End of training
Browse files- README.md +3 -3
- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Jul02_11-55-52_e9b91cbda493/events.out.tfevents.1719924194.e9b91cbda493.288.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +1333 -38
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/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.7663551401869159
|
| 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/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.8360
|
| 36 |
+
- Accuracy: 0.7664
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss":
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 93.33333333333333,
|
| 3 |
+
"eval_accuracy": 0.7663551401869159,
|
| 4 |
+
"eval_loss": 0.835954487323761,
|
| 5 |
+
"eval_runtime": 0.8722,
|
| 6 |
+
"eval_samples_per_second": 122.671,
|
| 7 |
+
"eval_steps_per_second": 4.586,
|
| 8 |
+
"total_flos": 2.226634183539118e+18,
|
| 9 |
+
"train_loss": 1.0035276814869472,
|
| 10 |
+
"train_runtime": 1522.5733,
|
| 11 |
+
"train_samples_per_second": 62.92,
|
| 12 |
+
"train_steps_per_second": 0.46
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 93.33333333333333,
|
| 3 |
+
"eval_accuracy": 0.7663551401869159,
|
| 4 |
+
"eval_loss": 0.835954487323761,
|
| 5 |
+
"eval_runtime": 0.8722,
|
| 6 |
+
"eval_samples_per_second": 122.671,
|
| 7 |
+
"eval_steps_per_second": 4.586
|
| 8 |
}
|
runs/Jul02_11-55-52_e9b91cbda493/events.out.tfevents.1719924194.e9b91cbda493.288.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f89d775f5e2a0f9770a1d47711a63816392f06a219da08548207096d225ee23
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 93.33333333333333,
|
| 3 |
+
"total_flos": 2.226634183539118e+18,
|
| 4 |
+
"train_loss": 1.0035276814869472,
|
| 5 |
+
"train_runtime": 1522.5733,
|
| 6 |
+
"train_samples_per_second": 62.92,
|
| 7 |
+
"train_steps_per_second": 0.46
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,68 +1,1363 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.9333333333333333,
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss": 3.
|
| 15 |
-
"eval_runtime": 0.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second":
|
| 18 |
"step": 7
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.3333333333333333,
|
| 22 |
-
"grad_norm": 4.
|
| 23 |
-
"learning_rate":
|
| 24 |
-
"loss":
|
| 25 |
"step": 10
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"epoch": 2.0,
|
| 29 |
-
"eval_accuracy": 0.
|
| 30 |
-
"eval_loss": 3.
|
| 31 |
-
"eval_runtime": 0.
|
| 32 |
-
"eval_samples_per_second":
|
| 33 |
-
"eval_steps_per_second": 6.
|
| 34 |
"step": 15
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 2.6666666666666665,
|
| 38 |
-
"grad_norm": 4.
|
| 39 |
-
"learning_rate":
|
| 40 |
-
"loss": 3.
|
| 41 |
"step": 20
|
| 42 |
},
|
| 43 |
{
|
| 44 |
-
"epoch": 2.
|
| 45 |
"eval_accuracy": 0.07476635514018691,
|
| 46 |
-
"eval_loss": 3.
|
| 47 |
-
"eval_runtime": 0.
|
| 48 |
-
"eval_samples_per_second":
|
| 49 |
-
"eval_steps_per_second": 6.
|
| 50 |
-
"step":
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
|
| 59 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
}
|
| 61 |
],
|
| 62 |
"logging_steps": 10,
|
| 63 |
-
"max_steps":
|
| 64 |
"num_input_tokens_seen": 0,
|
| 65 |
-
"num_train_epochs":
|
| 66 |
"save_steps": 500,
|
| 67 |
"stateful_callbacks": {
|
| 68 |
"TrainerControl": {
|
|
@@ -76,7 +1371,7 @@
|
|
| 76 |
"attributes": {}
|
| 77 |
}
|
| 78 |
},
|
| 79 |
-
"total_flos":
|
| 80 |
"train_batch_size": 32,
|
| 81 |
"trial_name": null,
|
| 82 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7663551401869159,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-435",
|
| 4 |
+
"epoch": 93.33333333333333,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.9333333333333333,
|
| 13 |
+
"eval_accuracy": 0.08411214953271028,
|
| 14 |
+
"eval_loss": 3.889423370361328,
|
| 15 |
+
"eval_runtime": 0.6153,
|
| 16 |
+
"eval_samples_per_second": 173.891,
|
| 17 |
+
"eval_steps_per_second": 6.501,
|
| 18 |
"step": 7
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.3333333333333333,
|
| 22 |
+
"grad_norm": 4.184154033660889,
|
| 23 |
+
"learning_rate": 7.142857142857143e-06,
|
| 24 |
+
"loss": 3.897,
|
| 25 |
"step": 10
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"epoch": 2.0,
|
| 29 |
+
"eval_accuracy": 0.08411214953271028,
|
| 30 |
+
"eval_loss": 3.8185415267944336,
|
| 31 |
+
"eval_runtime": 0.6194,
|
| 32 |
+
"eval_samples_per_second": 172.745,
|
| 33 |
+
"eval_steps_per_second": 6.458,
|
| 34 |
"step": 15
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 2.6666666666666665,
|
| 38 |
+
"grad_norm": 4.875367164611816,
|
| 39 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 40 |
+
"loss": 3.8553,
|
| 41 |
"step": 20
|
| 42 |
},
|
| 43 |
{
|
| 44 |
+
"epoch": 2.9333333333333336,
|
| 45 |
"eval_accuracy": 0.07476635514018691,
|
| 46 |
+
"eval_loss": 3.7401788234710693,
|
| 47 |
+
"eval_runtime": 0.6021,
|
| 48 |
+
"eval_samples_per_second": 177.698,
|
| 49 |
+
"eval_steps_per_second": 6.643,
|
| 50 |
+
"step": 22
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"grad_norm": 5.443772315979004,
|
| 55 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 56 |
+
"loss": 3.7568,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"eval_accuracy": 0.07476635514018691,
|
| 62 |
+
"eval_loss": 3.637192964553833,
|
| 63 |
+
"eval_runtime": 0.7262,
|
| 64 |
+
"eval_samples_per_second": 147.335,
|
| 65 |
+
"eval_steps_per_second": 5.508,
|
| 66 |
+
"step": 30
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.933333333333334,
|
| 70 |
+
"eval_accuracy": 0.08411214953271028,
|
| 71 |
+
"eval_loss": 3.5481796264648438,
|
| 72 |
+
"eval_runtime": 0.6382,
|
| 73 |
+
"eval_samples_per_second": 167.648,
|
| 74 |
+
"eval_steps_per_second": 6.267,
|
| 75 |
+
"step": 37
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.333333333333333,
|
| 79 |
+
"grad_norm": 5.656874656677246,
|
| 80 |
+
"learning_rate": 2.857142857142857e-05,
|
| 81 |
+
"loss": 3.5912,
|
| 82 |
+
"step": 40
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 6.0,
|
| 86 |
+
"eval_accuracy": 0.11214953271028037,
|
| 87 |
+
"eval_loss": 3.406933069229126,
|
| 88 |
