End of training
Browse files- README.md +4 -4
- all_results.json +18 -0
- eval_results.json +12 -0
- train_results.json +9 -0
- trainer_state.json +651 -0
README.md
CHANGED
|
@@ -4,7 +4,7 @@ base_model: xlm-roberta-base
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
-
- universal_ner
|
| 8 |
metrics:
|
| 9 |
- precision
|
| 10 |
- recall
|
|
@@ -17,8 +17,8 @@ model-index:
|
|
| 17 |
name: Token Classification
|
| 18 |
type: token-classification
|
| 19 |
dataset:
|
| 20 |
-
name: universal_ner
|
| 21 |
-
type: universal_ner
|
| 22 |
config: en_ewt
|
| 23 |
split: validation
|
| 24 |
args: en_ewt
|
|
@@ -42,7 +42,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 42 |
|
| 43 |
# UNER_subword_tk_en_lora_alpha_1024_drop_0.3_rank_512_seed_42
|
| 44 |
|
| 45 |
-
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the universal_ner dataset.
|
| 46 |
It achieves the following results on the evaluation set:
|
| 47 |
- Loss: 0.0633
|
| 48 |
- Precision: 0.7732
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
+
- universalner/universal_ner
|
| 8 |
metrics:
|
| 9 |
- precision
|
| 10 |
- recall
|
|
|
|
| 17 |
name: Token Classification
|
| 18 |
type: token-classification
|
| 19 |
dataset:
|
| 20 |
+
name: universalner/universal_ner en_ewt
|
| 21 |
+
type: universalner/universal_ner
|
| 22 |
config: en_ewt
|
| 23 |
split: validation
|
| 24 |
args: en_ewt
|
|
|
|
| 42 |
|
| 43 |
# UNER_subword_tk_en_lora_alpha_1024_drop_0.3_rank_512_seed_42
|
| 44 |
|
| 45 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the universalner/universal_ner en_ewt dataset.
|
| 46 |
It achieves the following results on the evaluation set:
|
| 47 |
- Loss: 0.0633
|
| 48 |
- Precision: 0.7732
|
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"eval_accuracy": 0.9844128991212374,
|
| 4 |
+
"eval_f1": 0.8001998001998001,
|
| 5 |
+
"eval_loss": 0.06326296180486679,
|
| 6 |
+
"eval_precision": 0.7731660231660231,
|
| 7 |
+
"eval_recall": 0.8291925465838509,
|
| 8 |
+
"eval_runtime": 1.9481,
|
| 9 |
+
"eval_samples": 2001,
|
| 10 |
+
"eval_samples_per_second": 1027.174,
|
| 11 |
+
"eval_steps_per_second": 32.34,
|
| 12 |
+
"total_flos": 1.8599928536379036e+16,
|
| 13 |
+
"train_loss": 0.03749203296166467,
|
| 14 |
+
"train_runtime": 1114.592,
|
| 15 |
+
"train_samples": 12543,
|
| 16 |
+
"train_samples_per_second": 393.871,
|
| 17 |
+
"train_steps_per_second": 12.309
|
| 18 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"eval_accuracy": 0.9844128991212374,
|
| 4 |
+
"eval_f1": 0.8001998001998001,
|
| 5 |
+
"eval_loss": 0.06326296180486679,
|
| 6 |
+
"eval_precision": 0.7731660231660231,
|
| 7 |
+
"eval_recall": 0.8291925465838509,
|
| 8 |
+
"eval_runtime": 1.9481,
|
| 9 |
+
"eval_samples": 2001,
|
| 10 |
+
"eval_samples_per_second": 1027.174,
|
| 11 |
+
"eval_steps_per_second": 32.34
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"total_flos": 1.8599928536379036e+16,
|
| 4 |
+
"train_loss": 0.03749203296166467,
|
| 5 |
+
"train_runtime": 1114.592,
|
| 6 |
+
"train_samples": 12543,
|
| 7 |
+
"train_samples_per_second": 393.871,
|
| 8 |
+
"train_steps_per_second": 12.309
