Commit
•
91f27c2
1
Parent(s):
75f2059
Training in progress, epoch 1
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- model.safetensors +1 -1
- runs/May01_14-50-35_d6eb9620a945/events.out.tfevents.1714575447.d6eb9620a945.304.1 +3 -0
- runs/May01_15-13-06_d6eb9620a945/events.out.tfevents.1714576415.d6eb9620a945.304.2 +3 -0
- runs/May01_15-13-06_d6eb9620a945/events.out.tfevents.1714576432.d6eb9620a945.304.3 +3 -0
- train_results.json +8 -0
- trainer_state.json +392 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.87,
|
| 4 |
+
"eval_loss": 0.40429016947746277,
|
| 5 |
+
"eval_runtime": 2.5766,
|
| 6 |
+
"eval_samples_per_second": 38.811,
|
| 7 |
+
"eval_steps_per_second": 1.552,
|
| 8 |
+
"total_flos": 1.98847911886848e+17,
|
| 9 |
+
"train_loss": 0.30984322795501124,
|
| 10 |
+
"train_runtime": 343.6308,
|
| 11 |
+
"train_samples_per_second": 23.281,
|
| 12 |
+
"train_steps_per_second": 0.757
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.87,
|
| 4 |
+
"eval_loss": 0.40429016947746277,
|
| 5 |
+
"eval_runtime": 2.5766,
|
| 6 |
+
"eval_samples_per_second": 38.811,
|
| 7 |
+
"eval_steps_per_second": 1.552
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110342832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44379d7a5346d81411cae547be326fc0568a26757c220f8ef6d67d19c560b224
|
| 3 |
size 110342832
|
runs/May01_14-50-35_d6eb9620a945/events.out.tfevents.1714575447.d6eb9620a945.304.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad33798289c2a26234c98cdd259dc2ba9cbe5f21ba1ef00e248574084fab4bc
|
| 3 |
+
size 411
|
runs/May01_15-13-06_d6eb9620a945/events.out.tfevents.1714576415.d6eb9620a945.304.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a742bde1d7176ea4e22ae12fc5179fa6b5c23078b47270dc3b649f5e708293f1
|
| 3 |
+
size 4184
|
runs/May01_15-13-06_d6eb9620a945/events.out.tfevents.1714576432.d6eb9620a945.304.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12451ffbbd72896acb4139307b7142b44faecb9133619f4ef86f01d18f2c4091
|
| 3 |
+
size 5776
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 1.98847911886848e+17,
|
| 4 |
+
"train_loss": 0.30984322795501124,
|
| 5 |
+
"train_runtime": 343.6308,
|
| 6 |
+
"train_samples_per_second": 23.281,
|
| 7 |
+
"train_steps_per_second": 0.757
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,392 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.87,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-student_two_classes/checkpoint-117",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 260,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7692307692307693,
|
| 13 |
+
"grad_norm": 11.056398391723633,
|
| 14 |
+
"learning_rate": 1.923076923076923e-05,
|
| 15 |
+
"loss": 0.6951,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.82,
|
| 21 |
+
"eval_loss": 0.4448259770870209,
|
| 22 |
+
"eval_runtime": 3.0273,
|
| 23 |
+
"eval_samples_per_second": 33.032,
|
| 24 |
+
"eval_steps_per_second": 1.321,
|
| 25 |
+
"step": 13
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.5384615384615383,
|
| 29 |
+
"grad_norm": 6.355745315551758,
|
| 30 |
+
"learning_rate": 3.846153846153846e-05,
|
| 31 |
+
"loss": 0.4292,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.82,
|
| 37 |
+
"eval_loss": 0.44606465101242065,
|
| 38 |
+
"eval_runtime": 2.4722,
|
| 39 |
+
"eval_samples_per_second": 40.45,
|
| 40 |
+
"eval_steps_per_second": 1.618,
|
| 41 |
+
"step": 26
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.3076923076923075,
|
| 45 |
+
"grad_norm": 5.6881914138793945,
|
| 46 |
+
"learning_rate": 4.9145299145299147e-05,
|
| 47 |
+
"loss": 0.4246,
|
| 48 |
+
"step": 30
