Upload folder using huggingface_hub
Browse files
checkpoints/checkpoint-627/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cf40f90ba338ac76a4b1d0f364a0e2fe020fa8a92b8e200ec46bdf4c1feca08
|
| 3 |
+
size 78947288
|
checkpoints/checkpoint-627/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:758d0ff0f7cf462b7572a23f74da4a78eb5c4b9f57b98fbc70094461f763adaa
|
| 3 |
+
size 157878906
|
checkpoints/checkpoint-627/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ec28ea0c416565eeac14a0e9c944f185ac250f4ed4bd15c84ff77ed78ba9301
|
| 3 |
+
size 14244
|
checkpoints/checkpoint-627/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f90aca6451b193db5c59b14756ae1f8f33b96ce8badec4b2be33c8f4d1ed57d8
|
| 3 |
+
size 1064
|
checkpoints/checkpoint-627/trainer_state.json
ADDED
|
@@ -0,0 +1,316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.0,
|
| 5 |
+
"eval_steps": 64,
|
| 6 |
+
"global_step": 627,
|
| 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": {
|
| 14 |
+
"accuracy": 0.6990740740740741
|
| 15 |
+
},
|
| 16 |
+
"eval_f1": {
|
| 17 |
+
"f1": 0.5246378412207559
|
| 18 |
+
},
|
| 19 |
+
"eval_loss": 1.4924211502075195,
|
| 20 |
+
"eval_precision": {
|
| 21 |
+
"precision": 0.4763165636952045
|
| 22 |
+
},
|
| 23 |
+
"eval_recall": {
|
| 24 |
+
"recall": 0.59375
|
| 25 |
+
},
|
| 26 |
+
"eval_runtime": 7.4612,
|
| 27 |
+
"eval_samples_per_second": 28.95,
|
| 28 |
+
"eval_steps_per_second": 7.237,
|
| 29 |
+
"step": 57
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.1228070175438596,
|
| 33 |
+
"grad_norm": 12.269176483154297,
|
| 34 |
+
"learning_rate": 1.1496350364963505e-06,
|
| 35 |
+
"loss": 1.5298,
|
| 36 |
+
"step": 64
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": {
|
| 41 |
+
"accuracy": 0.7129629629629629
|
| 42 |
+
},
|
| 43 |
+
"eval_f1": {
|
| 44 |
+
"f1": 0.53001124288253
|
| 45 |
+
},
|
| 46 |
+
"eval_loss": 1.3766342401504517,
|
| 47 |
+
"eval_precision": {
|
| 48 |
+
"precision": 0.4774156660949114
|
| 49 |
+
},
|
| 50 |
+
"eval_recall": {
|
| 51 |
+
"recall": 0.6041666666666666
|
| 52 |
+
},
|
| 53 |
+
"eval_runtime": 7.1848,
|
| 54 |
+
"eval_samples_per_second": 30.063,
|
| 55 |
+
"eval_steps_per_second": 7.516,
|
| 56 |
+
"step": 114
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.245614035087719,
|
| 60 |
+
"grad_norm": 11.047577857971191,
|
| 61 |
+
"learning_rate": 2.3175182481751825e-06,
|
| 62 |
+
"loss": 1.3875,
|
| 63 |
+
"step": 128
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 3.0,
|
| 67 |
+
"eval_accuracy": {
|
| 68 |
+
"accuracy": 0.7962962962962963
|
| 69 |
+
},
|
| 70 |
+
"eval_f1": {
|
| 71 |
+
"f1": 0.7359516439448823
|
| 72 |
+
},
|
| 73 |
+
"eval_loss": 1.3143658638000488,
|
| 74 |
+
"eval_precision": {
|
| 75 |
+
"precision": 0.8463221219578889
|
| 76 |
+
},
|
| 77 |
+
"eval_recall": {
|
| 78 |
+
"recall": 0.7291666666666666
|
| 79 |
+
},
|
| 80 |
+
"eval_runtime": 6.953,
|
| 81 |
+
"eval_samples_per_second": 31.066,
|
| 82 |
+
"eval_steps_per_second": 7.766,
|
| 83 |
+
"step": 171
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.3684210526315788,
|
| 87 |
+
"grad_norm": 10.464760780334473,
|
| 88 |
+
"learning_rate": 3.4854014598540146e-06,
|
| 89 |
+
"loss": 1.292,
|
| 90 |
+
"step": 192
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.0,
|
| 94 |
+
"eval_accuracy": {
|
| 95 |
+
"accuracy": 0.7824074074074074
|
| 96 |
+
},
|
| 97 |
+
"eval_f1": {
