End of training
Browse files- README.md +2 -0
- all_results.json +21 -21
- eval_results.json +9 -9
- predict_results.json +8 -8
- predictions.txt +0 -0
- runs/May24_14-22-15_indolem-petl-vm/events.out.tfevents.1716560704.indolem-petl-vm.1458986.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +23 -384
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
CHANGED
|
@@ -1,25 +1,25 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 5.
|
| 9 |
"eval_samples": 935,
|
| 10 |
-
"eval_samples_per_second": 177.
|
| 11 |
-
"eval_steps_per_second": 2.
|
| 12 |
-
"predict_accuracy": 0.
|
| 13 |
-
"predict_f1": 0.
|
| 14 |
-
"predict_loss": 0.
|
| 15 |
-
"predict_precision": 0.
|
| 16 |
-
"predict_recall": 0.
|
| 17 |
-
"predict_runtime": 12.
|
| 18 |
-
"predict_samples_per_second":
|
| 19 |
-
"predict_steps_per_second":
|
| 20 |
-
"train_loss": 0.
|
| 21 |
-
"train_runtime":
|
| 22 |
"train_samples": 8437,
|
| 23 |
-
"train_samples_per_second":
|
| 24 |
-
"train_steps_per_second": 4.
|
| 25 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.963231640663818,
|
| 4 |
+
"eval_f1": 0.8287262872628726,
|
| 5 |
+
"eval_loss": 0.15753257274627686,
|
| 6 |
+
"eval_precision": 0.776536312849162,
|
| 7 |
+
"eval_recall": 0.8884369552585706,
|
| 8 |
+
"eval_runtime": 5.2653,
|
| 9 |
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 177.577,
|
| 11 |
+
"eval_steps_per_second": 2.849,
|
| 12 |
+
"predict_accuracy": 0.9876279863481229,
|
| 13 |
+
"predict_f1": 0.9276586033774533,
|
| 14 |
+
"predict_loss": 0.04439631476998329,
|
| 15 |
+
"predict_precision": 0.9009308510638298,
|
| 16 |
+
"predict_recall": 0.9560206961429916,
|
| 17 |
+
"predict_runtime": 12.1307,
|
| 18 |
+
"predict_samples_per_second": 193.146,
|
| 19 |
+
"predict_steps_per_second": 3.05,
|
| 20 |
+
"train_loss": 0.2260448426911325,
|
| 21 |
+
"train_runtime": 121.6263,
|
| 22 |
"train_samples": 8437,
|
| 23 |
+
"train_samples_per_second": 69.368,
|
| 24 |
+
"train_steps_per_second": 4.341
|
| 25 |
}
|
eval_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 5.
|
| 9 |
"eval_samples": 935,
|
| 10 |
-
"eval_samples_per_second": 177.
|
| 11 |
-
"eval_steps_per_second": 2.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.963231640663818,
|
| 4 |
+
"eval_f1": 0.8287262872628726,
|
| 5 |
+
"eval_loss": 0.15753257274627686,
|
| 6 |
+
"eval_precision": 0.776536312849162,
|
| 7 |
+
"eval_recall": 0.8884369552585706,
|
| 8 |
+
"eval_runtime": 5.2653,
|
| 9 |
"eval_samples": 935,
|
| 10 |
+
"eval_samples_per_second": 177.577,
|
| 11 |
+
"eval_steps_per_second": 2.849
|
| 12 |
}
|
predict_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"predict_accuracy": 0.
|
| 3 |
-
"predict_f1": 0.
|
| 4 |
-
"predict_loss": 0.
|
| 5 |
-
"predict_precision": 0.
|
| 6 |
-
"predict_recall": 0.
|
| 7 |
-
"predict_runtime": 12.
