Training in progress, epoch 6, checkpoint
Browse files
checkpoint-60/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21be17c061ccc6e4ff2eb6ee2f69f1b0ef56bf4426cc95288b926fd9bd31b7ad
|
| 3 |
+
size 1214121120
|
checkpoint-60/trainer_state.json
ADDED
|
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 60,
|
| 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 |
+
"epoch": 3.1,
|
| 251 |
+
"grad_norm": 2.829819679260254,
|
| 252 |
+
"learning_rate": 8.2070410981557e-05,
|
| 253 |
+
"loss": 1.7684,
|
| 254 |
+
"step": 31
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.2,
|
| 258 |
+
"grad_norm": 2.830519437789917,
|
| 259 |
+
"learning_rate": 8.081142328004637e-05,
|
| 260 |
+
"loss": 1.7467,
|
| 261 |
+
"step": 32
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.3,
|
| 265 |
+
"grad_norm": 2.827852964401245,
|
| 266 |
+
"learning_rate": 7.952011865029614e-05,
|
| 267 |
+
"loss": 1.7348,
|
| 268 |
+
"step": 33
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.4,
|
| 272 |
+
"grad_norm": 2.8194892406463623,
|
| 273 |
+
"learning_rate": 7.819785149254532e-05,
|
| 274 |
+
"loss": 1.7118,
|
| 275 |
+
"step": 34
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.5,
|
| 279 |
+
"grad_norm": 2.788273334503174,
|
| 280 |
+
"learning_rate": 7.68460086824492e-05,
|
| 281 |
+
"loss": 1.6999,
|
| 282 |
+
"step": 35
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.6,
|
| 286 |
+
"grad_norm": 2.770765542984009,
|
| 287 |
+
"learning_rate": 7.546600811643816e-05,
|
| 288 |
+
"loss": 1.6856,
|
| 289 |
+
"step": 36
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.7,
|
| 293 |
+
"grad_norm": 2.784775972366333,
|
| 294 |
+
"learning_rate": 7.405929722454026e-05,
|
| 295 |
+
"loss": 1.6736,
|
| 296 |
+
"step": 37
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.8,
|
| 300 |
+
"grad_norm": 2.7415084838867188,
|
| 301 |
+
"learning_rate": 7.262735145222696e-05,
|
| 302 |
+
"loss": 1.6511,
|
| 303 |
+
"step": 38
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.9,
|
| 307 |
+
"grad_norm": 2.702268123626709,
|
| 308 |
+
"learning_rate": 7.117167271287453e-05,
|
| 309 |
+
"loss": 1.6376,
|
| 310 |
+
"step": 39
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.0,
|
| 314 |
+
"grad_norm": 2.713175058364868,
|
| 315 |
+
"learning_rate": 6.969378781246436e-05,
|
| 316 |
+
"loss": 1.6164,
|
| 317 |
+
"step": 40
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.0,
|
| 321 |
+
"eval_accuracy": 0.7026,
|
| 322 |
+
"eval_loss": 1.6059929132461548,
|
| 323 |
+
"eval_runtime": 19.2121,
|
| 324 |
+
"eval_samples_per_second": 520.506,
|
| 325 |
+
"eval_steps_per_second": 0.104,
|
| 326 |
+
"step": 40
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.1,
|
| 330 |
+
"grad_norm": 2.7123563289642334,
|
| 331 |
+
"learning_rate": 6.819524684817438e-05,
|
| 332 |
+
"loss": 1.6115,
|
| 333 |
+
"step": 41
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.2,
|
| 337 |
+
"grad_norm": 2.6732938289642334,
|
| 338 |
+
"learning_rate": 6.667762158254104e-05,
|
| 339 |
+
"loss": 1.5974,
|
| 340 |
+
"step": 42
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.3,
|
| 344 |
+
"grad_norm": 2.6421256065368652,
|
| 345 |
+
"learning_rate": 6.514250379489753e-05,
|
| 346 |
+
"loss": 1.5815,
|
| 347 |
+
"step": 43
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 4.4,
|
| 351 |
+
"grad_norm": 2.6315958499908447,
|
| 352 |
+
"learning_rate": 6.359150361181715e-05,
|
| 353 |
+
"loss": 1.5605,
|
| 354 |
+
"step": 44
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.5,
|
| 358 |
+
"grad_norm": 2.6411125659942627,
|
| 359 |
+
"learning_rate": 6.202624781831268e-05,
|
| 360 |
+
"loss": 1.547,
|
| 361 |
+
"step": 45
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.6,
|
| 365 |
+
"grad_norm": 2.5971579551696777,
|
| 366 |
+
"learning_rate": 6.044837815156377e-05,
|
| 367 |
+
"loss": 1.5264,
|
| 368 |
+
"step": 46
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.7,
|
| 372 |
+
"grad_norm": 2.60679030418396,
|
| 373 |
+
"learning_rate": 5.885954957896115e-05,
|
| 374 |
+
"loss": 1.5204,
|
| 375 |
+
"step": 47
