Commit
•
b7af886
1
Parent(s):
4115343
End of training
Browse files- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +402 -0
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.99,
|
| 3 |
+
"train_loss": 0.8767006197992594,
|
| 4 |
+
"train_runtime": 37037.5595,
|
| 5 |
+
"train_samples_per_second": 43.199,
|
| 6 |
+
"train_steps_per_second": 0.3
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.99,
|
| 3 |
+
"train_loss": 0.8767006197992594,
|
| 4 |
+
"train_runtime": 37037.5595,
|
| 5 |
+
"train_samples_per_second": 43.199,
|
| 6 |
+
"train_steps_per_second": 0.3
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,402 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.992800575953924,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 11104,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.48,
|
| 13 |
+
"learning_rate": 1.9399615754082615e-05,
|
| 14 |
+
"loss": 2.0304,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.96,
|
| 19 |
+
"learning_rate": 1.879923150816523e-05,
|
| 20 |
+
"loss": 1.781,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.0,
|
| 25 |
+
"eval_f1": 0.9088,
|
| 26 |
+
"eval_gen_len": 26.88909090909091,
|
| 27 |
+
"eval_loss": 1.579687476158142,
|
| 28 |
+
"eval_precision": 0.908,
|
| 29 |
+
"eval_recall": 0.91,
|
| 30 |
+
"eval_rouge1": 0.4708,
|
| 31 |
+
"eval_rouge2": 0.2219,
|
| 32 |
+
"eval_rougeL": 0.3892,
|
| 33 |
+
"eval_rougeLsum": 0.389,
|
| 34 |
+
"eval_runtime": 1186.1406,
|
| 35 |
+
"eval_samples_per_second": 4.637,
|
| 36 |
+
"eval_steps_per_second": 0.29,
|
| 37 |
+
"step": 1388
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.16,
|
| 41 |
+
"learning_rate": 1.729827089337176e-05,
|
| 42 |
+
"loss": 1.7026,
|
| 43 |
+
"step": 1500
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 2.88,
|
| 47 |
+
"learning_rate": 1.6397694524495677e-05,
|
| 48 |
+
"loss": 1.6618,
|
| 49 |
+
"step": 2000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"eval_f1": 0.91,
|
| 54 |
+
"eval_gen_len": 26.728181818181817,
|
| 55 |
+
"eval_loss": 1.5411016941070557,
|
| 56 |
+
"eval_precision": 0.9094,
|
| 57 |
+
"eval_recall": 0.9111,
|
| 58 |
+
"eval_rouge1": 0.4776,
|
| 59 |
+
"eval_rouge2": 0.2303,
|
| 60 |
+
"eval_rougeL": 0.3977,
|
| 61 |
+
"eval_rougeLsum": 0.3973,
|
| 62 |
+
"eval_runtime": 1083.838,
|
| 63 |
+
"eval_samples_per_second": 5.075,
|
| 64 |
+
"eval_steps_per_second": 0.317,
|
| 65 |
+
"step": 2083
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 3.6,
|
| 69 |
+
"learning_rate": 1.5497118155619597e-05,
|
| 70 |
+
"loss": 1.626,
|
| 71 |
+
"step": 2500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.0,
|
| 75 |
+
"eval_f1": 0.911,
|
| 76 |
+
"eval_gen_len": 26.759636363636364,
|
| 77 |
+
"eval_loss": 1.5170917510986328,
|
| 78 |
+
"eval_precision": 0.9102,
|
| 79 |
+
"eval_recall": 0.9121,
|
| 80 |
+
"eval_rouge1": 0.4834,
|
| 81 |
+
"eval_rouge2": 0.2345,
|
| 82 |
+
"eval_rougeL": 0.402,
|
| 83 |
+
"eval_rougeLsum": 0.402,
|
| 84 |
+
"eval_runtime": 1053.82,
|
| 85 |
+
"eval_samples_per_second": 5.219,
|
| 86 |
+
"eval_steps_per_second": 0.326,
|
| 87 |
+
"step": 2776
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.32,
|
| 91 |
+
"learning_rate": 1.4596541786743516e-05,
|
| 92 |
+
"loss": 1.5918,
|
| 93 |
+
"step": 3000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 5.0,
