End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Jun12_10-54-32_DESKTOP-SKBE9FB/events.out.tfevents.1718212148.DESKTOP-SKBE9FB.8968.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +984 -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/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) 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: 0.7391304347826086
|
| 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/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.7882
|
| 36 |
+
- Accuracy: 0.7391
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 73.85,
|
| 3 |
+
"eval_accuracy": 0.7391304347826086,
|
| 4 |
+
"eval_loss": 0.7882330417633057,
|
| 5 |
+
"eval_runtime": 0.9712,
|
| 6 |
+
"eval_samples_per_second": 47.364,
|
| 7 |
+
"eval_steps_per_second": 2.059,
|
| 8 |
+
"train_loss": 0.36262454763054847,
|
| 9 |
+
"train_runtime": 818.339,
|
| 10 |
+
"train_samples_per_second": 80.065,
|
| 11 |
+
"train_steps_per_second": 0.587
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 73.85,
|
| 3 |
+
"eval_accuracy": 0.7391304347826086,
|
| 4 |
+
"eval_loss": 0.7882330417633057,
|
| 5 |
+
"eval_runtime": 0.9712,
|
| 6 |
+
"eval_samples_per_second": 47.364,
|
| 7 |
+
"eval_steps_per_second": 2.059
|
| 8 |
+
}
|
runs/Jun12_10-54-32_DESKTOP-SKBE9FB/events.out.tfevents.1718212148.DESKTOP-SKBE9FB.8968.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c5e6189ba46372b239fd1d6bfea75e59010b138970987e4bce60b04e73c7d03
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 73.85,
|
| 3 |
+
"train_loss": 0.36262454763054847,
|
| 4 |
+
"train_runtime": 818.339,
|
| 5 |
+
"train_samples_per_second": 80.065,
|
| 6 |
+
"train_steps_per_second": 0.587
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,984 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7391304347826086,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-ve-U13-b-80\\checkpoint-91",
|
| 4 |
+
"epoch": 73.84615384615384,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 480,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.92,
|
| 13 |
+
"eval_accuracy": 0.13043478260869565,
|
| 14 |
+
"eval_loss": 1.385754942893982,
|
| 15 |
+
"eval_runtime": 0.7438,
|
| 16 |
+
"eval_samples_per_second": 61.847,
|
| 17 |
+
"eval_steps_per_second": 2.689,
|
| 18 |
+
"step": 6
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.54,
|
| 22 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 23 |
+
"loss": 1.3856,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.3695652173913043,
|
| 29 |
+
"eval_loss": 1.377731204032898,
|
| 30 |
+
"eval_runtime": 0.7263,
|
| 31 |
+
"eval_samples_per_second": 63.33,
|
| 32 |
+
"eval_steps_per_second": 2.753,
|
| 33 |
+
"step": 13
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.92,
|
| 37 |
+
"eval_accuracy": 0.2391304347826087,
|
| 38 |
+
"eval_loss": 1.348819375038147,
|
| 39 |
+
"eval_runtime": 0.75,
|
| 40 |
+
"eval_samples_per_second": 61.336,
|
| 41 |
+
"eval_steps_per_second": 2.667,
|
| 42 |
+
"step": 19
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.08,
|
| 46 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 47 |
+
"loss": 1.361,
|
| 48 |
+
"step": 20
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.2826086956521739,
|
| 53 |
+
"eval_loss": 1.2502505779266357,
|
| 54 |
+
"eval_runtime": 0.7438,
|
| 55 |
+
"eval_samples_per_second": 61.841,
|
| 56 |
+
"eval_steps_per_second": 2.689,
|
| 57 |
+
"step": 26
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.62,
|
| 61 |
+
"learning_rate": 5.4276315789473686e-05,
|
| 62 |
+
"loss": 1.2088,
|
| 63 |
+
"step": 30
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.92,
|
| 67 |
+
"eval_accuracy": 0.41304347826086957,
|
| 68 |
+
"eval_loss": 1.1317055225372314,
|
| 69 |
+
"eval_runtime": 0.7105,
|
| 70 |
+
"eval_samples_per_second": 64.741,
|
| 71 |
+
"eval_steps_per_second": 2.815,
|
| 72 |
+
"step": 32
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.45652173913043476,
|
| 77 |
+
"eval_loss": 1.0243556499481201,
|
| 78 |
+
"eval_runtime": 0.7994,
|
| 79 |
+
"eval_samples_per_second": 57.543,
|
| 80 |
+
"eval_steps_per_second": 2.502,
|
| 81 |