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,651 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 35.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 13720,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.9568571314962822,
|
| 14 |
+
"eval_f1": 0.3342198581560284,
|
| 15 |
+
"eval_loss": 0.13618186116218567,
|
| 16 |
+
"eval_precision": 0.29224806201550385,
|
| 17 |
+
"eval_recall": 0.39026915113871635,
|
| 18 |
+
"eval_runtime": 1.9412,
|
| 19 |
+
"eval_samples_per_second": 1030.806,
|
| 20 |
+
"eval_steps_per_second": 32.454,
|
| 21 |
+
"step": 392
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.2755102040816326,
|
| 25 |
+
"grad_norm": 2.648585557937622,
|
| 26 |
+
"learning_rate": 9.635568513119534e-06,
|
| 27 |
+
"loss": 0.2046,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_accuracy": 0.9744721460097817,
|
| 33 |
+
"eval_f1": 0.6309238870272857,
|
| 34 |
+
"eval_loss": 0.08885405957698822,
|
| 35 |
+
"eval_precision": 0.5868210151380232,
|
| 36 |
+
"eval_recall": 0.6821946169772257,
|
| 37 |
+
"eval_runtime": 1.9272,
|
| 38 |
+
"eval_samples_per_second": 1038.274,
|
| 39 |
+
"eval_steps_per_second": 32.689,
|
| 40 |
+
"step": 784
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.5510204081632653,
|
| 44 |
+
"grad_norm": 1.4755271673202515,
|
| 45 |
+
"learning_rate": 9.271137026239068e-06,
|
| 46 |
+
"loss": 0.085,
|
| 47 |
+
"step": 1000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"eval_accuracy": 0.977772476042785,
|
| 52 |
+
"eval_f1": 0.7259820160908661,
|
| 53 |
+
"eval_loss": 0.07718591392040253,
|
| 54 |
+
"eval_precision": 0.6687009590235397,
|
| 55 |
+
"eval_recall": 0.7939958592132506,
|
| 56 |
+
"eval_runtime": 1.9263,
|
| 57 |
+
"eval_samples_per_second": 1038.801,
|
| 58 |
+
"eval_steps_per_second": 32.706,
|
| 59 |
+
"step": 1176
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.826530612244898,
|
| 63 |
+
"grad_norm": 4.245046138763428,
|
| 64 |
+
"learning_rate": 8.906705539358601e-06,
|
| 65 |
+
"loss": 0.0591,
|
| 66 |
+
"step": 1500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"eval_accuracy": 0.980237782814426,
|
| 71 |
+
"eval_f1": 0.7492682926829267,
|
| 72 |
+
"eval_loss": 0.06919107586145401,
|
| 73 |
+
"eval_precision": 0.7084870848708487,
|
| 74 |
+
"eval_recall": 0.7950310559006211,
|
| 75 |
+
"eval_runtime": 1.9307,
|
| 76 |
+
"eval_samples_per_second": 1036.399,
|
| 77 |
+
"eval_steps_per_second": 32.63,
|
| 78 |
+
"step": 1568
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.9790846554534972,
|
| 83 |
+
"eval_f1": 0.7511781338360038,
|
| 84 |
+
"eval_loss": 0.06915295869112015,
|
| 85 |
+
"eval_precision": 0.6894463667820069,
|
| 86 |
+
"eval_recall": 0.8250517598343685,
|
| 87 |
+
"eval_runtime": 1.9302,
|
| 88 |
+
"eval_samples_per_second": 1036.671,
|
| 89 |
+
"eval_steps_per_second": 32.639,
|
| 90 |
+
"step": 1960
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.1020408163265305,
|
| 94 |
+
"grad_norm": 1.7189973592758179,
|
| 95 |
+
"learning_rate": 8.542274052478135e-06,
|
| 96 |
+
"loss": 0.0496,
|
| 97 |
+
"step": 2000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 6.0,
|
| 101 |
+
"eval_accuracy": 0.979124418465943,
|
| 102 |
+
"eval_f1": 0.7497621313035204,
|
| 103 |
+
"eval_loss": 0.06637787073850632,
|
| 104 |
+
"eval_precision": 0.6936619718309859,
|
| 105 |
