Upload folder using huggingface_hub
Browse files- all_results.json +13 -0
- checkpoint-500/config.json +68 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/preprocessor_config.json +36 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +416 -0
- checkpoint-500/training_args.bin +3 -0
- checkpoint-700/config.json +68 -0
- checkpoint-700/model.safetensors +3 -0
- checkpoint-700/optimizer.pt +3 -0
- checkpoint-700/preprocessor_config.json +36 -0
- checkpoint-700/rng_state.pth +3 -0
- checkpoint-700/scheduler.pt +3 -0
- checkpoint-700/trainer_state.json +574 -0
- checkpoint-700/training_args.bin +3 -0
- config.json +68 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/May11_09-58-51_7647228388c7/events.out.tfevents.1715421532.7647228388c7.34.0 +3 -0
- runs/May11_09-59-08_7647228388c7/events.out.tfevents.1715421548.7647228388c7.34.1 +3 -0
- runs/May11_09-59-08_7647228388c7/events.out.tfevents.1715422708.7647228388c7.34.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +583 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.82,
|
| 4 |
+
"eval_loss": 0.605766236782074,
|
| 5 |
+
"eval_runtime": 11.6705,
|
| 6 |
+
"eval_samples_per_second": 59.98,
|
| 7 |
+
"eval_steps_per_second": 3.77,
|
| 8 |
+
"total_flos": 1.7361006043594752e+18,
|
| 9 |
+
"train_loss": 0.5924043039764677,
|
| 10 |
+
"train_runtime": 756.4917,
|
| 11 |
+
"train_samples_per_second": 29.61,
|
| 12 |
+
"train_steps_per_second": 0.925
|
| 13 |
+
}
|
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Abyssinian",
|
| 13 |
+
"1": "American Bobtail",
|
| 14 |
+
"10": "Maine Coon",
|
| 15 |
+
"11": "Manx",
|
| 16 |
+
"12": "Norwegian Forest",
|
| 17 |
+
"13": "Persian",
|
| 18 |
+
"14": "Ragdoll",
|
| 19 |
+
"15": "Russian Blue",
|
| 20 |
+
"16": "Scottish Fold",
|
| 21 |
+
"17": "Siamese",
|
| 22 |
+
"18": "Sphynx",
|
| 23 |
+
"19": "Turkish Angora",
|
| 24 |
+
"2": "American Curl",
|
| 25 |
+
"3": "American Shorthair",
|
| 26 |
+
"4": "Bengal",
|
| 27 |
+
"5": "Birman",
|
| 28 |
+
"6": "Bombay",
|
| 29 |
+
"7": "British Shorthair",
|
| 30 |
+
"8": "Egyptian Mau",
|
| 31 |
+
"9": "Exotic Shorthair"
|
| 32 |
+
},
|
| 33 |
+
"image_size": 224,
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"Abyssinian": "0",
|
| 38 |
+
"American Bobtail": "1",
|
| 39 |
+
"American Curl": "2",
|
| 40 |
+
"American Shorthair": "3",
|
| 41 |
+
"Bengal": "4",
|
| 42 |
+
"Birman": "5",
|
| 43 |
+
"Bombay": "6",
|
| 44 |
+
"British Shorthair": "7",
|
| 45 |
+
"Egyptian Mau": "8",
|
| 46 |
+
"Exotic Shorthair": "9",
|
| 47 |
+
"Maine Coon": "10",
|
| 48 |
+
"Manx": "11",
|
| 49 |
+
"Norwegian Forest": "12",
|
| 50 |
+
"Persian": "13",
|
| 51 |
+
"Ragdoll": "14",
|
| 52 |
+
"Russian Blue": "15",
|
| 53 |
+
"Scottish Fold": "16",
|
| 54 |
+
"Siamese": "17",
|
| 55 |
+
"Sphynx": "18",
|
| 56 |
+
"Turkish Angora": "19"
|
| 57 |
+
},
|
| 58 |
+
"layer_norm_eps": 1e-12,
|
| 59 |
+
"model_type": "vit",
|
| 60 |
+
"num_attention_heads": 12,
|
| 61 |
+
"num_channels": 3,
|
| 62 |
+
"num_hidden_layers": 12,
|
| 63 |
+
"patch_size": 16,
|
| 64 |
+
"problem_type": "single_label_classification",
|
| 65 |
+
"qkv_bias": true,
|
| 66 |
+
"torch_dtype": "float32",
|
| 67 |
+
"transformers_version": "4.39.3"
|
| 68 |
+
}
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d651549752e81380e748886a7c451f5ddbaa555ca68212a2c6610eef1ce49e05
|
| 3 |
+
size 343279344
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb7ae6726c4556d53ba0b98ce9710eb81e0b652ae58a4e17a2fa6240f864b965
|
| 3 |
+
size 686679610
|
checkpoint-500/preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTImageProcessor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
|
| 3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ef496d823a04218685901cb17d468d82475f38185508b0125c167c96ef3ec0a
|
| 3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,416 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.605766236782074,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-cats/checkpoint-500",
|
| 4 |
+
"epoch": 2.857142857142857,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"grad_norm": 104665.1796875,
|
| 14 |
+
"learning_rate": 0.00019714285714285716,
|
| 15 |
+
"loss": 2.8888,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11,
|
| 20 |
+
"grad_norm": 102043.53125,
|
| 21 |
+
"learning_rate": 0.0001942857142857143,
|
| 22 |
+
"loss": 2.6146,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.17,
|
| 27 |
+
"grad_norm": 97863.03125,
|
| 28 |
+
"learning_rate": 0.00019142857142857145,
|
| 29 |
+
"loss": 2.3775,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.23,
|
| 34 |
+
"grad_norm": 98961.4453125,
|
| 35 |
+
"learning_rate": 0.00018857142857142857,
|
| 36 |
+
"loss": 2.0395,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.29,
|
| 41 |
+
"grad_norm": 142313.515625,
|
| 42 |
+
"learning_rate": 0.00018571428571428572,
|
| 43 |
+
"loss": 1.8599,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.34,
|
| 48 |
+
"grad_norm": 112630.1328125,
|
| 49 |
+
"learning_rate": 0.00018285714285714286,
|
| 50 |
+
"loss": 1.7573,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4,
|
| 55 |
+
"grad_norm": 180249.9375,
|
| 56 |
+
"learning_rate": 0.00018,
|
| 57 |
+
"loss": 1.5562,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.46,
|
| 62 |
+
"grad_norm": 124194.484375,
|
| 63 |
+
"learning_rate": 0.00017714285714285713,
|
| 64 |
+
"loss": 1.4203,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.51,
|
| 69 |
+
"grad_norm": 187150.671875,
|
| 70 |
+
"learning_rate": 0.0001742857142857143,
|
| 71 |
+
"loss": 1.2605,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.57,
|
| 76 |
+
"grad_norm": 151804.65625,
|
| 77 |
+
"learning_rate": 0.00017142857142857143,
|
| 78 |
+
"loss": 1.2422,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.57,
|
| 83 |
+
"eval_accuracy": 0.7314285714285714,
|
| 84 |
+
"eval_loss": 1.1657222509384155,
|
| 85 |
+
"eval_runtime": 15.2094,
|
| 86 |
+
"eval_samples_per_second": 46.024,
|
| 87 |
+
"eval_steps_per_second": 2.893,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.63,
|
| 92 |
+
"grad_norm": 134052.609375,
|
| 93 |
+
"learning_rate": 0.00016857142857142857,
|
| 94 |
+
"loss": 1.1438,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.69,
|
| 99 |
+
"grad_norm": 163657.515625,
|
| 100 |
+