+
"step": 39
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.15,
|
| 85 |
+
"learning_rate": 5.3070175438596496e-05,
|
| 86 |
+
"loss": 1.0729,
|
| 87 |
+
"step": 40
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.92,
|
| 91 |
+
"eval_accuracy": 0.45652173913043476,
|
| 92 |
+
"eval_loss": 1.041305422782898,
|
| 93 |
+
"eval_runtime": 0.7893,
|
| 94 |
+
"eval_samples_per_second": 58.282,
|
| 95 |
+
"eval_steps_per_second": 2.534,
|
| 96 |
+
"step": 45
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 7.69,
|
| 100 |
+
"learning_rate": 5.18640350877193e-05,
|
| 101 |
+
"loss": 0.9554,
|
| 102 |
+
"step": 50
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 8.0,
|
| 106 |
+
"eval_accuracy": 0.5652173913043478,
|
| 107 |
+
"eval_loss": 0.9286284446716309,
|
| 108 |
+
"eval_runtime": 0.7455,
|
| 109 |
+
"eval_samples_per_second": 61.704,
|
| 110 |
+
"eval_steps_per_second": 2.683,
|
| 111 |
+
"step": 52
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 8.92,
|
| 115 |
+
"eval_accuracy": 0.5652173913043478,
|
| 116 |
+
"eval_loss": 0.9103382229804993,
|
| 117 |
+
"eval_runtime": 0.7349,
|
| 118 |
+
"eval_samples_per_second": 62.593,
|
| 119 |
+
"eval_steps_per_second": 2.721,
|
| 120 |
+
"step": 58
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.23,
|
| 124 |
+
"learning_rate": 5.0657894736842104e-05,
|
| 125 |
+
"loss": 0.8221,
|
| 126 |
+
"step": 60
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 10.0,
|
| 130 |
+
"eval_accuracy": 0.6521739130434783,
|
| 131 |
+
"eval_loss": 0.8519319295883179,
|
| 132 |
+
"eval_runtime": 0.7139,
|
| 133 |
+
"eval_samples_per_second": 64.431,
|
| 134 |
+
"eval_steps_per_second": 2.801,
|
| 135 |
+
"step": 65
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.77,
|
| 139 |
+
"learning_rate": 4.9451754385964915e-05,
|
| 140 |
+
"loss": 0.732,
|
| 141 |
+
"step": 70
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.92,
|
| 145 |
+
"eval_accuracy": 0.5869565217391305,
|
| 146 |
+
"eval_loss": 0.8299721479415894,
|
| 147 |
+
"eval_runtime": 0.7596,
|
| 148 |
+
"eval_samples_per_second": 60.555,
|
| 149 |
+
"eval_steps_per_second": 2.633,
|
| 150 |
+
"step": 71
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 12.0,
|
| 154 |
+
"eval_accuracy": 0.6304347826086957,
|
| 155 |
+
"eval_loss": 0.810260534286499,
|
| 156 |
+
"eval_runtime": 0.7348,
|
| 157 |
+
"eval_samples_per_second": 62.603,
|
| 158 |
+
"eval_steps_per_second": 2.722,
|
| 159 |
+
"step": 78
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.31,
|
| 163 |
+
"learning_rate": 4.824561403508772e-05,
|
| 164 |
+
"loss": 0.6491,
|
| 165 |
+
"step": 80
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 12.92,
|
| 169 |
+
"eval_accuracy": 0.5869565217391305,
|
| 170 |
+
"eval_loss": 0.9533290266990662,
|
| 171 |
+
"eval_runtime": 0.736,
|
| 172 |
+
"eval_samples_per_second": 62.5,
|
| 173 |
+
"eval_steps_per_second": 2.717,
|
| 174 |
+
"step": 84
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 13.85,
|
| 178 |
+
"learning_rate": 4.703947368421053e-05,
|
| 179 |
+
"loss": 0.5724,
|
| 180 |
+
"step": 90
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 14.0,
|
| 184 |
+
"eval_accuracy": 0.7391304347826086,
|
| 185 |
+
"eval_loss": 0.7882330417633057,
|
| 186 |
+
"eval_runtime": 0.7754,
|
| 187 |
+
"eval_samples_per_second": 59.325,
|
| 188 |
+
"eval_steps_per_second": 2.579,
|
| 189 |
+
"step": 91
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 14.92,
|
| 193 |
+
"eval_accuracy": 0.6956521739130435,
|
| 194 |
+
"eval_loss": 0.8071939945220947,
|
| 195 |
+
"eval_runtime": 0.7958,
|
| 196 |
+
"eval_samples_per_second": 57.807,
|
| 197 |
+
"eval_steps_per_second": 2.513,
|
| 198 |
+
"step": 97
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 15.38,
|
| 202 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 203 |
+
"loss": 0.5305,
|
| 204 |
+
"step": 100
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 16.0,
|
| 208 |
+
"eval_accuracy": 0.7391304347826086,
|
| 209 |
+
"eval_loss": 0.7651436924934387,
|
| 210 |
+
"eval_runtime": 0.7895,
|
| 211 |
+
"eval_samples_per_second": 58.267,
|