|
| 8 |
-
"predict_samples_per_second":
|
| 9 |
-
"predict_steps_per_second":
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"predict_accuracy": 0.9876279863481229,
|
| 3 |
+
"predict_f1": 0.9276586033774533,
|
| 4 |
+
"predict_loss": 0.04439631476998329,
|
| 5 |
+
"predict_precision": 0.9009308510638298,
|
| 6 |
+
"predict_recall": 0.9560206961429916,
|
| 7 |
+
"predict_runtime": 12.1307,
|
| 8 |
+
"predict_samples_per_second": 193.146,
|
| 9 |
+
"predict_steps_per_second": 3.05
|
| 10 |
}
|
predictions.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/May24_14-22-15_indolem-petl-vm/events.out.tfevents.1716560704.indolem-petl-vm.1458986.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5545fe34c4deba0876f8d82d7cb77b1b464ec643fca5025c73252612695b6c66
|
| 3 |
+
size 560
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 8437,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 4.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.2260448426911325,
|
| 4 |
+
"train_runtime": 121.6263,
|
| 5 |
"train_samples": 8437,
|
| 6 |
+
"train_samples_per_second": 69.368,
|
| 7 |
+
"train_steps_per_second": 4.341
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,409 +1,48 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 528
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.0,
|
| 20 |
-
"eval_accuracy": 0.9596044917022757,
|
| 21 |
-
"eval_f1": 0.8202064095600217,
|
| 22 |
-
"eval_loss": 0.19388806819915771,
|
| 23 |
-
"eval_precision": 0.7700152983171851,
|
| 24 |
-
"eval_recall": 0.8773968622893666,
|
| 25 |
-
"eval_runtime": 5.1559,
|
| 26 |
-
"eval_samples_per_second": 181.347,
|
| 27 |
-
"eval_steps_per_second": 2.909,
|
| 28 |
-
"step": 528
|
| 29 |
-
},
|
| 30 |
-
{
|
| 31 |
-
"epoch": 2.0,
|
| 32 |
-
"grad_norm": 0.10079142451286316,
|
| 33 |
-
"learning_rate": 4.5e-05,
|
| 34 |
-
"loss": 0.0276,
|
| 35 |
-
"step": 1056
|
| 36 |
-
},
|
| 37 |
-
{
|
| 38 |
-
"epoch": 2.0,
|
| 39 |
-
"eval_accuracy": 0.9654178674351584,
|
| 40 |
-
"eval_f1": 0.849859943977591,
|
| 41 |
-
"eval_loss": 0.2743796706199646,
|
| 42 |
-
"eval_precision": 0.8204434829637642,
|
| 43 |
-
"eval_recall": 0.8814642649622313,
|
| 44 |
-
"eval_runtime": 5.6153,
|
| 45 |
-
"eval_samples_per_second": 166.508,
|
| 46 |
-
"eval_steps_per_second": 2.671,
|
| 47 |
-
"step": 1056
|
| 48 |
-
},
|
| 49 |
-
{
|
| 50 |
-
"epoch": 3.0,
|
| 51 |
-
"grad_norm": 0.28567248582839966,
|
| 52 |
-
"learning_rate": 4.25e-05,
|
| 53 |
-
"loss": 0.0118,
|
| 54 |
-
"step": 1584
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 3.0,
|
| 58 |
-
"eval_accuracy": 0.9648216237702475,
|
| 59 |
-
"eval_f1": 0.8464936499171728,
|
| 60 |
-
"eval_loss": 0.3014925420284271,
|
| 61 |
-
"eval_precision": 0.8064176749079431,
|
| 62 |
-
"eval_recall": 0.8907611853573504,
|
| 63 |
-
"eval_runtime": 5.5423,
|
| 64 |
-
"eval_samples_per_second": 168.703,
|
| 65 |
-
"eval_steps_per_second": 2.706,
|
| 66 |
-
"step": 1584
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 4.0,
|
| 70 |
-
"grad_norm": 0.011168558150529861,
|
| 71 |
-
"learning_rate": 4e-05,
|
| 72 |
-
"loss": 0.0069,
|
| 73 |
-
"step": 2112
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 4.0,
|
| 77 |
-
"eval_accuracy": 0.9608466660041737,
|
| 78 |
-
"eval_f1": 0.823240589198036,
|
| 79 |
-
"eval_loss": 0.3687806725502014,
