End of training
Browse files- README.md +2 -0
- all_results.json +25 -0
- eval_results.json +12 -0
- predict_results.json +10 -0
- predictions.txt +0 -0
- runs/May25_00-01-34_indolem-petl-vm/events.out.tfevents.1716596541.indolem-petl-vm.1797516.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +410 -0
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
base_model: indolem/indobert-base-uncased
|
| 4 |
tags:
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- id
|
| 4 |
license: mit
|
| 5 |
base_model: indolem/indobert-base-uncased
|
| 6 |
tags:
|
all_results.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9578654476796185,
|
| 4 |
+
"eval_f1": 0.800106894708712,
|
| 5 |
+
"eval_loss": 0.1304602026939392,
|
| 6 |
+
"eval_precision": 0.7407224146462148,
|
| 7 |
+
"eval_recall": 0.8698431144683324,
|
| 8 |
+
"eval_runtime": 4.505,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 207.546,
|
| 11 |
+
"eval_steps_per_second": 3.33,
|
| 12 |
+
"predict_accuracy": 0.968352466645982,
|
| 13 |
+
"predict_f1": 0.8217996904709264,
|
| 14 |
+
"predict_loss": 0.09529992192983627,
|
| 15 |
+
"predict_precision": 0.7753441802252816,
|
| 16 |
+
"predict_recall": 0.8741768579492004,
|
| 17 |
+
"predict_runtime": 10.4347,
|
| 18 |
+
"predict_samples_per_second": 224.539,
|
| 19 |
+
"predict_steps_per_second": 3.546,
|
| 20 |
+
"train_loss": 0.17226147796168473,
|
| 21 |
+
"train_runtime": 1230.5305,
|
| 22 |
+
"train_samples": 8437,
|
| 23 |
+
"train_samples_per_second": 137.128,
|
| 24 |
+
"train_steps_per_second": 8.582
|
| 25 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9578654476796185,
|
| 4 |
+
"eval_f1": 0.800106894708712,
|
| 5 |
+
"eval_loss": 0.1304602026939392,
|
| 6 |
+
"eval_precision": 0.7407224146462148,
|
| 7 |
+
"eval_recall": 0.8698431144683324,
|
| 8 |
+
"eval_runtime": 4.505,
|
| 9 |
+
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 207.546,
|
| 11 |
+
"eval_steps_per_second": 3.33
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.968352466645982,
|
| 3 |
+
"predict_f1": 0.8217996904709264,
|
| 4 |
+
"predict_loss": 0.09529992192983627,
|
| 5 |
+
"predict_precision": 0.7753441802252816,
|
| 6 |
+
"predict_recall": 0.8741768579492004,
|
| 7 |
+
"predict_runtime": 10.4347,
|
| 8 |
+
"predict_samples_per_second": 224.539,
|
| 9 |
+
"predict_steps_per_second": 3.546
|
| 10 |
+
}
|
predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/May25_00-01-34_indolem-petl-vm/events.out.tfevents.1716596541.indolem-petl-vm.1797516.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7ad8f8d4b854181272d69559422665e1c0bcf8529adad2e9b870f781861521f
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.17226147796168473,
|
| 4 |
+
"train_runtime": 1230.5305,
|
| 5 |
+
"train_samples": 8437,
|
| 6 |
+
"train_samples_per_second": 137.128,
|
| 7 |
+
"train_steps_per_second": 8.582
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10560,
|
| 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 |
+
"grad_norm": 1.2974101305007935,
|
| 14 |
+
"learning_rate": 4.75e-05,
|
| 15 |
+
"loss": 0.7682,
|
| 16 |
+
"step": 528
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.8662923581436948,
