End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Dec03_19-39-40_DESKTOP-SKBE9FB/events.out.tfevents.1733277623.DESKTOP-SKBE9FB.8824.1 +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/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: 0.616822429906542
|
| 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: 2.1002
|
| 36 |
+
- Accuracy: 0.6168
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 39.11,
|
| 3 |
+
"eval_accuracy": 0.616822429906542,
|
| 4 |
+
"eval_loss": 2.1001620292663574,
|
| 5 |
+
"eval_runtime": 2.6981,
|
| 6 |
+
"eval_samples_per_second": 39.657,
|
| 7 |
+
"eval_steps_per_second": 2.594,
|
| 8 |
+
"train_loss": 0.10380522197493437,
|
| 9 |
+
"train_runtime": 1214.1801,
|
| 10 |
+
"train_samples_per_second": 47.308,
|
| 11 |
+
"train_steps_per_second": 0.725
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 39.11,
|
| 3 |
+
"eval_accuracy": 0.616822429906542,
|
| 4 |
+
"eval_loss": 2.1001620292663574,
|
| 5 |
+
"eval_runtime": 2.6981,
|
| 6 |
+
"eval_samples_per_second": 39.657,
|
| 7 |
+
"eval_steps_per_second": 2.594
|
| 8 |
+
}
|
runs/Dec03_19-39-40_DESKTOP-SKBE9FB/events.out.tfevents.1733277623.DESKTOP-SKBE9FB.8824.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36a7fa6039a3ff3b5237c7c733159228d9f76611fc18d4e65d08971d95678b2b
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 39.11,
|
| 3 |
+
"train_loss": 0.10380522197493437,
|
| 4 |
+
"train_runtime": 1214.1801,
|
| 5 |
+
"train_samples_per_second": 47.308,
|
| 6 |
+
"train_steps_per_second": 0.725
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,918 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.616822429906542,
|
| 3 |
+
"best_model_checkpoint": "SW2-RHS-DA\\checkpoint-292",
|
| 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": 3.954545454545455e-05,
|
| 14 |
+
"loss": 1.6539,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.89,
|
| 19 |
+
"learning_rate": 3.909090909090909e-05,
|
| 20 |
+
"loss": 1.302,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.98,
|
| 25 |
+
"eval_accuracy": 0.411214953271028,
|
| 26 |
+
"eval_loss": 2.847358226776123,
|
| 27 |
+
"eval_runtime": 2.4491,
|
| 28 |
+
"eval_samples_per_second": 43.69,
|
| 29 |
+
"eval_steps_per_second": 2.858,
|
| 30 |
+
"step": 22
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.33,
|
| 34 |
+
"learning_rate": 3.863636363636364e-05,
|
| 35 |
+
"loss": 0.8548,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.78,
|
| 40 |
+
"learning_rate": 3.818181818181819e-05,
|
| 41 |
+
"loss": 0.6224,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.0,
|
| 46 |
+
"eval_accuracy": 0.411214953271028,
|
| 47 |
+
"eval_loss": 1.4649972915649414,
|
| 48 |
+
"eval_runtime": 2.5381,
|
| 49 |
+
"eval_samples_per_second": 42.157,
|
| 50 |
+
"eval_steps_per_second": 2.758,
|
| 51 |
+
"step": 45
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.22,
|
| 55 |
+
"learning_rate": 3.772727272727273e-05,
|
| 56 |
+
"loss": 0.4983,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.67,
|
| 61 |
+
"learning_rate": 3.7272727272727276e-05,
|
| 62 |
+
"loss": 0.3905,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.98,
|
| 67 |
+
"eval_accuracy": 0.411214953271028,
|
| 68 |
+
"eval_loss": 1.486470103263855,
|
| 69 |
+
"eval_runtime": 2.5569,
|
| 70 |
+
"eval_samples_per_second": 41.847,
|
| 71 |
+
"eval_steps_per_second": 2.738,
|
| 72 |
+
"step": 67
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 3.11,
|
| 76 |
+
"learning_rate": 3.681818181818182e-05,
|
| 77 |
+
"loss": 0.3143,
|
| 78 |
+
"step": 70