|
| 80 |
-
"eval_precision": 0.7758354755784062,
|
| 81 |
-
"eval_recall": 0.8768158047646717,
|
| 82 |
-
"eval_runtime": 5.5326,
|
| 83 |
-
"eval_samples_per_second": 168.999,
|
| 84 |
-
"eval_steps_per_second": 2.711,
|
| 85 |
-
"step": 2112
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"epoch": 5.0,
|
| 89 |
-
"grad_norm": 0.34764334559440613,
|
| 90 |
-
"learning_rate": 3.7500000000000003e-05,
|
| 91 |
-
"loss": 0.0057,
|
| 92 |
-
"step": 2640
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 5.0,
|
| 96 |
-
"eval_accuracy": 0.9646228758819437,
|
| 97 |
-
"eval_f1": 0.8587848932676518,
|
| 98 |
-
"eval_loss": 0.3538875877857208,
|
| 99 |
-
"eval_precision": 0.8116916709777547,
|
| 100 |
-
"eval_recall": 0.9116792562463684,
|
| 101 |
-
"eval_runtime": 5.4848,
|
| 102 |
-
"eval_samples_per_second": 170.471,
|
| 103 |
-
"eval_steps_per_second": 2.735,
|
| 104 |
-
"step": 2640
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 6.0,
|
| 108 |
-
"grad_norm": 0.3746017515659332,
|
| 109 |
-
"learning_rate": 3.5e-05,
|
| 110 |
-
"loss": 0.004,
|
| 111 |
-
"step": 3168
|
| 112 |
-
},
|
| 113 |
-
{
|
| 114 |
-
"epoch": 6.0,
|
| 115 |
-
"eval_accuracy": 0.9648216237702475,
|
| 116 |
-
"eval_f1": 0.8623391158365977,
|
| 117 |
-
"eval_loss": 0.3289966583251953,
|
| 118 |
-
"eval_precision": 0.8316243928764167,
|
| 119 |
-
"eval_recall": 0.89540964555491,
|
| 120 |
-
"eval_runtime": 5.8759,
|
| 121 |
-
"eval_samples_per_second": 159.123,
|
| 122 |
-
"eval_steps_per_second": 2.553,
|
| 123 |
-
"step": 3168
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 7.0,
|
| 127 |
-
"grad_norm": 0.07094522565603256,
|
| 128 |
-
"learning_rate": 3.2500000000000004e-05,
|
| 129 |
-
"loss": 0.0039,
|
| 130 |
-
"step": 3696
|
| 131 |
-
},
|
| 132 |
-
{
|
| 133 |
-
"epoch": 7.0,
|
| 134 |
-
"eval_accuracy": 0.9664116068766769,
|
| 135 |
-
"eval_f1": 0.8546674119619899,
|
| 136 |
-
"eval_loss": 0.3188040554523468,
|
| 137 |
-
"eval_precision": 0.823371028540657,
|
| 138 |
-
"eval_recall": 0.8884369552585706,
|
| 139 |
-
"eval_runtime": 5.5032,
|
| 140 |
-
"eval_samples_per_second": 169.901,
|
| 141 |
-
"eval_steps_per_second": 2.726,
|
| 142 |
-
"step": 3696
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 8.0,
|
| 146 |
-
"grad_norm": 0.0038832584396004677,
|
| 147 |
-
"learning_rate": 3e-05,
|
| 148 |
-
"loss": 0.0028,
|
| 149 |
-
"step": 4224
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 8.0,
|
| 153 |
-
"eval_accuracy": 0.9666103547649806,
|
| 154 |
-
"eval_f1": 0.8712926692781197,
|
| 155 |
-
"eval_loss": 0.34448835253715515,
|
| 156 |
-
"eval_precision": 0.8402590393955748,
|
| 157 |
-
"eval_recall": 0.9047065659500291,
|
| 158 |
-
"eval_runtime": 5.5531,
|
| 159 |
-
"eval_samples_per_second": 168.375,
|
| 160 |
-
"eval_steps_per_second": 2.701,
|
| 161 |
-
"step": 4224
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 9.0,
|
| 165 |
-
"grad_norm": 0.10262883454561234,
|
| 166 |
-
"learning_rate": 2.7500000000000004e-05,
|
| 167 |
-
"loss": 0.002,
|
| 168 |
-
"step": 4752
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 9.0,
|
| 172 |
"eval_accuracy": 0.963231640663818,
|
| 173 |
-
"eval_f1": 0.
|
| 174 |
-
"eval_loss": 0.
|
| 175 |
-
"eval_precision": 0.
|
| 176 |
-
"eval_recall": 0.
|
| 177 |
-
"eval_runtime": 5.
