End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +871 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-large-1k-224](https://huggingface.co/facebook/convnextv2-large-1k-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss:
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9681063122923588
|
| 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 [facebook/convnextv2-large-1k-224](https://huggingface.co/facebook/convnextv2-large-1k-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.1174
|
| 36 |
+
- Accuracy: 0.9681
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.94,
|
| 3 |
+
"eval_accuracy": 0.9681063122923588,
|
| 4 |
+
"eval_loss": 0.1173594519495964,
|
| 5 |
+
"eval_runtime": 42.9138,
|
| 6 |
+
"eval_samples_per_second": 105.211,
|
| 7 |
+
"eval_steps_per_second": 6.595,
|
| 8 |
+
"total_flos": 7.375405476885369e+18,
|
| 9 |
+
"train_loss": 0.7435173462795955,
|
| 10 |
+
"train_runtime": 8012.7314,
|
| 11 |
+
"train_samples_per_second": 5.229,
|
| 12 |
+
"train_steps_per_second": 0.081
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.94,
|
| 3 |
+
"eval_accuracy": 0.9681063122923588,
|
| 4 |
+
"eval_loss": 0.1173594519495964,
|
| 5 |
+
"eval_runtime": 42.9138,
|
| 6 |
+
"eval_samples_per_second": 105.211,
|
| 7 |
+
"eval_steps_per_second": 6.595
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.94,
|
| 3 |
+
"total_flos": 7.375405476885369e+18,
|
| 4 |
+
"train_loss": 0.7435173462795955,
|
| 5 |
+
"train_runtime": 8012.7314,
|
| 6 |
+
"train_samples_per_second": 5.229,
|
| 7 |
+
"train_steps_per_second": 0.081
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,871 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9681063122923588,
|
| 3 |
+
"best_model_checkpoint": "convnextv2-large-1k-224-finetuned-LungCancer-Classification-LC25000-AH-40-30-30-Shuffled-3rd/checkpoint-93",
|
| 4 |
+
"epoch": 6.944,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 651,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 7.668711656441718e-06,
|
| 14 |
+
"loss": 1.094,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 1.5337423312883436e-05,
|
| 20 |
+
"loss": 1.0587,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.16,
|
| 25 |
+
"learning_rate": 2.300613496932515e-05,
|
| 26 |
+
"loss": 0.9946,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.21,
|
| 31 |
+
"learning_rate": 3.067484662576687e-05,
|
| 32 |
+
"loss": 0.9056,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.27,
|
| 37 |
+
"learning_rate": 3.834355828220859e-05,
|
| 38 |
+
"loss": 0.7914,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.32,
|
| 43 |
+
"learning_rate": 4.60122699386503e-05,
|
| 44 |
+
"loss": 0.65,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.37,
|
| 49 |
+
"learning_rate": 5.368098159509203e-05,
|
| 50 |
+
"loss": 0.4872,
|
| 51 |
+
"step": 35
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.43,
|
| 55 |
+
"learning_rate": 6.134969325153375e-05,
|
| 56 |
+
"loss": 0.3592,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.48,
|
| 61 |
+
"learning_rate": 6.901840490797547e-05,
|
| 62 |
+
"loss": 0.3144,
|
| 63 |
+
"step": 45
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.53,
|
| 67 |
+
"learning_rate": 7.668711656441718e-05,
|
| 68 |
+
"loss": 0.2393,
|
| 69 |
+
"step": 50
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.59,
|
| 73 |
+
"learning_rate": 8.43558282208589e-05,
|
| 74 |
+
"loss": 0.1919,
|
| 75 |
+
"step": 55
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.64,
|
| 79 |
+
"learning_rate": 9.20245398773006e-05,
|
| 80 |
+
"loss": 0.2532,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.69,
|
| 85 |
