Upload folder using huggingface_hub
Browse files- config.json +50 -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 +400 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "acne",
|
| 13 |
+
"1": "basal cell carcinoma",
|
| 14 |
+
"10": "warts",
|
| 15 |
+
"2": "cold sores",
|
| 16 |
+
"3": "eczema",
|
| 17 |
+
"4": "herpes zoster",
|
| 18 |
+
"5": "hives",
|
| 19 |
+
"6": "lupus",
|
| 20 |
+
"7": "raynauds",
|
| 21 |
+
"8": "tinea",
|
| 22 |
+
"9": "vitiligo"
|
| 23 |
+
},
|
| 24 |
+
"image_size": 224,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"acne": "0",
|
| 29 |
+
"basal cell carcinoma": "1",
|
| 30 |
+
"cold sores": "2",
|
| 31 |
+
"eczema": "3",
|
| 32 |
+
"herpes zoster": "4",
|
| 33 |
+
"hives": "5",
|
| 34 |
+
"lupus": "6",
|
| 35 |
+
"raynauds": "7",
|
| 36 |
+
"tinea": "8",
|
| 37 |
+
"vitiligo": "9",
|
| 38 |
+
"warts": "10"
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_eps": 1e-12,
|
| 41 |
+
"model_type": "vit",
|
| 42 |
+
"num_attention_heads": 12,
|
| 43 |
+
"num_channels": 3,
|
| 44 |
+
"num_hidden_layers": 12,
|
| 45 |
+
"patch_size": 16,
|
| 46 |
+
"problem_type": "single_label_classification",
|
| 47 |
+
"qkv_bias": true,
|
| 48 |
+
"torch_dtype": "float32",
|
| 49 |
+
"transformers_version": "4.30.2"
|
| 50 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d7d5a0593632d032bf998c7032b0c4b7d8b22ca808daf7429da3ef1a9f76c60
|
| 3 |
+
size 686623749
|
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:f15383b73502c9ed0702239e4f5552fc9b0bdda736768051b04f88be2fc759cb
|
| 3 |
+
size 343296365
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ff66960b7e151d2f0ae14c182480b41f103b9a07efe4372c285b23d6c3f12d0
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42da4ab01bfe87a79f57df6272749bf20e2faf078b6c5acc4dba36ec4df83062
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.619316577911377,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-400",
|
| 4 |
+
"epoch": 3.883495145631068,
|
| 5 |
+
"global_step": 400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 0.00019805825242718447,
|
| 13 |
+
"loss": 2.2781,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.19,
|
| 18 |
+
"learning_rate": 0.00019611650485436895,
|
| 19 |
+
"loss": 2.0539,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.24,
|
| 24 |
+
"eval_accuracy": 0.6347826086956522,
|
| 25 |
+
"eval_loss": 1.684175968170166,
|
| 26 |
+
"eval_runtime": 199.797,
|
| 27 |
+
"eval_samples_per_second": 2.302,
|
| 28 |
+
"eval_steps_per_second": 0.29,
|
| 29 |
+
"step": 25
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.29,
|
| 33 |
+
"learning_rate": 0.0001941747572815534,
|
| 34 |
+
"loss": 1.7246,
|
| 35 |
+
"step": 30
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.39,
|
| 39 |
+
"learning_rate": 0.00019223300970873787,
|
| 40 |
+
"loss": 1.6027,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.49,
|
| 45 |
+
"learning_rate": 0.00019029126213592236,
|
| 46 |
+
"loss": 1.4159,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.49,
|
| 51 |
+
"eval_accuracy": 0.6934782608695652,
|
| 52 |
+
"eval_loss": 1.2154264450073242,
|
| 53 |
+
"eval_runtime": 14.461,
|
| 54 |
+
"eval_samples_per_second": 31.81,
|
| 55 |
+
"eval_steps_per_second": 4.011,
|
| 56 |
+
"step": 50
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.58,
|
| 60 |
+
"learning_rate": 0.00018834951456310681,
|