|
| 178 |
-
"eval_samples_per_second":
|
| 179 |
-
"eval_steps_per_second": 2.
|
| 180 |
-
"step":
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"epoch": 10.0,
|
| 184 |
-
"grad_norm": 1.7891979217529297,
|
| 185 |
-
"learning_rate": 2.5e-05,
|
| 186 |
-
"loss": 0.0022,
|
| 187 |
-
"step": 5280
|
| 188 |
-
},
|
| 189 |
-
{
|
| 190 |
-
"epoch": 10.0,
|
| 191 |
-
"eval_accuracy": 0.9652191195468548,
|
| 192 |
-
"eval_f1": 0.8500273672687466,
|
| 193 |
-
"eval_loss": 0.2817966639995575,
|
| 194 |
-
"eval_precision": 0.8034143817899638,
|
| 195 |
-
"eval_recall": 0.9023823358512493,
|
| 196 |
-
"eval_runtime": 5.5389,
|
| 197 |
-
"eval_samples_per_second": 168.805,
|
| 198 |
-
"eval_steps_per_second": 2.708,
|
| 199 |
-
"step": 5280
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 11.0,
|
| 203 |
-
"grad_norm": 0.0017159333219751716,
|
| 204 |
-
"learning_rate": 2.25e-05,
|
| 205 |
-
"loss": 0.0023,
|
| 206 |
-
"step": 5808
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 11.0,
|
| 210 |
-
"eval_accuracy": 0.9680015899831065,
|
| 211 |
-
"eval_f1": 0.8781163434903048,
|
| 212 |
-
"eval_loss": 0.33934566378593445,
|
| 213 |
-
"eval_precision": 0.8390682901005824,
|
| 214 |
-
"eval_recall": 0.9209761766414875,
|
| 215 |
-
"eval_runtime": 5.5417,
|
| 216 |
-
"eval_samples_per_second": 168.722,
|
| 217 |
-
"eval_steps_per_second": 2.707,
|
| 218 |
-
"step": 5808
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 12.0,
|
| 222 |
-
"grad_norm": 0.00038251353544183075,
|
| 223 |
-
"learning_rate": 2e-05,
|
| 224 |
-
"loss": 0.0015,
|
| 225 |
-
"step": 6336
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 12.0,
|
| 229 |
-
"eval_accuracy": 0.9697903209778396,
|
| 230 |
-
"eval_f1": 0.8782802903405917,
|
| 231 |
-
"eval_loss": 0.347611665725708,
|
| 232 |
-
"eval_precision": 0.8452444922084901,
|
| 233 |
-
"eval_recall": 0.9140034863451482,
|
| 234 |
-
"eval_runtime": 5.6047,
|
| 235 |
-
"eval_samples_per_second": 166.825,
|
| 236 |
-
"eval_steps_per_second": 2.676,
|
| 237 |
-
"step": 6336
|
| 238 |
-
},
|
| 239 |
-
{
|
| 240 |
-
"epoch": 13.0,
|
| 241 |
-
"grad_norm": 0.00045281249913387,
|
| 242 |
-
"learning_rate": 1.75e-05,
|
| 243 |
-
"loss": 0.001,
|
| 244 |
-
"step": 6864
|
| 245 |
-
},
|
| 246 |
-
{
|
| 247 |
-
"epoch": 13.0,
|
| 248 |
-
"eval_accuracy": 0.9668091026532843,
|
| 249 |
-
"eval_f1": 0.8676227247655818,
|
| 250 |
-
"eval_loss": 0.3708130419254303,
|
| 251 |
-
"eval_precision": 0.8257217847769028,
|
| 252 |
-
"eval_recall": 0.9140034863451482,
|
| 253 |
-
"eval_runtime": 5.9184,
|
| 254 |
-
"eval_samples_per_second": 157.983,
|
| 255 |
-
"eval_steps_per_second": 2.534,
|
| 256 |
-
"step": 6864
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 14.0,
|
| 260 |
-
"grad_norm": 0.00011146712495246902,
|
| 261 |
-
"learning_rate": 1.5e-05,
|
| 262 |
-
"loss": 0.0007,
|
| 263 |
-
"step": 7392
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 14.0,
|
| 267 |
-
"eval_accuracy": 0.9682003378714101,
|
| 268 |
-
