End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +220 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 2.196016829300736e+16,
|
| 4 |
+
"train_loss": 3.2251040794011065,
|
| 5 |
+
"train_runtime": 10442.016,
|
| 6 |
+
"train_samples_per_second": 6.142,
|
| 7 |
+
"train_steps_per_second": 0.768
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 2.196016829300736e+16,
|
| 4 |
+
"train_loss": 3.2251040794011065,
|
| 5 |
+
"train_runtime": 10442.016,
|
| 6 |
+
"train_samples_per_second": 6.142,
|
| 7 |
+
"train_steps_per_second": 0.768
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.359348773956299,
|
| 3 |
+
"best_model_checkpoint": "BASH-Coder-Flan-T5-base/checkpoint-5614",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8020,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 4.556818181818182e-05,
|
| 14 |
+
"loss": 4.3554,
|
| 15 |
+
"step": 802
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_gen_len": 15.2363,
|
| 20 |
+
"eval_loss": 3.59275484085083,
|
| 21 |
+
"eval_rouge1": 22.7234,
|
| 22 |
+
"eval_rouge2": 6.7951,
|
| 23 |
+
"eval_rougeL": 22.0647,
|
| 24 |
+
"eval_rougeLsum": 22.0744,
|
| 25 |
+
"eval_runtime": 190.6891,
|
| 26 |
+
"eval_samples_per_second": 9.675,
|
| 27 |
+
"eval_steps_per_second": 0.608,
|
| 28 |
+
"step": 802
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"learning_rate": 4.0505050505050506e-05,
|
| 33 |
+
"loss": 3.5335,
|
| 34 |
+
"step": 1604
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.0,
|
| 38 |
+
"eval_gen_len": 15.168,
|
| 39 |
+
"eval_loss": 3.4654388427734375,
|
| 40 |
+
"eval_rouge1": 25.7842,
|
| 41 |
+
"eval_rouge2": 8.5847,
|
| 42 |
+
"eval_rougeL": 24.8207,
|
| 43 |
+
"eval_rougeLsum": 24.8808,
|
| 44 |
+
"eval_runtime": 187.8163,
|
| 45 |
+
"eval_samples_per_second": 9.823,
|
| 46 |
+
"eval_steps_per_second": 0.618,
|
| 47 |
+
"step": 1604
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"learning_rate": 3.5441919191919196e-05,
|
| 52 |
+
"loss": 3.3341,
|
| 53 |
+
"step": 2406
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.0,
|
| 57 |
+
"eval_gen_len": 15.6472,
|
| 58 |
+
"eval_loss": 3.4077794551849365,
|
| 59 |
+
"eval_rouge1": 25.5756,
|
| 60 |
+
"eval_rouge2": 8.4456,
|
| 61 |
+
"eval_rougeL": 24.706,
|
| 62 |
+
"eval_rougeLsum": 24.7207,
|
| 63 |
+
"eval_runtime": 187.2408,
|
| 64 |
+
"eval_samples_per_second": 9.854,
|
| 65 |
+
"eval_steps_per_second": 0.62,
|
| 66 |
+
"step": 2406
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"learning_rate": 3.037878787878788e-05,
|
| 71 |
+
"loss": 3.2011,
|
| 72 |
+
"step": 3208
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.0,
|
| 76 |
+
"eval_gen_len": 16.2748,
|
| 77 |
+
"eval_loss": 3.3789384365081787,
|
| 78 |
+
"eval_rouge1": 26.0638,
|
| 79 |
+
"eval_rouge2": 8.6853,
|
| 80 |
+
"eval_rougeL": 25.0862,
|
| 81 |
+
"eval_rougeLsum": 25.1223,
|
| 82 |
+
"eval_runtime": 221.9787,
|
| 83 |
+
"eval_samples_per_second": 8.312,
|
| 84 |
+
"eval_steps_per_second": 0.523,
|
| 85 |
+
"step": 3208
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"learning_rate": 2.5315656565656566e-05,
|
| 90 |
+
"loss": 3.1059,
|
| 91 |
+
"step": 4010
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 5.0,
|
| 95 |
+
"eval_gen_len": 15.7366,
|
| 96 |
+
"eval_loss": 3.362180709838867,
|
| 97 |
+
"eval_rouge1": 26.7254,
|
| 98 |
+
"eval_rouge2": 9.1138,
|
| 99 |
+
"eval_rougeL": 25.7985,
|
| 100 |
+
"eval_rougeLsum": 25.8521,
|
| 101 |
+
"eval_runtime": 195.6438,
|
| 102 |
+
"eval_samples_per_second": 9.43,
|
| 103 |
+
"eval_steps_per_second": 0.593,
|
| 104 |
+