+
"eval_recall": 0.8157349896480331,
|
| 106 |
+
"eval_runtime": 1.9308,
|
| 107 |
+
"eval_samples_per_second": 1036.355,
|
| 108 |
+
"eval_steps_per_second": 32.629,
|
| 109 |
+
"step": 2352
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.377551020408164,
|
| 113 |
+
"grad_norm": 1.5220848321914673,
|
| 114 |
+
"learning_rate": 8.177842565597668e-06,
|
| 115 |
+
"loss": 0.0448,
|
| 116 |
+
"step": 2500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.0,
|
| 120 |
+
"eval_accuracy": 0.9797208636526303,
|
| 121 |
+
"eval_f1": 0.7604166666666666,
|
| 122 |
+
"eval_loss": 0.06713752448558807,
|
| 123 |
+
"eval_precision": 0.7006980802792321,
|
| 124 |
+
"eval_recall": 0.8312629399585921,
|
| 125 |
+
"eval_runtime": 1.9273,
|
| 126 |
+
"eval_samples_per_second": 1038.241,
|
| 127 |
+
"eval_steps_per_second": 32.688,
|
| 128 |
+
"step": 2744
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.653061224489796,
|
| 132 |
+
"grad_norm": 1.4208240509033203,
|
| 133 |
+
"learning_rate": 7.813411078717202e-06,
|
| 134 |
+
"loss": 0.0409,
|
| 135 |
+
"step": 3000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.0,
|
| 139 |
+
"eval_accuracy": 0.9814306731878008,
|
| 140 |
+
"eval_f1": 0.7644487615347257,
|
| 141 |
+
"eval_loss": 0.06736838817596436,
|
| 142 |
+
"eval_precision": 0.7200365965233303,
|
| 143 |
+
"eval_recall": 0.8146997929606625,
|
| 144 |
+
"eval_runtime": 1.9354,
|
| 145 |
+
"eval_samples_per_second": 1033.894,
|
| 146 |
+
"eval_steps_per_second": 32.551,
|
| 147 |
+
"step": 3136
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 8.928571428571429,
|
| 151 |
+
"grad_norm": 2.406752586364746,
|
| 152 |
+
"learning_rate": 7.448979591836736e-06,
|
| 153 |
+
"loss": 0.0388,
|
| 154 |
+
"step": 3500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 9.0,
|
| 158 |
+
"eval_accuracy": 0.981589725237584,
|
| 159 |
+
"eval_f1": 0.7848586487781506,
|
| 160 |
+
"eval_loss": 0.06350778043270111,
|
| 161 |
+
"eval_precision": 0.7305976806422837,
|
| 162 |
+
"eval_recall": 0.8478260869565217,
|
| 163 |
+
"eval_runtime": 1.9339,
|
| 164 |
+
"eval_samples_per_second": 1034.68,
|
| 165 |
+
"eval_steps_per_second": 32.576,
|
| 166 |
+
"step": 3528
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 10.0,
|
| 170 |
+
"eval_accuracy": 0.9832200087478628,
|
| 171 |
+
"eval_f1": 0.7828232971372162,
|
| 172 |
+
"eval_loss": 0.061989493668079376,
|
| 173 |
+
"eval_precision": 0.7481132075471698,
|
| 174 |
+
"eval_recall": 0.8209109730848861,
|
| 175 |
+
"eval_runtime": 1.9323,
|
| 176 |
+
"eval_samples_per_second": 1035.558,
|
| 177 |
+
"eval_steps_per_second": 32.604,
|
| 178 |
+
"step": 3920
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 10.204081632653061,
|
| 182 |
+
"grad_norm": 1.2731356620788574,
|
| 183 |
+
"learning_rate": 7.084548104956269e-06,
|
| 184 |
+
"loss": 0.0357,
|
| 185 |
+
"step": 4000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 11.0,
|
| 189 |
+
"eval_accuracy": 0.9843731361087916,
|
| 190 |
+
"eval_f1": 0.7991967871485944,
|
| 191 |
+
"eval_loss": 0.05860035866498947,
|
| 192 |
+
"eval_precision": 0.7758284600389863,
|
| 193 |
+
"eval_recall": 0.8240165631469979,
|
| 194 |
+
"eval_runtime": 1.927,
|
| 195 |
+