|
| 97 |
+
"eval_f1": 0.9112,
|
| 98 |
+
"eval_gen_len": 26.647636363636362,
|
| 99 |
+
"eval_loss": 1.500138521194458,
|
| 100 |
+
"eval_precision": 0.9106,
|
| 101 |
+
"eval_recall": 0.9122,
|
| 102 |
+
"eval_rouge1": 0.4853,
|
| 103 |
+
"eval_rouge2": 0.2365,
|
| 104 |
+
"eval_rougeL": 0.4045,
|
| 105 |
+
"eval_rougeLsum": 0.4045,
|
| 106 |
+
"eval_runtime": 1079.0919,
|
| 107 |
+
"eval_samples_per_second": 5.097,
|
| 108 |
+
"eval_steps_per_second": 0.319,
|
| 109 |
+
"step": 3471
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 5.04,
|
| 113 |
+
"learning_rate": 1.3695965417867436e-05,
|
| 114 |
+
"loss": 1.5798,
|
| 115 |
+
"step": 3500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.76,
|
| 119 |
+
"learning_rate": 1.2795389048991355e-05,
|
| 120 |
+
"loss": 1.5586,
|
| 121 |
+
"step": 4000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 6.0,
|
| 125 |
+
"eval_f1": 0.9116,
|
| 126 |
+
"eval_gen_len": 26.777818181818184,
|
| 127 |
+
"eval_loss": 1.4880452156066895,
|
| 128 |
+
"eval_precision": 0.9108,
|
| 129 |
+
"eval_recall": 0.9127,
|
| 130 |
+
"eval_rouge1": 0.4875,
|
| 131 |
+
"eval_rouge2": 0.2373,
|
| 132 |
+
"eval_rougeL": 0.4063,
|
| 133 |
+
"eval_rougeLsum": 0.4063,
|
| 134 |
+
"eval_runtime": 1027.5441,
|
| 135 |
+
"eval_samples_per_second": 5.353,
|
| 136 |
+
"eval_steps_per_second": 0.335,
|
| 137 |
+
"step": 4164
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 6.48,
|
| 141 |
+
"learning_rate": 1.1894812680115276e-05,
|
| 142 |
+
"loss": 1.5375,
|
| 143 |
+
"step": 4500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 7.0,
|
| 147 |
+
"eval_f1": 0.912,
|
| 148 |
+
"eval_gen_len": 26.39909090909091,
|
| 149 |
+
"eval_loss": 1.4768402576446533,
|
| 150 |
+
"eval_precision": 0.9116,
|
| 151 |
+
"eval_recall": 0.9128,
|
| 152 |
+
"eval_rouge1": 0.4898,
|
| 153 |
+
"eval_rouge2": 0.24,
|
| 154 |
+
"eval_rougeL": 0.4083,
|
| 155 |
+
"eval_rougeLsum": 0.4083,
|
| 156 |
+
"eval_runtime": 922.1893,
|
| 157 |
+
"eval_samples_per_second": 5.964,
|
| 158 |
+
"eval_steps_per_second": 0.373,
|
| 159 |
+
"step": 4858
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 7.2,
|
| 163 |
+
"learning_rate": 1.0994236311239194e-05,
|
| 164 |
+
"loss": 1.5228,
|
| 165 |
+
"step": 5000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 7.92,
|
| 169 |
+
"learning_rate": 1.0093659942363115e-05,
|
| 170 |
+
"loss": 1.5146,
|
| 171 |
+
"step": 5500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 8.0,
|
| 175 |
+
"eval_f1": 0.9126,
|
| 176 |
+
"eval_gen_len": 26.156,
|
| 177 |
+
"eval_loss": 1.4685654640197754,
|
| 178 |
+
"eval_precision": 0.9123,
|
| 179 |
+
"eval_recall": 0.9133,
|
| 180 |
+
"eval_rouge1": 0.4907,
|
| 181 |
+
"eval_rouge2": 0.241,
|
| 182 |
+
"eval_rougeL": 0.4088,
|
| 183 |
+
"eval_rougeLsum": 0.4089,
|
| 184 |
+
"eval_runtime": 865.3485,
|
| 185 |
+
"eval_samples_per_second": 6.356,
|
| 186 |
+
"eval_steps_per_second": 0.398,
|
| 187 |
+
"step": 5553
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 8.64,
|
| 191 |
+
"learning_rate": 9.193083573487034e-06,
|
| 192 |
+
"loss": 1.5006,
|
| 193 |
+
"step": 6000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 9.0,
|
| 197 |
+
"eval_f1": 0.9127,
|
| 198 |
+
"eval_gen_len": 26.26290909090909,
|
| 199 |
+
