Spaces:
Sleeping
Sleeping
Commit
·
1d56b50
1
Parent(s):
fea3e20
Upload folder using huggingface_hub
Browse files
checkpoint-905/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "cat",
|
| 13 |
+
"1": "dog",
|
| 14 |
+
"2": "other"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"cat": 0,
|
| 21 |
+
"dog": 1,
|
| 22 |
+
"other": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"model_type": "vit",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_channels": 3,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.26.1"
|
| 34 |
+
}
|
checkpoint-905/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": "ViTImageProcessor",
|
| 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 |
+
}
|
checkpoint-905/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e031943fdafdcdf33d24375e119ea6c9f7677beea85c7adc4a3123392a14b30
|
| 3 |
+
size 343270065
|
checkpoint-905/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1bda5d0b2753283cedeabe02783e3e9e08fff80f7f2c6395b5cb1a8aeef4325
|
| 3 |
+
size 14503
|
checkpoint-905/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd0e45af5242805b87cb383fa9ac92a12f0e6c302e2ca294bec1a9f466e0587e
|
| 3 |
+
size 623
|
checkpoint-905/trainer_state.json
ADDED
|
@@ -0,0 +1,601 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9917032698877501,
|
| 3 |
+
"best_model_checkpoint": "./checkpoint/checkpoint-905",
|
| 4 |
+
"epoch": 4.997245179063361,
|
| 5 |
+
"global_step": 905,
|
| 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": 3.6764705882352942e-06,
|
| 13 |
+
"loss": 1.0502,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 7.3529411764705884e-06,
|
| 19 |
+
"loss": 1.0183,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.17,
|
| 24 |
+
"learning_rate": 1.1029411764705883e-05,
|
| 25 |
+
"loss": 0.9565,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.22,
|
| 30 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 31 |
+
"loss": 0.8426,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.28,
|
| 36 |
+
"learning_rate": 1.8382352941176472e-05,
|
| 37 |
+
"loss": 0.6867,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.33,
|
| 42 |
+
"learning_rate": 2.2058823529411766e-05,
|
| 43 |
+
"loss": 0.5298,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.39,
|
| 48 |
+
"learning_rate": 2.5735294117647057e-05,
|
| 49 |
+
"loss": 0.3856,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.44,
|
| 54 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 55 |
+
"loss": 0.2925,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.5,
|
| 60 |
+
"learning_rate": 3.308823529411765e-05,
|
| 61 |
+
"loss": 0.234,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.55,
|
| 66 |
+
"learning_rate": 3.6764705882352945e-05,
|
| 67 |
+
"loss": 0.1777,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.61,
|
| 72 |
+
"learning_rate": 4.044117647058824e-05,
|
| 73 |
+
"loss": 0.1539,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.66,
|
| 78 |
+
"learning_rate": 4.411764705882353e-05,
|
| 79 |
+
"loss": 0.114,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.72,
|
| 84 |
+
"learning_rate": 4.7794117647058826e-05,
|
| 85 |
+
"loss": 0.123,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.77,
|
| 90 |
+
"learning_rate": 5.147058823529411e-05,
|
| 91 |
+
"loss": 0.1118,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.83,
|
| 96 |
+
"learning_rate": 5.514705882352942e-05,
|
| 97 |
+
"loss": 0.1032,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.88,
|
| 102 |
+
"learning_rate": 5.882352941176471e-05,
|
| 103 |
+
"loss": 0.1201,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.94,
|
| 108 |
+
"learning_rate": 6.25e-05,
|
| 109 |
+
"loss": 0.0914,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.99,
|
| 114 |
+
"learning_rate": 6.61764705882353e-05,
|
| 115 |
+
"loss": 0.0825,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0,
|
| 120 |
+
"eval_accuracy": 0.9858467545143973,
|
| 121 |
+
"eval_loss": 0.07265167683362961,
|
| 122 |
+
"eval_runtime": 59.8085,
|
| 123 |
+
"eval_samples_per_second": 68.519,
|
| 124 |
+
"eval_steps_per_second": 2.157,
|
| 125 |
+
"step": 181
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.05,
|
| 129 |
+
"learning_rate": 6.985294117647059e-05,
|
| 130 |
+
