Upload folder using huggingface_hub
Browse files- checkpoint-29100/config.json +170 -0
- checkpoint-29100/model.safetensors +3 -0
- checkpoint-29100/optimizer.pt +3 -0
- checkpoint-29100/preprocessor_config.json +22 -0
- checkpoint-29100/rng_state.pth +3 -0
- checkpoint-29100/scheduler.pt +3 -0
- checkpoint-29100/trainer_state.json +1439 -0
- checkpoint-29100/training_args.bin +3 -0
- config.json +135 -135
- model.safetensors +1 -1
- training_args.bin +2 -2
checkpoint-29100/config.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Afghan",
|
| 13 |
+
"1": "African Wild Dog",
|
| 14 |
+
"2": "Airedale",
|
| 15 |
+
"3": "American Spaniel",
|
| 16 |
+
"4": "American Hairless",
|
| 17 |
+
"5": "American Spaniel",
|
| 18 |
+
"6": "Basenji",
|
| 19 |
+
"7": "Basset",
|
| 20 |
+
"8": "Beagle",
|
| 21 |
+
"9": "Bearded Collie",
|
| 22 |
+
"10": "Bermaise",
|
| 23 |
+
"11": "Bichon Frise",
|
| 24 |
+
"12": "Blenheim",
|
| 25 |
+
"13": "Bloodhound",
|
| 26 |
+
"14": "Bluetick",
|
| 27 |
+
"15": "Border Collie",
|
| 28 |
+
"16": "Borzoi",
|
| 29 |
+
"17": "Boston Terrier",
|
| 30 |
+
"18": "Boxer",
|
| 31 |
+
"19": "Bull Mastiff",
|
| 32 |
+
"20": "Bull Terrier",
|
| 33 |
+
"21": "Bulldog",
|
| 34 |
+
"22": "Cairn",
|
| 35 |
+
"23": "Chihuahua",
|
| 36 |
+
"24": "Chinese Crested",
|
| 37 |
+
"25": "Chow",
|
| 38 |
+
"26": "Clumber",
|
| 39 |
+
"27": "Cockapoo",
|
| 40 |
+
"28": "Cocker",
|
| 41 |
+
"29": "Collie",
|
| 42 |
+
"30": "Corgi",
|
| 43 |
+
"31": "Coyote",
|
| 44 |
+
"32": "Dalmation",
|
| 45 |
+
"33": "Dhole",
|
| 46 |
+
"34": "Dingo",
|
| 47 |
+
"35": "Doberman",
|
| 48 |
+
"36": "Elk Hound",
|
| 49 |
+
"37": "French Bulldog",
|
| 50 |
+
"38": "German Sheperd",
|
| 51 |
+
"39": "Golden Retriever",
|
| 52 |
+
"40": "Great Dane",
|
| 53 |
+
"41": "Great Perenees",
|
| 54 |
+
"42": "Greyhound",
|
| 55 |
+
"43": "Groenendael",
|
| 56 |
+
"44": "Irish Spaniel",
|
| 57 |
+
"45": "Irish Wolfhound",
|
| 58 |
+
"46": "Japanese Spaniel",
|
| 59 |
+
"47": "Komondor",
|
| 60 |
+
"48": "Labradoodle",
|
| 61 |
+
"49": "Labrador",
|
| 62 |
+
"50": "Lhasa",
|
| 63 |
+
"51": "Malinois",
|
| 64 |
+
"52": "Maltese",
|
| 65 |
+
"53": "Mex Hairless",
|
| 66 |
+
"54": "Newfoundland",
|
| 67 |
+
"55": "Pekinese",
|
| 68 |
+
"56": "Pit Bull",
|
| 69 |
+
"57": "Pomeranian",
|
| 70 |
+
"58": "Poodle",
|
| 71 |
+
"59": "Pug",
|
| 72 |
+
"60": "Rhodesian",
|
| 73 |
+
"61": "Rottweiler",
|
| 74 |
+
"62": "Saint Bernard",
|
| 75 |
+
"63": "Schnauzer",
|
| 76 |
+
"64": "Scotch Terrier",
|
| 77 |
+
"65": "Shar_Pei",
|
| 78 |
+
"66": "Shiba Inu",
|
| 79 |
+
"67": "Shih-Tzu",
|
| 80 |
+
"68": "Siberian Husky",
|
| 81 |
+
"69": "Vizsla",
|
| 82 |
+
"70": "Yorkie"
|
| 83 |
+
},
|
| 84 |
+
"image_size": 224,
|
| 85 |
+
"initializer_range": 0.02,
|
| 86 |
+
"intermediate_size": 3072,
|
| 87 |
+
"label2id": {
|
| 88 |
+
"Afghan": 0,
|
| 89 |
+
"African Wild Dog": 1,
|
| 90 |
+
"Airedale": 2,
|
| 91 |
+
"American Spaniel": 3,
|
| 92 |
+
"American Hairless": 4,
|
| 93 |
+
"American Spaniel": 5,
|
| 94 |
+
"Basenji": 6,
|
| 95 |
+
"Basset": 7,
|
| 96 |
+
"Beagle": 8,
|
| 97 |
+
"Bearded Collie": 9,
|
| 98 |
+
"Bermaise": 10,
|
| 99 |
+
"Bichon Frise": 11,
|
| 100 |
+
"Blenheim": 12,
|
| 101 |
+
"Bloodhound": 13,
|
| 102 |
+
"Bluetick": 14,
|
| 103 |
+
"Border Collie": 15,
|
| 104 |
+
"Borzoi": 16,
|
| 105 |
+
"Boston Terrier": 17,
|
| 106 |
+
"Boxer": 18,
|
| 107 |
+
"Bull Mastiff": 19,
|
| 108 |
+
"Bull Terrier": 20,
|
| 109 |
+
"Bulldog": 21,
|
| 110 |
+
"Cairn": 22,
|
| 111 |
+
"Chihuahua": 23,
|
| 112 |
+
"Chinese Crested": 24,
|
| 113 |
+
"Chow": 25,
|
| 114 |
+
"Clumber": 26,
|
| 115 |
+
"Cockapoo": 27,
|
| 116 |
+
"Cocker": 28,
|
| 117 |
+
"Collie": 29,
|
| 118 |
+
"Corgi": 30,
|
| 119 |
+
"Coyote": 31,
|
| 120 |
+
"Dalmation": 32,
|
| 121 |
+
"Dhole": 33,
|
| 122 |
+
"Dingo": 34,
|
| 123 |
+
"Doberman": 35,
|
| 124 |
+
"Elk Hound": 36,
|
| 125 |
+
"French Bulldog": 37,
|
| 126 |
+
"German Sheperd": 38,
|
| 127 |
+
"Golden Retriever": 39,
|
| 128 |
+
"Great Dane": 40,
|
| 129 |
+
"Great Perenees": 41,
|
| 130 |
+
"Greyhound": 42,
|
| 131 |
+
"Groenendael": 43,
|
| 132 |
+
"Irish Spaniel": 44,
|
| 133 |
+
"Irish Wolfhound": 45,
|
| 134 |
+
"Japanese Spaniel": 46,
|
| 135 |
+
"Komondor": 47,
|
| 136 |
+
"Labradoodle": 48,
|
| 137 |
+
"Labrador": 49,
|
| 138 |
+
"Lhasa": 50,
|
| 139 |
+
"Malinois": 51,
|
| 140 |
+
"Maltese": 52,
|
| 141 |
+
"Mex Hairless": 53,
|
| 142 |
+
"Newfoundland": 54,
|
| 143 |
+
"Pekinese": 55,
|
| 144 |
+
"Pit Bull": 56,
|
| 145 |
+
"Pomeranian": 57,
|
| 146 |
+
"Poodle": 58,
|
| 147 |
+
"Pug": 59,
|
| 148 |
+
"Rhodesian": 60,
|
| 149 |
+
"Rottweiler": 61,
|
| 150 |
+
"Saint Bernard": 62,
|
| 151 |
+
"Schnauzer": 63,
|
| 152 |
+
"Scotch Terrier": 64,
|
| 153 |
+
"Shar_Pei": 65,
|
| 154 |
+
"Shiba Inu": 66,
|
| 155 |
+
"Shih-Tzu": 67,
|
| 156 |
+
"Siberian Husky": 68,
|
| 157 |
+
"Vizsla": 69,
|
| 158 |
+
"Yorkie": 70
|
| 159 |
+
},
|
| 160 |
+
"layer_norm_eps": 1e-12,
|
| 161 |
+
"model_type": "vit",
|
| 162 |
+
"num_attention_heads": 12,
|
| 163 |
+
"num_channels": 3,
|
| 164 |
+
"num_hidden_layers": 12,
|
| 165 |
+
"patch_size": 16,
|
| 166 |
+
"problem_type": "single_label_classification",
|
| 167 |
+
"qkv_bias": true,
|
| 168 |
+
"torch_dtype": "float32",
|
| 169 |
+
"transformers_version": "4.45.2"
|
| 170 |
+
}
|
checkpoint-29100/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bda49ac12533271a8bbe1efb216edbf2fe4d89614936f48267431eb3a0ba3b2d
|
| 3 |
+
size 343436228
|
checkpoint-29100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:511281389be430b2fb03483e94a311b1a2c75376a431f18dc4ccf850fa7ea08f
|
| 3 |
+
size 686992901
|
checkpoint-29100/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-29100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58d7eb547490fd3ce44f16684a4cffd4d2919eeb2e450290c045a18961b7af64
|
| 3 |
+
size 14575
|
checkpoint-29100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c0be2d33b4b212c32e1428697fafe194b0d0af3587c727030975cf991d6c3b5
|
| 3 |
+
size 627
|
checkpoint-29100/trainer_state.json
ADDED
|
@@ -0,0 +1,1439 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.2304611206054688,
|
| 3 |
+
"best_model_checkpoint": "dogs_70_breeds_image_detection/checkpoint-29100",
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 29100,
|
| 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 |
+
"eval_accuracy": 0.03811369509043928,
|
| 14 |
+
"eval_loss": 4.224255561828613,
|
| 15 |
+
"eval_model_preparation_time": 0.005,
|
| 16 |
+
"eval_runtime": 53.4638,
|
| 17 |
+
"eval_samples_per_second": 115.817,
|
| 18 |
+
"eval_steps_per_second": 14.477,
|
| 19 |
+
"step": 291
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 1.718213058419244,
|
| 23 |
+
"grad_norm": 1.1522711515426636,
|
| 24 |
+
"learning_rate": 9.845094664371773e-07,
|
| 25 |
+
"loss": 4.2286,
|
| 26 |
+
"step": 500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"eval_accuracy": 0.08301033591731266,
|
| 31 |
+
"eval_loss": 4.186123371124268,
|
| 32 |
+
"eval_model_preparation_time": 0.005,
|
| 33 |
+
"eval_runtime": 53.282,
|
| 34 |
+
"eval_samples_per_second": 116.212,
|
| 35 |
+
"eval_steps_per_second": 14.526,
|
| 36 |
+
"step": 582
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"eval_accuracy": 0.15536175710594316,
|
| 41 |
+
"eval_loss": 4.142723560333252,
|
| 42 |
+
"eval_model_preparation_time": 0.005,
|
| 43 |
+
"eval_runtime": 53.6144,
|
| 44 |
+
"eval_samples_per_second": 115.491,
|
| 45 |
+
"eval_steps_per_second": 14.436,
|
| 46 |
+
"step": 873
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.436426116838488,
|
| 50 |
+
"grad_norm": 1.341554880142212,
|
| 51 |
+
"learning_rate": 9.672977624784853e-07,
|
| 52 |
+
"loss": 4.1533,
|
| 53 |
+
"step": 1000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"eval_accuracy": 0.24563953488372092,
|
| 58 |
+
"eval_loss": 4.09642219543457,
|
| 59 |
+
"eval_model_preparation_time": 0.005,
|
| 60 |
+
"eval_runtime": 53.2746,
|
| 61 |
+
"eval_samples_per_second": 116.228,
|
| 62 |
+
"eval_steps_per_second": 14.529,
|
| 63 |
+
"step": 1164
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
+
"eval_accuracy": 0.35852713178294576,
|
| 68 |
+
"eval_loss": 4.050450801849365,
|
| 69 |
+
"eval_model_preparation_time": 0.005,
|
| 70 |
+
"eval_runtime": 53.2922,
|
| 71 |
+
"eval_samples_per_second": 116.19,
|
| 72 |
+
"eval_steps_per_second": 14.524,
|
| 73 |
+
"step": 1455
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.154639175257732,
|
| 77 |
+
"grad_norm": 1.4653651714324951,
|
| 78 |
+
"learning_rate": 9.500860585197934e-07,
