Upload 8 files
Browse files- config.json +57 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +424 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/convnext-small-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ConvNextForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"depths": [
|
| 7 |
+
3,
|
| 8 |
+
3,
|
| 9 |
+
27,
|
| 10 |
+
3
|
| 11 |
+
],
|
| 12 |
+
"drop_path_rate": 0.0,
|
| 13 |
+
"finetuning_task": "image-classification",
|
| 14 |
+
"hidden_act": "gelu",
|
| 15 |
+
"hidden_sizes": [
|
| 16 |
+
96,
|
| 17 |
+
192,
|
| 18 |
+
384,
|
| 19 |
+
768
|
| 20 |
+
],
|
| 21 |
+
"id2label": {
|
| 22 |
+
"0": "0",
|
| 23 |
+
"1": "1",
|
| 24 |
+
"2": "2",
|
| 25 |
+
"3": "3"
|
| 26 |
+
},
|
| 27 |
+
"image_size": 224,
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"label2id": {
|
| 30 |
+
"0": "0",
|
| 31 |
+
"1": "1",
|
| 32 |
+
"2": "2",
|
| 33 |
+
"3": "3"
|
| 34 |
+
},
|
| 35 |
+
"layer_norm_eps": 1e-12,
|
| 36 |
+
"layer_scale_init_value": 1e-06,
|
| 37 |
+
"model_type": "convnext",
|
| 38 |
+
"num_channels": 3,
|
| 39 |
+
"num_stages": 4,
|
| 40 |
+
"out_features": [
|
| 41 |
+
"stage4"
|
| 42 |
+
],
|
| 43 |
+
"out_indices": [
|
| 44 |
+
4
|
| 45 |
+
],
|
| 46 |
+
"patch_size": 4,
|
| 47 |
+
"problem_type": "single_label_classification",
|
| 48 |
+
"stage_names": [
|
| 49 |
+
"stem",
|
| 50 |
+
"stage1",
|
| 51 |
+
"stage2",
|
| 52 |
+
"stage3",
|
| 53 |
+
"stage4"
|
| 54 |
+
],
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.35.0"
|
| 57 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:612bea1073c2d4ef096288caf0df56a868bf2454f54f00463be8fd24c331c9f2
|
| 3 |
+
size 197871936
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6385ca2d91740b0be6cac8c7ec9f342ab317627533d539b5481f9a9c85fe65d
|
| 3 |
+
size 386015141
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"shortest_edge": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8482966b1502cda122536a836a0911b3524c473960cb7bf0bd9e0611ad099d4
|
| 3 |
+
size 14567
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:949278e3258b3bc8b1eb60a3206dfe7ee58a49e81c638e0977392c7d3fa25d1e
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.006926598027348518,
|
| 3 |
+
"best_model_checkpoint": "./outputs/checkpoint-605",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 605,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 1.9669421487603307e-05,
|
| 14 |
+
"loss": 1.3579,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.17,
|
| 19 |
+
"learning_rate": 1.9338842975206613e-05,
|
| 20 |
+
"loss": 1.2345,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.25,
|
| 25 |
+
"learning_rate": 1.900826446280992e-05,
|
| 26 |
+
"loss": 1.1497,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.33,
|
| 31 |
+
"learning_rate": 1.8677685950413225e-05,
|
| 32 |
+
"loss": 1.0313,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.41,
|
| 37 |
+
"learning_rate": 1.834710743801653e-05,
|
| 38 |
+
"loss": 0.9598,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.5,
|
| 43 |
+
"learning_rate": 1.8016528925619837e-05,
|
| 44 |
+
"loss": 0.802,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.58,
|
| 49 |
+
"learning_rate": 1.7685950413223143e-05,
|
| 50 |
+
"loss": 0.7353,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.66,
|
| 55 |
+
"learning_rate": 1.735537190082645e-05,
|
| 56 |
+
"loss": 0.6321,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.74,
|
| 61 |
+
"learning_rate": 1.7024793388429754e-05,
|
| 62 |
+
"loss": 0.5063,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.83,
|
| 67 |
+
"learning_rate": 1.669421487603306e-05,
|
| 68 |
+
"loss": 0.4158,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.91,
|
| 73 |
+
"learning_rate": 1.6363636363636366e-05,
|
| 74 |
+
"loss": 0.3683,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.99,
|
| 79 |
+
"learning_rate": 1.6033057851239672e-05,
|
| 80 |
+
"loss": 0.2849,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.0,
|
| 85 |
+
"eval_accuracy": 1.0,
|
| 86 |
+
"eval_loss": 0.15511935949325562,
|
| 87 |
+
"eval_runtime": 8.1016,
|
| 88 |
+
"eval_samples_per_second": 118.866,
|
| 89 |
+
"eval_steps_per_second": 7.529,
|
| 90 |
+
"step": 121
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.07,
|
| 94 |
+
"learning_rate": 1.5702479338842978e-05,
|
| 95 |
+
"loss": 0.2395,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.16,
|