"eval_samples_per_second": 1038.4,
|
| 196 |
+
"eval_steps_per_second": 32.693,
|
| 197 |
+
"step": 4312
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 11.479591836734693,
|
| 201 |
+
"grad_norm": 2.450951337814331,
|
| 202 |
+
"learning_rate": 6.720116618075803e-06,
|
| 203 |
+
"loss": 0.0333,
|
| 204 |
+
"step": 4500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 12.0,
|
| 208 |
+
"eval_accuracy": 0.9839755059843334,
|
| 209 |
+
"eval_f1": 0.7962506166748891,
|
| 210 |
+
"eval_loss": 0.06108121573925018,
|
| 211 |
+
"eval_precision": 0.760603204524034,
|
| 212 |
+
"eval_recall": 0.8354037267080745,
|
| 213 |
+
"eval_runtime": 1.928,
|
| 214 |
+
"eval_samples_per_second": 1037.838,
|
| 215 |
+
"eval_steps_per_second": 32.676,
|
| 216 |
+
"step": 4704
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 12.755102040816327,
|
| 220 |
+
"grad_norm": 0.4314533472061157,
|
| 221 |
+
"learning_rate": 6.355685131195336e-06,
|
| 222 |
+
"loss": 0.0323,
|
| 223 |
+
"step": 5000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 13.0,
|
| 227 |
+
"eval_accuracy": 0.9844128991212374,
|
| 228 |
+
"eval_f1": 0.8024193548387095,
|
| 229 |
+
"eval_loss": 0.060124173760414124,
|
| 230 |
+
"eval_precision": 0.7819253438113949,
|
| 231 |
+
"eval_recall": 0.8240165631469979,
|
| 232 |
+
"eval_runtime": 1.9272,
|
| 233 |
+
"eval_samples_per_second": 1038.313,
|
| 234 |
+
"eval_steps_per_second": 32.691,
|
| 235 |
+
"step": 5096
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 14.0,
|
| 239 |
+
"eval_accuracy": 0.9812318581255716,
|
| 240 |
+
"eval_f1": 0.7709335899903753,
|
| 241 |
+
"eval_loss": 0.06381431967020035,
|
| 242 |
+
"eval_precision": 0.7203237410071942,
|
| 243 |
+
"eval_recall": 0.8291925465838509,
|
| 244 |
+
"eval_runtime": 1.9343,
|
| 245 |
+
"eval_samples_per_second": 1034.476,
|
| 246 |
+
"eval_steps_per_second": 32.57,
|
| 247 |
+
"step": 5488
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 14.03061224489796,
|
| 251 |
+
"grad_norm": 3.0114917755126953,
|
| 252 |
+
"learning_rate": 5.99125364431487e-06,
|
| 253 |
+
"loss": 0.0303,
|
| 254 |
+
"step": 5500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 15.0,
|
| 258 |
+
"eval_accuracy": 0.9841345580341166,
|
| 259 |
+
"eval_f1": 0.8033847685415629,
|
| 260 |
+
"eval_loss": 0.06001782789826393,
|
| 261 |
+
"eval_precision": 0.7737296260786194,
|
| 262 |
+
"eval_recall": 0.8354037267080745,
|
| 263 |
+
"eval_runtime": 1.93,
|
| 264 |
+
"eval_samples_per_second": 1036.805,
|
| 265 |
+
"eval_steps_per_second": 32.643,
|
| 266 |
+
"step": 5880
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 15.306122448979592,
|
| 270 |
+
"grad_norm": 1.2943487167358398,
|
| 271 |
+
"learning_rate": 5.626822157434403e-06,
|
| 272 |
+
"loss": 0.0293,
|
| 273 |
+
"step": 6000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 16.0,
|
| 277 |
+
"eval_accuracy": 0.9840947950216709,
|
| 278 |
+
"eval_f1": 0.8005967180507211,
|
| 279 |
+
"eval_loss": 0.06019486486911774,
|
| 280 |
+
"eval_precision": 0.7703349282296651,
|
| 281 |
+
"eval_recall": 0.8333333333333334,
|
| 282 |
+
"eval_runtime": 1.9397,
|
| 283 |
+
"eval_samples_per_second": 1031.583,
|
| 284 |
+
"eval_steps_per_second": 32.479,
|
| 285 |
+
"step": 6272
