Upload folder using huggingface_hub
Browse files- checkpoint-4230/config.json +58 -0
- checkpoint-4230/model.safetensors +3 -0
- checkpoint-4230/optimizer.pt +3 -0
- checkpoint-4230/preprocessor_config.json +23 -0
- checkpoint-4230/rng_state.pth +3 -0
- checkpoint-4230/scheduler.pt +3 -0
- checkpoint-4230/trainer_state.json +389 -0
- checkpoint-4230/training_args.bin +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-4230/config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Blazer",
|
| 13 |
+
"1": "Coat",
|
| 14 |
+
"2": "Denim Jacket",
|
| 15 |
+
"3": "Dresses",
|
| 16 |
+
"4": "Hoodie",
|
| 17 |
+
"5": "Jacket",
|
| 18 |
+
"6": "Jeans",
|
| 19 |
+
"7": "Long Pants",
|
| 20 |
+
"8": "Polo",
|
| 21 |
+
"9": "Shirt",
|
| 22 |
+
"10": "Shorts",
|
| 23 |
+
"11": "Skirt",
|
| 24 |
+
"12": "Sports Jacket",
|
| 25 |
+
"13": "Sweater",
|
| 26 |
+
"14": "T-shirt"
|
| 27 |
+
},
|
| 28 |
+
"image_size": 224,
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"Blazer": 0,
|
| 33 |
+
"Coat": 1,
|
| 34 |
+
"Denim Jacket": 2,
|
| 35 |
+
"Dresses": 3,
|
| 36 |
+
"Hoodie": 4,
|
| 37 |
+
"Jacket": 5,
|
| 38 |
+
"Jeans": 6,
|
| 39 |
+
"Long Pants": 7,
|
| 40 |
+
"Polo": 8,
|
| 41 |
+
"Shirt": 9,
|
| 42 |
+
"Shorts": 10,
|
| 43 |
+
"Skirt": 11,
|
| 44 |
+
"Sports Jacket": 12,
|
| 45 |
+
"Sweater": 13,
|
| 46 |
+
"T-shirt": 14
|
| 47 |
+
},
|
| 48 |
+
"layer_norm_eps": 1e-12,
|
| 49 |
+
"model_type": "vit",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_channels": 3,
|
| 52 |
+
"num_hidden_layers": 12,
|
| 53 |
+
"patch_size": 16,
|
| 54 |
+
"problem_type": "single_label_classification",
|
| 55 |
+
"qkv_bias": true,
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.48.3"
|
| 58 |
+
}
|
checkpoint-4230/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23a080e7e8acf4c1d4e7f178e05dbec278d9a1156545ebd583c53dcfcf2495d1
|
| 3 |
+
size 343263964
|
checkpoint-4230/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff59a8600ca155cb1bbfe7a4846a08ebcbb5a84840aaaab7915910ee37770085
|
| 3 |
+
size 686648762
|
checkpoint-4230/preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-4230/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0473c83597605b4d7f3bd4a45b4b7be9945f3aa5f4d9b4adc9bd6cf9bdc3749f
|
| 3 |
+
size 14244
|
checkpoint-4230/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f179d87a714db15290527477f9cbdef82e1b1a97770ab6c3e413991c9939ad59
|
| 3 |
+
size 1064
|
checkpoint-4230/trainer_state.json
ADDED
|
@@ -0,0 +1,389 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.43010413646698,
|
| 3 |
+
"best_model_checkpoint": "clothes_image_detection/checkpoint-4230",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4230,
|
| 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": 0.21566666666666667,
|
| 14 |
+
"eval_loss": 2.645193338394165,
|
| 15 |
+
"eval_model_preparation_time": 0.0034,
|
| 16 |
+
"eval_runtime": 60.5917,
|
| 17 |
+
"eval_samples_per_second": 49.512,
|
| 18 |
+
"eval_steps_per_second": 6.189,
|
| 19 |
+
"step": 141
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_accuracy": 0.38333333333333336,
|
| 24 |
+
"eval_loss": 2.5685439109802246,
|
| 25 |
+
"eval_model_preparation_time": 0.0034,
|
| 26 |
+
"eval_runtime": 59.8482,
|