| 61 |
+
"loss": 1.243,
|
| 62 |
+
"step": 60
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.68,
|
| 66 |
+
"learning_rate": 0.00018640776699029127,
|
| 67 |
+
"loss": 1.2138,
|
| 68 |
+
"step": 70
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.73,
|
| 72 |
+
"eval_accuracy": 0.741304347826087,
|
| 73 |
+
"eval_loss": 1.0337247848510742,
|
| 74 |
+
"eval_runtime": 14.5332,
|
| 75 |
+
"eval_samples_per_second": 31.652,
|
| 76 |
+
"eval_steps_per_second": 3.991,
|
| 77 |
+
"step": 75
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.78,
|
| 81 |
+
"learning_rate": 0.00018446601941747576,
|
| 82 |
+
"loss": 1.096,
|
| 83 |
+
"step": 80
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.87,
|
| 87 |
+
"learning_rate": 0.00018252427184466022,
|
| 88 |
+
"loss": 1.012,
|
| 89 |
+
"step": 90
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.97,
|
| 93 |
+
"learning_rate": 0.00018058252427184467,
|
| 94 |
+
"loss": 0.8889,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.97,
|
| 99 |
+
"eval_accuracy": 0.7652173913043478,
|
| 100 |
+
"eval_loss": 0.845034122467041,
|
| 101 |
+
"eval_runtime": 14.4751,
|
| 102 |
+
"eval_samples_per_second": 31.779,
|
| 103 |
+
"eval_steps_per_second": 4.007,
|
| 104 |
+
"step": 100
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.07,
|
| 108 |
+
"learning_rate": 0.00017864077669902913,
|
| 109 |
+
"loss": 0.7514,
|
| 110 |
+
"step": 110
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.17,
|
| 114 |
+
"learning_rate": 0.00017669902912621362,
|
| 115 |
+
"loss": 0.7239,
|
| 116 |
+
"step": 120
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.21,
|
| 120 |
+
"eval_accuracy": 0.6869565217391305,
|
| 121 |
+
"eval_loss": 1.0301238298416138,
|
| 122 |
+
"eval_runtime": 13.8604,
|
| 123 |
+
"eval_samples_per_second": 33.188,
|
| 124 |
+
"eval_steps_per_second": 4.185,
|
| 125 |
+
"step": 125
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.26,
|
| 129 |
+
"learning_rate": 0.00017475728155339805,
|
| 130 |
+
"loss": 0.6558,
|
| 131 |
+
"step": 130
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.36,
|
| 135 |
+
"learning_rate": 0.00017281553398058253,
|
| 136 |
+
"loss": 0.6192,
|
| 137 |
+
"step": 140
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.46,
|
| 141 |
+
"learning_rate": 0.000170873786407767,
|
| 142 |
+
"loss": 0.6241,
|
| 143 |
+
"step": 150
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.46,
|
| 147 |
+
"eval_accuracy": 0.7869565217391304,
|
| 148 |
+
"eval_loss": 0.7646523118019104,
|
| 149 |
+
"eval_runtime": 13.9259,
|
| 150 |
+
"eval_samples_per_second": 33.032,
|
| 151 |
+
"eval_steps_per_second": 4.165,
|
| 152 |
+
"step": 150
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.55,
|
| 156 |
+
"learning_rate": 0.00016893203883495145,
|
| 157 |
+
"loss": 0.6511,
|
| 158 |
+
"step": 160
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.65,
|
| 162 |
+
"learning_rate": 0.00016699029126213594,
|
| 163 |
+
"loss": 0.7607,
|
| 164 |
+
"step": 170
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.7,
|
| 168 |
+
"eval_accuracy": 0.7956521739130434,
|
| 169 |
+
"eval_loss": 0.7208316922187805,
|
| 170 |
+
"eval_runtime": 15.3767,
|
| 171 |
+
"eval_samples_per_second": 29.915,
|
| 172 |
+
"eval_steps_per_second": 3.772,
|
| 173 |
+
"step": 175
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.75,
|
