Model save
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +457 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 7.811192553150874e+17,
|
| 4 |
+
"train_loss": 0.0414532983113849,
|
| 5 |
+
"train_runtime": 358.5996,
|
| 6 |
+
"train_samples_per_second": 28.109,
|
| 7 |
+
"train_steps_per_second": 1.757
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 7.811192553150874e+17,
|
| 4 |
+
"train_loss": 0.0414532983113849,
|
| 5 |
+
"train_runtime": 358.5996,
|
| 6 |
+
"train_samples_per_second": 28.109,
|
| 7 |
+
"train_steps_per_second": 1.757
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,457 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.043110452592372894,
|
| 3 |
+
"best_model_checkpoint": "./output/vit-base-riego/checkpoint-500",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 630,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 0.00019714285714285716,
|
| 13 |
+
"loss": 0.2579,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 0.000193968253968254,
|
| 19 |
+
"loss": 0.1457,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.14,
|
| 24 |
+
"learning_rate": 0.00019079365079365082,
|
| 25 |
+
"loss": 0.0975,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.19,
|
| 30 |
+
"learning_rate": 0.00018761904761904763,
|
| 31 |
+
"loss": 0.0565,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.24,
|
| 36 |
+
"learning_rate": 0.00018444444444444446,
|
| 37 |
+
"loss": 0.0579,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.29,
|
| 42 |
+
"learning_rate": 0.00018126984126984127,
|
| 43 |
+
"loss": 0.0302,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.33,
|
| 48 |
+
"learning_rate": 0.0001780952380952381,
|
| 49 |
+
"loss": 0.0039,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.38,
|
| 54 |
+
"learning_rate": 0.00017492063492063493,
|
| 55 |
+
"loss": 0.0441,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.43,
|
| 60 |
+
"learning_rate": 0.00017174603174603174,
|
| 61 |
+
"loss": 0.0414,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.48,
|
| 66 |
+
"learning_rate": 0.00016857142857142857,
|
| 67 |
+
"loss": 0.0443,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.48,
|
| 72 |
+
"eval_f1": 0.8742058449809403,
|
| 73 |
+
"eval_loss": 0.4737350344657898,
|
| 74 |
+
"eval_runtime": 8.752,
|
| 75 |
+
"eval_samples_per_second": 95.978,
|
| 76 |
+
"eval_steps_per_second": 11.997,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.52,
|
| 81 |
+
"learning_rate": 0.0001653968253968254,
|
| 82 |
+
"loss": 0.1463,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.57,
|
| 87 |
+
"learning_rate": 0.00016222222222222224,
|
| 88 |
+
"loss": 0.0683,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.62,
|
| 93 |
+
"learning_rate": 0.00015904761904761904,
|
| 94 |
+
"loss": 0.0551,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.67,
|
| 99 |
+
"learning_rate": 0.0001561904761904762,
|
| 100 |
+
"loss": 0.1104,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.71,
|
| 105 |
+
"learning_rate": 0.00015301587301587302,
|
| 106 |
+
"loss": 0.0087,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.76,
|
| 111 |
+
"learning_rate": 0.00014984126984126986,
|
| 112 |
+
"loss": 0.0566,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.81,
|
| 117 |
+
"learning_rate": 0.00014666666666666666,
|
| 118 |
+
"loss": 0.1618,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.86,
|
| 123 |
+
"learning_rate": 0.0001434920634920635,
|
| 124 |
+
"loss": 0.1098,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.9,
|
| 129 |
+
"learning_rate": 0.0001403174603174603,
|
| 130 |
+
"loss": 0.0608,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.95,
|
| 135 |
+
"learning_rate": 0.00013714285714285716,
|
| 136 |
+
"loss": 0.0349,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.95,
|
| 141 |
+
"eval_f1": 0.973293768545994,
|
| 142 |
+
"eval_loss": 0.07742569595575333,
|
| 143 |
+
"eval_runtime": 10.0816,
