Commit
•
374c50e
1
Parent(s):
fac7d7c
End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +505 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.03882113821138211,
|
| 4 |
+
"eval_loss": 2.857421875,
|
| 5 |
+
"eval_runtime": 5.517,
|
| 6 |
+
"eval_samples": 100,
|
| 7 |
+
"eval_samples_per_second": 18.126,
|
| 8 |
+
"eval_steps_per_second": 0.363,
|
| 9 |
+
"perplexity": 17.416566918622852,
|
| 10 |
+
"train_loss": 2.4493942260742188,
|
| 11 |
+
"train_runtime": 515.1457,
|
| 12 |
+
"train_samples": 1000,
|
| 13 |
+
"train_samples_per_second": 3.882,
|
| 14 |
+
"train_steps_per_second": 0.062
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.03882113821138211,
|
| 4 |
+
"eval_loss": 2.857421875,
|
| 5 |
+
"eval_runtime": 5.517,
|
| 6 |
+
"eval_samples": 100,
|
| 7 |
+
"eval_samples_per_second": 18.126,
|
| 8 |
+
"eval_steps_per_second": 0.363,
|
| 9 |
+
"perplexity": 17.416566918622852
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 2.4493942260742188,
|
| 4 |
+
"train_runtime": 515.1457,
|
| 5 |
+
"train_samples": 1000,
|
| 6 |
+
"train_samples_per_second": 3.882,
|
| 7 |
+
"train_steps_per_second": 0.062
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,505 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 32,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 0,
|
| 13 |
+
"loss": 2.9912,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"eval_accuracy": 0.040365853658536587,
|
| 19 |
+
"eval_loss": 2.744140625,
|
| 20 |
+
"eval_runtime": 4.8585,
|
| 21 |
+
"eval_samples_per_second": 20.583,
|
| 22 |
+
"eval_steps_per_second": 0.412,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"learning_rate": 0,
|
| 28 |
+
"loss": 2.9329,
|
| 29 |
+
"step": 2
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.12,
|
| 33 |
+
"eval_accuracy": 0.040365853658536587,
|
| 34 |
+
"eval_loss": 2.744140625,
|
| 35 |
+
"eval_runtime": 6.3845,
|
| 36 |
+
"eval_samples_per_second": 15.663,
|
| 37 |
+
"eval_steps_per_second": 0.313,
|
| 38 |
+
"step": 2
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.19,
|
| 42 |
+
"learning_rate": 0.0,
|
| 43 |
+
"loss": 2.9138,
|
| 44 |
+
"step": 3
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19,
|
| 48 |
+
"eval_accuracy": 0.038902439024390244,
|
| 49 |
+
"eval_loss": 2.826171875,
|
| 50 |
+
"eval_runtime": 5.4611,
|
| 51 |
+
"eval_samples_per_second": 18.311,
|
| 52 |
+
"eval_steps_per_second": 0.366,
|
| 53 |
+
"step": 3
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.25,
|
| 57 |
+
"learning_rate": 5e-05,
|
| 58 |
+
"loss": 2.9395,
|
| 59 |
+
"step": 4
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.25,
|
| 63 |
+
"eval_accuracy": 0.038902439024390244,
|
| 64 |
+
"eval_loss": 2.826171875,
|
| 65 |
+
"eval_runtime": 6.1625,
|
| 66 |
+
"eval_samples_per_second": 16.227,
|
| 67 |
+
"eval_steps_per_second": 0.325,
|
| 68 |
+
"step": 4
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.31,
|
| 72 |
+
"learning_rate": 5e-05,
|
| 73 |
+
"loss": 2.9109,
|
| 74 |
+
"step": 5
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.31,
|
| 78 |
+
"eval_accuracy": 0.03985772357723577,
|
| 79 |
+
