Upload 8 files
Browse files- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +465 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fc06cbe2a43b0a0c035ed87bf071a180679b4135f5645b2d266c2599065ae1c
|
| 3 |
+
size 33662074
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77d2e2048751f7b82b7d03a4d56de219162dbe5a0a285f2a2e022884f503a580
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c0ba6dee32a29c1b38007c255586352f19a3c1a7bfb24452b6b1f3673e8e047
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,465 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9955555555555555,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 562,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.035555555555555556,
|
| 13 |
+
"grad_norm": 11.767955780029297,
|
| 14 |
+
"learning_rate": 0.00019679715302491104,
|
| 15 |
+
"loss": 33.6554,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07111111111111111,
|
| 20 |
+
"grad_norm": 9.438668251037598,
|
| 21 |
+
"learning_rate": 0.0001932384341637011,
|
| 22 |
+
"loss": 33.8787,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10666666666666667,
|
| 27 |
+
"grad_norm": 10.174617767333984,
|
| 28 |
+
"learning_rate": 0.00018967971530249112,
|
| 29 |
+
"loss": 33.8919,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.14222222222222222,
|
| 34 |
+
"grad_norm": 8.84274673461914,
|
| 35 |
+
"learning_rate": 0.00018612099644128114,
|
| 36 |
+
"loss": 33.7011,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.17777777777777778,
|
| 41 |
+
"grad_norm": 10.169342041015625,
|
| 42 |
+
"learning_rate": 0.0001825622775800712,
|
| 43 |
+
"loss": 33.6306,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21333333333333335,
|
| 48 |
+
"grad_norm": 9.339362144470215,
|
| 49 |
+
"learning_rate": 0.0001790035587188612,
|
| 50 |
+
"loss": 33.5378,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.24888888888888888,
|
| 55 |
+
"grad_norm": 10.399051666259766,
|
| 56 |
+
"learning_rate": 0.00017544483985765125,
|
| 57 |
+
"loss": 33.1223,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.28444444444444444,
|
| 62 |
+
"grad_norm": 8.772202491760254,
|
| 63 |
+
"learning_rate": 0.00017188612099644127,
|
| 64 |
+
"loss": 34.3864,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.32,
|
| 69 |
+
"grad_norm": 9.338233947753906,
|
| 70 |
+
"learning_rate": 0.00016832740213523133,
|
| 71 |
+
"loss": 33.2955,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.35555555555555557,
|
| 76 |
+
"grad_norm": 9.439739227294922,
|
| 77 |
+
"learning_rate": 0.00016476868327402135,
|
| 78 |
+
"loss": 33.229,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.35555555555555557,
|
| 83 |
+
"eval_loss": 2.133469820022583,
|
| 84 |
+
"eval_runtime": 296.1668,
|
| 85 |
+
"eval_samples_per_second": 3.376,
|
| 86 |
+
"eval_steps_per_second": 0.422,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.39111111111111113,
|
| 91 |
+
"grad_norm": 9.046673774719238,
|
| 92 |
+
"learning_rate": 0.0001612099644128114,
|
| 93 |
+
"loss": 33.3667,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.4266666666666667,
|
| 98 |
+
"grad_norm": 8.99227237701416,
|
| 99 |
+
"learning_rate": 0.00015765124555160143,
|
| 100 |
+
"loss": 32.6701,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.4622222222222222,
|
| 105 |
+
"grad_norm": 7.6904144287109375,
|
| 106 |
+
"learning_rate": 0.00015409252669039148,
|
| 107 |
+
"loss": 33.2927,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.49777777777777776,
|
| 112 |
+
"grad_norm": 8.012206077575684,
