Upload 5 files
Browse files- pytorch_model.bin +1 -1
- trainer_state.json +560 -0
- training_args.bin +2 -2
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343293293
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af3985887d5b9a79da8b10ab17fc90fa3a0d10ad08fa065a1914f45fb91e2eff
|
| 3 |
size 343293293
|
trainer_state.json
ADDED
|
@@ -0,0 +1,560 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.722689075630252,
|
| 5 |
+
"global_step": 800,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 9.915966386554623e-05,
|
| 13 |
+
"loss": 0.5936,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 9.831932773109243e-05,
|
| 19 |
+
"loss": 0.4777,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.25,
|
| 24 |
+
"learning_rate": 9.747899159663865e-05,
|
| 25 |
+
"loss": 0.451,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.34,
|
| 30 |
+
"learning_rate": 9.663865546218487e-05,
|
| 31 |
+
"loss": 0.4346,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.42,
|
| 36 |
+
"learning_rate": 9.579831932773111e-05,
|
| 37 |
+
"loss": 0.4295,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.5,
|
| 42 |
+
"learning_rate": 9.495798319327731e-05,
|
| 43 |
+
"loss": 0.4145,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.59,
|
| 48 |
+
"learning_rate": 9.411764705882353e-05,
|
| 49 |
+
"loss": 0.4026,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.67,
|
| 54 |
+
"learning_rate": 9.327731092436976e-05,
|
| 55 |
+
"loss": 0.3883,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.76,
|
| 60 |
+
"learning_rate": 9.243697478991598e-05,
|
| 61 |
+
"loss": 0.3932,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.84,
|
| 66 |
+
"learning_rate": 9.159663865546218e-05,
|
| 67 |
+
"loss": 0.3789,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.84,
|
| 72 |
+
"eval_loss": 0.37311611553636664,
|
| 73 |
+
"eval_runtime": 3.6115,
|
| 74 |
+
"eval_samples_per_second": 118.51,
|
| 75 |
+
"eval_steps_per_second": 14.952,
|
| 76 |
+
"step": 100
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.92,
|
| 80 |
+
"learning_rate": 9.07563025210084e-05,
|
| 81 |
+
"loss": 0.3752,
|
| 82 |
+
"step": 110
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.01,
|
| 86 |
+
"learning_rate": 8.991596638655462e-05,
|
| 87 |
+
"loss": 0.3481,
|
| 88 |
+
"step": 120
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.09,
|
| 92 |
+
"learning_rate": 8.907563025210084e-05,
|
| 93 |
+
"loss": 0.3529,
|
| 94 |
+
"step": 130
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.18,
|
| 98 |
+
"learning_rate": 8.823529411764706e-05,
|
| 99 |
+
"loss": 0.3209,
|
| 100 |
+
"step": 140
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.26,
|
| 104 |
+
"learning_rate": 8.739495798319329e-05,
|
| 105 |
+
"loss": 0.3122,
|
| 106 |
+
"step": 150
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.34,
|
| 110 |
+
"learning_rate": 8.65546218487395e-05,
|
| 111 |
+
"loss": 0.3113,
|
| 112 |
+
"step": 160
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.43,
|
| 116 |
+
"learning_rate": 8.571428571428571e-05,
|
| 117 |
+
"loss": 0.3184,
|
| 118 |
+
"step": 170
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.51,
|
| 122 |
+
"learning_rate": 8.487394957983193e-05,
|
| 123 |
+
"loss": 0.3271,
|
| 124 |
+
"step": 180
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.6,
|
| 128 |
+
"learning_rate": 8.403361344537815e-05,
|
| 129 |
+
"loss": 0.3135,
|
| 130 |
+
"step": 190
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.68,
|
| 134 |
+
"learning_rate": 8.319327731092437e-05,
|
| 135 |
+
"loss": 0.3021,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.68,
|
| 140 |
+
"eval_loss": 0.314563896388651,
|
| 141 |
+
"eval_runtime": 4.1203,
|
| 142 |
+
"eval_samples_per_second": 103.876,
|
| 143 |
+
"eval_steps_per_second": 13.106,
|
| 144 |
+
"step": 200
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.76,