+
"learning_rate": 9.969325153374233e-05,
|
| 86 |
+
"loss": 0.1908,
|
| 87 |
+
"step": 65
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.75,
|
| 91 |
+
"learning_rate": 0.00010736196319018406,
|
| 92 |
+
"loss": 0.1911,
|
| 93 |
+
"step": 70
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.8,
|
| 97 |
+
"learning_rate": 0.00011503067484662577,
|
| 98 |
+
"loss": 0.1464,
|
| 99 |
+
"step": 75
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.85,
|
| 103 |
+
"learning_rate": 0.0001226993865030675,
|
| 104 |
+
"loss": 0.1723,
|
| 105 |
+
"step": 80
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.91,
|
| 109 |
+
"learning_rate": 0.0001303680981595092,
|
| 110 |
+
"loss": 0.3376,
|
| 111 |
+
"step": 85
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.96,
|
| 115 |
+
"learning_rate": 0.00013803680981595094,
|
| 116 |
+
"loss": 0.1749,
|
| 117 |
+
"step": 90
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.99,
|
| 121 |
+
"eval_accuracy": 0.9681063122923588,
|
| 122 |
+
"eval_loss": 0.1173594519495964,
|
| 123 |
+
"eval_runtime": 2947.7804,
|
| 124 |
+
"eval_samples_per_second": 1.532,
|
| 125 |
+
"eval_steps_per_second": 0.096,
|
| 126 |
+
"step": 93
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.01,
|
| 130 |
+
"learning_rate": 0.00014570552147239263,
|
| 131 |
+
"loss": 0.2813,
|
| 132 |
+
"step": 95
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.07,
|
| 136 |
+
"learning_rate": 0.00015337423312883436,
|
| 137 |
+
"loss": 0.2519,
|
| 138 |
+
"step": 100
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.12,
|
| 142 |
+
"learning_rate": 0.00016104294478527608,
|
| 143 |
+
"loss": 0.1291,
|
| 144 |
+
"step": 105
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.17,
|
| 148 |
+
"learning_rate": 0.0001687116564417178,
|
| 149 |
+
"loss": 0.1866,
|
| 150 |
+
"step": 110
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.23,
|
| 154 |
+
"learning_rate": 0.00017638036809815953,
|
| 155 |
+
"loss": 0.1476,
|
| 156 |
+
"step": 115
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.28,
|
| 160 |
+
"learning_rate": 0.0001840490797546012,
|
| 161 |
+
"loss": 0.2151,
|
| 162 |
+
"step": 120
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.33,
|
| 166 |
+
"learning_rate": 0.00019171779141104295,
|
| 167 |
+
"loss": 0.166,
|
| 168 |
+
"step": 125
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.39,
|
| 172 |
+
"learning_rate": 0.00019938650306748466,
|
| 173 |
+
"loss": 0.2285,
|
| 174 |
+
"step": 130
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.44,
|
| 178 |
+
"learning_rate": 0.00020705521472392637,
|
| 179 |
+
"loss": 0.26,
|
| 180 |
+
"step": 135
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.49,
|
| 184 |
+
"learning_rate": 0.0002147239263803681,
|
| 185 |
+
"loss": 0.2665,
|
| 186 |
+
"step": 140
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.55,
|
| 190 |
+
"learning_rate": 0.00022239263803680982,
|
| 191 |
+
"loss": 0.3498,
|
| 192 |
+
"step": 145
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.6,
|
| 196 |
+
"learning_rate": 0.00023006134969325153,
|
| 197 |
+
"loss": 0.2542,
|
| 198 |
+
"step": 150
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.65,
|
| 202 |
+
"learning_rate": 0.00023773006134969325,
|
| 203 |
+
"loss": 0.2703,
|
| 204 |
+
"step": 155
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.71,
|
| 208 |
+
"learning_rate": 0.000245398773006135,
|
| 209 |
+
"loss": 0.3452,
|
| 210 |
+
"step": 160
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.76,
|
| 214 |
+
"learning_rate": 0.00025306748466257667,
|
| 215 |
+
"loss": 0.2412,
|
| 216 |
+
"step": 165
