End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.2,
|
| 3 |
+
"eval_accuracy": 0.775,
|
| 4 |
+
"eval_loss": 0.48075541853904724,
|
| 5 |
+
"eval_runtime": 225.4225,
|
| 6 |
+
"eval_samples_per_second": 3.549,
|
| 7 |
+
"eval_steps_per_second": 0.222
|
| 8 |
+
}
|
runs/Nov20_03-47-59_ml-server03/events.out.tfevents.1732078897.ml-server03.3387279.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41808eae53cc891efa5665d05a57f875b74a624c8ac4dccb0fe7013beb657c1e
|
| 3 |
+
size 363
|
trainer_state.json
ADDED
|
@@ -0,0 +1,446 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.775,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-rwf2000-subset___v1/checkpoint-500",
|
| 4 |
+
"epoch": 4.2,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 6.027842044830322,
|
| 14 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 15 |
+
"loss": 0.6934,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"grad_norm": 5.1828837394714355,
|
| 21 |
+
"learning_rate": 4.000000000000001e-06,
|
| 22 |
+
"loss": 0.7343,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06,
|
| 27 |
+
"grad_norm": 6.022104740142822,
|
| 28 |
+
"learning_rate": 6e-06,
|
| 29 |
+
"loss": 0.6867,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08,
|
| 34 |
+
"grad_norm": 3.9819915294647217,
|
| 35 |
+
"learning_rate": 8.000000000000001e-06,
|
| 36 |
+
"loss": 0.6967,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1,
|
| 41 |
+
"grad_norm": 3.980625867843628,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 0.6699,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12,
|
| 48 |
+
"grad_norm": 6.501969337463379,
|
| 49 |
+
"learning_rate": 9.777777777777779e-06,
|
| 50 |
+
"loss": 0.6533,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14,
|
| 55 |
+
"grad_norm": 3.093120813369751,
|
| 56 |
+
"learning_rate": 9.555555555555556e-06,
|
| 57 |
+
"loss": 0.627,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16,
|
| 62 |
+
"grad_norm": 6.481435775756836,
|
| 63 |
+
"learning_rate": 9.333333333333334e-06,
|
| 64 |
+
"loss": 0.6128,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18,
|
| 69 |
+
"grad_norm": 5.1239118576049805,
|
| 70 |
+
"learning_rate": 9.111111111111112e-06,
|
| 71 |
+
"loss": 0.5995,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2,
|
| 76 |
+
"grad_norm": 3.803208351135254,
|
| 77 |
+
"learning_rate": 8.888888888888888e-06,
|
| 78 |
+
"loss": 0.5205,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2,
|
| 83 |
+
"eval_accuracy": 0.68375,
|
| 84 |
+
"eval_loss": 0.5434452891349792,
|
| 85 |
+
"eval_runtime": 225.7874,
|
| 86 |
+
"eval_samples_per_second": 3.543,
|
| 87 |
+
"eval_steps_per_second": 0.221,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.02,
|
| 92 |
+
"grad_norm": 4.416550159454346,
|
| 93 |
+
"learning_rate": 8.666666666666668e-06,
|
| 94 |
+
"loss": 0.5088,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.04,
|
| 99 |
+
"grad_norm": 6.156940460205078,
|
| 100 |
+
"learning_rate": 8.444444444444446e-06,
|
| 101 |
+
"loss": 0.5568,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.06,
|
| 106 |
+
"grad_norm": 5.02749490737915,
|
| 107 |
+
"learning_rate": 8.222222222222222e-06,
|
| 108 |
+
"loss": 0.5033,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.08,
|
| 113 |
+
"grad_norm": 5.65871524810791,
|
| 114 |
+
"learning_rate": 8.000000000000001e-06,
|
| 115 |
+
"loss": 0.4887,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.1,
|
| 120 |
+
"grad_norm": 5.758727550506592,
|
| 121 |
+
"learning_rate": 7.77777777777778e-06,
|
| 122 |
+
"loss": 0.5106,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.12,
|
| 127 |
+
"grad_norm": 11.959117889404297,
|
| 128 |
+
"learning_rate": 7.555555555555556e-06,
|
| 129 |
+
"loss": 0.5293,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.1400000000000001,
|
| 134 |
+
"grad_norm": 5.07788610458374,
|
| 135 |
+
"learning_rate": 7.333333333333333e-06,
|
| 136 |
+
"loss": 0.4665,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.16,
|
| 141 |
+
"grad_norm": 4.521602153778076,
|
| 142 |
+
"learning_rate": 7.111111111111112e-06,
|
| 143 |
+
"loss": 0.4658,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.18,
|
| 148 |