"loss": 0.0836,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.1,
|
| 135 |
+
"learning_rate": 7.352941176470589e-05,
|
| 136 |
+
"loss": 0.0691,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.16,
|
| 141 |
+
"learning_rate": 7.720588235294119e-05,
|
| 142 |
+
"loss": 0.0834,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.21,
|
| 147 |
+
"learning_rate": 8.088235294117648e-05,
|
| 148 |
+
"loss": 0.0876,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.27,
|
| 153 |
+
"learning_rate": 8.455882352941176e-05,
|
| 154 |
+
"loss": 0.077,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.33,
|
| 159 |
+
"learning_rate": 8.823529411764706e-05,
|
| 160 |
+
"loss": 0.0671,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.38,
|
| 165 |
+
"learning_rate": 9.191176470588235e-05,
|
| 166 |
+
"loss": 0.0623,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.44,
|
| 171 |
+
"learning_rate": 9.558823529411765e-05,
|
| 172 |
+
"loss": 0.0539,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.49,
|
| 177 |
+
"learning_rate": 9.926470588235295e-05,
|
| 178 |
+
"loss": 0.0645,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.55,
|
| 183 |
+
"learning_rate": 9.873617693522908e-05,
|
| 184 |
+
"loss": 0.061,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.6,
|
| 189 |
+
"learning_rate": 9.715639810426542e-05,
|
| 190 |
+
"loss": 0.0519,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.66,
|
| 195 |
+
"learning_rate": 9.557661927330174e-05,
|
| 196 |
+
"loss": 0.0697,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.71,
|
| 201 |
+
"learning_rate": 9.399684044233808e-05,
|
| 202 |
+
"loss": 0.062,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.77,
|
| 207 |
+
"learning_rate": 9.241706161137442e-05,
|
| 208 |
+
"loss": 0.0681,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.82,
|
| 213 |
+
"learning_rate": 9.083728278041075e-05,
|
| 214 |
+
"loss": 0.0698,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.88,
|
| 219 |
+
"learning_rate": 8.925750394944709e-05,
|
| 220 |
+
"loss": 0.067,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.93,
|
| 225 |
+
"learning_rate": 8.767772511848341e-05,
|
| 226 |
+
"loss": 0.0728,
|
| 227 |
+
"step": 350
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.99,
|
| 231 |
+
"learning_rate": 8.609794628751975e-05,
|
| 232 |
+
"loss": 0.06,
|
| 233 |
+
"step": 360
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.0,
|
| 237 |
+
"eval_accuracy": 0.9812103465104929,
|
| 238 |
+
"eval_loss": 0.06039927154779434,
|
| 239 |
+
"eval_runtime": 59.4929,
|
| 240 |
+
"eval_samples_per_second": 68.882,
|
| 241 |
+
"eval_steps_per_second": 2.168,
|
| 242 |
+
"step": 362
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.04,
|
| 246 |
+
"learning_rate": 8.451816745655609e-05,
|
| 247 |
+
"loss": 0.065,
|
| 248 |
+
"step": 370
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.1,
|
| 252 |
+
"learning_rate": 8.293838862559243e-05,
|
| 253 |
+
"loss": 0.0635,
|
| 254 |
+
"step": 380
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.15,
|
| 258 |
+
"learning_rate": 8.135860979462876e-05,
|
| 259 |
+
"loss": 0.0532,
|
| 260 |
+
"step": 390
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.21,
|
| 264 |
+
"learning_rate": 7.977883096366509e-05,
|
| 265 |
+
"loss": 0.0497,
|
| 266 |
+
"step": 400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.26,
|
| 270 |
+
"learning_rate": 7.819905213270142e-05,
|
| 271 |
+
"loss": 0.0665,
|
| 272 |
+
"step": 410
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.32,
|
| 276 |
+
"learning_rate": 7.661927330173776e-05,
|
| 277 |
+
"loss": 0.0525,
|
| 278 |
+
"step": 420
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.37,
|
| 282 |
+
"learning_rate": 7.50394944707741e-05,
|
| 283 |
+
"loss": 0.0514,
|
| 284 |
+
"step": 430
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.43,
|
| 288 |
+
"learning_rate": 7.345971563981043e-05,
|
| 289 |
+
"loss": 0.0649,
|
| 290 |
+
"step": 440
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.48,
|
| 294 |
+
"learning_rate": 7.187993680884676e-05,
|
| 295 |
+
"loss": 0.064,
|
| 296 |
+
"step": 450
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.54,
|
| 300 |
+
"learning_rate": 7.03001579778831e-05,
