🍻 cheers
Browse files- README.md +7 -6
- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Mar18_14-12-44_9c311a5b3773/events.out.tfevents.1710772666.9c311a5b3773.3314.19 +3 -0
- train_results.json +8 -0
- trainer_state.json +1506 -0
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -18,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# vit-lr-linear
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Accuracy: 0.
|
| 25 |
-
- Precision: 0.
|
| 26 |
-
- Recall: 0.
|
| 27 |
-
- F1: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
|
|
| 19 |
|
| 20 |
# vit-lr-linear
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the skin-cancer dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.4920
|
| 25 |
+
- Accuracy: 0.8322
|
| 26 |
+
- Precision: 0.8400
|
| 27 |
+
- Recall: 0.8322
|
| 28 |
+
- F1: 0.8323
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.61,
|
| 3 |
+
"eval_accuracy": 0.8321775312066574,
|
| 4 |
+
"eval_f1": 0.8323189306799796,
|
| 5 |
+
"eval_loss": 0.4919604957103729,
|
| 6 |
+
"eval_precision": 0.8400335349095535,
|
| 7 |
+
"eval_recall": 0.8321775312066574,
|
| 8 |
+
"eval_runtime": 40.0976,
|
| 9 |
+
"eval_samples_per_second": 71.924,
|
| 10 |
+
"eval_steps_per_second": 9.003,
|
| 11 |
+
"total_flos": 2.2287694956200755e+18,
|
| 12 |
+
"train_loss": 0.26933162180913817,
|
| 13 |
+
"train_runtime": 1430.4649,
|
| 14 |
+
"train_samples_per_second": 358.485,
|
| 15 |
+
"train_steps_per_second": 22.44
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.61,
|
| 3 |
+
"eval_accuracy": 0.8321775312066574,
|
| 4 |
+
"eval_f1": 0.8323189306799796,
|
| 5 |
+
"eval_loss": 0.4919604957103729,
|
| 6 |
+
"eval_precision": 0.8400335349095535,
|
| 7 |
+
"eval_recall": 0.8321775312066574,
|
| 8 |
+
"eval_runtime": 40.0976,
|
| 9 |
+
"eval_samples_per_second": 71.924,
|
| 10 |
+
"eval_steps_per_second": 9.003
|
| 11 |
+
}
|
runs/Mar18_14-12-44_9c311a5b3773/events.out.tfevents.1710772666.9c311a5b3773.3314.19
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b345a873dec8ec1bff10a76d535ae7bbe9b4c5de74b7ecb01088b46f2eb1cf30
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.61,
|
| 3 |
+
"total_flos": 2.2287694956200755e+18,
|
| 4 |
+
"train_loss": 0.26933162180913817,
|
| 5 |
+
"train_runtime": 1430.4649,
|
| 6 |
+
"train_samples_per_second": 358.485,
|
| 7 |
+
"train_steps_per_second": 22.44
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1506 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4919604957103729,
|
| 3 |
+
"best_model_checkpoint": "./vit-lr-linear/checkpoint-800",
|
| 4 |
+
"epoch": 5.607476635514018,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 3.5967516899108887,
|
| 14 |
+
"learning_rate": 9.997196261682243e-05,
|
| 15 |
+
"loss": 1.2508,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06,
|
| 20 |
+
"grad_norm": 4.702871799468994,
|
| 21 |
+
"learning_rate": 9.994080996884736e-05,
|
| 22 |
+
"loss": 0.7499,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09,
|
| 27 |
+
"grad_norm": 6.171701431274414,
|
| 28 |
+
"learning_rate": 9.990965732087227e-05,
|
| 29 |
+
"loss": 0.8834,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12,
|
| 34 |
+
"grad_norm": 10.749275207519531,
|
| 35 |
+
"learning_rate": 9.98785046728972e-05,
|
| 36 |
+
"loss": 1.0502,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16,
|
| 41 |
+
"grad_norm": 4.334569931030273,
|
| 42 |
+
"learning_rate": 9.984735202492212e-05,
|
| 43 |
+
"loss": 0.769,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19,
|
| 48 |
+
"grad_norm": 4.809230327606201,
|
| 49 |
+
"learning_rate": 9.981619937694705e-05,
|
| 50 |
+
"loss": 0.9034,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.22,
|
| 55 |
+
"grad_norm": 3.983206272125244,
|
| 56 |
+
"learning_rate": 9.978504672897196e-05,
|
| 57 |
+
"loss": 0.8274,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.25,
|
| 62 |
+
"grad_norm": 3.574300765991211,
|
| 63 |
+
"learning_rate": 9.975389408099689e-05,
|
| 64 |
+
"loss": 0.6348,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.28,
|
| 69 |
+
"grad_norm": 5.728092670440674,
|
| 70 |
+
"learning_rate": 9.972274143302182e-05,
|
| 71 |
+
"loss": 0.6568,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.31,
|
| 76 |
+
"grad_norm": 4.649799823760986,
|
| 77 |
+
"learning_rate": 9.969158878504672e-05,
|
| 78 |
+
"loss": 0.6029,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.31,
|
| 83 |
+
"eval_accuracy": 0.7805131761442441,
|
| 84 |
+
"eval_f1": 0.7528727438506023,
|
| 85 |
+
"eval_loss": 0.6126354932785034,
|
| 86 |
+
"eval_precision": 0.7602026831090402,
|
| 87 |
+
"eval_recall": 0.7805131761442441,
|
| 88 |
+
"eval_runtime": 39.2505,
|
| 89 |
+
"eval_samples_per_second": 73.477,
|
| 90 |
+
"eval_steps_per_second": 9.197,
|
| 91 |
+
"step": 100
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.34,
|
| 95 |
+
"grad_norm": 5.011153221130371,
|
| 96 |
+
"learning_rate": 9.966043613707165e-05,
|
| 97 |
+
"loss": 0.6847,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.37,
|
| 102 |
+
"grad_norm": 7.656059741973877,
|
| 103 |
+
"learning_rate": 9.962928348909658e-05,
|
| 104 |
+
"loss": 0.6162,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.4,
|
| 109 |
+
"grad_norm": 7.763223648071289,
|
| 110 |
+
"learning_rate": 9.95981308411215e-05,
|
| 111 |
+
"loss": 0.6389,
|
| 112 |
+
"step": 130
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.44,
|
| 116 |
+
"grad_norm": 2.2059271335601807,
|
| 117 |
+
"learning_rate": 9.956697819314643e-05,
|
| 118 |
+
"loss": 0.5381,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.47,
|
| 123 |
+
"grad_norm": 6.06673002243042,
|
| 124 |
+
"learning_rate": 9.953582554517134e-05,
|
| 125 |
+
"loss": 0.5674,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.5,
|
| 130 |
+
"grad_norm": 5.407893657684326,
|
| 131 |
+
"learning_rate": 9.950467289719627e-05,
|
| 132 |
+
"loss": 0.5598,
|
| 133 |
+
"step": 160
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.53,
|
| 137 |
+
"grad_norm": 7.515843391418457,
