Commit
·
611fd7b
1
Parent(s):
e4daada
Training 20 epocs
Browse files- all_results.json +9 -0
- checkpoint-152/config.json +32 -0
- checkpoint-152/optimizer.pt +3 -0
- checkpoint-152/preprocessor_config.json +22 -0
- checkpoint-152/pytorch_model.bin +3 -0
- checkpoint-152/rng_state.pth +3 -0
- checkpoint-152/scheduler.pt +3 -0
- checkpoint-152/trainer_state.json +320 -0
- checkpoint-152/training_args.bin +3 -0
- checkpoint-160/config.json +32 -0
- checkpoint-160/optimizer.pt +3 -0
- checkpoint-160/preprocessor_config.json +22 -0
- checkpoint-160/pytorch_model.bin +3 -0
- checkpoint-160/rng_state.pth +3 -0
- checkpoint-160/scheduler.pt +3 -0
- checkpoint-160/trainer_state.json +336 -0
- checkpoint-160/training_args.bin +3 -0
- eval_results.json +9 -0
- runs/Aug01_13-59-41_43191bdd660e/events.out.tfevents.1690898382.43191bdd660e.478503.0 +3 -0
- runs/Aug01_13-59-41_43191bdd660e/events.out.tfevents.1690903587.43191bdd660e.478503.1 +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.71,
|
| 4 |
+
"eval_f1": 0.7085720028137876,
|
| 5 |
+
"eval_loss": 0.5737453699111938,
|
| 6 |
+
"eval_runtime": 16.7507,
|
| 7 |
+
"eval_samples_per_second": 5.97,
|
| 8 |
+
"eval_steps_per_second": 0.119
|
| 9 |
+
}
|
checkpoint-152/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 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": "A",
|
| 13 |
+
"1": "C"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"A": "0",
|
| 20 |
+
"C": "1"
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.31.0"
|
| 32 |
+
}
|
checkpoint-152/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ecda96ea9114bb090c7b9f9ae2c03b42521c7e3ebefe7317006c54e2249f330
|
| 3 |
+
size 686513157
|
checkpoint-152/preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
checkpoint-152/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efa4c71892cc88ebb8a7ac324ea009ebb995b317c05bbec45957c50095ed6791
|
| 3 |
+
size 343265965
|
checkpoint-152/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab481121389fc093b6e4b4cedff51134e54418c5f593bd2470e383d000431fb4
|
| 3 |
+
size 13553
|
checkpoint-152/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25ec670c233b4b6924834a7a1960ba0286ca87c0200c967a75dbfefdb451fc7a
|
| 3 |
+
size 627
|
checkpoint-152/trainer_state.json
ADDED
|
@@ -0,0 +1,320 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5737959742546082,
|
| 3 |
+
"best_model_checkpoint": "./vit-molecul/checkpoint-128",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
+
"global_step": 152,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 2.85e-06,
|
| 13 |
+
"loss": 0.723,
|
| 14 |
+
"step": 8
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.61,
|
| 19 |
+
"eval_f1": 0.6096486838154338,
|
| 20 |
+
"eval_loss": 0.6790218949317932,
|
| 21 |
+
"eval_runtime": 19.8848,
|
| 22 |
+
"eval_samples_per_second": 5.029,
|
| 23 |
+
"eval_steps_per_second": 0.101,
|
| 24 |
+
"step": 8
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 2.7e-06,
|
| 29 |
+
"loss": 0.6915,
|
| 30 |
+
"step": 16
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.62,
|
| 35 |
+
"eval_f1": 0.5924495924495925,
|
| 36 |
+
"eval_loss": 0.6660856604576111,
|
| 37 |
+
"eval_runtime": 20.4688,
|
| 38 |
+
"eval_samples_per_second": 4.885,
|
| 39 |
+
"eval_steps_per_second": 0.098,
|
| 40 |
+
"step": 16
