 37.0,
|
| 1816 |
+
"eval_accuracy": 0.6668571938912209,
|
| 1817 |
+
"eval_loss": 1.6901220083236694,
|
| 1818 |
+
"eval_runtime": 2781.7361,
|
| 1819 |
+
"eval_samples_per_second": 60.378,
|
| 1820 |
+
"eval_steps_per_second": 7.547,
|
| 1821 |
+
"step": 97125
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 37.14,
|
| 1825 |
+
"learning_rate": 0.003142857142857143,
|
| 1826 |
+
"loss": 0.793,
|
| 1827 |
+
"step": 97500
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 37.33,
|
| 1831 |
+
"learning_rate": 0.0031333333333333335,
|
| 1832 |
+
"loss": 0.7985,
|
| 1833 |
+
"step": 98000
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 37.52,
|
| 1837 |
+
"learning_rate": 0.003123809523809524,
|
| 1838 |
+
"loss": 0.8144,
|
| 1839 |
+
"step": 98500
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 37.71,
|
| 1843 |
+
"learning_rate": 0.0031142857142857144,
|
| 1844 |
+
"loss": 0.8338,
|
| 1845 |
+
"step": 99000
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 37.9,
|
| 1849 |
+
"learning_rate": 0.003104761904761905,
|
| 1850 |
+
"loss": 0.847,
|
| 1851 |
+
"step": 99500
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 38.0,
|
| 1855 |
+
"eval_accuracy": 0.6682742401238427,
|
| 1856 |
+
"eval_loss": 1.7208112478256226,
|
| 1857 |
+
"eval_runtime": 2692.0576,
|
| 1858 |
+
"eval_samples_per_second": 62.389,
|
| 1859 |
+
"eval_steps_per_second": 7.799,
|
| 1860 |
+
"step": 99750
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 38.1,
|
| 1864 |
+
"learning_rate": 0.0030952380952380953,
|
| 1865 |
+
"loss": 0.8028,
|
| 1866 |
+
"step": 100000
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 38.29,
|
| 1870 |
+
"learning_rate": 0.0030857142857142854,
|
| 1871 |
+
"loss": 0.764,
|
| 1872 |
+
"step": 100500
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 38.48,
|
| 1876 |
+
"learning_rate": 0.0030761904761904763,
|
| 1877 |
+
"loss": 0.7868,
|
| 1878 |
+
"step": 101000
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 38.67,
|
| 1882 |
+
"learning_rate": 0.0030666666666666663,
|
| 1883 |
+
"loss": 0.8082,
|
| 1884 |
+
"step": 101500
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 38.86,
|
| 1888 |
+
"learning_rate": 0.0030571428571428572,
|
| 1889 |
+
"loss": 0.8349,
|
| 1890 |
+
"step": 102000
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 39.0,
|
| 1894 |
+
"eval_accuracy": 0.6679705873597095,
|
| 1895 |
+
"eval_loss": 1.7477226257324219,
|
| 1896 |
+
"eval_runtime": 2679.7183,
|
| 1897 |
+
"eval_samples_per_second": 62.676,
|
| 1898 |
+
"eval_steps_per_second": 7.835,
|
| 1899 |
+
"step": 102375
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 39.05,
|
| 1903 |
+
"learning_rate": 0.003047619047619048,
|
| 1904 |
+
"loss": 0.8031,
|
| 1905 |
+
"step": 102500
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 39.24,
|
| 1909 |
+
"learning_rate": 0.003038095238095238,
|
| 1910 |
+
"loss": 0.7409,
|
| 1911 |
+
"step": 103000
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 39.43,
|
| 1915 |
+
"learning_rate": 0.003028571428571429,
|
| 1916 |
+
"loss": 0.7646,
|
| 1917 |
+
"step": 103500
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 39.62,
|
| 1921 |
+
"learning_rate": 0.003019047619047619,
|
| 1922 |
+
"loss": 0.7781,
|
| 1923 |
+
"step": 104000
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 39.81,
|
| 1927 |
+
"learning_rate": 0.0030095238095238096,
|
| 1928 |
+
"loss": 0.8094,
|
| 1929 |
+
"step": 104500
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 40.0,
|
| 1933 |
+
"learning_rate": 0.003,
|
| 1934 |
+
"loss": 0.8159,
|
| 1935 |
+
"step": 105000
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 40.0,
|
| 1939 |
+
"eval_accuracy": 0.6640588252805811,
|
| 1940 |
+
"eval_loss": 1.7669143676757812,
|
| 1941 |
+
"eval_runtime": 2681.934,
|
| 1942 |
+
"eval_samples_per_second": 62.625,
|
| 1943 |
+
"eval_steps_per_second": 7.828,
|
| 1944 |
+
"step": 105000
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 40.19,
|
| 1948 |
+
"learning_rate": 0.0029904761904761905,
|
| 1949 |
+
"loss": 0.7129,
|
| 1950 |
+
"step": 105500
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 40.38,
|
| 1954 |
+
"learning_rate": 0.002980952380952381,
|
| 1955 |
