End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Dec03_21-55-45_DESKTOP-SKBE9FB/events.out.tfevents.1733286092.DESKTOP-SKBE9FB.22524.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +918 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss:
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.6355140186915887
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.7194
|
| 36 |
+
- Accuracy: 0.6355
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 39.11,
|
| 3 |
+
"eval_accuracy": 0.6355140186915887,
|
| 4 |
+
"eval_loss": 1.7194138765335083,
|
| 5 |
+
"eval_runtime": 2.9024,
|
| 6 |
+
"eval_samples_per_second": 36.866,
|
| 7 |
+
"eval_steps_per_second": 2.412,
|
| 8 |
+
"train_loss": 0.09111572096166624,
|
| 9 |
+
"train_runtime": 1452.6155,
|
| 10 |
+
"train_samples_per_second": 39.542,
|
| 11 |
+
"train_steps_per_second": 0.606
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 39.11,
|
| 3 |
+
"eval_accuracy": 0.6355140186915887,
|
| 4 |
+
"eval_loss": 1.7194138765335083,
|
| 5 |
+
"eval_runtime": 2.9024,
|
| 6 |
+
"eval_samples_per_second": 36.866,
|
| 7 |
+
"eval_steps_per_second": 2.412
|
| 8 |
+
}
|
runs/Dec03_21-55-45_DESKTOP-SKBE9FB/events.out.tfevents.1733286092.DESKTOP-SKBE9FB.22524.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f9c17ed836bb7ae1064a606840b905148fdfe09833e51e69429ed63e28b5d41
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 39.11,
|
| 3 |
+
"train_loss": 0.09111572096166624,
|
| 4 |
+
"train_runtime": 1452.6155,
|
| 5 |
+
"train_samples_per_second": 39.542,
|
| 6 |
+
"train_steps_per_second": 0.606
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,918 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6355140186915887,
|
| 3 |
+
"best_model_checkpoint": "BEiT-RHS-DA\\checkpoint-360",
|
| 4 |
+
"epoch": 39.111111111111114,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 880,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.44,
|
| 13 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 14 |
+
"loss": 1.3359,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.89,
|
| 19 |
+
"learning_rate": 2.272727272727273e-05,
|
| 20 |
+
"loss": 1.2357,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.98,
|
| 25 |
+
"eval_accuracy": 0.5887850467289719,
|
| 26 |
+
"eval_loss": 0.7114280462265015,
|
| 27 |
+
"eval_runtime": 2.6053,
|
| 28 |
+
"eval_samples_per_second": 41.07,
|
| 29 |
+
"eval_steps_per_second": 2.687,
|
| 30 |
+
"step": 22
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.33,
|
| 34 |
+
"learning_rate": 3.409090909090909e-05,
|
| 35 |
+
"loss": 0.9874,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.78,
|
| 40 |
+
"learning_rate": 4.545454545454546e-05,
|
| 41 |
+
"loss": 0.6596,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.0,
|
| 46 |
+
"eval_accuracy": 0.5981308411214953,
|
| 47 |
+
"eval_loss": 0.7058635950088501,
|
| 48 |
+
"eval_runtime": 2.8903,
|
| 49 |
+
"eval_samples_per_second": 37.02,
|
| 50 |
+
"eval_steps_per_second": 2.422,
|
| 51 |
+
"step": 45
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.22,
|
| 55 |
+
"learning_rate": 4.964114832535885e-05,
|
| 56 |
+
"loss": 0.3724,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.67,
|
| 61 |
+
"learning_rate": 4.904306220095694e-05,
|
| 62 |
+
"loss": 0.206,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.98,
|
| 67 |
+
"eval_accuracy": 0.5981308411214953,
|
| 68 |
+
"eval_loss": 1.14487624168396,
|
| 69 |
+
"eval_runtime": 2.567,
|
| 70 |
+
"eval_samples_per_second": 41.682,
|
| 71 |
+
"eval_steps_per_second": 2.727,
|
| 72 |
+
"step": 67
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 3.11,
