paul
commited on
Commit
·
88a7f45
1
Parent(s):
07a07f0
Training in progress, epoch 0
Browse files- all_results.json +6 -6
- config.json +19 -16
- preprocessor_config.json +9 -8
- pytorch_model.bin +2 -2
- runs/Jan21_17-25-09_teesta/events.out.tfevents.1674302123.teesta.7894.0 +2 -2
- runs/Jan21_17-44-37_teesta/1674303289.3745122/events.out.tfevents.1674303289.teesta.13319.1 +3 -0
- runs/Jan21_17-44-37_teesta/events.out.tfevents.1674303289.teesta.13319.0 +3 -0
- train_results.json +6 -6
- trainer_state.json +279 -267
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.97,
|
| 3 |
+
"total_flos": 3.206521023309693e+18,
|
| 4 |
+
"train_loss": 0.16232954878360034,
|
| 5 |
+
"train_runtime": 904.221,
|
| 6 |
+
"train_samples_per_second": 45.785,
|
| 7 |
+
"train_steps_per_second": 0.177
|
| 8 |
}
|
config.json
CHANGED
|
@@ -1,36 +1,39 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "angry",
|
| 13 |
"1": "happy",
|
| 14 |
"2": "neutral",
|
| 15 |
"3": "sad"
|
| 16 |
},
|
| 17 |
-
"image_size": 224,
|
| 18 |
-
"initializer_range": 0.02,
|
| 19 |
-
"intermediate_size": 3072,
|
| 20 |
"label2id": {
|
| 21 |
"angry": "0",
|
| 22 |
"happy": "1",
|
| 23 |
"neutral": "2",
|
| 24 |
"sad": "3"
|
| 25 |
},
|
| 26 |
-
"
|
| 27 |
-
"model_type": "
|
| 28 |
-
"num_attention_heads": 12,
|
| 29 |
"num_channels": 3,
|
| 30 |
-
"num_hidden_layers": 12,
|
| 31 |
-
"patch_size": 16,
|
| 32 |
"problem_type": "single_label_classification",
|
| 33 |
-
"qkv_bias": true,
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
"transformers_version": "4.24.0.dev0"
|
| 36 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
"architectures": [
|
| 4 |
+
"ResNetForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"depths": [
|
| 7 |
+
3,
|
| 8 |
+
4,
|
| 9 |
+
6,
|
| 10 |
+
3
|
| 11 |
+
],
|
| 12 |
+
"downsample_in_first_stage": false,
|
| 13 |
+
"embedding_size": 64,
|
| 14 |
+
"hidden_act": "relu",
|
| 15 |
+
"hidden_sizes": [
|
| 16 |
+
256,
|
| 17 |
+
512,
|
| 18 |
+
1024,
|
| 19 |
+
2048
|
| 20 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"id2label": {
|
| 22 |
"0": "angry",
|
| 23 |
"1": "happy",
|
| 24 |
"2": "neutral",
|
| 25 |
"3": "sad"
|
| 26 |
},
|
|
|
|
|
|
|
|
|
|
| 27 |
"label2id": {
|
| 28 |
"angry": "0",
|
| 29 |
"happy": "1",
|
| 30 |
"neutral": "2",
|
| 31 |
"sad": "3"
|
| 32 |
},
|
| 33 |
+
"layer_type": "bottleneck",
|
| 34 |
+
"model_type": "resnet",
|
|
|
|
| 35 |
"num_channels": 3,
|
|
|
|
|
|
|
| 36 |
"problem_type": "single_label_classification",
|
|
|
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
"transformers_version": "4.24.0.dev0"
|
| 39 |
}
|
preprocessor_config.json
CHANGED
|
@@ -1,17 +1,18 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"do_normalize": true,
|
| 3 |
"do_resize": true,
|
| 4 |
-
"feature_extractor_type": "
|
| 5 |
"image_mean": [
|
| 6 |
-
0.
|
| 7 |
-
0.
|
| 8 |
-
0.
|
| 9 |
],
|
| 10 |
"image_std": [
|
| 11 |
-
0.
|
| 12 |
-
0.