"eval_loss": 2.794921875,
|
| 80 |
+
"eval_runtime": 6.2368,
|
| 81 |
+
"eval_samples_per_second": 16.034,
|
| 82 |
+
"eval_steps_per_second": 0.321,
|
| 83 |
+
"step": 5
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.38,
|
| 87 |
+
"learning_rate": 5e-05,
|
| 88 |
+
"loss": 2.8394,
|
| 89 |
+
"step": 6
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.38,
|
| 93 |
+
"eval_accuracy": 0.04030487804878049,
|
| 94 |
+
"eval_loss": 2.74609375,
|
| 95 |
+
"eval_runtime": 6.1734,
|
| 96 |
+
"eval_samples_per_second": 16.198,
|
| 97 |
+
"eval_steps_per_second": 0.324,
|
| 98 |
+
"step": 6
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.44,
|
| 102 |
+
"learning_rate": 5e-05,
|
| 103 |
+
"loss": 2.9365,
|
| 104 |
+
"step": 7
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.44,
|
| 108 |
+
"eval_accuracy": 0.03985772357723577,
|
| 109 |
+
"eval_loss": 2.720703125,
|
| 110 |
+
"eval_runtime": 6.2486,
|
| 111 |
+
"eval_samples_per_second": 16.004,
|
| 112 |
+
"eval_steps_per_second": 0.32,
|
| 113 |
+
"step": 7
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.5,
|
| 117 |
+
"learning_rate": 5e-05,
|
| 118 |
+
"loss": 2.7588,
|
| 119 |
+
"step": 8
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.5,
|
| 123 |
+
"eval_accuracy": 0.040325203252032524,
|
| 124 |
+
"eval_loss": 2.70703125,
|
| 125 |
+
"eval_runtime": 6.0675,
|
| 126 |
+
"eval_samples_per_second": 16.481,
|
| 127 |
+
"eval_steps_per_second": 0.33,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.56,
|
| 132 |
+
"learning_rate": 5e-05,
|
| 133 |
+
"loss": 2.9751,
|
| 134 |
+
"step": 9
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.56,
|
| 138 |
+
"eval_accuracy": 0.04073170731707317,
|
| 139 |
+
"eval_loss": 2.681640625,
|
| 140 |
+
"eval_runtime": 6.0505,
|
| 141 |
+
"eval_samples_per_second": 16.528,
|
| 142 |
+
"eval_steps_per_second": 0.331,
|
| 143 |
+
"step": 9
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.62,
|
| 147 |
+
"learning_rate": 5e-05,
|
| 148 |
+
"loss": 2.844,
|
| 149 |
+
"step": 10
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.62,
|
| 153 |
+
"eval_accuracy": 0.040426829268292684,
|
| 154 |
+
"eval_loss": 2.673828125,
|
| 155 |
+
"eval_runtime": 5.8947,
|
| 156 |
+
"eval_samples_per_second": 16.964,
|
| 157 |
+
"eval_steps_per_second": 0.339,
|
| 158 |
+
"step": 10
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.69,
|
| 162 |
+
"learning_rate": 5e-05,
|
| 163 |
+
"loss": 2.731,
|
| 164 |
+
"step": 11
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.69,
|
| 168 |
+
"eval_accuracy": 0.04056910569105691,
|
| 169 |
+
"eval_loss": 2.66796875,
|
| 170 |
+
"eval_runtime": 5.7332,
|
| 171 |
+
"eval_samples_per_second": 17.442,
|
| 172 |
+
"eval_steps_per_second": 0.349,
|
| 173 |
+
"step": 11
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.75,
|
| 177 |
+
"learning_rate": 5e-05,
|
| 178 |
+
"loss": 2.7434,
|
| 179 |
+
"step": 12
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.75,
|
| 183 |
+
"eval_accuracy": 0.04040650406504065,
|
| 184 |
+
"eval_loss": 2.669921875,
|
| 185 |
+
"eval_runtime": 5.6141,
|
| 186 |
+
"eval_samples_per_second": 17.812,