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.81,
|
| 220 |
+
"learning_rate": 0.0002607361963190184,
|
| 221 |
+
"loss": 0.2198,
|
| 222 |
+
"step": 170
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.87,
|
| 226 |
+
"learning_rate": 0.00026840490797546015,
|
| 227 |
+
"loss": 0.2265,
|
| 228 |
+
"step": 175
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.92,
|
| 232 |
+
"learning_rate": 0.0002760736196319019,
|
| 233 |
+
"loss": 0.35,
|
| 234 |
+
"step": 180
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.97,
|
| 238 |
+
"learning_rate": 0.00028374233128834357,
|
| 239 |
+
"loss": 0.3183,
|
| 240 |
+
"step": 185
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.99,
|
| 244 |
+
"eval_accuracy": 0.9246954595791805,
|
| 245 |
+
"eval_loss": 0.17996589839458466,
|
| 246 |
+
"eval_runtime": 43.3309,
|
| 247 |
+
"eval_samples_per_second": 104.198,
|
| 248 |
+
"eval_steps_per_second": 6.531,
|
| 249 |
+
"step": 187
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.03,
|
| 253 |
+
"learning_rate": 0.00029141104294478525,
|
| 254 |
+
"loss": 0.2368,
|
| 255 |
+
"step": 190
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.08,
|
| 259 |
+
"learning_rate": 0.000299079754601227,
|
| 260 |
+
"loss": 0.2482,
|
| 261 |
+
"step": 195
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.13,
|
| 265 |
+
"learning_rate": 0.00030674846625766873,
|
| 266 |
+
"loss": 0.1572,
|
| 267 |
+
"step": 200
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.19,
|
| 271 |
+
"learning_rate": 0.00031441717791411047,
|
| 272 |
+
"loss": 0.1358,
|
| 273 |
+
"step": 205
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.24,
|
| 277 |
+
"learning_rate": 0.00032208588957055215,
|
| 278 |
+
"loss": 0.1966,
|
| 279 |
+
"step": 210
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.29,
|
| 283 |
+
"learning_rate": 0.00032975460122699384,
|
| 284 |
+
"loss": 0.1984,
|
| 285 |
+
"step": 215
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.35,
|
| 289 |
+
"learning_rate": 0.0003374233128834356,
|
| 290 |
+
"loss": 0.2055,
|
| 291 |
+
"step": 220
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.4,
|
| 295 |
+
"learning_rate": 0.0003450920245398773,
|
| 296 |
+
"loss": 0.2273,
|
| 297 |
+
"step": 225
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.45,
|
| 301 |
+
"learning_rate": 0.00035276073619631905,
|
| 302 |
+
"loss": 0.1351,
|
| 303 |
+
"step": 230
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.51,
|
| 307 |
+
"learning_rate": 0.00036042944785276074,
|
| 308 |
+
"loss": 0.17,
|
| 309 |
+
"step": 235
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.56,
|
| 313 |
+
"learning_rate": 0.0003680981595092024,
|
| 314 |
+
"loss": 0.2857,
|
| 315 |
+
"step": 240
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.61,
|
| 319 |
+
"learning_rate": 0.00037576687116564416,
|
| 320 |
+
"loss": 0.1333,
|
| 321 |
+
"step": 245
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.67,
|
| 325 |
+
"learning_rate": 0.0003834355828220859,
|
| 326 |
+
"loss": 0.5189,
|
| 327 |
+
"step": 250
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.72,
|
| 331 |
+
"learning_rate": 0.00039110429447852764,
|
| 332 |
+
"loss": 0.1638,
|
| 333 |
+
"step": 255
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.77,
|
| 337 |
+
"learning_rate": 0.0003987730061349693,
|
| 338 |
+
"loss": 0.1754,
|
| 339 |
+
"step": 260
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.83,
|
| 343 |
+
"learning_rate": 0.00040644171779141106,
|
| 344 |
+
"loss": 0.197,
|
| 345 |
+
"step": 265
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.88,
|
| 349 |
+
"learning_rate": 0.00041411042944785274,
