Mohammed Abdeldayem
commited on
End of training
Browse files- README.md +3 -3
- all_results.json +9 -9
- eval_results.json +4 -4
- runs/May25_20-15-01_5f59a01ef625/events.out.tfevents.1716670942.5f59a01ef625.42.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +2019 -12
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 [motheecreator/vit-Facial-Expression-Recognition](https://huggingface.co/motheecreator/vit-Facial-Expression-Recognition) on the image_folder 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: 0.7444126074498567
|
| 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 [motheecreator/vit-Facial-Expression-Recognition](https://huggingface.co/motheecreator/vit-Facial-Expression-Recognition) on the image_folder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.7038
|
| 36 |
+
- Accuracy: 0.7444
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_accuracy": 0.7444126074498567,
|
| 4 |
"eval_loss": 0.7038247585296631,
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 13.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
"eval_accuracy": 0.7444126074498567,
|
| 4 |
"eval_loss": 0.7038247585296631,
|
| 5 |
+
"eval_runtime": 50.1881,
|
| 6 |
+
"eval_samples_per_second": 104.308,
|
| 7 |
+
"eval_steps_per_second": 13.051,
|
| 8 |
+
"total_flos": 1.6218250349213123e+19,
|
| 9 |
+
"train_loss": 0.06548295821026195,
|
| 10 |
+
"train_runtime": 2722.3253,
|
| 11 |
+
"train_samples_per_second": 76.905,
|
| 12 |
+
"train_steps_per_second": 2.402
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_accuracy": 0.7444126074498567,
|
| 4 |
"eval_loss": 0.7038247585296631,
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 13.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
"eval_accuracy": 0.7444126074498567,
|
| 4 |
"eval_loss": 0.7038247585296631,
|
| 5 |
+
"eval_runtime": 50.1881,
|
| 6 |
+
"eval_samples_per_second": 104.308,
|
| 7 |
+
"eval_steps_per_second": 13.051
|
| 8 |
}
|
runs/May25_20-15-01_5f59a01ef625/events.out.tfevents.1716670942.5f59a01ef625.42.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:979557d094aeaad0e1d93f5fe166f6b99b0a810c97ce5ff3d1b02b787232ba02
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 1.6218250349213123e+19,
|
| 4 |
+
"train_loss": 0.06548295821026195,
|
| 5 |
+
"train_runtime": 2722.3253,
|
| 6 |
+
"train_samples_per_second": 76.905,
|
| 7 |
+
"train_steps_per_second": 2.402
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7444126074498567,
|
| 3 |
"best_model_checkpoint": "vit-Facial-Expression-Recognition/checkpoint-1962",
|
| 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,
|
|
@@ -2016,21 +2016,2028 @@
|
|
| 2016 |
"step": 3270
|
| 2017 |
},
|
| 2018 |
{
|
| 2019 |
-
"epoch": 5.
|
| 2020 |
-
"
|
| 2021 |
-
"
|
| 2022 |
-
"
|
| 2023 |
-
|
| 2024 |
-
|
| 2025 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2026 |
}
|
| 2027 |
],
|
| 2028 |
"logging_steps": 10,
|
| 2029 |
-
"max_steps":
|
| 2030 |
"num_input_tokens_seen": 0,
|
| 2031 |
-
"num_train_epochs":
|
| 2032 |
"save_steps": 500,
|
| 2033 |
-
"total_flos":
|
| 2034 |
"train_batch_size": 8,
|
| 2035 |
"trial_name": null,
|
| 2036 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7444126074498567,
|
| 3 |
"best_model_checkpoint": "vit-Facial-Expression-Recognition/checkpoint-1962",
|
| 4 |
+
"epoch": 9.9980894153611,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6540,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2016 |
"step": 3270
|
| 2017 |
},
|
| 2018 |
{
|
| 2019 |
+
"epoch": 5.02,
|
| 2020 |
+
"learning_rate": 2.7692830445124026e-05,
|
| 2021 |
+
"loss": 0.1929,
|
| 2022 |
+
"step": 3280
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 5.03,
|
| 2026 |
+
"learning_rate": 2.760788311247027e-05,
|
| 2027 |
+
"loss": 0.1936,
|
| 2028 |
+
"step": 3290
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 5.05,
|
| 2032 |
+
"learning_rate": 2.7522935779816515e-05,
|
| 2033 |
+
"loss": 0.1636,
|
| 2034 |
+
"step": 3300
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 5.06,
|
| 2038 |
+
"learning_rate": 2.743798844716276e-05,
|
| 2039 |
+
"loss": 0.1827,
|
| 2040 |
+
"step": 3310
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 5.08,
|
| 2044 |
+
"learning_rate": 2.7353041114509004e-05,
|
| 2045 |
+
"loss": 0.2437,
|
| 2046 |
+
"step": 3320
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 5.09,
|
| 2050 |
+
"learning_rate": 2.7268093781855254e-05,
|
| 2051 |
+
"loss": 0.2142,
|
| 2052 |
+
"step": 3330
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 5.11,
|
| 2056 |
+
"learning_rate": 2.7183146449201497e-05,
|
| 2057 |
+
"loss": 0.2637,
|
| 2058 |
+
"step": 3340
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 5.12,
|
| 2062 |
+
"learning_rate": 2.709819911654774e-05,
|
| 2063 |
+
"loss": 0.213,
|
| 2064 |
+
"step": 3350
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 5.14,
|
| 2068 |
+
"learning_rate": 2.701325178389399e-05,
|
| 2069 |
+
"loss": 0.2534,
|
| 2070 |
+
"step": 3360
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 5.15,
|
| 2074 |
+
"learning_rate": 2.6928304451240233e-05,
|
| 2075 |
+
"loss": 0.2819,
|
| 2076 |
+
"step": 3370
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 5.17,
|
| 2080 |
+
"learning_rate": 2.6843357118586476e-05,
|
| 2081 |
+
"loss": 0.2568,
|
| 2082 |
+
"step": 3380
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 5.18,
|
| 2086 |
+
"learning_rate": 2.6758409785932726e-05,
|
| 2087 |
+
"loss": 0.2391,
|
| 2088 |
+
"step": 3390
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 5.2,
|
| 2092 |
+
"learning_rate": 2.667346245327897e-05,
|
| 2093 |
+
"loss": 0.2604,
|
| 2094 |
+
"step": 3400
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 5.21,
|
| 2098 |
+
"learning_rate": 2.6588515120625212e-05,
|
| 2099 |
+
"loss": 0.2849,
|
| 2100 |
+
"step": 3410
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 5.23,
|
| 2104 |
+
"learning_rate": 2.6503567787971462e-05,
|
| 2105 |
+
"loss": 0.2233,
|
| 2106 |
+
"step": 3420
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 5.24,
|
| 2110 |
+
"learning_rate": 2.6418620455317705e-05,
|
| 2111 |
+
"loss": 0.2154,
|
| 2112 |
+
"step": 3430
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 5.26,
|
| 2116 |
+
"learning_rate": 2.6333673122663948e-05,
|
| 2117 |
+
"loss": 0.2891,
|
| 2118 |
+
"step": 3440
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 5.28,
|
| 2122 |
+
"learning_rate": 2.624872579001019e-05,
|
| 2123 |
+
"loss": 0.217,
|
| 2124 |
+
"step": 3450
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 5.29,
|
| 2128 |
+
"learning_rate": 2.616377845735644e-05,
|
| 2129 |
+
"loss": 0.2627,
|
| 2130 |
+
"step": 3460
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 5.31,
|
| 2134 |
+
"learning_rate": 2.6078831124702684e-05,
|
| 2135 |
+
"loss": 0.2276,
|
| 2136 |
+
"step": 3470
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 5.32,
|
| 2140 |
+
"learning_rate": 2.5993883792048927e-05,
|
| 2141 |
+
"loss": 0.2119,
|
| 2142 |
+
"step": 3480
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 5.34,
|
| 2146 |
+
"learning_rate": 2.5908936459395177e-05,
|
| 2147 |
+
"loss": 0.2302,
|
| 2148 |
+
"step": 3490
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 5.35,
|
| 2152 |
+
"learning_rate": 2.582398912674142e-05,
|
| 2153 |
+
"loss": 0.284,
|
| 2154 |
+
"step": 3500
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 5.37,
|
| 2158 |
+
"learning_rate": 2.5739041794087666e-05,
|
| 2159 |
+
"loss": 0.2456,
|
| 2160 |
+
"step": 3510
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 5.38,
|
| 2164 |
+
