Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +260 -14
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497805008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fefe5f0ea45646be108812e8c1453ba92bdc95d2d02b603c7133670673eeba15
|
| 3 |
size 497805008
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995704133
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e72f0c8a3b07a250a91b5d8aacb097a90d0777ab014441e46c8bcb7c3eb4537
|
| 3 |
size 995704133
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ffb0048e2cf4695cac5f2bc75487563fd01379a8f5c878f5405cd126fd821ba
|
| 3 |
size 14575
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87c8ea1662b60de4bc1af77a1d5f57df4bd34ba3d37570aafc8387132ebbe7bc
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,30 +1,276 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "tam_test_out_drug_data/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_runtime":
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second":
|
| 18 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"logging_steps": 500,
|
| 22 |
-
"max_steps":
|
| 23 |
"num_input_tokens_seen": 0,
|
| 24 |
-
"num_train_epochs":
|
| 25 |
"save_steps": 500,
|
| 26 |
-
"total_flos":
|
| 27 |
-
"train_batch_size":
|
| 28 |
"trial_name": null,
|
| 29 |
"trial_params": null
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.410697102546692,
|
| 3 |
+
"best_model_checkpoint": "tam_test_out_drug_data/checkpoint-1011",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6403,
|
| 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 |
+
"eval_accuracy": 0.46396354505719334,
|
| 14 |
+
"eval_loss": 1.46442449092865,
|
| 15 |
+
"eval_runtime": 15.0839,
|
| 16 |
+
"eval_samples_per_second": 712.879,
|
| 17 |
+
"eval_steps_per_second": 7.491,
|
| 18 |
+
"step": 337
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.48,
|
| 22 |
+
"grad_norm": 391296.28125,
|
| 23 |
+
"learning_rate": 5.554896142433234e-05,
|
| 24 |
+
"loss": 1.6493,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"eval_accuracy": 0.47372826188040545,
|
| 30 |
+
"eval_loss": 1.4272058010101318,
|
| 31 |
+
"eval_runtime": 15.1004,
|
| 32 |
+
"eval_samples_per_second": 712.101,
|
| 33 |
+
"eval_steps_per_second": 7.483,
|
| 34 |
+
"step": 674
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.97,
|
| 38 |
+
"grad_norm": 266398.21875,
|
| 39 |
+
"learning_rate": 5.109792284866469e-05,
|
| 40 |
+
"loss": 1.3762,
|
| 41 |
+
"step": 1000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"eval_accuracy": 0.47456523760810937,
|
| 46 |
+
"eval_loss": 1.410697102546692,
|
| 47 |
+
"eval_runtime": 15.0489,
|
| 48 |
+
"eval_samples_per_second": 714.539,
|
| 49 |
+
"eval_steps_per_second": 7.509,
|
| 50 |
+
"step": 1011
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"eval_accuracy": 0.4733562726680926,
|
| 55 |
+
"eval_loss": 1.4484425783157349,
|
| 56 |
+
"eval_runtime": 15.0431,
|
| 57 |
+
"eval_samples_per_second": 714.813,
|
| 58 |
+
"eval_steps_per_second": 7.512,
|
| 59 |
+
"step": 1348
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.45,
|
| 63 |
+
"grad_norm": 369044.0,
|
| 64 |
+
"learning_rate": 4.664688427299703e-05,
|
| 65 |
+
"loss": 1.2056,
|
| 66 |
+
"step": 1500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.0,
|
| 70 |
+
"eval_accuracy": 0.47503022412350043,
|
| 71 |
+
"eval_loss": 1.4948519468307495,
|