|
| 350 |
+
"loss": 0.1543,
|
| 351 |
+
"step": 270
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.93,
|
| 355 |
+
"learning_rate": 0.0004217791411042945,
|
| 356 |
+
"loss": 0.2147,
|
| 357 |
+
"step": 275
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.99,
|
| 361 |
+
"learning_rate": 0.0004294478527607362,
|
| 362 |
+
"loss": 0.3048,
|
| 363 |
+
"step": 280
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.0,
|
| 367 |
+
"eval_accuracy": 0.9233665559246954,
|
| 368 |
+
"eval_loss": 0.18979668617248535,
|
| 369 |
+
"eval_runtime": 43.4199,
|
| 370 |
+
"eval_samples_per_second": 103.985,
|
| 371 |
+
"eval_steps_per_second": 6.518,
|
| 372 |
+
"step": 281
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.04,
|
| 376 |
+
"learning_rate": 0.0004371165644171779,
|
| 377 |
+
"loss": 0.16,
|
| 378 |
+
"step": 285
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 3.09,
|
| 382 |
+
"learning_rate": 0.00044478527607361964,
|
| 383 |
+
"loss": 0.132,
|
| 384 |
+
"step": 290
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.15,
|
| 388 |
+
"learning_rate": 0.0004524539877300614,
|
| 389 |
+
"loss": 0.5492,
|
| 390 |
+
"step": 295
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 3.2,
|
| 394 |
+
"learning_rate": 0.00046012269938650307,
|
| 395 |
+
"loss": 1.1128,
|
| 396 |
+
"step": 300
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.25,
|
| 400 |
+
"learning_rate": 0.0004677914110429448,
|
| 401 |
+
"loss": 1.2612,
|
| 402 |
+
"step": 305
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 3.31,
|
| 406 |
+
"learning_rate": 0.0004754601226993865,
|
| 407 |
+
"loss": 1.154,
|
| 408 |
+
"step": 310
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.36,
|
| 412 |
+
"learning_rate": 0.00048312883435582823,
|
| 413 |
+
"loss": 1.1277,
|
| 414 |
+
"step": 315
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.41,
|
| 418 |
+
"learning_rate": 0.00049079754601227,
|
| 419 |
+
"loss": 1.1094,
|
| 420 |
+
"step": 320
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 3.47,
|
| 424 |
+
"learning_rate": 0.0004984662576687117,
|
| 425 |
+
"loss": 1.0978,
|
| 426 |
+
"step": 325
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 3.52,
|
| 430 |
+
"learning_rate": 0.0004938461538461538,
|
| 431 |
+
"loss": 1.1128,
|
| 432 |
+
"step": 330
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.57,
|
| 436 |
+
"learning_rate": 0.0004861538461538462,
|
| 437 |
+
"loss": 1.0989,
|
| 438 |
+
"step": 335
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 3.63,
|
| 442 |
+
"learning_rate": 0.00047846153846153844,
|
| 443 |
+
"loss": 1.1081,
|
| 444 |
+
"step": 340
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.68,
|
| 448 |
+
"learning_rate": 0.00047076923076923077,
|
| 449 |
+
"loss": 1.0983,
|
| 450 |
+
"step": 345
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.73,
|
| 454 |
+
"learning_rate": 0.00046307692307692304,
|
| 455 |
+
"loss": 1.1016,
|
| 456 |
+
"step": 350
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.79,
|
| 460 |
+
"learning_rate": 0.0004553846153846154,
|
| 461 |
+
"loss": 1.099,
|
| 462 |
+
"step": 355
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 3.84,
|
| 466 |
+
"learning_rate": 0.0004476923076923077,
|
| 467 |
+
"loss": 1.0987,
|
| 468 |
+
"step": 360
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.89,
|
| 472 |
+
"learning_rate": 0.00044,
|
| 473 |
+
"loss": 1.1142,
|
| 474 |
+
"step": 365
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.95,
|
| 478 |
+
"learning_rate": 0.0004323076923076923,
|
| 479 |
+
"loss": 1.0999,
|
| 480 |
+
"step": 370
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 4.0,
