End of training
Browse files- README.md +7 -7
- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Jul25_17-40-11_8840352ede30/events.out.tfevents.1721929633.8840352ede30.506.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1614 -0
README.md
CHANGED
|
@@ -25,13 +25,13 @@ model-index:
|
|
| 25 |
metrics:
|
| 26 |
- name: Accuracy
|
| 27 |
type: accuracy
|
| 28 |
-
value: 0.
|
| 29 |
- name: F1
|
| 30 |
type: f1
|
| 31 |
-
value: 0.
|
| 32 |
- name: Precision
|
| 33 |
type: precision
|
| 34 |
-
value: 0.
|
| 35 |
- name: Recall
|
| 36 |
type: recall
|
| 37 |
value: 0.8008849557522124
|
|
@@ -44,10 +44,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 44 |
|
| 45 |
This model is a fine-tuned version of [apple/mobilevitv2-1.0-imagenet1k-256](https://huggingface.co/apple/mobilevitv2-1.0-imagenet1k-256) on the webdataset dataset.
|
| 46 |
It achieves the following results on the evaluation set:
|
| 47 |
-
- Loss: 0.
|
| 48 |
-
- Accuracy: 0.
|
| 49 |
-
- F1: 0.
|
| 50 |
-
- Precision: 0.
|
| 51 |
- Recall: 0.8009
|
| 52 |
|
| 53 |
## Model description
|
|
|
|
| 25 |
metrics:
|
| 26 |
- name: Accuracy
|
| 27 |
type: accuracy
|
| 28 |
+
value: 0.9309734513274336
|
| 29 |
- name: F1
|
| 30 |
type: f1
|
| 31 |
+
value: 0.8227272727272726
|
| 32 |
- name: Precision
|
| 33 |
type: precision
|
| 34 |
+
value: 0.8457943925233645
|
| 35 |
- name: Recall
|
| 36 |
type: recall
|
| 37 |
value: 0.8008849557522124
|
|
|
|
| 44 |
|
| 45 |
This model is a fine-tuned version of [apple/mobilevitv2-1.0-imagenet1k-256](https://huggingface.co/apple/mobilevitv2-1.0-imagenet1k-256) on the webdataset dataset.
|
| 46 |
It achieves the following results on the evaluation set:
|
| 47 |
+
- Loss: 0.1896
|
| 48 |
+
- Accuracy: 0.9310
|
| 49 |
+
- F1: 0.8227
|
| 50 |
+
- Precision: 0.8458
|
| 51 |
- Recall: 0.8009
|
| 52 |
|
| 53 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.9309734513274336,
|
| 4 |
+
"eval_f1": 0.8227272727272726,
|
| 5 |
+
"eval_loss": 0.18961240351200104,
|
| 6 |
+
"eval_precision": 0.8457943925233645,
|
| 7 |
+
"eval_recall": 0.8008849557522124,
|
| 8 |
+
"eval_runtime": 1.0942,
|
| 9 |
+
"eval_samples_per_second": 103.267,
|
| 10 |
+
"eval_steps_per_second": 13.708,
|
| 11 |
+
"total_flos": 1.9916656541540352e+17,
|
| 12 |
+
"train_loss": 0.1991663834390541,
|
| 13 |
+
"train_runtime": 388.9258,
|
| 14 |
+
"train_samples_per_second": 78.061,
|
| 15 |
+
"train_steps_per_second": 4.937
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.9309734513274336,
|
| 4 |
+
"eval_f1": 0.8227272727272726,
|
| 5 |
+
"eval_loss": 0.18961240351200104,
|
| 6 |
+
"eval_precision": 0.8457943925233645,
|
| 7 |
+
"eval_recall": 0.8008849557522124,
|
| 8 |
+
"eval_runtime": 1.0942,
|
| 9 |
+
"eval_samples_per_second": 103.267,
|
| 10 |
+
"eval_steps_per_second": 13.708
|
| 11 |
+
}
|
runs/Jul25_17-40-11_8840352ede30/events.out.tfevents.1721929633.8840352ede30.506.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95e54f885eef0946742d39a8ef61697298dcba7ec66c3e33fb7a0bc72a94b7b2
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"total_flos": 1.9916656541540352e+17,
|
| 4 |
+
"train_loss": 0.1991663834390541,
|
| 5 |
+
"train_runtime": 388.9258,
|
| 6 |
+
"train_samples_per_second": 78.061,
|
| 7 |
+
"train_steps_per_second": 4.937
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1614 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.18961240351200104,
|
| 3 |
+
"best_model_checkpoint": "mobilevitv2-1.0-imagenet1k-256-finetuned_v2024-7-25-frost/checkpoint-1000",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1920,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.15625,
|
| 13 |
+
"grad_norm": 0.2519198954105377,
|
| 14 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 15 |
+
"loss": 0.6958,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3125,
|
| 20 |
+
"grad_norm": 0.21561957895755768,
|
| 21 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 22 |
+
"loss": 0.6958,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.46875,
|
| 27 |
+
"grad_norm": 0.2186066061258316,
|
| 28 |
+
"learning_rate": 3.125e-05,
|
| 29 |
+
"loss": 0.6948,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.625,
|
| 34 |
+
"grad_norm": 0.22916783392429352,
|
| 35 |
+
"learning_rate": 4.166666666666667e-05,
|
| 36 |
+
"loss": 0.6934,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.78125,
|
| 41 |
+
"grad_norm": 0.23298271000385284,
|
| 42 |
+
"learning_rate": 5.208333333333334e-05,
|
| 43 |
+
"loss": 0.691,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9375,
|
| 48 |
+
"grad_norm": 0.24950967729091644,
|
| 49 |
+
"learning_rate": 6.25e-05,
|
| 50 |
+
"loss": 0.6895,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.09375,
|
| 55 |
+
"grad_norm": 0.23937764763832092,
|
| 56 |
+
"learning_rate": 7.291666666666667e-05,
|
| 57 |
+
"loss": 0.684,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.25,
|
| 62 |
+
"grad_norm": 0.23057785630226135,
|
| 63 |
+
"learning_rate": 8.333333333333334e-05,
|
| 64 |
+
"loss": 0.6794,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.40625,
|
| 69 |
+
"grad_norm": 0.2983661890029907,
|
| 70 |
+
"learning_rate": 9.375e-05,
|
| 71 |
+
"loss": 0.6751,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.5625,
|
| 76 |
+
"grad_norm": 0.2652019262313843,
|
| 77 |
+
"learning_rate": 0.00010416666666666667,
|
| 78 |
+
"loss": 0.6687,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.5625,
|
| 83 |
+
"eval_accuracy": 0.7230088495575221,
|
| 84 |
+
"eval_f1": 0.5335320417287631,
|
| 85 |
+
"eval_loss": 0.6623277068138123,
|
| 86 |
+
"eval_precision": 0.40224719101123596,
|
| 87 |
+
"eval_recall": 0.7920353982300885,
|
| 88 |
+
"eval_runtime": 1.2295,
|
| 89 |
+
"eval_samples_per_second": 91.909,
|
| 90 |
+
"eval_steps_per_second": 12.2,
|
| 91 |
+
"step": 100
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.71875,
|
| 95 |
+
"grad_norm": 0.34594935178756714,
|
| 96 |
+
"learning_rate": 0.00011458333333333333,
|
| 97 |
+
"loss": 0.6586,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.875,
|
| 102 |
+
"grad_norm": 0.26900964975357056,
|
| 103 |
+
"learning_rate": 0.000125,
|
| 104 |
+
"loss": 0.6476,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.03125,
|
| 109 |
+
"grad_norm": 0.30181896686553955,
|
| 110 |
+
"learning_rate": 0.0001354166666666667,
|
| 111 |
+
"loss": 0.6336,
|
| 112 |
+
"step": 130
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.1875,
|
| 116 |
+
"grad_norm": 0.33757150173187256,
|
| 117 |
+
"learning_rate": 0.00014583333333333335,
|
| 118 |
+
"loss": 0.6079,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.34375,
|
| 123 |
+
"grad_norm": 0.54989093542099,
|
