Upload 5 files
Browse files- preprocessor_config.json +9 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +826 -0
- training_args.bin +3 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5338893c18bcde8c31e114775e198dd535e0c4f1b3f06eff63a5e847e395bdbd
|
| 3 |
+
size 14639
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5b8f9b7fa4b501dbc9b71aba7aa8dc9afe6bd255811e43631f29eea0484403a
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,826 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9564356435643564,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/wav2vec2-base2_temp/checkpoint-22702",
|
| 4 |
+
"epoch": 44.9990089197225,
|
| 5 |
+
"global_step": 22702,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.99,
|
| 12 |
+
"learning_rate": 5.869047619047619e-07,
|
| 13 |
+
"loss": 1.7909,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.22574257425742575,
|
| 19 |
+
"eval_f1": 0.08821474321649003,
|
| 20 |
+
"eval_loss": 1.7777053117752075,
|
| 21 |
+
"eval_precision": 0.11965788905676666,
|
| 22 |
+
"eval_recall": 0.17184714795008912,
|
| 23 |
+
"eval_runtime": 11.4913,
|
| 24 |
+
"eval_samples_per_second": 43.946,
|
| 25 |
+
"eval_steps_per_second": 11.052,
|
| 26 |
+
"step": 504
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.98,
|
| 30 |
+
"learning_rate": 1.1797619047619049e-06,
|
| 31 |
+
"loss": 1.7457,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.3485148514851485,
|
| 37 |
+
"eval_f1": 0.08614782183064122,
|
| 38 |
+
"eval_loss": 1.6808362007141113,
|
| 39 |
+
"eval_precision": 0.05808580858085808,
|
| 40 |
+
"eval_recall": 0.16666666666666666,
|
| 41 |
+
"eval_runtime": 9.5448,
|
| 42 |
+
"eval_samples_per_second": 52.908,
|
| 43 |
+
"eval_steps_per_second": 13.306,
|
| 44 |
+
"step": 1009
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.97,
|
| 48 |
+
"learning_rate": 1.775e-06,
|
| 49 |
+
"loss": 1.6522,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.0,
|
| 54 |
+
"eval_accuracy": 0.4277227722772277,
|
| 55 |
+
"eval_f1": 0.2012091077291391,
|
| 56 |
+
"eval_loss": 1.5670676231384277,
|
| 57 |
+
"eval_precision": 0.21909966172261253,
|
| 58 |
+
"eval_recall": 0.25960391732450555,
|
| 59 |
+
"eval_runtime": 11.3538,
|
| 60 |
+
"eval_samples_per_second": 44.479,
|
| 61 |
+
"eval_steps_per_second": 11.186,
|
| 62 |
+
"step": 1513
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.96,
|
| 66 |
+
"learning_rate": 2.3702380952380955e-06,
|
| 67 |
+
"loss": 1.5185,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.0,
|
| 72 |
+
"eval_accuracy": 0.5881188118811881,
|
| 73 |
+
"eval_f1": 0.3725029550190217,
|
| 74 |
+
"eval_loss": 1.3283705711364746,
|
| 75 |
+
"eval_precision": 0.44973544973544977,
|
| 76 |
+
"eval_recall": 0.42331231676819914,
|
| 77 |
+
"eval_runtime": 10.0287,
|
| 78 |
+
"eval_samples_per_second": 50.356,
|
| 79 |
+
"eval_steps_per_second": 12.664,
|
| 80 |
+
"step": 2018
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.96,
|
| 84 |
+
"learning_rate": 2.9654761904761905e-06,
|
| 85 |
+
"loss": 1.2985,
|
| 86 |
+
"step": 2500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.0,
|
| 90 |
+
"eval_accuracy": 0.6772277227722773,
|
| 91 |
+
"eval_f1": 0.4729958594455382,
|
| 92 |
+
"eval_loss": 1.0731083154678345,
|
| 93 |
+
"eval_precision": 0.43875160660457085,
|
| 94 |
+
"eval_recall": 0.528141923436041,
|
| 95 |
+
"eval_runtime": 12.9008,
|
| 96 |
+
"eval_samples_per_second": 39.145,
|
| 97 |
+
"eval_steps_per_second": 9.844,
|
| 98 |
+
"step": 2522
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 5.95,