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 16.581632653061224,
|
| 289 |
+
"grad_norm": 2.0324342250823975,
|
| 290 |
+
"learning_rate": 5.262390670553936e-06,
|
| 291 |
+
"loss": 0.0271,
|
| 292 |
+
"step": 6500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 17.0,
|
| 296 |
+
"eval_accuracy": 0.9841345580341166,
|
| 297 |
+
"eval_f1": 0.8005908419497785,
|
| 298 |
+
"eval_loss": 0.06088220328092575,
|
| 299 |
+
"eval_precision": 0.7633802816901408,
|
| 300 |
+
"eval_recall": 0.8416149068322981,
|
| 301 |
+
"eval_runtime": 1.9366,
|
| 302 |
+
"eval_samples_per_second": 1033.261,
|
| 303 |
+
"eval_steps_per_second": 32.531,
|
| 304 |
+
"step": 6664
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 17.857142857142858,
|
| 308 |
+
"grad_norm": 3.486292600631714,
|
| 309 |
+
"learning_rate": 4.897959183673469e-06,
|
| 310 |
+
"loss": 0.0269,
|
| 311 |
+
"step": 7000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 18.0,
|
| 315 |
+
"eval_accuracy": 0.9834585868225377,
|
| 316 |
+
"eval_f1": 0.7998046875,
|
| 317 |
+
"eval_loss": 0.06408777087926865,
|
| 318 |
+
"eval_precision": 0.7569316081330869,
|
| 319 |
+
"eval_recall": 0.8478260869565217,
|
| 320 |
+
"eval_runtime": 1.9311,
|
| 321 |
+
"eval_samples_per_second": 1036.171,
|
| 322 |
+
"eval_steps_per_second": 32.623,
|
| 323 |
+
"step": 7056
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 19.0,
|
| 327 |
+
"eval_accuracy": 0.9848502922581415,
|
| 328 |
+
"eval_f1": 0.8020100502512563,
|
| 329 |
+
"eval_loss": 0.05937599018216133,
|
| 330 |
+
"eval_precision": 0.779296875,
|
| 331 |
+
"eval_recall": 0.8260869565217391,
|
| 332 |
+
"eval_runtime": 1.9293,
|
| 333 |
+
"eval_samples_per_second": 1037.174,
|
| 334 |
+
"eval_steps_per_second": 32.655,
|
| 335 |
+
"step": 7448
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 19.132653061224488,
|
| 339 |
+
"grad_norm": 1.497888207435608,
|
| 340 |
+
"learning_rate": 4.533527696793003e-06,
|
| 341 |
+
"loss": 0.0263,
|
| 342 |
+
"step": 7500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 20.0,
|
| 346 |
+
"eval_accuracy": 0.9850491073203705,
|
| 347 |
+
"eval_f1": 0.8032454361054765,
|
| 348 |
+
"eval_loss": 0.060807984322309494,
|
| 349 |
+
"eval_precision": 0.7872763419483101,
|
| 350 |
+
"eval_recall": 0.8198757763975155,
|
| 351 |
+
"eval_runtime": 1.9313,
|
| 352 |
+
"eval_samples_per_second": 1036.1,
|
| 353 |
+
"eval_steps_per_second": 32.621,
|
| 354 |
+
"step": 7840
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 20.408163265306122,
|
| 358 |
+
"grad_norm": 1.9022024869918823,
|
| 359 |
+
"learning_rate": 4.169096209912537e-06,
|
| 360 |
+
"loss": 0.025,
|
| 361 |
+
"step": 8000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 21.0,
|
| 365 |
+
"eval_accuracy": 0.984969581295479,
|
| 366 |
+
"eval_f1": 0.802015113350126,
|
| 367 |
+
"eval_loss": 0.06064474582672119,
|
| 368 |
+
"eval_precision": 0.7811579980372915,
|
| 369 |
+
"eval_recall": 0.8240165631469979,
|
| 370 |
+
"eval_runtime": 1.9348,
|
| 371 |
+
"eval_samples_per_second": 1034.204,
|
| 372 |
+
"eval_steps_per_second": 32.561,
|
| 373 |
+
"step": 8232
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 21.683673469387756,
|
| 377 |
+
"grad_norm": 4.527287006378174,