|
| 76 |
+
"learning_rate": 4.844497607655503e-05,
|
| 77 |
+
"loss": 0.1872,
|
| 78 |
+
"step": 70
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.56,
|
| 82 |
+
"learning_rate": 4.784688995215311e-05,
|
| 83 |
+
"loss": 0.1164,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.0,
|
| 88 |
+
"learning_rate": 4.72488038277512e-05,
|
| 89 |
+
"loss": 0.1664,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.0,
|
| 94 |
+
"eval_accuracy": 0.3925233644859813,
|
| 95 |
+
"eval_loss": 2.2061808109283447,
|
| 96 |
+
"eval_runtime": 2.5208,
|
| 97 |
+
"eval_samples_per_second": 42.448,
|
| 98 |
+
"eval_steps_per_second": 2.777,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.44,
|
| 103 |
+
"learning_rate": 4.665071770334928e-05,
|
| 104 |
+
"loss": 0.1706,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.89,
|
| 109 |
+
"learning_rate": 4.605263157894737e-05,
|
| 110 |
+
"loss": 0.1011,
|
| 111 |
+
"step": 110
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.98,
|
| 115 |
+
"eval_accuracy": 0.4672897196261682,
|
| 116 |
+
"eval_loss": 2.040870189666748,
|
| 117 |
+
"eval_runtime": 2.5598,
|
| 118 |
+
"eval_samples_per_second": 41.8,
|
| 119 |
+
"eval_steps_per_second": 2.735,
|
| 120 |
+
"step": 112
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.33,
|
| 124 |
+
"learning_rate": 4.545454545454546e-05,
|
| 125 |
+
"loss": 0.2439,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.78,
|
| 130 |
+
"learning_rate": 4.485645933014354e-05,
|
| 131 |
+
"loss": 0.0653,
|
| 132 |
+
"step": 130
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 6.0,
|
| 136 |
+
"eval_accuracy": 0.6261682242990654,
|
| 137 |
+
"eval_loss": 1.3038437366485596,
|
| 138 |
+
"eval_runtime": 2.6986,
|
| 139 |
+
"eval_samples_per_second": 39.65,
|
| 140 |
+
"eval_steps_per_second": 2.594,
|
| 141 |
+
"step": 135
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.22,
|
| 145 |
+
"learning_rate": 4.425837320574163e-05,
|
| 146 |
+
"loss": 0.2341,
|
| 147 |
+
"step": 140
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.67,
|
| 151 |
+
"learning_rate": 4.366028708133971e-05,
|
| 152 |
+
"loss": 0.2843,
|
| 153 |
+
"step": 150
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 6.98,
|
| 157 |
+
"eval_accuracy": 0.5981308411214953,
|
| 158 |
+
"eval_loss": 1.7210038900375366,
|
| 159 |
+
"eval_runtime": 2.6158,
|
| 160 |
+
"eval_samples_per_second": 40.905,
|
| 161 |
+
"eval_steps_per_second": 2.676,
|
| 162 |
+
"step": 157
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 7.11,
|
| 166 |
+
"learning_rate": 4.3062200956937806e-05,
|
| 167 |
+
"loss": 0.0424,
|
| 168 |
+
"step": 160
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 7.56,
|
| 172 |
+
"learning_rate": 4.246411483253589e-05,
|
| 173 |
+
"loss": 0.0082,
|
| 174 |
+
"step": 170
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 8.0,
|
| 178 |
+
"learning_rate": 4.1866028708133976e-05,
|
| 179 |
+
"loss": 0.059,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 8.0,
|
| 184 |
+
"eval_accuracy": 0.4672897196261682,
|
| 185 |
+
"eval_loss": 2.870556116104126,
|
| 186 |
+
"eval_runtime": 2.8378,
|
| 187 |
+
"eval_samples_per_second": 37.705,
|
| 188 |
+
"eval_steps_per_second": 2.467,
|
| 189 |
+
"step": 180
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.44,
|
| 193 |
+
"learning_rate": 4.1267942583732064e-05,
|
| 194 |
+
"loss": 0.1224,
|
| 195 |
+
"step": 190
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 8.89,
|
| 199 |
+
"learning_rate": 4.0669856459330146e-05,
|
| 200 |
+
"loss": 0.1318,
|
| 201 |
+
