Training in progress, epoch 1
Browse files- all_results.json +14 -14
- eval_results.json +9 -9
- pytorch_model.bin +1 -1
- runs/Oct27_22-15-51_EE4E077/events.out.tfevents.1698417528.EE4E077.103115.11 +3 -0
- runs/Oct28_14-32-10_EE4E077/1698474732.9403577/events.out.tfevents.1698474732.EE4E077.316238.4 +3 -0
- runs/Oct28_14-32-10_EE4E077/events.out.tfevents.1698474732.EE4E077.316238.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +417 -93
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 10.
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 18.
|
| 11 |
-
"total_flos":
|
| 12 |
-
"train_loss": 0.
|
| 13 |
-
"train_runtime":
|
| 14 |
-
"train_samples_per_second":
|
| 15 |
-
"train_steps_per_second": 2.
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"eval_accuracy": 0.7936507936507936,
|
| 4 |
+
"eval_f1": 0.7835889985346738,
|
| 5 |
+
"eval_loss": 0.8658342361450195,
|
| 6 |
+
"eval_precision": 0.7871091627862145,
|
| 7 |
+
"eval_recall": 0.7936507936507936,
|
| 8 |
+
"eval_runtime": 10.1227,
|
| 9 |
+
"eval_samples_per_second": 149.367,
|
| 10 |
+
"eval_steps_per_second": 18.671,
|
| 11 |
+
"total_flos": 4.65670232933972e+18,
|
| 12 |
+
"train_loss": 0.08256206865654514,
|
| 13 |
+
"train_runtime": 1281.0434,
|
| 14 |
+
"train_samples_per_second": 46.907,
|
| 15 |
+
"train_steps_per_second": 2.932
|
| 16 |
}
|
eval_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 10.
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 18.
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"eval_accuracy": 0.7936507936507936,
|
| 4 |
+
"eval_f1": 0.7835889985346738,
|
| 5 |
+
"eval_loss": 0.8658342361450195,
|
| 6 |
+
"eval_precision": 0.7871091627862145,
|
| 7 |
+
"eval_recall": 0.7936507936507936,
|
| 8 |
+
"eval_runtime": 10.1227,
|
| 9 |
+
"eval_samples_per_second": 149.367,
|
| 10 |
+
"eval_steps_per_second": 18.671
|
| 11 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343284077
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b40294c6f0c3d75ff4e234d0988917afeb994bc1a11260eda81b3c699f1da944
|
| 3 |
size 343284077
|
runs/Oct27_22-15-51_EE4E077/events.out.tfevents.1698417528.EE4E077.103115.11
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e803cfe837b8cd4a2307dae00863c71a3b495cab291c1a333d621d8ffdc74972
|
| 3 |
+
size 560
|
runs/Oct28_14-32-10_EE4E077/1698474732.9403577/events.out.tfevents.1698474732.EE4E077.316238.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca4951d7e3c2a69382754eabb6317043f0de4de012b8e89d3f297488fe8dec50
|
| 3 |
+
size 5919
|
runs/Oct28_14-32-10_EE4E077/events.out.tfevents.1698474732.EE4E077.316238.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1e4778eed05fd65b2062c89924b6b893b340c4734f918166770d1b45ffd1fe5
|
| 3 |
+
size 6598
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"total_flos": 4.65670232933972e+18,
|
| 4 |
+
"train_loss": 0.08256206865654514,
|
| 5 |
+
"train_runtime": 1281.0434,
|
| 6 |
+
"train_samples_per_second": 46.907,
|
| 7 |
+
"train_steps_per_second": 2.932
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,223 +1,547 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.8704663212435233,
|
| 3 |
-
"best_model_checkpoint": "./vit-focal-skin/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.16,
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 100
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
{
|
| 17 |
"epoch": 0.32,
|
| 18 |
-
"learning_rate": 0.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 200
|
| 21 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
{
|
| 23 |
"epoch": 0.48,
|
| 24 |
-
"learning_rate": 0.
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 300
|
| 27 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
{
|
| 29 |
"epoch": 0.64,
|
| 30 |
-
"learning_rate": 0.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 400
|
| 33 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
{
|
| 35 |
"epoch": 0.8,
|
| 36 |
-
"learning_rate": 0.