|
| 13 |
-
0.
|
| 14 |
],
|
| 15 |
-
"resample":
|
| 16 |
"size": 224
|
| 17 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
"do_normalize": true,
|
| 4 |
"do_resize": true,
|
| 5 |
+
"feature_extractor_type": "ConvNextFeatureExtractor",
|
| 6 |
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
],
|
| 11 |
"image_std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
],
|
| 16 |
+
"resample": 3,
|
| 17 |
"size": 224
|
| 18 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c00f2c4ca471a8278df5c0f5bf23cebbeed07aabaf3380952726b472c47fe270
|
| 3 |
+
size 94389057
|
runs/Jan21_17-25-09_teesta/events.out.tfevents.1674302123.teesta.7894.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d7a23a468d78170e3ce70542197bc01c08d258b92a5d640dbc868667571ceb9
|
| 3 |
+
size 15999
|
runs/Jan21_17-44-37_teesta/1674303289.3745122/events.out.tfevents.1674303289.teesta.13319.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5de44eed53151468731d67e25f2877ce91d9eac0a9abaf82f67060a619df2514
|
| 3 |
+
size 5550
|
runs/Jan21_17-44-37_teesta/events.out.tfevents.1674303289.teesta.13319.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16a66831e7f0ab233ea63ec504bf0b5ebb533a6629adda1fef6093314aa79fea
|
| 3 |
+
size 4236
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.97,
|
| 3 |
+
"total_flos": 3.206521023309693e+18,
|
| 4 |
+
"train_loss": 0.16232954878360034,
|
| 5 |
+
"train_runtime": 904.221,
|
| 6 |
+
"train_samples_per_second": 45.785,
|
| 7 |
+
"train_steps_per_second": 0.177
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,349 +1,361 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "microsoft-resnet-50-cartoon-emotion-detection/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch":
|
| 12 |
-
"eval_accuracy": 0.
|
| 13 |
-
"eval_f1": 0.
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_precision": 0.
|
| 16 |
-
"eval_recall": 0.
|
| 17 |
-
"eval_runtime":
|
| 18 |
-
"eval_samples_per_second":
|
| 19 |
-
"eval_steps_per_second":
|
| 20 |
-
"step":
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 1.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 1.
|
| 26 |
"step": 10
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch":
|
| 30 |
-
"eval_accuracy": 0.
|
| 31 |
-
"eval_f1": 0.
|
| 32 |
-
"eval_loss":
|
| 33 |
-
"eval_precision": 0.
|
| 34 |
-
"eval_recall": 0.
|
| 35 |
-
"eval_runtime":
|
| 36 |
-
"eval_samples_per_second":
|
| 37 |
-
"eval_steps_per_second":
|
| 38 |
-
"step":
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 2.
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss":
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_f1": 0.
|
| 50 |
-
"eval_loss":
|
| 51 |
-
"eval_precision": 0.
|
| 52 |
-
"eval_recall": 0.
|
| 53 |
-
"eval_runtime":
|
| 54 |
-
"eval_samples_per_second":
|
| 55 |
-
"eval_steps_per_second":
|
| 56 |
-
"step":
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
"eval_loss": 1.3271173238754272,
|
| 63 |
-
"eval_precision": 0.7011109363353202,
|
| 64 |
-
"eval_recall": 0.3738532110091743,
|
| 65 |
-
"eval_runtime": 5.6438,
|
| 66 |
-
"eval_samples_per_second": 77.253,
|
| 67 |
-
"eval_steps_per_second": 1.24,
|
| 68 |
-
"step": 28
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 4.29,
|
| 72 |
-
"learning_rate": 0.00010476190476190477,
|
| 73 |
-
"loss": 1.3344,
|
| 74 |
"step": 30
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"eval_accuracy": 0.
|
| 79 |
-
"eval_f1": 0.
|
| 80 |
-
"eval_loss":
|
| 81 |
-
"eval_precision": 0.
|
| 82 |
-
"eval_recall": 0.
