Upload folder using huggingface_hub
Browse files- checkpoint-6030/config.json +118 -0
- checkpoint-6030/model.safetensors +3 -0
- checkpoint-6030/optimizer.pt +3 -0
- checkpoint-6030/preprocessor_config.json +22 -0
- checkpoint-6030/rng_state.pth +3 -0
- checkpoint-6030/scheduler.pt +3 -0
- checkpoint-6030/trainer_state.json +361 -0
- checkpoint-6030/training_args.bin +3 -0
- config.json +118 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
checkpoint-6030/config.json
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "african_elephant",
|
| 13 |
+
"1": "alpaca",
|
| 14 |
+
"2": "american_bison",
|
| 15 |
+
"3": "anteater",
|
| 16 |
+
"4": "arctic_fox",
|
| 17 |
+
"5": "armadillo",
|
| 18 |
+
"6": "baboon",
|
| 19 |
+
"7": "badger",
|
| 20 |
+
"8": "blue_whale",
|
| 21 |
+
"9": "brown_bear",
|
| 22 |
+
"10": "camel",
|
| 23 |
+
"11": "dolphin",
|
| 24 |
+
"12": "giraffe",
|
| 25 |
+
"13": "groundhog",
|
| 26 |
+
"14": "highland_cattle",
|
| 27 |
+
"15": "horse",
|
| 28 |
+
"16": "jackal",
|
| 29 |
+
"17": "kangaroo",
|
| 30 |
+
"18": "koala",
|
| 31 |
+
"19": "manatee",
|
| 32 |
+
"20": "mongoose",
|
| 33 |
+
"21": "mountain_goat",
|
| 34 |
+
"22": "opossum",
|
| 35 |
+
"23": "orangutan",
|
| 36 |
+
"24": "otter",
|
| 37 |
+
"25": "polar_bear",
|
| 38 |
+
"26": "porcupine",
|
| 39 |
+
"27": "red_panda",
|
| 40 |
+
"28": "rhinoceros",
|
| 41 |
+
"29": "sea_lion",
|
| 42 |
+
"30": "seal",
|
| 43 |
+
"31": "snow_leopard",
|
| 44 |
+
"32": "squirrel",
|
| 45 |
+
"33": "sugar_glider",
|
| 46 |
+
"34": "tapir",
|
| 47 |
+
"35": "vampire_bat",
|
| 48 |
+
"36": "vicuna",
|
| 49 |
+
"37": "walrus",
|
| 50 |
+
"38": "warthog",
|
| 51 |
+
"39": "water_buffalo",
|
| 52 |
+
"40": "weasel",
|
| 53 |
+
"41": "wildebeest",
|
| 54 |
+
"42": "wombat",
|
| 55 |
+
"43": "yak",
|
| 56 |
+
"44": "zebra"
|
| 57 |
+
},
|
| 58 |
+
"image_size": 224,
|
| 59 |
+
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 3072,
|
| 61 |
+
"label2id": {
|
| 62 |
+
"african_elephant": 0,
|
| 63 |
+
"alpaca": 1,
|
| 64 |
+
"american_bison": 2,
|
| 65 |
+
"anteater": 3,
|
| 66 |
+
"arctic_fox": 4,
|
| 67 |
+
"armadillo": 5,
|
| 68 |
+
"baboon": 6,
|
| 69 |
+
"badger": 7,
|
| 70 |
+
"blue_whale": 8,
|
| 71 |
+
"brown_bear": 9,
|
| 72 |
+
"camel": 10,
|
| 73 |
+
"dolphin": 11,
|
| 74 |
+
"giraffe": 12,
|
| 75 |
+
"groundhog": 13,
|
| 76 |
+
"highland_cattle": 14,
|
| 77 |
+
"horse": 15,
|
| 78 |
+
"jackal": 16,
|
| 79 |
+
"kangaroo": 17,
|
| 80 |
+
"koala": 18,
|
| 81 |
+
"manatee": 19,
|
| 82 |
+
"mongoose": 20,
|
| 83 |
+
"mountain_goat": 21,
|
| 84 |
+
"opossum": 22,
|
| 85 |
+
"orangutan": 23,
|
| 86 |
+
"otter": 24,
|
| 87 |
+
"polar_bear": 25,
|
| 88 |
+
"porcupine": 26,
|
| 89 |
+
"red_panda": 27,
|
| 90 |
+
"rhinoceros": 28,
|
| 91 |
+
"sea_lion": 29,
