Uploaded Model
Browse files- README.md +7 -6
- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Dec05_17-55-29_c16f2c6ab729/events.out.tfevents.1701800820.c16f2c6ab729.278.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1474 -0
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 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-base-16-thesis-demo-HAM10000
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Accuracy: 0.
|
| 25 |
-
- Recall: 0.
|
| 26 |
-
- F1: 0.
|
| 27 |
-
- Precision: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
|
|
| 19 |
|
| 20 |
# vit-base-16-thesis-demo-HAM10000
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the ahishamm/HAM_db_enhanced_balanced_reduced_50_20_20_50 dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.5296
|
| 25 |
+
- Accuracy: 0.8344
|
| 26 |
+
- Recall: 0.8344
|
| 27 |
+
- F1: 0.8344
|
| 28 |
+
- Precision: 0.8344
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.8344459279038718,
|
| 4 |
+
"eval_f1": 0.834445927903872,
|
| 5 |
+
"eval_loss": 0.5296002626419067,
|
| 6 |
+
"eval_precision": 0.8344459279038718,
|
| 7 |
+
"eval_recall": 0.8344459279038718,
|
| 8 |
+
"eval_runtime": 24.1277,
|
| 9 |
+
"eval_samples_per_second": 62.086,
|
| 10 |
+
"eval_steps_per_second": 7.792,
|
| 11 |
+
"total_flos": 2.1525139607212524e+18,
|
| 12 |
+
"train_loss": 0.438499038875927,
|
| 13 |
+
"train_runtime": 1854.8343,
|
| 14 |
+
"train_samples_per_second": 14.975,
|
| 15 |
+
"train_steps_per_second": 0.936
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.8344459279038718,
|
| 4 |
+
"eval_f1": 0.834445927903872,
|
| 5 |
+
"eval_loss": 0.5296002626419067,
|
| 6 |
+
"eval_precision": 0.8344459279038718,
|
| 7 |
+
"eval_recall": 0.8344459279038718,
|
| 8 |
+
"eval_runtime": 24.1277,
|
| 9 |
+
"eval_samples_per_second": 62.086,
|
| 10 |
+
"eval_steps_per_second": 7.792
|
| 11 |
+
}
|
runs/Dec05_17-55-29_c16f2c6ab729/events.out.tfevents.1701800820.c16f2c6ab729.278.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ed6bb587d82263fde01f62ea92feadebb57f08dea67f250143cfe2bea057a4c
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 2.1525139607212524e+18,
|
| 4 |
+
"train_loss": 0.438499038875927,
|
| 5 |
+
"train_runtime": 1854.8343,
|
| 6 |
+
"train_samples_per_second": 14.975,
|
| 7 |
+
"train_steps_per_second": 0.936
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1474 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5296002626419067,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-16-thesis-demo-HAM10000/checkpoint-1300",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 1736,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 0.00019884792626728113,
|
| 14 |
+
"loss": 1.8769,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 0.00019769585253456222,
|
| 20 |
+
"loss": 1.6987,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"learning_rate": 0.00019654377880184333,
|
| 26 |
+
"loss": 1.5002,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.09,
|
| 31 |
+
"learning_rate": 0.00019539170506912442,
|
| 32 |
+
"loss": 1.4262,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.12,
|
| 37 |
+
"learning_rate": 0.00019423963133640554,
|
| 38 |
+
"loss": 1.4855,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.12,
|
| 43 |
+
"eval_accuracy": 0.5093457943925234,
|
| 44 |
+
"eval_f1": 0.5093457943925234,
|
| 45 |
+
"eval_loss": 1.351930856704712,
|
| 46 |
+
"eval_precision": 0.5093457943925234,
|
| 47 |
+
"eval_recall": 0.5093457943925234,
|
| 48 |
+
"eval_runtime": 22.9282,
|
| 49 |
+
"eval_samples_per_second": 65.335,
|
| 50 |
+
"eval_steps_per_second": 8.2,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14,
|
| 55 |
+
"learning_rate": 0.00019308755760368663,
|
| 56 |
+
"loss": 1.2274,
|
| 57 |
+
"step": 60
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.16,
|
| 61 |
+
"learning_rate": 0.00019193548387096775,
|
| 62 |
+
"loss": 1.1676,
|
| 63 |
+
"step": 70
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.18,
|
| 67 |
+
"learning_rate": 0.00019078341013824886,
|
| 68 |
+
"loss": 1.0299,
|
| 69 |
+
"step": 80
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.21,
|
| 73 |
+
"learning_rate": 0.00018963133640552998,
|
| 74 |
+
"loss": 1.192,
|
| 75 |
+
"step": 90
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.23,
|
| 79 |
+
"learning_rate": 0.00018847926267281107,
|
| 80 |
+
"loss": 1.044,
|
| 81 |
+
"step": 100
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.23,
|
| 85 |
+
"eval_accuracy": 0.6268357810413885,
|
| 86 |
+
"eval_f1": 0.6268357810413885,
|
| 87 |
+
"eval_loss": 1.0514885187149048,
|
| 88 |
+
"eval_precision": 0.6268357810413885,
|
| 89 |
+
"eval_recall": 0.6268357810413885,
|
| 90 |
+
"eval_runtime": 23.586,
|
| 91 |
+
"eval_samples_per_second": 63.512,
|
| 92 |
+
"eval_steps_per_second": 7.971,
|
| 93 |
+
"step": 100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.25,
|
| 97 |
+
"learning_rate": 0.00018732718894009219,
|
| 98 |
+
"loss": 1.1791,
|
| 99 |
+
"step": 110
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.28,
|
| 103 |
+
"learning_rate": 0.00018617511520737328,
|
| 104 |
+
"loss": 0.9907,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.3,
|
| 109 |
+
"learning_rate": 0.0001850230414746544,
|
| 110 |
+
"loss": 0.9862,
|
| 111 |
+
"step": 130
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.32,
|
| 115 |
+
"learning_rate": 0.00018387096774193548,
|
| 116 |
+
"loss": 0.9692,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.35,
|
| 121 |
+
"learning_rate": 0.0001827188940092166,
|
| 122 |
+
"loss": 1.0774,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.35,
|
| 127 |
+
"eval_accuracy": 0.568090787716956,
|
| 128 |
+
"eval_f1": 0.568090787716956,
|
| 129 |
+
"eval_loss": 1.2103569507598877,
|
| 130 |
+