|
| 83 |
-
"eval_runtime":
|
| 84 |
-
"eval_samples_per_second":
|
| 85 |
-
"eval_steps_per_second":
|
| 86 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"
|
| 91 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
"step": 40
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch":
|
| 96 |
-
"eval_accuracy": 0.
|
| 97 |
-
"eval_f1": 0.
|
| 98 |
-
"eval_loss":
|
| 99 |
-
"eval_precision": 0.
|
| 100 |
-
"eval_recall": 0.
|
| 101 |
-
"eval_runtime":
|
| 102 |
-
"eval_samples_per_second":
|
| 103 |
-
"eval_steps_per_second":
|
| 104 |
-
"step":
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"
|
| 109 |
-
"
|
| 110 |
-
"eval_loss": 1.2649825811386108,
|
| 111 |
-
"eval_precision": 0.49930570990337153,
|
| 112 |
-
"eval_recall": 0.4426605504587156,
|
| 113 |
-
"eval_runtime": 5.7091,
|
| 114 |
-
"eval_samples_per_second": 76.37,
|
| 115 |
-
"eval_steps_per_second": 1.226,
|
| 116 |
-
"step": 49
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 7.14,
|
| 120 |
-
"learning_rate": 8.571428571428571e-05,
|
| 121 |
-
"loss": 1.2692,
|
| 122 |
"step": 50
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"eval_accuracy": 0.
|
| 127 |
-
"eval_f1": 0.
|
| 128 |
-
"eval_loss":
|
| 129 |
-
"eval_precision": 0.
|
| 130 |
-
"eval_recall": 0.
|
| 131 |
-
"eval_runtime":
|
| 132 |
-
"eval_samples_per_second":
|
| 133 |
-
"eval_steps_per_second":
|
| 134 |
"step": 56
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch":
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss":
|
| 140 |
"step": 60
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch":
|
| 144 |
-
"eval_accuracy": 0.
|
| 145 |
-
"eval_f1": 0.
|
| 146 |
-
"eval_loss":
|
| 147 |
-
"eval_precision": 0.
|
| 148 |
-
"eval_recall": 0.
|
| 149 |
-
"eval_runtime":
|
| 150 |
-
"eval_samples_per_second":
|
| 151 |
-
"eval_steps_per_second":
|
| 152 |
-
"step":
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch":
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss":
|
| 158 |
"step": 70
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch":
|
| 162 |
-
"eval_accuracy": 0.
|
| 163 |
-
"eval_f1": 0.
|
| 164 |
-
"eval_loss":
|
| 165 |
-
"eval_precision": 0.
|
| 166 |
-
"eval_recall": 0.
|
| 167 |
-
"eval_runtime":
|
| 168 |
-
"eval_samples_per_second":
|
| 169 |
-
"eval_steps_per_second":
|
| 170 |
-
"step":
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"
|
| 175 |
-
"
|
| 176 |
-
"
|
| 177 |
-
"eval_precision": 0.6977269943419414,
|
| 178 |
-
"eval_recall": 0.5137614678899083,
|
| 179 |
-
"eval_runtime": 5.9101,
|
| 180 |
-
"eval_samples_per_second": 73.772,
|
| 181 |
-
"eval_steps_per_second": 1.184,
|
| 182 |
-
"step": 77
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch":
|
| 186 |
-
"
|
| 187 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 188 |
"step": 80
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"eval_accuracy": 0.
|
| 193 |
-
"eval_f1": 0.
|
| 194 |
-
"eval_loss":
|
| 195 |
-
"eval_precision": 0.
|
| 196 |
-
"eval_recall": 0.
|
| 197 |
-
"eval_runtime":
|
| 198 |
-
"eval_samples_per_second":
|
| 199 |
-
"eval_steps_per_second":
|
| 200 |
-
"step":
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch":
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss":
|
| 206 |
"step": 90
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch":
|
| 210 |
-
"eval_accuracy": 0.
|
| 211 |
-
"eval_f1": 0.
|
| 212 |
-
"eval_loss":
|
| 213 |
-
"eval_precision": 0.
|
| 214 |
-
"eval_recall": 0.