+
"eval_runtime": 0.6307,
|
| 89 |
+
"eval_samples_per_second": 169.654,
|
| 90 |
+
"eval_steps_per_second": 6.342,
|
| 91 |
+
"step": 45
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.666666666666667,
|
| 95 |
+
"grad_norm": 6.326891899108887,
|
| 96 |
+
"learning_rate": 3.571428571428572e-05,
|
| 97 |
+
"loss": 3.4342,
|
| 98 |
+
"step": 50
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.933333333333334,
|
| 102 |
+
"eval_accuracy": 0.1308411214953271,
|
| 103 |
+
"eval_loss": 3.293895721435547,
|
| 104 |
+
"eval_runtime": 0.6244,
|
| 105 |
+
"eval_samples_per_second": 171.371,
|
| 106 |
+
"eval_steps_per_second": 6.406,
|
| 107 |
+
"step": 52
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"grad_norm": 12.78520393371582,
|
| 112 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 113 |
+
"loss": 3.2601,
|
| 114 |
+
"step": 60
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 8.0,
|
| 118 |
+
"eval_accuracy": 0.21495327102803738,
|
| 119 |
+
"eval_loss": 3.178621768951416,
|
| 120 |
+
"eval_runtime": 0.7022,
|
| 121 |
+
"eval_samples_per_second": 152.374,
|
| 122 |
+
"eval_steps_per_second": 5.696,
|
| 123 |
+
"step": 60
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 8.933333333333334,
|
| 127 |
+
"eval_accuracy": 0.2336448598130841,
|
| 128 |
+
"eval_loss": 3.032252311706543,
|
| 129 |
+
"eval_runtime": 0.6285,
|
| 130 |
+
"eval_samples_per_second": 170.255,
|
| 131 |
+
"eval_steps_per_second": 6.365,
|
| 132 |
+
"step": 67
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 9.333333333333334,
|
| 136 |
+
"grad_norm": 9.798720359802246,
|
| 137 |
+
"learning_rate": 5e-05,
|
| 138 |
+
"loss": 3.0498,
|
| 139 |
+
"step": 70
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 10.0,
|
| 143 |
+
"eval_accuracy": 0.2616822429906542,
|
| 144 |
+
"eval_loss": 2.869462728500366,
|
| 145 |
+
"eval_runtime": 0.6405,
|
| 146 |
+
"eval_samples_per_second": 167.062,
|
| 147 |
+
"eval_steps_per_second": 6.245,
|
| 148 |
+
"step": 75
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 10.666666666666666,
|
| 152 |
+
"grad_norm": 9.29806137084961,
|
| 153 |
+
"learning_rate": 4.9206349206349204e-05,
|
| 154 |
+
"loss": 2.849,
|
| 155 |
+
"step": 80
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 10.933333333333334,
|
| 159 |
+
"eval_accuracy": 0.2523364485981308,
|
| 160 |
+
"eval_loss": 2.8504700660705566,
|
| 161 |
+
"eval_runtime": 0.6315,
|
| 162 |
+
"eval_samples_per_second": 169.425,
|
| 163 |
+
"eval_steps_per_second": 6.334,
|
| 164 |
+
"step": 82
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 12.0,
|
| 168 |
+
"grad_norm": 15.086236000061035,
|
| 169 |
+
"learning_rate": 4.841269841269841e-05,
|
| 170 |
+
"loss": 2.6452,
|
| 171 |
+
"step": 90
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.0,
|
| 175 |
+
"eval_accuracy": 0.2803738317757009,
|
| 176 |
+
"eval_loss": 2.63193416595459,
|
| 177 |
+
"eval_runtime": 0.7011,
|
| 178 |
+
"eval_samples_per_second": 152.622,
|
| 179 |
+
"eval_steps_per_second": 5.706,
|
| 180 |
+
"step": 90
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 12.933333333333334,
|
| 184 |
+
"eval_accuracy": 0.32710280373831774,
|
| 185 |
+
"eval_loss": 2.465355157852173,
|
| 186 |
+
"eval_runtime": 0.6287,
|
| 187 |
+
"eval_samples_per_second": 170.194,
|
| 188 |
+
"eval_steps_per_second": 6.362,
|
| 189 |
+
"step": 97
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 13.333333333333334,
|
| 193 |
+
"grad_norm": 10.405584335327148,
|
| 194 |
+
"learning_rate": 4.761904761904762e-05,
|
| 195 |
+
"loss": 2.4123,
|
| 196 |
+
"step": 100
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 14.0,
|
| 200 |
+
"eval_accuracy": 0.3364485981308411,
|
| 201 |
+
"eval_loss": 2.399456262588501,
|
| 202 |
+
"eval_runtime": 0.6357,
|
| 203 |
+
"eval_samples_per_second": 168.322,
|
| 204 |
+
"eval_steps_per_second": 6.292,
|
| 205 |
+
"step": 105
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 14.666666666666666,
|
| 209 |
+
"grad_norm": 12.884756088256836,
|
| 210 |
+
"learning_rate": 4.682539682539683e-05,
|
| 211 |
+
"loss": 2.2561,
|
| 212 |
+
"step": 110
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 14.933333333333334,
|
| 216 |
+
"eval_accuracy": 0.40186915887850466,
|
| 217 |
+
"eval_loss": 2.258385419845581,
|
| 218 |
+
"eval_runtime": 0.6927,
|
| 219 |
+
"eval_samples_per_second": 154.461,
|
| 220 |
+
"eval_steps_per_second": 5.774,
|
| 221 |
+
"step": 112
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 16.0,
|
| 225 |
+
"grad_norm": 11.66384506225586,
|
| 226 |
+
"learning_rate": 4.603174603174603e-05,
|
| 227 |
+
"loss": 2.0447,
|
| 228 |
+
"step": 120
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 16.0,
|
| 232 |
+
"eval_accuracy": 0.42990654205607476,
|
| 233 |
+
"eval_loss": 2.1999597549438477,
|
| 234 |
+
"eval_runtime": 0.6407,
|
| 235 |
+
"eval_samples_per_second": 167.013,
|
| 236 |
+
"eval_steps_per_second": 6.243,
|
| 237 |
+
"step": 120
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 16.933333333333334,
|
| 241 |
+
"eval_accuracy": 0.4392523364485981,
|
| 242 |
+
"eval_loss": 2.080615282058716,
|
| 243 |
+
"eval_runtime": 0.6391,
|
| 244 |
+
"eval_samples_per_second": 167.427,
|
| 245 |
+
"eval_steps_per_second": 6.259,
|
| 246 |
+
"step": 127
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 17.333333333333332,
|
| 250 |
+
"grad_norm": 9.476760864257812,
|
| 251 |
+
"learning_rate": 4.523809523809524e-05,
|
| 252 |
+
"loss": 1.8569,
|
| 253 |
+
"step": 130
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 18.0,
|
| 257 |
+
"eval_accuracy": 0.4392523364485981,
|
| 258 |
+
"eval_loss": 2.0593273639678955,
|
| 259 |
+
"eval_runtime": 0.6302,
|
| 260 |
+
"eval_samples_per_second": 169.788,
|
| 261 |
+
"eval_steps_per_second": 6.347,
|
| 262 |
+
"step": 135
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 18.666666666666668,
|
| 266 |
+
"grad_norm": 11.518675804138184,
|
| 267 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 268 |
+
"loss": 1.7447,
|
| 269 |
+
"step": 140
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 18.933333333333334,
|
| 273 |
+
"eval_accuracy": 0.4672897196261682,
|
| 274 |
+