+
"loss": 0.7458,
|
| 1956 |
+
"step": 106000
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 40.57,
|
| 1960 |
+
"learning_rate": 0.0029714285714285715,
|
| 1961 |
+
"loss": 0.7784,
|
| 1962 |
+
"step": 106500
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 40.76,
|
| 1966 |
+
"learning_rate": 0.002961904761904762,
|
| 1967 |
+
"loss": 0.7782,
|
| 1968 |
+
"step": 107000
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 40.95,
|
| 1972 |
+
"learning_rate": 0.0029523809523809524,
|
| 1973 |
+
"loss": 0.7894,
|
| 1974 |
+
"step": 107500
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 41.0,
|
| 1978 |
+
"eval_accuracy": 0.669774642017207,
|
| 1979 |
+
"eval_loss": 1.79474675655365,
|
| 1980 |
+
"eval_runtime": 2697.7877,
|
| 1981 |
+
"eval_samples_per_second": 62.257,
|
| 1982 |
+
"eval_steps_per_second": 7.782,
|
| 1983 |
+
"step": 107625
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 41.14,
|
| 1987 |
+
"learning_rate": 0.002942857142857143,
|
| 1988 |
+
"loss": 0.7193,
|
| 1989 |
+
"step": 108000
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 41.33,
|
| 1993 |
+
"learning_rate": 0.0029333333333333334,
|
| 1994 |
+
"loss": 0.7162,
|
| 1995 |
+
"step": 108500
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 41.52,
|
| 1999 |
+
"learning_rate": 0.0029238095238095243,
|
| 2000 |
+
"loss": 0.7387,
|
| 2001 |
+
"step": 109000
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 41.71,
|
| 2005 |
+
"learning_rate": 0.0029142857142857143,
|
| 2006 |
+
"loss": 0.7592,
|
| 2007 |
+
"step": 109500
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 41.9,
|
| 2011 |
+
"learning_rate": 0.002904761904761905,
|
| 2012 |
+
"loss": 0.765,
|
| 2013 |
+
"step": 110000
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 42.0,
|
| 2017 |
+
"eval_accuracy": 0.6673335119526064,
|
| 2018 |
+
"eval_loss": 1.7770148515701294,
|
| 2019 |
+
"eval_runtime": 2711.4758,
|
| 2020 |
+
"eval_samples_per_second": 61.942,
|
| 2021 |
+
"eval_steps_per_second": 7.743,
|
| 2022 |
+
"step": 110250
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 42.1,
|
| 2026 |
+
"learning_rate": 0.0028952380952380953,
|
| 2027 |
+
"loss": 0.7184,
|
| 2028 |
+
"step": 110500
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 42.29,
|
| 2032 |
+
"learning_rate": 0.002885714285714286,
|
| 2033 |
+
"loss": 0.6956,
|
| 2034 |
+
"step": 111000
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 42.48,
|
| 2038 |
+
"learning_rate": 0.002876190476190476,
|
| 2039 |
+
"loss": 0.713,
|
| 2040 |
+
"step": 111500
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 42.67,
|
| 2044 |
+
"learning_rate": 0.0028666666666666667,
|
| 2045 |
+
"loss": 0.7328,
|
| 2046 |
+
"step": 112000
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 42.86,
|
| 2050 |
+
"learning_rate": 0.002857142857142857,
|
| 2051 |
+
"loss": 0.7417,
|
| 2052 |
+
"step": 112500
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 43.0,
|
| 2056 |
+
"eval_accuracy": 0.6685659849364413,
|
| 2057 |
+
"eval_loss": 1.8335988521575928,
|
| 2058 |
+
"eval_runtime": 4071.9751,
|
| 2059 |
+
"eval_samples_per_second": 41.247,
|
| 2060 |
+
"eval_steps_per_second": 5.156,
|
| 2061 |
+
"step": 112875
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 43.05,
|
| 2065 |
+
"learning_rate": 0.0028476190476190476,
|
| 2066 |
+
"loss": 0.7272,
|
| 2067 |
+
"step": 113000
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 43.24,
|
| 2071 |
+
"learning_rate": 0.002838095238095238,
|
| 2072 |
+
"loss": 0.6728,
|
| 2073 |
+
"step": 113500
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 43.43,
|
| 2077 |
+
"learning_rate": 0.0028285714285714286,
|
| 2078 |
+
"loss": 0.6954,
|
| 2079 |
+
"step": 114000
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 43.62,
|
| 2083 |
+
"learning_rate": 0.002819047619047619,
|
| 2084 |
+
"loss": 0.7025,
|
| 2085 |
+
"step": 114500
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 43.81,
|
| 2089 |
+
"learning_rate": 0.0028095238095238095,
|
| 2090 |
+
"loss": 0.7208,
|
| 2091 |
+
"step": 115000
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 44.0,
|
| 2095 |
+
"learning_rate": 0.0028000000000000004,
|
| 2096 |
+
"loss": 0.7214,
|
| 2097 |
