Upload folder using huggingface_hub
Browse files- checkpoint-5640/config.json +32 -0
- checkpoint-5640/model.safetensors +3 -0
- checkpoint-5640/optimizer.pt +3 -0
- checkpoint-5640/preprocessor_config.json +22 -0
- checkpoint-5640/rng_state.pth +3 -0
- checkpoint-5640/scheduler.pt +3 -0
- checkpoint-5640/trainer_state.json +410 -0
- checkpoint-5640/training_args.bin +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-5640/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "AI-Generated Images",
|
| 13 |
+
"1": "Real Images"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"AI-Generated Images": 0,
|
| 20 |
+
"Real Images": 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": "4.44.2"
|
| 32 |
+
}
|
checkpoint-5640/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cc2ba85a57a120dc6bc4c3e89b971906ad05c24f53da867125ffef3204b3e04
|
| 3 |
+
size 343223968
|
checkpoint-5640/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f159b94f7160c738b5f09c603bb31a286c435ad2816af73bd01326a21e946f9e
|
| 3 |
+
size 686568890
|
checkpoint-5640/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-5640/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8199a5eafcbaf3d2c542539947ec9d31a260e7bea63cc11fd637ed4208f518da
|
| 3 |
+
size 14244
|
checkpoint-5640/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21270894a258c70a05d5683e8af3e2e5d4eb10f39c9d620b8cb4db90ad79b66d
|
| 3 |
+
size 1064
|
checkpoint-5640/trainer_state.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.020942676812410355,
|
| 3 |
+
"best_model_checkpoint": "human_faces_ai_vs_real_image_detection/checkpoint-5640",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5640,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.7825,
|
| 14 |
+
"eval_loss": 0.5565322041511536,
|
| 15 |
+
"eval_model_preparation_time": 0.0052,
|
| 16 |
+
"eval_runtime": 39.5027,
|
| 17 |
+
"eval_samples_per_second": 101.259,
|
| 18 |
+
"eval_steps_per_second": 12.657,
|
| 19 |
+
"step": 188
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_accuracy": 0.986,
|
| 24 |
+
"eval_loss": 0.4245019555091858,
|
| 25 |
+
"eval_model_preparation_time": 0.0052,
|
| 26 |
+
"eval_runtime": 38.9508,
|
| 27 |
+
"eval_samples_per_second": 102.694,
|
| 28 |
+
"eval_steps_per_second": 12.837,
|
| 29 |
+
"step": 376
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.6595744680851063,
|
| 33 |
+
"grad_norm": 1.0198960304260254,
|
| 34 |
+
"learning_rate": 6.43649373881932e-07,
|
| 35 |
+
"loss": 0.473,
|
| 36 |
+
"step": 500
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"eval_accuracy": 0.9995,
|
| 41 |
+
"eval_loss": 0.28928709030151367,
|
| 42 |
+
"eval_model_preparation_time": 0.0052,
|
| 43 |
+
"eval_runtime": 38.6783,
|
| 44 |
+
"eval_samples_per_second": 103.417,
|
| 45 |
+
"eval_steps_per_second": 12.927,
|
| 46 |
+
"step": 564
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 4.0,
|
| 50 |
+
"eval_accuracy": 1.0,
|
| 51 |
+
"eval_loss": 0.19994351267814636,
|
| 52 |
+
"eval_model_preparation_time": 0.0052,
|
| 53 |
+
"eval_runtime": 39.0111,
|
| 54 |
+
"eval_samples_per_second": 102.535,
|
| 55 |
+