|
| 144 |
+
"eval_samples_per_second": 83.32,
|
| 145 |
+
"eval_steps_per_second": 10.415,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.0,
|
| 150 |
+
"learning_rate": 0.00013396825396825397,
|
| 151 |
+
"loss": 0.0455,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.05,
|
| 156 |
+
"learning_rate": 0.0001307936507936508,
|
| 157 |
+
"loss": 0.0756,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.1,
|
| 162 |
+
"learning_rate": 0.0001276190476190476,
|
| 163 |
+
"loss": 0.0065,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.14,
|
| 168 |
+
"learning_rate": 0.00012444444444444444,
|
| 169 |
+
"loss": 0.0255,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.19,
|
| 174 |
+
"learning_rate": 0.00012126984126984127,
|
| 175 |
+
"loss": 0.0841,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.24,
|
| 180 |
+
"learning_rate": 0.0001180952380952381,
|
| 181 |
+
"loss": 0.1931,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.29,
|
| 186 |
+
"learning_rate": 0.00011492063492063491,
|
| 187 |
+
"loss": 0.0206,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.33,
|
| 192 |
+
"learning_rate": 0.00011174603174603176,
|
| 193 |
+
"loss": 0.0431,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.38,
|
| 198 |
+
"learning_rate": 0.00010857142857142856,
|
| 199 |
+
"loss": 0.0103,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.43,
|
| 204 |
+
"learning_rate": 0.00010539682539682541,
|
| 205 |
+
"loss": 0.003,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.43,
|
| 210 |
+
"eval_f1": 0.9794117647058823,
|
| 211 |
+
"eval_loss": 0.0675111711025238,
|
| 212 |
+
"eval_runtime": 9.6291,
|
| 213 |
+
"eval_samples_per_second": 87.235,
|
| 214 |
+
"eval_steps_per_second": 10.904,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.48,
|
| 219 |
+
"learning_rate": 0.00010222222222222222,
|
| 220 |
+
"loss": 0.0345,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.52,
|
| 225 |
+
"learning_rate": 9.904761904761905e-05,
|
| 226 |
+
"loss": 0.0022,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.57,
|
| 231 |
+
"learning_rate": 9.587301587301588e-05,
|
| 232 |
+
"loss": 0.0362,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.62,
|
| 237 |
+
"learning_rate": 9.26984126984127e-05,
|
| 238 |
+
"loss": 0.0733,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.67,
|
| 243 |
+
"learning_rate": 8.952380952380953e-05,
|
| 244 |
+
"loss": 0.1402,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.71,
|
| 249 |
+
"learning_rate": 8.634920634920635e-05,
|
| 250 |
+
"loss": 0.0135,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.76,
|
| 255 |
+
"learning_rate": 8.317460317460319e-05,
|
| 256 |
+
"loss": 0.0309,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.81,
|
| 261 |
+
"learning_rate": 8e-05,
|
| 262 |
+
"loss": 0.0301,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.86,
|
| 267 |
+
"learning_rate": 7.682539682539684e-05,
|
| 268 |
+
"loss": 0.0023,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.9,
|
| 273 |
+
"learning_rate": 7.365079365079366e-05,
|
| 274 |
+
"loss": 0.002,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.9,
|
| 279 |
+
"eval_f1": 0.9809663250366033,
|
| 280 |
+
"eval_loss": 0.06742586195468903,
|
| 281 |
+
"eval_runtime": 9.4801,
|
| 282 |
+
"eval_samples_per_second": 88.606,
|
| 283 |
+
"eval_steps_per_second": 11.076,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.95,
|
| 288 |
+
"learning_rate": 7.047619047619048e-05,
|
| 289 |
+
"loss": 0.0193,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.0,
|
| 294 |
+
"learning_rate": 6.730158730158731e-05,
|
| 295 |
+
"loss": 0.0465,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.05,
|
| 300 |
+
"learning_rate": 6.412698412698413e-05,
|
| 301 |
+
"loss": 0.0019,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.1,
|
| 306 |
+
"learning_rate": 6.0952380952380964e-05,
|
| 307 |
+
