Training in progress, epoch 28
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +425 -5
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3359741661
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a523d3b6334f6de4cfe938b124acc74f6e920e02b978919a5bc10e988425b460
|
| 3 |
size 3359741661
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1680212909
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26216648098c14e4ba6ffec645eb9ad4a8ac34e91bfcbc10876e53b9fb255fac
|
| 3 |
size 1680212909
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3560197ccceeedcb264b77ccdc2c8d3107dd09afe711ecc158f3eaaad21f105
|
| 3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4491687887918e0107d5d93321e5d5275629c6050b0b80e61089ad3a3f2e3f3b
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "thermo-predictor-thermo-evotuning-prot_bert/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -21,11 +21,431 @@
|
|
| 21 |
"eval_spearmanr": 0.3358911230016707,
|
| 22 |
"eval_steps_per_second": 7.187,
|
| 23 |
"step": 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
}
|
| 25 |
],
|
| 26 |
"max_steps": 100,
|
| 27 |
"num_train_epochs": 50,
|
| 28 |
-
"total_flos":
|
| 29 |
"trial_name": null,
|
| 30 |
"trial_params": null
|
| 31 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.18365982174873352,
|
| 3 |
+
"best_model_checkpoint": "thermo-predictor-thermo-evotuning-prot_bert/checkpoint-58",
|
| 4 |
+
"epoch": 28.677248677248677,
|
| 5 |
+
"global_step": 58,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 21 |
"eval_spearmanr": 0.3358911230016707,
|
| 22 |
"eval_steps_per_second": 7.187,
|
| 23 |
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.68,
|
| 27 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 28 |
+
"loss": 0.4392,
|
| 29 |
+
"step": 4
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.68,
|
| 33 |
+
"eval_loss": 0.29363012313842773,
|
| 34 |
+
"eval_runtime": 2.904,
|
| 35 |
+
"eval_samples_per_second": 1846.417,
|
| 36 |
+
"eval_spearmanr": 0.34070735481419273,
|
| 37 |
+
"eval_steps_per_second": 7.231,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.68,
|
| 42 |
+
"learning_rate": 1.88e-05,
|
| 43 |
+
"loss": 0.4034,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.68,
|
| 48 |
+
"eval_loss": 0.2633129358291626,
|
| 49 |
+
"eval_runtime": 3.0574,
|
| 50 |
+
"eval_samples_per_second": 1753.755,
|
| 51 |
+
"eval_spearmanr": 0.36959161893964504,
|
| 52 |
+
"eval_steps_per_second": 6.868,
|
| 53 |
+
"step": 6
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.68,
|
| 57 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 58 |
+
"loss": 0.3669,
|
| 59 |
+
"step": 8
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.68,
|
| 63 |
+
"eval_loss": 0.24365590512752533,
|
| 64 |
+
"eval_runtime": 2.9265,
|
| 65 |
+
"eval_samples_per_second": 1832.235,
|
| 66 |
+
"eval_spearmanr": 0.390325257804677,
|
| 67 |
+
"eval_steps_per_second": 7.176,
|
| 68 |
+
"step": 8
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.68,
|
| 72 |
+
"learning_rate": 1.8e-05,
|
| 73 |
+
"loss": 0.3496,
|
| 74 |
+
"step": 10
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.68,
|
| 78 |
+
"eval_loss": 0.23773197829723358,
|
| 79 |
+
"eval_runtime": 2.9224,
|
| 80 |
+
"eval_samples_per_second": 1834.793,
|
| 81 |
+
"eval_spearmanr": 0.41020718084494817,
|
| 82 |
+
"eval_steps_per_second": 7.186,
|
| 83 |
+
"step": 10
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.68,
|
| 87 |
+
"learning_rate": 1.76e-05,
|
| 88 |
+
"loss": 0.3351,
|
| 89 |
+
"step": 12
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.68,
|
| 93 |
+
"eval_loss": 0.22854185104370117,
|
| 94 |
+
"eval_runtime": 3.4499,
|
| 95 |
+
"eval_samples_per_second": 1554.251,
|
| 96 |
+
"eval_spearmanr": 0.42040641918816646,
|
| 97 |
+
"eval_steps_per_second": 6.087,
|
