Upload folder using huggingface_hub
Browse files- config.json +145 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- trainer_state.json +145 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-101",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ResNetForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"depths": [
|
| 7 |
+
3,
|
| 8 |
+
4,
|
| 9 |
+
23,
|
| 10 |
+
3
|
| 11 |
+
],
|
| 12 |
+
"downsample_in_bottleneck": false,
|
| 13 |
+
"downsample_in_first_stage": false,
|
| 14 |
+
"embedding_size": 64,
|
| 15 |
+
"hidden_act": "relu",
|
| 16 |
+
"hidden_sizes": [
|
| 17 |
+
256,
|
| 18 |
+
512,
|
| 19 |
+
1024,
|
| 20 |
+
2048
|
| 21 |
+
],
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "LABEL_0",
|
| 24 |
+
"1": "LABEL_1",
|
| 25 |
+
"2": "LABEL_2",
|
| 26 |
+
"3": "LABEL_3",
|
| 27 |
+
"4": "LABEL_4",
|
| 28 |
+
"5": "LABEL_5",
|
| 29 |
+
"6": "LABEL_6",
|
| 30 |
+
"7": "LABEL_7",
|
| 31 |
+
"8": "LABEL_8",
|
| 32 |
+
"9": "LABEL_9",
|
| 33 |
+
"10": "LABEL_10",
|
| 34 |
+
"11": "LABEL_11",
|
| 35 |
+
"12": "LABEL_12",
|
| 36 |
+
"13": "LABEL_13",
|
| 37 |
+
"14": "LABEL_14",
|
| 38 |
+
"15": "LABEL_15",
|
| 39 |
+
"16": "LABEL_16",
|
| 40 |
+
"17": "LABEL_17",
|
| 41 |
+
"18": "LABEL_18",
|
| 42 |
+
"19": "LABEL_19",
|
| 43 |
+
"20": "LABEL_20",
|
| 44 |
+
"21": "LABEL_21",
|
| 45 |
+
"22": "LABEL_22",
|
| 46 |
+
"23": "LABEL_23",
|
| 47 |
+
"24": "LABEL_24",
|
| 48 |
+
"25": "LABEL_25",
|
| 49 |
+
"26": "LABEL_26",
|
| 50 |
+
"27": "LABEL_27",
|
| 51 |
+
"28": "LABEL_28",
|
| 52 |
+
"29": "LABEL_29",
|
| 53 |
+
"30": "LABEL_30",
|
| 54 |
+
"31": "LABEL_31",
|
| 55 |
+
"32": "LABEL_32",
|
| 56 |
+
"33": "LABEL_33",
|
| 57 |
+
"34": "LABEL_34",
|
| 58 |
+
"35": "LABEL_35",
|
| 59 |
+
"36": "LABEL_36",
|
| 60 |
+
"37": "LABEL_37",
|
| 61 |
+
"38": "LABEL_38",
|
| 62 |
+
"39": "LABEL_39",
|
| 63 |
+
"40": "LABEL_40",
|
| 64 |
+
"41": "LABEL_41",
|
| 65 |
+
"42": "LABEL_42",
|
| 66 |
+
"43": "LABEL_43",
|
| 67 |
+
"44": "LABEL_44",
|
| 68 |
+
"45": "LABEL_45",
|
| 69 |
+
"46": "LABEL_46",
|
| 70 |
+
"47": "LABEL_47",
|
| 71 |
+
"48": "LABEL_48",
|
| 72 |
+
"49": "LABEL_49"
|
| 73 |
+
},
|
| 74 |
+
"label2id": {
|
| 75 |
+
"LABEL_0": 0,
|
| 76 |
+
"LABEL_1": 1,
|
| 77 |
+
"LABEL_10": 10,
|
| 78 |
+
"LABEL_11": 11,
|
| 79 |
+
"LABEL_12": 12,
|
| 80 |
+
"LABEL_13": 13,
|
| 81 |
+
"LABEL_14": 14,
|
| 82 |
+
"LABEL_15": 15,
|
| 83 |
+
"LABEL_16": 16,
|
| 84 |
+
"LABEL_17": 17,
|
| 85 |
+
"LABEL_18": 18,
|
| 86 |
+
"LABEL_19": 19,
|
| 87 |
+
"LABEL_2": 2,
|
| 88 |
+
"LABEL_20": 20,
|
| 89 |
+
"LABEL_21": 21,
|
| 90 |
+
"LABEL_22": 22,
|
| 91 |
+
"LABEL_23": 23,
|
| 92 |
+
"LABEL_24": 24,
|
| 93 |
+
"LABEL_25": 25,
|
| 94 |
+
"LABEL_26": 26,
|
| 95 |
+
"LABEL_27": 27,
|
| 96 |
+
"LABEL_28": 28,
|
| 97 |
+
"LABEL_29": 29,
|
| 98 |
+
"LABEL_3": 3,
|
| 99 |
+
"LABEL_30": 30,
|
| 100 |