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.56,
|
| 82 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 83 |
+
"loss": 0.2038,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.0,
|
| 88 |
+
"learning_rate": 3.590909090909091e-05,
|
| 89 |
+
"loss": 0.1416,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.0,
|
| 94 |
+
"eval_accuracy": 0.5981308411214953,
|
| 95 |
+
"eval_loss": 0.9452531933784485,
|
| 96 |
+
"eval_runtime": 2.8177,
|
| 97 |
+
"eval_samples_per_second": 37.974,
|
| 98 |
+
"eval_steps_per_second": 2.484,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.44,
|
| 103 |
+
"learning_rate": 3.545454545454546e-05,
|
| 104 |
+
"loss": 0.1267,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.89,
|
| 109 |
+
"learning_rate": 3.5000000000000004e-05,
|
| 110 |
+
"loss": 0.1116,
|
| 111 |
+
"step": 110
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.98,
|
| 115 |
+
"eval_accuracy": 0.5514018691588785,
|
| 116 |
+
"eval_loss": 0.9800727963447571,
|
| 117 |
+
"eval_runtime": 2.4796,
|
| 118 |
+
"eval_samples_per_second": 43.152,
|
| 119 |
+
"eval_steps_per_second": 2.823,
|
| 120 |
+
"step": 112
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.33,
|
| 124 |
+
"learning_rate": 3.454545454545455e-05,
|
| 125 |
+
"loss": 0.1516,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.78,
|
| 130 |
+
"learning_rate": 3.409090909090909e-05,
|
| 131 |
+
"loss": 0.0866,
|
| 132 |
+
"step": 130
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 6.0,
|
| 136 |
+
"eval_accuracy": 0.6074766355140186,
|
| 137 |
+
"eval_loss": 1.520142912864685,
|
| 138 |
+
"eval_runtime": 2.5261,
|
| 139 |
+
"eval_samples_per_second": 42.358,
|
| 140 |
+
"eval_steps_per_second": 2.771,
|
| 141 |
+
"step": 135
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.22,
|
| 145 |
+
"learning_rate": 3.363636363636364e-05,
|
| 146 |
+
"loss": 0.1082,
|
| 147 |
+
"step": 140
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.67,
|
| 151 |
+
"learning_rate": 3.318181818181819e-05,
|
| 152 |
+
"loss": 0.0579,
|
| 153 |
+
"step": 150
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 6.98,
|
| 157 |
+
"eval_accuracy": 0.5981308411214953,
|
| 158 |
+
"eval_loss": 1.723357915878296,
|
| 159 |
+
"eval_runtime": 2.4956,
|
| 160 |
+
"eval_samples_per_second": 42.876,
|
| 161 |
+
"eval_steps_per_second": 2.805,
|
| 162 |
+
"step": 157
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 7.11,
|
| 166 |
+
"learning_rate": 3.272727272727273e-05,
|
| 167 |
+
"loss": 0.0679,
|
| 168 |
+
"step": 160
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 7.56,
|
| 172 |
+
"learning_rate": 3.2272727272727276e-05,
|
| 173 |
+
"loss": 0.1047,
|
| 174 |
+
"step": 170
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 8.0,
|
| 178 |
+
"learning_rate": 3.181818181818182e-05,
|
| 179 |
+
"loss": 0.0667,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 8.0,
|
| 184 |
+
"eval_accuracy": 0.5981308411214953,
|
| 185 |
+
"eval_loss": 1.9649068117141724,
|
| 186 |
+
"eval_runtime": 2.4861,
|
| 187 |
+
"eval_samples_per_second": 43.04,
|
| 188 |
+
"eval_steps_per_second": 2.816,
|
| 189 |
+
"step": 180
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.44,
|
| 193 |
+
"learning_rate": 3.1363636363636365e-05,
|
| 194 |
+
"loss": 0.0661,
|
| 195 |
+
"step": 190
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 8.89,
|
| 199 |
+
"learning_rate": 3.090909090909091e-05,
|
| 200 |
+
"loss": 0.0664,
|
| 201 |
+
"step": 200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 8.98,
|
| 205 |
+
"eval_accuracy": 0.5981308411214953,