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.8,
|
| 379 |
+
"grad_norm": 2.6132194995880127,
|
| 380 |
+
"learning_rate": 5.726142856227452e-05,
|
| 381 |
+
"loss": 1.5138,
|
| 382 |
+
"step": 48
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 4.9,
|
| 386 |
+
"grad_norm": 2.5883078575134277,
|
| 387 |
+
"learning_rate": 5.565569130976422e-05,
|
| 388 |
+
"loss": 1.5027,
|
| 389 |
+
"step": 49
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 5.0,
|
| 393 |
+
"grad_norm": 2.5475687980651855,
|
| 394 |
+
"learning_rate": 5.4044022018070214e-05,
|
| 395 |
+
"loss": 1.4917,
|
| 396 |
+
"step": 50
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.0,
|
| 400 |
+
"eval_accuracy": 0.7804,
|
| 401 |
+
"eval_loss": 1.4809952974319458,
|
| 402 |
+
"eval_runtime": 19.4674,
|
| 403 |
+
"eval_samples_per_second": 513.679,
|
| 404 |
+
"eval_steps_per_second": 0.103,
|
| 405 |
+
"step": 50
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 5.1,
|
| 409 |
+
"grad_norm": 2.5411295890808105,
|
| 410 |
+
"learning_rate": 5.242811110572242e-05,
|
| 411 |
+
"loss": 1.4768,
|
| 412 |
+
"step": 51
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 5.2,
|
| 416 |
+
"grad_norm": 2.529762029647827,
|
| 417 |
+
"learning_rate": 5.080965344012508e-05,
|
| 418 |
+
"loss": 1.4711,
|
| 419 |
+
"step": 52
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.3,
|
| 423 |
+
"grad_norm": 2.547415256500244,
|
| 424 |
+
"learning_rate": 4.919034655987493e-05,
|
| 425 |
+
"loss": 1.4621,
|
| 426 |
+
"step": 53
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.4,
|
| 430 |
+
"grad_norm": 2.500286817550659,
|
| 431 |
+
"learning_rate": 4.7571888894277604e-05,
|
| 432 |
+
"loss": 1.4553,
|
| 433 |
+
"step": 54
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.5,
|
| 437 |
+
"grad_norm": 2.536651611328125,
|
| 438 |
+
"learning_rate": 4.59559779819298e-05,
|
| 439 |
+
"loss": 1.4408,
|
| 440 |
+
"step": 55
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.6,
|
| 444 |
+
"grad_norm": 2.4803407192230225,
|
| 445 |
+
"learning_rate": 4.434430869023579e-05,
|
| 446 |
+
"loss": 1.4245,
|
| 447 |
+
"step": 56
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 5.7,
|
| 451 |
+
"grad_norm": 2.4855239391326904,
|
| 452 |
+
"learning_rate": 4.27385714377255e-05,
|
| 453 |
+
"loss": 1.4253,
|
| 454 |
+
"step": 57
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 5.8,
|
| 458 |
+
"grad_norm": 2.4846363067626953,
|
| 459 |
+
"learning_rate": 4.114045042103887e-05,
|
| 460 |
+
"loss": 1.4154,
|
| 461 |
+
"step": 58
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.9,
|
| 465 |
+
"grad_norm": 2.5024306774139404,
|
| 466 |
+
"learning_rate": 3.955162184843625e-05,
|
| 467 |
+
"loss": 1.4044,
|
| 468 |
+
"step": 59
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 6.0,
|
| 472 |
+
"grad_norm": 2.460845470428467,
|
| 473 |
+
"learning_rate": 3.7973752181687335e-05,
|
| 474 |
+
"loss": 1.3896,
|
| 475 |
+
"step": 60
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 6.0,
|
| 479 |
+
"eval_accuracy": 0.8226,
|
| 480 |
+
"eval_loss": 1.393266201019287,
|
| 481 |
+
"eval_runtime": 19.4581,
|
| 482 |
+
"eval_samples_per_second": 513.924,
|
| 483 |
+
"eval_steps_per_second": 0.103,
|
| 484 |
+
"step": 60
|
| 485 |
+
}
|
| 486 |
+
],
|
| 487 |
+
"logging_steps": 1,
|
| 488 |
+
"max_steps": 100,
|
| 489 |
+
"num_input_tokens_seen": 0,
|
| 490 |
+
"num_train_epochs": 10,
|
| 491 |
+
"save_steps": 1,
|
| 492 |
+
"stateful_callbacks": {
|
| 493 |
+
"TrainerControl": {
|
| 494 |
+
"args": {
|
| 495 |
+
"should_epoch_stop": false,
|
| 496 |
+
"should_evaluate": false,
|
| 497 |
+
"should_log": false,
|
| 498 |
+
"should_save": true,
|
| 499 |
+
"should_training_stop": false
|
| 500 |
+
},
|
| 501 |
+
"attributes": {}
|
| 502 |
+
}
|
| 503 |
+
},
|
| 504 |
+
"total_flos": 0.0,
|
| 505 |
+
"train_batch_size": 512,
|
| 506 |
+
"trial_name": null,
|
| 507 |
+
"trial_params": null
|
| 508 |
+
}
|
checkpoint-60/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8791579e23520b4bd71b23dd7de782fc70967c05dcdd1d44ffc944f00ab7f116
|
| 3 |
+
size 5777
|