|
| 92 |
+
"seal": 30,
|
| 93 |
+
"snow_leopard": 31,
|
| 94 |
+
"squirrel": 32,
|
| 95 |
+
"sugar_glider": 33,
|
| 96 |
+
"tapir": 34,
|
| 97 |
+
"vampire_bat": 35,
|
| 98 |
+
"vicuna": 36,
|
| 99 |
+
"walrus": 37,
|
| 100 |
+
"warthog": 38,
|
| 101 |
+
"water_buffalo": 39,
|
| 102 |
+
"weasel": 40,
|
| 103 |
+
"wildebeest": 41,
|
| 104 |
+
"wombat": 42,
|
| 105 |
+
"yak": 43,
|
| 106 |
+
"zebra": 44
|
| 107 |
+
},
|
| 108 |
+
"layer_norm_eps": 1e-12,
|
| 109 |
+
"model_type": "vit",
|
| 110 |
+
"num_attention_heads": 12,
|
| 111 |
+
"num_channels": 3,
|
| 112 |
+
"num_hidden_layers": 12,
|
| 113 |
+
"patch_size": 16,
|
| 114 |
+
"problem_type": "single_label_classification",
|
| 115 |
+
"qkv_bias": true,
|
| 116 |
+
"torch_dtype": "float32",
|
| 117 |
+
"transformers_version": "4.35.2"
|
| 118 |
+
}
|
checkpoint-6030/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e336fe2f266eac9c541f7cd98489c16682b0b349fa876705809f69df2e8da690
|
| 3 |
+
size 343356252
|
checkpoint-6030/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be82dba8a742e51fa8f1a31b446e8557b29504a8b4c026aad66fe655a95cc0d0
|
| 3 |
+
size 686832901
|
checkpoint-6030/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-6030/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eab91c06f2177895c10f88a42e4259722cca4d384b69c8b4270780fe14964cd6
|
| 3 |
+
size 14575
|
checkpoint-6030/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:334524325fda2014362a0a24d0a73b2682e4cc1cd6994e7e2f7898b702c3e945
|
| 3 |
+
size 627
|
checkpoint-6030/trainer_state.json
ADDED
|
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.9018115997314453,
|
| 3 |
+
"best_model_checkpoint": "mammals_45_types_image_classification/checkpoint-6030",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6030,
|
| 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": 0.08114856429463171,
|
| 14 |
+
"eval_loss": 3.75849986076355,
|
| 15 |
+
"eval_runtime": 30.5405,
|
| 16 |
+
"eval_samples_per_second": 104.91,
|
| 17 |
+
"eval_steps_per_second": 3.307,
|
| 18 |
+
"step": 201
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.2075530586766542,
|
| 23 |
+
"eval_loss": 3.7100367546081543,
|
| 24 |
+
"eval_runtime": 29.9814,
|
| 25 |
+
"eval_samples_per_second": 106.866,
|
| 26 |
+
"eval_steps_per_second": 3.369,
|
| 27 |
+
"step": 402
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.49,
|
| 31 |
+
"learning_rate": 9.247491638795987e-07,
|
| 32 |
+
"loss": 3.7416,
|
| 33 |
+
"step": 500
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.3611111111111111,
|
| 38 |
+
"eval_loss": 3.656773567199707,
|
| 39 |
+
"eval_runtime": 30.4974,
|
| 40 |
+
"eval_samples_per_second": 105.058,
|
| 41 |
+
"eval_steps_per_second": 3.312,
|
| 42 |
+
"step": 603
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 4.0,