"learning_rate": 0.00016571428571428575,
|
| 101 |
+
"loss": 1.2158,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.74,
|
| 106 |
+
"grad_norm": 159906.9375,
|
| 107 |
+
"learning_rate": 0.00016285714285714287,
|
| 108 |
+
"loss": 1.0575,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.8,
|
| 113 |
+
"grad_norm": 171710.640625,
|
| 114 |
+
"learning_rate": 0.00016,
|
| 115 |
+
"loss": 1.0049,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.86,
|
| 120 |
+
"grad_norm": 171094.046875,
|
| 121 |
+
"learning_rate": 0.00015714285714285716,
|
| 122 |
+
"loss": 1.0786,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.91,
|
| 127 |
+
"grad_norm": 140285.921875,
|
| 128 |
+
"learning_rate": 0.0001542857142857143,
|
| 129 |
+
"loss": 0.9912,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.97,
|
| 134 |
+
"grad_norm": 170517.640625,
|
| 135 |
+
"learning_rate": 0.00015142857142857143,
|
| 136 |
+
"loss": 0.9448,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.03,
|
| 141 |
+
"grad_norm": 125416.1484375,
|
| 142 |
+
"learning_rate": 0.00014857142857142857,
|
| 143 |
+
"loss": 0.826,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.09,
|
| 148 |
+
"grad_norm": 205800.3125,
|
| 149 |
+
"learning_rate": 0.00014571428571428572,
|
| 150 |
+
"loss": 0.7471,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.14,
|
| 155 |
+
"grad_norm": 74866.34375,
|
| 156 |
+
"learning_rate": 0.00014285714285714287,
|
| 157 |
+
"loss": 0.5948,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.14,
|
| 162 |
+
"eval_accuracy": 0.8,
|
| 163 |
+
"eval_loss": 0.7744152545928955,
|
| 164 |
+
"eval_runtime": 11.8882,
|
| 165 |
+
"eval_samples_per_second": 58.882,
|
| 166 |
+
"eval_steps_per_second": 3.701,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.2,
|
| 171 |
+
"grad_norm": 191153.328125,
|
| 172 |
+
"learning_rate": 0.00014,
|
| 173 |
+
"loss": 0.5425,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.26,
|
| 178 |
+
"grad_norm": 181985.578125,
|
| 179 |
+
"learning_rate": 0.00013714285714285716,
|
| 180 |
+
"loss": 0.6606,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.31,
|
| 185 |
+
"grad_norm": 193704.78125,
|
| 186 |
+
"learning_rate": 0.00013428571428571428,
|
| 187 |
+
"loss": 0.5681,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.37,
|
| 192 |
+
"grad_norm": 135817.890625,
|
| 193 |
+
"learning_rate": 0.00013142857142857143,
|
| 194 |
+
"loss": 0.5497,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.43,
|
| 199 |
+
"grad_norm": 154213.90625,
|
| 200 |
+
"learning_rate": 0.00012857142857142858,
|
| 201 |
+
"loss": 0.562,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.49,
|
| 206 |
+
"grad_norm": 132152.8125,
|
| 207 |
+
"learning_rate": 0.00012571428571428572,
|
| 208 |
+
"loss": 0.5728,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.54,
|
| 213 |
+
"grad_norm": 207587.0625,
|
| 214 |
+
"learning_rate": 0.00012285714285714287,
|
| 215 |
+
"loss": 0.6254,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.6,
|
| 220 |
+
"grad_norm": 98314.2109375,
|
| 221 |
+
"learning_rate": 0.00012,
|
| 222 |
+
"loss": 0.4033,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.66,
|
| 227 |
+
"grad_norm": 107417.6328125,
|
| 228 |
+
"learning_rate": 0.00011714285714285715,
|
| 229 |
+
"loss": 0.4892,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.71,
|
| 234 |
+
"grad_norm": 250248.421875,
|
| 235 |
+
"learning_rate": 0.00011428571428571428,
|
| 236 |
+
"loss": 0.5324,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.71,
|
| 241 |
+
"eval_accuracy": 0.8128571428571428,
|
| 242 |
+
"eval_loss": 0.6736084818840027,
|
| 243 |
+
"eval_runtime": 13.3903,
|
| 244 |
+
"eval_samples_per_second": 52.277,
|
| 245 |
+
"eval_steps_per_second": 3.286,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.77,
|
| 250 |
+
"grad_norm": 165674.15625,
|
| 251 |
+
"learning_rate": 0.00011142857142857144,
|
| 252 |
+
"loss": 0.4641,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.83,
|
| 257 |
+
"grad_norm": 194581.40625,
|
| 258 |
+
"learning_rate": 0.00010857142857142856,
|
| 259 |
+
"loss": 0.4818,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.89,
|
| 264 |
+
"grad_norm": 138774.1875,
|
| 265 |
+
"learning_rate": 0.00010571428571428572,
|
| 266 |
+
"loss": 0.4677,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.94,
|
| 271 |
+
"grad_norm": 203262.421875,
|
| 272 |
+
"learning_rate": 0.00010285714285714286,
|
| 273 |
+
"loss": 0.4034,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.0,
|
| 278 |
+
"grad_norm": 128663.1875,
|
| 279 |
+
"learning_rate": 0.0001,
|
| 280 |
+
"loss": 0.3978,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.06,
|
| 285 |
+
"grad_norm": 35406.80078125,
|
| 286 |
+
"learning_rate": 9.714285714285715e-05,
|
| 287 |
+
"loss": 0.2415,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.11,
|
| 292 |
+
"grad_norm": 128107.3046875,
|
| 293 |
+
"learning_rate": 9.428571428571429e-05,
|
| 294 |
+
"loss": 0.2798,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.17,
|
| 299 |
+
"grad_norm": 52566.515625,
|
| 300 |
+
"learning_rate": 9.142857142857143e-05,
|
| 301 |
+
"loss": 0.2742,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.23,
|
| 306 |
+
"grad_norm": 49925.12890625,
|
| 307 |
+
"learning_rate": 8.857142857142857e-05,
|
| 308 |
+
"loss": 0.2293,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.29,
|
| 313 |
+
"grad_norm": 175336.984375,
|
| 314 |
+
"learning_rate": 8.571428571428571e-05,
|
| 315 |
+
"loss": 0.212,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.29,
|
| 320 |
+
"eval_accuracy": 0.8085714285714286,
|
| 321 |
+
"eval_loss": 0.7056272625923157,
|
| 322 |
+
"eval_runtime": 11.5847,
|
| 323 |
+
"eval_samples_per_second": 60.424,
|
| 324 |
+
"eval_steps_per_second": 3.798,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.34,
|
| 329 |
+
"grad_norm": 24206.984375,
|
| 330 |
+
"learning_rate": 8.285714285714287e-05,
|
| 331 |
+
"loss": 0.2311,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.4,
|
| 336 |
+
"grad_norm": 124311.4140625,
|
| 337 |
+
"learning_rate": 8e-05,
|
| 338 |
+
"loss": 0.2342,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.46,
|
| 343 |
+
"grad_norm": 68467.265625,
|
| 344 |
+
"learning_rate": 7.714285714285715e-05,
|
| 345 |
+