|
| 206 |
+
"eval_loss": 1.9504597187042236,
|
| 207 |
+
"eval_runtime": 2.4306,
|
| 208 |
+
"eval_samples_per_second": 44.022,
|
| 209 |
+
"eval_steps_per_second": 2.88,
|
| 210 |
+
"step": 202
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 9.33,
|
| 214 |
+
"learning_rate": 3.0454545454545456e-05,
|
| 215 |
+
"loss": 0.0647,
|
| 216 |
+
"step": 210
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 9.78,
|
| 220 |
+
"learning_rate": 3.0000000000000004e-05,
|
| 221 |
+
"loss": 0.0742,
|
| 222 |
+
"step": 220
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 10.0,
|
| 226 |
+
"eval_accuracy": 0.5981308411214953,
|
| 227 |
+
"eval_loss": 1.9448089599609375,
|
| 228 |
+
"eval_runtime": 2.4836,
|
| 229 |
+
"eval_samples_per_second": 43.083,
|
| 230 |
+
"eval_steps_per_second": 2.819,
|
| 231 |
+
"step": 225
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 10.22,
|
| 235 |
+
"learning_rate": 2.954545454545455e-05,
|
| 236 |
+
"loss": 0.0588,
|
| 237 |
+
"step": 230
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 10.67,
|
| 241 |
+
"learning_rate": 2.9090909090909093e-05,
|
| 242 |
+
"loss": 0.0558,
|
| 243 |
+
"step": 240
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 10.98,
|
| 247 |
+
"eval_accuracy": 0.5981308411214953,
|
| 248 |
+
"eval_loss": 1.9545286893844604,
|
| 249 |
+
"eval_runtime": 2.5206,
|
| 250 |
+
"eval_samples_per_second": 42.45,
|
| 251 |
+
"eval_steps_per_second": 2.777,
|
| 252 |
+
"step": 247
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 11.11,
|
| 256 |
+
"learning_rate": 2.863636363636364e-05,
|
| 257 |
+
"loss": 0.0699,
|
| 258 |
+
"step": 250
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 11.56,
|
| 262 |
+
"learning_rate": 2.8181818181818185e-05,
|
| 263 |
+
"loss": 0.0564,
|
| 264 |
+
"step": 260
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 12.0,
|
| 268 |
+
"learning_rate": 2.7727272727272732e-05,
|
| 269 |
+
"loss": 0.0475,
|
| 270 |
+
"step": 270
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 12.0,
|
| 274 |
+
"eval_accuracy": 0.5887850467289719,
|
| 275 |
+
"eval_loss": 2.1516401767730713,
|
| 276 |
+
"eval_runtime": 2.4679,
|
| 277 |
+
"eval_samples_per_second": 43.356,
|
| 278 |
+
"eval_steps_per_second": 2.836,
|
| 279 |
+
"step": 270
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 12.44,
|
| 283 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 284 |
+
"loss": 0.0408,
|
| 285 |
+
"step": 280
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 12.89,
|
| 289 |
+
"learning_rate": 2.6818181818181817e-05,
|
| 290 |
+
"loss": 0.114,
|
| 291 |
+
"step": 290
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 12.98,
|
| 295 |
+
"eval_accuracy": 0.616822429906542,
|
| 296 |
+
"eval_loss": 2.1001620292663574,
|
| 297 |
+
"eval_runtime": 2.4814,
|
| 298 |
+
"eval_samples_per_second": 43.122,
|
| 299 |
+
"eval_steps_per_second": 2.821,
|
| 300 |
+
"step": 292
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 13.33,
|
| 304 |
+
"learning_rate": 2.6363636363636365e-05,
|
| 305 |
+
"loss": 0.0592,
|
| 306 |
+
"step": 300
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 13.78,
|
| 310 |
+
"learning_rate": 2.590909090909091e-05,
|
| 311 |
+
"loss": 0.051,
|
| 312 |
+
"step": 310
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 14.0,
|
| 316 |
+
"eval_accuracy": 0.5981308411214953,
|
| 317 |
+
"eval_loss": 2.2643392086029053,
|
| 318 |
+
"eval_runtime": 2.4411,
|
| 319 |
+
"eval_samples_per_second": 43.833,
|
| 320 |
+
"eval_steps_per_second": 2.868,
|
| 321 |
+
"step": 315
