Training in progress, epoch 0
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- model.safetensors +1 -1
- train_results.json +8 -0
- trainer_state.json +286 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.985781990521327,
|
| 3 |
+
"eval_accuracy": 0.43766666666666665,
|
| 4 |
+
"eval_loss": 2.0961079597473145,
|
| 5 |
+
"eval_runtime": 24.6417,
|
| 6 |
+
"eval_samples_per_second": 243.49,
|
| 7 |
+
"eval_steps_per_second": 1.907,
|
| 8 |
+
"total_flos": 4.411646023570175e+19,
|
| 9 |
+
"train_loss": 2.214817982628232,
|
| 10 |
+
"train_runtime": 948.9642,
|
| 11 |
+
"train_samples_per_second": 170.712,
|
| 12 |
+
"train_steps_per_second": 0.332
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.985781990521327,
|
| 3 |
+
"eval_accuracy": 0.43766666666666665,
|
| 4 |
+
"eval_loss": 2.0961079597473145,
|
| 5 |
+
"eval_runtime": 24.6417,
|
| 6 |
+
"eval_samples_per_second": 243.49,
|
| 7 |
+
"eval_steps_per_second": 1.907
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1212808056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:488a1bc8dea4cbbb6584502aa19dc706b874be37a1eff673d529e05c42ccff36
|
| 3 |
size 1212808056
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.985781990521327,
|
| 3 |
+
"total_flos": 4.411646023570175e+19,
|
| 4 |
+
"train_loss": 2.214817982628232,
|
| 5 |
+
"train_runtime": 948.9642,
|
| 6 |
+
"train_samples_per_second": 170.712,
|
| 7 |
+
"train_steps_per_second": 0.332
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,286 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.43766666666666665,
|
| 3 |
+
"best_model_checkpoint": "clip-vit-large-patch14-finetuned-clip-vit-large-patch14-mnist_linear_probe/checkpoint-315",
|
| 4 |
+
"epoch": 2.985781990521327,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 315,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0947867298578199,
|
| 13 |
+
"grad_norm": 2.288234233856201,
|
| 14 |
+
"learning_rate": 1.5625e-05,
|
| 15 |
+
"loss": 2.4094,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1895734597156398,
|
| 20 |
+
"grad_norm": 2.1556286811828613,
|
| 21 |
+
"learning_rate": 3.125e-05,
|
| 22 |
+
"loss": 2.3858,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2843601895734597,
|
| 27 |
+
"grad_norm": 2.1012516021728516,
|
| 28 |
+
"learning_rate": 4.6875e-05,
|
| 29 |
+
"loss": 2.3743,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3791469194312796,
|
| 34 |
+
"grad_norm": 1.212685227394104,
|
| 35 |
+
"learning_rate": 4.858657243816255e-05,
|
| 36 |
+
"loss": 2.3353,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.47393364928909953,
|
| 41 |
+
"grad_norm": 1.0641510486602783,
|
| 42 |
+
"learning_rate": 4.6819787985865726e-05,
|
| 43 |
+
"loss": 2.3048,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5687203791469194,
|
| 48 |
+
"grad_norm": 0.9478774070739746,
|
| 49 |
+
"learning_rate": 4.50530035335689e-05,
|
| 50 |
+
"loss": 2.2905,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6635071090047393,
|
| 55 |
+
"grad_norm": 0.7033135294914246,
|
| 56 |
+
"learning_rate": 4.328621908127209e-05,
|
| 57 |
+
"loss": 2.2732,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7582938388625592,
|
| 62 |
+
"grad_norm": 0.8783323168754578,
|
| 63 |
+
"learning_rate": 4.1519434628975266e-05,
|
| 64 |
+
