End of training
Browse files- README.md +22 -2
- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +670 -0
README.md
CHANGED
|
@@ -1,12 +1,29 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
base_model: Tural/language-modeling-from-scratch-ml
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- glue
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: ml-out-glue-cola
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -14,7 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# ml-out-glue-cola
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [Tural/language-modeling-from-scratch-ml](https://huggingface.co/Tural/language-modeling-from-scratch-ml) on the
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
base_model: Tural/language-modeling-from-scratch-ml
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- glue
|
| 9 |
+
metrics:
|
| 10 |
+
- matthews_correlation
|
| 11 |
model-index:
|
| 12 |
- name: ml-out-glue-cola
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Text Classification
|
| 16 |
+
type: text-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: GLUE COLA
|
| 19 |
+
type: glue
|
| 20 |
+
config: cola
|
| 21 |
+
split: validation
|
| 22 |
+
args: cola
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Matthews Correlation
|
| 25 |
+
type: matthews_correlation
|
| 26 |
+
value: 0.2052273727942896
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 31 |
|
| 32 |
# ml-out-glue-cola
|
| 33 |
|
| 34 |
+
This model is a fine-tuned version of [Tural/language-modeling-from-scratch-ml](https://huggingface.co/Tural/language-modeling-from-scratch-ml) on the GLUE COLA dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 1.9269
|
| 37 |
+
- Matthews Correlation: 0.2052
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_loss": 1.9269137382507324,
|
| 4 |
+
"eval_matthews_correlation": 0.2052273727942896,
|
| 5 |
+
"eval_runtime": 6.4158,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 162.567,
|
| 8 |
+
"eval_steps_per_second": 1.403,
|
| 9 |
+
"train_loss": 0.2142893238688138,
|
| 10 |
+
"train_runtime": 3029.2991,
|
| 11 |
+
"train_samples": 8551,
|
| 12 |
+
"train_samples_per_second": 56.455,
|
| 13 |
+
"train_steps_per_second": 0.885
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_loss": 1.9269137382507324,
|
| 4 |
+
"eval_matthews_correlation": 0.2052273727942896,
|
| 5 |
+
"eval_runtime": 6.4158,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 162.567,
|
| 8 |
+
"eval_steps_per_second": 1.403
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.2142893238688138,
|
| 4 |
+
"train_runtime": 3029.2991,
|
| 5 |
+
"train_samples": 8551,
|
| 6 |
+
"train_samples_per_second": 56.455,
|
| 7 |
+
"train_steps_per_second": 0.885
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,670 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 2.0,
|
| 6 |
+
"global_step": 2680,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.19,
|
| 13 |
+
"learning_rate": 1.9813432835820897e-05,
|
| 14 |
+
"loss": 0.6233,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.37,
|
| 19 |
+
"learning_rate": 1.9626865671641793e-05,
|
| 20 |
+
"loss": 0.6221,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.56,
|
| 25 |
+
"learning_rate": 1.9440298507462686e-05,
|
| 26 |
+
"loss": 0.6235,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.75,
|
| 31 |
+
"learning_rate": 1.9253731343283585e-05,
|
| 32 |
+
"loss": 0.5969,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.93,
|
| 37 |
+
"learning_rate": 1.9067164179104477e-05,
|
| 38 |
+
"loss": 0.6,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.12,
|
| 43 |
+
"learning_rate": 1.8880597014925376e-05,
|
| 44 |
+
"loss": 0.615,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.31,
|
| 49 |
+
"learning_rate": 1.869402985074627e-05,
|
| 50 |
+
"loss": 0.5995,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.49,
|
| 55 |
+
"learning_rate": 1.8507462686567165e-05,
|
| 56 |
+
"loss": 0.5833,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.68,
|
| 61 |
+
"learning_rate": 1.832089552238806e-05,
|
| 62 |
+
"loss": 0.6055,
|
| 63 |
+
"step": 225
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.87,