| 72 |
+
"eval_runtime": 15.1534,
|
| 73 |
+
"eval_samples_per_second": 709.61,
|
| 74 |
+
"eval_steps_per_second": 7.457,
|
| 75 |
+
"step": 1685
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.93,
|
| 79 |
+
"grad_norm": 454632.0625,
|
| 80 |
+
"learning_rate": 4.219584569732938e-05,
|
| 81 |
+
"loss": 1.0582,
|
| 82 |
+
"step": 2000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 6.0,
|
| 86 |
+
"eval_accuracy": 0.4732632753650144,
|
| 87 |
+
"eval_loss": 1.5683261156082153,
|
| 88 |
+
"eval_runtime": 15.1769,
|
| 89 |
+
"eval_samples_per_second": 708.512,
|
| 90 |
+
"eval_steps_per_second": 7.446,
|
| 91 |
+
"step": 2022
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 7.0,
|
| 95 |
+
"eval_accuracy": 0.4656374965126011,
|
| 96 |
+
"eval_loss": 1.6979163885116577,
|
| 97 |
+
"eval_runtime": 15.1051,
|
| 98 |
+
"eval_samples_per_second": 711.881,
|
| 99 |
+
"eval_steps_per_second": 7.481,
|
| 100 |
+
"step": 2359
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 7.42,
|
| 104 |
+
"grad_norm": 407773.9375,
|
| 105 |
+
"learning_rate": 3.774480712166172e-05,
|
| 106 |
+
"loss": 0.8549,
|
| 107 |
+
"step": 2500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_accuracy": 0.47707616479122106,
|
| 112 |
+
"eval_loss": 1.8021113872528076,
|
| 113 |
+
"eval_runtime": 15.07,
|
| 114 |
+
"eval_samples_per_second": 713.539,
|
| 115 |
+
"eval_steps_per_second": 7.498,
|
| 116 |
+
"step": 2696
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 8.9,
|
| 120 |
+
"grad_norm": 589767.5,
|
| 121 |
+
"learning_rate": 3.3293768545994065e-05,
|
| 122 |
+
"loss": 0.7149,
|
| 123 |
+
"step": 3000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 9.0,
|
| 127 |
+
"eval_accuracy": 0.477913140518925,
|
| 128 |
+
"eval_loss": 1.9680180549621582,
|
| 129 |
+
"eval_runtime": 15.2684,
|
| 130 |
+
"eval_samples_per_second": 704.265,
|
| 131 |
+
"eval_steps_per_second": 7.401,
|
| 132 |
+
"step": 3033
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 10.0,
|
| 136 |
+
"eval_accuracy": 0.4806100623081931,
|
| 137 |
+
"eval_loss": 2.1097300052642822,
|
| 138 |
+
"eval_runtime": 15.2893,
|
| 139 |
+
"eval_samples_per_second": 703.301,
|
| 140 |
+
"eval_steps_per_second": 7.391,
|
| 141 |
+
"step": 3370
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.39,
|
| 145 |
+
"grad_norm": 584814.1875,
|
| 146 |
+
"learning_rate": 2.884272997032641e-05,
|
| 147 |
+
"loss": 0.5551,
|
| 148 |
+
"step": 3500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 11.0,
|
| 152 |
+
"eval_accuracy": 0.46675346414953967,
|
| 153 |
+
"eval_loss": 2.3649089336395264,
|
| 154 |
+
"eval_runtime": 15.0959,
|
| 155 |
+
"eval_samples_per_second": 712.313,
|
| 156 |
+
"eval_steps_per_second": 7.485,
|
| 157 |
+
"step": 3707
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 11.87,
|
| 161 |
+
"grad_norm": 582511.875,
|
| 162 |
+
"learning_rate": 2.4391691394658753e-05,
|
| 163 |
+
"loss": 0.4522,
|
| 164 |
+
"step": 4000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 12.0,
|
| 168 |
+
"eval_accuracy": 0.47447224030503116,
|
| 169 |
+
"eval_loss": 2.432915210723877,
|
| 170 |
+
"eval_runtime": 15.1278,
|
| 171 |
+
"eval_samples_per_second": 710.811,
|
| 172 |
+
"eval_steps_per_second": 7.47,
|
| 173 |
+
"step": 4044
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 13.0,
|
| 177 |
+
"eval_accuracy": 0.4858179112805729,
|