|
| 138 |
+
"learning_rate": 9.947352024922119e-05,
|
| 139 |
+
"loss": 0.5488,
|
| 140 |
+
"step": 170
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.56,
|
| 144 |
+
"grad_norm": 7.197587966918945,
|
| 145 |
+
"learning_rate": 9.944236760124612e-05,
|
| 146 |
+
"loss": 0.7078,
|
| 147 |
+
"step": 180
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.59,
|
| 151 |
+
"grad_norm": 4.026732921600342,
|
| 152 |
+
"learning_rate": 9.941121495327103e-05,
|
| 153 |
+
"loss": 0.595,
|
| 154 |
+
"step": 190
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.62,
|
| 158 |
+
"grad_norm": 5.807314872741699,
|
| 159 |
+
"learning_rate": 9.938006230529595e-05,
|
| 160 |
+
"loss": 0.5726,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.62,
|
| 165 |
+
"eval_accuracy": 0.7649098474341193,
|
| 166 |
+
"eval_f1": 0.7177347277722194,
|
| 167 |
+
"eval_loss": 0.6950196623802185,
|
| 168 |
+
"eval_precision": 0.7613231169607695,
|
| 169 |
+
"eval_recall": 0.7649098474341193,
|
| 170 |
+
"eval_runtime": 39.3588,
|
| 171 |
+
"eval_samples_per_second": 73.275,
|
| 172 |
+
"eval_steps_per_second": 9.172,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.65,
|
| 177 |
+
"grad_norm": 5.1864399909973145,
|
| 178 |
+
"learning_rate": 9.934890965732088e-05,
|
| 179 |
+
"loss": 0.6681,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.69,
|
| 184 |
+
"grad_norm": 7.364803314208984,
|
| 185 |
+
"learning_rate": 9.93177570093458e-05,
|
| 186 |
+
"loss": 0.7502,
|
| 187 |
+
"step": 220
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.72,
|
| 191 |
+
"grad_norm": 1.9555000066757202,
|
| 192 |
+
"learning_rate": 9.928660436137072e-05,
|
| 193 |
+
"loss": 0.3976,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.75,
|
| 198 |
+
"grad_norm": 2.5017478466033936,
|
| 199 |
+
"learning_rate": 9.925545171339564e-05,
|
| 200 |
+
"loss": 0.5505,
|
| 201 |
+
"step": 240
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.78,
|
| 205 |
+
"grad_norm": 4.633613109588623,
|
| 206 |
+
"learning_rate": 9.922429906542056e-05,
|
| 207 |
+
"loss": 0.7452,
|
| 208 |
+
"step": 250
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.81,
|
| 212 |
+
"grad_norm": 4.068040370941162,
|
| 213 |
+
"learning_rate": 9.91931464174455e-05,
|
| 214 |
+
"loss": 0.5837,
|
| 215 |
+
"step": 260
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.84,
|
| 219 |
+
"grad_norm": 3.191166639328003,
|
| 220 |
+
"learning_rate": 9.916199376947041e-05,
|
| 221 |
+
"loss": 0.4488,
|
| 222 |
+
"step": 270
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.87,
|
| 226 |
+
"grad_norm": 2.8749473094940186,
|
| 227 |
+
"learning_rate": 9.913084112149534e-05,
|
| 228 |
+
"loss": 0.4906,
|
| 229 |
+
"step": 280
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.9,
|
| 233 |
+
"grad_norm": 7.547589302062988,
|
| 234 |
+
"learning_rate": 9.909968847352025e-05,
|
| 235 |
+
"loss": 0.6191,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.93,
|
| 240 |
+
"grad_norm": 5.1279096603393555,
|
| 241 |
+
"learning_rate": 9.906853582554517e-05,
|
| 242 |
+
"loss": 0.6521,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.93,
|
| 247 |
+
"eval_accuracy": 0.8124133148404993,
|
| 248 |
+
"eval_f1": 0.8060484287452215,
|
| 249 |
+
"eval_loss": 0.5102406740188599,
|
| 250 |
+
"eval_precision": 0.8148843275891411,
|
| 251 |
+
"eval_recall": 0.8124133148404993,
|
| 252 |
+
"eval_runtime": 39.7509,
|
| 253 |
+
"eval_samples_per_second": 72.552,
|
| 254 |
+
"eval_steps_per_second": 9.082,
|
| 255 |
+
"step": 300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.97,
|
| 259 |
+
"grad_norm": 3.052353858947754,
|
| 260 |
+
"learning_rate": 9.90373831775701e-05,
|
| 261 |
+
"loss": 0.5616,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.0,
|
| 266 |
+
"grad_norm": 4.507020473480225,
|
| 267 |
+
"learning_rate": 9.900623052959503e-05,
|
| 268 |
+
"loss": 0.5192,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.03,
|
| 273 |
+
"grad_norm": 5.176488876342773,
|
| 274 |
+
"learning_rate": 9.897507788161994e-05,
|
| 275 |
+
"loss": 0.4461,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.06,
|
| 280 |
+
"grad_norm": 4.797460079193115,
|
| 281 |
+
"learning_rate": 9.894392523364486e-05,
|
| 282 |
+
"loss": 0.3651,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.09,
|
| 287 |
+
"grad_norm": 2.186629295349121,
|
| 288 |
+
"learning_rate": 9.891277258566979e-05,
|
| 289 |
+
"loss": 0.4004,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.12,
|
| 294 |
+
"grad_norm": 2.1874918937683105,
|
| 295 |
+
"learning_rate": 9.888161993769472e-05,
|
| 296 |
+
"loss": 0.3475,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.15,
|
| 301 |
+
"grad_norm": 4.8143486976623535,
|
| 302 |
+
"learning_rate": 9.885046728971963e-05,
|
| 303 |
+
"loss": 0.4073,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.18,
|
| 308 |
+
"grad_norm": 7.921704292297363,
|
| 309 |
+
"learning_rate": 9.881931464174455e-05,
|
| 310 |
+
"loss": 0.3765,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.21,
|
| 315 |
+
"grad_norm": 5.491533279418945,
|
| 316 |
+
"learning_rate": 9.878816199376948e-05,
|
| 317 |
+
"loss": 0.4707,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.25,
|
| 322 |
+
"grad_norm": 2.563472032546997,
|
| 323 |
+
"learning_rate": 9.875700934579439e-05,
|
| 324 |
+
"loss": 0.3803,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.25,
|
| 329 |
+
"eval_accuracy": 0.7843273231622746,
|
| 330 |
+
"eval_f1": 0.7933752302092828,
|
| 331 |
+
"eval_loss": 0.6124634146690369,
|
| 332 |
+
"eval_precision": 0.8128379357321871,
|
| 333 |
+
"eval_recall": 0.7843273231622746,
|
| 334 |
+
"eval_runtime": 39.1164,
|
| 335 |
+
"eval_samples_per_second": 73.729,
|
| 336 |
+
"eval_steps_per_second": 9.229,
|
| 337 |
+
"step": 400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.28,
|
| 341 |
+
"grad_norm": 3.978813648223877,
|
| 342 |
+
"learning_rate": 9.872585669781932e-05,
|
| 343 |
+
"loss": 0.4527,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.31,