"eval_precision": 0.568090787716956,
|
| 131 |
+
"eval_recall": 0.568090787716956,
|
| 132 |
+
"eval_runtime": 23.5075,
|
| 133 |
+
"eval_samples_per_second": 63.724,
|
| 134 |
+
"eval_steps_per_second": 7.997,
|
| 135 |
+
"step": 150
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.37,
|
| 139 |
+
"learning_rate": 0.0001815668202764977,
|
| 140 |
+
"loss": 1.0483,
|
| 141 |
+
"step": 160
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.39,
|
| 145 |
+
"learning_rate": 0.0001804147465437788,
|
| 146 |
+
"loss": 0.8997,
|
| 147 |
+
"step": 170
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.41,
|
| 151 |
+
"learning_rate": 0.0001792626728110599,
|
| 152 |
+
"loss": 0.9513,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.44,
|
| 157 |
+
"learning_rate": 0.000178110599078341,
|
| 158 |
+
"loss": 0.9172,
|
| 159 |
+
"step": 190
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.46,
|
| 163 |
+
"learning_rate": 0.00017695852534562213,
|
| 164 |
+
"loss": 0.9508,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.46,
|
| 169 |
+
"eval_accuracy": 0.6061415220293725,
|
| 170 |
+
"eval_f1": 0.6061415220293725,
|
| 171 |
+
"eval_loss": 1.0623714923858643,
|
| 172 |
+
"eval_precision": 0.6061415220293725,
|
| 173 |
+
"eval_recall": 0.6061415220293725,
|
| 174 |
+
"eval_runtime": 23.18,
|
| 175 |
+
"eval_samples_per_second": 64.625,
|
| 176 |
+
"eval_steps_per_second": 8.11,
|
| 177 |
+
"step": 200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.48,
|
| 181 |
+
"learning_rate": 0.00017580645161290325,
|
| 182 |
+
"loss": 0.7999,
|
| 183 |
+
"step": 210
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.51,
|
| 187 |
+
"learning_rate": 0.00017465437788018436,
|
| 188 |
+
"loss": 0.8259,
|
| 189 |
+
"step": 220
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.53,
|
| 193 |
+
"learning_rate": 0.00017350230414746545,
|
| 194 |
+
"loss": 0.6937,
|
| 195 |
+
"step": 230
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.55,
|
| 199 |
+
"learning_rate": 0.00017235023041474657,
|
| 200 |
+
"loss": 0.7381,
|
| 201 |
+
"step": 240
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.58,
|
| 205 |
+
"learning_rate": 0.00017119815668202766,
|
| 206 |
+
"loss": 0.9522,
|
| 207 |
+
"step": 250
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.58,
|
| 211 |
+
"eval_accuracy": 0.6448598130841121,
|
| 212 |
+
"eval_f1": 0.6448598130841121,
|
| 213 |
+
"eval_loss": 0.9337974786758423,
|
| 214 |
+
"eval_precision": 0.6448598130841121,
|
| 215 |
+
"eval_recall": 0.6448598130841121,
|
| 216 |
+
"eval_runtime": 23.4699,
|
| 217 |
+
"eval_samples_per_second": 63.826,
|
| 218 |
+
"eval_steps_per_second": 8.01,
|
| 219 |
+
"step": 250
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6,
|
| 223 |
+
"learning_rate": 0.00017004608294930878,
|
| 224 |
+
"loss": 0.964,
|
| 225 |
+
"step": 260
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.62,
|
| 229 |
+
"learning_rate": 0.00016889400921658987,
|
| 230 |
+
"loss": 0.9078,
|
| 231 |
+
"step": 270
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.65,
|
| 235 |
+
"learning_rate": 0.00016774193548387098,
|
| 236 |
+
"loss": 0.8004,
|
| 237 |
+
"step": 280
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.67,
|
| 241 |
+
"learning_rate": 0.00016658986175115207,
|
| 242 |
+
"loss": 0.8192,
|
| 243 |
+
"step": 290
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.69,
|
| 247 |
+
"learning_rate": 0.0001654377880184332,
|
| 248 |
+
"loss": 0.774,
|
| 249 |
+
"step": 300
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.69,
|
| 253 |
+
"eval_accuracy": 0.6675567423230975,
|
| 254 |
+
"eval_f1": 0.6675567423230975,
|
| 255 |
+
"eval_loss": 0.8939006328582764,
|
| 256 |
+
"eval_precision": 0.6675567423230975,
|
| 257 |
+
"eval_recall": 0.6675567423230975,
|
| 258 |
+
"eval_runtime": 22.8187,
|
| 259 |
+
"eval_samples_per_second": 65.648,
|
| 260 |
+
"eval_steps_per_second": 8.239,
|
| 261 |
+
"step": 300
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.71,
|
| 265 |
+
"learning_rate": 0.00016428571428571428,
|
| 266 |
+
"loss": 0.6929,
|
| 267 |
+
"step": 310
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.74,
|
| 271 |
+
"learning_rate": 0.0001631336405529954,
|
| 272 |
+
"loss": 0.8671,
|
| 273 |
+
"step": 320
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.76,
|
| 277 |
+
"learning_rate": 0.00016198156682027649,
|
| 278 |
+
"loss": 0.843,
|
| 279 |
+
"step": 330
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.78,
|
| 283 |
+
"learning_rate": 0.0001608294930875576,
|
| 284 |
+
"loss": 0.7337,
|
| 285 |
+
"step": 340
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.81,
|
| 289 |
+
"learning_rate": 0.00015967741935483872,
|
| 290 |
+
"loss": 0.7675,
|
| 291 |
+
"step": 350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.81,
|
| 295 |
+
"eval_accuracy": 0.7182910547396528,
|
| 296 |
+
"eval_f1": 0.7182910547396528,
|
| 297 |
+
"eval_loss": 0.774177074432373,
|
| 298 |
+
"eval_precision": 0.7182910547396528,
|
| 299 |
+
"eval_recall": 0.7182910547396528,
|
| 300 |
+
"eval_runtime": 23.9091,
|
| 301 |
+
"eval_samples_per_second": 62.654,
|
| 302 |
+
"eval_steps_per_second": 7.863,
|
| 303 |
+
"step": 350
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.83,
|
| 307 |
+
"learning_rate": 0.00015852534562211984,
|
| 308 |
+
"loss": 0.7298,
|
| 309 |
+
"step": 360
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.85,
|
| 313 |
+
"learning_rate": 0.00015737327188940093,
|
| 314 |
+
"loss": 0.716,
|
| 315 |
+
"step": 370
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.88,
|
| 319 |
+
"learning_rate": 0.00015622119815668204,
|
| 320 |
+
"loss": 0.6206,
|
| 321 |
+
"step": 380
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.9,
|
| 325 |
+
"learning_rate": 0.00015506912442396313,
|
| 326 |
