Upload folder using huggingface_hub
Browse files- checkpoint-375/model.safetensors +1 -1
- checkpoint-375/optimizer.pt +1 -1
- checkpoint-375/trainer_state.json +276 -17
- checkpoint-375/training_args.bin +1 -1
- runs/Apr15_14-25-03_b91f66ac42ed/events.out.tfevents.1744727118.b91f66ac42ed.192.2 +3 -0
- runs/Apr15_14-25-03_b91f66ac42ed/events.out.tfevents.1744727300.b91f66ac42ed.192.3 +3 -0
checkpoint-375/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 435602240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a525ccb7c6e844bc15c684d71245bb98a2912c63b2a554a7dd8b6d3e211f2ffb
|
| 3 |
size 435602240
|
checkpoint-375/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 871324218
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2a333900e9bdc932bb7ae6c3c25412350031f1fb4ca8da601132e6968fc2ff5
|
| 3 |
size 871324218
|
checkpoint-375/trainer_state.json
CHANGED
|
@@ -9,32 +9,291 @@
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
-
"eval_accuracy": 0.
|
| 15 |
-
"eval_f1": 0.
|
| 16 |
-
"eval_loss": 0.
|
| 17 |
-
"eval_precision": 0.
|
| 18 |
-
"eval_recall": 0.
|
| 19 |
-
"eval_runtime": 1.
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second": 7.
|
| 22 |
"step": 125
|
| 23 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
{
|
| 25 |
"epoch": 2.0,
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
-
"eval_precision": 0.7634408602150538,
|
| 30 |
-
"eval_recall": 0.8641896220371557,
|
| 31 |
-
"eval_runtime": 1.3459,
|
| 32 |
-
"eval_samples_per_second": 111.452,
|
| 33 |
-
"eval_steps_per_second": 7.43,
|
| 34 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
}
|
| 36 |
],
|
| 37 |
-
"logging_steps":
|
| 38 |
"max_steps": 375,
|
| 39 |
"num_input_tokens_seen": 0,
|
| 40 |
"num_train_epochs": 3,
|
|
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.08,
|
| 14 |
+
"grad_norm": 2.411430835723877,
|
| 15 |
+
"learning_rate": 1.9520000000000003e-05,
|
| 16 |
+
"loss": 0.2283,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.16,
|
| 21 |
+
"grad_norm": 1.634353518486023,
|
| 22 |
+
"learning_rate": 1.898666666666667e-05,
|
| 23 |
+
"loss": 0.2332,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.24,
|
| 28 |
+
"grad_norm": 1.4850561618804932,
|
| 29 |
+
"learning_rate": 1.8453333333333335e-05,
|
| 30 |
+
"loss": 0.1957,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.32,
|
| 35 |
+
"grad_norm": 1.818241000175476,
|
| 36 |
+
"learning_rate": 1.792e-05,
|
| 37 |
+
"loss": 0.2057,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.4,
|
| 42 |
+
"grad_norm": 1.1182990074157715,
|
| 43 |
+
"learning_rate": 1.7386666666666667e-05,
|
| 44 |
+
"loss": 0.2033,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.48,
|
| 49 |
+
"grad_norm": 1.7503159046173096,
|
| 50 |
+
"learning_rate": 1.6853333333333333e-05,
|
| 51 |
+
"loss": 0.2026,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.56,
|
| 56 |
+
"grad_norm": 1.2493916749954224,
|
| 57 |
+
"learning_rate": 1.632e-05,
|
| 58 |
+
"loss": 0.1888,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.64,
|
| 63 |
+
"grad_norm": 2.819777488708496,
|
| 64 |
+
"learning_rate": 1.578666666666667e-05,
|
| 65 |
+
"loss": 0.1877,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.72,
|
| 70 |
+
"grad_norm": 2.9391438961029053,
|
| 71 |
+
"learning_rate": 1.5253333333333335e-05,
|
| 72 |
+
"loss": 0.2035,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.8,
|
| 77 |
+
"grad_norm": 1.5021731853485107,
|
| 78 |
+
"learning_rate": 1.4720000000000001e-05,
|
| 79 |
+
"loss": 0.2014,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.88,