| 177 |
+
"learning_rate": 0.0001650485436893204,
|
| 178 |
+
"loss": 0.6508,
|
| 179 |
+
"step": 180
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.84,
|
| 183 |
+
"learning_rate": 0.00016310679611650485,
|
| 184 |
+
"loss": 0.5474,
|
| 185 |
+
"step": 190
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.94,
|
| 189 |
+
"learning_rate": 0.0001611650485436893,
|
| 190 |
+
"loss": 0.5841,
|
| 191 |
+
"step": 200
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.94,
|
| 195 |
+
"eval_accuracy": 0.7913043478260869,
|
| 196 |
+
"eval_loss": 0.6974421143531799,
|
| 197 |
+
"eval_runtime": 13.8536,
|
| 198 |
+
"eval_samples_per_second": 33.204,
|
| 199 |
+
"eval_steps_per_second": 4.187,
|
| 200 |
+
"step": 200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.04,
|
| 204 |
+
"learning_rate": 0.0001592233009708738,
|
| 205 |
+
"loss": 0.5992,
|
| 206 |
+
"step": 210
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.14,
|
| 210 |
+
"learning_rate": 0.00015728155339805825,
|
| 211 |
+
"loss": 0.3827,
|
| 212 |
+
"step": 220
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.18,
|
| 216 |
+
"eval_accuracy": 0.7869565217391304,
|
| 217 |
+
"eval_loss": 0.6890577077865601,
|
| 218 |
+
"eval_runtime": 14.5884,
|
| 219 |
+
"eval_samples_per_second": 31.532,
|
| 220 |
+
"eval_steps_per_second": 3.976,
|
| 221 |
+
"step": 225
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.23,
|
| 225 |
+
"learning_rate": 0.0001553398058252427,
|
| 226 |
+
"loss": 0.4169,
|
| 227 |
+
"step": 230
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.33,
|
| 231 |
+
"learning_rate": 0.0001533980582524272,
|
| 232 |
+
"loss": 0.3825,
|
| 233 |
+
"step": 240
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.43,
|
| 237 |
+
"learning_rate": 0.00015145631067961166,
|
| 238 |
+
"loss": 0.3534,
|
| 239 |
+
"step": 250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.43,
|
| 243 |
+
"eval_accuracy": 0.8,
|
| 244 |
+
"eval_loss": 0.6881299614906311,
|
| 245 |
+
"eval_runtime": 14.5452,
|
| 246 |
+
"eval_samples_per_second": 31.626,
|
| 247 |
+
"eval_steps_per_second": 3.988,
|
| 248 |
+
"step": 250
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.52,
|
| 252 |
+
"learning_rate": 0.00014951456310679611,
|
| 253 |
+
"loss": 0.2475,
|
| 254 |
+
"step": 260
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.62,
|
| 258 |
+
"learning_rate": 0.0001475728155339806,
|
| 259 |
+
"loss": 0.438,
|
| 260 |
+
"step": 270
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.67,
|
| 264 |
+
"eval_accuracy": 0.7869565217391304,
|
| 265 |
+
"eval_loss": 0.794903039932251,
|
| 266 |
+
"eval_runtime": 14.6276,
|
| 267 |
+
"eval_samples_per_second": 31.447,
|
| 268 |
+
"eval_steps_per_second": 3.965,
|
| 269 |
+
"step": 275
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.72,
|
| 273 |
+
"learning_rate": 0.00014563106796116506,
|
| 274 |
+
"loss": 0.3039,
|
| 275 |
+
"step": 280
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.82,
|
| 279 |
+
"learning_rate": 0.00014368932038834952,
|
| 280 |
+
"loss": 0.2605,
|
| 281 |
+
"step": 290
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.91,
|
| 285 |
+
"learning_rate": 0.000141747572815534,
|
| 286 |
+
"loss": 0.4453,
|
| 287 |
+
"step": 300
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.91,
|
| 291 |
+
"eval_accuracy": 0.7804347826086957,
|
| 292 |
+