|
| 102 |
+
"learning_rate": 3.5595238095238097e-06,
|
| 103 |
+
"loss": 1.0891,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"eval_accuracy": 0.6871287128712872,
|
| 109 |
+
"eval_f1": 0.5190569356664213,
|
| 110 |
+
"eval_loss": 0.9219310879707336,
|
| 111 |
+
"eval_precision": 0.5714776497659865,
|
| 112 |
+
"eval_recall": 0.5614828961887786,
|
| 113 |
+
"eval_runtime": 11.3089,
|
| 114 |
+
"eval_samples_per_second": 44.655,
|
| 115 |
+
"eval_steps_per_second": 11.23,
|
| 116 |
+
"step": 3027
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.94,
|
| 120 |
+
"learning_rate": 4.152380952380952e-06,
|
| 121 |
+
"loss": 0.898,
|
| 122 |
+
"step": 3500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.0,
|
| 126 |
+
"eval_accuracy": 0.7623762376237624,
|
| 127 |
+
"eval_f1": 0.6067418025396825,
|
| 128 |
+
"eval_loss": 0.7551212906837463,
|
| 129 |
+
"eval_precision": 0.6263669695520484,
|
| 130 |
+
"eval_recall": 0.6273902894491129,
|
| 131 |
+
"eval_runtime": 10.502,
|
| 132 |
+
"eval_samples_per_second": 48.086,
|
| 133 |
+
"eval_steps_per_second": 12.093,
|
| 134 |
+
"step": 3531
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 7.93,
|
| 138 |
+
"learning_rate": 4.7476190476190475e-06,
|
| 139 |
+
"loss": 0.7131,
|
| 140 |
+
"step": 4000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 8.0,
|
| 144 |
+
"eval_accuracy": 0.8237623762376237,
|
| 145 |
+
"eval_f1": 0.6820230695773629,
|
| 146 |
+
"eval_loss": 0.5713428258895874,
|
| 147 |
+
"eval_precision": 0.6794105204506714,
|
| 148 |
+
"eval_recall": 0.7097026992615229,
|
| 149 |
+
"eval_runtime": 11.2886,
|
| 150 |
+
"eval_samples_per_second": 44.736,
|
| 151 |
+
"eval_steps_per_second": 11.25,
|
| 152 |
+
"step": 4036
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 8.92,
|
| 156 |
+
"learning_rate": 5.342857142857143e-06,
|
| 157 |
+
"loss": 0.5432,
|
| 158 |
+
"step": 4500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 9.0,
|
| 162 |
+
"eval_accuracy": 0.8613861386138614,
|
| 163 |
+
"eval_f1": 0.7306731549704363,
|
| 164 |
+
"eval_loss": 0.4402145743370056,
|
| 165 |
+
"eval_precision": 0.7078735307061095,
|
| 166 |
+
"eval_recall": 0.7635915881504117,
|
| 167 |
+
"eval_runtime": 10.2752,
|
| 168 |
+
"eval_samples_per_second": 49.147,
|
| 169 |
+
"eval_steps_per_second": 12.36,
|
| 170 |
+
"step": 4540
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 9.91,
|
| 174 |
+
"learning_rate": 5.9380952380952385e-06,
|
| 175 |
+
"loss": 0.4296,
|
| 176 |
+
"step": 5000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.0,
|
| 180 |
+
"eval_accuracy": 0.8534653465346534,
|
| 181 |
+
"eval_f1": 0.7203056745493539,
|
| 182 |
+
"eval_loss": 0.42783123254776,
|
| 183 |
+
"eval_precision": 0.7042866897841077,
|
| 184 |
+
"eval_recall": 0.7496972880061116,
|
| 185 |
+
"eval_runtime": 10.0025,
|
| 186 |
+
"eval_samples_per_second": 50.488,
|
| 187 |
+
"eval_steps_per_second": 12.697,
|
| 188 |
+
"step": 5045
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 10.9,
|
| 192 |
+
"learning_rate": 6.532142857142857e-06,
|
| 193 |
+
"loss": 0.3869,
|
| 194 |
+
"step": 5500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 11.0,
|
| 198 |
+
"eval_accuracy": 0.8772277227722772,
|
| 199 |
+
"eval_f1": 0.7461735637601347,
|
| 200 |
+
"eval_loss": 0.3639691174030304,
|
| 201 |
+
"eval_precision": 0.7306143706983171,
|
| 202 |
+
"eval_recall": 0.7771949537390714,
|
| 203 |
+
"eval_runtime": 12.5987,
|
| 204 |
+
"eval_samples_per_second": 40.083,
|
| 205 |
+
"eval_steps_per_second": 10.08,