"eval_steps_per_second": 12.817,
|
| 56 |
+
"step": 752
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 5.0,
|
| 60 |
+
"eval_accuracy": 1.0,
|
| 61 |
+
"eval_loss": 0.1481410264968872,
|
| 62 |
+
"eval_model_preparation_time": 0.0052,
|
| 63 |
+
"eval_runtime": 39.2806,
|
| 64 |
+
"eval_samples_per_second": 101.831,
|
| 65 |
+
"eval_steps_per_second": 12.729,
|
| 66 |
+
"step": 940
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.319148936170213,
|
| 70 |
+
"grad_norm": 0.4813893139362335,
|
| 71 |
+
"learning_rate": 5.810375670840786e-07,
|
| 72 |
+
"loss": 0.1329,
|
| 73 |
+
"step": 1000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 6.0,
|
| 77 |
+
"eval_accuracy": 1.0,
|
| 78 |
+
"eval_loss": 0.11500898748636246,
|
| 79 |
+
"eval_model_preparation_time": 0.0052,
|
| 80 |
+
"eval_runtime": 38.6021,
|
| 81 |
+
"eval_samples_per_second": 103.621,
|
| 82 |
+
"eval_steps_per_second": 12.953,
|
| 83 |
+
"step": 1128
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 7.0,
|
| 87 |
+
"eval_accuracy": 1.0,
|
| 88 |
+
"eval_loss": 0.09291090071201324,
|
| 89 |
+
"eval_model_preparation_time": 0.0052,
|
| 90 |
+
"eval_runtime": 39.1028,
|
| 91 |
+
"eval_samples_per_second": 102.295,
|
| 92 |
+
"eval_steps_per_second": 12.787,
|
| 93 |
+
"step": 1316
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.9787234042553195,
|
| 97 |
+
"grad_norm": 0.3040165603160858,
|
| 98 |
+
"learning_rate": 5.184257602862254e-07,
|
| 99 |
+
"loss": 0.0572,
|
| 100 |
+
"step": 1500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 8.0,
|
| 104 |
+
"eval_accuracy": 1.0,
|
| 105 |
+
"eval_loss": 0.0777982771396637,
|
| 106 |
+
"eval_model_preparation_time": 0.0052,
|
| 107 |
+
"eval_runtime": 38.3545,
|
| 108 |
+
"eval_samples_per_second": 104.29,
|
| 109 |
+
"eval_steps_per_second": 13.036,
|
| 110 |
+
"step": 1504
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 9.0,
|
| 114 |
+
"eval_accuracy": 1.0,
|
| 115 |
+
"eval_loss": 0.06646119803190231,
|
| 116 |
+
"eval_model_preparation_time": 0.0052,
|
| 117 |
+
"eval_runtime": 39.2736,
|
| 118 |
+
"eval_samples_per_second": 101.85,
|
| 119 |
+
"eval_steps_per_second": 12.731,
|
| 120 |
+
"step": 1692
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 10.0,
|
| 124 |
+
"eval_accuracy": 1.0,
|
| 125 |
+
"eval_loss": 0.057849109172821045,
|
| 126 |
+
"eval_model_preparation_time": 0.0052,
|
| 127 |
+
"eval_runtime": 38.344,
|
| 128 |
+
"eval_samples_per_second": 104.319,
|
| 129 |
+
"eval_steps_per_second": 13.04,
|
| 130 |
+
"step": 1880
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 10.638297872340425,
|
| 134 |
+
"grad_norm": 0.2159370332956314,
|
| 135 |
+
"learning_rate": 4.558139534883721e-07,
|
| 136 |
+
"loss": 0.0363,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 11.0,
|
| 141 |
+
"eval_accuracy": 1.0,
|
| 142 |
+
"eval_loss": 0.051288772374391556,
|
| 143 |
+
"eval_model_preparation_time": 0.0052,
|
| 144 |
+
"eval_runtime": 38.851,
|
| 145 |
+
"eval_samples_per_second": 102.957,
|
| 146 |
+
"eval_steps_per_second": 12.87,
|
| 147 |
+
"step": 2068
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 12.0,
