Upload checkpoint-52/trainer_state.json with huggingface_hub
Browse files- checkpoint-52/trainer_state.json +469 -0
checkpoint-52/trainer_state.json
ADDED
|
@@ -0,0 +1,469 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 6,
|
| 6 |
+
"global_step": 52,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.038461538461538464,
|
| 13 |
+
"grad_norm": 8.71969985961914,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 1.7925,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.038461538461538464,
|
| 20 |
+
"eval_loss": 2.0411531925201416,
|
| 21 |
+
"eval_runtime": 1.6566,
|
| 22 |
+
"eval_samples_per_second": 13.28,
|
| 23 |
+
"eval_steps_per_second": 1.207,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.07692307692307693,
|
| 28 |
+
"grad_norm": 4.587398052215576,
|
| 29 |
+
"learning_rate": 2e-05,
|
| 30 |
+
"loss": 2.1894,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.11538461538461539,
|
| 35 |
+
"grad_norm": 4.494429111480713,
|
| 36 |
+
"learning_rate": 3e-05,
|
| 37 |
+
"loss": 1.9438,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15384615384615385,
|
| 42 |
+
"grad_norm": 7.78571891784668,
|
| 43 |
+
"learning_rate": 4e-05,
|
| 44 |
+
"loss": 1.9463,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.19230769230769232,
|
| 49 |
+
"grad_norm": 6.792930603027344,
|
| 50 |
+
"learning_rate": 5e-05,
|
| 51 |
+
"loss": 1.8652,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.23076923076923078,
|
| 56 |
+
"grad_norm": 10.765946388244629,
|
| 57 |
+
"learning_rate": 6e-05,
|
| 58 |
+
"loss": 1.6872,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.23076923076923078,
|
| 63 |
+
"eval_loss": 1.6089171171188354,
|
| 64 |
+
"eval_runtime": 1.667,
|
| 65 |
+
"eval_samples_per_second": 13.198,
|
| 66 |
+
"eval_steps_per_second": 1.2,
|
| 67 |
+
"step": 6
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.2692307692307692,
|
| 71 |
+
"grad_norm": 3.0110535621643066,
|
| 72 |
+
"learning_rate": 7e-05,
|
| 73 |
+
"loss": 1.6877,
|
| 74 |
+
"step": 7
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.3076923076923077,
|
| 78 |
+
"grad_norm": 2.871809959411621,
|
| 79 |
+
"learning_rate": 8e-05,
|
| 80 |
+
"loss": 1.4855,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.34615384615384615,
|
| 85 |
+
"grad_norm": 2.223036050796509,
|
| 86 |
+
"learning_rate": 9e-05,
|
| 87 |
+
"loss": 1.2108,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.38461538461538464,
|
| 92 |
+
"grad_norm": 2.2891507148742676,
|
| 93 |
+
"learning_rate": 0.0001,
|
| 94 |
+
"loss": 1.0259,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.4230769230769231,
|
| 99 |
+
"grad_norm": 2.058546543121338,
|
| 100 |
+
"learning_rate": 9.997207818651274e-05,
|
| 101 |
+
"loss": 0.8116,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.46153846153846156,
|
| 106 |
+
"grad_norm": 2.8107495307922363,
|
| 107 |
+
"learning_rate": 9.988834393115767e-05,
|
| 108 |
+
"loss": 0.6967,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.46153846153846156,
|
| 113 |
+
"eval_loss": 0.6327503323554993,
|
| 114 |
+
"eval_runtime": 1.6315,
|
| 115 |
+
"eval_samples_per_second": 13.485,
|
| 116 |
+
"eval_steps_per_second": 1.226,
|
| 117 |
+
"step": 12
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.5,
|
| 121 |
+
"grad_norm": 2.0721328258514404,
|
| 122 |
+
"learning_rate": 9.974889075442521e-05,
|
| 123 |
+
"loss": 0.5983,
|
| 124 |
+
"step": 13
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.5384615384615384,
|
| 128 |
+
"grad_norm": 1.9303380250930786,
|
| 129 |
+