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_accuracy": 0.82,
|
| 53 |
+
"eval_loss": 0.4553927481174469,
|
| 54 |
+
"eval_runtime": 2.5808,
|
| 55 |
+
"eval_samples_per_second": 38.748,
|
| 56 |
+
"eval_steps_per_second": 1.55,
|
| 57 |
+
"step": 39
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.076923076923077,
|
| 61 |
+
"grad_norm": 9.89670181274414,
|
| 62 |
+
"learning_rate": 4.700854700854701e-05,
|
| 63 |
+
"loss": 0.4424,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 3.8461538461538463,
|
| 68 |
+
"grad_norm": 6.457494258880615,
|
| 69 |
+
"learning_rate": 4.4871794871794874e-05,
|
| 70 |
+
"loss": 0.3983,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.0,
|
| 75 |
+
"eval_accuracy": 0.83,
|
| 76 |
+
"eval_loss": 0.4219551384449005,
|
| 77 |
+
"eval_runtime": 2.9766,
|
| 78 |
+
"eval_samples_per_second": 33.596,
|
| 79 |
+
"eval_steps_per_second": 1.344,
|
| 80 |
+
"step": 52
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.615384615384615,
|
| 84 |
+
"grad_norm": 5.4807610511779785,
|
| 85 |
+
"learning_rate": 4.2735042735042735e-05,
|
| 86 |
+
"loss": 0.314,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 5.0,
|
| 91 |
+
"eval_accuracy": 0.83,
|
| 92 |
+
"eval_loss": 0.44294700026512146,
|
| 93 |
+
"eval_runtime": 2.417,
|
| 94 |
+
"eval_samples_per_second": 41.374,
|
| 95 |
+
"eval_steps_per_second": 1.655,
|
| 96 |
+
"step": 65
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.384615384615385,
|
| 100 |
+
"grad_norm": 5.0344414710998535,
|
| 101 |
+
"learning_rate": 4.05982905982906e-05,
|
| 102 |
+
"loss": 0.4176,
|
| 103 |
+
"step": 70
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 6.0,
|
| 107 |
+
"eval_accuracy": 0.82,
|
| 108 |
+
"eval_loss": 0.4005734324455261,
|
| 109 |
+
"eval_runtime": 3.0995,
|
| 110 |
+
"eval_samples_per_second": 32.264,
|
| 111 |
+
"eval_steps_per_second": 1.291,
|
| 112 |
+
"step": 78
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.153846153846154,
|
| 116 |
+
"grad_norm": 6.132039546966553,
|
| 117 |
+
"learning_rate": 3.846153846153846e-05,
|
| 118 |
+
"loss": 0.3512,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 6.923076923076923,
|
| 123 |
+
"grad_norm": 3.423215389251709,
|
| 124 |
+
"learning_rate": 3.6324786324786323e-05,
|
| 125 |
+
"loss": 0.2862,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 7.0,
|
| 130 |
+
"eval_accuracy": 0.84,
|
| 131 |
+
"eval_loss": 0.4145370423793793,
|
| 132 |
+
"eval_runtime": 2.5336,
|
| 133 |
+
"eval_samples_per_second": 39.47,
|
| 134 |
+
"eval_steps_per_second": 1.579,
|
| 135 |
+
"step": 91
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 7.6923076923076925,
|
| 139 |
+
"grad_norm": 4.900909423828125,
|
| 140 |
+
"learning_rate": 3.418803418803419e-05,
|
| 141 |
+
"loss": 0.3072,
|
| 142 |
+
"step": 100
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"eval_accuracy": 0.83,
|
| 147 |
+
"eval_loss": 0.38473400473594666,
|
| 148 |
+
"eval_runtime": 2.5184,
|
| 149 |
+
"eval_samples_per_second": 39.708,
|
| 150 |
+
"eval_steps_per_second": 1.588,
|
| 151 |
+
"step": 104
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 8.461538461538462,
|
| 155 |
+
"grad_norm": 6.61647891998291,
|
| 156 |
+
"learning_rate": 3.205128205128206e-05,
|
| 157 |
+
"loss": 0.3001,
|
| 158 |
+
"step": 110
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 9.0,
|
| 162 |
+
"eval_accuracy": 0.87,
|
| 163 |
+
"eval_loss": 0.40429016947746277,
|
| 164 |
+
"eval_runtime": 3.3603,
|
| 165 |
+
"eval_samples_per_second": 29.76,
|
| 166 |
+
"eval_steps_per_second": 1.19,
|
| 167 |
+
"step": 117
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 9.23076923076923,