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"learning_rate": 2.55e-06,
|
| 45 |
+
"loss": 0.6689,
|
| 46 |
+
"step": 24
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.69,
|
| 51 |
+
"eval_f1": 0.6892230576441103,
|
| 52 |
+
"eval_loss": 0.647020697593689,
|
| 53 |
+
"eval_runtime": 20.1108,
|
| 54 |
+
"eval_samples_per_second": 4.972,
|
| 55 |
+
"eval_steps_per_second": 0.099,
|
| 56 |
+
"step": 24
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 61 |
+
"loss": 0.6517,
|
| 62 |
+
"step": 32
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.64,
|
| 67 |
+
"eval_f1": 0.6376811594202898,
|
| 68 |
+
"eval_loss": 0.6355536580085754,
|
| 69 |
+
"eval_runtime": 17.3784,
|
| 70 |
+
"eval_samples_per_second": 5.754,
|
| 71 |
+
"eval_steps_per_second": 0.115,
|
| 72 |
+
"step": 32
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.0,
|
| 76 |
+
"learning_rate": 2.25e-06,
|
| 77 |
+
"loss": 0.6368,
|
| 78 |
+
"step": 40
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.72,
|
| 83 |
+
"eval_f1": 0.7198879551820727,
|
| 84 |
+
"eval_loss": 0.6288898587226868,
|
| 85 |
+
"eval_runtime": 19.3335,
|
| 86 |
+
"eval_samples_per_second": 5.172,
|
| 87 |
+
"eval_steps_per_second": 0.103,
|
| 88 |
+
"step": 40
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.0,
|
| 92 |
+
"learning_rate": 2.1e-06,
|
| 93 |
+
"loss": 0.621,
|
| 94 |
+
"step": 48
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.73,
|
| 99 |
+
"eval_f1": 0.7293233082706766,
|
| 100 |
+
"eval_loss": 0.621720552444458,
|
| 101 |
+
"eval_runtime": 21.1008,
|
| 102 |
+
"eval_samples_per_second": 4.739,
|
| 103 |
+
"eval_steps_per_second": 0.095,
|
| 104 |
+
"step": 48
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"learning_rate": 1.95e-06,
|
| 109 |
+
"loss": 0.6061,
|
| 110 |
+
"step": 56
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.0,
|
| 114 |
+
"eval_accuracy": 0.69,
|
| 115 |
+
"eval_f1": 0.6862030569895738,
|
| 116 |
+
"eval_loss": 0.6197251081466675,
|
| 117 |
+
"eval_runtime": 20.06,
|
| 118 |
+
"eval_samples_per_second": 4.985,
|
| 119 |
+
"eval_steps_per_second": 0.1,
|
| 120 |
+
"step": 56
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 8.0,
|
| 124 |
+
"learning_rate": 1.8e-06,
|
| 125 |
+
"loss": 0.5924,
|
| 126 |
+
"step": 64
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.73,
|
| 131 |
+
"eval_f1": 0.7293233082706766,
|
| 132 |
+
"eval_loss": 0.6086930632591248,
|
| 133 |
+
"eval_runtime": 18.4413,
|
| 134 |
+
"eval_samples_per_second": 5.423,
|
| 135 |
+
"eval_steps_per_second": 0.108,
|
| 136 |
+
"step": 64
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"learning_rate": 1.65e-06,
|
| 141 |
+
"loss": 0.5767,
|
| 142 |
+
"step": 72
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 9.0,
|
| 146 |
+
"eval_accuracy": 0.72,
|
| 147 |
+
"eval_f1": 0.7198879551820727,
|
| 148 |
+
"eval_loss": 0.6002515554428101,
|
| 149 |
+
"eval_runtime": 19.1541,
|
| 150 |
+
"eval_samples_per_second": 5.221,
|
| 151 |
+
"eval_steps_per_second": 0.104,
|
| 152 |
+
"step": 72
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 1.5e-06,
|
| 157 |
+
"loss": 0.5633,
|
| 158 |
+
"step": 80
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.0,
|
| 162 |
+
"eval_accuracy": 0.72,
|
| 163 |
+
"eval_f1": 0.7195512820512822,
|
| 164 |
+
