Upload folder using huggingface_hub
Browse files- checkpoint-15740/config.json +42 -0
- checkpoint-15740/optimizer.pt +3 -0
- checkpoint-15740/preprocessor_config.json +22 -0
- checkpoint-15740/pytorch_model.bin +3 -0
- checkpoint-15740/rng_state.pth +3 -0
- checkpoint-15740/scheduler.pt +3 -0
- checkpoint-15740/trainer_state.json +295 -0
- checkpoint-15740/training_args.bin +3 -0
- config.json +12 -12
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
checkpoint-15740/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": "sad",
|
| 13 |
+
"1": "disgust",
|
| 14 |
+
"2": "angry",
|
| 15 |
+
"3": "neutral",
|
| 16 |
+
"4": "fear",
|
| 17 |
+
"5": "surprise",
|
| 18 |
+
"6": "happy"
|
| 19 |
+
},
|
| 20 |
+
"image_size": 224,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"angry": 2,
|
| 25 |
+
"disgust": 1,
|
| 26 |
+
"fear": 4,
|
| 27 |
+
"happy": 6,
|
| 28 |
+
"neutral": 3,
|
| 29 |
+
"sad": 0,
|
| 30 |
+
"surprise": 5
|
| 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": "4.33.3"
|
| 42 |
+
}
|
checkpoint-15740/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac054760eb7be1735767627048f8575bd48082e39a0b4d2c28b4cda232cf91db
|
| 3 |
+
size 686599173
|
checkpoint-15740/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-15740/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcebce67a9ad54f8778a0274d31f904af73025f3eaaf8301f47920f7db29a567
|
| 3 |
+
size 343284077
|
checkpoint-15740/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6da11932a00ba3c22d65cca3ce0eed71ee7fbb6229986476e7b37e57e16eb416
|
| 3 |
+
size 14575
|
checkpoint-15740/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5652bb62c654fcdb2e0edd17c5199c98b9cb10ced1a2e8ec21174e5de298f889
|
| 3 |
+
size 627
|
checkpoint-15740/trainer_state.json
ADDED
|
@@ -0,0 +1,295 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5859972834587097,
|
| 3 |
+
"best_model_checkpoint": "facial_emotions_image_detection/checkpoint-15740",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 15740,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.32,
|
| 13 |
+
"learning_rate": 9.7131931166348e-06,
|
| 14 |
+
"loss": 1.5691,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.64,
|
| 19 |
+
"learning_rate": 9.394518801784576e-06,
|
| 20 |
+
"loss": 1.1566,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.95,
|
| 25 |
+
"learning_rate": 9.075844486934355e-06,
|
| 26 |
+
"loss": 1.005,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.0,
|
| 31 |
+
"eval_accuracy": 0.6603098927294399,
|
| 32 |
+
"eval_loss": 1.0014679431915283,
|
| 33 |
+
"eval_runtime": 113.4351,
|
| 34 |
+
"eval_samples_per_second": 110.944,
|
| 35 |
+
"eval_steps_per_second": 13.876,
|
| 36 |
+
"step": 1574
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.27,
|
| 40 |
+
"learning_rate": 8.757170172084131e-06,
|
| 41 |
+
"loss": 0.9148,
|
| 42 |
+
"step": 2000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.59,
|
| 46 |
+
"learning_rate": 8.438495857233908e-06,
|
| 47 |
+
"loss": 0.8522,
|
| 48 |
+
"step": 2500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.91,
|
| 52 |
+
"learning_rate": 8.119821542383684e-06,
|
| 53 |
+
"loss": 0.8063,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.0,
|
| 58 |
+
"eval_accuracy": 0.7133889551052841,
|
| 59 |
+
"eval_loss": 0.8330217003822327,
|
| 60 |
+
"eval_runtime": 108.2894,
|
| 61 |
+
"eval_samples_per_second": 116.216,
|
| 62 |
+
"eval_steps_per_second": 14.535,
|
| 63 |
+
"step": 3148
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.22,
|
| 67 |
+
"learning_rate": 7.80114722753346e-06,
|
| 68 |
+
"loss": 0.7566,
|
| 69 |
+
"step": 3500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.54,
|
| 73 |
+
"learning_rate": 7.482472912683239e-06,
|
| 74 |
+
"loss": 0.7097,
|
| 75 |
+
"step": 4000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.86,
|
| 79 |
+
"learning_rate": 7.163798597833015e-06,
|
| 80 |
+
"loss": 0.7016,
|
| 81 |
+
"step": 4500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.0,