"eval_f1": 0.8759002770083102,
|
| 269 |
-
"eval_loss": 0.36658215522766113,
|
| 270 |
-
"eval_precision": 0.8369507676019058,
|
| 271 |
-
"eval_recall": 0.9186519465427078,
|
| 272 |
-
"eval_runtime": 5.5299,
|
| 273 |
-
"eval_samples_per_second": 169.08,
|
| 274 |
-
"eval_steps_per_second": 2.713,
|
| 275 |
-
"step": 7392
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 15.0,
|
| 279 |
-
"grad_norm": 0.00011501595872687176,
|
| 280 |
-
"learning_rate": 1.25e-05,
|
| 281 |
-
"loss": 0.0006,
|
| 282 |
-
"step": 7920
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 15.0,
|
| 286 |
-
"eval_accuracy": 0.9691940773129285,
|
| 287 |
-
"eval_f1": 0.8664440734557595,
|
| 288 |
-
"eval_loss": 0.37411239743232727,
|
| 289 |
-
"eval_precision": 0.8312867058195409,
|
| 290 |
-
"eval_recall": 0.9047065659500291,
|
| 291 |
-
"eval_runtime": 5.4901,
|
| 292 |
-
"eval_samples_per_second": 170.305,
|
| 293 |
-
"eval_steps_per_second": 2.732,
|
| 294 |
-
"step": 7920
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 16.0,
|
| 298 |
-
"grad_norm": 0.00025895825820043683,
|
| 299 |
-
"learning_rate": 1e-05,
|
| 300 |
-
"loss": 0.0003,
|
| 301 |
-
"step": 8448
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"epoch": 16.0,
|
| 305 |
-
"eval_accuracy": 0.9658153632117659,
|
| 306 |
-
"eval_f1": 0.8607242339832869,
|
| 307 |
-
"eval_loss": 0.39565855264663696,
|
| 308 |
-
"eval_precision": 0.826645264847512,
|
| 309 |
-
"eval_recall": 0.8977338756536897,
|
| 310 |
-
"eval_runtime": 5.5324,
|
| 311 |
-
"eval_samples_per_second": 169.003,
|
| 312 |
-
"eval_steps_per_second": 2.711,
|
| 313 |
-
"step": 8448
|
| 314 |
-
},
|
| 315 |
-
{
|
| 316 |
-
"epoch": 17.0,
|
| 317 |
-
"grad_norm": 0.0003481700550764799,
|
| 318 |
-
"learning_rate": 7.5e-06,
|
| 319 |
-
"loss": 0.0005,
|
| 320 |
-
"step": 8976
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 17.0,
|
| 324 |
-
"eval_accuracy": 0.9668091026532843,
|
| 325 |
-
"eval_f1": 0.8669598680593732,
|
| 326 |
-
"eval_loss": 0.3977995216846466,
|
| 327 |
-
"eval_precision": 0.8226395409494001,
|
| 328 |
-
"eval_recall": 0.916327716443928,
|
| 329 |
-
"eval_runtime": 5.5647,
|
| 330 |
-
"eval_samples_per_second": 168.025,
|
| 331 |
-
"eval_steps_per_second": 2.696,
|
| 332 |
-
"step": 8976
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 18.0,
|
| 336 |
-
"grad_norm": 0.0018348400481045246,
|
| 337 |
-
"learning_rate": 5e-06,
|
| 338 |
-
"loss": 0.0003,
|
| 339 |
-
"step": 9504
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 18.0,
|
| 343 |
-
"eval_accuracy": 0.9695915730895359,
|
| 344 |
-
"eval_f1": 0.8696378830083566,
|
| 345 |
-
"eval_loss": 0.369892954826355,
|
| 346 |
-
"eval_precision": 0.8352059925093633,
|
| 347 |
-
"eval_recall": 0.9070307960488089,
|
| 348 |
-
"eval_runtime": 5.5296,
|
| 349 |
-
"eval_samples_per_second": 169.09,
|
| 350 |
-
"eval_steps_per_second": 2.713,
|
| 351 |
-
"step": 9504
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 19.0,
|
| 355 |
-
"grad_norm": 0.009025489911437035,