"learning_rate": 2.5654094461433913e-05,
|
| 2165 |
+
"loss": 0.2087,
|
| 2166 |
+
"step": 3520
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 5.4,
|
| 2170 |
+
"learning_rate": 2.556914712878016e-05,
|
| 2171 |
+
"loss": 0.282,
|
| 2172 |
+
"step": 3530
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 5.41,
|
| 2176 |
+
"learning_rate": 2.5484199796126402e-05,
|
| 2177 |
+
"loss": 0.213,
|
| 2178 |
+
"step": 3540
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 5.43,
|
| 2182 |
+
"learning_rate": 2.539925246347265e-05,
|
| 2183 |
+
"loss": 0.207,
|
| 2184 |
+
"step": 3550
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 5.44,
|
| 2188 |
+
"learning_rate": 2.5314305130818895e-05,
|
| 2189 |
+
"loss": 0.2326,
|
| 2190 |
+
"step": 3560
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 5.46,
|
| 2194 |
+
"learning_rate": 2.5229357798165138e-05,
|
| 2195 |
+
"loss": 0.2557,
|
| 2196 |
+
"step": 3570
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 5.47,
|
| 2200 |
+
"learning_rate": 2.5144410465511388e-05,
|
| 2201 |
+
"loss": 0.2524,
|
| 2202 |
+
"step": 3580
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 5.49,
|
| 2206 |
+
"learning_rate": 2.505946313285763e-05,
|
| 2207 |
+
"loss": 0.3032,
|
| 2208 |
+
"step": 3590
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 5.5,
|
| 2212 |
+
"learning_rate": 2.4974515800203874e-05,
|
| 2213 |
+
"loss": 0.3316,
|
| 2214 |
+
"step": 3600
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 5.52,
|
| 2218 |
+
"learning_rate": 2.488956846755012e-05,
|
| 2219 |
+
"loss": 0.2447,
|
| 2220 |
+
"step": 3610
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 5.53,
|
| 2224 |
+
"learning_rate": 2.4804621134896367e-05,
|
| 2225 |
+
"loss": 0.3041,
|
| 2226 |
+
"step": 3620
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 5.55,
|
| 2230 |
+
"learning_rate": 2.471967380224261e-05,
|
| 2231 |
+
"loss": 0.1924,
|
| 2232 |
+
"step": 3630
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 5.57,
|
| 2236 |
+
"learning_rate": 2.4634726469588856e-05,
|
| 2237 |
+
"loss": 0.2868,
|
| 2238 |
+
"step": 3640
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 5.58,
|
| 2242 |
+
"learning_rate": 2.4549779136935103e-05,
|
| 2243 |
+
"loss": 0.2278,
|
| 2244 |
+
"step": 3650
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 5.6,
|
| 2248 |
+
"learning_rate": 2.4464831804281346e-05,
|
| 2249 |
+
"loss": 0.3065,
|
| 2250 |
+
"step": 3660
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 5.61,
|
| 2254 |
+
"learning_rate": 2.4379884471627592e-05,
|
| 2255 |
+
"loss": 0.2801,
|
| 2256 |
+
"step": 3670
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 5.63,
|
| 2260 |
+
"learning_rate": 2.4294937138973835e-05,
|
| 2261 |
+
"loss": 0.2434,
|
| 2262 |
+
"step": 3680
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 5.64,
|
| 2266 |
+
"learning_rate": 2.4209989806320082e-05,
|
| 2267 |
+
"loss": 0.2846,
|
| 2268 |
+
"step": 3690
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 5.66,
|
| 2272 |
+
"learning_rate": 2.4125042473666328e-05,
|
| 2273 |
+
"loss": 0.2783,
|
| 2274 |
+
"step": 3700
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 5.67,
|
| 2278 |
+
"learning_rate": 2.404009514101257e-05,
|
| 2279 |
+
"loss": 0.271,
|
| 2280 |
+
"step": 3710
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 5.69,
|
| 2284 |
+
"learning_rate": 2.3955147808358818e-05,
|
| 2285 |
+
"loss": 0.1965,
|
| 2286 |
+
"step": 3720
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 5.7,
|
| 2290 |
+
"learning_rate": 2.3870200475705064e-05,
|
| 2291 |
+
"loss": 0.2836,
|
| 2292 |
+
"step": 3730
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 5.72,
|
| 2296 |
+
"learning_rate": 2.3785253143051307e-05,
|
| 2297 |
+
"loss": 0.2765,
|
| 2298 |
+
"step": 3740
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 5.73,
|
| 2302 |
+
"learning_rate": 2.3700305810397554e-05,
|
| 2303 |
+
"loss": 0.267,
|
| 2304 |
+
"step": 3750
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 5.75,
|
| 2308 |
+
"learning_rate": 2.36153584777438e-05,
|
| 2309 |
+
"loss": 0.2518,
|
| 2310 |
+
"step": 3760
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 5.76,
|
| 2314 |
+
"learning_rate": 2.3530411145090047e-05,
|
| 2315 |
+
"loss": 0.3005,
|
| 2316 |
+
"step": 3770
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 5.78,
|
| 2320 |
+
"learning_rate": 2.3445463812436293e-05,
|
| 2321 |
+
"loss": 0.2205,
|
| 2322 |
+
"step": 3780
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 5.79,
|
| 2326 |
+
"learning_rate": 2.3360516479782536e-05,
|
| 2327 |
+
"loss": 0.2288,
|
| 2328 |
+
"step": 3790
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 5.81,
|
| 2332 |
+
"learning_rate": 2.3275569147128782e-05,
|
| 2333 |
+
"loss": 0.2786,
|
| 2334 |
+
"step": 3800
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 5.83,
|
| 2338 |
+
"learning_rate": 2.319062181447503e-05,
|
| 2339 |
+
"loss": 0.2371,
|
| 2340 |
+
"step": 3810
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 5.84,
|
| 2344 |
+
"learning_rate": 2.3105674481821272e-05,
|
| 2345 |
+
"loss": 0.2495,
|
| 2346 |
+
"step": 3820
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 5.86,
|
| 2350 |
+
"learning_rate": 2.302072714916752e-05,
|
| 2351 |
+
"loss": 0.3372,
|
| 2352 |
+
"step": 3830
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 5.87,
|
| 2356 |
+
"learning_rate": 2.2935779816513765e-05,
|
| 2357 |
+
"loss": 0.286,
|
| 2358 |
+
"step": 3840
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 5.89,
|
| 2362 |
+
"learning_rate": 2.2850832483860008e-05,
|
| 2363 |
+
"loss": 0.1617,
|
| 2364 |
+
"step": 3850
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 5.9,
|
| 2368 |
+
"learning_rate": 2.2765885151206254e-05,
|
| 2369 |
+
"loss": 0.3336,
|
| 2370 |
+
"step": 3860
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 5.92,
|
| 2374 |
+
"learning_rate": 2.2680937818552497e-05,
|
| 2375 |
+
"loss": 0.2747,
|
| 2376 |
+
"step": 3870
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 5.93,
|
| 2380 |
+
"learning_rate": 2.2595990485898744e-05,
|
| 2381 |
+
"loss": 0.2783,
|
| 2382 |
+
"step": 3880
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 5.95,
|
| 2386 |
+
"learning_rate": 2.251104315324499e-05,
|
| 2387 |
+
"loss": 0.2528,
|
| 2388 |
+
"step": 3890
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 5.96,
|
| 2392 |
+
"learning_rate": 2.2426095820591233e-05,
|
| 2393 |
+
"loss": 0.2145,
|
| 2394 |
+
"step": 3900
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 5.98,
|
| 2398 |
+
"learning_rate": 2.234114848793748e-05,
|
| 2399 |
+
"loss": 0.2747,
|
| 2400 |
+
"step": 3910
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 5.99,
|
| 2404 |
+
"learning_rate": 2.2256201155283726e-05,
|
| 2405 |
+
"loss": 0.276,
|
| 2406 |
+
"step": 3920
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 6.0,
|
| 2410 |
+
"eval_accuracy": 0.7335243553008596,
|
| 2411 |
+
"eval_loss": 0.8875630497932434,
|
| 2412 |
+
"eval_runtime": 52.9673,
|
| 2413 |
+
"eval_samples_per_second": 98.835,
|
| 2414 |
+
"eval_steps_per_second": 12.366,
|
| 2415 |
+
"step": 3924
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 6.01,
|
| 2419 |
+
"learning_rate": 2.217125382262997e-05,
|
| 2420 |
+
"loss": 0.2266,
|
| 2421 |
+
"step": 3930
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 6.02,
|
| 2425 |
+
"learning_rate": 2.2086306489976216e-05,
|
| 2426 |
+
"loss": 0.1317,
|
| 2427 |
+
"step": 3940
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 6.04,
|
| 2431 |
+
"learning_rate": 2.200135915732246e-05,