| 27 |
+
"eval_samples_per_second": 50.127,
|
| 28 |
+
"eval_steps_per_second": 6.266,
|
| 29 |
+
"step": 282
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 3.0,
|
| 33 |
+
"eval_accuracy": 0.5196666666666667,
|
| 34 |
+
"eval_loss": 2.4840424060821533,
|
| 35 |
+
"eval_model_preparation_time": 0.0034,
|
| 36 |
+
"eval_runtime": 56.8548,
|
| 37 |
+
"eval_samples_per_second": 52.766,
|
| 38 |
+
"eval_steps_per_second": 6.596,
|
| 39 |
+
"step": 423
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.546099290780142,
|
| 43 |
+
"grad_norm": 1.593246579170227,
|
| 44 |
+
"learning_rate": 2.6770334928229665e-06,
|
| 45 |
+
"loss": 2.5827,
|
| 46 |
+
"step": 500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 4.0,
|
| 50 |
+
"eval_accuracy": 0.594,
|
| 51 |
+
"eval_loss": 2.3924148082733154,
|
| 52 |
+
"eval_model_preparation_time": 0.0034,
|
| 53 |
+
"eval_runtime": 59.5738,
|
| 54 |
+
"eval_samples_per_second": 50.358,
|
| 55 |
+
"eval_steps_per_second": 6.295,
|
| 56 |
+
"step": 564
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 5.0,
|
| 60 |
+
"eval_accuracy": 0.637,
|
| 61 |
+
"eval_loss": 2.2984158992767334,
|
| 62 |
+
"eval_model_preparation_time": 0.0034,
|
| 63 |
+
"eval_runtime": 59.8179,
|
| 64 |
+
"eval_samples_per_second": 50.152,
|
| 65 |
+
"eval_steps_per_second": 6.269,
|
| 66 |
+
"step": 705
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 6.0,
|
| 70 |
+
"eval_accuracy": 0.6786666666666666,
|
| 71 |
+
"eval_loss": 2.204831123352051,
|
| 72 |
+
"eval_model_preparation_time": 0.0034,
|
| 73 |
+
"eval_runtime": 59.5967,
|
| 74 |
+
"eval_samples_per_second": 50.338,
|
| 75 |
+
"eval_steps_per_second": 6.292,
|
| 76 |
+
"step": 846
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 7.0,
|
| 80 |
+
"eval_accuracy": 0.7026666666666667,
|
| 81 |
+
"eval_loss": 2.114955186843872,
|
| 82 |
+
"eval_model_preparation_time": 0.0034,
|
| 83 |
+
"eval_runtime": 58.0933,
|
| 84 |
+
"eval_samples_per_second": 51.641,
|
| 85 |
+
"eval_steps_per_second": 6.455,
|
| 86 |
+
"step": 987
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 7.092198581560283,
|
| 90 |
+
"grad_norm": 1.663735032081604,
|
| 91 |
+
"learning_rate": 2.318181818181818e-06,
|
| 92 |
+
"loss": 2.2373,
|
| 93 |
+
"step": 1000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.0,
|
| 97 |
+
"eval_accuracy": 0.7193333333333334,
|
| 98 |
+
"eval_loss": 2.0335097312927246,
|
| 99 |
+
"eval_model_preparation_time": 0.0034,
|
| 100 |
+
"eval_runtime": 58.4613,
|
| 101 |
+
"eval_samples_per_second": 51.316,
|
| 102 |
+
"eval_steps_per_second": 6.414,
|
| 103 |
+
"step": 1128
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 9.0,
|
| 107 |
+
"eval_accuracy": 0.732,
|
| 108 |
+
"eval_loss": 1.9591959714889526,
|
| 109 |
+
"eval_model_preparation_time": 0.0034,
|
| 110 |
+
"eval_runtime": 60.8155,
|
| 111 |
+
"eval_samples_per_second": 49.33,
|
| 112 |
+
"eval_steps_per_second": 6.166,
|
| 113 |
+
"step": 1269
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 10.0,
|
| 117 |
+
"eval_accuracy": 0.7413333333333333,
|
| 118 |
+
"eval_loss": 1.8956468105316162,
|
| 119 |
+
"eval_model_preparation_time": 0.0034,
|
| 120 |
+
"eval_runtime": 58.6099,
|
| 121 |
+
"eval_samples_per_second": 51.186,
