Upload folder using huggingface_hub
Browse files- config.json +42 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +430 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "European%20Starling%20-%20Invasive",
|
| 13 |
+
"1": "Feral_pigeon%20%281%29",
|
| 14 |
+
"2": "House%20sparrow%20%28Passer%20domesticus%29",
|
| 15 |
+
"3": "Muscovy%20Duck",
|
| 16 |
+
"4": "Non-invasive",
|
| 17 |
+
"5": "bulbul",
|
| 18 |
+
"6": "peacock"
|
| 19 |
+
},
|
| 20 |
+
"image_size": 224,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"European%20Starling%20-%20Invasive": "0",
|
| 25 |
+
"Feral_pigeon%20%281%29": "1",
|
| 26 |
+
"House%20sparrow%20%28Passer%20domesticus%29": "2",
|
| 27 |
+
"Muscovy%20Duck": "3",
|
| 28 |
+
"Non-invasive": "4",
|
| 29 |
+
"bulbul": "5",
|
| 30 |
+
"peacock": "6"
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"model_type": "vit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"patch_size": 16,
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"qkv_bias": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.30.2"
|
| 42 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff2d49a2ad2df39c3c1b8ba9be349127ce620615e5d7fd3e5d5121180e011ab5
|
| 3 |
+
size 686549637
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTFeatureExtractor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f754c81e253146cf8f143265ea8a0855432a701853aa6eabfbfe4cb4ec02dc0b
|
| 3 |
+
size 343284077
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bb3860d98363e44bc4704fb9458deec927fd96997d1d09c80639070db959d22
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e5c5410236a01c76e00a372a6d100405306d921ea2e7b7cc3083628f1364373
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,430 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.07279229909181595,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-500",
|
| 4 |
+
"epoch": 3.6144578313253013,
|
| 5 |
+
"global_step": 600,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 0.00019698795180722893,
|
| 13 |
+
"loss": 1.6355,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 0.00019397590361445782,
|
| 19 |
+
"loss": 1.0697,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.18,
|
| 24 |
+
"learning_rate": 0.00019096385542168677,
|
| 25 |
+
"loss": 0.6398,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 0.00018795180722891569,
|
| 31 |
+
"loss": 0.4757,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.3,
|
| 36 |
+
"learning_rate": 0.00018493975903614458,
|
| 37 |
+
"loss": 0.3393,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.36,
|
| 42 |
+
"learning_rate": 0.0001819277108433735,
|
| 43 |
+
"loss": 0.297,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.42,
|
| 48 |
+
"learning_rate": 0.00017891566265060242,
|
| 49 |
+
"loss": 0.2623,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.48,
|
| 54 |
+
"learning_rate": 0.00017590361445783134,
|
| 55 |
+
"loss": 0.2053,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.54,
|
| 60 |
+
"learning_rate": 0.00017289156626506026,
|
| 61 |
+
"loss": 0.1578,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.6,
|
| 66 |
+
"learning_rate": 0.00016987951807228917,
|
| 67 |
+
"loss": 0.1579,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.6,
|
| 72 |
+
"eval_accuracy": 0.967479674796748,
|
| 73 |
+
"eval_loss": 0.16562165319919586,
|
| 74 |
+
"eval_runtime": 3.9225,
|
| 75 |
+
"eval_samples_per_second": 62.716,
|
| 76 |
+
"eval_steps_per_second": 7.903,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.66,
|
| 81 |
+
"learning_rate": 0.0001668674698795181,
|
| 82 |
+
"loss": 0.1362,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.72,
|
| 87 |
+
"learning_rate": 0.00016385542168674699,
|
| 88 |
+
"loss": 0.1524,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.78,
|
| 93 |
+
"learning_rate": 0.0001608433734939759,
|
| 94 |
+
"loss": 0.0724,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.84,
|
| 99 |
+
"learning_rate": 0.00015783132530120482,
|
| 100 |
+
"loss": 0.2021,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.9,
|
| 105 |
+