|
| 21 |
+
"eval_f1": 0.18337078651685396,
|
| 22 |
+
"eval_loss": 0.43944087624549866,
|
| 23 |
+
"eval_precision": 0.40476190476190477,
|
| 24 |
+
"eval_recall": 0.11853573503776874,
|
| 25 |
+
"eval_runtime": 4.5164,
|
| 26 |
+
"eval_samples_per_second": 207.024,
|
| 27 |
+
"eval_steps_per_second": 3.321,
|
| 28 |
+
"step": 528
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 0.8939604759216309,
|
| 33 |
+
"learning_rate": 4.5e-05,
|
| 34 |
+
"loss": 0.3466,
|
| 35 |
+
"step": 1056
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9326741528371261,
|
| 40 |
+
"eval_f1": 0.6631853785900783,
|
| 41 |
+
"eval_loss": 0.22170819342136383,
|
| 42 |
+
"eval_precision": 0.602181128496918,
|
| 43 |
+
"eval_recall": 0.7379430563625798,
|
| 44 |
+
"eval_runtime": 4.5717,
|
| 45 |
+
"eval_samples_per_second": 204.517,
|
| 46 |
+
"eval_steps_per_second": 3.281,
|
| 47 |
+
"step": 1056
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 1.3257710933685303,
|
| 52 |
+
"learning_rate": 4.25e-05,
|
| 53 |
+
"loss": 0.2131,
|
| 54 |
+
"step": 1584
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.9428102951406141,
|
| 59 |
+
"eval_f1": 0.7492870106300232,
|
| 60 |
+
"eval_loss": 0.172767773270607,
|
| 61 |
+
"eval_precision": 0.6764981273408239,
|
| 62 |
+
"eval_recall": 0.8396281231841952,
|
| 63 |
+
"eval_runtime": 4.5361,
|
| 64 |
+
"eval_samples_per_second": 206.122,
|
| 65 |
+
"eval_steps_per_second": 3.307,
|
| 66 |
+
"step": 1584
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 1.8121825456619263,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.1759,
|
| 73 |
+
"step": 2112
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.9515552022259763,
|
| 78 |
+
"eval_f1": 0.7833023132145706,
|
| 79 |
+
"eval_loss": 0.15085110068321228,
|
| 80 |
+
"eval_precision": 0.7220588235294118,
|
| 81 |
+
"eval_recall": 0.8558977338756537,
|
| 82 |
+
"eval_runtime": 4.5254,
|
| 83 |
+
"eval_samples_per_second": 206.611,
|
| 84 |
+
"eval_steps_per_second": 3.315,
|
| 85 |
+
"step": 2112
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 1.214239478111267,
|
| 90 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 91 |
+
"loss": 0.1563,
|
| 92 |
+
"step": 2640
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9533439332207095,
|
| 97 |
+
"eval_f1": 0.7900773539610563,
|
| 98 |
+
"eval_loss": 0.14215560257434845,
|
| 99 |
+
"eval_precision": 0.730276134122288,
|
| 100 |
+
"eval_recall": 0.8605461940732132,
|
| 101 |
+
"eval_runtime": 4.5339,
|
| 102 |
+
"eval_samples_per_second": 206.225,
|
| 103 |
+
"eval_steps_per_second": 3.308,
|
| 104 |
+
"step": 2640
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 1.626373291015625,
|
| 109 |
+
"learning_rate": 3.5e-05,
|
| 110 |
+
"loss": 0.1464,
|
| 111 |
+
"step": 3168
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.9541389247739243,
|
| 116 |
+
"eval_f1": 0.7889618922470434,
|
| 117 |
+
"eval_loss": 0.14294518530368805,
|
| 118 |
+
"eval_precision": 0.7202495201535508,
|
| 119 |
+
"eval_recall": 0.8721673445671121,
|
| 120 |
+
"eval_runtime": 4.5494,
|
| 121 |
+
"eval_samples_per_second": 205.524,
|
| 122 |