|
| 206 |
+
"step": 5549
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.89,
|
| 210 |
+
"learning_rate": 7.127380952380952e-06,
|
| 211 |
+
"loss": 0.3606,
|
| 212 |
+
"step": 6000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 12.0,
|
| 216 |
+
"eval_accuracy": 0.8673267326732673,
|
| 217 |
+
"eval_f1": 0.7317576200752773,
|
| 218 |
+
"eval_loss": 0.4499942660331726,
|
| 219 |
+
"eval_precision": 0.7133735090373348,
|
| 220 |
+
"eval_recall": 0.7651407987437399,
|
| 221 |
+
"eval_runtime": 10.9939,
|
| 222 |
+
"eval_samples_per_second": 45.934,
|
| 223 |
+
"eval_steps_per_second": 11.552,
|
| 224 |
+
"step": 6054
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 12.88,
|
| 228 |
+
"learning_rate": 7.722619047619049e-06,
|
| 229 |
+
"loss": 0.3626,
|
| 230 |
+
"step": 6500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 13.0,
|
| 234 |
+
"eval_accuracy": 0.8653465346534653,
|
| 235 |
+
"eval_f1": 0.7374268578667081,
|
| 236 |
+
"eval_loss": 0.460127055644989,
|
| 237 |
+
"eval_precision": 0.7374934142677786,
|
| 238 |
+
"eval_recall": 0.7631706773618538,
|
| 239 |
+
"eval_runtime": 10.5614,
|
| 240 |
+
"eval_samples_per_second": 47.816,
|
| 241 |
+
"eval_steps_per_second": 12.025,
|
| 242 |
+
"step": 6558
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 13.88,
|
| 246 |
+
"learning_rate": 8.317857142857142e-06,
|
| 247 |
+
"loss": 0.3276,
|
| 248 |
+
"step": 7000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 14.0,
|
| 252 |
+
"eval_accuracy": 0.8732673267326733,
|
| 253 |
+
"eval_f1": 0.7421428470955433,
|
| 254 |
+
"eval_loss": 0.41789284348487854,
|
| 255 |
+
"eval_precision": 0.7395445813585981,
|
| 256 |
+
"eval_recall": 0.7673902894491129,
|
| 257 |
+
"eval_runtime": 10.505,
|
| 258 |
+
"eval_samples_per_second": 48.072,
|
| 259 |
+
"eval_steps_per_second": 12.09,
|
| 260 |
+
"step": 7063
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 14.87,
|
| 264 |
+
"learning_rate": 8.913095238095238e-06,
|
| 265 |
+
"loss": 0.3327,
|
| 266 |
+
"step": 7500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 15.0,
|
| 270 |
+
"eval_accuracy": 0.8910891089108911,
|
| 271 |
+
"eval_f1": 0.7616771274725501,
|
| 272 |
+
"eval_loss": 0.3447856605052948,
|
| 273 |
+
"eval_precision": 0.7497788374032539,
|
| 274 |
+
"eval_recall": 0.7904575163398694,
|
| 275 |
+
"eval_runtime": 10.1528,
|
| 276 |
+
"eval_samples_per_second": 49.74,
|
| 277 |
+
"eval_steps_per_second": 12.509,
|
| 278 |
+
"step": 7567
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 15.86,
|
| 282 |
+
"learning_rate": 9.508333333333333e-06,
|
| 283 |
+
"loss": 0.3043,
|
| 284 |
+
"step": 8000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 16.0,
|
| 288 |
+
"eval_accuracy": 0.8851485148514852,
|
| 289 |
+
"eval_f1": 0.7518326259740746,
|
| 290 |
+
"eval_loss": 0.3687730133533478,
|
| 291 |
+
"eval_precision": 0.7422745662572229,
|
| 292 |
+
"eval_recall": 0.7788982259570495,
|
| 293 |
+
"eval_runtime": 11.1359,
|
| 294 |
+
"eval_samples_per_second": 45.349,
|
| 295 |
+
"eval_steps_per_second": 11.405,
|
| 296 |
+
"step": 8072
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 16.85,
|
| 300 |
+
"learning_rate": 1.0103571428571429e-05,
|
| 301 |
+
"loss": 0.3127,
|
| 302 |
+
"step": 8500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 17.0,
|
| 306 |
+
"eval_accuracy": 0.8891089108910891,
|
| 307 |
+
"eval_f1": 0.7565562985281078,
|
| 308 |
+
"eval_loss": 0.3414187431335449,
|
| 309 |
+
"eval_precision": 0.7434316232942377,
|
| 310 |
+
"eval_recall": 0.7861912189118071,