|
| 2432 |
+
"loss": 0.1782,
|
| 2433 |
+
"step": 3950
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 6.05,
|
| 2437 |
+
"learning_rate": 2.1916411824668705e-05,
|
| 2438 |
+
"loss": 0.1682,
|
| 2439 |
+
"step": 3960
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 6.07,
|
| 2443 |
+
"learning_rate": 2.183146449201495e-05,
|
| 2444 |
+
"loss": 0.136,
|
| 2445 |
+
"step": 3970
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 6.09,
|
| 2449 |
+
"learning_rate": 2.1746517159361194e-05,
|
| 2450 |
+
"loss": 0.1868,
|
| 2451 |
+
"step": 3980
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 6.1,
|
| 2455 |
+
"learning_rate": 2.166156982670744e-05,
|
| 2456 |
+
"loss": 0.2079,
|
| 2457 |
+
"step": 3990
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 6.12,
|
| 2461 |
+
"learning_rate": 2.1576622494053687e-05,
|
| 2462 |
+
"loss": 0.1697,
|
| 2463 |
+
"step": 4000
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"epoch": 6.13,
|
| 2467 |
+
"learning_rate": 2.1491675161399934e-05,
|
| 2468 |
+
"loss": 0.1892,
|
| 2469 |
+
"step": 4010
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 6.15,
|
| 2473 |
+
"learning_rate": 2.140672782874618e-05,
|
| 2474 |
+
"loss": 0.2033,
|
| 2475 |
+
"step": 4020
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 6.16,
|
| 2479 |
+
"learning_rate": 2.1321780496092427e-05,
|
| 2480 |
+
"loss": 0.1372,
|
| 2481 |
+
"step": 4030
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 6.18,
|
| 2485 |
+
"learning_rate": 2.123683316343867e-05,
|
| 2486 |
+
"loss": 0.199,
|
| 2487 |
+
"step": 4040
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 6.19,
|
| 2491 |
+
"learning_rate": 2.1151885830784916e-05,
|
| 2492 |
+
"loss": 0.1655,
|
| 2493 |
+
"step": 4050
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 6.21,
|
| 2497 |
+
"learning_rate": 2.106693849813116e-05,
|
| 2498 |
+
"loss": 0.1681,
|
| 2499 |
+
"step": 4060
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 6.22,
|
| 2503 |
+
"learning_rate": 2.0981991165477406e-05,
|
| 2504 |
+
"loss": 0.2172,
|
| 2505 |
+
"step": 4070
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 6.24,
|
| 2509 |
+
"learning_rate": 2.0897043832823652e-05,
|
| 2510 |
+
"loss": 0.1542,
|
| 2511 |
+
"step": 4080
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 6.25,
|
| 2515 |
+
"learning_rate": 2.0812096500169895e-05,
|
| 2516 |
+
"loss": 0.1596,
|
| 2517 |
+
"step": 4090
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 6.27,
|
| 2521 |
+
"learning_rate": 2.072714916751614e-05,
|
| 2522 |
+
"loss": 0.1871,
|
| 2523 |
+
"step": 4100
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 6.28,
|
| 2527 |
+
"learning_rate": 2.0642201834862388e-05,
|
| 2528 |
+
"loss": 0.1852,
|
| 2529 |
+
"step": 4110
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 6.3,
|
| 2533 |
+
"learning_rate": 2.055725450220863e-05,
|
| 2534 |
+
"loss": 0.2118,
|
| 2535 |
+
"step": 4120
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 6.31,
|
| 2539 |
+
"learning_rate": 2.0472307169554877e-05,
|
| 2540 |
+
"loss": 0.1648,
|
| 2541 |
+
"step": 4130
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 6.33,
|
| 2545 |
+
"learning_rate": 2.038735983690112e-05,
|
| 2546 |
+
"loss": 0.1759,
|
| 2547 |
+
"step": 4140
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 6.35,
|
| 2551 |
+
"learning_rate": 2.0302412504247367e-05,
|
| 2552 |
+
"loss": 0.1385,
|
| 2553 |
+
"step": 4150
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 6.36,
|
| 2557 |
+
"learning_rate": 2.0217465171593613e-05,
|
| 2558 |
+
"loss": 0.1848,
|
| 2559 |
+
"step": 4160
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 6.38,
|
| 2563 |
+
"learning_rate": 2.0132517838939856e-05,
|
| 2564 |
+
"loss": 0.2324,
|
| 2565 |
+
"step": 4170
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 6.39,
|
| 2569 |
+
"learning_rate": 2.0047570506286103e-05,
|
| 2570 |
+
"loss": 0.2223,
|
| 2571 |
+
"step": 4180
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 6.41,
|
| 2575 |
+
"learning_rate": 1.996262317363235e-05,
|
| 2576 |
+
"loss": 0.1592,
|
| 2577 |
+
"step": 4190
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 6.42,
|
| 2581 |
+
"learning_rate": 1.9877675840978592e-05,
|
| 2582 |
+
"loss": 0.1849,
|
| 2583 |
+
"step": 4200
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 6.44,
|
| 2587 |
+
"learning_rate": 1.979272850832484e-05,
|
| 2588 |
+
"loss": 0.1592,
|
| 2589 |
+
"step": 4210
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 6.45,
|
| 2593 |
+
"learning_rate": 1.9707781175671085e-05,
|
| 2594 |
+
"loss": 0.147,
|
| 2595 |
+
"step": 4220
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 6.47,
|
| 2599 |
+
"learning_rate": 1.9622833843017328e-05,
|
| 2600 |
+
"loss": 0.2434,
|
| 2601 |
+
"step": 4230
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 6.48,
|
| 2605 |
+
"learning_rate": 1.9537886510363575e-05,
|
| 2606 |
+
"loss": 0.1759,
|
| 2607 |
+
"step": 4240
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 6.5,
|
| 2611 |
+
"learning_rate": 1.945293917770982e-05,
|
| 2612 |
+
"loss": 0.1086,
|
| 2613 |
+
"step": 4250
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 6.51,
|
| 2617 |
+
"learning_rate": 1.9367991845056068e-05,
|
| 2618 |
+
"loss": 0.1473,
|
| 2619 |
+
"step": 4260
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 6.53,
|
| 2623 |
+
"learning_rate": 1.9283044512402314e-05,
|
| 2624 |
+
"loss": 0.2267,
|
| 2625 |
+
"step": 4270
|
| 2626 |
+
},
|
| 2627 |
+
{
|
| 2628 |
+
"epoch": 6.54,
|
| 2629 |
+
"learning_rate": 1.9198097179748557e-05,
|
| 2630 |
+
"loss": 0.1617,
|
| 2631 |
+
"step": 4280
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 6.56,
|
| 2635 |
+
"learning_rate": 1.9113149847094803e-05,
|
| 2636 |
+
"loss": 0.1352,
|
| 2637 |
+
"step": 4290
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 6.57,
|
| 2641 |
+
"learning_rate": 1.902820251444105e-05,
|
| 2642 |
+
"loss": 0.1824,
|
| 2643 |
+
"step": 4300
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 6.59,
|
| 2647 |
+
"learning_rate": 1.8943255181787293e-05,
|
| 2648 |
+
"loss": 0.2317,
|
| 2649 |
+
"step": 4310
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 6.6,
|
| 2653 |
+
"learning_rate": 1.885830784913354e-05,
|
| 2654 |
+
"loss": 0.1288,
|
| 2655 |
+
"step": 4320
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 6.62,
|
| 2659 |
+
"learning_rate": 1.8773360516479782e-05,
|
| 2660 |
+
"loss": 0.1705,
|
| 2661 |
+
"step": 4330
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 6.64,
|
| 2665 |
+
"learning_rate": 1.868841318382603e-05,
|
| 2666 |
+
"loss": 0.1666,
|
| 2667 |
+
"step": 4340
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 6.65,
|
| 2671 |
+
"learning_rate": 1.8603465851172275e-05,
|
| 2672 |
+
"loss": 0.1805,
|
| 2673 |
+
"step": 4350
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"epoch": 6.67,
|
| 2677 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 2678 |
+
"loss": 0.1735,
|
| 2679 |
+
"step": 4360
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 6.68,
|
| 2683 |
+
"learning_rate": 1.8433571185864765e-05,
|
| 2684 |
+
"loss": 0.1469,
|
| 2685 |
+
"step": 4370
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 6.7,
|
| 2689 |
+
"learning_rate": 1.834862385321101e-05,
|
| 2690 |
+
"loss": 0.1741,
|
| 2691 |
+
"step": 4380
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 6.71,
|
| 2695 |
+
"learning_rate": 1.8263676520557254e-05,
|
| 2696 |
+
"loss": 0.1928,
|
| 2697 |
+
"step": 4390
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 6.73,
|
| 2701 |