"loss": 0.0019,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.14,
|
| 312 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 313 |
+
"loss": 0.0017,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.19,
|
| 318 |
+
"learning_rate": 5.46031746031746e-05,
|
| 319 |
+
"loss": 0.0015,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.24,
|
| 324 |
+
"learning_rate": 5.142857142857143e-05,
|
| 325 |
+
"loss": 0.0014,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.29,
|
| 330 |
+
"learning_rate": 4.8253968253968255e-05,
|
| 331 |
+
"loss": 0.0014,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.33,
|
| 336 |
+
"learning_rate": 4.507936507936508e-05,
|
| 337 |
+
"loss": 0.0014,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.38,
|
| 342 |
+
"learning_rate": 4.190476190476191e-05,
|
| 343 |
+
"loss": 0.0014,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.38,
|
| 348 |
+
"eval_f1": 0.9870875179340028,
|
| 349 |
+
"eval_loss": 0.043110452592372894,
|
| 350 |
+
"eval_runtime": 12.9756,
|
| 351 |
+
"eval_samples_per_second": 64.737,
|
| 352 |
+
"eval_steps_per_second": 8.092,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.43,
|
| 357 |
+
"learning_rate": 3.8730158730158734e-05,
|
| 358 |
+
"loss": 0.0014,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.48,
|
| 363 |
+
"learning_rate": 3.555555555555556e-05,
|
| 364 |
+
"loss": 0.0013,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.52,
|
| 369 |
+
"learning_rate": 3.2380952380952386e-05,
|
| 370 |
+
"loss": 0.0014,
|
| 371 |
+
"step": 530
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.57,
|
| 375 |
+
"learning_rate": 2.920634920634921e-05,
|
| 376 |
+
"loss": 0.0104,
|
| 377 |
+
"step": 540
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.62,
|
| 381 |
+
"learning_rate": 2.6031746031746035e-05,
|
| 382 |
+
"loss": 0.0012,
|
| 383 |
+
"step": 550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.67,
|
| 387 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 388 |
+
"loss": 0.0012,
|
| 389 |
+
"step": 560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.71,
|
| 393 |
+
"learning_rate": 1.9682539682539684e-05,
|
| 394 |
+
"loss": 0.0013,
|
| 395 |
+
"step": 570
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.76,
|
| 399 |
+
"learning_rate": 1.6507936507936507e-05,
|
| 400 |
+
"loss": 0.0013,
|
| 401 |
+
"step": 580
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.81,
|
| 405 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 406 |
+
"loss": 0.0013,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.86,
|
| 411 |
+
"learning_rate": 1.015873015873016e-05,
|
| 412 |
+
"loss": 0.0011,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.86,
|
| 417 |
+
"eval_f1": 0.9853801169590642,
|
| 418 |
+
"eval_loss": 0.05441011115908623,
|
| 419 |
+
"eval_runtime": 11.2209,
|
| 420 |
+
"eval_samples_per_second": 74.86,
|
| 421 |
+
"eval_steps_per_second": 9.358,
|
| 422 |
+
"step": 600
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.9,
|
| 426 |
+
"learning_rate": 6.984126984126985e-06,
|
| 427 |
+
"loss": 0.0424,
|
| 428 |
+
"step": 610
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.95,
|
| 432 |
+
"learning_rate": 3.8095238095238102e-06,
|
| 433 |
+
"loss": 0.0013,
|
| 434 |
+
"step": 620
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.0,
|
| 438 |
+
"learning_rate": 6.34920634920635e-07,
|
| 439 |
+
"loss": 0.0033,
|
| 440 |
+
"step": 630
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.0,
|
| 444 |
+
"step": 630,
|
| 445 |
+
"total_flos": 7.811192553150874e+17,
|
| 446 |
+
"train_loss": 0.0414532983113849,
|
| 447 |
+
"train_runtime": 358.5996,
|
| 448 |
+
"train_samples_per_second": 28.109,
|
| 449 |
+
"train_steps_per_second": 1.757
|
| 450 |
+
}
|
| 451 |
+
],
|
| 452 |
+
"max_steps": 630,
|
| 453 |
+
"num_train_epochs": 3,
|
| 454 |
+
"total_flos": 7.811192553150874e+17,
|
| 455 |
+
"trial_name": null,
|
| 456 |
+
"trial_params": null
|
| 457 |
+
}
|