|
| 46 |
+
"eval_accuracy": 0.5074906367041199,
|
| 47 |
+
"eval_loss": 3.599795341491699,
|
| 48 |
+
"eval_runtime": 30.7929,
|
| 49 |
+
"eval_samples_per_second": 104.05,
|
| 50 |
+
"eval_steps_per_second": 3.28,
|
| 51 |
+
"step": 804
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.98,
|
| 55 |
+
"learning_rate": 8.411371237458194e-07,
|
| 56 |
+
"loss": 3.584,
|
| 57 |
+
"step": 1000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 5.0,
|
| 61 |
+
"eval_accuracy": 0.6448189762796505,
|
| 62 |
+
"eval_loss": 3.5441219806671143,
|
| 63 |
+
"eval_runtime": 31.0865,
|
| 64 |
+
"eval_samples_per_second": 103.067,
|
| 65 |
+
"eval_steps_per_second": 3.249,
|
| 66 |
+
"step": 1005
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 6.0,
|
| 70 |
+
"eval_accuracy": 0.7471910112359551,
|
| 71 |
+
"eval_loss": 3.491813898086548,
|
| 72 |
+
"eval_runtime": 30.1716,
|
| 73 |
+
"eval_samples_per_second": 106.192,
|
| 74 |
+
"eval_steps_per_second": 3.348,
|
| 75 |
+
"step": 1206
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 7.0,
|
| 79 |
+
"eval_accuracy": 0.8074282147315855,
|
| 80 |
+
"eval_loss": 3.4418811798095703,
|
| 81 |
+
"eval_runtime": 29.0772,
|
| 82 |
+
"eval_samples_per_second": 110.189,
|
| 83 |
+
"eval_steps_per_second": 3.474,
|
| 84 |
+
"step": 1407
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 7.46,
|
| 88 |
+
"learning_rate": 7.575250836120402e-07,
|
| 89 |
+
"loss": 3.4263,
|
| 90 |
+
"step": 1500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 8.0,
|
| 94 |
+
"eval_accuracy": 0.8433208489388264,
|
| 95 |
+
"eval_loss": 3.394082546234131,
|
| 96 |
+
"eval_runtime": 30.2291,
|
| 97 |
+
"eval_samples_per_second": 105.991,
|
| 98 |
+
"eval_steps_per_second": 3.341,
|
| 99 |
+
"step": 1608
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 9.0,
|
| 103 |
+
"eval_accuracy": 0.8664169787765293,
|
| 104 |
+
"eval_loss": 3.349376916885376,
|
| 105 |
+
"eval_runtime": 29.5587,
|
| 106 |
+
"eval_samples_per_second": 108.395,
|
| 107 |
+
"eval_steps_per_second": 3.417,
|
| 108 |
+
"step": 1809
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 9.95,
|
| 112 |
+
"learning_rate": 6.739130434782609e-07,
|
| 113 |
+
"loss": 3.2922,
|
| 114 |
+
"step": 2000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 10.0,
|
| 118 |
+
"eval_accuracy": 0.8820224719101124,
|
| 119 |
+
"eval_loss": 3.305469512939453,
|
| 120 |
+
"eval_runtime": 29.4868,
|
| 121 |
+
"eval_samples_per_second": 108.659,
|
| 122 |
+
"eval_steps_per_second": 3.425,
|
| 123 |
+
"step": 2010
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 11.0,
|
| 127 |
+
"eval_accuracy": 0.8948189762796505,
|
| 128 |
+
"eval_loss": 3.2643473148345947,
|
| 129 |
+
"eval_runtime": 29.5531,
|
| 130 |
+