+
"step": 115500
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 44.0,
|
| 2101 |
+
"eval_accuracy": 0.6755142746569022,
|
| 2102 |
+
"eval_loss": 1.7522037029266357,
|
| 2103 |
+
"eval_runtime": 3540.85,
|
| 2104 |
+
"eval_samples_per_second": 47.434,
|
| 2105 |
+
"eval_steps_per_second": 5.929,
|
| 2106 |
+
"step": 115500
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 44.19,
|
| 2110 |
+
"learning_rate": 0.0027904761904761904,
|
| 2111 |
+
"loss": 0.6433,
|
| 2112 |
+
"step": 116000
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 44.38,
|
| 2116 |
+
"learning_rate": 0.0027809523809523813,
|
| 2117 |
+
"loss": 0.6634,
|
| 2118 |
+
"step": 116500
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 44.57,
|
| 2122 |
+
"learning_rate": 0.0027714285714285714,
|
| 2123 |
+
"loss": 0.6854,
|
| 2124 |
+
"step": 117000
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 44.76,
|
| 2128 |
+
"learning_rate": 0.0027619047619047623,
|
| 2129 |
+
"loss": 0.7026,
|
| 2130 |
+
"step": 117500
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 44.95,
|
| 2134 |
+
"learning_rate": 0.0027523809523809523,
|
| 2135 |
+
"loss": 0.7113,
|
| 2136 |
+
"step": 118000
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 45.0,
|
| 2140 |
+
"eval_accuracy": 0.6773778690720729,
|
| 2141 |
+
"eval_loss": 1.7851730585098267,
|
| 2142 |
+
"eval_runtime": 2781.7496,
|
| 2143 |
+
"eval_samples_per_second": 60.377,
|
| 2144 |
+
"eval_steps_per_second": 7.547,
|
| 2145 |
+
"step": 118125
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 45.14,
|
| 2149 |
+
"learning_rate": 0.0027428571428571432,
|
| 2150 |
+
"loss": 0.6189,
|
| 2151 |
+
"step": 118500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 45.33,
|
| 2155 |
+
"learning_rate": 0.0027333333333333333,
|
| 2156 |
+
"loss": 0.6497,
|
| 2157 |
+
"step": 119000
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 45.52,
|
| 2161 |
+
"learning_rate": 0.0027238095238095237,
|
| 2162 |
+
"loss": 0.666,
|
| 2163 |
+
"step": 119500
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 45.71,
|
| 2167 |
+
"learning_rate": 0.0027142857142857142,
|
| 2168 |
+
"loss": 0.6832,
|
| 2169 |
+
"step": 120000
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 45.9,
|
| 2173 |
+
"learning_rate": 0.0027047619047619047,
|
| 2174 |
+
"loss": 0.6954,
|
| 2175 |
+
"step": 120500
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 46.0,
|
| 2179 |
+
"eval_accuracy": 0.6773719150963056,
|
| 2180 |
+
"eval_loss": 1.7557201385498047,
|
| 2181 |
+
"eval_runtime": 6130.4043,
|
| 2182 |
+
"eval_samples_per_second": 27.397,
|
| 2183 |
+
"eval_steps_per_second": 3.425,
|
| 2184 |
+
"step": 120750
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 46.1,
|
| 2188 |
+
"learning_rate": 0.002695238095238095,
|
| 2189 |
+
"loss": 0.6582,
|
| 2190 |
+
"step": 121000
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 46.29,
|
| 2194 |
+
"learning_rate": 0.0026857142857142856,
|
| 2195 |
+
"loss": 0.6174,
|
| 2196 |
+
"step": 121500
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 46.48,
|
| 2200 |
+
"learning_rate": 0.0026761904761904765,
|
| 2201 |
+
"loss": 0.6356,
|
| 2202 |
+
"step": 122000
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 46.67,
|
| 2206 |
+
"learning_rate": 0.0026666666666666666,
|
| 2207 |
+
"loss": 0.6565,
|
| 2208 |
+
"step": 122500
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 46.86,
|
| 2212 |
+
"learning_rate": 0.0026571428571428575,
|
| 2213 |
+
"loss": 0.6658,
|
| 2214 |
+
"step": 123000
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 47.0,
|
| 2218 |
+
"eval_accuracy": 0.678836593135066,
|
| 2219 |
+
"eval_loss": 1.8116456270217896,
|
| 2220 |
+
"eval_runtime": 5170.8601,
|
| 2221 |
+
"eval_samples_per_second": 32.481,
|
| 2222 |
+
"eval_steps_per_second": 4.06,
|
| 2223 |
+
"step": 123375
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 47.05,
|
| 2227 |
+
"learning_rate": 0.0026476190476190475,
|
| 2228 |
+
"loss": 0.6552,
|
| 2229 |
+
"step": 123500
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 47.24,
|
| 2233 |
+
"learning_rate": 0.0026380952380952384,
|
| 2234 |
+
"loss": 0.5994,
|
| 2235 |
+
"step": 124000