"loss": 0.2055,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.51,
|
| 350 |
+
"grad_norm": 104893.53125,
|
| 351 |
+
"learning_rate": 7.428571428571429e-05,
|
| 352 |
+
"loss": 0.1814,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.57,
|
| 357 |
+
"grad_norm": 76138.921875,
|
| 358 |
+
"learning_rate": 7.142857142857143e-05,
|
| 359 |
+
"loss": 0.2127,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.63,
|
| 364 |
+
"grad_norm": 138337.28125,
|
| 365 |
+
"learning_rate": 6.857142857142858e-05,
|
| 366 |
+
"loss": 0.1863,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.69,
|
| 371 |
+
"grad_norm": 47311.3203125,
|
| 372 |
+
"learning_rate": 6.571428571428571e-05,
|
| 373 |
+
"loss": 0.2281,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.74,
|
| 378 |
+
"grad_norm": 107393.203125,
|
| 379 |
+
"learning_rate": 6.285714285714286e-05,
|
| 380 |
+
"loss": 0.1875,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.8,
|
| 385 |
+
"grad_norm": 167001.0,
|
| 386 |
+
"learning_rate": 6e-05,
|
| 387 |
+
"loss": 0.1896,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.86,
|
| 392 |
+
"grad_norm": 90490.375,
|
| 393 |
+
"learning_rate": 5.714285714285714e-05,
|
| 394 |
+
"loss": 0.2158,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.86,
|
| 399 |
+
"eval_accuracy": 0.82,
|
| 400 |
+
"eval_loss": 0.605766236782074,
|
| 401 |
+
"eval_runtime": 11.55,
|
| 402 |
+
"eval_samples_per_second": 60.606,
|
| 403 |
+
"eval_steps_per_second": 3.81,
|
| 404 |
+
"step": 500
|
| 405 |
+
}
|
| 406 |
+
],
|
| 407 |
+
"logging_steps": 10,
|
| 408 |
+
"max_steps": 700,
|
| 409 |
+
"num_input_tokens_seen": 0,
|
| 410 |
+
"num_train_epochs": 4,
|
| 411 |
+
"save_steps": 100,
|
| 412 |
+
"total_flos": 1.240071860256768e+18,
|
| 413 |
+
"train_batch_size": 32,
|
| 414 |
+
"trial_name": null,
|
| 415 |
+
"trial_params": null
|
| 416 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b696add107e34028cff294268207622430a98082e509d660850e58e78a8a3080
|
| 3 |
+
size 4920
|
checkpoint-700/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Abyssinian",
|
| 13 |
+
"1": "American Bobtail",
|
| 14 |
+
"10": "Maine Coon",
|
| 15 |
+
"11": "Manx",
|
| 16 |
+
"12": "Norwegian Forest",
|
| 17 |
+
"13": "Persian",
|
| 18 |
+
"14": "Ragdoll",
|
| 19 |
+
"15": "Russian Blue",
|
| 20 |
+
"16": "Scottish Fold",
|
| 21 |
+
"17": "Siamese",
|
| 22 |
+
"18": "Sphynx",
|
| 23 |
+
"19": "Turkish Angora",
|
| 24 |
+
"2": "American Curl",
|
| 25 |
+
"3": "American Shorthair",
|
| 26 |
+
"4": "Bengal",
|
| 27 |
+
"5": "Birman",
|
| 28 |
+
"6": "Bombay",
|
| 29 |
+
"7": "British Shorthair",
|
| 30 |
+
"8": "Egyptian Mau",
|
| 31 |
+
"9": "Exotic Shorthair"
|
| 32 |
+
},
|
| 33 |
+
"image_size": 224,
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"Abyssinian": "0",
|
| 38 |
+
"American Bobtail": "1",
|
| 39 |
+
"American Curl": "2",
|
| 40 |
+
"American Shorthair": "3",
|
| 41 |
+
"Bengal": "4",
|
| 42 |
+
"Birman": "5",
|
| 43 |
+
"Bombay": "6",
|
| 44 |
+
"British Shorthair": "7",
|
| 45 |
+
"Egyptian Mau": "8",
|
| 46 |
+
"Exotic Shorthair": "9",
|
| 47 |
+
"Maine Coon": "10",
|
| 48 |
+
"Manx": "11",
|
| 49 |
+
"Norwegian Forest": "12",
|
| 50 |
+
"Persian": "13",
|
| 51 |
+
"Ragdoll": "14",
|
| 52 |
+
"Russian Blue": "15",
|
| 53 |
+
"Scottish Fold": "16",
|
| 54 |
+
"Siamese": "17",
|
| 55 |
+
"Sphynx": "18",
|
| 56 |
+
"Turkish Angora": "19"
|
| 57 |
+
},
|
| 58 |
+
"layer_norm_eps": 1e-12,
|
| 59 |
+
"model_type": "vit",
|
| 60 |
+
"num_attention_heads": 12,
|
| 61 |
+
"num_channels": 3,
|
| 62 |
+
"num_hidden_layers": 12,
|
| 63 |
+
"patch_size": 16,
|
| 64 |
+
"problem_type": "single_label_classification",
|
| 65 |
+
"qkv_bias": true,
|
| 66 |
+
"torch_dtype": "float32",
|
| 67 |
+
"transformers_version": "4.39.3"
|
| 68 |
+
}
|
checkpoint-700/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afb5b2ef3cd3db07427f293fb7fe45b838ababd6b5b97fe1f5b500f98d033bc6
|
| 3 |
+
size 343279344
|
checkpoint-700/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56e990bfc39fcdc14ffb905416338b0e8ea24843b5c464e2d7877b6052e8ccc0
|
| 3 |
+
size 686679610
|
checkpoint-700/preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTImageProcessor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
checkpoint-700/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5edb34d031c0c2b447f3eaadb401a4c1e7e7e6d8c096e28b7092e01a8bd48c92
|
| 3 |
+
size 14244
|
checkpoint-700/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29b956a233cae8e71e6a35696b04ca41104cbd5e983f012c5f848e37e99f565e
|
| 3 |
+
size 1064
|
checkpoint-700/trainer_state.json
ADDED
|
@@ -0,0 +1,574 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.605766236782074,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-cats/checkpoint-500",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 700,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"grad_norm": 104665.1796875,
|
| 14 |
+
"learning_rate": 0.00019714285714285716,
|
| 15 |
+
"loss": 2.8888,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11,
|
| 20 |
+
"grad_norm": 102043.53125,
|
| 21 |
+
"learning_rate": 0.0001942857142857143,
|
| 22 |
+
"loss": 2.6146,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.17,
|
| 27 |
+
"grad_norm": 97863.03125,
|
| 28 |
+
"learning_rate": 0.00019142857142857145,
|
| 29 |
+
"loss": 2.3775,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.23,
|
| 34 |
+
"grad_norm": 98961.4453125,
|
| 35 |
+
"learning_rate": 0.00018857142857142857,
|
| 36 |
+
"loss": 2.0395,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.29,
|
| 41 |
+
"grad_norm": 142313.515625,
|
| 42 |
+
"learning_rate": 0.00018571428571428572,
|
| 43 |
+
"loss": 1.8599,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.34,
|
| 48 |
+
"grad_norm": 112630.1328125,
|
| 49 |
+
"learning_rate": 0.00018285714285714286,
|
| 50 |
+
"loss": 1.7573,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4,
|
| 55 |
+
"grad_norm": 180249.9375,
|
| 56 |
+
"learning_rate": 0.00018,
|
| 57 |
+
"loss": 1.5562,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.46,
|
| 62 |
+
"grad_norm": 124194.484375,
|
| 63 |
+
"learning_rate": 0.00017714285714285713,
|
| 64 |
+
"loss": 1.4203,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.51,
|
| 69 |
+
"grad_norm": 187150.671875,
|
| 70 |
+
"learning_rate": 0.0001742857142857143,