+
"learning_rate": 1.81787291879035e-05,
|
| 2702 |
+
"loss": 0.1633,
|
| 2703 |
+
"step": 4400
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 6.74,
|
| 2707 |
+
"learning_rate": 1.8093781855249747e-05,
|
| 2708 |
+
"loss": 0.171,
|
| 2709 |
+
"step": 4410
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 6.76,
|
| 2713 |
+
"learning_rate": 1.800883452259599e-05,
|
| 2714 |
+
"loss": 0.1172,
|
| 2715 |
+
"step": 4420
|
| 2716 |
+
},
|
| 2717 |
+
{
|
| 2718 |
+
"epoch": 6.77,
|
| 2719 |
+
"learning_rate": 1.7923887189942237e-05,
|
| 2720 |
+
"loss": 0.1969,
|
| 2721 |
+
"step": 4430
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 6.79,
|
| 2725 |
+
"learning_rate": 1.783893985728848e-05,
|
| 2726 |
+
"loss": 0.1892,
|
| 2727 |
+
"step": 4440
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 6.8,
|
| 2731 |
+
"learning_rate": 1.7753992524634726e-05,
|
| 2732 |
+
"loss": 0.1663,
|
| 2733 |
+
"step": 4450
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 6.82,
|
| 2737 |
+
"learning_rate": 1.7669045191980972e-05,
|
| 2738 |
+
"loss": 0.1804,
|
| 2739 |
+
"step": 4460
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 6.83,
|
| 2743 |
+
"learning_rate": 1.7584097859327215e-05,
|
| 2744 |
+
"loss": 0.1847,
|
| 2745 |
+
"step": 4470
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 6.85,
|
| 2749 |
+
"learning_rate": 1.7499150526673462e-05,
|
| 2750 |
+
"loss": 0.1542,
|
| 2751 |
+
"step": 4480
|
| 2752 |
+
},
|
| 2753 |
+
{
|
| 2754 |
+
"epoch": 6.86,
|
| 2755 |
+
"learning_rate": 1.741420319401971e-05,
|
| 2756 |
+
"loss": 0.2272,
|
| 2757 |
+
"step": 4490
|
| 2758 |
+
},
|
| 2759 |
+
{
|
| 2760 |
+
"epoch": 6.88,
|
| 2761 |
+
"learning_rate": 1.7329255861365955e-05,
|
| 2762 |
+
"loss": 0.2078,
|
| 2763 |
+
"step": 4500
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 6.9,
|
| 2767 |
+
"learning_rate": 1.72443085287122e-05,
|
| 2768 |
+
"loss": 0.1508,
|
| 2769 |
+
"step": 4510
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 6.91,
|
| 2773 |
+
"learning_rate": 1.7159361196058444e-05,
|
| 2774 |
+
"loss": 0.1619,
|
| 2775 |
+
"step": 4520
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 6.93,
|
| 2779 |
+
"learning_rate": 1.707441386340469e-05,
|
| 2780 |
+
"loss": 0.147,
|
| 2781 |
+
"step": 4530
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 6.94,
|
| 2785 |
+
"learning_rate": 1.6989466530750937e-05,
|
| 2786 |
+
"loss": 0.1696,
|
| 2787 |
+
"step": 4540
|
| 2788 |
+
},
|
| 2789 |
+
{
|
| 2790 |
+
"epoch": 6.96,
|
| 2791 |
+
"learning_rate": 1.690451919809718e-05,
|
| 2792 |
+
"loss": 0.1835,
|
| 2793 |
+
"step": 4550
|
| 2794 |
+
},
|
| 2795 |
+
{
|
| 2796 |
+
"epoch": 6.97,
|
| 2797 |
+
"learning_rate": 1.6819571865443427e-05,
|
| 2798 |
+
"loss": 0.2407,
|
| 2799 |
+
"step": 4560
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 6.99,
|
| 2803 |
+
"learning_rate": 1.6734624532789673e-05,
|
| 2804 |
+
"loss": 0.2217,
|
| 2805 |
+
"step": 4570
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 7.0,
|
| 2809 |
+
"eval_accuracy": 0.7255014326647564,
|
| 2810 |
+
"eval_loss": 0.975210428237915,
|
| 2811 |
+
"eval_runtime": 48.2463,
|
| 2812 |
+
"eval_samples_per_second": 108.506,
|
| 2813 |
+
"eval_steps_per_second": 13.576,
|
| 2814 |
+
"step": 4578
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 7.0,
|
| 2818 |
+
"learning_rate": 1.6649677200135916e-05,
|
| 2819 |
+
"loss": 0.1381,
|
| 2820 |
+
"step": 4580
|
| 2821 |
+
},
|
| 2822 |
+
{
|
| 2823 |
+
"epoch": 7.02,
|
| 2824 |
+
"learning_rate": 1.6564729867482163e-05,
|
| 2825 |
+
"loss": 0.1104,
|
| 2826 |
+
"step": 4590
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 7.03,
|
| 2830 |
+
"learning_rate": 1.647978253482841e-05,
|
| 2831 |
+
"loss": 0.1027,
|
| 2832 |
+
"step": 4600
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 7.05,
|
| 2836 |
+
"learning_rate": 1.6394835202174652e-05,
|
| 2837 |
+
"loss": 0.0925,
|
| 2838 |
+
"step": 4610
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 7.06,
|
| 2842 |
+
"learning_rate": 1.63098878695209e-05,
|
| 2843 |
+
"loss": 0.0849,
|
| 2844 |
+
"step": 4620
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 7.08,
|
| 2848 |
+
"learning_rate": 1.622494053686714e-05,
|
| 2849 |
+
"loss": 0.1063,
|
| 2850 |
+
"step": 4630
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"epoch": 7.09,
|
| 2854 |
+
"learning_rate": 1.6139993204213388e-05,
|
| 2855 |
+
"loss": 0.1039,
|
| 2856 |
+
"step": 4640
|
| 2857 |
+
},
|
| 2858 |
+
{
|
| 2859 |
+
"epoch": 7.11,
|
| 2860 |
+
"learning_rate": 1.6055045871559634e-05,
|
| 2861 |
+
"loss": 0.0816,
|
| 2862 |
+
"step": 4650
|
| 2863 |
+
},
|
| 2864 |
+
{
|
| 2865 |
+
"epoch": 7.12,
|
| 2866 |
+
"learning_rate": 1.5970098538905877e-05,
|
| 2867 |
+
"loss": 0.1369,
|
| 2868 |
+
"step": 4660
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 7.14,
|
| 2872 |
+
"learning_rate": 1.5885151206252124e-05,
|
| 2873 |
+
"loss": 0.072,
|
| 2874 |
+
"step": 4670
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 7.16,
|
| 2878 |
+
"learning_rate": 1.580020387359837e-05,
|
| 2879 |
+
"loss": 0.1572,
|
| 2880 |
+
"step": 4680
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 7.17,
|
| 2884 |
+
"learning_rate": 1.5715256540944613e-05,
|
| 2885 |
+
"loss": 0.1364,
|
| 2886 |
+
"step": 4690
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 7.19,
|
| 2890 |
+
"learning_rate": 1.563030920829086e-05,
|
| 2891 |
+
"loss": 0.1231,
|
| 2892 |
+
"step": 4700
|
| 2893 |
+
},
|
| 2894 |
+
{
|
| 2895 |
+
"epoch": 7.2,
|
| 2896 |
+
"learning_rate": 1.5545361875637103e-05,
|
| 2897 |
+
"loss": 0.1029,
|
| 2898 |
+
"step": 4710
|
| 2899 |
+
},
|
| 2900 |
+
{
|
| 2901 |
+
"epoch": 7.22,
|
| 2902 |
+
"learning_rate": 1.546041454298335e-05,
|
| 2903 |
+
"loss": 0.1086,
|
| 2904 |
+
"step": 4720
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 7.23,
|
| 2908 |
+
"learning_rate": 1.5375467210329596e-05,
|
| 2909 |
+
"loss": 0.1288,
|
| 2910 |
+
"step": 4730
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 7.25,
|
| 2914 |
+
"learning_rate": 1.5290519877675842e-05,
|
| 2915 |
+
"loss": 0.0978,
|
| 2916 |
+
"step": 4740
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 7.26,
|
| 2920 |
+
"learning_rate": 1.5205572545022087e-05,
|
| 2921 |
+
"loss": 0.132,
|
| 2922 |
+
"step": 4750
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 7.28,
|
| 2926 |
+
"learning_rate": 1.5120625212368333e-05,
|
| 2927 |
+
"loss": 0.1073,
|
| 2928 |
+
"step": 4760
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 7.29,
|
| 2932 |
+
"learning_rate": 1.5035677879714576e-05,
|
| 2933 |
+
"loss": 0.0635,
|
| 2934 |
+
"step": 4770
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"epoch": 7.31,
|
| 2938 |
+
"learning_rate": 1.4950730547060823e-05,
|
| 2939 |
+
"loss": 0.1048,
|
| 2940 |
+
"step": 4780
|
| 2941 |
+
},
|
| 2942 |
+
{
|
| 2943 |
+
"epoch": 7.32,
|
| 2944 |
+
"learning_rate": 1.4865783214407069e-05,
|
| 2945 |
+
"loss": 0.0925,
|
| 2946 |
+
"step": 4790
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 7.34,
|
| 2950 |
+
"learning_rate": 1.4780835881753314e-05,
|
| 2951 |
+
"loss": 0.0982,
|
| 2952 |
+
"step": 4800
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 7.35,
|
| 2956 |
+
"learning_rate": 1.469588854909956e-05,
|
| 2957 |
+
"loss": 0.1385,
|
| 2958 |
+
"step": 4810
|
| 2959 |
+
},
|
| 2960 |
+
{
|
| 2961 |
+
"epoch": 7.37,
|
| 2962 |
+
"learning_rate": 1.4610941216445803e-05,
|
| 2963 |
+
"loss": 0.112,
|
| 2964 |
+
"step": 4820
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 7.38,
|
| 2968 |
+