|
| 378 |
+
"learning_rate": 3.8046647230320706e-06,
|
| 379 |
+
"loss": 0.0236,
|
| 380 |
+
"step": 8500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 22.0,
|
| 384 |
+
"eval_accuracy": 0.9839357429718876,
|
| 385 |
+
"eval_f1": 0.7941031941031941,
|
| 386 |
+
"eval_loss": 0.06386730074882507,
|
| 387 |
+
"eval_precision": 0.7558465855940131,
|
| 388 |
+
"eval_recall": 0.8364389233954451,
|
| 389 |
+
"eval_runtime": 1.9347,
|
| 390 |
+
"eval_samples_per_second": 1034.248,
|
| 391 |
+
"eval_steps_per_second": 32.563,
|
| 392 |
+
"step": 8624
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 22.959183673469386,
|
| 396 |
+
"grad_norm": 1.3462114334106445,
|
| 397 |
+
"learning_rate": 3.440233236151604e-06,
|
| 398 |
+
"loss": 0.0228,
|
| 399 |
+
"step": 9000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 23.0,
|
| 403 |
+
"eval_accuracy": 0.9844924251461291,
|
| 404 |
+
"eval_f1": 0.8005937654626424,
|
| 405 |
+
"eval_loss": 0.0619705505669117,
|
| 406 |
+
"eval_precision": 0.7668246445497631,
|
| 407 |
+
"eval_recall": 0.8374741200828157,
|
| 408 |
+
"eval_runtime": 2.0856,
|
| 409 |
+
"eval_samples_per_second": 959.448,
|
| 410 |
+
"eval_steps_per_second": 30.207,
|
| 411 |
+
"step": 9016
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 24.0,
|
| 415 |
+
"eval_accuracy": 0.9842140840590083,
|
| 416 |
+
"eval_f1": 0.7980198019801981,
|
| 417 |
+
"eval_loss": 0.061182938516139984,
|
| 418 |
+
"eval_precision": 0.7647058823529411,
|
| 419 |
+
"eval_recall": 0.8343685300207039,
|
| 420 |
+
"eval_runtime": 1.9322,
|
| 421 |
+
"eval_samples_per_second": 1035.611,
|
| 422 |
+
"eval_steps_per_second": 32.605,
|
| 423 |
+
"step": 9408
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 24.23469387755102,
|
| 427 |
+
"grad_norm": 1.7153197526931763,
|
| 428 |
+
"learning_rate": 3.075801749271137e-06,
|
| 429 |
+
"loss": 0.0229,
|
| 430 |
+
"step": 9500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 25.0,
|
| 434 |
+
"eval_accuracy": 0.9838959799594418,
|
| 435 |
+
"eval_f1": 0.7964601769911506,
|
| 436 |
+
"eval_loss": 0.06181613728404045,
|
| 437 |
+
"eval_precision": 0.7584269662921348,
|
| 438 |
+
"eval_recall": 0.8385093167701864,
|
| 439 |
+
"eval_runtime": 1.9325,
|
| 440 |
+
"eval_samples_per_second": 1035.42,
|
| 441 |
+
"eval_steps_per_second": 32.599,
|
| 442 |
+
"step": 9800
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 25.510204081632654,
|
| 446 |
+
"grad_norm": 1.0961247682571411,
|
| 447 |
+
"learning_rate": 2.7113702623906706e-06,
|
| 448 |
+
"loss": 0.0227,
|
| 449 |
+
"step": 10000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 26.0,
|
| 453 |
+
"eval_accuracy": 0.9842140840590083,
|
| 454 |
+
"eval_f1": 0.8015833745670461,
|
| 455 |
+
"eval_loss": 0.06314929574728012,
|
| 456 |
+
"eval_precision": 0.7677725118483413,
|
| 457 |
+
"eval_recall": 0.8385093167701864,
|
| 458 |
+
"eval_runtime": 1.9308,
|
| 459 |
+
"eval_samples_per_second": 1036.345,
|
| 460 |
+
"eval_steps_per_second": 32.629,
|
| 461 |
+
"step": 10192
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 26.785714285714285,
|
| 465 |
+
"grad_norm": 2.071167230606079,
|
| 466 |
+
"learning_rate": 2.3469387755102044e-06,
|
| 467 |
+
"loss": 0.0216,