|
| 215 |
-
"eval_runtime":
|
| 216 |
-
"eval_samples_per_second":
|
| 217 |
-
"eval_steps_per_second":
|
| 218 |
-
"step":
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch":
|
| 222 |
-
"
|
| 223 |
-
"
|
| 224 |
-
"eval_loss": 1.102858066558838,
|
| 225 |
-
"eval_precision": 0.4585875088630616,
|
| 226 |
-
"eval_recall": 0.5527522935779816,
|
| 227 |
-
"eval_runtime": 5.6798,
|
| 228 |
-
"eval_samples_per_second": 76.764,
|
| 229 |
-
"eval_steps_per_second": 1.232,
|
| 230 |
-
"step": 98
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 14.29,
|
| 234 |
-
"learning_rate": 3.809523809523809e-05,
|
| 235 |
-
"loss": 1.0763,
|
| 236 |
"step": 100
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch":
|
| 240 |
-
"eval_accuracy": 0.
|
| 241 |
-
"eval_f1": 0.
|
| 242 |
-
"eval_loss":
|
| 243 |
-
"eval_precision": 0.
|
| 244 |
-
"eval_recall": 0.
|
| 245 |
-
"eval_runtime":
|
| 246 |
-
"eval_samples_per_second":
|
| 247 |
-
"eval_steps_per_second":
|
| 248 |
-
"step":
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch":
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss":
|
| 254 |
"step": 110
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch":
|
| 258 |
-
"eval_accuracy": 0.
|
| 259 |
-
"eval_f1": 0.
|
| 260 |
-
"eval_loss":
|
| 261 |
-
"eval_precision": 0.
|
| 262 |
-
"eval_recall": 0.
|
| 263 |
-
"eval_runtime": 5.
|
| 264 |
-
"eval_samples_per_second":
|
| 265 |
-
"eval_steps_per_second":
|
| 266 |
"step": 112
|
| 267 |
},
|
| 268 |
{
|
| 269 |
-
"epoch":
|
| 270 |
-
"
|
| 271 |
-
"
|
| 272 |
-
"
|
| 273 |
-
"eval_precision": 0.597456441198868,
|
| 274 |
-
"eval_recall": 0.5527522935779816,
|
| 275 |
-
"eval_runtime": 5.7578,
|
| 276 |
-
"eval_samples_per_second": 75.723,
|
| 277 |
-
"eval_steps_per_second": 1.216,
|
| 278 |
-
"step": 119
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch":
|
| 282 |
-
"
|
| 283 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 284 |
"step": 120
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch":
|
| 288 |
-
"eval_accuracy": 0.
|
| 289 |
-
"eval_f1": 0.
|
| 290 |
-
"eval_loss":
|
| 291 |
-
"eval_precision": 0.
|
| 292 |
-
"eval_recall": 0.
|
| 293 |
-
"eval_runtime":
|
| 294 |
-
"eval_samples_per_second":
|
| 295 |
-
"eval_steps_per_second":
|
| 296 |
-
"step":
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch":
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss":
|
| 302 |
"step": 130
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch":
|
| 306 |
-
"eval_accuracy": 0.
|
| 307 |
-
"eval_f1": 0.
|
| 308 |
-
"eval_loss":
|
| 309 |
-
"eval_precision": 0.
|
| 310 |
-
"eval_recall": 0.
|
| 311 |
-
"eval_runtime":
|
| 312 |
-
"eval_samples_per_second":
|
| 313 |
-
"eval_steps_per_second":
|
| 314 |
-
"step":
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch":
|
| 318 |
-
"learning_rate":
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 140
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch":
|
| 324 |
-
"eval_accuracy": 0.
|
| 325 |
-
"eval_f1": 0.
|
| 326 |
-
"eval_loss":
|
| 327 |
-
"eval_precision": 0.
|
| 328 |
-
"eval_recall": 0.