"eval_loss": 1.8832261562347412,
|
| 275 |
+
"eval_runtime": 0.7003,
|
| 276 |
+
"eval_samples_per_second": 152.783,
|
| 277 |
+
"eval_steps_per_second": 5.712,
|
| 278 |
+
"step": 142
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 20.0,
|
| 282 |
+
"grad_norm": 10.125329971313477,
|
| 283 |
+
"learning_rate": 4.3650793650793655e-05,
|
| 284 |
+
"loss": 1.5821,
|
| 285 |
+
"step": 150
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 20.0,
|
| 289 |
+
"eval_accuracy": 0.5046728971962616,
|
| 290 |
+
"eval_loss": 1.8217570781707764,
|
| 291 |
+
"eval_runtime": 0.6316,
|
| 292 |
+
"eval_samples_per_second": 169.416,
|
| 293 |
+
"eval_steps_per_second": 6.333,
|
| 294 |
+
"step": 150
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 20.933333333333334,
|
| 298 |
+
"eval_accuracy": 0.5420560747663551,
|
| 299 |
+
"eval_loss": 1.7333636283874512,
|
| 300 |
+
"eval_runtime": 0.6313,
|
| 301 |
+
"eval_samples_per_second": 169.494,
|
| 302 |
+
"eval_steps_per_second": 6.336,
|
| 303 |
+
"step": 157
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 21.333333333333332,
|
| 307 |
+
"grad_norm": 11.70013427734375,
|
| 308 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 309 |
+
"loss": 1.3999,
|
| 310 |
+
"step": 160
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 22.0,
|
| 314 |
+
"eval_accuracy": 0.5514018691588785,
|
| 315 |
+
"eval_loss": 1.6213181018829346,
|
| 316 |
+
"eval_runtime": 0.6355,
|
| 317 |
+
"eval_samples_per_second": 168.373,
|
| 318 |
+
"eval_steps_per_second": 6.294,
|
| 319 |
+
"step": 165
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 22.666666666666668,
|
| 323 |
+
"grad_norm": 9.099847793579102,
|
| 324 |
+
"learning_rate": 4.2063492063492065e-05,
|
| 325 |
+
"loss": 1.2901,
|
| 326 |
+
"step": 170
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 22.933333333333334,
|
| 330 |
+
"eval_accuracy": 0.5233644859813084,
|
| 331 |
+
"eval_loss": 1.593188762664795,
|
| 332 |
+
"eval_runtime": 0.7026,
|
| 333 |
+
"eval_samples_per_second": 152.289,
|
| 334 |
+
"eval_steps_per_second": 5.693,
|
| 335 |
+
"step": 172
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 24.0,
|
| 339 |
+
"grad_norm": 10.077893257141113,
|
| 340 |
+
"learning_rate": 4.126984126984127e-05,
|
| 341 |
+
"loss": 1.1569,
|
| 342 |
+
"step": 180
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 24.0,
|
| 346 |
+
"eval_accuracy": 0.5700934579439252,
|
| 347 |
+
"eval_loss": 1.5255681276321411,
|
| 348 |
+
"eval_runtime": 0.6286,
|
| 349 |
+
"eval_samples_per_second": 170.213,
|
| 350 |
+
"eval_steps_per_second": 6.363,
|
| 351 |
+
"step": 180
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 24.933333333333334,
|
| 355 |
+
"eval_accuracy": 0.5887850467289719,
|
| 356 |
+
"eval_loss": 1.428060531616211,
|
| 357 |
+
"eval_runtime": 0.6322,
|
| 358 |
+
"eval_samples_per_second": 169.258,
|
| 359 |
+
"eval_steps_per_second": 6.327,
|
| 360 |
+
"step": 187
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 25.333333333333332,
|
| 364 |
+
"grad_norm": 10.525726318359375,
|
| 365 |
+
"learning_rate": 4.047619047619048e-05,
|
| 366 |
+
"loss": 1.0903,
|
| 367 |
+
"step": 190
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 26.0,
|
| 371 |
+
"eval_accuracy": 0.5794392523364486,
|
| 372 |
+
"eval_loss": 1.3997470140457153,
|
| 373 |
+
"eval_runtime": 0.6928,
|
| 374 |
+
"eval_samples_per_second": 154.457,
|
| 375 |
+
"eval_steps_per_second": 5.774,
|
| 376 |
+
"step": 195
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 26.666666666666668,
|
| 380 |
+
"grad_norm": 8.83031177520752,
|
| 381 |
+
"learning_rate": 3.968253968253968e-05,
|
| 382 |
+
"loss": 0.9674,
|
| 383 |
+
"step": 200
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 26.933333333333334,
|
| 387 |
+
"eval_accuracy": 0.5887850467289719,
|
| 388 |
+
"eval_loss": 1.4017095565795898,
|
| 389 |
+
"eval_runtime": 0.634,
|
| 390 |
+
"eval_samples_per_second": 168.758,
|
| 391 |
+
"eval_steps_per_second": 6.309,
|
| 392 |
+
"step": 202
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 28.0,
|
| 396 |
+
"grad_norm": 9.685677528381348,
|
| 397 |
+
"learning_rate": 3.888888888888889e-05,
|
| 398 |
+
"loss": 0.98,
|
| 399 |
+
"step": 210
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 28.0,
|
| 403 |
+
"eval_accuracy": 0.5981308411214953,
|
| 404 |
+
"eval_loss": 1.2915815114974976,
|
| 405 |
+
"eval_runtime": 0.6453,
|
| 406 |
+
"eval_samples_per_second": 165.816,
|
| 407 |
+
"eval_steps_per_second": 6.199,
|
| 408 |
+
"step": 210
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 28.933333333333334,
|
| 412 |
+
"eval_accuracy": 0.5981308411214953,
|
| 413 |
+
"eval_loss": 1.301841378211975,
|
| 414 |
+
"eval_runtime": 0.6256,
|
| 415 |
+
"eval_samples_per_second": 171.047,
|
| 416 |
+
"eval_steps_per_second": 6.394,
|
| 417 |
+
"step": 217
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 29.333333333333332,
|
| 421 |
+
"grad_norm": 11.74543285369873,
|
| 422 |
+
"learning_rate": 3.809523809523809e-05,
|
| 423 |
+
"loss": 0.8772,
|
| 424 |
+
"step": 220
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 30.0,
|
| 428 |
+
"eval_accuracy": 0.6355140186915887,
|
| 429 |
+
"eval_loss": 1.2552070617675781,
|
| 430 |
+
"eval_runtime": 0.6964,
|
| 431 |
+
"eval_samples_per_second": 153.648,
|
| 432 |
+
"eval_steps_per_second": 5.744,
|
| 433 |
+
"step": 225
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 30.666666666666668,
|
| 437 |
+
"grad_norm": 11.836760520935059,
|
| 438 |
+
"learning_rate": 3.730158730158731e-05,
|
| 439 |
+
"loss": 0.7842,
|
| 440 |
+
"step": 230
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 30.933333333333334,
|
| 444 |
+
"eval_accuracy": 0.6074766355140186,
|
| 445 |
+
"eval_loss": 1.2371814250946045,
|
| 446 |
+
"eval_runtime": 0.6411,
|
| 447 |
+
"eval_samples_per_second": 166.89,
|
| 448 |
+
"eval_steps_per_second": 6.239,
|
| 449 |
+
"step": 232
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 32.0,
|
| 453 |
+
"grad_norm": 8.279513359069824,
|
| 454 |
+
"learning_rate": 3.650793650793651e-05,
|
| 455 |
+
"loss": 0.7438,
|
| 456 |
+
"step": 240
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 32.0,
