Upload folder using huggingface_hub
Browse files- all_results.json +8 -0
- checkpoint-100/config.json +44 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/preprocessor_config.json +22 -0
- checkpoint-100/pytorch_model.bin +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +166 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-250/config.json +44 -0
- checkpoint-250/optimizer.pt +3 -0
- checkpoint-250/preprocessor_config.json +22 -0
- checkpoint-250/pytorch_model.bin +3 -0
- checkpoint-250/rng_state.pth +3 -0
- checkpoint-250/scheduler.pt +3 -0
- checkpoint-250/trainer_state.json +391 -0
- checkpoint-250/training_args.bin +3 -0
- config.json +44 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- train_results.json +8 -0
- trainer_state.json +460 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 3.545449175052288e+17,
|
| 4 |
+
"train_loss": 0.48534091012231234,
|
| 5 |
+
"train_runtime": 1027.0889,
|
| 6 |
+
"train_samples_per_second": 4.454,
|
| 7 |
+
"train_steps_per_second": 0.282
|
| 8 |
+
}
|
checkpoint-100/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "acne",
|
| 13 |
+
"1": "eczema",
|
| 14 |
+
"2": "herpes zoster",
|
| 15 |
+
"3": "hives",
|
| 16 |
+
"4": "lupus",
|
| 17 |
+
"5": "raynauds",
|
| 18 |
+
"6": "tinea",
|
| 19 |
+
"7": "vitiligo"
|
| 20 |
+
},
|
| 21 |
+
"image_size": 224,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"acne": "0",
|
| 26 |
+
"eczema": "1",
|
| 27 |
+
"herpes zoster": "2",
|
| 28 |
+
"hives": "3",
|
| 29 |
+
"lupus": "4",
|
| 30 |
+
"raynauds": "5",
|
| 31 |
+
"tinea": "6",
|
| 32 |
+
"vitiligo": "7"
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-12,
|
| 35 |
+
"model_type": "vit",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_channels": 3,
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"patch_size": 16,
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"qkv_bias": true,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.30.2"
|
| 44 |
+
}
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b7815cc44b1b8af2219ec3f15dba65e7bb309bfca10ee63767e5867df570bdc
|
| 3 |
+
size 686605317
|
checkpoint-100/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 |
+
}
|
checkpoint-100/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92df0ed344bb275826e9a28655a22f187b8af79649ce7be3dea7b52c180f14b0
|
| 3 |
+
size 343287149
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e6fc19375cce74c0862b9871b9a851432a335ebdd452df1c7d81b4e0b89b159
|
| 3 |
+
size 14575
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc55bb5635500af2d3d3f5d8e6a36f126d8277798e32baa5fb8228cf3b9773af
|
| 3 |
+
size 627
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,166 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.2660315036773682,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-100",
|
| 4 |
+
"epoch": 1.7241379310344827,
|
| 5 |
+
"global_step": 100,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.17,
|
| 12 |
+
"learning_rate": 0.0001931034482758621,
|
| 13 |
+
"loss": 1.7999,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"eval_accuracy": 0.25555555555555554,
|
| 19 |
+
"eval_loss": 1.9382611513137817,
|
| 20 |
+
"eval_runtime": 128.8894,
|
| 21 |
+
"eval_samples_per_second": 2.095,
|
| 22 |
+
"eval_steps_per_second": 0.264,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.34,
|
| 27 |
+
"learning_rate": 0.00018620689655172415,
|
| 28 |
+
"loss": 1.5424,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.34,
|
| 33 |
+
"eval_accuracy": 0.4148148148148148,
|
| 34 |
+
"eval_loss": 1.5738633871078491,
|
| 35 |
+
"eval_runtime": 7.0871,
|
| 36 |
+
"eval_samples_per_second": 38.097,
|
| 37 |
+
"eval_steps_per_second": 4.797,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.52,
|
| 42 |
+
"learning_rate": 0.0001793103448275862,
|
| 43 |
+
"loss": 1.257,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.52,
|
| 48 |
+
"eval_accuracy": 0.5777777777777777,
|
| 49 |
+
"eval_loss": 1.3710002899169922,
|
| 50 |
+
"eval_runtime": 8.6728,
|
| 51 |
+
"eval_samples_per_second": 31.132,
|
| 52 |
+
"eval_steps_per_second": 3.92,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.69,
|
| 57 |
+
"learning_rate": 0.00017241379310344826,
|
| 58 |
+
"loss": 1.0721,
|
| 59 |
+
"step": 40
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.69,
|
| 63 |
+
"eval_accuracy": 0.5074074074074074,
|
| 64 |
+
"eval_loss": 1.4735559225082397,
|
| 65 |
+
"eval_runtime": 7.1381,
|
| 66 |
+