|
| 301 |
+
"loss": 0.0488,
|
| 302 |
+
"step": 460
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.6,
|
| 306 |
+
"learning_rate": 6.872037914691943e-05,
|
| 307 |
+
"loss": 0.0405,
|
| 308 |
+
"step": 470
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.65,
|
| 312 |
+
"learning_rate": 6.714060031595577e-05,
|
| 313 |
+
"loss": 0.0357,
|
| 314 |
+
"step": 480
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.71,
|
| 318 |
+
"learning_rate": 6.556082148499211e-05,
|
| 319 |
+
"loss": 0.0439,
|
| 320 |
+
"step": 490
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.76,
|
| 324 |
+
"learning_rate": 6.398104265402843e-05,
|
| 325 |
+
"loss": 0.0469,
|
| 326 |
+
"step": 500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.82,
|
| 330 |
+
"learning_rate": 6.240126382306477e-05,
|
| 331 |
+
"loss": 0.0289,
|
| 332 |
+
"step": 510
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.87,
|
| 336 |
+
"learning_rate": 6.0821484992101105e-05,
|
| 337 |
+
"loss": 0.0431,
|
| 338 |
+
"step": 520
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.93,
|
| 342 |
+
"learning_rate": 5.924170616113744e-05,
|
| 343 |
+
"loss": 0.0284,
|
| 344 |
+
"step": 530
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.98,
|
| 348 |
+
"learning_rate": 5.766192733017378e-05,
|
| 349 |
+
"loss": 0.0467,
|
| 350 |
+
"step": 540
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.0,
|
| 354 |
+
"eval_accuracy": 0.9838945827232797,
|
| 355 |
+
"eval_loss": 0.04717087373137474,
|
| 356 |
+
"eval_runtime": 59.6298,
|
| 357 |
+
"eval_samples_per_second": 68.724,
|
| 358 |
+
"eval_steps_per_second": 2.163,
|
| 359 |
+
"step": 543
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.04,
|
| 363 |
+
"learning_rate": 5.608214849921012e-05,
|
| 364 |
+
"loss": 0.0503,
|
| 365 |
+
"step": 550
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.09,
|
| 369 |
+
"learning_rate": 5.450236966824645e-05,
|
| 370 |
+
"loss": 0.043,
|
| 371 |
+
"step": 560
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.15,
|
| 375 |
+
"learning_rate": 5.2922590837282785e-05,
|
| 376 |
+
"loss": 0.0381,
|
| 377 |
+
"step": 570
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.2,
|
| 381 |
+
"learning_rate": 5.134281200631912e-05,
|
| 382 |
+
"loss": 0.0295,
|
| 383 |
+
"step": 580
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.26,
|
| 387 |
+
"learning_rate": 4.976303317535545e-05,
|
| 388 |
+
"loss": 0.0411,
|
| 389 |
+
"step": 590
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.31,
|
| 393 |
+
"learning_rate": 4.818325434439179e-05,
|
| 394 |
+
"loss": 0.0242,
|
| 395 |
+
"step": 600
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.37,
|
| 399 |
+
"learning_rate": 4.660347551342813e-05,
|
| 400 |
+
"loss": 0.0365,
|
| 401 |
+
"step": 610
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.42,
|
| 405 |
+
"learning_rate": 4.502369668246446e-05,
|
| 406 |
+
"loss": 0.021,
|
| 407 |
+
"step": 620
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.48,
|
| 411 |
+
"learning_rate": 4.3443917851500794e-05,
|
| 412 |
+
"loss": 0.0492,
|
| 413 |
+
"step": 630
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.53,
|
| 417 |
+
"learning_rate": 4.1864139020537125e-05,
|
| 418 |
+
"loss": 0.0391,
|
| 419 |
+
"step": 640
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.59,
|
| 423 |
+
"learning_rate": 4.028436018957346e-05,
|
| 424 |
+
"loss": 0.0291,
|
| 425 |
+
"step": 650
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.64,
|
| 429 |
+
"learning_rate": 3.87045813586098e-05,
|
| 430 |
+
"loss": 0.0317,
|
| 431 |
+
"step": 660
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.7,
|
| 435 |
+
"learning_rate": 3.712480252764613e-05,
|
| 436 |
+
"loss": 0.0355,
|
| 437 |
+
"step": 670
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.75,
|
| 441 |
+
"learning_rate": 3.554502369668247e-05,
|
| 442 |
+
"loss": 0.0407,
|
| 443 |
+
"step": 680
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.81,
|
| 447 |
+
"learning_rate": 3.39652448657188e-05,
|
| 448 |
+
"loss": 0.0257,
|
| 449 |
+
"step": 690
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.87,
|
| 453 |
+
"learning_rate": 3.2385466034755135e-05,
|
| 454 |
+
"loss": 0.0382,
|
| 455 |
+
"step": 700