|
| 187 |
+
"eval_steps_per_second": 0.356,
|
| 188 |
+
"step": 12
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.81,
|
| 192 |
+
"learning_rate": 5e-05,
|
| 193 |
+
"loss": 2.9043,
|
| 194 |
+
"step": 13
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.81,
|
| 198 |
+
"eval_accuracy": 0.039979674796747966,
|
| 199 |
+
"eval_loss": 2.685546875,
|
| 200 |
+
"eval_runtime": 5.112,
|
| 201 |
+
"eval_samples_per_second": 19.562,
|
| 202 |
+
"eval_steps_per_second": 0.391,
|
| 203 |
+
"step": 13
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.88,
|
| 207 |
+
"learning_rate": 5e-05,
|
| 208 |
+
"loss": 2.8564,
|
| 209 |
+
"step": 14
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.88,
|
| 213 |
+
"eval_accuracy": 0.039979674796747966,
|
| 214 |
+
"eval_loss": 2.685546875,
|
| 215 |
+
"eval_runtime": 6.1791,
|
| 216 |
+
"eval_samples_per_second": 16.184,
|
| 217 |
+
"eval_steps_per_second": 0.324,
|
| 218 |
+
"step": 14
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.94,
|
| 222 |
+
"learning_rate": 5e-05,
|
| 223 |
+
"loss": 2.8716,
|
| 224 |
+
"step": 15
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.94,
|
| 228 |
+
"eval_accuracy": 0.039979674796747966,
|
| 229 |
+
"eval_loss": 2.685546875,
|
| 230 |
+
"eval_runtime": 6.2221,
|
| 231 |
+
"eval_samples_per_second": 16.072,
|
| 232 |
+
"eval_steps_per_second": 0.321,
|
| 233 |
+
"step": 15
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.0,
|
| 237 |
+
"learning_rate": 5e-05,
|
| 238 |
+
"loss": 2.896,
|
| 239 |
+
"step": 16
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.0,
|
| 243 |
+
"eval_accuracy": 0.03975609756097561,
|
| 244 |
+
"eval_loss": 2.6953125,
|
| 245 |
+
"eval_runtime": 5.7373,
|
| 246 |
+
"eval_samples_per_second": 17.43,
|
| 247 |
+
"eval_steps_per_second": 0.349,
|
| 248 |
+
"step": 16
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.06,
|
| 252 |
+
"learning_rate": 5e-05,
|
| 253 |
+
"loss": 1.9858,
|
| 254 |
+
"step": 17
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.06,
|
| 258 |
+
"eval_accuracy": 0.039979674796747966,
|
| 259 |
+
"eval_loss": 2.70703125,
|
| 260 |
+
"eval_runtime": 5.5135,
|
| 261 |
+
"eval_samples_per_second": 18.137,
|
| 262 |
+
"eval_steps_per_second": 0.363,
|
| 263 |
+
"step": 17
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.12,
|
| 267 |
+
"learning_rate": 5e-05,
|
| 268 |
+
"loss": 2.0563,
|
| 269 |
+
"step": 18
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.12,
|
| 273 |
+
"eval_accuracy": 0.040020325203252036,
|
| 274 |
+
"eval_loss": 2.728515625,
|
| 275 |
+
"eval_runtime": 6.3828,
|
| 276 |
+
"eval_samples_per_second": 15.667,
|
| 277 |
+
"eval_steps_per_second": 0.313,
|
| 278 |
+
"step": 18
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.19,
|
| 282 |
+
"learning_rate": 5e-05,
|
| 283 |
+
"loss": 2.04,
|
| 284 |
+
"step": 19
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.19,
|
| 288 |
+
"eval_accuracy": 0.03981707317073171,
|
| 289 |
+
"eval_loss": 2.767578125,
|
| 290 |
+
"eval_runtime": 5.4095,
|
| 291 |
+
"eval_samples_per_second": 18.486,
|
| 292 |
+
"eval_steps_per_second": 0.37,