|
| 79 |
+
"loss": 4.0657,
|
| 80 |
+
"step": 1500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.0,
|
| 84 |
+
"eval_accuracy": 0.44993540051679587,
|
| 85 |
+
"eval_loss": 4.003639221191406,
|
| 86 |
+
"eval_model_preparation_time": 0.005,
|
| 87 |
+
"eval_runtime": 53.2227,
|
| 88 |
+
"eval_samples_per_second": 116.341,
|
| 89 |
+
"eval_steps_per_second": 14.543,
|
| 90 |
+
"step": 1746
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.872852233676976,
|
| 94 |
+
"grad_norm": 1.3512729406356812,
|
| 95 |
+
"learning_rate": 9.328743545611016e-07,
|
| 96 |
+
"loss": 3.9797,
|
| 97 |
+
"step": 2000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 7.0,
|
| 101 |
+
"eval_accuracy": 0.5489341085271318,
|
| 102 |
+
"eval_loss": 3.956012725830078,
|
| 103 |
+
"eval_model_preparation_time": 0.005,
|
| 104 |
+
"eval_runtime": 53.824,
|
| 105 |
+
"eval_samples_per_second": 115.042,
|
| 106 |
+
"eval_steps_per_second": 14.38,
|
| 107 |
+
"step": 2037
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_accuracy": 0.6153100775193798,
|
| 112 |
+
"eval_loss": 3.908579111099243,
|
| 113 |
+
"eval_model_preparation_time": 0.005,
|
| 114 |
+
"eval_runtime": 53.6148,
|
| 115 |
+
"eval_samples_per_second": 115.491,
|
| 116 |
+
"eval_steps_per_second": 14.436,
|
| 117 |
+
"step": 2328
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 8.59106529209622,
|
| 121 |
+
"grad_norm": 1.6852034330368042,
|
| 122 |
+
"learning_rate": 9.156626506024095e-07,
|
| 123 |
+
"loss": 3.8945,
|
| 124 |
+
"step": 2500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 9.0,
|
| 128 |
+
"eval_accuracy": 0.6690891472868217,
|
| 129 |
+
"eval_loss": 3.861515522003174,
|
| 130 |
+
"eval_model_preparation_time": 0.005,
|
| 131 |
+
"eval_runtime": 53.3317,
|
| 132 |
+
"eval_samples_per_second": 116.104,
|
| 133 |
+
"eval_steps_per_second": 14.513,
|
| 134 |
+
"step": 2619
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.0,
|
| 138 |
+
"eval_accuracy": 0.7041343669250646,
|
| 139 |
+
"eval_loss": 3.8151276111602783,
|
| 140 |
+
"eval_model_preparation_time": 0.005,
|
| 141 |
+
"eval_runtime": 53.7261,
|
| 142 |
+
"eval_samples_per_second": 115.251,
|
| 143 |
+
"eval_steps_per_second": 14.406,
|
| 144 |
+
"step": 2910
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 10.309278350515465,
|
| 148 |
+
"grad_norm": 1.4977772235870361,
|
| 149 |
+
"learning_rate": 8.984509466437177e-07,
|
| 150 |
+
"loss": 3.8073,
|
| 151 |
+
"step": 3000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 11.0,
|
| 155 |
+
"eval_accuracy": 0.7333656330749354,
|
| 156 |
+
"eval_loss": 3.767709732055664,
|
| 157 |
+
"eval_model_preparation_time": 0.005,
|
| 158 |
+
"eval_runtime": 53.2216,
|
| 159 |
+
"eval_samples_per_second": 116.344,
|
| 160 |
+
"eval_steps_per_second": 14.543,
|
| 161 |
+
"step": 3201
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 12.0,
|
| 165 |
+
"eval_accuracy": 0.7543604651162791,
|
| 166 |
+
"eval_loss": 3.7216570377349854,
|
| 167 |
+
"eval_model_preparation_time": 0.005,
|
| 168 |
+
"eval_runtime": 52.8673,
|
| 169 |
+
"eval_samples_per_second": 117.123,
|
| 170 |
+
"eval_steps_per_second": 14.64,
|
| 171 |
+
"step": 3492
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.027491408934708,
|
| 175 |
+
"grad_norm": 1.4954266548156738,
|
| 176 |
+
"learning_rate": 8.812392426850258e-07,
|
| 177 |
+
"loss": 3.7217,
|
| 178 |
+
"step": 3500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 13.0,
|
| 182 |
+
"eval_accuracy": 0.7698643410852714,
|
| 183 |
+
"eval_loss": 3.6769490242004395,
|
| 184 |
+
"eval_model_preparation_time": 0.005,
|
| 185 |
+
"eval_runtime": 53.1587,
|
| 186 |
+
"eval_samples_per_second": 116.481,
|
| 187 |
+
"eval_steps_per_second": 14.56,
|
| 188 |
+
"step": 3783
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 13.745704467353953,
|
| 192 |
+
"grad_norm": 1.6733068227767944,
|
| 193 |
+
"learning_rate": 8.640275387263338e-07,
|
| 194 |
+
"loss": 3.6412,
|
| 195 |
+
"step": 4000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 14.0,
|
| 199 |
+
"eval_accuracy": 0.7805232558139535,
|
| 200 |
+
"eval_loss": 3.6332757472991943,
|
| 201 |
+
"eval_model_preparation_time": 0.005,
|
| 202 |
+
"eval_runtime": 52.6862,
|
| 203 |
+
"eval_samples_per_second": 117.526,
|
| 204 |
+
"eval_steps_per_second": 14.691,
|
| 205 |
+
"step": 4074
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 15.0,
|
| 209 |
+
"eval_accuracy": 0.7876291989664083,
|
| 210 |
+
"eval_loss": 3.58959698677063,
|
| 211 |
+
"eval_model_preparation_time": 0.005,
|
| 212 |
+
"eval_runtime": 52.5851,
|
| 213 |
+
"eval_samples_per_second": 117.752,
|
| 214 |
+
"eval_steps_per_second": 14.719,
|
| 215 |
+
"step": 4365
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 15.463917525773196,
|
| 219 |
+
"grad_norm": 1.5803037881851196,
|
| 220 |
+
"learning_rate": 8.46815834767642e-07,
|
| 221 |
+
"loss": 3.56,
|
| 222 |
+
"step": 4500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 16.0,
|
| 226 |
+
"eval_accuracy": 0.7963501291989664,
|
| 227 |
+
"eval_loss": 3.547574520111084,
|
| 228 |
+
"eval_model_preparation_time": 0.005,
|
| 229 |
+
"eval_runtime": 52.7736,
|
| 230 |
+
"eval_samples_per_second": 117.331,
|
| 231 |
+
"eval_steps_per_second": 14.666,
|
| 232 |
+
"step": 4656
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 17.0,
|
| 236 |
+
"eval_accuracy": 0.8026485788113695,
|
| 237 |
+
"eval_loss": 3.507601737976074,
|
| 238 |
+
"eval_model_preparation_time": 0.005,
|
| 239 |
+
"eval_runtime": 53.0827,
|
| 240 |
+
"eval_samples_per_second": 116.648,
|
| 241 |
+
"eval_steps_per_second": 14.581,
|
| 242 |
+
"step": 4947
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 17.18213058419244,
|
| 246 |
+
"grad_norm": 1.741551399230957,
|
| 247 |
+
"learning_rate": 8.2960413080895e-07,
|
| 248 |
+
"loss": 3.4839,
|
| 249 |
+
"step": 5000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 18.0,
|
| 253 |
+
"eval_accuracy": 0.8086240310077519,
|
| 254 |
+
"eval_loss": 3.467883825302124,
|
| 255 |
+
"eval_model_preparation_time": 0.005,
|
| 256 |
+
"eval_runtime": 52.7555,
|
| 257 |
+
"eval_samples_per_second": 117.372,
|
| 258 |
+
"eval_steps_per_second": 14.671,
|
| 259 |
+
"step": 5238
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 18.900343642611684,
|
| 263 |
+
"grad_norm": 1.6814472675323486,
|
| 264 |
+
"learning_rate": 8.123924268502581e-07,
|
| 265 |
+
"loss": 3.4135,
|
| 266 |
+
"step": 5500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 19.0,
|
| 270 |
+
"eval_accuracy": 0.8162144702842378,
|
| 271 |
+
"eval_loss": 3.429760694503784,
|
| 272 |
+
"eval_model_preparation_time": 0.005,
|
| 273 |
+
"eval_runtime": 52.6582,
|
| 274 |
+
"eval_samples_per_second": 117.589,
|
| 275 |
+
"eval_steps_per_second": 14.699,
|
| 276 |
+
"step": 5529
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 20.0,
|
| 280 |
+
"eval_accuracy": 0.8207364341085271,
|
| 281 |
+
"eval_loss": 3.3927395343780518,
|
| 282 |
+
"eval_model_preparation_time": 0.005,
|
| 283 |
+
"eval_runtime": 52.6007,
|
| 284 |
+
"eval_samples_per_second": 117.717,
|
| 285 |
+
"eval_steps_per_second": 14.715,
|
| 286 |
+
"step": 5820
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 20.61855670103093,
|
| 290 |
+
"grad_norm": 1.8037664890289307,
|
| 291 |
+
"learning_rate": 7.951807228915662e-07,
|
| 292 |
+
"loss": 3.3452,
|
| 293 |
+
"step": 6000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 21.0,
|
| 297 |
+
"eval_accuracy": 0.8254198966408268,
|
| 298 |
+
"eval_loss": 3.3561041355133057,
|
| 299 |
+
"eval_model_preparation_time": 0.005,
|
| 300 |
+
"eval_runtime": 52.766,
|
| 301 |
+
"eval_samples_per_second": 117.348,
|
| 302 |
+
"eval_steps_per_second": 14.669,
|
| 303 |
+
"step": 6111
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 22.0,
|
| 307 |
+
"eval_accuracy": 0.8283268733850129,
|
| 308 |
+
"eval_loss": 3.3211123943328857,
|
| 309 |
+
"eval_model_preparation_time": 0.005,
|
| 310 |
+
"eval_runtime": 52.9233,
|
| 311 |
+
"eval_samples_per_second": 117.0,
|
| 312 |
+
"eval_steps_per_second": 14.625,
|
| 313 |
+
"step": 6402
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 22.33676975945017,
|
| 317 |
+
"grad_norm": 1.7638081312179565,
|
| 318 |
+
"learning_rate": 7.779690189328744e-07,
|
| 319 |
+
"loss": 3.2809,
|
| 320 |
+
"step": 6500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 23.0,
|
| 324 |
+
"eval_accuracy": 0.8330103359173127,
|
| 325 |
+
"eval_loss": 3.2866406440734863,
|
| 326 |
+
"eval_model_preparation_time": 0.005,
|
| 327 |