| 212 |
+
"eval_steps_per_second": 2.533,
|
| 213 |
+
"step": 104
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 16.92,
|
| 217 |
+
"learning_rate": 4.462719298245614e-05,
|
| 218 |
+
"loss": 0.4879,
|
| 219 |
+
"step": 110
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.92,
|
| 223 |
+
"eval_accuracy": 0.717391304347826,
|
| 224 |
+
"eval_loss": 0.7378753423690796,
|
| 225 |
+
"eval_runtime": 0.7421,
|
| 226 |
+
"eval_samples_per_second": 61.986,
|
| 227 |
+
"eval_steps_per_second": 2.695,
|
| 228 |
+
"step": 110
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 18.0,
|
| 232 |
+
"eval_accuracy": 0.6739130434782609,
|
| 233 |
+
"eval_loss": 0.7589738368988037,
|
| 234 |
+
"eval_runtime": 0.8499,
|
| 235 |
+
"eval_samples_per_second": 54.125,
|
| 236 |
+
"eval_steps_per_second": 2.353,
|
| 237 |
+
"step": 117
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 18.46,
|
| 241 |
+
"learning_rate": 4.342105263157895e-05,
|
| 242 |
+
"loss": 0.4346,
|
| 243 |
+
"step": 120
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 18.92,
|
| 247 |
+
"eval_accuracy": 0.6739130434782609,
|
| 248 |
+
"eval_loss": 0.9283233284950256,
|
| 249 |
+
"eval_runtime": 0.8223,
|
| 250 |
+
"eval_samples_per_second": 55.938,
|
| 251 |
+
"eval_steps_per_second": 2.432,
|
| 252 |
+
"step": 123
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 20.0,
|
| 256 |
+
"learning_rate": 4.221491228070176e-05,
|
| 257 |
+
"loss": 0.3671,
|
| 258 |
+
"step": 130
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 20.0,
|
| 262 |
+
"eval_accuracy": 0.6304347826086957,
|
| 263 |
+
"eval_loss": 1.0188376903533936,
|
| 264 |
+
"eval_runtime": 0.7701,
|
| 265 |
+
"eval_samples_per_second": 59.73,
|
| 266 |
+
"eval_steps_per_second": 2.597,
|
| 267 |
+
"step": 130
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 20.92,
|
| 271 |
+
"eval_accuracy": 0.7391304347826086,
|
| 272 |
+
"eval_loss": 0.895862340927124,
|
| 273 |
+
"eval_runtime": 0.8493,
|
| 274 |
+
"eval_samples_per_second": 54.165,
|
| 275 |
+
"eval_steps_per_second": 2.355,
|
| 276 |
+
"step": 136
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 21.54,
|
| 280 |
+
"learning_rate": 4.100877192982456e-05,
|
| 281 |
+
"loss": 0.3725,
|
| 282 |
+
"step": 140
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 22.0,
|
| 286 |
+
"eval_accuracy": 0.6956521739130435,
|
| 287 |
+
"eval_loss": 0.950153112411499,
|
| 288 |
+
"eval_runtime": 0.7826,
|
| 289 |
+
"eval_samples_per_second": 58.782,
|
| 290 |
+
"eval_steps_per_second": 2.556,
|
| 291 |
+
"step": 143
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 22.92,
|
| 295 |
+
"eval_accuracy": 0.6521739130434783,
|
| 296 |
+
"eval_loss": 0.9626518487930298,
|
| 297 |
+
"eval_runtime": 0.749,
|
| 298 |
+
"eval_samples_per_second": 61.418,
|
| 299 |
+
"eval_steps_per_second": 2.67,
|
| 300 |
+
"step": 149
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 23.08,
|
| 304 |
+
"learning_rate": 3.9802631578947374e-05,
|
| 305 |
+
"loss": 0.3321,
|
| 306 |
+
"step": 150
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 24.0,
|
| 310 |
+
"eval_accuracy": 0.6956521739130435,
|
| 311 |
+
"eval_loss": 0.9619277715682983,
|
| 312 |
+
"eval_runtime": 0.767,
|
| 313 |
+
"eval_samples_per_second": 59.974,
|
| 314 |
+
"eval_steps_per_second": 2.608,
|
| 315 |
+
"step": 156
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 24.62,
|
| 319 |
+
"learning_rate": 3.859649122807018e-05,
|
| 320 |
+
"loss": 0.3376,
|
| 321 |
+
"step": 160
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 24.92,
|
| 325 |
+
"eval_accuracy": 0.6739130434782609,
|
| 326 |
+
"eval_loss": 1.0459153652191162,
|
| 327 |
+
"eval_runtime": 0.7694,
|
| 328 |
+
"eval_samples_per_second": 59.79,
|
| 329 |
+
"eval_steps_per_second": 2.6,
|
| 330 |
+
"step": 162
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 26.0,
|
| 334 |
+
"eval_accuracy": 0.6521739130434783,
|
| 335 |
+
"eval_loss": 1.0166922807693481,
|
| 336 |
+
"eval_runtime": 0.7571,
|
| 337 |
+
"eval_samples_per_second": 60.757,
|
| 338 |
+
"eval_steps_per_second": 2.642,
|
| 339 |
+
"step": 169