|
| 311 |
+
"eval_runtime": 10.7404,
|
| 312 |
+
"eval_samples_per_second": 47.019,
|
| 313 |
+
"eval_steps_per_second": 11.824,
|
| 314 |
+
"step": 8576
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 17.84,
|
| 318 |
+
"learning_rate": 1.0698809523809525e-05,
|
| 319 |
+
"loss": 0.306,
|
| 320 |
+
"step": 9000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 18.0,
|
| 324 |
+
"eval_accuracy": 0.8792079207920792,
|
| 325 |
+
"eval_f1": 0.7478424649155898,
|
| 326 |
+
"eval_loss": 0.4159949719905853,
|
| 327 |
+
"eval_precision": 0.7357367052282306,
|
| 328 |
+
"eval_recall": 0.7744677871148459,
|
| 329 |
+
"eval_runtime": 10.479,
|
| 330 |
+
"eval_samples_per_second": 48.192,
|
| 331 |
+
"eval_steps_per_second": 12.119,
|
| 332 |
+
"step": 9081
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.83,
|
| 336 |
+
"learning_rate": 1.1294047619047618e-05,
|
| 337 |
+
"loss": 0.2756,
|
| 338 |
+
"step": 9500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 19.0,
|
| 342 |
+
"eval_accuracy": 0.8495049504950495,
|
| 343 |
+
"eval_f1": 0.7182407626265085,
|
| 344 |
+
"eval_loss": 0.7052268981933594,
|
| 345 |
+
"eval_precision": 0.7064460784313725,
|
| 346 |
+
"eval_recall": 0.7463492063492062,
|
| 347 |
+
"eval_runtime": 11.111,
|
| 348 |
+
"eval_samples_per_second": 45.45,
|
| 349 |
+
"eval_steps_per_second": 11.43,
|
| 350 |
+
"step": 9585
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 19.82,
|
| 354 |
+
"learning_rate": 1.1888095238095239e-05,
|
| 355 |
+
"loss": 0.3233,
|
| 356 |
+
"step": 10000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 20.0,
|
| 360 |
+
"eval_accuracy": 0.904950495049505,
|
| 361 |
+
"eval_f1": 0.7712251064475479,
|
| 362 |
+
"eval_loss": 0.2911510169506073,
|
| 363 |
+
"eval_precision": 0.7413165742555666,
|
| 364 |
+
"eval_recall": 0.8109531236737119,
|
| 365 |
+
"eval_runtime": 10.6787,
|
| 366 |
+
"eval_samples_per_second": 47.29,
|
| 367 |
+
"eval_steps_per_second": 11.893,
|
| 368 |
+
"step": 10090
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 20.81,
|
| 372 |
+
"learning_rate": 1.2483333333333333e-05,
|
| 373 |
+
"loss": 0.2932,
|
| 374 |
+
"step": 10500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 21.0,
|
| 378 |
+
"eval_accuracy": 0.904950495049505,
|
| 379 |
+
"eval_f1": 0.8543450476033496,
|
| 380 |
+
"eval_loss": 0.42383888363838196,
|
| 381 |
+
"eval_precision": 0.8654226983060155,
|
| 382 |
+
"eval_recall": 0.853277359895007,
|
| 383 |
+
"eval_runtime": 9.6742,
|
| 384 |
+
"eval_samples_per_second": 52.201,
|
| 385 |
+
"eval_steps_per_second": 13.128,
|
| 386 |
+
"step": 10594
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 21.8,
|
| 390 |
+
"learning_rate": 1.307857142857143e-05,
|
| 391 |
+
"loss": 0.2698,
|
| 392 |
+
"step": 11000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 22.0,
|
| 396 |
+
"eval_accuracy": 0.9128712871287129,
|
| 397 |
+
"eval_f1": 0.8604450377673127,
|
| 398 |
+
"eval_loss": 0.386119544506073,
|
| 399 |
+
"eval_precision": 0.9000550023499306,
|
| 400 |
+
"eval_recall": 0.8544778424190188,
|
| 401 |
+
"eval_runtime": 11.5253,
|
| 402 |
+
"eval_samples_per_second": 43.817,
|
| 403 |
+
"eval_steps_per_second": 11.019,
|
| 404 |
+
"step": 11099
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 22.79,
|
| 408 |
+
"learning_rate": 1.3673809523809524e-05,
|
| 409 |
+
"loss": 0.2658,
|
| 410 |
+
"step": 11500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 23.0,
|
| 414 |
+
"eval_accuracy": 0.9366336633663367,
|
| 415 |
+
"eval_f1": 0.9043163728295133,
|
| 416 |