|
| 348 |
+
"grad_norm": 3.3713996410369873,
|
| 349 |
+
"learning_rate": 9.869470404984425e-05,
|
| 350 |
+
"loss": 0.4344,
|
| 351 |
+
"step": 420
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.34,
|
| 355 |
+
"grad_norm": 3.685149669647217,
|
| 356 |
+
"learning_rate": 9.866355140186917e-05,
|
| 357 |
+
"loss": 0.5163,
|
| 358 |
+
"step": 430
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.37,
|
| 362 |
+
"grad_norm": 3.9468307495117188,
|
| 363 |
+
"learning_rate": 9.863239875389408e-05,
|
| 364 |
+
"loss": 0.4187,
|
| 365 |
+
"step": 440
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.4,
|
| 369 |
+
"grad_norm": 4.608047962188721,
|
| 370 |
+
"learning_rate": 9.860124610591901e-05,
|
| 371 |
+
"loss": 0.3643,
|
| 372 |
+
"step": 450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.43,
|
| 376 |
+
"grad_norm": 3.3221333026885986,
|
| 377 |
+
"learning_rate": 9.857009345794394e-05,
|
| 378 |
+
"loss": 0.3324,
|
| 379 |
+
"step": 460
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.46,
|
| 383 |
+
"grad_norm": 3.251314640045166,
|
| 384 |
+
"learning_rate": 9.853894080996885e-05,
|
| 385 |
+
"loss": 0.3229,
|
| 386 |
+
"step": 470
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.5,
|
| 390 |
+
"grad_norm": 7.8897552490234375,
|
| 391 |
+
"learning_rate": 9.850778816199377e-05,
|
| 392 |
+
"loss": 0.3684,
|
| 393 |
+
"step": 480
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.53,
|
| 397 |
+
"grad_norm": 5.32474422454834,
|
| 398 |
+
"learning_rate": 9.84766355140187e-05,
|
| 399 |
+
"loss": 0.3567,
|
| 400 |
+
"step": 490
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.56,
|
| 404 |
+
"grad_norm": 2.955794334411621,
|
| 405 |
+
"learning_rate": 9.844548286604361e-05,
|
| 406 |
+
"loss": 0.4048,
|
| 407 |
+
"step": 500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.56,
|
| 411 |
+
"eval_accuracy": 0.8214285714285714,
|
| 412 |
+
"eval_f1": 0.80775004871548,
|
| 413 |
+
"eval_loss": 0.5058895349502563,
|
| 414 |
+
"eval_precision": 0.8156080811716645,
|
| 415 |
+
"eval_recall": 0.8214285714285714,
|
| 416 |
+
"eval_runtime": 39.0979,
|
| 417 |
+
"eval_samples_per_second": 73.764,
|
| 418 |
+
"eval_steps_per_second": 9.233,
|
| 419 |
+
"step": 500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.59,
|
| 423 |
+
"grad_norm": 3.655855894088745,
|
| 424 |
+
"learning_rate": 9.841433021806854e-05,
|
| 425 |
+
"loss": 0.4464,
|
| 426 |
+
"step": 510
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.62,
|
| 430 |
+
"grad_norm": 3.6523778438568115,
|
| 431 |
+
"learning_rate": 9.838317757009346e-05,
|
| 432 |
+
"loss": 0.4154,
|
| 433 |
+
"step": 520
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.65,
|
| 437 |
+
"grad_norm": 6.649527072906494,
|
| 438 |
+
"learning_rate": 9.835202492211837e-05,
|
| 439 |
+
"loss": 0.4337,
|
| 440 |
+
"step": 530
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.68,
|
| 444 |
+
"grad_norm": 4.308875560760498,
|
| 445 |
+
"learning_rate": 9.83208722741433e-05,
|
| 446 |
+
"loss": 0.3551,
|
| 447 |
+
"step": 540
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.71,
|
| 451 |
+
"grad_norm": 5.290976047515869,
|
| 452 |
+
"learning_rate": 9.828971962616823e-05,
|
| 453 |
+
"loss": 0.4329,
|
| 454 |
+
"step": 550
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.74,
|
| 458 |
+
"grad_norm": 3.688100814819336,
|
| 459 |
+
"learning_rate": 9.825856697819316e-05,
|
| 460 |
+
"loss": 0.4306,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.78,
|
| 465 |
+
"grad_norm": 2.4794669151306152,
|
| 466 |
+
"learning_rate": 9.822741433021808e-05,
|
| 467 |
+
"loss": 0.3281,
|
| 468 |
+
"step": 570
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.81,
|
| 472 |
+
"grad_norm": 3.5106523036956787,
|
| 473 |
+
"learning_rate": 9.819626168224299e-05,
|
| 474 |
+
"loss": 0.3184,
|
| 475 |
+
"step": 580
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.84,
|
| 479 |
+
"grad_norm": 5.135136604309082,
|
| 480 |
+
"learning_rate": 9.816510903426792e-05,
|
| 481 |
+
"loss": 0.3644,
|
| 482 |
+
"step": 590
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.87,
|
| 486 |
+
"grad_norm": 3.2593114376068115,
|
| 487 |
+
"learning_rate": 9.813395638629284e-05,
|
| 488 |
+
"loss": 0.2939,
|
| 489 |
+
"step": 600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.87,
|
| 493 |
+
"eval_accuracy": 0.7680305131761442,
|
| 494 |
+
"eval_f1": 0.7817959651329371,
|
| 495 |
+
"eval_loss": 0.6723023653030396,
|
| 496 |
+
"eval_precision": 0.8366418813297796,
|
| 497 |
+
"eval_recall": 0.7680305131761442,
|
| 498 |
+
"eval_runtime": 39.3089,
|
| 499 |
+
"eval_samples_per_second": 73.368,
|
| 500 |
+
"eval_steps_per_second": 9.184,
|
| 501 |
+
"step": 600
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.9,
|
| 505 |
+
"grad_norm": 7.719142913818359,
|
| 506 |
+
"learning_rate": 9.810280373831777e-05,
|
| 507 |
+
"loss": 0.5629,
|
| 508 |
+
"step": 610
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.93,
|
| 512 |
+
"grad_norm": 4.130067348480225,
|
| 513 |
+
"learning_rate": 9.807165109034268e-05,
|
| 514 |
+
"loss": 0.4416,
|
| 515 |
+
"step": 620
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.96,
|
| 519 |
+
"grad_norm": 1.9364572763442993,
|
| 520 |
+
"learning_rate": 9.80404984423676e-05,
|
| 521 |
+
"loss": 0.2339,
|
| 522 |
+
"step": 630
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.99,
|
| 526 |
+
"grad_norm": 2.4033007621765137,
|
| 527 |
+
"learning_rate": 9.800934579439253e-05,
|
| 528 |
+
"loss": 0.3284,
|
| 529 |
+
"step": 640
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.02,
|
| 533 |
+
"grad_norm": 3.25533390045166,
|
| 534 |
+
"learning_rate": 9.797819314641746e-05,
|
| 535 |
+
"loss": 0.2307,
|
| 536 |
+
"step": 650
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.06,
|
| 540 |
+
"grad_norm": 3.1277670860290527,
|
| 541 |
+
"learning_rate": 9.794704049844237e-05,
|
| 542 |
+
"loss": 0.2063,
|
| 543 |
+
"step": 660
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.09,