|
| 484 |
+
"learning_rate": 0.0004246153846153846,
|
| 485 |
+
"loss": 1.1006,
|
| 486 |
+
"step": 375
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 4.0,
|
| 490 |
+
"eval_accuracy": 0.3337763012181617,
|
| 491 |
+
"eval_loss": 1.1143020391464233,
|
| 492 |
+
"eval_runtime": 43.0798,
|
| 493 |
+
"eval_samples_per_second": 104.806,
|
| 494 |
+
"eval_steps_per_second": 6.569,
|
| 495 |
+
"step": 375
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 4.05,
|
| 499 |
+
"learning_rate": 0.0004169230769230769,
|
| 500 |
+
"loss": 1.1025,
|
| 501 |
+
"step": 380
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 4.11,
|
| 505 |
+
"learning_rate": 0.00040923076923076926,
|
| 506 |
+
"loss": 1.112,
|
| 507 |
+
"step": 385
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 4.16,
|
| 511 |
+
"learning_rate": 0.00040153846153846153,
|
| 512 |
+
"loss": 1.1014,
|
| 513 |
+
"step": 390
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 4.21,
|
| 517 |
+
"learning_rate": 0.00039384615384615386,
|
| 518 |
+
"loss": 1.1004,
|
| 519 |
+
"step": 395
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 4.27,
|
| 523 |
+
"learning_rate": 0.0003861538461538462,
|
| 524 |
+
"loss": 1.1119,
|
| 525 |
+
"step": 400
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.32,
|
| 529 |
+
"learning_rate": 0.00037846153846153845,
|
| 530 |
+
"loss": 1.1033,
|
| 531 |
+
"step": 405
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 4.37,
|
| 535 |
+
"learning_rate": 0.0003707692307692308,
|
| 536 |
+
"loss": 1.1073,
|
| 537 |
+
"step": 410
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.43,
|
| 541 |
+
"learning_rate": 0.0003630769230769231,
|
| 542 |
+
"loss": 1.0973,
|
| 543 |
+
"step": 415
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 4.48,
|
| 547 |
+
"learning_rate": 0.00035538461538461543,
|
| 548 |
+
"loss": 1.1094,
|
| 549 |
+
"step": 420
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.53,
|
| 553 |
+
"learning_rate": 0.0003476923076923077,
|
| 554 |
+
"loss": 1.0951,
|
| 555 |
+
"step": 425
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 4.59,
|
| 559 |
+
"learning_rate": 0.00034,
|
| 560 |
+
"loss": 1.1049,
|
| 561 |
+
"step": 430
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.64,
|
| 565 |
+
"learning_rate": 0.0003323076923076923,
|
| 566 |
+
"loss": 1.1005,
|
| 567 |
+
"step": 435
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 4.69,
|
| 571 |
+
"learning_rate": 0.0003246153846153846,
|
| 572 |
+
"loss": 1.1,
|
| 573 |
+
"step": 440
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 4.75,
|
| 577 |
+
"learning_rate": 0.00031692307692307695,
|
| 578 |
+
"loss": 1.0979,
|
| 579 |
+
"step": 445
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.8,
|
| 583 |
+
"learning_rate": 0.00030923076923076927,
|
| 584 |
+
"loss": 1.1013,
|
| 585 |
+
"step": 450
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.85,
|
| 589 |
+
"learning_rate": 0.00030153846153846154,
|
| 590 |
+
"loss": 1.1027,
|
| 591 |
+
"step": 455
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.91,
|
| 595 |
+
"learning_rate": 0.00029384615384615387,
|
| 596 |
+
"loss": 1.0969,
|
| 597 |
+
"step": 460
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.96,
|
| 601 |
+
"learning_rate": 0.00028615384615384614,
|
| 602 |
+
"loss": 1.0988,
|
| 603 |
+
"step": 465
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.99,
|
| 607 |
+
"eval_accuracy": 0.3238095238095238,
|
| 608 |
+
"eval_loss": 1.0992164611816406,
|
| 609 |
+
"eval_runtime": 42.9354,
|
| 610 |
+
"eval_samples_per_second": 105.158,
|
| 611 |
+
"eval_steps_per_second": 6.591,
