Upload folder using huggingface_hub
Browse files- 10epoc-lr1e-4/config.json +46 -0
- 10epoc-lr1e-4/optimizer.pt +3 -0
- 10epoc-lr1e-4/preprocessor_config.json +22 -0
- 10epoc-lr1e-4/pytorch_model.bin +3 -0
- 10epoc-lr1e-4/rng_state.pth +3 -0
- 10epoc-lr1e-4/scheduler.pt +3 -0
- 10epoc-lr1e-4/trainer_state.json +556 -0
- 10epoc-lr1e-4/training_args.bin +3 -0
10epoc-lr1e-4/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-large-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": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "actinic keratosis",
|
| 13 |
+
"1": "basal cell carcinoma",
|
| 14 |
+
"2": "dermatofibroma",
|
| 15 |
+
"3": "melanoma",
|
| 16 |
+
"4": "nevus",
|
| 17 |
+
"5": "pigmented benign keratosis",
|
| 18 |
+
"6": "seborrheic keratosis",
|
| 19 |
+
"7": "squamous cell carcinoma",
|
| 20 |
+
"8": "vascular lesion"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 4096,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"actinic keratosis": "0",
|
| 27 |
+
"basal cell carcinoma": "1",
|
| 28 |
+
"dermatofibroma": "2",
|
| 29 |
+
"melanoma": "3",
|
| 30 |
+
"nevus": "4",
|
| 31 |
+
"pigmented benign keratosis": "5",
|
| 32 |
+
"seborrheic keratosis": "6",
|
| 33 |
+
"squamous cell carcinoma": "7",
|
| 34 |
+
"vascular lesion": "8"
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"model_type": "vit",
|
| 38 |
+
"num_attention_heads": 16,
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"num_hidden_layers": 24,
|
| 41 |
+
"patch_size": 16,
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"qkv_bias": true,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.31.0"
|
| 46 |
+
}
|
10epoc-lr1e-4/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:923f38157864924cfe54896b42a774d4935a66626f922fa11c9c5b1081c40684
|
| 3 |
+
size 2426717125
|
10epoc-lr1e-4/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": "ViTFeatureExtractor",
|
| 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 |
+
}
|
10epoc-lr1e-4/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cec76b3342e4a40e43e9b63008c45b4a253e02160c1afe1c2b439241ded45567
|
| 3 |
+
size 1213377325
|
10epoc-lr1e-4/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e46ce4eb16240da9f3a8b3066acb6f59a234249ee2a3052f3323786da479838
|
| 3 |
+
size 14575
|
10epoc-lr1e-4/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99a0129e07fb06495563e0dd6cfade49996c64a0be76589bab3288c965d9ad77
|
| 3 |
+
size 627
|
10epoc-lr1e-4/trainer_state.json
ADDED
|
@@ -0,0 +1,556 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7834821428571429,
|
| 3 |
+
"best_model_checkpoint": "/content/10epcoh1/checkpoint-600",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 750,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 13 |
+
"loss": 2.1275,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.27,
|
| 18 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 19 |
+
"loss": 1.8422,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.4,
|
| 24 |
+
"learning_rate": 4e-05,
|
| 25 |
+
"loss": 1.5182,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.53,
|
| 30 |
+
"learning_rate": 5.333333333333333e-05,
|
| 31 |
+
"loss": 1.2899,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.67,
|
| 36 |
+
"learning_rate": 6.666666666666667e-05,
|
| 37 |
+
"loss": 1.1166,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.8,
|
| 42 |
+
"learning_rate": 8e-05,
|
| 43 |
+
"loss": 0.9772,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.93,
|
| 48 |
+
"learning_rate": 9.333333333333334e-05,
|
| 49 |
+
"loss": 1.0362,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.0,
|
| 54 |
+
"eval_accuracy": 0.6339285714285714,
|
| 55 |
+
"eval_loss": 1.1306579113006592,
|
| 56 |
+
"eval_runtime": 15.6391,
|
| 57 |
+
"eval_samples_per_second": 28.646,
|
| 58 |
+
"eval_steps_per_second": 3.581,
|
| 59 |
+
"step": 75
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.07,
|
| 63 |
+
"learning_rate": 9.925925925925926e-05,
|
| 64 |
+
"loss": 1.1734,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.2,
|
| 69 |
+
"learning_rate": 9.777777777777778e-05,
|
| 70 |
+
"loss": 0.9443,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.33,
|
| 75 |
+
"learning_rate": 9.62962962962963e-05,
|
| 76 |
+
"loss": 0.8425,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.47,
|
| 81 |
+