+
"eval_runtime": 53.5163,
|
| 328 |
+
"eval_samples_per_second": 115.703,
|
| 329 |
+
"eval_steps_per_second": 14.463,
|
| 330 |
+
"step": 6693
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 24.0,
|
| 334 |
+
"eval_accuracy": 0.838501291989664,
|
| 335 |
+
"eval_loss": 3.2538506984710693,
|
| 336 |
+
"eval_model_preparation_time": 0.005,
|
| 337 |
+
"eval_runtime": 53.3194,
|
| 338 |
+
"eval_samples_per_second": 116.13,
|
| 339 |
+
"eval_steps_per_second": 14.516,
|
| 340 |
+
"step": 6984
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 24.054982817869416,
|
| 344 |
+
"grad_norm": 2.052138328552246,
|
| 345 |
+
"learning_rate": 7.607573149741824e-07,
|
| 346 |
+
"loss": 3.2174,
|
| 347 |
+
"step": 7000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 25.0,
|
| 351 |
+
"eval_accuracy": 0.8410852713178295,
|
| 352 |
+
"eval_loss": 3.221360445022583,
|
| 353 |
+
"eval_model_preparation_time": 0.005,
|
| 354 |
+
"eval_runtime": 53.5019,
|
| 355 |
+
"eval_samples_per_second": 115.734,
|
| 356 |
+
"eval_steps_per_second": 14.467,
|
| 357 |
+
"step": 7275
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 25.77319587628866,
|
| 361 |
+
"grad_norm": 1.6119282245635986,
|
| 362 |
+
"learning_rate": 7.435456110154906e-07,
|
| 363 |
+
"loss": 3.1592,
|
| 364 |
+
"step": 7500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 26.0,
|
| 368 |
+
"eval_accuracy": 0.8443152454780362,
|
| 369 |
+
"eval_loss": 3.189776659011841,
|
| 370 |
+
"eval_model_preparation_time": 0.005,
|
| 371 |
+
"eval_runtime": 53.7691,
|
| 372 |
+
"eval_samples_per_second": 115.159,
|
| 373 |
+
"eval_steps_per_second": 14.395,
|
| 374 |
+
"step": 7566
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 27.0,
|
| 378 |
+
"eval_accuracy": 0.8464147286821705,
|
| 379 |
+
"eval_loss": 3.1592888832092285,
|
| 380 |
+
"eval_model_preparation_time": 0.005,
|
| 381 |
+
"eval_runtime": 53.6596,
|
| 382 |
+
"eval_samples_per_second": 115.394,
|
| 383 |
+
"eval_steps_per_second": 14.424,
|
| 384 |
+
"step": 7857
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 27.491408934707902,
|
| 388 |
+
"grad_norm": 1.8645163774490356,
|
| 389 |
+
"learning_rate": 7.263339070567986e-07,
|
| 390 |
+
"loss": 3.1041,
|
| 391 |
+
"step": 8000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 28.0,
|
| 395 |
+
"eval_accuracy": 0.8481912144702842,
|
| 396 |
+
"eval_loss": 3.1283702850341797,
|
| 397 |
+
"eval_model_preparation_time": 0.005,
|
| 398 |
+
"eval_runtime": 53.3822,
|
| 399 |
+
"eval_samples_per_second": 115.994,
|
| 400 |
+
"eval_steps_per_second": 14.499,
|
| 401 |
+
"step": 8148
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 29.0,
|
| 405 |
+
"eval_accuracy": 0.8510981912144703,
|
| 406 |
+
"eval_loss": 3.1002068519592285,
|
| 407 |
+
"eval_model_preparation_time": 0.005,
|
| 408 |
+
"eval_runtime": 53.0972,
|
| 409 |
+
"eval_samples_per_second": 116.616,
|
| 410 |
+
"eval_steps_per_second": 14.577,
|
| 411 |
+
"step": 8439
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 29.209621993127147,
|
| 415 |
+
"grad_norm": 2.0290517807006836,
|
| 416 |
+
"learning_rate": 7.091222030981066e-07,
|
| 417 |
+
"loss": 3.047,
|
| 418 |
+
"step": 8500
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 30.0,
|
| 422 |
+
"eval_accuracy": 0.853843669250646,
|
| 423 |
+
"eval_loss": 3.071702480316162,
|
| 424 |
+
"eval_model_preparation_time": 0.005,
|
| 425 |
+
"eval_runtime": 53.8219,
|
| 426 |
+
"eval_samples_per_second": 115.046,
|
| 427 |
+
"eval_steps_per_second": 14.381,
|
| 428 |
+
"step": 8730
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 30.927835051546392,
|
| 432 |
+
"grad_norm": 1.9484608173370361,
|
| 433 |
+
"learning_rate": 6.919104991394148e-07,
|
| 434 |
+
"loss": 2.9999,
|
| 435 |
+
"step": 9000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 31.0,
|
| 439 |
+
"eval_accuracy": 0.8552971576227391,
|
| 440 |
+
"eval_loss": 3.044823408126831,
|
| 441 |
+
"eval_model_preparation_time": 0.005,
|
| 442 |
+
"eval_runtime": 54.0725,
|
| 443 |
+
"eval_samples_per_second": 114.513,
|
| 444 |
+
"eval_steps_per_second": 14.314,
|
| 445 |
+
"step": 9021
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 32.0,
|
| 449 |
+
"eval_accuracy": 0.8562661498708011,
|
| 450 |
+
"eval_loss": 3.0170109272003174,
|
| 451 |
+
"eval_model_preparation_time": 0.005,
|
| 452 |
+
"eval_runtime": 54.2696,
|
| 453 |
+
"eval_samples_per_second": 114.097,
|
| 454 |
+
"eval_steps_per_second": 14.262,
|
| 455 |
+
"step": 9312
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 32.64604810996563,
|
| 459 |
+
"grad_norm": 1.9190058708190918,
|
| 460 |
+
"learning_rate": 6.746987951807228e-07,
|
| 461 |
+
"loss": 2.951,
|
| 462 |
+
"step": 9500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 33.0,
|
| 466 |
+
"eval_accuracy": 0.8580426356589147,
|
| 467 |
+
"eval_loss": 2.9910173416137695,
|
| 468 |
+
"eval_model_preparation_time": 0.005,
|
| 469 |
+
"eval_runtime": 53.2749,
|
| 470 |
+
"eval_samples_per_second": 116.227,
|
| 471 |
+
"eval_steps_per_second": 14.528,
|
| 472 |
+
"step": 9603
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 34.0,
|
| 476 |
+
"eval_accuracy": 0.8594961240310077,
|
| 477 |
+
"eval_loss": 2.965754747390747,
|
| 478 |
+
"eval_model_preparation_time": 0.005,
|
| 479 |
+
"eval_runtime": 53.3652,
|
| 480 |
+
"eval_samples_per_second": 116.031,
|
| 481 |
+
"eval_steps_per_second": 14.504,
|
| 482 |
+
"step": 9894
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 34.36426116838488,
|
| 486 |
+
"grad_norm": 2.104431390762329,
|
| 487 |
+
"learning_rate": 6.57487091222031e-07,
|
| 488 |
+
"loss": 2.8999,
|
| 489 |
+
"step": 10000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 35.0,
|
| 493 |
+
"eval_accuracy": 0.8609496124031008,
|
| 494 |
+
"eval_loss": 2.9400594234466553,
|
| 495 |
+
"eval_model_preparation_time": 0.005,
|
| 496 |
+
"eval_runtime": 52.9247,
|
| 497 |
+
"eval_samples_per_second": 116.996,
|
| 498 |
+
"eval_steps_per_second": 14.625,
|
| 499 |
+
"step": 10185
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 36.0,
|
| 503 |
+
"eval_accuracy": 0.8627260981912145,
|
| 504 |
+
"eval_loss": 2.9151716232299805,
|
| 505 |
+
"eval_model_preparation_time": 0.005,
|
| 506 |
+
"eval_runtime": 52.9313,
|
| 507 |
+
"eval_samples_per_second": 116.982,
|
| 508 |
+
"eval_steps_per_second": 14.623,
|
| 509 |
+
"step": 10476
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 36.08247422680412,
|
| 513 |
+
"grad_norm": 1.8955918550491333,
|
| 514 |
+
"learning_rate": 6.402753872633391e-07,
|
| 515 |
+
"loss": 2.8589,
|
| 516 |
+
"step": 10500
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 37.0,
|
| 520 |
+
"eval_accuracy": 0.8643410852713178,
|
| 521 |
+
"eval_loss": 2.8920605182647705,
|
| 522 |
+
"eval_model_preparation_time": 0.005,
|
| 523 |
+
"eval_runtime": 53.1759,
|
| 524 |
+
"eval_samples_per_second": 116.444,
|
| 525 |
+
"eval_steps_per_second": 14.555,
|
| 526 |
+
"step": 10767
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 37.80068728522337,
|
| 530 |
+
"grad_norm": 2.0740840435028076,
|
| 531 |
+
"learning_rate": 6.230636833046471e-07,
|
| 532 |
+
"loss": 2.8145,
|
| 533 |
+
"step": 11000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 38.0,
|
| 537 |
+
"eval_accuracy": 0.8646640826873385,
|
| 538 |
+
"eval_loss": 2.8690123558044434,
|
| 539 |
+
"eval_model_preparation_time": 0.005,
|
| 540 |
+
"eval_runtime": 52.8932,
|
| 541 |
+
"eval_samples_per_second": 117.066,
|
| 542 |
+
"eval_steps_per_second": 14.633,
|
| 543 |
+
"step": 11058
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 39.0,
|
| 547 |
+
"eval_accuracy": 0.8659560723514211,
|
| 548 |
+
"eval_loss": 2.845964193344116,
|
| 549 |
+
"eval_model_preparation_time": 0.005,
|
| 550 |
+
"eval_runtime": 52.8287,
|
| 551 |
+
"eval_samples_per_second": 117.209,
|
| 552 |
+
"eval_steps_per_second": 14.651,
|
| 553 |
+
"step": 11349
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 39.51890034364261,
|
| 557 |
+
"grad_norm": 1.9286776781082153,
|
| 558 |
+
"learning_rate": 6.058519793459552e-07,
|
| 559 |
+
"loss": 2.7734,
|
| 560 |
+
"step": 11500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 40.0,
|
| 564 |
+
"eval_accuracy": 0.8674095607235142,
|
| 565 |
+
"eval_loss": 2.8238561153411865,
|
| 566 |
+
"eval_model_preparation_time": 0.005,
|
| 567 |
+
"eval_runtime": 52.9947,
|
| 568 |
+
"eval_samples_per_second": 116.842,
|
| 569 |
+
"eval_steps_per_second": 14.605,
|
| 570 |
+
"step": 11640
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 41.0,
|
| 574 |