+
"eval_loss": 0.336636483669281,
|
| 417 |
+
"eval_precision": 0.9078665759004835,
|
| 418 |
+
"eval_recall": 0.9021482439129498,
|
| 419 |
+
"eval_runtime": 11.333,
|
| 420 |
+
"eval_samples_per_second": 44.56,
|
| 421 |
+
"eval_steps_per_second": 11.206,
|
| 422 |
+
"step": 11603
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 23.79,
|
| 426 |
+
"learning_rate": 1.426904761904762e-05,
|
| 427 |
+
"loss": 0.2393,
|
| 428 |
+
"step": 12000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 24.0,
|
| 432 |
+
"eval_accuracy": 0.9188118811881189,
|
| 433 |
+
"eval_f1": 0.8657850889640667,
|
| 434 |
+
"eval_loss": 0.4375390410423279,
|
| 435 |
+
"eval_precision": 0.8887849766332739,
|
| 436 |
+
"eval_recall": 0.8638055735114559,
|
| 437 |
+
"eval_runtime": 11.0648,
|
| 438 |
+
"eval_samples_per_second": 45.64,
|
| 439 |
+
"eval_steps_per_second": 11.478,
|
| 440 |
+
"step": 12108
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 24.78,
|
| 444 |
+
"learning_rate": 1.4864285714285713e-05,
|
| 445 |
+
"loss": 0.2401,
|
| 446 |
+
"step": 12500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 25.0,
|
| 450 |
+
"eval_accuracy": 0.9207920792079208,
|
| 451 |
+
"eval_f1": 0.8888781151825805,
|
| 452 |
+
"eval_loss": 0.4757852256298065,
|
| 453 |
+
"eval_precision": 0.8961036612926598,
|
| 454 |
+
"eval_recall": 0.8866903929403929,
|
| 455 |
+
"eval_runtime": 10.4698,
|
| 456 |
+
"eval_samples_per_second": 48.234,
|
| 457 |
+
"eval_steps_per_second": 12.13,
|
| 458 |
+
"step": 12612
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 25.77,
|
| 462 |
+
"learning_rate": 1.545952380952381e-05,
|
| 463 |
+
"loss": 0.2041,
|
| 464 |
+
"step": 13000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 26.0,
|
| 468 |
+
"eval_accuracy": 0.9425742574257425,
|
| 469 |
+
"eval_f1": 0.9155025903592865,
|
| 470 |
+
"eval_loss": 0.3074367940425873,
|
| 471 |
+
"eval_precision": 0.9170299642442648,
|
| 472 |
+
"eval_recall": 0.9228144078144078,
|
| 473 |
+
"eval_runtime": 10.5628,
|
| 474 |
+
"eval_samples_per_second": 47.809,
|
| 475 |
+
"eval_steps_per_second": 12.023,
|
| 476 |
+
"step": 13117
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 26.76,
|
| 480 |
+
"learning_rate": 1.605357142857143e-05,
|
| 481 |
+
"loss": 0.1845,
|
| 482 |
+
"step": 13500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 27.0,
|
| 486 |
+
"eval_accuracy": 0.9108910891089109,
|
| 487 |
+
"eval_f1": 0.8599750617887297,
|
| 488 |
+
"eval_loss": 0.4771750867366791,
|
| 489 |
+
"eval_precision": 0.864481386177137,
|
| 490 |
+
"eval_recall": 0.8576941032823386,
|
| 491 |
+
"eval_runtime": 11.1655,
|
| 492 |
+
"eval_samples_per_second": 45.229,
|
| 493 |
+
"eval_steps_per_second": 11.374,
|
| 494 |
+
"step": 13621
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 27.75,
|
| 498 |
+
"learning_rate": 1.6648809523809525e-05,
|
| 499 |
+
"loss": 0.1743,
|
| 500 |
+
"step": 14000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 28.0,
|
| 504 |
+
"eval_accuracy": 0.9386138613861386,
|
| 505 |
+
"eval_f1": 0.9057775638831363,
|
| 506 |
+
"eval_loss": 0.37529292702674866,
|
| 507 |
+
"eval_precision": 0.9140135491407343,
|
| 508 |
+
"eval_recall": 0.9027411722264663,
|
| 509 |
+
"eval_runtime": 9.6192,
|
| 510 |
+
"eval_samples_per_second": 52.499,
|
| 511 |
+
"eval_steps_per_second": 13.203,
|
| 512 |
+
"step": 14126
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 28.74,
|
| 516 |
+
"learning_rate": 1.7244047619047617e-05,
|
| 517 |
+
"loss": 0.1539,
|
| 518 |
+
