Upload folder using huggingface_hub
Browse files- checkpoint-6650/config.json +38 -0
- checkpoint-6650/model.safetensors +3 -0
- checkpoint-6650/optimizer.pt +3 -0
- checkpoint-6650/preprocessor_config.json +22 -0
- checkpoint-6650/rng_state.pth +3 -0
- checkpoint-6650/scheduler.pt +3 -0
- checkpoint-6650/trainer_state.json +547 -0
- checkpoint-6650/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
checkpoint-6650/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Cargo",
|
| 13 |
+
"1": "Carrier",
|
| 14 |
+
"2": "Cruise",
|
| 15 |
+
"3": "Military",
|
| 16 |
+
"4": "Tankers"
|
| 17 |
+
},
|
| 18 |
+
"image_size": 224,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Cargo": 0,
|
| 23 |
+
"Carrier": 1,
|
| 24 |
+
"Cruise": 2,
|
| 25 |
+
"Military": 3,
|
| 26 |
+
"Tankers": 4
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"model_type": "vit",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_channels": 3,
|
| 32 |
+
"num_hidden_layers": 12,
|
| 33 |
+
"patch_size": 16,
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"qkv_bias": true,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.35.2"
|
| 38 |
+
}
|
checkpoint-6650/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30f3155419517d01e2859d32e6e36d669af32d3c2ef16a1124c44238cc0675b0
|
| 3 |
+
size 343233204
|
checkpoint-6650/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a7e82383130a118a807f63e23d8b6bb83c5c99e68f6bdf33df1c0c002ec62bb
|
| 3 |
+
size 686586885
|
checkpoint-6650/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-6650/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1322e801e5f5af7d9a87f5bde3e3155e8375b40cbf03ee6eb7a8f82baea4777
|
| 3 |
+
size 14575
|
checkpoint-6650/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f67f6693c1d997bb5f45346c81f57492295a5c123c765feccc16054d4f2e1dad
|
| 3 |
+
size 627
|
checkpoint-6650/trainer_state.json
ADDED
|
@@ -0,0 +1,547 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.18469373881816864,
|
| 3 |
+
"best_model_checkpoint": "vessel_ship_types_image_detection/checkpoint-6650",
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6650,
|
| 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": 0.7160377358490566,
|
| 14 |
+
"eval_loss": 1.4629170894622803,
|
| 15 |
+
"eval_runtime": 18.5467,
|
| 16 |
+
"eval_samples_per_second": 114.306,
|
| 17 |
+
"eval_steps_per_second": 3.613,
|
| 18 |
+
"step": 133
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.8495283018867924,
|
| 23 |
+
"eval_loss": 1.2206131219863892,
|
| 24 |
+
"eval_runtime": 18.2977,
|
| 25 |
+
"eval_samples_per_second": 115.862,
|
| 26 |
+
"eval_steps_per_second": 3.662,
|
| 27 |
+
"step": 266
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.870754716981132,
|
| 32 |
+
"eval_loss": 1.0089887380599976,
|
| 33 |
+
"eval_runtime": 18.4043,
|
| 34 |
+
"eval_samples_per_second": 115.19,
|
| 35 |
+
"eval_steps_per_second": 3.64,
|
| 36 |
+
"step": 399
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.76,
|
| 40 |
+
"learning_rate": 1.8636363636363635e-06,
|
| 41 |
+
"loss": 1.1877,
|
| 42 |
+
"step": 500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 4.0,
|
| 46 |
+
"eval_accuracy": 0.8962264150943396,
|
| 47 |
+