"step": 200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 8.98,
|
| 205 |
+
"eval_accuracy": 0.5887850467289719,
|
| 206 |
+
"eval_loss": 2.451904058456421,
|
| 207 |
+
"eval_runtime": 2.6549,
|
| 208 |
+
"eval_samples_per_second": 40.303,
|
| 209 |
+
"eval_steps_per_second": 2.637,
|
| 210 |
+
"step": 202
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 9.33,
|
| 214 |
+
"learning_rate": 4.0071770334928235e-05,
|
| 215 |
+
"loss": 0.0267,
|
| 216 |
+
"step": 210
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 9.78,
|
| 220 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 221 |
+
"loss": 0.0501,
|
| 222 |
+
"step": 220
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 10.0,
|
| 226 |
+
"eval_accuracy": 0.5887850467289719,
|
| 227 |
+
"eval_loss": 2.2037127017974854,
|
| 228 |
+
"eval_runtime": 2.6808,
|
| 229 |
+
"eval_samples_per_second": 39.913,
|
| 230 |
+
"eval_steps_per_second": 2.611,
|
| 231 |
+
"step": 225
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 10.22,
|
| 235 |
+
"learning_rate": 3.8875598086124405e-05,
|
| 236 |
+
"loss": 0.0481,
|
| 237 |
+
"step": 230
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 10.67,
|
| 241 |
+
"learning_rate": 3.8277511961722486e-05,
|
| 242 |
+
"loss": 0.054,
|
| 243 |
+
"step": 240
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 10.98,
|
| 247 |
+
"eval_accuracy": 0.5887850467289719,
|
| 248 |
+
"eval_loss": 2.646747589111328,
|
| 249 |
+
"eval_runtime": 2.8537,
|
| 250 |
+
"eval_samples_per_second": 37.495,
|
| 251 |
+
"eval_steps_per_second": 2.453,
|
| 252 |
+
"step": 247
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 11.11,
|
| 256 |
+
"learning_rate": 3.7679425837320575e-05,
|
| 257 |
+
"loss": 0.0495,
|
| 258 |
+
"step": 250
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 11.56,
|
| 262 |
+
"learning_rate": 3.7081339712918663e-05,
|
| 263 |
+
"loss": 0.0367,
|
| 264 |
+
"step": 260
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 12.0,
|
| 268 |
+
"learning_rate": 3.6483253588516745e-05,
|
| 269 |
+
"loss": 0.0263,
|
| 270 |
+
"step": 270
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 12.0,
|
| 274 |
+
"eval_accuracy": 0.5981308411214953,
|
| 275 |
+
"eval_loss": 2.4033188819885254,
|
| 276 |
+
"eval_runtime": 2.6437,
|
| 277 |
+
"eval_samples_per_second": 40.474,
|
| 278 |
+
"eval_steps_per_second": 2.648,
|
| 279 |
+
"step": 270
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 12.44,
|
| 283 |
+
"learning_rate": 3.5885167464114834e-05,
|
| 284 |
+
"loss": 0.0138,
|
| 285 |
+
"step": 280
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 12.89,
|
| 289 |
+
"learning_rate": 3.5287081339712915e-05,
|
| 290 |
+
"loss": 0.0553,
|
| 291 |
+
"step": 290
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 12.98,
|
| 295 |
+
"eval_accuracy": 0.5887850467289719,
|
| 296 |
+
"eval_loss": 1.6589338779449463,
|
| 297 |
+
"eval_runtime": 2.6219,
|
| 298 |
+
"eval_samples_per_second": 40.811,
|
| 299 |
+
"eval_steps_per_second": 2.67,
|
| 300 |
+
"step": 292
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 13.33,
|
| 304 |
+
"learning_rate": 3.4688995215311004e-05,
|
| 305 |
+
"loss": 0.0092,
|
| 306 |
+
"step": 300
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 13.78,
|
| 310 |
+
"learning_rate": 3.409090909090909e-05,
|
| 311 |
+
"loss": 0.0898,
|
| 312 |
+
"step": 310
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 14.0,
|
| 316 |
+
"eval_accuracy": 0.5981308411214953,
|
| 317 |
+
"eval_loss": 1.7657066583633423,
|
| 318 |
+
"eval_runtime": 2.6872,
|
| 319 |
+
"eval_samples_per_second": 39.819,
|
| 320 |
+
"eval_steps_per_second": 2.605,