+
"loss": 0.8554,
|
| 327 |
+
"step": 390
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.92,
|
| 331 |
+
"learning_rate": 0.00015391705069124425,
|
| 332 |
+
"loss": 0.7167,
|
| 333 |
+
"step": 400
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.92,
|
| 337 |
+
"eval_accuracy": 0.7216288384512684,
|
| 338 |
+
"eval_f1": 0.7216288384512684,
|
| 339 |
+
"eval_loss": 0.7695363163948059,
|
| 340 |
+
"eval_precision": 0.7216288384512684,
|
| 341 |
+
"eval_recall": 0.7216288384512684,
|
| 342 |
+
"eval_runtime": 23.7595,
|
| 343 |
+
"eval_samples_per_second": 63.049,
|
| 344 |
+
"eval_steps_per_second": 7.913,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.94,
|
| 349 |
+
"learning_rate": 0.00015276497695852537,
|
| 350 |
+
"loss": 0.8005,
|
| 351 |
+
"step": 410
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.97,
|
| 355 |
+
"learning_rate": 0.00015161290322580646,
|
| 356 |
+
"loss": 0.6622,
|
| 357 |
+
"step": 420
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.99,
|
| 361 |
+
"learning_rate": 0.00015046082949308757,
|
| 362 |
+
"loss": 0.7918,
|
| 363 |
+
"step": 430
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.01,
|
| 367 |
+
"learning_rate": 0.00014930875576036866,
|
| 368 |
+
"loss": 0.5941,
|
| 369 |
+
"step": 440
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.04,
|
| 373 |
+
"learning_rate": 0.00014815668202764978,
|
| 374 |
+
"loss": 0.5204,
|
| 375 |
+
"step": 450
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.04,
|
| 379 |
+
"eval_accuracy": 0.7303070761014686,
|
| 380 |
+
"eval_f1": 0.7303070761014686,
|
| 381 |
+
"eval_loss": 0.8005053400993347,
|
| 382 |
+
"eval_precision": 0.7303070761014686,
|
| 383 |
+
"eval_recall": 0.7303070761014686,
|
| 384 |
+
"eval_runtime": 23.4092,
|
| 385 |
+
"eval_samples_per_second": 63.992,
|
| 386 |
+
"eval_steps_per_second": 8.031,
|
| 387 |
+
"step": 450
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.06,
|
| 391 |
+
"learning_rate": 0.00014700460829493087,
|
| 392 |
+
"loss": 0.6149,
|
| 393 |
+
"step": 460
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.08,
|
| 397 |
+
"learning_rate": 0.00014585253456221199,
|
| 398 |
+
"loss": 0.459,
|
| 399 |
+
"step": 470
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.11,
|
| 403 |
+
"learning_rate": 0.0001447004608294931,
|
| 404 |
+
"loss": 0.5677,
|
| 405 |
+
"step": 480
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.13,
|
| 409 |
+
"learning_rate": 0.00014354838709677422,
|
| 410 |
+
"loss": 0.5199,
|
| 411 |
+
"step": 490
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.15,
|
| 415 |
+
"learning_rate": 0.0001423963133640553,
|
| 416 |
+
"loss": 0.456,
|
| 417 |
+
"step": 500
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.15,
|
| 421 |
+
"eval_accuracy": 0.6902536715620827,
|
| 422 |
+
"eval_f1": 0.6902536715620827,
|
| 423 |
+
"eval_loss": 0.8523401618003845,
|
| 424 |
+
"eval_precision": 0.6902536715620827,
|
| 425 |
+
"eval_recall": 0.6902536715620827,
|
| 426 |
+
"eval_runtime": 24.2665,
|
| 427 |
+
"eval_samples_per_second": 61.731,
|
| 428 |
+
"eval_steps_per_second": 7.747,
|
| 429 |
+
"step": 500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.18,
|
| 433 |
+
"learning_rate": 0.00014124423963133643,
|
| 434 |
+
"loss": 0.5875,
|
| 435 |
+
"step": 510
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.2,
|
| 439 |
+
"learning_rate": 0.00014009216589861752,
|
| 440 |
+
"loss": 0.4803,
|
| 441 |
+
"step": 520
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.22,
|
| 445 |
+
"learning_rate": 0.00013894009216589863,
|
| 446 |
+
"loss": 0.6385,
|
| 447 |
+
"step": 530
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.24,
|
| 451 |
+
"learning_rate": 0.00013778801843317972,
|
| 452 |
+
"loss": 0.5299,
|
| 453 |
+
"step": 540
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.27,
|
| 457 |
+
"learning_rate": 0.00013663594470046084,
|
| 458 |
+
"loss": 0.5421,
|
| 459 |
+
"step": 550
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.27,
|
| 463 |
+
"eval_accuracy": 0.7543391188251002,
|
| 464 |
+
"eval_f1": 0.7543391188251003,
|
| 465 |
+
"eval_loss": 0.6753360629081726,
|
| 466 |
+
"eval_precision": 0.7543391188251002,
|
| 467 |
+
"eval_recall": 0.7543391188251002,
|
| 468 |
+
"eval_runtime": 24.4291,
|
| 469 |
+
"eval_samples_per_second": 61.32,
|
| 470 |
+
"eval_steps_per_second": 7.696,
|
| 471 |
+
"step": 550
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.29,
|
| 475 |
+
"learning_rate": 0.00013548387096774193,
|
| 476 |
+
"loss": 0.4458,
|
| 477 |
+
"step": 560
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.31,
|
| 481 |
+
"learning_rate": 0.00013433179723502305,
|
| 482 |
+
"loss": 0.5533,
|
| 483 |
+
"step": 570
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.34,
|
| 487 |
+
"learning_rate": 0.00013317972350230414,
|
| 488 |
+
"loss": 0.4426,
|
| 489 |
+
"step": 580
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.36,
|
| 493 |
+
"learning_rate": 0.00013202764976958525,
|
| 494 |
+
"loss": 0.4254,
|
| 495 |
+
"step": 590
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.38,
|
| 499 |
+
"learning_rate": 0.00013087557603686637,
|
| 500 |
+
"loss": 0.4446,
|
| 501 |
+
"step": 600
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.38,
|
| 505 |
+
"eval_accuracy": 0.7810413885180241,
|
| 506 |
+
"eval_f1": 0.7810413885180241,
|
| 507 |
+
"eval_loss": 0.6042020320892334,
|
| 508 |
+
"eval_precision": 0.7810413885180241,
|
| 509 |
+
"eval_recall": 0.7810413885180241,
|
| 510 |
+
"eval_runtime": 24.5813,
|
| 511 |
+
"eval_samples_per_second": 60.941,
|
| 512 |
+
"eval_steps_per_second": 7.648,
|
| 513 |
+
"step": 600
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.41,
|
| 517 |
+
"learning_rate": 0.00012972350230414746,
|
| 518 |
+
"loss": 0.5428,