|
| 547 |
+
"grad_norm": 2.923804521560669,
|
| 548 |
+
"learning_rate": 9.791588785046729e-05,
|
| 549 |
+
"loss": 0.1563,
|
| 550 |
+
"step": 670
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.12,
|
| 554 |
+
"grad_norm": 4.745158672332764,
|
| 555 |
+
"learning_rate": 9.788473520249222e-05,
|
| 556 |
+
"loss": 0.2451,
|
| 557 |
+
"step": 680
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.15,
|
| 561 |
+
"grad_norm": 5.691440582275391,
|
| 562 |
+
"learning_rate": 9.785358255451714e-05,
|
| 563 |
+
"loss": 0.2315,
|
| 564 |
+
"step": 690
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.18,
|
| 568 |
+
"grad_norm": 7.0971550941467285,
|
| 569 |
+
"learning_rate": 9.782242990654206e-05,
|
| 570 |
+
"loss": 0.2138,
|
| 571 |
+
"step": 700
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.18,
|
| 575 |
+
"eval_accuracy": 0.812760055478502,
|
| 576 |
+
"eval_f1": 0.8169834700772869,
|
| 577 |
+
"eval_loss": 0.635110080242157,
|
| 578 |
+
"eval_precision": 0.8480203726240728,
|
| 579 |
+
"eval_recall": 0.812760055478502,
|
| 580 |
+
"eval_runtime": 39.4295,
|
| 581 |
+
"eval_samples_per_second": 73.143,
|
| 582 |
+
"eval_steps_per_second": 9.156,
|
| 583 |
+
"step": 700
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.21,
|
| 587 |
+
"grad_norm": 2.342768430709839,
|
| 588 |
+
"learning_rate": 9.779127725856699e-05,
|
| 589 |
+
"loss": 0.2763,
|
| 590 |
+
"step": 710
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.24,
|
| 594 |
+
"grad_norm": 4.194737434387207,
|
| 595 |
+
"learning_rate": 9.77601246105919e-05,
|
| 596 |
+
"loss": 0.3159,
|
| 597 |
+
"step": 720
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.27,
|
| 601 |
+
"grad_norm": 4.488862991333008,
|
| 602 |
+
"learning_rate": 9.772897196261682e-05,
|
| 603 |
+
"loss": 0.2594,
|
| 604 |
+
"step": 730
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.31,
|
| 608 |
+
"grad_norm": 3.612229347229004,
|
| 609 |
+
"learning_rate": 9.769781931464175e-05,
|
| 610 |
+
"loss": 0.1651,
|
| 611 |
+
"step": 740
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.34,
|
| 615 |
+
"grad_norm": 4.490918159484863,
|
| 616 |
+
"learning_rate": 9.766666666666668e-05,
|
| 617 |
+
"loss": 0.1714,
|
| 618 |
+
"step": 750
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.37,
|
| 622 |
+
"grad_norm": 1.2064989805221558,
|
| 623 |
+
"learning_rate": 9.76355140186916e-05,
|
| 624 |
+
"loss": 0.1423,
|
| 625 |
+
"step": 760
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.4,
|
| 629 |
+
"grad_norm": 3.8275320529937744,
|
| 630 |
+
"learning_rate": 9.760436137071651e-05,
|
| 631 |
+
"loss": 0.2647,
|
| 632 |
+
"step": 770
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.43,
|
| 636 |
+
"grad_norm": 6.258784294128418,
|
| 637 |
+
"learning_rate": 9.757320872274144e-05,
|
| 638 |
+
"loss": 0.1925,
|
| 639 |
+
"step": 780
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.46,
|
| 643 |
+
"grad_norm": 6.503872394561768,
|
| 644 |
+
"learning_rate": 9.754205607476637e-05,
|
| 645 |
+
"loss": 0.3565,
|
| 646 |
+
"step": 790
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.49,
|
| 650 |
+
"grad_norm": 4.768139362335205,
|
| 651 |
+
"learning_rate": 9.751090342679128e-05,
|
| 652 |
+
"loss": 0.2615,
|
| 653 |
+
"step": 800
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.49,
|
| 657 |
+
"eval_accuracy": 0.8321775312066574,
|
| 658 |
+
"eval_f1": 0.8323189306799796,
|
| 659 |
+
"eval_loss": 0.4919604957103729,
|
| 660 |
+
"eval_precision": 0.8400335349095535,
|
| 661 |
+
"eval_recall": 0.8321775312066574,
|
| 662 |
+
"eval_runtime": 39.8278,
|
| 663 |
+
"eval_samples_per_second": 72.412,
|
| 664 |
+
"eval_steps_per_second": 9.064,
|
| 665 |
+
"step": 800
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.52,
|
| 669 |
+
"grad_norm": 3.3493497371673584,
|
| 670 |
+
"learning_rate": 9.74797507788162e-05,
|
| 671 |
+
"loss": 0.179,
|
| 672 |
+
"step": 810
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.55,
|
| 676 |
+
"grad_norm": 6.209288597106934,
|
| 677 |
+
"learning_rate": 9.744859813084113e-05,
|
| 678 |
+
"loss": 0.1872,
|
| 679 |
+
"step": 820
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 2.59,
|
| 683 |
+
"grad_norm": 3.6066982746124268,
|
| 684 |
+
"learning_rate": 9.741744548286604e-05,
|
| 685 |
+
"loss": 0.24,
|
| 686 |
+
"step": 830
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.62,
|
| 690 |
+
"grad_norm": 2.330963611602783,
|
| 691 |
+
"learning_rate": 9.738629283489097e-05,
|
| 692 |
+
"loss": 0.177,
|
| 693 |
+
"step": 840
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.65,
|
| 697 |
+
"grad_norm": 0.31879034638404846,
|
| 698 |
+
"learning_rate": 9.73551401869159e-05,
|
| 699 |
+
"loss": 0.1846,
|
| 700 |
+
"step": 850
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.68,
|
| 704 |
+
"grad_norm": 6.56818151473999,
|
| 705 |
+
"learning_rate": 9.732398753894082e-05,
|
| 706 |
+
"loss": 0.2731,
|
| 707 |
+
"step": 860
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.71,
|
| 711 |
+
"grad_norm": 1.255943775177002,
|
| 712 |
+
"learning_rate": 9.729283489096573e-05,
|
| 713 |
+
"loss": 0.3217,
|
| 714 |
+
"step": 870
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.74,
|
| 718 |
+
"grad_norm": 5.009977340698242,
|
| 719 |
+
"learning_rate": 9.726168224299066e-05,
|
| 720 |
+
"loss": 0.2576,
|
| 721 |
+
"step": 880
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.77,
|
| 725 |
+
"grad_norm": 1.8944584131240845,
|
| 726 |
+
"learning_rate": 9.723052959501559e-05,
|
| 727 |
+
"loss": 0.2223,
|
| 728 |
+
"step": 890
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.8,
|
| 732 |
+
"grad_norm": 3.543699026107788,
|
| 733 |
+
"learning_rate": 9.71993769470405e-05,
|
| 734 |
+
"loss": 0.2125,
|
| 735 |
+
"step": 900
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.8,
|
| 739 |
+
"eval_accuracy": 0.8491678224687933,
|
| 740 |
+
"eval_f1": 0.843224216265628,
|
| 741 |
+
"eval_loss": 0.5596445202827454,
|
| 742 |
+