|
| 151 |
+
"eval_accuracy": 1.0,
|
| 152 |
+
"eval_loss": 0.0460113026201725,
|
| 153 |
+
"eval_model_preparation_time": 0.0052,
|
| 154 |
+
"eval_runtime": 39.5997,
|
| 155 |
+
"eval_samples_per_second": 101.011,
|
| 156 |
+
"eval_steps_per_second": 12.626,
|
| 157 |
+
"step": 2256
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 13.0,
|
| 161 |
+
"eval_accuracy": 1.0,
|
| 162 |
+
"eval_loss": 0.041803594678640366,
|
| 163 |
+
"eval_model_preparation_time": 0.0052,
|
| 164 |
+
"eval_runtime": 39.1227,
|
| 165 |
+
"eval_samples_per_second": 102.243,
|
| 166 |
+
"eval_steps_per_second": 12.78,
|
| 167 |
+
"step": 2444
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 13.297872340425531,
|
| 171 |
+
"grad_norm": 0.17549511790275574,
|
| 172 |
+
"learning_rate": 3.932021466905188e-07,
|
| 173 |
+
"loss": 0.0273,
|
| 174 |
+
"step": 2500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 14.0,
|
| 178 |
+
"eval_accuracy": 1.0,
|
| 179 |
+
"eval_loss": 0.038368262350559235,
|
| 180 |
+
"eval_model_preparation_time": 0.0052,
|
| 181 |
+
"eval_runtime": 39.6857,
|
| 182 |
+
"eval_samples_per_second": 100.792,
|
| 183 |
+
"eval_steps_per_second": 12.599,
|
| 184 |
+
"step": 2632
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 15.0,
|
| 188 |
+
"eval_accuracy": 1.0,
|
| 189 |
+
"eval_loss": 0.035478074103593826,
|
| 190 |
+
"eval_model_preparation_time": 0.0052,
|
| 191 |
+
"eval_runtime": 38.8297,
|
| 192 |
+
"eval_samples_per_second": 103.014,
|
| 193 |
+
"eval_steps_per_second": 12.877,
|
| 194 |
+
"step": 2820
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 15.957446808510639,
|
| 198 |
+
"grad_norm": 0.1561371237039566,
|
| 199 |
+
"learning_rate": 3.3059033989266543e-07,
|
| 200 |
+
"loss": 0.0222,
|
| 201 |
+
"step": 3000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 16.0,
|
| 205 |
+
"eval_accuracy": 1.0,
|
| 206 |
+
"eval_loss": 0.03299877420067787,
|
| 207 |
+
"eval_model_preparation_time": 0.0052,
|
| 208 |
+
"eval_runtime": 39.3201,
|
| 209 |
+
"eval_samples_per_second": 101.729,
|
| 210 |
+
"eval_steps_per_second": 12.716,
|
| 211 |
+
"step": 3008
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 17.0,
|
| 215 |
+
"eval_accuracy": 1.0,
|
| 216 |
+
"eval_loss": 0.03099164180457592,
|
| 217 |
+
"eval_model_preparation_time": 0.0052,
|
| 218 |
+
"eval_runtime": 38.815,
|
| 219 |
+
"eval_samples_per_second": 103.053,
|
| 220 |
+
"eval_steps_per_second": 12.882,
|
| 221 |
+
"step": 3196
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 18.0,
|
| 225 |
+
"eval_accuracy": 1.0,
|
| 226 |
+
"eval_loss": 0.029285429045557976,
|
| 227 |
+
"eval_model_preparation_time": 0.0052,
|
| 228 |
+
"eval_runtime": 39.0284,
|
| 229 |
+
"eval_samples_per_second": 102.49,
|
| 230 |
+
"eval_steps_per_second": 12.811,
|
| 231 |
+
"step": 3384
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 18.617021276595743,
|
| 235 |
+
"grad_norm": 0.13681600987911224,
|
| 236 |
+
"learning_rate": 2.679785330948122e-07,
|
| 237 |
+
"loss": 0.0191,
|
| 238 |
+
"step": 3500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 19.0,