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 500
|
| 39 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
{
|
| 41 |
"epoch": 0.96,
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 600
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 1.0,
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_f1": 0.
|
| 50 |
-
"eval_loss": 0.
|
| 51 |
-
"eval_precision": 0.
|
| 52 |
-
"eval_recall": 0.
|
| 53 |
-
"eval_runtime": 1.
|
| 54 |
-
"eval_samples_per_second":
|
| 55 |
-
"eval_steps_per_second":
|
| 56 |
"step": 626
|
| 57 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
{
|
| 59 |
"epoch": 1.12,
|
| 60 |
-
"learning_rate": 0.
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 700
|
| 63 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
{
|
| 65 |
"epoch": 1.28,
|
| 66 |
-
"learning_rate": 0.
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 800
|
| 69 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
{
|
| 71 |
"epoch": 1.44,
|
| 72 |
-
"learning_rate": 0.
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 900
|
| 75 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
{
|
| 77 |
"epoch": 1.6,
|
| 78 |
-
"learning_rate": 0.
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 1000
|
| 81 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
{
|
| 83 |
"epoch": 1.76,
|
| 84 |
-
"learning_rate": 0.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 1100
|
| 87 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
{
|
| 89 |
"epoch": 1.92,
|
| 90 |
-
"learning_rate": 0.
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 1200
|
| 93 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
{
|
| 95 |
"epoch": 2.0,
|
| 96 |
"eval_accuracy": 0.8238341968911918,
|
| 97 |
-
"eval_f1": 0.
|
| 98 |
-
"eval_loss": 0.
|
| 99 |
-
"eval_precision": 0.
|
| 100 |
"eval_recall": 0.8238341968911918,
|
| 101 |
-
"eval_runtime": 1.
|
| 102 |
-
"eval_samples_per_second":
|
| 103 |
-
"eval_steps_per_second": 17.
|
| 104 |
"step": 1252
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 2.08,
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 1300
|
| 111 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 112 |
{
|
| 113 |
"epoch": 2.24,
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 1400
|
| 117 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
{
|
| 119 |
"epoch": 2.4,
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 1500
|
| 123 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
{
|
| 125 |
"epoch": 2.56,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 1600
|
| 129 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 130 |
{
|
| 131 |
"epoch": 2.72,
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 1700
|
| 135 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
{
|
| 137 |
"epoch": 2.88,
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss": 0.
|
| 140 |
"step": 1800
|
| 141 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 142 |
{
|
| 143 |
"epoch": 3.0,
|
| 144 |
-
"eval_accuracy": 0.
|
| 145 |
-
"eval_f1": 0.
|
| 146 |
-
"eval_loss": 0.
|
| 147 |
-
"eval_precision": 0.
|
| 148 |
-
"eval_recall": 0.
|
| 149 |
-
"eval_runtime": 1.
|
| 150 |
-
"eval_samples_per_second": 130.
|
| 151 |
-
"eval_steps_per_second": 16.
|
| 152 |
"step": 1878
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 3.04,
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 1900
|
| 159 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 160 |
{
|
| 161 |
"epoch": 3.19,
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 2000
|
| 165 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
{
|
| 167 |
"epoch": 3.35,
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 2100
|
| 171 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 172 |
{
|
| 173 |
"epoch": 3.51,
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 2200
|
| 177 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 178 |
{
|
| 179 |
"epoch": 3.67,
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 2300
|
| 183 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 184 |
{
|
| 185 |
"epoch": 3.83,
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 2400
|
| 189 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 190 |
{
|
| 191 |
"epoch": 3.99,
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 2500
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 4.0,
|
| 198 |
-
"eval_accuracy": 0.
|
| 199 |
-
"eval_f1": 0.
|
| 200 |
-
"eval_loss": 0.
|
| 201 |
-
"eval_precision": 0.
|
| 202 |
-
"eval_recall": 0.
|
| 203 |
-
"eval_runtime": 1.
|
| 204 |
-
"eval_samples_per_second": 128.
|
| 205 |
-
"eval_steps_per_second": 16.
|
| 206 |
"step": 2504
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch": 4.
