Training in progress, epoch 0
Browse files- adapter_model.safetensors +1 -1
- trainer_state.json +366 -0
- training_args.bin +1 -1
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 47236352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ead3f110690346764ff7fc86674464d69e6828375388c1b15a205f0732b4581a
|
| 3 |
size 47236352
|
trainer_state.json
ADDED
|
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.846153846153847,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 480,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.20512820512820512,
|
| 13 |
+
"grad_norm": 0.68310546875,
|
| 14 |
+
"learning_rate": 0.00019978589232386035,
|
| 15 |
+
"loss": 1.5545,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.41025641025641024,
|
| 20 |
+
"grad_norm": 0.71240234375,
|
| 21 |
+
"learning_rate": 0.00019914448613738106,
|
| 22 |
+
"loss": 1.4203,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6153846153846154,
|
| 27 |
+
"grad_norm": 0.6708984375,
|
| 28 |
+
"learning_rate": 0.00019807852804032305,
|
| 29 |
+
"loss": 1.4322,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8205128205128205,
|
| 34 |
+
"grad_norm": 0.69482421875,
|
| 35 |
+
"learning_rate": 0.00019659258262890683,
|
| 36 |
+
"loss": 1.377,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0256410256410255,
|
| 41 |
+
"grad_norm": 0.62890625,
|
| 42 |
+
"learning_rate": 0.0001946930129495106,
|
| 43 |
+
"loss": 1.3246,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.2307692307692308,
|
| 48 |
+
"grad_norm": 0.85107421875,
|
| 49 |
+
"learning_rate": 0.0001923879532511287,
|
| 50 |
+
"loss": 1.2329,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.435897435897436,
|
| 55 |
+
"grad_norm": 0.7978515625,
|
| 56 |
+
"learning_rate": 0.00018968727415326884,
|
| 57 |
+
"loss": 1.1856,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.641025641025641,
|
| 62 |
+
"grad_norm": 0.8544921875,
|
| 63 |
+
"learning_rate": 0.00018660254037844388,
|
| 64 |
+
"loss": 1.2045,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.8461538461538463,
|
| 69 |
+
"grad_norm": 0.8330078125,
|
| 70 |
+
"learning_rate": 0.00018314696123025454,
|
| 71 |
+
"loss": 1.1925,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.051282051282051,
|
| 76 |
+
"grad_norm": 0.8515625,
|
| 77 |
+
"learning_rate": 0.00017933533402912354,
|
| 78 |
+
"loss": 1.159,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.2564102564102564,
|
| 83 |
+
"grad_norm": 0.87353515625,
|
| 84 |
+
"learning_rate": 0.00017518398074789775,
|
| 85 |
+
"loss": 0.9939,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.4615384615384617,
|
| 90 |
+
"grad_norm": 1.0078125,
|
| 91 |
+
"learning_rate": 0.00017071067811865476,
|
| 92 |
+
"loss": 1.0583,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.6666666666666665,
|
| 97 |
+
"grad_norm": 0.9453125,
|
| 98 |
+
"learning_rate": 0.00016593458151000688,
|
| 99 |
+
"loss": 1.0258,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.871794871794872,
|
| 104 |
+
"grad_norm": 0.9384765625,
|
| 105 |
+
"learning_rate": 0.00016087614290087208,
|
| 106 |
+
"loss": 1.0612,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.076923076923077,
|
| 111 |
+
"grad_norm": 1.08984375,
|
| 112 |
+
"learning_rate": 0.00015555702330196023,
|
| 113 |
+
"loss": 1.0167,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.282051282051282,
|
| 118 |
+
"grad_norm": 1.1005859375,
|
| 119 |
+
"learning_rate": 0.00015000000000000001,
|
| 120 |
+
"loss": 0.9019,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.4871794871794872,
|
| 125 |
+
"grad_norm": 1.154296875,
|
| 126 |
+
"learning_rate": 0.00014422886902190014,
|
| 127 |
+
"loss": 0.8952,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.6923076923076925,
|
| 132 |
+
"grad_norm": 1.06640625,
|
| 133 |
+
"learning_rate": 0.000138268343236509,
|
| 134 |
+
"loss": 0.9395,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.8974358974358974,
|
| 139 |
+
"grad_norm": 1.1083984375,
|
| 140 |
+
"learning_rate": 0.00013214394653031616,
|
| 141 |
+
"loss": 0.9138,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.102564102564102,
|
| 146 |
+
"grad_norm": 1.240234375,
|
| 147 |
+
"learning_rate": 0.00012588190451025207,
|
| 148 |
+
"loss": 0.8003,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.3076923076923075,
|
| 153 |
+
"grad_norm": 1.1552734375,
|
| 154 |
+
"learning_rate": 0.00011950903220161285,
|
| 155 |
+
"loss": 0.7733,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.512820512820513,
|
| 160 |
+
"grad_norm": 1.0068359375,
|
| 161 |
+
"learning_rate": 0.00011305261922200519,
|
| 162 |
+
"loss": 0.7342,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.717948717948718,
|
| 167 |
+
"grad_norm": 1.271484375,
|
| 168 |
+
"learning_rate": 0.00010654031292301432,
|
| 169 |
+
"loss": 0.7787,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.923076923076923,
|
| 174 |
+
"grad_norm": 1.1484375,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 0.8549,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.128205128205128,
|
| 181 |
+
"grad_norm": 1.3203125,
|
| 182 |
+
"learning_rate": 9.345968707698569e-05,
|
| 183 |
+