"eval_loss": 0.5953283905982971,
|
| 165 |
+
"eval_runtime": 18.6111,
|
| 166 |
+
"eval_samples_per_second": 5.373,
|
| 167 |
+
"eval_steps_per_second": 0.107,
|
| 168 |
+
"step": 80
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 11.0,
|
| 172 |
+
"learning_rate": 1.35e-06,
|
| 173 |
+
"loss": 0.5491,
|
| 174 |
+
"step": 88
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 11.0,
|
| 178 |
+
"eval_accuracy": 0.72,
|
| 179 |
+
"eval_f1": 0.7198879551820727,
|
| 180 |
+
"eval_loss": 0.5884998440742493,
|
| 181 |
+
"eval_runtime": 19.1596,
|
| 182 |
+
"eval_samples_per_second": 5.219,
|
| 183 |
+
"eval_steps_per_second": 0.104,
|
| 184 |
+
"step": 88
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 12.0,
|
| 188 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 189 |
+
"loss": 0.5351,
|
| 190 |
+
"step": 96
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 12.0,
|
| 194 |
+
"eval_accuracy": 0.71,
|
| 195 |
+
"eval_f1": 0.7099709970997101,
|
| 196 |
+
"eval_loss": 0.5868653655052185,
|
| 197 |
+
"eval_runtime": 19.9846,
|
| 198 |
+
"eval_samples_per_second": 5.004,
|
| 199 |
+
"eval_steps_per_second": 0.1,
|
| 200 |
+
"step": 96
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 13.0,
|
| 204 |
+
"learning_rate": 1.05e-06,
|
| 205 |
+
"loss": 0.5239,
|
| 206 |
+
"step": 104
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 13.0,
|
| 210 |
+
"eval_accuracy": 0.7,
|
| 211 |
+
"eval_f1": 0.6995192307692307,
|
| 212 |
+
"eval_loss": 0.5866873264312744,
|
| 213 |
+
"eval_runtime": 18.0538,
|
| 214 |
+
"eval_samples_per_second": 5.539,
|
| 215 |
+
"eval_steps_per_second": 0.111,
|
| 216 |
+
"step": 104
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 14.0,
|
| 220 |
+
"learning_rate": 9e-07,
|
| 221 |
+
"loss": 0.5118,
|
| 222 |
+
"step": 112
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 14.0,
|
| 226 |
+
"eval_accuracy": 0.71,
|
| 227 |
+
"eval_f1": 0.7099709970997101,
|
| 228 |
+
"eval_loss": 0.5804287195205688,
|
| 229 |
+
"eval_runtime": 13.1833,
|
| 230 |
+
"eval_samples_per_second": 7.585,
|
| 231 |
+
"eval_steps_per_second": 0.152,
|
| 232 |
+
"step": 112
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 15.0,
|
| 236 |
+
"learning_rate": 7.5e-07,
|
| 237 |
+
"loss": 0.502,
|
| 238 |
+
"step": 120
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 15.0,
|
| 242 |
+
"eval_accuracy": 0.71,
|
| 243 |
+
"eval_f1": 0.7099709970997101,
|
| 244 |
+
"eval_loss": 0.5751881003379822,
|
| 245 |
+
"eval_runtime": 14.0771,
|
| 246 |
+
"eval_samples_per_second": 7.104,
|
| 247 |
+
"eval_steps_per_second": 0.142,
|
| 248 |
+
"step": 120
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.0,
|
| 252 |
+
"learning_rate": 6.000000000000001e-07,
|
| 253 |
+
"loss": 0.4942,
|
| 254 |
+
"step": 128
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 16.0,
|
| 258 |
+
"eval_accuracy": 0.72,
|
| 259 |
+
"eval_f1": 0.7198879551820727,
|
| 260 |
+
"eval_loss": 0.5737959742546082,
|
| 261 |
+
"eval_runtime": 9.472,
|
| 262 |
+
"eval_samples_per_second": 10.557,
|
| 263 |
+
"eval_steps_per_second": 0.211,
|
| 264 |
+
"step": 128
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 17.0,
|
| 268 |
+
"learning_rate": 4.5e-07,
|
| 269 |
+
"loss": 0.4885,
|
| 270 |
+
"step": 136
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 17.0,