|
| 210 |
-
"
|
| 211 |
-
"
|
| 212 |
-
"
|
| 213 |
-
|
| 214 |
-
|
| 215 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 216 |
}
|
| 217 |
],
|
| 218 |
-
"max_steps":
|
| 219 |
-
"num_train_epochs":
|
| 220 |
-
"total_flos":
|
| 221 |
"trial_name": null,
|
| 222 |
"trial_params": null
|
| 223 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.8704663212435233,
|
| 3 |
+
"best_model_checkpoint": "./vit-focal-skin/checkpoint-3130",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 3756,
|
| 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": 0.00019733759318423856,
|
| 13 |
+
"loss": 0.325,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
{
|
| 17 |
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 0.0001946751863684771,
|
| 19 |
+
"loss": 0.2897,
|
| 20 |
"step": 100
|
| 21 |
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.24,
|
| 24 |
+
"learning_rate": 0.00019201277955271565,
|
| 25 |
+
"loss": 0.2508,
|
| 26 |
+
"step": 150
|
| 27 |
+
},
|
| 28 |
{
|
| 29 |
"epoch": 0.32,
|
| 30 |
+
"learning_rate": 0.00018935037273695422,
|
| 31 |
+
"loss": 0.2626,
|
| 32 |
"step": 200
|
| 33 |
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.4,
|
| 36 |
+
"learning_rate": 0.00018668796592119277,
|
| 37 |
+
"loss": 0.2308,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
{
|
| 41 |
"epoch": 0.48,
|
| 42 |
+
"learning_rate": 0.00018402555910543132,
|
| 43 |
+
"loss": 0.2437,
|
| 44 |
"step": 300
|
| 45 |
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.56,
|
| 48 |
+
"learning_rate": 0.00018136315228966987,
|
| 49 |
+
"loss": 0.2594,
|
| 50 |
+
"step": 350
|
| 51 |
+
},
|
| 52 |
{
|
| 53 |
"epoch": 0.64,
|
| 54 |
+
"learning_rate": 0.0001787007454739084,
|
| 55 |
+
"loss": 0.2355,
|
| 56 |
"step": 400
|
| 57 |
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.72,
|
| 60 |
+
"learning_rate": 0.000176038338658147,
|
| 61 |
+
"loss": 0.2457,
|
| 62 |
+
"step": 450
|
| 63 |
+
},
|
| 64 |
{
|
| 65 |
"epoch": 0.8,
|
| 66 |
+
"learning_rate": 0.0001733759318423855,
|
| 67 |
+
"loss": 0.2136,
|
| 68 |
"step": 500
|
| 69 |
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.88,
|
| 72 |
+
"learning_rate": 0.00017071352502662408,
|
| 73 |
+
"loss": 0.2622,
|
| 74 |
+
"step": 550
|
| 75 |
+
},
|
| 76 |
{
|
| 77 |
"epoch": 0.96,
|
| 78 |
+
"learning_rate": 0.00016805111821086263,
|
| 79 |
+
"loss": 0.1966,
|
| 80 |
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 1.0,
|
| 84 |
+
"eval_accuracy": 0.8290155440414507,
|
| 85 |
+
"eval_f1": 0.8306733167328754,
|
| 86 |
+
"eval_loss": 0.3647349774837494,
|
| 87 |
+
"eval_precision": 0.8430511449105799,
|
| 88 |
+
"eval_recall": 0.8290155440414507,
|
| 89 |
+
"eval_runtime": 1.4278,
|
| 90 |
+
"eval_samples_per_second": 135.17,
|
| 91 |
+
"eval_steps_per_second": 17.509,
|
| 92 |
"step": 626
|
| 93 |
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.04,
|
| 96 |
+
"learning_rate": 0.00016538871139510118,
|
| 97 |
+
"loss": 0.1998,
|
| 98 |
+
"step": 650
|
| 99 |
+
},
|
| 100 |
{
|
| 101 |
"epoch": 1.12,
|
| 102 |
+
"learning_rate": 0.00016272630457933972,
|
| 103 |
+
"loss": 0.1312,
|
| 104 |
"step": 700
|
| 105 |
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.2,
|
| 108 |
