File size: 6,359 Bytes
34e05be | 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 | {
"best_global_step": 150,
"best_metric": 1.0139193534851074,
"best_model_checkpoint": "/data/output/checkpoint-150",
"epoch": 0.5123825789923142,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"entropy": 1.1713112026453019,
"epoch": 0.034158838599487616,
"grad_norm": 3.3329014778137207,
"learning_rate": 0.00012,
"loss": 1.2999439239501953,
"mean_token_accuracy": 0.6959523037075996,
"num_tokens": 643010.0,
"step": 10
},
{
"entropy": 1.1543982975184917,
"epoch": 0.06831767719897523,
"grad_norm": 2.581118106842041,
"learning_rate": 0.00019989785286500295,
"loss": 1.1518776893615723,
"mean_token_accuracy": 0.7155417971313,
"num_tokens": 1251488.0,
"step": 20
},
{
"entropy": 0.9459363672882318,
"epoch": 0.10247651579846286,
"grad_norm": 2.3779942989349365,
"learning_rate": 0.00019875109281794825,
"loss": 0.9381013870239258,
"mean_token_accuracy": 0.7682368114590645,
"num_tokens": 1696074.0,
"step": 30
},
{
"entropy": 0.9385578982532025,
"epoch": 0.13663535439795046,
"grad_norm": 2.0882723331451416,
"learning_rate": 0.00019634456691705702,
"loss": 0.9547281265258789,
"mean_token_accuracy": 0.7626850850880146,
"num_tokens": 2006643.0,
"step": 40
},
{
"entropy": 0.9006230250000954,
"epoch": 0.1707941929974381,
"grad_norm": 2.151762008666992,
"learning_rate": 0.00019270897516847403,
"loss": 0.9329019546508789,
"mean_token_accuracy": 0.7718432284891605,
"num_tokens": 2177826.0,
"step": 50
},
{
"epoch": 0.1707941929974381,
"eval_entropy": 1.0149640817940235,
"eval_loss": 1.071570634841919,
"eval_mean_token_accuracy": 0.742358745932579,
"eval_num_tokens": 2177826.0,
"eval_runtime": 95.085,
"eval_samples_per_second": 1.052,
"eval_steps_per_second": 1.052,
"step": 50
},
{
"entropy": 1.2094877127557992,
"epoch": 0.2049530315969257,
"grad_norm": 2.767357587814331,
"learning_rate": 0.0001878906967484966,
"loss": 1.209201717376709,
"mean_token_accuracy": 0.7017950341105461,
"num_tokens": 644405.0,
"step": 60
},
{
"entropy": 1.1481261406093837,
"epoch": 0.23911187019641333,
"grad_norm": 2.805593252182007,
"learning_rate": 0.00018195119834528534,
"loss": 1.1588325500488281,
"mean_token_accuracy": 0.7221003979444504,
"num_tokens": 1268539.0,
"step": 70
},
{
"entropy": 0.9842961743474007,
"epoch": 0.27327070879590093,
"grad_norm": 2.233400344848633,
"learning_rate": 0.000174966250029467,
"loss": 1.0100913047790527,
"mean_token_accuracy": 0.7561626233160496,
"num_tokens": 1729123.0,
"step": 80
},
{
"entropy": 0.9889072403311729,
"epoch": 0.3074295473953886,
"grad_norm": 1.992038369178772,
"learning_rate": 0.0001670249586567531,
"loss": 1.0143807411193848,
"mean_token_accuracy": 0.7507779069244862,
"num_tokens": 2034736.0,
"step": 90
},
{
"entropy": 0.8992462156340479,
"epoch": 0.3415883859948762,
"grad_norm": 2.0321593284606934,
"learning_rate": 0.00015822863113343935,
"loss": 0.9014181137084961,
"mean_token_accuracy": 0.7751547530293464,
"num_tokens": 2199862.0,
"step": 100
},
{
"epoch": 0.3415883859948762,
"eval_entropy": 0.9943241326510907,
"eval_loss": 1.043296456336975,
"eval_mean_token_accuracy": 0.7519984298944473,
"eval_num_tokens": 2199862.0,
"eval_runtime": 95.5899,
"eval_samples_per_second": 1.046,
"eval_steps_per_second": 1.046,
"step": 100
},
{
"entropy": 1.1760564662516118,
"epoch": 0.37574722459436377,
"grad_norm": 3.0291037559509277,
"learning_rate": 0.000148689482046087,
"loss": 1.2000227928161622,
"mean_token_accuracy": 0.711453115195036,
"num_tokens": 643606.0,
"step": 110
},
{
"entropy": 1.1263522632420062,
"epoch": 0.4099060631938514,
"grad_norm": 2.554089307785034,
"learning_rate": 0.00013852920214212964,
"loss": 1.1538644790649415,
"mean_token_accuracy": 0.7203516490757466,
"num_tokens": 1250932.0,
"step": 120
},
{
"entropy": 0.9661639135330915,
"epoch": 0.444064901793339,
"grad_norm": 2.2706644535064697,
"learning_rate": 0.0001278774059232723,
"loss": 0.9473760604858399,
"mean_token_accuracy": 0.7646104976534843,
"num_tokens": 1690510.0,
"step": 130
},
{
"entropy": 0.9644285907968879,
"epoch": 0.47822374039282667,
"grad_norm": 1.8326361179351807,
"learning_rate": 0.00011686997815570473,
"loss": 0.9465847969055176,
"mean_token_accuracy": 0.760813869535923,
"num_tokens": 1991606.0,
"step": 140
},
{
"entropy": 0.847778935264796,
"epoch": 0.5123825789923142,
"grad_norm": 2.5428972244262695,
"learning_rate": 0.00010564734039066699,
"loss": 0.8805885314941406,
"mean_token_accuracy": 0.784095474332571,
"num_tokens": 2153462.0,
"step": 150
},
{
"epoch": 0.5123825789923142,
"eval_entropy": 1.0146987434476613,
"eval_loss": 1.0139193534851074,
"eval_mean_token_accuracy": 0.7562771487236023,
"eval_num_tokens": 2153462.0,
"eval_runtime": 95.2112,
"eval_samples_per_second": 1.05,
"eval_steps_per_second": 1.05,
"step": 150
}
],
"logging_steps": 10,
"max_steps": 293,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.823512478009262e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|