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 47.43,
|
| 2239 |
+
"learning_rate": 0.0026285714285714285,
|
| 2240 |
+
"loss": 0.6221,
|
| 2241 |
+
"step": 124500
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 47.62,
|
| 2245 |
+
"learning_rate": 0.0026190476190476194,
|
| 2246 |
+
"loss": 0.635,
|
| 2247 |
+
"step": 125000
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 47.81,
|
| 2251 |
+
"learning_rate": 0.0026095238095238094,
|
| 2252 |
+
"loss": 0.648,
|
| 2253 |
+
"step": 125500
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 48.0,
|
| 2257 |
+
"learning_rate": 0.0026000000000000003,
|
| 2258 |
+
"loss": 0.6593,
|
| 2259 |
+
"step": 126000
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 48.0,
|
| 2263 |
+
"eval_accuracy": 0.6829388824387485,
|
| 2264 |
+
"eval_loss": 1.8153612613677979,
|
| 2265 |
+
"eval_runtime": 3984.2658,
|
| 2266 |
+
"eval_samples_per_second": 42.155,
|
| 2267 |
+
"eval_steps_per_second": 5.269,
|
| 2268 |
+
"step": 126000
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 48.19,
|
| 2272 |
+
"learning_rate": 0.0025904761904761904,
|
| 2273 |
+
"loss": 0.58,
|
| 2274 |
+
"step": 126500
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 48.38,
|
| 2278 |
+
"learning_rate": 0.0025809523809523813,
|
| 2279 |
+
"loss": 0.5966,
|
| 2280 |
+
"step": 127000
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 48.57,
|
| 2284 |
+
"learning_rate": 0.0025714285714285713,
|
| 2285 |
+
"loss": 0.6184,
|
| 2286 |
+
"step": 127500
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 48.76,
|
| 2290 |
+
"learning_rate": 0.0025619047619047618,
|
| 2291 |
+
"loss": 0.6257,
|
| 2292 |
+
"step": 128000
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 48.95,
|
| 2296 |
+
"learning_rate": 0.0025523809523809527,
|
| 2297 |
+
"loss": 0.6384,
|
| 2298 |
+
"step": 128500
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 49.0,
|
| 2302 |
+
"eval_accuracy": 0.6795213003483076,
|
| 2303 |
+
"eval_loss": 1.7874691486358643,
|
| 2304 |
+
"eval_runtime": 3000.761,
|
| 2305 |
+
"eval_samples_per_second": 55.971,
|
| 2306 |
+
"eval_steps_per_second": 6.997,
|
| 2307 |
+
"step": 128625
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 49.14,
|
| 2311 |
+
"learning_rate": 0.0025428571428571427,
|
| 2312 |
+
"loss": 0.5834,
|
| 2313 |
+
"step": 129000
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 49.33,
|
| 2317 |
+
"learning_rate": 0.0025333333333333336,
|
| 2318 |
+
"loss": 0.5847,
|
| 2319 |
+
"step": 129500
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 49.52,
|
| 2323 |
+
"learning_rate": 0.0025238095238095237,
|
| 2324 |
+
"loss": 0.5981,
|
| 2325 |
+
"step": 130000
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 49.71,
|
| 2329 |
+
"learning_rate": 0.0025142857142857146,
|
| 2330 |
+
"loss": 0.6141,
|
| 2331 |
+
"step": 130500
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 49.9,
|
| 2335 |
+
"learning_rate": 0.0025047619047619046,
|
| 2336 |
+
"loss": 0.6257,
|
| 2337 |
+
"step": 131000
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 50.0,
|
| 2341 |
+
"eval_accuracy": 0.6811050579024144,
|
| 2342 |
+
"eval_loss": 1.882097840309143,
|
| 2343 |
+
"eval_runtime": 2757.9073,
|
| 2344 |
+
"eval_samples_per_second": 60.899,
|
| 2345 |
+
"eval_steps_per_second": 7.613,
|
| 2346 |
+
"step": 131250
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 50.1,
|
| 2350 |
+
"learning_rate": 0.0024952380952380955,
|
| 2351 |
+
"loss": 0.5799,
|
| 2352 |
+
"step": 131500
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 50.29,
|
| 2356 |
+
"learning_rate": 0.002485714285714286,
|
| 2357 |
+
"loss": 0.5715,
|
| 2358 |
+
"step": 132000
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 50.48,
|
| 2362 |
+
"learning_rate": 0.0024761904761904764,
|
| 2363 |
+
"loss": 0.5847,
|
| 2364 |
+
"step": 132500
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 50.67,
|
| 2368 |
+
"learning_rate": 0.002466666666666667,
|
| 2369 |
+
"loss": 0.5942,
|
| 2370 |
+
"step": 133000
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 50.86,
|
| 2374 |
+
"learning_rate": 0.0024571428571428574,
|
| 2375 |
+
"loss": 0.5999,
|
| 2376 |
+
"step": 133500
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 51.0,