"eval_samples_per_second": 37.825,
|
| 67 |
+
"eval_steps_per_second": 4.763,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.86,
|
| 72 |
+
"learning_rate": 0.00016551724137931035,
|
| 73 |
+
"loss": 1.1026,
|
| 74 |
+
"step": 50
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.86,
|
| 78 |
+
"eval_accuracy": 0.6370370370370371,
|
| 79 |
+
"eval_loss": 1.2928471565246582,
|
| 80 |
+
"eval_runtime": 8.3556,
|
| 81 |
+
"eval_samples_per_second": 32.314,
|
| 82 |
+
"eval_steps_per_second": 4.069,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.03,
|
| 87 |
+
"learning_rate": 0.00015862068965517243,
|
| 88 |
+
"loss": 0.9359,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.03,
|
| 93 |
+
"eval_accuracy": 0.6074074074074074,
|
| 94 |
+
"eval_loss": 1.2788481712341309,
|
| 95 |
+
"eval_runtime": 7.1042,
|
| 96 |
+
"eval_samples_per_second": 38.006,
|
| 97 |
+
"eval_steps_per_second": 4.786,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.21,
|
| 102 |
+
"learning_rate": 0.00015172413793103449,
|
| 103 |
+
"loss": 0.7,
|
| 104 |
+
"step": 70
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.21,
|
| 108 |
+
"eval_accuracy": 0.6592592592592592,
|
| 109 |
+
"eval_loss": 1.2249455451965332,
|
| 110 |
+
"eval_runtime": 7.5614,
|
| 111 |
+
"eval_samples_per_second": 35.708,
|
| 112 |
+
"eval_steps_per_second": 4.497,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.38,
|
| 117 |
+
"learning_rate": 0.00014482758620689657,
|
| 118 |
+
"loss": 0.5367,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.38,
|
| 123 |
+
"eval_accuracy": 0.6222222222222222,
|
| 124 |
+
"eval_loss": 1.3300864696502686,
|
| 125 |
+
"eval_runtime": 7.852,
|
| 126 |
+
"eval_samples_per_second": 34.386,
|
| 127 |
+
"eval_steps_per_second": 4.33,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.55,
|
| 132 |
+
"learning_rate": 0.00013793103448275863,
|
| 133 |
+
"loss": 0.6017,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.55,
|
| 138 |
+
"eval_accuracy": 0.6666666666666666,
|
| 139 |
+
"eval_loss": 1.2042837142944336,
|
| 140 |
+
"eval_runtime": 8.2241,
|
| 141 |
+
"eval_samples_per_second": 32.83,
|
| 142 |
+
"eval_steps_per_second": 4.134,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.72,
|
| 147 |
+
"learning_rate": 0.00013103448275862068,
|
| 148 |
+
"loss": 0.6007,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.72,
|
| 153 |
+
"eval_accuracy": 0.6703703703703704,
|
| 154 |
+
"eval_loss": 1.2660315036773682,
|
| 155 |
+
"eval_runtime": 8.6405,
|
| 156 |
+
"eval_samples_per_second": 31.248,
|
| 157 |
+
"eval_steps_per_second": 3.935,
|
| 158 |
+
"step": 100
|
| 159 |
+
}
|
| 160 |
+
],
|
| 161 |
+
"max_steps": 290,
|
| 162 |
+
"num_train_epochs": 5,
|
| 163 |
+
"total_flos": 1.2298640089197773e+17,
|
| 164 |
+
"trial_name": null,
|
| 165 |
+
"trial_params": null
|
| 166 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:779ef95e31750d3943e4f7f30b53438699b481978b1b059b4a24fa8736da35a6
|
| 3 |
+
size 3899
|
checkpoint-250/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "acne",
|
| 13 |
+
"1": "eczema",
|
| 14 |
+
"2": "herpes zoster",
|
| 15 |
+
"3": "hives",
|
| 16 |
+
"4": "lupus",
|
| 17 |
+
"5": "raynauds",
|
| 18 |
+
"6": "tinea",
|
| 19 |
+
"7": "vitiligo"
|
| 20 |
+
},
|
| 21 |
+
"image_size": 224,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"acne": "0",
|
| 26 |
+
"eczema": "1",
|
| 27 |
+
"herpes zoster": "2",
|
| 28 |
+
"hives": "3",
|
| 29 |
+
"lupus": "4",
|
| 30 |
+
"raynauds": "5",
|
| 31 |
+
"tinea": "6",
|
| 32 |
+
"vitiligo": "7"
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-12,
|
| 35 |
+
"model_type": "vit",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_channels": 3,
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"patch_size": 16,
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"qkv_bias": true,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.30.2"
|
| 44 |
+
}
|
checkpoint-250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0612b5fe8cea030d4eeccda553bd400d4387d4dbf23ba147a3b4c7ceeb45a57f
|
| 3 |
+
size 686605317
|
checkpoint-250/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 |
+
}
|
checkpoint-250/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f43ee2364c034f6b356851d2a09050f3412a1b81bfa2442cdefaefb485c23aa4
|
| 3 |
+
size 343287149
|
checkpoint-250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab20ec22798cfb03ec9b0af2e45ca3a7d282a1ec1c6c852be97ba0580928637b
|
| 3 |
+