|
| 113 |
+
"learning_rate": 0.00015053380782918148,
|
| 114 |
+
"loss": 33.2934,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.5333333333333333,
|
| 119 |
+
"grad_norm": 10.931622505187988,
|
| 120 |
+
"learning_rate": 0.00014697508896797153,
|
| 121 |
+
"loss": 33.3676,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5688888888888889,
|
| 126 |
+
"grad_norm": 7.606035232543945,
|
| 127 |
+
"learning_rate": 0.00014341637010676156,
|
| 128 |
+
"loss": 34.1758,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6044444444444445,
|
| 133 |
+
"grad_norm": 9.531214714050293,
|
| 134 |
+
"learning_rate": 0.0001398576512455516,
|
| 135 |
+
"loss": 33.0847,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.64,
|
| 140 |
+
"grad_norm": 8.761300086975098,
|
| 141 |
+
"learning_rate": 0.00013629893238434164,
|
| 142 |
+
"loss": 33.5206,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6755555555555556,
|
| 147 |
+
"grad_norm": 9.155729293823242,
|
| 148 |
+
"learning_rate": 0.0001327402135231317,
|
| 149 |
+
"loss": 33.2403,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.7111111111111111,
|
| 154 |
+
"grad_norm": 9.354476928710938,
|
| 155 |
+
"learning_rate": 0.00012918149466192172,
|
| 156 |
+
"loss": 33.5548,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.7111111111111111,
|
| 161 |
+
"eval_loss": 2.126850128173828,
|
| 162 |
+
"eval_runtime": 296.1679,
|
| 163 |
+
"eval_samples_per_second": 3.376,
|
| 164 |
+
"eval_steps_per_second": 0.422,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.7466666666666667,
|
| 169 |
+
"grad_norm": 8.922224998474121,
|
| 170 |
+
"learning_rate": 0.00012562277580071177,
|
| 171 |
+
"loss": 33.279,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.7822222222222223,
|
| 176 |
+
"grad_norm": 9.973633766174316,
|
| 177 |
+
"learning_rate": 0.00012206405693950178,
|
| 178 |
+
"loss": 33.5481,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.8177777777777778,
|
| 183 |
+
"grad_norm": 8.771803855895996,
|
| 184 |
+
"learning_rate": 0.00011850533807829183,
|
| 185 |
+
"loss": 33.1058,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.8533333333333334,
|
| 190 |
+
"grad_norm": 10.16543960571289,
|
| 191 |
+
"learning_rate": 0.00011494661921708185,
|
| 192 |
+
"loss": 33.3706,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.8888888888888888,
|
| 197 |
+
"grad_norm": 9.286821365356445,
|
| 198 |
+
"learning_rate": 0.0001113879003558719,
|
| 199 |
+
"loss": 33.3456,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.9244444444444444,
|
| 204 |
+
"grad_norm": 9.520956039428711,
|
| 205 |
+
"learning_rate": 0.00010782918149466192,
|
| 206 |
+
"loss": 33.5781,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.96,
|
| 211 |
+
"grad_norm": 10.376456260681152,
|
| 212 |
+
"learning_rate": 0.00010427046263345198,
|
| 213 |
+
"loss": 32.9687,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.9955555555555555,
|
| 218 |
+
"grad_norm": 8.36178207397461,
|
| 219 |
+
"learning_rate": 0.00010071174377224199,
|
| 220 |
+
"loss": 33.7239,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.0284444444444445,
|
| 225 |
+
"grad_norm": 10.113052368164062,
|
| 226 |
+
"learning_rate": 9.715302491103203e-05,
|
| 227 |
+
"loss": 29.9997,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.064,
|
| 232 |
+
"grad_norm": 11.123631477355957,
|
| 233 |
+
"learning_rate": 9.359430604982207e-05,
|
| 234 |
+
"loss": 32.5004,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.064,
|
| 239 |
+