+
"grad_norm": 5.800256252288818,
|
| 149 |
+
"learning_rate": 6.88888888888889e-06,
|
| 150 |
+
"loss": 0.5002,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.2,
|
| 155 |
+
"grad_norm": 3.6714704036712646,
|
| 156 |
+
"learning_rate": 6.666666666666667e-06,
|
| 157 |
+
"loss": 0.4084,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.2,
|
| 162 |
+
"eval_accuracy": 0.655,
|
| 163 |
+
"eval_loss": 0.5904867053031921,
|
| 164 |
+
"eval_runtime": 247.6204,
|
| 165 |
+
"eval_samples_per_second": 3.231,
|
| 166 |
+
"eval_steps_per_second": 0.202,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.02,
|
| 171 |
+
"grad_norm": 6.782428741455078,
|
| 172 |
+
"learning_rate": 6.444444444444445e-06,
|
| 173 |
+
"loss": 0.4441,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.04,
|
| 178 |
+
"grad_norm": 4.966807842254639,
|
| 179 |
+
"learning_rate": 6.222222222222223e-06,
|
| 180 |
+
"loss": 0.4307,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.06,
|
| 185 |
+
"grad_norm": 8.04571533203125,
|
| 186 |
+
"learning_rate": 6e-06,
|
| 187 |
+
"loss": 0.4022,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.08,
|
| 192 |
+
"grad_norm": 6.805935859680176,
|
| 193 |
+
"learning_rate": 5.777777777777778e-06,
|
| 194 |
+
"loss": 0.4298,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.1,
|
| 199 |
+
"grad_norm": 6.641063213348389,
|
| 200 |
+
"learning_rate": 5.555555555555557e-06,
|
| 201 |
+
"loss": 0.4494,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.12,
|
| 206 |
+
"grad_norm": 6.542612552642822,
|
| 207 |
+
"learning_rate": 5.333333333333334e-06,
|
| 208 |
+
"loss": 0.4735,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.14,
|
| 213 |
+
"grad_norm": 6.421093940734863,
|
| 214 |
+
"learning_rate": 5.1111111111111115e-06,
|
| 215 |
+
"loss": 0.3762,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.16,
|
| 220 |
+
"grad_norm": 5.869024753570557,
|
| 221 |
+
"learning_rate": 4.888888888888889e-06,
|
| 222 |
+
"loss": 0.4387,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.18,
|
| 227 |
+
"grad_norm": 9.899517059326172,
|
| 228 |
+
"learning_rate": 4.666666666666667e-06,
|
| 229 |
+
"loss": 0.4453,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.2,
|
| 234 |
+
"grad_norm": 11.099763870239258,
|
| 235 |
+
"learning_rate": 4.444444444444444e-06,
|
| 236 |
+
"loss": 0.4198,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.2,
|
| 241 |
+
"eval_accuracy": 0.74625,
|
| 242 |
+
"eval_loss": 0.48142582178115845,
|
| 243 |
+
"eval_runtime": 271.5798,
|
| 244 |
+
"eval_samples_per_second": 2.946,
|
| 245 |
+
"eval_steps_per_second": 0.184,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.02,
|
| 250 |
+
"grad_norm": 8.095602989196777,
|
| 251 |
+
"learning_rate": 4.222222222222223e-06,
|
| 252 |
+
"loss": 0.4279,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.04,
|
| 257 |
+
"grad_norm": 5.949367046356201,
|
| 258 |
+
"learning_rate": 4.000000000000001e-06,
|
| 259 |
+
"loss": 0.3158,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.06,
|
| 264 |
+
"grad_norm": 10.842527389526367,
|
| 265 |
+
"learning_rate": 3.777777777777778e-06,
|
| 266 |
+
"loss": 0.3554,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.08,
|
| 271 |
+
"grad_norm": 5.070864677429199,
|
| 272 |
+
"learning_rate": 3.555555555555556e-06,
|
| 273 |
+
"loss": 0.2949,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.1,
|
| 278 |
+
"grad_norm": 15.597376823425293,
|
| 279 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 280 |
+
"loss": 0.3548,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.12,
|
| 285 |
+
"grad_norm": 4.660379409790039,
|
| 286 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 287 |
+
"loss": 0.4349,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.14,
|
| 292 |
+
"grad_norm": 11.151165008544922,
|
| 293 |
+
"learning_rate": 2.888888888888889e-06,
|
| 294 |
+
"loss": 0.3602,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.16,
|
| 299 |
+
"grad_norm": 9.200762748718262,
|
| 300 |
+
"learning_rate": 2.666666666666667e-06,
|
| 301 |
+
"loss": 0.3891,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.18,
|
| 306 |
+
"grad_norm": 6.462916851043701,
|