|
| 519 |
+
"step": 610
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.43,
|
| 523 |
+
"learning_rate": 0.00012857142857142858,
|
| 524 |
+
"loss": 0.5215,
|
| 525 |
+
"step": 620
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.45,
|
| 529 |
+
"learning_rate": 0.0001274193548387097,
|
| 530 |
+
"loss": 0.4636,
|
| 531 |
+
"step": 630
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.47,
|
| 535 |
+
"learning_rate": 0.0001262672811059908,
|
| 536 |
+
"loss": 0.5301,
|
| 537 |
+
"step": 640
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.5,
|
| 541 |
+
"learning_rate": 0.0001251152073732719,
|
| 542 |
+
"loss": 0.455,
|
| 543 |
+
"step": 650
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.5,
|
| 547 |
+
"eval_accuracy": 0.7409879839786382,
|
| 548 |
+
"eval_f1": 0.7409879839786382,
|
| 549 |
+
"eval_loss": 0.6912689208984375,
|
| 550 |
+
"eval_precision": 0.7409879839786382,
|
| 551 |
+
"eval_recall": 0.7409879839786382,
|
| 552 |
+
"eval_runtime": 24.0409,
|
| 553 |
+
"eval_samples_per_second": 62.31,
|
| 554 |
+
"eval_steps_per_second": 7.82,
|
| 555 |
+
"step": 650
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.52,
|
| 559 |
+
"learning_rate": 0.00012396313364055302,
|
| 560 |
+
"loss": 0.6054,
|
| 561 |
+
"step": 660
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.54,
|
| 565 |
+
"learning_rate": 0.0001228110599078341,
|
| 566 |
+
"loss": 0.4855,
|
| 567 |
+
"step": 670
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.57,
|
| 571 |
+
"learning_rate": 0.00012165898617511522,
|
| 572 |
+
"loss": 0.4318,
|
| 573 |
+
"step": 680
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.59,
|
| 577 |
+
"learning_rate": 0.00012050691244239631,
|
| 578 |
+
"loss": 0.5567,
|
| 579 |
+
"step": 690
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.61,
|
| 583 |
+
"learning_rate": 0.00011935483870967743,
|
| 584 |
+
"loss": 0.4175,
|
| 585 |
+
"step": 700
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.61,
|
| 589 |
+
"eval_accuracy": 0.7810413885180241,
|
| 590 |
+
"eval_f1": 0.7810413885180241,
|
| 591 |
+
"eval_loss": 0.6142333745956421,
|
| 592 |
+
"eval_precision": 0.7810413885180241,
|
| 593 |
+
"eval_recall": 0.7810413885180241,
|
| 594 |
+
"eval_runtime": 24.8763,
|
| 595 |
+
"eval_samples_per_second": 60.218,
|
| 596 |
+
"eval_steps_per_second": 7.557,
|
| 597 |
+
"step": 700
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.64,
|
| 601 |
+
"learning_rate": 0.00011820276497695852,
|
| 602 |
+
"loss": 0.6193,
|
| 603 |
+
"step": 710
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.66,
|
| 607 |
+
"learning_rate": 0.00011705069124423964,
|
| 608 |
+
"loss": 0.4553,
|
| 609 |
+
"step": 720
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.68,
|
| 613 |
+
"learning_rate": 0.00011589861751152074,
|
| 614 |
+
"loss": 0.4813,
|
| 615 |
+
"step": 730
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.71,
|
| 619 |
+
"learning_rate": 0.00011474654377880186,
|
| 620 |
+
"loss": 0.4984,
|
| 621 |
+
"step": 740
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.73,
|
| 625 |
+
"learning_rate": 0.00011359447004608295,
|
| 626 |
+
"loss": 0.3626,
|
| 627 |
+
"step": 750
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.73,
|
| 631 |
+
"eval_accuracy": 0.8004005340453939,
|
| 632 |
+
"eval_f1": 0.8004005340453939,
|
| 633 |
+
"eval_loss": 0.5830577611923218,
|
| 634 |
+
"eval_precision": 0.8004005340453939,
|
| 635 |
+
"eval_recall": 0.8004005340453939,
|
| 636 |
+
"eval_runtime": 24.5527,
|
| 637 |
+
"eval_samples_per_second": 61.012,
|
| 638 |
+
"eval_steps_per_second": 7.657,
|
| 639 |
+
"step": 750
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.75,
|
| 643 |
+
"learning_rate": 0.00011244239631336406,
|
| 644 |
+
"loss": 0.3285,
|
| 645 |
+
"step": 760
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.77,
|
| 649 |
+
"learning_rate": 0.00011140552995391706,
|
| 650 |
+
"loss": 0.5726,
|
| 651 |
+
"step": 770
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.8,
|
| 655 |
+
"learning_rate": 0.00011025345622119817,
|
| 656 |
+
"loss": 0.4853,
|
| 657 |
+
"step": 780
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.82,
|
| 661 |
+
"learning_rate": 0.00010910138248847928,
|
| 662 |
+
"loss": 0.5274,
|
| 663 |
+
"step": 790
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.84,
|
| 667 |
+
"learning_rate": 0.00010794930875576037,
|
| 668 |
+
"loss": 0.4816,
|
| 669 |
+
"step": 800
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.84,
|
| 673 |
+
"eval_accuracy": 0.7890520694259012,
|
| 674 |
+
"eval_f1": 0.7890520694259012,
|
| 675 |
+
"eval_loss": 0.5586402416229248,
|
| 676 |
+
"eval_precision": 0.7890520694259012,
|
| 677 |
+
"eval_recall": 0.7890520694259012,
|
| 678 |
+
"eval_runtime": 25.1015,
|
| 679 |
+
"eval_samples_per_second": 59.678,
|
| 680 |
+
"eval_steps_per_second": 7.49,
|
| 681 |
+
"step": 800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.87,
|
| 685 |
+
"learning_rate": 0.00010679723502304149,
|
| 686 |
+
"loss": 0.4794,
|
| 687 |
+
"step": 810
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.89,
|
| 691 |
+
"learning_rate": 0.00010564516129032258,
|
| 692 |
+
"loss": 0.418,
|
| 693 |
+
"step": 820
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.91,
|
| 697 |
+
"learning_rate": 0.0001044930875576037,
|
| 698 |
+
"loss": 0.3756,
|
| 699 |
+
"step": 830
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.94,
|
| 703 |
+
"learning_rate": 0.00010334101382488478,
|
| 704 |
+
"loss": 0.5326,
|
| 705 |
+
"step": 840
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.96,
|
| 709 |
+
"learning_rate": 0.0001021889400921659,
|
| 710 |
+
"loss": 0.3257,
|
| 711 |
+
"step": 850
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.96,
|
| 715 |
+
"eval_accuracy": 0.7990654205607477,