size 14575
|
checkpoint-250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7ac8a0883e053c6167ed582feec5ddfc131ae22f197d0fba801d4921afedc58
|
| 3 |
+
size 627
|
checkpoint-250/trainer_state.json
ADDED
|
@@ -0,0 +1,391 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.2660315036773682,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-100",
|
| 4 |
+
"epoch": 4.310344827586207,
|
| 5 |
+
"global_step": 250,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.17,
|
| 12 |
+
"learning_rate": 0.0001931034482758621,
|
| 13 |
+
"loss": 1.7999,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"eval_accuracy": 0.25555555555555554,
|
| 19 |
+
"eval_loss": 1.9382611513137817,
|
| 20 |
+
"eval_runtime": 128.8894,
|
| 21 |
+
"eval_samples_per_second": 2.095,
|
| 22 |
+
"eval_steps_per_second": 0.264,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.34,
|
| 27 |
+
"learning_rate": 0.00018620689655172415,
|
| 28 |
+
"loss": 1.5424,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.34,
|
| 33 |
+
"eval_accuracy": 0.4148148148148148,
|
| 34 |
+
"eval_loss": 1.5738633871078491,
|
| 35 |
+
"eval_runtime": 7.0871,
|
| 36 |
+
"eval_samples_per_second": 38.097,
|
| 37 |
+
"eval_steps_per_second": 4.797,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.52,
|
| 42 |
+
"learning_rate": 0.0001793103448275862,
|
| 43 |
+
"loss": 1.257,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.52,
|
| 48 |
+
"eval_accuracy": 0.5777777777777777,
|
| 49 |
+
"eval_loss": 1.3710002899169922,
|
| 50 |
+
"eval_runtime": 8.6728,
|
| 51 |
+
"eval_samples_per_second": 31.132,
|
| 52 |
+
"eval_steps_per_second": 3.92,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.69,
|
| 57 |
+
"learning_rate": 0.00017241379310344826,
|
| 58 |
+
"loss": 1.0721,
|
| 59 |
+
"step": 40
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.69,
|
| 63 |
+
"eval_accuracy": 0.5074074074074074,
|
| 64 |
+
"eval_loss": 1.4735559225082397,
|
| 65 |
+
"eval_runtime": 7.1381,
|
| 66 |
+
"eval_samples_per_second": 37.825,
|
| 67 |
+
"eval_steps_per_second": 4.763,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.86,
|
| 72 |
+
"learning_rate": 0.00016551724137931035,
|
| 73 |
+
"loss": 1.1026,
|
| 74 |
+
"step": 50
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.86,
|
| 78 |
+
"eval_accuracy": 0.6370370370370371,
|
| 79 |
+
"eval_loss": 1.2928471565246582,
|
| 80 |
+
"eval_runtime": 8.3556,
|
| 81 |
+
"eval_samples_per_second": 32.314,
|
| 82 |
+
"eval_steps_per_second": 4.069,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.03,
|
| 87 |
+
"learning_rate": 0.00015862068965517243,
|
| 88 |
+
"loss": 0.9359,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.03,
|
| 93 |
+
"eval_accuracy": 0.6074074074074074,
|
| 94 |
+
"eval_loss": 1.2788481712341309,
|
| 95 |
+
"eval_runtime": 7.1042,
|
| 96 |
+
"eval_samples_per_second": 38.006,
|
| 97 |
+
"eval_steps_per_second": 4.786,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.21,
|
| 102 |
+
"learning_rate": 0.00015172413793103449,
|
| 103 |
+
"loss": 0.7,
|
| 104 |
+
"step": 70
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.21,
|
| 108 |
+
"eval_accuracy": 0.6592592592592592,
|
| 109 |
+
"eval_loss": 1.2249455451965332,
|
| 110 |
+
"eval_runtime": 7.5614,
|
| 111 |
+
"eval_samples_per_second": 35.708,
|
| 112 |
+
"eval_steps_per_second": 4.497,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.38,
|
| 117 |
+
"learning_rate": 0.00014482758620689657,
|
| 118 |
+
"loss": 0.5367,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.38,
|
| 123 |
+
"eval_accuracy": 0.6222222222222222,
|
| 124 |
+
"eval_loss": 1.3300864696502686,
|
| 125 |
+
"eval_runtime": 7.852,
|
| 126 |
+
"eval_samples_per_second": 34.386,
|
| 127 |
+
"eval_steps_per_second": 4.33,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.55,
|
| 132 |
+
"learning_rate": 0.00013793103448275863,
|
| 133 |
+
"loss": 0.6017,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.55,
|
| 138 |
+
"eval_accuracy": 0.6666666666666666,
|
| 139 |
+
"eval_loss": 1.2042837142944336,
|
| 140 |
+
"eval_runtime": 8.2241,
|
| 141 |
+
"eval_samples_per_second": 32.83,
|
| 142 |
+
"eval_steps_per_second": 4.134,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.72,
|
| 147 |
+
"learning_rate": 0.00013103448275862068,
|
| 148 |
+
"loss": 0.6007,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.72,
|
| 153 |
+
"eval_accuracy": 0.6703703703703704,
|
| 154 |
+
"eval_loss": 1.2660315036773682,