|
| 242 |
+
"eval_accuracy": 1.0,
|
| 243 |
+
"eval_loss": 0.027754757553339005,
|
| 244 |
+
"eval_model_preparation_time": 0.0052,
|
| 245 |
+
"eval_runtime": 39.0357,
|
| 246 |
+
"eval_samples_per_second": 102.47,
|
| 247 |
+
"eval_steps_per_second": 12.809,
|
| 248 |
+
"step": 3572
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 20.0,
|
| 252 |
+
"eval_accuracy": 1.0,
|
| 253 |
+
"eval_loss": 0.026402976363897324,
|
| 254 |
+
"eval_model_preparation_time": 0.0052,
|
| 255 |
+
"eval_runtime": 39.3862,
|
| 256 |
+
"eval_samples_per_second": 101.558,
|
| 257 |
+
"eval_steps_per_second": 12.695,
|
| 258 |
+
"step": 3760
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 21.0,
|
| 262 |
+
"eval_accuracy": 1.0,
|
| 263 |
+
"eval_loss": 0.02528988942503929,
|
| 264 |
+
"eval_model_preparation_time": 0.0052,
|
| 265 |
+
"eval_runtime": 39.0126,
|
| 266 |
+
"eval_samples_per_second": 102.531,
|
| 267 |
+
"eval_steps_per_second": 12.816,
|
| 268 |
+
"step": 3948
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 21.27659574468085,
|
| 272 |
+
"grad_norm": 0.12338540703058243,
|
| 273 |
+
"learning_rate": 2.0536672629695882e-07,
|
| 274 |
+
"loss": 0.017,
|
| 275 |
+
"step": 4000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 22.0,
|
| 279 |
+
"eval_accuracy": 1.0,
|
| 280 |
+
"eval_loss": 0.0243725273758173,
|
| 281 |
+
"eval_model_preparation_time": 0.0052,
|
| 282 |
+
"eval_runtime": 38.6964,
|
| 283 |
+
"eval_samples_per_second": 103.369,
|
| 284 |
+
"eval_steps_per_second": 12.921,
|
| 285 |
+
"step": 4136
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 23.0,
|
| 289 |
+
"eval_accuracy": 1.0,
|
| 290 |
+
"eval_loss": 0.023562923073768616,
|
| 291 |
+
"eval_model_preparation_time": 0.0052,
|
| 292 |
+
"eval_runtime": 38.7139,
|
| 293 |
+
"eval_samples_per_second": 103.322,
|
| 294 |
+
"eval_steps_per_second": 12.915,
|
| 295 |
+
"step": 4324
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 23.93617021276596,
|
| 299 |
+
"grad_norm": 0.11832650005817413,
|
| 300 |
+
"learning_rate": 1.4275491949910554e-07,
|
| 301 |
+
"loss": 0.0156,
|
| 302 |
+
"step": 4500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 24.0,
|
| 306 |
+
"eval_accuracy": 1.0,
|
| 307 |
+
"eval_loss": 0.02286355197429657,
|
| 308 |
+
"eval_model_preparation_time": 0.0052,
|
| 309 |
+
"eval_runtime": 39.3324,
|
| 310 |
+
"eval_samples_per_second": 101.697,
|
| 311 |
+
"eval_steps_per_second": 12.712,
|
| 312 |
+
"step": 4512
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 25.0,
|
| 316 |
+
"eval_accuracy": 1.0,
|
| 317 |
+
"eval_loss": 0.02227471023797989,
|
| 318 |
+
"eval_model_preparation_time": 0.0052,
|
| 319 |
+
"eval_runtime": 38.5625,
|
| 320 |
+
"eval_samples_per_second": 103.728,
|
| 321 |
+
"eval_steps_per_second": 12.966,
|
| 322 |
+
"step": 4700
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 26.0,
|
| 326 |
+
"eval_accuracy": 1.0,
|
| 327 |
+
"eval_loss": 0.02179701067507267,
|
| 328 |
+
"eval_model_preparation_time": 0.0052,
|
| 329 |
+
"eval_runtime": 38.9832,
|
| 330 |
+
"eval_samples_per_second": 102.608,
|