"eval_samples_per_second": 108.415,
|
| 131 |
+
"eval_steps_per_second": 3.418,
|
| 132 |
+
"step": 2211
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 12.0,
|
| 136 |
+
"eval_accuracy": 0.9054307116104869,
|
| 137 |
+
"eval_loss": 3.225986957550049,
|
| 138 |
+
"eval_runtime": 30.7268,
|
| 139 |
+
"eval_samples_per_second": 104.274,
|
| 140 |
+
"eval_steps_per_second": 3.287,
|
| 141 |
+
"step": 2412
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 12.44,
|
| 145 |
+
"learning_rate": 5.903010033444817e-07,
|
| 146 |
+
"loss": 3.1728,
|
| 147 |
+
"step": 2500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 13.0,
|
| 151 |
+
"eval_accuracy": 0.9113607990012484,
|
| 152 |
+
"eval_loss": 3.1893086433410645,
|
| 153 |
+
"eval_runtime": 30.7156,
|
| 154 |
+
"eval_samples_per_second": 104.312,
|
| 155 |
+
"eval_steps_per_second": 3.288,
|
| 156 |
+
"step": 2613
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 14.0,
|
| 160 |
+
"eval_accuracy": 0.9147940074906367,
|
| 161 |
+
"eval_loss": 3.1561264991760254,
|
| 162 |
+
"eval_runtime": 29.1629,
|
| 163 |
+
"eval_samples_per_second": 109.866,
|
| 164 |
+
"eval_steps_per_second": 3.463,
|
| 165 |
+
"step": 2814
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 14.93,
|
| 169 |
+
"learning_rate": 5.066889632107023e-07,
|
| 170 |
+
"loss": 3.0729,
|
| 171 |
+
"step": 3000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 15.0,
|
| 175 |
+
"eval_accuracy": 0.9210362047440699,
|
| 176 |
+
"eval_loss": 3.1243045330047607,
|
| 177 |
+
"eval_runtime": 29.6226,
|
| 178 |
+
"eval_samples_per_second": 108.161,
|
| 179 |
+
"eval_steps_per_second": 3.41,
|
| 180 |
+
"step": 3015
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 16.0,
|
| 184 |
+
"eval_accuracy": 0.9244694132334582,
|
| 185 |
+
"eval_loss": 3.0949244499206543,
|
| 186 |
+
"eval_runtime": 29.2749,
|
| 187 |
+
"eval_samples_per_second": 109.445,
|
| 188 |
+
"eval_steps_per_second": 3.45,
|
| 189 |
+
"step": 3216
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 17.0,
|
| 193 |
+
"eval_accuracy": 0.9269662921348315,
|
| 194 |
+
"eval_loss": 3.0683112144470215,
|
| 195 |
+
"eval_runtime": 29.1985,
|
| 196 |
+
"eval_samples_per_second": 109.732,
|
| 197 |
+
"eval_steps_per_second": 3.459,
|
| 198 |
+
"step": 3417
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 17.41,
|
| 202 |
+
"learning_rate": 4.2307692307692304e-07,
|
| 203 |
+
"loss": 2.9872,
|
| 204 |
+
"step": 3500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 18.0,
|
| 208 |
+
"eval_accuracy": 0.931023720349563,
|
| 209 |
+
"eval_loss": 3.0429186820983887,
|
| 210 |
+
"eval_runtime": 29.3871,
|
| 211 |
+
"eval_samples_per_second": 109.027,
|
| 212 |
+
"eval_steps_per_second": 3.437,
|
| 213 |
+
"step": 3618
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 19.0,