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 14.22,
|
| 325 |
+
"learning_rate": 2.5454545454545457e-05,
|
| 326 |
+
"loss": 0.0575,
|
| 327 |
+
"step": 320
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 14.67,
|
| 331 |
+
"learning_rate": 2.5e-05,
|
| 332 |
+
"loss": 0.0318,
|
| 333 |
+
"step": 330
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 14.98,
|
| 337 |
+
"eval_accuracy": 0.5981308411214953,
|
| 338 |
+
"eval_loss": 2.346831798553467,
|
| 339 |
+
"eval_runtime": 2.4771,
|
| 340 |
+
"eval_samples_per_second": 43.196,
|
| 341 |
+
"eval_steps_per_second": 2.826,
|
| 342 |
+
"step": 337
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 15.11,
|
| 346 |
+
"learning_rate": 2.454545454545455e-05,
|
| 347 |
+
"loss": 0.0273,
|
| 348 |
+
"step": 340
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 15.56,
|
| 352 |
+
"learning_rate": 2.4090909090909093e-05,
|
| 353 |
+
"loss": 0.0232,
|
| 354 |
+
"step": 350
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 16.0,
|
| 358 |
+
"learning_rate": 2.363636363636364e-05,
|
| 359 |
+
"loss": 0.0673,
|
| 360 |
+
"step": 360
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 16.0,
|
| 364 |
+
"eval_accuracy": 0.6074766355140186,
|
| 365 |
+
"eval_loss": 2.334057092666626,
|
| 366 |
+
"eval_runtime": 2.5831,
|
| 367 |
+
"eval_samples_per_second": 41.422,
|
| 368 |
+
"eval_steps_per_second": 2.71,
|
| 369 |
+
"step": 360
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 16.44,
|
| 373 |
+
"learning_rate": 2.3181818181818185e-05,
|
| 374 |
+
"loss": 0.0402,
|
| 375 |
+
"step": 370
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 16.89,
|
| 379 |
+
"learning_rate": 2.2727272727272733e-05,
|
| 380 |
+
"loss": 0.0566,
|
| 381 |
+
"step": 380
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 16.98,
|
| 385 |
+
"eval_accuracy": 0.6074766355140186,
|
| 386 |
+
"eval_loss": 2.319139003753662,
|
| 387 |
+
"eval_runtime": 2.4296,
|
| 388 |
+
"eval_samples_per_second": 44.04,
|
| 389 |
+
"eval_steps_per_second": 2.881,
|
| 390 |
+
"step": 382
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 17.33,
|
| 394 |
+
"learning_rate": 2.2272727272727274e-05,
|
| 395 |
+
"loss": 0.0445,
|
| 396 |
+
"step": 390
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 17.78,
|
| 400 |
+
"learning_rate": 2.1818181818181818e-05,
|
| 401 |
+
"loss": 0.0543,
|
| 402 |
+
"step": 400
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.0,
|
| 406 |
+
"eval_accuracy": 0.616822429906542,
|
| 407 |
+
"eval_loss": 2.280747413635254,
|
| 408 |
+
"eval_runtime": 2.5226,
|
| 409 |
+
"eval_samples_per_second": 42.417,
|
| 410 |
+
"eval_steps_per_second": 2.775,
|
| 411 |
+
"step": 405
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 18.22,
|
| 415 |
+
"learning_rate": 2.1363636363636365e-05,
|
| 416 |
+
"loss": 0.0419,
|
| 417 |
+
"step": 410
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 18.67,
|
| 421 |
+
"learning_rate": 2.090909090909091e-05,
|
| 422 |
+
"loss": 0.0458,
|
| 423 |
+
"step": 420
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 18.98,
|
| 427 |
+
"eval_accuracy": 0.616822429906542,
|
| 428 |
+
"eval_loss": 2.2148241996765137,
|
| 429 |
+
"eval_runtime": 2.5536,
|
| 430 |
+
"eval_samples_per_second": 41.901,
|
| 431 |
+
"eval_steps_per_second": 2.741,
|
| 432 |
+
"step": 427
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 19.11,
|
| 436 |
+
"learning_rate": 2.0454545454545457e-05,
|
| 437 |
+
"loss": 0.0255,
|
| 438 |
+
"step": 430
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 19.56,
|
| 442 |
+