|
| 460 |
+
"eval_accuracy": 0.616822429906542,
|
| 461 |
+
"eval_loss": 1.1908384561538696,
|
| 462 |
+
"eval_runtime": 0.636,
|
| 463 |
+
"eval_samples_per_second": 168.249,
|
| 464 |
+
"eval_steps_per_second": 6.29,
|
| 465 |
+
"step": 240
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 32.93333333333333,
|
| 469 |
+
"eval_accuracy": 0.6635514018691588,
|
| 470 |
+
"eval_loss": 1.1566777229309082,
|
| 471 |
+
"eval_runtime": 0.6312,
|
| 472 |
+
"eval_samples_per_second": 169.507,
|
| 473 |
+
"eval_steps_per_second": 6.337,
|
| 474 |
+
"step": 247
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 33.333333333333336,
|
| 478 |
+
"grad_norm": 8.077630996704102,
|
| 479 |
+
"learning_rate": 3.571428571428572e-05,
|
| 480 |
+
"loss": 0.725,
|
| 481 |
+
"step": 250
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 34.0,
|
| 485 |
+
"eval_accuracy": 0.6261682242990654,
|
| 486 |
+
"eval_loss": 1.1541680097579956,
|
| 487 |
+
"eval_runtime": 0.6806,
|
| 488 |
+
"eval_samples_per_second": 157.204,
|
| 489 |
+
"eval_steps_per_second": 5.877,
|
| 490 |
+
"step": 255
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 34.666666666666664,
|
| 494 |
+
"grad_norm": 10.355536460876465,
|
| 495 |
+
"learning_rate": 3.492063492063492e-05,
|
| 496 |
+
"loss": 0.6709,
|
| 497 |
+
"step": 260
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 34.93333333333333,
|
| 501 |
+
"eval_accuracy": 0.6261682242990654,
|
| 502 |
+
"eval_loss": 1.137677550315857,
|
| 503 |
+
"eval_runtime": 0.6265,
|
| 504 |
+
"eval_samples_per_second": 170.787,
|
| 505 |
+
"eval_steps_per_second": 6.385,
|
| 506 |
+
"step": 262
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 36.0,
|
| 510 |
+
"grad_norm": 7.819301128387451,
|
| 511 |
+
"learning_rate": 3.412698412698413e-05,
|
| 512 |
+
"loss": 0.6898,
|
| 513 |
+
"step": 270
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 36.0,
|
| 517 |
+
"eval_accuracy": 0.6635514018691588,
|
| 518 |
+
"eval_loss": 1.0523799657821655,
|
| 519 |
+
"eval_runtime": 0.6376,
|
| 520 |
+
"eval_samples_per_second": 167.806,
|
| 521 |
+
"eval_steps_per_second": 6.273,
|
| 522 |
+
"step": 270
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 36.93333333333333,
|
| 526 |
+
"eval_accuracy": 0.6728971962616822,
|
| 527 |
+
"eval_loss": 1.027221441268921,
|
| 528 |
+
"eval_runtime": 0.6345,
|
| 529 |
+
"eval_samples_per_second": 168.642,
|
| 530 |
+
"eval_steps_per_second": 6.304,
|
| 531 |
+
"step": 277
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 37.333333333333336,
|
| 535 |
+
"grad_norm": 12.395262718200684,
|
| 536 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 537 |
+
"loss": 0.6125,
|
| 538 |
+
"step": 280
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 38.0,
|
| 542 |
+
"eval_accuracy": 0.6355140186915887,
|
| 543 |
+
"eval_loss": 1.0398948192596436,
|
| 544 |
+
"eval_runtime": 0.6985,
|
| 545 |
+
"eval_samples_per_second": 153.19,
|
| 546 |
+
"eval_steps_per_second": 5.727,
|
| 547 |
+
"step": 285
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 38.666666666666664,
|
| 551 |
+
"grad_norm": 8.95246410369873,
|
| 552 |
+
"learning_rate": 3.253968253968254e-05,
|
| 553 |
+
"loss": 0.6153,
|
| 554 |
+
"step": 290
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 38.93333333333333,
|
| 558 |
+
"eval_accuracy": 0.6822429906542056,
|
| 559 |
+
"eval_loss": 1.0307663679122925,
|
| 560 |
+
"eval_runtime": 0.6229,
|
| 561 |
+
"eval_samples_per_second": 171.769,
|
| 562 |
+
"eval_steps_per_second": 6.421,
|
| 563 |
+
"step": 292
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 40.0,
|
| 567 |
+
"grad_norm": 10.705389022827148,
|
| 568 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 569 |
+
"loss": 0.5898,
|
| 570 |
+
"step": 300
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 40.0,
|
| 574 |
+
"eval_accuracy": 0.7009345794392523,
|
| 575 |
+
"eval_loss": 1.0150656700134277,
|
| 576 |
+
"eval_runtime": 0.6404,
|
| 577 |
+
"eval_samples_per_second": 167.072,
|
| 578 |
+
"eval_steps_per_second": 6.246,
|
| 579 |
+
"step": 300
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 40.93333333333333,
|
| 583 |
+
"eval_accuracy": 0.6542056074766355,
|
| 584 |
+
"eval_loss": 1.0482978820800781,
|
| 585 |
+
"eval_runtime": 0.696,
|
| 586 |
+
"eval_samples_per_second": 153.738,
|
| 587 |
+
"eval_steps_per_second": 5.747,
|
| 588 |
+
"step": 307
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 41.333333333333336,
|
| 592 |
+
"grad_norm": 9.051219940185547,
|
| 593 |
+
"learning_rate": 3.095238095238095e-05,
|
| 594 |
+
"loss": 0.5881,
|
| 595 |
+
"step": 310
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 42.0,
|
| 599 |
+
"eval_accuracy": 0.7009345794392523,
|
| 600 |
+
"eval_loss": 0.992605984210968,
|
| 601 |
+
"eval_runtime": 0.6887,
|
| 602 |
+
"eval_samples_per_second": 155.368,
|
| 603 |
+
"eval_steps_per_second": 5.808,
|
| 604 |
+
"step": 315
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 42.666666666666664,
|
| 608 |
+
"grad_norm": 8.400652885437012,
|
| 609 |
+
"learning_rate": 3.0158730158730158e-05,
|
| 610 |
+
"loss": 0.54,
|
| 611 |
+
"step": 320
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 42.93333333333333,
|
| 615 |
+
"eval_accuracy": 0.6915887850467289,
|
| 616 |
+
"eval_loss": 1.0300043821334839,
|
| 617 |
+
"eval_runtime": 0.6255,
|
| 618 |
+
"eval_samples_per_second": 171.052,
|
| 619 |
+
"eval_steps_per_second": 6.394,
|
| 620 |
+
"step": 322
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 44.0,
|
| 624 |
+
"grad_norm": 10.61039924621582,
|
| 625 |
+
"learning_rate": 2.9365079365079366e-05,
|
| 626 |
+
"loss": 0.4515,
|
| 627 |
+
"step": 330
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 44.0,
|
| 631 |
+
"eval_accuracy": 0.7383177570093458,
|
| 632 |
+
"eval_loss": 0.926239013671875,
|
| 633 |
+
"eval_runtime": 0.689,
|
| 634 |
+
"eval_samples_per_second": 155.308,
|
| 635 |
+
"eval_steps_per_second": 5.806,
|
| 636 |
+
"step": 330
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 44.93333333333333,
|
| 640 |
+
"eval_accuracy": 0.7289719626168224,
|
| 641 |
+
"eval_loss": 0.9486252069473267,
|
| 642 |
+