| 98 |
+
"step": 12
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.68,
|
| 102 |
+
"learning_rate": 1.72e-05,
|
| 103 |
+
"loss": 0.3289,
|
| 104 |
+
"step": 14
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.68,
|
| 108 |
+
"eval_loss": 0.2267082780599594,
|
| 109 |
+
"eval_runtime": 3.0431,
|
| 110 |
+
"eval_samples_per_second": 1762.044,
|
| 111 |
+
"eval_spearmanr": 0.41796639021828647,
|
| 112 |
+
"eval_steps_per_second": 6.901,
|
| 113 |
+
"step": 14
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 7.68,
|
| 117 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 118 |
+
"loss": 0.3267,
|
| 119 |
+
"step": 16
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 7.68,
|
| 123 |
+
"eval_loss": 0.22581231594085693,
|
| 124 |
+
"eval_runtime": 3.1089,
|
| 125 |
+
"eval_samples_per_second": 1724.753,
|
| 126 |
+
"eval_spearmanr": 0.4242454004002921,
|
| 127 |
+
"eval_steps_per_second": 6.755,
|
| 128 |
+
"step": 16
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.68,
|
| 132 |
+
"learning_rate": 1.64e-05,
|
| 133 |
+
"loss": 0.3177,
|
| 134 |
+
"step": 18
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.68,
|
| 138 |
+
"eval_loss": 0.2206145077943802,
|
| 139 |
+
"eval_runtime": 2.9131,
|
| 140 |
+
"eval_samples_per_second": 1840.623,
|
| 141 |
+
"eval_spearmanr": 0.42951271566156707,
|
| 142 |
+
"eval_steps_per_second": 7.209,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 9.68,
|
| 147 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 148 |
+
"loss": 0.3116,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 9.68,
|
| 153 |
+
"eval_loss": 0.21502549946308136,
|
| 154 |
+
"eval_runtime": 2.8807,
|
| 155 |
+
"eval_samples_per_second": 1861.38,
|
| 156 |
+
"eval_spearmanr": 0.43652182698224073,
|
| 157 |
+
"eval_steps_per_second": 7.29,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.68,
|
| 162 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 163 |
+
"loss": 0.3039,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 10.68,
|
| 168 |
+
"eval_loss": 0.21152722835540771,
|
| 169 |
+
"eval_runtime": 2.8687,
|
| 170 |
+
"eval_samples_per_second": 1869.16,
|
| 171 |
+
"eval_spearmanr": 0.4364973861642812,
|
| 172 |
+
"eval_steps_per_second": 7.32,
|
| 173 |
+
"step": 22
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 11.68,
|
| 177 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 178 |
+
"loss": 0.2985,
|
| 179 |
+
"step": 24
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 11.68,
|
| 183 |
+
"eval_loss": 0.20623379945755005,
|
| 184 |
+
"eval_runtime": 2.9943,
|
| 185 |
+
"eval_samples_per_second": 1790.717,
|
| 186 |
+
"eval_spearmanr": 0.4469415528786085,
|
| 187 |
+
"eval_steps_per_second": 7.013,
|
| 188 |
+
"step": 24
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 12.68,
|
| 192 |
+
"learning_rate": 1.48e-05,
|
| 193 |
+
"loss": 0.2927,
|
| 194 |
+
"step": 26
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 12.68,
|
| 198 |
+
"eval_loss": 0.20452716946601868,
|
| 199 |
+
"eval_runtime": 3.0404,
|
| 200 |
+
"eval_samples_per_second": 1763.602,
|
| 201 |
+
"eval_spearmanr": 0.45307896545734583,
|
| 202 |
+
"eval_steps_per_second": 6.907,
|
| 203 |
+
"step": 26
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 13.68,
|
| 207 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 208 |
+
"loss": 0.2885,
|
| 209 |
+
"step": 28
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 13.68,
|
| 213 |
+
"eval_loss": 0.2004762440919876,
|
| 214 |
+
"eval_runtime": 2.8984,
|
| 215 |
+
"eval_samples_per_second": 1849.957,
|
| 216 |
+
"eval_spearmanr": 0.4602718574665676,
|
| 217 |
+
"eval_steps_per_second": 7.245,
|
| 218 |
+
"step": 28
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 14.68,
|
| 222 |
+
"learning_rate": 1.4e-05,
|
| 223 |
+
"loss": 0.2838,
|
| 224 |
+
