File size: 7,997 Bytes
c0b0edb | 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": 0.25436246395111084,
"best_model_checkpoint": "./python-code-refactoring-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": 1.2112591058015822,
"epoch": 0.047058823529411764,
"grad_norm": 0.6328933835029602,
"learning_rate": 7.500000000000001e-06,
"loss": 1.7004,
"mean_token_accuracy": 0.6649438560009002,
"num_tokens": 16836.0,
"step": 10
},
{
"entropy": 1.2078000918030738,
"epoch": 0.09411764705882353,
"grad_norm": 0.5308480858802795,
"learning_rate": 9.991971098713136e-06,
"loss": 1.5909,
"mean_token_accuracy": 0.6793556809425354,
"num_tokens": 33851.0,
"step": 20
},
{
"entropy": 1.193270905315876,
"epoch": 0.1411764705882353,
"grad_norm": 0.5148553252220154,
"learning_rate": 9.952707929045018e-06,
"loss": 1.3732,
"mean_token_accuracy": 0.7048414140939713,
"num_tokens": 51118.0,
"step": 30
},
{
"entropy": 1.1802570581436158,
"epoch": 0.18823529411764706,
"grad_norm": 0.5968846082687378,
"learning_rate": 9.88099273969759e-06,
"loss": 1.1662,
"mean_token_accuracy": 0.728707967698574,
"num_tokens": 67851.0,
"step": 40
},
{
"entropy": 0.8819854319095611,
"epoch": 0.23529411764705882,
"grad_norm": 0.5468736290931702,
"learning_rate": 9.777295435775165e-06,
"loss": 0.8373,
"mean_token_accuracy": 0.815536054968834,
"num_tokens": 84988.0,
"step": 50
},
{
"epoch": 0.23529411764705882,
"eval_entropy": 0.7242053945859274,
"eval_loss": 0.6968294978141785,
"eval_mean_token_accuracy": 0.8591729084650676,
"eval_num_tokens": 84988.0,
"eval_runtime": 18.242,
"eval_samples_per_second": 8.223,
"eval_steps_per_second": 8.223,
"step": 50
},
{
"entropy": 0.593521349132061,
"epoch": 0.2823529411764706,
"grad_norm": 0.3674946427345276,
"learning_rate": 9.64229548131959e-06,
"loss": 0.5825,
"mean_token_accuracy": 0.8873148798942566,
"num_tokens": 102092.0,
"step": 60
},
{
"entropy": 0.45081270560622216,
"epoch": 0.32941176470588235,
"grad_norm": 0.40957480669021606,
"learning_rate": 9.476877447204308e-06,
"loss": 0.4838,
"mean_token_accuracy": 0.9021970316767692,
"num_tokens": 118935.0,
"step": 70
},
{
"entropy": 0.36085937917232513,
"epoch": 0.3764705882352941,
"grad_norm": 0.39999279379844666,
"learning_rate": 9.282125215090694e-06,
"loss": 0.3868,
"mean_token_accuracy": 0.919852776825428,
"num_tokens": 135700.0,
"step": 80
},
{
"entropy": 0.3600465551018715,
"epoch": 0.4235294117647059,
"grad_norm": 0.24208979308605194,
"learning_rate": 9.059314875424553e-06,
"loss": 0.3347,
"mean_token_accuracy": 0.9249877437949181,
"num_tokens": 152723.0,
"step": 90
},
{
"entropy": 0.3371710181236267,
"epoch": 0.47058823529411764,
"grad_norm": 0.24354608356952667,
"learning_rate": 8.809906366007832e-06,
"loss": 0.3068,
"mean_token_accuracy": 0.9299718767404557,
"num_tokens": 169857.0,
"step": 100
},
{
"epoch": 0.47058823529411764,
"eval_entropy": 0.3274345314502716,
"eval_loss": 0.3101823031902313,
"eval_mean_token_accuracy": 0.9297333884239197,
"eval_num_tokens": 169857.0,
"eval_runtime": 18.3304,
"eval_samples_per_second": 8.183,
"eval_steps_per_second": 8.183,