|
| 2380 |
+
"eval_accuracy": 0.6871840671608467,
|
| 2381 |
+
"eval_loss": 1.8406310081481934,
|
| 2382 |
+
"eval_runtime": 2763.7082,
|
| 2383 |
+
"eval_samples_per_second": 60.772,
|
| 2384 |
+
"eval_steps_per_second": 7.597,
|
| 2385 |
+
"step": 133875
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 51.05,
|
| 2389 |
+
"learning_rate": 0.002447619047619048,
|
| 2390 |
+
"loss": 0.5872,
|
| 2391 |
+
"step": 134000
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 51.24,
|
| 2395 |
+
"learning_rate": 0.0024380952380952383,
|
| 2396 |
+
"loss": 0.5511,
|
| 2397 |
+
"step": 134500
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 51.43,
|
| 2401 |
+
"learning_rate": 0.002428571428571429,
|
| 2402 |
+
"loss": 0.5592,
|
| 2403 |
+
"step": 135000
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 51.62,
|
| 2407 |
+
"learning_rate": 0.002419047619047619,
|
| 2408 |
+
"loss": 0.5658,
|
| 2409 |
+
"step": 135500
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 51.81,
|
| 2413 |
+
"learning_rate": 0.0024095238095238093,
|
| 2414 |
+
"loss": 0.5887,
|
| 2415 |
+
"step": 136000
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 52.0,
|
| 2419 |
+
"learning_rate": 0.0024,
|
| 2420 |
+
"loss": 0.5924,
|
| 2421 |
+
"step": 136500
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 52.0,
|
| 2425 |
+
"eval_accuracy": 0.6764728647554404,
|
| 2426 |
+
"eval_loss": 1.9697257280349731,
|
| 2427 |
+
"eval_runtime": 2760.1617,
|
| 2428 |
+
"eval_samples_per_second": 60.85,
|
| 2429 |
+
"eval_steps_per_second": 7.606,
|
| 2430 |
+
"step": 136500
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 52.19,
|
| 2434 |
+
"learning_rate": 0.0023904761904761903,
|
| 2435 |
+
"loss": 0.5313,
|
| 2436 |
+
"step": 137000
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"epoch": 52.38,
|
| 2440 |
+
"learning_rate": 0.0023809523809523807,
|
| 2441 |
+
"loss": 0.5451,
|
| 2442 |
+
"step": 137500
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 52.57,
|
| 2446 |
+
"learning_rate": 0.0023714285714285716,
|
| 2447 |
+
"loss": 0.56,
|
| 2448 |
+
"step": 138000
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 52.76,
|
| 2452 |
+
"learning_rate": 0.002361904761904762,
|
| 2453 |
+
"loss": 0.5676,
|
| 2454 |
+
"step": 138500
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 52.95,
|
| 2458 |
+
"learning_rate": 0.0023523809523809526,
|
| 2459 |
+
"loss": 0.5812,
|
| 2460 |
+
"step": 139000
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 53.0,
|
| 2464 |
+
"eval_accuracy": 0.6818195349944925,
|
| 2465 |
+
"eval_loss": 1.9344266653060913,
|
| 2466 |
+
"eval_runtime": 2852.1671,
|
| 2467 |
+
"eval_samples_per_second": 58.887,
|
| 2468 |
+
"eval_steps_per_second": 7.361,
|
| 2469 |
+
"step": 139125
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 53.14,
|
| 2473 |
+
"learning_rate": 0.002342857142857143,
|
| 2474 |
+
"loss": 0.506,
|
| 2475 |
+
"step": 139500
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 53.33,
|
| 2479 |
+
"learning_rate": 0.0023333333333333335,
|
| 2480 |
+
"loss": 0.541,
|
| 2481 |
+
"step": 140000
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 53.52,
|
| 2485 |
+
"learning_rate": 0.002323809523809524,
|
| 2486 |
+
"loss": 0.5445,
|
| 2487 |
+
"step": 140500
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 53.71,
|
| 2491 |
+
"learning_rate": 0.0023142857142857145,
|
| 2492 |
+
"loss": 0.5547,
|
| 2493 |
+
"step": 141000
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 53.9,
|
| 2497 |
+
"learning_rate": 0.002304761904761905,
|
| 2498 |
+
"loss": 0.5521,
|
| 2499 |
+
"step": 141500
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 54.0,
|
| 2503 |
+
"eval_accuracy": 0.6802060075615493,
|
| 2504 |
+
"eval_loss": 1.9845408201217651,
|
| 2505 |
+
"eval_runtime": 3383.9959,
|
| 2506 |
+
"eval_samples_per_second": 49.632,
|
| 2507 |
+
"eval_steps_per_second": 6.204,
|
| 2508 |
+
"step": 141750
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 54.1,
|
| 2512 |
+
"learning_rate": 0.0022952380952380954,
|
| 2513 |
+
"loss": 0.5328,
|
| 2514 |
+
"step": 142000
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 54.29,
|
| 2518 |
+
"learning_rate": 0.002285714285714286,