|
| 274 |
+
"eval_accuracy": 0.71,
|
| 275 |
+
"eval_f1": 0.7085720028137876,
|
| 276 |
+
"eval_loss": 0.5770530104637146,
|
| 277 |
+
"eval_runtime": 12.9019,
|
| 278 |
+
"eval_samples_per_second": 7.751,
|
| 279 |
+
"eval_steps_per_second": 0.155,
|
| 280 |
+
"step": 136
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 18.0,
|
| 284 |
+
"learning_rate": 3.0000000000000004e-07,
|
| 285 |
+
"loss": 0.4831,
|
| 286 |
+
"step": 144
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 18.0,
|
| 290 |
+
"eval_accuracy": 0.71,
|
| 291 |
+
"eval_f1": 0.7085720028137876,
|
| 292 |
+
"eval_loss": 0.5750694870948792,
|
| 293 |
+
"eval_runtime": 10.5808,
|
| 294 |
+
"eval_samples_per_second": 9.451,
|
| 295 |
+
"eval_steps_per_second": 0.189,
|
| 296 |
+
"step": 144
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 19.0,
|
| 300 |
+
"learning_rate": 1.5000000000000002e-07,
|
| 301 |
+
"loss": 0.4793,
|
| 302 |
+
"step": 152
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 19.0,
|
| 306 |
+
"eval_accuracy": 0.71,
|
| 307 |
+
"eval_f1": 0.7085720028137876,
|
| 308 |
+
"eval_loss": 0.5742676258087158,
|
| 309 |
+
"eval_runtime": 12.6314,
|
| 310 |
+
"eval_samples_per_second": 7.917,
|
| 311 |
+
"eval_steps_per_second": 0.158,
|
| 312 |
+
"step": 152
|
| 313 |
+
}
|
| 314 |
+
],
|
| 315 |
+
"max_steps": 160,
|
| 316 |
+
"num_train_epochs": 20,
|
| 317 |
+
"total_flos": 5.889391210708992e+17,
|
| 318 |
+
"trial_name": null,
|
| 319 |
+
"trial_params": null
|
| 320 |
+
}
|
checkpoint-152/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1420de36bba2c0538d4308eae1ef87ce2407627c3abf540ae0d76c7a96dae807
|
| 3 |
+
size 3963
|
checkpoint-160/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 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": "A",
|
| 13 |
+
"1": "C"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"A": "0",
|
| 20 |
+
"C": "1"
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.31.0"
|
| 32 |
+
}
|
checkpoint-160/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5ef86abd266c92441689f4452f4fcf1b0b2f706af081cf221699b15a2a27b43
|
| 3 |
+
size 686513157
|
checkpoint-160/preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
checkpoint-160/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5275ced9923b842e81052cee6ac2ef238e61f0dd7837dc5bccf3b0ea983ff9e8
|
| 3 |
+
size 343265965
|
checkpoint-160/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc5bc7f228b046116ccd43a2bde1a893bf7d7cab58c60e505a230870c40a9f22
|
| 3 |
+
size 13553
|
checkpoint-160/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77910a7065c9ef76665a193729dced0f9d16b9b33200527f9c6292e302e75bf8
|
| 3 |
+
size 627
|
checkpoint-160/trainer_state.json
ADDED
|
@@ -0,0 +1,336 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5737453699111938,
|
| 3 |
+
"best_model_checkpoint": "./vit-molecul/checkpoint-160",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 160,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 2.85e-06,
|
| 13 |
+
"loss": 0.723,
|
| 14 |
+
"step": 8
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.61,
|
| 19 |
+
"eval_f1": 0.6096486838154338,
|
| 20 |
+
"eval_loss": 0.6790218949317932,
|
| 21 |
+
"eval_runtime": 19.8848,
|
| 22 |
+
"eval_samples_per_second": 5.029,
|
| 23 |
+
"eval_steps_per_second": 0.101,