"learning_rate": 1.452599388379205e-05,
|
| 2969 |
+
"loss": 0.1666,
|
| 2970 |
+
"step": 4830
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 7.4,
|
| 2974 |
+
"learning_rate": 1.4441046551138296e-05,
|
| 2975 |
+
"loss": 0.1001,
|
| 2976 |
+
"step": 4840
|
| 2977 |
+
},
|
| 2978 |
+
{
|
| 2979 |
+
"epoch": 7.41,
|
| 2980 |
+
"learning_rate": 1.435609921848454e-05,
|
| 2981 |
+
"loss": 0.1285,
|
| 2982 |
+
"step": 4850
|
| 2983 |
+
},
|
| 2984 |
+
{
|
| 2985 |
+
"epoch": 7.43,
|
| 2986 |
+
"learning_rate": 1.4271151885830786e-05,
|
| 2987 |
+
"loss": 0.1185,
|
| 2988 |
+
"step": 4860
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 7.45,
|
| 2992 |
+
"learning_rate": 1.4186204553177032e-05,
|
| 2993 |
+
"loss": 0.0936,
|
| 2994 |
+
"step": 4870
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 7.46,
|
| 2998 |
+
"learning_rate": 1.4101257220523275e-05,
|
| 2999 |
+
"loss": 0.0754,
|
| 3000 |
+
"step": 4880
|
| 3001 |
+
},
|
| 3002 |
+
{
|
| 3003 |
+
"epoch": 7.48,
|
| 3004 |
+
"learning_rate": 1.4016309887869522e-05,
|
| 3005 |
+
"loss": 0.0842,
|
| 3006 |
+
"step": 4890
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 7.49,
|
| 3010 |
+
"learning_rate": 1.3931362555215766e-05,
|
| 3011 |
+
"loss": 0.1387,
|
| 3012 |
+
"step": 4900
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 7.51,
|
| 3016 |
+
"learning_rate": 1.3846415222562013e-05,
|
| 3017 |
+
"loss": 0.1285,
|
| 3018 |
+
"step": 4910
|
| 3019 |
+
},
|
| 3020 |
+
{
|
| 3021 |
+
"epoch": 7.52,
|
| 3022 |
+
"learning_rate": 1.3761467889908258e-05,
|
| 3023 |
+
"loss": 0.1909,
|
| 3024 |
+
"step": 4920
|
| 3025 |
+
},
|
| 3026 |
+
{
|
| 3027 |
+
"epoch": 7.54,
|
| 3028 |
+
"learning_rate": 1.3676520557254502e-05,
|
| 3029 |
+
"loss": 0.0862,
|
| 3030 |
+
"step": 4930
|
| 3031 |
+
},
|
| 3032 |
+
{
|
| 3033 |
+
"epoch": 7.55,
|
| 3034 |
+
"learning_rate": 1.3591573224600749e-05,
|
| 3035 |
+
"loss": 0.0951,
|
| 3036 |
+
"step": 4940
|
| 3037 |
+
},
|
| 3038 |
+
{
|
| 3039 |
+
"epoch": 7.57,
|
| 3040 |
+
"learning_rate": 1.3506625891946995e-05,
|
| 3041 |
+
"loss": 0.0812,
|
| 3042 |
+
"step": 4950
|
| 3043 |
+
},
|
| 3044 |
+
{
|
| 3045 |
+
"epoch": 7.58,
|
| 3046 |
+
"learning_rate": 1.3421678559293238e-05,
|
| 3047 |
+
"loss": 0.1107,
|
| 3048 |
+
"step": 4960
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 7.6,
|
| 3052 |
+
"learning_rate": 1.3336731226639485e-05,
|
| 3053 |
+
"loss": 0.1025,
|
| 3054 |
+
"step": 4970
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 7.61,
|
| 3058 |
+
"learning_rate": 1.3251783893985731e-05,
|
| 3059 |
+
"loss": 0.1235,
|
| 3060 |
+
"step": 4980
|
| 3061 |
+
},
|
| 3062 |
+
{
|
| 3063 |
+
"epoch": 7.63,
|
| 3064 |
+
"learning_rate": 1.3166836561331974e-05,
|
| 3065 |
+
"loss": 0.1164,
|
| 3066 |
+
"step": 4990
|
| 3067 |
+
},
|
| 3068 |
+
{
|
| 3069 |
+
"epoch": 7.64,
|
| 3070 |
+
"learning_rate": 1.308188922867822e-05,
|
| 3071 |
+
"loss": 0.1105,
|
| 3072 |
+
"step": 5000
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 7.66,
|
| 3076 |
+
"learning_rate": 1.2996941896024464e-05,
|
| 3077 |
+
"loss": 0.0727,
|
| 3078 |
+
"step": 5010
|
| 3079 |
+
},
|
| 3080 |
+
{
|
| 3081 |
+
"epoch": 7.67,
|
| 3082 |
+
"learning_rate": 1.291199456337071e-05,
|
| 3083 |
+
"loss": 0.1,
|
| 3084 |
+
"step": 5020
|
| 3085 |
+
},
|
| 3086 |
+
{
|
| 3087 |
+
"epoch": 7.69,
|
| 3088 |
+
"learning_rate": 1.2827047230716956e-05,
|
| 3089 |
+
"loss": 0.0591,
|
| 3090 |
+
"step": 5030
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 7.71,
|
| 3094 |
+
"learning_rate": 1.2742099898063201e-05,
|
| 3095 |
+
"loss": 0.1469,
|
| 3096 |
+
"step": 5040
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 7.72,
|
| 3100 |
+
"learning_rate": 1.2657152565409448e-05,
|
| 3101 |
+
"loss": 0.094,
|
| 3102 |
+
"step": 5050
|
| 3103 |
+
},
|
| 3104 |
+
{
|
| 3105 |
+
"epoch": 7.74,
|
| 3106 |
+
"learning_rate": 1.2572205232755694e-05,
|
| 3107 |
+
"loss": 0.1413,
|
| 3108 |
+
"step": 5060
|
| 3109 |
+
},
|
| 3110 |
+
{
|
| 3111 |
+
"epoch": 7.75,
|
| 3112 |
+
"learning_rate": 1.2487257900101937e-05,
|
| 3113 |
+
"loss": 0.1544,
|
| 3114 |
+
"step": 5070
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 7.77,
|
| 3118 |
+
"learning_rate": 1.2402310567448183e-05,
|
| 3119 |
+
"loss": 0.0947,
|
| 3120 |
+
"step": 5080
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 7.78,
|
| 3124 |
+
"learning_rate": 1.2317363234794428e-05,
|
| 3125 |
+
"loss": 0.0794,
|
| 3126 |
+
"step": 5090
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 7.8,
|
| 3130 |
+
"learning_rate": 1.2232415902140673e-05,
|
| 3131 |
+
"loss": 0.0734,
|
| 3132 |
+
"step": 5100
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 7.81,
|
| 3136 |
+
"learning_rate": 1.2147468569486918e-05,
|
| 3137 |
+
"loss": 0.1328,
|
| 3138 |
+
"step": 5110
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 7.83,
|
| 3142 |
+
"learning_rate": 1.2062521236833164e-05,
|
| 3143 |
+
"loss": 0.1425,
|
| 3144 |
+
"step": 5120
|
| 3145 |
+
},
|
| 3146 |
+
{
|
| 3147 |
+
"epoch": 7.84,
|
| 3148 |
+
"learning_rate": 1.1977573904179409e-05,
|
| 3149 |
+
"loss": 0.1404,
|
| 3150 |
+
"step": 5130
|
| 3151 |
+
},
|
| 3152 |
+
{
|
| 3153 |
+
"epoch": 7.86,
|
| 3154 |
+
"learning_rate": 1.1892626571525654e-05,
|
| 3155 |
+
"loss": 0.1005,
|
| 3156 |
+
"step": 5140
|
| 3157 |
+
},
|
| 3158 |
+
{
|
| 3159 |
+
"epoch": 7.87,
|
| 3160 |
+
"learning_rate": 1.18076792388719e-05,
|
| 3161 |
+
"loss": 0.1057,
|
| 3162 |
+
"step": 5150
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 7.89,
|
| 3166 |
+
"learning_rate": 1.1722731906218146e-05,
|
| 3167 |
+
"loss": 0.089,
|
| 3168 |
+
"step": 5160
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"epoch": 7.9,
|
| 3172 |
+
"learning_rate": 1.1637784573564391e-05,
|
| 3173 |
+
"loss": 0.1242,
|
| 3174 |
+
"step": 5170
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 7.92,
|
| 3178 |
+
"learning_rate": 1.1552837240910636e-05,
|
| 3179 |
+
"loss": 0.114,
|
| 3180 |
+
"step": 5180
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 7.93,
|
| 3184 |
+
"learning_rate": 1.1467889908256882e-05,
|
| 3185 |
+
"loss": 0.0863,
|
| 3186 |
+
"step": 5190
|
| 3187 |
+
},
|
| 3188 |
+
{
|
| 3189 |
+
"epoch": 7.95,
|
| 3190 |
+
"learning_rate": 1.1382942575603127e-05,
|
| 3191 |
+
"loss": 0.1092,
|
| 3192 |
+
"step": 5200
|
| 3193 |
+
},
|
| 3194 |
+
{
|
| 3195 |
+
"epoch": 7.97,
|
| 3196 |
+
"learning_rate": 1.1297995242949372e-05,
|
| 3197 |
+
"loss": 0.1331,
|
| 3198 |
+
"step": 5210
|
| 3199 |
+
},
|
| 3200 |
+
{
|
| 3201 |
+
"epoch": 7.98,
|
| 3202 |
+
"learning_rate": 1.1213047910295617e-05,
|
| 3203 |
+
"loss": 0.0932,
|
| 3204 |
+
"step": 5220
|
| 3205 |
+
},
|
| 3206 |
+
{
|
| 3207 |
+
"epoch": 8.0,
|
| 3208 |
+
"learning_rate": 1.1128100577641863e-05,
|
| 3209 |
+
"loss": 0.0646,
|
| 3210 |
+
"step": 5230
|
| 3211 |
+
},
|
| 3212 |
+
{
|
| 3213 |
+
"epoch": 8.0,
|
| 3214 |
+
"eval_accuracy": 0.7262655205348615,
|
| 3215 |
+
"eval_loss": 1.0956766605377197,
|
| 3216 |
+
"eval_runtime": 48.2758,
|
| 3217 |
+
"eval_samples_per_second": 108.439,
|
| 3218 |
+
"eval_steps_per_second": 13.568,
|
| 3219 |
+
"step": 5232
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 8.01,
|
| 3223 |
+
"learning_rate": 1.1043153244988108e-05,
|
| 3224 |
+
"loss": 0.0684,
|
| 3225 |
+
"step": 5240
|
| 3226 |
+
},
|
| 3227 |
+
{
|
| 3228 |
+
"epoch": 8.03,
|
| 3229 |
+
"learning_rate": 1.0958205912334353e-05,
|
| 3230 |
+
"loss": 0.0661,
|
| 3231 |
+
"step": 5250
|
| 3232 |
+
},
|
| 3233 |
+
{
|
| 3234 |
+
"epoch": 8.04,
|
| 3235 |
+
"learning_rate": 1.0873258579680597e-05,