"eval_loss": 0.7851635217666626,
|
| 293 |
+
"eval_runtime": 14.6262,
|
| 294 |
+
"eval_samples_per_second": 31.45,
|
| 295 |
+
"eval_steps_per_second": 3.965,
|
| 296 |
+
"step": 300
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.01,
|
| 300 |
+
"learning_rate": 0.00013980582524271846,
|
| 301 |
+
"loss": 0.3196,
|
| 302 |
+
"step": 310
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.11,
|
| 306 |
+
"learning_rate": 0.00013786407766990292,
|
| 307 |
+
"loss": 0.1714,
|
| 308 |
+
"step": 320
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.16,
|
| 312 |
+
"eval_accuracy": 0.7956521739130434,
|
| 313 |
+
"eval_loss": 0.7182856798171997,
|
| 314 |
+
"eval_runtime": 16.1817,
|
| 315 |
+
"eval_samples_per_second": 28.427,
|
| 316 |
+
"eval_steps_per_second": 3.584,
|
| 317 |
+
"step": 325
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.2,
|
| 321 |
+
"learning_rate": 0.0001359223300970874,
|
| 322 |
+
"loss": 0.1467,
|
| 323 |
+
"step": 330
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.3,
|
| 327 |
+
"learning_rate": 0.00013398058252427186,
|
| 328 |
+
"loss": 0.1825,
|
| 329 |
+
"step": 340
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.4,
|
| 333 |
+
"learning_rate": 0.00013203883495145632,
|
| 334 |
+
"loss": 0.1664,
|
| 335 |
+
"step": 350
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.4,
|
| 339 |
+
"eval_accuracy": 0.8,
|
| 340 |
+
"eval_loss": 0.6710854172706604,
|
| 341 |
+
"eval_runtime": 14.7551,
|
| 342 |
+
"eval_samples_per_second": 31.176,
|
| 343 |
+
"eval_steps_per_second": 3.931,
|
| 344 |
+
"step": 350
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.5,
|
| 348 |
+
"learning_rate": 0.00013009708737864078,
|
| 349 |
+
"loss": 0.1266,
|
| 350 |
+
"step": 360
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.59,
|
| 354 |
+
"learning_rate": 0.00012815533980582526,
|
| 355 |
+
"loss": 0.1962,
|
| 356 |
+
"step": 370
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.64,
|
| 360 |
+
"eval_accuracy": 0.8043478260869565,
|
| 361 |
+
"eval_loss": 0.7439975738525391,
|
| 362 |
+
"eval_runtime": 14.5665,
|
| 363 |
+
"eval_samples_per_second": 31.579,
|
| 364 |
+
"eval_steps_per_second": 3.982,
|
| 365 |
+
"step": 375
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.69,
|
| 369 |
+
"learning_rate": 0.00012621359223300972,
|
| 370 |
+
"loss": 0.1609,
|
| 371 |
+
"step": 380
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.79,
|
| 375 |
+
"learning_rate": 0.00012427184466019418,
|
| 376 |
+
"loss": 0.1891,
|
| 377 |
+
"step": 390
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.88,
|
| 381 |
+
"learning_rate": 0.00012233009708737864,
|
| 382 |
+
"loss": 0.1961,
|
| 383 |
+
"step": 400
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.88,
|
| 387 |
+
"eval_accuracy": 0.8391304347826087,
|
| 388 |
+
"eval_loss": 0.619316577911377,
|
| 389 |
+
"eval_runtime": 14.1432,
|
| 390 |
+
"eval_samples_per_second": 32.525,
|
| 391 |
+
"eval_steps_per_second": 4.101,
|
| 392 |
+
"step": 400
|
| 393 |
+
}
|
| 394 |
+
],
|
| 395 |
+
"max_steps": 1030,
|
| 396 |
+
"num_train_epochs": 10,
|
| 397 |
+
"total_flos": 4.929663074408755e+17,
|
| 398 |
+
"trial_name": null,
|
| 399 |
+
"trial_params": null
|
| 400 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8862a1c5b21525e620afc66b300907a9ea89d72423fb81b6d1d942e2cd0a1d24
|
| 3 |
+
size 3899
|