"step": 14500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 29.0,
|
| 522 |
+
"eval_accuracy": 0.9247524752475248,
|
| 523 |
+
"eval_f1": 0.8866243367627531,
|
| 524 |
+
"eval_loss": 0.5404527187347412,
|
| 525 |
+
"eval_precision": 0.9116518987029846,
|
| 526 |
+
"eval_recall": 0.8748301616683968,
|
| 527 |
+
"eval_runtime": 10.8581,
|
| 528 |
+
"eval_samples_per_second": 46.509,
|
| 529 |
+
"eval_steps_per_second": 11.696,
|
| 530 |
+
"step": 14630
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 29.73,
|
| 534 |
+
"learning_rate": 1.7839285714285716e-05,
|
| 535 |
+
"loss": 0.1646,
|
| 536 |
+
"step": 15000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 30.0,
|
| 540 |
+
"eval_accuracy": 0.9346534653465347,
|
| 541 |
+
"eval_f1": 0.9015438899526216,
|
| 542 |
+
"eval_loss": 0.43599411845207214,
|
| 543 |
+
"eval_precision": 0.9116436291187194,
|
| 544 |
+
"eval_recall": 0.8942752998635353,
|
| 545 |
+
"eval_runtime": 9.916,
|
| 546 |
+
"eval_samples_per_second": 50.928,
|
| 547 |
+
"eval_steps_per_second": 12.808,
|
| 548 |
+
"step": 15135
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 30.72,
|
| 552 |
+
"learning_rate": 1.843452380952381e-05,
|
| 553 |
+
"loss": 0.183,
|
| 554 |
+
"step": 15500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 31.0,
|
| 558 |
+
"eval_accuracy": 0.9346534653465347,
|
| 559 |
+
"eval_f1": 0.9052713311328079,
|
| 560 |
+
"eval_loss": 0.4353509545326233,
|
| 561 |
+
"eval_precision": 0.9100534785215237,
|
| 562 |
+
"eval_recall": 0.9015345357257122,
|
| 563 |
+
"eval_runtime": 9.7228,
|
| 564 |
+
"eval_samples_per_second": 51.94,
|
| 565 |
+
"eval_steps_per_second": 13.062,
|
| 566 |
+
"step": 15639
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 31.71,
|
| 570 |
+
"learning_rate": 1.9028571428571427e-05,
|
| 571 |
+
"loss": 0.1547,
|
| 572 |
+
"step": 16000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 32.0,
|
| 576 |
+
"eval_accuracy": 0.9306930693069307,
|
| 577 |
+
"eval_f1": 0.8978119183659733,
|
| 578 |
+
"eval_loss": 0.49971604347229004,
|
| 579 |
+
"eval_precision": 0.9138477382798044,
|
| 580 |
+
"eval_recall": 0.888716153127918,
|
| 581 |
+
"eval_runtime": 10.4672,
|
| 582 |
+
"eval_samples_per_second": 48.246,
|
| 583 |
+
"eval_steps_per_second": 12.133,
|
| 584 |
+
"step": 16144
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 32.71,
|
| 588 |
+
"learning_rate": 1.9623809523809523e-05,
|
| 589 |
+
"loss": 0.1658,
|
| 590 |
+
"step": 16500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 33.0,
|
| 594 |
+
"eval_accuracy": 0.9089108910891089,
|
| 595 |
+
"eval_f1": 0.8687334612012699,
|
| 596 |
+
"eval_loss": 0.5864279270172119,
|
| 597 |
+
"eval_precision": 0.8899122777729049,
|
| 598 |
+
"eval_recall": 0.8847601091718739,
|
| 599 |
+
"eval_runtime": 10.5773,
|
| 600 |
+
"eval_samples_per_second": 47.744,
|
| 601 |
+
"eval_steps_per_second": 12.007,
|
| 602 |
+
"step": 16648
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 33.7,
|
| 606 |
+
"learning_rate": 2.0219047619047622e-05,
|
| 607 |
+
"loss": 0.1333,
|
| 608 |
+
"step": 17000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 34.0,
|
| 612 |
+
"eval_accuracy": 0.9089108910891089,
|
| 613 |
+
"eval_f1": 0.8674149596498353,
|
| 614 |
+
"eval_loss": 0.6616652607917786,
|
| 615 |
+
"eval_precision": 0.8953076547670352,
|
| 616 |
+
"eval_recall": 0.8615549809667457,
|
| 617 |
+
"eval_runtime": 9.287,
|
| 618 |
+
"eval_samples_per_second": 54.377,
|
| 619 |
+
"eval_steps_per_second": 13.675,
|
| 620 |
+
"step": 17153
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 34.69,