+
"eval_accuracy": 0.8680555555555556,
|
| 575 |
+
"eval_loss": 2.8031866550445557,
|
| 576 |
+
"eval_model_preparation_time": 0.005,
|
| 577 |
+
"eval_runtime": 53.11,
|
| 578 |
+
"eval_samples_per_second": 116.588,
|
| 579 |
+
"eval_steps_per_second": 14.574,
|
| 580 |
+
"step": 11931
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 41.23711340206186,
|
| 584 |
+
"grad_norm": 1.892899751663208,
|
| 585 |
+
"learning_rate": 5.886402753872633e-07,
|
| 586 |
+
"loss": 2.7352,
|
| 587 |
+
"step": 12000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 42.0,
|
| 591 |
+
"eval_accuracy": 0.8704780361757106,
|
| 592 |
+
"eval_loss": 2.782097816467285,
|
| 593 |
+
"eval_model_preparation_time": 0.005,
|
| 594 |
+
"eval_runtime": 53.2125,
|
| 595 |
+
"eval_samples_per_second": 116.364,
|
| 596 |
+
"eval_steps_per_second": 14.545,
|
| 597 |
+
"step": 12222
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 42.955326460481096,
|
| 601 |
+
"grad_norm": 1.8656749725341797,
|
| 602 |
+
"learning_rate": 5.714285714285714e-07,
|
| 603 |
+
"loss": 2.695,
|
| 604 |
+
"step": 12500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 43.0,
|
| 608 |
+
"eval_accuracy": 0.8716085271317829,
|
| 609 |
+
"eval_loss": 2.7616491317749023,
|
| 610 |
+
"eval_model_preparation_time": 0.005,
|
| 611 |
+
"eval_runtime": 52.6755,
|
| 612 |
+
"eval_samples_per_second": 117.55,
|
| 613 |
+
"eval_steps_per_second": 14.694,
|
| 614 |
+
"step": 12513
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 44.0,
|
| 618 |
+
"eval_accuracy": 0.873062015503876,
|
| 619 |
+
"eval_loss": 2.7412848472595215,
|
| 620 |
+
"eval_model_preparation_time": 0.005,
|
| 621 |
+
"eval_runtime": 53.2571,
|
| 622 |
+
"eval_samples_per_second": 116.266,
|
| 623 |
+
"eval_steps_per_second": 14.533,
|
| 624 |
+
"step": 12804
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 44.67353951890034,
|
| 628 |
+
"grad_norm": 1.9270859956741333,
|
| 629 |
+
"learning_rate": 5.542168674698795e-07,
|
| 630 |
+
"loss": 2.6587,
|
| 631 |
+
"step": 13000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 45.0,
|
| 635 |
+
"eval_accuracy": 0.8717700258397932,
|
| 636 |
+
"eval_loss": 2.721040725708008,
|
| 637 |
+
"eval_model_preparation_time": 0.005,
|
| 638 |
+
"eval_runtime": 52.9963,
|
| 639 |
+
"eval_samples_per_second": 116.838,
|
| 640 |
+
"eval_steps_per_second": 14.605,
|
| 641 |
+
"step": 13095
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 46.0,
|
| 645 |
+
"eval_accuracy": 0.8741925064599483,
|
| 646 |
+
"eval_loss": 2.702544689178467,
|
| 647 |
+
"eval_model_preparation_time": 0.005,
|
| 648 |
+
"eval_runtime": 53.1374,
|
| 649 |
+
"eval_samples_per_second": 116.528,
|
| 650 |
+
"eval_steps_per_second": 14.566,
|
| 651 |
+
"step": 13386
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 46.391752577319586,
|
| 655 |
+
"grad_norm": 2.173807382583618,
|
| 656 |
+
"learning_rate": 5.370051635111877e-07,
|
| 657 |
+
"loss": 2.6245,
|
| 658 |
+
"step": 13500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 47.0,
|
| 662 |
+
"eval_accuracy": 0.8743540051679587,
|
| 663 |
+
"eval_loss": 2.6839137077331543,
|
| 664 |
+
"eval_model_preparation_time": 0.005,
|
| 665 |
+
"eval_runtime": 53.0364,
|
| 666 |
+
"eval_samples_per_second": 116.75,
|
| 667 |
+
"eval_steps_per_second": 14.594,
|
| 668 |
+
"step": 13677
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 48.0,
|
| 672 |
+
"eval_accuracy": 0.8761304909560723,
|
| 673 |
+
"eval_loss": 2.666257619857788,
|
| 674 |
+
"eval_model_preparation_time": 0.005,
|
| 675 |
+
"eval_runtime": 52.9704,
|
| 676 |
+
"eval_samples_per_second": 116.895,
|
| 677 |
+
"eval_steps_per_second": 14.612,
|
| 678 |
+
"step": 13968
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 48.10996563573883,
|
| 682 |
+
"grad_norm": 2.061178207397461,
|
| 683 |
+
"learning_rate": 5.197934595524956e-07,
|
| 684 |
+
"loss": 2.5929,
|
| 685 |
+
"step": 14000
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 49.0,
|
| 689 |
+
"eval_accuracy": 0.875968992248062,
|
| 690 |
+
"eval_loss": 2.648406505584717,
|
| 691 |
+
"eval_model_preparation_time": 0.005,
|
| 692 |
+
"eval_runtime": 52.8971,
|
| 693 |
+
"eval_samples_per_second": 117.057,
|
| 694 |
+
"eval_steps_per_second": 14.632,
|
| 695 |
+
"step": 14259
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 49.828178694158076,
|
| 699 |
+
"grad_norm": 2.2463059425354004,
|
| 700 |
+
"learning_rate": 5.025817555938038e-07,
|
| 701 |
+
"loss": 2.5577,
|
| 702 |
+
"step": 14500
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 50.0,
|
| 706 |
+
"eval_accuracy": 0.8780684754521964,
|
| 707 |
+
"eval_loss": 2.630814790725708,
|
| 708 |
+
"eval_model_preparation_time": 0.005,
|
| 709 |
+
"eval_runtime": 52.7435,
|
| 710 |
+
"eval_samples_per_second": 117.398,
|
| 711 |
+
"eval_steps_per_second": 14.675,
|
| 712 |
+
"step": 14550
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 51.0,
|
| 716 |
+
"eval_accuracy": 0.8793604651162791,
|
| 717 |
+
"eval_loss": 2.613746404647827,
|
| 718 |
+
"eval_model_preparation_time": 0.005,
|
| 719 |
+
"eval_runtime": 53.3318,
|
| 720 |
+
"eval_samples_per_second": 116.103,
|
| 721 |
+
"eval_steps_per_second": 14.513,
|
| 722 |
+
"step": 14841
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 51.54639175257732,
|
| 726 |
+
"grad_norm": 2.0589890480041504,
|
| 727 |
+
"learning_rate": 4.853700516351119e-07,
|
| 728 |
+
"loss": 2.5317,
|
| 729 |
+
"step": 15000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 52.0,
|
| 733 |
+
"eval_accuracy": 0.8791989664082688,
|
| 734 |
+
"eval_loss": 2.5976715087890625,
|
| 735 |
+
"eval_model_preparation_time": 0.005,
|
| 736 |
+
"eval_runtime": 52.6721,
|
| 737 |
+
"eval_samples_per_second": 117.558,
|
| 738 |
+
"eval_steps_per_second": 14.695,
|
| 739 |
+
"step": 15132
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 53.0,
|
| 743 |
+
"eval_accuracy": 0.8804909560723514,
|
| 744 |
+
"eval_loss": 2.5813040733337402,
|
| 745 |
+
"eval_model_preparation_time": 0.005,
|
| 746 |
+
"eval_runtime": 53.2754,
|
| 747 |
+
"eval_samples_per_second": 116.226,
|
| 748 |
+
"eval_steps_per_second": 14.528,
|
| 749 |
+
"step": 15423
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 53.264604810996566,
|
| 753 |
+
"grad_norm": 2.004828929901123,
|
| 754 |
+
"learning_rate": 4.6815834767641994e-07,
|
| 755 |
+
"loss": 2.4971,
|
| 756 |
+
"step": 15500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 54.0,
|
| 760 |
+
"eval_accuracy": 0.8808139534883721,
|
| 761 |
+
"eval_loss": 2.566027879714966,
|
| 762 |
+
"eval_model_preparation_time": 0.005,
|
| 763 |
+
"eval_runtime": 53.3637,
|
| 764 |
+
"eval_samples_per_second": 116.034,
|
| 765 |
+
"eval_steps_per_second": 14.504,
|
| 766 |
+
"step": 15714
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 54.982817869415804,
|
| 770 |
+
"grad_norm": 1.9317859411239624,
|
| 771 |
+
"learning_rate": 4.5094664371772807e-07,
|
| 772 |
+
"loss": 2.4695,
|
| 773 |
+
"step": 16000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 55.0,
|
| 777 |
+
"eval_accuracy": 0.8812984496124031,
|
| 778 |
+
"eval_loss": 2.551055431365967,
|
| 779 |
+
"eval_model_preparation_time": 0.005,
|
| 780 |
+
"eval_runtime": 52.4399,
|
| 781 |
+
"eval_samples_per_second": 118.078,
|
| 782 |
+
"eval_steps_per_second": 14.76,
|
| 783 |
+
"step": 16005
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 56.0,
|
| 787 |
+
"eval_accuracy": 0.8806524547803618,
|
| 788 |
+
"eval_loss": 2.536409854888916,
|
| 789 |
+
"eval_model_preparation_time": 0.005,
|
| 790 |
+
"eval_runtime": 52.5325,
|
| 791 |
+
"eval_samples_per_second": 117.87,
|
| 792 |
+
"eval_steps_per_second": 14.734,
|
| 793 |
+
"step": 16296
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 56.70103092783505,
|
| 797 |
+
"grad_norm": 2.0537452697753906,
|
| 798 |
+
"learning_rate": 4.3373493975903615e-07,
|
| 799 |
+
"loss": 2.444,
|
| 800 |
+
"step": 16500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 57.0,
|
| 804 |
+
"eval_accuracy": 0.8827519379844961,
|
| 805 |
+
"eval_loss": 2.521925449371338,
|
| 806 |
+
"eval_model_preparation_time": 0.005,
|
| 807 |
+
"eval_runtime": 52.5122,
|
| 808 |
+
"eval_samples_per_second": 117.915,
|
| 809 |
+
"eval_steps_per_second": 14.739,
|
| 810 |
+
"step": 16587
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 58.0,
|
| 814 |
+
"eval_accuracy": 0.8824289405684754,
|
| 815 |
+
"eval_loss": 2.508209228515625,
|
| 816 |
+
"eval_model_preparation_time": 0.005,
|
| 817 |
+
"eval_runtime": 52.9146,
|
| 818 |
+
"eval_samples_per_second": 117.019,