"step": 30
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.68,
|
| 228 |
+
"eval_loss": 0.1986912339925766,
|
| 229 |
+
"eval_runtime": 3.0267,
|
| 230 |
+
"eval_samples_per_second": 1771.545,
|
| 231 |
+
"eval_spearmanr": 0.46902799622360686,
|
| 232 |
+
"eval_steps_per_second": 6.938,
|
| 233 |
+
"step": 30
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.68,
|
| 237 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 238 |
+
"loss": 0.2806,
|
| 239 |
+
"step": 32
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 15.68,
|
| 243 |
+
"eval_loss": 0.19752489030361176,
|
| 244 |
+
"eval_runtime": 2.9976,
|
| 245 |
+
"eval_samples_per_second": 1788.761,
|
| 246 |
+
"eval_spearmanr": 0.47439420407286187,
|
| 247 |
+
"eval_steps_per_second": 7.006,
|
| 248 |
+
"step": 32
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.68,
|
| 252 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 253 |
+
"loss": 0.2772,
|
| 254 |
+
"step": 34
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 16.68,
|
| 258 |
+
"eval_loss": 0.19701921939849854,
|
| 259 |
+
"eval_runtime": 2.9895,
|
| 260 |
+
"eval_samples_per_second": 1793.634,
|
| 261 |
+
"eval_spearmanr": 0.47652315821607377,
|
| 262 |
+
"eval_steps_per_second": 7.025,
|
| 263 |
+
"step": 34
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 17.68,
|
| 267 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 268 |
+
"loss": 0.2728,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 17.68,
|
| 273 |
+
"eval_loss": 0.19386564195156097,
|
| 274 |
+
"eval_runtime": 3.2955,
|
| 275 |
+
"eval_samples_per_second": 1627.048,
|
| 276 |
+
"eval_spearmanr": 0.48447898122969435,
|
| 277 |
+
"eval_steps_per_second": 6.372,
|
| 278 |
+
"step": 36
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 18.68,
|
| 282 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 283 |
+
"loss": 0.2684,
|
| 284 |
+
"step": 38
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 18.68,
|
| 288 |
+
"eval_loss": 0.19311943650245667,
|
| 289 |
+
"eval_runtime": 2.9977,
|
| 290 |
+
"eval_samples_per_second": 1788.676,
|
| 291 |
+
"eval_spearmanr": 0.4858414916440366,
|
| 292 |
+
"eval_steps_per_second": 7.005,
|
| 293 |
+
"step": 38
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 19.68,
|
| 297 |
+
"learning_rate": 1.2e-05,
|
| 298 |
+
"loss": 0.2641,
|
| 299 |
+
"step": 40
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 19.68,
|
| 303 |
+
"eval_loss": 0.19249317049980164,
|
| 304 |
+
"eval_runtime": 3.1202,
|
| 305 |
+
"eval_samples_per_second": 1718.506,
|
| 306 |
+
"eval_spearmanr": 0.4935711457073984,
|
| 307 |
+
"eval_steps_per_second": 6.73,
|
| 308 |
+
"step": 40
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 20.68,
|
| 312 |
+
"learning_rate": 1.16e-05,
|
| 313 |
+
"loss": 0.2608,
|
| 314 |
+
"step": 42
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 20.68,
|
| 318 |
+
"eval_loss": 0.19051019847393036,
|
| 319 |
+
"eval_runtime": 3.0142,
|
| 320 |
+
"eval_samples_per_second": 1778.905,
|
| 321 |
+
"eval_spearmanr": 0.4929029010849903,
|
| 322 |
+
"eval_steps_per_second": 6.967,
|
| 323 |
+
"step": 42
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 21.68,
|
| 327 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 328 |
+
"loss": 0.2566,
|
| 329 |
+
"step": 44
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 21.68,
|
| 333 |
+
"eval_loss": 0.18856459856033325,
|
| 334 |
+
"eval_runtime": 2.9879,
|
| 335 |
+
"eval_samples_per_second": 1794.551,
|
| 336 |
+
"eval_spearmanr": 0.5048595718357143,
|
| 337 |
+
"eval_steps_per_second": 7.028,
|
| 338 |
+
"step": 44
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 22.68,
|
| 342 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 343 |
+
"loss": 0.2518,
|
| 344 |
+
"step": 46
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 22.68,