"eval_runtime": 0.6286,
|
| 643 |
+
"eval_samples_per_second": 170.217,
|
| 644 |
+
"eval_steps_per_second": 6.363,
|
| 645 |
+
"step": 337
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 45.333333333333336,
|
| 649 |
+
"grad_norm": 11.857452392578125,
|
| 650 |
+
"learning_rate": 2.857142857142857e-05,
|
| 651 |
+
"loss": 0.5057,
|
| 652 |
+
"step": 340
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 46.0,
|
| 656 |
+
"eval_accuracy": 0.7102803738317757,
|
| 657 |
+
"eval_loss": 0.9219488501548767,
|
| 658 |
+
"eval_runtime": 0.6365,
|
| 659 |
+
"eval_samples_per_second": 168.094,
|
| 660 |
+
"eval_steps_per_second": 6.284,
|
| 661 |
+
"step": 345
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 46.666666666666664,
|
| 665 |
+
"grad_norm": 8.10464096069336,
|
| 666 |
+
"learning_rate": 2.777777777777778e-05,
|
| 667 |
+
"loss": 0.4905,
|
| 668 |
+
"step": 350
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 46.93333333333333,
|
| 672 |
+
"eval_accuracy": 0.6822429906542056,
|
| 673 |
+
"eval_loss": 1.0184197425842285,
|
| 674 |
+
"eval_runtime": 0.6292,
|
| 675 |
+
"eval_samples_per_second": 170.066,
|
| 676 |
+
"eval_steps_per_second": 6.358,
|
| 677 |
+
"step": 352
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 48.0,
|
| 681 |
+
"grad_norm": 9.08785629272461,
|
| 682 |
+
"learning_rate": 2.6984126984126984e-05,
|
| 683 |
+
"loss": 0.4669,
|
| 684 |
+
"step": 360
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 48.0,
|
| 688 |
+
"eval_accuracy": 0.7289719626168224,
|
| 689 |
+
"eval_loss": 0.9337471127510071,
|
| 690 |
+
"eval_runtime": 0.6967,
|
| 691 |
+
"eval_samples_per_second": 153.592,
|
| 692 |
+
"eval_steps_per_second": 5.742,
|
| 693 |
+
"step": 360
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 48.93333333333333,
|
| 697 |
+
"eval_accuracy": 0.7102803738317757,
|
| 698 |
+
"eval_loss": 0.9431414604187012,
|
| 699 |
+
"eval_runtime": 0.6378,
|
| 700 |
+
"eval_samples_per_second": 167.775,
|
| 701 |
+
"eval_steps_per_second": 6.272,
|
| 702 |
+
"step": 367
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 49.333333333333336,
|
| 706 |
+
"grad_norm": 8.805204391479492,
|
| 707 |
+
"learning_rate": 2.6190476190476192e-05,
|
| 708 |
+
"loss": 0.4437,
|
| 709 |
+
"step": 370
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 50.0,
|
| 713 |
+
"eval_accuracy": 0.7009345794392523,
|
| 714 |
+
"eval_loss": 0.9311835169792175,
|
| 715 |
+
"eval_runtime": 0.6277,
|
| 716 |
+
"eval_samples_per_second": 170.465,
|
| 717 |
+
"eval_steps_per_second": 6.373,
|
| 718 |
+
"step": 375
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 50.666666666666664,
|
| 722 |
+
"grad_norm": 7.111200332641602,
|
| 723 |
+
"learning_rate": 2.5396825396825397e-05,
|
| 724 |
+
"loss": 0.4754,
|
| 725 |
+
"step": 380
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 50.93333333333333,
|
| 729 |
+
"eval_accuracy": 0.719626168224299,
|
| 730 |
+
"eval_loss": 0.9244596362113953,
|
| 731 |
+
"eval_runtime": 0.6252,
|
| 732 |
+
"eval_samples_per_second": 171.138,
|
| 733 |
+
"eval_steps_per_second": 6.398,
|
| 734 |
+
"step": 382
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 52.0,
|
| 738 |
+
"grad_norm": 7.307917594909668,
|
| 739 |
+
"learning_rate": 2.4603174603174602e-05,
|
| 740 |
+
"loss": 0.4119,
|
| 741 |
+
"step": 390
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 52.0,
|
| 745 |
+
"eval_accuracy": 0.7383177570093458,
|
| 746 |
+
"eval_loss": 0.8826178908348083,
|
| 747 |
+
"eval_runtime": 0.6908,
|
| 748 |
+
"eval_samples_per_second": 154.896,
|
| 749 |
+
"eval_steps_per_second": 5.79,
|
| 750 |
+
"step": 390
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 52.93333333333333,
|
| 754 |
+
"eval_accuracy": 0.719626168224299,
|
| 755 |
+
"eval_loss": 0.9261904358863831,
|
| 756 |
+
"eval_runtime": 0.6228,
|
| 757 |
+
"eval_samples_per_second": 171.799,
|
| 758 |
+
"eval_steps_per_second": 6.422,
|
| 759 |
+
"step": 397
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 53.333333333333336,
|
| 763 |
+
"grad_norm": 8.19266128540039,
|
| 764 |
+
"learning_rate": 2.380952380952381e-05,
|
| 765 |
+
"loss": 0.4087,
|
| 766 |
+
"step": 400
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 54.0,
|
| 770 |
+
"eval_accuracy": 0.7476635514018691,
|
| 771 |
+
"eval_loss": 0.888160765171051,
|
| 772 |
+
"eval_runtime": 0.6231,
|
| 773 |
+
"eval_samples_per_second": 171.734,
|
| 774 |
+
"eval_steps_per_second": 6.42,
|
| 775 |
+
"step": 405
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 54.666666666666664,
|
| 779 |
+
"grad_norm": 7.831826210021973,
|
| 780 |
+
"learning_rate": 2.3015873015873015e-05,
|
| 781 |
+
"loss": 0.3987,
|
| 782 |
+
"step": 410
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 54.93333333333333,
|
| 786 |
+
"eval_accuracy": 0.7289719626168224,
|
| 787 |
+
"eval_loss": 0.9281949400901794,
|
| 788 |
+
"eval_runtime": 0.63,
|
| 789 |
+
"eval_samples_per_second": 169.85,
|
| 790 |
+
"eval_steps_per_second": 6.35,
|
| 791 |
+
"step": 412
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 56.0,
|
| 795 |
+
"grad_norm": 8.277617454528809,
|
| 796 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 797 |
+
"loss": 0.4253,
|
| 798 |
+
"step": 420
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 56.0,
|
| 802 |
+
"eval_accuracy": 0.7476635514018691,
|
| 803 |
+
"eval_loss": 0.9003600478172302,
|
| 804 |
+
"eval_runtime": 0.738,
|
| 805 |
+
"eval_samples_per_second": 144.99,
|
| 806 |
+
"eval_steps_per_second": 5.42,
|
| 807 |
+
"step": 420
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 56.93333333333333,
|
| 811 |
+
"eval_accuracy": 0.7476635514018691,
|
| 812 |
+
"eval_loss": 0.8783094882965088,
|
| 813 |
+
"eval_runtime": 0.6305,
|
| 814 |
+
"eval_samples_per_second": 169.701,
|
| 815 |
+
"eval_steps_per_second": 6.344,
|
| 816 |
+
"step": 427
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 57.333333333333336,
|
| 820 |
+
"grad_norm": 7.786144256591797,
|
| 821 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 822 |
+
"loss": 0.4134,
|
| 823 |
+
"step": 430
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 58.0,
|
| 827 |
+