|
| 356 |
-
"learning_rate": 2.5e-06,
|
| 357 |
-
"loss": 0.0003,
|
| 358 |
-
"step": 10032
|
| 359 |
-
},
|
| 360 |
-
{
|
| 361 |
-
"epoch": 19.0,
|
| 362 |
-
"eval_accuracy": 0.9676040942064991,
|
| 363 |
-
"eval_f1": 0.8635112823335168,
|
| 364 |
-
"eval_loss": 0.3967481553554535,
|
| 365 |
-
"eval_precision": 0.8201777313120753,
|
| 366 |
-
"eval_recall": 0.9116792562463684,
|
| 367 |
-
"eval_runtime": 5.5982,
|
| 368 |
-
"eval_samples_per_second": 167.019,
|
| 369 |
-
"eval_steps_per_second": 2.679,
|
| 370 |
-
"step": 10032
|
| 371 |
-
},
|
| 372 |
-
{
|
| 373 |
-
"epoch": 20.0,
|
| 374 |
-
"grad_norm": 0.00020879444491583854,
|
| 375 |
-
"learning_rate": 0.0,
|
| 376 |
-
"loss": 0.0004,
|
| 377 |
-
"step": 10560
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 20.0,
|
| 381 |
-
"eval_accuracy": 0.9680015899831065,
|
| 382 |
-
"eval_f1": 0.8632101489244347,
|
| 383 |
-
"eval_loss": 0.38609787821769714,
|
| 384 |
-
"eval_precision": 0.821522309711286,
|
| 385 |
-
"eval_recall": 0.9093550261475886,
|
| 386 |
-
"eval_runtime": 5.6205,
|
| 387 |
-
"eval_samples_per_second": 166.355,
|
| 388 |
-
"eval_steps_per_second": 2.669,
|
| 389 |
-
"step": 10560
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch":
|
| 393 |
-
"step":
|
| 394 |
-
"total_flos":
|
| 395 |
-
"train_loss": 0.
|
| 396 |
-
"train_runtime":
|
| 397 |
-
"train_samples_per_second":
|
| 398 |
-
"train_steps_per_second": 4.
|
| 399 |
}
|
| 400 |
],
|
| 401 |
"logging_steps": 500,
|
| 402 |
-
"max_steps":
|
| 403 |
"num_input_tokens_seen": 0,
|
| 404 |
-
"num_train_epochs":
|
| 405 |
"save_steps": 500,
|
| 406 |
-
"total_flos":
|
| 407 |
"train_batch_size": 16,
|
| 408 |
"trial_name": null,
|
| 409 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 528,
|
| 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": 1.4932644367218018,
|
| 14 |
+
"learning_rate": 0.0,
|
| 15 |
+
"loss": 0.226,
|
| 16 |
"step": 528
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"eval_accuracy": 0.963231640663818,
|
| 21 |
+
"eval_f1": 0.8287262872628726,
|
| 22 |
+
"eval_loss": 0.15753257274627686,
|
| 23 |
+
"eval_precision": 0.776536312849162,
|
| 24 |
+
"eval_recall": 0.8884369552585706,
|
| 25 |
+
"eval_runtime": 5.3398,
|
| 26 |
+
"eval_samples_per_second": 175.101,
|
| 27 |
+
"eval_steps_per_second": 2.809,
|
| 28 |
+
"step": 528
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
},
|
| 30 |
{
|
| 31 |
+
"epoch": 1.0,
|
| 32 |
+
"step": 528,
|
| 33 |
+
"total_flos": 230610745968444.0,
|
| 34 |
+
"train_loss": 0.2260448426911325,
|
| 35 |
+
"train_runtime": 121.6263,
|
| 36 |
+
"train_samples_per_second": 69.368,
|
| 37 |
+
"train_steps_per_second": 4.341
|
| 38 |
}
|
| 39 |
],
|
| 40 |
"logging_steps": 500,
|
| 41 |
+
"max_steps": 528,
|
| 42 |
"num_input_tokens_seen": 0,
|
| 43 |
+
"num_train_epochs": 1,
|
| 44 |
"save_steps": 500,
|
| 45 |
+
"total_flos": 230610745968444.0,
|
| 46 |
"train_batch_size": 16,
|
| 47 |
"trial_name": null,
|
| 48 |
"trial_params": null
|