Commit ·
c15d8c9
1
Parent(s): 12051d0
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.1218645572662354,
|
| 4 |
+
"eval_runtime": 157.5371,
|
| 5 |
+
"eval_samples": 5000,
|
| 6 |
+
"eval_samples_per_second": 31.739,
|
| 7 |
+
"eval_steps_per_second": 15.869,
|
| 8 |
+
"train_loss": 2.348203765869141,
|
| 9 |
+
"train_runtime": 5753.6194,
|
| 10 |
+
"train_samples": 20000,
|
| 11 |
+
"train_samples_per_second": 3.476,
|
| 12 |
+
"train_steps_per_second": 1.738
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.1218645572662354,
|
| 4 |
+
"eval_runtime": 157.5371,
|
| 5 |
+
"eval_samples": 5000,
|
| 6 |
+
"eval_samples_per_second": 31.739,
|
| 7 |
+
"eval_steps_per_second": 15.869
|
| 8 |
+
}
|
runs/Dec03_23-21-17_ba6bd7ea695a/events.out.tfevents.1670118673.ba6bd7ea695a.253.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:922a1a420f36d1e4d87f8e44ab3791d720cd25ddf77e71074b8e81245bb63786
|
| 3 |
+
size 311
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 2.348203765869141,
|
| 4 |
+
"train_runtime": 5753.6194,
|
| 5 |
+
"train_samples": 20000,
|
| 6 |
+
"train_samples_per_second": 3.476,
|
| 7 |
+
"train_steps_per_second": 1.738
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,225 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 10000,
|
| 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": 9.693877551020408e-06,
|
| 13 |
+
"loss": 3.9702,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 9.183673469387756e-06,
|
| 19 |
+
"loss": 2.878,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"eval_loss": 2.5845324993133545,
|
| 25 |
+
"eval_runtime": 157.5682,
|
| 26 |
+
"eval_samples_per_second": 31.732,
|
| 27 |
+
"eval_steps_per_second": 15.866,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.15,
|
| 32 |
+
"learning_rate": 8.673469387755103e-06,
|
| 33 |
+
"loss": 2.63,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.2,
|
| 38 |
+
"learning_rate": 8.16326530612245e-06,
|
| 39 |
+
"loss": 2.5583,
|
| 40 |
+
"step": 2000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.2,
|
| 44 |
+
"eval_loss": 2.420644760131836,
|
| 45 |
+
"eval_runtime": 157.2633,
|
| 46 |
+
"eval_samples_per_second": 31.794,
|
| 47 |
+
"eval_steps_per_second": 15.897,
|
| 48 |
+
"step": 2000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.25,
|
| 52 |
+
"learning_rate": 7.653061224489796e-06,
|
| 53 |
+
"loss": 2.4798,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.3,
|
| 58 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 59 |
+
"loss": 2.3887,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.3,
|
| 64 |
+
"eval_loss": 2.3397743701934814,
|
| 65 |
+
"eval_runtime": 157.3422,
|
| 66 |
+
"eval_samples_per_second": 31.778,
|
| 67 |
+
"eval_steps_per_second": 15.889,
|
| 68 |
+
"step": 3000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.35,
|
| 72 |
+
"learning_rate": 6.63265306122449e-06,
|
| 73 |
+
"loss": 2.3793,
|
| 74 |
+
"step": 3500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.4,
|
| 78 |
+
"learning_rate": 6.122448979591837e-06,
|
| 79 |
+
"loss": 2.244,
|
| 80 |
+
"step": 4000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.4,
|
| 84 |
+
"eval_loss": 2.285295248031616,
|
| 85 |
+
"eval_runtime": 157.1868,
|
| 86 |
+
"eval_samples_per_second": 31.809,
|
| 87 |
+
"eval_steps_per_second": 15.905,
|
| 88 |
+
"step": 4000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.45,
|
| 92 |
+
"learning_rate": 5.6122448979591834e-06,
|
| 93 |
+
"loss": 2.265,
|
| 94 |
+
"step": 4500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5,
|
| 98 |
+
"learning_rate": 5.1020408163265315e-06,
|
| 99 |
+