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.92,
|
| 459 |
+
"learning_rate": 3.080568720379147e-05,
|
| 460 |
+
"loss": 0.0323,
|
| 461 |
+
"step": 710
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.98,
|
| 465 |
+
"learning_rate": 2.9225908372827802e-05,
|
| 466 |
+
"loss": 0.0233,
|
| 467 |
+
"step": 720
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.0,
|
| 471 |
+
"eval_accuracy": 0.9897510980966325,
|
| 472 |
+
"eval_loss": 0.028671853244304657,
|
| 473 |
+
"eval_runtime": 59.9206,
|
| 474 |
+
"eval_samples_per_second": 68.391,
|
| 475 |
+
"eval_steps_per_second": 2.153,
|
| 476 |
+
"step": 724
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.03,
|
| 480 |
+
"learning_rate": 2.764612954186414e-05,
|
| 481 |
+
"loss": 0.031,
|
| 482 |
+
"step": 730
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.09,
|
| 486 |
+
"learning_rate": 2.6066350710900477e-05,
|
| 487 |
+
"loss": 0.0272,
|
| 488 |
+
"step": 740
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.14,
|
| 492 |
+
"learning_rate": 2.448657187993681e-05,
|
| 493 |
+
"loss": 0.0283,
|
| 494 |
+
"step": 750
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.2,
|
| 498 |
+
"learning_rate": 2.2906793048973144e-05,
|
| 499 |
+
"loss": 0.0208,
|
| 500 |
+
"step": 760
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.25,
|
| 504 |
+
"learning_rate": 2.132701421800948e-05,
|
| 505 |
+
"loss": 0.0439,
|
| 506 |
+
"step": 770
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 4.31,
|
| 510 |
+
"learning_rate": 1.9747235387045815e-05,
|
| 511 |
+
"loss": 0.0339,
|
| 512 |
+
"step": 780
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.36,
|
| 516 |
+
"learning_rate": 1.816745655608215e-05,
|
| 517 |
+
"loss": 0.0298,
|
| 518 |
+
"step": 790
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.42,
|
| 522 |
+
"learning_rate": 1.6587677725118483e-05,
|
| 523 |
+
"loss": 0.0279,
|
| 524 |
+
"step": 800
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 4.47,
|
| 528 |
+
"learning_rate": 1.500789889415482e-05,
|
| 529 |
+
"loss": 0.0227,
|
| 530 |
+
"step": 810
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 4.53,
|
| 534 |
+
"learning_rate": 1.3428120063191154e-05,
|
| 535 |
+
"loss": 0.0215,
|
| 536 |
+
"step": 820
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.58,
|
| 540 |
+
"learning_rate": 1.184834123222749e-05,
|
| 541 |
+
"loss": 0.0276,
|
| 542 |
+
"step": 830
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 4.64,
|
| 546 |
+
"learning_rate": 1.0268562401263823e-05,
|
| 547 |
+
"loss": 0.0356,
|
| 548 |
+
"step": 840
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 4.69,
|
| 552 |
+
"learning_rate": 8.688783570300159e-06,
|
| 553 |
+
"loss": 0.0168,
|
| 554 |
+
"step": 850
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 4.75,
|
| 558 |
+
"learning_rate": 7.109004739336493e-06,
|
| 559 |
+
"loss": 0.0316,
|
| 560 |
+
"step": 860
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.8,
|
| 564 |
+
"learning_rate": 5.529225908372828e-06,
|
| 565 |
+
"loss": 0.0237,
|
| 566 |
+
"step": 870
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 4.86,
|
| 570 |
+
"learning_rate": 3.949447077409163e-06,
|
| 571 |
+
"loss": 0.0207,
|
| 572 |
+
"step": 880
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.91,
|
| 576 |
+
"learning_rate": 2.3696682464454976e-06,
|
| 577 |
+
"loss": 0.0305,
|
| 578 |
+
"step": 890
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 4.97,
|
| 582 |
+
"learning_rate": 7.898894154818326e-07,
|
| 583 |
+
"loss": 0.0327,
|
| 584 |
+
"step": 900
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 5.0,
|
| 588 |
+
"eval_accuracy": 0.9917032698877501,
|
| 589 |
+
"eval_loss": 0.025840837508440018,
|
| 590 |
+
"eval_runtime": 59.7361,
|
| 591 |
+
"eval_samples_per_second": 68.602,
|
| 592 |
+
"eval_steps_per_second": 2.159,
|
| 593 |
+
"step": 905
|
| 594 |
+
}
|
| 595 |
+
],
|
| 596 |
+
"max_steps": 905,
|
| 597 |
+
"num_train_epochs": 5,
|
| 598 |
+
"total_flos": 8.992561039593578e+18,
|
| 599 |
+
"trial_name": null,
|
| 600 |
+
"trial_params": null
|
| 601 |
+
}
|
checkpoint-905/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0105415554a67062681a9094bf7c8619e78a3769da9d376b7d76f9f4a1c2e54c
|
| 3 |
+
size 3503
|