"learning_rate": 2e-05,
|
| 443 |
+
"loss": 0.0306,
|
| 444 |
+
"step": 440
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 20.0,
|
| 448 |
+
"learning_rate": 1.9545454545454546e-05,
|
| 449 |
+
"loss": 0.0421,
|
| 450 |
+
"step": 450
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 20.0,
|
| 454 |
+
"eval_accuracy": 0.5887850467289719,
|
| 455 |
+
"eval_loss": 2.5467782020568848,
|
| 456 |
+
"eval_runtime": 2.4846,
|
| 457 |
+
"eval_samples_per_second": 43.065,
|
| 458 |
+
"eval_steps_per_second": 2.817,
|
| 459 |
+
"step": 450
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 20.44,
|
| 463 |
+
"learning_rate": 1.9090909090909094e-05,
|
| 464 |
+
"loss": 0.0509,
|
| 465 |
+
"step": 460
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 20.89,
|
| 469 |
+
"learning_rate": 1.8636363636363638e-05,
|
| 470 |
+
"loss": 0.0139,
|
| 471 |
+
"step": 470
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 20.98,
|
| 475 |
+
"eval_accuracy": 0.616822429906542,
|
| 476 |
+
"eval_loss": 2.2408316135406494,
|
| 477 |
+
"eval_runtime": 2.5411,
|
| 478 |
+
"eval_samples_per_second": 42.108,
|
| 479 |
+
"eval_steps_per_second": 2.755,
|
| 480 |
+
"step": 472
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 21.33,
|
| 484 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 485 |
+
"loss": 0.0208,
|
| 486 |
+
"step": 480
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 21.78,
|
| 490 |
+
"learning_rate": 1.772727272727273e-05,
|
| 491 |
+
"loss": 0.012,
|
| 492 |
+
"step": 490
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 22.0,
|
| 496 |
+
"eval_accuracy": 0.5887850467289719,
|
| 497 |
+
"eval_loss": 2.568880796432495,
|
| 498 |
+
"eval_runtime": 2.4491,
|
| 499 |
+
"eval_samples_per_second": 43.69,
|
| 500 |
+
"eval_steps_per_second": 2.858,
|
| 501 |
+
"step": 495
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 22.22,
|
| 505 |
+
"learning_rate": 1.7272727272727274e-05,
|
| 506 |
+
"loss": 0.0375,
|
| 507 |
+
"step": 500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 22.67,
|
| 511 |
+
"learning_rate": 1.681818181818182e-05,
|
| 512 |
+
"loss": 0.017,
|
| 513 |
+
"step": 510
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 22.98,
|
| 517 |
+
"eval_accuracy": 0.616822429906542,
|
| 518 |
+
"eval_loss": 2.548487901687622,
|
| 519 |
+
"eval_runtime": 2.5416,
|
| 520 |
+
"eval_samples_per_second": 42.1,
|
| 521 |
+
"eval_steps_per_second": 2.754,
|
| 522 |
+
"step": 517
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 23.11,
|
| 526 |
+
"learning_rate": 1.6363636363636366e-05,
|
| 527 |
+
"loss": 0.0293,
|
| 528 |
+
"step": 520
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 23.56,
|
| 532 |
+
"learning_rate": 1.590909090909091e-05,
|
| 533 |
+
"loss": 0.0482,
|
| 534 |
+
"step": 530
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 24.0,
|
| 538 |
+
"learning_rate": 1.5454545454545454e-05,
|
| 539 |
+
"loss": 0.0529,
|
| 540 |
+
"step": 540
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 24.0,
|
| 544 |
+
"eval_accuracy": 0.6074766355140186,
|
| 545 |
+
"eval_loss": 2.674633502960205,
|
| 546 |
+
"eval_runtime": 2.5767,
|
| 547 |
+
"eval_samples_per_second": 41.526,
|
| 548 |
+
"eval_steps_per_second": 2.717,
|
| 549 |
+
"step": 540
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 24.44,
|
| 553 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 554 |
+
"loss": 0.0063,
|
| 555 |
+
"step": 550
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 24.89,
|
| 559 |
+
"learning_rate": 1.4545454545454546e-05,
|
| 560 |
+
"loss": 0.0414,
|
| 561 |