"loss": 2.2182,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5,
|
| 104 |
+
"eval_loss": 2.235461711883545,
|
| 105 |
+
"eval_runtime": 157.7693,
|
| 106 |
+
"eval_samples_per_second": 31.692,
|
| 107 |
+
"eval_steps_per_second": 15.846,
|
| 108 |
+
"step": 5000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.55,
|
| 112 |
+
"learning_rate": 4.591836734693878e-06,
|
| 113 |
+
"loss": 2.1425,
|
| 114 |
+
"step": 5500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6,
|
| 118 |
+
"learning_rate": 4.081632653061225e-06,
|
| 119 |
+
"loss": 2.1509,
|
| 120 |
+
"step": 6000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.6,
|
| 124 |
+
"eval_loss": 2.1871836185455322,
|
| 125 |
+
"eval_runtime": 158.3077,
|
| 126 |
+
"eval_samples_per_second": 31.584,
|
| 127 |
+
"eval_steps_per_second": 15.792,
|
| 128 |
+
"step": 6000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.65,
|
| 132 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 133 |
+
"loss": 2.1598,
|
| 134 |
+
"step": 6500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.7,
|
| 138 |
+
"learning_rate": 3.0612244897959185e-06,
|
| 139 |
+
"loss": 2.0912,
|
| 140 |
+
"step": 7000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.7,
|
| 144 |
+
"eval_loss": 2.158203601837158,
|
| 145 |
+
"eval_runtime": 157.8036,
|
| 146 |
+
"eval_samples_per_second": 31.685,
|
| 147 |
+
"eval_steps_per_second": 15.842,
|
| 148 |
+
"step": 7000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.75,
|
| 152 |
+
"learning_rate": 2.5510204081632657e-06,
|
| 153 |
+
"loss": 2.12,
|
| 154 |
+
"step": 7500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.8,
|
| 158 |
+
"learning_rate": 2.0408163265306125e-06,
|
| 159 |
+
"loss": 2.1208,
|
| 160 |
+
"step": 8000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.8,
|
| 164 |
+
"eval_loss": 2.143484354019165,
|
| 165 |
+
"eval_runtime": 157.8874,
|
| 166 |
+
"eval_samples_per_second": 31.668,
|
| 167 |
+
"eval_steps_per_second": 15.834,
|
| 168 |
+
"step": 8000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.85,
|
| 172 |
+
"learning_rate": 1.5306122448979593e-06,
|
| 173 |
+
"loss": 2.06,
|
| 174 |
+
"step": 8500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.9,
|
| 178 |
+
"learning_rate": 1.0204081632653063e-06,
|
| 179 |
+
"loss": 2.0248,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.9,
|
| 184 |
+
"eval_loss": 2.1309216022491455,
|
| 185 |
+
"eval_runtime": 157.5406,
|
| 186 |
+
"eval_samples_per_second": 31.738,
|
| 187 |
+
"eval_steps_per_second": 15.869,
|
| 188 |
+
"step": 9000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.95,
|
| 192 |
+
"learning_rate": 5.102040816326531e-07,
|
| 193 |
+
"loss": 2.0431,
|
| 194 |
+
"step": 9500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.0,
|
| 198 |
+
"learning_rate": 0.0,
|
| 199 |
+
"loss": 2.0394,
|
| 200 |
+
"step": 10000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.0,
|
| 204 |
+
"eval_loss": 2.1218645572662354,
|
| 205 |
+
"eval_runtime": 158.0316,
|
| 206 |
+
"eval_samples_per_second": 31.639,
|
| 207 |
+
"eval_steps_per_second": 15.82,
|
| 208 |
+
"step": 10000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.0,
|
| 212 |
+
"step": 10000,
|
| 213 |
+
"total_flos": 1465576441823232.0,
|
| 214 |
+
"train_loss": 2.348203765869141,
|
| 215 |
+
"train_runtime": 5753.6194,
|
| 216 |
+
"train_samples_per_second": 3.476,
|
| 217 |
+
"train_steps_per_second": 1.738
|
| 218 |
+
}
|
| 219 |
+
],
|
| 220 |
+
"max_steps": 10000,
|
| 221 |
+
"num_train_epochs": 1,
|
| 222 |
+
"total_flos": 1465576441823232.0,
|
| 223 |
+
"trial_name": null,
|
| 224 |
+
"trial_params": null
|
| 225 |
+
}
|