File size: 6,876 Bytes
2d6f02f |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.22005226241232292,
"eval_steps": 200,
"global_step": 2400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"eval_bertscore": 0.7401605248451233,
"eval_loss": 1.9530484676361084,
"eval_rouge1": 0.6562857460474375,
"eval_rouge2": 0.3640670727106235,
"eval_rougeL": 0.5655212336424695,
"eval_rougeLsum": 0.6414840198810386,
"eval_runtime": 21.7196,
"eval_samples_per_second": 1.381,
"eval_steps_per_second": 0.691,
"step": 200
},
{
"epoch": 0.02,
"grad_norm": 0.25105270743370056,
"learning_rate": 0.00019771674842969145,
"loss": 1.7353,
"step": 250
},
{
"epoch": 0.04,
"eval_bertscore": 0.7432050108909607,
"eval_loss": 1.9583823680877686,
"eval_rouge1": 0.6554226269617707,
"eval_rouge2": 0.36661086995296877,
"eval_rougeL": 0.5637448790342183,
"eval_rougeLsum": 0.6419796784912521,
"eval_runtime": 21.9623,
"eval_samples_per_second": 1.366,
"eval_steps_per_second": 0.683,
"step": 400
},
{
"epoch": 0.05,
"grad_norm": 0.26550447940826416,
"learning_rate": 0.00019542432717436156,
"loss": 1.7786,
"step": 500
},
{
"epoch": 0.06,
"eval_bertscore": 0.7469045519828796,
"eval_loss": 1.9245686531066895,
"eval_rouge1": 0.6662431635890791,
"eval_rouge2": 0.3735263724826765,
"eval_rougeL": 0.5755071616151013,
"eval_rougeLsum": 0.6538383087686117,
"eval_runtime": 21.5302,
"eval_samples_per_second": 1.393,
"eval_steps_per_second": 0.697,
"step": 600
},
{
"epoch": 0.07,
"grad_norm": 0.1538015753030777,
"learning_rate": 0.0001931319059190317,
"loss": 1.8851,
"step": 750
},
{
"epoch": 0.07,
"eval_bertscore": 0.7442477941513062,
"eval_loss": 1.9187489748001099,
"eval_rouge1": 0.6606221897489035,
"eval_rouge2": 0.368654563659435,
"eval_rougeL": 0.5731546210408094,
"eval_rougeLsum": 0.6470590823125606,
"eval_runtime": 21.9831,
"eval_samples_per_second": 1.365,
"eval_steps_per_second": 0.682,
"step": 800
},
{
"epoch": 0.09,
"grad_norm": 0.1681252270936966,
"learning_rate": 0.0001908394846637018,
"loss": 1.8919,
"step": 1000
},
{
"epoch": 0.09,
"eval_bertscore": 0.7458053231239319,
"eval_loss": 1.9159075021743774,
"eval_rouge1": 0.6621259186456026,
"eval_rouge2": 0.372024043683234,
"eval_rougeL": 0.5743354509339939,
"eval_rougeLsum": 0.6491550893780276,
"eval_runtime": 21.7159,
"eval_samples_per_second": 1.381,
"eval_steps_per_second": 0.691,
"step": 1000
},
{
"epoch": 0.11,
"eval_bertscore": 0.7468854784965515,
"eval_loss": 1.9140182733535767,
"eval_rouge1": 0.6626581781149132,
"eval_rouge2": 0.37318557504782157,
"eval_rougeL": 0.5759264203594217,
"eval_rougeLsum": 0.6490702446275723,
"eval_runtime": 21.6486,
"eval_samples_per_second": 1.386,
"eval_steps_per_second": 0.693,
"step": 1200
},
{
"epoch": 0.11,
"grad_norm": 0.1552441120147705,
"learning_rate": 0.00018854706340837193,
"loss": 1.9052,
"step": 1250
},
{
"epoch": 0.13,
"eval_bertscore": 0.7475314736366272,
"eval_loss": 1.913794755935669,
"eval_rouge1": 0.6648687174353192,
"eval_rouge2": 0.3760379232448734,
"eval_rougeL": 0.5784915488164926,
"eval_rougeLsum": 0.6513864520108938,
"eval_runtime": 21.664,
"eval_samples_per_second": 1.385,
"eval_steps_per_second": 0.692,
"step": 1400
},
{
"epoch": 0.14,
"grad_norm": 0.14638397097587585,
"learning_rate": 0.00018625464215304204,
"loss": 1.8843,
"step": 1500
},
{
"epoch": 0.15,
"eval_bertscore": 0.747238039970398,
"eval_loss": 1.9117029905319214,
"eval_rouge1": 0.6638085237198453,
"eval_rouge2": 0.3742779818055127,
"eval_rougeL": 0.5754209460423059,
"eval_rougeLsum": 0.6506476155592722,
"eval_runtime": 21.9308,
"eval_samples_per_second": 1.368,
"eval_steps_per_second": 0.684,
"step": 1600
},
{
"epoch": 0.16,
"grad_norm": 0.15738993883132935,
"learning_rate": 0.00018396222089771218,
"loss": 1.8964,
"step": 1750
},
{
"epoch": 0.17,
"eval_bertscore": 0.7473016381263733,
"eval_loss": 1.9117563962936401,
"eval_rouge1": 0.6620053151663765,
"eval_rouge2": 0.37406692119411245,
"eval_rougeL": 0.5758911607323577,
"eval_rougeLsum": 0.6494070575604445,
"eval_runtime": 21.6727,
"eval_samples_per_second": 1.384,
"eval_steps_per_second": 0.692,
"step": 1800
},
{
"epoch": 0.18,
"grad_norm": 0.1588907092809677,
"learning_rate": 0.00018166979964238228,
"loss": 1.8827,
"step": 2000
},
{
"epoch": 0.18,
"eval_bertscore": 0.7485987544059753,
"eval_loss": 1.9126006364822388,
"eval_rouge1": 0.6641836156334741,
"eval_rouge2": 0.37320215574735827,
"eval_rougeL": 0.5783015040447993,
"eval_rougeLsum": 0.6522235940423647,
"eval_runtime": 21.9759,
"eval_samples_per_second": 1.365,
"eval_steps_per_second": 0.683,
"step": 2000
},
{
"epoch": 0.2,
"eval_bertscore": 0.7482583522796631,
"eval_loss": 1.9075205326080322,
"eval_rouge1": 0.6658219484766166,
"eval_rouge2": 0.37723364952258465,
"eval_rougeL": 0.5769040785174693,
"eval_rougeLsum": 0.6511328888044219,
"eval_runtime": 21.5892,
"eval_samples_per_second": 1.39,
"eval_steps_per_second": 0.695,
"step": 2200
},
{
"epoch": 0.21,
"grad_norm": 0.15247465670108795,
"learning_rate": 0.00017937737838705242,
"loss": 1.8831,
"step": 2250
},
{
"epoch": 0.22,
"eval_bertscore": 0.7460805177688599,
"eval_loss": 1.9088668823242188,
"eval_rouge1": 0.6627321043292516,
"eval_rouge2": 0.3696581195003696,
"eval_rougeL": 0.5740988544467178,
"eval_rougeLsum": 0.6478729042661874,
"eval_runtime": 21.9221,
"eval_samples_per_second": 1.368,
"eval_steps_per_second": 0.684,
"step": 2400
}
],
"logging_steps": 250,
"max_steps": 21812,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 800,
"total_flos": 1.61787760607232e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|