Training in progress, epoch 1
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- model.safetensors +1 -1
- runs/Jun10_09-28-54_4c61f7eac1f1/events.out.tfevents.1718012227.4c61f7eac1f1.793.2 +3 -0
- runs/Jun10_09-37-38_4c61f7eac1f1/events.out.tfevents.1718012258.4c61f7eac1f1.793.3 +3 -0
- train_results.json +8 -0
- trainer_state.json +362 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.896875,
|
| 4 |
+
"eval_loss": 0.31735172867774963,
|
| 5 |
+
"eval_runtime": 2.8593,
|
| 6 |
+
"eval_samples_per_second": 111.914,
|
| 7 |
+
"eval_steps_per_second": 3.497,
|
| 8 |
+
"total_flos": 8.32925255860224e+17,
|
| 9 |
+
"train_loss": 0.5535187506675721,
|
| 10 |
+
"train_runtime": 481.721,
|
| 11 |
+
"train_samples_per_second": 53.143,
|
| 12 |
+
"train_steps_per_second": 0.415
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.896875,
|
| 4 |
+
"eval_loss": 0.31735172867774963,
|
| 5 |
+
"eval_runtime": 2.8593,
|
| 6 |
+
"eval_samples_per_second": 111.914,
|
| 7 |
+
"eval_steps_per_second": 3.497
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110356296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0278b709279c95fa9a2b680774aba7261590ae38c95ca85e7169662cee8cbb9e
|
| 3 |
size 110356296
|
runs/Jun10_09-28-54_4c61f7eac1f1/events.out.tfevents.1718012227.4c61f7eac1f1.793.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a579c12b545be7c500775d24e9540a0460271d13f750333564c393a152df275b
|
| 3 |
+
size 411
|
runs/Jun10_09-37-38_4c61f7eac1f1/events.out.tfevents.1718012258.4c61f7eac1f1.793.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eb63c6898d8720c473f5ed137c4419ebd57b7180dd786ed1c1c0316c1cede50
|
| 3 |
+
size 5910
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 8.32925255860224e+17,
|
| 4 |
+
"train_loss": 0.5535187506675721,
|
| 5 |
+
"train_runtime": 481.721,
|
| 6 |
+
"train_samples_per_second": 53.143,
|
| 7 |
+
"train_steps_per_second": 0.415
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,362 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.896875,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finalterm/checkpoint-160",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 3.0463645458221436,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 1.397,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.35625,
|
| 21 |
+
"eval_loss": 1.3485567569732666,
|
| 22 |
+
"eval_runtime": 2.7657,
|
| 23 |
+
"eval_samples_per_second": 115.703,
|
| 24 |
+
"eval_steps_per_second": 3.616,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 9.14601993560791,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 1.2224,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.509375,
|
| 37 |
+
"eval_loss": 1.0746052265167236,
|
| 38 |
+
"eval_runtime": 2.8349,
|
| 39 |
+
"eval_samples_per_second": 112.879,
|
| 40 |
+
"eval_steps_per_second": 3.527,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"grad_norm": 8.623628616333008,
|
| 46 |
+
"learning_rate": 4.722222222222222e-05,
|
| 47 |
+
"loss": 0.8883,
|
| 48 |
+
"step": 30
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_accuracy": 0.709375,
|
| 53 |
+
"eval_loss": 0.7385674715042114,
|
| 54 |
+
"eval_runtime": 3.0143,
|
| 55 |
+
"eval_samples_per_second": 106.162,
|
| 56 |
+
"eval_steps_per_second": 3.318,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"grad_norm": 7.014606475830078,
|
| 62 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 63 |
+
"loss": 0.73,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.71875,
|
| 69 |
+
"eval_loss": 0.6787489056587219,
|
| 70 |
+
"eval_runtime": 3.0319,
|
| 71 |
+
"eval_samples_per_second": 105.543,
|
| 72 |
+
"eval_steps_per_second": 3.298,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.0,
|
| 77 |
+
"grad_norm": 5.60139799118042,
|
| 78 |
+
"learning_rate": 4.166666666666667e-05,
|
| 79 |
+
"loss": 0.6132,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_accuracy": 0.75,
|
| 85 |
+
"eval_loss": 0.5557254552841187,
|
| 86 |
+
"eval_runtime": 2.7949,
|
| 87 |
+
"eval_samples_per_second": 114.494,
|
| 88 |
+
"eval_steps_per_second": 3.578,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"grad_norm": 6.750443458557129,