|
| 155 |
+
"eval_runtime": 8.6405,
|
| 156 |
+
"eval_samples_per_second": 31.248,
|
| 157 |
+
"eval_steps_per_second": 3.935,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.9,
|
| 162 |
+
"learning_rate": 0.00012413793103448277,
|
| 163 |
+
"loss": 0.6083,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.9,
|
| 168 |
+
"eval_accuracy": 0.6851851851851852,
|
| 169 |
+
"eval_loss": 1.2744337320327759,
|
| 170 |
+
"eval_runtime": 8.1117,
|
| 171 |
+
"eval_samples_per_second": 33.285,
|
| 172 |
+
"eval_steps_per_second": 4.191,
|
| 173 |
+
"step": 110
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.07,
|
| 177 |
+
"learning_rate": 0.00011724137931034482,
|
| 178 |
+
"loss": 0.4428,
|
| 179 |
+
"step": 120
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.07,
|
| 183 |
+
"eval_accuracy": 0.6481481481481481,
|
| 184 |
+
"eval_loss": 1.3982332944869995,
|
| 185 |
+
"eval_runtime": 9.593,
|
| 186 |
+
"eval_samples_per_second": 28.145,
|
| 187 |
+
"eval_steps_per_second": 3.544,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.24,
|
| 192 |
+
"learning_rate": 0.0001103448275862069,
|
| 193 |
+
"loss": 0.3967,
|
| 194 |
+
"step": 130
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.24,
|
| 198 |
+
"eval_accuracy": 0.6851851851851852,
|
| 199 |
+
"eval_loss": 1.2987446784973145,
|
| 200 |
+
"eval_runtime": 7.0774,
|
| 201 |
+
"eval_samples_per_second": 38.15,
|
| 202 |
+
"eval_steps_per_second": 4.804,
|
| 203 |
+
"step": 130
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.41,
|
| 207 |
+
"learning_rate": 0.00010344827586206898,
|
| 208 |
+
"loss": 0.3308,
|
| 209 |
+
"step": 140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.41,
|
| 213 |
+
"eval_accuracy": 0.7,
|
| 214 |
+
"eval_loss": 1.3469077348709106,
|
| 215 |
+
"eval_runtime": 7.0247,
|
| 216 |
+
"eval_samples_per_second": 38.436,
|
| 217 |
+
"eval_steps_per_second": 4.84,
|
| 218 |
+
"step": 140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.59,
|
| 222 |
+
"learning_rate": 9.655172413793105e-05,
|
| 223 |
+
"loss": 0.2844,
|
| 224 |
+
"step": 150
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.59,
|
| 228 |
+
"eval_accuracy": 0.6962962962962963,
|
| 229 |
+
"eval_loss": 1.2884557247161865,
|
| 230 |
+
"eval_runtime": 9.6127,
|
| 231 |
+
"eval_samples_per_second": 28.088,
|
| 232 |
+
"eval_steps_per_second": 3.537,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.76,
|
| 237 |
+
"learning_rate": 8.96551724137931e-05,
|
| 238 |
+
"loss": 0.2313,
|
| 239 |
+
"step": 160
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.76,
|
| 243 |
+
"eval_accuracy": 0.6851851851851852,
|
| 244 |
+
"eval_loss": 1.4098496437072754,
|
| 245 |
+
"eval_runtime": 8.6491,
|
| 246 |
+
"eval_samples_per_second": 31.217,
|
| 247 |
+
"eval_steps_per_second": 3.931,
|
| 248 |
+
"step": 160
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.93,
|
| 252 |
+
"learning_rate": 8.275862068965517e-05,
|
| 253 |
+
"loss": 0.2378,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.93,
|
| 258 |
+
"eval_accuracy": 0.6851851851851852,
|
| 259 |
+
"eval_loss": 1.4552189111709595,
|
| 260 |
+
"eval_runtime": 8.3406,
|
| 261 |
+
"eval_samples_per_second": 32.372,
|
| 262 |
+
"eval_steps_per_second": 4.076,
|
| 263 |
+
"step": 170
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.1,
|
| 267 |
+
"learning_rate": 7.586206896551724e-05,
|
| 268 |
+
"loss": 0.1724,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.1,
|
| 273 |
+
"eval_accuracy": 0.6851851851851852,
|
| 274 |
+
"eval_loss": 1.3009414672851562,
|
| 275 |
+
"eval_runtime": 7.8433,
|
| 276 |
+
"eval_samples_per_second": 34.424,
|
| 277 |
+
"eval_steps_per_second": 4.335,
|
| 278 |
+
"step": 180
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.28,
|
| 282 |
+
"learning_rate": 6.896551724137931e-05,
|
| 283 |
+
"loss": 0.1712,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.28,
|
| 288 |
+
"eval_accuracy": 0.6888888888888889,
|
| 289 |
+
"eval_loss": 1.3433070182800293,
|
| 290 |
+
"eval_runtime": 7.412,
|
| 291 |
+
"eval_samples_per_second": 36.427,
|
| 292 |
+
"eval_steps_per_second": 4.587,
|
| 293 |
+
"step": 190
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.45,
|
| 297 |
+
"learning_rate": 6.206896551724138e-05,
|
| 298 |
+
"loss": 0.1521,
|
| 299 |
+
"step": 200
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.45,
|
| 303 |
+
"eval_accuracy": 0.6888888888888889,
|
| 304 |
+
"eval_loss": 1.4084450006484985,