|
| 217 |
+
"eval_accuracy": 0.9353932584269663,
|
| 218 |
+
"eval_loss": 3.02020263671875,
|
| 219 |
+
"eval_runtime": 30.5734,
|
| 220 |
+
"eval_samples_per_second": 104.797,
|
| 221 |
+
"eval_steps_per_second": 3.304,
|
| 222 |
+
"step": 3819
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 19.9,
|
| 226 |
+
"learning_rate": 3.394648829431438e-07,
|
| 227 |
+
"loss": 2.9179,
|
| 228 |
+
"step": 4000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 20.0,
|
| 232 |
+
"eval_accuracy": 0.936641697877653,
|
| 233 |
+
"eval_loss": 2.998936176300049,
|
| 234 |
+
"eval_runtime": 29.6935,
|
| 235 |
+
"eval_samples_per_second": 107.902,
|
| 236 |
+
"eval_steps_per_second": 3.401,
|
| 237 |
+
"step": 4020
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 21.0,
|
| 241 |
+
"eval_accuracy": 0.9382022471910112,
|
| 242 |
+
"eval_loss": 2.98030424118042,
|
| 243 |
+
"eval_runtime": 29.567,
|
| 244 |
+
"eval_samples_per_second": 108.364,
|
| 245 |
+
"eval_steps_per_second": 3.416,
|
| 246 |
+
"step": 4221
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 22.0,
|
| 250 |
+
"eval_accuracy": 0.9391385767790262,
|
| 251 |
+
"eval_loss": 2.963463544845581,
|
| 252 |
+
"eval_runtime": 29.139,
|
| 253 |
+
"eval_samples_per_second": 109.956,
|
| 254 |
+
"eval_steps_per_second": 3.466,
|
| 255 |
+
"step": 4422
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 22.39,
|
| 259 |
+
"learning_rate": 2.5585284280936454e-07,
|
| 260 |
+
"loss": 2.8631,
|
| 261 |
+
"step": 4500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 23.0,
|
| 265 |
+
"eval_accuracy": 0.9397627965043696,
|
| 266 |
+
"eval_loss": 2.948824882507324,
|
| 267 |
+
"eval_runtime": 29.1663,
|
| 268 |
+
"eval_samples_per_second": 109.853,
|
| 269 |
+
"eval_steps_per_second": 3.463,
|
| 270 |
+
"step": 4623
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 24.0,
|
| 274 |
+
"eval_accuracy": 0.9406991260923845,
|
| 275 |
+
"eval_loss": 2.9361581802368164,
|
| 276 |
+
"eval_runtime": 29.4311,
|
| 277 |
+
"eval_samples_per_second": 108.865,
|
| 278 |
+
"eval_steps_per_second": 3.432,
|
| 279 |
+
"step": 4824
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 24.88,
|
| 283 |
+
"learning_rate": 1.7224080267558528e-07,
|
| 284 |
+
"loss": 2.8232,
|
| 285 |
+
"step": 5000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 25.0,
|
| 289 |
+
"eval_accuracy": 0.9410112359550562,
|
| 290 |
+
"eval_loss": 2.925414800643921,
|
| 291 |
+
"eval_runtime": 29.1531,
|
| 292 |
+
"eval_samples_per_second": 109.902,
|
| 293 |
+
"eval_steps_per_second": 3.464,
|
| 294 |
+
"step": 5025
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 26.0,
|
| 298 |
+
"eval_accuracy": 0.9410112359550562,
|
| 299 |
+
"eval_loss": 2.9169344902038574,
|
| 300 |
+