|
| 94 |
+
"learning_rate": 3.888888888888889e-05,
|
| 95 |
+
"loss": 0.5297,
|
| 96 |
+
"step": 60
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.828125,
|
| 101 |
+
"eval_loss": 0.4563722610473633,
|
| 102 |
+
"eval_runtime": 2.8163,
|
| 103 |
+
"eval_samples_per_second": 113.622,
|
| 104 |
+
"eval_steps_per_second": 3.551,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.0,
|
| 109 |
+
"grad_norm": 8.682096481323242,
|
| 110 |
+
"learning_rate": 3.611111111111111e-05,
|
| 111 |
+
"loss": 0.4811,
|
| 112 |
+
"step": 70
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 7.0,
|
| 116 |
+
"eval_accuracy": 0.859375,
|
| 117 |
+
"eval_loss": 0.4000449776649475,
|
| 118 |
+
"eval_runtime": 2.8732,
|
| 119 |
+
"eval_samples_per_second": 111.373,
|
| 120 |
+
"eval_steps_per_second": 3.48,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"grad_norm": 4.585944652557373,
|
| 126 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 127 |
+
"loss": 0.484,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.853125,
|
| 133 |
+
"eval_loss": 0.40824002027511597,
|
| 134 |
+
"eval_runtime": 2.7794,
|
| 135 |
+
"eval_samples_per_second": 115.134,
|
| 136 |
+
"eval_steps_per_second": 3.598,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 9.0,
|
| 141 |
+
"grad_norm": 5.7387237548828125,
|
| 142 |
+
"learning_rate": 3.055555555555556e-05,
|
| 143 |
+
"loss": 0.4525,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.0,
|
| 148 |
+
"eval_accuracy": 0.890625,
|
| 149 |
+
"eval_loss": 0.3567732274532318,
|
| 150 |
+
"eval_runtime": 2.8097,
|
| 151 |
+
"eval_samples_per_second": 113.893,
|
| 152 |
+
"eval_steps_per_second": 3.559,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10.0,
|
| 157 |
+
"grad_norm": 5.609104633331299,
|
| 158 |
+
"learning_rate": 2.777777777777778e-05,
|
| 159 |
+
"loss": 0.429,
|
| 160 |
+
"step": 100
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 10.0,
|
| 164 |
+
"eval_accuracy": 0.875,
|
| 165 |
+
"eval_loss": 0.3661341071128845,
|
| 166 |
+
"eval_runtime": 2.8278,
|
| 167 |
+
"eval_samples_per_second": 113.164,
|
| 168 |
+
"eval_steps_per_second": 3.536,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 11.0,
|
| 173 |
+
"grad_norm": 5.6711225509643555,
|
| 174 |
+
"learning_rate": 2.5e-05,
|
| 175 |
+
"loss": 0.4383,
|
| 176 |
+
"step": 110
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.0,
|
| 180 |
+
"eval_accuracy": 0.85,
|
| 181 |
+
"eval_loss": 0.4051894247531891,
|
| 182 |
+
"eval_runtime": 2.947,
|
| 183 |
+
"eval_samples_per_second": 108.586,
|
| 184 |
+
"eval_steps_per_second": 3.393,
|
| 185 |
+
"step": 110
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 12.0,
|
| 189 |
+
"grad_norm": 6.238234996795654,
|
| 190 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 191 |
+
"loss": 0.4586,
|
| 192 |
+
"step": 120
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 12.0,
|
| 196 |
+
"eval_accuracy": 0.88125,
|
| 197 |
+
"eval_loss": 0.3318403363227844,
|
| 198 |
+
"eval_runtime": 2.8475,
|
| 199 |
+
"eval_samples_per_second": 112.381,
|
| 200 |
+
"eval_steps_per_second": 3.512,
|
| 201 |
+
"step": 120
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 13.0,
|
| 205 |
+
"grad_norm": 6.806089401245117,
|
| 206 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 207 |
+
"loss": 0.4036,
|
| 208 |
+
"step": 130
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 13.0,
|
| 212 |
+
"eval_accuracy": 0.865625,
|
| 213 |
+
"eval_loss": 0.35395950078964233,
|
| 214 |
+
"eval_runtime": 2.8595,
|
| 215 |
+
"eval_samples_per_second": 111.906,
|
| 216 |
+
"eval_steps_per_second": 3.497,
|
| 217 |
+
"step": 130
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 14.0,
|
| 221 |
+
"grad_norm": 4.199438095092773,
|
| 222 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 223 |
+
"loss": 0.3652,
|
| 224 |
+
"step": 140
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.0,
|
| 228 |
+
"eval_accuracy": 0.871875,
|
| 229 |
+
"eval_loss": 0.3941846787929535,
|
| 230 |
+
"eval_runtime": 2.8862,
|
| 231 |
+
"eval_samples_per_second": 110.871,
|
| 232 |
+