+
"LABEL_31": 31,
|
| 101 |
+
"LABEL_32": 32,
|
| 102 |
+
"LABEL_33": 33,
|
| 103 |
+
"LABEL_34": 34,
|
| 104 |
+
"LABEL_35": 35,
|
| 105 |
+
"LABEL_36": 36,
|
| 106 |
+
"LABEL_37": 37,
|
| 107 |
+
"LABEL_38": 38,
|
| 108 |
+
"LABEL_39": 39,
|
| 109 |
+
"LABEL_4": 4,
|
| 110 |
+
"LABEL_40": 40,
|
| 111 |
+
"LABEL_41": 41,
|
| 112 |
+
"LABEL_42": 42,
|
| 113 |
+
"LABEL_43": 43,
|
| 114 |
+
"LABEL_44": 44,
|
| 115 |
+
"LABEL_45": 45,
|
| 116 |
+
"LABEL_46": 46,
|
| 117 |
+
"LABEL_47": 47,
|
| 118 |
+
"LABEL_48": 48,
|
| 119 |
+
"LABEL_49": 49,
|
| 120 |
+
"LABEL_5": 5,
|
| 121 |
+
"LABEL_6": 6,
|
| 122 |
+
"LABEL_7": 7,
|
| 123 |
+
"LABEL_8": 8,
|
| 124 |
+
"LABEL_9": 9
|
| 125 |
+
},
|
| 126 |
+
"layer_type": "bottleneck",
|
| 127 |
+
"model_type": "resnet",
|
| 128 |
+
"num_channels": 3,
|
| 129 |
+
"out_features": [
|
| 130 |
+
"stage4"
|
| 131 |
+
],
|
| 132 |
+
"out_indices": [
|
| 133 |
+
4
|
| 134 |
+
],
|
| 135 |
+
"problem_type": "single_label_classification",
|
| 136 |
+
"stage_names": [
|
| 137 |
+
"stem",
|
| 138 |
+
"stage1",
|
| 139 |
+
"stage2",
|
| 140 |
+
"stage3",
|
| 141 |
+
"stage4"
|
| 142 |
+
],
|
| 143 |
+
"torch_dtype": "float32",
|
| 144 |
+
"transformers_version": "4.44.0"
|
| 145 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b8862c8c5adfba7f68691ce92ee88bba45e0939590ad53f0f923ec0d0a548f5
|
| 3 |
+
size 170916112
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"shortest_edge": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.896,
|
| 3 |
+
"best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0548/checkpoints/checkpoint-2331",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2331,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 165.78256225585938,
|
| 14 |
+
"learning_rate": 9.619397662556435e-05,
|
| 15 |
+
"loss": 2.5104,
|
| 16 |
+
"step": 333
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.7874666666666666,
|
| 21 |
+
"eval_loss": 0.7962279319763184,
|
| 22 |
+
"eval_runtime": 12.501,
|
| 23 |
+
"eval_samples_per_second": 299.977,
|
| 24 |
+
"eval_steps_per_second": 4.72,
|
| 25 |
+
"step": 333
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 97.7348403930664,
|
| 30 |
+
"learning_rate": 8.535533905932738e-05,
|
| 31 |
+
"loss": 0.6035,
|
| 32 |
+
"step": 666
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.8616,
|
| 37 |
+
"eval_loss": 0.46331414580345154,
|
| 38 |
+
"eval_runtime": 12.4669,
|
| 39 |
+
"eval_samples_per_second": 300.797,
|
| 40 |
+
"eval_steps_per_second": 4.733,
|
| 41 |
+
"step": 666
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"grad_norm": 106.37476348876953,
|
| 46 |
+
"learning_rate": 6.91341716182545e-05,
|
| 47 |
+
"loss": 0.3475,
|
| 48 |
+
"step": 999
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_accuracy": 0.8842666666666666,
|
| 53 |
+
"eval_loss": 0.3724762499332428,
|
| 54 |