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 26.15,
|
| 343 |
+
"learning_rate": 3.739035087719298e-05,
|
| 344 |
+
"loss": 0.3699,
|
| 345 |
+
"step": 170
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 26.92,
|
| 349 |
+
"eval_accuracy": 0.6304347826086957,
|
| 350 |
+
"eval_loss": 0.9949257969856262,
|
| 351 |
+
"eval_runtime": 0.8034,
|
| 352 |
+
"eval_samples_per_second": 57.258,
|
| 353 |
+
"eval_steps_per_second": 2.489,
|
| 354 |
+
"step": 175
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 27.69,
|
| 358 |
+
"learning_rate": 3.618421052631579e-05,
|
| 359 |
+
"loss": 0.3098,
|
| 360 |
+
"step": 180
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 28.0,
|
| 364 |
+
"eval_accuracy": 0.6739130434782609,
|
| 365 |
+
"eval_loss": 0.9944018721580505,
|
| 366 |
+
"eval_runtime": 0.7886,
|
| 367 |
+
"eval_samples_per_second": 58.329,
|
| 368 |
+
"eval_steps_per_second": 2.536,
|
| 369 |
+
"step": 182
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 28.92,
|
| 373 |
+
"eval_accuracy": 0.6304347826086957,
|
| 374 |
+
"eval_loss": 1.0860100984573364,
|
| 375 |
+
"eval_runtime": 0.7948,
|
| 376 |
+
"eval_samples_per_second": 57.876,
|
| 377 |
+
"eval_steps_per_second": 2.516,
|
| 378 |
+
"step": 188
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 29.23,
|
| 382 |
+
"learning_rate": 3.49780701754386e-05,
|
| 383 |
+
"loss": 0.253,
|
| 384 |
+
"step": 190
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 30.0,
|
| 388 |
+
"eval_accuracy": 0.6521739130434783,
|
| 389 |
+
"eval_loss": 1.1720929145812988,
|
| 390 |
+
"eval_runtime": 0.8196,
|
| 391 |
+
"eval_samples_per_second": 56.128,
|
| 392 |
+
"eval_steps_per_second": 2.44,
|
| 393 |
+
"step": 195
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 30.77,
|
| 397 |
+
"learning_rate": 3.377192982456141e-05,
|
| 398 |
+
"loss": 0.2615,
|
| 399 |
+
"step": 200
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 30.92,
|
| 403 |
+
"eval_accuracy": 0.6739130434782609,
|
| 404 |
+
"eval_loss": 1.1625701189041138,
|
| 405 |
+
"eval_runtime": 0.7635,
|
| 406 |
+
"eval_samples_per_second": 60.248,
|
| 407 |
+
"eval_steps_per_second": 2.619,
|
| 408 |
+
"step": 201
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 32.0,
|
| 412 |
+
"eval_accuracy": 0.6304347826086957,
|
| 413 |
+
"eval_loss": 1.2463836669921875,
|
| 414 |
+
"eval_runtime": 0.7858,
|
| 415 |
+
"eval_samples_per_second": 58.541,
|
| 416 |
+
"eval_steps_per_second": 2.545,
|
| 417 |
+
"step": 208
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 32.31,
|
| 421 |
+
"learning_rate": 3.256578947368421e-05,
|
| 422 |
+
"loss": 0.242,
|
| 423 |
+
"step": 210
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 32.92,
|
| 427 |
+
"eval_accuracy": 0.6521739130434783,
|
| 428 |
+
"eval_loss": 1.2178901433944702,
|
| 429 |
+
"eval_runtime": 0.7976,
|
| 430 |
+
"eval_samples_per_second": 57.676,
|
| 431 |
+
"eval_steps_per_second": 2.508,
|
| 432 |
+
"step": 214
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 33.85,
|
| 436 |
+
"learning_rate": 3.1359649122807015e-05,
|
| 437 |
+
"loss": 0.2173,
|
| 438 |
+
"step": 220
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 34.0,
|
| 442 |
+
"eval_accuracy": 0.6304347826086957,
|
| 443 |
+
"eval_loss": 1.2406569719314575,
|
| 444 |
+
"eval_runtime": 0.7647,
|
| 445 |
+
"eval_samples_per_second": 60.158,
|
| 446 |
+
"eval_steps_per_second": 2.616,
|
| 447 |
+
"step": 221
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 34.92,
|
| 451 |
+
"eval_accuracy": 0.6739130434782609,
|
| 452 |
+
"eval_loss": 1.1584811210632324,
|
| 453 |
+
"eval_runtime": 0.8017,
|
| 454 |
+
"eval_samples_per_second": 57.382,
|
| 455 |
+
"eval_steps_per_second": 2.495,
|
| 456 |
+
"step": 227
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 35.38,
|
| 460 |
+
"learning_rate": 3.0153508771929826e-05,
|
| 461 |
+
"loss": 0.2305,
|
| 462 |
+
"step": 230
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 36.0,
|
| 466 |
+
"eval_accuracy": 0.6521739130434783,
|
| 467 |
+
"eval_loss": 1.304764747619629,
|
| 468 |
+
"eval_runtime": 0.7581,
|
| 469 |
+
"eval_samples_per_second": 60.68,