"eval_runtime": 29.0329,
|
| 301 |
+
"eval_samples_per_second": 110.358,
|
| 302 |
+
"eval_steps_per_second": 3.479,
|
| 303 |
+
"step": 5226
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 27.0,
|
| 307 |
+
"eval_accuracy": 0.9413233458177278,
|
| 308 |
+
"eval_loss": 2.910374402999878,
|
| 309 |
+
"eval_runtime": 29.9412,
|
| 310 |
+
"eval_samples_per_second": 107.01,
|
| 311 |
+
"eval_steps_per_second": 3.373,
|
| 312 |
+
"step": 5427
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 27.36,
|
| 316 |
+
"learning_rate": 8.862876254180602e-08,
|
| 317 |
+
"loss": 2.7973,
|
| 318 |
+
"step": 5500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 28.0,
|
| 322 |
+
"eval_accuracy": 0.9416354556803995,
|
| 323 |
+
"eval_loss": 2.905684232711792,
|
| 324 |
+
"eval_runtime": 29.9557,
|
| 325 |
+
"eval_samples_per_second": 106.958,
|
| 326 |
+
"eval_steps_per_second": 3.372,
|
| 327 |
+
"step": 5628
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 29.0,
|
| 331 |
+
"eval_accuracy": 0.9416354556803995,
|
| 332 |
+
"eval_loss": 2.9027676582336426,
|
| 333 |
+
"eval_runtime": 29.4346,
|
| 334 |
+
"eval_samples_per_second": 108.851,
|
| 335 |
+
"eval_steps_per_second": 3.431,
|
| 336 |
+
"step": 5829
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 29.85,
|
| 340 |
+
"learning_rate": 5.016722408026756e-09,
|
| 341 |
+
"loss": 2.7825,
|
| 342 |
+
"step": 6000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 30.0,
|
| 346 |
+
"eval_accuracy": 0.9416354556803995,
|
| 347 |
+
"eval_loss": 2.9018115997314453,
|
| 348 |
+
"eval_runtime": 29.2154,
|
| 349 |
+
"eval_samples_per_second": 109.668,
|
| 350 |
+
"eval_steps_per_second": 3.457,
|
| 351 |
+
"step": 6030
|
| 352 |
+
}
|
| 353 |
+
],
|
| 354 |
+
"logging_steps": 500,
|
| 355 |
+
"max_steps": 6030,
|
| 356 |
+
"num_train_epochs": 30,
|
| 357 |
+
"save_steps": 500,
|
| 358 |
+
"total_flos": 2.980560268384764e+19,
|
| 359 |
+
"trial_name": null,
|
| 360 |
+
"trial_params": null
|
| 361 |
+
}
|
checkpoint-6030/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5197112e7aafa3b6ccf7ea7d30b828ea9762f503efb192189d71522ef61f01e3
|
| 3 |
+
size 4091
|
config.json
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "african_elephant",
|
| 13 |
+
"1": "alpaca",
|
| 14 |
+
"2": "american_bison",
|
| 15 |
+
"3": "anteater",
|
| 16 |
+
"4": "arctic_fox",
|
| 17 |
+
"5": "armadillo",
|
| 18 |
+
"6": "baboon",
|
| 19 |
+
"7": "badger",
|
| 20 |
+
"8": "blue_whale",
|
| 21 |
+
"9": "brown_bear",
|
| 22 |
+
"10": "camel",
|
| 23 |
+
"11": "dolphin",
|
| 24 |
+
"12": "giraffe",
|
| 25 |
+
"13": "groundhog",
|
| 26 |
+
"14": "highland_cattle",
|
| 27 |
+
"15": "horse",
|
| 28 |
+
"16": "jackal",
|
| 29 |
+
"17": "kangaroo",
|
| 30 |
+
"18": "koala",
|
| 31 |
+
"19": "manatee",