|
| 24 |
+
"step": 8
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 2.7e-06,
|
| 29 |
+
"loss": 0.6915,
|
| 30 |
+
"step": 16
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.62,
|
| 35 |
+
"eval_f1": 0.5924495924495925,
|
| 36 |
+
"eval_loss": 0.6660856604576111,
|
| 37 |
+
"eval_runtime": 20.4688,
|
| 38 |
+
"eval_samples_per_second": 4.885,
|
| 39 |
+
"eval_steps_per_second": 0.098,
|
| 40 |
+
"step": 16
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"learning_rate": 2.55e-06,
|
| 45 |
+
"loss": 0.6689,
|
| 46 |
+
"step": 24
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.69,
|
| 51 |
+
"eval_f1": 0.6892230576441103,
|
| 52 |
+
"eval_loss": 0.647020697593689,
|
| 53 |
+
"eval_runtime": 20.1108,
|
| 54 |
+
"eval_samples_per_second": 4.972,
|
| 55 |
+
"eval_steps_per_second": 0.099,
|
| 56 |
+
"step": 24
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 61 |
+
"loss": 0.6517,
|
| 62 |
+
"step": 32
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.64,
|
| 67 |
+
"eval_f1": 0.6376811594202898,
|
| 68 |
+
"eval_loss": 0.6355536580085754,
|
| 69 |
+
"eval_runtime": 17.3784,
|
| 70 |
+
"eval_samples_per_second": 5.754,
|
| 71 |
+
"eval_steps_per_second": 0.115,
|
| 72 |
+
"step": 32
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.0,
|
| 76 |
+
"learning_rate": 2.25e-06,
|
| 77 |
+
"loss": 0.6368,
|
| 78 |
+
"step": 40
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.72,
|
| 83 |
+
"eval_f1": 0.7198879551820727,
|
| 84 |
+
"eval_loss": 0.6288898587226868,
|
| 85 |
+
"eval_runtime": 19.3335,
|
| 86 |
+
"eval_samples_per_second": 5.172,
|
| 87 |
+
"eval_steps_per_second": 0.103,
|
| 88 |
+
"step": 40
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.0,
|
| 92 |
+
"learning_rate": 2.1e-06,
|
| 93 |
+
"loss": 0.621,
|
| 94 |
+
"step": 48
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.73,
|
| 99 |
+
"eval_f1": 0.7293233082706766,
|
| 100 |
+
"eval_loss": 0.621720552444458,
|
| 101 |
+
"eval_runtime": 21.1008,
|
| 102 |
+
"eval_samples_per_second": 4.739,
|
| 103 |
+
"eval_steps_per_second": 0.095,
|
| 104 |
+
"step": 48
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"learning_rate": 1.95e-06,
|
| 109 |
+
"loss": 0.6061,
|
| 110 |
+
"step": 56
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.0,
|
| 114 |
+
"eval_accuracy": 0.69,
|
| 115 |
+
"eval_f1": 0.6862030569895738,
|
| 116 |
+
"eval_loss": 0.6197251081466675,
|
| 117 |
+
"eval_runtime": 20.06,
|
| 118 |
+
"eval_samples_per_second": 4.985,
|
| 119 |
+
"eval_steps_per_second": 0.1,
|
| 120 |
+
"step": 56
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 8.0,
|
| 124 |
+
"learning_rate": 1.8e-06,
|
| 125 |
+
"loss": 0.5924,
|
| 126 |
+
"step": 64
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.73,
|
| 131 |
+
"eval_f1": 0.7293233082706766,
|
| 132 |
+
"eval_loss": 0.6086930632591248,
|
| 133 |
+
"eval_runtime": 18.4413,
|
| 134 |
+
"eval_samples_per_second": 5.423,
|
| 135 |
+
"eval_steps_per_second": 0.108,
|
| 136 |
+
"step": 64
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"learning_rate": 1.65e-06,
|
| 141 |
+
"loss": 0.5767,
|
| 142 |
+
"step": 72
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 9.0,
|
| 146 |
+
"eval_accuracy": 0.72,
|
| 147 |
+
"eval_f1": 0.7198879551820727,
|
| 148 |
+