|
| 122 |
+
"eval_steps_per_second": 6.398,
|
| 123 |
+
"step": 1410
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 10.638297872340425,
|
| 127 |
+
"grad_norm": 2.2240982055664062,
|
| 128 |
+
"learning_rate": 1.95933014354067e-06,
|
| 129 |
+
"loss": 1.9201,
|
| 130 |
+
"step": 1500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 11.0,
|
| 134 |
+
"eval_accuracy": 0.7506666666666667,
|
| 135 |
+
"eval_loss": 1.8356391191482544,
|
| 136 |
+
"eval_model_preparation_time": 0.0034,
|
| 137 |
+
"eval_runtime": 61.3536,
|
| 138 |
+
"eval_samples_per_second": 48.897,
|
| 139 |
+
"eval_steps_per_second": 6.112,
|
| 140 |
+
"step": 1551
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 12.0,
|
| 144 |
+
"eval_accuracy": 0.7506666666666667,
|
| 145 |
+
"eval_loss": 1.7848457098007202,
|
| 146 |
+
"eval_model_preparation_time": 0.0034,
|
| 147 |
+
"eval_runtime": 59.2943,
|
| 148 |
+
"eval_samples_per_second": 50.595,
|
| 149 |
+
"eval_steps_per_second": 6.324,
|
| 150 |
+
"step": 1692
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 13.0,
|
| 154 |
+
"eval_accuracy": 0.764,
|
| 155 |
+
"eval_loss": 1.736997365951538,
|
| 156 |
+
"eval_model_preparation_time": 0.0034,
|
| 157 |
+
"eval_runtime": 58.9962,
|
| 158 |
+
"eval_samples_per_second": 50.851,
|
| 159 |
+
"eval_steps_per_second": 6.356,
|
| 160 |
+
"step": 1833
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 14.0,
|
| 164 |
+
"eval_accuracy": 0.7626666666666667,
|
| 165 |
+
"eval_loss": 1.6969176530838013,
|
| 166 |
+
"eval_model_preparation_time": 0.0034,
|
| 167 |
+
"eval_runtime": 59.8754,
|
| 168 |
+
"eval_samples_per_second": 50.104,
|
| 169 |
+
"eval_steps_per_second": 6.263,
|
| 170 |
+
"step": 1974
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 14.184397163120567,
|
| 174 |
+
"grad_norm": 2.2442896366119385,
|
| 175 |
+
"learning_rate": 1.6004784688995215e-06,
|
| 176 |
+
"loss": 1.7006,
|
| 177 |
+
"step": 2000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 15.0,
|
| 181 |
+
"eval_accuracy": 0.768,
|
| 182 |
+
"eval_loss": 1.6571820974349976,
|
| 183 |
+
"eval_model_preparation_time": 0.0034,
|
| 184 |
+
"eval_runtime": 58.7702,
|
| 185 |
+
"eval_samples_per_second": 51.046,
|
| 186 |
+
"eval_steps_per_second": 6.381,
|
| 187 |
+
"step": 2115
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 16.0,
|
| 191 |
+
"eval_accuracy": 0.7653333333333333,
|
| 192 |
+
"eval_loss": 1.6255625486373901,
|
| 193 |
+
"eval_model_preparation_time": 0.0034,
|
| 194 |
+
"eval_runtime": 59.8291,
|
| 195 |
+
"eval_samples_per_second": 50.143,
|
| 196 |
+
"eval_steps_per_second": 6.268,
|
| 197 |
+
"step": 2256
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 17.0,
|
| 201 |
+
"eval_accuracy": 0.771,
|
| 202 |
+
"eval_loss": 1.5948454141616821,
|
| 203 |
+
"eval_model_preparation_time": 0.0034,
|
| 204 |
+
"eval_runtime": 56.7649,
|
| 205 |
+
"eval_samples_per_second": 52.85,
|
| 206 |
+
"eval_steps_per_second": 6.606,
|
| 207 |
+
"step": 2397
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 17.73049645390071,
|
| 211 |
+
"grad_norm": 2.0100739002227783,
|
| 212 |
+
"learning_rate": 1.2416267942583733e-06,
|
| 213 |
+
"loss": 1.5525,
|
| 214 |
+