| 124 |
+
"learning_rate": 0.00015625,
|
| 125 |
+
"loss": 0.5823,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.5,
|
| 130 |
+
"grad_norm": 0.6273936629295349,
|
| 131 |
+
"learning_rate": 0.0001666666666666667,
|
| 132 |
+
"loss": 0.5598,
|
| 133 |
+
"step": 160
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.65625,
|
| 137 |
+
"grad_norm": 0.46115073561668396,
|
| 138 |
+
"learning_rate": 0.00017708333333333335,
|
| 139 |
+
"loss": 0.5239,
|
| 140 |
+
"step": 170
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.8125,
|
| 144 |
+
"grad_norm": 0.47255411744117737,
|
| 145 |
+
"learning_rate": 0.0001875,
|
| 146 |
+
"loss": 0.4972,
|
| 147 |
+
"step": 180
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.96875,
|
| 151 |
+
"grad_norm": 0.522071361541748,
|
| 152 |
+
"learning_rate": 0.0001979166666666667,
|
| 153 |
+
"loss": 0.4617,
|
| 154 |
+
"step": 190
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 3.125,
|
| 158 |
+
"grad_norm": 1.0379081964492798,
|
| 159 |
+
"learning_rate": 0.0001990740740740741,
|
| 160 |
+
"loss": 0.4454,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.125,
|
| 165 |
+
"eval_accuracy": 0.8831858407079646,
|
| 166 |
+
"eval_f1": 0.7490494296577946,
|
| 167 |
+
"eval_loss": 0.41519004106521606,
|
| 168 |
+
"eval_precision": 0.6566666666666666,
|
| 169 |
+
"eval_recall": 0.8716814159292036,
|
| 170 |
+
"eval_runtime": 0.9401,
|
| 171 |
+
"eval_samples_per_second": 120.203,
|
| 172 |
+
"eval_steps_per_second": 15.956,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.28125,
|
| 177 |
+
"grad_norm": 0.545850932598114,
|
| 178 |
+
"learning_rate": 0.0001979166666666667,
|
| 179 |
+
"loss": 0.4247,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.4375,
|
| 184 |
+
"grad_norm": 0.7891977429389954,
|
| 185 |
+
"learning_rate": 0.00019675925925925926,
|
| 186 |
+
"loss": 0.4041,
|
| 187 |
+
"step": 220
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 3.59375,
|
| 191 |
+
"grad_norm": 1.542927861213684,
|
| 192 |
+
"learning_rate": 0.00019560185185185186,
|
| 193 |
+
"loss": 0.3845,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.75,
|
| 198 |
+
"grad_norm": 0.44223108887672424,
|
| 199 |
+
"learning_rate": 0.00019444444444444446,
|
| 200 |
+
"loss": 0.3278,
|
| 201 |
+
"step": 240
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 3.90625,
|
| 205 |
+
"grad_norm": 0.8207859396934509,
|
| 206 |
+
"learning_rate": 0.00019328703703703706,
|
| 207 |
+
"loss": 0.3507,
|
| 208 |
+
"step": 250
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 4.0625,
|
| 212 |
+
"grad_norm": 0.42037203907966614,
|
| 213 |
+
"learning_rate": 0.00019212962962962963,
|
| 214 |
+
"loss": 0.3481,
|
| 215 |
+
"step": 260
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.21875,
|
| 219 |
+
"grad_norm": 1.829210877418518,
|
| 220 |
+
"learning_rate": 0.00019097222222222223,
|
| 221 |
+
"loss": 0.3133,
|
| 222 |
+
"step": 270
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 4.375,
|
| 226 |
+
"grad_norm": 1.213773250579834,
|
| 227 |
+
"learning_rate": 0.00018981481481481483,
|
| 228 |
+
"loss": 0.2934,
|
| 229 |
+
"step": 280
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 4.53125,
|
| 233 |
+
"grad_norm": 0.6154431104660034,
|
| 234 |
+
"learning_rate": 0.00018865740740740743,
|
| 235 |
+
"loss": 0.2923,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.6875,
|
| 240 |
+
"grad_norm": 0.3814193606376648,
|
| 241 |
+
"learning_rate": 0.0001875,
|
| 242 |
+
"loss": 0.2835,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 4.6875,
|
| 247 |
+
"eval_accuracy": 0.9097345132743363,
|
| 248 |
+
"eval_f1": 0.7660550458715596,
|
| 249 |
+
"eval_loss": 0.26609960198402405,
|
| 250 |
+
"eval_precision": 0.7952380952380952,
|
| 251 |
+
"eval_recall": 0.7389380530973452,
|
| 252 |
+
"eval_runtime": 1.4414,
|
| 253 |
+
"eval_samples_per_second": 78.394,
|
| 254 |
+
"eval_steps_per_second": 10.406,
|
| 255 |
+
"step": 300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.84375,
|
| 259 |
+
"grad_norm": 0.4515719711780548,
|
| 260 |
+
"learning_rate": 0.0001863425925925926,
|
| 261 |
+
"loss": 0.2672,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 5.0,
|
| 266 |
+
"grad_norm": 2.077721357345581,
|
| 267 |
+
"learning_rate": 0.0001851851851851852,
|
| 268 |
+
"loss": 0.2914,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 5.15625,
|
| 273 |
+
"grad_norm": 0.9644371867179871,
|
| 274 |
+
"learning_rate": 0.00018402777777777778,
|
| 275 |
+
"loss": 0.2527,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 5.3125,
|
| 280 |
+
"grad_norm": 0.8245725631713867,
|
| 281 |
+
"learning_rate": 0.00018287037037037038,
|
| 282 |
+
"loss": 0.2477,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 5.46875,
|
| 287 |
+
"grad_norm": 0.5262947082519531,
|
| 288 |
+
"learning_rate": 0.00018171296296296297,
|
| 289 |
+
"loss": 0.2452,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 5.625,
|
| 294 |
+
"grad_norm": 0.6464282870292664,
|
| 295 |
+
"learning_rate": 0.00018055555555555557,
|
| 296 |
+
"loss": 0.2308,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 5.78125,
|
| 301 |
+
"grad_norm": 0.6029626131057739,
|
| 302 |
+
"learning_rate": 0.00017939814814814815,
|
| 303 |
+
"loss": 0.233,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 5.9375,
|
| 308 |
+
"grad_norm": 0.683201789855957,
|
| 309 |
+
"learning_rate": 0.00017824074074074075,
|
| 310 |
+
"loss": 0.2258,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 6.09375,
|
| 315 |
+
"grad_norm": 0.5622811317443848,
|
| 316 |
+
"learning_rate": 0.00017708333333333335,
|
| 317 |
+
"loss": 0.2342,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 6.25,
|
| 322 |
+
"grad_norm": 0.5229126214981079,
|
| 323 |
+
"learning_rate": 0.00017592592592592595,
|
| 324 |
+
"loss": 0.2197,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 6.25,
|
| 329 |
+
"eval_accuracy": 0.9194690265486726,
|
| 330 |
+
"eval_f1": 0.7868852459016394,
|
| 331 |
+
"eval_loss": 0.21510393917560577,
|
| 332 |
+
"eval_precision": 0.835820895522388,
|
| 333 |
+
"eval_recall": 0.7433628318584071,
|
| 334 |
+
"eval_runtime": 0.9737,
|
| 335 |
+
"eval_samples_per_second": 116.048,
|
| 336 |
+
"eval_steps_per_second": 15.405,
|
| 337 |
+
"step": 400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 6.40625,
|
| 341 |
+
"grad_norm": 0.5103662610054016,
|
| 342 |
+
"learning_rate": 0.00017476851851851852,
|
| 343 |
+
"loss": 0.2084,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.5625,
|
| 348 |
+
"grad_norm": 1.2655210494995117,
|
| 349 |
+
"learning_rate": 0.00017361111111111112,
|
| 350 |
+
"loss": 0.2005,
|
| 351 |
+
"step": 420