|
| 612 |
+
"step": 468
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 5.01,
|
| 616 |
+
"learning_rate": 0.00027846153846153846,
|
| 617 |
+
"loss": 1.1023,
|
| 618 |
+
"step": 470
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 5.07,
|
| 622 |
+
"learning_rate": 0.0002707692307692308,
|
| 623 |
+
"loss": 1.1027,
|
| 624 |
+
"step": 475
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.12,
|
| 628 |
+
"learning_rate": 0.0002630769230769231,
|
| 629 |
+
"loss": 1.1045,
|
| 630 |
+
"step": 480
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 5.17,
|
| 634 |
+
"learning_rate": 0.0002553846153846154,
|
| 635 |
+
"loss": 1.0956,
|
| 636 |
+
"step": 485
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 5.23,
|
| 640 |
+
"learning_rate": 0.0002476923076923077,
|
| 641 |
+
"loss": 1.1015,
|
| 642 |
+
"step": 490
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 5.28,
|
| 646 |
+
"learning_rate": 0.00024,
|
| 647 |
+
"loss": 1.101,
|
| 648 |
+
"step": 495
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 5.33,
|
| 652 |
+
"learning_rate": 0.0002323076923076923,
|
| 653 |
+
"loss": 1.0938,
|
| 654 |
+
"step": 500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 5.39,
|
| 658 |
+
"learning_rate": 0.0002246153846153846,
|
| 659 |
+
"loss": 1.0983,
|
| 660 |
+
"step": 505
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 5.44,
|
| 664 |
+
"learning_rate": 0.00021692307692307693,
|
| 665 |
+
"loss": 1.0988,
|
| 666 |
+
"step": 510
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 5.49,
|
| 670 |
+
"learning_rate": 0.00020923076923076922,
|
| 671 |
+
"loss": 1.1023,
|
| 672 |
+
"step": 515
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 5.55,
|
| 676 |
+
"learning_rate": 0.00020153846153846152,
|
| 677 |
+
"loss": 1.1016,
|
| 678 |
+
"step": 520
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 5.6,
|
| 682 |
+
"learning_rate": 0.00019384615384615385,
|
| 683 |
+
"loss": 1.0993,
|
| 684 |
+
"step": 525
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 5.65,
|
| 688 |
+
"learning_rate": 0.00018615384615384615,
|
| 689 |
+
"loss": 1.0945,
|
| 690 |
+
"step": 530
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 5.71,
|
| 694 |
+
"learning_rate": 0.00017846153846153844,
|
| 695 |
+
"loss": 1.1035,
|
| 696 |
+
"step": 535
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 5.76,
|
| 700 |
+
"learning_rate": 0.00017076923076923077,
|
| 701 |
+
"loss": 1.1048,
|
| 702 |
+
"step": 540
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 5.81,
|
| 706 |
+
"learning_rate": 0.00016307692307692307,
|
| 707 |
+
"loss": 1.1051,
|
| 708 |
+
"step": 545
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 5.87,
|
| 712 |
+
"learning_rate": 0.00015538461538461536,
|
| 713 |
+
"loss": 1.0989,
|
| 714 |
+
"step": 550
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 5.92,
|
| 718 |
+
"learning_rate": 0.00014769230769230772,
|
| 719 |
+
"loss": 1.0994,
|
| 720 |
+
"step": 555
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 5.97,
|
| 724 |
+
"learning_rate": 0.00014000000000000001,
|
| 725 |
+
"loss": 1.0961,
|
| 726 |
+
"step": 560
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 5.99,
|
| 730 |
+
"eval_accuracy": 0.3238095238095238,
|
| 731 |
+
"eval_loss": 1.1005984544754028,
|
| 732 |
+
"eval_runtime": 43.2538,
|
| 733 |
+
"eval_samples_per_second": 104.384,
|
| 734 |
+
"eval_steps_per_second": 6.543,
|
| 735 |
+
"step": 562
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 6.03,
|
| 739 |
+
"learning_rate": 0.0001323076923076923,
|
| 740 |
+
"loss": 1.0989,
|
| 741 |
+
"step": 565
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 6.08,