|
| 329 |
-
"eval_runtime":
|
| 330 |
-
"eval_samples_per_second":
|
| 331 |
-
"eval_steps_per_second":
|
| 332 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch":
|
| 336 |
-
"
|
| 337 |
-
"
|
| 338 |
-
"
|
| 339 |
-
"
|
| 340 |
-
"
|
| 341 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 342 |
}
|
| 343 |
],
|
| 344 |
-
"max_steps":
|
| 345 |
"num_train_epochs": 20,
|
| 346 |
-
"total_flos":
|
| 347 |
"trial_name": null,
|
| 348 |
"trial_params": null
|
| 349 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.926605504587156,
|
| 3 |
+
"best_model_checkpoint": "microsoft-resnet-50-cartoon-emotion-detection/checkpoint-104",
|
| 4 |
+
"epoch": 19.96969696969697,
|
| 5 |
+
"global_step": 160,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.97,
|
| 12 |
+
"eval_accuracy": 0.5688073394495413,
|
| 13 |
+
"eval_f1": 0.5205063195793977,
|
| 14 |
+
"eval_loss": 1.0349371433258057,
|
| 15 |
+
"eval_precision": 0.6064329401485365,
|
| 16 |
+
"eval_recall": 0.5688073394495413,
|
| 17 |
+
"eval_runtime": 5.2245,
|
| 18 |
+
"eval_samples_per_second": 20.863,
|
| 19 |
+
"eval_steps_per_second": 0.383,
|
| 20 |
+
"step": 8
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.24,
|
| 24 |
+
"learning_rate": 7.500000000000001e-05,
|
| 25 |
+
"loss": 1.3234,
|
| 26 |
"step": 10
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 1.97,
|
| 30 |
+
"eval_accuracy": 0.7155963302752294,
|
| 31 |
+
"eval_f1": 0.7103044003811094,
|
| 32 |
+
"eval_loss": 0.6375869512557983,
|
| 33 |
+
"eval_precision": 0.7219158744471064,
|
| 34 |
+
"eval_recall": 0.7155963302752294,
|
| 35 |
+
"eval_runtime": 4.2955,
|
| 36 |
+
"eval_samples_per_second": 25.376,
|
| 37 |
+
"eval_steps_per_second": 0.466,
|
| 38 |
+
"step": 16
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 2.48,
|
| 42 |
+
"learning_rate": 0.00011666666666666667,
|
| 43 |
+
"loss": 0.6646,
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 2.97,
|
| 48 |
+
"eval_accuracy": 0.8440366972477065,
|
| 49 |
+
"eval_f1": 0.8433607463583995,
|
| 50 |
+
"eval_loss": 0.43562328815460205,
|
| 51 |
+
"eval_precision": 0.8464833894577979,
|
| 52 |
+
"eval_recall": 0.8440366972477065,
|
| 53 |
+
"eval_runtime": 4.4756,
|
| 54 |
+
"eval_samples_per_second": 24.354,
|
| 55 |
+
"eval_steps_per_second": 0.447,
|
| 56 |
+
"step": 24
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.73,
|
| 60 |
+
"learning_rate": 0.00010833333333333334,
|
| 61 |
+
"loss": 0.2376,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
"step": 30
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 3.97,
|
| 66 |
+
"eval_accuracy": 0.8899082568807339,
|
| 67 |
+
"eval_f1": 0.8908603960857651,
|
| 68 |
+
"eval_loss": 0.2919904291629791,
|
| 69 |
+
"eval_precision": 0.8996439968089349,
|
| 70 |
+
"eval_recall": 0.8899082568807339,
|
| 71 |
+
"eval_runtime": 4.3506,
|
| 72 |
+
"eval_samples_per_second": 25.054,
|
| 73 |
+
"eval_steps_per_second": 0.46,
|
| 74 |
+
"step": 32
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.97,
|
| 78 |
+
"learning_rate": 0.0001,
|
| 79 |
+
"loss": 0.0977,
|
| 80 |
+
"step": 40
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 4.97,
|
| 84 |
+
"eval_accuracy": 0.8532110091743119,
|
| 85 |
+