|
| 67 |
+
"learning_rate": 1.8134328358208956e-05,
|
| 68 |
+
"loss": 0.5892,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.05,
|
| 73 |
+
"learning_rate": 1.7947761194029852e-05,
|
| 74 |
+
"loss": 0.5942,
|
| 75 |
+
"step": 275
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.24,
|
| 79 |
+
"learning_rate": 1.7761194029850748e-05,
|
| 80 |
+
"loss": 0.5543,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.43,
|
| 85 |
+
"learning_rate": 1.7574626865671644e-05,
|
| 86 |
+
"loss": 0.5465,
|
| 87 |
+
"step": 325
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.61,
|
| 91 |
+
"learning_rate": 1.738805970149254e-05,
|
| 92 |
+
"loss": 0.5416,
|
| 93 |
+
"step": 350
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.8,
|
| 97 |
+
"learning_rate": 1.7201492537313432e-05,
|
| 98 |
+
"loss": 0.5653,
|
| 99 |
+
"step": 375
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.99,
|
| 103 |
+
"learning_rate": 1.701492537313433e-05,
|
| 104 |
+
"loss": 0.5215,
|
| 105 |
+
"step": 400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.17,
|
| 109 |
+
"learning_rate": 1.6828358208955223e-05,
|
| 110 |
+
"loss": 0.4565,
|
| 111 |
+
"step": 425
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.36,
|
| 115 |
+
"learning_rate": 1.6641791044776122e-05,
|
| 116 |
+
"loss": 0.4517,
|
| 117 |
+
"step": 450
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.54,
|
| 121 |
+
"learning_rate": 1.6455223880597015e-05,
|
| 122 |
+
"loss": 0.4791,
|
| 123 |
+
"step": 475
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 3.73,
|
| 127 |
+
"learning_rate": 1.626865671641791e-05,
|
| 128 |
+
"loss": 0.4519,
|
| 129 |
+
"step": 500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.92,
|
| 133 |
+
"learning_rate": 1.6082089552238806e-05,
|
| 134 |
+
"loss": 0.4671,
|
| 135 |
+
"step": 525
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.1,
|
| 139 |
+
"learning_rate": 1.5895522388059702e-05,
|
| 140 |
+
"loss": 0.438,
|
| 141 |
+
"step": 550
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.29,
|
| 145 |
+
"learning_rate": 1.5708955223880598e-05,
|
| 146 |
+
"loss": 0.3501,
|
| 147 |
+
"step": 575
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.48,
|
| 151 |
+
"learning_rate": 1.5522388059701494e-05,
|
| 152 |
+
"loss": 0.3944,
|
| 153 |
+
"step": 600
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.66,
|
| 157 |
+
"learning_rate": 1.533582089552239e-05,
|
| 158 |
+
"loss": 0.3881,
|
| 159 |
+
"step": 625
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.85,
|
| 163 |
+
"learning_rate": 1.5149253731343285e-05,
|
| 164 |
+
"loss": 0.3794,
|
| 165 |
+
"step": 650
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 5.04,
|
| 169 |
+
"learning_rate": 1.496268656716418e-05,
|
| 170 |
+
"loss": 0.3824,
|
| 171 |
+
"step": 675
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.22,
|
| 175 |
+
"learning_rate": 1.4776119402985077e-05,
|
| 176 |
+
"loss": 0.3098,
|
| 177 |
+
"step": 700
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.41,
|
| 181 |
+
"learning_rate": 1.4589552238805971e-05,
|
| 182 |
+
"loss": 0.2898,
|
| 183 |
+
"step": 725
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 5.6,
|
| 187 |
+
"learning_rate": 1.4402985074626867e-05,
|
| 188 |
+
"loss": 0.3009,
|
| 189 |
+
"step": 750
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 5.78,
|
| 193 |
+
"learning_rate": 1.4216417910447761e-05,
|
| 194 |
+
"loss": 0.3145,
|
| 195 |
+
"step": 775
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 5.97,
|
| 199 |
+
"learning_rate": 1.4029850746268658e-05,
|
| 200 |
+
"loss": 0.323,
|
| 201 |
+
"step": 800
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.16,
|
| 205 |
+
"learning_rate": 1.3843283582089553e-05,
|
| 206 |
+
"loss": 0.2488,
|
| 207 |
+
"step": 825
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.34,
|
| 211 |
+
"learning_rate": 1.365671641791045e-05,
|
| 212 |
+
"loss": 0.2145,
|
| 213 |
+
"step": 850
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 6.53,
|
| 217 |
+
"learning_rate": 1.3470149253731344e-05,
|
| 218 |
+
"loss": 0.2635,
|
| 219 |
+
"step": 875
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.72,
