End of training
Browse files- README.md +1 -1
- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +376 -0
README.md
CHANGED
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
- Accuracy: 1.0
|
| 22 |
|
| 23 |
## Model description
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0007
|
| 21 |
- Accuracy: 1.0
|
| 22 |
|
| 23 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.08,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.0007012621499598026,
|
| 5 |
+
"eval_runtime": 18.6184,
|
| 6 |
+
"eval_samples_per_second": 1.02,
|
| 7 |
+
"eval_steps_per_second": 0.269
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.08,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.0007012621499598026,
|
| 5 |
+
"eval_runtime": 18.6184,
|
| 6 |
+
"eval_samples_per_second": 1.02,
|
| 7 |
+
"eval_steps_per_second": 0.269
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-OKN-Test-V27\\checkpoint-328",
|
| 4 |
+
"epoch": 9.0775,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 1.25e-05,
|
| 14 |
+
"loss": 0.7255,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 2.5e-05,
|
| 20 |
+
"loss": 0.5251,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 26 |
+
"loss": 0.6081,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.1,
|
| 31 |
+
"learning_rate": 5e-05,
|
| 32 |
+
"loss": 0.3018,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.1,
|
| 37 |
+
"eval_accuracy": 0.8421052631578947,
|
| 38 |
+
"eval_loss": 0.2653438150882721,
|
| 39 |
+
"eval_runtime": 16.9042,
|
| 40 |
+
"eval_samples_per_second": 1.124,
|
| 41 |
+
"eval_steps_per_second": 0.296,
|
| 42 |
+
"step": 41
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.02,
|
| 46 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 47 |
+
"loss": 0.537,
|
| 48 |
+
"step": 50
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.05,
|
| 52 |
+
"learning_rate": 4.722222222222222e-05,
|
| 53 |
+
"loss": 0.3357,
|
| 54 |
+
"step": 60
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.07,
|
| 58 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 59 |
+
"loss": 0.2755,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.1,
|
| 64 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 65 |
+
"loss": 0.4595,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.1,
|
| 70 |
+
"eval_accuracy": 0.7894736842105263,
|
| 71 |
+
"eval_loss": 0.3112753927707672,
|
| 72 |
+
"eval_runtime": 16.8432,
|
| 73 |
+
"eval_samples_per_second": 1.128,
|
| 74 |
+
"eval_steps_per_second": 0.297,
|
| 75 |
+
"step": 82
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.02,
|
| 79 |
+
"learning_rate": 4.305555555555556e-05,
|
| 80 |
+
"loss": 0.2786,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.04,
|
| 85 |
+
"learning_rate": 4.166666666666667e-05,
|
| 86 |
+
"loss": 0.2892,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.07,
|
| 91 |
+
"learning_rate": 4.027777777777778e-05,
|
| 92 |
+
"loss": 0.3056,
|
| 93 |
+
"step": 110
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.1,
|
| 97 |
+
"learning_rate": 3.888888888888889e-05,
|
| 98 |
+
"loss": 0.4487,
|
| 99 |
+
"step": 120
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.1,
|
| 103 |
+
"eval_accuracy": 0.8421052631578947,
|
| 104 |
+
"eval_loss": 0.3188110291957855,
|
| 105 |
+
"eval_runtime": 16.124,
|
| 106 |
+
"eval_samples_per_second": 1.178,
|
| 107 |
+
"eval_steps_per_second": 0.31,
|
| 108 |
+
"step": 123
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.02,
|
| 112 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 113 |
+
"loss": 0.361,
|
| 114 |
+
"step": 130
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.04,
|
| 118 |
+
"learning_rate": 3.611111111111111e-05,
|
| 119 |
+