|
| 71 |
+
"loss": 1.2605,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.57,
|
| 76 |
+
"grad_norm": 151804.65625,
|
| 77 |
+
"learning_rate": 0.00017142857142857143,
|
| 78 |
+
"loss": 1.2422,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.57,
|
| 83 |
+
"eval_accuracy": 0.7314285714285714,
|
| 84 |
+
"eval_loss": 1.1657222509384155,
|
| 85 |
+
"eval_runtime": 15.2094,
|
| 86 |
+
"eval_samples_per_second": 46.024,
|
| 87 |
+
"eval_steps_per_second": 2.893,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.63,
|
| 92 |
+
"grad_norm": 134052.609375,
|
| 93 |
+
"learning_rate": 0.00016857142857142857,
|
| 94 |
+
"loss": 1.1438,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.69,
|
| 99 |
+
"grad_norm": 163657.515625,
|
| 100 |
+
"learning_rate": 0.00016571428571428575,
|
| 101 |
+
"loss": 1.2158,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.74,
|
| 106 |
+
"grad_norm": 159906.9375,
|
| 107 |
+
"learning_rate": 0.00016285714285714287,
|
| 108 |
+
"loss": 1.0575,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.8,
|
| 113 |
+
"grad_norm": 171710.640625,
|
| 114 |
+
"learning_rate": 0.00016,
|
| 115 |
+
"loss": 1.0049,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.86,
|
| 120 |
+
"grad_norm": 171094.046875,
|
| 121 |
+
"learning_rate": 0.00015714285714285716,
|
| 122 |
+
"loss": 1.0786,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.91,
|
| 127 |
+
"grad_norm": 140285.921875,
|
| 128 |
+
"learning_rate": 0.0001542857142857143,
|
| 129 |
+
"loss": 0.9912,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.97,
|
| 134 |
+
"grad_norm": 170517.640625,
|
| 135 |
+
"learning_rate": 0.00015142857142857143,
|
| 136 |
+
"loss": 0.9448,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.03,
|
| 141 |
+
"grad_norm": 125416.1484375,
|
| 142 |
+
"learning_rate": 0.00014857142857142857,
|
| 143 |
+
"loss": 0.826,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.09,
|
| 148 |
+
"grad_norm": 205800.3125,
|
| 149 |
+
"learning_rate": 0.00014571428571428572,
|
| 150 |
+
"loss": 0.7471,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.14,
|
| 155 |
+
"grad_norm": 74866.34375,
|
| 156 |
+
"learning_rate": 0.00014285714285714287,
|
| 157 |
+
"loss": 0.5948,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.14,
|
| 162 |
+
"eval_accuracy": 0.8,
|
| 163 |
+
"eval_loss": 0.7744152545928955,
|
| 164 |
+
"eval_runtime": 11.8882,
|
| 165 |
+
"eval_samples_per_second": 58.882,
|
| 166 |
+
"eval_steps_per_second": 3.701,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.2,
|
| 171 |
+
"grad_norm": 191153.328125,
|
| 172 |
+
"learning_rate": 0.00014,
|
| 173 |
+
"loss": 0.5425,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.26,
|
| 178 |
+
"grad_norm": 181985.578125,
|
| 179 |
+
"learning_rate": 0.00013714285714285716,
|
| 180 |
+
"loss": 0.6606,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.31,
|
| 185 |
+
"grad_norm": 193704.78125,
|
| 186 |
+
"learning_rate": 0.00013428571428571428,
|
| 187 |
+
"loss": 0.5681,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.37,
|
| 192 |
+
"grad_norm": 135817.890625,
|
| 193 |
+
"learning_rate": 0.00013142857142857143,
|
| 194 |
+
"loss": 0.5497,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.43,
|
| 199 |
+
"grad_norm": 154213.90625,
|
| 200 |
+
"learning_rate": 0.00012857142857142858,
|
| 201 |
+
"loss": 0.562,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.49,
|
| 206 |
+
"grad_norm": 132152.8125,
|
| 207 |
+
"learning_rate": 0.00012571428571428572,
|
| 208 |
+
"loss": 0.5728,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.54,
|
| 213 |
+
"grad_norm": 207587.0625,
|
| 214 |
+
"learning_rate": 0.00012285714285714287,
|
| 215 |
+
"loss": 0.6254,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.6,
|
| 220 |
+
"grad_norm": 98314.2109375,
|
| 221 |
+
"learning_rate": 0.00012,
|
| 222 |
+
"loss": 0.4033,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.66,
|
| 227 |
+
"grad_norm": 107417.6328125,
|
| 228 |
+
"learning_rate": 0.00011714285714285715,
|
| 229 |
+
"loss": 0.4892,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.71,
|
| 234 |
+
"grad_norm": 250248.421875,
|
| 235 |
+
"learning_rate": 0.00011428571428571428,
|
| 236 |
+
"loss": 0.5324,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.71,
|
| 241 |
+
"eval_accuracy": 0.8128571428571428,
|
| 242 |
+
"eval_loss": 0.6736084818840027,
|
| 243 |
+
"eval_runtime": 13.3903,
|
| 244 |
+
"eval_samples_per_second": 52.277,
|
| 245 |
+
"eval_steps_per_second": 3.286,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.77,
|
| 250 |
+
"grad_norm": 165674.15625,
|
| 251 |
+
"learning_rate": 0.00011142857142857144,
|
| 252 |
+
"loss": 0.4641,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.83,
|
| 257 |
+
"grad_norm": 194581.40625,
|
| 258 |
+
"learning_rate": 0.00010857142857142856,
|
| 259 |
+
"loss": 0.4818,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.89,
|
| 264 |
+
"grad_norm": 138774.1875,
|
| 265 |
+
"learning_rate": 0.00010571428571428572,
|
| 266 |
+
"loss": 0.4677,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.94,
|
| 271 |
+
"grad_norm": 203262.421875,
|
| 272 |
+
"learning_rate": 0.00010285714285714286,
|
| 273 |
+
"loss": 0.4034,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.0,
|
| 278 |
+
"grad_norm": 128663.1875,
|
| 279 |
+
"learning_rate": 0.0001,
|
| 280 |
+
"loss": 0.3978,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.06,
|
| 285 |
+
"grad_norm": 35406.80078125,
|
| 286 |
+
"learning_rate": 9.714285714285715e-05,
|
| 287 |
+
"loss": 0.2415,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.11,
|
| 292 |
+
"grad_norm": 128107.3046875,
|
| 293 |
+
"learning_rate": 9.428571428571429e-05,
|
| 294 |
+
"loss": 0.2798,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.17,
|
| 299 |
+
"grad_norm": 52566.515625,
|
| 300 |
+
"learning_rate": 9.142857142857143e-05,
|
| 301 |
+
"loss": 0.2742,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.23,
|
| 306 |
+
"grad_norm": 49925.12890625,
|
| 307 |
+
"learning_rate": 8.857142857142857e-05,
|
| 308 |
+
"loss": 0.2293,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.29,
|
| 313 |
+
"grad_norm": 175336.984375,
|
| 314 |
+
"learning_rate": 8.571428571428571e-05,
|
| 315 |
+
"loss": 0.212,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.29,