"eval_precision": 0.8508841434558159,
|
| 743 |
+
"eval_recall": 0.8491678224687933,
|
| 744 |
+
"eval_runtime": 39.2828,
|
| 745 |
+
"eval_samples_per_second": 73.416,
|
| 746 |
+
"eval_steps_per_second": 9.19,
|
| 747 |
+
"step": 900
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.83,
|
| 751 |
+
"grad_norm": 5.571394920349121,
|
| 752 |
+
"learning_rate": 9.716822429906542e-05,
|
| 753 |
+
"loss": 0.2826,
|
| 754 |
+
"step": 910
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.87,
|
| 758 |
+
"grad_norm": 5.057092666625977,
|
| 759 |
+
"learning_rate": 9.713707165109035e-05,
|
| 760 |
+
"loss": 0.2647,
|
| 761 |
+
"step": 920
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.9,
|
| 765 |
+
"grad_norm": 3.190361738204956,
|
| 766 |
+
"learning_rate": 9.710591900311527e-05,
|
| 767 |
+
"loss": 0.4015,
|
| 768 |
+
"step": 930
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.93,
|
| 772 |
+
"grad_norm": 6.205695629119873,
|
| 773 |
+
"learning_rate": 9.70747663551402e-05,
|
| 774 |
+
"loss": 0.312,
|
| 775 |
+
"step": 940
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.96,
|
| 779 |
+
"grad_norm": 4.805609226226807,
|
| 780 |
+
"learning_rate": 9.704361370716511e-05,
|
| 781 |
+
"loss": 0.2098,
|
| 782 |
+
"step": 950
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.99,
|
| 786 |
+
"grad_norm": 3.2721455097198486,
|
| 787 |
+
"learning_rate": 9.701246105919004e-05,
|
| 788 |
+
"loss": 0.1959,
|
| 789 |
+
"step": 960
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.02,
|
| 793 |
+
"grad_norm": 4.190710067749023,
|
| 794 |
+
"learning_rate": 9.698130841121495e-05,
|
| 795 |
+
"loss": 0.1048,
|
| 796 |
+
"step": 970
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 3.05,
|
| 800 |
+
"grad_norm": 0.5176565051078796,
|
| 801 |
+
"learning_rate": 9.695015576323988e-05,
|
| 802 |
+
"loss": 0.0816,
|
| 803 |
+
"step": 980
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 3.08,
|
| 807 |
+
"grad_norm": 0.1512940376996994,
|
| 808 |
+
"learning_rate": 9.691900311526481e-05,
|
| 809 |
+
"loss": 0.0327,
|
| 810 |
+
"step": 990
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 3.12,
|
| 814 |
+
"grad_norm": 5.473361015319824,
|
| 815 |
+
"learning_rate": 9.688785046728971e-05,
|
| 816 |
+
"loss": 0.0768,
|
| 817 |
+
"step": 1000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 3.12,
|
| 821 |
+
"eval_accuracy": 0.8290568654646324,
|
| 822 |
+
"eval_f1": 0.8235345080050543,
|
| 823 |
+
"eval_loss": 0.823904275894165,
|
| 824 |
+
"eval_precision": 0.8499722083747269,
|
| 825 |
+
"eval_recall": 0.8290568654646324,
|
| 826 |
+
"eval_runtime": 39.6039,
|
| 827 |
+
"eval_samples_per_second": 72.821,
|
| 828 |
+
"eval_steps_per_second": 9.115,
|
| 829 |
+
"step": 1000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 3.15,
|
| 833 |
+
"grad_norm": 2.461423635482788,
|
| 834 |
+
"learning_rate": 9.685669781931464e-05,
|
| 835 |
+
"loss": 0.1258,
|
| 836 |
+
"step": 1010
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.18,
|
| 840 |
+
"grad_norm": 5.284664154052734,
|
| 841 |
+
"learning_rate": 9.682554517133957e-05,
|
| 842 |
+
"loss": 0.1124,
|
| 843 |
+
"step": 1020
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 3.21,
|
| 847 |
+
"grad_norm": 1.3465226888656616,
|
| 848 |
+
"learning_rate": 9.679439252336449e-05,
|
| 849 |
+
"loss": 0.0986,
|
| 850 |
+
"step": 1030
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 3.24,
|
| 854 |
+
"grad_norm": 3.916722297668457,
|
| 855 |
+
"learning_rate": 9.676323987538942e-05,
|
| 856 |
+
"loss": 0.0541,
|
| 857 |
+
"step": 1040
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.27,
|
| 861 |
+
"grad_norm": 0.6409209966659546,
|
| 862 |
+
"learning_rate": 9.673208722741433e-05,
|
| 863 |
+
"loss": 0.1176,
|
| 864 |
+
"step": 1050
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.3,
|
| 868 |
+
"grad_norm": 4.325451374053955,
|
| 869 |
+
"learning_rate": 9.670093457943926e-05,
|
| 870 |
+
"loss": 0.2169,
|
| 871 |
+
"step": 1060
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 3.33,
|
| 875 |
+
"grad_norm": 0.5127350687980652,
|
| 876 |
+
"learning_rate": 9.666978193146418e-05,
|
| 877 |
+
"loss": 0.0739,
|
| 878 |
+
"step": 1070
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.36,
|
| 882 |
+
"grad_norm": 7.527690410614014,
|
| 883 |
+
"learning_rate": 9.66386292834891e-05,
|
| 884 |
+
"loss": 0.184,
|
| 885 |
+
"step": 1080
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.4,
|
| 889 |
+
"grad_norm": 2.938415765762329,
|
| 890 |
+
"learning_rate": 9.660747663551402e-05,
|
| 891 |
+
"loss": 0.1526,
|
| 892 |
+
"step": 1090
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.43,
|
| 896 |
+
"grad_norm": 0.9604325890541077,
|
| 897 |
+
"learning_rate": 9.657632398753894e-05,
|
| 898 |
+
"loss": 0.0649,
|
| 899 |
+
"step": 1100
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.43,
|
| 903 |
+
"eval_accuracy": 0.8366851595006934,
|
| 904 |
+
"eval_f1": 0.8359690431594896,
|
| 905 |
+
"eval_loss": 0.6827093958854675,
|
| 906 |
+
"eval_precision": 0.8480904372623412,
|
| 907 |
+
"eval_recall": 0.8366851595006934,
|
| 908 |
+
"eval_runtime": 39.8316,
|
| 909 |
+
"eval_samples_per_second": 72.405,
|
| 910 |
+
"eval_steps_per_second": 9.063,
|
| 911 |
+
"step": 1100
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.46,
|
| 915 |
+
"grad_norm": 0.6656555533409119,
|
| 916 |
+
"learning_rate": 9.654517133956387e-05,
|
| 917 |
+
"loss": 0.0866,
|
| 918 |
+
"step": 1110
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 3.49,
|
| 922 |
+
"grad_norm": 1.8327091932296753,
|
| 923 |
+
"learning_rate": 9.65140186915888e-05,
|
| 924 |
+
"loss": 0.1117,
|
| 925 |
+
"step": 1120
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 3.52,
|
| 929 |
+
"grad_norm": 6.639819145202637,
|
| 930 |
+
"learning_rate": 9.648286604361371e-05,
|
| 931 |
+
"loss": 0.0607,
|
| 932 |
+
"step": 1130
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.55,
|
| 936 |
+
"grad_norm": 9.595551490783691,
|
| 937 |
+