"eval_loss": 1.4636152982711792,
|
| 200 |
+
"eval_precision": 0.9122,
|
| 201 |
+
"eval_recall": 0.9135,
|
| 202 |
+
"eval_rouge1": 0.4914,
|
| 203 |
+
"eval_rouge2": 0.2419,
|
| 204 |
+
"eval_rougeL": 0.4097,
|
| 205 |
+
"eval_rougeLsum": 0.4099,
|
| 206 |
+
"eval_runtime": 874.612,
|
| 207 |
+
"eval_samples_per_second": 6.289,
|
| 208 |
+
"eval_steps_per_second": 0.393,
|
| 209 |
+
"step": 6247
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 9.36,
|
| 213 |
+
"learning_rate": 8.29250720461095e-06,
|
| 214 |
+
"loss": 1.49,
|
| 215 |
+
"step": 6500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 10.0,
|
| 219 |
+
"eval_f1": 0.9127,
|
| 220 |
+
"eval_gen_len": 26.027272727272727,
|
| 221 |
+
"eval_loss": 1.4580360651016235,
|
| 222 |
+
"eval_precision": 0.9125,
|
| 223 |
+
"eval_recall": 0.9133,
|
| 224 |
+
"eval_rouge1": 0.4911,
|
| 225 |
+
"eval_rouge2": 0.2429,
|
| 226 |
+
"eval_rougeL": 0.4109,
|
| 227 |
+
"eval_rougeLsum": 0.411,
|
| 228 |
+
"eval_runtime": 855.8845,
|
| 229 |
+
"eval_samples_per_second": 6.426,
|
| 230 |
+
"eval_steps_per_second": 0.402,
|
| 231 |
+
"step": 6942
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 10.08,
|
| 235 |
+
"learning_rate": 7.391930835734871e-06,
|
| 236 |
+
"loss": 1.485,
|
| 237 |
+
"step": 7000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 10.8,
|
| 241 |
+
"learning_rate": 6.491354466858791e-06,
|
| 242 |
+
"loss": 1.4749,
|
| 243 |
+
"step": 7500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 11.0,
|
| 247 |
+
"eval_f1": 0.9131,
|
| 248 |
+
"eval_gen_len": 26.230363636363638,
|
| 249 |
+
"eval_loss": 1.4546109437942505,
|
| 250 |
+
"eval_precision": 0.9127,
|
| 251 |
+
"eval_recall": 0.9138,
|
| 252 |
+
"eval_rouge1": 0.4932,
|
| 253 |
+
"eval_rouge2": 0.244,
|
| 254 |
+
"eval_rougeL": 0.4121,
|
| 255 |
+
"eval_rougeLsum": 0.4123,
|
| 256 |
+
"eval_runtime": 871.4205,
|
| 257 |
+
"eval_samples_per_second": 6.312,
|
| 258 |
+
"eval_steps_per_second": 0.395,
|
| 259 |
+
"step": 7636
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 11.52,
|
| 263 |
+
"learning_rate": 5.590778097982709e-06,
|
| 264 |
+
"loss": 1.4661,
|
| 265 |
+
"step": 8000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 12.0,
|
| 269 |
+
"eval_f1": 0.9132,
|
| 270 |
+
"eval_gen_len": 25.87781818181818,
|
| 271 |
+
"eval_loss": 1.4514495134353638,
|
| 272 |
+
"eval_precision": 0.9133,
|
| 273 |
+
"eval_recall": 0.9136,
|
| 274 |
+
"eval_rouge1": 0.4937,
|
| 275 |
+
"eval_rouge2": 0.2448,
|
| 276 |
+
"eval_rougeL": 0.4126,
|
| 277 |
+
"eval_rougeLsum": 0.4127,
|
| 278 |
+
"eval_runtime": 867.3574,
|
| 279 |
+
"eval_samples_per_second": 6.341,
|
| 280 |
+
"eval_steps_per_second": 0.397,
|
| 281 |
+
"step": 8331
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 12.24,
|
| 285 |
+
"learning_rate": 4.690201729106629e-06,
|
| 286 |
+
"loss": 1.4626,
|
| 287 |
+
"step": 8500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 12.96,
|
| 291 |
+
"learning_rate": 3.7896253602305477e-06,
|
| 292 |
+
"loss": 1.4575,
|
| 293 |
+
"step": 9000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 13.0,
|
| 297 |
+
"eval_f1": 0.9133,
|
| 298 |
+
"eval_gen_len": 26.11509090909091,
|
| 299 |
+
"eval_loss": 1.4499082565307617,
|
| 300 |
+
"eval_precision": 0.913,
|
| 301 |
+
"eval_recall": 0.914,
|