+
"step": 560
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 24.98,
|
| 565 |
+
"eval_accuracy": 0.5887850467289719,
|
| 566 |
+
"eval_loss": 2.7693288326263428,
|
| 567 |
+
"eval_runtime": 2.6239,
|
| 568 |
+
"eval_samples_per_second": 40.778,
|
| 569 |
+
"eval_steps_per_second": 2.668,
|
| 570 |
+
"step": 562
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 25.33,
|
| 574 |
+
"learning_rate": 1.4090909090909092e-05,
|
| 575 |
+
"loss": 0.0203,
|
| 576 |
+
"step": 570
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 25.78,
|
| 580 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 581 |
+
"loss": 0.0158,
|
| 582 |
+
"step": 580
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 26.0,
|
| 586 |
+
"eval_accuracy": 0.5887850467289719,
|
| 587 |
+
"eval_loss": 2.7446506023406982,
|
| 588 |
+
"eval_runtime": 2.5651,
|
| 589 |
+
"eval_samples_per_second": 41.714,
|
| 590 |
+
"eval_steps_per_second": 2.729,
|
| 591 |
+
"step": 585
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 26.22,
|
| 595 |
+
"learning_rate": 1.3181818181818183e-05,
|
| 596 |
+
"loss": 0.0185,
|
| 597 |
+
"step": 590
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 26.67,
|
| 601 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 602 |
+
"loss": 0.0205,
|
| 603 |
+
"step": 600
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 26.98,
|
| 607 |
+
"eval_accuracy": 0.5887850467289719,
|
| 608 |
+
"eval_loss": 2.8566343784332275,
|
| 609 |
+
"eval_runtime": 2.5211,
|
| 610 |
+
"eval_samples_per_second": 42.442,
|
| 611 |
+
"eval_steps_per_second": 2.777,
|
| 612 |
+
"step": 607
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 27.11,
|
| 616 |
+
"learning_rate": 1.2272727272727274e-05,
|
| 617 |
+
"loss": 0.04,
|
| 618 |
+
"step": 610
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 27.56,
|
| 622 |
+
"learning_rate": 1.181818181818182e-05,
|
| 623 |
+
"loss": 0.0133,
|
| 624 |
+
"step": 620
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 28.0,
|
| 628 |
+
"learning_rate": 1.1363636363636366e-05,
|
| 629 |
+
"loss": 0.0205,
|
| 630 |
+
"step": 630
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 28.0,
|
| 634 |
+
"eval_accuracy": 0.5887850467289719,
|
| 635 |
+
"eval_loss": 2.846874713897705,
|
| 636 |
+
"eval_runtime": 2.4371,
|
| 637 |
+
"eval_samples_per_second": 43.905,
|
| 638 |
+
"eval_steps_per_second": 2.872,
|
| 639 |
+
"step": 630
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 28.44,
|
| 643 |
+
"learning_rate": 1.0909090909090909e-05,
|
| 644 |
+
"loss": 0.0211,
|
| 645 |
+
"step": 640
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 28.89,
|
| 649 |
+
"learning_rate": 1.0454545454545455e-05,
|
| 650 |
+
"loss": 0.006,
|
| 651 |
+
"step": 650
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 28.98,
|
| 655 |
+
"eval_accuracy": 0.5887850467289719,
|
| 656 |
+
"eval_loss": 2.9508450031280518,
|
| 657 |
+
"eval_runtime": 2.4616,
|
| 658 |
+
"eval_samples_per_second": 43.468,
|
| 659 |
+
"eval_steps_per_second": 2.844,
|
| 660 |
+
"step": 652
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 29.33,
|
| 664 |
+
"learning_rate": 1e-05,
|
| 665 |
+
"loss": 0.0198,
|
| 666 |
+
"step": 660
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 29.78,
|
| 670 |
+
"learning_rate": 9.545454545454547e-06,
|
| 671 |
+
"loss": 0.0061,
|
| 672 |
+
"step": 670
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 30.0,
|
| 676 |
+
"eval_accuracy": 0.5887850467289719,
|
| 677 |
+
"eval_loss": 3.0560247898101807,
|
| 678 |
+
"eval_runtime": 2.6005,
|
| 679 |
+