|
| 84 |
+
"grad_norm": 2.2055695056915283,
|
| 85 |
+
"learning_rate": 1.418666666666667e-05,
|
| 86 |
+
"loss": 0.1883,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.96,
|
| 91 |
+
"grad_norm": 1.4860285520553589,
|
| 92 |
+
"learning_rate": 1.3653333333333334e-05,
|
| 93 |
+
"loss": 0.1603,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
{
|
| 97 |
"epoch": 1.0,
|
| 98 |
+
"eval_accuracy": 0.8924624363591208,
|
| 99 |
+
"eval_f1": 0.8189732812969078,
|
| 100 |
+
"eval_loss": 0.34129005670547485,
|
| 101 |
+
"eval_precision": 0.7706214689265537,
|
| 102 |
+
"eval_recall": 0.8737988468930173,
|
| 103 |
+
"eval_runtime": 1.2518,
|
| 104 |
+
"eval_samples_per_second": 119.829,
|
| 105 |
+
"eval_steps_per_second": 7.989,
|
| 106 |
"step": 125
|
| 107 |
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.04,
|
| 110 |
+
"grad_norm": 1.8653055429458618,
|
| 111 |
+
"learning_rate": 1.3120000000000001e-05,
|
| 112 |
+
"loss": 0.177,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.12,
|
| 117 |
+
"grad_norm": 1.1053411960601807,
|
| 118 |
+
"learning_rate": 1.2586666666666668e-05,
|
| 119 |
+
"loss": 0.1112,
|
| 120 |
+
"step": 140
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.2,
|
| 124 |
+
"grad_norm": 3.528696060180664,
|
| 125 |
+
"learning_rate": 1.2053333333333335e-05,
|
| 126 |
+
"loss": 0.1741,
|
| 127 |
+
"step": 150
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.28,
|
| 131 |
+
"grad_norm": 0.7176101803779602,
|
| 132 |
+
"learning_rate": 1.152e-05,
|
| 133 |
+
"loss": 0.154,
|
| 134 |
+
"step": 160
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.3599999999999999,
|
| 138 |
+
"grad_norm": 2.781198024749756,
|
| 139 |
+
"learning_rate": 1.0986666666666668e-05,
|
| 140 |
+
"loss": 0.1583,
|
| 141 |
+
"step": 170
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.44,
|
| 145 |
+
"grad_norm": 1.81239914894104,
|
| 146 |
+
"learning_rate": 1.0453333333333334e-05,
|
| 147 |
+
"loss": 0.1469,
|
| 148 |
+
"step": 180
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.52,
|
| 152 |
+
"grad_norm": 2.6247360706329346,
|
| 153 |
+
"learning_rate": 9.920000000000002e-06,
|
| 154 |
+
"loss": 0.1611,
|
| 155 |
+
"step": 190
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.6,
|
| 159 |
+
"grad_norm": 3.0847527980804443,
|
| 160 |
+
"learning_rate": 9.386666666666668e-06,
|
| 161 |
+
"loss": 0.1847,
|
| 162 |
+
"step": 200
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.6800000000000002,
|
| 166 |
+
"grad_norm": 1.1336817741394043,
|
| 167 |
+
"learning_rate": 8.853333333333334e-06,
|
| 168 |
+
"loss": 0.1417,
|
| 169 |
+
"step": 210
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.76,
|
| 173 |
+
"grad_norm": 1.5952337980270386,
|
| 174 |
+
"learning_rate": 8.32e-06,
|
| 175 |
+
"loss": 0.1461,
|
| 176 |
+
"step": 220
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.8399999999999999,
|
| 180 |
+
"grad_norm": 2.0221853256225586,
|
| 181 |
+
"learning_rate": 7.786666666666666e-06,
|
| 182 |
+
"loss": 0.1805,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.92,
|
| 187 |
+
"grad_norm": 2.383049964904785,
|
| 188 |
+
"learning_rate": 7.253333333333335e-06,
|
| 189 |
+
"loss": 0.1478,
|
| 190 |
+
"step": 240
|
| 191 |
+
},
|
| 192 |
{
|
| 193 |
"epoch": 2.0,
|
| 194 |
+
"grad_norm": 2.451894760131836,
|
| 195 |
+
"learning_rate": 6.720000000000001e-06,
|
| 196 |
+
"loss": 0.1565,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 197 |
"step": 250
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.0,
|
| 201 |
+