+
"eval_steps_per_second": 3.297,
|
| 123 |
+
"step": 3168
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 3.158684015274048,
|
| 128 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 129 |
+
"loss": 0.1394,
|
| 130 |
+
"step": 3696
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.9525489416674948,
|
| 135 |
+
"eval_f1": 0.7869281045751634,
|
| 136 |
+
"eval_loss": 0.14403149485588074,
|
| 137 |
+
"eval_precision": 0.7153041825095057,
|
| 138 |
+
"eval_recall": 0.8744915746658919,
|
| 139 |
+
"eval_runtime": 4.5356,
|
| 140 |
+
"eval_samples_per_second": 206.146,
|
| 141 |
+
"eval_steps_per_second": 3.307,
|
| 142 |
+
"step": 3696
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.7790516018867493,
|
| 147 |
+
"learning_rate": 3e-05,
|
| 148 |
+
"loss": 0.1325,
|
| 149 |
+
"step": 4224
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.9553314121037464,
|
| 154 |
+
"eval_f1": 0.796106287818995,
|
| 155 |
+
"eval_loss": 0.1397974044084549,
|
| 156 |
+
"eval_precision": 0.7274038461538461,
|
| 157 |
+
"eval_recall": 0.8791400348634515,
|
| 158 |
+
"eval_runtime": 4.496,
|
| 159 |
+
"eval_samples_per_second": 207.961,
|
| 160 |
+
"eval_steps_per_second": 3.336,
|
| 161 |
+
"step": 4224
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 1.278489589691162,
|
| 166 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 167 |
+
"loss": 0.1269,
|
| 168 |
+
"step": 4752
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.0,
|
| 172 |
+
"eval_accuracy": 0.9579151346516943,
|
| 173 |
+
"eval_f1": 0.7998928475756765,
|
| 174 |
+
"eval_loss": 0.13412921130657196,
|
| 175 |
+
"eval_precision": 0.7420477137176938,
|
| 176 |
+
"eval_recall": 0.8675188843695526,
|
| 177 |
+
"eval_runtime": 4.5039,
|
| 178 |
+
"eval_samples_per_second": 207.596,
|
| 179 |
+
"eval_steps_per_second": 3.33,
|
| 180 |
+
"step": 4752
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 1.4628835916519165,
|
| 185 |
+
"learning_rate": 2.5e-05,
|
| 186 |
+
"loss": 0.124,
|
| 187 |
+
"step": 5280
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.9564742124614926,
|
| 192 |
+
"eval_f1": 0.8013807753584705,
|
| 193 |
+
"eval_loss": 0.13306674361228943,
|
| 194 |
+
"eval_precision": 0.7378973105134474,
|
| 195 |
+
"eval_recall": 0.8768158047646717,
|
| 196 |
+
"eval_runtime": 4.57,
|
| 197 |
+
"eval_samples_per_second": 204.597,
|
| 198 |
+
"eval_steps_per_second": 3.282,
|
| 199 |
+
"step": 5280
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 2.4508931636810303,
|
| 204 |
+
"learning_rate": 2.25e-05,
|
| 205 |
+
"loss": 0.1194,
|
| 206 |
+
"step": 5808
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.9568717082381,
|
| 211 |
+
"eval_f1": 0.803921568627451,
|
| 212 |
+
"eval_loss": 0.13287858664989471,
|
| 213 |
+
"eval_precision": 0.7389186556259133,
|
| 214 |
+
"eval_recall": 0.8814642649622313,
|
| 215 |
+
"eval_runtime": 4.5315,
|
| 216 |
+
"eval_samples_per_second": 206.333,
|
| 217 |
+
"eval_steps_per_second": 3.31,
|
| 218 |
+
"step": 5808
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 12.0,
|
| 222 |
+
"grad_norm": 1.7830716371536255,
|
| 223 |
+
"learning_rate": 2e-05,
|
| 224 |