"eval_accuracy": 0.7663551401869159,
|
| 828 |
+
"eval_loss": 0.835954487323761,
|
| 829 |
+
"eval_runtime": 0.6311,
|
| 830 |
+
"eval_samples_per_second": 169.557,
|
| 831 |
+
"eval_steps_per_second": 6.339,
|
| 832 |
+
"step": 435
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 58.666666666666664,
|
| 836 |
+
"grad_norm": 8.696057319641113,
|
| 837 |
+
"learning_rate": 2.0634920634920636e-05,
|
| 838 |
+
"loss": 0.4024,
|
| 839 |
+
"step": 440
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 58.93333333333333,
|
| 843 |
+
"eval_accuracy": 0.719626168224299,
|
| 844 |
+
"eval_loss": 0.901554524898529,
|
| 845 |
+
"eval_runtime": 0.6321,
|
| 846 |
+
"eval_samples_per_second": 169.266,
|
| 847 |
+
"eval_steps_per_second": 6.328,
|
| 848 |
+
"step": 442
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 60.0,
|
| 852 |
+
"grad_norm": 7.4623284339904785,
|
| 853 |
+
"learning_rate": 1.984126984126984e-05,
|
| 854 |
+
"loss": 0.3688,
|
| 855 |
+
"step": 450
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 60.0,
|
| 859 |
+
"eval_accuracy": 0.6822429906542056,
|
| 860 |
+
"eval_loss": 0.9250590205192566,
|
| 861 |
+
"eval_runtime": 0.7012,
|
| 862 |
+
"eval_samples_per_second": 152.597,
|
| 863 |
+
"eval_steps_per_second": 5.705,
|
| 864 |
+
"step": 450
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 60.93333333333333,
|
| 868 |
+
"eval_accuracy": 0.7102803738317757,
|
| 869 |
+
"eval_loss": 0.9085938930511475,
|
| 870 |
+
"eval_runtime": 0.6226,
|
| 871 |
+
"eval_samples_per_second": 171.866,
|
| 872 |
+
"eval_steps_per_second": 6.425,
|
| 873 |
+
"step": 457
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 61.333333333333336,
|
| 877 |
+
"grad_norm": 8.650228500366211,
|
| 878 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 879 |
+
"loss": 0.3833,
|
| 880 |
+
"step": 460
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 62.0,
|
| 884 |
+
"eval_accuracy": 0.7383177570093458,
|
| 885 |
+
"eval_loss": 0.8493680953979492,
|
| 886 |
+
"eval_runtime": 0.6222,
|
| 887 |
+
"eval_samples_per_second": 171.977,
|
| 888 |
+
"eval_steps_per_second": 6.429,
|
| 889 |
+
"step": 465
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 62.666666666666664,
|
| 893 |
+
"grad_norm": 9.089720726013184,
|
| 894 |
+
"learning_rate": 1.8253968253968254e-05,
|
| 895 |
+
"loss": 0.3614,
|
| 896 |
+
"step": 470
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 62.93333333333333,
|
| 900 |
+
"eval_accuracy": 0.7289719626168224,
|
| 901 |
+
"eval_loss": 0.8298574686050415,
|
| 902 |
+
"eval_runtime": 0.6823,
|
| 903 |
+
"eval_samples_per_second": 156.816,
|
| 904 |
+
"eval_steps_per_second": 5.862,
|
| 905 |
+
"step": 472
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 64.0,
|
| 909 |
+
"grad_norm": 9.999822616577148,
|
| 910 |
+
"learning_rate": 1.746031746031746e-05,
|
| 911 |
+
"loss": 0.3792,
|
| 912 |
+
"step": 480
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 64.0,
|
| 916 |
+
"eval_accuracy": 0.7383177570093458,
|
| 917 |
+
"eval_loss": 0.9015009999275208,
|
| 918 |
+
"eval_runtime": 0.647,
|
| 919 |
+
"eval_samples_per_second": 165.386,
|
| 920 |
+
"eval_steps_per_second": 6.183,
|
| 921 |
+
"step": 480
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 64.93333333333334,
|
| 925 |
+
"eval_accuracy": 0.719626168224299,
|
| 926 |
+
"eval_loss": 0.8801712989807129,
|
| 927 |
+
"eval_runtime": 0.6283,
|
| 928 |
+
"eval_samples_per_second": 170.303,
|
| 929 |
+
"eval_steps_per_second": 6.366,
|
| 930 |
+
"step": 487
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 65.33333333333333,
|
| 934 |
+
"grad_norm": 7.207292556762695,
|
| 935 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 936 |
+
"loss": 0.3632,
|
| 937 |
+
"step": 490
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 66.0,
|
| 941 |
+
"eval_accuracy": 0.7009345794392523,
|
| 942 |
+
"eval_loss": 0.8881424069404602,
|
| 943 |
+
"eval_runtime": 0.6298,
|
| 944 |
+
"eval_samples_per_second": 169.883,
|
| 945 |
+
"eval_steps_per_second": 6.351,
|
| 946 |
+
"step": 495
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 66.66666666666667,
|
| 950 |
+
"grad_norm": 9.152532577514648,
|
| 951 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 952 |
+
"loss": 0.3405,
|
| 953 |
+
"step": 500
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 66.93333333333334,
|
| 957 |
+
"eval_accuracy": 0.7383177570093458,
|
| 958 |
+
"eval_loss": 0.857825517654419,
|
| 959 |
+
"eval_runtime": 0.7094,
|
| 960 |
+
"eval_samples_per_second": 150.84,
|
| 961 |
+
"eval_steps_per_second": 5.639,
|
| 962 |
+
"step": 502
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 68.0,
|
| 966 |
+
"grad_norm": 6.808733940124512,
|
| 967 |
+
"learning_rate": 1.5079365079365079e-05,
|
| 968 |
+
"loss": 0.3673,
|
| 969 |
+
"step": 510
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 68.0,
|
| 973 |
+
"eval_accuracy": 0.7570093457943925,
|
| 974 |
+
"eval_loss": 0.8540030717849731,
|
| 975 |
+
"eval_runtime": 0.6324,
|
| 976 |
+
"eval_samples_per_second": 169.206,
|
| 977 |
+
"eval_steps_per_second": 6.325,
|
| 978 |
+
"step": 510
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 68.93333333333334,
|
| 982 |
+
"eval_accuracy": 0.7383177570093458,
|
| 983 |
+
"eval_loss": 0.834481954574585,
|
| 984 |
+
"eval_runtime": 0.6329,
|
| 985 |
+
"eval_samples_per_second": 169.057,
|
| 986 |
+
"eval_steps_per_second": 6.32,
|
| 987 |
+
"step": 517
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 69.33333333333333,
|
| 991 |
+
"grad_norm": 7.036710262298584,
|
| 992 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 993 |
+
"loss": 0.3379,
|
| 994 |
+
"step": 520
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 70.0,
|
| 998 |
+
"eval_accuracy": 0.7383177570093458,
|
| 999 |
+
"eval_loss": 0.7918941974639893,
|
| 1000 |
+
"eval_runtime": 0.6863,
|
| 1001 |
+
"eval_samples_per_second": 155.912,
|
| 1002 |
+
"eval_steps_per_second": 5.828,
|
| 1003 |
+
"step": 525
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 70.66666666666667,
|
| 1007 |
+
"grad_norm": 8.039285659790039,
|
| 1008 |
+
"learning_rate": 1.3492063492063492e-05,
|
| 1009 |
+
"loss": 0.3389,
|
| 1010 |