"loss": 2.2636,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.8530805687203792,
|
| 69 |
+
"grad_norm": 0.9178075790405273,
|
| 70 |
+
"learning_rate": 3.975265017667845e-05,
|
| 71 |
+
"loss": 2.2455,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.9478672985781991,
|
| 76 |
+
"grad_norm": 0.6878641843795776,
|
| 77 |
+
"learning_rate": 3.7985865724381624e-05,
|
| 78 |
+
"loss": 2.2376,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.995260663507109,
|
| 83 |
+
"eval_accuracy": 0.2981666666666667,
|
| 84 |
+
"eval_loss": 2.2017133235931396,
|
| 85 |
+
"eval_runtime": 24.7638,
|
| 86 |
+
"eval_samples_per_second": 242.289,
|
| 87 |
+
"eval_steps_per_second": 1.898,
|
| 88 |
+
"step": 105
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.042654028436019,
|
| 92 |
+
"grad_norm": 0.9457613229751587,
|
| 93 |
+
"learning_rate": 3.621908127208481e-05,
|
| 94 |
+
"loss": 2.2256,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.1374407582938388,
|
| 99 |
+
"grad_norm": 0.850648820400238,
|
| 100 |
+
"learning_rate": 3.445229681978799e-05,
|
| 101 |
+
"loss": 2.2144,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.2322274881516588,
|
| 106 |
+
"grad_norm": 0.8362263441085815,
|
| 107 |
+
"learning_rate": 3.2685512367491163e-05,
|
| 108 |
+
"loss": 2.2111,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.3270142180094786,
|
| 113 |
+
"grad_norm": 0.6047300100326538,
|
| 114 |
+
"learning_rate": 3.0918727915194346e-05,
|
| 115 |
+
"loss": 2.2002,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.4218009478672986,
|
| 120 |
+
"grad_norm": 0.9275925755500793,
|
| 121 |
+
"learning_rate": 2.915194346289753e-05,
|
| 122 |
+
"loss": 2.1941,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.5165876777251186,
|
| 127 |
+
"grad_norm": 0.8383633494377136,
|
| 128 |
+
"learning_rate": 2.738515901060071e-05,
|
| 129 |
+
"loss": 2.1916,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.6113744075829384,
|
| 134 |
+
"grad_norm": 0.7653341293334961,
|
| 135 |
+
"learning_rate": 2.5618374558303885e-05,
|
| 136 |
+
"loss": 2.1859,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.7061611374407581,
|
| 141 |
+
"grad_norm": 0.775774359703064,
|
| 142 |
+
"learning_rate": 2.3851590106007068e-05,
|
| 143 |
+
"loss": 2.1796,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.8009478672985781,
|
| 148 |
+
"grad_norm": 0.932090699672699,
|
| 149 |
+
"learning_rate": 2.2084805653710246e-05,
|
| 150 |
+
"loss": 2.1708,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.8957345971563981,
|
| 155 |
+
"grad_norm": 0.9772677421569824,
|
| 156 |
+
"learning_rate": 2.031802120141343e-05,
|
| 157 |
+
"loss": 2.1684,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.9905213270142181,
|
| 162 |
+
"grad_norm": 0.7905783653259277,
|
| 163 |
+
"learning_rate": 1.855123674911661e-05,
|
| 164 |
+
"loss": 2.1641,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.0,
|
| 169 |
+
"eval_accuracy": 0.4041666666666667,
|
| 170 |
+
"eval_loss": 2.1207876205444336,
|
| 171 |
+
"eval_runtime": 24.705,
|
| 172 |
+
"eval_samples_per_second": 242.866,
|
| 173 |
+
"eval_steps_per_second": 1.902,
|
| 174 |
+
"step": 211
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.085308056872038,
|
| 178 |
+
"grad_norm": 1.0608142614364624,
|
| 179 |
+
"learning_rate": 1.678445229681979e-05,