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.71875,
|
| 355 |
+
"grad_norm": 0.5232699513435364,
|
| 356 |
+
"learning_rate": 0.00017245370370370372,
|
| 357 |
+
"loss": 0.2296,
|
| 358 |
+
"step": 430
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 6.875,
|
| 362 |
+
"grad_norm": 0.8142613172531128,
|
| 363 |
+
"learning_rate": 0.00017129629629629632,
|
| 364 |
+
"loss": 0.187,
|
| 365 |
+
"step": 440
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 7.03125,
|
| 369 |
+
"grad_norm": 0.9919219017028809,
|
| 370 |
+
"learning_rate": 0.0001701388888888889,
|
| 371 |
+
"loss": 0.2027,
|
| 372 |
+
"step": 450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 7.1875,
|
| 376 |
+
"grad_norm": 1.2590153217315674,
|
| 377 |
+
"learning_rate": 0.0001689814814814815,
|
| 378 |
+
"loss": 0.1873,
|
| 379 |
+
"step": 460
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 7.34375,
|
| 383 |
+
"grad_norm": 0.6513100266456604,
|
| 384 |
+
"learning_rate": 0.0001678240740740741,
|
| 385 |
+
"loss": 0.1939,
|
| 386 |
+
"step": 470
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 7.5,
|
| 390 |
+
"grad_norm": 1.0872722864151,
|
| 391 |
+
"learning_rate": 0.0001666666666666667,
|
| 392 |
+
"loss": 0.2156,
|
| 393 |
+
"step": 480
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 7.65625,
|
| 397 |
+
"grad_norm": 0.3712750971317291,
|
| 398 |
+
"learning_rate": 0.00016550925925925926,
|
| 399 |
+
"loss": 0.1968,
|
| 400 |
+
"step": 490
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 7.8125,
|
| 404 |
+
"grad_norm": 0.8672028183937073,
|
| 405 |
+
"learning_rate": 0.00016435185185185186,
|
| 406 |
+
"loss": 0.1613,
|
| 407 |
+
"step": 500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 7.8125,
|
| 411 |
+
"eval_accuracy": 0.9292035398230089,
|
| 412 |
+
"eval_f1": 0.813953488372093,
|
| 413 |
+
"eval_loss": 0.20068036019802094,
|
| 414 |
+
"eval_precision": 0.8578431372549019,
|
| 415 |
+
"eval_recall": 0.7743362831858407,
|
| 416 |
+
"eval_runtime": 0.9681,
|
| 417 |
+
"eval_samples_per_second": 116.722,
|
| 418 |
+
"eval_steps_per_second": 15.494,
|
| 419 |
+
"step": 500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 7.96875,
|
| 423 |
+
"grad_norm": 1.2281358242034912,
|
| 424 |
+
"learning_rate": 0.00016319444444444446,
|
| 425 |
+
"loss": 0.1864,
|
| 426 |
+
"step": 510
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 8.125,
|
| 430 |
+
"grad_norm": 1.1462125778198242,
|
| 431 |
+
"learning_rate": 0.00016203703703703706,
|
| 432 |
+
"loss": 0.1743,
|
| 433 |
+
"step": 520
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 8.28125,
|
| 437 |
+
"grad_norm": 0.5552182197570801,
|
| 438 |
+
"learning_rate": 0.00016087962962962963,
|
| 439 |
+
"loss": 0.1963,
|
| 440 |
+
"step": 530
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 8.4375,
|
| 444 |
+
"grad_norm": 0.8015744686126709,
|
| 445 |
+
"learning_rate": 0.00015972222222222223,
|
| 446 |
+
"loss": 0.1987,
|
| 447 |
+
"step": 540
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 8.59375,
|
| 451 |
+
"grad_norm": 0.8516111969947815,
|
| 452 |
+
"learning_rate": 0.00015856481481481483,
|
| 453 |
+
"loss": 0.1753,
|
| 454 |
+
"step": 550
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 8.75,
|
| 458 |
+
"grad_norm": 1.3942711353302002,
|
| 459 |
+
"learning_rate": 0.00015740740740740743,
|
| 460 |
+
"loss": 0.1577,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 8.90625,
|
| 465 |
+
"grad_norm": 0.812676191329956,
|
| 466 |
+
"learning_rate": 0.00015625,
|
| 467 |
+
"loss": 0.1726,
|
| 468 |
+
"step": 570
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 9.0625,
|
| 472 |
+
"grad_norm": 0.567040205001831,
|
| 473 |
+
"learning_rate": 0.0001550925925925926,
|
| 474 |
+
"loss": 0.1665,
|
| 475 |
+
"step": 580
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 9.21875,
|
| 479 |
+
"grad_norm": 0.7389497756958008,
|
| 480 |
+
"learning_rate": 0.0001539351851851852,
|
| 481 |
+
"loss": 0.1445,
|
| 482 |
+
"step": 590
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 9.375,
|
| 486 |
+
"grad_norm": 0.6939622163772583,
|
| 487 |
+
"learning_rate": 0.00015277777777777777,
|
| 488 |
+
"loss": 0.1655,
|
| 489 |
+
"step": 600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 9.375,
|
| 493 |
+
"eval_accuracy": 0.9309734513274336,
|
| 494 |
+
"eval_f1": 0.8227272727272726,
|
| 495 |
+
"eval_loss": 0.1935483068227768,
|
| 496 |
+
"eval_precision": 0.8457943925233645,
|
| 497 |
+
"eval_recall": 0.8008849557522124,
|
| 498 |
+
"eval_runtime": 1.422,
|
| 499 |
+
"eval_samples_per_second": 79.467,
|
| 500 |
+
"eval_steps_per_second": 10.549,
|
| 501 |
+
"step": 600
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 9.53125,
|
| 505 |
+
"grad_norm": 0.6073923110961914,
|
| 506 |
+
"learning_rate": 0.00015162037037037037,
|
| 507 |
+
"loss": 0.159,
|
| 508 |
+
"step": 610
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 9.6875,
|
| 512 |
+
"grad_norm": 0.8762220740318298,
|
| 513 |
+
"learning_rate": 0.00015046296296296297,
|
| 514 |
+
"loss": 0.1959,
|
| 515 |
+
"step": 620
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 9.84375,
|
| 519 |
+
"grad_norm": 0.7490831017494202,
|
| 520 |
+
"learning_rate": 0.00014930555555555557,
|
| 521 |
+
"loss": 0.1465,
|
| 522 |
+
"step": 630
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 10.0,
|
| 526 |
+
"grad_norm": 1.0123506784439087,
|
| 527 |
+
"learning_rate": 0.00014814814814814815,
|
| 528 |
+
"loss": 0.1683,
|
| 529 |
+
"step": 640
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 10.15625,
|
| 533 |
+
"grad_norm": 0.5325204133987427,
|
| 534 |
+
"learning_rate": 0.00014699074074074075,
|
| 535 |
+
"loss": 0.1636,
|
| 536 |
+
"step": 650
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 10.3125,
|
| 540 |
+
"grad_norm": 0.5814504623413086,
|
| 541 |
+
"learning_rate": 0.00014583333333333335,
|
| 542 |
+
"loss": 0.1729,
|
| 543 |
+
"step": 660
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 10.46875,
|
| 547 |
+
"grad_norm": 1.0156935453414917,
|
| 548 |
+
"learning_rate": 0.00014467592592592594,
|
| 549 |
+
"loss": 0.1569,
|
| 550 |
+
"step": 670
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 10.625,
|
| 554 |
+
"grad_norm": 1.257921576499939,
|
| 555 |
+
"learning_rate": 0.00014351851851851852,
|
| 556 |
+
"loss": 0.1429,
|
| 557 |
+
"step": 680
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 10.78125,
|
| 561 |
+
"grad_norm": 0.929108202457428,
|
| 562 |
+
"learning_rate": 0.00014236111111111112,
|
| 563 |
+
"loss": 0.1554,
|
| 564 |
+
"step": 690
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 10.9375,
|
| 568 |
+
"grad_norm": 0.5256894826889038,
|