|
| 321 |
+
"step": 315
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 14.22,
|
| 325 |
+
"learning_rate": 3.349282296650718e-05,
|
| 326 |
+
"loss": 0.0304,
|
| 327 |
+
"step": 320
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 14.67,
|
| 331 |
+
"learning_rate": 3.289473684210527e-05,
|
| 332 |
+
"loss": 0.0324,
|
| 333 |
+
"step": 330
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 14.98,
|
| 337 |
+
"eval_accuracy": 0.5887850467289719,
|
| 338 |
+
"eval_loss": 2.8265936374664307,
|
| 339 |
+
"eval_runtime": 2.6021,
|
| 340 |
+
"eval_samples_per_second": 41.121,
|
| 341 |
+
"eval_steps_per_second": 2.69,
|
| 342 |
+
"step": 337
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 15.11,
|
| 346 |
+
"learning_rate": 3.229665071770335e-05,
|
| 347 |
+
"loss": 0.0424,
|
| 348 |
+
"step": 340
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 15.56,
|
| 352 |
+
"learning_rate": 3.169856459330144e-05,
|
| 353 |
+
"loss": 0.0556,
|
| 354 |
+
"step": 350
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 16.0,
|
| 358 |
+
"learning_rate": 3.110047846889952e-05,
|
| 359 |
+
"loss": 0.0322,
|
| 360 |
+
"step": 360
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 16.0,
|
| 364 |
+
"eval_accuracy": 0.6355140186915887,
|
| 365 |
+
"eval_loss": 1.7194138765335083,
|
| 366 |
+
"eval_runtime": 2.6447,
|
| 367 |
+
"eval_samples_per_second": 40.458,
|
| 368 |
+
"eval_steps_per_second": 2.647,
|
| 369 |
+
"step": 360
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 16.44,
|
| 373 |
+
"learning_rate": 3.050239234449761e-05,
|
| 374 |
+
"loss": 0.0236,
|
| 375 |
+
"step": 370
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 16.89,
|
| 379 |
+
"learning_rate": 2.9904306220095695e-05,
|
| 380 |
+
"loss": 0.03,
|
| 381 |
+
"step": 380
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 16.98,
|
| 385 |
+
"eval_accuracy": 0.616822429906542,
|
| 386 |
+
"eval_loss": 2.035153865814209,
|
| 387 |
+
"eval_runtime": 2.6411,
|
| 388 |
+
"eval_samples_per_second": 40.513,
|
| 389 |
+
"eval_steps_per_second": 2.65,
|
| 390 |
+
"step": 382
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 17.33,
|
| 394 |
+
"learning_rate": 2.9306220095693783e-05,
|
| 395 |
+
"loss": 0.0244,
|
| 396 |
+
"step": 390
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 17.78,
|
| 400 |
+
"learning_rate": 2.8708133971291868e-05,
|
| 401 |
+
"loss": 0.0392,
|
| 402 |
+
"step": 400
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.0,
|
| 406 |
+
"eval_accuracy": 0.616822429906542,
|
| 407 |
+
"eval_loss": 2.412965774536133,
|
| 408 |
+
"eval_runtime": 2.7163,
|
| 409 |
+
"eval_samples_per_second": 39.392,
|
| 410 |
+
"eval_steps_per_second": 2.577,
|
| 411 |
+
"step": 405
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 18.22,
|
| 415 |
+
"learning_rate": 2.8110047846889953e-05,
|
| 416 |
+
"loss": 0.0096,
|
| 417 |
+
"step": 410
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 18.67,
|
| 421 |
+
"learning_rate": 2.751196172248804e-05,
|
| 422 |
+
"loss": 0.0428,
|
| 423 |
+
"step": 420
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 18.98,
|
| 427 |
+
"eval_accuracy": 0.6074766355140186,
|
| 428 |
+
"eval_loss": 2.0628373622894287,
|
| 429 |
+
"eval_runtime": 2.5916,
|
| 430 |
+
"eval_samples_per_second": 41.288,
|
| 431 |
+
"eval_steps_per_second": 2.701,
|
| 432 |
+
"step": 427
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 19.11,
|
| 436 |
+
"learning_rate": 2.6913875598086123e-05,
|
| 437 |
+
"loss": 0.0189,
|
| 438 |
+
"step": 430
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 19.56,
|