"eval_loss": 2.122236490249634,
|
| 240 |
+
"eval_runtime": 296.127,
|
| 241 |
+
"eval_samples_per_second": 3.377,
|
| 242 |
+
"eval_steps_per_second": 0.422,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.0995555555555556,
|
| 247 |
+
"grad_norm": 9.897551536560059,
|
| 248 |
+
"learning_rate": 9.00355871886121e-05,
|
| 249 |
+
"loss": 32.5046,
|
| 250 |
+
"step": 310
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.1351111111111112,
|
| 254 |
+
"grad_norm": 9.53073501586914,
|
| 255 |
+
"learning_rate": 8.647686832740213e-05,
|
| 256 |
+
"loss": 32.2727,
|
| 257 |
+
"step": 320
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.1706666666666667,
|
| 261 |
+
"grad_norm": 10.394311904907227,
|
| 262 |
+
"learning_rate": 8.291814946619217e-05,
|
| 263 |
+
"loss": 32.688,
|
| 264 |
+
"step": 330
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.2062222222222223,
|
| 268 |
+
"grad_norm": 9.498970031738281,
|
| 269 |
+
"learning_rate": 7.935943060498221e-05,
|
| 270 |
+
"loss": 33.6316,
|
| 271 |
+
"step": 340
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.2417777777777779,
|
| 275 |
+
"grad_norm": 10.150975227355957,
|
| 276 |
+
"learning_rate": 7.580071174377225e-05,
|
| 277 |
+
"loss": 33.0713,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.2773333333333334,
|
| 282 |
+
"grad_norm": 9.899177551269531,
|
| 283 |
+
"learning_rate": 7.224199288256229e-05,
|
| 284 |
+
"loss": 32.4769,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.3128888888888888,
|
| 289 |
+
"grad_norm": 9.39831829071045,
|
| 290 |
+
"learning_rate": 6.868327402135231e-05,
|
| 291 |
+
"loss": 32.2654,
|
| 292 |
+
"step": 370
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.3484444444444446,
|
| 296 |
+
"grad_norm": 10.761151313781738,
|
| 297 |
+
"learning_rate": 6.512455516014235e-05,
|
| 298 |
+
"loss": 32.491,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.384,
|
| 303 |
+
"grad_norm": 9.932414054870605,
|
| 304 |
+
"learning_rate": 6.156583629893239e-05,
|
| 305 |
+
"loss": 33.5308,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.4195555555555557,
|
| 310 |
+
"grad_norm": 11.054327011108398,
|
| 311 |
+
"learning_rate": 5.8007117437722425e-05,
|
| 312 |
+
"loss": 31.7061,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.4195555555555557,
|
| 317 |
+
"eval_loss": 2.120673418045044,
|
| 318 |
+
"eval_runtime": 296.1092,
|
| 319 |
+
"eval_samples_per_second": 3.377,
|
| 320 |
+
"eval_steps_per_second": 0.422,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.455111111111111,
|
| 325 |
+
"grad_norm": 10.89476203918457,
|
| 326 |
+
"learning_rate": 5.4448398576512464e-05,
|
| 327 |
+
"loss": 32.485,
|
| 328 |
+
"step": 410
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.4906666666666666,
|
| 332 |
+
"grad_norm": 9.823376655578613,
|
| 333 |
+
"learning_rate": 5.0889679715302496e-05,
|
| 334 |
+
"loss": 32.9951,
|
| 335 |
+
"step": 420
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.5262222222222221,
|
| 339 |
+
"grad_norm": 11.316079139709473,
|
| 340 |
+
"learning_rate": 4.733096085409253e-05,
|
| 341 |
+
"loss": 32.3443,
|
| 342 |
+
"step": 430
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.561777777777778,
|
| 346 |
+
"grad_norm": 11.608524322509766,
|
| 347 |
+
"learning_rate": 4.377224199288256e-05,
|
| 348 |
+
"loss": 32.2948,
|
| 349 |
+
"step": 440
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.5973333333333333,
|
| 353 |
+
"grad_norm": 11.020298957824707,
|
| 354 |
+
"learning_rate": 4.02135231316726e-05,