"learning_rate": 9.645171339563863e-05,
|
| 938 |
+
"loss": 0.1603,
|
| 939 |
+
"step": 1140
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 3.58,
|
| 943 |
+
"grad_norm": 4.852327346801758,
|
| 944 |
+
"learning_rate": 9.642056074766356e-05,
|
| 945 |
+
"loss": 0.1289,
|
| 946 |
+
"step": 1150
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.61,
|
| 950 |
+
"grad_norm": 0.8141772150993347,
|
| 951 |
+
"learning_rate": 9.638940809968848e-05,
|
| 952 |
+
"loss": 0.2513,
|
| 953 |
+
"step": 1160
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.64,
|
| 957 |
+
"grad_norm": 2.2528672218322754,
|
| 958 |
+
"learning_rate": 9.63582554517134e-05,
|
| 959 |
+
"loss": 0.1033,
|
| 960 |
+
"step": 1170
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.68,
|
| 964 |
+
"grad_norm": 4.099298000335693,
|
| 965 |
+
"learning_rate": 9.632710280373833e-05,
|
| 966 |
+
"loss": 0.2042,
|
| 967 |
+
"step": 1180
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 3.71,
|
| 971 |
+
"grad_norm": 2.307119131088257,
|
| 972 |
+
"learning_rate": 9.629595015576324e-05,
|
| 973 |
+
"loss": 0.0714,
|
| 974 |
+
"step": 1190
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 3.74,
|
| 978 |
+
"grad_norm": 6.8174543380737305,
|
| 979 |
+
"learning_rate": 9.626479750778816e-05,
|
| 980 |
+
"loss": 0.1382,
|
| 981 |
+
"step": 1200
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 3.74,
|
| 985 |
+
"eval_accuracy": 0.84500693481276,
|
| 986 |
+
"eval_f1": 0.8398698444204201,
|
| 987 |
+
"eval_loss": 0.6838334798812866,
|
| 988 |
+
"eval_precision": 0.8466724060209081,
|
| 989 |
+
"eval_recall": 0.84500693481276,
|
| 990 |
+
"eval_runtime": 39.4271,
|
| 991 |
+
"eval_samples_per_second": 73.148,
|
| 992 |
+
"eval_steps_per_second": 9.156,
|
| 993 |
+
"step": 1200
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.77,
|
| 997 |
+
"grad_norm": 3.4418959617614746,
|
| 998 |
+
"learning_rate": 9.623364485981309e-05,
|
| 999 |
+
"loss": 0.0921,
|
| 1000 |
+
"step": 1210
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 3.8,
|
| 1004 |
+
"grad_norm": 3.6201603412628174,
|
| 1005 |
+
"learning_rate": 9.620249221183802e-05,
|
| 1006 |
+
"loss": 0.15,
|
| 1007 |
+
"step": 1220
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 3.83,
|
| 1011 |
+
"grad_norm": 6.8857550621032715,
|
| 1012 |
+
"learning_rate": 9.617133956386293e-05,
|
| 1013 |
+
"loss": 0.0965,
|
| 1014 |
+
"step": 1230
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 3.86,
|
| 1018 |
+
"grad_norm": 3.10553240776062,
|
| 1019 |
+
"learning_rate": 9.614018691588785e-05,
|
| 1020 |
+
"loss": 0.1674,
|
| 1021 |
+
"step": 1240
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 3.89,
|
| 1025 |
+
"grad_norm": 9.131609916687012,
|
| 1026 |
+
"learning_rate": 9.610903426791278e-05,
|
| 1027 |
+
"loss": 0.1596,
|
| 1028 |
+
"step": 1250
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 3.93,
|
| 1032 |
+
"grad_norm": 0.35134002566337585,
|
| 1033 |
+
"learning_rate": 9.607788161993771e-05,
|
| 1034 |
+
"loss": 0.1157,
|
| 1035 |
+
"step": 1260
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 3.96,
|
| 1039 |
+
"grad_norm": 5.575935363769531,
|
| 1040 |
+
"learning_rate": 9.604672897196262e-05,
|
| 1041 |
+
"loss": 0.0822,
|
| 1042 |
+
"step": 1270
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 3.99,
|
| 1046 |
+
"grad_norm": 0.6137746572494507,
|
| 1047 |
+
"learning_rate": 9.601557632398754e-05,
|
| 1048 |
+
"loss": 0.1316,
|
| 1049 |
+
"step": 1280
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.02,
|
| 1053 |
+
"grad_norm": 0.34164953231811523,
|
| 1054 |
+
"learning_rate": 9.598442367601247e-05,
|
| 1055 |
+
"loss": 0.0739,
|
| 1056 |
+
"step": 1290
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 4.05,
|
| 1060 |
+
"grad_norm": 4.076730728149414,
|
| 1061 |
+
"learning_rate": 9.595327102803738e-05,
|
| 1062 |
+
"loss": 0.0486,
|
| 1063 |
+
"step": 1300
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 4.05,
|
| 1067 |
+
"eval_accuracy": 0.8578363384188626,
|
| 1068 |
+
"eval_f1": 0.8494463868744596,
|
| 1069 |
+
"eval_loss": 0.6367300748825073,
|
| 1070 |
+
"eval_precision": 0.8548000651229425,
|
| 1071 |
+
"eval_recall": 0.8578363384188626,
|
| 1072 |
+
"eval_runtime": 39.1728,
|
| 1073 |
+
"eval_samples_per_second": 73.623,
|
| 1074 |
+
"eval_steps_per_second": 9.216,
|
| 1075 |
+
"step": 1300
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 4.08,
|
| 1079 |
+
"grad_norm": 0.4267037808895111,
|
| 1080 |
+
"learning_rate": 9.592211838006231e-05,
|
| 1081 |
+
"loss": 0.0499,
|
| 1082 |
+
"step": 1310
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 4.11,
|
| 1086 |
+
"grad_norm": 8.932145118713379,
|
| 1087 |
+
"learning_rate": 9.589096573208724e-05,
|
| 1088 |
+
"loss": 0.058,
|
| 1089 |
+
"step": 1320
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 4.14,
|
| 1093 |
+
"grad_norm": 7.81501579284668,
|
| 1094 |
+
"learning_rate": 9.585981308411214e-05,
|
| 1095 |
+
"loss": 0.0497,
|
| 1096 |
+
"step": 1330
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 4.17,
|
| 1100 |
+
"grad_norm": 3.25376296043396,
|
| 1101 |
+
"learning_rate": 9.582866043613707e-05,
|
| 1102 |
+
"loss": 0.0613,
|
| 1103 |
+
"step": 1340
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 4.21,
|
| 1107 |
+
"grad_norm": 0.009625586681067944,
|
| 1108 |
+
"learning_rate": 9.5797507788162e-05,
|
| 1109 |
+
"loss": 0.0882,
|
| 1110 |
+
"step": 1350
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 4.24,
|
| 1114 |
+
"grad_norm": 8.644308090209961,
|
| 1115 |
+
"learning_rate": 9.576635514018693e-05,
|
| 1116 |
+
"loss": 0.0729,
|
| 1117 |
+
"step": 1360
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 4.27,
|
| 1121 |
+
"grad_norm": 11.613913536071777,
|
| 1122 |
+
"learning_rate": 9.573520249221185e-05,
|
| 1123 |
+
"loss": 0.1285,
|
| 1124 |
+
"step": 1370
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.3,
|
| 1128 |
+
"grad_norm": 0.9490543603897095,
|
| 1129 |
+
"learning_rate": 9.570404984423676e-05,