"learning_rate": 9.9553874407739e-05,
|
| 130 |
+
"loss": 0.4963,
|
| 131 |
+
"step": 14
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.5769230769230769,
|
| 135 |
+
"grad_norm": 1.40817391872406,
|
| 136 |
+
"learning_rate": 9.930351269950143e-05,
|
| 137 |
+
"loss": 0.3881,
|
| 138 |
+
"step": 15
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.6153846153846154,
|
| 142 |
+
"grad_norm": 1.4169831275939941,
|
| 143 |
+
"learning_rate": 9.899808525182935e-05,
|
| 144 |
+
"loss": 0.3139,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.6538461538461539,
|
| 149 |
+
"grad_norm": 0.9847315549850464,
|
| 150 |
+
"learning_rate": 9.863793318825186e-05,
|
| 151 |
+
"loss": 0.2776,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.6923076923076923,
|
| 156 |
+
"grad_norm": 1.2575572729110718,
|
| 157 |
+
"learning_rate": 9.822345875271883e-05,
|
| 158 |
+
"loss": 0.3327,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.6923076923076923,
|
| 163 |
+
"eval_loss": 0.2710803747177124,
|
| 164 |
+
"eval_runtime": 1.6739,
|
| 165 |
+
"eval_samples_per_second": 13.143,
|
| 166 |
+
"eval_steps_per_second": 1.195,
|
| 167 |
+
"step": 18
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.7307692307692307,
|
| 171 |
+
"grad_norm": 0.7373743057250977,
|
| 172 |
+
"learning_rate": 9.775512486034563e-05,
|
| 173 |
+
"loss": 0.1967,
|
| 174 |
+
"step": 19
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.7692307692307693,
|
| 178 |
+
"grad_norm": 0.8841055035591125,
|
| 179 |
+
"learning_rate": 9.723345458039594e-05,
|
| 180 |
+
"loss": 0.244,
|
| 181 |
+
"step": 20
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.8076923076923077,
|
| 185 |
+
"grad_norm": 0.8621382713317871,
|
| 186 |
+
"learning_rate": 9.665903055208014e-05,
|
| 187 |
+
"loss": 0.1927,
|
| 188 |
+
"step": 21
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.8461538461538461,
|
| 192 |
+
"grad_norm": 0.9871663451194763,
|
| 193 |
+
"learning_rate": 9.603249433382144e-05,
|
| 194 |
+
"loss": 0.2435,
|
| 195 |
+
"step": 22
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.8846153846153846,
|
| 199 |
+
"grad_norm": 0.6780880689620972,
|
| 200 |
+
"learning_rate": 9.535454568671704e-05,
|
| 201 |
+
"loss": 0.1498,
|
| 202 |
+
"step": 23
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.9230769230769231,
|
| 206 |
+
"grad_norm": 0.7006078958511353,
|
| 207 |
+
"learning_rate": 9.462594179299406e-05,
|
| 208 |
+
"loss": 0.1784,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.9230769230769231,
|
| 213 |
+
"eval_loss": 0.17325076460838318,
|
| 214 |
+
"eval_runtime": 1.6307,
|
| 215 |
+
"eval_samples_per_second": 13.491,
|
| 216 |
+
"eval_steps_per_second": 1.226,
|
| 217 |
+
"step": 24
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.9615384615384616,
|
| 221 |
+
"grad_norm": 0.69418865442276,
|
| 222 |
+
"learning_rate": 9.384749641033359e-05,
|
| 223 |
+
"loss": 0.2146,
|
| 224 |
+
"step": 25
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.0,
|
| 228 |
+
"grad_norm": 0.5629783272743225,
|
| 229 |
+
"learning_rate": 9.302007896300698e-05,
|
| 230 |
+
"loss": 0.1474,
|
| 231 |
+
"step": 26
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.0384615384615385,
|
| 235 |
+
"grad_norm": 0.5029877424240112,
|
| 236 |
+
"learning_rate": 9.214461357083985e-05,
|
| 237 |
+
"loss": 0.1358,
|
| 238 |
+
"step": 27
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.0769230769230769,
|
| 242 |
+
"grad_norm": 0.5899357199668884,
|
| 243 |
+
"learning_rate": 9.122207801708802e-05,
|