"learning_rate": 0.00015481927710843374,
|
| 106 |
+
"loss": 0.0813,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.96,
|
| 111 |
+
"learning_rate": 0.00015180722891566266,
|
| 112 |
+
"loss": 0.0626,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.02,
|
| 117 |
+
"learning_rate": 0.00014879518072289158,
|
| 118 |
+
"loss": 0.0959,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.08,
|
| 123 |
+
"learning_rate": 0.00014578313253012047,
|
| 124 |
+
"loss": 0.0884,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.14,
|
| 129 |
+
"learning_rate": 0.0001427710843373494,
|
| 130 |
+
"loss": 0.0713,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.2,
|
| 135 |
+
"learning_rate": 0.00013975903614457834,
|
| 136 |
+
"loss": 0.0604,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.2,
|
| 141 |
+
"eval_accuracy": 0.983739837398374,
|
| 142 |
+
"eval_loss": 0.11851482838392258,
|
| 143 |
+
"eval_runtime": 4.1596,
|
| 144 |
+
"eval_samples_per_second": 59.14,
|
| 145 |
+
"eval_steps_per_second": 7.453,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.27,
|
| 150 |
+
"learning_rate": 0.00013674698795180723,
|
| 151 |
+
"loss": 0.0534,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.33,
|
| 156 |
+
"learning_rate": 0.00013373493975903615,
|
| 157 |
+
"loss": 0.0292,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.39,
|
| 162 |
+
"learning_rate": 0.00013072289156626507,
|
| 163 |
+
"loss": 0.0395,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.45,
|
| 168 |
+
"learning_rate": 0.00012771084337349396,
|
| 169 |
+
"loss": 0.0325,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.51,
|
| 174 |
+
"learning_rate": 0.00012469879518072288,
|
| 175 |
+
"loss": 0.0298,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.57,
|
| 180 |
+
"learning_rate": 0.00012168674698795181,
|
| 181 |
+
"loss": 0.0211,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.63,
|
| 186 |
+
"learning_rate": 0.00011867469879518073,
|
| 187 |
+
"loss": 0.07,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.69,
|
| 192 |
+
"learning_rate": 0.00011566265060240964,
|
| 193 |
+
"loss": 0.0411,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.75,
|
| 198 |
+
"learning_rate": 0.00011265060240963856,
|
| 199 |
+
"loss": 0.0201,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.81,
|
| 204 |
+
"learning_rate": 0.00010963855421686749,
|
| 205 |
+
"loss": 0.0178,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.81,
|
| 210 |
+
"eval_accuracy": 0.9634146341463414,
|
| 211 |
+
"eval_loss": 0.1352052390575409,
|
| 212 |
+
"eval_runtime": 4.1303,
|
| 213 |
+
"eval_samples_per_second": 59.559,
|
| 214 |
+
"eval_steps_per_second": 7.505,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.87,
|
| 219 |
+
"learning_rate": 0.00010662650602409638,
|
| 220 |
+
"loss": 0.0229,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.93,
|
| 225 |
+
"learning_rate": 0.0001036144578313253,
|
| 226 |
+
"loss": 0.0155,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.99,
|
| 231 |
+
"learning_rate": 0.00010060240963855423,
|
| 232 |
+
"loss": 0.0148,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.05,
|
| 237 |
+
"learning_rate": 9.759036144578314e-05,
|
| 238 |
+
"loss": 0.0156,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.11,
|
| 243 |
+
"learning_rate": 9.457831325301205e-05,
|
| 244 |
+
"loss": 0.0135,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.17,
|
| 249 |
+
"learning_rate": 9.156626506024096e-05,
|
| 250 |
+
"loss": 0.0139,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.23,
|
| 255 |
+
"learning_rate": 8.855421686746988e-05,
|
| 256 |
+
"loss": 0.0229,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.29,
|
| 261 |
+
"learning_rate": 8.55421686746988e-05,
|
| 262 |
+
"loss": 0.0122,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.35,
|
| 267 |
+
"learning_rate": 8.253012048192772e-05,
|
| 268 |
+
"loss": 0.0121,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.41,
|
| 273 |
+
"learning_rate": 7.951807228915663e-05,
|
| 274 |
+
"loss": 0.0112,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.41,