|
| 348 |
+
"eval_loss": 0.18753479421138763,
|
| 349 |
+
"eval_runtime": 3.2412,
|
| 350 |
+
"eval_samples_per_second": 1654.33,
|
| 351 |
+
"eval_spearmanr": 0.5095133606919371,
|
| 352 |
+
"eval_steps_per_second": 6.479,
|
| 353 |
+
"step": 46
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 23.68,
|
| 357 |
+
"learning_rate": 1.04e-05,
|
| 358 |
+
"loss": 0.2467,
|
| 359 |
+
"step": 48
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 23.68,
|
| 363 |
+
"eval_loss": 0.18694807589054108,
|
| 364 |
+
"eval_runtime": 3.6439,
|
| 365 |
+
"eval_samples_per_second": 1471.507,
|
| 366 |
+
"eval_spearmanr": 0.5140557788640083,
|
| 367 |
+
"eval_steps_per_second": 5.763,
|
| 368 |
+
"step": 48
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 24.68,
|
| 372 |
+
"learning_rate": 1e-05,
|
| 373 |
+
"loss": 0.2424,
|
| 374 |
+
"step": 50
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 24.68,
|
| 378 |
+
"eval_loss": 0.18594887852668762,
|
| 379 |
+
"eval_runtime": 3.0425,
|
| 380 |
+
"eval_samples_per_second": 1762.352,
|
| 381 |
+
"eval_spearmanr": 0.5161498654457386,
|
| 382 |
+
"eval_steps_per_second": 6.902,
|
| 383 |
+
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 25.68,
|
| 387 |
+
"learning_rate": 9.600000000000001e-06,
|
| 388 |
+
"loss": 0.2375,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 25.68,
|
| 393 |
+
"eval_loss": 0.1849762201309204,
|
| 394 |
+
"eval_runtime": 2.8745,
|
| 395 |
+
"eval_samples_per_second": 1865.365,
|
| 396 |
+
"eval_spearmanr": 0.5223331654258908,
|
| 397 |
+
"eval_steps_per_second": 7.306,
|
| 398 |
+
"step": 52
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 26.68,
|
| 402 |
+
"learning_rate": 9.200000000000002e-06,
|
| 403 |
+
"loss": 0.2329,
|
| 404 |
+
"step": 54
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 26.68,
|
| 408 |
+
"eval_loss": 0.18514755368232727,
|
| 409 |
+
"eval_runtime": 2.8748,
|
| 410 |
+
"eval_samples_per_second": 1865.157,
|
| 411 |
+
"eval_spearmanr": 0.5210178115492534,
|
| 412 |
+
"eval_steps_per_second": 7.305,
|
| 413 |
+
"step": 54
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 27.68,
|
| 417 |
+
"learning_rate": 8.8e-06,
|
| 418 |
+
"loss": 0.2279,
|
| 419 |
+
"step": 56
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 27.68,
|
| 423 |
+
"eval_loss": 0.18495012819766998,
|
| 424 |
+
"eval_runtime": 2.9179,
|
| 425 |
+
"eval_samples_per_second": 1837.612,
|
| 426 |
+
"eval_spearmanr": 0.5294199372441676,
|
| 427 |
+
"eval_steps_per_second": 7.197,
|
| 428 |
+
"step": 56
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 28.68,
|
| 432 |
+
"learning_rate": 8.400000000000001e-06,
|
| 433 |
+
"loss": 0.2226,
|
| 434 |
+
"step": 58
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 28.68,
|
| 438 |
+
"eval_loss": 0.18365982174873352,
|
| 439 |
+
"eval_runtime": 2.8753,
|
| 440 |
+
"eval_samples_per_second": 1864.829,
|
| 441 |
+
"eval_spearmanr": 0.5309868099654046,
|
| 442 |
+
"eval_steps_per_second": 7.304,
|
| 443 |
+
"step": 58
|
| 444 |
}
|
| 445 |
],
|
| 446 |
"max_steps": 100,
|
| 447 |
"num_train_epochs": 50,
|
| 448 |
+
"total_flos": 1.6543891233169373e+17,
|
| 449 |
"trial_name": null,
|
| 450 |
"trial_params": null
|
| 451 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3247
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e615ca7b54e69a7dd39cd3cf92a7ee56fe4d94a86e23ee9f3a0e5c9429720f0
|
| 3 |
size 3247
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1680212909
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26216648098c14e4ba6ffec645eb9ad4a8ac34e91bfcbc10876e53b9fb255fac
|
| 3 |
size 1680212909
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3247
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e615ca7b54e69a7dd39cd3cf92a7ee56fe4d94a86e23ee9f3a0e5c9429720f0
|
| 3 |
size 3247
|