|
| 819 |
+
"eval_steps_per_second": 14.627,
|
| 820 |
+
"step": 16878
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 58.419243986254294,
|
| 824 |
+
"grad_norm": 2.472633123397827,
|
| 825 |
+
"learning_rate": 4.165232358003442e-07,
|
| 826 |
+
"loss": 2.4143,
|
| 827 |
+
"step": 17000
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 59.0,
|
| 831 |
+
"eval_accuracy": 0.8845284237726099,
|
| 832 |
+
"eval_loss": 2.4946951866149902,
|
| 833 |
+
"eval_model_preparation_time": 0.005,
|
| 834 |
+
"eval_runtime": 53.263,
|
| 835 |
+
"eval_samples_per_second": 116.253,
|
| 836 |
+
"eval_steps_per_second": 14.532,
|
| 837 |
+
"step": 17169
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 60.0,
|
| 841 |
+
"eval_accuracy": 0.8837209302325582,
|
| 842 |
+
"eval_loss": 2.4811995029449463,
|
| 843 |
+
"eval_model_preparation_time": 0.005,
|
| 844 |
+
"eval_runtime": 53.3521,
|
| 845 |
+
"eval_samples_per_second": 116.059,
|
| 846 |
+
"eval_steps_per_second": 14.507,
|
| 847 |
+
"step": 17460
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 60.13745704467354,
|
| 851 |
+
"grad_norm": 2.3744590282440186,
|
| 852 |
+
"learning_rate": 3.9931153184165226e-07,
|
| 853 |
+
"loss": 2.3935,
|
| 854 |
+
"step": 17500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 61.0,
|
| 858 |
+
"eval_accuracy": 0.8838824289405685,
|
| 859 |
+
"eval_loss": 2.468451499938965,
|
| 860 |
+
"eval_model_preparation_time": 0.005,
|
| 861 |
+
"eval_runtime": 53.0799,
|
| 862 |
+
"eval_samples_per_second": 116.654,
|
| 863 |
+
"eval_steps_per_second": 14.582,
|
| 864 |
+
"step": 17751
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 61.855670103092784,
|
| 868 |
+
"grad_norm": 2.0248947143554688,
|
| 869 |
+
"learning_rate": 3.820998278829604e-07,
|
| 870 |
+
"loss": 2.3717,
|
| 871 |
+
"step": 18000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 62.0,
|
| 875 |
+
"eval_accuracy": 0.8858204134366925,
|
| 876 |
+
"eval_loss": 2.456092119216919,
|
| 877 |
+
"eval_model_preparation_time": 0.005,
|
| 878 |
+
"eval_runtime": 52.7271,
|
| 879 |
+
"eval_samples_per_second": 117.435,
|
| 880 |
+
"eval_steps_per_second": 14.679,
|
| 881 |
+
"step": 18042
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 63.0,
|
| 885 |
+
"eval_accuracy": 0.8866279069767442,
|
| 886 |
+
"eval_loss": 2.444223403930664,
|
| 887 |
+
"eval_model_preparation_time": 0.005,
|
| 888 |
+
"eval_runtime": 53.2783,
|
| 889 |
+
"eval_samples_per_second": 116.22,
|
| 890 |
+
"eval_steps_per_second": 14.528,
|
| 891 |
+
"step": 18333
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 63.57388316151203,
|
| 895 |
+
"grad_norm": 2.6887121200561523,
|
| 896 |
+
"learning_rate": 3.648881239242685e-07,
|
| 897 |
+
"loss": 2.3475,
|
| 898 |
+
"step": 18500
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 64.0,
|
| 902 |
+
"eval_accuracy": 0.8875968992248062,
|
| 903 |
+
"eval_loss": 2.432462215423584,
|
| 904 |
+
"eval_model_preparation_time": 0.005,
|
| 905 |
+
"eval_runtime": 53.2565,
|
| 906 |
+
"eval_samples_per_second": 116.267,
|
| 907 |
+
"eval_steps_per_second": 14.533,
|
| 908 |
+
"step": 18624
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 65.0,
|
| 912 |
+
"eval_accuracy": 0.8875968992248062,
|
| 913 |
+
"eval_loss": 2.42094087600708,
|
| 914 |
+
"eval_model_preparation_time": 0.005,
|
| 915 |
+
"eval_runtime": 53.453,
|
| 916 |
+
"eval_samples_per_second": 115.84,
|
| 917 |
+
"eval_steps_per_second": 14.48,
|
| 918 |
+
"step": 18915
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 65.29209621993127,
|
| 922 |
+
"grad_norm": 1.8884248733520508,
|
| 923 |
+
"learning_rate": 3.4767641996557657e-07,
|
| 924 |
+
"loss": 2.3262,
|
| 925 |
+
"step": 19000
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 66.0,
|
| 929 |
+
"eval_accuracy": 0.8884043927648578,
|
| 930 |
+
"eval_loss": 2.410001754760742,
|
| 931 |
+
"eval_model_preparation_time": 0.005,
|
| 932 |
+
"eval_runtime": 53.9318,
|
| 933 |
+
"eval_samples_per_second": 114.812,
|
| 934 |
+
"eval_steps_per_second": 14.351,
|
| 935 |
+
"step": 19206
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 67.0,
|
| 939 |
+
"eval_accuracy": 0.8887273901808785,
|
| 940 |
+
"eval_loss": 2.3990447521209717,
|
| 941 |
+
"eval_model_preparation_time": 0.005,
|
| 942 |
+
"eval_runtime": 53.9445,
|
| 943 |
+
"eval_samples_per_second": 114.785,
|
| 944 |
+
"eval_steps_per_second": 14.348,
|
| 945 |
+
"step": 19497
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 67.01030927835052,
|
| 949 |
+
"grad_norm": 2.0446999073028564,
|
| 950 |
+
"learning_rate": 3.304647160068847e-07,
|
| 951 |
+
"loss": 2.3043,
|
| 952 |
+
"step": 19500
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 68.0,
|
| 956 |
+
"eval_accuracy": 0.8885658914728682,
|
| 957 |
+
"eval_loss": 2.3888654708862305,
|
| 958 |
+
"eval_model_preparation_time": 0.005,
|
| 959 |
+
"eval_runtime": 53.8449,
|
| 960 |
+
"eval_samples_per_second": 114.997,
|
| 961 |
+
"eval_steps_per_second": 14.375,
|
| 962 |
+
"step": 19788
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 68.72852233676976,
|
| 966 |
+
"grad_norm": 2.0572509765625,
|
| 967 |
+
"learning_rate": 3.132530120481928e-07,
|
| 968 |
+
"loss": 2.2841,
|
| 969 |
+
"step": 20000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 69.0,
|
| 973 |
+
"eval_accuracy": 0.8906653746770026,
|
| 974 |
+
"eval_loss": 2.3787026405334473,
|
| 975 |
+
"eval_model_preparation_time": 0.005,
|
| 976 |
+
"eval_runtime": 53.7045,
|
| 977 |
+
"eval_samples_per_second": 115.298,
|
| 978 |
+
"eval_steps_per_second": 14.412,
|
| 979 |
+
"step": 20079
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 70.0,
|
| 983 |
+
"eval_accuracy": 0.8903423772609819,
|
| 984 |
+
"eval_loss": 2.369292736053467,
|
| 985 |
+
"eval_model_preparation_time": 0.005,
|
| 986 |
+
"eval_runtime": 53.8822,
|
| 987 |
+
"eval_samples_per_second": 114.917,
|
| 988 |
+
"eval_steps_per_second": 14.365,
|
| 989 |
+
"step": 20370
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 70.44673539518901,
|
| 993 |
+
"grad_norm": 1.8821637630462646,
|
| 994 |
+
"learning_rate": 2.9604130808950087e-07,
|
| 995 |
+
"loss": 2.2718,
|
| 996 |
+
"step": 20500
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 71.0,
|
| 1000 |
+
"eval_accuracy": 0.8906653746770026,
|
| 1001 |
+
"eval_loss": 2.3600070476531982,
|
| 1002 |
+
"eval_model_preparation_time": 0.005,
|
| 1003 |
+
"eval_runtime": 53.9421,
|
| 1004 |
+
"eval_samples_per_second": 114.79,
|
| 1005 |
+
"eval_steps_per_second": 14.349,
|
| 1006 |
+
"step": 20661
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 72.0,
|
| 1010 |
+
"eval_accuracy": 0.8919573643410853,
|
| 1011 |
+
"eval_loss": 2.350867509841919,
|
| 1012 |
+
"eval_model_preparation_time": 0.005,
|
| 1013 |
+
"eval_runtime": 54.6506,
|
| 1014 |
+
"eval_samples_per_second": 113.302,
|
| 1015 |
+
"eval_steps_per_second": 14.163,
|
| 1016 |
+
"step": 20952
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 72.16494845360825,
|
| 1020 |
+
"grad_norm": 2.260333299636841,
|
| 1021 |
+
"learning_rate": 2.788296041308089e-07,
|
| 1022 |
+
"loss": 2.2487,
|
| 1023 |
+
"step": 21000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 73.0,
|
| 1027 |
+
"eval_accuracy": 0.8924418604651163,
|
| 1028 |
+
"eval_loss": 2.3422977924346924,
|
| 1029 |
+
"eval_model_preparation_time": 0.005,
|
| 1030 |
+
"eval_runtime": 53.8113,
|
| 1031 |
+
"eval_samples_per_second": 115.069,
|
| 1032 |
+
"eval_steps_per_second": 14.384,
|
| 1033 |
+
"step": 21243
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 73.88316151202748,
|
| 1037 |
+
"grad_norm": 2.037961006164551,
|
| 1038 |
+
"learning_rate": 2.6161790017211703e-07,
|
| 1039 |
+
"loss": 2.2375,
|
| 1040 |
+
"step": 21500
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 74.0,
|
| 1044 |
+
"eval_accuracy": 0.8916343669250646,
|
| 1045 |
+
"eval_loss": 2.3344151973724365,
|
| 1046 |
+
"eval_model_preparation_time": 0.005,
|
| 1047 |
+
"eval_runtime": 53.589,
|
| 1048 |
+
"eval_samples_per_second": 115.546,
|
| 1049 |
+
"eval_steps_per_second": 14.443,
|
| 1050 |
+
"step": 21534
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 75.0,
|
| 1054 |
+
"eval_accuracy": 0.8930878552971576,
|
| 1055 |
+
"eval_loss": 2.326270580291748,
|
| 1056 |
+
"eval_model_preparation_time": 0.005,
|
| 1057 |
+
"eval_runtime": 54.0166,
|
| 1058 |
+
"eval_samples_per_second": 114.631,
|
| 1059 |
+
"eval_steps_per_second": 14.329,
|
| 1060 |
+
"step": 21825
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 75.60137457044674,