"learning_rate": 9.481481481481483e-05,
|
| 82 |
+
"loss": 0.9121,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.6,
|
| 87 |
+
"learning_rate": 9.333333333333334e-05,
|
| 88 |
+
"loss": 0.7943,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.73,
|
| 93 |
+
"learning_rate": 9.185185185185186e-05,
|
| 94 |
+
"loss": 0.8326,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.87,
|
| 99 |
+
"learning_rate": 9.037037037037038e-05,
|
| 100 |
+
"loss": 0.8621,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.0,
|
| 105 |
+
"learning_rate": 8.888888888888889e-05,
|
| 106 |
+
"loss": 0.7188,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.0,
|
| 111 |
+
"eval_accuracy": 0.7366071428571429,
|
| 112 |
+
"eval_loss": 0.7066014409065247,
|
| 113 |
+
"eval_runtime": 15.9611,
|
| 114 |
+
"eval_samples_per_second": 28.068,
|
| 115 |
+
"eval_steps_per_second": 3.509,
|
| 116 |
+
"step": 150
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.13,
|
| 120 |
+
"learning_rate": 8.740740740740741e-05,
|
| 121 |
+
"loss": 0.4786,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.27,
|
| 126 |
+
"learning_rate": 8.592592592592593e-05,
|
| 127 |
+
"loss": 0.5607,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.4,
|
| 132 |
+
"learning_rate": 8.444444444444444e-05,
|
| 133 |
+
"loss": 0.5072,
|
| 134 |
+
"step": 180
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.53,
|
| 138 |
+
"learning_rate": 8.296296296296296e-05,
|
| 139 |
+
"loss": 0.5531,
|
| 140 |
+
"step": 190
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.67,
|
| 144 |
+
"learning_rate": 8.148148148148148e-05,
|
| 145 |
+
"loss": 0.4221,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.8,
|
| 150 |
+
"learning_rate": 8e-05,
|
| 151 |
+
"loss": 0.5585,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.93,
|
| 156 |
+
"learning_rate": 7.851851851851852e-05,
|
| 157 |
+
"loss": 0.6219,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.0,
|
| 162 |
+
"eval_accuracy": 0.7299107142857143,
|
| 163 |
+
"eval_loss": 0.7877911925315857,
|
| 164 |
+
"eval_runtime": 17.0375,
|
| 165 |
+
"eval_samples_per_second": 26.295,
|
| 166 |
+
"eval_steps_per_second": 3.287,
|
| 167 |
+
"step": 225
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.07,
|
| 171 |
+
"learning_rate": 7.703703703703704e-05,
|
| 172 |
+
"loss": 0.5331,
|
| 173 |
+
"step": 230
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.2,
|
| 177 |
+
"learning_rate": 7.555555555555556e-05,
|
| 178 |
+
"loss": 0.3028,
|
| 179 |
+
"step": 240
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.33,
|
| 183 |
+
"learning_rate": 7.407407407407407e-05,
|
| 184 |
+
"loss": 0.3088,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.47,
|
| 189 |
+
"learning_rate": 7.25925925925926e-05,
|
| 190 |
+
"loss": 0.3205,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.6,
|
| 195 |
+
"learning_rate": 7.111111111111112e-05,
|
| 196 |
+
"loss": 0.2972,
|
| 197 |
+
"step": 270
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.73,
|
| 201 |
+
"learning_rate": 6.962962962962964e-05,
|
| 202 |
+
"loss": 0.3062,
|
| 203 |
+
"step": 280
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.87,
|
| 207 |
+
"learning_rate": 6.814814814814815e-05,
|
| 208 |
+
"loss": 0.3865,
|
| 209 |
+
"step": 290
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.0,
|
| 213 |
+
"learning_rate": 6.666666666666667e-05,
|
| 214 |
+
"loss": 0.3372,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.0,
|
| 219 |
+
"eval_accuracy": 0.7767857142857143,
|
| 220 |
+
"eval_loss": 0.6498553156852722,
|
| 221 |
+
"eval_runtime": 15.0316,
|
| 222 |
+
"eval_samples_per_second": 29.804,
|
| 223 |
+
"eval_steps_per_second": 3.725,
|
| 224 |
+
"step": 300
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.13,
|
| 228 |
+
"learning_rate": 6.51851851851852e-05,
|
| 229 |
+
"loss": 0.1711,
|
| 230 |
+
"step": 310
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.27,
|
| 234 |
+
"learning_rate": 6.37037037037037e-05,
|
| 235 |
+
"loss": 0.2188,
|
| 236 |
+
"step": 320
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.4,
|
| 240 |
+
"learning_rate": 6.222222222222222e-05,
|
| 241 |
+
"loss": 0.3254,
|
| 242 |
+
"step": 330
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.53,
|
| 246 |
+
"learning_rate": 6.074074074074074e-05,
|
| 247 |