|
| 2519 |
+
"loss": 0.5141,
|
| 2520 |
+
"step": 142500
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 54.48,
|
| 2524 |
+
"learning_rate": 0.0022761904761904764,
|
| 2525 |
+
"loss": 0.5266,
|
| 2526 |
+
"step": 143000
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"epoch": 54.67,
|
| 2530 |
+
"learning_rate": 0.0022666666666666664,
|
| 2531 |
+
"loss": 0.5354,
|
| 2532 |
+
"step": 143500
|
| 2533 |
+
},
|
| 2534 |
+
{
|
| 2535 |
+
"epoch": 54.86,
|
| 2536 |
+
"learning_rate": 0.002257142857142857,
|
| 2537 |
+
"loss": 0.556,
|
| 2538 |
+
"step": 144000
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 55.0,
|
| 2542 |
+
"eval_accuracy": 0.6826173677473133,
|
| 2543 |
+
"eval_loss": 2.0039005279541016,
|
| 2544 |
+
"eval_runtime": 2747.9149,
|
| 2545 |
+
"eval_samples_per_second": 61.121,
|
| 2546 |
+
"eval_steps_per_second": 7.64,
|
| 2547 |
+
"step": 144375
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 55.05,
|
| 2551 |
+
"learning_rate": 0.0022476190476190478,
|
| 2552 |
+
"loss": 0.5317,
|
| 2553 |
+
"step": 144500
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 55.24,
|
| 2557 |
+
"learning_rate": 0.0022380952380952382,
|
| 2558 |
+
"loss": 0.4956,
|
| 2559 |
+
"step": 145000
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 55.43,
|
| 2563 |
+
"learning_rate": 0.0022285714285714287,
|
| 2564 |
+
"loss": 0.512,
|
| 2565 |
+
"step": 145500
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 55.62,
|
| 2569 |
+
"learning_rate": 0.002219047619047619,
|
| 2570 |
+
"loss": 0.5243,
|
| 2571 |
+
"step": 146000
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 55.81,
|
| 2575 |
+
"learning_rate": 0.0022095238095238097,
|
| 2576 |
+
"loss": 0.5283,
|
| 2577 |
+
"step": 146500
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 56.0,
|
| 2581 |
+
"learning_rate": 0.0022,
|
| 2582 |
+
"loss": 0.5412,
|
| 2583 |
+
"step": 147000
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 56.0,
|
| 2587 |
+
"eval_accuracy": 0.6856896192432497,
|
| 2588 |
+
"eval_loss": 1.9339253902435303,
|
| 2589 |
+
"eval_runtime": 3227.3643,
|
| 2590 |
+
"eval_samples_per_second": 52.041,
|
| 2591 |
+
"eval_steps_per_second": 6.505,
|
| 2592 |
+
"step": 147000
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 56.19,
|
| 2596 |
+
"learning_rate": 0.0021904761904761906,
|
| 2597 |
+
"loss": 0.4902,
|
| 2598 |
+
"step": 147500
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 56.38,
|
| 2602 |
+
"learning_rate": 0.002180952380952381,
|
| 2603 |
+
"loss": 0.4989,
|
| 2604 |
+
"step": 148000
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 56.57,
|
| 2608 |
+
"learning_rate": 0.0021714285714285715,
|
| 2609 |
+
"loss": 0.4979,
|
| 2610 |
+
"step": 148500
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 56.76,
|
| 2614 |
+
"learning_rate": 0.002161904761904762,
|
| 2615 |
+
"loss": 0.5194,
|
| 2616 |
+
"step": 149000
|
| 2617 |
+
},
|
| 2618 |
+
{
|
| 2619 |
+
"epoch": 56.95,
|
| 2620 |
+
"learning_rate": 0.0021523809523809525,
|
| 2621 |
+
"loss": 0.5204,
|
| 2622 |
+
"step": 149500
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 57.0,
|
| 2626 |
+
"eval_accuracy": 0.6872436069185198,
|
| 2627 |
+
"eval_loss": 2.0444183349609375,
|
| 2628 |
+
"eval_runtime": 2731.7184,
|
| 2629 |
+
"eval_samples_per_second": 61.483,
|
| 2630 |
+
"eval_steps_per_second": 7.686,
|
| 2631 |
+
"step": 149625
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 57.14,
|
| 2635 |
+
"learning_rate": 0.002142857142857143,
|
| 2636 |
+
"loss": 0.4842,
|
| 2637 |
+
"step": 150000
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 57.33,
|
| 2641 |
+
"learning_rate": 0.0021333333333333334,
|
| 2642 |
+
"loss": 0.4815,
|
| 2643 |
+
"step": 150500
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 57.52,
|
| 2647 |
+
"learning_rate": 0.002123809523809524,
|
| 2648 |
+
"loss": 0.4911,
|
| 2649 |
+
"step": 151000
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 57.71,
|
| 2653 |
+
"learning_rate": 0.0021142857142857144,
|
| 2654 |
+
"loss": 0.4954,
|
| 2655 |
+
"step": 151500
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 57.9,
|
| 2659 |
+
"learning_rate": 0.002104761904761905,
|
| 2660 |
+