|
| 1064 |
+
"grad_norm": 2.1131231784820557,
|
| 1065 |
+
"learning_rate": 2.444061962134251e-07,
|
| 1066 |
+
"loss": 2.2226,
|
| 1067 |
+
"step": 22000
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 76.0,
|
| 1071 |
+
"eval_accuracy": 0.8922803617571059,
|
| 1072 |
+
"eval_loss": 2.318610668182373,
|
| 1073 |
+
"eval_model_preparation_time": 0.005,
|
| 1074 |
+
"eval_runtime": 53.7404,
|
| 1075 |
+
"eval_samples_per_second": 115.221,
|
| 1076 |
+
"eval_steps_per_second": 14.403,
|
| 1077 |
+
"step": 22116
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 77.0,
|
| 1081 |
+
"eval_accuracy": 0.8932493540051679,
|
| 1082 |
+
"eval_loss": 2.3115651607513428,
|
| 1083 |
+
"eval_model_preparation_time": 0.005,
|
| 1084 |
+
"eval_runtime": 53.7352,
|
| 1085 |
+
"eval_samples_per_second": 115.232,
|
| 1086 |
+
"eval_steps_per_second": 14.404,
|
| 1087 |
+
"step": 22407
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 77.31958762886597,
|
| 1091 |
+
"grad_norm": 2.1695611476898193,
|
| 1092 |
+
"learning_rate": 2.2719449225473322e-07,
|
| 1093 |
+
"loss": 2.206,
|
| 1094 |
+
"step": 22500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 78.0,
|
| 1098 |
+
"eval_accuracy": 0.8935723514211886,
|
| 1099 |
+
"eval_loss": 2.3046042919158936,
|
| 1100 |
+
"eval_model_preparation_time": 0.005,
|
| 1101 |
+
"eval_runtime": 54.1529,
|
| 1102 |
+
"eval_samples_per_second": 114.343,
|
| 1103 |
+
"eval_steps_per_second": 14.293,
|
| 1104 |
+
"step": 22698
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 79.0,
|
| 1108 |
+
"eval_accuracy": 0.8943798449612403,
|
| 1109 |
+
"eval_loss": 2.297482490539551,
|
| 1110 |
+
"eval_model_preparation_time": 0.005,
|
| 1111 |
+
"eval_runtime": 52.2319,
|
| 1112 |
+
"eval_samples_per_second": 118.548,
|
| 1113 |
+
"eval_steps_per_second": 14.819,
|
| 1114 |
+
"step": 22989
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 79.03780068728523,
|
| 1118 |
+
"grad_norm": 2.3586909770965576,
|
| 1119 |
+
"learning_rate": 2.099827882960413e-07,
|
| 1120 |
+
"loss": 2.1947,
|
| 1121 |
+
"step": 23000
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 80.0,
|
| 1125 |
+
"eval_accuracy": 0.8938953488372093,
|
| 1126 |
+
"eval_loss": 2.291203260421753,
|
| 1127 |
+
"eval_model_preparation_time": 0.005,
|
| 1128 |
+
"eval_runtime": 52.1733,
|
| 1129 |
+
"eval_samples_per_second": 118.681,
|
| 1130 |
+
"eval_steps_per_second": 14.835,
|
| 1131 |
+
"step": 23280
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 80.75601374570446,
|
| 1135 |
+
"grad_norm": 2.4226436614990234,
|
| 1136 |
+
"learning_rate": 1.9277108433734939e-07,
|
| 1137 |
+
"loss": 2.1804,
|
| 1138 |
+
"step": 23500
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 81.0,
|
| 1142 |
+
"eval_accuracy": 0.8937338501291989,
|
| 1143 |
+
"eval_loss": 2.285174608230591,
|
| 1144 |
+
"eval_model_preparation_time": 0.005,
|
| 1145 |
+
"eval_runtime": 52.1705,
|
| 1146 |
+
"eval_samples_per_second": 118.688,
|
| 1147 |
+
"eval_steps_per_second": 14.836,
|
| 1148 |
+
"step": 23571
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 82.0,
|
| 1152 |
+
"eval_accuracy": 0.8940568475452196,
|
| 1153 |
+
"eval_loss": 2.2793898582458496,
|
| 1154 |
+
"eval_model_preparation_time": 0.005,
|
| 1155 |
+
"eval_runtime": 53.532,
|
| 1156 |
+
"eval_samples_per_second": 115.669,
|
| 1157 |
+
"eval_steps_per_second": 14.459,
|
| 1158 |
+
"step": 23862
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 82.47422680412372,
|
| 1162 |
+
"grad_norm": 2.2000808715820312,
|
| 1163 |
+
"learning_rate": 1.7555938037865747e-07,
|
| 1164 |
+
"loss": 2.1725,
|
| 1165 |
+
"step": 24000
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 83.0,
|
| 1169 |
+
"eval_accuracy": 0.895187338501292,
|
| 1170 |
+
"eval_loss": 2.2743537425994873,
|
| 1171 |
+
"eval_model_preparation_time": 0.005,
|
| 1172 |
+
"eval_runtime": 52.7704,
|
| 1173 |
+
"eval_samples_per_second": 117.338,
|
| 1174 |
+
"eval_steps_per_second": 14.667,
|
| 1175 |
+
"step": 24153
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 84.0,
|
| 1179 |
+
"eval_accuracy": 0.8953488372093024,
|
| 1180 |
+
"eval_loss": 2.2692511081695557,
|
| 1181 |
+
"eval_model_preparation_time": 0.005,
|
| 1182 |
+
"eval_runtime": 52.6929,
|
| 1183 |
+
"eval_samples_per_second": 117.511,
|
| 1184 |
+
"eval_steps_per_second": 14.689,
|
| 1185 |
+
"step": 24444
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 84.19243986254295,
|
| 1189 |
+
"grad_norm": 1.9906361103057861,
|
| 1190 |
+
"learning_rate": 1.5834767641996558e-07,
|
| 1191 |
+
"loss": 2.165,
|
| 1192 |
+
"step": 24500
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 85.0,
|
| 1196 |
+
"eval_accuracy": 0.895187338501292,
|
| 1197 |
+
"eval_loss": 2.264594078063965,
|
| 1198 |
+
"eval_model_preparation_time": 0.005,
|
| 1199 |
+
"eval_runtime": 53.0382,
|
| 1200 |
+
"eval_samples_per_second": 116.746,
|
| 1201 |
+
"eval_steps_per_second": 14.593,
|
| 1202 |
+
"step": 24735
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 85.91065292096219,
|
| 1206 |
+
"grad_norm": 2.219193935394287,
|
| 1207 |
+
"learning_rate": 1.4113597246127366e-07,
|
| 1208 |
+
"loss": 2.1539,
|
| 1209 |
+
"step": 25000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 86.0,
|
| 1213 |
+
"eval_accuracy": 0.8955103359173127,
|
| 1214 |
+
"eval_loss": 2.2601823806762695,
|
| 1215 |
+
"eval_model_preparation_time": 0.005,
|
| 1216 |
+
"eval_runtime": 53.4023,
|
| 1217 |
+
"eval_samples_per_second": 115.95,
|
| 1218 |
+
"eval_steps_per_second": 14.494,
|
| 1219 |
+
"step": 25026
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 87.0,
|
| 1223 |
+
"eval_accuracy": 0.8955103359173127,
|
| 1224 |
+
"eval_loss": 2.2560276985168457,
|
| 1225 |
+
"eval_model_preparation_time": 0.005,
|
| 1226 |
+
"eval_runtime": 52.4937,
|
| 1227 |
+
"eval_samples_per_second": 117.957,
|
| 1228 |
+
"eval_steps_per_second": 14.745,
|
| 1229 |
+
"step": 25317
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 87.62886597938144,
|
| 1233 |
+
"grad_norm": 1.8535250425338745,
|
| 1234 |
+
"learning_rate": 1.2392426850258174e-07,
|
| 1235 |
+
"loss": 2.1479,
|
| 1236 |
+
"step": 25500
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 88.0,
|
| 1240 |
+
"eval_accuracy": 0.895671834625323,
|
| 1241 |
+
"eval_loss": 2.2524540424346924,
|
| 1242 |
+
"eval_model_preparation_time": 0.005,
|
| 1243 |
+
"eval_runtime": 52.1601,
|
| 1244 |
+
"eval_samples_per_second": 118.712,
|
| 1245 |
+
"eval_steps_per_second": 14.839,
|
| 1246 |
+
"step": 25608
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 89.0,
|
| 1250 |
+
"eval_accuracy": 0.8964793281653747,
|
| 1251 |
+
"eval_loss": 2.2489233016967773,
|
| 1252 |
+
"eval_model_preparation_time": 0.005,
|
| 1253 |
+
"eval_runtime": 52.5825,
|
| 1254 |
+
"eval_samples_per_second": 117.758,
|
| 1255 |
+
"eval_steps_per_second": 14.72,
|
| 1256 |
+
"step": 25899
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 89.34707903780068,
|
| 1260 |
+
"grad_norm": 1.8873833417892456,
|
| 1261 |
+
"learning_rate": 1.0671256454388984e-07,
|
| 1262 |
+
"loss": 2.1392,
|
| 1263 |
+
"step": 26000
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 90.0,
|
| 1267 |
+
"eval_accuracy": 0.896640826873385,
|
| 1268 |
+
"eval_loss": 2.2456018924713135,
|
| 1269 |
+
"eval_model_preparation_time": 0.005,
|
| 1270 |
+
"eval_runtime": 52.5499,
|
| 1271 |
+
"eval_samples_per_second": 117.831,
|
| 1272 |
+
"eval_steps_per_second": 14.729,
|
| 1273 |
+
"step": 26190
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 91.0,
|
| 1277 |
+
"eval_accuracy": 0.896640826873385,
|
| 1278 |
+
"eval_loss": 2.2428722381591797,
|
| 1279 |
+
"eval_model_preparation_time": 0.005,
|
| 1280 |
+
"eval_runtime": 52.35,
|
| 1281 |
+
"eval_samples_per_second": 118.281,
|
| 1282 |
+
"eval_steps_per_second": 14.785,
|
| 1283 |
+
"step": 26481
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 91.06529209621993,
|
| 1287 |
+
"grad_norm": 1.9566396474838257,
|
| 1288 |
+
"learning_rate": 8.950086058519793e-08,
|
| 1289 |
+
"loss": 2.1339,
|
| 1290 |
+
"step": 26500
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 92.0,
|
| 1294 |
+
"eval_accuracy": 0.8968023255813954,
|
| 1295 |
+
"eval_loss": 2.240267515182495,
|
| 1296 |
+
"eval_model_preparation_time": 0.005,
|
| 1297 |
+
"eval_runtime": 53.7343,
|
| 1298 |
+
"eval_samples_per_second": 115.234,
|
| 1299 |
+
"eval_steps_per_second": 14.404,
|
| 1300 |
+
"step": 26772
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 92.78350515463917,
|
| 1304 |
+
"grad_norm": 2.347038745880127,