"eval_f1": 0.8525250020662865,
|
| 86 |
+
"eval_loss": 0.35606762766838074,
|
| 87 |
+
"eval_precision": 0.8528657393706224,
|
| 88 |
+
"eval_recall": 0.8532110091743119,
|
| 89 |
+
"eval_runtime": 4.3072,
|
| 90 |
+
"eval_samples_per_second": 25.306,
|
| 91 |
+
"eval_steps_per_second": 0.464,
|
| 92 |
"step": 40
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 5.97,
|
| 96 |
+
"eval_accuracy": 0.8807339449541285,
|
| 97 |
+
"eval_f1": 0.8809735026706942,
|
| 98 |
+
"eval_loss": 0.3267204165458679,
|
| 99 |
+
"eval_precision": 0.8815679733110926,
|
| 100 |
+
"eval_recall": 0.8807339449541285,
|
| 101 |
+
"eval_runtime": 4.3611,
|
| 102 |
+
"eval_samples_per_second": 24.994,
|
| 103 |
+
"eval_steps_per_second": 0.459,
|
| 104 |
+
"step": 48
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.24,
|
| 108 |
+
"learning_rate": 9.166666666666667e-05,
|
| 109 |
+
"loss": 0.0422,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
"step": 50
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 6.97,
|
| 114 |
+
"eval_accuracy": 0.8807339449541285,
|
| 115 |
+
"eval_f1": 0.8758890667147549,
|
| 116 |
+
"eval_loss": 0.34823524951934814,
|
| 117 |
+
"eval_precision": 0.877448829794359,
|
| 118 |
+
"eval_recall": 0.8807339449541285,
|
| 119 |
+
"eval_runtime": 4.2385,
|
| 120 |
+
"eval_samples_per_second": 25.717,
|
| 121 |
+
"eval_steps_per_second": 0.472,
|
| 122 |
"step": 56
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 7.48,
|
| 126 |
+
"learning_rate": 8.333333333333333e-05,
|
| 127 |
+
"loss": 0.0352,
|
| 128 |
"step": 60
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 7.97,
|
| 132 |
+
"eval_accuracy": 0.8807339449541285,
|
| 133 |
+
"eval_f1": 0.8769527912936894,
|
| 134 |
+
"eval_loss": 0.296451598405838,
|
| 135 |
+
"eval_precision": 0.878291958985429,
|
| 136 |
+
"eval_recall": 0.8807339449541285,
|
| 137 |
+
"eval_runtime": 6.3259,
|
| 138 |
+
"eval_samples_per_second": 17.231,
|
| 139 |
+
"eval_steps_per_second": 0.316,
|
| 140 |
+
"step": 64
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 8.73,
|
| 144 |
+
"learning_rate": 7.500000000000001e-05,
|
| 145 |
+
"loss": 0.0324,
|
| 146 |
"step": 70
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 8.97,
|
| 150 |
+
"eval_accuracy": 0.8990825688073395,
|
| 151 |
+
"eval_f1": 0.9006792586174571,
|
| 152 |
+
"eval_loss": 0.33714091777801514,
|
| 153 |
+
"eval_precision": 0.9127208085351091,
|
| 154 |
+
"eval_recall": 0.8990825688073395,
|
| 155 |
+
"eval_runtime": 4.2915,
|
| 156 |
+
"eval_samples_per_second": 25.399,
|
| 157 |
+
"eval_steps_per_second": 0.466,
|
| 158 |
+
"step": 72
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 9.97,
|
| 162 |
+
"learning_rate": 6.666666666666667e-05,
|
| 163 |
+
"loss": 0.0308,
|
| 164 |
+
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 9.97,
|
| 168 |
+
"eval_accuracy": 0.8715596330275229,
|
| 169 |
+
"eval_f1": 0.8741519870271233,
|
| 170 |
+
"eval_loss": 0.3839414417743683,
|
| 171 |
+
"eval_precision": 0.8884073716401094,
|
| 172 |
+
"eval_recall": 0.8715596330275229,
|
| 173 |
+
"eval_runtime": 4.2989,
|
| 174 |
+
"eval_samples_per_second": 25.355,
|
| 175 |
+
"eval_steps_per_second": 0.465,
|
| 176 |
"step": 80
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 10.97,