"step": 100
},
{
"entropy": 0.3301278352737427,
"epoch": 0.5176470588235295,
"grad_norm": 0.24222862720489502,
"learning_rate": 8.535533905932739e-06,
"loss": 0.297,
"mean_token_accuracy": 0.9317866399884224,
"num_tokens": 186799.0,
"step": 110
},
{
"entropy": 0.3344870314002037,
"epoch": 0.5647058823529412,
"grad_norm": 0.24282677471637726,
"learning_rate": 8.237995287558801e-06,
"loss": 0.2942,
"mean_token_accuracy": 0.9307269603013992,
"num_tokens": 203775.0,
"step": 120
},
{
"entropy": 0.32817855961620807,
"epoch": 0.611764705882353,
"grad_norm": 0.20758755505084991,
"learning_rate": 7.919240096695877e-06,
"loss": 0.2832,
"mean_token_accuracy": 0.9334745943546295,
"num_tokens": 220919.0,
"step": 130
},
{
"entropy": 0.2978081665933132,
"epoch": 0.6588235294117647,
"grad_norm": 0.25893646478652954,
"learning_rate": 7.58135693817893e-06,
"loss": 0.2731,
"mean_token_accuracy": 0.9333468064665794,
"num_tokens": 238215.0,
"step": 140
},
{
"entropy": 0.28119575753808024,
"epoch": 0.7058823529411765,
"grad_norm": 0.26739779114723206,
"learning_rate": 7.226559750537462e-06,
"loss": 0.2673,
"mean_token_accuracy": 0.9358425229787827,
"num_tokens": 254625.0,
"step": 150
},
{
"epoch": 0.7058823529411765,
"eval_entropy": 0.2825607425967852,
"eval_loss": 0.27234065532684326,
"eval_mean_token_accuracy": 0.9340071042378744,
"eval_num_tokens": 254625.0,
"eval_runtime": 18.2949,
"eval_samples_per_second": 8.199,
"eval_steps_per_second": 8.199,
"step": 150
},
{
"entropy": 0.28226450830698013,
"epoch": 0.7529411764705882,
"grad_norm": 0.27276191115379333,
"learning_rate": 6.857173299431084e-06,
"loss": 0.2697,
"mean_token_accuracy": 0.9357088133692741,
"num_tokens": 271437.0,
"step": 160
},
{
"entropy": 0.2687517054378986,
"epoch": 0.8,
"grad_norm": 0.2764045000076294,
"learning_rate": 6.475617944903693e-06,
"loss": 0.2438,
"mean_token_accuracy": 0.9380499675869942,
"num_tokens": 288419.0,
"step": 170
},
{
"entropy": 0.2816390782594681,
"epoch": 0.8470588235294118,
"grad_norm": 0.23346015810966492,
"learning_rate": 6.084393782267039e-06,
"loss": 0.2607,
"mean_token_accuracy": 0.9347616925835609,
"num_tokens": 305535.0,
"step": 180
},
{
"entropy": 0.2635271079838276,
"epoch": 0.8941176470588236,
"grad_norm": 0.2241382598876953,
"learning_rate": 5.686064260528577e-06,
"loss": 0.2437,
"mean_token_accuracy": 0.9385963633656502,
"num_tokens": 322499.0,
"step": 190
},
{
"entropy": 0.2634481403976679,
"epoch": 0.9411764705882353,
"grad_norm": 0.25238925218582153,
"learning_rate": 5.283239385701882e-06,
"loss": 0.2478,
"mean_token_accuracy": 0.9358779728412628,
"num_tokens": 340031.0,
"step": 200
},
{
"epoch": 0.9411764705882353,
"eval_entropy": 0.2671808664004008,
"eval_loss": 0.25436246395111084,
"eval_mean_token_accuracy": 0.9354545970757803,
"eval_num_tokens": 340031.0,
"eval_runtime": 18.3601,
"eval_samples_per_second": 8.17,
"eval_steps_per_second": 8.17,
"step": 200
}
],
"logging_steps": 10,
"max_steps": 400,
"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": 1.5622775805616128e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|