|
| 1305 |
+
"learning_rate": 7.228915662650602e-08,
|
| 1306 |
+
"loss": 2.1307,
|
| 1307 |
+
"step": 27000
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 93.0,
|
| 1311 |
+
"eval_accuracy": 0.8964793281653747,
|
| 1312 |
+
"eval_loss": 2.2379775047302246,
|
| 1313 |
+
"eval_model_preparation_time": 0.005,
|
| 1314 |
+
"eval_runtime": 52.7112,
|
| 1315 |
+
"eval_samples_per_second": 117.47,
|
| 1316 |
+
"eval_steps_per_second": 14.684,
|
| 1317 |
+
"step": 27063
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 94.0,
|
| 1321 |
+
"eval_accuracy": 0.8964793281653747,
|
| 1322 |
+
"eval_loss": 2.2358651161193848,
|
| 1323 |
+
"eval_model_preparation_time": 0.005,
|
| 1324 |
+
"eval_runtime": 52.7355,
|
| 1325 |
+
"eval_samples_per_second": 117.416,
|
| 1326 |
+
"eval_steps_per_second": 14.677,
|
| 1327 |
+
"step": 27354
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 94.50171821305842,
|
| 1331 |
+
"grad_norm": 2.1997811794281006,
|
| 1332 |
+
"learning_rate": 5.507745266781411e-08,
|
| 1333 |
+
"loss": 2.1234,
|
| 1334 |
+
"step": 27500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 95.0,
|
| 1338 |
+
"eval_accuracy": 0.8963178294573644,
|
| 1339 |
+
"eval_loss": 2.2341957092285156,
|
| 1340 |
+
"eval_model_preparation_time": 0.005,
|
| 1341 |
+
"eval_runtime": 52.5471,
|
| 1342 |
+
"eval_samples_per_second": 117.837,
|
| 1343 |
+
"eval_steps_per_second": 14.73,
|
| 1344 |
+
"step": 27645
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 96.0,
|
| 1348 |
+
"eval_accuracy": 0.8964793281653747,
|
| 1349 |
+
"eval_loss": 2.2328357696533203,
|
| 1350 |
+
"eval_model_preparation_time": 0.005,
|
| 1351 |
+
"eval_runtime": 53.6532,
|
| 1352 |
+
"eval_samples_per_second": 115.408,
|
| 1353 |
+
"eval_steps_per_second": 14.426,
|
| 1354 |
+
"step": 27936
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 96.21993127147766,
|
| 1358 |
+
"grad_norm": 1.939498782157898,
|
| 1359 |
+
"learning_rate": 3.78657487091222e-08,
|
| 1360 |
+
"loss": 2.1212,
|
| 1361 |
+
"step": 28000
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 97.0,
|
| 1365 |
+
"eval_accuracy": 0.8964793281653747,
|
| 1366 |
+
"eval_loss": 2.2317166328430176,
|
| 1367 |
+
"eval_model_preparation_time": 0.005,
|
| 1368 |
+
"eval_runtime": 52.8569,
|
| 1369 |
+
"eval_samples_per_second": 117.146,
|
| 1370 |
+
"eval_steps_per_second": 14.643,
|
| 1371 |
+
"step": 28227
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 97.9381443298969,
|
| 1375 |
+
"grad_norm": 2.966059684753418,
|
| 1376 |
+
"learning_rate": 2.0654044750430294e-08,
|
| 1377 |
+
"loss": 2.1197,
|
| 1378 |
+
"step": 28500
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 98.0,
|
| 1382 |
+
"eval_accuracy": 0.8963178294573644,
|
| 1383 |
+
"eval_loss": 2.231013059616089,
|
| 1384 |
+
"eval_model_preparation_time": 0.005,
|
| 1385 |
+
"eval_runtime": 52.9339,
|
| 1386 |
+
"eval_samples_per_second": 116.976,
|
| 1387 |
+
"eval_steps_per_second": 14.622,
|
| 1388 |
+
"step": 28518
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 99.0,
|
| 1392 |
+
"eval_accuracy": 0.8964793281653747,
|
| 1393 |
+
"eval_loss": 2.2305853366851807,
|
| 1394 |
+
"eval_model_preparation_time": 0.005,
|
| 1395 |
+
"eval_runtime": 53.021,
|
| 1396 |
+
"eval_samples_per_second": 116.784,
|
| 1397 |
+
"eval_steps_per_second": 14.598,
|
| 1398 |
+
"step": 28809
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 99.65635738831615,
|
| 1402 |
+
"grad_norm": 2.3651483058929443,
|
| 1403 |
+
"learning_rate": 3.442340791738382e-09,
|
| 1404 |
+
"loss": 2.1161,
|
| 1405 |
+
"step": 29000
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 100.0,
|
| 1409 |
+
"eval_accuracy": 0.8963178294573644,
|
| 1410 |
+
"eval_loss": 2.2304611206054688,
|
| 1411 |
+
"eval_model_preparation_time": 0.005,
|
| 1412 |
+
"eval_runtime": 52.8568,
|
| 1413 |
+
"eval_samples_per_second": 117.147,
|
| 1414 |
+
"eval_steps_per_second": 14.643,
|
| 1415 |
+
"step": 29100
|
| 1416 |
+
}
|
| 1417 |
+
],
|
| 1418 |
+
"logging_steps": 500,
|
| 1419 |
+
"max_steps": 29100,
|
| 1420 |
+
"num_input_tokens_seen": 0,
|
| 1421 |
+
"num_train_epochs": 100,
|
| 1422 |
+
"save_steps": 500,
|
| 1423 |
+
"stateful_callbacks": {
|
| 1424 |
+
"TrainerControl": {
|
| 1425 |
+
"args": {
|
| 1426 |
+
"should_epoch_stop": false,
|
| 1427 |
+
"should_evaluate": false,
|
| 1428 |
+
"should_log": false,
|
| 1429 |
+
"should_save": true,
|
| 1430 |
+
"should_training_stop": true
|
| 1431 |
+
},
|
| 1432 |
+
"attributes": {}
|
| 1433 |
+
}
|
| 1434 |
+
},
|
| 1435 |
+
"total_flos": 7.200356285135443e+19,
|
| 1436 |
+
"train_batch_size": 32,
|
| 1437 |
+
"trial_name": null,
|
| 1438 |
+
"trial_params": null
|
| 1439 |
+
}
|
checkpoint-29100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:375fecfe3250f0d7d4d281c005412dc987d92419d67a86bffe4969cb248991cd
|
| 3 |
+
size 4731
|
config.json
CHANGED
|
@@ -9,152 +9,152 @@
|
|
| 9 |
"hidden_dropout_prob": 0.0,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
-
"0": "
|
| 13 |
-
"1": "
|
| 14 |
-
"2": "
|
| 15 |
-
"3": "
|
| 16 |
-
"4": "
|
| 17 |
-
"5": "
|
| 18 |
-
"6": "
|
| 19 |
-
"7": "
|
| 20 |
-
"8": "
|
| 21 |
-
"9": "
|
| 22 |
-
"10": "
|
| 23 |
-
"11": "
|
| 24 |
-
"12": "
|
| 25 |
-
"13": "
|
| 26 |
-
"14": "
|
| 27 |
-
"15": "
|
| 28 |
-
"16": "
|
| 29 |
-
"17": "
|
| 30 |
-
"18": "
|
| 31 |
-
"19": "
|
| 32 |
-
"20": "
|
| 33 |
-
"21": "
|
| 34 |
-
"22": "
|
| 35 |
-
"23": "
|
| 36 |
-
"24": "
|
| 37 |
"25": "Chow",
|
| 38 |
-
"26": "
|
| 39 |
-
"27": "
|
| 40 |
-
"28": "
|
| 41 |
-
"29": "
|
| 42 |
-
"30": "
|
| 43 |
-
"31": "
|
| 44 |
-
"32": "
|
| 45 |
-
"33": "
|
| 46 |
-
"34": "
|
| 47 |
-
"35": "
|
| 48 |
-
"36": "
|
| 49 |
-
"37": "
|
| 50 |
-
"38": "
|
| 51 |
-
"39": "
|
| 52 |
-
"40": "
|
| 53 |
-
"41": "
|
| 54 |
-
"42": "
|
| 55 |
-
"43": "
|
| 56 |
-
"44": "
|
| 57 |
-
"45": "
|
| 58 |
"46": "Japanese Spaniel",
|
| 59 |
-
"47": "
|
| 60 |
"48": "Labradoodle",
|
| 61 |
-
"49": "
|
| 62 |
-
"50": "
|
| 63 |
-
"51": "
|
| 64 |
-
"52": "
|
| 65 |
-
"53": "
|
| 66 |
-
"54": "
|
| 67 |
-
"55": "
|
| 68 |
-
"56": "
|
| 69 |
-
"57": "
|
| 70 |
-
"58": "
|
| 71 |
-
"59": "
|
| 72 |
-
"60": "
|
| 73 |
-
"61": "
|
| 74 |
-
"62": "
|
| 75 |
-
"63": "
|
| 76 |
-
"64": "
|
| 77 |
-
"65": "
|
| 78 |
-
"66": "
|
| 79 |
-
"67": "
|
| 80 |
-
"68": "
|
| 81 |
-
"69": "
|
| 82 |
"70": "Yorkie"
|
| 83 |
},
|
| 84 |
"image_size": 224,
|
| 85 |
"initializer_range": 0.02,
|
| 86 |
"intermediate_size": 3072,
|
| 87 |
"label2id": {
|
| 88 |
-
"Afghan":
|
| 89 |
-
"African Wild Dog":
|
| 90 |
-
"Airedale":
|
| 91 |
-
"American Spaniel":
|
| 92 |
-
"American Hairless":
|
| 93 |
-
"American Spaniel":
|
| 94 |
-
"Basenji":
|
| 95 |
-
"Basset":
|
| 96 |
-
"Beagle":
|
| 97 |
-
"Bearded Collie":
|
| 98 |
-
"Bermaise":
|
| 99 |
-
"Bichon Frise":
|
| 100 |
-
"Blenheim":
|
| 101 |
-
"Bloodhound":
|
| 102 |
-
"Bluetick":
|
| 103 |
-
"Border Collie":
|
| 104 |
-
"Borzoi":
|
| 105 |
-
"Boston Terrier":
|
| 106 |
-
"Boxer":
|
| 107 |
-
"Bull Mastiff":
|
| 108 |
-
"Bull Terrier":
|
| 109 |
-
"Bulldog":
|
| 110 |
-
"Cairn":
|
| 111 |
-
"Chihuahua":
|
| 112 |
-
"Chinese Crested":
|
| 113 |
"Chow": 25,
|
| 114 |
-
"Clumber":
|
| 115 |
-
"Cockapoo":
|
| 116 |
-
"Cocker":
|
| 117 |
-
"Collie":
|
| 118 |
-
"Corgi":
|
| 119 |
-
"Coyote":
|
| 120 |
-
"Dalmation":
|
| 121 |
-
"Dhole":
|
| 122 |
-
"Dingo":
|
| 123 |
-
"Doberman":
|
| 124 |
-
"Elk Hound":
|
| 125 |
-
"French Bulldog":
|
| 126 |
-
"German Sheperd":
|
| 127 |
-
"Golden Retriever":
|
| 128 |
-
"Great Dane":
|
| 129 |
-
"Great Perenees":
|
| 130 |
-
"Greyhound":
|
| 131 |
-
"Groenendael":
|
| 132 |
-
"Irish Spaniel":
|
| 133 |
-
"Irish Wolfhound":
|
| 134 |
"Japanese Spaniel": 46,
|
| 135 |
-
"Komondor":
|
| 136 |
"Labradoodle": 48,
|
| 137 |
-
"Labrador":
|
| 138 |
-
"Lhasa":
|
| 139 |
-
"Malinois":
|
| 140 |
-
"Maltese":
|
| 141 |
-
"Mex Hairless":
|
| 142 |
-
"Newfoundland":
|
| 143 |
-
"Pekinese":
|
| 144 |
-
"Pit Bull":
|
| 145 |
-
"Pomeranian":
|
| 146 |
-
"Poodle":
|
| 147 |
-
"Pug":
|
| 148 |
-
"Rhodesian":
|
| 149 |
-
"Rottweiler":
|
| 150 |
-
"Saint Bernard":
|
| 151 |
-
"Schnauzer":
|
| 152 |
-
"Scotch Terrier":
|
| 153 |
-
"Shar_Pei":
|
| 154 |
-
"Shiba Inu":
|
| 155 |
-
"Shih-Tzu":
|
| 156 |
-
"Siberian Husky":
|
| 157 |
-
"Vizsla":
|
| 158 |
"Yorkie": 70
|
| 159 |
},
|
| 160 |
"layer_norm_eps": 1e-12,
|
|
@@ -166,5 +166,5 @@
|
|
| 166 |
"problem_type": "single_label_classification",
|
| 167 |
"qkv_bias": true,
|
| 168 |
"torch_dtype": "float32",
|
| 169 |
-
"transformers_version": "4.