|
| 85 |
+
"eval_accuracy": 0.7423917361938817,
|
| 86 |
+
"eval_loss": 0.7428602576255798,
|
| 87 |
+
"eval_runtime": 107.858,
|
| 88 |
+
"eval_samples_per_second": 116.681,
|
| 89 |
+
"eval_steps_per_second": 14.593,
|
| 90 |
+
"step": 4722
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.18,
|
| 94 |
+
"learning_rate": 6.8451242829827925e-06,
|
| 95 |
+
"loss": 0.6608,
|
| 96 |
+
"step": 5000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.49,
|
| 100 |
+
"learning_rate": 6.526449968132569e-06,
|
| 101 |
+
"loss": 0.6235,
|
| 102 |
+
"step": 5500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 3.81,
|
| 106 |
+
"learning_rate": 6.207775653282346e-06,
|
| 107 |
+
"loss": 0.6138,
|
| 108 |
+
"step": 6000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.0,
|
| 112 |
+
"eval_accuracy": 0.7507350019864919,
|
| 113 |
+
"eval_loss": 0.7060629725456238,
|
| 114 |
+
"eval_runtime": 109.3785,
|
| 115 |
+
"eval_samples_per_second": 115.059,
|
| 116 |
+
"eval_steps_per_second": 14.39,
|
| 117 |
+
"step": 6296
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.13,
|
| 121 |
+
"learning_rate": 5.889101338432123e-06,
|
| 122 |
+
"loss": 0.5723,
|
| 123 |
+
"step": 6500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.45,
|
| 127 |
+
"learning_rate": 5.5704270235819e-06,
|
| 128 |
+
"loss": 0.5429,
|
| 129 |
+
"step": 7000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.76,
|
| 133 |
+
"learning_rate": 5.251752708731677e-06,
|
| 134 |
+
"loss": 0.5403,
|
| 135 |
+
"step": 7500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 5.0,
|
| 139 |
+
"eval_accuracy": 0.7726658720699245,
|
| 140 |
+
"eval_loss": 0.6644242405891418,
|
| 141 |
+
"eval_runtime": 108.6283,
|
| 142 |
+
"eval_samples_per_second": 115.854,
|
| 143 |
+
"eval_steps_per_second": 14.49,
|
| 144 |
+
"step": 7870
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 5.08,
|
| 148 |
+
"learning_rate": 4.933078393881454e-06,
|
| 149 |
+
"loss": 0.5112,
|
| 150 |
+
"step": 8000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 5.4,
|
| 154 |
+
"learning_rate": 4.61440407903123e-06,
|
| 155 |
+
"loss": 0.4647,
|
| 156 |
+
"step": 8500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.72,
|
| 160 |
+
"learning_rate": 4.295729764181008e-06,
|
| 161 |
+
"loss": 0.4584,
|
| 162 |
+
"step": 9000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 6.0,
|
| 166 |
+
"eval_accuracy": 0.7871275327771157,
|
| 167 |
+
"eval_loss": 0.6358364820480347,
|
| 168 |
+
"eval_runtime": 108.2696,
|
| 169 |
+
"eval_samples_per_second": 116.238,
|
| 170 |
+
"eval_steps_per_second": 14.538,
|
| 171 |
+
"step": 9444
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.04,
|
| 175 |
+
"learning_rate": 3.977055449330784e-06,
|
| 176 |
+
"loss": 0.4567,
|
| 177 |
+
"step": 9500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.35,
|
| 181 |
+
"learning_rate": 3.6583811344805616e-06,
|
| 182 |
+
"loss": 0.4134,
|
| 183 |
+
"step": 10000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.67,
|
| 187 |
+
"learning_rate": 3.339706819630338e-06,
|
| 188 |
+
"loss": 0.3957,
|
| 189 |
+
"step": 10500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.99,
|
| 193 |
+
"learning_rate": 3.021032504780115e-06,
|
| 194 |
+
"loss": 0.3991,
|
| 195 |
+
"step": 11000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 7.0,
|
| 199 |
+
"eval_accuracy": 0.800238379022646,
|
| 200 |
+
"eval_loss": 0.6062497496604919,
|
| 201 |
+
"eval_runtime": 108.4345,
|
| 202 |
+
"eval_samples_per_second": 116.061,
|
| 203 |
+
"eval_steps_per_second": 14.516,
|
| 204 |
+
"step": 11018
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 7.31,
|
| 208 |
+
"learning_rate": 2.702358189929892e-06,
|
| 209 |
+
"loss": 0.3545,
|
| 210 |
+
"step": 11500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 7.62,
|
| 214 |
+
"learning_rate": 2.3836838750796687e-06,
|
| 215 |
+
"loss": 0.3538,
|
| 216 |
+
"step": 12000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 7.94,
|
| 220 |
+