|
| 293 |
+
"step": 19
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.25,
|
| 297 |
+
"learning_rate": 5e-05,
|
| 298 |
+
"loss": 1.9885,
|
| 299 |
+
"step": 20
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.25,
|
| 303 |
+
"eval_accuracy": 0.03955284552845528,
|
| 304 |
+
"eval_loss": 2.791015625,
|
| 305 |
+
"eval_runtime": 5.4272,
|
| 306 |
+
"eval_samples_per_second": 18.426,
|
| 307 |
+
"eval_steps_per_second": 0.369,
|
| 308 |
+
"step": 20
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.31,
|
| 312 |
+
"learning_rate": 5e-05,
|
| 313 |
+
"loss": 2.09,
|
| 314 |
+
"step": 21
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.31,
|
| 318 |
+
"eval_accuracy": 0.03930894308943089,
|
| 319 |
+
"eval_loss": 2.796875,
|
| 320 |
+
"eval_runtime": 6.3475,
|
| 321 |
+
"eval_samples_per_second": 15.754,
|
| 322 |
+
"eval_steps_per_second": 0.315,
|
| 323 |
+
"step": 21
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.38,
|
| 327 |
+
"learning_rate": 5e-05,
|
| 328 |
+
"loss": 2.059,
|
| 329 |
+
"step": 22
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.38,
|
| 333 |
+
"eval_accuracy": 0.03951219512195122,
|
| 334 |
+
"eval_loss": 2.810546875,
|
| 335 |
+
"eval_runtime": 6.0188,
|
| 336 |
+
"eval_samples_per_second": 16.615,
|
| 337 |
+
"eval_steps_per_second": 0.332,
|
| 338 |
+
"step": 22
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.44,
|
| 342 |
+
"learning_rate": 5e-05,
|
| 343 |
+
"loss": 2.0498,
|
| 344 |
+
"step": 23
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.44,
|
| 348 |
+
"eval_accuracy": 0.03975609756097561,
|
| 349 |
+
"eval_loss": 2.79296875,
|
| 350 |
+
"eval_runtime": 5.4742,
|
| 351 |
+
"eval_samples_per_second": 18.268,
|
| 352 |
+
"eval_steps_per_second": 0.365,
|
| 353 |
+
"step": 23
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.5,
|
| 357 |
+
"learning_rate": 5e-05,
|
| 358 |
+
"loss": 1.9568,
|
| 359 |
+
"step": 24
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.5,
|
| 363 |
+
"eval_accuracy": 0.04008130081300813,
|
| 364 |
+
"eval_loss": 2.791015625,
|
| 365 |
+
"eval_runtime": 5.9198,
|
| 366 |
+
"eval_samples_per_second": 16.892,
|
| 367 |
+
"eval_steps_per_second": 0.338,
|
| 368 |
+
"step": 24
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.56,
|
| 372 |
+
"learning_rate": 5e-05,
|
| 373 |
+
"loss": 2.1418,
|
| 374 |
+
"step": 25
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.56,
|
| 378 |
+
"eval_accuracy": 0.039776422764227645,
|
| 379 |
+
"eval_loss": 2.79296875,
|
| 380 |
+
"eval_runtime": 5.5505,
|
| 381 |
+
"eval_samples_per_second": 18.016,
|
| 382 |
+
"eval_steps_per_second": 0.36,
|
| 383 |
+
"step": 25
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.62,
|
| 387 |
+
"learning_rate": 5e-05,
|
| 388 |
+
"loss": 1.975,
|
| 389 |
+
"step": 26
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.62,
|
| 393 |
+
"eval_accuracy": 0.03967479674796748,
|
| 394 |
+
"eval_loss": 2.79296875,
|
| 395 |
+
"eval_runtime": 5.108,
|
| 396 |
+
"eval_samples_per_second": 19.577,
|
| 397 |
+
"eval_steps_per_second": 0.392,
|
| 398 |
+
"step": 26