|
| 716 |
+
"eval_f1": 0.7990654205607477,
|
| 717 |
+
"eval_loss": 0.5758947134017944,
|
| 718 |
+
"eval_precision": 0.7990654205607477,
|
| 719 |
+
"eval_recall": 0.7990654205607477,
|
| 720 |
+
"eval_runtime": 23.5154,
|
| 721 |
+
"eval_samples_per_second": 63.703,
|
| 722 |
+
"eval_steps_per_second": 7.995,
|
| 723 |
+
"step": 850
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.98,
|
| 727 |
+
"learning_rate": 0.000101036866359447,
|
| 728 |
+
"loss": 0.3173,
|
| 729 |
+
"step": 860
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.0,
|
| 733 |
+
"learning_rate": 9.988479262672812e-05,
|
| 734 |
+
"loss": 0.3198,
|
| 735 |
+
"step": 870
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.03,
|
| 739 |
+
"learning_rate": 9.873271889400923e-05,
|
| 740 |
+
"loss": 0.2706,
|
| 741 |
+
"step": 880
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.05,
|
| 745 |
+
"learning_rate": 9.758064516129033e-05,
|
| 746 |
+
"loss": 0.2695,
|
| 747 |
+
"step": 890
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.07,
|
| 751 |
+
"learning_rate": 9.642857142857143e-05,
|
| 752 |
+
"loss": 0.3111,
|
| 753 |
+
"step": 900
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.07,
|
| 757 |
+
"eval_accuracy": 0.7930574098798397,
|
| 758 |
+
"eval_f1": 0.7930574098798397,
|
| 759 |
+
"eval_loss": 0.6100362539291382,
|
| 760 |
+
"eval_precision": 0.7930574098798397,
|
| 761 |
+
"eval_recall": 0.7930574098798397,
|
| 762 |
+
"eval_runtime": 22.7882,
|
| 763 |
+
"eval_samples_per_second": 65.736,
|
| 764 |
+
"eval_steps_per_second": 8.25,
|
| 765 |
+
"step": 900
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.1,
|
| 769 |
+
"learning_rate": 9.527649769585254e-05,
|
| 770 |
+
"loss": 0.2007,
|
| 771 |
+
"step": 910
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.12,
|
| 775 |
+
"learning_rate": 9.412442396313365e-05,
|
| 776 |
+
"loss": 0.2584,
|
| 777 |
+
"step": 920
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.14,
|
| 781 |
+
"learning_rate": 9.297235023041476e-05,
|
| 782 |
+
"loss": 0.257,
|
| 783 |
+
"step": 930
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.17,
|
| 787 |
+
"learning_rate": 9.182027649769586e-05,
|
| 788 |
+
"loss": 0.3709,
|
| 789 |
+
"step": 940
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.19,
|
| 793 |
+
"learning_rate": 9.066820276497696e-05,
|
| 794 |
+
"loss": 0.2052,
|
| 795 |
+
"step": 950
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.19,
|
| 799 |
+
"eval_accuracy": 0.8110814419225634,
|
| 800 |
+
"eval_f1": 0.8110814419225634,
|
| 801 |
+
"eval_loss": 0.5674178600311279,
|
| 802 |
+
"eval_precision": 0.8110814419225634,
|
| 803 |
+
"eval_recall": 0.8110814419225634,
|
| 804 |
+
"eval_runtime": 23.6606,
|
| 805 |
+
"eval_samples_per_second": 63.312,
|
| 806 |
+
"eval_steps_per_second": 7.946,
|
| 807 |
+
"step": 950
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.21,
|
| 811 |
+
"learning_rate": 8.951612903225806e-05,
|
| 812 |
+
"loss": 0.1869,
|
| 813 |
+
"step": 960
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.24,
|
| 817 |
+
"learning_rate": 8.836405529953917e-05,
|
| 818 |
+
"loss": 0.3195,
|
| 819 |
+
"step": 970
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.26,
|
| 823 |
+
"learning_rate": 8.721198156682027e-05,
|
| 824 |
+
"loss": 0.3406,
|
| 825 |
+
"step": 980
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.28,
|
| 829 |
+
"learning_rate": 8.605990783410139e-05,
|
| 830 |
+
"loss": 0.26,
|
| 831 |
+
"step": 990
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.3,
|
| 835 |
+
"learning_rate": 8.490783410138249e-05,
|
| 836 |
+
"loss": 0.2273,
|
| 837 |
+
"step": 1000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.3,
|
| 841 |
+
"eval_accuracy": 0.80173564753004,
|
| 842 |
+
"eval_f1": 0.8017356475300401,
|
| 843 |
+
"eval_loss": 0.5974730253219604,
|
| 844 |
+
"eval_precision": 0.80173564753004,
|
| 845 |
+
"eval_recall": 0.80173564753004,
|
| 846 |
+
"eval_runtime": 22.7233,
|
| 847 |
+
"eval_samples_per_second": 65.923,
|
| 848 |
+
"eval_steps_per_second": 8.273,
|
| 849 |
+
"step": 1000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.33,
|
| 853 |
+
"learning_rate": 8.37557603686636e-05,
|
| 854 |
+
"loss": 0.2222,
|
| 855 |
+
"step": 1010
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.35,
|
| 859 |
+
"learning_rate": 8.26036866359447e-05,
|
| 860 |
+
"loss": 0.2741,
|
| 861 |
+
"step": 1020
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.37,
|
| 865 |
+
"learning_rate": 8.145161290322582e-05,
|
| 866 |
+
"loss": 0.2503,
|
| 867 |
+
"step": 1030
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.4,
|
| 871 |
+
"learning_rate": 8.029953917050692e-05,
|
| 872 |
+
"loss": 0.2778,
|
| 873 |
+
"step": 1040
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.42,
|
| 877 |
+
"learning_rate": 7.914746543778802e-05,
|
| 878 |
+
"loss": 0.3007,
|
| 879 |
+
"step": 1050
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.42,
|
| 883 |
+
"eval_accuracy": 0.8204272363150867,
|
| 884 |
+
"eval_f1": 0.8204272363150867,
|
| 885 |
+
"eval_loss": 0.5713711977005005,
|
| 886 |
+
"eval_precision": 0.8204272363150867,
|
| 887 |
+
"eval_recall": 0.8204272363150867,
|
| 888 |
+
"eval_runtime": 23.4991,
|
| 889 |
+
"eval_samples_per_second": 63.747,
|
| 890 |
+
"eval_steps_per_second": 8.0,
|
| 891 |
+
"step": 1050
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.44,
|
| 895 |
+
"learning_rate": 7.799539170506914e-05,
|
| 896 |
+
"loss": 0.2108,
|
| 897 |
+
"step": 1060
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.47,
|
| 901 |
+
"learning_rate": 7.684331797235024e-05,
|
| 902 |
+
"loss": 0.2268,
|
| 903 |
+
"step": 1070
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.49,
|
| 907 |
+
"learning_rate": 7.569124423963135e-05,