|
| 1130 |
+
"loss": 0.0408,
|
| 1131 |
+
"step": 1380
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 4.33,
|
| 1135 |
+
"grad_norm": 2.557040214538574,
|
| 1136 |
+
"learning_rate": 9.567289719626169e-05,
|
| 1137 |
+
"loss": 0.0689,
|
| 1138 |
+
"step": 1390
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 4.36,
|
| 1142 |
+
"grad_norm": 7.547731399536133,
|
| 1143 |
+
"learning_rate": 9.56417445482866e-05,
|
| 1144 |
+
"loss": 0.1122,
|
| 1145 |
+
"step": 1400
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.36,
|
| 1149 |
+
"eval_accuracy": 0.8398058252427184,
|
| 1150 |
+
"eval_f1": 0.833035822565054,
|
| 1151 |
+
"eval_loss": 0.7330206036567688,
|
| 1152 |
+
"eval_precision": 0.836759139491613,
|
| 1153 |
+
"eval_recall": 0.8398058252427184,
|
| 1154 |
+
"eval_runtime": 39.5302,
|
| 1155 |
+
"eval_samples_per_second": 72.957,
|
| 1156 |
+
"eval_steps_per_second": 9.132,
|
| 1157 |
+
"step": 1400
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 4.39,
|
| 1161 |
+
"grad_norm": 0.47195371985435486,
|
| 1162 |
+
"learning_rate": 9.561059190031153e-05,
|
| 1163 |
+
"loss": 0.0087,
|
| 1164 |
+
"step": 1410
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 4.42,
|
| 1168 |
+
"grad_norm": 0.02496817521750927,
|
| 1169 |
+
"learning_rate": 9.557943925233645e-05,
|
| 1170 |
+
"loss": 0.0678,
|
| 1171 |
+
"step": 1420
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 4.45,
|
| 1175 |
+
"grad_norm": 0.044717635959386826,
|
| 1176 |
+
"learning_rate": 9.554828660436137e-05,
|
| 1177 |
+
"loss": 0.0409,
|
| 1178 |
+
"step": 1430
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 4.49,
|
| 1182 |
+
"grad_norm": 2.304049015045166,
|
| 1183 |
+
"learning_rate": 9.55171339563863e-05,
|
| 1184 |
+
"loss": 0.0661,
|
| 1185 |
+
"step": 1440
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 4.52,
|
| 1189 |
+
"grad_norm": 11.10191822052002,
|
| 1190 |
+
"learning_rate": 9.548598130841122e-05,
|
| 1191 |
+
"loss": 0.3254,
|
| 1192 |
+
"step": 1450
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 4.55,
|
| 1196 |
+
"grad_norm": 0.0031379794236272573,
|
| 1197 |
+
"learning_rate": 9.545482866043615e-05,
|
| 1198 |
+
"loss": 0.0655,
|
| 1199 |
+
"step": 1460
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 4.58,
|
| 1203 |
+
"grad_norm": 1.050758719444275,
|
| 1204 |
+
"learning_rate": 9.542367601246105e-05,
|
| 1205 |
+
"loss": 0.0968,
|
| 1206 |
+
"step": 1470
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 4.61,
|
| 1210 |
+
"grad_norm": 0.027871431782841682,
|
| 1211 |
+
"learning_rate": 9.539252336448598e-05,
|
| 1212 |
+
"loss": 0.1033,
|
| 1213 |
+
"step": 1480
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 4.64,
|
| 1217 |
+
"grad_norm": 0.054837290197610855,
|
| 1218 |
+
"learning_rate": 9.536137071651091e-05,
|
| 1219 |
+
"loss": 0.0225,
|
| 1220 |
+
"step": 1490
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 4.67,
|
| 1224 |
+
"grad_norm": 5.67630672454834,
|
| 1225 |
+
"learning_rate": 9.533021806853583e-05,
|
| 1226 |
+
"loss": 0.0302,
|
| 1227 |
+
"step": 1500
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 4.67,
|
| 1231 |
+
"eval_accuracy": 0.84500693481276,
|
| 1232 |
+
"eval_f1": 0.8442384441117506,
|
| 1233 |
+
"eval_loss": 0.7136919498443604,
|
| 1234 |
+
"eval_precision": 0.8469740143199302,
|
| 1235 |
+
"eval_recall": 0.84500693481276,
|
| 1236 |
+
"eval_runtime": 39.1304,
|
| 1237 |
+
"eval_samples_per_second": 73.702,
|
| 1238 |
+
"eval_steps_per_second": 9.226,
|
| 1239 |
+
"step": 1500
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 4.7,
|
| 1243 |
+
"grad_norm": 0.295539915561676,
|
| 1244 |
+
"learning_rate": 9.529906542056076e-05,
|
| 1245 |
+
"loss": 0.1178,
|
| 1246 |
+
"step": 1510
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 4.74,
|
| 1250 |
+
"grad_norm": 0.0796700268983841,
|
| 1251 |
+
"learning_rate": 9.526791277258567e-05,
|
| 1252 |
+
"loss": 0.0481,
|
| 1253 |
+
"step": 1520
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 4.77,
|
| 1257 |
+
"grad_norm": 0.1068115308880806,
|
| 1258 |
+
"learning_rate": 9.523676012461059e-05,
|
| 1259 |
+
"loss": 0.0282,
|
| 1260 |
+
"step": 1530
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 4.8,
|
| 1264 |
+
"grad_norm": 1.0221561193466187,
|
| 1265 |
+
"learning_rate": 9.520560747663552e-05,
|
| 1266 |
+
"loss": 0.0538,
|
| 1267 |
+
"step": 1540
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 4.83,
|
| 1271 |
+
"grad_norm": 7.369207859039307,
|
| 1272 |
+
"learning_rate": 9.517445482866045e-05,
|
| 1273 |
+
"loss": 0.1239,
|
| 1274 |
+
"step": 1550
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.86,
|
| 1278 |
+
"grad_norm": 9.008218765258789,
|
| 1279 |
+
"learning_rate": 9.514330218068536e-05,
|
| 1280 |
+
"loss": 0.055,
|
| 1281 |
+
"step": 1560
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 4.89,
|
| 1285 |
+
"grad_norm": 3.585855722427368,
|
| 1286 |
+
"learning_rate": 9.511214953271028e-05,
|
| 1287 |
+
"loss": 0.03,
|
| 1288 |
+
"step": 1570
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 4.92,
|
| 1292 |
+
"grad_norm": 0.15154320001602173,
|
| 1293 |
+
"learning_rate": 9.50809968847352e-05,
|
| 1294 |
+
"loss": 0.0168,
|
| 1295 |
+
"step": 1580
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 4.95,
|
| 1299 |
+
"grad_norm": 0.030903339385986328,
|
| 1300 |
+
"learning_rate": 9.504984423676014e-05,
|
| 1301 |
+
"loss": 0.1067,
|
| 1302 |
+
"step": 1590
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 4.98,
|
| 1306 |
+
"grad_norm": 0.4652014672756195,
|
| 1307 |
+
"learning_rate": 9.501869158878505e-05,
|
| 1308 |
+
"loss": 0.0462,
|
| 1309 |
+
"step": 1600
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 4.98,
|
| 1313 |
+
"eval_accuracy": 0.8515950069348127,
|
| 1314 |
+
"eval_f1": 0.8455611718307666,
|
| 1315 |
+
"eval_loss": 0.8198381066322327,
|
| 1316 |
+
"eval_precision": 0.8519412050125947,
|
| 1317 |
+
"eval_recall": 0.8515950069348127,
|
| 1318 |
+
"eval_runtime": 39.6856,
|
| 1319 |