| 569 |
+
"learning_rate": 0.00014120370370370372,
|
| 570 |
+
"loss": 0.1815,
|
| 571 |
+
"step": 700
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 10.9375,
|
| 575 |
+
"eval_accuracy": 0.9265486725663716,
|
| 576 |
+
"eval_f1": 0.8074245939675174,
|
| 577 |
+
"eval_loss": 0.18833249807357788,
|
| 578 |
+
"eval_precision": 0.848780487804878,
|
| 579 |
+
"eval_recall": 0.7699115044247787,
|
| 580 |
+
"eval_runtime": 0.9484,
|
| 581 |
+
"eval_samples_per_second": 119.151,
|
| 582 |
+
"eval_steps_per_second": 15.817,
|
| 583 |
+
"step": 700
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 11.09375,
|
| 587 |
+
"grad_norm": 1.1333953142166138,
|
| 588 |
+
"learning_rate": 0.00014004629629629632,
|
| 589 |
+
"loss": 0.1703,
|
| 590 |
+
"step": 710
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 11.25,
|
| 594 |
+
"grad_norm": 0.6658828854560852,
|
| 595 |
+
"learning_rate": 0.0001388888888888889,
|
| 596 |
+
"loss": 0.1475,
|
| 597 |
+
"step": 720
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 11.40625,
|
| 601 |
+
"grad_norm": 1.04364812374115,
|
| 602 |
+
"learning_rate": 0.0001377314814814815,
|
| 603 |
+
"loss": 0.1598,
|
| 604 |
+
"step": 730
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 11.5625,
|
| 608 |
+
"grad_norm": 0.8811527490615845,
|
| 609 |
+
"learning_rate": 0.0001365740740740741,
|
| 610 |
+
"loss": 0.1678,
|
| 611 |
+
"step": 740
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 11.71875,
|
| 615 |
+
"grad_norm": 0.8651083111763,
|
| 616 |
+
"learning_rate": 0.0001354166666666667,
|
| 617 |
+
"loss": 0.1681,
|
| 618 |
+
"step": 750
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 11.875,
|
| 622 |
+
"grad_norm": 0.833223283290863,
|
| 623 |
+
"learning_rate": 0.00013425925925925926,
|
| 624 |
+
"loss": 0.1616,
|
| 625 |
+
"step": 760
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 12.03125,
|
| 629 |
+
"grad_norm": 0.5667290687561035,
|
| 630 |
+
"learning_rate": 0.00013310185185185186,
|
| 631 |
+
"loss": 0.1185,
|
| 632 |
+
"step": 770
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 12.1875,
|
| 636 |
+
"grad_norm": 1.3427128791809082,
|
| 637 |
+
"learning_rate": 0.00013194444444444446,
|
| 638 |
+
"loss": 0.1442,
|
| 639 |
+
"step": 780
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 12.34375,
|
| 643 |
+
"grad_norm": 0.859018087387085,
|
| 644 |
+
"learning_rate": 0.00013078703703703706,
|
| 645 |
+
"loss": 0.1552,
|
| 646 |
+
"step": 790
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 12.5,
|
| 650 |
+
"grad_norm": 0.6311579942703247,
|
| 651 |
+
"learning_rate": 0.00012962962962962963,
|
| 652 |
+
"loss": 0.1316,
|
| 653 |
+
"step": 800
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 12.5,
|
| 657 |
+
"eval_accuracy": 0.9327433628318584,
|
| 658 |
+
"eval_f1": 0.8272727272727272,
|
| 659 |
+
"eval_loss": 0.18246687948703766,
|
| 660 |
+
"eval_precision": 0.8504672897196262,
|
| 661 |
+
"eval_recall": 0.8053097345132744,
|
| 662 |
+
"eval_runtime": 0.9594,
|
| 663 |
+
"eval_samples_per_second": 117.786,
|
| 664 |
+
"eval_steps_per_second": 15.635,
|
| 665 |
+
"step": 800
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 12.65625,
|
| 669 |
+
"grad_norm": 0.8464061617851257,
|
| 670 |
+
"learning_rate": 0.00012847222222222223,
|
| 671 |
+
"loss": 0.1344,
|
| 672 |
+
"step": 810
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 12.8125,
|
| 676 |
+
"grad_norm": 0.6711329221725464,
|
| 677 |
+
"learning_rate": 0.00012731481481481483,
|
| 678 |
+
"loss": 0.1602,
|
| 679 |
+
"step": 820
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 12.96875,
|
| 683 |
+
"grad_norm": 1.0340158939361572,
|
| 684 |
+
"learning_rate": 0.00012615740740740743,
|
| 685 |
+
"loss": 0.1483,
|
| 686 |
+
"step": 830
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 13.125,
|
| 690 |
+
"grad_norm": 0.711726725101471,
|
| 691 |
+
"learning_rate": 0.000125,
|
| 692 |
+
"loss": 0.1507,
|
| 693 |
+
"step": 840
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 13.28125,
|
| 697 |
+
"grad_norm": 0.8784794211387634,
|
| 698 |
+
"learning_rate": 0.00012384259259259258,
|
| 699 |
+
"loss": 0.1515,
|
| 700 |
+
"step": 850
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 13.4375,
|
| 704 |
+
"grad_norm": 0.9908888339996338,
|
| 705 |
+
"learning_rate": 0.0001226851851851852,
|
| 706 |
+
"loss": 0.1583,
|
| 707 |
+
"step": 860
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 13.59375,
|
| 711 |
+
"grad_norm": 0.5473937392234802,
|
| 712 |
+
"learning_rate": 0.00012152777777777777,
|
| 713 |
+
"loss": 0.1433,
|
| 714 |
+
"step": 870
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 13.75,
|
| 718 |
+
"grad_norm": 1.6888905763626099,
|
| 719 |
+
"learning_rate": 0.00012037037037037037,
|
| 720 |
+
"loss": 0.1371,
|
| 721 |
+
"step": 880
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 13.90625,
|
| 725 |
+
"grad_norm": 1.0640438795089722,
|
| 726 |
+
"learning_rate": 0.00011921296296296296,
|
| 727 |
+
"loss": 0.1376,
|
| 728 |
+
"step": 890
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 14.0625,
|
| 732 |
+
"grad_norm": 1.9941257238388062,
|
| 733 |
+
"learning_rate": 0.00011805555555555556,
|
| 734 |
+
"loss": 0.1612,
|
| 735 |
+
"step": 900
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 14.0625,
|
| 739 |
+
"eval_accuracy": 0.9256637168141593,
|
| 740 |
+
"eval_f1": 0.8099547511312217,
|
| 741 |
+
"eval_loss": 0.18371373414993286,
|
| 742 |
+
"eval_precision": 0.8287037037037037,
|
| 743 |
+
"eval_recall": 0.7920353982300885,
|
| 744 |
+
"eval_runtime": 1.4255,
|
| 745 |
+
"eval_samples_per_second": 79.27,
|
| 746 |
+
"eval_steps_per_second": 10.523,
|
| 747 |
+
"step": 900
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 14.21875,
|
| 751 |
+
"grad_norm": 0.650867760181427,
|
| 752 |
+
"learning_rate": 0.00011689814814814815,
|
| 753 |
+
"loss": 0.1468,
|
| 754 |
+
"step": 910
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 14.375,
|
| 758 |
+
"grad_norm": 0.7459059357643127,
|
| 759 |
+
"learning_rate": 0.00011574074074074075,
|
| 760 |
+
"loss": 0.1468,
|
| 761 |
+
"step": 920
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 14.53125,
|
| 765 |
+
"grad_norm": 0.7468872666358948,
|
| 766 |
+
"learning_rate": 0.00011458333333333333,
|
| 767 |
+
"loss": 0.1169,
|
| 768 |
+
"step": 930
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 14.6875,
|
| 772 |
+
"grad_norm": 0.6512945890426636,
|
| 773 |
+
"learning_rate": 0.00011342592592592593,
|
| 774 |
+
"loss": 0.1373,
|
| 775 |
+
"step": 940
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 14.84375,
|
| 779 |
+
"grad_norm": 0.710382878780365,
|
| 780 |
+