| 244 |
+
"loss": 0.134,
|
| 245 |
+
"step": 28
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.1153846153846154,
|
| 249 |
+
"grad_norm": 0.7418510913848877,
|
| 250 |
+
"learning_rate": 9.025350265637815e-05,
|
| 251 |
+
"loss": 0.1158,
|
| 252 |
+
"step": 29
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.1538461538461537,
|
| 256 |
+
"grad_norm": 0.7511109113693237,
|
| 257 |
+
"learning_rate": 8.923996926393305e-05,
|
| 258 |
+
"loss": 0.1136,
|
| 259 |
+
"step": 30
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.1538461538461537,
|
| 263 |
+
"eval_loss": 0.1189715564250946,
|
| 264 |
+
"eval_runtime": 1.672,
|
| 265 |
+
"eval_samples_per_second": 13.158,
|
| 266 |
+
"eval_steps_per_second": 1.196,
|
| 267 |
+
"step": 30
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.1923076923076923,
|
| 271 |
+
"grad_norm": 0.7893090844154358,
|
| 272 |
+
"learning_rate": 8.818260982736661e-05,
|
| 273 |
+
"loss": 0.1249,
|
| 274 |
+
"step": 31
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.2307692307692308,
|
| 278 |
+
"grad_norm": 0.5709223747253418,
|
| 279 |
+
"learning_rate": 8.708260528239788e-05,
|
| 280 |
+
"loss": 0.0824,
|
| 281 |
+
"step": 32
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.2692307692307692,
|
| 285 |
+
"grad_norm": 0.5314195156097412,
|
| 286 |
+
"learning_rate": 8.594118419389647e-05,
|
| 287 |
+
"loss": 0.0906,
|
| 288 |
+
"step": 33
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.3076923076923077,
|
| 292 |
+
"grad_norm": 0.5469984412193298,
|
| 293 |
+
"learning_rate": 8.475962138373213e-05,
|
| 294 |
+
"loss": 0.0918,
|
| 295 |
+
"step": 34
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.3461538461538463,
|
| 299 |
+
"grad_norm": 0.5641104578971863,
|
| 300 |
+
"learning_rate": 8.353923650696118e-05,
|
| 301 |
+
"loss": 0.0866,
|
| 302 |
+
"step": 35
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.3846153846153846,
|
| 306 |
+
"grad_norm": 0.5818964838981628,
|
| 307 |
+
"learning_rate": 8.228139257794012e-05,
|
| 308 |
+
"loss": 0.0891,
|
| 309 |
+
"step": 36
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.3846153846153846,
|
| 313 |
+
"eval_loss": 0.08501879870891571,
|
| 314 |
+
"eval_runtime": 1.6676,
|
| 315 |
+
"eval_samples_per_second": 13.193,
|
| 316 |
+
"eval_steps_per_second": 1.199,
|
| 317 |
+
"step": 36
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.4230769230769231,
|
| 321 |
+
"grad_norm": 0.7663794159889221,
|
| 322 |
+
"learning_rate": 8.098749444801224e-05,
|
| 323 |
+
"loss": 0.0934,
|
| 324 |
+
"step": 37
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.4615384615384617,
|
| 328 |
+
"grad_norm": 0.48853516578674316,
|
| 329 |
+
"learning_rate": 7.965898723646776e-05,
|
| 330 |
+
"loss": 0.0597,
|
| 331 |
+
"step": 38
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.5,
|
| 335 |
+
"grad_norm": 0.608406662940979,
|
| 336 |
+
"learning_rate": 7.829735471652978e-05,
|
| 337 |
+
"loss": 0.0579,
|
| 338 |
+
"step": 39
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.5384615384615383,
|
| 342 |
+
"grad_norm": 0.49656111001968384,
|
| 343 |
+
"learning_rate": 7.690411765816864e-05,
|
| 344 |
+
"loss": 0.0607,
|
| 345 |
+
"step": 40
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.5769230769230769,
|
| 349 |
+
"grad_norm": 0.6709762215614319,
|
| 350 |
+
"learning_rate": 7.548083212959588e-05,
|
| 351 |
+
"loss": 0.0761,
|
| 352 |
+
"step": 41
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.6153846153846154,
|
| 356 |
+
"grad_norm": 0.6458861827850342,