|
| 305 |
+
"eval_runtime": 7.1569,
|
| 306 |
+
"eval_samples_per_second": 37.726,
|
| 307 |
+
"eval_steps_per_second": 4.751,
|
| 308 |
+
"step": 200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.62,
|
| 312 |
+
"learning_rate": 5.517241379310345e-05,
|
| 313 |
+
"loss": 0.1178,
|
| 314 |
+
"step": 210
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.62,
|
| 318 |
+
"eval_accuracy": 0.6925925925925925,
|
| 319 |
+
"eval_loss": 1.4383904933929443,
|
| 320 |
+
"eval_runtime": 15.5468,
|
| 321 |
+
"eval_samples_per_second": 17.367,
|
| 322 |
+
"eval_steps_per_second": 2.187,
|
| 323 |
+
"step": 210
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.79,
|
| 327 |
+
"learning_rate": 4.827586206896552e-05,
|
| 328 |
+
"loss": 0.0968,
|
| 329 |
+
"step": 220
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.79,
|
| 333 |
+
"eval_accuracy": 0.6888888888888889,
|
| 334 |
+
"eval_loss": 1.44044029712677,
|
| 335 |
+
"eval_runtime": 8.8794,
|
| 336 |
+
"eval_samples_per_second": 30.407,
|
| 337 |
+
"eval_steps_per_second": 3.829,
|
| 338 |
+
"step": 220
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.97,
|
| 342 |
+
"learning_rate": 4.1379310344827587e-05,
|
| 343 |
+
"loss": 0.1471,
|
| 344 |
+
"step": 230
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.97,
|
| 348 |
+
"eval_accuracy": 0.6888888888888889,
|
| 349 |
+
"eval_loss": 1.4447485208511353,
|
| 350 |
+
"eval_runtime": 9.2898,
|
| 351 |
+
"eval_samples_per_second": 29.064,
|
| 352 |
+
"eval_steps_per_second": 3.66,
|
| 353 |
+
"step": 230
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.14,
|
| 357 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 358 |
+
"loss": 0.1114,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.14,
|
| 363 |
+
"eval_accuracy": 0.6888888888888889,
|
| 364 |
+
"eval_loss": 1.4719408750534058,
|
| 365 |
+
"eval_runtime": 12.6934,
|
| 366 |
+
"eval_samples_per_second": 21.271,
|
| 367 |
+
"eval_steps_per_second": 2.679,
|
| 368 |
+
"step": 240
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.31,
|
| 372 |
+
"learning_rate": 2.7586206896551727e-05,
|
| 373 |
+
"loss": 0.0967,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.31,
|
| 378 |
+
"eval_accuracy": 0.6925925925925925,
|
| 379 |
+
"eval_loss": 1.4684562683105469,
|
| 380 |
+
"eval_runtime": 7.9455,
|
| 381 |
+
"eval_samples_per_second": 33.982,
|
| 382 |
+
"eval_steps_per_second": 4.279,
|
| 383 |
+
"step": 250
|
| 384 |
+
}
|
| 385 |
+
],
|
| 386 |
+
"max_steps": 290,
|
| 387 |
+
"num_train_epochs": 5,
|
| 388 |
+
"total_flos": 3.059548271717253e+17,
|
| 389 |
+
"trial_name": null,
|
| 390 |
+
"trial_params": null
|
| 391 |
+
}
|
checkpoint-250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:779ef95e31750d3943e4f7f30b53438699b481978b1b059b4a24fa8736da35a6
|
| 3 |
+
size 3899
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "acne",
|
| 13 |
+
"1": "eczema",
|
| 14 |
+
"2": "herpes zoster",
|
| 15 |
+
"3": "hives",
|
| 16 |
+
"4": "lupus",
|
| 17 |
+
"5": "raynauds",
|
| 18 |
+
"6": "tinea",
|
| 19 |
+
"7": "vitiligo"
|
| 20 |
+
},
|
| 21 |
+
"image_size": 224,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"acne": "0",
|
| 26 |
+
"eczema": "1",
|
| 27 |
+
"herpes zoster": "2",
|
| 28 |
+
"hives": "3",
|
| 29 |
+
"lupus": "4",
|
| 30 |
+
"raynauds": "5",
|
| 31 |
+
"tinea": "6",
|
| 32 |
+
"vitiligo": "7"
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-12,
|
| 35 |
+
"model_type": "vit",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_channels": 3,
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"patch_size": 16,
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"qkv_bias": true,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.30.2"
|
| 44 |
+
}
|
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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92df0ed344bb275826e9a28655a22f187b8af79649ce7be3dea7b52c180f14b0
|
| 3 |
+
size 343287149
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 3.545449175052288e+17,
|
| 4 |
+
"train_loss": 0.48534091012231234,
|
| 5 |
+
"train_runtime": 1027.0889,
|
| 6 |
+
"train_samples_per_second": 4.454,
|
| 7 |
+
"train_steps_per_second": 0.282
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.2660315036773682,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-100",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 290,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.17,
|
| 12 |
+
