File size: 7,966 Bytes
ec4f065 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 | {
"best_global_step": 200,
"best_metric": 0.6800833940505981,
"best_model_checkpoint": "./python-code-completion-ministral-8B/checkpoint-200",
"epoch": 0.9411764705882353,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"entropy": 1.4469833582639695,
"epoch": 0.047058823529411764,
"grad_norm": 0.49369218945503235,
"learning_rate": 9.999578688879085e-06,
"loss": 1.7076,
"mean_token_accuracy": 0.6342830918729305,
"num_tokens": 25138.0,
"step": 10
},
{
"entropy": 1.430517853796482,
"epoch": 0.09411764705882353,
"grad_norm": 0.51407390832901,
"learning_rate": 9.949107209404664e-06,
"loss": 1.5636,
"mean_token_accuracy": 0.6443205893039703,
"num_tokens": 47578.0,
"step": 20
},
{
"entropy": 1.4371182411909103,
"epoch": 0.1411764705882353,
"grad_norm": 0.6639813184738159,
"learning_rate": 9.815347070757234e-06,
"loss": 1.4756,
"mean_token_accuracy": 0.6693132996559144,
"num_tokens": 71393.0,
"step": 30
},
{
"entropy": 1.3472976341843605,
"epoch": 0.18823529411764706,
"grad_norm": 0.3675422668457031,
"learning_rate": 9.60054932593026e-06,
"loss": 1.2256,
"mean_token_accuracy": 0.6993286892771721,
"num_tokens": 96359.0,
"step": 40
},
{
"entropy": 1.1503819346427917,
"epoch": 0.23529411764705882,
"grad_norm": 0.4163525104522705,
"learning_rate": 9.30832881198487e-06,
"loss": 1.0136,
"mean_token_accuracy": 0.7729795873165131,
"num_tokens": 123155.0,
"step": 50
},
{
"epoch": 0.23529411764705882,
"eval_entropy": 1.0332347961266835,
"eval_loss": 0.9837512373924255,
"eval_mean_token_accuracy": 0.8083523658911387,
"eval_num_tokens": 123155.0,
"eval_runtime": 25.0181,
"eval_samples_per_second": 5.996,
"eval_steps_per_second": 5.996,
"step": 50
},
{
"entropy": 0.8932387962937355,
"epoch": 0.2823529411764706,
"grad_norm": 0.2984226942062378,
"learning_rate": 8.943603315859101e-06,
"loss": 0.8519,
"mean_token_accuracy": 0.8314538225531578,
"num_tokens": 149237.0,
"step": 60
},
{
"entropy": 0.7480494946241378,
"epoch": 0.32941176470588235,
"grad_norm": 0.409252405166626,
"learning_rate": 8.512510812798426e-06,
"loss": 0.7625,
"mean_token_accuracy": 0.853736138343811,
"num_tokens": 173954.0,
"step": 70
},
{
"entropy": 0.733599005267024,
"epoch": 0.3764705882352941,
"grad_norm": 0.3177991211414337,
"learning_rate": 8.022306170204233e-06,
"loss": 0.7384,
"mean_token_accuracy": 0.8508381456136703,
"num_tokens": 202672.0,
"step": 80
},
{
"entropy": 0.6522206105291843,
"epoch": 0.4235294117647059,
"grad_norm": 0.5717107057571411,
"learning_rate": 7.481239055273959e-06,
"loss": 0.6701,
"mean_token_accuracy": 0.8760824427008629,
"num_tokens": 224695.0,
"step": 90
},
{
"entropy": 0.7285707335919142,
"epoch": 0.47058823529411764,
"grad_norm": 0.21871985495090485,
"learning_rate": 6.898415101128571e-06,
"loss": 0.7319,
"mean_token_accuracy": 0.8523965805768967,
"num_tokens": 251370.0,
"step": 100
},
{
"epoch": 0.47058823529411764,
"eval_entropy": 0.73099374294281,
"eval_loss": 0.7096962332725525,
"eval_mean_token_accuracy": 0.8550362022717793,
"eval_num_tokens": 251370.0,
"eval_runtime": 25.1112,