| 100 |
+
"learning_rate": 1.5371900826446283e-05,
|
| 101 |
+
"loss": 0.1841,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.24,
|
| 106 |
+
"learning_rate": 1.504132231404959e-05,
|
| 107 |
+
"loss": 0.1696,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.32,
|
| 112 |
+
"learning_rate": 1.4710743801652893e-05,
|
| 113 |
+
"loss": 0.1363,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.4,
|
| 118 |
+
"learning_rate": 1.4380165289256201e-05,
|
| 119 |
+
"loss": 0.103,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.49,
|
| 124 |
+
"learning_rate": 1.4049586776859505e-05,
|
| 125 |
+
"loss": 0.104,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.57,
|
| 130 |
+
"learning_rate": 1.3719008264462813e-05,
|
| 131 |
+
"loss": 0.1042,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.65,
|
| 136 |
+
"learning_rate": 1.3388429752066117e-05,
|
| 137 |
+
"loss": 0.0718,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.74,
|
| 142 |
+
"learning_rate": 1.3057851239669424e-05,
|
| 143 |
+
"loss": 0.0798,
|
| 144 |
+
"step": 210
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.82,
|
| 148 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 149 |
+
"loss": 0.0758,
|
| 150 |
+
"step": 220
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.9,
|
| 154 |
+
"learning_rate": 1.2396694214876034e-05,
|
| 155 |
+
"loss": 0.0589,
|
| 156 |
+
"step": 230
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.98,
|
| 160 |
+
"learning_rate": 1.206611570247934e-05,
|
| 161 |
+
"loss": 0.0734,
|
| 162 |
+
"step": 240
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.0,
|
| 166 |
+
"eval_accuracy": 1.0,
|
| 167 |
+
"eval_loss": 0.01950172521173954,
|
| 168 |
+
"eval_runtime": 8.0335,
|
| 169 |
+
"eval_samples_per_second": 119.873,
|
| 170 |
+
"eval_steps_per_second": 7.593,
|
| 171 |
+
"step": 242
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.07,
|
| 175 |
+
"learning_rate": 1.1735537190082646e-05,
|
| 176 |
+
"loss": 0.0698,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.15,
|
| 181 |
+
"learning_rate": 1.1404958677685952e-05,
|
| 182 |
+
"loss": 0.0705,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.23,
|
| 187 |
+
"learning_rate": 1.1074380165289258e-05,
|
| 188 |
+
"loss": 0.0522,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.31,
|
| 193 |
+
"learning_rate": 1.0743801652892562e-05,
|
| 194 |
+
"loss": 0.0645,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.4,
|
| 199 |
+
"learning_rate": 1.041322314049587e-05,
|
| 200 |
+
"loss": 0.0433,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.48,
|
| 205 |
+
"learning_rate": 1.0082644628099174e-05,
|
| 206 |
+
"loss": 0.0382,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.56,
|
| 211 |
+
"learning_rate": 9.75206611570248e-06,
|
| 212 |
+
"loss": 0.0583,
|
| 213 |
+
"step": 310
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.64,
|
| 217 |
+
"learning_rate": 9.421487603305785e-06,
|
| 218 |
+
"loss": 0.0435,
|
| 219 |
+
"step": 320
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.73,
|
| 223 |
+
"learning_rate": 9.090909090909091e-06,
|
| 224 |
+
"loss": 0.0377,
|
| 225 |
+
"step": 330
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.81,
|
| 229 |
+
"learning_rate": 8.760330578512397e-06,
|
| 230 |
+
"loss": 0.0477,
|
| 231 |
+
"step": 340
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.89,
|
| 235 |
+
"learning_rate": 8.429752066115703e-06,
|
| 236 |
+
"loss": 0.0443,
|
| 237 |
+
"step": 350
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.98,
|
| 241 |
+
"learning_rate": 8.099173553719009e-06,
|
| 242 |
+
"loss": 0.0412,
|
| 243 |
+
"step": 360
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.0,
|
| 247 |
+
"eval_accuracy": 1.0,
|
| 248 |
+
"eval_loss": 0.009915151633322239,
|
| 249 |
+
"eval_runtime": 8.1318,
|
| 250 |
+
"eval_samples_per_second": 118.423,
|
| 251 |
+
"eval_steps_per_second": 7.501,
|
| 252 |
+
"step": 363
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.06,
|
| 256 |
+
"learning_rate": 7.768595041322314e-06,
|
| 257 |
+
"loss": 0.0295,
|
| 258 |
+
"step": 370
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 3.14,
|
| 262 |
+
"learning_rate": 7.43801652892562e-06,
|
| 263 |
+
"loss": 0.025,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.22,
|
| 268 |
+
"learning_rate": 7.107438016528926e-06,
|
| 269 |
+