| 302 |
+
"eval_rouge1": 0.4947,
|
| 303 |
+
"eval_rouge2": 0.2453,
|
| 304 |
+
"eval_rougeL": 0.4139,
|
| 305 |
+
"eval_rougeLsum": 0.414,
|
| 306 |
+
"eval_runtime": 860.9844,
|
| 307 |
+
"eval_samples_per_second": 6.388,
|
| 308 |
+
"eval_steps_per_second": 0.4,
|
| 309 |
+
"step": 9025
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 13.68,
|
| 313 |
+
"learning_rate": 2.8890489913544673e-06,
|
| 314 |
+
"loss": 1.4511,
|
| 315 |
+
"step": 9500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 14.0,
|
| 319 |
+
"eval_f1": 0.9133,
|
| 320 |
+
"eval_gen_len": 26.028727272727274,
|
| 321 |
+
"eval_loss": 1.44780433177948,
|
| 322 |
+
"eval_precision": 0.9131,
|
| 323 |
+
"eval_recall": 0.9138,
|
| 324 |
+
"eval_rouge1": 0.4939,
|
| 325 |
+
"eval_rouge2": 0.2451,
|
| 326 |
+
"eval_rougeL": 0.4133,
|
| 327 |
+
"eval_rougeLsum": 0.4134,
|
| 328 |
+
"eval_runtime": 862.0827,
|
| 329 |
+
"eval_samples_per_second": 6.38,
|
| 330 |
+
"eval_steps_per_second": 0.399,
|
| 331 |
+
"step": 9720
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 14.4,
|
| 335 |
+
"learning_rate": 1.988472622478386e-06,
|
| 336 |
+
"loss": 1.4519,
|
| 337 |
+
"step": 10000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 15.0,
|
| 341 |
+
"eval_f1": 0.9133,
|
| 342 |
+
"eval_gen_len": 25.907818181818183,
|
| 343 |
+
"eval_loss": 1.4471020698547363,
|
| 344 |
+
"eval_precision": 0.9132,
|
| 345 |
+
"eval_recall": 0.9137,
|
| 346 |
+
"eval_rouge1": 0.4938,
|
| 347 |
+
"eval_rouge2": 0.2451,
|
| 348 |
+
"eval_rougeL": 0.4134,
|
| 349 |
+
"eval_rougeLsum": 0.4134,
|
| 350 |
+
"eval_runtime": 855.2673,
|
| 351 |
+
"eval_samples_per_second": 6.431,
|
| 352 |
+
"eval_steps_per_second": 0.402,
|
| 353 |
+
"step": 10414
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 15.12,
|
| 357 |
+
"learning_rate": 1.0878962536023055e-06,
|
| 358 |
+
"loss": 1.4475,
|
| 359 |
+
"step": 10500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 15.84,
|
| 363 |
+
"learning_rate": 1.8731988472622478e-07,
|
| 364 |
+
"loss": 1.4439,
|
| 365 |
+
"step": 11000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 15.99,
|
| 369 |
+
"eval_f1": 0.9134,
|
| 370 |
+
"eval_gen_len": 25.96290909090909,
|
| 371 |
+
"eval_loss": 1.4468724727630615,
|
| 372 |
+
"eval_precision": 0.9133,
|
| 373 |
+
"eval_recall": 0.9138,
|
| 374 |
+
"eval_rouge1": 0.4939,
|
| 375 |
+
"eval_rouge2": 0.2453,
|
| 376 |
+
"eval_rougeL": 0.4133,
|
| 377 |
+
"eval_rougeLsum": 0.4134,
|
| 378 |
+
"eval_runtime": 864.4194,
|
| 379 |
+
"eval_samples_per_second": 6.363,
|
| 380 |
+
"eval_steps_per_second": 0.398,
|
| 381 |
+
"step": 11104
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 15.99,
|
| 385 |
+
"step": 11104,
|
| 386 |
+
"total_flos": 2.2405705733792072e+18,
|
| 387 |
+
"train_loss": 0.8767006197992594,
|
| 388 |
+
"train_runtime": 37037.5595,
|
| 389 |
+
"train_samples_per_second": 43.199,
|
| 390 |
+
"train_steps_per_second": 0.3
|
| 391 |
+
}
|
| 392 |
+
],
|
| 393 |
+
"logging_steps": 500,
|
| 394 |
+
"max_steps": 11104,
|
| 395 |
+
"num_input_tokens_seen": 0,
|
| 396 |
+
"num_train_epochs": 16,
|
| 397 |
+
"save_steps": 500,
|
| 398 |
+
"total_flos": 2.2405705733792072e+18,
|
| 399 |
+
"train_batch_size": 24,
|
| 400 |
+
"trial_name": null,
|
| 401 |
+
"trial_params": null
|
| 402 |
+
}
|