+
"loss": 0.1171,
|
| 225 |
+
"step": 6336
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 12.0,
|
| 229 |
+
"eval_accuracy": 0.9566729603497963,
|
| 230 |
+
"eval_f1": 0.8026525198938992,
|
| 231 |
+
"eval_loss": 0.13365061581134796,
|
| 232 |
+
"eval_precision": 0.7384089799902391,
|
| 233 |
+
"eval_recall": 0.8791400348634515,
|
| 234 |
+
"eval_runtime": 4.4971,
|
| 235 |
+
"eval_samples_per_second": 207.913,
|
| 236 |
+
"eval_steps_per_second": 3.336,
|
| 237 |
+
"step": 6336
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 13.0,
|
| 241 |
+
"grad_norm": 2.1622517108917236,
|
| 242 |
+
"learning_rate": 1.75e-05,
|
| 243 |
+
"loss": 0.1153,
|
| 244 |
+
"step": 6864
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 13.0,
|
| 248 |
+
"eval_accuracy": 0.9586604392328332,
|
| 249 |
+
"eval_f1": 0.8043826830571886,
|
| 250 |
+
"eval_loss": 0.129431813955307,
|
| 251 |
+
"eval_precision": 0.7446808510638298,
|
| 252 |
+
"eval_recall": 0.8744915746658919,
|
| 253 |
+
"eval_runtime": 4.7971,
|
| 254 |
+
"eval_samples_per_second": 194.907,
|
| 255 |
+
"eval_steps_per_second": 3.127,
|
| 256 |
+
"step": 6864
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 14.0,
|
| 260 |
+
"grad_norm": 1.1562857627868652,
|
| 261 |
+
"learning_rate": 1.5e-05,
|
| 262 |
+
"loss": 0.1119,
|
| 263 |
+
"step": 7392
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 14.0,
|
| 267 |
+
"eval_accuracy": 0.9572692040147074,
|
| 268 |
+
"eval_f1": 0.807794981313401,
|
| 269 |
+
"eval_loss": 0.13104024529457092,
|
| 270 |
+
"eval_precision": 0.7471604938271605,
|
| 271 |
+
"eval_recall": 0.8791400348634515,
|
| 272 |
+
"eval_runtime": 4.8909,
|
| 273 |
+
"eval_samples_per_second": 191.171,
|
| 274 |
+
"eval_steps_per_second": 3.067,
|
| 275 |
+
"step": 7392
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 15.0,
|
| 279 |
+
"grad_norm": 1.6378480195999146,
|
| 280 |
+
"learning_rate": 1.25e-05,
|
| 281 |
+
"loss": 0.1109,
|
| 282 |
+
"step": 7920
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.0,
|
| 286 |
+
"eval_accuracy": 0.9578654476796185,
|
| 287 |
+
"eval_f1": 0.803963577932512,
|
| 288 |
+
"eval_loss": 0.1311807483434677,
|
| 289 |
+
"eval_precision": 0.7456532538499752,
|
| 290 |
+
"eval_recall": 0.8721673445671121,
|
| 291 |
+
"eval_runtime": 4.5487,
|
| 292 |
+
"eval_samples_per_second": 205.552,
|
| 293 |
+
"eval_steps_per_second": 3.298,
|
| 294 |
+
"step": 7920
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.0,
|
| 298 |
+
"grad_norm": 2.3020808696746826,
|
| 299 |
+
"learning_rate": 1e-05,
|
| 300 |
+
"loss": 0.1102,
|
| 301 |
+
"step": 8448
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 16.0,
|
| 305 |
+
"eval_accuracy": 0.9580641955679221,
|
| 306 |
+
"eval_f1": 0.8060735215769846,
|
| 307 |
+
"eval_loss": 0.13092459738254547,
|
| 308 |
+
"eval_precision": 0.7442203639940974,
|
| 309 |
+
"eval_recall": 0.8791400348634515,
|
| 310 |
+
"eval_runtime": 4.5909,
|
| 311 |
+
"eval_samples_per_second": 203.666,
|
| 312 |
+
"eval_steps_per_second": 3.267,
|
| 313 |
+
"step": 8448
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 17.0,
|
| 317 |
+