"eval_loss": 0.6002515554428101,
|
| 149 |
+
"eval_runtime": 19.1541,
|
| 150 |
+
"eval_samples_per_second": 5.221,
|
| 151 |
+
"eval_steps_per_second": 0.104,
|
| 152 |
+
"step": 72
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 1.5e-06,
|
| 157 |
+
"loss": 0.5633,
|
| 158 |
+
"step": 80
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.0,
|
| 162 |
+
"eval_accuracy": 0.72,
|
| 163 |
+
"eval_f1": 0.7195512820512822,
|
| 164 |
+
"eval_loss": 0.5953283905982971,
|
| 165 |
+
"eval_runtime": 18.6111,
|
| 166 |
+
"eval_samples_per_second": 5.373,
|
| 167 |
+
"eval_steps_per_second": 0.107,
|
| 168 |
+
"step": 80
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 11.0,
|
| 172 |
+
"learning_rate": 1.35e-06,
|
| 173 |
+
"loss": 0.5491,
|
| 174 |
+
"step": 88
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 11.0,
|
| 178 |
+
"eval_accuracy": 0.72,
|
| 179 |
+
"eval_f1": 0.7198879551820727,
|
| 180 |
+
"eval_loss": 0.5884998440742493,
|
| 181 |
+
"eval_runtime": 19.1596,
|
| 182 |
+
"eval_samples_per_second": 5.219,
|
| 183 |
+
"eval_steps_per_second": 0.104,
|
| 184 |
+
"step": 88
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 12.0,
|
| 188 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 189 |
+
"loss": 0.5351,
|
| 190 |
+
"step": 96
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 12.0,
|
| 194 |
+
"eval_accuracy": 0.71,
|
| 195 |
+
"eval_f1": 0.7099709970997101,
|
| 196 |
+
"eval_loss": 0.5868653655052185,
|
| 197 |
+
"eval_runtime": 19.9846,
|
| 198 |
+
"eval_samples_per_second": 5.004,
|
| 199 |
+
"eval_steps_per_second": 0.1,
|
| 200 |
+
"step": 96
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 13.0,
|
| 204 |
+
"learning_rate": 1.05e-06,
|
| 205 |
+
"loss": 0.5239,
|
| 206 |
+
"step": 104
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 13.0,
|
| 210 |
+
"eval_accuracy": 0.7,
|
| 211 |
+
"eval_f1": 0.6995192307692307,
|
| 212 |
+
"eval_loss": 0.5866873264312744,
|
| 213 |
+
"eval_runtime": 18.0538,
|
| 214 |
+
"eval_samples_per_second": 5.539,
|
| 215 |
+
"eval_steps_per_second": 0.111,
|
| 216 |
+
"step": 104
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 14.0,
|
| 220 |
+
"learning_rate": 9e-07,
|
| 221 |
+
"loss": 0.5118,
|
| 222 |
+
"step": 112
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 14.0,
|
| 226 |
+
"eval_accuracy": 0.71,
|
| 227 |
+
"eval_f1": 0.7099709970997101,
|
| 228 |
+
"eval_loss": 0.5804287195205688,
|
| 229 |
+
"eval_runtime": 13.1833,
|
| 230 |
+
"eval_samples_per_second": 7.585,
|
| 231 |
+
"eval_steps_per_second": 0.152,
|
| 232 |
+
"step": 112
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 15.0,
|
| 236 |
+
"learning_rate": 7.5e-07,
|
| 237 |
+
"loss": 0.502,
|
| 238 |
+
"step": 120
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 15.0,
|
| 242 |
+
"eval_accuracy": 0.71,
|
| 243 |
+
"eval_f1": 0.7099709970997101,
|
| 244 |
+
"eval_loss": 0.5751881003379822,
|
| 245 |
+
"eval_runtime": 14.0771,
|
| 246 |
+
"eval_samples_per_second": 7.104,
|
| 247 |
+
"eval_steps_per_second": 0.142,
|
| 248 |
+
"step": 120
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.0,
|
| 252 |
+
"learning_rate": 6.000000000000001e-07,
|
| 253 |
+
"loss": 0.4942,
|
| 254 |
+
"step": 128
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 16.0,
|
| 258 |
+
"eval_accuracy": 0.72,