|
| 223 |
+
"learning_rate": 1.328358208955224e-05,
|
| 224 |
+
"loss": 0.2422,
|
| 225 |
+
"step": 900
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 6.9,
|
| 229 |
+
"learning_rate": 1.3097014925373134e-05,
|
| 230 |
+
"loss": 0.2691,
|
| 231 |
+
"step": 925
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 7.09,
|
| 235 |
+
"learning_rate": 1.2910447761194032e-05,
|
| 236 |
+
"loss": 0.2335,
|
| 237 |
+
"step": 950
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 7.28,
|
| 241 |
+
"learning_rate": 1.2723880597014926e-05,
|
| 242 |
+
"loss": 0.2011,
|
| 243 |
+
"step": 975
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 7.46,
|
| 247 |
+
"learning_rate": 1.2537313432835823e-05,
|
| 248 |
+
"loss": 0.1889,
|
| 249 |
+
"step": 1000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 7.65,
|
| 253 |
+
"learning_rate": 1.2350746268656717e-05,
|
| 254 |
+
"loss": 0.2176,
|
| 255 |
+
"step": 1025
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 7.84,
|
| 259 |
+
"learning_rate": 1.2164179104477613e-05,
|
| 260 |
+
"loss": 0.2217,
|
| 261 |
+
"step": 1050
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.02,
|
| 265 |
+
"learning_rate": 1.1977611940298509e-05,
|
| 266 |
+
"loss": 0.2057,
|
| 267 |
+
"step": 1075
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 8.21,
|
| 271 |
+
"learning_rate": 1.1791044776119405e-05,
|
| 272 |
+
"loss": 0.1614,
|
| 273 |
+
"step": 1100
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.4,
|
| 277 |
+
"learning_rate": 1.1604477611940299e-05,
|
| 278 |
+
"loss": 0.1548,
|
| 279 |
+
"step": 1125
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 8.58,
|
| 283 |
+
"learning_rate": 1.1417910447761196e-05,
|
| 284 |
+
"loss": 0.1576,
|
| 285 |
+
"step": 1150
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 8.77,
|
| 289 |
+
"learning_rate": 1.123134328358209e-05,
|
| 290 |
+
"loss": 0.1666,
|
| 291 |
+
"step": 1175
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 8.96,
|
| 295 |
+
"learning_rate": 1.1044776119402986e-05,
|
| 296 |
+
"loss": 0.1633,
|
| 297 |
+
"step": 1200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 9.14,
|
| 301 |
+
"learning_rate": 1.0858208955223882e-05,
|
| 302 |
+
"loss": 0.122,
|
| 303 |
+
"step": 1225
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 9.33,
|
| 307 |
+
"learning_rate": 1.0671641791044778e-05,
|
| 308 |
+
"loss": 0.1254,
|
| 309 |
+
"step": 1250
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 9.51,
|
| 313 |
+
"learning_rate": 1.0485074626865672e-05,
|
| 314 |
+
"loss": 0.1193,
|
| 315 |
+
"step": 1275
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 9.7,
|
| 319 |
+
"learning_rate": 1.029850746268657e-05,
|
| 320 |
+
"loss": 0.1602,
|
| 321 |
+
"step": 1300
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 9.89,
|
| 325 |
+
"learning_rate": 1.0111940298507463e-05,
|
| 326 |
+
"loss": 0.161,
|
| 327 |
+
"step": 1325
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 10.07,
|
| 331 |
+
"learning_rate": 9.925373134328359e-06,
|
| 332 |
+
"loss": 0.1128,
|
| 333 |
+
"step": 1350
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 10.26,
|
| 337 |
+
"learning_rate": 9.738805970149255e-06,
|
| 338 |
+
"loss": 0.0877,
|
| 339 |
+
"step": 1375
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 10.45,
|
| 343 |
+
"learning_rate": 9.552238805970149e-06,
|
| 344 |
+
"loss": 0.1165,
|
| 345 |
+
"step": 1400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 10.63,
|
| 349 |
+
"learning_rate": 9.365671641791045e-06,
|
| 350 |
+
"loss": 0.1232,
|
| 351 |
+
"step": 1425
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 10.82,
|
| 355 |
+
"learning_rate": 9.17910447761194e-06,
|
| 356 |
+
"loss": 0.1285,
|
| 357 |
+
"step": 1450
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 11.01,
|
| 361 |
+
"learning_rate": 8.992537313432836e-06,
|
| 362 |
+
"loss": 0.1214,
|
| 363 |
+
"step": 1475
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 11.19,
|
| 367 |
+
"learning_rate": 8.805970149253732e-06,
|
| 368 |
+
"loss": 0.0804,
|
| 369 |
+
"step": 1500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 11.38,
|
| 373 |
+
