File size: 5,625 Bytes
c19876f |
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 |
{
"best_metric": 0.4623475670814514,
"best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-80k-08/checkpoint-3500",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1,
"grad_norm": 0.9981909990310669,
"learning_rate": 4.8333333333333334e-05,
"loss": 0.3691,
"step": 500
},
{
"epoch": 0.1,
"eval_gen_len": 11.77575,
"eval_loss": 0.4729623794555664,
"eval_rouge1": 39.8086,
"eval_rouge2": 14.7674,
"eval_rougeL": 36.1546,
"eval_rougeLsum": 36.1739,
"eval_runtime": 459.5392,
"eval_samples_per_second": 8.704,
"eval_steps_per_second": 2.176,
"step": 500
},
{
"epoch": 0.2,
"grad_norm": 0.8220647573471069,
"learning_rate": 4.666666666666667e-05,
"loss": 0.3706,
"step": 1000
},
{
"epoch": 0.2,
"eval_gen_len": 11.59775,
"eval_loss": 0.47387805581092834,
"eval_rouge1": 39.8972,
"eval_rouge2": 14.9064,
"eval_rougeL": 36.1193,
"eval_rougeLsum": 36.138,
"eval_runtime": 446.0956,
"eval_samples_per_second": 8.967,
"eval_steps_per_second": 2.242,
"step": 1000
},
{
"epoch": 0.3,
"grad_norm": 1.052058219909668,
"learning_rate": 4.5e-05,
"loss": 0.3709,
"step": 1500
},
{
"epoch": 0.3,
"eval_gen_len": 11.71025,
"eval_loss": 0.47592678666114807,
"eval_rouge1": 39.9874,
"eval_rouge2": 14.8528,
"eval_rougeL": 36.3155,
"eval_rougeLsum": 36.3317,
"eval_runtime": 466.5502,
"eval_samples_per_second": 8.574,
"eval_steps_per_second": 2.143,
"step": 1500
},
{
"epoch": 0.4,
"grad_norm": 0.8642559051513672,
"learning_rate": 4.3333333333333334e-05,
"loss": 0.3721,
"step": 2000
},
{
"epoch": 0.4,
"eval_gen_len": 12.175,
"eval_loss": 0.4677760601043701,
"eval_rouge1": 39.7192,
"eval_rouge2": 14.5844,
"eval_rougeL": 35.8447,
"eval_rougeLsum": 35.8728,
"eval_runtime": 455.6895,
"eval_samples_per_second": 8.778,
"eval_steps_per_second": 2.194,
"step": 2000
},
{
"epoch": 0.5,
"grad_norm": 0.8769400715827942,
"learning_rate": 4.166666666666667e-05,
"loss": 0.3655,
"step": 2500
},
{
"epoch": 0.5,
"eval_gen_len": 11.90025,
"eval_loss": 0.4683643877506256,
"eval_rouge1": 40.3132,
"eval_rouge2": 15.1157,
"eval_rougeL": 36.5749,
"eval_rougeLsum": 36.5823,
"eval_runtime": 449.7304,
"eval_samples_per_second": 8.894,
"eval_steps_per_second": 2.224,
"step": 2500
},
{
"epoch": 0.6,
"grad_norm": 0.8613843321800232,
"learning_rate": 4e-05,
"loss": 0.3623,
"step": 3000
},
{
"epoch": 0.6,
"eval_gen_len": 12.025,
"eval_loss": 0.4671708345413208,
"eval_rouge1": 40.1643,
"eval_rouge2": 14.978,
"eval_rougeL": 36.3002,
"eval_rougeLsum": 36.3232,
"eval_runtime": 451.1814,
"eval_samples_per_second": 8.866,
"eval_steps_per_second": 2.216,
"step": 3000
},
{
"epoch": 0.7,
"grad_norm": 0.8106393814086914,
"learning_rate": 3.8333333333333334e-05,
"loss": 0.3676,
"step": 3500
},
{
"epoch": 0.7,
"eval_gen_len": 11.815,
"eval_loss": 0.4623475670814514,
"eval_rouge1": 40.5036,
"eval_rouge2": 15.3751,
"eval_rougeL": 36.8369,
"eval_rougeLsum": 36.867,
"eval_runtime": 458.4461,
"eval_samples_per_second": 8.725,
"eval_steps_per_second": 2.181,
"step": 3500
},
{
"epoch": 0.8,
"grad_norm": 0.914828360080719,
"learning_rate": 3.6666666666666666e-05,
"loss": 0.3613,
"step": 4000
},
{
"epoch": 0.8,
"eval_gen_len": 12.054,
"eval_loss": 0.46470996737480164,
"eval_rouge1": 40.4078,
"eval_rouge2": 15.3105,
"eval_rougeL": 36.65,
"eval_rougeLsum": 36.6732,
"eval_runtime": 457.1563,
"eval_samples_per_second": 8.75,
"eval_steps_per_second": 2.187,
"step": 4000
},
{
"epoch": 0.9,
"grad_norm": 0.8004090189933777,
"learning_rate": 3.5e-05,
"loss": 0.3539,
"step": 4500
},
{
"epoch": 0.9,
"eval_gen_len": 11.904,
"eval_loss": 0.46335914731025696,
"eval_rouge1": 40.3794,
"eval_rouge2": 15.233,
"eval_rougeL": 36.7155,
"eval_rougeLsum": 36.7435,
"eval_runtime": 445.5568,
"eval_samples_per_second": 8.978,
"eval_steps_per_second": 2.244,
"step": 4500
},
{
"epoch": 1.0,
"grad_norm": 0.876920223236084,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.3481,
"step": 5000
},
{
"epoch": 1.0,
"eval_gen_len": 11.738,
"eval_loss": 0.46441808342933655,
"eval_rouge1": 40.037,
"eval_rouge2": 14.8477,
"eval_rougeL": 36.3648,
"eval_rougeLsum": 36.3903,
"eval_runtime": 442.7978,
"eval_samples_per_second": 9.033,
"eval_steps_per_second": 2.258,
"step": 5000
}
],
"logging_steps": 500,
"max_steps": 15000,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 1.443711128961024e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|