File size: 4,989 Bytes
9df1e56 |
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 |
{
"best_metric": 0.07183855026960373,
"best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_dj_aragpt2-large/checkpoint-10716",
"epoch": 7.0,
"eval_steps": 500,
"global_step": 37506,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.1402301788330078,
"learning_rate": 4.772267016688543e-05,
"loss": 0.1323,
"step": 5358
},
{
"epoch": 1.0,
"eval_bleu": 0.08300663646266425,
"eval_loss": 0.07568918913602829,
"eval_rouge1": 0.4072217751588082,
"eval_rouge2": 0.18254715184887235,
"eval_rougeL": 0.4034974548012786,
"eval_runtime": 706.7922,
"eval_samples_per_second": 7.612,
"eval_steps_per_second": 1.903,
"step": 5358
},
{
"epoch": 2.0,
"grad_norm": 0.7255021929740906,
"learning_rate": 4.521095068441778e-05,
"loss": 0.0662,
"step": 10716
},
{
"epoch": 2.0,
"eval_bleu": 0.10627535338849203,
"eval_loss": 0.07183855026960373,
"eval_rouge1": 0.45517089056426413,
"eval_rouge2": 0.2232454846856679,
"eval_rougeL": 0.4515800058148628,
"eval_runtime": 715.8215,
"eval_samples_per_second": 7.516,
"eval_steps_per_second": 1.879,
"step": 10716
},
{
"epoch": 3.0,
"grad_norm": 0.5735991597175598,
"learning_rate": 4.269923120195012e-05,
"loss": 0.0526,
"step": 16074
},
{
"epoch": 3.0,
"eval_bleu": 0.11970864457422921,
"eval_loss": 0.07271187007427216,
"eval_rouge1": 0.47525716850104355,
"eval_rouge2": 0.25197591385088847,
"eval_rougeL": 0.47186762638658064,
"eval_runtime": 766.9396,
"eval_samples_per_second": 7.015,
"eval_steps_per_second": 1.754,
"step": 16074
},
{
"epoch": 4.0,
"grad_norm": 0.9193664789199829,
"learning_rate": 4.018751171948247e-05,
"loss": 0.0414,
"step": 21432
},
{
"epoch": 4.0,
"eval_bleu": 0.12737868761714774,
"eval_loss": 0.07567169517278671,
"eval_rouge1": 0.4894464779386084,
"eval_rouge2": 0.2644220876804199,
"eval_rougeL": 0.48620236061532013,
"eval_runtime": 767.056,
"eval_samples_per_second": 7.014,
"eval_steps_per_second": 1.753,
"step": 21432
},
{
"epoch": 5.0,
"grad_norm": 1.2567533254623413,
"learning_rate": 3.7675792237014815e-05,
"loss": 0.0325,
"step": 26790
},
{
"epoch": 5.0,
"eval_bleu": 0.12904171218936847,
"eval_loss": 0.08186400681734085,
"eval_rouge1": 0.4910163857094879,
"eval_rouge2": 0.26712580782902845,
"eval_rougeL": 0.4874926457795191,
"eval_runtime": 767.2369,
"eval_samples_per_second": 7.012,
"eval_steps_per_second": 1.753,
"step": 26790
},
{
"epoch": 6.0,
"grad_norm": 1.125952124595642,
"learning_rate": 3.516407275454716e-05,
"loss": 0.0262,
"step": 32148
},
{
"epoch": 6.0,
"eval_bleu": 0.12974770289755774,
"eval_loss": 0.08628461509943008,
"eval_rouge1": 0.4922385680285879,
"eval_rouge2": 0.26649486337370165,
"eval_rougeL": 0.4887932180100094,
"eval_runtime": 828.4635,
"eval_samples_per_second": 6.494,
"eval_steps_per_second": 1.623,
"step": 32148
},
{
"epoch": 7.0,
"grad_norm": 0.9687314629554749,
"learning_rate": 3.26523532720795e-05,
"loss": 0.0221,
"step": 37506
},
{
"epoch": 7.0,
"eval_bleu": 0.13258665968806682,
"eval_loss": 0.09302929788827896,
"eval_rouge1": 0.4960344976284088,
"eval_rouge2": 0.2712943985267227,
"eval_rougeL": 0.4923109277459174,
"eval_runtime": 828.274,
"eval_samples_per_second": 6.495,
"eval_steps_per_second": 1.624,
"step": 37506
},
{
"epoch": 7.0,
"step": 37506,
"total_flos": 6.528656496918528e+17,
"train_loss": 0.0533416826159377,
"train_runtime": 67570.4522,
"train_samples_per_second": 6.343,
"train_steps_per_second": 1.586
}
],
"logging_steps": 500,
"max_steps": 107160,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.528656496918528e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|