|
| 320 |
+
"eval_accuracy": 0.8085714285714286,
|
| 321 |
+
"eval_loss": 0.7056272625923157,
|
| 322 |
+
"eval_runtime": 11.5847,
|
| 323 |
+
"eval_samples_per_second": 60.424,
|
| 324 |
+
"eval_steps_per_second": 3.798,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.34,
|
| 329 |
+
"grad_norm": 24206.984375,
|
| 330 |
+
"learning_rate": 8.285714285714287e-05,
|
| 331 |
+
"loss": 0.2311,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.4,
|
| 336 |
+
"grad_norm": 124311.4140625,
|
| 337 |
+
"learning_rate": 8e-05,
|
| 338 |
+
"loss": 0.2342,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.46,
|
| 343 |
+
"grad_norm": 68467.265625,
|
| 344 |
+
"learning_rate": 7.714285714285715e-05,
|
| 345 |
+
"loss": 0.2055,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.51,
|
| 350 |
+
"grad_norm": 104893.53125,
|
| 351 |
+
"learning_rate": 7.428571428571429e-05,
|
| 352 |
+
"loss": 0.1814,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.57,
|
| 357 |
+
"grad_norm": 76138.921875,
|
| 358 |
+
"learning_rate": 7.142857142857143e-05,
|
| 359 |
+
"loss": 0.2127,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.63,
|
| 364 |
+
"grad_norm": 138337.28125,
|
| 365 |
+
"learning_rate": 6.857142857142858e-05,
|
| 366 |
+
"loss": 0.1863,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.69,
|
| 371 |
+
"grad_norm": 47311.3203125,
|
| 372 |
+
"learning_rate": 6.571428571428571e-05,
|
| 373 |
+
"loss": 0.2281,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.74,
|
| 378 |
+
"grad_norm": 107393.203125,
|
| 379 |
+
"learning_rate": 6.285714285714286e-05,
|
| 380 |
+
"loss": 0.1875,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.8,
|
| 385 |
+
"grad_norm": 167001.0,
|
| 386 |
+
"learning_rate": 6e-05,
|
| 387 |
+
"loss": 0.1896,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.86,
|
| 392 |
+
"grad_norm": 90490.375,
|
| 393 |
+
"learning_rate": 5.714285714285714e-05,
|
| 394 |
+
"loss": 0.2158,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.86,
|
| 399 |
+
"eval_accuracy": 0.82,
|
| 400 |
+
"eval_loss": 0.605766236782074,
|
| 401 |
+
"eval_runtime": 11.55,
|
| 402 |
+
"eval_samples_per_second": 60.606,
|
| 403 |
+
"eval_steps_per_second": 3.81,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.91,
|
| 408 |
+
"grad_norm": 77742.671875,
|
| 409 |
+
"learning_rate": 5.428571428571428e-05,
|
| 410 |
+
"loss": 0.1612,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.97,
|
| 415 |
+
"grad_norm": 63372.32421875,
|
| 416 |
+
"learning_rate": 5.142857142857143e-05,
|
| 417 |
+
"loss": 0.187,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 3.03,
|
| 422 |
+
"grad_norm": 45292.62890625,
|
| 423 |
+
"learning_rate": 4.8571428571428576e-05,
|
| 424 |
+
"loss": 0.1405,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.09,
|
| 429 |
+
"grad_norm": 26526.5625,
|
| 430 |
+
"learning_rate": 4.5714285714285716e-05,
|
| 431 |
+
"loss": 0.0887,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.14,
|
| 436 |
+
"grad_norm": 41573.1015625,
|
| 437 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 438 |
+
"loss": 0.1021,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.2,
|
| 443 |
+
"grad_norm": 139364.9375,
|
| 444 |
+
"learning_rate": 4e-05,
|
| 445 |
+
"loss": 0.1197,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.26,
|
| 450 |
+
"grad_norm": 30005.94140625,
|
| 451 |
+
"learning_rate": 3.7142857142857143e-05,
|
| 452 |
+
"loss": 0.1053,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.31,
|
| 457 |
+
"grad_norm": 20724.45703125,
|
| 458 |
+
"learning_rate": 3.428571428571429e-05,
|
| 459 |
+
"loss": 0.0893,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.37,
|
| 464 |
+
"grad_norm": 34746.91796875,
|
| 465 |
+
"learning_rate": 3.142857142857143e-05,
|
| 466 |
+
"loss": 0.0616,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.43,
|
| 471 |
+
"grad_norm": 6497.982421875,
|
| 472 |
+
"learning_rate": 2.857142857142857e-05,
|
| 473 |
+
"loss": 0.0899,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.43,
|
| 478 |
+
"eval_accuracy": 0.8285714285714286,
|
| 479 |
+
"eval_loss": 0.6227328181266785,
|
| 480 |
+
"eval_runtime": 11.9351,
|
| 481 |
+
"eval_samples_per_second": 58.651,
|
| 482 |
+
"eval_steps_per_second": 3.687,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.49,
|
| 487 |
+
"grad_norm": 116260.6796875,
|
| 488 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 489 |
+
"loss": 0.0703,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 3.54,
|
| 494 |
+
"grad_norm": 21543.369140625,
|
| 495 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 496 |
+
"loss": 0.0606,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 3.6,
|
| 501 |
+
"grad_norm": 52411.12890625,
|
| 502 |
+
"learning_rate": 2e-05,
|
| 503 |
+
"loss": 0.0525,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.66,
|
| 508 |
+
"grad_norm": 19344.330078125,
|
| 509 |
+
"learning_rate": 1.7142857142857145e-05,
|
| 510 |
+
"loss": 0.0689,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 3.71,
|
| 515 |
+
"grad_norm": 5230.615234375,
|
| 516 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 517 |
+
"loss": 0.0741,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.77,
|
| 522 |
+
"grad_norm": 45295.99609375,
|
| 523 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 524 |
+
"loss": 0.0812,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.83,
|
| 529 |
+
"grad_norm": 8915.515625,
|
| 530 |
+
"learning_rate": 8.571428571428573e-06,
|
| 531 |
+
"loss": 0.0601,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.89,
|
| 536 |
+
"grad_norm": 98771.65625,
|
| 537 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 538 |
+
"loss": 0.0719,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.94,
|
| 543 |
+
"grad_norm": 52097.53125,
|
| 544 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 545 |
+
"loss": 0.0715,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 4.0,
|
| 550 |
+
"grad_norm": 24277.24609375,
|
| 551 |
+
"learning_rate": 0.0,
|
| 552 |
+
"loss": 0.0609,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 4.0,
|
| 557 |
+
"eval_accuracy": 0.8357142857142857,
|
| 558 |
+
"eval_loss": 0.6181082725524902,
|
| 559 |
+
"eval_runtime": 10.9983,
|
| 560 |
+
"eval_samples_per_second": 63.646,
|