| 442 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 443 |
+
"loss": 0.0119,
|
| 444 |
+
"step": 440
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 20.0,
|
| 448 |
+
"learning_rate": 2.5717703349282297e-05,
|
| 449 |
+
"loss": 0.0127,
|
| 450 |
+
"step": 450
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 20.0,
|
| 454 |
+
"eval_accuracy": 0.5887850467289719,
|
| 455 |
+
"eval_loss": 2.743129253387451,
|
| 456 |
+
"eval_runtime": 2.5383,
|
| 457 |
+
"eval_samples_per_second": 42.154,
|
| 458 |
+
"eval_steps_per_second": 2.758,
|
| 459 |
+
"step": 450
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 20.44,
|
| 463 |
+
"learning_rate": 2.5119617224880382e-05,
|
| 464 |
+
"loss": 0.0164,
|
| 465 |
+
"step": 460
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 20.89,
|
| 469 |
+
"learning_rate": 2.452153110047847e-05,
|
| 470 |
+
"loss": 0.0187,
|
| 471 |
+
"step": 470
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 20.98,
|
| 475 |
+
"eval_accuracy": 0.5981308411214953,
|
| 476 |
+
"eval_loss": 2.700892686843872,
|
| 477 |
+
"eval_runtime": 2.592,
|
| 478 |
+
"eval_samples_per_second": 41.281,
|
| 479 |
+
"eval_steps_per_second": 2.701,
|
| 480 |
+
"step": 472
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 21.33,
|
| 484 |
+
"learning_rate": 2.3923444976076556e-05,
|
| 485 |
+
"loss": 0.0349,
|
| 486 |
+
"step": 480
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 21.78,
|
| 490 |
+
"learning_rate": 2.332535885167464e-05,
|
| 491 |
+
"loss": 0.0469,
|
| 492 |
+
"step": 490
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 22.0,
|
| 496 |
+
"eval_accuracy": 0.5981308411214953,
|
| 497 |
+
"eval_loss": 2.578273057937622,
|
| 498 |
+
"eval_runtime": 2.6372,
|
| 499 |
+
"eval_samples_per_second": 40.573,
|
| 500 |
+
"eval_steps_per_second": 2.654,
|
| 501 |
+
"step": 495
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 22.22,
|
| 505 |
+
"learning_rate": 2.272727272727273e-05,
|
| 506 |
+
"loss": 0.0196,
|
| 507 |
+
"step": 500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 22.67,
|
| 511 |
+
"learning_rate": 2.2129186602870814e-05,
|
| 512 |
+
"loss": 0.0095,
|
| 513 |
+
"step": 510
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 22.98,
|
| 517 |
+
"eval_accuracy": 0.5981308411214953,
|
| 518 |
+
"eval_loss": 2.304006338119507,
|
| 519 |
+
"eval_runtime": 2.5827,
|
| 520 |
+
"eval_samples_per_second": 41.429,
|
| 521 |
+
"eval_steps_per_second": 2.71,
|
| 522 |
+
"step": 517
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 23.11,
|
| 526 |
+
"learning_rate": 2.1531100478468903e-05,
|
| 527 |
+
"loss": 0.0428,
|
| 528 |
+
"step": 520
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 23.56,
|
| 532 |
+
"learning_rate": 2.0933014354066988e-05,
|
| 533 |
+
"loss": 0.0007,
|
| 534 |
+
"step": 530
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 24.0,
|
| 538 |
+
"learning_rate": 2.0334928229665073e-05,
|
| 539 |
+
"loss": 0.0025,
|
| 540 |
+
"step": 540
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 24.0,
|
| 544 |
+
"eval_accuracy": 0.616822429906542,
|
| 545 |
+
"eval_loss": 2.521818161010742,
|
| 546 |
+
"eval_runtime": 2.612,
|
| 547 |
+
"eval_samples_per_second": 40.964,
|
| 548 |
+
"eval_steps_per_second": 2.68,
|
| 549 |
+
"step": 540
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 24.44,
|
| 553 |
+
"learning_rate": 1.9736842105263158e-05,
|
| 554 |
+
"loss": 0.0005,
|
| 555 |
+
"step": 550
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 24.89,
|
| 559 |
+
"learning_rate": 1.9138755980861243e-05,
|
| 560 |
+
"loss": 0.0281,
|
| 561 |
+
"step": 560