"loss": 0.5051,
|
| 2661 |
+
"step": 152000
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 58.0,
|
| 2665 |
+
"eval_accuracy": 0.689601381322378,
|
| 2666 |
+
"eval_loss": 1.9677560329437256,
|
| 2667 |
+
"eval_runtime": 2701.9047,
|
| 2668 |
+
"eval_samples_per_second": 62.162,
|
| 2669 |
+
"eval_steps_per_second": 7.77,
|
| 2670 |
+
"step": 152250
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 58.1,
|
| 2674 |
+
"learning_rate": 0.0020952380952380953,
|
| 2675 |
+
"loss": 0.4901,
|
| 2676 |
+
"step": 152500
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 58.29,
|
| 2680 |
+
"learning_rate": 0.002085714285714286,
|
| 2681 |
+
"loss": 0.4763,
|
| 2682 |
+
"step": 153000
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 58.48,
|
| 2686 |
+
"learning_rate": 0.0020761904761904763,
|
| 2687 |
+
"loss": 0.4806,
|
| 2688 |
+
"step": 153500
|
| 2689 |
+
},
|
| 2690 |
+
{
|
| 2691 |
+
"epoch": 58.67,
|
| 2692 |
+
"learning_rate": 0.0020666666666666667,
|
| 2693 |
+
"loss": 0.4858,
|
| 2694 |
+
"step": 154000
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 58.86,
|
| 2698 |
+
"learning_rate": 0.002057142857142857,
|
| 2699 |
+
"loss": 0.4977,
|
| 2700 |
+
"step": 154500
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 59.0,
|
| 2704 |
+
"eval_accuracy": 0.6877735107618111,
|
| 2705 |
+
"eval_loss": 2.0384891033172607,
|
| 2706 |
+
"eval_runtime": 2728.0396,
|
| 2707 |
+
"eval_samples_per_second": 61.566,
|
| 2708 |
+
"eval_steps_per_second": 7.696,
|
| 2709 |
+
"step": 154875
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 59.05,
|
| 2713 |
+
"learning_rate": 0.0020476190476190477,
|
| 2714 |
+
"loss": 0.483,
|
| 2715 |
+
"step": 155000
|
| 2716 |
+
},
|
| 2717 |
+
{
|
| 2718 |
+
"epoch": 59.24,
|
| 2719 |
+
"learning_rate": 0.002038095238095238,
|
| 2720 |
+
"loss": 0.4575,
|
| 2721 |
+
"step": 155500
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 59.43,
|
| 2725 |
+
"learning_rate": 0.0020285714285714286,
|
| 2726 |
+
"loss": 0.4705,
|
| 2727 |
+
"step": 156000
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 59.62,
|
| 2731 |
+
"learning_rate": 0.002019047619047619,
|
| 2732 |
+
"loss": 0.4846,
|
| 2733 |
+
"step": 156500
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 59.81,
|
| 2737 |
+
"learning_rate": 0.0020095238095238096,
|
| 2738 |
+
"loss": 0.4872,
|
| 2739 |
+
"step": 157000
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 60.0,
|
| 2743 |
+
"learning_rate": 0.002,
|
| 2744 |
+
"loss": 0.4932,
|
| 2745 |
+
"step": 157500
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 60.0,
|
| 2749 |
+
"eval_accuracy": 0.6890178916971808,
|
| 2750 |
+
"eval_loss": 2.05938720703125,
|
| 2751 |
+
"eval_runtime": 2847.0911,
|
| 2752 |
+
"eval_samples_per_second": 58.992,
|
| 2753 |
+
"eval_steps_per_second": 7.374,
|
| 2754 |
+
"step": 157500
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 60.19,
|
| 2758 |
+
"learning_rate": 0.0019904761904761905,
|
| 2759 |
+
"loss": 0.4454,
|
| 2760 |
+
"step": 158000
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 60.38,
|
| 2764 |
+
"learning_rate": 0.001980952380952381,
|
| 2765 |
+
"loss": 0.4559,
|
| 2766 |
+
"step": 158500
|
| 2767 |
+
},
|
| 2768 |
+
{
|
| 2769 |
+
"epoch": 60.57,
|
| 2770 |
+
"learning_rate": 0.0019714285714285715,
|
| 2771 |
+
"loss": 0.46,
|
| 2772 |
+
"step": 159000
|
| 2773 |
+
},
|
| 2774 |
+
{
|
| 2775 |
+
"epoch": 60.76,
|
| 2776 |
+
"learning_rate": 0.001961904761904762,
|
| 2777 |
+
"loss": 0.472,
|
| 2778 |
+
"step": 159500
|
| 2779 |
+
},
|
| 2780 |
+
{
|
| 2781 |
+
"epoch": 60.95,
|
| 2782 |
+
"learning_rate": 0.0019523809523809524,
|
| 2783 |
+
"loss": 0.4689,
|
| 2784 |
+
"step": 160000
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 61.0,
|
| 2788 |
+
"eval_accuracy": 0.6834806942335745,
|
| 2789 |
+
"eval_loss": 2.1333200931549072,
|
| 2790 |
+
"eval_runtime": 3489.1293,
|
| 2791 |
+
"eval_samples_per_second": 48.137,
|
| 2792 |
+
"eval_steps_per_second": 6.017,
|
| 2793 |
+
"step": 160125
|
| 2794 |
+
},
|
| 2795 |
+
{
|
| 2796 |
+
"epoch": 61.14,
|
| 2797 |
+
"learning_rate": 0.0019428571428571429,
|
| 2798 |
+
"loss": 0.4402,
|
| 2799 |
+
"step": 160500