| 561 |
+
"eval_steps_per_second": 4.001,
|
| 562 |
+
"step": 700
|
| 563 |
+
}
|
| 564 |
+
],
|
| 565 |
+
"logging_steps": 10,
|
| 566 |
+
"max_steps": 700,
|
| 567 |
+
"num_input_tokens_seen": 0,
|
| 568 |
+
"num_train_epochs": 4,
|
| 569 |
+
"save_steps": 100,
|
| 570 |
+
"total_flos": 1.7361006043594752e+18,
|
| 571 |
+
"train_batch_size": 32,
|
| 572 |
+
"trial_name": null,
|
| 573 |
+
"trial_params": null
|
| 574 |
+
}
|
checkpoint-700/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b696add107e34028cff294268207622430a98082e509d660850e58e78a8a3080
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Abyssinian",
|
| 13 |
+
"1": "American Bobtail",
|
| 14 |
+
"10": "Maine Coon",
|
| 15 |
+
"11": "Manx",
|
| 16 |
+
"12": "Norwegian Forest",
|
| 17 |
+
"13": "Persian",
|
| 18 |
+
"14": "Ragdoll",
|
| 19 |
+
"15": "Russian Blue",
|
| 20 |
+
"16": "Scottish Fold",
|
| 21 |
+
"17": "Siamese",
|
| 22 |
+
"18": "Sphynx",
|
| 23 |
+
"19": "Turkish Angora",
|
| 24 |
+
"2": "American Curl",
|
| 25 |
+
"3": "American Shorthair",
|
| 26 |
+
"4": "Bengal",
|
| 27 |
+
"5": "Birman",
|
| 28 |
+
"6": "Bombay",
|
| 29 |
+
"7": "British Shorthair",
|
| 30 |
+
"8": "Egyptian Mau",
|
| 31 |
+
"9": "Exotic Shorthair"
|
| 32 |
+
},
|
| 33 |
+
"image_size": 224,
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"Abyssinian": "0",
|
| 38 |
+
"American Bobtail": "1",
|
| 39 |
+
"American Curl": "2",
|
| 40 |
+
"American Shorthair": "3",
|
| 41 |
+
"Bengal": "4",
|
| 42 |
+
"Birman": "5",
|
| 43 |
+
"Bombay": "6",
|
| 44 |
+
"British Shorthair": "7",
|
| 45 |
+
"Egyptian Mau": "8",
|
| 46 |
+
"Exotic Shorthair": "9",
|
| 47 |
+
"Maine Coon": "10",
|
| 48 |
+
"Manx": "11",
|
| 49 |
+
"Norwegian Forest": "12",
|
| 50 |
+
"Persian": "13",
|
| 51 |
+
"Ragdoll": "14",
|
| 52 |
+
"Russian Blue": "15",
|
| 53 |
+
"Scottish Fold": "16",
|
| 54 |
+
"Siamese": "17",
|
| 55 |
+
"Sphynx": "18",
|
| 56 |
+
"Turkish Angora": "19"
|
| 57 |
+
},
|
| 58 |
+
"layer_norm_eps": 1e-12,
|
| 59 |
+
"model_type": "vit",
|
| 60 |
+
"num_attention_heads": 12,
|
| 61 |
+
"num_channels": 3,
|
| 62 |
+
"num_hidden_layers": 12,
|
| 63 |
+
"patch_size": 16,
|
| 64 |
+
"problem_type": "single_label_classification",
|
| 65 |
+
"qkv_bias": true,
|
| 66 |
+
"torch_dtype": "float32",
|
| 67 |
+
"transformers_version": "4.39.3"
|
| 68 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.82,
|
| 4 |
+
"eval_loss": 0.605766236782074,
|
| 5 |
+
"eval_runtime": 11.6705,
|
| 6 |
+
"eval_samples_per_second": 59.98,
|
| 7 |
+
"eval_steps_per_second": 3.77
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d651549752e81380e748886a7c451f5ddbaa555ca68212a2c6610eef1ce49e05
|
| 3 |
+
size 343279344
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTImageProcessor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
runs/May11_09-58-51_7647228388c7/events.out.tfevents.1715421532.7647228388c7.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5523c49af986634f529e3610f3cf5c6b17fd1691f0332f748361870c60652894
|
| 3 |
+
size 5478
|
runs/May11_09-59-08_7647228388c7/events.out.tfevents.1715421548.7647228388c7.34.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89d3cc529b40072a0c23ded5fc76c541d9b21b7880b92e88fdbc3d771fc7e7b6
|
| 3 |
+
size 22809
|
runs/May11_09-59-08_7647228388c7/events.out.tfevents.1715422708.7647228388c7.34.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1b7ceef0a6055b7636955f69a6ea34f00c3c00ce67f597b4d828ec83aded65b
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.7361006043594752e+18,
|
| 4 |
+
"train_loss": 0.5924043039764677,
|
| 5 |
+
"train_runtime": 756.4917,
|
| 6 |
+
"train_samples_per_second": 29.61,
|
| 7 |
+
"train_steps_per_second": 0.925
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,583 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.605766236782074,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-cats/checkpoint-500",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 700,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"grad_norm": 104665.1796875,
|
| 14 |
+
"learning_rate": 0.00019714285714285716,
|
| 15 |
+
"loss": 2.8888,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11,
|
| 20 |
+
"grad_norm": 102043.53125,
|
| 21 |
+
"learning_rate": 0.0001942857142857143,
|
| 22 |
+
"loss": 2.6146,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.17,
|
| 27 |
+
"grad_norm": 97863.03125,
|
| 28 |
+
"learning_rate": 0.00019142857142857145,
|
| 29 |
+
"loss": 2.3775,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.23,
|
| 34 |
+
"grad_norm": 98961.4453125,
|
| 35 |
+
"learning_rate": 0.00018857142857142857,
|
| 36 |
+
"loss": 2.0395,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.29,
|
| 41 |
+
"grad_norm": 142313.515625,
|
| 42 |
+
"learning_rate": 0.00018571428571428572,
|
| 43 |
+
"loss": 1.8599,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.34,
|
| 48 |
+
"grad_norm": 112630.1328125,
|
| 49 |
+
"learning_rate": 0.00018285714285714286,
|
| 50 |
+
"loss": 1.7573,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4,
|
| 55 |
+
"grad_norm": 180249.9375,
|
| 56 |
+
"learning_rate": 0.00018,
|
| 57 |
+
"loss": 1.5562,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.46,
|
| 62 |
+
"grad_norm": 124194.484375,
|
| 63 |
+
"learning_rate": 0.00017714285714285713,
|
| 64 |
+
"loss": 1.4203,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.51,
|
| 69 |
+
"grad_norm": 187150.671875,
|
| 70 |
+
"learning_rate": 0.0001742857142857143,
|
| 71 |
+
"loss": 1.2605,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.57,
|
| 76 |
+
"grad_norm": 151804.65625,
|
| 77 |
+
"learning_rate": 0.00017142857142857143,
|
| 78 |
+
"loss": 1.2422,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.57,
|
| 83 |
+
"eval_accuracy": 0.7314285714285714,
|
| 84 |
+
"eval_loss": 1.1657222509384155,
|
| 85 |
+
"eval_runtime": 15.2094,
|
| 86 |
+
"eval_samples_per_second": 46.024,
|
| 87 |
+
"eval_steps_per_second": 2.893,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.63,
|
| 92 |
+
"grad_norm": 134052.609375,
|
| 93 |
+
"learning_rate": 0.00016857142857142857,
|
| 94 |
+
"loss": 1.1438,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.69,
|
| 99 |
+
"grad_norm": 163657.515625,
|
| 100 |
+
"learning_rate": 0.00016571428571428575,
|
| 101 |
+