|
| 148 |
+
"learning_rate": 8.23529411764706e-05,
|
| 149 |
+
"loss": 0.304,
|
| 150 |
+
"step": 210
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.85,
|
| 154 |
+
"learning_rate": 8.151260504201682e-05,
|
| 155 |
+
"loss": 0.3037,
|
| 156 |
+
"step": 220
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.93,
|
| 160 |
+
"learning_rate": 8.067226890756304e-05,
|
| 161 |
+
"loss": 0.2985,
|
| 162 |
+
"step": 230
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.02,
|
| 166 |
+
"learning_rate": 7.983193277310926e-05,
|
| 167 |
+
"loss": 0.2855,
|
| 168 |
+
"step": 240
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.1,
|
| 172 |
+
"learning_rate": 7.899159663865546e-05,
|
| 173 |
+
"loss": 0.2632,
|
| 174 |
+
"step": 250
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.18,
|
| 178 |
+
"learning_rate": 7.815126050420168e-05,
|
| 179 |
+
"loss": 0.2544,
|
| 180 |
+
"step": 260
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.27,
|
| 184 |
+
"learning_rate": 7.73109243697479e-05,
|
| 185 |
+
"loss": 0.256,
|
| 186 |
+
"step": 270
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.35,
|
| 190 |
+
"learning_rate": 7.647058823529411e-05,
|
| 191 |
+
"loss": 0.2563,
|
| 192 |
+
"step": 280
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.44,
|
| 196 |
+
"learning_rate": 7.563025210084033e-05,
|
| 197 |
+
"loss": 0.2595,
|
| 198 |
+
"step": 290
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.52,
|
| 202 |
+
"learning_rate": 7.478991596638657e-05,
|
| 203 |
+
"loss": 0.2623,
|
| 204 |
+
"step": 300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.52,
|
| 208 |
+
"eval_loss": 0.28808101955931803,
|
| 209 |
+
"eval_runtime": 3.6745,
|
| 210 |
+
"eval_samples_per_second": 116.478,
|
| 211 |
+
"eval_steps_per_second": 14.696,
|
| 212 |
+
"step": 300
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.61,
|
| 216 |
+
"learning_rate": 7.394957983193279e-05,
|
| 217 |
+
"loss": 0.2556,
|
| 218 |
+
"step": 310
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.69,
|
| 222 |
+
"learning_rate": 7.310924369747899e-05,
|
| 223 |
+
"loss": 0.2405,
|
| 224 |
+
"step": 320
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.77,
|
| 228 |
+
"learning_rate": 7.226890756302521e-05,
|
| 229 |
+
"loss": 0.2423,
|
| 230 |
+
"step": 330
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.86,
|
| 234 |
+
"learning_rate": 7.142857142857143e-05,
|
| 235 |
+
"loss": 0.2425,
|
| 236 |
+
"step": 340
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.94,
|
| 240 |
+
"learning_rate": 7.058823529411765e-05,
|
| 241 |
+
"loss": 0.2483,
|
| 242 |
+
"step": 350
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.03,
|
| 246 |
+
"learning_rate": 6.974789915966386e-05,
|
| 247 |
+
"loss": 0.2377,
|
| 248 |
+
"step": 360
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.11,
|
| 252 |
+
"learning_rate": 6.890756302521008e-05,
|
| 253 |
+
"loss": 0.217,
|
| 254 |
+
"step": 370
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.19,
|
| 258 |
+
"learning_rate": 6.80672268907563e-05,
|
| 259 |
+
"loss": 0.2078,
|
| 260 |
+
"step": 380
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.28,
|
| 264 |
+
"learning_rate": 6.722689075630254e-05,
|
| 265 |
+
"loss": 0.218,
|
| 266 |
+
"step": 390
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.36,
|
| 270 |
+
"learning_rate": 6.638655462184874e-05,
|
| 271 |
+
"loss": 0.2057,
|
| 272 |
+
"step": 400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.36,
|
| 276 |
+
"eval_loss": 0.26705644754910507,
|
| 277 |
+
"eval_runtime": 3.8185,
|
| 278 |
+
"eval_samples_per_second": 112.085,
|
| 279 |
+
"eval_steps_per_second": 14.142,
|
| 280 |
+
"step": 400
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 3.45,
|
| 284 |
+
"learning_rate": 6.554621848739496e-05,
|
| 285 |
+
"loss": 0.2105,
|
| 286 |
+
"step": 410