|
| 470 |
+
"eval_steps_per_second": 2.638,
|
| 471 |
+
"step": 234
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 36.92,
|
| 475 |
+
"learning_rate": 2.894736842105263e-05,
|
| 476 |
+
"loss": 0.2114,
|
| 477 |
+
"step": 240
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 36.92,
|
| 481 |
+
"eval_accuracy": 0.6521739130434783,
|
| 482 |
+
"eval_loss": 1.1775559186935425,
|
| 483 |
+
"eval_runtime": 0.724,
|
| 484 |
+
"eval_samples_per_second": 63.534,
|
| 485 |
+
"eval_steps_per_second": 2.762,
|
| 486 |
+
"step": 240
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 38.0,
|
| 490 |
+
"eval_accuracy": 0.6521739130434783,
|
| 491 |
+
"eval_loss": 1.1460415124893188,
|
| 492 |
+
"eval_runtime": 0.7523,
|
| 493 |
+
"eval_samples_per_second": 61.147,
|
| 494 |
+
"eval_steps_per_second": 2.659,
|
| 495 |
+
"step": 247
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 38.46,
|
| 499 |
+
"learning_rate": 2.774122807017544e-05,
|
| 500 |
+
"loss": 0.2243,
|
| 501 |
+
"step": 250
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 38.92,
|
| 505 |
+
"eval_accuracy": 0.6956521739130435,
|
| 506 |
+
"eval_loss": 1.2424203157424927,
|
| 507 |
+
"eval_runtime": 0.759,
|
| 508 |
+
"eval_samples_per_second": 60.607,
|
| 509 |
+
"eval_steps_per_second": 2.635,
|
| 510 |
+
"step": 253
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 40.0,
|
| 514 |
+
"learning_rate": 2.6535087719298248e-05,
|
| 515 |
+
"loss": 0.1822,
|
| 516 |
+
"step": 260
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 40.0,
|
| 520 |
+
"eval_accuracy": 0.6739130434782609,
|
| 521 |
+
"eval_loss": 1.2804019451141357,
|
| 522 |
+
"eval_runtime": 0.7624,
|
| 523 |
+
"eval_samples_per_second": 60.336,
|
| 524 |
+
"eval_steps_per_second": 2.623,
|
| 525 |
+
"step": 260
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 40.92,
|
| 529 |
+
"eval_accuracy": 0.6739130434782609,
|
| 530 |
+
"eval_loss": 1.3472291231155396,
|
| 531 |
+
"eval_runtime": 0.7688,
|
| 532 |
+
"eval_samples_per_second": 59.835,
|
| 533 |
+
"eval_steps_per_second": 2.602,
|
| 534 |
+
"step": 266
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 41.54,
|
| 538 |
+
"learning_rate": 2.5328947368421052e-05,
|
| 539 |
+
"loss": 0.2065,
|
| 540 |
+
"step": 270
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 42.0,
|
| 544 |
+
"eval_accuracy": 0.6739130434782609,
|
| 545 |
+
"eval_loss": 1.3632473945617676,
|
| 546 |
+
"eval_runtime": 0.775,
|
| 547 |
+
"eval_samples_per_second": 59.355,
|
| 548 |
+
"eval_steps_per_second": 2.581,
|
| 549 |
+
"step": 273
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 42.92,
|
| 553 |
+
"eval_accuracy": 0.6739130434782609,
|
| 554 |
+
"eval_loss": 1.28322434425354,
|
| 555 |
+
"eval_runtime": 0.7318,
|
| 556 |
+
"eval_samples_per_second": 62.856,
|
| 557 |
+
"eval_steps_per_second": 2.733,
|
| 558 |
+
"step": 279
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 43.08,
|
| 562 |
+
"learning_rate": 2.412280701754386e-05,
|
| 563 |
+
"loss": 0.1942,
|
| 564 |
+
"step": 280
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 44.0,
|
| 568 |
+
"eval_accuracy": 0.6739130434782609,
|
| 569 |
+
"eval_loss": 1.3499536514282227,
|
| 570 |
+
"eval_runtime": 0.7849,
|
| 571 |
+
"eval_samples_per_second": 58.604,
|
| 572 |
+
"eval_steps_per_second": 2.548,
|
| 573 |
+
"step": 286
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 44.62,
|
| 577 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 578 |
+
"loss": 0.1699,
|
| 579 |
+
"step": 290
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 44.92,
|
| 583 |
+
"eval_accuracy": 0.6739130434782609,
|
| 584 |
+
"eval_loss": 1.3242206573486328,
|
| 585 |
+
"eval_runtime": 0.7599,
|
| 586 |
+
"eval_samples_per_second": 60.533,
|
| 587 |
+
"eval_steps_per_second": 2.632,
|
| 588 |
+
"step": 292
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 46.0,
|
| 592 |
+
"eval_accuracy": 0.6956521739130435,
|
| 593 |
+
"eval_loss": 1.3188772201538086,
|
| 594 |
+
"eval_runtime": 0.7449,
|
| 595 |
+
"eval_samples_per_second": 61.753,
|
| 596 |
+
"eval_steps_per_second": 2.685,
|
| 597 |
+
"step": 299