|
| 468 |
+
"step": 10500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 27.0,
|
| 472 |
+
"eval_accuracy": 0.984969581295479,
|
| 473 |
+
"eval_f1": 0.8116524359618282,
|
| 474 |
+
"eval_loss": 0.062842957675457,
|
| 475 |
+
"eval_precision": 0.7882926829268293,
|
| 476 |
+
"eval_recall": 0.8364389233954451,
|
| 477 |
+
"eval_runtime": 1.9298,
|
| 478 |
+
"eval_samples_per_second": 1036.891,
|
| 479 |
+
"eval_steps_per_second": 32.646,
|
| 480 |
+
"step": 10584
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 28.0,
|
| 484 |
+
"eval_accuracy": 0.9849298182830332,
|
| 485 |
+
"eval_f1": 0.8043912175648702,
|
| 486 |
+
"eval_loss": 0.061074595898389816,
|
| 487 |
+
"eval_precision": 0.7764932562620424,
|
| 488 |
+
"eval_recall": 0.8343685300207039,
|
| 489 |
+
"eval_runtime": 1.9287,
|
| 490 |
+
"eval_samples_per_second": 1037.465,
|
| 491 |
+
"eval_steps_per_second": 32.664,
|
| 492 |
+
"step": 10976
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 28.06122448979592,
|
| 496 |
+
"grad_norm": 0.31353890895843506,
|
| 497 |
+
"learning_rate": 1.982507288629738e-06,
|
| 498 |
+
"loss": 0.0203,
|
| 499 |
+
"step": 11000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 29.0,
|
| 503 |
+
"eval_accuracy": 0.9846514771959124,
|
| 504 |
+
"eval_f1": 0.8067560854446101,
|
| 505 |
+
"eval_loss": 0.06154615432024002,
|
| 506 |
+
"eval_precision": 0.775549188156638,
|
| 507 |
+
"eval_recall": 0.8405797101449275,
|
| 508 |
+
"eval_runtime": 1.9351,
|
| 509 |
+
"eval_samples_per_second": 1034.041,
|
| 510 |
+
"eval_steps_per_second": 32.556,
|
| 511 |
+
"step": 11368
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 29.336734693877553,
|
| 515 |
+
"grad_norm": 1.2790480852127075,
|
| 516 |
+
"learning_rate": 1.6180758017492712e-06,
|
| 517 |
+
"loss": 0.02,
|
| 518 |
+
"step": 11500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 30.0,
|
| 522 |
+
"eval_accuracy": 0.984731003220804,
|
| 523 |
+
"eval_f1": 0.8031888390632785,
|
| 524 |
+
"eval_loss": 0.06289386004209518,
|
| 525 |
+
"eval_precision": 0.7742555235350624,
|
| 526 |
+
"eval_recall": 0.8343685300207039,
|
| 527 |
+
"eval_runtime": 1.9333,
|
| 528 |
+
"eval_samples_per_second": 1035.02,
|
| 529 |
+
"eval_steps_per_second": 32.587,
|
| 530 |
+
"step": 11760
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 30.612244897959183,
|
| 534 |
+
"grad_norm": 0.9062312841415405,
|
| 535 |
+
"learning_rate": 1.2536443148688048e-06,
|
| 536 |
+
"loss": 0.0197,
|
| 537 |
+
"step": 12000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 31.0,
|
| 541 |
+
"eval_accuracy": 0.9843333730963458,
|
| 542 |
+
"eval_f1": 0.8037943085371941,
|
| 543 |
+
"eval_loss": 0.061957862228155136,
|
| 544 |
+
"eval_precision": 0.7762777242044359,
|
| 545 |
+
"eval_recall": 0.8333333333333334,
|
| 546 |
+
"eval_runtime": 1.9331,
|
| 547 |
+
"eval_samples_per_second": 1035.13,
|
| 548 |
+
"eval_steps_per_second": 32.59,
|
| 549 |
+
"step": 12152
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 31.887755102040817,
|
| 553 |
+
"grad_norm": 1.8540356159210205,
|
| 554 |
+
"learning_rate": 8.892128279883383e-07,
|
| 555 |
+
"loss": 0.0197,
|
| 556 |
+
"step": 12500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 32.0,