"learning_rate": 0.0001931034482758621,
|
| 13 |
+
"loss": 1.7999,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"eval_accuracy": 0.25555555555555554,
|
| 19 |
+
"eval_loss": 1.9382611513137817,
|
| 20 |
+
"eval_runtime": 128.8894,
|
| 21 |
+
"eval_samples_per_second": 2.095,
|
| 22 |
+
"eval_steps_per_second": 0.264,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.34,
|
| 27 |
+
"learning_rate": 0.00018620689655172415,
|
| 28 |
+
"loss": 1.5424,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.34,
|
| 33 |
+
"eval_accuracy": 0.4148148148148148,
|
| 34 |
+
"eval_loss": 1.5738633871078491,
|
| 35 |
+
"eval_runtime": 7.0871,
|
| 36 |
+
"eval_samples_per_second": 38.097,
|
| 37 |
+
"eval_steps_per_second": 4.797,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.52,
|
| 42 |
+
"learning_rate": 0.0001793103448275862,
|
| 43 |
+
"loss": 1.257,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.52,
|
| 48 |
+
"eval_accuracy": 0.5777777777777777,
|
| 49 |
+
"eval_loss": 1.3710002899169922,
|
| 50 |
+
"eval_runtime": 8.6728,
|
| 51 |
+
"eval_samples_per_second": 31.132,
|
| 52 |
+
"eval_steps_per_second": 3.92,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.69,
|
| 57 |
+
"learning_rate": 0.00017241379310344826,
|
| 58 |
+
"loss": 1.0721,
|
| 59 |
+
"step": 40
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.69,
|
| 63 |
+
"eval_accuracy": 0.5074074074074074,
|
| 64 |
+
"eval_loss": 1.4735559225082397,
|
| 65 |
+
"eval_runtime": 7.1381,
|
| 66 |
+
"eval_samples_per_second": 37.825,
|
| 67 |
+
"eval_steps_per_second": 4.763,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.86,
|
| 72 |
+
"learning_rate": 0.00016551724137931035,
|
| 73 |
+
"loss": 1.1026,
|
| 74 |
+
"step": 50
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.86,
|
| 78 |
+
"eval_accuracy": 0.6370370370370371,
|
| 79 |
+
"eval_loss": 1.2928471565246582,
|
| 80 |
+
"eval_runtime": 8.3556,
|
| 81 |
+
"eval_samples_per_second": 32.314,
|
| 82 |
+
"eval_steps_per_second": 4.069,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.03,
|
| 87 |
+
"learning_rate": 0.00015862068965517243,
|
| 88 |
+
"loss": 0.9359,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.03,
|
| 93 |
+
"eval_accuracy": 0.6074074074074074,
|
| 94 |
+
"eval_loss": 1.2788481712341309,
|
| 95 |
+
"eval_runtime": 7.1042,
|
| 96 |
+
"eval_samples_per_second": 38.006,
|
| 97 |
+
"eval_steps_per_second": 4.786,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.21,
|
| 102 |
+
"learning_rate": 0.00015172413793103449,
|
| 103 |
+
"loss": 0.7,
|
| 104 |
+
"step": 70
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.21,
|
| 108 |
+
"eval_accuracy": 0.6592592592592592,
|
| 109 |
+
"eval_loss": 1.2249455451965332,
|
| 110 |
+
"eval_runtime": 7.5614,
|
| 111 |
+
"eval_samples_per_second": 35.708,
|
| 112 |
+
"eval_steps_per_second": 4.497,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.38,
|
| 117 |
+
"learning_rate": 0.00014482758620689657,
|
| 118 |
+
"loss": 0.5367,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.38,
|
| 123 |
+
"eval_accuracy": 0.6222222222222222,
|
| 124 |
+
"eval_loss": 1.3300864696502686,
|
| 125 |
+
"eval_runtime": 7.852,
|
| 126 |
+
"eval_samples_per_second": 34.386,
|
| 127 |
+
"eval_steps_per_second": 4.33,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.55,
|
| 132 |
+
"learning_rate": 0.00013793103448275863,
|
| 133 |
+
"loss": 0.6017,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.55,
|
| 138 |
+
"eval_accuracy": 0.6666666666666666,
|
| 139 |
+
"eval_loss": 1.2042837142944336,
|
| 140 |
+
"eval_runtime": 8.2241,
|
| 141 |
+
"eval_samples_per_second": 32.83,
|
| 142 |
+
"eval_steps_per_second": 4.134,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.72,
|
| 147 |
+
"learning_rate": 0.00013103448275862068,
|
| 148 |
+
"loss": 0.6007,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.72,
|
| 153 |
+
"eval_accuracy": 0.6703703703703704,
|
| 154 |
+
"eval_loss": 1.2660315036773682,
|
| 155 |
+
"eval_runtime": 8.6405,
|
| 156 |
+
"eval_samples_per_second": 31.248,
|
| 157 |
+
"eval_steps_per_second": 3.935,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.9,
|
| 162 |
+
"learning_rate": 0.00012413793103448277,
|
| 163 |
+
"loss": 0.6083,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.9,
|
| 168 |
+
"eval_accuracy": 0.6851851851851852,
|
| 169 |
+
"eval_loss": 1.2744337320327759,
|
| 170 |
+
"eval_runtime": 8.1117,
|
| 171 |
+
"eval_samples_per_second": 33.285,