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 24.98,
|
| 565 |
+
"eval_accuracy": 0.5981308411214953,
|
| 566 |
+
"eval_loss": 3.231044292449951,
|
| 567 |
+
"eval_runtime": 2.5813,
|
| 568 |
+
"eval_samples_per_second": 41.451,
|
| 569 |
+
"eval_steps_per_second": 2.712,
|
| 570 |
+
"step": 562
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 25.33,
|
| 574 |
+
"learning_rate": 1.8540669856459332e-05,
|
| 575 |
+
"loss": 0.0084,
|
| 576 |
+
"step": 570
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 25.78,
|
| 580 |
+
"learning_rate": 1.7942583732057417e-05,
|
| 581 |
+
"loss": 0.0004,
|
| 582 |
+
"step": 580
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 26.0,
|
| 586 |
+
"eval_accuracy": 0.5981308411214953,
|
| 587 |
+
"eval_loss": 3.273077964782715,
|
| 588 |
+
"eval_runtime": 2.6145,
|
| 589 |
+
"eval_samples_per_second": 40.925,
|
| 590 |
+
"eval_steps_per_second": 2.677,
|
| 591 |
+
"step": 585
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 26.22,
|
| 595 |
+
"learning_rate": 1.7344497607655502e-05,
|
| 596 |
+
"loss": 0.001,
|
| 597 |
+
"step": 590
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 26.67,
|
| 601 |
+
"learning_rate": 1.674641148325359e-05,
|
| 602 |
+
"loss": 0.0109,
|
| 603 |
+
"step": 600
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 26.98,
|
| 607 |
+
"eval_accuracy": 0.6261682242990654,
|
| 608 |
+
"eval_loss": 2.480931282043457,
|
| 609 |
+
"eval_runtime": 2.6486,
|
| 610 |
+
"eval_samples_per_second": 40.399,
|
| 611 |
+
"eval_steps_per_second": 2.643,
|
| 612 |
+
"step": 607
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 27.11,
|
| 616 |
+
"learning_rate": 1.6148325358851675e-05,
|
| 617 |
+
"loss": 0.0158,
|
| 618 |
+
"step": 610
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 27.56,
|
| 622 |
+
"learning_rate": 1.555023923444976e-05,
|
| 623 |
+
"loss": 0.0375,
|
| 624 |
+
"step": 620
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 28.0,
|
| 628 |
+
"learning_rate": 1.4952153110047847e-05,
|
| 629 |
+
"loss": 0.0191,
|
| 630 |
+
"step": 630
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 28.0,
|
| 634 |
+
"eval_accuracy": 0.5887850467289719,
|
| 635 |
+
"eval_loss": 2.782459259033203,
|
| 636 |
+
"eval_runtime": 2.7194,
|
| 637 |
+
"eval_samples_per_second": 39.347,
|
| 638 |
+
"eval_steps_per_second": 2.574,
|
| 639 |
+
"step": 630
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 28.44,
|
| 643 |
+
"learning_rate": 1.4354066985645934e-05,
|
| 644 |
+
"loss": 0.0057,
|
| 645 |
+
"step": 640
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 28.89,
|
| 649 |
+
"learning_rate": 1.375598086124402e-05,
|
| 650 |
+
"loss": 0.0005,
|
| 651 |
+
"step": 650
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 28.98,
|
| 655 |
+
"eval_accuracy": 0.5887850467289719,
|
| 656 |
+
"eval_loss": 3.528034210205078,
|
| 657 |
+
"eval_runtime": 2.584,
|
| 658 |
+
"eval_samples_per_second": 41.408,
|
| 659 |
+
"eval_steps_per_second": 2.709,
|
| 660 |
+
"step": 652
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 29.33,
|
| 664 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 665 |
+
"loss": 0.0136,
|
| 666 |
+
"step": 660
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 29.78,
|
| 670 |
+
"learning_rate": 1.2559808612440191e-05,
|
| 671 |
+
"loss": 0.0093,
|
| 672 |
+
"step": 670
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 30.0,
|
| 676 |
+
"eval_accuracy": 0.6074766355140186,
|
| 677 |
+
"eval_loss": 2.828961133956909,
|
| 678 |
+
"eval_runtime": 2.5935,
|
| 679 |
+
"eval_samples_per_second": 41.257,
|
| 680 |
+
"eval_steps_per_second": 2.699,