|
| 180 |
+
"loss": 2.1633,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.1800947867298577,
|
| 185 |
+
"grad_norm": 1.0211544036865234,
|
| 186 |
+
"learning_rate": 1.501766784452297e-05,
|
| 187 |
+
"loss": 2.1518,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.2748815165876777,
|
| 192 |
+
"grad_norm": 0.9483183026313782,
|
| 193 |
+
"learning_rate": 1.3250883392226149e-05,
|
| 194 |
+
"loss": 2.1507,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.3696682464454977,
|
| 199 |
+
"grad_norm": 0.6434796452522278,
|
| 200 |
+
"learning_rate": 1.148409893992933e-05,
|
| 201 |
+
"loss": 2.1477,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.4644549763033177,
|
| 206 |
+
"grad_norm": 0.7338018417358398,
|
| 207 |
+
"learning_rate": 9.717314487632508e-06,
|
| 208 |
+
"loss": 2.1439,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.5592417061611377,
|
| 213 |
+
"grad_norm": 0.8191038966178894,
|
| 214 |
+
"learning_rate": 7.950530035335689e-06,
|
| 215 |
+
"loss": 2.1466,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.654028436018957,
|
| 220 |
+
"grad_norm": 0.8383843898773193,
|
| 221 |
+
"learning_rate": 6.18374558303887e-06,
|
| 222 |
+
"loss": 2.1435,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.748815165876777,
|
| 227 |
+
"grad_norm": 0.7335329055786133,
|
| 228 |
+
"learning_rate": 4.41696113074205e-06,
|
| 229 |
+
"loss": 2.1399,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.843601895734597,
|
| 234 |
+
"grad_norm": 0.9002769589424133,
|
| 235 |
+
"learning_rate": 2.65017667844523e-06,
|
| 236 |
+
"loss": 2.142,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.938388625592417,
|
| 241 |
+
"grad_norm": 0.8580403327941895,
|
| 242 |
+
"learning_rate": 8.8339222614841e-07,
|
| 243 |
+
"loss": 2.1453,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.985781990521327,
|
| 248 |
+
"eval_accuracy": 0.43766666666666665,
|
| 249 |
+
"eval_loss": 2.0961079597473145,
|
| 250 |
+
"eval_runtime": 24.9225,
|
| 251 |
+
"eval_samples_per_second": 240.747,
|
| 252 |
+
"eval_steps_per_second": 1.886,
|
| 253 |
+
"step": 315
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.985781990521327,
|
| 257 |
+
"step": 315,
|
| 258 |
+
"total_flos": 4.411646023570175e+19,
|
| 259 |
+
"train_loss": 2.214817982628232,
|
| 260 |
+
"train_runtime": 948.9642,
|
| 261 |
+
"train_samples_per_second": 170.712,
|
| 262 |
+
"train_steps_per_second": 0.332
|
| 263 |
+
}
|
| 264 |
+
],
|
| 265 |
+
"logging_steps": 10,
|
| 266 |
+
"max_steps": 315,
|
| 267 |
+
"num_input_tokens_seen": 0,
|
| 268 |
+
"num_train_epochs": 3,
|
| 269 |
+
"save_steps": 500,
|
| 270 |
+
"stateful_callbacks": {
|
| 271 |
+
"TrainerControl": {
|
| 272 |
+
"args": {
|
| 273 |
+
"should_epoch_stop": false,
|
| 274 |
+
"should_evaluate": false,
|
| 275 |
+
"should_log": false,
|
| 276 |
+
"should_save": true,
|
| 277 |
+
"should_training_stop": true
|
| 278 |
+
},
|
| 279 |
+
"attributes": {}
|
| 280 |
+
}
|
| 281 |
+
},
|
| 282 |
+
"total_flos": 4.411646023570175e+19,
|
| 283 |
+
"train_batch_size": 128,
|
| 284 |
+
"trial_name": null,
|
| 285 |
+
"trial_params": null
|
| 286 |
+
}
|
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 sha256:281039b64ae59b55c230306a566c0dc20a32c69abd89b52f9831b2ba17247217
|
| 3 |
size 5304
|