|
| 279 |
+
"eval_accuracy": 0.975609756097561,
|
| 280 |
+
"eval_loss": 0.10706935822963715,
|
| 281 |
+
"eval_runtime": 4.0159,
|
| 282 |
+
"eval_samples_per_second": 61.257,
|
| 283 |
+
"eval_steps_per_second": 7.719,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.47,
|
| 288 |
+
"learning_rate": 7.650602409638555e-05,
|
| 289 |
+
"loss": 0.0269,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.53,
|
| 294 |
+
"learning_rate": 7.349397590361447e-05,
|
| 295 |
+
"loss": 0.0119,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.59,
|
| 300 |
+
"learning_rate": 7.048192771084337e-05,
|
| 301 |
+
"loss": 0.0346,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.65,
|
| 306 |
+
"learning_rate": 6.746987951807229e-05,
|
| 307 |
+
"loss": 0.0104,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.71,
|
| 312 |
+
"learning_rate": 6.445783132530121e-05,
|
| 313 |
+
"loss": 0.0101,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.77,
|
| 318 |
+
"learning_rate": 6.144578313253012e-05,
|
| 319 |
+
"loss": 0.0114,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.83,
|
| 324 |
+
"learning_rate": 5.843373493975904e-05,
|
| 325 |
+
"loss": 0.0098,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.89,
|
| 330 |
+
"learning_rate": 5.5421686746987955e-05,
|
| 331 |
+
"loss": 0.0094,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.95,
|
| 336 |
+
"learning_rate": 5.240963855421687e-05,
|
| 337 |
+
"loss": 0.0099,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.01,
|
| 342 |
+
"learning_rate": 4.9397590361445786e-05,
|
| 343 |
+
"loss": 0.0092,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.01,
|
| 348 |
+
"eval_accuracy": 0.983739837398374,
|
| 349 |
+
"eval_loss": 0.07279229909181595,
|
| 350 |
+
"eval_runtime": 4.4168,
|
| 351 |
+
"eval_samples_per_second": 55.696,
|
| 352 |
+
"eval_steps_per_second": 7.019,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.07,
|
| 357 |
+
"learning_rate": 4.63855421686747e-05,
|
| 358 |
+
"loss": 0.009,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.13,
|
| 363 |
+
"learning_rate": 4.337349397590362e-05,
|
| 364 |
+
"loss": 0.0089,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.19,
|
| 369 |
+
"learning_rate": 4.036144578313254e-05,
|
| 370 |
+
"loss": 0.0087,
|
| 371 |
+
"step": 530
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.25,
|
| 375 |
+
"learning_rate": 3.734939759036144e-05,
|
| 376 |
+
"loss": 0.0085,
|
| 377 |
+
"step": 540
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.31,
|
| 381 |
+
"learning_rate": 3.433734939759036e-05,
|
| 382 |
+
"loss": 0.0083,
|
| 383 |
+
"step": 550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.37,
|
| 387 |
+
"learning_rate": 3.132530120481928e-05,
|
| 388 |
+
"loss": 0.0082,
|
| 389 |
+
"step": 560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.43,
|
| 393 |
+
"learning_rate": 2.8313253012048197e-05,
|
| 394 |
+
"loss": 0.0083,
|
| 395 |
+
"step": 570
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.49,
|
| 399 |
+
"learning_rate": 2.530120481927711e-05,
|
| 400 |
+
"loss": 0.0317,
|
| 401 |
+
"step": 580
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.55,
|
| 405 |
+
"learning_rate": 2.2289156626506025e-05,
|
| 406 |
+
"loss": 0.0079,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.61,
|
| 411 |
+
"learning_rate": 1.927710843373494e-05,
|
| 412 |
+
"loss": 0.008,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.61,
|
| 417 |
+
"eval_accuracy": 0.983739837398374,
|
| 418 |
+
"eval_loss": 0.08243442326784134,
|
| 419 |
+
"eval_runtime": 3.9885,
|
| 420 |
+
"eval_samples_per_second": 61.677,
|
| 421 |
+
"eval_steps_per_second": 7.772,
|
| 422 |
+
"step": 600
|
| 423 |
+
}
|
| 424 |
+
],
|
| 425 |
+
"max_steps": 664,
|
| 426 |
+
"num_train_epochs": 4,
|
| 427 |
+
"total_flos": 7.430264924897526e+17,
|
| 428 |
+
"trial_name": null,
|
| 429 |
+
"trial_params": null
|
| 430 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8366d37c75d8f34e90410171cc6618ba8f6df896670df7c5bdb12c3704ca209
|
| 3 |
+
size 3899
|