|
| 560 |
+
"eval_accuracy": 0.9844526621336832,
|
| 561 |
+
"eval_f1": 0.800200300450676,
|
| 562 |
+
"eval_loss": 0.06327783316373825,
|
| 563 |
+
"eval_precision": 0.7749757516973812,
|
| 564 |
+
"eval_recall": 0.8271221532091098,
|
| 565 |
+
"eval_runtime": 1.9274,
|
| 566 |
+
"eval_samples_per_second": 1038.212,
|
| 567 |
+
"eval_steps_per_second": 32.687,
|
| 568 |
+
"step": 12544
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 33.0,
|
| 572 |
+
"eval_accuracy": 0.9844924251461291,
|
| 573 |
+
"eval_f1": 0.806015037593985,
|
| 574 |
+
"eval_loss": 0.0630687028169632,
|
| 575 |
+
"eval_precision": 0.7813411078717201,
|
| 576 |
+
"eval_recall": 0.8322981366459627,
|
| 577 |
+
"eval_runtime": 1.9283,
|
| 578 |
+
"eval_samples_per_second": 1037.684,
|
| 579 |
+
"eval_steps_per_second": 32.671,
|
| 580 |
+
"step": 12936
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 33.16326530612245,
|
| 584 |
+
"grad_norm": 1.0332142114639282,
|
| 585 |
+
"learning_rate": 5.247813411078718e-07,
|
| 586 |
+
"loss": 0.0192,
|
| 587 |
+
"step": 13000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 34.0,
|
| 591 |
+
"eval_accuracy": 0.9844924251461291,
|
| 592 |
+
"eval_f1": 0.8035982008995503,
|
| 593 |
+
"eval_loss": 0.06286123394966125,
|
| 594 |
+
"eval_precision": 0.7768115942028986,
|
| 595 |
+
"eval_recall": 0.8322981366459627,
|
| 596 |
+
"eval_runtime": 1.9265,
|
| 597 |
+
"eval_samples_per_second": 1038.68,
|
| 598 |
+
"eval_steps_per_second": 32.702,
|
| 599 |
+
"step": 13328
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 34.43877551020408,
|
| 603 |
+
"grad_norm": 1.071878433227539,
|
| 604 |
+
"learning_rate": 1.6034985422740527e-07,
|
| 605 |
+
"loss": 0.0188,
|
| 606 |
+
"step": 13500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 35.0,
|
| 610 |
+
"eval_accuracy": 0.9844128991212374,
|
| 611 |
+
"eval_f1": 0.8001998001998001,
|
| 612 |
+
"eval_loss": 0.06326296180486679,
|
| 613 |
+
"eval_precision": 0.7731660231660231,
|
| 614 |
+
"eval_recall": 0.8291925465838509,
|
| 615 |
+
"eval_runtime": 1.9328,
|
| 616 |
+
"eval_samples_per_second": 1035.307,
|
| 617 |
+
"eval_steps_per_second": 32.596,
|
| 618 |
+
"step": 13720
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 35.0,
|
| 622 |
+
"step": 13720,
|
| 623 |
+
"total_flos": 1.8599928536379036e+16,
|
| 624 |
+
"train_loss": 0.03749203296166467,
|
| 625 |
+
"train_runtime": 1114.592,
|
| 626 |
+
"train_samples_per_second": 393.871,
|
| 627 |
+
"train_steps_per_second": 12.309
|
| 628 |
+
}
|
| 629 |
+
],
|
| 630 |
+
"logging_steps": 500,
|
| 631 |
+
"max_steps": 13720,
|
| 632 |
+
"num_input_tokens_seen": 0,
|
| 633 |
+
"num_train_epochs": 35,
|
| 634 |
+
"save_steps": 500,
|
| 635 |
+
"stateful_callbacks": {
|
| 636 |
+
"TrainerControl": {
|
| 637 |
+
"args": {
|
| 638 |
+
"should_epoch_stop": false,
|
| 639 |
+
"should_evaluate": false,
|
| 640 |
+
"should_log": false,
|
| 641 |
+
"should_save": true,
|
| 642 |
+
"should_training_stop": true
|
| 643 |
+
},
|
| 644 |
+
"attributes": {}
|
| 645 |
+
}
|
| 646 |
+
},
|
| 647 |
+
"total_flos": 1.8599928536379036e+16,
|
| 648 |
+
"train_batch_size": 32,
|
| 649 |
+
"trial_name": null,
|
| 650 |
+
"trial_params": null
|
| 651 |
+
}
|