"eval_samples_per_second": 41.145,
|
| 680 |
+
"eval_steps_per_second": 2.692,
|
| 681 |
+
"step": 675
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 30.22,
|
| 685 |
+
"learning_rate": 9.090909090909091e-06,
|
| 686 |
+
"loss": 0.0124,
|
| 687 |
+
"step": 680
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 30.67,
|
| 691 |
+
"learning_rate": 8.636363636363637e-06,
|
| 692 |
+
"loss": 0.0227,
|
| 693 |
+
"step": 690
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 30.98,
|
| 697 |
+
"eval_accuracy": 0.5887850467289719,
|
| 698 |
+
"eval_loss": 3.0431346893310547,
|
| 699 |
+
"eval_runtime": 2.5396,
|
| 700 |
+
"eval_samples_per_second": 42.132,
|
| 701 |
+
"eval_steps_per_second": 2.756,
|
| 702 |
+
"step": 697
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 31.11,
|
| 706 |
+
"learning_rate": 8.181818181818183e-06,
|
| 707 |
+
"loss": 0.0261,
|
| 708 |
+
"step": 700
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 31.56,
|
| 712 |
+
"learning_rate": 7.727272727272727e-06,
|
| 713 |
+
"loss": 0.0174,
|
| 714 |
+
"step": 710
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 32.0,
|
| 718 |
+
"learning_rate": 7.272727272727273e-06,
|
| 719 |
+
"loss": 0.034,
|
| 720 |
+
"step": 720
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 32.0,
|
| 724 |
+
"eval_accuracy": 0.5887850467289719,
|
| 725 |
+
"eval_loss": 3.0496559143066406,
|
| 726 |
+
"eval_runtime": 2.4746,
|
| 727 |
+
"eval_samples_per_second": 43.24,
|
| 728 |
+
"eval_steps_per_second": 2.829,
|
| 729 |
+
"step": 720
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 32.44,
|
| 733 |
+
"learning_rate": 6.818181818181818e-06,
|
| 734 |
+
"loss": 0.0277,
|
| 735 |
+
"step": 730
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 32.89,
|
| 739 |
+
"learning_rate": 6.363636363636364e-06,
|
| 740 |
+
"loss": 0.0039,
|
| 741 |
+
"step": 740
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 32.98,
|
| 745 |
+
"eval_accuracy": 0.5887850467289719,
|
| 746 |
+
"eval_loss": 3.0935721397399902,
|
| 747 |
+
"eval_runtime": 2.5656,
|
| 748 |
+
"eval_samples_per_second": 41.706,
|
| 749 |
+
"eval_steps_per_second": 2.728,
|
| 750 |
+
"step": 742
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 33.33,
|
| 754 |
+
"learning_rate": 5.90909090909091e-06,
|
| 755 |
+
"loss": 0.02,
|
| 756 |
+
"step": 750
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 33.78,
|
| 760 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 761 |
+
"loss": 0.0031,
|
| 762 |
+
"step": 760
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 34.0,
|
| 766 |
+
"eval_accuracy": 0.5887850467289719,
|
| 767 |
+
"eval_loss": 3.1158316135406494,
|
| 768 |
+
"eval_runtime": 2.4251,
|
| 769 |
+
"eval_samples_per_second": 44.123,
|
| 770 |
+
"eval_steps_per_second": 2.887,
|
| 771 |
+
"step": 765
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 34.22,
|
| 775 |
+
"learning_rate": 5e-06,
|
| 776 |
+
"loss": 0.0178,
|
| 777 |
+
"step": 770
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 34.67,
|
| 781 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 782 |
+
"loss": 0.0118,
|
| 783 |
+
"step": 780
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 34.98,
|
| 787 |
+
"eval_accuracy": 0.5887850467289719,
|
| 788 |
+
"eval_loss": 3.109339714050293,
|
| 789 |
+
"eval_runtime": 2.5796,
|
| 790 |
+
"eval_samples_per_second": 41.479,
|
| 791 |
+
"eval_steps_per_second": 2.714,
|
| 792 |
+
"step": 787
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 35.11,
|
| 796 |
+
"learning_rate": 4.0909090909090915e-06,
|
| 797 |
+