"eval_samples_per_second": 5.973,
"eval_steps_per_second": 5.973,
"step": 100
},
{
"entropy": 0.6658912554383278,
"epoch": 0.5176470588235295,
"grad_norm": 0.2736637592315674,
"learning_rate": 6.283642667866317e-06,
"loss": 0.6646,
"mean_token_accuracy": 0.8663464844226837,
"num_tokens": 276477.0,
"step": 110
},
{
"entropy": 0.6516228564083576,
"epoch": 0.5647058823529412,
"grad_norm": 0.2847215533256531,
"learning_rate": 5.647267777405178e-06,
"loss": 0.6503,
"mean_token_accuracy": 0.8681117251515389,
"num_tokens": 302513.0,
"step": 120
},
{
"entropy": 0.7009131267666817,
"epoch": 0.611764705882353,
"grad_norm": 0.22739574313163757,
"learning_rate": 5e-06,
"loss": 0.6881,
"mean_token_accuracy": 0.8624396547675133,
"num_tokens": 329679.0,
"step": 130
},
{
"entropy": 0.6468490872532129,
"epoch": 0.6588235294117647,
"grad_norm": 0.3506576716899872,
"learning_rate": 4.352732222594823e-06,
"loss": 0.6462,
"mean_token_accuracy": 0.871060524880886,
"num_tokens": 353837.0,
"step": 140
},
{
"entropy": 0.6587031967937946,
"epoch": 0.7058823529411765,
"grad_norm": 0.2826354205608368,
"learning_rate": 3.7163573321336867e-06,
"loss": 0.6779,
"mean_token_accuracy": 0.8682561233639717,
"num_tokens": 376786.0,
"step": 150
},
{
"epoch": 0.7058823529411765,
"eval_entropy": 0.7037040118376414,
"eval_loss": 0.6883785724639893,
"eval_mean_token_accuracy": 0.8590577419598897,
"eval_num_tokens": 376786.0,
"eval_runtime": 25.1113,
"eval_samples_per_second": 5.973,
"eval_steps_per_second": 5.973,
"step": 150
},
{
"entropy": 0.6935035854578018,
"epoch": 0.7529411764705882,
"grad_norm": 0.32049205899238586,
"learning_rate": 3.101584898871431e-06,
"loss": 0.7223,
"mean_token_accuracy": 0.8527676403522492,
"num_tokens": 404164.0,
"step": 160
},
{
"entropy": 0.6355765651911497,
"epoch": 0.8,
"grad_norm": 0.27511146664619446,
"learning_rate": 2.518760944726042e-06,
"loss": 0.641,
"mean_token_accuracy": 0.8753799632191658,
"num_tokens": 427356.0,
"step": 170
},
{
"entropy": 0.6331917632371187,
"epoch": 0.8470588235294118,
"grad_norm": 0.289739191532135,
"learning_rate": 1.977693829795769e-06,
"loss": 0.646,
"mean_token_accuracy": 0.8754393547773361,
"num_tokens": 450321.0,
"step": 180
},
{
"entropy": 0.7034022852778434,
"epoch": 0.8941176470588236,
"grad_norm": 0.32424843311309814,
"learning_rate": 1.4874891872015735e-06,
"loss": 0.7084,
"mean_token_accuracy": 0.857265616953373,
"num_tokens": 478364.0,
"step": 190
},
{
"entropy": 0.6966812558472156,
"epoch": 0.9411764705882353,
"grad_norm": 0.27991771697998047,
"learning_rate": 1.0563966841408995e-06,
"loss": 0.7108,
"mean_token_accuracy": 0.857306943833828,
"num_tokens": 505339.0,
"step": 200
},
{
"epoch": 0.9411764705882353,
"eval_entropy": 0.6970382163921992,
"eval_loss": 0.6800833940505981,
"eval_mean_token_accuracy": 0.8598487377166748,
"eval_num_tokens": 505339.0,
"eval_runtime": 25.145,
"eval_samples_per_second": 5.965,
"eval_steps_per_second": 5.965,
"step": 200
}
],
"logging_steps": 10,
"max_steps": 250,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.321787690779443e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|