"learning_rate": 0.00011226851851851852,
|
| 781 |
+
"loss": 0.1223,
|
| 782 |
+
"step": 950
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 15.0,
|
| 786 |
+
"grad_norm": 1.2112369537353516,
|
| 787 |
+
"learning_rate": 0.00011111111111111112,
|
| 788 |
+
"loss": 0.1257,
|
| 789 |
+
"step": 960
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 15.15625,
|
| 793 |
+
"grad_norm": 4.069777965545654,
|
| 794 |
+
"learning_rate": 0.0001099537037037037,
|
| 795 |
+
"loss": 0.1369,
|
| 796 |
+
"step": 970
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 15.3125,
|
| 800 |
+
"grad_norm": 0.9751072525978088,
|
| 801 |
+
"learning_rate": 0.0001087962962962963,
|
| 802 |
+
"loss": 0.1316,
|
| 803 |
+
"step": 980
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 15.46875,
|
| 807 |
+
"grad_norm": 0.49943211674690247,
|
| 808 |
+
"learning_rate": 0.00010763888888888889,
|
| 809 |
+
"loss": 0.1088,
|
| 810 |
+
"step": 990
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 15.625,
|
| 814 |
+
"grad_norm": 0.7845533490180969,
|
| 815 |
+
"learning_rate": 0.00010648148148148149,
|
| 816 |
+
"loss": 0.118,
|
| 817 |
+
"step": 1000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 15.625,
|
| 821 |
+
"eval_accuracy": 0.9309734513274336,
|
| 822 |
+
"eval_f1": 0.8227272727272726,
|
| 823 |
+
"eval_loss": 0.18961240351200104,
|
| 824 |
+
"eval_precision": 0.8457943925233645,
|
| 825 |
+
"eval_recall": 0.8008849557522124,
|
| 826 |
+
"eval_runtime": 0.9541,
|
| 827 |
+
"eval_samples_per_second": 118.435,
|
| 828 |
+
"eval_steps_per_second": 15.721,
|
| 829 |
+
"step": 1000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 15.78125,
|
| 833 |
+
"grad_norm": 0.5193383693695068,
|
| 834 |
+
"learning_rate": 0.00010532407407407407,
|
| 835 |
+
"loss": 0.1233,
|
| 836 |
+
"step": 1010
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 15.9375,
|
| 840 |
+
"grad_norm": 0.5976629257202148,
|
| 841 |
+
"learning_rate": 0.00010416666666666667,
|
| 842 |
+
"loss": 0.1351,
|
| 843 |
+
"step": 1020
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 16.09375,
|
| 847 |
+
"grad_norm": 1.0629384517669678,
|
| 848 |
+
"learning_rate": 0.00010300925925925926,
|
| 849 |
+
"loss": 0.1597,
|
| 850 |
+
"step": 1030
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 16.25,
|
| 854 |
+
"grad_norm": 0.8576996326446533,
|
| 855 |
+
"learning_rate": 0.00010185185185185186,
|
| 856 |
+
"loss": 0.1268,
|
| 857 |
+
"step": 1040
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 16.40625,
|
| 861 |
+
"grad_norm": 0.7236841917037964,
|
| 862 |
+
"learning_rate": 0.00010069444444444445,
|
| 863 |
+
"loss": 0.1411,
|
| 864 |
+
"step": 1050
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 16.5625,
|
| 868 |
+
"grad_norm": 1.1142785549163818,
|
| 869 |
+
"learning_rate": 9.953703703703704e-05,
|
| 870 |
+
"loss": 0.1297,
|
| 871 |
+
"step": 1060
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 16.71875,
|
| 875 |
+
"grad_norm": 0.8304411768913269,
|
| 876 |
+
"learning_rate": 9.837962962962963e-05,
|
| 877 |
+
"loss": 0.1231,
|
| 878 |
+
"step": 1070
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 16.875,
|
| 882 |
+
"grad_norm": 0.8226402997970581,
|
| 883 |
+
"learning_rate": 9.722222222222223e-05,
|
| 884 |
+
"loss": 0.1399,
|
| 885 |
+
"step": 1080
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 17.03125,
|
| 889 |
+
"grad_norm": 0.6692397594451904,
|
| 890 |
+
"learning_rate": 9.606481481481482e-05,
|
| 891 |
+
"loss": 0.1833,
|
| 892 |
+
"step": 1090
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 17.1875,
|
| 896 |
+
"grad_norm": 0.6689762473106384,
|
| 897 |
+
"learning_rate": 9.490740740740742e-05,
|
| 898 |
+
"loss": 0.1178,
|
| 899 |
+
"step": 1100
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 17.1875,
|
| 903 |
+
"eval_accuracy": 0.9238938053097345,
|
| 904 |
+
"eval_f1": 0.8027522935779817,
|
| 905 |
+
"eval_loss": 0.19371576607227325,
|
| 906 |
+
"eval_precision": 0.8333333333333334,
|
| 907 |
+
"eval_recall": 0.7743362831858407,
|
| 908 |
+
"eval_runtime": 0.9499,
|
| 909 |
+
"eval_samples_per_second": 118.958,
|
| 910 |
+
"eval_steps_per_second": 15.791,
|
| 911 |
+
"step": 1100
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 17.34375,
|
| 915 |
+
"grad_norm": 0.6079881191253662,
|
| 916 |
+
"learning_rate": 9.375e-05,
|
| 917 |
+
"loss": 0.1259,
|
| 918 |
+
"step": 1110
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 17.5,
|
| 922 |
+
"grad_norm": 0.37670084834098816,
|
| 923 |
+
"learning_rate": 9.25925925925926e-05,
|
| 924 |
+
"loss": 0.1101,
|
| 925 |
+
"step": 1120
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 17.65625,
|
| 929 |
+
"grad_norm": 0.7734571695327759,
|
| 930 |
+
"learning_rate": 9.143518518518519e-05,
|
| 931 |
+
"loss": 0.1279,
|
| 932 |
+
"step": 1130
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 17.8125,
|
| 936 |
+
"grad_norm": 1.0208630561828613,
|
| 937 |
+
"learning_rate": 9.027777777777779e-05,
|
| 938 |
+
"loss": 0.1258,
|
| 939 |
+
"step": 1140
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 17.96875,
|
| 943 |
+
"grad_norm": 0.5698951482772827,
|
| 944 |
+
"learning_rate": 8.912037037037037e-05,
|
| 945 |
+
"loss": 0.1111,
|
| 946 |
+
"step": 1150
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 18.125,
|
| 950 |
+
"grad_norm": 1.77188241481781,
|
| 951 |
+
"learning_rate": 8.796296296296297e-05,
|
| 952 |
+
"loss": 0.1254,
|
| 953 |
+
"step": 1160
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 18.28125,
|
| 957 |
+
"grad_norm": 0.8389852643013,
|
| 958 |
+
"learning_rate": 8.680555555555556e-05,
|
| 959 |
+
"loss": 0.1042,
|
| 960 |
+
"step": 1170
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 18.4375,
|
| 964 |
+
"grad_norm": 0.6655524969100952,
|
| 965 |
+
"learning_rate": 8.564814814814816e-05,
|
| 966 |
+
"loss": 0.1272,
|
| 967 |
+
"step": 1180
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 18.59375,
|
| 971 |
+
"grad_norm": 0.4668845236301422,
|
| 972 |
+
"learning_rate": 8.449074074074074e-05,
|
| 973 |
+
"loss": 0.1096,
|
| 974 |
+
"step": 1190
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 18.75,
|
| 978 |
+
"grad_norm": 0.8379706740379333,
|
| 979 |
+
"learning_rate": 8.333333333333334e-05,
|
| 980 |
+
"loss": 0.1248,
|
| 981 |
+
"step": 1200
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 18.75,
|
| 985 |
+
"eval_accuracy": 0.9300884955752212,
|
| 986 |
+
"eval_f1": 0.8192219679633868,
|
| 987 |
+
"eval_loss": 0.19132623076438904,
|
| 988 |
+
"eval_precision": 0.8483412322274881,
|
| 989 |
+
"eval_recall": 0.7920353982300885,
|
| 990 |
+
"eval_runtime": 1.2549,
|
| 991 |
+
"eval_samples_per_second": 90.047,