+
"loss": 0.2683,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.67,
|
| 252 |
+
"learning_rate": 5.925925925925926e-05,
|
| 253 |
+
"loss": 0.2208,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.8,
|
| 258 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 259 |
+
"loss": 0.1729,
|
| 260 |
+
"step": 360
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.93,
|
| 264 |
+
"learning_rate": 5.62962962962963e-05,
|
| 265 |
+
"loss": 0.2024,
|
| 266 |
+
"step": 370
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.0,
|
| 270 |
+
"eval_accuracy": 0.765625,
|
| 271 |
+
"eval_loss": 0.7129976153373718,
|
| 272 |
+
"eval_runtime": 15.0955,
|
| 273 |
+
"eval_samples_per_second": 29.678,
|
| 274 |
+
"eval_steps_per_second": 3.71,
|
| 275 |
+
"step": 375
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 5.07,
|
| 279 |
+
"learning_rate": 5.4814814814814817e-05,
|
| 280 |
+
"loss": 0.2077,
|
| 281 |
+
"step": 380
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 5.2,
|
| 285 |
+
"learning_rate": 5.333333333333333e-05,
|
| 286 |
+
"loss": 0.17,
|
| 287 |
+
"step": 390
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 5.33,
|
| 291 |
+
"learning_rate": 5.185185185185185e-05,
|
| 292 |
+
"loss": 0.1838,
|
| 293 |
+
"step": 400
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 5.47,
|
| 297 |
+
"learning_rate": 5.0370370370370366e-05,
|
| 298 |
+
"loss": 0.2272,
|
| 299 |
+
"step": 410
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 5.6,
|
| 303 |
+
"learning_rate": 4.888888888888889e-05,
|
| 304 |
+
"loss": 0.185,
|
| 305 |
+
"step": 420
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 5.73,
|
| 309 |
+
"learning_rate": 4.740740740740741e-05,
|
| 310 |
+
"loss": 0.1832,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 5.87,
|
| 315 |
+
"learning_rate": 4.592592592592593e-05,
|
| 316 |
+
"loss": 0.1449,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 6.0,
|
| 321 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 322 |
+
"loss": 0.169,
|
| 323 |
+
"step": 450
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 6.0,
|
| 327 |
+
"eval_accuracy": 0.7790178571428571,
|
| 328 |
+
"eval_loss": 0.756848156452179,
|
| 329 |
+
"eval_runtime": 14.9826,
|
| 330 |
+
"eval_samples_per_second": 29.901,
|
| 331 |
+
"eval_steps_per_second": 3.738,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.13,
|
| 336 |
+
"learning_rate": 4.296296296296296e-05,
|
| 337 |
+
"loss": 0.1311,
|
| 338 |
+
"step": 460
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.27,
|
| 342 |
+
"learning_rate": 4.148148148148148e-05,
|
| 343 |
+
"loss": 0.1196,
|
| 344 |
+
"step": 470
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.4,
|
| 348 |
+
"learning_rate": 4e-05,
|
| 349 |
+
"loss": 0.12,
|
| 350 |
+
"step": 480
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.53,
|
| 354 |
+
"learning_rate": 3.851851851851852e-05,
|
| 355 |
+
"loss": 0.1471,
|
| 356 |
+
"step": 490
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.67,
|
| 360 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 361 |
+
"loss": 0.1104,
|
| 362 |
+
"step": 500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.8,
|
| 366 |
+
"learning_rate": 3.555555555555556e-05,
|
| 367 |
+
"loss": 0.1529,
|
| 368 |
+
"step": 510
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 6.93,
|
| 372 |
+
"learning_rate": 3.4074074074074077e-05,
|
| 373 |
+
"loss": 0.1375,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 7.0,
|
| 378 |
+
"eval_accuracy": 0.7723214285714286,
|
| 379 |
+
"eval_loss": 0.8526908159255981,
|
| 380 |
+
"eval_runtime": 15.1218,
|
| 381 |
+
"eval_samples_per_second": 29.626,
|
| 382 |
+
"eval_steps_per_second": 3.703,
|
| 383 |
+
"step": 525
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 7.07,
|
| 387 |
+
"learning_rate": 3.25925925925926e-05,
|
| 388 |
+
"loss": 0.1935,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 7.2,
|
| 393 |
+
"learning_rate": 3.111111111111111e-05,
|
| 394 |
+
"loss": 0.131,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 7.33,
|
| 399 |
+
"learning_rate": 2.962962962962963e-05,
|
| 400 |
+
"loss": 0.0954,
|
| 401 |
+
"step": 550
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 7.47,
|
| 405 |
+
"learning_rate": 2.814814814814815e-05,
|
| 406 |
+
"loss": 0.0971,
|
| 407 |
+
