Training in progress, epoch 3, checkpoint
Browse files
checkpoint-30/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0541191af5ab85457dfa9a0f72fe4aa90d25b52ddb14cfba993bf428c1f96cae
|
| 3 |
+
size 1214121120
|
checkpoint-30/trainer_state.json
ADDED
|
@@ -0,0 +1,271 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 30,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.1,
|
| 14 |
+
"grad_norm": 4.817715644836426,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 2.4596,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.2,
|
| 21 |
+
"grad_norm": 4.894565105438232,
|
| 22 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 23 |
+
"loss": 2.468,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.3,
|
| 28 |
+
"grad_norm": 4.599151134490967,
|
| 29 |
+
"learning_rate": 6.666666666666667e-05,
|
| 30 |
+
"loss": 2.4369,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.4,
|
| 35 |
+
"grad_norm": 4.634383678436279,
|
| 36 |
+
"learning_rate": 0.0001,
|
| 37 |
+
"loss": 2.4219,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.5,
|
| 42 |
+
"grad_norm": 4.405484676361084,
|
| 43 |
+
"learning_rate": 9.997377845227576e-05,
|
| 44 |
+
"loss": 2.3884,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.6,
|
| 49 |
+
"grad_norm": 4.227508068084717,
|
| 50 |
+
"learning_rate": 9.989514131188559e-05,
|
| 51 |
+
"loss": 2.3539,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.7,
|
| 56 |
+
"grad_norm": 3.989192247390747,
|
| 57 |
+
"learning_rate": 9.97641710583307e-05,
|
| 58 |
+
"loss": 2.3132,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.8,
|
| 63 |
+
"grad_norm": 3.904679775238037,
|
| 64 |
+
"learning_rate": 9.958100506132127e-05,
|
| 65 |
+
"loss": 2.2919,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.9,
|
| 70 |
+
"grad_norm": 3.8267431259155273,
|
| 71 |
+
"learning_rate": 9.934583543669453e-05,
|
| 72 |
+
"loss": 2.2709,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.0,
|
| 77 |
+
"grad_norm": 3.6127519607543945,
|
| 78 |
+
"learning_rate": 9.905890884491195e-05,
|
| 79 |
+
"loss": 2.2313,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0,
|
| 84 |
+
"eval_accuracy": 0.1856,
|
| 85 |
+
"eval_loss": 2.2107839584350586,
|
| 86 |
+
"eval_runtime": 18.3869,
|
| 87 |
+
"eval_samples_per_second": 543.864,
|
| 88 |
+
"eval_steps_per_second": 0.109,
|
| 89 |
+
"step": 10
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.1,
|
| 93 |
+
"grad_norm": 3.6324033737182617,
|
| 94 |
+
"learning_rate": 9.872052623234632e-05,
|
| 95 |
+
"loss": 2.2162,
|
| 96 |
+
"step": 11
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.2,
|
| 100 |
+
"grad_norm": 3.4379923343658447,
|
| 101 |
+
"learning_rate": 9.833104251563056e-05,
|
| 102 |
+
"loss": 2.1835,
|
| 103 |
+
"step": 12
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.3,
|
| 107 |
+
"grad_norm": 3.394665479660034,
|
| 108 |
+
"learning_rate": 9.789086620939936e-05,
|
| 109 |
+
"loss": 2.1677,
|
| 110 |
+
"step": 13
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.4,
|
| 114 |
+
"grad_norm": 3.3317911624908447,
|
| 115 |
+
"learning_rate": 9.740045899781352e-05,
|
| 116 |
+
"loss": 2.1358,
|
| 117 |
+
"step": 14
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.5,
|
| 121 |
+
"grad_norm": 3.2182583808898926,
|
| 122 |
+
"learning_rate": 9.686033525031719e-05,
|
| 123 |
+
"loss": 2.1124,
|
| 124 |
+
"step": 15
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.6,
|
| 128 |
+
"grad_norm": 3.1929690837860107,
|
| 129 |
+
"learning_rate": 9.627106148213522e-05,
|
| 130 |
+
"loss": 2.0794,
|
| 131 |
+
"step": 16
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.7,
|
| 135 |
+
"grad_norm": 3.1744496822357178,
|
| 136 |
+
"learning_rate": 9.563325576007701e-05,
|
| 137 |
+
"loss": 2.0664,
|
| 138 |
+
"step": 17
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.8,
|
| 142 |
+
"grad_norm": 3.2177734375,
|
| 143 |
+
"learning_rate": 9.494758705426978e-05,