+
"eval_runtime": 12.5478,
|
| 55 |
+
"eval_samples_per_second": 298.858,
|
| 56 |
+
"eval_steps_per_second": 4.702,
|
| 57 |
+
"step": 999
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"grad_norm": 107.25939178466797,
|
| 62 |
+
"learning_rate": 5e-05,
|
| 63 |
+
"loss": 0.2215,
|
| 64 |
+
"step": 1332
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.8904,
|
| 69 |
+
"eval_loss": 0.34392863512039185,
|
| 70 |
+
"eval_runtime": 12.4428,
|
| 71 |
+
"eval_samples_per_second": 301.38,
|
| 72 |
+
"eval_steps_per_second": 4.742,
|
| 73 |
+
"step": 1332
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.0,
|
| 77 |
+
"grad_norm": 67.79757690429688,
|
| 78 |
+
"learning_rate": 3.086582838174551e-05,
|
| 79 |
+
"loss": 0.1488,
|
| 80 |
+
"step": 1665
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_accuracy": 0.8944,
|
| 85 |
+
"eval_loss": 0.346574991941452,
|
| 86 |
+
"eval_runtime": 13.0895,
|
| 87 |
+
"eval_samples_per_second": 286.49,
|
| 88 |
+
"eval_steps_per_second": 4.507,
|
| 89 |
+
"step": 1665
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"grad_norm": 67.08159637451172,
|
| 94 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 95 |
+
"loss": 0.1094,
|
| 96 |
+
"step": 1998
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.8946666666666667,
|
| 101 |
+
"eval_loss": 0.3477937579154968,
|
| 102 |
+
"eval_runtime": 12.6286,
|
| 103 |
+
"eval_samples_per_second": 296.944,
|
| 104 |
+
"eval_steps_per_second": 4.672,
|
| 105 |
+
"step": 1998
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.0,
|
| 109 |
+
"grad_norm": 44.662315368652344,
|
| 110 |
+
"learning_rate": 3.8060233744356633e-06,
|
| 111 |
+
"loss": 0.0843,
|
| 112 |
+
"step": 2331
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 7.0,
|
| 116 |
+
"eval_accuracy": 0.896,
|
| 117 |
+
"eval_loss": 0.3452041745185852,
|
| 118 |
+
"eval_runtime": 12.6166,
|
| 119 |
+
"eval_samples_per_second": 297.229,
|
| 120 |
+
"eval_steps_per_second": 4.676,
|
| 121 |
+
"step": 2331
|
| 122 |
+
}
|
| 123 |
+
],
|
| 124 |
+
"logging_steps": 500,
|
| 125 |
+
"max_steps": 2664,
|
| 126 |
+
"num_input_tokens_seen": 0,
|
| 127 |
+
"num_train_epochs": 8,
|
| 128 |
+
"save_steps": 500,
|
| 129 |
+
"stateful_callbacks": {
|
| 130 |
+
"TrainerControl": {
|
| 131 |
+
"args": {
|
| 132 |
+
"should_epoch_stop": false,
|
| 133 |
+
"should_evaluate": false,
|
| 134 |
+
"should_log": false,
|
| 135 |
+
"should_save": true,
|
| 136 |
+
"should_training_stop": false
|
| 137 |
+
},
|
| 138 |
+
"attributes": {}
|
| 139 |
+
}
|
| 140 |
+
},
|
| 141 |
+
"total_flos": 5.7235004676864e+18,
|
| 142 |
+
"train_batch_size": 64,
|
| 143 |
+
"trial_name": null,
|
| 144 |
+
"trial_params": null
|
| 145 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3253917e3f2dff8bf3a4081e9063dfde7d99fa154c1a0fbeca0143d5d8c6274
|
| 3 |
+
size 5368
|