"step": 560
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 7.6,
|
| 411 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 412 |
+
"loss": 0.1179,
|
| 413 |
+
"step": 570
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 7.73,
|
| 417 |
+
"learning_rate": 2.5185185185185183e-05,
|
| 418 |
+
"loss": 0.1074,
|
| 419 |
+
"step": 580
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 7.87,
|
| 423 |
+
"learning_rate": 2.3703703703703707e-05,
|
| 424 |
+
"loss": 0.1349,
|
| 425 |
+
"step": 590
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 8.0,
|
| 429 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 430 |
+
"loss": 0.0893,
|
| 431 |
+
"step": 600
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 8.0,
|
| 435 |
+
"eval_accuracy": 0.7834821428571429,
|
| 436 |
+
"eval_loss": 0.9136894941329956,
|
| 437 |
+
"eval_runtime": 14.9574,
|
| 438 |
+
"eval_samples_per_second": 29.952,
|
| 439 |
+
"eval_steps_per_second": 3.744,
|
| 440 |
+
"step": 600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 8.13,
|
| 444 |
+
"learning_rate": 2.074074074074074e-05,
|
| 445 |
+
"loss": 0.0898,
|
| 446 |
+
"step": 610
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 8.27,
|
| 450 |
+
"learning_rate": 1.925925925925926e-05,
|
| 451 |
+
"loss": 0.1095,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 8.4,
|
| 456 |
+
"learning_rate": 1.777777777777778e-05,
|
| 457 |
+
"loss": 0.0696,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 8.53,
|
| 462 |
+
"learning_rate": 1.62962962962963e-05,
|
| 463 |
+
"loss": 0.1215,
|
| 464 |
+
"step": 640
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 8.67,
|
| 468 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 469 |
+
"loss": 0.1103,
|
| 470 |
+
"step": 650
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 8.8,
|
| 474 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 475 |
+
"loss": 0.1112,
|
| 476 |
+
"step": 660
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 8.93,
|
| 480 |
+
"learning_rate": 1.1851851851851853e-05,
|
| 481 |
+
"loss": 0.0804,
|
| 482 |
+
"step": 670
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 9.0,
|
| 486 |
+
"eval_accuracy": 0.7834821428571429,
|
| 487 |
+
"eval_loss": 0.9393314719200134,
|
| 488 |
+
"eval_runtime": 15.2041,
|
| 489 |
+
"eval_samples_per_second": 29.466,
|
| 490 |
+
"eval_steps_per_second": 3.683,
|
| 491 |
+
"step": 675
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 9.07,
|
| 495 |
+
"learning_rate": 1.037037037037037e-05,
|
| 496 |
+
"loss": 0.1229,
|
| 497 |
+
"step": 680
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 9.2,
|
| 501 |
+
"learning_rate": 8.88888888888889e-06,
|
| 502 |
+
"loss": 0.078,
|
| 503 |
+
"step": 690
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 9.33,
|
| 507 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 508 |
+
"loss": 0.068,
|
| 509 |
+
"step": 700
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 9.47,
|
| 513 |
+
"learning_rate": 5.925925925925927e-06,
|
| 514 |
+
"loss": 0.1024,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 9.6,
|
| 519 |
+
"learning_rate": 4.444444444444445e-06,
|
| 520 |
+
"loss": 0.0794,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 9.73,
|
| 525 |
+
"learning_rate": 2.9629629629629633e-06,
|
| 526 |
+
"loss": 0.0874,
|
| 527 |
+
"step": 730
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 9.87,
|
| 531 |
+
"learning_rate": 1.4814814814814817e-06,
|
| 532 |
+
"loss": 0.0562,
|
| 533 |
+
"step": 740
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 10.0,
|
| 537 |
+
"learning_rate": 0.0,
|
| 538 |
+
"loss": 0.11,
|
| 539 |
+
"step": 750
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 10.0,
|
| 543 |
+
"eval_accuracy": 0.7723214285714286,
|
| 544 |
+
"eval_loss": 0.9582878947257996,
|
| 545 |
+
"eval_runtime": 15.0752,
|
| 546 |
+
"eval_samples_per_second": 29.718,
|
| 547 |
+
"eval_steps_per_second": 3.715,
|
| 548 |
+
"step": 750
|
| 549 |
+
}
|
| 550 |
+
],
|
| 551 |
+
"max_steps": 750,
|
| 552 |
+
"num_train_epochs": 10,
|
| 553 |
+
"total_flos": 4.90627722230102e+18,
|
| 554 |
+
"trial_name": null,
|
| 555 |
+
"trial_params": null
|
| 556 |
+
}
|
10epoc-lr1e-4/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a83cf740a270b670bd17c76205d2c89c6825e7b3e6b5b4318299228d53ec75
|
| 3 |
+
size 3963
|