|
| 3236 |
+
"loss": 0.1048,
|
| 3237 |
+
"step": 5260
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 8.06,
|
| 3241 |
+
"learning_rate": 1.0788311247026844e-05,
|
| 3242 |
+
"loss": 0.0763,
|
| 3243 |
+
"step": 5270
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 8.07,
|
| 3247 |
+
"learning_rate": 1.070336391437309e-05,
|
| 3248 |
+
"loss": 0.0477,
|
| 3249 |
+
"step": 5280
|
| 3250 |
+
},
|
| 3251 |
+
{
|
| 3252 |
+
"epoch": 8.09,
|
| 3253 |
+
"learning_rate": 1.0618416581719335e-05,
|
| 3254 |
+
"loss": 0.0662,
|
| 3255 |
+
"step": 5290
|
| 3256 |
+
},
|
| 3257 |
+
{
|
| 3258 |
+
"epoch": 8.1,
|
| 3259 |
+
"learning_rate": 1.053346924906558e-05,
|
| 3260 |
+
"loss": 0.0479,
|
| 3261 |
+
"step": 5300
|
| 3262 |
+
},
|
| 3263 |
+
{
|
| 3264 |
+
"epoch": 8.12,
|
| 3265 |
+
"learning_rate": 1.0448521916411826e-05,
|
| 3266 |
+
"loss": 0.065,
|
| 3267 |
+
"step": 5310
|
| 3268 |
+
},
|
| 3269 |
+
{
|
| 3270 |
+
"epoch": 8.13,
|
| 3271 |
+
"learning_rate": 1.036357458375807e-05,
|
| 3272 |
+
"loss": 0.0685,
|
| 3273 |
+
"step": 5320
|
| 3274 |
+
},
|
| 3275 |
+
{
|
| 3276 |
+
"epoch": 8.15,
|
| 3277 |
+
"learning_rate": 1.0278627251104316e-05,
|
| 3278 |
+
"loss": 0.0763,
|
| 3279 |
+
"step": 5330
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 8.16,
|
| 3283 |
+
"learning_rate": 1.019367991845056e-05,
|
| 3284 |
+
"loss": 0.061,
|
| 3285 |
+
"step": 5340
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 8.18,
|
| 3289 |
+
"learning_rate": 1.0108732585796807e-05,
|
| 3290 |
+
"loss": 0.0848,
|
| 3291 |
+
"step": 5350
|
| 3292 |
+
},
|
| 3293 |
+
{
|
| 3294 |
+
"epoch": 8.19,
|
| 3295 |
+
"learning_rate": 1.0023785253143051e-05,
|
| 3296 |
+
"loss": 0.0621,
|
| 3297 |
+
"step": 5360
|
| 3298 |
+
},
|
| 3299 |
+
{
|
| 3300 |
+
"epoch": 8.21,
|
| 3301 |
+
"learning_rate": 9.938837920489296e-06,
|
| 3302 |
+
"loss": 0.0505,
|
| 3303 |
+
"step": 5370
|
| 3304 |
+
},
|
| 3305 |
+
{
|
| 3306 |
+
"epoch": 8.23,
|
| 3307 |
+
"learning_rate": 9.853890587835543e-06,
|
| 3308 |
+
"loss": 0.0823,
|
| 3309 |
+
"step": 5380
|
| 3310 |
+
},
|
| 3311 |
+
{
|
| 3312 |
+
"epoch": 8.24,
|
| 3313 |
+
"learning_rate": 9.768943255181787e-06,
|
| 3314 |
+
"loss": 0.0637,
|
| 3315 |
+
"step": 5390
|
| 3316 |
+
},
|
| 3317 |
+
{
|
| 3318 |
+
"epoch": 8.26,
|
| 3319 |
+
"learning_rate": 9.683995922528034e-06,
|
| 3320 |
+
"loss": 0.05,
|
| 3321 |
+
"step": 5400
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 8.27,
|
| 3325 |
+
"learning_rate": 9.599048589874278e-06,
|
| 3326 |
+
"loss": 0.0393,
|
| 3327 |
+
"step": 5410
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 8.29,
|
| 3331 |
+
"learning_rate": 9.514101257220525e-06,
|
| 3332 |
+
"loss": 0.0983,
|
| 3333 |
+
"step": 5420
|
| 3334 |
+
},
|
| 3335 |
+
{
|
| 3336 |
+
"epoch": 8.3,
|
| 3337 |
+
"learning_rate": 9.42915392456677e-06,
|
| 3338 |
+
"loss": 0.0467,
|
| 3339 |
+
"step": 5430
|
| 3340 |
+
},
|
| 3341 |
+
{
|
| 3342 |
+
"epoch": 8.32,
|
| 3343 |
+
"learning_rate": 9.344206591913014e-06,
|
| 3344 |
+
"loss": 0.0898,
|
| 3345 |
+
"step": 5440
|
| 3346 |
+
},
|
| 3347 |
+
{
|
| 3348 |
+
"epoch": 8.33,
|
| 3349 |
+
"learning_rate": 9.259259259259259e-06,
|
| 3350 |
+
"loss": 0.0757,
|
| 3351 |
+
"step": 5450
|
| 3352 |
+
},
|
| 3353 |
+
{
|
| 3354 |
+
"epoch": 8.35,
|
| 3355 |
+
"learning_rate": 9.174311926605506e-06,
|
| 3356 |
+
"loss": 0.0849,
|
| 3357 |
+
"step": 5460
|
| 3358 |
+
},
|
| 3359 |
+
{
|
| 3360 |
+
"epoch": 8.36,
|
| 3361 |
+
"learning_rate": 9.08936459395175e-06,
|
| 3362 |
+
"loss": 0.0653,
|
| 3363 |
+
"step": 5470
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 8.38,
|
| 3367 |
+
"learning_rate": 9.004417261297995e-06,
|
| 3368 |
+
"loss": 0.0816,
|
| 3369 |
+
"step": 5480
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 8.39,
|
| 3373 |
+
"learning_rate": 8.91946992864424e-06,
|
| 3374 |
+
"loss": 0.0846,
|
| 3375 |
+
"step": 5490
|
| 3376 |
+
},
|
| 3377 |
+
{
|
| 3378 |
+
"epoch": 8.41,
|
| 3379 |
+
"learning_rate": 8.834522595990486e-06,
|
| 3380 |
+
"loss": 0.0766,
|
| 3381 |
+
"step": 5500
|
| 3382 |
+
},
|
| 3383 |
+
{
|
| 3384 |
+
"epoch": 8.42,
|
| 3385 |
+
"learning_rate": 8.749575263336731e-06,
|
| 3386 |
+
"loss": 0.0697,
|
| 3387 |
+
"step": 5510
|
| 3388 |
+
},
|
| 3389 |
+
{
|
| 3390 |
+
"epoch": 8.44,
|
| 3391 |
+
"learning_rate": 8.664627930682977e-06,
|
| 3392 |
+
"loss": 0.0611,
|
| 3393 |
+
"step": 5520
|
| 3394 |
+
},
|
| 3395 |
+
{
|
| 3396 |
+
"epoch": 8.45,
|
| 3397 |
+
"learning_rate": 8.579680598029222e-06,
|
| 3398 |
+
"loss": 0.0808,
|
| 3399 |
+
"step": 5530
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 8.47,
|
| 3403 |
+
"learning_rate": 8.494733265375469e-06,
|
| 3404 |
+
"loss": 0.0697,
|
| 3405 |
+
"step": 5540
|
| 3406 |
+
},
|
| 3407 |
+
{
|
| 3408 |
+
"epoch": 8.48,
|
| 3409 |
+
"learning_rate": 8.409785932721713e-06,
|
| 3410 |
+
"loss": 0.1034,
|
| 3411 |
+
"step": 5550
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 8.5,
|
| 3415 |
+
"learning_rate": 8.324838600067958e-06,
|
| 3416 |
+
"loss": 0.0583,
|
| 3417 |
+
"step": 5560
|
| 3418 |
+
},
|
| 3419 |
+
{
|
| 3420 |
+
"epoch": 8.52,
|
| 3421 |
+
"learning_rate": 8.239891267414204e-06,
|
| 3422 |
+
"loss": 0.0638,
|
| 3423 |
+
"step": 5570
|
| 3424 |
+
},
|
| 3425 |
+
{
|
| 3426 |
+
"epoch": 8.53,
|
| 3427 |
+
"learning_rate": 8.15494393476045e-06,
|
| 3428 |
+
"loss": 0.0319,
|
| 3429 |
+
"step": 5580
|
| 3430 |
+
},
|
| 3431 |
+
{
|
| 3432 |
+
"epoch": 8.55,
|
| 3433 |
+
"learning_rate": 8.069996602106694e-06,
|
| 3434 |
+
"loss": 0.071,
|
| 3435 |
+
"step": 5590
|
| 3436 |
+
},
|
| 3437 |
+
{
|
| 3438 |
+
"epoch": 8.56,
|
| 3439 |
+
"learning_rate": 7.985049269452939e-06,
|
| 3440 |
+
"loss": 0.0929,
|
| 3441 |
+
"step": 5600
|
| 3442 |
+
},
|
| 3443 |
+
{
|
| 3444 |
+
"epoch": 8.58,
|
| 3445 |
+
"learning_rate": 7.900101936799185e-06,
|
| 3446 |
+
"loss": 0.0728,
|
| 3447 |
+
"step": 5610
|
| 3448 |
+
},
|
| 3449 |
+
{
|
| 3450 |
+
"epoch": 8.59,
|
| 3451 |
+
"learning_rate": 7.81515460414543e-06,
|
| 3452 |
+
"loss": 0.0868,
|
| 3453 |
+
"step": 5620
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 8.61,
|
| 3457 |
+
"learning_rate": 7.730207271491675e-06,
|
| 3458 |
+
"loss": 0.0725,
|
| 3459 |
+
"step": 5630
|
| 3460 |
+
},
|
| 3461 |
+
{
|
| 3462 |
+
"epoch": 8.62,
|
| 3463 |
+
"learning_rate": 7.645259938837921e-06,
|
| 3464 |
+
"loss": 0.1055,
|
| 3465 |
+
"step": 5640
|
| 3466 |
+
},
|
| 3467 |
+
{
|
| 3468 |
+
"epoch": 8.64,
|
| 3469 |
+
"learning_rate": 7.560312606184167e-06,
|
| 3470 |
+
"loss": 0.0678,
|
| 3471 |
+
"step": 5650
|
| 3472 |
+
},
|
| 3473 |
+
{
|
| 3474 |
+
"epoch": 8.65,
|
| 3475 |
+
"learning_rate": 7.475365273530411e-06,
|
| 3476 |
+
"loss": 0.0914,
|
| 3477 |
+
"step": 5660
|
| 3478 |
+
},
|
| 3479 |
+
{
|
| 3480 |
+
"epoch": 8.67,
|
| 3481 |
+
"learning_rate": 7.390417940876657e-06,
|
| 3482 |
+
"loss": 0.0646,
|
| 3483 |
+
"step": 5670
|
| 3484 |
+
},
|
| 3485 |
+
{
|
| 3486 |
+
"epoch": 8.68,
|
| 3487 |
+
"learning_rate": 7.305470608222902e-06,
|
| 3488 |
+
"loss": 0.0699,
|
| 3489 |
+
"step": 5680
|
| 3490 |
+
},
|
| 3491 |
+
{
|
| 3492 |
+
"epoch": 8.7,
|
| 3493 |
+
"learning_rate": 7.220523275569148e-06,
|
| 3494 |
+
"loss": 0.071,
|
| 3495 |
+
"step": 5690
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 8.71,
|
| 3499 |
+
"learning_rate": 7.135575942915393e-06,
|
| 3500 |
+
"loss": 0.1006,
|
| 3501 |
+
"step": 5700
|
| 3502 |
+
},
|
| 3503 |
+
{
|
| 3504 |
+
"epoch": 8.73,
|
| 3505 |
+
"learning_rate": 7.050628610261638e-06,
|
| 3506 |
+
"loss": 0.0402,
|
| 3507 |
+
"step": 5710