|
| 681 |
+
"step": 675
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 30.22,
|
| 685 |
+
"learning_rate": 1.1961722488038278e-05,
|
| 686 |
+
"loss": 0.0004,
|
| 687 |
+
"step": 680
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 30.67,
|
| 691 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 692 |
+
"loss": 0.0224,
|
| 693 |
+
"step": 690
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 30.98,
|
| 697 |
+
"eval_accuracy": 0.5794392523364486,
|
| 698 |
+
"eval_loss": 2.9545552730560303,
|
| 699 |
+
"eval_runtime": 2.7643,
|
| 700 |
+
"eval_samples_per_second": 38.707,
|
| 701 |
+
"eval_steps_per_second": 2.532,
|
| 702 |
+
"step": 697
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 31.11,
|
| 706 |
+
"learning_rate": 1.0765550239234451e-05,
|
| 707 |
+
"loss": 0.0325,
|
| 708 |
+
"step": 700
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 31.56,
|
| 712 |
+
"learning_rate": 1.0167464114832537e-05,
|
| 713 |
+
"loss": 0.0102,
|
| 714 |
+
"step": 710
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 32.0,
|
| 718 |
+
"learning_rate": 9.569377990430622e-06,
|
| 719 |
+
"loss": 0.0011,
|
| 720 |
+
"step": 720
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 32.0,
|
| 724 |
+
"eval_accuracy": 0.6074766355140186,
|
| 725 |
+
"eval_loss": 3.0147745609283447,
|
| 726 |
+
"eval_runtime": 2.6,
|
| 727 |
+
"eval_samples_per_second": 41.155,
|
| 728 |
+
"eval_steps_per_second": 2.692,
|
| 729 |
+
"step": 720
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 32.44,
|
| 733 |
+
"learning_rate": 8.971291866028708e-06,
|
| 734 |
+
"loss": 0.0014,
|
| 735 |
+
"step": 730
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 32.89,
|
| 739 |
+
"learning_rate": 8.373205741626795e-06,
|
| 740 |
+
"loss": 0.003,
|
| 741 |
+
"step": 740
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 32.98,
|
| 745 |
+
"eval_accuracy": 0.5981308411214953,
|
| 746 |
+
"eval_loss": 3.2915587425231934,
|
| 747 |
+
"eval_runtime": 2.5651,
|
| 748 |
+
"eval_samples_per_second": 41.714,
|
| 749 |
+
"eval_steps_per_second": 2.729,
|
| 750 |
+
"step": 742
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 33.33,
|
| 754 |
+
"learning_rate": 7.77511961722488e-06,
|
| 755 |
+
"loss": 0.0005,
|
| 756 |
+
"step": 750
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 33.78,
|
| 760 |
+
"learning_rate": 7.177033492822967e-06,
|
| 761 |
+
"loss": 0.0003,
|
| 762 |
+
"step": 760
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 34.0,
|
| 766 |
+
"eval_accuracy": 0.5981308411214953,
|
| 767 |
+
"eval_loss": 3.292980909347534,
|
| 768 |
+
"eval_runtime": 2.5274,
|
| 769 |
+
"eval_samples_per_second": 42.337,
|
| 770 |
+
"eval_steps_per_second": 2.77,
|
| 771 |
+
"step": 765
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 34.22,
|
| 775 |
+
"learning_rate": 6.578947368421053e-06,
|
| 776 |
+
"loss": 0.0003,
|
| 777 |
+
"step": 770
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 34.67,
|
| 781 |
+
"learning_rate": 5.980861244019139e-06,
|
| 782 |
+
"loss": 0.0003,
|
| 783 |
+
"step": 780
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 34.98,
|
| 787 |
+
"eval_accuracy": 0.5887850467289719,
|
| 788 |
+
"eval_loss": 3.628692626953125,
|
| 789 |
+
"eval_runtime": 2.6394,
|
| 790 |
+
"eval_samples_per_second": 40.539,
|
| 791 |
+
"eval_steps_per_second": 2.652,
|
| 792 |
+
"step": 787
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 35.11,
|
| 796 |
+
"learning_rate": 5.382775119617226e-06,
|
| 797 |
+
"loss": 0.0029,
|
| 798 |
+
"step": 790
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 35.56,
|