|
| 992 |
+
"eval_steps_per_second": 11.953,
|
| 993 |
+
"step": 1200
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 18.90625,
|
| 997 |
+
"grad_norm": 0.9271652698516846,
|
| 998 |
+
"learning_rate": 8.217592592592593e-05,
|
| 999 |
+
"loss": 0.1126,
|
| 1000 |
+
"step": 1210
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 19.0625,
|
| 1004 |
+
"grad_norm": 1.1356163024902344,
|
| 1005 |
+
"learning_rate": 8.113425925925926e-05,
|
| 1006 |
+
"loss": 0.129,
|
| 1007 |
+
"step": 1220
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 19.21875,
|
| 1011 |
+
"grad_norm": 0.4993898570537567,
|
| 1012 |
+
"learning_rate": 7.997685185185186e-05,
|
| 1013 |
+
"loss": 0.1385,
|
| 1014 |
+
"step": 1230
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 19.375,
|
| 1018 |
+
"grad_norm": 1.2999491691589355,
|
| 1019 |
+
"learning_rate": 7.881944444444444e-05,
|
| 1020 |
+
"loss": 0.1242,
|
| 1021 |
+
"step": 1240
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 19.53125,
|
| 1025 |
+
"grad_norm": 1.1871651411056519,
|
| 1026 |
+
"learning_rate": 7.766203703703704e-05,
|
| 1027 |
+
"loss": 0.113,
|
| 1028 |
+
"step": 1250
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 19.6875,
|
| 1032 |
+
"grad_norm": 1.5129660367965698,
|
| 1033 |
+
"learning_rate": 7.650462962962963e-05,
|
| 1034 |
+
"loss": 0.1024,
|
| 1035 |
+
"step": 1260
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 19.84375,
|
| 1039 |
+
"grad_norm": 0.7286781072616577,
|
| 1040 |
+
"learning_rate": 7.534722222222223e-05,
|
| 1041 |
+
"loss": 0.0994,
|
| 1042 |
+
"step": 1270
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 20.0,
|
| 1046 |
+
"grad_norm": 1.0448476076126099,
|
| 1047 |
+
"learning_rate": 7.418981481481481e-05,
|
| 1048 |
+
"loss": 0.1115,
|
| 1049 |
+
"step": 1280
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 20.15625,
|
| 1053 |
+
"grad_norm": 0.6149379014968872,
|
| 1054 |
+
"learning_rate": 7.303240740740741e-05,
|
| 1055 |
+
"loss": 0.1243,
|
| 1056 |
+
"step": 1290
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 20.3125,
|
| 1060 |
+
"grad_norm": 0.7020682692527771,
|
| 1061 |
+
"learning_rate": 7.1875e-05,
|
| 1062 |
+
"loss": 0.1169,
|
| 1063 |
+
"step": 1300
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 20.3125,
|
| 1067 |
+
"eval_accuracy": 0.9300884955752212,
|
| 1068 |
+
"eval_f1": 0.8167053364269141,
|
| 1069 |
+
"eval_loss": 0.19162432849407196,
|
| 1070 |
+
"eval_precision": 0.8585365853658536,
|
| 1071 |
+
"eval_recall": 0.7787610619469026,
|
| 1072 |
+
"eval_runtime": 0.958,
|
| 1073 |
+
"eval_samples_per_second": 117.951,
|
| 1074 |
+
"eval_steps_per_second": 15.657,
|
| 1075 |
+
"step": 1300
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 20.46875,
|
| 1079 |
+
"grad_norm": 1.8554919958114624,
|
| 1080 |
+
"learning_rate": 7.07175925925926e-05,
|
| 1081 |
+
"loss": 0.1175,
|
| 1082 |
+
"step": 1310
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 20.625,
|
| 1086 |
+
"grad_norm": 1.1227444410324097,
|
| 1087 |
+
"learning_rate": 6.956018518518518e-05,
|
| 1088 |
+
"loss": 0.1004,
|
| 1089 |
+
"step": 1320
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 20.78125,
|
| 1093 |
+
"grad_norm": 1.376546025276184,
|
| 1094 |
+
"learning_rate": 6.840277777777778e-05,
|
| 1095 |
+
"loss": 0.1099,
|
| 1096 |
+
"step": 1330
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 20.9375,
|
| 1100 |
+
"grad_norm": 0.86075758934021,
|
| 1101 |
+
"learning_rate": 6.724537037037037e-05,
|
| 1102 |
+
"loss": 0.133,
|
| 1103 |
+
"step": 1340
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 21.09375,
|
| 1107 |
+
"grad_norm": 1.093257188796997,
|
| 1108 |
+
"learning_rate": 6.608796296296297e-05,
|
| 1109 |
+
"loss": 0.1143,
|
| 1110 |
+
"step": 1350
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 21.25,
|
| 1114 |
+
"grad_norm": 0.5665271282196045,
|
| 1115 |
+
"learning_rate": 6.493055555555556e-05,
|
| 1116 |
+
"loss": 0.1065,
|
| 1117 |
+
"step": 1360
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 21.40625,
|
| 1121 |
+
"grad_norm": 0.607912003993988,
|
| 1122 |
+
"learning_rate": 6.377314814814816e-05,
|
| 1123 |
+
"loss": 0.1221,
|
| 1124 |
+
"step": 1370
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 21.5625,
|
| 1128 |
+
"grad_norm": 0.4708748161792755,
|
| 1129 |
+
"learning_rate": 6.261574074074074e-05,
|
| 1130 |
+
"loss": 0.0941,
|
| 1131 |
+
"step": 1380
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 21.71875,
|
| 1135 |
+
"grad_norm": 0.8719390630722046,
|
| 1136 |
+
"learning_rate": 6.145833333333334e-05,
|
| 1137 |
+
"loss": 0.112,
|
| 1138 |
+
"step": 1390
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 21.875,
|
| 1142 |
+
"grad_norm": 0.45299583673477173,
|
| 1143 |
+
"learning_rate": 6.0300925925925934e-05,
|
| 1144 |
+
"loss": 0.1094,
|
| 1145 |
+
"step": 1400
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 21.875,
|
| 1149 |
+
"eval_accuracy": 0.9292035398230089,
|
| 1150 |
+
"eval_f1": 0.8181818181818182,
|
| 1151 |
+
"eval_loss": 0.19246041774749756,
|
| 1152 |
+
"eval_precision": 0.8411214953271028,
|
| 1153 |
+
"eval_recall": 0.7964601769911505,
|
| 1154 |
+
"eval_runtime": 1.2007,
|
| 1155 |
+
"eval_samples_per_second": 94.111,
|
| 1156 |
+
"eval_steps_per_second": 12.493,
|
| 1157 |
+
"step": 1400
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 22.03125,
|
| 1161 |
+
"grad_norm": 0.7893074154853821,
|
| 1162 |
+
"learning_rate": 5.9143518518518527e-05,
|
| 1163 |
+
"loss": 0.1142,
|
| 1164 |
+
"step": 1410
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 22.1875,
|
| 1168 |
+
"grad_norm": 1.0832182168960571,
|
| 1169 |
+
"learning_rate": 5.798611111111112e-05,
|
| 1170 |
+
"loss": 0.096,
|
| 1171 |
+
"step": 1420
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 22.34375,
|
| 1175 |
+
"grad_norm": 0.5880953669548035,
|
| 1176 |
+
"learning_rate": 5.682870370370371e-05,
|
| 1177 |
+
"loss": 0.1142,
|
| 1178 |
+
"step": 1430
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 22.5,
|
| 1182 |
+
"grad_norm": 0.6071570515632629,
|
| 1183 |
+
"learning_rate": 5.567129629629629e-05,
|
| 1184 |
+
"loss": 0.1146,
|
| 1185 |
+
"step": 1440
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 22.65625,
|
| 1189 |
+
"grad_norm": 1.7968199253082275,
|
| 1190 |
+
"learning_rate": 5.4513888888888884e-05,
|
| 1191 |
+
"loss": 0.1141,
|
| 1192 |
+
"step": 1450
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 22.8125,
|
| 1196 |
+
"grad_norm": 0.6409327983856201,
|
| 1197 |
+
"learning_rate": 5.335648148148148e-05,
|
| 1198 |
+
"loss": 0.0907,
|
| 1199 |
+
"step": 1460
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 22.96875,
