Commit ·
12eda73
1
Parent(s): e921504
End of training
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Jun14_12-22-13_labgpu/events.out.tfevents.1655218507.labgpu.15532.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +193 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.5,
|
| 3 |
+
"eval_accuracy": 0.8988869651249073,
|
| 4 |
+
"eval_combined_score": 0.8829459876050719,
|
| 5 |
+
"eval_f1": 0.8670050100852366,
|
| 6 |
+
"eval_loss": 0.24575121700763702,
|
| 7 |
+
"eval_runtime": 221.9991,
|
| 8 |
+
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 182.118,
|
| 10 |
+
"eval_steps_per_second": 22.766,
|
| 11 |
+
"train_loss": 1386.6627225032541,
|
| 12 |
+
"train_runtime": 8097.4527,
|
| 13 |
+
"train_samples": 363846,
|
| 14 |
+
"train_samples_per_second": 112.333,
|
| 15 |
+
"train_steps_per_second": 1.755
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.5,
|
| 3 |
+
"eval_accuracy": 0.8988869651249073,
|
| 4 |
+
"eval_combined_score": 0.8829459876050719,
|
| 5 |
+
"eval_f1": 0.8670050100852366,
|
| 6 |
+
"eval_loss": 0.24575121700763702,
|
| 7 |
+
"eval_runtime": 221.9991,
|
| 8 |
+
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 182.118,
|
| 10 |
+
"eval_steps_per_second": 22.766
|
| 11 |
+
}
|
runs/Jun14_12-22-13_labgpu/events.out.tfevents.1655218507.labgpu.15532.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73524705d05d452b3550b909b123997f6b11a71036694e3399eb38cf091d0423
|
| 3 |
+
size 467
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.5,
|
| 3 |
+
"train_loss": 1386.6627225032541,
|
| 4 |
+
"train_runtime": 8097.4527,
|
| 5 |
+
"train_samples": 363846,
|
| 6 |
+
"train_samples_per_second": 112.333,
|
| 7 |
+
"train_steps_per_second": 1.755
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.5,
|
| 5 |
+
"global_step": 14215,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 4.8241294407316215e-05,
|
| 13 |
+
"loss": 39415.716,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 4.6482588814632434e-05,
|
| 19 |
+
"loss": 0.3762,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.26,
|
| 24 |
+
"learning_rate": 4.472388322194865e-05,
|
| 25 |
+
"loss": 0.4107,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.35,
|
| 30 |
+
"learning_rate": 4.2965177629264866e-05,
|
| 31 |
+
"loss": 0.3225,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.44,
|
| 36 |
+
"learning_rate": 4.120647203658108e-05,
|
| 37 |
+
"loss": 0.3177,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.53,
|
| 42 |
+
"learning_rate": 3.944776644389729e-05,
|
| 43 |
+
"loss": 0.2994,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.62,
|
| 48 |
+
"learning_rate": 3.768906085121351e-05,
|
| 49 |
+
"loss": 0.3909,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.7,
|
| 54 |
+
"learning_rate": 3.5930355258529723e-05,
|
| 55 |
+
"loss": 0.2921,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.79,
|
| 60 |
+
"learning_rate": 3.417164966584594e-05,
|
| 61 |
+
"loss": 0.279,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.88,
|
| 66 |
+
"learning_rate": 3.2412944073162155e-05,
|
| 67 |
+
"loss": 0.2796,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.97,
|
| 72 |
+
"learning_rate": 3.065423848047837e-05,
|
| 73 |
+
"loss": 0.2694,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.06,
|
| 78 |
+
"learning_rate": 2.8895532887794584e-05,
|
| 79 |
+
"loss": 0.2447,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.14,
|
| 84 |
+
"learning_rate": 2.71368272951108e-05,
|
| 85 |
+
"loss": 0.234,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.23,
|
| 90 |
+
"learning_rate": 2.5378121702427016e-05,
|
| 91 |
+
"loss": 0.2273,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.32,
|
| 96 |
+
"learning_rate": 2.3619416109743232e-05,
|
| 97 |
+
"loss": 0.2558,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.41,
|
| 102 |
+
"learning_rate": 2.1860710517059448e-05,
|
| 103 |
+
"loss": 0.2255,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.49,
|
| 108 |
+
"learning_rate": 2.010200492437566e-05,
|
| 109 |
+
"loss": 0.2263,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.58,
|
| 114 |
+
"learning_rate": 1.8343299331691876e-05,
|
| 115 |
+
"loss": 0.2825,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.67,
|
| 120 |
+
"learning_rate": 1.6584593739008092e-05,
|
| 121 |
+
"loss": 0.2196,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.76,
|
| 126 |
+
"learning_rate": 1.4825888146324307e-05,
|
| 127 |
+
"loss": 0.2178,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.85,
|
| 132 |
+
"learning_rate": 1.3067182553640523e-05,
|
| 133 |
+
"loss": 0.2175,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.93,
|
| 138 |
+
"learning_rate": 1.1308476960956737e-05,
|
| 139 |
+
"loss": 0.2177,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.02,
|
| 144 |
+
"learning_rate": 9.549771368272951e-06,
|
| 145 |
+
"loss": 0.2053,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.11,
|
| 150 |
+
"learning_rate": 7.791065775589167e-06,
|
| 151 |
+
"loss": 0.3079,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.2,
|
| 156 |
+
"learning_rate": 6.032360182905382e-06,
|
| 157 |
+
"loss": 0.1813,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.29,
|
| 162 |
+
"learning_rate": 4.2736545902215974e-06,
|
| 163 |
+
"loss": 0.1804,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.37,
|
| 168 |
+
"learning_rate": 2.5149489975378126e-06,
|
| 169 |
+
"loss": 0.1771,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.46,
|
| 174 |
+
"learning_rate": 7.562434048540275e-07,
|
| 175 |
+
"loss": 0.1697,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.5,
|
| 180 |
+
"step": 14215,
|
| 181 |
+
"total_flos": 1.426060746003456e+16,
|
| 182 |
+
"train_loss": 1386.6627225032541,
|
| 183 |
+
"train_runtime": 8097.4527,
|
| 184 |
+
"train_samples_per_second": 112.333,
|
| 185 |
+
"train_steps_per_second": 1.755
|
| 186 |
+
}
|
| 187 |
+
],
|
| 188 |
+
"max_steps": 14215,
|
| 189 |
+
"num_train_epochs": 3,
|
| 190 |
+
"total_flos": 1.426060746003456e+16,
|
| 191 |
+
"trial_name": null,
|
| 192 |
+
"trial_params": null
|
| 193 |
+
}
|