|
| 3508 |
+
},
|
| 3509 |
+
{
|
| 3510 |
+
"epoch": 8.74,
|
| 3511 |
+
"learning_rate": 6.965681277607883e-06,
|
| 3512 |
+
"loss": 0.1133,
|
| 3513 |
+
"step": 5720
|
| 3514 |
+
},
|
| 3515 |
+
{
|
| 3516 |
+
"epoch": 8.76,
|
| 3517 |
+
"learning_rate": 6.880733944954129e-06,
|
| 3518 |
+
"loss": 0.0616,
|
| 3519 |
+
"step": 5730
|
| 3520 |
+
},
|
| 3521 |
+
{
|
| 3522 |
+
"epoch": 8.78,
|
| 3523 |
+
"learning_rate": 6.795786612300374e-06,
|
| 3524 |
+
"loss": 0.0836,
|
| 3525 |
+
"step": 5740
|
| 3526 |
+
},
|
| 3527 |
+
{
|
| 3528 |
+
"epoch": 8.79,
|
| 3529 |
+
"learning_rate": 6.710839279646619e-06,
|
| 3530 |
+
"loss": 0.0516,
|
| 3531 |
+
"step": 5750
|
| 3532 |
+
},
|
| 3533 |
+
{
|
| 3534 |
+
"epoch": 8.81,
|
| 3535 |
+
"learning_rate": 6.6258919469928655e-06,
|
| 3536 |
+
"loss": 0.0467,
|
| 3537 |
+
"step": 5760
|
| 3538 |
+
},
|
| 3539 |
+
{
|
| 3540 |
+
"epoch": 8.82,
|
| 3541 |
+
"learning_rate": 6.54094461433911e-06,
|
| 3542 |
+
"loss": 0.1025,
|
| 3543 |
+
"step": 5770
|
| 3544 |
+
},
|
| 3545 |
+
{
|
| 3546 |
+
"epoch": 8.84,
|
| 3547 |
+
"learning_rate": 6.455997281685355e-06,
|
| 3548 |
+
"loss": 0.071,
|
| 3549 |
+
"step": 5780
|
| 3550 |
+
},
|
| 3551 |
+
{
|
| 3552 |
+
"epoch": 8.85,
|
| 3553 |
+
"learning_rate": 6.3710499490316006e-06,
|
| 3554 |
+
"loss": 0.154,
|
| 3555 |
+
"step": 5790
|
| 3556 |
+
},
|
| 3557 |
+
{
|
| 3558 |
+
"epoch": 8.87,
|
| 3559 |
+
"learning_rate": 6.286102616377847e-06,
|
| 3560 |
+
"loss": 0.0633,
|
| 3561 |
+
"step": 5800
|
| 3562 |
+
},
|
| 3563 |
+
{
|
| 3564 |
+
"epoch": 8.88,
|
| 3565 |
+
"learning_rate": 6.201155283724092e-06,
|
| 3566 |
+
"loss": 0.0912,
|
| 3567 |
+
"step": 5810
|
| 3568 |
+
},
|
| 3569 |
+
{
|
| 3570 |
+
"epoch": 8.9,
|
| 3571 |
+
"learning_rate": 6.1162079510703365e-06,
|
| 3572 |
+
"loss": 0.051,
|
| 3573 |
+
"step": 5820
|
| 3574 |
+
},
|
| 3575 |
+
{
|
| 3576 |
+
"epoch": 8.91,
|
| 3577 |
+
"learning_rate": 6.031260618416582e-06,
|
| 3578 |
+
"loss": 0.0584,
|
| 3579 |
+
"step": 5830
|
| 3580 |
+
},
|
| 3581 |
+
{
|
| 3582 |
+
"epoch": 8.93,
|
| 3583 |
+
"learning_rate": 5.946313285762827e-06,
|
| 3584 |
+
"loss": 0.0714,
|
| 3585 |
+
"step": 5840
|
| 3586 |
+
},
|
| 3587 |
+
{
|
| 3588 |
+
"epoch": 8.94,
|
| 3589 |
+
"learning_rate": 5.861365953109073e-06,
|
| 3590 |
+
"loss": 0.0534,
|
| 3591 |
+
"step": 5850
|
| 3592 |
+
},
|
| 3593 |
+
{
|
| 3594 |
+
"epoch": 8.96,
|
| 3595 |
+
"learning_rate": 5.776418620455318e-06,
|
| 3596 |
+
"loss": 0.0411,
|
| 3597 |
+
"step": 5860
|
| 3598 |
+
},
|
| 3599 |
+
{
|
| 3600 |
+
"epoch": 8.97,
|
| 3601 |
+
"learning_rate": 5.6914712878015636e-06,
|
| 3602 |
+
"loss": 0.0461,
|
| 3603 |
+
"step": 5870
|
| 3604 |
+
},
|
| 3605 |
+
{
|
| 3606 |
+
"epoch": 8.99,
|
| 3607 |
+
"learning_rate": 5.606523955147808e-06,
|
| 3608 |
+
"loss": 0.063,
|
| 3609 |
+
"step": 5880
|
| 3610 |
+
},
|
| 3611 |
+
{
|
| 3612 |
+
"epoch": 9.0,
|
| 3613 |
+
"eval_accuracy": 0.7262655205348615,
|
| 3614 |
+
"eval_loss": 1.1334831714630127,
|
| 3615 |
+
"eval_runtime": 48.13,
|
| 3616 |
+
"eval_samples_per_second": 108.768,
|
| 3617 |
+
"eval_steps_per_second": 13.609,
|
| 3618 |
+
"step": 5887
|
| 3619 |
+
},
|
| 3620 |
+
{
|
| 3621 |
+
"epoch": 9.0,
|
| 3622 |
+
"learning_rate": 5.521576622494054e-06,
|
| 3623 |
+
"loss": 0.0773,
|
| 3624 |
+
"step": 5890
|
| 3625 |
+
},
|
| 3626 |
+
{
|
| 3627 |
+
"epoch": 9.02,
|
| 3628 |
+
"learning_rate": 5.436629289840299e-06,
|
| 3629 |
+
"loss": 0.0471,
|
| 3630 |
+
"step": 5900
|
| 3631 |
+
},
|
| 3632 |
+
{
|
| 3633 |
+
"epoch": 9.04,
|
| 3634 |
+
"learning_rate": 5.351681957186545e-06,
|
| 3635 |
+
"loss": 0.0497,
|
| 3636 |
+
"step": 5910
|
| 3637 |
+
},
|
| 3638 |
+
{
|
| 3639 |
+
"epoch": 9.05,
|
| 3640 |
+
"learning_rate": 5.26673462453279e-06,
|
| 3641 |
+
"loss": 0.1033,
|
| 3642 |
+
"step": 5920
|
| 3643 |
+
},
|
| 3644 |
+
{
|
| 3645 |
+
"epoch": 9.07,
|
| 3646 |
+
"learning_rate": 5.181787291879035e-06,
|
| 3647 |
+
"loss": 0.0409,
|
| 3648 |
+
"step": 5930
|
| 3649 |
+
},
|
| 3650 |
+
{
|
| 3651 |
+
"epoch": 9.08,
|
| 3652 |
+
"learning_rate": 5.09683995922528e-06,
|
| 3653 |
+
"loss": 0.0626,
|
| 3654 |
+
"step": 5940
|
| 3655 |
+
},
|
| 3656 |
+
{
|
| 3657 |
+
"epoch": 9.1,
|
| 3658 |
+
"learning_rate": 5.011892626571526e-06,
|
| 3659 |
+
"loss": 0.05,
|
| 3660 |
+
"step": 5950
|
| 3661 |
+
},
|
| 3662 |
+
{
|
| 3663 |
+
"epoch": 9.11,
|
| 3664 |
+
"learning_rate": 4.926945293917771e-06,
|
| 3665 |
+
"loss": 0.0466,
|
| 3666 |
+
"step": 5960
|
| 3667 |
+
},
|
| 3668 |
+
{
|
| 3669 |
+
"epoch": 9.13,
|
| 3670 |
+
"learning_rate": 4.841997961264017e-06,
|
| 3671 |
+
"loss": 0.0698,
|
| 3672 |
+
"step": 5970
|
| 3673 |
+
},
|
| 3674 |
+
{
|
| 3675 |
+
"epoch": 9.14,
|
| 3676 |
+
"learning_rate": 4.7570506286102625e-06,
|
| 3677 |
+
"loss": 0.0583,
|
| 3678 |
+
"step": 5980
|
| 3679 |
+
},
|
| 3680 |
+
{
|
| 3681 |
+
"epoch": 9.16,
|
| 3682 |
+
"learning_rate": 4.672103295956507e-06,
|
| 3683 |
+
"loss": 0.0232,
|
| 3684 |
+
"step": 5990
|
| 3685 |
+
},
|
| 3686 |
+
{
|
| 3687 |
+
"epoch": 9.17,
|
| 3688 |
+
"learning_rate": 4.587155963302753e-06,
|
| 3689 |
+
"loss": 0.0466,
|
| 3690 |
+
"step": 6000
|
| 3691 |
+
},
|
| 3692 |
+
{
|
| 3693 |
+
"epoch": 9.19,
|
| 3694 |
+
"learning_rate": 4.5022086306489975e-06,
|
| 3695 |
+
"loss": 0.0613,
|
| 3696 |
+
"step": 6010
|
| 3697 |
+
},
|
| 3698 |
+
{
|
| 3699 |
+
"epoch": 9.2,
|
| 3700 |
+
"learning_rate": 4.417261297995243e-06,
|
| 3701 |
+
"loss": 0.0691,
|
| 3702 |
+
"step": 6020
|
| 3703 |
+
},
|
| 3704 |
+
{
|
| 3705 |
+
"epoch": 9.22,
|
| 3706 |
+
"learning_rate": 4.332313965341489e-06,
|
| 3707 |
+
"loss": 0.0281,
|
| 3708 |
+
"step": 6030
|
| 3709 |
+
},
|
| 3710 |
+
{
|
| 3711 |
+
"epoch": 9.23,
|
| 3712 |
+
"learning_rate": 4.247366632687734e-06,
|
| 3713 |
+
"loss": 0.0601,
|
| 3714 |
+
"step": 6040
|
| 3715 |
+
},
|
| 3716 |
+
{
|
| 3717 |
+
"epoch": 9.25,
|
| 3718 |
+
"learning_rate": 4.162419300033979e-06,
|
| 3719 |
+
"loss": 0.059,
|
| 3720 |
+
"step": 6050
|
| 3721 |
+
},
|
| 3722 |
+
{
|
| 3723 |
+
"epoch": 9.26,
|
| 3724 |
+
"learning_rate": 4.077471967380225e-06,
|
| 3725 |
+
"loss": 0.0577,
|
| 3726 |
+
"step": 6060
|
| 3727 |
+
},
|
| 3728 |
+
{
|
| 3729 |
+
"epoch": 9.28,
|
| 3730 |
+
"learning_rate": 3.992524634726469e-06,
|
| 3731 |
+
"loss": 0.085,
|
| 3732 |
+
"step": 6070
|
| 3733 |
+
},
|
| 3734 |
+
{
|
| 3735 |
+
"epoch": 9.29,
|
| 3736 |
+
"learning_rate": 3.907577302072715e-06,
|
| 3737 |
+
"loss": 0.0246,
|
| 3738 |
+
"step": 6080
|
| 3739 |
+
},
|
| 3740 |
+
{
|
| 3741 |
+
"epoch": 9.31,
|
| 3742 |
+
"learning_rate": 3.8226299694189605e-06,
|
| 3743 |
+
"loss": 0.0697,
|
| 3744 |
+
"step": 6090
|
| 3745 |
+
},
|
| 3746 |
+
{
|
| 3747 |
+
"epoch": 9.33,
|
| 3748 |
+
"learning_rate": 3.7376826367652057e-06,
|
| 3749 |
+
"loss": 0.0333,
|
| 3750 |
+
"step": 6100
|
| 3751 |
+
},
|
| 3752 |
+
{
|
| 3753 |
+
"epoch": 9.34,
|
| 3754 |
+
"learning_rate": 3.652735304111451e-06,
|
| 3755 |
+
"loss": 0.0165,
|
| 3756 |
+
"step": 6110
|
| 3757 |
+
},
|
| 3758 |
+
{
|
| 3759 |
+
"epoch": 9.36,
|
| 3760 |
+
"learning_rate": 3.5677879714576964e-06,
|
| 3761 |
+
"loss": 0.0401,
|
| 3762 |
+
"step": 6120
|
| 3763 |
+
},
|
| 3764 |
+
{
|
| 3765 |
+
"epoch": 9.37,
|
| 3766 |
+
"learning_rate": 3.4828406388039416e-06,
|
| 3767 |
+
"loss": 0.0526,
|
| 3768 |
+
"step": 6130
|
| 3769 |
+
},
|
| 3770 |
+
{
|
| 3771 |
+
"epoch": 9.39,
|
| 3772 |
+
"learning_rate": 3.397893306150187e-06,
|
| 3773 |
+
"loss": 0.0617,
|
| 3774 |
+
"step": 6140
|
| 3775 |
+
},
|
| 3776 |
+
{
|
| 3777 |
+
"epoch": 9.4,
|
| 3778 |
+