| 331 |
+
"eval_steps_per_second": 12.826,
|
| 332 |
+
"step": 4888
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 26.595744680851062,
|
| 336 |
+
"grad_norm": 0.1103362962603569,
|
| 337 |
+
"learning_rate": 8.014311270125224e-08,
|
| 338 |
+
"loss": 0.0147,
|
| 339 |
+
"step": 5000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 27.0,
|
| 343 |
+
"eval_accuracy": 1.0,
|
| 344 |
+
"eval_loss": 0.021414099261164665,
|
| 345 |
+
"eval_model_preparation_time": 0.0052,
|
| 346 |
+
"eval_runtime": 39.4394,
|
| 347 |
+
"eval_samples_per_second": 101.421,
|
| 348 |
+
"eval_steps_per_second": 12.678,
|
| 349 |
+
"step": 5076
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 28.0,
|
| 353 |
+
"eval_accuracy": 1.0,
|
| 354 |
+
"eval_loss": 0.021164603531360626,
|
| 355 |
+
"eval_model_preparation_time": 0.0052,
|
| 356 |
+
"eval_runtime": 38.8061,
|
| 357 |
+
"eval_samples_per_second": 103.077,
|
| 358 |
+
"eval_steps_per_second": 12.885,
|
| 359 |
+
"step": 5264
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 29.0,
|
| 363 |
+
"eval_accuracy": 1.0,
|
| 364 |
+
"eval_loss": 0.020994121208786964,
|
| 365 |
+
"eval_model_preparation_time": 0.0052,
|
| 366 |
+
"eval_runtime": 38.7168,
|
| 367 |
+
"eval_samples_per_second": 103.314,
|
| 368 |
+
"eval_steps_per_second": 12.914,
|
| 369 |
+
"step": 5452
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 29.25531914893617,
|
| 373 |
+
"grad_norm": 0.10874511301517487,
|
| 374 |
+
"learning_rate": 1.7531305903398928e-08,
|
| 375 |
+
"loss": 0.0142,
|
| 376 |
+
"step": 5500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 30.0,
|
| 380 |
+
"eval_accuracy": 1.0,
|
| 381 |
+
"eval_loss": 0.020942676812410355,
|
| 382 |
+
"eval_model_preparation_time": 0.0052,
|
| 383 |
+
"eval_runtime": 39.1075,
|
| 384 |
+
"eval_samples_per_second": 102.282,
|
| 385 |
+
"eval_steps_per_second": 12.785,
|
| 386 |
+
"step": 5640
|
| 387 |
+
}
|
| 388 |
+
],
|
| 389 |
+
"logging_steps": 500,
|
| 390 |
+
"max_steps": 5640,
|
| 391 |
+
"num_input_tokens_seen": 0,
|
| 392 |
+
"num_train_epochs": 30,
|
| 393 |
+
"save_steps": 500,
|
| 394 |
+
"stateful_callbacks": {
|
| 395 |
+
"TrainerControl": {
|
| 396 |
+
"args": {
|
| 397 |
+
"should_epoch_stop": false,
|
| 398 |
+
"should_evaluate": false,
|
| 399 |
+
"should_log": false,
|
| 400 |
+
"should_save": true,
|
| 401 |
+
"should_training_stop": true
|
| 402 |
+
},
|
| 403 |
+
"attributes": {}
|
| 404 |
+
}
|
| 405 |
+
},
|
| 406 |
+
"total_flos": 1.394855813062656e+19,
|
| 407 |
+
"train_batch_size": 32,
|
| 408 |
+
"trial_name": null,
|
| 409 |
+
"trial_params": null
|
| 410 |
+
}
|
checkpoint-5640/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5c3b4616b7b67f5c119bcf2d7f2802583d6056622941c1b547360115c5426f9
|
| 3 |
+
size 5176
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343223968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cc2ba85a57a120dc6bc4c3e89b971906ad05c24f53da867125ffef3204b3e04
|
| 3 |
size 343223968
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5c3b4616b7b67f5c119bcf2d7f2802583d6056622941c1b547360115c5426f9
|
| 3 |
size 5176
|