|
| 1203 |
+
"grad_norm": 1.28959321975708,
|
| 1204 |
+
"learning_rate": 5.219907407407407e-05,
|
| 1205 |
+
"loss": 0.0945,
|
| 1206 |
+
"step": 1470
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 23.125,
|
| 1210 |
+
"grad_norm": 1.0384379625320435,
|
| 1211 |
+
"learning_rate": 5.115740740740741e-05,
|
| 1212 |
+
"loss": 0.1062,
|
| 1213 |
+
"step": 1480
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 23.28125,
|
| 1217 |
+
"grad_norm": 0.8010191917419434,
|
| 1218 |
+
"learning_rate": 5e-05,
|
| 1219 |
+
"loss": 0.1029,
|
| 1220 |
+
"step": 1490
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 23.4375,
|
| 1224 |
+
"grad_norm": 1.078620195388794,
|
| 1225 |
+
"learning_rate": 4.8842592592592595e-05,
|
| 1226 |
+
"loss": 0.1108,
|
| 1227 |
+
"step": 1500
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 23.4375,
|
| 1231 |
+
"eval_accuracy": 0.9345132743362832,
|
| 1232 |
+
"eval_f1": 0.8333333333333334,
|
| 1233 |
+
"eval_loss": 0.19605357944965363,
|
| 1234 |
+
"eval_precision": 0.8486238532110092,
|
| 1235 |
+
"eval_recall": 0.8185840707964602,
|
| 1236 |
+
"eval_runtime": 0.9739,
|
| 1237 |
+
"eval_samples_per_second": 116.033,
|
| 1238 |
+
"eval_steps_per_second": 15.403,
|
| 1239 |
+
"step": 1500
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 23.59375,
|
| 1243 |
+
"grad_norm": 0.9104486703872681,
|
| 1244 |
+
"learning_rate": 4.768518518518519e-05,
|
| 1245 |
+
"loss": 0.1039,
|
| 1246 |
+
"step": 1510
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 23.75,
|
| 1250 |
+
"grad_norm": 1.1187772750854492,
|
| 1251 |
+
"learning_rate": 4.652777777777778e-05,
|
| 1252 |
+
"loss": 0.1179,
|
| 1253 |
+
"step": 1520
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 23.90625,
|
| 1257 |
+
"grad_norm": 0.6038283109664917,
|
| 1258 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 1259 |
+
"loss": 0.0981,
|
| 1260 |
+
"step": 1530
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 24.0625,
|
| 1264 |
+
"grad_norm": 1.483780860900879,
|
| 1265 |
+
"learning_rate": 4.4212962962962966e-05,
|
| 1266 |
+
"loss": 0.1287,
|
| 1267 |
+
"step": 1540
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 24.21875,
|
| 1271 |
+
"grad_norm": 0.9008955359458923,
|
| 1272 |
+
"learning_rate": 4.305555555555556e-05,
|
| 1273 |
+
"loss": 0.1038,
|
| 1274 |
+
"step": 1550
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 24.375,
|
| 1278 |
+
"grad_norm": 1.3843752145767212,
|
| 1279 |
+
"learning_rate": 4.1898148148148145e-05,
|
| 1280 |
+
"loss": 0.1177,
|
| 1281 |
+
"step": 1560
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 24.53125,
|
| 1285 |
+
"grad_norm": 1.3227291107177734,
|
| 1286 |
+
"learning_rate": 4.074074074074074e-05,
|
| 1287 |
+
"loss": 0.0992,
|
| 1288 |
+
"step": 1570
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 24.6875,
|
| 1292 |
+
"grad_norm": 0.4530428349971771,
|
| 1293 |
+
"learning_rate": 3.958333333333333e-05,
|
| 1294 |
+
"loss": 0.1064,
|
| 1295 |
+
"step": 1580
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 24.84375,
|
| 1299 |
+
"grad_norm": 1.476251244544983,
|
| 1300 |
+
"learning_rate": 3.8425925925925924e-05,
|
| 1301 |
+
"loss": 0.1008,
|
| 1302 |
+
"step": 1590
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 25.0,
|
| 1306 |
+
"grad_norm": 1.4163908958435059,
|
| 1307 |
+
"learning_rate": 3.726851851851852e-05,
|
| 1308 |
+
"loss": 0.1089,
|
| 1309 |
+
"step": 1600
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 25.0,
|
| 1313 |
+
"eval_accuracy": 0.9283185840707965,
|
| 1314 |
+
"eval_f1": 0.8171557562076749,
|
| 1315 |
+
"eval_loss": 0.1992984265089035,
|
| 1316 |
+
"eval_precision": 0.8341013824884793,
|
| 1317 |
+
"eval_recall": 0.8008849557522124,
|
| 1318 |
+
"eval_runtime": 0.9786,
|
| 1319 |
+
"eval_samples_per_second": 115.465,
|
| 1320 |
+
"eval_steps_per_second": 15.327,
|
| 1321 |
+
"step": 1600
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 25.15625,
|
| 1325 |
+
"grad_norm": 0.805210292339325,
|
| 1326 |
+
"learning_rate": 3.611111111111111e-05,
|
| 1327 |
+
"loss": 0.0922,
|
| 1328 |
+
"step": 1610
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 25.3125,
|
| 1332 |
+
"grad_norm": 0.7946519255638123,
|
| 1333 |
+
"learning_rate": 3.49537037037037e-05,
|
| 1334 |
+
"loss": 0.1033,
|
| 1335 |
+
"step": 1620
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 25.46875,
|
| 1339 |
+
"grad_norm": 0.7051573991775513,
|
| 1340 |
+
"learning_rate": 3.3796296296296295e-05,
|
| 1341 |
+
"loss": 0.1031,
|
| 1342 |
+
"step": 1630
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 25.625,
|
| 1346 |
+
"grad_norm": 0.6867948174476624,
|
| 1347 |
+
"learning_rate": 3.263888888888889e-05,
|
| 1348 |
+
"loss": 0.1203,
|
| 1349 |
+
"step": 1640
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 25.78125,
|
| 1353 |
+
"grad_norm": 0.9575832486152649,
|
| 1354 |
+
"learning_rate": 3.148148148148148e-05,
|
| 1355 |
+
"loss": 0.101,
|
| 1356 |
+
"step": 1650
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 25.9375,
|
| 1360 |
+
"grad_norm": 1.125503420829773,
|
| 1361 |
+
"learning_rate": 3.0324074074074077e-05,
|
| 1362 |
+
"loss": 0.0868,
|
| 1363 |
+
"step": 1660
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 26.09375,
|
| 1367 |
+
"grad_norm": 0.694492757320404,
|
| 1368 |
+
"learning_rate": 2.916666666666667e-05,
|
| 1369 |
+
"loss": 0.0916,
|
| 1370 |
+
"step": 1670
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 26.25,
|
| 1374 |
+
"grad_norm": 0.606955885887146,
|
| 1375 |
+
"learning_rate": 2.8009259259259263e-05,
|
| 1376 |
+
"loss": 0.0978,
|
| 1377 |
+
"step": 1680
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 26.40625,
|
| 1381 |
+
"grad_norm": 0.855603814125061,
|
| 1382 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 1383 |
+
"loss": 0.0988,
|
| 1384 |
+
"step": 1690
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 26.5625,
|
| 1388 |
+
"grad_norm": 0.6119447946548462,
|
| 1389 |
+
"learning_rate": 2.5694444444444445e-05,
|
| 1390 |
+
"loss": 0.0919,
|
| 1391 |
+
"step": 1700
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 26.5625,
|
| 1395 |
+
"eval_accuracy": 0.9318584070796461,
|
| 1396 |
+
"eval_f1": 0.8261851015801355,
|
| 1397 |
+
"eval_loss": 0.19360247254371643,
|
| 1398 |
+
"eval_precision": 0.8433179723502304,
|
| 1399 |
+
"eval_recall": 0.8097345132743363,
|
| 1400 |
+
"eval_runtime": 1.5343,
|
| 1401 |
+
"eval_samples_per_second": 73.651,
|
| 1402 |
+
"eval_steps_per_second": 9.777,
|
| 1403 |
+
"step": 1700
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 26.71875,
|
| 1407 |
+
"grad_norm": 0.9873837828636169,
|
| 1408 |