|
| 908 |
+
"loss": 0.1861,
|
| 909 |
+
"step": 1080
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.51,
|
| 913 |
+
"learning_rate": 7.453917050691245e-05,
|
| 914 |
+
"loss": 0.2302,
|
| 915 |
+
"step": 1090
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.53,
|
| 919 |
+
"learning_rate": 7.338709677419355e-05,
|
| 920 |
+
"loss": 0.2812,
|
| 921 |
+
"step": 1100
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.53,
|
| 925 |
+
"eval_accuracy": 0.8004005340453939,
|
| 926 |
+
"eval_f1": 0.8004005340453939,
|
| 927 |
+
"eval_loss": 0.6080873608589172,
|
| 928 |
+
"eval_precision": 0.8004005340453939,
|
| 929 |
+
"eval_recall": 0.8004005340453939,
|
| 930 |
+
"eval_runtime": 23.4447,
|
| 931 |
+
"eval_samples_per_second": 63.895,
|
| 932 |
+
"eval_steps_per_second": 8.019,
|
| 933 |
+
"step": 1100
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.56,
|
| 937 |
+
"learning_rate": 7.223502304147465e-05,
|
| 938 |
+
"loss": 0.2486,
|
| 939 |
+
"step": 1110
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.58,
|
| 943 |
+
"learning_rate": 7.108294930875576e-05,
|
| 944 |
+
"loss": 0.1691,
|
| 945 |
+
"step": 1120
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.6,
|
| 949 |
+
"learning_rate": 6.993087557603687e-05,
|
| 950 |
+
"loss": 0.2579,
|
| 951 |
+
"step": 1130
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 2.63,
|
| 955 |
+
"learning_rate": 6.877880184331798e-05,
|
| 956 |
+
"loss": 0.2635,
|
| 957 |
+
"step": 1140
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.65,
|
| 961 |
+
"learning_rate": 6.762672811059908e-05,
|
| 962 |
+
"loss": 0.2661,
|
| 963 |
+
"step": 1150
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.65,
|
| 967 |
+
"eval_accuracy": 0.822429906542056,
|
| 968 |
+
"eval_f1": 0.822429906542056,
|
| 969 |
+
"eval_loss": 0.5652973651885986,
|
| 970 |
+
"eval_precision": 0.822429906542056,
|
| 971 |
+
"eval_recall": 0.822429906542056,
|
| 972 |
+
"eval_runtime": 23.861,
|
| 973 |
+
"eval_samples_per_second": 62.78,
|
| 974 |
+
"eval_steps_per_second": 7.879,
|
| 975 |
+
"step": 1150
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.67,
|
| 979 |
+
"learning_rate": 6.647465437788018e-05,
|
| 980 |
+
"loss": 0.3103,
|
| 981 |
+
"step": 1160
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.7,
|
| 985 |
+
"learning_rate": 6.532258064516129e-05,
|
| 986 |
+
"loss": 0.2789,
|
| 987 |
+
"step": 1170
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 2.72,
|
| 991 |
+
"learning_rate": 6.417050691244239e-05,
|
| 992 |
+
"loss": 0.1855,
|
| 993 |
+
"step": 1180
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 2.74,
|
| 997 |
+
"learning_rate": 6.301843317972351e-05,
|
| 998 |
+
"loss": 0.1857,
|
| 999 |
+
"step": 1190
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.76,
|
| 1003 |
+
"learning_rate": 6.186635944700461e-05,
|
| 1004 |
+
"loss": 0.1796,
|
| 1005 |
+
"step": 1200
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.76,
|
| 1009 |
+
"eval_accuracy": 0.8337783711615487,
|
| 1010 |
+
"eval_f1": 0.8337783711615487,
|
| 1011 |
+
"eval_loss": 0.544723629951477,
|
| 1012 |
+
"eval_precision": 0.8337783711615487,
|
| 1013 |
+
"eval_recall": 0.8337783711615487,
|
| 1014 |
+
"eval_runtime": 23.9024,
|
| 1015 |
+
"eval_samples_per_second": 62.672,
|
| 1016 |
+
"eval_steps_per_second": 7.865,
|
| 1017 |
+
"step": 1200
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.79,
|
| 1021 |
+
"learning_rate": 6.0714285714285715e-05,
|
| 1022 |
+
"loss": 0.1997,
|
| 1023 |
+
"step": 1210
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.81,
|
| 1027 |
+
"learning_rate": 5.956221198156682e-05,
|
| 1028 |
+
"loss": 0.2206,
|
| 1029 |
+
"step": 1220
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.83,
|
| 1033 |
+
"learning_rate": 5.8410138248847935e-05,
|
| 1034 |
+
"loss": 0.1756,
|
| 1035 |
+
"step": 1230
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.86,
|
| 1039 |
+
"learning_rate": 5.725806451612904e-05,
|
| 1040 |
+
"loss": 0.232,
|
| 1041 |
+
"step": 1240
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.88,
|
| 1045 |
+
"learning_rate": 5.610599078341015e-05,
|
| 1046 |
+
"loss": 0.1882,
|
| 1047 |
+
"step": 1250
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.88,
|
| 1051 |
+
"eval_accuracy": 0.828437917222964,
|
| 1052 |
+
"eval_f1": 0.828437917222964,
|
| 1053 |
+
"eval_loss": 0.5357471704483032,
|
| 1054 |
+
"eval_precision": 0.828437917222964,
|
| 1055 |
+
"eval_recall": 0.828437917222964,
|
| 1056 |
+
"eval_runtime": 23.7377,
|
| 1057 |
+
"eval_samples_per_second": 63.106,
|
| 1058 |
+
"eval_steps_per_second": 7.92,
|
| 1059 |
+
"step": 1250
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.9,
|
| 1063 |
+
"learning_rate": 5.495391705069125e-05,
|
| 1064 |
+
"loss": 0.1958,
|
| 1065 |
+
"step": 1260
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.93,
|
| 1069 |
+
"learning_rate": 5.3801843317972355e-05,
|
| 1070 |
+
"loss": 0.1584,
|
| 1071 |
+
"step": 1270
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 2.95,
|
| 1075 |
+
"learning_rate": 5.264976958525346e-05,
|
| 1076 |
+
"loss": 0.1785,
|
| 1077 |
+
"step": 1280
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 2.97,
|
| 1081 |
+
"learning_rate": 5.149769585253457e-05,
|
| 1082 |
+
"loss": 0.144,
|
| 1083 |
+
"step": 1290
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 3.0,
|
| 1087 |
+
"learning_rate": 5.034562211981567e-05,
|
| 1088 |
+
"loss": 0.1596,
|
| 1089 |
+
"step": 1300
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 3.0,
|
| 1093 |
+
"eval_accuracy": 0.8344459279038718,
|
| 1094 |
+
"eval_f1": 0.834445927903872,
|
| 1095 |
+
"eval_loss": 0.5296002626419067,
|
| 1096 |
+
"eval_precision": 0.8344459279038718,
|
| 1097 |
+
"eval_recall": 0.8344459279038718,
|
| 1098 |
+
"eval_runtime": 23.9184,