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 46.15,
|
| 601 |
+
"learning_rate": 2.1710526315789474e-05,
|
| 602 |
+
"loss": 0.1764,
|
| 603 |
+
"step": 300
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 46.92,
|
| 607 |
+
"eval_accuracy": 0.6739130434782609,
|
| 608 |
+
"eval_loss": 1.2839657068252563,
|
| 609 |
+
"eval_runtime": 0.723,
|
| 610 |
+
"eval_samples_per_second": 63.626,
|
| 611 |
+
"eval_steps_per_second": 2.766,
|
| 612 |
+
"step": 305
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 47.69,
|
| 616 |
+
"learning_rate": 2.050438596491228e-05,
|
| 617 |
+
"loss": 0.1771,
|
| 618 |
+
"step": 310
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 48.0,
|
| 622 |
+
"eval_accuracy": 0.6956521739130435,
|
| 623 |
+
"eval_loss": 1.3069181442260742,
|
| 624 |
+
"eval_runtime": 0.8128,
|
| 625 |
+
"eval_samples_per_second": 56.596,
|
| 626 |
+
"eval_steps_per_second": 2.461,
|
| 627 |
+
"step": 312
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 48.92,
|
| 631 |
+
"eval_accuracy": 0.6956521739130435,
|
| 632 |
+
"eval_loss": 1.1584603786468506,
|
| 633 |
+
"eval_runtime": 0.7739,
|
| 634 |
+
"eval_samples_per_second": 59.436,
|
| 635 |
+
"eval_steps_per_second": 2.584,
|
| 636 |
+
"step": 318
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 49.23,
|
| 640 |
+
"learning_rate": 1.929824561403509e-05,
|
| 641 |
+
"loss": 0.2095,
|
| 642 |
+
"step": 320
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 50.0,
|
| 646 |
+
"eval_accuracy": 0.6956521739130435,
|
| 647 |
+
"eval_loss": 1.3702274560928345,
|
| 648 |
+
"eval_runtime": 0.7551,
|
| 649 |
+
"eval_samples_per_second": 60.918,
|
| 650 |
+
"eval_steps_per_second": 2.649,
|
| 651 |
+
"step": 325
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 50.77,
|
| 655 |
+
"learning_rate": 1.8092105263157896e-05,
|
| 656 |
+
"loss": 0.1404,
|
| 657 |
+
"step": 330
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 50.92,
|
| 661 |
+
"eval_accuracy": 0.6956521739130435,
|
| 662 |
+
"eval_loss": 1.3539283275604248,
|
| 663 |
+
"eval_runtime": 0.7611,
|
| 664 |
+
"eval_samples_per_second": 60.437,
|
| 665 |
+
"eval_steps_per_second": 2.628,
|
| 666 |
+
"step": 331
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 52.0,
|
| 670 |
+
"eval_accuracy": 0.6956521739130435,
|
| 671 |
+
"eval_loss": 1.372290015220642,
|
| 672 |
+
"eval_runtime": 0.7589,
|
| 673 |
+
"eval_samples_per_second": 60.611,
|
| 674 |
+
"eval_steps_per_second": 2.635,
|
| 675 |
+
"step": 338
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 52.31,
|
| 679 |
+
"learning_rate": 1.6885964912280704e-05,
|
| 680 |
+
"loss": 0.1449,
|
| 681 |
+
"step": 340
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 52.92,
|
| 685 |
+
"eval_accuracy": 0.6956521739130435,
|
| 686 |
+
"eval_loss": 1.387741208076477,
|
| 687 |
+
"eval_runtime": 0.7822,
|
| 688 |
+
"eval_samples_per_second": 58.807,
|
| 689 |
+
"eval_steps_per_second": 2.557,
|
| 690 |
+
"step": 344
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 53.85,
|
| 694 |
+
"learning_rate": 1.5679824561403508e-05,
|
| 695 |
+
"loss": 0.1348,
|
| 696 |
+
"step": 350
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 54.0,
|
| 700 |
+
"eval_accuracy": 0.6739130434782609,
|
| 701 |
+
"eval_loss": 1.3381210565567017,
|
| 702 |
+
"eval_runtime": 0.7641,
|
| 703 |
+
"eval_samples_per_second": 60.202,
|
| 704 |
+
"eval_steps_per_second": 2.617,
|
| 705 |
+
"step": 351
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 54.92,
|
| 709 |
+
"eval_accuracy": 0.6739130434782609,
|
| 710 |
+
"eval_loss": 1.3700389862060547,
|
| 711 |
+
"eval_runtime": 0.7668,
|
| 712 |
+
"eval_samples_per_second": 59.989,
|
| 713 |
+
"eval_steps_per_second": 2.608,
|
| 714 |
+
"step": 357
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 55.38,
|
| 718 |
+
"learning_rate": 1.4473684210526315e-05,
|
| 719 |
+
"loss": 0.1683,
|
| 720 |
+
"step": 360
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 56.0,
|
| 724 |
+
"eval_accuracy": 0.6956521739130435,
|
| 725 |
+
"eval_loss": 1.2870872020721436,
|
| 726 |
+
"eval_runtime": 0.7471,
|
| 727 |
+