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.69,
|
| 402 |
+
"learning_rate": 5e-05,
|
| 403 |
+
"loss": 1.996,
|
| 404 |
+
"step": 27
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.69,
|
| 408 |
+
"eval_accuracy": 0.03932926829268293,
|
| 409 |
+
"eval_loss": 2.794921875,
|
| 410 |
+
"eval_runtime": 5.1867,
|
| 411 |
+
"eval_samples_per_second": 19.28,
|
| 412 |
+
"eval_steps_per_second": 0.386,
|
| 413 |
+
"step": 27
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.75,
|
| 417 |
+
"learning_rate": 5e-05,
|
| 418 |
+
"loss": 1.9617,
|
| 419 |
+
"step": 28
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.75,
|
| 423 |
+
"eval_accuracy": 0.03916666666666667,
|
| 424 |
+
"eval_loss": 2.8046875,
|
| 425 |
+
"eval_runtime": 5.8792,
|
| 426 |
+
"eval_samples_per_second": 17.009,
|
| 427 |
+
"eval_steps_per_second": 0.34,
|
| 428 |
+
"step": 28
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.81,
|
| 432 |
+
"learning_rate": 5e-05,
|
| 433 |
+
"loss": 2.2062,
|
| 434 |
+
"step": 29
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.81,
|
| 438 |
+
"eval_accuracy": 0.038760162601626014,
|
| 439 |
+
"eval_loss": 2.814453125,
|
| 440 |
+
"eval_runtime": 5.1614,
|
| 441 |
+
"eval_samples_per_second": 19.375,
|
| 442 |
+
"eval_steps_per_second": 0.387,
|
| 443 |
+
"step": 29
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.88,
|
| 447 |
+
"learning_rate": 5e-05,
|
| 448 |
+
"loss": 1.9929,
|
| 449 |
+
"step": 30
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.88,
|
| 453 |
+
"eval_accuracy": 0.038597560975609756,
|
| 454 |
+
"eval_loss": 2.814453125,
|
| 455 |
+
"eval_runtime": 5.7986,
|
| 456 |
+
"eval_samples_per_second": 17.245,
|
| 457 |
+
"eval_steps_per_second": 0.345,
|
| 458 |
+
"step": 30
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.94,
|
| 462 |
+
"learning_rate": 5e-05,
|
| 463 |
+
"loss": 1.9235,
|
| 464 |
+
"step": 31
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.94,
|
| 468 |
+
"eval_accuracy": 0.039004065040650404,
|
| 469 |
+
"eval_loss": 2.828125,
|
| 470 |
+
"eval_runtime": 6.2602,
|
| 471 |
+
"eval_samples_per_second": 15.974,
|
| 472 |
+
"eval_steps_per_second": 0.319,
|
| 473 |
+
"step": 31
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.0,
|
| 477 |
+
"learning_rate": 5e-05,
|
| 478 |
+
"loss": 1.9127,
|
| 479 |
+
"step": 32
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.0,
|
| 483 |
+
"eval_accuracy": 0.03882113821138211,
|
| 484 |
+
"eval_loss": 2.857421875,
|
| 485 |
+
"eval_runtime": 5.5269,
|
| 486 |
+
"eval_samples_per_second": 18.093,
|
| 487 |
+
"eval_steps_per_second": 0.362,
|
| 488 |
+
"step": 32
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.0,
|
| 492 |
+
"step": 32,
|
| 493 |
+
"total_flos": 10341801000960.0,
|
| 494 |
+
"train_loss": 2.4493942260742188,
|
| 495 |
+
"train_runtime": 515.1457,
|
| 496 |
+
"train_samples_per_second": 3.882,
|
| 497 |
+
"train_steps_per_second": 0.062
|
| 498 |
+
}
|
| 499 |
+
],
|
| 500 |
+
"max_steps": 32,
|
| 501 |
+
"num_train_epochs": 2,
|
| 502 |
+
"total_flos": 10341801000960.0,
|
| 503 |
+
"trial_name": null,
|
| 504 |
+
"trial_params": null
|
| 505 |
+
}
|