"step": 4010
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"learning_rate": 2.0252525252525253e-05,
|
| 109 |
+
"loss": 3.0336,
|
| 110 |
+
"step": 4812
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 6.0,
|
| 114 |
+
"eval_gen_len": 16.548,
|
| 115 |
+
"eval_loss": 3.366245746612549,
|
| 116 |
+
"eval_rouge1": 26.4655,
|
| 117 |
+
"eval_rouge2": 9.1283,
|
| 118 |
+
"eval_rougeL": 25.4587,
|
| 119 |
+
"eval_rougeLsum": 25.5112,
|
| 120 |
+
"eval_runtime": 221.12,
|
| 121 |
+
"eval_samples_per_second": 8.344,
|
| 122 |
+
"eval_steps_per_second": 0.525,
|
| 123 |
+
"step": 4812
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"learning_rate": 1.518939393939394e-05,
|
| 128 |
+
"loss": 2.9727,
|
| 129 |
+
"step": 5614
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"eval_gen_len": 15.5431,
|
| 134 |
+
"eval_loss": 3.359348773956299,
|
| 135 |
+
"eval_rouge1": 26.8211,
|
| 136 |
+
"eval_rouge2": 9.3045,
|
| 137 |
+
"eval_rougeL": 25.8497,
|
| 138 |
+
"eval_rougeLsum": 25.8772,
|
| 139 |
+
"eval_runtime": 192.8568,
|
| 140 |
+
"eval_samples_per_second": 9.567,
|
| 141 |
+
"eval_steps_per_second": 0.601,
|
| 142 |
+
"step": 5614
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"learning_rate": 1.0126262626262626e-05,
|
| 147 |
+
"loss": 2.9298,
|
| 148 |
+
"step": 6416
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 8.0,
|
| 152 |
+
"eval_gen_len": 15.916,
|
| 153 |
+
"eval_loss": 3.364309549331665,
|
| 154 |
+
"eval_rouge1": 26.8932,
|
| 155 |
+
"eval_rouge2": 9.3537,
|
| 156 |
+
"eval_rougeL": 25.9444,
|
| 157 |
+
"eval_rougeLsum": 26.0088,
|
| 158 |
+
"eval_runtime": 199.9625,
|
| 159 |
+
"eval_samples_per_second": 9.227,
|
| 160 |
+
"eval_steps_per_second": 0.58,
|
| 161 |
+
"step": 6416
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"learning_rate": 5.063131313131313e-06,
|
| 166 |
+
"loss": 2.9005,
|
| 167 |
+
"step": 7218
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 9.0,
|
| 171 |
+
"eval_gen_len": 15.71,
|
| 172 |
+
"eval_loss": 3.3606483936309814,
|
| 173 |
+
"eval_rouge1": 27.1732,
|
| 174 |
+
"eval_rouge2": 9.5661,
|
| 175 |
+
"eval_rougeL": 26.1198,
|
| 176 |
+
"eval_rougeLsum": 26.1515,
|
| 177 |
+
"eval_runtime": 186.8674,
|
| 178 |
+
"eval_samples_per_second": 9.873,
|
| 179 |
+
"eval_steps_per_second": 0.621,
|
| 180 |
+
"step": 7218
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"learning_rate": 0.0,
|
| 185 |
+
"loss": 2.8846,
|
| 186 |
+
"step": 8020
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 10.0,
|
| 190 |
+
"eval_gen_len": 15.5767,
|
| 191 |
+
"eval_loss": 3.3608038425445557,
|
| 192 |
+
"eval_rouge1": 27.0741,
|
| 193 |
+
"eval_rouge2": 9.3824,
|
| 194 |
+
"eval_rougeL": 26.133,
|
| 195 |
+
"eval_rougeLsum": 26.1559,
|
| 196 |
+
"eval_runtime": 189.991,
|
| 197 |
+
"eval_samples_per_second": 9.711,
|
| 198 |
+
"eval_steps_per_second": 0.611,
|
| 199 |
+
"step": 8020
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 10.0,
|
| 203 |
+
"step": 8020,
|
| 204 |
+
"total_flos": 2.196016829300736e+16,
|
| 205 |
+
"train_loss": 3.2251040794011065,
|
| 206 |
+
"train_runtime": 10442.016,
|
| 207 |
+
"train_samples_per_second": 6.142,
|
| 208 |
+
"train_steps_per_second": 0.768
|
| 209 |
+
}
|
| 210 |
+
],
|
| 211 |
+
"logging_steps": 500,
|
| 212 |
+
"max_steps": 8020,
|
| 213 |
+
"num_input_tokens_seen": 0,
|
| 214 |
+
"num_train_epochs": 10,
|
| 215 |
+
"save_steps": 500,
|
| 216 |
+
"total_flos": 2.196016829300736e+16,
|
| 217 |
+
"train_batch_size": 8,
|
| 218 |
+
"trial_name": null,
|
| 219 |
+
"trial_params": null
|
| 220 |
+
}
|