| 178 |
+
"eval_loss": 2.5537261962890625,
|
| 179 |
+
"eval_runtime": 15.2471,
|
| 180 |
+
"eval_samples_per_second": 705.247,
|
| 181 |
+
"eval_steps_per_second": 7.411,
|
| 182 |
+
"step": 4381
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.35,
|
| 186 |
+
"grad_norm": 696384.0625,
|
| 187 |
+
"learning_rate": 1.9940652818991097e-05,
|
| 188 |
+
"loss": 0.3587,
|
| 189 |
+
"step": 4500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 14.0,
|
| 193 |
+
"eval_accuracy": 0.4863758950990421,
|
| 194 |
+
"eval_loss": 2.6619648933410645,
|
| 195 |
+
"eval_runtime": 15.473,
|
| 196 |
+
"eval_samples_per_second": 694.953,
|
| 197 |
+
"eval_steps_per_second": 7.303,
|
| 198 |
+
"step": 4718
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 14.84,
|
| 202 |
+
"grad_norm": 512484.6875,
|
| 203 |
+
"learning_rate": 1.548961424332344e-05,
|
| 204 |
+
"loss": 0.2918,
|
| 205 |
+
"step": 5000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 15.0,
|
| 209 |
+
"eval_accuracy": 0.4929787036175951,
|
| 210 |
+
"eval_loss": 2.762254476547241,
|
| 211 |
+
"eval_runtime": 15.2999,
|
| 212 |
+
"eval_samples_per_second": 702.817,
|
| 213 |
+
"eval_steps_per_second": 7.386,
|
| 214 |
+
"step": 5055
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 16.0,
|
| 218 |
+
"eval_accuracy": 0.48079605691434946,
|
| 219 |
+
"eval_loss": 2.8322901725769043,
|
| 220 |
+
"eval_runtime": 15.0354,
|
| 221 |
+
"eval_samples_per_second": 715.178,
|
| 222 |
+
"eval_steps_per_second": 7.516,
|
| 223 |
+
"step": 5392
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 16.32,
|
| 227 |
+
"grad_norm": 442634.8125,
|
| 228 |
+
"learning_rate": 1.1038575667655787e-05,
|
| 229 |
+
"loss": 0.2289,
|
| 230 |
+
"step": 5500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 17.0,
|
| 234 |
+
"eval_accuracy": 0.4767971728819864,
|
| 235 |
+
"eval_loss": 2.9443678855895996,
|
| 236 |
+
"eval_runtime": 15.2489,
|
| 237 |
+
"eval_samples_per_second": 705.165,
|
| 238 |
+
"eval_steps_per_second": 7.41,
|
| 239 |
+
"step": 5729
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.8,
|
| 243 |
+
"grad_norm": 365735.21875,
|
| 244 |
+
"learning_rate": 6.587537091988131e-06,
|
| 245 |
+
"loss": 0.1962,
|
| 246 |
+
"step": 6000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"eval_accuracy": 0.47828512973123777,
|
| 251 |
+
"eval_loss": 3.0224764347076416,
|
| 252 |
+
"eval_runtime": 15.2048,
|
| 253 |
+
"eval_samples_per_second": 707.209,
|
| 254 |
+
"eval_steps_per_second": 7.432,
|
| 255 |
+
"step": 6066
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 19.0,
|
| 259 |
+
"eval_accuracy": 0.4858179112805729,
|
| 260 |
+
"eval_loss": 3.0596585273742676,
|
| 261 |
+
"eval_runtime": 15.3501,
|
| 262 |
+
"eval_samples_per_second": 700.515,
|
| 263 |
+
"eval_steps_per_second": 7.361,
|
| 264 |
+
"step": 6403
|
| 265 |
}
|
| 266 |
],
|
| 267 |
"logging_steps": 500,
|
| 268 |
+
"max_steps": 6740,
|
| 269 |
"num_input_tokens_seen": 0,
|
| 270 |
+
"num_train_epochs": 20,
|
| 271 |
"save_steps": 500,
|
| 272 |
+
"total_flos": 8.068848695212032e+16,
|
| 273 |
+
"train_batch_size": 96,
|
| 274 |
"trial_name": null,
|
| 275 |
"trial_params": null
|
| 276 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4603
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcf86aa1afbdd702b3daff78f76586a0908e4459d837fc5a7ab105fe1af7cc23
|
| 3 |
size 4603
|