+
"step": 530
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 70.93333333333334,
|
| 1014 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1015 |
+
"eval_loss": 0.8383651375770569,
|
| 1016 |
+
"eval_runtime": 0.6238,
|
| 1017 |
+
"eval_samples_per_second": 171.538,
|
| 1018 |
+
"eval_steps_per_second": 6.413,
|
| 1019 |
+
"step": 532
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 72.0,
|
| 1023 |
+
"grad_norm": 8.855910301208496,
|
| 1024 |
+
"learning_rate": 1.2698412698412699e-05,
|
| 1025 |
+
"loss": 0.3363,
|
| 1026 |
+
"step": 540
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 72.0,
|
| 1030 |
+
"eval_accuracy": 0.7383177570093458,
|
| 1031 |
+
"eval_loss": 0.8305981159210205,
|
| 1032 |
+
"eval_runtime": 0.6209,
|
| 1033 |
+
"eval_samples_per_second": 172.332,
|
| 1034 |
+
"eval_steps_per_second": 6.442,
|
| 1035 |
+
"step": 540
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 72.93333333333334,
|
| 1039 |
+
"eval_accuracy": 0.7476635514018691,
|
| 1040 |
+
"eval_loss": 0.8875143527984619,
|
| 1041 |
+
"eval_runtime": 0.6229,
|
| 1042 |
+
"eval_samples_per_second": 171.771,
|
| 1043 |
+
"eval_steps_per_second": 6.421,
|
| 1044 |
+
"step": 547
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 73.33333333333333,
|
| 1048 |
+
"grad_norm": 8.251914978027344,
|
| 1049 |
+
"learning_rate": 1.1904761904761905e-05,
|
| 1050 |
+
"loss": 0.3494,
|
| 1051 |
+
"step": 550
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 74.0,
|
| 1055 |
+
"eval_accuracy": 0.7009345794392523,
|
| 1056 |
+
"eval_loss": 0.9151278138160706,
|
| 1057 |
+
"eval_runtime": 0.6911,
|
| 1058 |
+
"eval_samples_per_second": 154.833,
|
| 1059 |
+
"eval_steps_per_second": 5.788,
|
| 1060 |
+
"step": 555
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 74.66666666666667,
|
| 1064 |
+
"grad_norm": 6.429625988006592,
|
| 1065 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 1066 |
+
"loss": 0.2989,
|
| 1067 |
+
"step": 560
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 74.93333333333334,
|
| 1071 |
+
"eval_accuracy": 0.7102803738317757,
|
| 1072 |
+
"eval_loss": 0.8605906963348389,
|
| 1073 |
+
"eval_runtime": 0.6304,
|
| 1074 |
+
"eval_samples_per_second": 169.733,
|
| 1075 |
+
"eval_steps_per_second": 6.345,
|
| 1076 |
+
"step": 562
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 76.0,
|
| 1080 |
+
"grad_norm": 26.255657196044922,
|
| 1081 |
+
"learning_rate": 1.0317460317460318e-05,
|
| 1082 |
+
"loss": 0.3157,
|
| 1083 |
+
"step": 570
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 76.0,
|
| 1087 |
+
"eval_accuracy": 0.7383177570093458,
|
| 1088 |
+
"eval_loss": 0.8639878630638123,
|
| 1089 |
+
"eval_runtime": 0.6362,
|
| 1090 |
+
"eval_samples_per_second": 168.197,
|
| 1091 |
+
"eval_steps_per_second": 6.288,
|
| 1092 |
+
"step": 570
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 76.93333333333334,
|
| 1096 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1097 |
+
"eval_loss": 0.8531526327133179,
|
| 1098 |
+
"eval_runtime": 0.6397,
|
| 1099 |
+
"eval_samples_per_second": 167.268,
|
| 1100 |
+
"eval_steps_per_second": 6.253,
|
| 1101 |
+
"step": 577
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 77.33333333333333,
|
| 1105 |
+
"grad_norm": 7.6963958740234375,
|
| 1106 |
+
"learning_rate": 9.523809523809523e-06,
|
| 1107 |
+
"loss": 0.3013,
|
| 1108 |
+
"step": 580
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 78.0,
|
| 1112 |
+
"eval_accuracy": 0.7102803738317757,
|
| 1113 |
+
"eval_loss": 0.8478634357452393,
|
| 1114 |
+
"eval_runtime": 0.6402,
|
| 1115 |
+
"eval_samples_per_second": 167.14,
|
| 1116 |
+
"eval_steps_per_second": 6.248,
|
| 1117 |
+
"step": 585
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 78.66666666666667,
|
| 1121 |
+
"grad_norm": 6.458745956420898,
|
| 1122 |
+
"learning_rate": 8.73015873015873e-06,
|
| 1123 |
+
"loss": 0.2968,
|
| 1124 |
+
"step": 590
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 78.93333333333334,
|
| 1128 |
+
"eval_accuracy": 0.7383177570093458,
|
| 1129 |
+
"eval_loss": 0.8838663101196289,
|
| 1130 |
+
"eval_runtime": 0.6283,
|
| 1131 |
+
"eval_samples_per_second": 170.3,
|
| 1132 |
+
"eval_steps_per_second": 6.366,
|
| 1133 |
+
"step": 592
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 80.0,
|
| 1137 |
+
"grad_norm": 7.113694667816162,
|
| 1138 |
+
"learning_rate": 7.936507936507936e-06,
|
| 1139 |
+
"loss": 0.3013,
|
| 1140 |
+
"step": 600
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 80.0,
|
| 1144 |
+
"eval_accuracy": 0.719626168224299,
|
| 1145 |
+
"eval_loss": 0.8837152719497681,
|
| 1146 |
+
"eval_runtime": 0.6296,
|
| 1147 |
+
"eval_samples_per_second": 169.941,
|
| 1148 |
+
"eval_steps_per_second": 6.353,
|
| 1149 |
+
"step": 600
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 80.93333333333334,
|
| 1153 |
+
"eval_accuracy": 0.7102803738317757,
|
| 1154 |
+
"eval_loss": 0.8694174289703369,
|
| 1155 |
+
"eval_runtime": 0.6384,
|
| 1156 |
+
"eval_samples_per_second": 167.61,
|
| 1157 |
+
"eval_steps_per_second": 6.266,
|
| 1158 |
+
"step": 607
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 81.33333333333333,
|
| 1162 |
+
"grad_norm": 7.3130645751953125,
|
| 1163 |
+
"learning_rate": 7.142857142857143e-06,
|
| 1164 |
+
"loss": 0.3247,
|
| 1165 |
+
"step": 610
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 82.0,
|
| 1169 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1170 |
+
"eval_loss": 0.8721389174461365,
|
| 1171 |
+
"eval_runtime": 0.6303,
|
| 1172 |
+
"eval_samples_per_second": 169.753,
|
| 1173 |
+
"eval_steps_per_second": 6.346,
|
| 1174 |
+
"step": 615
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 82.66666666666667,
|
| 1178 |
+
"grad_norm": 7.383735179901123,
|
| 1179 |
+
"learning_rate": 6.349206349206349e-06,
|
| 1180 |
+
"loss": 0.2515,
|
| 1181 |
+
"step": 620
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 82.93333333333334,
|
| 1185 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1186 |
+
"eval_loss": 0.8605012893676758,
|
| 1187 |
+
"eval_runtime": 0.6316,
|
| 1188 |
+
"eval_samples_per_second": 169.406,
|
| 1189 |
+
"eval_steps_per_second": 6.333,