|
| 357 |
+
"learning_rate": 7.402908775933419e-05,
|
| 358 |
+
"loss": 0.0746,
|
| 359 |
+
"step": 42
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.6153846153846154,
|
| 363 |
+
"eval_loss": 0.06257763504981995,
|
| 364 |
+
"eval_runtime": 1.6397,
|
| 365 |
+
"eval_samples_per_second": 13.417,
|
| 366 |
+
"eval_steps_per_second": 1.22,
|
| 367 |
+
"step": 42
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.6538461538461537,
|
| 371 |
+
"grad_norm": 0.527205765247345,
|
| 372 |
+
"learning_rate": 7.255050596080509e-05,
|
| 373 |
+
"loss": 0.0597,
|
| 374 |
+
"step": 43
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.6923076923076923,
|
| 378 |
+
"grad_norm": 0.4971027672290802,
|
| 379 |
+
"learning_rate": 7.104673812141675e-05,
|
| 380 |
+
"loss": 0.0574,
|
| 381 |
+
"step": 44
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.7307692307692308,
|
| 385 |
+
"grad_norm": 0.521812915802002,
|
| 386 |
+
"learning_rate": 6.951946375817474e-05,
|
| 387 |
+
"loss": 0.0611,
|
| 388 |
+
"step": 45
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.7692307692307692,
|
| 392 |
+
"grad_norm": 0.49732235074043274,
|
| 393 |
+
"learning_rate": 6.797038864187564e-05,
|
| 394 |
+
"loss": 0.0411,
|
| 395 |
+
"step": 46
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.8076923076923077,
|
| 399 |
+
"grad_norm": 0.4331294000148773,
|
| 400 |
+
"learning_rate": 6.640124289197845e-05,
|
| 401 |
+
"loss": 0.0377,
|
| 402 |
+
"step": 47
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.8461538461538463,
|
| 406 |
+
"grad_norm": 0.5265694260597229,
|
| 407 |
+
"learning_rate": 6.481377904428171e-05,
|
| 408 |
+
"loss": 0.0522,
|
| 409 |
+
"step": 48
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.8461538461538463,
|
| 413 |
+
"eval_loss": 0.046460047364234924,
|
| 414 |
+
"eval_runtime": 1.6754,
|
| 415 |
+
"eval_samples_per_second": 13.131,
|
| 416 |
+
"eval_steps_per_second": 1.194,
|
| 417 |
+
"step": 48
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.8846153846153846,
|
| 421 |
+
"grad_norm": 0.5977218747138977,
|
| 422 |
+
"learning_rate": 6.320977009356431e-05,
|
| 423 |
+
"loss": 0.0543,
|
| 424 |
+
"step": 49
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.9230769230769231,
|
| 428 |
+
"grad_norm": 0.4617597758769989,
|
| 429 |
+
"learning_rate": 6.159100751337642e-05,
|
| 430 |
+
"loss": 0.0388,
|
| 431 |
+
"step": 50
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.9615384615384617,
|
| 435 |
+
"grad_norm": 0.4888545572757721,
|
| 436 |
+
"learning_rate": 5.99592992551918e-05,
|
| 437 |
+
"loss": 0.0377,
|
| 438 |
+
"step": 51
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.0,
|
| 442 |
+
"grad_norm": 0.43416959047317505,
|
| 443 |
+
"learning_rate": 5.831646772915651e-05,
|
| 444 |
+
"loss": 0.0326,
|
| 445 |
+
"step": 52
|
| 446 |
+
}
|
| 447 |
+
],
|
| 448 |
+
"logging_steps": 1,
|
| 449 |
+
"max_steps": 104,
|
| 450 |
+
"num_input_tokens_seen": 0,
|
| 451 |
+
"num_train_epochs": 4,
|
| 452 |
+
"save_steps": 500,
|
| 453 |
+
"stateful_callbacks": {
|
| 454 |
+
"TrainerControl": {
|
| 455 |
+
"args": {
|
| 456 |
+
"should_epoch_stop": false,
|
| 457 |
+
"should_evaluate": false,
|
| 458 |
+
"should_log": false,
|
| 459 |
+
"should_save": true,
|
| 460 |
+
"should_training_stop": false
|
| 461 |
+
},
|
| 462 |
+
"attributes": {}
|
| 463 |
+
}
|
| 464 |
+
},
|
| 465 |
+
"total_flos": 2.6914539966562304e+16,
|
| 466 |
+
"train_batch_size": 4,
|
| 467 |
+
"trial_name": null,
|
| 468 |
+
"trial_params": null
|
| 469 |
+
}
|