"learning_rate": 8.619402985074628e-06,
|
| 374 |
+
"loss": 0.105,
|
| 375 |
+
"step": 1525
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 11.57,
|
| 379 |
+
"learning_rate": 8.432835820895524e-06,
|
| 380 |
+
"loss": 0.0885,
|
| 381 |
+
"step": 1550
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 11.75,
|
| 385 |
+
"learning_rate": 8.246268656716418e-06,
|
| 386 |
+
"loss": 0.1015,
|
| 387 |
+
"step": 1575
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 11.94,
|
| 391 |
+
"learning_rate": 8.059701492537314e-06,
|
| 392 |
+
"loss": 0.101,
|
| 393 |
+
"step": 1600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 12.13,
|
| 397 |
+
"learning_rate": 7.87313432835821e-06,
|
| 398 |
+
"loss": 0.1017,
|
| 399 |
+
"step": 1625
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 12.31,
|
| 403 |
+
"learning_rate": 7.686567164179105e-06,
|
| 404 |
+
"loss": 0.08,
|
| 405 |
+
"step": 1650
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 12.5,
|
| 409 |
+
"learning_rate": 7.500000000000001e-06,
|
| 410 |
+
"loss": 0.1013,
|
| 411 |
+
"step": 1675
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 12.69,
|
| 415 |
+
"learning_rate": 7.313432835820896e-06,
|
| 416 |
+
"loss": 0.088,
|
| 417 |
+
"step": 1700
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 12.87,
|
| 421 |
+
"learning_rate": 7.126865671641792e-06,
|
| 422 |
+
"loss": 0.0816,
|
| 423 |
+
"step": 1725
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 13.06,
|
| 427 |
+
"learning_rate": 6.9402985074626876e-06,
|
| 428 |
+
"loss": 0.0657,
|
| 429 |
+
"step": 1750
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 13.25,
|
| 433 |
+
"learning_rate": 6.7537313432835825e-06,
|
| 434 |
+
"loss": 0.0765,
|
| 435 |
+
"step": 1775
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 13.43,
|
| 439 |
+
"learning_rate": 6.567164179104478e-06,
|
| 440 |
+
"loss": 0.0655,
|
| 441 |
+
"step": 1800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 13.62,
|
| 445 |
+
"learning_rate": 6.380597014925374e-06,
|
| 446 |
+
"loss": 0.0854,
|
| 447 |
+
"step": 1825
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 13.81,
|
| 451 |
+
"learning_rate": 6.194029850746269e-06,
|
| 452 |
+
"loss": 0.0792,
|
| 453 |
+
"step": 1850
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 13.99,
|
| 457 |
+
"learning_rate": 6.007462686567165e-06,
|
| 458 |
+
"loss": 0.0778,
|
| 459 |
+
"step": 1875
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 14.18,
|
| 463 |
+
"learning_rate": 5.820895522388061e-06,
|
| 464 |
+
"loss": 0.049,
|
| 465 |
+
"step": 1900
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 14.37,
|
| 469 |
+
"learning_rate": 5.6343283582089556e-06,
|
| 470 |
+
"loss": 0.0625,
|
| 471 |
+
"step": 1925
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 14.55,
|
| 475 |
+
"learning_rate": 5.447761194029851e-06,
|
| 476 |
+
"loss": 0.0655,
|
| 477 |
+
"step": 1950
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 14.74,
|
| 481 |
+
"learning_rate": 5.261194029850747e-06,
|
| 482 |
+
"loss": 0.0636,
|
| 483 |
+
"step": 1975
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 14.93,
|
| 487 |
+
"learning_rate": 5.074626865671642e-06,
|
| 488 |
+
"loss": 0.0548,
|
| 489 |
+
"step": 2000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 15.11,
|
| 493 |
+
"learning_rate": 4.888059701492538e-06,
|
| 494 |
+
"loss": 0.0509,
|
| 495 |
+
"step": 2025
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 15.3,
|
| 499 |
+
"learning_rate": 4.701492537313434e-06,
|
| 500 |
+
"loss": 0.0424,
|
| 501 |
+
"step": 2050
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 15.49,
|
| 505 |
+
"learning_rate": 4.514925373134329e-06,
|
| 506 |
+
"loss": 0.0566,
|
| 507 |
+
"step": 2075
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 15.67,
|
| 511 |
+
"learning_rate": 4.3283582089552236e-06,
|
| 512 |
+
"loss": 0.0547,
|
| 513 |
+
"step": 2100
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 15.86,
|
| 517 |
+
"learning_rate": 4.141791044776119e-06,
|
| 518 |
+
"loss": 0.0612,
|
| 519 |
+
"step": 2125
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 16.04,
|
| 523 |
+
"learning_rate": 3.955223880597015e-06,