+
"learning_rate": 0.0001600638977635783,
|
| 109 |
+
"loss": 0.1477,
|
| 110 |
+
"step": 750
|
| 111 |
+
},
|
| 112 |
{
|
| 113 |
"epoch": 1.28,
|
| 114 |
+
"learning_rate": 0.00015740149094781684,
|
| 115 |
+
"loss": 0.1155,
|
| 116 |
"step": 800
|
| 117 |
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.36,
|
| 120 |
+
"learning_rate": 0.0001547390841320554,
|
| 121 |
+
"loss": 0.1591,
|
| 122 |
+
"step": 850
|
| 123 |
+
},
|
| 124 |
{
|
| 125 |
"epoch": 1.44,
|
| 126 |
+
"learning_rate": 0.00015207667731629394,
|
| 127 |
+
"loss": 0.1568,
|
| 128 |
"step": 900
|
| 129 |
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.52,
|
| 132 |
+
"learning_rate": 0.00014941427050053249,
|
| 133 |
+
"loss": 0.1322,
|
| 134 |
+
"step": 950
|
| 135 |
+
},
|
| 136 |
{
|
| 137 |
"epoch": 1.6,
|
| 138 |
+
"learning_rate": 0.00014675186368477103,
|
| 139 |
+
"loss": 0.1478,
|
| 140 |
"step": 1000
|
| 141 |
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.68,
|
| 144 |
+
"learning_rate": 0.00014408945686900958,
|
| 145 |
+
"loss": 0.1145,
|
| 146 |
+
"step": 1050
|
| 147 |
+
},
|
| 148 |
{
|
| 149 |
"epoch": 1.76,
|
| 150 |
+
"learning_rate": 0.00014142705005324815,
|
| 151 |
+
"loss": 0.1483,
|
| 152 |
"step": 1100
|
| 153 |
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.84,
|
| 156 |
+
"learning_rate": 0.0001387646432374867,
|
| 157 |
+
"loss": 0.1517,
|
| 158 |
+
"step": 1150
|
| 159 |
+
},
|
| 160 |
{
|
| 161 |
"epoch": 1.92,
|
| 162 |
+
"learning_rate": 0.00013610223642172525,
|
| 163 |
+
"loss": 0.1294,
|
| 164 |
"step": 1200
|
| 165 |
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.0,
|
| 168 |
+
"learning_rate": 0.0001334398296059638,
|
| 169 |
+
"loss": 0.1434,
|
| 170 |
+
"step": 1250
|
| 171 |
+
},
|
| 172 |
{
|
| 173 |
"epoch": 2.0,
|
| 174 |
"eval_accuracy": 0.8238341968911918,
|
| 175 |
+
"eval_f1": 0.825913518485432,
|
| 176 |
+
"eval_loss": 0.38836923241615295,
|
| 177 |
+
"eval_precision": 0.8418087741274269,
|
| 178 |
"eval_recall": 0.8238341968911918,
|
| 179 |
+
"eval_runtime": 1.4008,
|
| 180 |
+
"eval_samples_per_second": 137.782,
|
| 181 |
+
"eval_steps_per_second": 17.847,
|
| 182 |
"step": 1252
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 2.08,
|
| 186 |
+
"learning_rate": 0.00013077742279020234,
|
| 187 |
+
"loss": 0.0846,
|
| 188 |
"step": 1300
|
| 189 |
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.16,
|
| 192 |
+
"learning_rate": 0.00012811501597444092,
|
| 193 |
+
"loss": 0.0635,
|
| 194 |
+
"step": 1350
|
| 195 |
+
},
|
| 196 |
{
|
| 197 |
"epoch": 2.24,
|
| 198 |
+
"learning_rate": 0.00012545260915867944,
|
| 199 |
+
"loss": 0.0466,
|
| 200 |
"step": 1400
|
| 201 |
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.32,
|
| 204 |
+
"learning_rate": 0.000122790202342918,
|
| 205 |
+
"loss": 0.0757,
|
| 206 |
+
"step": 1450
|
| 207 |
+
},
|
| 208 |
{
|
| 209 |
"epoch": 2.4,
|
| 210 |
+
"learning_rate": 0.00012012779552715656,
|
| 211 |
+
"loss": 0.0996,
|
| 212 |
"step": 1500
|
| 213 |
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.48,
|
| 216 |
+
"learning_rate": 0.00011746538871139509,
|
| 217 |
+
"loss": 0.089,
|
| 218 |
+
"step": 1550
|
| 219 |
+
},
|
| 220 |
{
|
| 221 |
"epoch": 2.56,