| 802 |
+
"learning_rate": 4.784688995215311e-06,
|
| 803 |
+
"loss": 0.0003,
|
| 804 |
+
"step": 800
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 36.0,
|
| 808 |
+
"learning_rate": 4.186602870813398e-06,
|
| 809 |
+
"loss": 0.0002,
|
| 810 |
+
"step": 810
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 36.0,
|
| 814 |
+
"eval_accuracy": 0.5887850467289719,
|
| 815 |
+
"eval_loss": 3.6918015480041504,
|
| 816 |
+
"eval_runtime": 2.7357,
|
| 817 |
+
"eval_samples_per_second": 39.112,
|
| 818 |
+
"eval_steps_per_second": 2.559,
|
| 819 |
+
"step": 810
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 36.44,
|
| 823 |
+
"learning_rate": 3.5885167464114835e-06,
|
| 824 |
+
"loss": 0.0003,
|
| 825 |
+
"step": 820
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 36.89,
|
| 829 |
+
"learning_rate": 2.9904306220095695e-06,
|
| 830 |
+
"loss": 0.0004,
|
| 831 |
+
"step": 830
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 36.98,
|
| 835 |
+
"eval_accuracy": 0.5887850467289719,
|
| 836 |
+
"eval_loss": 3.659736156463623,
|
| 837 |
+
"eval_runtime": 2.6137,
|
| 838 |
+
"eval_samples_per_second": 40.938,
|
| 839 |
+
"eval_steps_per_second": 2.678,
|
| 840 |
+
"step": 832
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 37.33,
|
| 844 |
+
"learning_rate": 2.3923444976076554e-06,
|
| 845 |
+
"loss": 0.0002,
|
| 846 |
+
"step": 840
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 37.78,
|
| 850 |
+
"learning_rate": 1.7942583732057418e-06,
|
| 851 |
+
"loss": 0.0003,
|
| 852 |
+
"step": 850
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 38.0,
|
| 856 |
+
"eval_accuracy": 0.5887850467289719,
|
| 857 |
+
"eval_loss": 3.65986967086792,
|
| 858 |
+
"eval_runtime": 2.5356,
|
| 859 |
+
"eval_samples_per_second": 42.198,
|
| 860 |
+
"eval_steps_per_second": 2.761,
|
| 861 |
+
"step": 855
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 38.22,
|
| 865 |
+
"learning_rate": 1.1961722488038277e-06,
|
| 866 |
+
"loss": 0.0022,
|
| 867 |
+
"step": 860
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 38.67,
|
| 871 |
+
"learning_rate": 5.980861244019139e-07,
|
| 872 |
+
"loss": 0.0002,
|
| 873 |
+
"step": 870
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 38.98,
|
| 877 |
+
"eval_accuracy": 0.5887850467289719,
|
| 878 |
+
"eval_loss": 3.673996925354004,
|
| 879 |
+
"eval_runtime": 2.6372,
|
| 880 |
+
"eval_samples_per_second": 40.573,
|
| 881 |
+
"eval_steps_per_second": 2.654,
|
| 882 |
+
"step": 877
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 39.11,
|
| 886 |
+
"learning_rate": 0.0,
|
| 887 |
+
"loss": 0.0002,
|
| 888 |
+
"step": 880
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 39.11,
|
| 892 |
+
"eval_accuracy": 0.5887850467289719,
|
| 893 |
+
"eval_loss": 3.674065351486206,
|
| 894 |
+
"eval_runtime": 2.9557,
|
| 895 |
+
"eval_samples_per_second": 36.201,
|
| 896 |
+
"eval_steps_per_second": 2.368,
|
| 897 |
+
"step": 880
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 39.11,
|
| 901 |
+
"step": 880,
|
| 902 |
+
"total_flos": 4.350399898167558e+18,
|
| 903 |
+
"train_loss": 0.09111572096166624,
|
| 904 |
+
"train_runtime": 1452.6155,
|
| 905 |
+
"train_samples_per_second": 39.542,
|
| 906 |
+
"train_steps_per_second": 0.606
|
| 907 |
+
}
|
| 908 |
+
],
|
| 909 |
+
"logging_steps": 10,
|
| 910 |
+
"max_steps": 880,
|
| 911 |
+
"num_input_tokens_seen": 0,
|
| 912 |
+
"num_train_epochs": 40,
|
| 913 |
+
"save_steps": 500,
|
| 914 |
+
"total_flos": 4.350399898167558e+18,
|
| 915 |
+
"train_batch_size": 16,
|
| 916 |
+
"trial_name": null,
|
| 917 |
+
"trial_params": null
|
| 918 |
+
}
|