"loss": 1.2158,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.74,
|
| 106 |
+
"grad_norm": 159906.9375,
|
| 107 |
+
"learning_rate": 0.00016285714285714287,
|
| 108 |
+
"loss": 1.0575,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.8,
|
| 113 |
+
"grad_norm": 171710.640625,
|
| 114 |
+
"learning_rate": 0.00016,
|
| 115 |
+
"loss": 1.0049,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.86,
|
| 120 |
+
"grad_norm": 171094.046875,
|
| 121 |
+
"learning_rate": 0.00015714285714285716,
|
| 122 |
+
"loss": 1.0786,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.91,
|
| 127 |
+
"grad_norm": 140285.921875,
|
| 128 |
+
"learning_rate": 0.0001542857142857143,
|
| 129 |
+
"loss": 0.9912,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.97,
|
| 134 |
+
"grad_norm": 170517.640625,
|
| 135 |
+
"learning_rate": 0.00015142857142857143,
|
| 136 |
+
"loss": 0.9448,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.03,
|
| 141 |
+
"grad_norm": 125416.1484375,
|
| 142 |
+
"learning_rate": 0.00014857142857142857,
|
| 143 |
+
"loss": 0.826,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.09,
|
| 148 |
+
"grad_norm": 205800.3125,
|
| 149 |
+
"learning_rate": 0.00014571428571428572,
|
| 150 |
+
"loss": 0.7471,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.14,
|
| 155 |
+
"grad_norm": 74866.34375,
|
| 156 |
+
"learning_rate": 0.00014285714285714287,
|
| 157 |
+
"loss": 0.5948,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.14,
|
| 162 |
+
"eval_accuracy": 0.8,
|
| 163 |
+
"eval_loss": 0.7744152545928955,
|
| 164 |
+
"eval_runtime": 11.8882,
|
| 165 |
+
"eval_samples_per_second": 58.882,
|
| 166 |
+
"eval_steps_per_second": 3.701,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.2,
|
| 171 |
+
"grad_norm": 191153.328125,
|
| 172 |
+
"learning_rate": 0.00014,
|
| 173 |
+
"loss": 0.5425,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.26,
|
| 178 |
+
"grad_norm": 181985.578125,
|
| 179 |
+
"learning_rate": 0.00013714285714285716,
|
| 180 |
+
"loss": 0.6606,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.31,
|
| 185 |
+
"grad_norm": 193704.78125,
|
| 186 |
+
"learning_rate": 0.00013428571428571428,
|
| 187 |
+
"loss": 0.5681,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.37,
|
| 192 |
+
"grad_norm": 135817.890625,
|
| 193 |
+
"learning_rate": 0.00013142857142857143,
|
| 194 |
+
"loss": 0.5497,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.43,
|
| 199 |
+
"grad_norm": 154213.90625,
|
| 200 |
+
"learning_rate": 0.00012857142857142858,
|
| 201 |
+
"loss": 0.562,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.49,
|
| 206 |
+
"grad_norm": 132152.8125,
|
| 207 |
+
"learning_rate": 0.00012571428571428572,
|
| 208 |
+
"loss": 0.5728,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.54,
|
| 213 |
+
"grad_norm": 207587.0625,
|
| 214 |
+
"learning_rate": 0.00012285714285714287,
|
| 215 |
+
"loss": 0.6254,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.6,
|
| 220 |
+
"grad_norm": 98314.2109375,
|
| 221 |
+
"learning_rate": 0.00012,
|
| 222 |
+
"loss": 0.4033,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.66,
|
| 227 |
+
"grad_norm": 107417.6328125,
|
| 228 |
+
"learning_rate": 0.00011714285714285715,
|
| 229 |
+
"loss": 0.4892,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.71,
|
| 234 |
+
"grad_norm": 250248.421875,
|
| 235 |
+
"learning_rate": 0.00011428571428571428,
|
| 236 |
+
"loss": 0.5324,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.71,
|
| 241 |
+
"eval_accuracy": 0.8128571428571428,
|
| 242 |
+
"eval_loss": 0.6736084818840027,
|
| 243 |
+
"eval_runtime": 13.3903,
|
| 244 |
+
"eval_samples_per_second": 52.277,
|
| 245 |
+
"eval_steps_per_second": 3.286,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.77,
|
| 250 |
+
"grad_norm": 165674.15625,
|
| 251 |
+
"learning_rate": 0.00011142857142857144,
|
| 252 |
+
"loss": 0.4641,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.83,
|
| 257 |
+
"grad_norm": 194581.40625,
|
| 258 |
+
"learning_rate": 0.00010857142857142856,
|
| 259 |
+
"loss": 0.4818,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.89,
|
| 264 |
+
"grad_norm": 138774.1875,
|
| 265 |
+
"learning_rate": 0.00010571428571428572,
|
| 266 |
+
"loss": 0.4677,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.94,
|
| 271 |
+
"grad_norm": 203262.421875,
|
| 272 |
+
"learning_rate": 0.00010285714285714286,
|
| 273 |
+
"loss": 0.4034,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.0,
|
| 278 |
+
"grad_norm": 128663.1875,
|
| 279 |
+
"learning_rate": 0.0001,
|
| 280 |
+
"loss": 0.3978,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.06,
|
| 285 |
+
"grad_norm": 35406.80078125,
|
| 286 |
+
"learning_rate": 9.714285714285715e-05,
|
| 287 |
+
"loss": 0.2415,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.11,
|
| 292 |
+
"grad_norm": 128107.3046875,
|
| 293 |
+
"learning_rate": 9.428571428571429e-05,
|
| 294 |
+
"loss": 0.2798,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.17,
|
| 299 |
+
"grad_norm": 52566.515625,
|
| 300 |
+
"learning_rate": 9.142857142857143e-05,
|
| 301 |
+
"loss": 0.2742,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.23,
|
| 306 |
+
"grad_norm": 49925.12890625,
|
| 307 |
+
"learning_rate": 8.857142857142857e-05,
|
| 308 |
+
"loss": 0.2293,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.29,
|
| 313 |
+
"grad_norm": 175336.984375,
|
| 314 |
+
"learning_rate": 8.571428571428571e-05,
|
| 315 |
+
"loss": 0.212,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.29,
|
| 320 |
+
"eval_accuracy": 0.8085714285714286,
|
| 321 |
+
"eval_loss": 0.7056272625923157,
|
| 322 |
+
"eval_runtime": 11.5847,
|
| 323 |
+
"eval_samples_per_second": 60.424,
|
| 324 |
+
"eval_steps_per_second": 3.798,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.34,
|
| 329 |
+
"grad_norm": 24206.984375,
|
| 330 |
+
"learning_rate": 8.285714285714287e-05,
|
| 331 |
+
"loss": 0.2311,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.4,
|
| 336 |
+
"grad_norm": 124311.4140625,
|
| 337 |
+
"learning_rate": 8e-05,
|
| 338 |
+
"loss": 0.2342,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.46,
|
| 343 |
+
"grad_norm": 68467.265625,
|
| 344 |
+
"learning_rate": 7.714285714285715e-05,
|
| 345 |
+
"loss": 0.2055,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.51,
|
| 350 |
+