|
| 222 |
+
"learning_rate": 0.00011480298189563365,
|
| 223 |
+
"loss": 0.0679,
|
| 224 |
"step": 1600
|
| 225 |
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.64,
|
| 228 |
+
"learning_rate": 0.00011214057507987221,
|
| 229 |
+
"loss": 0.0747,
|
| 230 |
+
"step": 1650
|
| 231 |
+
},
|
| 232 |
{
|
| 233 |
"epoch": 2.72,
|
| 234 |
+
"learning_rate": 0.00010947816826411077,
|
| 235 |
+
"loss": 0.066,
|
| 236 |
"step": 1700
|
| 237 |
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.8,
|
| 240 |
+
"learning_rate": 0.0001068157614483493,
|
| 241 |
+
"loss": 0.0714,
|
| 242 |
+
"step": 1750
|
| 243 |
+
},
|
| 244 |
{
|
| 245 |
"epoch": 2.88,
|
| 246 |
+
"learning_rate": 0.00010415335463258787,
|
| 247 |
+
"loss": 0.0776,
|
| 248 |
"step": 1800
|
| 249 |
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.96,
|
| 252 |
+
"learning_rate": 0.00010149094781682643,
|
| 253 |
+
"loss": 0.058,
|
| 254 |
+
"step": 1850
|
| 255 |
+
},
|
| 256 |
{
|
| 257 |
"epoch": 3.0,
|
| 258 |
+
"eval_accuracy": 0.8186528497409327,
|
| 259 |
+
"eval_f1": 0.8136687258538028,
|
| 260 |
+
"eval_loss": 0.5063741207122803,
|
| 261 |
+
"eval_precision": 0.8183198316271921,
|
| 262 |
+
"eval_recall": 0.8186528497409327,
|
| 263 |
+
"eval_runtime": 1.4832,
|
| 264 |
+
"eval_samples_per_second": 130.125,
|
| 265 |
+
"eval_steps_per_second": 16.856,
|
| 266 |
"step": 1878
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 3.04,
|
| 270 |
+
"learning_rate": 9.882854100106496e-05,
|
| 271 |
+
"loss": 0.0361,
|
| 272 |
"step": 1900
|
| 273 |
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.12,
|
| 276 |
+
"learning_rate": 9.616613418530351e-05,
|
| 277 |
+
"loss": 0.0305,
|
| 278 |
+
"step": 1950
|
| 279 |
+
},
|
| 280 |
{
|
| 281 |
"epoch": 3.19,
|
| 282 |
+
"learning_rate": 9.350372736954207e-05,
|
| 283 |
+
"loss": 0.0224,
|
| 284 |
"step": 2000
|
| 285 |
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.27,
|
| 288 |
+
"learning_rate": 9.084132055378062e-05,
|
| 289 |
+
"loss": 0.0186,
|
| 290 |
+
"step": 2050
|
| 291 |
+
},
|
| 292 |
{
|
| 293 |
"epoch": 3.35,
|
| 294 |
+
"learning_rate": 8.817891373801918e-05,
|
| 295 |
+
"loss": 0.0138,
|
| 296 |
"step": 2100
|
| 297 |
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.43,
|
| 300 |
+
"learning_rate": 8.556975505857295e-05,
|
| 301 |
+
"loss": 0.0344,
|
| 302 |
+
"step": 2150
|
| 303 |
+
},
|
| 304 |
{
|
| 305 |
"epoch": 3.51,
|
| 306 |
+
"learning_rate": 8.29073482428115e-05,
|
| 307 |
+
"loss": 0.0158,
|
| 308 |
"step": 2200
|
| 309 |
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.59,
|
| 312 |
+
"learning_rate": 8.029818956336529e-05,
|
| 313 |
+
"loss": 0.0557,
|
| 314 |
+
"step": 2250
|
| 315 |
+
},
|
| 316 |
{
|
| 317 |
"epoch": 3.67,
|
| 318 |
+
"learning_rate": 7.763578274760383e-05,
|
| 319 |
+
"loss": 0.0409,
|
| 320 |
"step": 2300
|
| 321 |
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.75,
|
| 324 |
+
"learning_rate": 7.49733759318424e-05,
|
| 325 |
+
"loss": 0.0374,
|
| 326 |
+
"step": 2350
|
| 327 |
+
},
|
| 328 |
{
|
| 329 |
"epoch": 3.83,
|
| 330 |
+
"learning_rate": 7.231096911608094e-05,
|
| 331 |
+
"loss": 0.0301,
|
| 332 |
"step": 2400
|
| 333 |