|
| 259 |
+
"eval_f1": 0.7198879551820727,
|
| 260 |
+
"eval_loss": 0.5737959742546082,
|
| 261 |
+
"eval_runtime": 9.472,
|
| 262 |
+
"eval_samples_per_second": 10.557,
|
| 263 |
+
"eval_steps_per_second": 0.211,
|
| 264 |
+
"step": 128
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 17.0,
|
| 268 |
+
"learning_rate": 4.5e-07,
|
| 269 |
+
"loss": 0.4885,
|
| 270 |
+
"step": 136
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 17.0,
|
| 274 |
+
"eval_accuracy": 0.71,
|
| 275 |
+
"eval_f1": 0.7085720028137876,
|
| 276 |
+
"eval_loss": 0.5770530104637146,
|
| 277 |
+
"eval_runtime": 12.9019,
|
| 278 |
+
"eval_samples_per_second": 7.751,
|
| 279 |
+
"eval_steps_per_second": 0.155,
|
| 280 |
+
"step": 136
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 18.0,
|
| 284 |
+
"learning_rate": 3.0000000000000004e-07,
|
| 285 |
+
"loss": 0.4831,
|
| 286 |
+
"step": 144
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 18.0,
|
| 290 |
+
"eval_accuracy": 0.71,
|
| 291 |
+
"eval_f1": 0.7085720028137876,
|
| 292 |
+
"eval_loss": 0.5750694870948792,
|
| 293 |
+
"eval_runtime": 10.5808,
|
| 294 |
+
"eval_samples_per_second": 9.451,
|
| 295 |
+
"eval_steps_per_second": 0.189,
|
| 296 |
+
"step": 144
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 19.0,
|
| 300 |
+
"learning_rate": 1.5000000000000002e-07,
|
| 301 |
+
"loss": 0.4793,
|
| 302 |
+
"step": 152
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 19.0,
|
| 306 |
+
"eval_accuracy": 0.71,
|
| 307 |
+
"eval_f1": 0.7085720028137876,
|
| 308 |
+
"eval_loss": 0.5742676258087158,
|
| 309 |
+
"eval_runtime": 12.6314,
|
| 310 |
+
"eval_samples_per_second": 7.917,
|
| 311 |
+
"eval_steps_per_second": 0.158,
|
| 312 |
+
"step": 152
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 20.0,
|
| 316 |
+
"learning_rate": 0.0,
|
| 317 |
+
"loss": 0.4774,
|
| 318 |
+
"step": 160
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 20.0,
|
| 322 |
+
"eval_accuracy": 0.71,
|
| 323 |
+
"eval_f1": 0.7085720028137876,
|
| 324 |
+
"eval_loss": 0.5737453699111938,
|
| 325 |
+
"eval_runtime": 16.6943,
|
| 326 |
+
"eval_samples_per_second": 5.99,
|
| 327 |
+
"eval_steps_per_second": 0.12,
|
| 328 |
+
"step": 160
|
| 329 |
+
}
|
| 330 |
+
],
|
| 331 |
+
"max_steps": 160,
|
| 332 |
+
"num_train_epochs": 20,
|
| 333 |
+
"total_flos": 6.19935916916736e+17,
|
| 334 |
+
"trial_name": null,
|
| 335 |
+
"trial_params": null
|
| 336 |
+
}
|
checkpoint-160/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1420de36bba2c0538d4308eae1ef87ce2407627c3abf540ae0d76c7a96dae807
|
| 3 |
+
size 3963
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.71,
|
| 4 |
+
"eval_f1": 0.7085720028137876,
|
| 5 |
+
"eval_loss": 0.5737453699111938,
|
| 6 |
+
"eval_runtime": 16.7507,
|
| 7 |
+
"eval_samples_per_second": 5.97,
|
| 8 |
+
"eval_steps_per_second": 0.119
|
| 9 |
+
}
|
runs/Aug01_13-59-41_43191bdd660e/events.out.tfevents.1690898382.43191bdd660e.478503.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44811497470f8dc97c76a15a2cf5d4e4d04fdb5a96469ae2f2fa957206803bca
|
| 3 |
+
size 14746
|
runs/Aug01_13-59-41_43191bdd660e/events.out.tfevents.1690903587.43191bdd660e.478503.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c8197085b82baf1d3cb570b16c5a5dcecee741aa46e6564a66abff93e6fc1d4
|
| 3 |
+
size 457
|