|
| 1190 |
+
"step": 622
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 84.0,
|
| 1194 |
+
"grad_norm": 10.514152526855469,
|
| 1195 |
+
"learning_rate": 5.555555555555556e-06,
|
| 1196 |
+
"loss": 0.3175,
|
| 1197 |
+
"step": 630
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 84.0,
|
| 1201 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1202 |
+
"eval_loss": 0.8504555225372314,
|
| 1203 |
+
"eval_runtime": 0.6431,
|
| 1204 |
+
"eval_samples_per_second": 166.371,
|
| 1205 |
+
"eval_steps_per_second": 6.219,
|
| 1206 |
+
"step": 630
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 84.93333333333334,
|
| 1210 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1211 |
+
"eval_loss": 0.8487720489501953,
|
| 1212 |
+
"eval_runtime": 0.7009,
|
| 1213 |
+
"eval_samples_per_second": 152.657,
|
| 1214 |
+
"eval_steps_per_second": 5.707,
|
| 1215 |
+
"step": 637
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 85.33333333333333,
|
| 1219 |
+
"grad_norm": 7.461284637451172,
|
| 1220 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 1221 |
+
"loss": 0.3015,
|
| 1222 |
+
"step": 640
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 86.0,
|
| 1226 |
+
"eval_accuracy": 0.7383177570093458,
|
| 1227 |
+
"eval_loss": 0.8554015755653381,
|
| 1228 |
+
"eval_runtime": 0.63,
|
| 1229 |
+
"eval_samples_per_second": 169.848,
|
| 1230 |
+
"eval_steps_per_second": 6.349,
|
| 1231 |
+
"step": 645
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 86.66666666666667,
|
| 1235 |
+
"grad_norm": 7.623924732208252,
|
| 1236 |
+
"learning_rate": 3.968253968253968e-06,
|
| 1237 |
+
"loss": 0.2989,
|
| 1238 |
+
"step": 650
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 86.93333333333334,
|
| 1242 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1243 |
+
"eval_loss": 0.8706844449043274,
|
| 1244 |
+
"eval_runtime": 0.619,
|
| 1245 |
+
"eval_samples_per_second": 172.858,
|
| 1246 |
+
"eval_steps_per_second": 6.462,
|
| 1247 |
+
"step": 652
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 88.0,
|
| 1251 |
+
"grad_norm": 8.086990356445312,
|
| 1252 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 1253 |
+
"loss": 0.3155,
|
| 1254 |
+
"step": 660
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 88.0,
|
| 1258 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1259 |
+
"eval_loss": 0.8711610436439514,
|
| 1260 |
+
"eval_runtime": 0.6221,
|
| 1261 |
+
"eval_samples_per_second": 171.99,
|
| 1262 |
+
"eval_steps_per_second": 6.43,
|
| 1263 |
+
"step": 660
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 88.93333333333334,
|
| 1267 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1268 |
+
"eval_loss": 0.8659169673919678,
|
| 1269 |
+
"eval_runtime": 0.6827,
|
| 1270 |
+
"eval_samples_per_second": 156.733,
|
| 1271 |
+
"eval_steps_per_second": 5.859,
|
| 1272 |
+
"step": 667
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 89.33333333333333,
|
| 1276 |
+
"grad_norm": 7.784951210021973,
|
| 1277 |
+
"learning_rate": 2.3809523809523808e-06,
|
| 1278 |
+
"loss": 0.2871,
|
| 1279 |
+
"step": 670
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 90.0,
|
| 1283 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1284 |
+
"eval_loss": 0.8573119044303894,
|
| 1285 |
+
"eval_runtime": 0.6276,
|
| 1286 |
+
"eval_samples_per_second": 170.489,
|
| 1287 |
+
"eval_steps_per_second": 6.373,
|
| 1288 |
+
"step": 675
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 90.66666666666667,
|
| 1292 |
+
"grad_norm": 5.8744587898254395,
|
| 1293 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 1294 |
+
"loss": 0.2872,
|
| 1295 |
+
"step": 680
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 90.93333333333334,
|
| 1299 |
+
"eval_accuracy": 0.7289719626168224,
|
| 1300 |
+
"eval_loss": 0.8529960513114929,
|
| 1301 |
+
"eval_runtime": 0.6227,
|
| 1302 |
+
"eval_samples_per_second": 171.823,
|
| 1303 |
+
"eval_steps_per_second": 6.423,
|
| 1304 |
+
"step": 682
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 92.0,
|
| 1308 |
+
"grad_norm": 7.09710168838501,
|
| 1309 |
+
"learning_rate": 7.936507936507937e-07,
|
| 1310 |
+
"loss": 0.2587,
|
| 1311 |
+
"step": 690
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 92.0,
|
| 1315 |
+
"eval_accuracy": 0.7383177570093458,
|
| 1316 |
+
"eval_loss": 0.8516349196434021,
|
| 1317 |
+
"eval_runtime": 0.6363,
|
| 1318 |
+
"eval_samples_per_second": 168.151,
|
| 1319 |
+
"eval_steps_per_second": 6.286,
|
| 1320 |
+
"step": 690
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 92.93333333333334,
|
| 1324 |
+
"eval_accuracy": 0.7383177570093458,
|
| 1325 |
+
"eval_loss": 0.8501598238945007,
|
| 1326 |
+
"eval_runtime": 0.6733,
|
| 1327 |
+
"eval_samples_per_second": 158.923,
|
| 1328 |
+
"eval_steps_per_second": 5.941,
|
| 1329 |
+
"step": 697
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 93.33333333333333,
|
| 1333 |
+
"grad_norm": 9.111827850341797,
|
| 1334 |
+
"learning_rate": 0.0,
|
| 1335 |
+
"loss": 0.3133,
|
| 1336 |
+
"step": 700
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 93.33333333333333,
|
| 1340 |
+
"eval_accuracy": 0.7383177570093458,
|
| 1341 |
+
"eval_loss": 0.8501192331314087,
|
| 1342 |
+
"eval_runtime": 0.6288,
|
| 1343 |
+
"eval_samples_per_second": 170.154,
|
| 1344 |
+
"eval_steps_per_second": 6.361,
|
| 1345 |
+
"step": 700
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 93.33333333333333,
|
| 1349 |
+
"step": 700,
|
| 1350 |
+
"total_flos": 2.226634183539118e+18,
|
| 1351 |
+
"train_loss": 1.0035276814869472,
|
| 1352 |
+
"train_runtime": 1522.5733,
|
| 1353 |
+
"train_samples_per_second": 62.92,
|
| 1354 |
+
"train_steps_per_second": 0.46
|
| 1355 |
}
|
| 1356 |
],
|
| 1357 |
"logging_steps": 10,
|
| 1358 |
+
"max_steps": 700,
|
| 1359 |
"num_input_tokens_seen": 0,
|
| 1360 |
+
"num_train_epochs": 100,
|
| 1361 |
"save_steps": 500,
|
| 1362 |
"stateful_callbacks": {
|
| 1363 |
"TrainerControl": {
|
|
|
|
| 1371 |
"attributes": {}
|
| 1372 |
}
|
| 1373 |
},
|
| 1374 |
+
"total_flos": 2.226634183539118e+18,
|
| 1375 |
"train_batch_size": 32,
|
| 1376 |
"trial_name": null,
|
| 1377 |
"trial_params": null
|