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.91,
|
| 336 |
+
"learning_rate": 6.96485623003195e-05,
|
| 337 |
+
"loss": 0.02,
|
| 338 |
+
"step": 2450
|
| 339 |
+
},
|
| 340 |
{
|
| 341 |
"epoch": 3.99,
|
| 342 |
+
"learning_rate": 6.698615548455805e-05,
|
| 343 |
+
"loss": 0.02,
|
| 344 |
"step": 2500
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 4.0,
|
| 348 |
+
"eval_accuracy": 0.8393782383419689,
|
| 349 |
+
"eval_f1": 0.8431497010182372,
|
| 350 |
+
"eval_loss": 0.5476517081260681,
|
| 351 |
+
"eval_precision": 0.8537832767554047,
|
| 352 |
+
"eval_recall": 0.8393782383419689,
|
| 353 |
+
"eval_runtime": 1.5001,
|
| 354 |
+
"eval_samples_per_second": 128.658,
|
| 355 |
+
"eval_steps_per_second": 16.666,
|
| 356 |
"step": 2504
|
| 357 |
},
|
| 358 |
{
|
| 359 |
+
"epoch": 4.07,
|
| 360 |
+
"learning_rate": 6.43237486687966e-05,
|
| 361 |
+
"loss": 0.0096,
|
| 362 |
+
"step": 2550
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.15,
|
| 366 |
+
"learning_rate": 6.166134185303514e-05,
|
| 367 |
+
"loss": 0.0025,
|
| 368 |
+
"step": 2600
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.23,
|
| 372 |
+
"learning_rate": 5.8998935037273696e-05,
|
| 373 |
+
"loss": 0.0031,
|
| 374 |
+
"step": 2650
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.31,
|
| 378 |
+
"learning_rate": 5.633652822151225e-05,
|
| 379 |
+
"loss": 0.0018,
|
| 380 |
+
"step": 2700
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.39,
|
| 384 |
+
"learning_rate": 5.36741214057508e-05,
|
| 385 |
+
"loss": 0.0035,
|
| 386 |
+
"step": 2750
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.47,
|
| 390 |
+
"learning_rate": 5.101171458998936e-05,
|
| 391 |
+
"loss": 0.0042,
|
| 392 |
+
"step": 2800
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.55,
|
| 396 |
+
"learning_rate": 4.8349307774227905e-05,
|
| 397 |
+
"loss": 0.0046,
|
| 398 |
+
"step": 2850
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.63,
|
| 402 |
+
"learning_rate": 4.568690095846646e-05,
|
| 403 |
+
"loss": 0.002,
|
| 404 |
+
"step": 2900
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.71,
|
| 408 |
+
"learning_rate": 4.3024494142705005e-05,
|
| 409 |
+
"loss": 0.0039,
|
| 410 |
+
"step": 2950
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 4.79,
|
| 414 |
+
"learning_rate": 4.036208732694356e-05,
|
| 415 |
+
"loss": 0.0011,
|
| 416 |
+
"step": 3000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.87,
|
| 420 |
+
"learning_rate": 3.769968051118211e-05,
|
| 421 |
+
"loss": 0.0106,
|
| 422 |
+
"step": 3050
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.95,
|
| 426 |
+
"learning_rate": 3.503727369542067e-05,
|
| 427 |
+
"loss": 0.0018,
|
| 428 |
+
"step": 3100
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 5.0,
|
| 432 |
+
"eval_accuracy": 0.8704663212435233,
|
| 433 |
+
"eval_f1": 0.8749284792904506,
|
| 434 |
+
"eval_loss": 0.48757874965667725,
|
| 435 |
+
"eval_precision": 0.8863835430545274,
|
| 436 |
+
"eval_recall": 0.8704663212435233,
|
| 437 |
+
"eval_runtime": 1.4425,
|
| 438 |
+
"eval_samples_per_second": 133.795,
|
| 439 |
+
"eval_steps_per_second": 17.331,
|
| 440 |
+
"step": 3130
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.03,
|
| 444 |
+