"grad_norm": 1.444940209388733,
|
| 318 |
+
"learning_rate": 7.5e-06,
|
| 319 |
+
"loss": 0.1095,
|
| 320 |
+
"step": 8976
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 17.0,
|
| 324 |
+
"eval_accuracy": 0.9586604392328332,
|
| 325 |
+
"eval_f1": 0.8073443320915381,
|
| 326 |
+
"eval_loss": 0.13140013813972473,
|
| 327 |
+
"eval_precision": 0.7447226313205695,
|
| 328 |
+
"eval_recall": 0.8814642649622313,
|
| 329 |
+
"eval_runtime": 4.5169,
|
| 330 |
+
"eval_samples_per_second": 206.999,
|
| 331 |
+
"eval_steps_per_second": 3.321,
|
| 332 |
+
"step": 8976
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.0,
|
| 336 |
+
"grad_norm": 1.5871490240097046,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.1073,
|
| 339 |
+
"step": 9504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.0,
|
| 343 |
+
"eval_accuracy": 0.9576666997913147,
|
| 344 |
+
"eval_f1": 0.8018114011720832,
|
| 345 |
+
"eval_loss": 0.1323314905166626,
|
| 346 |
+
"eval_precision": 0.7402852926709297,
|
| 347 |
+
"eval_recall": 0.8744915746658919,
|
| 348 |
+
"eval_runtime": 4.5193,
|
| 349 |
+
"eval_samples_per_second": 206.89,
|
| 350 |
+
"eval_steps_per_second": 3.319,
|
| 351 |
+
"step": 9504
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 19.0,
|
| 355 |
+
"grad_norm": 0.673528254032135,
|
| 356 |
+
"learning_rate": 2.5e-06,
|
| 357 |
+
"loss": 0.107,
|
| 358 |
+
"step": 10032
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 19.0,
|
| 362 |
+
"eval_accuracy": 0.9580641955679221,
|
| 363 |
+
"eval_f1": 0.800106894708712,
|
| 364 |
+
"eval_loss": 0.1300082504749298,
|
| 365 |
+
"eval_precision": 0.7407224146462148,
|
| 366 |
+
"eval_recall": 0.8698431144683324,
|
| 367 |
+
"eval_runtime": 4.5118,
|
| 368 |
+
"eval_samples_per_second": 207.233,
|
| 369 |
+
"eval_steps_per_second": 3.325,
|
| 370 |
+
"step": 10032
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 20.0,
|
| 374 |
+
"grad_norm": 2.0137035846710205,
|
| 375 |
+
"learning_rate": 0.0,
|
| 376 |
+
"loss": 0.1073,
|
| 377 |
+
"step": 10560
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 20.0,
|
| 381 |
+
"eval_accuracy": 0.9578654476796185,
|
| 382 |
+
"eval_f1": 0.800106894708712,
|
| 383 |
+
"eval_loss": 0.1304602026939392,
|
| 384 |
+
"eval_precision": 0.7407224146462148,
|
| 385 |
+
"eval_recall": 0.8698431144683324,
|
| 386 |
+
"eval_runtime": 4.5035,
|
| 387 |
+
"eval_samples_per_second": 207.618,
|
| 388 |
+
"eval_steps_per_second": 3.331,
|
| 389 |
+
"step": 10560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 20.0,
|
| 393 |
+
"step": 10560,
|
| 394 |
+
"total_flos": 4545096690358590.0,
|
| 395 |
+
"train_loss": 0.17226147796168473,
|
| 396 |
+
"train_runtime": 1230.5305,
|
| 397 |
+
"train_samples_per_second": 137.128,
|
| 398 |
+
"train_steps_per_second": 8.582
|
| 399 |
+
}
|
| 400 |
+
],
|
| 401 |
+
"logging_steps": 500,
|
| 402 |
+
"max_steps": 10560,
|
| 403 |
+
"num_input_tokens_seen": 0,
|
| 404 |
+
"num_train_epochs": 20,
|
| 405 |
+
"save_steps": 500,
|
| 406 |
+
"total_flos": 4545096690358590.0,
|
| 407 |
+
"train_batch_size": 16,
|
| 408 |
+
"trial_name": null,
|
| 409 |
+
"trial_params": null
|
| 410 |
+
}
|