"loss": 0.1396,
|
| 120 |
+
"step": 140
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.07,
|
| 124 |
+
"learning_rate": 3.472222222222222e-05,
|
| 125 |
+
"loss": 0.238,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.09,
|
| 130 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 131 |
+
"loss": 0.1211,
|
| 132 |
+
"step": 160
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.1,
|
| 136 |
+
"eval_accuracy": 0.8421052631578947,
|
| 137 |
+
"eval_loss": 0.8331090211868286,
|
| 138 |
+
"eval_runtime": 16.4908,
|
| 139 |
+
"eval_samples_per_second": 1.152,
|
| 140 |
+
"eval_steps_per_second": 0.303,
|
| 141 |
+
"step": 164
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.01,
|
| 145 |
+
"learning_rate": 3.194444444444444e-05,
|
| 146 |
+
"loss": 0.5472,
|
| 147 |
+
"step": 170
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.04,
|
| 151 |
+
"learning_rate": 3.055555555555556e-05,
|
| 152 |
+
"loss": 0.332,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.07,
|
| 157 |
+
"learning_rate": 2.916666666666667e-05,
|
| 158 |
+
"loss": 0.2465,
|
| 159 |
+
"step": 190
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.09,
|
| 163 |
+
"learning_rate": 2.777777777777778e-05,
|
| 164 |
+
"loss": 0.309,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.1,
|
| 169 |
+
"eval_accuracy": 0.8947368421052632,
|
| 170 |
+
"eval_loss": 0.29101037979125977,
|
| 171 |
+
"eval_runtime": 16.4706,
|
| 172 |
+
"eval_samples_per_second": 1.154,
|
| 173 |
+
"eval_steps_per_second": 0.304,
|
| 174 |
+
"step": 205
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 5.01,
|
| 178 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 179 |
+
"loss": 0.1975,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.04,
|
| 184 |
+
"learning_rate": 2.5e-05,
|
| 185 |
+
"loss": 0.0963,
|
| 186 |
+
"step": 220
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 5.06,
|
| 190 |
+
"learning_rate": 2.361111111111111e-05,
|
| 191 |
+
"loss": 0.366,
|
| 192 |
+
"step": 230
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 5.09,
|
| 196 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 197 |
+
"loss": 0.1185,
|
| 198 |
+
"step": 240
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 5.1,
|
| 202 |
+
"eval_accuracy": 0.8421052631578947,
|
| 203 |
+
"eval_loss": 0.20961391925811768,
|
| 204 |
+
"eval_runtime": 17.1194,
|
| 205 |
+
"eval_samples_per_second": 1.11,
|
| 206 |
+
"eval_steps_per_second": 0.292,
|
| 207 |
+
"step": 246
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.01,
|
| 211 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 212 |
+
"loss": 0.616,
|
| 213 |
+
"step": 250
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 6.04,
|
| 217 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 218 |
+
"loss": 0.0551,
|
| 219 |
+
"step": 260
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.06,
|
| 223 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 224 |
+
"loss": 0.2922,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 6.08,
|
| 229 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 230 |
+
"loss": 0.2193,
|
| 231 |
+
"step": 280
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 6.1,
|
| 235 |
+
"eval_accuracy": 0.8947368421052632,
|
| 236 |
+
"eval_loss": 0.31129229068756104,
|
| 237 |
+
"eval_runtime": 16.4386,
|
| 238 |
+
"eval_samples_per_second": 1.156,
|
| 239 |
+
"eval_steps_per_second": 0.304,
|
| 240 |
+
"step": 287
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.01,
|
| 244 |
+
"learning_rate": 1.527777777777778e-05,
|
| 245 |
+
"loss": 0.1423,
|
| 246 |
+
"step": 290
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 7.03,
|
| 250 |
+
"learning_rate": 1.388888888888889e-05,