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 61.33,
|
| 2803 |
+
"learning_rate": 0.0019333333333333333,
|
| 2804 |
+
"loss": 0.445,
|
| 2805 |
+
"step": 161000
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 61.52,
|
| 2809 |
+
"learning_rate": 0.0019238095238095238,
|
| 2810 |
+
"loss": 0.4504,
|
| 2811 |
+
"step": 161500
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 61.71,
|
| 2815 |
+
"learning_rate": 0.0019142857142857143,
|
| 2816 |
+
"loss": 0.4577,
|
| 2817 |
+
"step": 162000
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 61.9,
|
| 2821 |
+
"learning_rate": 0.0019047619047619048,
|
| 2822 |
+
"loss": 0.4652,
|
| 2823 |
+
"step": 162500
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 62.0,
|
| 2827 |
+
"eval_accuracy": 0.6899228960138132,
|
| 2828 |
+
"eval_loss": 2.1436057090759277,
|
| 2829 |
+
"eval_runtime": 2832.828,
|
| 2830 |
+
"eval_samples_per_second": 59.289,
|
| 2831 |
+
"eval_steps_per_second": 7.411,
|
| 2832 |
+
"step": 162750
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 62.1,
|
| 2836 |
+
"learning_rate": 0.0018952380952380952,
|
| 2837 |
+
"loss": 0.4362,
|
| 2838 |
+
"step": 163000
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 62.29,
|
| 2842 |
+
"learning_rate": 0.001885714285714286,
|
| 2843 |
+
"loss": 0.4351,
|
| 2844 |
+
"step": 163500
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 62.48,
|
| 2848 |
+
"learning_rate": 0.0018761904761904764,
|
| 2849 |
+
"loss": 0.4404,
|
| 2850 |
+
"step": 164000
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"epoch": 62.67,
|
| 2854 |
+
"learning_rate": 0.0018666666666666669,
|
| 2855 |
+
"loss": 0.4443,
|
| 2856 |
+
"step": 164500
|
| 2857 |
+
},
|
| 2858 |
+
{
|
| 2859 |
+
"epoch": 62.86,
|
| 2860 |
+
"learning_rate": 0.0018571428571428573,
|
| 2861 |
+
"loss": 0.4515,
|
| 2862 |
+
"step": 165000
|
| 2863 |
+
},
|
| 2864 |
+
{
|
| 2865 |
+
"epoch": 63.0,
|
| 2866 |
+
"eval_accuracy": 0.6923283022238099,
|
| 2867 |
+
"eval_loss": 2.1558289527893066,
|
| 2868 |
+
"eval_runtime": 2793.0236,
|
| 2869 |
+
"eval_samples_per_second": 60.134,
|
| 2870 |
+
"eval_steps_per_second": 7.517,
|
| 2871 |
+
"step": 165375
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 63.05,
|
| 2875 |
+
"learning_rate": 0.0018476190476190476,
|
| 2876 |
+
"loss": 0.4448,
|
| 2877 |
+
"step": 165500
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"epoch": 63.24,
|
| 2881 |
+
"learning_rate": 0.001838095238095238,
|
| 2882 |
+
"loss": 0.4217,
|
| 2883 |
+
"step": 166000
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 63.43,
|
| 2887 |
+
"learning_rate": 0.0018285714285714285,
|
| 2888 |
+
"loss": 0.4293,
|
| 2889 |
+
"step": 166500
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 63.62,
|
| 2893 |
+
"learning_rate": 0.001819047619047619,
|
| 2894 |
+
"loss": 0.4295,
|
| 2895 |
+
"step": 167000
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 63.81,
|
| 2899 |
+
"learning_rate": 0.0018095238095238095,
|
| 2900 |
+
"loss": 0.4383,
|
| 2901 |
+
"step": 167500
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 64.0,
|
| 2905 |
+
"learning_rate": 0.0018,
|
| 2906 |
+
"loss": 0.4542,
|
| 2907 |
+
"step": 168000
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 64.0,
|
| 2911 |
+
"eval_accuracy": 0.6934059718376946,
|
| 2912 |
+
"eval_loss": 2.0637614727020264,
|
| 2913 |
+
"eval_runtime": 2998.8188,
|
| 2914 |
+
"eval_samples_per_second": 56.007,
|
| 2915 |
+
"eval_steps_per_second": 7.001,
|
| 2916 |
+
"step": 168000
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 64.0,
|
| 2920 |
+
"step": 168000,
|
| 2921 |
+
"total_flos": 4.5354579076109147e+21,
|
| 2922 |
+
"train_loss": 0.0,
|
| 2923 |
+
"train_runtime": 758.3182,
|
| 2924 |
+
"train_samples_per_second": 53155.811,
|
| 2925 |
+
"train_steps_per_second": 207.696
|
| 2926 |
}
|
| 2927 |
],
|
| 2928 |
"logging_steps": 500,
|
| 2929 |
+
"max_steps": 157500,
|
| 2930 |
+
"num_train_epochs": 60,
|
| 2931 |
"save_steps": 500,
|
| 2932 |
+
"total_flos": 4.5354579076109147e+21,
|
| 2933 |
"trial_name": null,
|
| 2934 |
"trial_params": null
|
| 2935 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a25946f7825b00ddb42330dbeeb0f0a0fa0970c7672d1e70207329539d0944b1
|
| 3 |
size 4792
|