|
| 524 |
+
"loss": 0.0502,
|
| 525 |
+
"step": 2150
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 16.23,
|
| 529 |
+
"learning_rate": 3.7686567164179105e-06,
|
| 530 |
+
"loss": 0.0392,
|
| 531 |
+
"step": 2175
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 16.42,
|
| 535 |
+
"learning_rate": 3.582089552238806e-06,
|
| 536 |
+
"loss": 0.0346,
|
| 537 |
+
"step": 2200
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 16.6,
|
| 541 |
+
"learning_rate": 3.3955223880597017e-06,
|
| 542 |
+
"loss": 0.043,
|
| 543 |
+
"step": 2225
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 16.79,
|
| 547 |
+
"learning_rate": 3.208955223880597e-06,
|
| 548 |
+
"loss": 0.0498,
|
| 549 |
+
"step": 2250
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 16.98,
|
| 553 |
+
"learning_rate": 3.022388059701493e-06,
|
| 554 |
+
"loss": 0.0511,
|
| 555 |
+
"step": 2275
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 17.16,
|
| 559 |
+
"learning_rate": 2.835820895522388e-06,
|
| 560 |
+
"loss": 0.0358,
|
| 561 |
+
"step": 2300
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 17.35,
|
| 565 |
+
"learning_rate": 2.6492537313432836e-06,
|
| 566 |
+
"loss": 0.0345,
|
| 567 |
+
"step": 2325
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 17.54,
|
| 571 |
+
"learning_rate": 2.4626865671641794e-06,
|
| 572 |
+
"loss": 0.0267,
|
| 573 |
+
"step": 2350
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 17.72,
|
| 577 |
+
"learning_rate": 2.2761194029850747e-06,
|
| 578 |
+
"loss": 0.0237,
|
| 579 |
+
"step": 2375
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 17.91,
|
| 583 |
+
"learning_rate": 2.08955223880597e-06,
|
| 584 |
+
"loss": 0.0383,
|
| 585 |
+
"step": 2400
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 18.1,
|
| 589 |
+
"learning_rate": 1.9029850746268657e-06,
|
| 590 |
+
"loss": 0.0396,
|
| 591 |
+
"step": 2425
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 18.28,
|
| 595 |
+
"learning_rate": 1.7164179104477613e-06,
|
| 596 |
+
"loss": 0.0361,
|
| 597 |
+
"step": 2450
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 18.47,
|
| 601 |
+
"learning_rate": 1.5298507462686568e-06,
|
| 602 |
+
"loss": 0.0279,
|
| 603 |
+
"step": 2475
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 18.66,
|
| 607 |
+
"learning_rate": 1.3432835820895524e-06,
|
| 608 |
+
"loss": 0.0385,
|
| 609 |
+
"step": 2500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 18.84,
|
| 613 |
+
"learning_rate": 1.1567164179104478e-06,
|
| 614 |
+
"loss": 0.0313,
|
| 615 |
+
"step": 2525
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 19.03,
|
| 619 |
+
"learning_rate": 9.701492537313434e-07,
|
| 620 |
+
"loss": 0.0357,
|
| 621 |
+
"step": 2550
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 19.22,
|
| 625 |
+
"learning_rate": 7.835820895522389e-07,
|
| 626 |
+
"loss": 0.0366,
|
| 627 |
+
"step": 2575
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 19.4,
|
| 631 |
+
"learning_rate": 5.970149253731343e-07,
|
| 632 |
+
"loss": 0.0236,
|
| 633 |
+
"step": 2600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 19.59,
|
| 637 |
+
"learning_rate": 4.104477611940299e-07,
|
| 638 |
+
"loss": 0.0205,
|
| 639 |
+
"step": 2625
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 19.78,
|
| 643 |
+
"learning_rate": 2.2388059701492537e-07,
|
| 644 |
+
"loss": 0.035,
|
| 645 |
+
"step": 2650
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 19.96,
|
| 649 |
+
"learning_rate": 3.7313432835820895e-08,
|
| 650 |
+
"loss": 0.0303,
|
| 651 |
+
"step": 2675
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 20.0,
|
| 655 |
+
"step": 2680,
|
| 656 |
+
"total_flos": 1.12493131719168e+16,
|
| 657 |
+
"train_loss": 0.2142893238688138,
|
| 658 |
+
"train_runtime": 3029.2991,
|
| 659 |
+
"train_samples_per_second": 56.455,
|
| 660 |
+
"train_steps_per_second": 0.885
|
| 661 |
+
}
|
| 662 |
+
],
|
| 663 |
+
"logging_steps": 25,
|
| 664 |
+
"max_steps": 2680,
|
| 665 |
+
"num_train_epochs": 20,
|
| 666 |
+
"save_steps": 500,
|
| 667 |
+
"total_flos": 1.12493131719168e+16,
|
| 668 |
+
"trial_name": null,
|
| 669 |
+
"trial_params": null
|
| 670 |
+
}
|