|
| 171 |
+
"grad_norm": 9.093049049377441,
|
| 172 |
+
"learning_rate": 2.9914529914529915e-05,
|
| 173 |
+
"loss": 0.3225,
|
| 174 |
+
"step": 120
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 10.0,
|
| 178 |
+
"grad_norm": 8.699834823608398,
|
| 179 |
+
"learning_rate": 2.777777777777778e-05,
|
| 180 |
+
"loss": 0.2937,
|
| 181 |
+
"step": 130
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 10.0,
|
| 185 |
+
"eval_accuracy": 0.82,
|
| 186 |
+
"eval_loss": 0.40262600779533386,
|
| 187 |
+
"eval_runtime": 2.4958,
|
| 188 |
+
"eval_samples_per_second": 40.067,
|
| 189 |
+
"eval_steps_per_second": 1.603,
|
| 190 |
+
"step": 130
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 10.76923076923077,
|
| 194 |
+
"grad_norm": 3.0456953048706055,
|
| 195 |
+
"learning_rate": 2.564102564102564e-05,
|
| 196 |
+
"loss": 0.2206,
|
| 197 |
+
"step": 140
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 11.0,
|
| 201 |
+
"eval_accuracy": 0.83,
|
| 202 |
+
"eval_loss": 0.3972433805465698,
|
| 203 |
+
"eval_runtime": 2.6788,
|
| 204 |
+
"eval_samples_per_second": 37.329,
|
| 205 |
+
"eval_steps_per_second": 1.493,
|
| 206 |
+
"step": 143
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.538461538461538,
|
| 210 |
+
"grad_norm": 6.638078689575195,
|
| 211 |
+
"learning_rate": 2.3504273504273504e-05,
|
| 212 |
+
"loss": 0.2287,
|
| 213 |
+
"step": 150
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 12.0,
|
| 217 |
+
"eval_accuracy": 0.86,
|
| 218 |
+
"eval_loss": 0.38398703932762146,
|
| 219 |
+
"eval_runtime": 2.4563,
|
| 220 |
+
"eval_samples_per_second": 40.711,
|
| 221 |
+
"eval_steps_per_second": 1.628,
|
| 222 |
+
"step": 156
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.307692307692308,
|
| 226 |
+
"grad_norm": 6.832516670227051,
|
| 227 |
+
"learning_rate": 2.1367521367521368e-05,
|
| 228 |
+
"loss": 0.3318,
|
| 229 |
+
"step": 160
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 13.0,
|
| 233 |
+
"eval_accuracy": 0.84,
|
| 234 |
+
"eval_loss": 0.3740682899951935,
|
| 235 |
+
"eval_runtime": 2.6452,
|
| 236 |
+
"eval_samples_per_second": 37.805,
|
| 237 |
+
"eval_steps_per_second": 1.512,
|
| 238 |
+
"step": 169
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 13.076923076923077,
|
| 242 |
+
"grad_norm": 6.917372226715088,
|
| 243 |
+
"learning_rate": 1.923076923076923e-05,
|
| 244 |
+
"loss": 0.2099,
|
| 245 |
+
"step": 170
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 13.846153846153847,
|
| 249 |
+
"grad_norm": 6.500430107116699,
|
| 250 |
+
"learning_rate": 1.7094017094017095e-05,
|
| 251 |
+
"loss": 0.232,
|
| 252 |
+
"step": 180
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 14.0,
|
| 256 |
+
"eval_accuracy": 0.85,
|
| 257 |
+
"eval_loss": 0.38503700494766235,
|
| 258 |
+
"eval_runtime": 2.5332,
|
| 259 |
+
"eval_samples_per_second": 39.476,
|
| 260 |
+
"eval_steps_per_second": 1.579,
|
| 261 |
+
"step": 182
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 14.615384615384615,
|
| 265 |
+
"grad_norm": 7.342576503753662,
|
| 266 |
+
"learning_rate": 1.4957264957264958e-05,
|
| 267 |
+
"loss": 0.2277,
|
| 268 |
+
"step": 190
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 15.0,
|
| 272 |
+
"eval_accuracy": 0.85,
|
| 273 |
+
"eval_loss": 0.3989230692386627,
|
| 274 |
+
"eval_runtime": 2.5166,
|
| 275 |
+
"eval_samples_per_second": 39.737,
|
| 276 |
+
"eval_steps_per_second": 1.589,
|
| 277 |
+
"step": 195
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 15.384615384615385,
|
| 281 |
+
"grad_norm": 6.8460235595703125,
|
| 282 |
+
"learning_rate": 1.282051282051282e-05,