"learning_rate": 3.3129459734964328e-06,
|
| 3779 |
+
"loss": 0.0576,
|
| 3780 |
+
"step": 6150
|
| 3781 |
+
},
|
| 3782 |
+
{
|
| 3783 |
+
"epoch": 9.42,
|
| 3784 |
+
"learning_rate": 3.2279986408426775e-06,
|
| 3785 |
+
"loss": 0.0541,
|
| 3786 |
+
"step": 6160
|
| 3787 |
+
},
|
| 3788 |
+
{
|
| 3789 |
+
"epoch": 9.43,
|
| 3790 |
+
"learning_rate": 3.1430513081889235e-06,
|
| 3791 |
+
"loss": 0.0522,
|
| 3792 |
+
"step": 6170
|
| 3793 |
+
},
|
| 3794 |
+
{
|
| 3795 |
+
"epoch": 9.45,
|
| 3796 |
+
"learning_rate": 3.0581039755351682e-06,
|
| 3797 |
+
"loss": 0.031,
|
| 3798 |
+
"step": 6180
|
| 3799 |
+
},
|
| 3800 |
+
{
|
| 3801 |
+
"epoch": 9.46,
|
| 3802 |
+
"learning_rate": 2.9731566428814134e-06,
|
| 3803 |
+
"loss": 0.0298,
|
| 3804 |
+
"step": 6190
|
| 3805 |
+
},
|
| 3806 |
+
{
|
| 3807 |
+
"epoch": 9.48,
|
| 3808 |
+
"learning_rate": 2.888209310227659e-06,
|
| 3809 |
+
"loss": 0.022,
|
| 3810 |
+
"step": 6200
|
| 3811 |
+
},
|
| 3812 |
+
{
|
| 3813 |
+
"epoch": 9.49,
|
| 3814 |
+
"learning_rate": 2.803261977573904e-06,
|
| 3815 |
+
"loss": 0.0553,
|
| 3816 |
+
"step": 6210
|
| 3817 |
+
},
|
| 3818 |
+
{
|
| 3819 |
+
"epoch": 9.51,
|
| 3820 |
+
"learning_rate": 2.7183146449201493e-06,
|
| 3821 |
+
"loss": 0.0275,
|
| 3822 |
+
"step": 6220
|
| 3823 |
+
},
|
| 3824 |
+
{
|
| 3825 |
+
"epoch": 9.52,
|
| 3826 |
+
"learning_rate": 2.633367312266395e-06,
|
| 3827 |
+
"loss": 0.0227,
|
| 3828 |
+
"step": 6230
|
| 3829 |
+
},
|
| 3830 |
+
{
|
| 3831 |
+
"epoch": 9.54,
|
| 3832 |
+
"learning_rate": 2.54841997961264e-06,
|
| 3833 |
+
"loss": 0.0528,
|
| 3834 |
+
"step": 6240
|
| 3835 |
+
},
|
| 3836 |
+
{
|
| 3837 |
+
"epoch": 9.55,
|
| 3838 |
+
"learning_rate": 2.4634726469588856e-06,
|
| 3839 |
+
"loss": 0.0635,
|
| 3840 |
+
"step": 6250
|
| 3841 |
+
},
|
| 3842 |
+
{
|
| 3843 |
+
"epoch": 9.57,
|
| 3844 |
+
"learning_rate": 2.3785253143051312e-06,
|
| 3845 |
+
"loss": 0.0572,
|
| 3846 |
+
"step": 6260
|
| 3847 |
+
},
|
| 3848 |
+
{
|
| 3849 |
+
"epoch": 9.59,
|
| 3850 |
+
"learning_rate": 2.2935779816513764e-06,
|
| 3851 |
+
"loss": 0.042,
|
| 3852 |
+
"step": 6270
|
| 3853 |
+
},
|
| 3854 |
+
{
|
| 3855 |
+
"epoch": 9.6,
|
| 3856 |
+
"learning_rate": 2.2086306489976216e-06,
|
| 3857 |
+
"loss": 0.0422,
|
| 3858 |
+
"step": 6280
|
| 3859 |
+
},
|
| 3860 |
+
{
|
| 3861 |
+
"epoch": 9.62,
|
| 3862 |
+
"learning_rate": 2.123683316343867e-06,
|
| 3863 |
+
"loss": 0.0311,
|
| 3864 |
+
"step": 6290
|
| 3865 |
+
},
|
| 3866 |
+
{
|
| 3867 |
+
"epoch": 9.63,
|
| 3868 |
+
"learning_rate": 2.0387359836901123e-06,
|
| 3869 |
+
"loss": 0.0375,
|
| 3870 |
+
"step": 6300
|
| 3871 |
+
},
|
| 3872 |
+
{
|
| 3873 |
+
"epoch": 9.65,
|
| 3874 |
+
"learning_rate": 1.9537886510363575e-06,
|
| 3875 |
+
"loss": 0.0491,
|
| 3876 |
+
"step": 6310
|
| 3877 |
+
},
|
| 3878 |
+
{
|
| 3879 |
+
"epoch": 9.66,
|
| 3880 |
+
"learning_rate": 1.8688413183826028e-06,
|
| 3881 |
+
"loss": 0.0537,
|
| 3882 |
+
"step": 6320
|
| 3883 |
+
},
|
| 3884 |
+
{
|
| 3885 |
+
"epoch": 9.68,
|
| 3886 |
+
"learning_rate": 1.7838939857288482e-06,
|
| 3887 |
+
"loss": 0.0496,
|
| 3888 |
+
"step": 6330
|
| 3889 |
+
},
|
| 3890 |
+
{
|
| 3891 |
+
"epoch": 9.69,
|
| 3892 |
+
"learning_rate": 1.6989466530750936e-06,
|
| 3893 |
+
"loss": 0.0478,
|
| 3894 |
+
"step": 6340
|
| 3895 |
+
},
|
| 3896 |
+
{
|
| 3897 |
+
"epoch": 9.71,
|
| 3898 |
+
"learning_rate": 1.6139993204213387e-06,
|
| 3899 |
+
"loss": 0.0283,
|
| 3900 |
+
"step": 6350
|
| 3901 |
+
},
|
| 3902 |
+
{
|
| 3903 |
+
"epoch": 9.72,
|
| 3904 |
+
"learning_rate": 1.5290519877675841e-06,
|
| 3905 |
+
"loss": 0.0373,
|
| 3906 |
+
"step": 6360
|
| 3907 |
+
},
|
| 3908 |
+
{
|
| 3909 |
+
"epoch": 9.74,
|
| 3910 |
+
"learning_rate": 1.4441046551138295e-06,
|
| 3911 |
+
"loss": 0.0491,
|
| 3912 |
+
"step": 6370
|
| 3913 |
+
},
|
| 3914 |
+
{
|
| 3915 |
+
"epoch": 9.75,
|
| 3916 |
+
"learning_rate": 1.3591573224600747e-06,
|
| 3917 |
+
"loss": 0.0213,
|
| 3918 |
+
"step": 6380
|
| 3919 |
+
},
|
| 3920 |
+
{
|
| 3921 |
+
"epoch": 9.77,
|
| 3922 |
+
"learning_rate": 1.27420998980632e-06,
|
| 3923 |
+
"loss": 0.0414,
|
| 3924 |
+
"step": 6390
|
| 3925 |
+
},
|
| 3926 |
+
{
|
| 3927 |
+
"epoch": 9.78,
|
| 3928 |
+
"learning_rate": 1.1892626571525656e-06,
|
| 3929 |
+
"loss": 0.0573,
|
| 3930 |
+
"step": 6400
|
| 3931 |
+
},
|
| 3932 |
+
{
|
| 3933 |
+
"epoch": 9.8,
|
| 3934 |
+
"learning_rate": 1.1043153244988108e-06,
|
| 3935 |
+
"loss": 0.0467,
|
| 3936 |
+
"step": 6410
|
| 3937 |
+
},
|
| 3938 |
+
{
|
| 3939 |
+
"epoch": 9.81,
|
| 3940 |
+
"learning_rate": 1.0193679918450562e-06,
|
| 3941 |
+
"loss": 0.0545,
|
| 3942 |
+
"step": 6420
|
| 3943 |
+
},
|
| 3944 |
+
{
|
| 3945 |
+
"epoch": 9.83,
|
| 3946 |
+
"learning_rate": 9.344206591913014e-07,
|
| 3947 |
+
"loss": 0.042,
|
| 3948 |
+
"step": 6430
|
| 3949 |
+
},
|
| 3950 |
+
{
|
| 3951 |
+
"epoch": 9.85,
|
| 3952 |
+
"learning_rate": 8.494733265375468e-07,
|
| 3953 |
+
"loss": 0.0404,
|
| 3954 |
+
"step": 6440
|
| 3955 |
+
},
|
| 3956 |
+
{
|
| 3957 |
+
"epoch": 9.86,
|
| 3958 |
+
"learning_rate": 7.645259938837921e-07,
|
| 3959 |
+
"loss": 0.0524,
|
| 3960 |
+
"step": 6450
|
| 3961 |
+
},
|
| 3962 |
+
{
|
| 3963 |
+
"epoch": 9.88,
|
| 3964 |
+
"learning_rate": 6.795786612300373e-07,
|
| 3965 |
+
"loss": 0.0228,
|
| 3966 |
+
"step": 6460
|
| 3967 |
+
},
|
| 3968 |
+
{
|
| 3969 |
+
"epoch": 9.89,
|
| 3970 |
+
"learning_rate": 5.946313285762828e-07,
|
| 3971 |
+
"loss": 0.0444,
|
| 3972 |
+
"step": 6470
|
| 3973 |
+
},
|
| 3974 |
+
{
|
| 3975 |
+
"epoch": 9.91,
|
| 3976 |
+
"learning_rate": 5.096839959225281e-07,
|
| 3977 |
+
"loss": 0.0197,
|
| 3978 |
+
"step": 6480
|
| 3979 |
+
},
|
| 3980 |
+
{
|
| 3981 |
+
"epoch": 9.92,
|
| 3982 |
+
"learning_rate": 4.247366632687734e-07,
|
| 3983 |
+
"loss": 0.0297,
|
| 3984 |
+
"step": 6490
|
| 3985 |
+
},
|
| 3986 |
+
{
|
| 3987 |
+
"epoch": 9.94,
|
| 3988 |
+
"learning_rate": 3.3978933061501866e-07,
|
| 3989 |
+
"loss": 0.0422,
|
| 3990 |
+
"step": 6500
|
| 3991 |
+
},
|
| 3992 |
+
{
|
| 3993 |
+
"epoch": 9.95,
|
| 3994 |
+
"learning_rate": 2.5484199796126404e-07,
|
| 3995 |
+
"loss": 0.041,
|
| 3996 |
+
"step": 6510
|
| 3997 |
+
},
|
| 3998 |
+
{
|
| 3999 |
+
"epoch": 9.97,
|
| 4000 |
+
"learning_rate": 1.6989466530750933e-07,
|
| 4001 |
+
"loss": 0.0314,
|
| 4002 |
+
"step": 6520
|
| 4003 |
+
},
|
| 4004 |
+
{
|
| 4005 |
+
"epoch": 9.98,
|
| 4006 |
+
"learning_rate": 8.494733265375467e-08,
|
| 4007 |
+
"loss": 0.0388,
|
| 4008 |
+
"step": 6530
|
| 4009 |
+
},
|
| 4010 |
+
{
|
| 4011 |
+
"epoch": 10.0,
|
| 4012 |
+
"learning_rate": 0.0,
|
| 4013 |
+
"loss": 0.0562,
|
| 4014 |
+
"step": 6540
|
| 4015 |
+
},
|
| 4016 |
+
{
|
| 4017 |
+
"epoch": 10.0,
|
| 4018 |
+
"eval_accuracy": 0.7306590257879656,
|
| 4019 |
+
"eval_loss": 1.1663085222244263,
|
| 4020 |
+
"eval_runtime": 50.0529,
|
| 4021 |
+
"eval_samples_per_second": 104.589,
|
| 4022 |
+
"eval_steps_per_second": 13.086,
|
| 4023 |
+
"step": 6540
|
| 4024 |
+
},
|
| 4025 |
+
{
|
| 4026 |
+
"epoch": 10.0,
|
| 4027 |
+
"step": 6540,
|
| 4028 |
+
"total_flos": 1.6218250349213123e+19,
|
| 4029 |
+
"train_loss": 0.06548295821026195,
|
| 4030 |
+
"train_runtime": 2722.3253,
|
| 4031 |
+
"train_samples_per_second": 76.905,
|
| 4032 |
+
"train_steps_per_second": 2.402
|
| 4033 |
}
|
| 4034 |
],
|
| 4035 |
"logging_steps": 10,
|
| 4036 |
+
"max_steps": 6540,
|
| 4037 |
"num_input_tokens_seen": 0,
|
| 4038 |
+
"num_train_epochs": 10,
|
| 4039 |
"save_steps": 500,
|
| 4040 |
+
"total_flos": 1.6218250349213123e+19,
|
| 4041 |
"train_batch_size": 8,
|
| 4042 |
"trial_name": null,
|
| 4043 |
"trial_params": null
|