|
| 172 |
+
"eval_steps_per_second": 4.191,
|
| 173 |
+
"step": 110
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.07,
|
| 177 |
+
"learning_rate": 0.00011724137931034482,
|
| 178 |
+
"loss": 0.4428,
|
| 179 |
+
"step": 120
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.07,
|
| 183 |
+
"eval_accuracy": 0.6481481481481481,
|
| 184 |
+
"eval_loss": 1.3982332944869995,
|
| 185 |
+
"eval_runtime": 9.593,
|
| 186 |
+
"eval_samples_per_second": 28.145,
|
| 187 |
+
"eval_steps_per_second": 3.544,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.24,
|
| 192 |
+
"learning_rate": 0.0001103448275862069,
|
| 193 |
+
"loss": 0.3967,
|
| 194 |
+
"step": 130
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.24,
|
| 198 |
+
"eval_accuracy": 0.6851851851851852,
|
| 199 |
+
"eval_loss": 1.2987446784973145,
|
| 200 |
+
"eval_runtime": 7.0774,
|
| 201 |
+
"eval_samples_per_second": 38.15,
|
| 202 |
+
"eval_steps_per_second": 4.804,
|
| 203 |
+
"step": 130
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.41,
|
| 207 |
+
"learning_rate": 0.00010344827586206898,
|
| 208 |
+
"loss": 0.3308,
|
| 209 |
+
"step": 140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.41,
|
| 213 |
+
"eval_accuracy": 0.7,
|
| 214 |
+
"eval_loss": 1.3469077348709106,
|
| 215 |
+
"eval_runtime": 7.0247,
|
| 216 |
+
"eval_samples_per_second": 38.436,
|
| 217 |
+
"eval_steps_per_second": 4.84,
|
| 218 |
+
"step": 140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.59,
|
| 222 |
+
"learning_rate": 9.655172413793105e-05,
|
| 223 |
+
"loss": 0.2844,
|
| 224 |
+
"step": 150
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.59,
|
| 228 |
+
"eval_accuracy": 0.6962962962962963,
|
| 229 |
+
"eval_loss": 1.2884557247161865,
|
| 230 |
+
"eval_runtime": 9.6127,
|
| 231 |
+
"eval_samples_per_second": 28.088,
|
| 232 |
+
"eval_steps_per_second": 3.537,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.76,
|
| 237 |
+
"learning_rate": 8.96551724137931e-05,
|
| 238 |
+
"loss": 0.2313,
|
| 239 |
+
"step": 160
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.76,
|
| 243 |
+
"eval_accuracy": 0.6851851851851852,
|
| 244 |
+
"eval_loss": 1.4098496437072754,
|
| 245 |
+
"eval_runtime": 8.6491,
|
| 246 |
+
"eval_samples_per_second": 31.217,
|
| 247 |
+
"eval_steps_per_second": 3.931,
|
| 248 |
+
"step": 160
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.93,
|
| 252 |
+
"learning_rate": 8.275862068965517e-05,
|
| 253 |
+
"loss": 0.2378,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.93,
|
| 258 |
+
"eval_accuracy": 0.6851851851851852,
|
| 259 |
+
"eval_loss": 1.4552189111709595,
|
| 260 |
+
"eval_runtime": 8.3406,
|
| 261 |
+
"eval_samples_per_second": 32.372,
|
| 262 |
+
"eval_steps_per_second": 4.076,
|
| 263 |
+
"step": 170
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.1,
|
| 267 |
+
"learning_rate": 7.586206896551724e-05,
|
| 268 |
+
"loss": 0.1724,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.1,
|
| 273 |
+
"eval_accuracy": 0.6851851851851852,
|
| 274 |
+
"eval_loss": 1.3009414672851562,
|
| 275 |
+
"eval_runtime": 7.8433,
|
| 276 |
+
"eval_samples_per_second": 34.424,
|
| 277 |
+
"eval_steps_per_second": 4.335,
|
| 278 |
+
"step": 180
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.28,
|
| 282 |
+
"learning_rate": 6.896551724137931e-05,
|
| 283 |
+
"loss": 0.1712,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.28,
|
| 288 |
+
"eval_accuracy": 0.6888888888888889,
|
| 289 |
+
"eval_loss": 1.3433070182800293,
|
| 290 |
+
"eval_runtime": 7.412,
|
| 291 |
+
"eval_samples_per_second": 36.427,
|
| 292 |
+
"eval_steps_per_second": 4.587,
|
| 293 |
+
"step": 190
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.45,
|
| 297 |
+
"learning_rate": 6.206896551724138e-05,
|
| 298 |
+
"loss": 0.1521,
|
| 299 |
+
"step": 200
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.45,
|
| 303 |
+
"eval_accuracy": 0.6888888888888889,
|
| 304 |
+
"eval_loss": 1.4084450006484985,
|
| 305 |
+
"eval_runtime": 7.1569,
|
| 306 |
+
"eval_samples_per_second": 37.726,
|
| 307 |
+
"eval_steps_per_second": 4.751,
|
| 308 |
+
"step": 200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.62,
|
| 312 |
+
"learning_rate": 5.517241379310345e-05,
|
| 313 |
+
"loss": 0.1178,
|
| 314 |
+
"step": 210
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.62,
|
| 318 |
+
"eval_accuracy": 0.6925925925925925,
|
| 319 |
+
"eval_loss": 1.4383904933929443,
|
| 320 |
+
"eval_runtime": 15.5468,