|
| 144 |
+
"loss": 2.0374,
|
| 145 |
+
"step": 18
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.9,
|
| 149 |
+
"grad_norm": 3.143730640411377,
|
| 150 |
+
"learning_rate": 9.421477453650118e-05,
|
| 151 |
+
"loss": 2.0087,
|
| 152 |
+
"step": 19
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.0,
|
| 156 |
+
"grad_norm": 3.086007595062256,
|
| 157 |
+
"learning_rate": 9.343558682590756e-05,
|
| 158 |
+
"loss": 1.9995,
|
| 159 |
+
"step": 20
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.0,
|
| 163 |
+
"eval_accuracy": 0.3659,
|
| 164 |
+
"eval_loss": 1.9728946685791016,
|
| 165 |
+
"eval_runtime": 18.2892,
|
| 166 |
+
"eval_samples_per_second": 546.77,
|
| 167 |
+
"eval_steps_per_second": 0.109,
|
| 168 |
+
"step": 20
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.1,
|
| 172 |
+
"grad_norm": 3.093388795852661,
|
| 173 |
+
"learning_rate": 9.261084118279847e-05,
|
| 174 |
+
"loss": 1.9768,
|
| 175 |
+
"step": 21
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 2.2,
|
| 179 |
+
"grad_norm": 3.0235588550567627,
|
| 180 |
+
"learning_rate": 9.174140265146356e-05,
|
| 181 |
+
"loss": 1.9573,
|
| 182 |
+
"step": 22
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.3,
|
| 186 |
+
"grad_norm": 3.054340362548828,
|
| 187 |
+
"learning_rate": 9.082818315286055e-05,
|
| 188 |
+
"loss": 1.9279,
|
| 189 |
+
"step": 23
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.4,
|
| 193 |
+
"grad_norm": 2.977816104888916,
|
| 194 |
+
"learning_rate": 8.987214052813604e-05,
|
| 195 |
+
"loss": 1.9009,
|
| 196 |
+
"step": 24
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.5,
|
| 200 |
+
"grad_norm": 2.974107027053833,
|
| 201 |
+
"learning_rate": 8.887427753398248e-05,
|
| 202 |
+
"loss": 1.8879,
|
| 203 |
+
"step": 25
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.6,
|
| 207 |
+
"grad_norm": 2.926490545272827,
|
| 208 |
+
"learning_rate": 8.783564079088477e-05,
|
| 209 |
+
"loss": 1.8672,
|
| 210 |
+
"step": 26
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.7,
|
| 214 |
+
"grad_norm": 2.8999850749969482,
|
| 215 |
+
"learning_rate": 8.675731968536002e-05,
|
| 216 |
+
"loss": 1.8563,
|
| 217 |
+
"step": 27
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.8,
|
| 221 |
+
"grad_norm": 2.8928842544555664,
|
| 222 |
+
"learning_rate": 8.564044522734147e-05,
|
| 223 |
+
"loss": 1.832,
|
| 224 |
+
"step": 28
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.9,
|
| 228 |
+
"grad_norm": 2.8881161212921143,
|
| 229 |
+
"learning_rate": 8.448618886390522e-05,
|
| 230 |
+
"loss": 1.8051,
|
| 231 |
+
"step": 29
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 3.0,
|
| 235 |
+
"grad_norm": 2.852555274963379,
|
| 236 |
+
"learning_rate": 8.329576125058406e-05,
|
| 237 |
+
"loss": 1.7828,
|
| 238 |
+
"step": 30
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.0,
|
| 242 |
+
"eval_accuracy": 0.5687,
|
| 243 |
+
"eval_loss": 1.7709296941757202,
|
| 244 |
+
"eval_runtime": 18.5173,
|
| 245 |
+
"eval_samples_per_second": 540.036,
|
| 246 |
+
"eval_steps_per_second": 0.108,
|
| 247 |
+
"step": 30
|
| 248 |
+
}
|
| 249 |
+
],
|
| 250 |
+
"logging_steps": 1,
|
| 251 |
+
"max_steps": 100,
|
| 252 |
+
"num_input_tokens_seen": 0,
|
| 253 |
+
"num_train_epochs": 10,
|
| 254 |
+
"save_steps": 1,
|
| 255 |
+
"stateful_callbacks": {
|
| 256 |
+
"TrainerControl": {
|
| 257 |
+
"args": {
|
| 258 |
+
"should_epoch_stop": false,
|
| 259 |
+
"should_evaluate": false,
|
| 260 |
+
"should_log": false,
|
| 261 |
+
"should_save": true,
|
| 262 |
+
"should_training_stop": false
|
| 263 |
+
},
|
| 264 |
+
"attributes": {}
|
| 265 |
+
}
|
| 266 |
+
},
|
| 267 |
+
"total_flos": 0.0,
|
| 268 |
+
"train_batch_size": 512,
|
| 269 |
+
"trial_name": null,
|
| 270 |
+
"trial_params": null
|
| 271 |
+
}
|
checkpoint-30/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8791579e23520b4bd71b23dd7de782fc70967c05dcdd1d44ffc944f00ab7f116
|
| 3 |
+
size 5777
|