Upload trainer_state.json
Browse files- trainer_state.json +268 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,268 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 9441,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"loss": 5.6498,
|
| 13 |
+
"step": 500
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"epoch": 0.05,
|
| 17 |
+
"eval_loss": 3.2174227237701416,
|
| 18 |
+
"eval_runtime": 50.998,
|
| 19 |
+
"eval_samples_per_second": 236.362,
|
| 20 |
+
"eval_steps_per_second": 0.941,
|
| 21 |
+
"eval_wer": 0.053516471892462315,
|
| 22 |
+
"step": 500
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.11,
|
| 26 |
+
"loss": 2.7794,
|
| 27 |
+
"step": 1000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.11,
|
| 31 |
+
"eval_loss": 2.011007070541382,
|
| 32 |
+
"eval_runtime": 51.5372,
|
| 33 |
+
"eval_samples_per_second": 233.889,
|
| 34 |
+
"eval_steps_per_second": 0.931,
|
| 35 |
+
"eval_wer": 0.049977469992612156,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.16,
|
| 40 |
+
"loss": 1.8179,
|
| 41 |
+
"step": 1500
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.16,
|
| 45 |
+
"eval_loss": 0.8721506595611572,
|
| 46 |
+
"eval_runtime": 53.762,
|
| 47 |
+
"eval_samples_per_second": 224.21,
|
| 48 |
+
"eval_steps_per_second": 0.893,
|
| 49 |
+
"eval_wer": 0.04245802797052525,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.21,
|
| 54 |
+
"loss": 0.7713,
|
| 55 |
+
"step": 2000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.21,
|
| 59 |
+
"eval_loss": 0.3388041853904724,
|
| 60 |
+
"eval_runtime": 57.0462,
|
| 61 |
+
"eval_samples_per_second": 211.303,
|
| 62 |
+
"eval_steps_per_second": 0.841,
|
| 63 |
+
"eval_wer": 0.036441974611471896,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.26,
|
| 68 |
+
"loss": 0.4234,
|
| 69 |
+
"step": 2500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.26,
|
| 73 |
+
"eval_loss": 0.2034144103527069,
|
| 74 |
+
"eval_runtime": 65.9674,
|
| 75 |
+
"eval_samples_per_second": 182.727,
|
| 76 |
+
"eval_steps_per_second": 0.728,
|
| 77 |
+
"eval_wer": 0.03474535261335592,
|
| 78 |
+
"step": 2500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.32,
|
| 82 |
+
"loss": 0.2822,
|
| 83 |
+
"step": 3000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.32,
|
| 87 |
+
"eval_loss": 0.13999593257904053,
|
| 88 |
+
"eval_runtime": 51.8439,
|
| 89 |
+
"eval_samples_per_second": 232.506,
|
| 90 |
+
"eval_steps_per_second": 0.926,
|
| 91 |
+
"eval_wer": 0.03314867889200672,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.37,
|
| 96 |
+
"loss": 0.211,
|
| 97 |
+
"step": 3500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.37,
|
| 101 |
+
"eval_loss": 0.10781644284725189,
|
| 102 |
+
"eval_runtime": 50.8714,
|
| 103 |
+
"eval_samples_per_second": 236.95,
|
| 104 |
+
"eval_steps_per_second": 0.944,
|
| 105 |
+
"eval_wer": 0.032414059057770936,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.42,
|
| 110 |
+
"loss": 0.1715,
|
| 111 |
+
"step": 4000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.42,
|
| 115 |
+
"eval_loss": 0.09290529042482376,
|
| 116 |
+
"eval_runtime": 51.4425,
|
| 117 |
+
"eval_samples_per_second": 234.32,
|
| 118 |
+
"eval_steps_per_second": 0.933,
|
| 119 |
+
"eval_wer": 0.03216918577969234,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.48,
|
| 124 |
+
"loss": 0.1441,
|
| 125 |
+
"step": 4500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.48,
|
| 129 |
+
"eval_loss": 0.07368380576372147,
|
| 130 |
+
"eval_runtime": 51.0907,
|
| 131 |
+
"eval_samples_per_second": 235.933,
|
| 132 |
+
"eval_steps_per_second": 0.94,
|
| 133 |
+
"eval_wer": 0.031723583045773815,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.53,
|
| 138 |
+
"loss": 0.1263,
|
| 139 |
+
"step": 5000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.53,