|
| 624 |
+
"learning_rate": 2.0814285714285714e-05,
|
| 625 |
+
"loss": 0.1606,
|
| 626 |
+
"step": 17500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 35.0,
|
| 630 |
+
"eval_accuracy": 0.9346534653465347,
|
| 631 |
+
"eval_f1": 0.9065032718742226,
|
| 632 |
+
"eval_loss": 0.4562079906463623,
|
| 633 |
+
"eval_precision": 0.9101611693862718,
|
| 634 |
+
"eval_recall": 0.922783189033189,
|
| 635 |
+
"eval_runtime": 10.427,
|
| 636 |
+
"eval_samples_per_second": 48.432,
|
| 637 |
+
"eval_steps_per_second": 12.18,
|
| 638 |
+
"step": 17657
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 35.68,
|
| 642 |
+
"learning_rate": 2.140952380952381e-05,
|
| 643 |
+
"loss": 0.1562,
|
| 644 |
+
"step": 18000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 36.0,
|
| 648 |
+
"eval_accuracy": 0.9346534653465347,
|
| 649 |
+
"eval_f1": 0.9056285926854001,
|
| 650 |
+
"eval_loss": 0.5119304060935974,
|
| 651 |
+
"eval_precision": 0.9221614278132352,
|
| 652 |
+
"eval_recall": 0.8947665732959851,
|
| 653 |
+
"eval_runtime": 10.7345,
|
| 654 |
+
"eval_samples_per_second": 47.045,
|
| 655 |
+
"eval_steps_per_second": 11.831,
|
| 656 |
+
"step": 18162
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 36.67,
|
| 660 |
+
"learning_rate": 2.200357142857143e-05,
|
| 661 |
+
"loss": 0.1238,
|
| 662 |
+
"step": 18500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 37.0,
|
| 666 |
+
"eval_accuracy": 0.9465346534653465,
|
| 667 |
+
"eval_f1": 0.9233277365446494,
|
| 668 |
+
"eval_loss": 0.37833738327026367,
|
| 669 |
+
"eval_precision": 0.9264774557165861,
|
| 670 |
+
"eval_recall": 0.9206345615169145,
|
| 671 |
+
"eval_runtime": 10.6894,
|
| 672 |
+
"eval_samples_per_second": 47.243,
|
| 673 |
+
"eval_steps_per_second": 11.881,
|
| 674 |
+
"step": 18666
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 37.66,
|
| 678 |
+
"learning_rate": 2.2598809523809527e-05,
|
| 679 |
+
"loss": 0.133,
|
| 680 |
+
"step": 19000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 38.0,
|
| 684 |
+
"eval_accuracy": 0.9207920792079208,
|
| 685 |
+
"eval_f1": 0.88282026816653,
|
| 686 |
+
"eval_loss": 0.44697701930999756,
|
| 687 |
+
"eval_precision": 0.8940768234014104,
|
| 688 |
+
"eval_recall": 0.9017844573726927,
|
| 689 |
+
"eval_runtime": 9.8397,
|
| 690 |
+
"eval_samples_per_second": 51.323,
|
| 691 |
+
"eval_steps_per_second": 12.907,
|
| 692 |
+
"step": 19171
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 38.65,
|
| 696 |
+
"learning_rate": 2.319404761904762e-05,
|
| 697 |
+
"loss": 0.1817,
|
| 698 |
+
"step": 19500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 39.0,
|
| 702 |
+
"eval_accuracy": 0.9287128712871288,
|
| 703 |
+
"eval_f1": 0.8884108101819078,
|
| 704 |
+
"eval_loss": 0.4824526309967041,
|
| 705 |
+
"eval_precision": 0.9067813929838341,
|
| 706 |
+
"eval_recall": 0.8854446125769654,
|
| 707 |
+
"eval_runtime": 10.5682,
|
| 708 |
+
"eval_samples_per_second": 47.785,
|
| 709 |
+
"eval_steps_per_second": 12.017,
|
| 710 |
+
"step": 19675
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 39.64,
|
| 714 |
+
"learning_rate": 2.3789285714285715e-05,
|
| 715 |
+
"loss": 0.1504,
|
| 716 |
+
"step": 20000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 40.0,
|
| 720 |
+
"eval_accuracy": 0.9346534653465347,
|
| 721 |
+
"eval_f1": 0.9079267627717296,
|
| 722 |
+
"eval_loss": 0.48847106099128723,
|
| 723 |
+
"eval_precision": 0.9168877258505742,
|
| 724 |
+
"eval_recall": 0.9021284924226101,
|
| 725 |
+
"eval_runtime": 9.5244,
|
| 726 |