|
| 170 |
}
|
|
|
|
| 9 |
"hidden_dropout_prob": 0.0,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
+
"0": "Afghan",
|
| 13 |
+
"1": "African Wild Dog",
|
| 14 |
+
"2": "Airedale",
|
| 15 |
+
"3": "American Spaniel",
|
| 16 |
+
"4": "American Hairless",
|
| 17 |
+
"5": "American Spaniel",
|
| 18 |
+
"6": "Basenji",
|
| 19 |
+
"7": "Basset",
|
| 20 |
+
"8": "Beagle",
|
| 21 |
+
"9": "Bearded Collie",
|
| 22 |
+
"10": "Bermaise",
|
| 23 |
+
"11": "Bichon Frise",
|
| 24 |
+
"12": "Blenheim",
|
| 25 |
+
"13": "Bloodhound",
|
| 26 |
+
"14": "Bluetick",
|
| 27 |
+
"15": "Border Collie",
|
| 28 |
+
"16": "Borzoi",
|
| 29 |
+
"17": "Boston Terrier",
|
| 30 |
+
"18": "Boxer",
|
| 31 |
+
"19": "Bull Mastiff",
|
| 32 |
+
"20": "Bull Terrier",
|
| 33 |
+
"21": "Bulldog",
|
| 34 |
+
"22": "Cairn",
|
| 35 |
+
"23": "Chihuahua",
|
| 36 |
+
"24": "Chinese Crested",
|
| 37 |
"25": "Chow",
|
| 38 |
+
"26": "Clumber",
|
| 39 |
+
"27": "Cockapoo",
|
| 40 |
+
"28": "Cocker",
|
| 41 |
+
"29": "Collie",
|
| 42 |
+
"30": "Corgi",
|
| 43 |
+
"31": "Coyote",
|
| 44 |
+
"32": "Dalmation",
|
| 45 |
+
"33": "Dhole",
|
| 46 |
+
"34": "Dingo",
|
| 47 |
+
"35": "Doberman",
|
| 48 |
+
"36": "Elk Hound",
|
| 49 |
+
"37": "French Bulldog",
|
| 50 |
+
"38": "German Sheperd",
|
| 51 |
+
"39": "Golden Retriever",
|
| 52 |
+
"40": "Great Dane",
|
| 53 |
+
"41": "Great Perenees",
|
| 54 |
+
"42": "Greyhound",
|
| 55 |
+
"43": "Groenendael",
|
| 56 |
+
"44": "Irish Spaniel",
|
| 57 |
+
"45": "Irish Wolfhound",
|
| 58 |
"46": "Japanese Spaniel",
|
| 59 |
+
"47": "Komondor",
|
| 60 |
"48": "Labradoodle",
|
| 61 |
+
"49": "Labrador",
|
| 62 |
+
"50": "Lhasa",
|
| 63 |
+
"51": "Malinois",
|
| 64 |
+
"52": "Maltese",
|
| 65 |
+
"53": "Mex Hairless",
|
| 66 |
+
"54": "Newfoundland",
|
| 67 |
+
"55": "Pekinese",
|
| 68 |
+
"56": "Pit Bull",
|
| 69 |
+
"57": "Pomeranian",
|
| 70 |
+
"58": "Poodle",
|
| 71 |
+
"59": "Pug",
|
| 72 |
+
"60": "Rhodesian",
|
| 73 |
+
"61": "Rottweiler",
|
| 74 |
+
"62": "Saint Bernard",
|
| 75 |
+
"63": "Schnauzer",
|
| 76 |
+
"64": "Scotch Terrier",
|
| 77 |
+
"65": "Shar_Pei",
|
| 78 |
+
"66": "Shiba Inu",
|
| 79 |
+
"67": "Shih-Tzu",
|
| 80 |
+
"68": "Siberian Husky",
|
| 81 |
+
"69": "Vizsla",
|
| 82 |
"70": "Yorkie"
|
| 83 |
},
|
| 84 |
"image_size": 224,
|
| 85 |
"initializer_range": 0.02,
|
| 86 |
"intermediate_size": 3072,
|
| 87 |
"label2id": {
|
| 88 |
+
"Afghan": 0,
|
| 89 |
+
"African Wild Dog": 1,
|
| 90 |
+
"Airedale": 2,
|
| 91 |
+
"American Spaniel": 3,
|
| 92 |
+
"American Hairless": 4,
|
| 93 |
+
"American Spaniel": 5,
|
| 94 |
+
"Basenji": 6,
|
| 95 |
+
"Basset": 7,
|
| 96 |
+
"Beagle": 8,
|
| 97 |
+
"Bearded Collie": 9,
|
| 98 |
+
"Bermaise": 10,
|
| 99 |
+
"Bichon Frise": 11,
|
| 100 |
+
"Blenheim": 12,
|
| 101 |
+
"Bloodhound": 13,
|
| 102 |
+
"Bluetick": 14,
|
| 103 |
+
"Border Collie": 15,
|
| 104 |
+
"Borzoi": 16,
|
| 105 |
+
"Boston Terrier": 17,
|
| 106 |
+
"Boxer": 18,
|
| 107 |
+
"Bull Mastiff": 19,
|
| 108 |
+
"Bull Terrier": 20,
|
| 109 |
+
"Bulldog": 21,
|
| 110 |
+
"Cairn": 22,
|
| 111 |
+
"Chihuahua": 23,
|
| 112 |
+
"Chinese Crested": 24,
|
| 113 |
"Chow": 25,
|
| 114 |
+
"Clumber": 26,
|
| 115 |
+
"Cockapoo": 27,
|
| 116 |
+
"Cocker": 28,
|
| 117 |
+
"Collie": 29,
|
| 118 |
+
"Corgi": 30,
|
| 119 |
+
"Coyote": 31,
|
| 120 |
+
"Dalmation": 32,
|
| 121 |
+
"Dhole": 33,
|
| 122 |
+
"Dingo": 34,
|
| 123 |
+
"Doberman": 35,
|
| 124 |
+
"Elk Hound": 36,
|
| 125 |
+
"French Bulldog": 37,
|
| 126 |
+
"German Sheperd": 38,
|
| 127 |
+
"Golden Retriever": 39,
|
| 128 |
+
"Great Dane": 40,
|
| 129 |
+
"Great Perenees": 41,
|
| 130 |
+
"Greyhound": 42,
|
| 131 |
+
"Groenendael": 43,
|
| 132 |
+
"Irish Spaniel": 44,
|
| 133 |
+
"Irish Wolfhound": 45,
|
| 134 |
"Japanese Spaniel": 46,
|
| 135 |
+
"Komondor": 47,
|
| 136 |
"Labradoodle": 48,
|
| 137 |
+
"Labrador": 49,
|
| 138 |
+
"Lhasa": 50,
|
| 139 |
+
"Malinois": 51,
|
| 140 |
+
"Maltese": 52,
|
| 141 |
+
"Mex Hairless": 53,
|
| 142 |
+
"Newfoundland": 54,
|
| 143 |
+
"Pekinese": 55,
|
| 144 |
+
"Pit Bull": 56,
|
| 145 |
+
"Pomeranian": 57,
|
| 146 |
+
"Poodle": 58,
|
| 147 |
+
"Pug": 59,
|
| 148 |
+
"Rhodesian": 60,
|
| 149 |
+
"Rottweiler": 61,
|
| 150 |
+
"Saint Bernard": 62,
|
| 151 |
+
"Schnauzer": 63,
|
| 152 |
+
"Scotch Terrier": 64,
|
| 153 |
+
"Shar_Pei": 65,
|
| 154 |
+
"Shiba Inu": 66,
|
| 155 |
+
"Shih-Tzu": 67,
|
| 156 |
+
"Siberian Husky": 68,
|
| 157 |
+
"Vizsla": 69,
|
| 158 |
"Yorkie": 70
|
| 159 |
},
|
| 160 |
"layer_norm_eps": 1e-12,
|
|
|
|
| 166 |
"problem_type": "single_label_classification",
|
| 167 |
"qkv_bias": true,
|
| 168 |
"torch_dtype": "float32",
|
| 169 |
+
"transformers_version": "4.45.2"
|
| 170 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343436228
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bda49ac12533271a8bbe1efb216edbf2fe4d89614936f48267431eb3a0ba3b2d
|
| 3 |
size 343436228
|
training_args.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 sha256:375fecfe3250f0d7d4d281c005412dc987d92419d67a86bffe4969cb248991cd
|
| 3 |
+
size 4731
|