|
| 180 |
+
"eval_accuracy": 0.8990825688073395,
|
| 181 |
+
"eval_f1": 0.8986747527591001,
|
| 182 |
+
"eval_loss": 0.31560054421424866,
|
| 183 |
+
"eval_precision": 0.9002089387809372,
|
| 184 |
+
"eval_recall": 0.8990825688073395,
|
| 185 |
+
"eval_runtime": 4.2045,
|
| 186 |
+
"eval_samples_per_second": 25.925,
|
| 187 |
+
"eval_steps_per_second": 0.476,
|
| 188 |
+
"step": 88
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 11.24,
|
| 192 |
+
"learning_rate": 5.833333333333333e-05,
|
| 193 |
+
"loss": 0.0208,
|
| 194 |
"step": 90
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 11.97,
|
| 198 |
+
"eval_accuracy": 0.8899082568807339,
|
| 199 |
+
"eval_f1": 0.8914240127642601,
|
| 200 |
+
"eval_loss": 0.3775542974472046,
|
| 201 |
+
"eval_precision": 0.9030201242971294,
|
| 202 |
+
"eval_recall": 0.8899082568807339,
|
| 203 |
+
"eval_runtime": 4.4087,
|
| 204 |
+
"eval_samples_per_second": 24.724,
|
| 205 |
+
"eval_steps_per_second": 0.454,
|
| 206 |
+
"step": 96
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 12.48,
|
| 210 |
+
"learning_rate": 5e-05,
|
| 211 |
+
"loss": 0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 212 |
"step": 100
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 12.97,
|
| 216 |
+
"eval_accuracy": 0.926605504587156,
|
| 217 |
+
"eval_f1": 0.9262786556364538,
|
| 218 |
+
"eval_loss": 0.3406970798969269,
|
| 219 |
+
"eval_precision": 0.9271816691042857,
|
| 220 |
+
"eval_recall": 0.926605504587156,
|
| 221 |
+
"eval_runtime": 4.324,
|
| 222 |
+
"eval_samples_per_second": 25.208,
|
| 223 |
+
"eval_steps_per_second": 0.463,
|
| 224 |
+
"step": 104
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 13.73,
|
| 228 |
+
"learning_rate": 4.1666666666666665e-05,
|
| 229 |
+
"loss": 0.0165,
|
| 230 |
"step": 110
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 13.97,
|
| 234 |
+
"eval_accuracy": 0.8990825688073395,
|
| 235 |
+
"eval_f1": 0.8983956662694428,
|
| 236 |
+
"eval_loss": 0.3158816397190094,
|
| 237 |
+
"eval_precision": 0.8980817347789825,
|
| 238 |
+
"eval_recall": 0.8990825688073395,
|
| 239 |
+
"eval_runtime": 5.3633,
|
| 240 |
+
"eval_samples_per_second": 20.323,
|
| 241 |
+
"eval_steps_per_second": 0.373,
|
| 242 |
"step": 112
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 14.97,
|
| 246 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 247 |
+
"loss": 0.0165,
|
| 248 |
+
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 14.97,
|
| 252 |
+
"eval_accuracy": 0.8899082568807339,
|
| 253 |
+
"eval_f1": 0.8921075361735258,
|
| 254 |
+
"eval_loss": 0.3500370979309082,
|
| 255 |
+
"eval_precision": 0.8997053099805394,
|
| 256 |
+
"eval_recall": 0.8899082568807339,
|
| 257 |
+
"eval_runtime": 4.3771,
|
| 258 |
+
"eval_samples_per_second": 24.902,
|
| 259 |
+
"eval_steps_per_second": 0.457,
|
| 260 |
"step": 120
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 15.97,
|
| 264 |
+
"eval_accuracy": 0.8990825688073395,
|
| 265 |
+
"eval_f1": 0.8999561449878029,
|
| 266 |
+
"eval_loss": 0.3516785204410553,
|
| 267 |
+
"eval_precision": 0.9059255297288804,
|
| 268 |
+
"eval_recall": 0.8990825688073395,
|
| 269 |
+
"eval_runtime": 4.6257,
|
| 270 |
+