|
| 355 |
+
"loss": 32.6702,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.6328888888888888,
|
| 360 |
+
"grad_norm": 9.804555892944336,
|
| 361 |
+
"learning_rate": 3.665480427046263e-05,
|
| 362 |
+
"loss": 31.6452,
|
| 363 |
+
"step": 460
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.6684444444444444,
|
| 367 |
+
"grad_norm": 11.037073135375977,
|
| 368 |
+
"learning_rate": 3.309608540925267e-05,
|
| 369 |
+
"loss": 32.479,
|
| 370 |
+
"step": 470
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.704,
|
| 374 |
+
"grad_norm": 9.837021827697754,
|
| 375 |
+
"learning_rate": 2.9537366548042704e-05,
|
| 376 |
+
"loss": 32.72,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.7395555555555555,
|
| 381 |
+
"grad_norm": 11.720721244812012,
|
| 382 |
+
"learning_rate": 2.597864768683274e-05,
|
| 383 |
+
"loss": 32.6789,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.775111111111111,
|
| 388 |
+
"grad_norm": 11.738125801086426,
|
| 389 |
+
"learning_rate": 2.2419928825622775e-05,
|
| 390 |
+
"loss": 33.3128,
|
| 391 |
+
"step": 500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.775111111111111,
|
| 395 |
+
"eval_loss": 2.11881947517395,
|
| 396 |
+
"eval_runtime": 296.1216,
|
| 397 |
+
"eval_samples_per_second": 3.377,
|
| 398 |
+
"eval_steps_per_second": 0.422,
|
| 399 |
+
"step": 500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.8106666666666666,
|
| 403 |
+
"grad_norm": 11.249613761901855,
|
| 404 |
+
"learning_rate": 1.8861209964412814e-05,
|
| 405 |
+
"loss": 31.9298,
|
| 406 |
+
"step": 510
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.8462222222222222,
|
| 410 |
+
"grad_norm": 11.530637741088867,
|
| 411 |
+
"learning_rate": 1.530249110320285e-05,
|
| 412 |
+
"loss": 31.8878,
|
| 413 |
+
"step": 520
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.8817777777777778,
|
| 417 |
+
"grad_norm": 11.147592544555664,
|
| 418 |
+
"learning_rate": 1.1743772241992882e-05,
|
| 419 |
+
"loss": 32.6852,
|
| 420 |
+
"step": 530
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.9173333333333333,
|
| 424 |
+
"grad_norm": 9.81916332244873,
|
| 425 |
+
"learning_rate": 8.185053380782918e-06,
|
| 426 |
+
"loss": 32.1578,
|
| 427 |
+
"step": 540
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.952888888888889,
|
| 431 |
+
"grad_norm": 10.557317733764648,
|
| 432 |
+
"learning_rate": 4.626334519572954e-06,
|
| 433 |
+
"loss": 32.2151,
|
| 434 |
+
"step": 550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.9884444444444445,
|
| 438 |
+
"grad_norm": 10.493524551391602,
|
| 439 |
+
"learning_rate": 1.0676156583629894e-06,
|
| 440 |
+
"loss": 31.9549,
|
| 441 |
+
"step": 560
|
| 442 |
+
}
|
| 443 |
+
],
|
| 444 |
+
"logging_steps": 10,
|
| 445 |
+
"max_steps": 562,
|
| 446 |
+
"num_input_tokens_seen": 0,
|
| 447 |
+
"num_train_epochs": 2,
|
| 448 |
+
"save_steps": 100,
|
| 449 |
+
"stateful_callbacks": {
|
| 450 |
+
"TrainerControl": {
|
| 451 |
+
"args": {
|
| 452 |
+
"should_epoch_stop": false,
|
| 453 |
+
"should_evaluate": false,
|
| 454 |
+
"should_log": false,
|
| 455 |
+
"should_save": true,
|
| 456 |
+
"should_training_stop": true
|
| 457 |
+
},
|
| 458 |
+
"attributes": {}
|
| 459 |
+
}
|
| 460 |
+
},
|
| 461 |
+
"total_flos": 5.93400073703424e+16,
|
| 462 |
+
"train_batch_size": 2,
|
| 463 |
+
"trial_name": null,
|
| 464 |
+
"trial_params": null
|
| 465 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f8fc3b0faf567e506d36321edce6eabba9e66e2254f1e24c9840de83a3bb7cb
|
| 3 |
+
size 5304
|