"eval_samples_per_second": 61.572,
|
| 728 |
+
"eval_steps_per_second": 2.677,
|
| 729 |
+
"step": 364
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 56.92,
|
| 733 |
+
"learning_rate": 1.3267543859649124e-05,
|
| 734 |
+
"loss": 0.1577,
|
| 735 |
+
"step": 370
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 56.92,
|
| 739 |
+
"eval_accuracy": 0.6956521739130435,
|
| 740 |
+
"eval_loss": 1.3214082717895508,
|
| 741 |
+
"eval_runtime": 0.7501,
|
| 742 |
+
"eval_samples_per_second": 61.328,
|
| 743 |
+
"eval_steps_per_second": 2.666,
|
| 744 |
+
"step": 370
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 58.0,
|
| 748 |
+
"eval_accuracy": 0.6521739130434783,
|
| 749 |
+
"eval_loss": 1.3992477655410767,
|
| 750 |
+
"eval_runtime": 0.7374,
|
| 751 |
+
"eval_samples_per_second": 62.382,
|
| 752 |
+
"eval_steps_per_second": 2.712,
|
| 753 |
+
"step": 377
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 58.46,
|
| 757 |
+
"learning_rate": 1.206140350877193e-05,
|
| 758 |
+
"loss": 0.1474,
|
| 759 |
+
"step": 380
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 58.92,
|
| 763 |
+
"eval_accuracy": 0.6521739130434783,
|
| 764 |
+
"eval_loss": 1.379963755607605,
|
| 765 |
+
"eval_runtime": 0.7819,
|
| 766 |
+
"eval_samples_per_second": 58.83,
|
| 767 |
+
"eval_steps_per_second": 2.558,
|
| 768 |
+
"step": 383
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 60.0,
|
| 772 |
+
"learning_rate": 1.0855263157894737e-05,
|
| 773 |
+
"loss": 0.1267,
|
| 774 |
+
"step": 390
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 60.0,
|
| 778 |
+
"eval_accuracy": 0.6739130434782609,
|
| 779 |
+
"eval_loss": 1.2534880638122559,
|
| 780 |
+
"eval_runtime": 0.7531,
|
| 781 |
+
"eval_samples_per_second": 61.078,
|
| 782 |
+
"eval_steps_per_second": 2.656,
|
| 783 |
+
"step": 390
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 60.92,
|
| 787 |
+
"eval_accuracy": 0.6739130434782609,
|
| 788 |
+
"eval_loss": 1.3200269937515259,
|
| 789 |
+
"eval_runtime": 0.7796,
|
| 790 |
+
"eval_samples_per_second": 59.004,
|
| 791 |
+
"eval_steps_per_second": 2.565,
|
| 792 |
+
"step": 396
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 61.54,
|
| 796 |
+
"learning_rate": 9.649122807017545e-06,
|
| 797 |
+
"loss": 0.1171,
|
| 798 |
+
"step": 400
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 62.0,
|
| 802 |
+
"eval_accuracy": 0.6739130434782609,
|
| 803 |
+
"eval_loss": 1.373002290725708,
|
| 804 |
+
"eval_runtime": 0.7716,
|
| 805 |
+
"eval_samples_per_second": 59.614,
|
| 806 |
+
"eval_steps_per_second": 2.592,
|
| 807 |
+
"step": 403
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 62.92,
|
| 811 |
+
"eval_accuracy": 0.6739130434782609,
|
| 812 |
+
"eval_loss": 1.3677655458450317,
|
| 813 |
+
"eval_runtime": 0.7677,
|
| 814 |
+
"eval_samples_per_second": 59.92,
|
| 815 |
+
"eval_steps_per_second": 2.605,
|
| 816 |
+
"step": 409
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 63.08,
|
| 820 |
+
"learning_rate": 8.442982456140352e-06,
|
| 821 |
+
"loss": 0.1461,
|
| 822 |
+
"step": 410
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 64.0,
|
| 826 |
+
"eval_accuracy": 0.6739130434782609,
|
| 827 |
+
"eval_loss": 1.378843069076538,
|
| 828 |
+
"eval_runtime": 0.7824,
|
| 829 |
+
"eval_samples_per_second": 58.791,
|
| 830 |
+
"eval_steps_per_second": 2.556,
|
| 831 |
+
"step": 416
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 64.62,
|
| 835 |
+
"learning_rate": 7.2368421052631575e-06,
|
| 836 |
+
"loss": 0.1124,
|
| 837 |
+
"step": 420
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 64.92,
|
| 841 |
+
"eval_accuracy": 0.6739130434782609,
|
| 842 |
+
"eval_loss": 1.3944367170333862,
|
| 843 |
+
"eval_runtime": 0.8361,
|
| 844 |
+
"eval_samples_per_second": 55.02,
|
| 845 |
+
"eval_steps_per_second": 2.392,
|
| 846 |
+
"step": 422
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 66.0,
|
| 850 |
+
"eval_accuracy": 0.6739130434782609,
|
| 851 |
+
"eval_loss": 1.372430682182312,
|
| 852 |
+
"eval_runtime": 0.7514,
|
| 853 |
+
"eval_samples_per_second": 61.223,
|
| 854 |
+
"eval_steps_per_second": 2.662,