"step": 2500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 18.0,
|
| 218 |
+
"eval_accuracy": 0.7736666666666666,
|
| 219 |
+
"eval_loss": 1.5684410333633423,
|
| 220 |
+
"eval_model_preparation_time": 0.0034,
|
| 221 |
+
"eval_runtime": 59.7778,
|
| 222 |
+
"eval_samples_per_second": 50.186,
|
| 223 |
+
"eval_steps_per_second": 6.273,
|
| 224 |
+
"step": 2538
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 19.0,
|
| 228 |
+
"eval_accuracy": 0.7746666666666666,
|
| 229 |
+
"eval_loss": 1.5451995134353638,
|
| 230 |
+
"eval_model_preparation_time": 0.0034,
|
| 231 |
+
"eval_runtime": 56.7165,
|
| 232 |
+
"eval_samples_per_second": 52.895,
|
| 233 |
+
"eval_steps_per_second": 6.612,
|
| 234 |
+
"step": 2679
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 20.0,
|
| 238 |
+
"eval_accuracy": 0.776,
|
| 239 |
+
"eval_loss": 1.5241280794143677,
|
| 240 |
+
"eval_model_preparation_time": 0.0034,
|
| 241 |
+
"eval_runtime": 59.6632,
|
| 242 |
+
"eval_samples_per_second": 50.282,
|
| 243 |
+
"eval_steps_per_second": 6.285,
|
| 244 |
+
"step": 2820
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 21.0,
|
| 248 |
+
"eval_accuracy": 0.778,
|
| 249 |
+
"eval_loss": 1.5055561065673828,
|
| 250 |
+
"eval_model_preparation_time": 0.0034,
|
| 251 |
+
"eval_runtime": 61.0991,
|
| 252 |
+
"eval_samples_per_second": 49.101,
|
| 253 |
+
"eval_steps_per_second": 6.138,
|
| 254 |
+
"step": 2961
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 21.27659574468085,
|
| 258 |
+
"grad_norm": 2.603900194168091,
|
| 259 |
+
"learning_rate": 8.827751196172249e-07,
|
| 260 |
+
"loss": 1.4511,
|
| 261 |
+
"step": 3000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 22.0,
|
| 265 |
+
"eval_accuracy": 0.7773333333333333,
|
| 266 |
+
"eval_loss": 1.4899275302886963,
|
| 267 |
+
"eval_model_preparation_time": 0.0034,
|
| 268 |
+
"eval_runtime": 60.2357,
|
| 269 |
+
"eval_samples_per_second": 49.804,
|
| 270 |
+
"eval_steps_per_second": 6.226,
|
| 271 |
+
"step": 3102
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 23.0,
|
| 275 |
+
"eval_accuracy": 0.779,
|
| 276 |
+
"eval_loss": 1.4755609035491943,
|
| 277 |
+
"eval_model_preparation_time": 0.0034,
|
| 278 |
+
"eval_runtime": 58.2979,
|
| 279 |
+
"eval_samples_per_second": 51.46,
|
| 280 |
+
"eval_steps_per_second": 6.432,
|
| 281 |
+
"step": 3243
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 24.0,
|
| 285 |
+
"eval_accuracy": 0.7796666666666666,
|
| 286 |
+
"eval_loss": 1.4629756212234497,
|
| 287 |
+
"eval_model_preparation_time": 0.0034,
|
| 288 |
+
"eval_runtime": 59.4982,
|
| 289 |
+
"eval_samples_per_second": 50.422,
|
| 290 |
+
"eval_steps_per_second": 6.303,
|
| 291 |
+
"step": 3384
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 24.822695035460992,
|
| 295 |
+
"grad_norm": 2.867500066757202,
|
| 296 |
+
"learning_rate": 5.239234449760765e-07,
|
| 297 |
+
"loss": 1.3856,
|
| 298 |
+
"step": 3500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 25.0,
|
| 302 |
+
"eval_accuracy": 0.7803333333333333,
|
| 303 |
+
"eval_loss": 1.452785849571228,
|
| 304 |
+
"eval_model_preparation_time": 0.0034,
|
| 305 |
+
"eval_runtime": 61.5325,
|
| 306 |
+
"eval_samples_per_second": 48.755,
|
| 307 |
+