"grad_norm": 104893.53125,
|
| 351 |
+
"learning_rate": 7.428571428571429e-05,
|
| 352 |
+
"loss": 0.1814,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.57,
|
| 357 |
+
"grad_norm": 76138.921875,
|
| 358 |
+
"learning_rate": 7.142857142857143e-05,
|
| 359 |
+
"loss": 0.2127,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.63,
|
| 364 |
+
"grad_norm": 138337.28125,
|
| 365 |
+
"learning_rate": 6.857142857142858e-05,
|
| 366 |
+
"loss": 0.1863,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.69,
|
| 371 |
+
"grad_norm": 47311.3203125,
|
| 372 |
+
"learning_rate": 6.571428571428571e-05,
|
| 373 |
+
"loss": 0.2281,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.74,
|
| 378 |
+
"grad_norm": 107393.203125,
|
| 379 |
+
"learning_rate": 6.285714285714286e-05,
|
| 380 |
+
"loss": 0.1875,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.8,
|
| 385 |
+
"grad_norm": 167001.0,
|
| 386 |
+
"learning_rate": 6e-05,
|
| 387 |
+
"loss": 0.1896,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.86,
|
| 392 |
+
"grad_norm": 90490.375,
|
| 393 |
+
"learning_rate": 5.714285714285714e-05,
|
| 394 |
+
"loss": 0.2158,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.86,
|
| 399 |
+
"eval_accuracy": 0.82,
|
| 400 |
+
"eval_loss": 0.605766236782074,
|
| 401 |
+
"eval_runtime": 11.55,
|
| 402 |
+
"eval_samples_per_second": 60.606,
|
| 403 |
+
"eval_steps_per_second": 3.81,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.91,
|
| 408 |
+
"grad_norm": 77742.671875,
|
| 409 |
+
"learning_rate": 5.428571428571428e-05,
|
| 410 |
+
"loss": 0.1612,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.97,
|
| 415 |
+
"grad_norm": 63372.32421875,
|
| 416 |
+
"learning_rate": 5.142857142857143e-05,
|
| 417 |
+
"loss": 0.187,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 3.03,
|
| 422 |
+
"grad_norm": 45292.62890625,
|
| 423 |
+
"learning_rate": 4.8571428571428576e-05,
|
| 424 |
+
"loss": 0.1405,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.09,
|
| 429 |
+
"grad_norm": 26526.5625,
|
| 430 |
+
"learning_rate": 4.5714285714285716e-05,
|
| 431 |
+
"loss": 0.0887,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.14,
|
| 436 |
+
"grad_norm": 41573.1015625,
|
| 437 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 438 |
+
"loss": 0.1021,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.2,
|
| 443 |
+
"grad_norm": 139364.9375,
|
| 444 |
+
"learning_rate": 4e-05,
|
| 445 |
+
"loss": 0.1197,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.26,
|
| 450 |
+
"grad_norm": 30005.94140625,
|
| 451 |
+
"learning_rate": 3.7142857142857143e-05,
|
| 452 |
+
"loss": 0.1053,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.31,
|
| 457 |
+
"grad_norm": 20724.45703125,
|
| 458 |
+
"learning_rate": 3.428571428571429e-05,
|
| 459 |
+
"loss": 0.0893,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.37,
|
| 464 |
+
"grad_norm": 34746.91796875,
|
| 465 |
+
"learning_rate": 3.142857142857143e-05,
|
| 466 |
+
"loss": 0.0616,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.43,
|
| 471 |
+
"grad_norm": 6497.982421875,
|
| 472 |
+
"learning_rate": 2.857142857142857e-05,
|
| 473 |
+
"loss": 0.0899,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.43,
|
| 478 |
+
"eval_accuracy": 0.8285714285714286,
|
| 479 |
+
"eval_loss": 0.6227328181266785,
|
| 480 |
+
"eval_runtime": 11.9351,
|
| 481 |
+
"eval_samples_per_second": 58.651,
|
| 482 |
+
"eval_steps_per_second": 3.687,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.49,
|
| 487 |
+
"grad_norm": 116260.6796875,
|
| 488 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 489 |
+
"loss": 0.0703,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 3.54,
|
| 494 |
+
"grad_norm": 21543.369140625,
|
| 495 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 496 |
+
"loss": 0.0606,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 3.6,
|
| 501 |
+
"grad_norm": 52411.12890625,
|
| 502 |
+
"learning_rate": 2e-05,
|
| 503 |
+
"loss": 0.0525,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.66,
|
| 508 |
+
"grad_norm": 19344.330078125,
|
| 509 |
+
"learning_rate": 1.7142857142857145e-05,
|
| 510 |
+
"loss": 0.0689,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 3.71,
|
| 515 |
+
"grad_norm": 5230.615234375,
|
| 516 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 517 |
+
"loss": 0.0741,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.77,
|
| 522 |
+
"grad_norm": 45295.99609375,
|
| 523 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 524 |
+
"loss": 0.0812,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.83,
|
| 529 |
+
"grad_norm": 8915.515625,
|
| 530 |
+
"learning_rate": 8.571428571428573e-06,
|
| 531 |
+
"loss": 0.0601,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.89,
|
| 536 |
+
"grad_norm": 98771.65625,
|
| 537 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 538 |
+
"loss": 0.0719,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.94,
|
| 543 |
+
"grad_norm": 52097.53125,
|
| 544 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 545 |
+
"loss": 0.0715,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 4.0,
|
| 550 |
+
"grad_norm": 24277.24609375,
|
| 551 |
+
"learning_rate": 0.0,
|
| 552 |
+
"loss": 0.0609,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 4.0,
|
| 557 |
+
"eval_accuracy": 0.8357142857142857,
|
| 558 |
+
"eval_loss": 0.6181082725524902,
|
| 559 |
+
"eval_runtime": 10.9983,
|
| 560 |
+
"eval_samples_per_second": 63.646,
|
| 561 |
+
"eval_steps_per_second": 4.001,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 4.0,
|
| 566 |
+
"step": 700,
|
| 567 |
+
"total_flos": 1.7361006043594752e+18,
|
| 568 |
+
"train_loss": 0.5924043039764677,
|
| 569 |
+
"train_runtime": 756.4917,
|
| 570 |
+
"train_samples_per_second": 29.61,
|
| 571 |
+
"train_steps_per_second": 0.925
|
| 572 |
+
}
|
| 573 |
+
],
|
| 574 |
+
"logging_steps": 10,
|
| 575 |
+
"max_steps": 700,
|
| 576 |
+
"num_input_tokens_seen": 0,
|
| 577 |
+
"num_train_epochs": 4,
|
| 578 |
+
"save_steps": 100,
|
| 579 |
+
"total_flos": 1.7361006043594752e+18,
|
| 580 |
+
"train_batch_size": 32,
|
| 581 |
+
"trial_name": null,
|
| 582 |
+
"trial_params": null
|
| 583 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b696add107e34028cff294268207622430a98082e509d660850e58e78a8a3080
|
| 3 |
+
size 4920
|