|
| 32 |
+
"20": "mongoose",
|
| 33 |
+
"21": "mountain_goat",
|
| 34 |
+
"22": "opossum",
|
| 35 |
+
"23": "orangutan",
|
| 36 |
+
"24": "otter",
|
| 37 |
+
"25": "polar_bear",
|
| 38 |
+
"26": "porcupine",
|
| 39 |
+
"27": "red_panda",
|
| 40 |
+
"28": "rhinoceros",
|
| 41 |
+
"29": "sea_lion",
|
| 42 |
+
"30": "seal",
|
| 43 |
+
"31": "snow_leopard",
|
| 44 |
+
"32": "squirrel",
|
| 45 |
+
"33": "sugar_glider",
|
| 46 |
+
"34": "tapir",
|
| 47 |
+
"35": "vampire_bat",
|
| 48 |
+
"36": "vicuna",
|
| 49 |
+
"37": "walrus",
|
| 50 |
+
"38": "warthog",
|
| 51 |
+
"39": "water_buffalo",
|
| 52 |
+
"40": "weasel",
|
| 53 |
+
"41": "wildebeest",
|
| 54 |
+
"42": "wombat",
|
| 55 |
+
"43": "yak",
|
| 56 |
+
"44": "zebra"
|
| 57 |
+
},
|
| 58 |
+
"image_size": 224,
|
| 59 |
+
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 3072,
|
| 61 |
+
"label2id": {
|
| 62 |
+
"african_elephant": 0,
|
| 63 |
+
"alpaca": 1,
|
| 64 |
+
"american_bison": 2,
|
| 65 |
+
"anteater": 3,
|
| 66 |
+
"arctic_fox": 4,
|
| 67 |
+
"armadillo": 5,
|
| 68 |
+
"baboon": 6,
|
| 69 |
+
"badger": 7,
|
| 70 |
+
"blue_whale": 8,
|
| 71 |
+
"brown_bear": 9,
|
| 72 |
+
"camel": 10,
|
| 73 |
+
"dolphin": 11,
|
| 74 |
+
"giraffe": 12,
|
| 75 |
+
"groundhog": 13,
|
| 76 |
+
"highland_cattle": 14,
|
| 77 |
+
"horse": 15,
|
| 78 |
+
"jackal": 16,
|
| 79 |
+
"kangaroo": 17,
|
| 80 |
+
"koala": 18,
|
| 81 |
+
"manatee": 19,
|
| 82 |
+
"mongoose": 20,
|
| 83 |
+
"mountain_goat": 21,
|
| 84 |
+
"opossum": 22,
|
| 85 |
+
"orangutan": 23,
|
| 86 |
+
"otter": 24,
|
| 87 |
+
"polar_bear": 25,
|
| 88 |
+
"porcupine": 26,
|
| 89 |
+
"red_panda": 27,
|
| 90 |
+
"rhinoceros": 28,
|
| 91 |
+
"sea_lion": 29,
|
| 92 |
+
"seal": 30,
|
| 93 |
+
"snow_leopard": 31,
|
| 94 |
+
"squirrel": 32,
|
| 95 |
+
"sugar_glider": 33,
|
| 96 |
+
"tapir": 34,
|
| 97 |
+
"vampire_bat": 35,
|
| 98 |
+
"vicuna": 36,
|
| 99 |
+
"walrus": 37,
|
| 100 |
+
"warthog": 38,
|
| 101 |
+
"water_buffalo": 39,
|
| 102 |
+
"weasel": 40,
|
| 103 |
+
"wildebeest": 41,
|
| 104 |
+
"wombat": 42,
|
| 105 |
+
"yak": 43,
|
| 106 |
+
"zebra": 44
|
| 107 |
+
},
|
| 108 |
+
"layer_norm_eps": 1e-12,
|
| 109 |
+
"model_type": "vit",
|
| 110 |
+
"num_attention_heads": 12,
|
| 111 |
+
"num_channels": 3,
|
| 112 |
+
"num_hidden_layers": 12,
|
| 113 |
+
"patch_size": 16,
|
| 114 |
+
"problem_type": "single_label_classification",
|
| 115 |
+
"qkv_bias": true,
|
| 116 |
+
"torch_dtype": "float32",
|
| 117 |
+
"transformers_version": "4.35.2"
|
| 118 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e336fe2f266eac9c541f7cd98489c16682b0b349fa876705809f69df2e8da690
|
| 3 |
+
size 343356252
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5197112e7aafa3b6ccf7ea7d30b828ea9762f503efb192189d71522ef61f01e3
|
| 3 |
+
size 4091
|