|
| 855 |
+
"step": 429
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 66.15,
|
| 859 |
+
"learning_rate": 6.030701754385965e-06,
|
| 860 |
+
"loss": 0.1168,
|
| 861 |
+
"step": 430
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 66.92,
|
| 865 |
+
"eval_accuracy": 0.6521739130434783,
|
| 866 |
+
"eval_loss": 1.3552623987197876,
|
| 867 |
+
"eval_runtime": 0.8385,
|
| 868 |
+
"eval_samples_per_second": 54.858,
|
| 869 |
+
"eval_steps_per_second": 2.385,
|
| 870 |
+
"step": 435
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 67.69,
|
| 874 |
+
"learning_rate": 4.824561403508772e-06,
|
| 875 |
+
"loss": 0.1243,
|
| 876 |
+
"step": 440
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 68.0,
|
| 880 |
+
"eval_accuracy": 0.6739130434782609,
|
| 881 |
+
"eval_loss": 1.3829400539398193,
|
| 882 |
+
"eval_runtime": 0.8253,
|
| 883 |
+
"eval_samples_per_second": 55.74,
|
| 884 |
+
"eval_steps_per_second": 2.423,
|
| 885 |
+
"step": 442
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 68.92,
|
| 889 |
+
"eval_accuracy": 0.6739130434782609,
|
| 890 |
+
"eval_loss": 1.4040273427963257,
|
| 891 |
+
"eval_runtime": 0.7374,
|
| 892 |
+
"eval_samples_per_second": 62.382,
|
| 893 |
+
"eval_steps_per_second": 2.712,
|
| 894 |
+
"step": 448
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 69.23,
|
| 898 |
+
"learning_rate": 3.6184210526315788e-06,
|
| 899 |
+
"loss": 0.1375,
|
| 900 |
+
"step": 450
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 70.0,
|
| 904 |
+
"eval_accuracy": 0.6521739130434783,
|
| 905 |
+
"eval_loss": 1.4126824140548706,
|
| 906 |
+
"eval_runtime": 0.803,
|
| 907 |
+
"eval_samples_per_second": 57.287,
|
| 908 |
+
"eval_steps_per_second": 2.491,
|
| 909 |
+
"step": 455
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 70.77,
|
| 913 |
+
"learning_rate": 2.412280701754386e-06,
|
| 914 |
+
"loss": 0.1017,
|
| 915 |
+
"step": 460
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 70.92,
|
| 919 |
+
"eval_accuracy": 0.6521739130434783,
|
| 920 |
+
"eval_loss": 1.4069550037384033,
|
| 921 |
+
"eval_runtime": 0.7557,
|
| 922 |
+
"eval_samples_per_second": 60.867,
|
| 923 |
+
"eval_steps_per_second": 2.646,
|
| 924 |
+
"step": 461
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 72.0,
|
| 928 |
+
"eval_accuracy": 0.6739130434782609,
|
| 929 |
+
"eval_loss": 1.398921012878418,
|
| 930 |
+
"eval_runtime": 0.7798,
|
| 931 |
+
"eval_samples_per_second": 58.99,
|
| 932 |
+
"eval_steps_per_second": 2.565,
|
| 933 |
+
"step": 468
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 72.31,
|
| 937 |
+
"learning_rate": 1.206140350877193e-06,
|
| 938 |
+
"loss": 0.1346,
|
| 939 |
+
"step": 470
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 72.92,
|
| 943 |
+
"eval_accuracy": 0.6739130434782609,
|
| 944 |
+
"eval_loss": 1.3995212316513062,
|
| 945 |
+
"eval_runtime": 0.7372,
|
| 946 |
+
"eval_samples_per_second": 62.399,
|
| 947 |
+
"eval_steps_per_second": 2.713,
|
| 948 |
+
"step": 474
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 73.85,
|
| 952 |
+
"learning_rate": 0.0,
|
| 953 |
+
"loss": 0.1382,
|
| 954 |
+
"step": 480
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 73.85,
|
| 958 |
+
"eval_accuracy": 0.6739130434782609,
|
| 959 |
+
"eval_loss": 1.3988333940505981,
|
| 960 |
+
"eval_runtime": 0.8028,
|
| 961 |
+
"eval_samples_per_second": 57.301,
|
| 962 |
+
"eval_steps_per_second": 2.491,
|
| 963 |
+
"step": 480
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 73.85,
|
| 967 |
+
"step": 480,
|
| 968 |
+
"total_flos": 1.9681438145406566e+18,
|
| 969 |
+
"train_loss": 0.36262454763054847,
|
| 970 |
+
"train_runtime": 818.339,
|
| 971 |
+
"train_samples_per_second": 80.065,
|
| 972 |
+
"train_steps_per_second": 0.587
|
| 973 |
+
}
|
| 974 |
+
],
|
| 975 |
+
"logging_steps": 10,
|
| 976 |
+
"max_steps": 480,
|
| 977 |
+
"num_input_tokens_seen": 0,
|
| 978 |
+
"num_train_epochs": 80,
|
| 979 |
+
"save_steps": 500,
|
| 980 |
+
"total_flos": 1.9681438145406566e+18,
|
| 981 |
+
"train_batch_size": 32,
|
| 982 |
+
"trial_name": null,
|
| 983 |
+
"trial_params": null
|
| 984 |
+
}
|