|
| 745 |
+
"learning_rate": 0.0001246153846153846,
|
| 746 |
+
"loss": 1.0992,
|
| 747 |
+
"step": 570
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 6.13,
|
| 751 |
+
"learning_rate": 0.00011692307692307692,
|
| 752 |
+
"loss": 1.096,
|
| 753 |
+
"step": 575
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 6.19,
|
| 757 |
+
"learning_rate": 0.00010923076923076923,
|
| 758 |
+
"loss": 1.1023,
|
| 759 |
+
"step": 580
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 6.24,
|
| 763 |
+
"learning_rate": 0.00010153846153846153,
|
| 764 |
+
"loss": 1.0979,
|
| 765 |
+
"step": 585
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 6.29,
|
| 769 |
+
"learning_rate": 9.384615384615384e-05,
|
| 770 |
+
"loss": 1.1023,
|
| 771 |
+
"step": 590
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 6.35,
|
| 775 |
+
"learning_rate": 8.615384615384615e-05,
|
| 776 |
+
"loss": 1.0991,
|
| 777 |
+
"step": 595
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 6.4,
|
| 781 |
+
"learning_rate": 7.846153846153845e-05,
|
| 782 |
+
"loss": 1.0971,
|
| 783 |
+
"step": 600
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 6.45,
|
| 787 |
+
"learning_rate": 7.076923076923076e-05,
|
| 788 |
+
"loss": 1.0987,
|
| 789 |
+
"step": 605
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 6.51,
|
| 793 |
+
"learning_rate": 6.307692307692308e-05,
|
| 794 |
+
"loss": 1.095,
|
| 795 |
+
"step": 610
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 6.56,
|
| 799 |
+
"learning_rate": 5.538461538461539e-05,
|
| 800 |
+
"loss": 1.1003,
|
| 801 |
+
"step": 615
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 6.61,
|
| 805 |
+
"learning_rate": 4.769230769230769e-05,
|
| 806 |
+
"loss": 1.0994,
|
| 807 |
+
"step": 620
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 6.67,
|
| 811 |
+
"learning_rate": 4e-05,
|
| 812 |
+
"loss": 1.1029,
|
| 813 |
+
"step": 625
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 6.72,
|
| 817 |
+
"learning_rate": 3.230769230769231e-05,
|
| 818 |
+
"loss": 1.1004,
|
| 819 |
+
"step": 630
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 6.77,
|
| 823 |
+
"learning_rate": 2.4615384615384616e-05,
|
| 824 |
+
"loss": 1.098,
|
| 825 |
+
"step": 635
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 6.83,
|
| 829 |
+
"learning_rate": 1.6923076923076924e-05,
|
| 830 |
+
"loss": 1.0991,
|
| 831 |
+
"step": 640
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 6.88,
|
| 835 |
+
"learning_rate": 9.230769230769232e-06,
|
| 836 |
+
"loss": 1.0984,
|
| 837 |
+
"step": 645
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 6.93,
|
| 841 |
+
"learning_rate": 1.5384615384615385e-06,
|
| 842 |
+
"loss": 1.0987,
|
| 843 |
+
"step": 650
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 6.94,
|
| 847 |
+
"eval_accuracy": 0.3238095238095238,
|
| 848 |
+
"eval_loss": 1.0993690490722656,
|
| 849 |
+
"eval_runtime": 43.0492,
|
| 850 |
+
"eval_samples_per_second": 104.88,
|
| 851 |
+
"eval_steps_per_second": 6.574,
|
| 852 |
+
"step": 651
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 6.94,
|
| 856 |
+
"step": 651,
|
| 857 |
+
"total_flos": 7.375405476885369e+18,
|
| 858 |
+
"train_loss": 0.7435173462795955,
|
| 859 |
+
"train_runtime": 8012.7314,
|
| 860 |
+
"train_samples_per_second": 5.229,
|
| 861 |
+
"train_steps_per_second": 0.081
|
| 862 |
+
}
|
| 863 |
+
],
|
| 864 |
+
"logging_steps": 5,
|
| 865 |
+
"max_steps": 651,
|
| 866 |
+
"num_train_epochs": 7,
|
| 867 |
+
"save_steps": 500,
|
| 868 |
+
"total_flos": 7.375405476885369e+18,
|
| 869 |
+
"trial_name": null,
|
| 870 |
+
"trial_params": null
|
| 871 |
+
}
|