|
| 98 |
+
"f1": 0.7084821399163013
|
| 99 |
+
},
|
| 100 |
+
"eval_loss": 1.2212026119232178,
|
| 101 |
+
"eval_precision": {
|
| 102 |
+
"precision": 0.8394571333995365
|
| 103 |
+
},
|
| 104 |
+
"eval_recall": {
|
| 105 |
+
"recall": 0.7083333333333334
|
| 106 |
+
},
|
| 107 |
+
"eval_runtime": 7.4938,
|
| 108 |
+
"eval_samples_per_second": 28.824,
|
| 109 |
+
"eval_steps_per_second": 7.206,
|
| 110 |
+
"step": 228
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.491228070175438,
|
| 114 |
+
"grad_norm": 12.949272155761719,
|
| 115 |
+
"learning_rate": 4.653284671532847e-06,
|
| 116 |
+
"loss": 1.2461,
|
| 117 |
+
"step": 256
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 5.0,
|
| 121 |
+
"eval_accuracy": {
|
| 122 |
+
"accuracy": 0.8055555555555556
|
| 123 |
+
},
|
| 124 |
+
"eval_f1": {
|
| 125 |
+
"f1": 0.7569049164117302
|
| 126 |
+
},
|
| 127 |
+
"eval_loss": 1.1568979024887085,
|
| 128 |
+
"eval_precision": {
|
| 129 |
+
"precision": 0.8381390145435089
|
| 130 |
+
},
|
| 131 |
+
"eval_recall": {
|
| 132 |
+
"recall": 0.7465277777777778
|
| 133 |
+
},
|
| 134 |
+
"eval_runtime": 7.129,
|
| 135 |
+
"eval_samples_per_second": 30.299,
|
| 136 |
+
"eval_steps_per_second": 7.575,
|
| 137 |
+
"step": 285
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 5.614035087719298,
|
| 141 |
+
"grad_norm": 10.92992877960205,
|
| 142 |
+
"learning_rate": 5.821167883211679e-06,
|
| 143 |
+
"loss": 1.1103,
|
| 144 |
+
"step": 320
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 6.0,
|
| 148 |
+
"eval_accuracy": {
|
| 149 |
+
"accuracy": 0.7777777777777778
|
| 150 |
+
},
|
| 151 |
+
"eval_f1": {
|
| 152 |
+
"f1": 0.7295260138258725
|
| 153 |
+
},
|
| 154 |
+
"eval_loss": 1.1286191940307617,
|
| 155 |
+
"eval_precision": {
|
| 156 |
+
"precision": 0.8194070080862534
|
| 157 |
+
},
|
| 158 |
+
"eval_recall": {
|
| 159 |
+
"recall": 0.7800925925925926
|
| 160 |
+
},
|
| 161 |
+
"eval_runtime": 7.0035,
|
| 162 |
+
"eval_samples_per_second": 30.842,
|
| 163 |
+
"eval_steps_per_second": 7.71,
|
| 164 |
+
"step": 342
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.7368421052631575,
|
| 168 |
+
"grad_norm": 21.803577423095703,
|
| 169 |
+
"learning_rate": 6.989051094890511e-06,
|
| 170 |
+
"loss": 1.0695,
|
| 171 |
+
"step": 384
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.0,
|
| 175 |
+
"eval_accuracy": {
|
| 176 |
+
"accuracy": 0.6574074074074074
|
| 177 |
+
},
|
| 178 |
+
"eval_f1": {
|
| 179 |
+
"f1": 0.5127626686719305
|
| 180 |
+
},
|
| 181 |
+
"eval_loss": 1.287270188331604,
|
| 182 |
+
"eval_precision": {
|
| 183 |
+
"precision": 0.441052029731275
|
| 184 |
+
},
|
| 185 |
+
"eval_recall": {
|
| 186 |
+
"recall": 0.6597222222222222
|
| 187 |
+
},
|
| 188 |
+
"eval_runtime": 7.1142,
|
| 189 |
+
"eval_samples_per_second": 30.362,
|
| 190 |
+
"eval_steps_per_second": 7.591,
|
| 191 |
+
"step": 399
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 7.859649122807017,
|
| 195 |
+
"grad_norm": 6.482203960418701,
|
| 196 |
+
"learning_rate": 8.156934306569345e-06,
|
| 197 |
+
"loss": 0.9602,
|
| 198 |
+
"step": 448
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 8.0,
|
| 202 |
+
"eval_accuracy": {
|
| 203 |
+
"accuracy": 0.8796296296296297
|
| 204 |
+
},
|
| 205 |
+
"eval_f1": {
|
| 206 |
+
"f1": 0.8678067806780678
|
| 207 |
+
},
|
| 208 |
+
"eval_loss": 0.871719241142273,
|
| 209 |
+
"eval_precision": {