|
| 283 |
+
"loss": 0.2253,
|
| 284 |
+
"step": 200
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 16.0,
|
| 288 |
+
"eval_accuracy": 0.85,
|
| 289 |
+
"eval_loss": 0.4070873260498047,
|
| 290 |
+
"eval_runtime": 3.0059,
|
| 291 |
+
"eval_samples_per_second": 33.267,
|
| 292 |
+
"eval_steps_per_second": 1.331,
|
| 293 |
+
"step": 208
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 16.153846153846153,
|
| 297 |
+
"grad_norm": 3.827336311340332,
|
| 298 |
+
"learning_rate": 1.0683760683760684e-05,
|
| 299 |
+
"loss": 0.2202,
|
| 300 |
+
"step": 210
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 16.923076923076923,
|
| 304 |
+
"grad_norm": 6.873669624328613,
|
| 305 |
+
"learning_rate": 8.547008547008548e-06,
|
| 306 |
+
"loss": 0.2463,
|
| 307 |
+
"step": 220
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 17.0,
|
| 311 |
+
"eval_accuracy": 0.85,
|
| 312 |
+
"eval_loss": 0.40268489718437195,
|
| 313 |
+
"eval_runtime": 2.5105,
|
| 314 |
+
"eval_samples_per_second": 39.833,
|
| 315 |
+
"eval_steps_per_second": 1.593,
|
| 316 |
+
"step": 221
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 17.692307692307693,
|
| 320 |
+
"grad_norm": 8.530336380004883,
|
| 321 |
+
"learning_rate": 6.41025641025641e-06,
|
| 322 |
+
"loss": 0.2496,
|
| 323 |
+
"step": 230
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 18.0,
|
| 327 |
+
"eval_accuracy": 0.83,
|
| 328 |
+
"eval_loss": 0.41463416814804077,
|
| 329 |
+
"eval_runtime": 2.5445,
|
| 330 |
+
"eval_samples_per_second": 39.301,
|
| 331 |
+
"eval_steps_per_second": 1.572,
|
| 332 |
+
"step": 234
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.46153846153846,
|
| 336 |
+
"grad_norm": 3.6479477882385254,
|
| 337 |
+
"learning_rate": 4.273504273504274e-06,
|
| 338 |
+
"loss": 0.1969,
|
| 339 |
+
"step": 240
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 19.0,
|
| 343 |
+
"eval_accuracy": 0.83,
|
| 344 |
+
"eval_loss": 0.41043660044670105,
|
| 345 |
+
"eval_runtime": 3.1127,
|
| 346 |
+
"eval_samples_per_second": 32.127,
|
| 347 |
+
"eval_steps_per_second": 1.285,
|
| 348 |
+
"step": 247
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 19.23076923076923,
|
| 352 |
+
"grad_norm": 5.254897117614746,
|
| 353 |
+
"learning_rate": 2.136752136752137e-06,
|
| 354 |
+
"loss": 0.257,
|
| 355 |
+
"step": 250
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 20.0,
|
| 359 |
+
"grad_norm": 8.73101806640625,
|
| 360 |
+
"learning_rate": 0.0,
|
| 361 |
+
"loss": 0.2279,
|
| 362 |
+
"step": 260
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 20.0,
|
| 366 |
+
"eval_accuracy": 0.82,
|
| 367 |
+
"eval_loss": 0.41871729493141174,
|
| 368 |
+
"eval_runtime": 2.516,
|
| 369 |
+
"eval_samples_per_second": 39.746,
|
| 370 |
+
"eval_steps_per_second": 1.59,
|
| 371 |
+
"step": 260
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 20.0,
|
| 375 |
+
"step": 260,
|
| 376 |
+
"total_flos": 1.98847911886848e+17,
|
| 377 |
+
"train_loss": 0.30984322795501124,
|
| 378 |
+
"train_runtime": 343.6308,
|
| 379 |
+
"train_samples_per_second": 23.281,
|
| 380 |
+
"train_steps_per_second": 0.757
|
| 381 |
+
}
|
| 382 |
+
],
|
| 383 |
+
"logging_steps": 10,
|
| 384 |
+
"max_steps": 260,
|
| 385 |
+
"num_input_tokens_seen": 0,
|
| 386 |
+
"num_train_epochs": 20,
|
| 387 |
+
"save_steps": 500,
|
| 388 |
+
"total_flos": 1.98847911886848e+17,
|
| 389 |
+
"train_batch_size": 32,
|
| 390 |
+
"trial_name": null,
|
| 391 |
+
"trial_params": null
|
| 392 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e52f74d254afa65d0442792843c29612d3340e5c4e9e5f971ddaf13443f39957
|
| 3 |
size 5112
|