|
| 251 |
+
"loss": 0.0269,
|
| 252 |
+
"step": 300
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 7.06,
|
| 256 |
+
"learning_rate": 1.25e-05,
|
| 257 |
+
"loss": 0.0218,
|
| 258 |
+
"step": 310
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 7.08,
|
| 262 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 263 |
+
"loss": 0.056,
|
| 264 |
+
"step": 320
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 7.1,
|
| 268 |
+
"eval_accuracy": 1.0,
|
| 269 |
+
"eval_loss": 0.000889659917447716,
|
| 270 |
+
"eval_runtime": 15.8787,
|
| 271 |
+
"eval_samples_per_second": 1.197,
|
| 272 |
+
"eval_steps_per_second": 0.315,
|
| 273 |
+
"step": 328
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.01,
|
| 277 |
+
"learning_rate": 9.722222222222223e-06,
|
| 278 |
+
"loss": 0.0011,
|
| 279 |
+
"step": 330
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 8.03,
|
| 283 |
+
"learning_rate": 8.333333333333334e-06,
|
| 284 |
+
"loss": 0.0007,
|
| 285 |
+
"step": 340
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 8.05,
|
| 289 |
+
"learning_rate": 6.944444444444445e-06,
|
| 290 |
+
"loss": 0.001,
|
| 291 |
+
"step": 350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 8.08,
|
| 295 |
+
"learning_rate": 5.555555555555556e-06,
|
| 296 |
+
"loss": 0.002,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 8.1,
|
| 301 |
+
"eval_accuracy": 1.0,
|
| 302 |
+
"eval_loss": 0.0006986224907450378,
|
| 303 |
+
"eval_runtime": 16.4309,
|
| 304 |
+
"eval_samples_per_second": 1.156,
|
| 305 |
+
"eval_steps_per_second": 0.304,
|
| 306 |
+
"step": 369
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 9.0,
|
| 310 |
+
"learning_rate": 4.166666666666667e-06,
|
| 311 |
+
"loss": 0.0005,
|
| 312 |
+
"step": 370
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 9.03,
|
| 316 |
+
"learning_rate": 2.777777777777778e-06,
|
| 317 |
+
"loss": 0.0005,
|
| 318 |
+
"step": 380
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 9.05,
|
| 322 |
+
"learning_rate": 1.388888888888889e-06,
|
| 323 |
+
"loss": 0.0005,
|
| 324 |
+
"step": 390
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 9.08,
|
| 328 |
+
"learning_rate": 0.0,
|
| 329 |
+
"loss": 0.0005,
|
| 330 |
+
"step": 400
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 9.08,
|
| 334 |
+
"eval_accuracy": 1.0,
|
| 335 |
+
"eval_loss": 0.0006409377092495561,
|
| 336 |
+
"eval_runtime": 17.0698,
|
| 337 |
+
"eval_samples_per_second": 1.113,
|
| 338 |
+
"eval_steps_per_second": 0.293,
|
| 339 |
+
"step": 400
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 9.08,
|
| 343 |
+
"step": 400,
|
| 344 |
+
"total_flos": 1.9824887618495447e+18,
|
| 345 |
+
"train_loss": 0.23998755085049198,
|
| 346 |
+
"train_runtime": 4577.1455,
|
| 347 |
+
"train_samples_per_second": 0.35,
|
| 348 |
+
"train_steps_per_second": 0.087
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 9.08,
|
| 352 |
+
"eval_accuracy": 1.0,
|
| 353 |
+
"eval_loss": 0.0008896598010323942,
|
| 354 |
+
"eval_runtime": 17.4007,
|
| 355 |
+
"eval_samples_per_second": 1.092,
|
| 356 |
+
"eval_steps_per_second": 0.287,
|
| 357 |
+
"step": 400
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 9.08,
|
| 361 |
+
"eval_accuracy": 1.0,
|
| 362 |
+
"eval_loss": 0.0007012621499598026,
|
| 363 |
+
"eval_runtime": 18.6184,
|
| 364 |
+
"eval_samples_per_second": 1.02,
|
| 365 |
+
"eval_steps_per_second": 0.269,
|
| 366 |
+
"step": 400
|
| 367 |
+
}
|
| 368 |
+
],
|
| 369 |
+
"logging_steps": 10,
|
| 370 |
+
"max_steps": 400,
|
| 371 |
+
"num_train_epochs": 9223372036854775807,
|
| 372 |
+
"save_steps": 500,
|
| 373 |
+
"total_flos": 1.9824887618495447e+18,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|