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 3.53,
|
| 290 |
+
"learning_rate": 6.470588235294118e-05,
|
| 291 |
+
"loss": 0.2122,
|
| 292 |
+
"step": 420
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 3.61,
|
| 296 |
+
"learning_rate": 6.386554621848739e-05,
|
| 297 |
+
"loss": 0.2009,
|
| 298 |
+
"step": 430
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.7,
|
| 302 |
+
"learning_rate": 6.302521008403361e-05,
|
| 303 |
+
"loss": 0.2134,
|
| 304 |
+
"step": 440
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 3.78,
|
| 308 |
+
"learning_rate": 6.218487394957983e-05,
|
| 309 |
+
"loss": 0.1925,
|
| 310 |
+
"step": 450
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 3.87,
|
| 314 |
+
"learning_rate": 6.134453781512605e-05,
|
| 315 |
+
"loss": 0.2059,
|
| 316 |
+
"step": 460
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.95,
|
| 320 |
+
"learning_rate": 6.0504201680672267e-05,
|
| 321 |
+
"loss": 0.2044,
|
| 322 |
+
"step": 470
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.03,
|
| 326 |
+
"learning_rate": 5.966386554621849e-05,
|
| 327 |
+
"loss": 0.1894,
|
| 328 |
+
"step": 480
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.12,
|
| 332 |
+
"learning_rate": 5.882352941176471e-05,
|
| 333 |
+
"loss": 0.1803,
|
| 334 |
+
"step": 490
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 4.2,
|
| 338 |
+
"learning_rate": 5.7983193277310935e-05,
|
| 339 |
+
"loss": 0.1662,
|
| 340 |
+
"step": 500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.2,
|
| 344 |
+
"eval_loss": 0.2607619765164575,
|
| 345 |
+
"eval_runtime": 3.6275,
|
| 346 |
+
"eval_samples_per_second": 117.987,
|
| 347 |
+
"eval_steps_per_second": 14.886,
|
| 348 |
+
"step": 500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 4.29,
|
| 352 |
+
"learning_rate": 5.714285714285714e-05,
|
| 353 |
+
"loss": 0.1697,
|
| 354 |
+
"step": 510
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.37,
|
| 358 |
+
"learning_rate": 5.630252100840336e-05,
|
| 359 |
+
"loss": 0.178,
|
| 360 |
+
"step": 520
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.45,
|
| 364 |
+
"learning_rate": 5.546218487394958e-05,
|
| 365 |
+
"loss": 0.1715,
|
| 366 |
+
"step": 530
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 4.54,
|
| 370 |
+
"learning_rate": 5.4621848739495796e-05,
|
| 371 |
+
"loss": 0.1543,
|
| 372 |
+
"step": 540
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 4.62,
|
| 376 |
+
"learning_rate": 5.378151260504202e-05,
|
| 377 |
+
"loss": 0.1642,
|
| 378 |
+
"step": 550
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 4.71,
|
| 382 |
+
"learning_rate": 5.294117647058824e-05,
|
| 383 |
+
"loss": 0.1588,
|
| 384 |
+
"step": 560
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 4.79,
|
| 388 |
+
"learning_rate": 5.210084033613446e-05,
|
| 389 |
+
"loss": 0.1637,
|
| 390 |
+
"step": 570
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 4.87,
|
| 394 |
+
"learning_rate": 5.126050420168067e-05,
|
| 395 |
+
"loss": 0.1586,
|
| 396 |
+
"step": 580
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 4.96,
|
| 400 |
+
"learning_rate": 5.042016806722689e-05,
|
| 401 |
+
"loss": 0.1597,
|
| 402 |
+
"step": 590
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.04,
|
| 406 |
+
"learning_rate": 4.957983193277311e-05,
|
| 407 |
+
"loss": 0.1499,
|
| 408 |
+
"step": 600
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.04,
|
| 412 |
+
"eval_loss": 0.2822469831651042,
|
| 413 |
+
"eval_runtime": 4.0436,
|
| 414 |
+
"eval_samples_per_second": 105.845,
|
| 415 |
+
"eval_steps_per_second": 13.354,
|
| 416 |
+
"step": 600
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 5.13,
|
| 420 |
+
"learning_rate": 4.8739495798319326e-05,
|
| 421 |
+
"loss": 0.13,
|
| 422 |
+
"step": 610
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.21,
|
| 426 |
+
"learning_rate": 4.7899159663865554e-05,