"learning_rate": 3.2374866879659214e-05,
|
| 445 |
+
"loss": 0.0037,
|
| 446 |
+
"step": 3150
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.11,
|
| 450 |
+
"learning_rate": 2.971246006389776e-05,
|
| 451 |
+
"loss": 0.0004,
|
| 452 |
+
"step": 3200
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 5.19,
|
| 456 |
+
"learning_rate": 2.7050053248136315e-05,
|
| 457 |
+
"loss": 0.0004,
|
| 458 |
+
"step": 3250
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.27,
|
| 462 |
+
"learning_rate": 2.438764643237487e-05,
|
| 463 |
+
"loss": 0.0004,
|
| 464 |
+
"step": 3300
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.35,
|
| 468 |
+
"learning_rate": 2.172523961661342e-05,
|
| 469 |
+
"loss": 0.0003,
|
| 470 |
+
"step": 3350
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.43,
|
| 474 |
+
"learning_rate": 1.906283280085197e-05,
|
| 475 |
+
"loss": 0.0014,
|
| 476 |
+
"step": 3400
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.51,
|
| 480 |
+
"learning_rate": 1.6400425985090524e-05,
|
| 481 |
+
"loss": 0.0004,
|
| 482 |
+
"step": 3450
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.59,
|
| 486 |
+
"learning_rate": 1.3738019169329076e-05,
|
| 487 |
+
"loss": 0.0004,
|
| 488 |
+
"step": 3500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.67,
|
| 492 |
+
"learning_rate": 1.1075612353567626e-05,
|
| 493 |
+
"loss": 0.0014,
|
| 494 |
+
"step": 3550
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.75,
|
| 498 |
+
"learning_rate": 8.413205537806178e-06,
|
| 499 |
+
"loss": 0.0004,
|
| 500 |
+
"step": 3600
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 5.83,
|
| 504 |
+
"learning_rate": 5.750798722044729e-06,
|
| 505 |
+
"loss": 0.0003,
|
| 506 |
+
"step": 3650
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 5.91,
|
| 510 |
+
"learning_rate": 3.08839190628328e-06,
|
| 511 |
+
"loss": 0.0003,
|
| 512 |
+
"step": 3700
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 5.99,
|
| 516 |
+
"learning_rate": 4.259850905218318e-07,
|
| 517 |
+
"loss": 0.0003,
|
| 518 |
+
"step": 3750
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.0,
|
| 522 |
+
"eval_accuracy": 0.8704663212435233,
|
| 523 |
+
"eval_f1": 0.8761642097552051,
|
| 524 |
+
"eval_loss": 0.4871196746826172,
|
| 525 |
+
"eval_precision": 0.8862443826726218,
|
| 526 |
+
"eval_recall": 0.8704663212435233,
|
| 527 |
+
"eval_runtime": 1.5001,
|
| 528 |
+
"eval_samples_per_second": 128.657,
|
| 529 |
+
"eval_steps_per_second": 16.665,
|
| 530 |
+
"step": 3756
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.0,
|
| 534 |
+
"step": 3756,
|
| 535 |
+
"total_flos": 4.65670232933972e+18,
|
| 536 |
+
"train_loss": 0.08256206865654514,
|
| 537 |
+
"train_runtime": 1281.0434,
|
| 538 |
+
"train_samples_per_second": 46.907,
|
| 539 |
+
"train_steps_per_second": 2.932
|
| 540 |
}
|
| 541 |
],
|
| 542 |
+
"max_steps": 3756,
|
| 543 |
+
"num_train_epochs": 6,
|
| 544 |
+
"total_flos": 4.65670232933972e+18,
|
| 545 |
"trial_name": null,
|
| 546 |
"trial_params": null
|
| 547 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3899
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a31e83d843e19f25dcc3e3bb54479c7d12ca68324f3971ccbd3897138f4357e9
|
| 3 |
size 3899
|