"eval_accuracy": 0.8908481311312554,
|
| 202 |
+
"eval_f1": 0.810126582278481,
|
| 203 |
+
"eval_loss": 0.35696592926979065,
|
| 204 |
+
"eval_precision": 0.7649402390438247,
|
| 205 |
+
"eval_recall": 0.8609865470852018,
|
| 206 |
+
"eval_runtime": 1.2788,
|
| 207 |
+
"eval_samples_per_second": 117.295,
|
| 208 |
+
"eval_steps_per_second": 7.82,
|
| 209 |
+
"step": 250
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.08,
|
| 213 |
+
"grad_norm": 1.107708215713501,
|
| 214 |
+
"learning_rate": 6.186666666666668e-06,
|
| 215 |
+
"loss": 0.0882,
|
| 216 |
+
"step": 260
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.16,
|
| 220 |
+
"grad_norm": 2.009230375289917,
|
| 221 |
+
"learning_rate": 5.653333333333334e-06,
|
| 222 |
+
"loss": 0.1579,
|
| 223 |
+
"step": 270
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.24,
|
| 227 |
+
"grad_norm": 1.4875034093856812,
|
| 228 |
+
"learning_rate": 5.12e-06,
|
| 229 |
+
"loss": 0.1289,
|
| 230 |
+
"step": 280
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.32,
|
| 234 |
+
"grad_norm": 2.073133945465088,
|
| 235 |
+
"learning_rate": 4.586666666666667e-06,
|
| 236 |
+
"loss": 0.1078,
|
| 237 |
+
"step": 290
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.4,
|
| 241 |
+
"grad_norm": 1.5456774234771729,
|
| 242 |
+
"learning_rate": 4.053333333333333e-06,
|
| 243 |
+
"loss": 0.1182,
|
| 244 |
+
"step": 300
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.48,
|
| 248 |
+
"grad_norm": 1.452431559562683,
|
| 249 |
+
"learning_rate": 3.52e-06,
|
| 250 |
+
"loss": 0.1282,
|
| 251 |
+
"step": 310
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.56,
|
| 255 |
+
"grad_norm": 2.7509889602661133,
|
| 256 |
+
"learning_rate": 2.986666666666667e-06,
|
| 257 |
+
"loss": 0.1292,
|
| 258 |
+
"step": 320
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.64,
|
| 262 |
+
"grad_norm": 1.7021485567092896,
|
| 263 |
+
"learning_rate": 2.4533333333333333e-06,
|
| 264 |
+
"loss": 0.1447,
|
| 265 |
+
"step": 330
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.7199999999999998,
|
| 269 |
+
"grad_norm": 1.1116437911987305,
|
| 270 |
+
"learning_rate": 1.9200000000000003e-06,
|
| 271 |
+
"loss": 0.1225,
|
| 272 |
+
"step": 340
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.8,
|
| 276 |
+
"grad_norm": 1.4331567287445068,
|
| 277 |
+
"learning_rate": 1.3866666666666668e-06,
|
| 278 |
+
"loss": 0.2136,
|
| 279 |
+
"step": 350
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.88,
|
| 283 |
+
"grad_norm": 7.344844341278076,
|
| 284 |
+
"learning_rate": 8.533333333333334e-07,
|
| 285 |
+
"loss": 0.1619,
|
| 286 |
+
"step": 360
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.96,
|
| 290 |
+
"grad_norm": 2.206089496612549,
|
| 291 |
+
"learning_rate": 3.2e-07,
|
| 292 |
+
"loss": 0.1553,
|
| 293 |
+
"step": 370
|
| 294 |
}
|
| 295 |
],
|
| 296 |
+
"logging_steps": 10,
|
| 297 |
"max_steps": 375,
|
| 298 |
"num_input_tokens_seen": 0,
|
| 299 |
"num_train_epochs": 3,
|
checkpoint-375/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fa7d366c03748023ffcd51748dbaa02295149972fdc642b974b21b1895ef967
|
| 3 |
size 5304
|
runs/Apr15_14-25-03_b91f66ac42ed/events.out.tfevents.1744727118.b91f66ac42ed.192.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbf3de3517236f614d83c2f564dd9f0f73ae23fe5deb3fe8613b701873ae6b17
|
| 3 |
+
size 14652
|
runs/Apr15_14-25-03_b91f66ac42ed/events.out.tfevents.1744727300.b91f66ac42ed.192.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67687076d3469cae433e9539a41744c7940e156944b837a6fa1a4900c922094a
|
| 3 |
+
size 560
|