| 307 |
+
"learning_rate": 2.4444444444444447e-06,
|
| 308 |
+
"loss": 0.2933,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.2,
|
| 313 |
+
"grad_norm": 8.92557144165039,
|
| 314 |
+
"learning_rate": 2.222222222222222e-06,
|
| 315 |
+
"loss": 0.3188,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.2,
|
| 320 |
+
"eval_accuracy": 0.755,
|
| 321 |
+
"eval_loss": 0.5160250663757324,
|
| 322 |
+
"eval_runtime": 225.8295,
|
| 323 |
+
"eval_samples_per_second": 3.542,
|
| 324 |
+
"eval_steps_per_second": 0.221,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.02,
|
| 329 |
+
"grad_norm": 7.164823532104492,
|
| 330 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 331 |
+
"loss": 0.2785,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.04,
|
| 336 |
+
"grad_norm": 4.740599155426025,
|
| 337 |
+
"learning_rate": 1.777777777777778e-06,
|
| 338 |
+
"loss": 0.3388,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.06,
|
| 343 |
+
"grad_norm": 8.506775856018066,
|
| 344 |
+
"learning_rate": 1.5555555555555558e-06,
|
| 345 |
+
"loss": 0.3093,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.08,
|
| 350 |
+
"grad_norm": 4.401611804962158,
|
| 351 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 352 |
+
"loss": 0.2399,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.1,
|
| 357 |
+
"grad_norm": 7.568962574005127,
|
| 358 |
+
"learning_rate": 1.111111111111111e-06,
|
| 359 |
+
"loss": 0.3434,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.12,
|
| 364 |
+
"grad_norm": 9.326196670532227,
|
| 365 |
+
"learning_rate": 8.88888888888889e-07,
|
| 366 |
+
"loss": 0.2818,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.14,
|
| 371 |
+
"grad_norm": 6.332729816436768,
|
| 372 |
+
"learning_rate": 6.666666666666667e-07,
|
| 373 |
+
"loss": 0.3154,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.16,
|
| 378 |
+
"grad_norm": 11.177745819091797,
|
| 379 |
+
"learning_rate": 4.444444444444445e-07,
|
| 380 |
+
"loss": 0.3217,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.18,
|
| 385 |
+
"grad_norm": 6.826053619384766,
|
| 386 |
+
"learning_rate": 2.2222222222222224e-07,
|
| 387 |
+
"loss": 0.3167,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.2,
|
| 392 |
+
"grad_norm": 2.244813919067383,
|
| 393 |
+
"learning_rate": 0.0,
|
| 394 |
+
"loss": 0.2687,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.2,
|
| 399 |
+
"eval_accuracy": 0.775,
|
| 400 |
+
"eval_loss": 0.48075544834136963,
|
| 401 |
+
"eval_runtime": 229.5259,
|
| 402 |
+
"eval_samples_per_second": 3.485,
|
| 403 |
+
"eval_steps_per_second": 0.218,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.2,
|
| 408 |
+
"step": 500,
|
| 409 |
+
"total_flos": 9.968516715773952e+18,
|
| 410 |
+
"train_loss": 0.4460222806930542,
|
| 411 |
+
"train_runtime": 4184.8427,
|
| 412 |
+
"train_samples_per_second": 1.912,
|
| 413 |
+
"train_steps_per_second": 0.119
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.2,
|
| 417 |
+
"eval_accuracy": 0.775,
|
| 418 |
+
"eval_loss": 0.48075541853904724,
|
| 419 |
+
"eval_runtime": 225.4225,
|
| 420 |
+
"eval_samples_per_second": 3.549,
|
| 421 |
+
"eval_steps_per_second": 0.222,
|
| 422 |
+
"step": 500
|
| 423 |
+
}
|
| 424 |
+
],
|
| 425 |
+
"logging_steps": 10,
|
| 426 |
+
"max_steps": 500,
|
| 427 |
+
"num_input_tokens_seen": 0,
|
| 428 |
+
"num_train_epochs": 9223372036854775807,
|
| 429 |
+
"save_steps": 500,
|
| 430 |
+
"stateful_callbacks": {
|
| 431 |
+
"TrainerControl": {
|
| 432 |
+
"args": {
|
| 433 |
+
"should_epoch_stop": false,
|
| 434 |
+
"should_evaluate": false,
|
| 435 |
+
"should_log": false,
|
| 436 |
+
"should_save": true,
|
| 437 |
+
"should_training_stop": true
|
| 438 |
+
},
|
| 439 |
+
"attributes": {}
|
| 440 |
+
}
|
| 441 |
+
},
|
| 442 |
+
"total_flos": 9.968516715773952e+18,
|
| 443 |
+
"train_batch_size": 16,
|
| 444 |
+
"trial_name": null,
|
| 445 |
+
"trial_params": null
|
| 446 |
+
}
|
val_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.2,
|
| 3 |
+
"eval_accuracy": 0.775,
|
| 4 |
+
"eval_loss": 0.48075541853904724,
|
| 5 |
+
"eval_runtime": 225.4225,
|
| 6 |
+
"eval_samples_per_second": 3.549,
|
| 7 |
+
"eval_steps_per_second": 0.222
|
| 8 |
+
}
|