"learning_rate": 2.0650095602294456e-06,
|
| 221 |
+
"loss": 0.3544,
|
| 222 |
+
"step": 12500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 8.0,
|
| 226 |
+
"eval_accuracy": 0.8045292014302742,
|
| 227 |
+
"eval_loss": 0.6008493900299072,
|
| 228 |
+
"eval_runtime": 110.3834,
|
| 229 |
+
"eval_samples_per_second": 114.012,
|
| 230 |
+
"eval_steps_per_second": 14.259,
|
| 231 |
+
"step": 12592
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 8.26,
|
| 235 |
+
"learning_rate": 1.7463352453792225e-06,
|
| 236 |
+
"loss": 0.3183,
|
| 237 |
+
"step": 13000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 8.58,
|
| 241 |
+
"learning_rate": 1.4276609305289997e-06,
|
| 242 |
+
"loss": 0.3218,
|
| 243 |
+
"step": 13500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.89,
|
| 247 |
+
"learning_rate": 1.1089866156787763e-06,
|
| 248 |
+
"loss": 0.3184,
|
| 249 |
+
"step": 14000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 9.0,
|
| 253 |
+
"eval_accuracy": 0.8116805721096544,
|
| 254 |
+
"eval_loss": 0.590340256690979,
|
| 255 |
+
"eval_runtime": 108.9419,
|
| 256 |
+
"eval_samples_per_second": 115.52,
|
| 257 |
+
"eval_steps_per_second": 14.448,
|
| 258 |
+
"step": 14166
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 9.21,
|
| 262 |
+
"learning_rate": 7.903123008285534e-07,
|
| 263 |
+
"loss": 0.3054,
|
| 264 |
+
"step": 14500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 9.53,
|
| 268 |
+
"learning_rate": 4.7163798597833015e-07,
|
| 269 |
+
"loss": 0.2813,
|
| 270 |
+
"step": 15000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.85,
|
| 274 |
+
"learning_rate": 1.5296367112810708e-07,
|
| 275 |
+
"loss": 0.2984,
|
| 276 |
+
"step": 15500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 10.0,
|
| 280 |
+
"eval_accuracy": 0.8162097735399285,
|
| 281 |
+
"eval_loss": 0.5859972834587097,
|
| 282 |
+
"eval_runtime": 111.4622,
|
| 283 |
+
"eval_samples_per_second": 112.908,
|
| 284 |
+
"eval_steps_per_second": 14.121,
|
| 285 |
+
"step": 15740
|
| 286 |
+
}
|
| 287 |
+
],
|
| 288 |
+
"logging_steps": 500,
|
| 289 |
+
"max_steps": 15740,
|
| 290 |
+
"num_train_epochs": 10,
|
| 291 |
+
"save_steps": 500,
|
| 292 |
+
"total_flos": 3.900966581033497e+19,
|
| 293 |
+
"trial_name": null,
|
| 294 |
+
"trial_params": null
|
| 295 |
+
}
|
checkpoint-15740/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88f8d355cab9ef739f5fc476aba7f6e893c6c8f92be3fff90b9d4091956a9dd9
|
| 3 |
+
size 4027
|
config.json
CHANGED
|
@@ -10,24 +10,24 @@
|
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
"0": "sad",
|
| 13 |
-
"1": "
|
| 14 |
-
"2": "
|
| 15 |
-
"3": "
|
| 16 |
-
"4": "
|
| 17 |
-
"5": "
|
| 18 |
-
"6": "
|
| 19 |
},
|
| 20 |
"image_size": 224,
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"intermediate_size": 3072,
|
| 23 |
"label2id": {
|
| 24 |
-
"angry":
|
| 25 |
-
"disgust":
|
| 26 |
-
"fear":
|
| 27 |
-
"happy":
|
| 28 |
-
"neutral":
|
| 29 |
"sad": 0,
|
| 30 |
-
"surprise":
|
| 31 |
},
|
| 32 |
"layer_norm_eps": 1e-12,
|
| 33 |
"model_type": "vit",
|
|
|
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
"0": "sad",
|
| 13 |
+
"1": "disgust",
|
| 14 |
+
"2": "angry",
|
| 15 |
+
"3": "neutral",
|
| 16 |
+
"4": "fear",
|
| 17 |
+
"5": "surprise",
|
| 18 |
+
"6": "happy"
|
| 19 |
},
|
| 20 |
"image_size": 224,
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"intermediate_size": 3072,
|
| 23 |
"label2id": {
|
| 24 |
+
"angry": 2,
|
| 25 |
+
"disgust": 1,
|
| 26 |
+
"fear": 4,
|
| 27 |
+
"happy": 6,
|
| 28 |
+
"neutral": 3,
|
| 29 |
"sad": 0,
|
| 30 |
+
"surprise": 5
|
| 31 |
},
|
| 32 |
"layer_norm_eps": 1e-12,
|
| 33 |
"model_type": "vit",
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343284077
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcebce67a9ad54f8778a0274d31f904af73025f3eaaf8301f47920f7db29a567
|
| 3 |
size 343284077
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88f8d355cab9ef739f5fc476aba7f6e893c6c8f92be3fff90b9d4091956a9dd9
|
| 3 |
size 4027
|