"loss": 0.748,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.333333333333333,
|
| 188 |
+
"grad_norm": 1.296875,
|
| 189 |
+
"learning_rate": 8.694738077799488e-05,
|
| 190 |
+
"loss": 0.6502,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.538461538461538,
|
| 195 |
+
"grad_norm": 1.18359375,
|
| 196 |
+
"learning_rate": 8.049096779838719e-05,
|
| 197 |
+
"loss": 0.678,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 5.743589743589744,
|
| 202 |
+
"grad_norm": 1.2099609375,
|
| 203 |
+
"learning_rate": 7.411809548974792e-05,
|
| 204 |
+
"loss": 0.6956,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 5.948717948717949,
|
| 209 |
+
"grad_norm": 1.3115234375,
|
| 210 |
+
"learning_rate": 6.785605346968386e-05,
|
| 211 |
+
"loss": 0.7146,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.153846153846154,
|
| 216 |
+
"grad_norm": 1.2412109375,
|
| 217 |
+
"learning_rate": 6.173165676349103e-05,
|
| 218 |
+
"loss": 0.6016,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.358974358974359,
|
| 223 |
+
"grad_norm": 1.318359375,
|
| 224 |
+
"learning_rate": 5.577113097809989e-05,
|
| 225 |
+
"loss": 0.6325,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 6.564102564102564,
|
| 230 |
+
"grad_norm": 1.3349609375,
|
| 231 |
+
"learning_rate": 5.000000000000002e-05,
|
| 232 |
+
"loss": 0.6448,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.769230769230769,
|
| 237 |
+
"grad_norm": 1.2177734375,
|
| 238 |
+
"learning_rate": 4.444297669803981e-05,
|
| 239 |
+
"loss": 0.607,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 6.9743589743589745,
|
| 244 |
+
"grad_norm": 1.166015625,
|
| 245 |
+
"learning_rate": 3.9123857099127936e-05,
|
| 246 |
+
"loss": 0.6006,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 7.17948717948718,
|
| 251 |
+
"grad_norm": 1.2724609375,
|
| 252 |
+
"learning_rate": 3.406541848999312e-05,
|
| 253 |
+
"loss": 0.5849,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.384615384615385,
|
| 258 |
+
"grad_norm": 1.4111328125,
|
| 259 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 260 |
+
"loss": 0.6052,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 7.589743589743589,
|
| 265 |
+
"grad_norm": 1.2001953125,
|
| 266 |
+
"learning_rate": 2.4816019252102273e-05,
|
| 267 |
+
"loss": 0.5591,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 7.794871794871795,
|
| 272 |
+
"grad_norm": 1.3798828125,
|
| 273 |
+
"learning_rate": 2.0664665970876496e-05,
|
| 274 |
+
"loss": 0.5398,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 8.0,
|
| 279 |
+
"grad_norm": 1.2548828125,
|
| 280 |
+
"learning_rate": 1.6853038769745467e-05,
|
| 281 |
+
"loss": 0.531,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 8.205128205128204,
|
| 286 |
+
"grad_norm": 1.146484375,
|
| 287 |
+
"learning_rate": 1.339745962155613e-05,
|
| 288 |
+
"loss": 0.5311,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 8.41025641025641,
|
| 293 |
+
"grad_norm": 1.3310546875,
|
| 294 |
+
"learning_rate": 1.0312725846731175e-05,
|
| 295 |
+
"loss": 0.5371,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 8.615384615384615,
|
| 300 |
+
"grad_norm": 1.365234375,
|
| 301 |
+
"learning_rate": 7.612046748871327e-06,
|
| 302 |
+
"loss": 0.511,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.820512820512821,
|
| 307 |
+
"grad_norm": 1.302734375,
|
| 308 |
+
"learning_rate": 5.306987050489442e-06,
|
| 309 |
+
"loss": 0.5505,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 9.025641025641026,
|
| 314 |
+
"grad_norm": 1.3994140625,
|
| 315 |
+
"learning_rate": 3.40741737109318e-06,
|
| 316 |
+
"loss": 0.556,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 9.23076923076923,
|
| 321 |
+
"grad_norm": 1.3046875,
|
| 322 |
+
"learning_rate": 1.921471959676957e-06,
|
| 323 |
+
"loss": 0.5174,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 9.435897435897436,
|
| 328 |
+
"grad_norm": 1.337890625,
|
| 329 |
+
"learning_rate": 8.555138626189618e-07,
|
| 330 |
+
"loss": 0.5164,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 9.64102564102564,
|
| 335 |
+
"grad_norm": 1.2578125,
|
| 336 |
+
"learning_rate": 2.141076761396521e-07,
|
| 337 |
+
"loss": 0.498,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 9.846153846153847,
|
| 342 |
+
"grad_norm": 1.3984375,
|
| 343 |
+
"learning_rate": 0.0,
|
| 344 |
+
"loss": 0.5447,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 9.846153846153847,
|
| 349 |
+
"step": 480,
|
| 350 |
+
"total_flos": 3.1522610479104e+16,
|
| 351 |
+
"train_loss": 0.833039856950442,
|
| 352 |
+
"train_runtime": 560.469,
|
| 353 |
+
"train_samples_per_second": 3.479,
|
| 354 |
+
"train_steps_per_second": 0.856
|
| 355 |
+
}
|
| 356 |
+
],
|
| 357 |
+
"logging_steps": 10,
|
| 358 |
+
"max_steps": 480,
|
| 359 |
+
"num_input_tokens_seen": 0,
|
| 360 |
+
"num_train_epochs": 10,
|
| 361 |
+
"save_steps": 500,
|
| 362 |
+
"total_flos": 3.1522610479104e+16,
|
| 363 |
+
"train_batch_size": 1,
|
| 364 |
+
"trial_name": null,
|
| 365 |
+
"trial_params": null
|
| 366 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4539
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64f147eb8554f736d96ef2495e65d5ae231446cf3caef3ce3685e1c6cbd2f883
|
| 3 |
size 4539
|