"loss": 0.047,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.31,
|
| 274 |
+
"learning_rate": 6.776859504132232e-06,
|
| 275 |
+
"loss": 0.0375,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.39,
|
| 280 |
+
"learning_rate": 6.446280991735537e-06,
|
| 281 |
+
"loss": 0.035,
|
| 282 |
+
"step": 410
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.47,
|
| 286 |
+
"learning_rate": 6.115702479338843e-06,
|
| 287 |
+
"loss": 0.0241,
|
| 288 |
+
"step": 420
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.55,
|
| 292 |
+
"learning_rate": 5.785123966942149e-06,
|
| 293 |
+
"loss": 0.0253,
|
| 294 |
+
"step": 430
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.64,
|
| 298 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 299 |
+
"loss": 0.0458,
|
| 300 |
+
"step": 440
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.72,
|
| 304 |
+
"learning_rate": 5.12396694214876e-06,
|
| 305 |
+
"loss": 0.0241,
|
| 306 |
+
"step": 450
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.8,
|
| 310 |
+
"learning_rate": 4.793388429752067e-06,
|
| 311 |
+
"loss": 0.0267,
|
| 312 |
+
"step": 460
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 3.88,
|
| 316 |
+
"learning_rate": 4.462809917355372e-06,
|
| 317 |
+
"loss": 0.0324,
|
| 318 |
+
"step": 470
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.97,
|
| 322 |
+
"learning_rate": 4.132231404958678e-06,
|
| 323 |
+
"loss": 0.0457,
|
| 324 |
+
"step": 480
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.0,
|
| 328 |
+
"eval_accuracy": 1.0,
|
| 329 |
+
"eval_loss": 0.007458301726728678,
|
| 330 |
+
"eval_runtime": 8.0474,
|
| 331 |
+
"eval_samples_per_second": 119.667,
|
| 332 |
+
"eval_steps_per_second": 7.58,
|
| 333 |
+
"step": 484
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.05,
|
| 337 |
+
"learning_rate": 3.801652892561984e-06,
|
| 338 |
+
"loss": 0.031,
|
| 339 |
+
"step": 490
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.13,
|
| 343 |
+
"learning_rate": 3.4710743801652895e-06,
|
| 344 |
+
"loss": 0.0622,
|
| 345 |
+
"step": 500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.21,
|
| 349 |
+
"learning_rate": 3.1404958677685953e-06,
|
| 350 |
+
"loss": 0.0399,
|
| 351 |
+
"step": 510
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.3,
|
| 355 |
+
"learning_rate": 2.809917355371901e-06,
|
| 356 |
+
"loss": 0.0287,
|
| 357 |
+
"step": 520
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.38,
|
| 361 |
+
"learning_rate": 2.479338842975207e-06,
|
| 362 |
+
"loss": 0.0363,
|
| 363 |
+
"step": 530
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 4.46,
|
| 367 |
+
"learning_rate": 2.1487603305785124e-06,
|
| 368 |
+
"loss": 0.0484,
|
| 369 |
+
"step": 540
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.55,
|
| 373 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 374 |
+
"loss": 0.0532,
|
| 375 |
+
"step": 550
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.63,
|
| 379 |
+
"learning_rate": 1.4876033057851241e-06,
|
| 380 |
+
"loss": 0.046,
|
| 381 |
+
"step": 560
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.71,
|
| 385 |
+
"learning_rate": 1.15702479338843e-06,
|
| 386 |
+
"loss": 0.016,
|
| 387 |
+
"step": 570
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.79,
|
| 391 |
+
"learning_rate": 8.264462809917356e-07,
|
| 392 |
+
"loss": 0.0331,
|
| 393 |
+
"step": 580
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.88,
|
| 397 |
+
"learning_rate": 4.958677685950413e-07,
|
| 398 |
+
"loss": 0.0554,
|
| 399 |
+
"step": 590
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.96,
|
| 403 |
+
"learning_rate": 1.6528925619834713e-07,
|
| 404 |
+
"loss": 0.0342,
|
| 405 |
+
"step": 600
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 5.0,
|
| 409 |
+
"eval_accuracy": 1.0,
|
| 410 |
+
"eval_loss": 0.006926598027348518,
|
| 411 |
+
"eval_runtime": 8.1069,
|
| 412 |
+
"eval_samples_per_second": 118.788,
|
| 413 |
+
"eval_steps_per_second": 7.524,
|
| 414 |
+
"step": 605
|
| 415 |
+
}
|
| 416 |
+
],
|
| 417 |
+
"logging_steps": 10,
|
| 418 |
+
"max_steps": 605,
|
| 419 |
+
"num_train_epochs": 5,
|
| 420 |
+
"save_steps": 500,
|
| 421 |
+
"total_flos": 8.594252068818125e+17,
|
| 422 |
+
"trial_name": null,
|
| 423 |
+
"trial_params": null
|
| 424 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e70747afd391915ed98eba271eab99c6e195b92a75b2b0c50a67b77591e65e9
|
| 3 |
+
size 4079
|