|
| 321 |
+
"eval_samples_per_second": 17.367,
|
| 322 |
+
"eval_steps_per_second": 2.187,
|
| 323 |
+
"step": 210
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.79,
|
| 327 |
+
"learning_rate": 4.827586206896552e-05,
|
| 328 |
+
"loss": 0.0968,
|
| 329 |
+
"step": 220
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.79,
|
| 333 |
+
"eval_accuracy": 0.6888888888888889,
|
| 334 |
+
"eval_loss": 1.44044029712677,
|
| 335 |
+
"eval_runtime": 8.8794,
|
| 336 |
+
"eval_samples_per_second": 30.407,
|
| 337 |
+
"eval_steps_per_second": 3.829,
|
| 338 |
+
"step": 220
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.97,
|
| 342 |
+
"learning_rate": 4.1379310344827587e-05,
|
| 343 |
+
"loss": 0.1471,
|
| 344 |
+
"step": 230
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.97,
|
| 348 |
+
"eval_accuracy": 0.6888888888888889,
|
| 349 |
+
"eval_loss": 1.4447485208511353,
|
| 350 |
+
"eval_runtime": 9.2898,
|
| 351 |
+
"eval_samples_per_second": 29.064,
|
| 352 |
+
"eval_steps_per_second": 3.66,
|
| 353 |
+
"step": 230
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.14,
|
| 357 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 358 |
+
"loss": 0.1114,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.14,
|
| 363 |
+
"eval_accuracy": 0.6888888888888889,
|
| 364 |
+
"eval_loss": 1.4719408750534058,
|
| 365 |
+
"eval_runtime": 12.6934,
|
| 366 |
+
"eval_samples_per_second": 21.271,
|
| 367 |
+
"eval_steps_per_second": 2.679,
|
| 368 |
+
"step": 240
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.31,
|
| 372 |
+
"learning_rate": 2.7586206896551727e-05,
|
| 373 |
+
"loss": 0.0967,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.31,
|
| 378 |
+
"eval_accuracy": 0.6925925925925925,
|
| 379 |
+
"eval_loss": 1.4684562683105469,
|
| 380 |
+
"eval_runtime": 7.9455,
|
| 381 |
+
"eval_samples_per_second": 33.982,
|
| 382 |
+
"eval_steps_per_second": 4.279,
|
| 383 |
+
"step": 250
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.48,
|
| 387 |
+
"learning_rate": 2.0689655172413793e-05,
|
| 388 |
+
"loss": 0.0974,
|
| 389 |
+
"step": 260
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 4.48,
|
| 393 |
+
"eval_accuracy": 0.6925925925925925,
|
| 394 |
+
"eval_loss": 1.473760962486267,
|
| 395 |
+
"eval_runtime": 8.2858,
|
| 396 |
+
"eval_samples_per_second": 32.586,
|
| 397 |
+
"eval_steps_per_second": 4.103,
|
| 398 |
+
"step": 260
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.66,
|
| 402 |
+
"learning_rate": 1.3793103448275863e-05,
|
| 403 |
+
"loss": 0.0647,
|
| 404 |
+
"step": 270
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.66,
|
| 408 |
+
"eval_accuracy": 0.6925925925925925,
|
| 409 |
+
"eval_loss": 1.4769530296325684,
|
| 410 |
+
"eval_runtime": 7.728,
|
| 411 |
+
"eval_samples_per_second": 34.938,
|
| 412 |
+
"eval_steps_per_second": 4.4,
|
| 413 |
+
"step": 270
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.83,
|
| 417 |
+
"learning_rate": 6.896551724137932e-06,
|
| 418 |
+
"loss": 0.0899,
|
| 419 |
+
"step": 280
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 4.83,
|
| 423 |
+
"eval_accuracy": 0.6925925925925925,
|
| 424 |
+
"eval_loss": 1.4792803525924683,
|
| 425 |
+
"eval_runtime": 7.3284,
|
| 426 |
+
"eval_samples_per_second": 36.843,
|
| 427 |
+
"eval_steps_per_second": 4.64,
|
| 428 |
+
"step": 280
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 5.0,
|
| 432 |
+
"learning_rate": 0.0,
|
| 433 |
+
"loss": 0.0763,
|
| 434 |
+
"step": 290
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.0,
|
| 438 |
+
"eval_accuracy": 0.6925925925925925,
|
| 439 |
+
"eval_loss": 1.4800288677215576,
|
| 440 |
+
"eval_runtime": 7.1527,
|
| 441 |
+
"eval_samples_per_second": 37.748,
|
| 442 |
+
"eval_steps_per_second": 4.753,
|
| 443 |
+
"step": 290
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.0,
|
| 447 |
+
"step": 290,
|
| 448 |
+
"total_flos": 3.545449175052288e+17,
|
| 449 |
+
"train_loss": 0.48534091012231234,
|
| 450 |
+
"train_runtime": 1027.0889,
|
| 451 |
+
"train_samples_per_second": 4.454,
|
| 452 |
+
"train_steps_per_second": 0.282
|
| 453 |
+
}
|
| 454 |
+
],
|
| 455 |
+
"max_steps": 290,
|
| 456 |
+
"num_train_epochs": 5,
|
| 457 |
+
"total_flos": 3.545449175052288e+17,
|
| 458 |
+
"trial_name": null,
|
| 459 |
+
"trial_params": null
|
| 460 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:779ef95e31750d3943e4f7f30b53438699b481978b1b059b4a24fa8736da35a6
|
| 3 |
+
size 3899
|