"loss": 0.0061,
|
| 798 |
+
"step": 790
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 35.56,
|
| 802 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 803 |
+
"loss": 0.018,
|
| 804 |
+
"step": 800
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 36.0,
|
| 808 |
+
"learning_rate": 3.181818181818182e-06,
|
| 809 |
+
"loss": 0.0045,
|
| 810 |
+
"step": 810
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 36.0,
|
| 814 |
+
"eval_accuracy": 0.5887850467289719,
|
| 815 |
+
"eval_loss": 3.088502883911133,
|
| 816 |
+
"eval_runtime": 2.4691,
|
| 817 |
+
"eval_samples_per_second": 43.336,
|
| 818 |
+
"eval_steps_per_second": 2.835,
|
| 819 |
+
"step": 810
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 36.44,
|
| 823 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 824 |
+
"loss": 0.0224,
|
| 825 |
+
"step": 820
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 36.89,
|
| 829 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 830 |
+
"loss": 0.0168,
|
| 831 |
+
"step": 830
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 36.98,
|
| 835 |
+
"eval_accuracy": 0.5887850467289719,
|
| 836 |
+
"eval_loss": 3.0813817977905273,
|
| 837 |
+
"eval_runtime": 2.46,
|
| 838 |
+
"eval_samples_per_second": 43.495,
|
| 839 |
+
"eval_steps_per_second": 2.845,
|
| 840 |
+
"step": 832
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 37.33,
|
| 844 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 845 |
+
"loss": 0.0106,
|
| 846 |
+
"step": 840
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 37.78,
|
| 850 |
+
"learning_rate": 1.3636363636363636e-06,
|
| 851 |
+
"loss": 0.0071,
|
| 852 |
+
"step": 850
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 38.0,
|
| 856 |
+
"eval_accuracy": 0.5887850467289719,
|
| 857 |
+
"eval_loss": 3.073270320892334,
|
| 858 |
+
"eval_runtime": 2.8765,
|
| 859 |
+
"eval_samples_per_second": 37.198,
|
| 860 |
+
"eval_steps_per_second": 2.433,
|
| 861 |
+
"step": 855
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 38.22,
|
| 865 |
+
"learning_rate": 9.090909090909091e-07,
|
| 866 |
+
"loss": 0.0123,
|
| 867 |
+
"step": 860
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 38.67,
|
| 871 |
+
"learning_rate": 4.5454545454545457e-07,
|
| 872 |
+
"loss": 0.0238,
|
| 873 |
+
"step": 870
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 38.98,
|
| 877 |
+
"eval_accuracy": 0.5887850467289719,
|
| 878 |
+
"eval_loss": 3.0825016498565674,
|
| 879 |
+
"eval_runtime": 2.6096,
|
| 880 |
+
"eval_samples_per_second": 41.002,
|
| 881 |
+
"eval_steps_per_second": 2.682,
|
| 882 |
+
"step": 877
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 39.11,
|
| 886 |
+
"learning_rate": 0.0,
|
| 887 |
+
"loss": 0.0072,
|
| 888 |
+
"step": 880
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 39.11,
|
| 892 |
+
"eval_accuracy": 0.5887850467289719,
|
| 893 |
+
"eval_loss": 3.082833766937256,
|
| 894 |
+
"eval_runtime": 2.596,
|
| 895 |
+
"eval_samples_per_second": 41.217,
|
| 896 |
+
"eval_steps_per_second": 2.696,
|
| 897 |
+
"step": 880
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 39.11,
|
| 901 |
+
"step": 880,
|
| 902 |
+
"total_flos": 1.8272580263466762e+18,
|
| 903 |
+
"train_loss": 0.10380522197493437,
|
| 904 |
+
"train_runtime": 1214.1801,
|
| 905 |
+
"train_samples_per_second": 47.308,
|
| 906 |
+
"train_steps_per_second": 0.725
|
| 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": 1.8272580263466762e+18,
|
| 915 |
+
"train_batch_size": 16,
|
| 916 |
+
"trial_name": null,
|
| 917 |
+
"trial_params": null
|
| 918 |
+
}
|