+
"learning_rate": 2.4537037037037038e-05,
|
| 1409 |
+
"loss": 0.0829,
|
| 1410 |
+
"step": 1710
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 26.875,
|
| 1414 |
+
"grad_norm": 0.9287075996398926,
|
| 1415 |
+
"learning_rate": 2.337962962962963e-05,
|
| 1416 |
+
"loss": 0.1128,
|
| 1417 |
+
"step": 1720
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 27.03125,
|
| 1421 |
+
"grad_norm": 0.8201906681060791,
|
| 1422 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 1423 |
+
"loss": 0.1084,
|
| 1424 |
+
"step": 1730
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 27.1875,
|
| 1428 |
+
"grad_norm": 1.1874263286590576,
|
| 1429 |
+
"learning_rate": 2.1064814814814816e-05,
|
| 1430 |
+
"loss": 0.1065,
|
| 1431 |
+
"step": 1740
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 27.34375,
|
| 1435 |
+
"grad_norm": 1.0616997480392456,
|
| 1436 |
+
"learning_rate": 1.990740740740741e-05,
|
| 1437 |
+
"loss": 0.1014,
|
| 1438 |
+
"step": 1750
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 27.5,
|
| 1442 |
+
"grad_norm": 0.8941544890403748,
|
| 1443 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 1444 |
+
"loss": 0.1008,
|
| 1445 |
+
"step": 1760
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 27.65625,
|
| 1449 |
+
"grad_norm": 0.9521628022193909,
|
| 1450 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 1451 |
+
"loss": 0.0908,
|
| 1452 |
+
"step": 1770
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 27.8125,
|
| 1456 |
+
"grad_norm": 0.79527348279953,
|
| 1457 |
+
"learning_rate": 1.6435185185185187e-05,
|
| 1458 |
+
"loss": 0.1137,
|
| 1459 |
+
"step": 1780
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 27.96875,
|
| 1463 |
+
"grad_norm": 0.8606336116790771,
|
| 1464 |
+
"learning_rate": 1.527777777777778e-05,
|
| 1465 |
+
"loss": 0.0929,
|
| 1466 |
+
"step": 1790
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 28.125,
|
| 1470 |
+
"grad_norm": 1.2438716888427734,
|
| 1471 |
+
"learning_rate": 1.412037037037037e-05,
|
| 1472 |
+
"loss": 0.0969,
|
| 1473 |
+
"step": 1800
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 28.125,
|
| 1477 |
+
"eval_accuracy": 0.9309734513274336,
|
| 1478 |
+
"eval_f1": 0.8227272727272726,
|
| 1479 |
+
"eval_loss": 0.19780634343624115,
|
| 1480 |
+
"eval_precision": 0.8457943925233645,
|
| 1481 |
+
"eval_recall": 0.8008849557522124,
|
| 1482 |
+
"eval_runtime": 0.9685,
|
| 1483 |
+
"eval_samples_per_second": 116.67,
|
| 1484 |
+
"eval_steps_per_second": 15.487,
|
| 1485 |
+
"step": 1800
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 28.28125,
|
| 1489 |
+
"grad_norm": 0.9101031422615051,
|
| 1490 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 1491 |
+
"loss": 0.0977,
|
| 1492 |
+
"step": 1810
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 28.4375,
|
| 1496 |
+
"grad_norm": 0.6852589249610901,
|
| 1497 |
+
"learning_rate": 1.1805555555555555e-05,
|
| 1498 |
+
"loss": 0.1018,
|
| 1499 |
+
"step": 1820
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 28.59375,
|
| 1503 |
+
"grad_norm": 0.8925357460975647,
|
| 1504 |
+
"learning_rate": 1.0648148148148148e-05,
|
| 1505 |
+
"loss": 0.0985,
|
| 1506 |
+
"step": 1830
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 28.75,
|
| 1510 |
+
"grad_norm": 0.8219801783561707,
|
| 1511 |
+
"learning_rate": 9.490740740740741e-06,
|
| 1512 |
+
"loss": 0.1014,
|
| 1513 |
+
"step": 1840
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 28.90625,
|
| 1517 |
+
"grad_norm": 0.6065762639045715,
|
| 1518 |
+
"learning_rate": 8.333333333333334e-06,
|
| 1519 |
+
"loss": 0.1161,
|
| 1520 |
+
"step": 1850
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 29.0625,
|
| 1524 |
+
"grad_norm": 0.7718455791473389,
|
| 1525 |
+
"learning_rate": 7.1759259259259266e-06,
|
| 1526 |
+
"loss": 0.1101,
|
| 1527 |
+
"step": 1860
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 29.21875,
|
| 1531 |
+
"grad_norm": 1.0950359106063843,
|
| 1532 |
+
"learning_rate": 6.0185185185185185e-06,
|
| 1533 |
+
"loss": 0.1042,
|
| 1534 |
+
"step": 1870
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 29.375,
|
| 1538 |
+
"grad_norm": 0.7298617362976074,
|
| 1539 |
+
"learning_rate": 4.861111111111111e-06,
|
| 1540 |
+
"loss": 0.0823,
|
| 1541 |
+
"step": 1880
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 29.53125,
|
| 1545 |
+
"grad_norm": 0.782146692276001,
|
| 1546 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 1547 |
+
"loss": 0.1051,
|
| 1548 |
+
"step": 1890
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 29.6875,
|
| 1552 |
+
"grad_norm": 0.7693170309066772,
|
| 1553 |
+
"learning_rate": 2.546296296296296e-06,
|
| 1554 |
+
"loss": 0.1093,
|
| 1555 |
+
"step": 1900
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 29.6875,
|
| 1559 |
+
"eval_accuracy": 0.9283185840707965,
|
| 1560 |
+
"eval_f1": 0.8171557562076749,
|
| 1561 |
+
"eval_loss": 0.19546246528625488,
|
| 1562 |
+
"eval_precision": 0.8341013824884793,
|
| 1563 |
+
"eval_recall": 0.8008849557522124,
|
| 1564 |
+
"eval_runtime": 1.3969,
|
| 1565 |
+
"eval_samples_per_second": 80.891,
|
| 1566 |
+
"eval_steps_per_second": 10.738,
|
| 1567 |
+
"step": 1900
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 29.84375,
|
| 1571 |
+
"grad_norm": 1.2105658054351807,
|
| 1572 |
+
"learning_rate": 1.388888888888889e-06,
|
| 1573 |
+
"loss": 0.0836,
|
| 1574 |
+
"step": 1910
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 30.0,
|
| 1578 |
+
"grad_norm": 2.1491291522979736,
|
| 1579 |
+
"learning_rate": 2.3148148148148148e-07,
|
| 1580 |
+
"loss": 0.1122,
|
| 1581 |
+
"step": 1920
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 30.0,
|
| 1585 |
+
"step": 1920,
|
| 1586 |
+
"total_flos": 1.9916656541540352e+17,
|
| 1587 |
+
"train_loss": 0.1991663834390541,
|
| 1588 |
+
"train_runtime": 388.9258,
|
| 1589 |
+
"train_samples_per_second": 78.061,
|
| 1590 |
+
"train_steps_per_second": 4.937
|
| 1591 |
+
}
|
| 1592 |
+
],
|
| 1593 |
+
"logging_steps": 10,
|
| 1594 |
+
"max_steps": 1920,
|
| 1595 |
+
"num_input_tokens_seen": 0,
|
| 1596 |
+
"num_train_epochs": 30,
|
| 1597 |
+
"save_steps": 500,
|
| 1598 |
+
"stateful_callbacks": {
|
| 1599 |
+
"TrainerControl": {
|
| 1600 |
+
"args": {
|
| 1601 |
+
"should_epoch_stop": false,
|
| 1602 |
+
"should_evaluate": false,
|
| 1603 |
+
"should_log": false,
|
| 1604 |
+
"should_save": true,
|
| 1605 |
+
"should_training_stop": true
|
| 1606 |
+
},
|
| 1607 |
+
"attributes": {}
|
| 1608 |
+
}
|
| 1609 |
+
},
|
| 1610 |
+
"total_flos": 1.9916656541540352e+17,
|
| 1611 |
+
"train_batch_size": 16,
|
| 1612 |
+
"trial_name": null,
|
| 1613 |
+
"trial_params": null
|
| 1614 |
+
}
|