|
| 1099 |
+
"eval_samples_per_second": 62.629,
|
| 1100 |
+
"eval_steps_per_second": 7.86,
|
| 1101 |
+
"step": 1300
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.02,
|
| 1105 |
+
"learning_rate": 4.9193548387096775e-05,
|
| 1106 |
+
"loss": 0.0465,
|
| 1107 |
+
"step": 1310
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 3.04,
|
| 1111 |
+
"learning_rate": 4.8041474654377885e-05,
|
| 1112 |
+
"loss": 0.1005,
|
| 1113 |
+
"step": 1320
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 3.06,
|
| 1117 |
+
"learning_rate": 4.688940092165899e-05,
|
| 1118 |
+
"loss": 0.133,
|
| 1119 |
+
"step": 1330
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 3.09,
|
| 1123 |
+
"learning_rate": 4.573732718894009e-05,
|
| 1124 |
+
"loss": 0.1057,
|
| 1125 |
+
"step": 1340
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 3.11,
|
| 1129 |
+
"learning_rate": 4.45852534562212e-05,
|
| 1130 |
+
"loss": 0.075,
|
| 1131 |
+
"step": 1350
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 3.11,
|
| 1135 |
+
"eval_accuracy": 0.8197596795727636,
|
| 1136 |
+
"eval_f1": 0.8197596795727636,
|
| 1137 |
+
"eval_loss": 0.5875993967056274,
|
| 1138 |
+
"eval_precision": 0.8197596795727636,
|
| 1139 |
+
"eval_recall": 0.8197596795727636,
|
| 1140 |
+
"eval_runtime": 24.1647,
|
| 1141 |
+
"eval_samples_per_second": 61.991,
|
| 1142 |
+
"eval_steps_per_second": 7.78,
|
| 1143 |
+
"step": 1350
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.13,
|
| 1147 |
+
"learning_rate": 4.3433179723502305e-05,
|
| 1148 |
+
"loss": 0.0836,
|
| 1149 |
+
"step": 1360
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 3.16,
|
| 1153 |
+
"learning_rate": 4.228110599078341e-05,
|
| 1154 |
+
"loss": 0.0834,
|
| 1155 |
+
"step": 1370
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 3.18,
|
| 1159 |
+
"learning_rate": 4.112903225806452e-05,
|
| 1160 |
+
"loss": 0.1301,
|
| 1161 |
+
"step": 1380
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 3.2,
|
| 1165 |
+
"learning_rate": 3.997695852534563e-05,
|
| 1166 |
+
"loss": 0.0711,
|
| 1167 |
+
"step": 1390
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 3.23,
|
| 1171 |
+
"learning_rate": 3.882488479262673e-05,
|
| 1172 |
+
"loss": 0.1128,
|
| 1173 |
+
"step": 1400
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 3.23,
|
| 1177 |
+
"eval_accuracy": 0.8337783711615487,
|
| 1178 |
+
"eval_f1": 0.8337783711615487,
|
| 1179 |
+
"eval_loss": 0.56122225522995,
|
| 1180 |
+
"eval_precision": 0.8337783711615487,
|
| 1181 |
+
"eval_recall": 0.8337783711615487,
|
| 1182 |
+
"eval_runtime": 24.1153,
|
| 1183 |
+
"eval_samples_per_second": 62.118,
|
| 1184 |
+
"eval_steps_per_second": 7.796,
|
| 1185 |
+
"step": 1400
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.25,
|
| 1189 |
+
"learning_rate": 3.7672811059907835e-05,
|
| 1190 |
+
"loss": 0.0848,
|
| 1191 |
+
"step": 1410
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 3.27,
|
| 1195 |
+
"learning_rate": 3.6520737327188945e-05,
|
| 1196 |
+
"loss": 0.0885,
|
| 1197 |
+
"step": 1420
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 3.29,
|
| 1201 |
+
"learning_rate": 3.536866359447005e-05,
|
| 1202 |
+
"loss": 0.0432,
|
| 1203 |
+
"step": 1430
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 3.32,
|
| 1207 |
+
"learning_rate": 3.421658986175115e-05,
|
| 1208 |
+
"loss": 0.0557,
|
| 1209 |
+
"step": 1440
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.34,
|
| 1213 |
+
"learning_rate": 3.306451612903226e-05,
|
| 1214 |
+
"loss": 0.0677,
|
| 1215 |
+
"step": 1450
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 3.34,
|
| 1219 |
+
"eval_accuracy": 0.8331108144192256,
|
| 1220 |
+
"eval_f1": 0.8331108144192256,
|
| 1221 |
+
"eval_loss": 0.5910764932632446,
|
| 1222 |
+
"eval_precision": 0.8331108144192256,
|
| 1223 |
+
"eval_recall": 0.8331108144192256,
|
| 1224 |
+
"eval_runtime": 22.9405,
|
| 1225 |
+
"eval_samples_per_second": 65.299,
|
| 1226 |
+
"eval_steps_per_second": 8.195,
|
| 1227 |
+
"step": 1450
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.36,
|
| 1231 |
+
"learning_rate": 3.1912442396313365e-05,
|
| 1232 |
+
"loss": 0.0931,
|
| 1233 |
+
"step": 1460
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 3.39,
|
| 1237 |
+
"learning_rate": 3.076036866359447e-05,
|
| 1238 |
+
"loss": 0.0276,
|
| 1239 |
+
"step": 1470
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 3.41,
|
| 1243 |
+
"learning_rate": 2.960829493087558e-05,
|
| 1244 |
+
"loss": 0.0311,
|
| 1245 |
+
"step": 1480
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 3.43,
|
| 1249 |
+
"learning_rate": 2.8456221198156685e-05,
|
| 1250 |
+
"loss": 0.0513,
|
| 1251 |
+
"step": 1490
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 3.46,
|
| 1255 |
+
"learning_rate": 2.730414746543779e-05,
|
| 1256 |
+
"loss": 0.0794,
|
| 1257 |
+
"step": 1500
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 3.46,
|
| 1261 |
+
"eval_accuracy": 0.8304405874499332,
|
| 1262 |
+
"eval_f1": 0.8304405874499331,
|
| 1263 |
+
"eval_loss": 0.5970631837844849,
|
| 1264 |
+
"eval_precision": 0.8304405874499332,
|
| 1265 |
+
"eval_recall": 0.8304405874499332,
|
| 1266 |
+
"eval_runtime": 24.072,
|
| 1267 |
+
"eval_samples_per_second": 62.23,
|
| 1268 |
+
"eval_steps_per_second": 7.81,
|
| 1269 |
+
"step": 1500
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.48,
|
| 1273 |
+
"learning_rate": 2.6152073732718895e-05,
|
| 1274 |
+
"loss": 0.0655,
|
| 1275 |
+
"step": 1510
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 3.5,
|
| 1279 |
+
"learning_rate": 2.5e-05,
|
| 1280 |
+
"loss": 0.0626,
|
| 1281 |
+
"step": 1520
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 3.53,
|
| 1285 |
+
"learning_rate": 2.3847926267281108e-05,
|
| 1286 |
+
"loss": 0.0936,
|
| 1287 |
+
"step": 1530