"eval_samples_per_second": 23.564,
|
| 271 |
+
"eval_steps_per_second": 0.432,
|
| 272 |
+
"step": 128
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 16.24,
|
| 276 |
+
"learning_rate": 2.5e-05,
|
| 277 |
+
"loss": 0.0158,
|
| 278 |
"step": 130
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 16.97,
|
| 282 |
+
"eval_accuracy": 0.8899082568807339,
|
| 283 |
+
"eval_f1": 0.8891290687445018,
|
| 284 |
+
"eval_loss": 0.3615852892398834,
|
| 285 |
+
"eval_precision": 0.8909895150720838,
|
| 286 |
+
"eval_recall": 0.8899082568807339,
|
| 287 |
+
"eval_runtime": 4.2685,
|
| 288 |
+
"eval_samples_per_second": 25.536,
|
| 289 |
+
"eval_steps_per_second": 0.469,
|
| 290 |
+
"step": 136
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"epoch": 17.48,
|
| 294 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 295 |
+
"loss": 0.0131,
|
| 296 |
"step": 140
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 17.97,
|
| 300 |
+
"eval_accuracy": 0.9174311926605505,
|
| 301 |
+
"eval_f1": 0.9182514283005002,
|
| 302 |
+
"eval_loss": 0.3539947271347046,
|
| 303 |
+
"eval_precision": 0.9225702791541971,
|
| 304 |
+
"eval_recall": 0.9174311926605505,
|
| 305 |
+
"eval_runtime": 4.3473,
|
| 306 |
+
"eval_samples_per_second": 25.073,
|
| 307 |
+
"eval_steps_per_second": 0.46,
|
| 308 |
+
"step": 144
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 18.73,
|
| 312 |
+
"learning_rate": 8.333333333333334e-06,
|
| 313 |
+
"loss": 0.0169,
|
| 314 |
+
"step": 150
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 18.97,
|
| 318 |
+
"eval_accuracy": 0.8990825688073395,
|
| 319 |
+
"eval_f1": 0.8991347225185501,
|
| 320 |
+
"eval_loss": 0.3490186631679535,
|
| 321 |
+
"eval_precision": 0.9028663592209193,
|
| 322 |
+
"eval_recall": 0.8990825688073395,
|
| 323 |
+
"eval_runtime": 4.3359,
|
| 324 |
+
"eval_samples_per_second": 25.139,
|
| 325 |
+
"eval_steps_per_second": 0.461,
|
| 326 |
+
"step": 152
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 19.97,
|
| 330 |
+
"learning_rate": 0.0,
|
| 331 |
+
"loss": 0.0138,
|
| 332 |
+
"step": 160
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 19.97,
|
| 336 |
+
"eval_accuracy": 0.908256880733945,
|
| 337 |
+
"eval_f1": 0.908998108752599,
|
| 338 |
+
"eval_loss": 0.34498509764671326,
|
| 339 |
+
"eval_precision": 0.9150937979717397,
|
| 340 |
+
"eval_recall": 0.908256880733945,
|
| 341 |
+
"eval_runtime": 4.3055,
|
| 342 |
+
"eval_samples_per_second": 25.316,
|
| 343 |
+
"eval_steps_per_second": 0.465,
|
| 344 |
+
"step": 160
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 19.97,
|
| 348 |
+
"step": 160,
|
| 349 |
+
"total_flos": 3.206521023309693e+18,
|
| 350 |
+
"train_loss": 0.16232954878360034,
|
| 351 |
+
"train_runtime": 904.221,
|
| 352 |
+
"train_samples_per_second": 45.785,
|
| 353 |
+
"train_steps_per_second": 0.177
|
| 354 |
}
|
| 355 |
],
|
| 356 |
+
"max_steps": 160,
|
| 357 |
"num_train_epochs": 20,
|
| 358 |
+
"total_flos": 3.206521023309693e+18,
|
| 359 |
"trial_name": null,
|
| 360 |
"trial_params": null
|
| 361 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3439
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d6da71bdf8b24b73dceb8f55e2fc28d5c448d4ba3c1a73226d516a72ad9b7b2
|
| 3 |
size 3439
|