"eval_steps_per_second": 6.094,
|
| 308 |
+
"step": 3525
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 26.0,
|
| 312 |
+
"eval_accuracy": 0.783,
|
| 313 |
+
"eval_loss": 1.4447195529937744,
|
| 314 |
+
"eval_model_preparation_time": 0.0034,
|
| 315 |
+
"eval_runtime": 59.5703,
|
| 316 |
+
"eval_samples_per_second": 50.361,
|
| 317 |
+
"eval_steps_per_second": 6.295,
|
| 318 |
+
"step": 3666
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 27.0,
|
| 322 |
+
"eval_accuracy": 0.7823333333333333,
|
| 323 |
+
"eval_loss": 1.438262701034546,
|
| 324 |
+
"eval_model_preparation_time": 0.0034,
|
| 325 |
+
"eval_runtime": 60.0356,
|
| 326 |
+
"eval_samples_per_second": 49.97,
|
| 327 |
+
"eval_steps_per_second": 6.246,
|
| 328 |
+
"step": 3807
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 28.0,
|
| 332 |
+
"eval_accuracy": 0.783,
|
| 333 |
+
"eval_loss": 1.4334560632705688,
|
| 334 |
+
"eval_model_preparation_time": 0.0034,
|
| 335 |
+
"eval_runtime": 60.0215,
|
| 336 |
+
"eval_samples_per_second": 49.982,
|
| 337 |
+
"eval_steps_per_second": 6.248,
|
| 338 |
+
"step": 3948
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 28.368794326241133,
|
| 342 |
+
"grad_norm": 3.527007579803467,
|
| 343 |
+
"learning_rate": 1.6507177033492823e-07,
|
| 344 |
+
"loss": 1.3468,
|
| 345 |
+
"step": 4000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 29.0,
|
| 349 |
+
"eval_accuracy": 0.784,
|
| 350 |
+
"eval_loss": 1.4309223890304565,
|
| 351 |
+
"eval_model_preparation_time": 0.0034,
|
| 352 |
+
"eval_runtime": 57.775,
|
| 353 |
+
"eval_samples_per_second": 51.926,
|
| 354 |
+
"eval_steps_per_second": 6.491,
|
| 355 |
+
"step": 4089
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 30.0,
|
| 359 |
+
"eval_accuracy": 0.7846666666666666,
|
| 360 |
+
"eval_loss": 1.43010413646698,
|
| 361 |
+
"eval_model_preparation_time": 0.0034,
|
| 362 |
+
"eval_runtime": 60.9928,
|
| 363 |
+
"eval_samples_per_second": 49.186,
|
| 364 |
+
"eval_steps_per_second": 6.148,
|
| 365 |
+
"step": 4230
|
| 366 |
+
}
|
| 367 |
+
],
|
| 368 |
+
"logging_steps": 500,
|
| 369 |
+
"max_steps": 4230,
|
| 370 |
+
"num_input_tokens_seen": 0,
|
| 371 |
+
"num_train_epochs": 30,
|
| 372 |
+
"save_steps": 500,
|
| 373 |
+
"stateful_callbacks": {
|
| 374 |
+
"TrainerControl": {
|
| 375 |
+
"args": {
|
| 376 |
+
"should_epoch_stop": false,
|
| 377 |
+
"should_evaluate": false,
|
| 378 |
+
"should_log": false,
|
| 379 |
+
"should_save": true,
|
| 380 |
+
"should_training_stop": true
|
| 381 |
+
},
|
| 382 |
+
"attributes": {}
|
| 383 |
+
}
|
| 384 |
+
},
|
| 385 |
+
"total_flos": 1.046263750898688e+19,
|
| 386 |
+
"train_batch_size": 32,
|
| 387 |
+
"trial_name": null,
|
| 388 |
+
"trial_params": null
|
| 389 |
+
}
|
checkpoint-4230/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:348a7626fa4c360c7b86e7c9aaa401da6136daa29e45038dc6ab9fa90da3c856
|
| 3 |
+
size 5304
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343263964
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23a080e7e8acf4c1d4e7f178e05dbec278d9a1156545ebd583c53dcfcf2495d1
|
| 3 |
size 343263964
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:348a7626fa4c360c7b86e7c9aaa401da6136daa29e45038dc6ab9fa90da3c856
|
| 3 |
size 5304
|