|
| 427 |
+
"loss": 0.1319,
|
| 428 |
+
"step": 620
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 5.29,
|
| 432 |
+
"learning_rate": 4.705882352941177e-05,
|
| 433 |
+
"loss": 0.1256,
|
| 434 |
+
"step": 630
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.38,
|
| 438 |
+
"learning_rate": 4.621848739495799e-05,
|
| 439 |
+
"loss": 0.1339,
|
| 440 |
+
"step": 640
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.46,
|
| 444 |
+
"learning_rate": 4.53781512605042e-05,
|
| 445 |
+
"loss": 0.1216,
|
| 446 |
+
"step": 650
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.55,
|
| 450 |
+
"learning_rate": 4.453781512605042e-05,
|
| 451 |
+
"loss": 0.1236,
|
| 452 |
+
"step": 660
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 5.63,
|
| 456 |
+
"learning_rate": 4.369747899159664e-05,
|
| 457 |
+
"loss": 0.1304,
|
| 458 |
+
"step": 670
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.71,
|
| 462 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 463 |
+
"loss": 0.1163,
|
| 464 |
+
"step": 680
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.8,
|
| 468 |
+
"learning_rate": 4.201680672268908e-05,
|
| 469 |
+
"loss": 0.1099,
|
| 470 |
+
"step": 690
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.88,
|
| 474 |
+
"learning_rate": 4.11764705882353e-05,
|
| 475 |
+
"loss": 0.1129,
|
| 476 |
+
"step": 700
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.88,
|
| 480 |
+
"eval_loss": 0.258842878695795,
|
| 481 |
+
"eval_runtime": 3.7037,
|
| 482 |
+
"eval_samples_per_second": 115.559,
|
| 483 |
+
"eval_steps_per_second": 14.58,
|
| 484 |
+
"step": 700
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 5.97,
|
| 488 |
+
"learning_rate": 4.033613445378152e-05,
|
| 489 |
+
"loss": 0.1264,
|
| 490 |
+
"step": 710
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 6.05,
|
| 494 |
+
"learning_rate": 3.949579831932773e-05,
|
| 495 |
+
"loss": 0.1137,
|
| 496 |
+
"step": 720
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 6.13,
|
| 500 |
+
"learning_rate": 3.865546218487395e-05,
|
| 501 |
+
"loss": 0.0875,
|
| 502 |
+
"step": 730
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 6.22,
|
| 506 |
+
"learning_rate": 3.7815126050420166e-05,
|
| 507 |
+
"loss": 0.0894,
|
| 508 |
+
"step": 740
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 6.3,
|
| 512 |
+
"learning_rate": 3.697478991596639e-05,
|
| 513 |
+
"loss": 0.09,
|
| 514 |
+
"step": 750
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 6.39,
|
| 518 |
+
"learning_rate": 3.613445378151261e-05,
|
| 519 |
+
"loss": 0.0957,
|
| 520 |
+
"step": 760
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 6.47,
|
| 524 |
+
"learning_rate": 3.529411764705883e-05,
|
| 525 |
+
"loss": 0.0906,
|
| 526 |
+
"step": 770
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 6.55,
|
| 530 |
+
"learning_rate": 3.445378151260504e-05,
|
| 531 |
+
"loss": 0.0843,
|
| 532 |
+
"step": 780
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.64,
|
| 536 |
+
"learning_rate": 3.361344537815127e-05,
|
| 537 |
+
"loss": 0.082,
|
| 538 |
+
"step": 790
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 6.72,
|
| 542 |
+
"learning_rate": 3.277310924369748e-05,
|
| 543 |
+
"loss": 0.0918,
|
| 544 |
+
"step": 800
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 6.72,
|
| 548 |
+
"eval_loss": 0.25530371967056836,
|
| 549 |
+
"eval_runtime": 4.1287,
|
| 550 |
+
"eval_samples_per_second": 103.666,
|
| 551 |
+
"eval_steps_per_second": 13.079,
|
| 552 |
+
"step": 800
|
| 553 |
+
}
|
| 554 |
+
],
|
| 555 |
+
"max_steps": 1190,
|
| 556 |
+
"num_train_epochs": 10,
|
| 557 |
+
"total_flos": 6.810484334054769e+17,
|
| 558 |
+
"trial_name": null,
|
| 559 |
+
"trial_params": null
|
| 560 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9aa9f4af04d6b2a16c4ed5d03438aa42e43d5d7845f0967de5c90fe6d9d138a5
|
| 3 |
+
size 3387
|