|
| 143 |
+
"eval_loss": 0.06525683403015137,
|
| 144 |
+
"eval_runtime": 51.1104,
|
| 145 |
+
"eval_samples_per_second": 235.843,
|
| 146 |
+
"eval_steps_per_second": 0.939,
|
| 147 |
+
"eval_wer": 0.03161363994133036,
|
| 148 |
+
"step": 5000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.58,
|
| 152 |
+
"loss": 0.1114,
|
| 153 |
+
"step": 5500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.58,
|
| 157 |
+
"eval_loss": 0.06087009608745575,
|
| 158 |
+
"eval_runtime": 54.1523,
|
| 159 |
+
"eval_samples_per_second": 222.595,
|
| 160 |
+
"eval_steps_per_second": 0.886,
|
| 161 |
+
"eval_wer": 0.03163362959668371,
|
| 162 |
+
"step": 5500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.64,
|
| 166 |
+
"loss": 0.1007,
|
| 167 |
+
"step": 6000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.64,
|
| 171 |
+
"eval_loss": 0.05339992418885231,
|
| 172 |
+
"eval_runtime": 51.3822,
|
| 173 |
+
"eval_samples_per_second": 234.595,
|
| 174 |
+
"eval_steps_per_second": 0.934,
|
| 175 |
+
"eval_wer": 0.031447892382358796,
|
| 176 |
+
"step": 6000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.69,
|
| 180 |
+
"loss": 0.0912,
|
| 181 |
+
"step": 6500
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.69,
|
| 185 |
+
"eval_loss": 0.050159111618995667,
|
| 186 |
+
"eval_runtime": 51.2486,
|
| 187 |
+
"eval_samples_per_second": 235.206,
|
| 188 |
+
"eval_steps_per_second": 0.937,
|
| 189 |
+
"eval_wer": 0.031327121547932275,
|
| 190 |
+
"step": 6500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.74,
|
| 194 |
+
"loss": 0.085,
|
| 195 |
+
"step": 7000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.74,
|
| 199 |
+
"eval_loss": 0.04742148146033287,
|
| 200 |
+
"eval_runtime": 51.4277,
|
| 201 |
+
"eval_samples_per_second": 234.387,
|
| 202 |
+
"eval_steps_per_second": 0.933,
|
| 203 |
+
"eval_wer": 0.03132129123178755,
|
| 204 |
+
"step": 7000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.79,
|
| 208 |
+
"loss": 0.0797,
|
| 209 |
+
"step": 7500
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.79,
|
| 213 |
+
"eval_loss": 0.044490132480859756,
|
| 214 |
+
"eval_runtime": 51.2937,
|
| 215 |
+
"eval_samples_per_second": 235.0,
|
| 216 |
+
"eval_steps_per_second": 0.936,
|
| 217 |
+
"eval_wer": 0.031255491949582756,
|
| 218 |
+
"step": 7500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.85,
|
| 222 |
+
"loss": 0.0741,
|
| 223 |
+
"step": 8000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.85,
|
| 227 |
+
"eval_loss": 0.04160303622484207,
|
| 228 |
+
"eval_runtime": 51.2978,
|
| 229 |
+
"eval_samples_per_second": 234.981,
|
| 230 |
+
"eval_steps_per_second": 0.936,
|
| 231 |
+
"eval_wer": 0.031156376575122373,
|
| 232 |
+
"step": 8000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.9,
|
| 236 |
+
"loss": 0.072,
|
| 237 |
+
"step": 8500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.9,
|
| 241 |
+
"eval_loss": 0.04107438027858734,
|
| 242 |
+
"eval_runtime": 51.3225,
|
| 243 |
+
"eval_samples_per_second": 234.868,
|
| 244 |
+
"eval_steps_per_second": 0.935,
|
| 245 |
+
"eval_wer": 0.031193857178909913,
|
| 246 |
+
"step": 8500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.95,
|
| 250 |
+
"loss": 0.0682,
|
| 251 |
+
"step": 9000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.95,
|
| 255 |
+
"eval_loss": 0.03936346620321274,
|
| 256 |
+
"eval_runtime": 51.3106,
|
| 257 |
+
"eval_samples_per_second": 234.922,
|
| 258 |
+
"eval_steps_per_second": 0.935,
|
| 259 |
+
"eval_wer": 0.031177199132782118,
|
| 260 |
+
"step": 9000
|
| 261 |
+
}
|
| 262 |
+
],
|
| 263 |
+
"max_steps": 9441,
|
| 264 |
+
"num_train_epochs": 1,
|
| 265 |
+
"total_flos": 2.3280237219423744e+17,
|
| 266 |
+
"trial_name": null,
|
| 267 |
+
"trial_params": null
|
| 268 |
+
}
|