+
"eval_samples_per_second": 72.671,
|
| 1320 |
+
"eval_steps_per_second": 9.096,
|
| 1321 |
+
"step": 1600
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 5.02,
|
| 1325 |
+
"grad_norm": 14.000198364257812,
|
| 1326 |
+
"learning_rate": 9.498753894080997e-05,
|
| 1327 |
+
"loss": 0.0785,
|
| 1328 |
+
"step": 1610
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 5.05,
|
| 1332 |
+
"grad_norm": 0.21171867847442627,
|
| 1333 |
+
"learning_rate": 9.49563862928349e-05,
|
| 1334 |
+
"loss": 0.019,
|
| 1335 |
+
"step": 1620
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 5.08,
|
| 1339 |
+
"grad_norm": 0.004491983912885189,
|
| 1340 |
+
"learning_rate": 9.492523364485981e-05,
|
| 1341 |
+
"loss": 0.0111,
|
| 1342 |
+
"step": 1630
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 5.11,
|
| 1346 |
+
"grad_norm": 0.016514340415596962,
|
| 1347 |
+
"learning_rate": 9.489408099688474e-05,
|
| 1348 |
+
"loss": 0.0897,
|
| 1349 |
+
"step": 1640
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 5.14,
|
| 1353 |
+
"grad_norm": 8.40817928314209,
|
| 1354 |
+
"learning_rate": 9.486292834890967e-05,
|
| 1355 |
+
"loss": 0.0798,
|
| 1356 |
+
"step": 1650
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 5.17,
|
| 1360 |
+
"grad_norm": 0.07949113100767136,
|
| 1361 |
+
"learning_rate": 9.483177570093458e-05,
|
| 1362 |
+
"loss": 0.0216,
|
| 1363 |
+
"step": 1660
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 5.2,
|
| 1367 |
+
"grad_norm": 4.111806869506836,
|
| 1368 |
+
"learning_rate": 9.48006230529595e-05,
|
| 1369 |
+
"loss": 0.03,
|
| 1370 |
+
"step": 1670
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 5.23,
|
| 1374 |
+
"grad_norm": 0.036615125834941864,
|
| 1375 |
+
"learning_rate": 9.476947040498443e-05,
|
| 1376 |
+
"loss": 0.0115,
|
| 1377 |
+
"step": 1680
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 5.26,
|
| 1381 |
+
"grad_norm": 0.11661379039287567,
|
| 1382 |
+
"learning_rate": 9.473831775700936e-05,
|
| 1383 |
+
"loss": 0.01,
|
| 1384 |
+
"step": 1690
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 5.3,
|
| 1388 |
+
"grad_norm": 0.16430974006652832,
|
| 1389 |
+
"learning_rate": 9.470716510903427e-05,
|
| 1390 |
+
"loss": 0.0109,
|
| 1391 |
+
"step": 1700
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 5.3,
|
| 1395 |
+
"eval_accuracy": 0.8477808599167822,
|
| 1396 |
+
"eval_f1": 0.8378487316868508,
|
| 1397 |
+
"eval_loss": 0.8481851816177368,
|
| 1398 |
+
"eval_precision": 0.8383786998144745,
|
| 1399 |
+
"eval_recall": 0.8477808599167822,
|
| 1400 |
+
"eval_runtime": 39.3442,
|
| 1401 |
+
"eval_samples_per_second": 73.302,
|
| 1402 |
+
"eval_steps_per_second": 9.175,
|
| 1403 |
+
"step": 1700
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 5.33,
|
| 1407 |
+
"grad_norm": 0.005747305229306221,
|
| 1408 |
+
"learning_rate": 9.467601246105919e-05,
|
| 1409 |
+
"loss": 0.0333,
|
| 1410 |
+
"step": 1710
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 5.36,
|
| 1414 |
+
"grad_norm": 5.644034385681152,
|
| 1415 |
+
"learning_rate": 9.464485981308412e-05,
|
| 1416 |
+
"loss": 0.0148,
|
| 1417 |
+
"step": 1720
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 5.39,
|
| 1421 |
+
"grad_norm": 0.002410849556326866,
|
| 1422 |
+
"learning_rate": 9.461370716510903e-05,
|
| 1423 |
+
"loss": 0.0518,
|
| 1424 |
+
"step": 1730
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 5.42,
|
| 1428 |
+
"grad_norm": 0.002693226793780923,
|
| 1429 |
+
"learning_rate": 9.458255451713396e-05,
|
| 1430 |
+
"loss": 0.0508,
|
| 1431 |
+
"step": 1740
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 5.45,
|
| 1435 |
+
"grad_norm": 10.301042556762695,
|
| 1436 |
+
"learning_rate": 9.455140186915888e-05,
|
| 1437 |
+
"loss": 0.071,
|
| 1438 |
+
"step": 1750
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 5.48,
|
| 1442 |
+
"grad_norm": 0.06220326945185661,
|
| 1443 |
+
"learning_rate": 9.452024922118381e-05,
|
| 1444 |
+
"loss": 0.0568,
|
| 1445 |
+
"step": 1760
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 5.51,
|
| 1449 |
+
"grad_norm": 0.07617553323507309,
|
| 1450 |
+
"learning_rate": 9.448909657320872e-05,
|
| 1451 |
+
"loss": 0.078,
|
| 1452 |
+
"step": 1770
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 5.55,
|
| 1456 |
+
"grad_norm": 0.08313547819852829,
|
| 1457 |
+
"learning_rate": 9.445794392523365e-05,
|
| 1458 |
+
"loss": 0.0483,
|
| 1459 |
+
"step": 1780
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 5.58,
|
| 1463 |
+
"grad_norm": 5.813291072845459,
|
| 1464 |
+
"learning_rate": 9.442679127725858e-05,
|
| 1465 |
+
"loss": 0.0369,
|
| 1466 |
+
"step": 1790
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 5.61,
|
| 1470 |
+
"grad_norm": 6.673477649688721,
|
| 1471 |
+
"learning_rate": 9.43956386292835e-05,
|
| 1472 |
+
"loss": 0.0545,
|
| 1473 |
+
"step": 1800
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 5.61,
|
| 1477 |
+
"eval_accuracy": 0.8498613037447988,
|
| 1478 |
+
"eval_f1": 0.8506454763787459,
|
| 1479 |
+
"eval_loss": 0.8046442270278931,
|
| 1480 |
+
"eval_precision": 0.8546625043916174,
|
| 1481 |
+
"eval_recall": 0.8498613037447988,
|
| 1482 |
+
"eval_runtime": 39.6817,
|
| 1483 |
+
"eval_samples_per_second": 72.678,
|
| 1484 |
+
"eval_steps_per_second": 9.097,
|
| 1485 |
+
"step": 1800
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 5.61,
|
| 1489 |
+
"step": 1800,
|
| 1490 |
+
"total_flos": 2.2287694956200755e+18,
|
| 1491 |
+
"train_loss": 0.26933162180913817,
|
| 1492 |
+
"train_runtime": 1430.4649,
|
| 1493 |
+
"train_samples_per_second": 358.485,
|
| 1494 |
+
"train_steps_per_second": 22.44
|
| 1495 |
+
}
|
| 1496 |
+
],
|
| 1497 |
+
"logging_steps": 10,
|
| 1498 |
+
"max_steps": 32100,
|
| 1499 |
+
"num_input_tokens_seen": 0,
|
| 1500 |
+
"num_train_epochs": 100,
|
| 1501 |
+
"save_steps": 100,
|
| 1502 |
+
"total_flos": 2.2287694956200755e+18,
|
| 1503 |
+
"train_batch_size": 16,
|
| 1504 |
+
"trial_name": null,
|
| 1505 |
+
"trial_params": null
|
| 1506 |
+
}
|