|
| 210 |
+
"precision": 0.8869953337390951
|
| 211 |
+
},
|
| 212 |
+
"eval_recall": {
|
| 213 |
+
"recall": 0.8819444444444443
|
| 214 |
+
},
|
| 215 |
+
"eval_runtime": 7.2624,
|
| 216 |
+
"eval_samples_per_second": 29.742,
|
| 217 |
+
"eval_steps_per_second": 7.436,
|
| 218 |
+
"step": 456
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 8.982456140350877,
|
| 222 |
+
"grad_norm": 24.75027847290039,
|
| 223 |
+
"learning_rate": 9.306569343065694e-06,
|
| 224 |
+
"loss": 0.907,
|
| 225 |
+
"step": 512
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 9.0,
|
| 229 |
+
"eval_accuracy": {
|
| 230 |
+
"accuracy": 0.8796296296296297
|
| 231 |
+
},
|
| 232 |
+
"eval_f1": {
|
| 233 |
+
"f1": 0.8678067806780678
|
| 234 |
+
},
|
| 235 |
+
"eval_loss": 0.7951932549476624,
|
| 236 |
+
"eval_precision": {
|
| 237 |
+
"precision": 0.8869953337390951
|
| 238 |
+
},
|
| 239 |
+
"eval_recall": {
|
| 240 |
+
"recall": 0.8819444444444443
|
| 241 |
+
},
|
| 242 |
+
"eval_runtime": 7.9299,
|
| 243 |
+
"eval_samples_per_second": 27.239,
|
| 244 |
+
"eval_steps_per_second": 6.81,
|
| 245 |
+
"step": 513
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 10.0,
|
| 249 |
+
"eval_accuracy": {
|
| 250 |
+
"accuracy": 0.8611111111111112
|
| 251 |
+
},
|
| 252 |
+
"eval_f1": {
|
| 253 |
+
"f1": 0.8535169178557792
|
| 254 |
+
},
|
| 255 |
+
"eval_loss": 0.8125227689743042,
|
| 256 |
+
"eval_precision": {
|
| 257 |
+
"precision": 0.8559314456035767
|
| 258 |
+
},
|
| 259 |
+
"eval_recall": {
|
| 260 |
+
"recall": 0.8692129629629629
|
| 261 |
+
},
|
| 262 |
+
"eval_runtime": 7.3185,
|
| 263 |
+
"eval_samples_per_second": 29.514,
|
| 264 |
+
"eval_steps_per_second": 7.379,
|
| 265 |
+
"step": 570
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 10.105263157894736,
|
| 269 |
+
"grad_norm": 15.228086471557617,
|
| 270 |
+
"learning_rate": 9.682926829268292e-06,
|
| 271 |
+
"loss": 0.8145,
|
| 272 |
+
"step": 576
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 11.0,
|
| 276 |
+
"eval_accuracy": {
|
| 277 |
+
"accuracy": 0.8796296296296297
|
| 278 |
+
},
|
| 279 |
+
"eval_f1": {
|
| 280 |
+
"f1": 0.8678067806780678
|
| 281 |
+
},
|
| 282 |
+
"eval_loss": 0.807636559009552,
|
| 283 |
+
"eval_precision": {
|
| 284 |
+
"precision": 0.8869953337390951
|
| 285 |
+
},
|
| 286 |
+
"eval_recall": {
|
| 287 |
+
"recall": 0.8819444444444443
|
| 288 |
+
},
|
| 289 |
+
"eval_runtime": 7.4338,
|
| 290 |
+
"eval_samples_per_second": 29.057,
|
| 291 |
+
"eval_steps_per_second": 7.264,
|
| 292 |
+
"step": 627
|
| 293 |
+
}
|
| 294 |
+
],
|
| 295 |
+
"logging_steps": 64,
|
| 296 |
+
"max_steps": 1368,
|
| 297 |
+
"num_input_tokens_seen": 0,
|
| 298 |
+
"num_train_epochs": 24,
|
| 299 |
+
"save_steps": 64,
|
| 300 |
+
"stateful_callbacks": {
|
| 301 |
+
"TrainerControl": {
|
| 302 |
+
"args": {
|
| 303 |
+
"should_epoch_stop": false,
|
| 304 |
+
"should_evaluate": false,
|
| 305 |
+
"should_log": false,
|
| 306 |
+
"should_save": true,
|
| 307 |
+
"should_training_stop": false
|
| 308 |
+
},
|
| 309 |
+
"attributes": {}
|
| 310 |
+
}
|
| 311 |
+
},
|
| 312 |
+
"total_flos": 0.0,
|
| 313 |
+
"train_batch_size": 16,
|
| 314 |
+
"trial_name": null,
|
| 315 |
+
"trial_params": null
|
| 316 |
+
}
|
checkpoints/checkpoint-627/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4229f73f210e46319463b8ac3691f8a1d0602065fd6dccda4819f6160cb9b1e0
|
| 3 |
+
size 5176
|