"eval_steps_per_second": 3.465,
|
| 233 |
+
"step": 140
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"grad_norm": 4.736207485198975,
|
| 238 |
+
"learning_rate": 1.388888888888889e-05,
|
| 239 |
+
"loss": 0.3822,
|
| 240 |
+
"step": 150
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 15.0,
|
| 244 |
+
"eval_accuracy": 0.890625,
|
| 245 |
+
"eval_loss": 0.3420585095882416,
|
| 246 |
+
"eval_runtime": 2.8296,
|
| 247 |
+
"eval_samples_per_second": 113.091,
|
| 248 |
+
"eval_steps_per_second": 3.534,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 16.0,
|
| 253 |
+
"grad_norm": 5.99350643157959,
|
| 254 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 255 |
+
"loss": 0.3564,
|
| 256 |
+
"step": 160
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 16.0,
|
| 260 |
+
"eval_accuracy": 0.896875,
|
| 261 |
+
"eval_loss": 0.31735172867774963,
|
| 262 |
+
"eval_runtime": 2.7873,
|
| 263 |
+
"eval_samples_per_second": 114.807,
|
| 264 |
+
"eval_steps_per_second": 3.588,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 17.0,
|
| 269 |
+
"grad_norm": 4.5202741622924805,
|
| 270 |
+
"learning_rate": 8.333333333333334e-06,
|
| 271 |
+
"loss": 0.3635,
|
| 272 |
+
"step": 170
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 17.0,
|
| 276 |
+
"eval_accuracy": 0.884375,
|
| 277 |
+
"eval_loss": 0.3356662690639496,
|
| 278 |
+
"eval_runtime": 2.8073,
|
| 279 |
+
"eval_samples_per_second": 113.988,
|
| 280 |
+
"eval_steps_per_second": 3.562,
|
| 281 |
+
"step": 170
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 18.0,
|
| 285 |
+
"grad_norm": 5.483897686004639,
|
| 286 |
+
"learning_rate": 5.555555555555556e-06,
|
| 287 |
+
"loss": 0.3645,
|
| 288 |
+
"step": 180
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 18.0,
|
| 292 |
+
"eval_accuracy": 0.89375,
|
| 293 |
+
"eval_loss": 0.3204434812068939,
|
| 294 |
+
"eval_runtime": 3.0124,
|
| 295 |
+
"eval_samples_per_second": 106.229,
|
| 296 |
+
"eval_steps_per_second": 3.32,
|
| 297 |
+
"step": 180
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 19.0,
|
| 301 |
+
"grad_norm": 7.001428604125977,
|
| 302 |
+
"learning_rate": 2.777777777777778e-06,
|
| 303 |
+
"loss": 0.3576,
|
| 304 |
+
"step": 190
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 19.0,
|
| 308 |
+
"eval_accuracy": 0.878125,
|
| 309 |
+
"eval_loss": 0.33071213960647583,
|
| 310 |
+
"eval_runtime": 2.9125,
|
| 311 |
+
"eval_samples_per_second": 109.87,
|
| 312 |
+
"eval_steps_per_second": 3.433,
|
| 313 |
+
"step": 190
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 20.0,
|
| 317 |
+
"grad_norm": 5.229546070098877,
|
| 318 |
+
"learning_rate": 0.0,
|
| 319 |
+
"loss": 0.3532,
|
| 320 |
+
"step": 200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 20.0,
|
| 324 |
+
"eval_accuracy": 0.878125,
|
| 325 |
+
"eval_loss": 0.3238596022129059,
|
| 326 |
+
"eval_runtime": 2.976,
|
| 327 |
+
"eval_samples_per_second": 107.525,
|
| 328 |
+
"eval_steps_per_second": 3.36,
|
| 329 |
+
"step": 200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 20.0,
|
| 333 |
+
"step": 200,
|
| 334 |
+
"total_flos": 8.32925255860224e+17,
|
| 335 |
+
"train_loss": 0.5535187506675721,
|
| 336 |
+
"train_runtime": 481.721,
|
| 337 |
+
"train_samples_per_second": 53.143,
|
| 338 |
+
"train_steps_per_second": 0.415
|
| 339 |
+
}
|
| 340 |
+
],
|
| 341 |
+
"logging_steps": 10,
|
| 342 |
+
"max_steps": 200,
|
| 343 |
+
"num_input_tokens_seen": 0,
|
| 344 |
+
"num_train_epochs": 20,
|
| 345 |
+
"save_steps": 500,
|
| 346 |
+
"stateful_callbacks": {
|
| 347 |
+
"TrainerControl": {
|
| 348 |
+
"args": {
|
| 349 |
+
"should_epoch_stop": false,
|
| 350 |
+
"should_evaluate": false,
|
| 351 |
+
"should_log": false,
|
| 352 |
+
"should_save": true,
|
| 353 |
+
"should_training_stop": true
|
| 354 |
+
},
|
| 355 |
+
"attributes": {}
|
| 356 |
+
}
|
| 357 |
+
},
|
| 358 |
+
"total_flos": 8.32925255860224e+17,
|
| 359 |
+
"train_batch_size": 32,
|
| 360 |
+
"trial_name": null,
|
| 361 |
+
"trial_params": null
|
| 362 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d8328c9300d53c4a9860213fe5ae6d51d67058d24a9fd10051247ba0b5a58f6
|
| 3 |
size 5176
|