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 3.55,
|
| 1291 |
+
"learning_rate": 2.269585253456221e-05,
|
| 1292 |
+
"loss": 0.0507,
|
| 1293 |
+
"step": 1540
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 3.57,
|
| 1297 |
+
"learning_rate": 2.154377880184332e-05,
|
| 1298 |
+
"loss": 0.0367,
|
| 1299 |
+
"step": 1550
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 3.57,
|
| 1303 |
+
"eval_accuracy": 0.8377837116154874,
|
| 1304 |
+
"eval_f1": 0.8377837116154874,
|
| 1305 |
+
"eval_loss": 0.5634308457374573,
|
| 1306 |
+
"eval_precision": 0.8377837116154874,
|
| 1307 |
+
"eval_recall": 0.8377837116154874,
|
| 1308 |
+
"eval_runtime": 24.4701,
|
| 1309 |
+
"eval_samples_per_second": 61.218,
|
| 1310 |
+
"eval_steps_per_second": 7.683,
|
| 1311 |
+
"step": 1550
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.59,
|
| 1315 |
+
"learning_rate": 2.0391705069124424e-05,
|
| 1316 |
+
"loss": 0.1449,
|
| 1317 |
+
"step": 1560
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 3.62,
|
| 1321 |
+
"learning_rate": 1.923963133640553e-05,
|
| 1322 |
+
"loss": 0.0286,
|
| 1323 |
+
"step": 1570
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 3.64,
|
| 1327 |
+
"learning_rate": 1.8087557603686638e-05,
|
| 1328 |
+
"loss": 0.0877,
|
| 1329 |
+
"step": 1580
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.66,
|
| 1333 |
+
"learning_rate": 1.693548387096774e-05,
|
| 1334 |
+
"loss": 0.0332,
|
| 1335 |
+
"step": 1590
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 3.69,
|
| 1339 |
+
"learning_rate": 1.578341013824885e-05,
|
| 1340 |
+
"loss": 0.0279,
|
| 1341 |
+
"step": 1600
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 3.69,
|
| 1345 |
+
"eval_accuracy": 0.8391188251001335,
|
| 1346 |
+
"eval_f1": 0.8391188251001335,
|
| 1347 |
+
"eval_loss": 0.5674164891242981,
|
| 1348 |
+
"eval_precision": 0.8391188251001335,
|
| 1349 |
+
"eval_recall": 0.8391188251001335,
|
| 1350 |
+
"eval_runtime": 23.0964,
|
| 1351 |
+
"eval_samples_per_second": 64.859,
|
| 1352 |
+
"eval_steps_per_second": 8.14,
|
| 1353 |
+
"step": 1600
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 3.71,
|
| 1357 |
+
"learning_rate": 1.4631336405529954e-05,
|
| 1358 |
+
"loss": 0.0474,
|
| 1359 |
+
"step": 1610
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 3.73,
|
| 1363 |
+
"learning_rate": 1.3479262672811061e-05,
|
| 1364 |
+
"loss": 0.0546,
|
| 1365 |
+
"step": 1620
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 3.76,
|
| 1369 |
+
"learning_rate": 1.2327188940092166e-05,
|
| 1370 |
+
"loss": 0.1128,
|
| 1371 |
+
"step": 1630
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 3.78,
|
| 1375 |
+
"learning_rate": 1.1175115207373273e-05,
|
| 1376 |
+
"loss": 0.0242,
|
| 1377 |
+
"step": 1640
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 3.8,
|
| 1381 |
+
"learning_rate": 1.0023041474654378e-05,
|
| 1382 |
+
"loss": 0.0216,
|
| 1383 |
+
"step": 1650
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 3.8,
|
| 1387 |
+
"eval_accuracy": 0.835781041388518,
|
| 1388 |
+
"eval_f1": 0.835781041388518,
|
| 1389 |
+
"eval_loss": 0.5776631236076355,
|
| 1390 |
+
"eval_precision": 0.835781041388518,
|
| 1391 |
+
"eval_recall": 0.835781041388518,
|
| 1392 |
+
"eval_runtime": 23.9672,
|
| 1393 |
+
"eval_samples_per_second": 62.502,
|
| 1394 |
+
"eval_steps_per_second": 7.844,
|
| 1395 |
+
"step": 1650
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.82,
|
| 1399 |
+
"learning_rate": 8.870967741935484e-06,
|
| 1400 |
+
"loss": 0.0495,
|
| 1401 |
+
"step": 1660
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 3.85,
|
| 1405 |
+
"learning_rate": 7.71889400921659e-06,
|
| 1406 |
+
"loss": 0.0738,
|
| 1407 |
+
"step": 1670
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 3.87,
|
| 1411 |
+
"learning_rate": 6.566820276497695e-06,
|
| 1412 |
+
"loss": 0.0212,
|
| 1413 |
+
"step": 1680
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 3.89,
|
| 1417 |
+
"learning_rate": 5.414746543778802e-06,
|
| 1418 |
+
"loss": 0.0874,
|
| 1419 |
+
"step": 1690
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 3.92,
|
| 1423 |
+
"learning_rate": 4.2626728110599085e-06,
|
| 1424 |
+
"loss": 0.0161,
|
| 1425 |
+
"step": 1700
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 3.92,
|
| 1429 |
+
"eval_accuracy": 0.8437917222963952,
|
| 1430 |
+
"eval_f1": 0.8437917222963952,
|
| 1431 |
+
"eval_loss": 0.5607731342315674,
|
| 1432 |
+
"eval_precision": 0.8437917222963952,
|
| 1433 |
+
"eval_recall": 0.8437917222963952,
|
| 1434 |
+
"eval_runtime": 22.8075,
|
| 1435 |
+
"eval_samples_per_second": 65.68,
|
| 1436 |
+
"eval_steps_per_second": 8.243,
|
| 1437 |
+
"step": 1700
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 3.94,
|
| 1441 |
+
"learning_rate": 3.110599078341014e-06,
|
| 1442 |
+
"loss": 0.018,
|
| 1443 |
+
"step": 1710
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 3.96,
|
| 1447 |
+
"learning_rate": 1.9585253456221198e-06,
|
| 1448 |
+
"loss": 0.0698,
|
| 1449 |
+
"step": 1720
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 3.99,
|
| 1453 |
+
"learning_rate": 8.064516129032258e-07,
|
| 1454 |
+
"loss": 0.0687,
|
| 1455 |
+
"step": 1730
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 4.0,
|
| 1459 |
+
"step": 1736,
|
| 1460 |
+
"total_flos": 2.1525139607212524e+18,
|
| 1461 |
+
"train_loss": 0.438499038875927,
|
| 1462 |
+
"train_runtime": 1854.8343,
|
| 1463 |
+
"train_samples_per_second": 14.975,
|
| 1464 |
+
"train_steps_per_second": 0.936
|
| 1465 |
+
}
|
| 1466 |
+
],
|
| 1467 |
+
"logging_steps": 10,
|
| 1468 |
+
"max_steps": 1736,
|
| 1469 |
+
"num_train_epochs": 4,
|
| 1470 |
+
"save_steps": 50,
|
| 1471 |
+
"total_flos": 2.1525139607212524e+18,
|
| 1472 |
+
"trial_name": null,
|
| 1473 |
+
"trial_params": null
|
| 1474 |
+
}
|