+
"eval_samples_per_second": 53.021,
|
| 727 |
+
"eval_steps_per_second": 13.334,
|
| 728 |
+
"step": 20180
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 40.63,
|
| 732 |
+
"learning_rate": 2.4383333333333334e-05,
|
| 733 |
+
"loss": 0.1367,
|
| 734 |
+
"step": 20500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 41.0,
|
| 738 |
+
"eval_accuracy": 0.902970297029703,
|
| 739 |
+
"eval_f1": 0.8748563062275386,
|
| 740 |
+
"eval_loss": 0.6201313734054565,
|
| 741 |
+
"eval_precision": 0.8975989253974328,
|
| 742 |
+
"eval_recall": 0.8675623151358445,
|
| 743 |
+
"eval_runtime": 11.0171,
|
| 744 |
+
"eval_samples_per_second": 45.838,
|
| 745 |
+
"eval_steps_per_second": 11.528,
|
| 746 |
+
"step": 20684
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 41.63,
|
| 750 |
+
"learning_rate": 2.497857142857143e-05,
|
| 751 |
+
"loss": 0.1786,
|
| 752 |
+
"step": 21000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 42.0,
|
| 756 |
+
"eval_accuracy": 0.9089108910891089,
|
| 757 |
+
"eval_f1": 0.8833714971261983,
|
| 758 |
+
"eval_loss": 0.6504853963851929,
|
| 759 |
+
"eval_precision": 0.9036762862738423,
|
| 760 |
+
"eval_recall": 0.8743047475400418,
|
| 761 |
+
"eval_runtime": 9.3899,
|
| 762 |
+
"eval_samples_per_second": 53.781,
|
| 763 |
+
"eval_steps_per_second": 13.525,
|
| 764 |
+
"step": 21189
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 42.62,
|
| 768 |
+
"learning_rate": 2.5573809523809525e-05,
|
| 769 |
+
"loss": 0.1589,
|
| 770 |
+
"step": 21500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 43.0,
|
| 774 |
+
"eval_accuracy": 0.9504950495049505,
|
| 775 |
+
"eval_f1": 0.9268454843019528,
|
| 776 |
+
"eval_loss": 0.35494372248649597,
|
| 777 |
+
"eval_precision": 0.9327534998068862,
|
| 778 |
+
"eval_recall": 0.9231311498958558,
|
| 779 |
+
"eval_runtime": 10.3634,
|
| 780 |
+
"eval_samples_per_second": 48.729,
|
| 781 |
+
"eval_steps_per_second": 12.255,
|
| 782 |
+
"step": 21693
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 43.61,
|
| 786 |
+
"learning_rate": 2.616904761904762e-05,
|
| 787 |
+
"loss": 0.0857,
|
| 788 |
+
"step": 22000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 44.0,
|
| 792 |
+
"eval_accuracy": 0.9485148514851485,
|
| 793 |
+
"eval_f1": 0.9224485798890482,
|
| 794 |
+
"eval_loss": 0.41820821166038513,
|
| 795 |
+
"eval_precision": 0.9441624977223921,
|
| 796 |
+
"eval_recall": 0.9108187890540833,
|
| 797 |
+
"eval_runtime": 9.3522,
|
| 798 |
+
"eval_samples_per_second": 53.998,
|
| 799 |
+
"eval_steps_per_second": 13.58,
|
| 800 |
+
"step": 22198
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 44.6,
|
| 804 |
+
"learning_rate": 2.6763095238095236e-05,
|
| 805 |
+
"loss": 0.102,
|
| 806 |
+
"step": 22500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 45.0,
|
| 810 |
+
"eval_accuracy": 0.9564356435643564,
|
| 811 |
+
"eval_f1": 0.9306293793472796,
|
| 812 |
+
"eval_loss": 0.29131555557250977,
|
| 813 |
+
"eval_precision": 0.9291726584104362,
|
| 814 |
+
"eval_recall": 0.9330733318968613,
|
| 815 |
+
"eval_runtime": 9.5553,
|
| 816 |
+
"eval_samples_per_second": 52.85,
|
| 817 |
+
"eval_steps_per_second": 13.291,
|
| 818 |
+
"step": 22702
|
| 819 |
+
}
|
| 820 |
+
],
|
| 821 |
+
"max_steps": 252000,
|
| 822 |
+
"num_train_epochs": 500,
|
| 823 |
+
"total_flos": 1.9381803431060155e+18,
|
| 824 |
+
"trial_name": null,
|
| 825 |
+
"trial_params": null
|
| 826 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c75888749bf6887513e503aeeb31f47900c4ae695053b074fc57567f59025c1
|
| 3 |
+
size 4027
|