"eval_loss": 0.8400751352310181,
|
| 48 |
+
"eval_runtime": 18.4514,
|
| 49 |
+
"eval_samples_per_second": 114.896,
|
| 50 |
+
"eval_steps_per_second": 3.631,
|
| 51 |
+
"step": 532
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 5.0,
|
| 55 |
+
"eval_accuracy": 0.9155660377358491,
|
| 56 |
+
"eval_loss": 0.714967668056488,
|
| 57 |
+
"eval_runtime": 18.5178,
|
| 58 |
+
"eval_samples_per_second": 114.484,
|
| 59 |
+
"eval_steps_per_second": 3.618,
|
| 60 |
+
"step": 665
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 6.0,
|
| 64 |
+
"eval_accuracy": 0.9292452830188679,
|
| 65 |
+
"eval_loss": 0.625623345375061,
|
| 66 |
+
"eval_runtime": 18.8638,
|
| 67 |
+
"eval_samples_per_second": 112.385,
|
| 68 |
+
"eval_steps_per_second": 3.552,
|
| 69 |
+
"step": 798
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 7.0,
|
| 73 |
+
"eval_accuracy": 0.9382075471698114,
|
| 74 |
+
"eval_loss": 0.556588888168335,
|
| 75 |
+
"eval_runtime": 18.4533,
|
| 76 |
+
"eval_samples_per_second": 114.885,
|
| 77 |
+
"eval_steps_per_second": 3.631,
|
| 78 |
+
"step": 931
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 7.52,
|
| 82 |
+
"learning_rate": 1.712121212121212e-06,
|
| 83 |
+
"loss": 0.5507,
|
| 84 |
+
"step": 1000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 8.0,
|
| 88 |
+
"eval_accuracy": 0.9424528301886792,
|
| 89 |
+
"eval_loss": 0.5028243064880371,
|
| 90 |
+
"eval_runtime": 18.7405,
|
| 91 |
+
"eval_samples_per_second": 113.124,
|
| 92 |
+
"eval_steps_per_second": 3.575,
|
| 93 |
+
"step": 1064
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 9.0,
|
| 97 |
+
"eval_accuracy": 0.9481132075471698,
|
| 98 |
+
"eval_loss": 0.4585725665092468,
|
| 99 |
+
"eval_runtime": 18.5812,
|
| 100 |
+
"eval_samples_per_second": 114.094,
|
| 101 |
+
"eval_steps_per_second": 3.606,
|
| 102 |
+
"step": 1197
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 10.0,
|
| 106 |
+
"eval_accuracy": 0.9495283018867925,
|
| 107 |
+
"eval_loss": 0.42831137776374817,
|
| 108 |
+
"eval_runtime": 18.6399,
|
| 109 |
+
"eval_samples_per_second": 113.734,
|
| 110 |
+
"eval_steps_per_second": 3.594,
|
| 111 |
+
"step": 1330
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 11.0,
|
| 115 |
+
"eval_accuracy": 0.9537735849056603,
|
| 116 |
+
"eval_loss": 0.398691326379776,
|
| 117 |
+
"eval_runtime": 18.7098,
|
| 118 |
+
"eval_samples_per_second": 113.309,
|
| 119 |
+
"eval_steps_per_second": 3.581,
|
| 120 |
+
"step": 1463
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 11.28,
|
| 124 |
+
"learning_rate": 1.5606060606060604e-06,
|
| 125 |
+
"loss": 0.3457,
|
| 126 |
+
"step": 1500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 12.0,
|
| 130 |
+
"eval_accuracy": 0.9556603773584905,
|
| 131 |
+
"eval_loss": 0.37774720788002014,
|
| 132 |
+
"eval_runtime": 18.6811,
|
| 133 |
+
"eval_samples_per_second": 113.484,
|
| 134 |
+
"eval_steps_per_second": 3.587,
|
| 135 |
+
"step": 1596
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 13.0,
|
| 139 |
+
"eval_accuracy": 0.9570754716981132,
|
| 140 |
+
"eval_loss": 0.35789886116981506,
|
| 141 |
+
"eval_runtime": 19.0448,
|
| 142 |
+
"eval_samples_per_second": 111.317,
|
| 143 |
+
"eval_steps_per_second": 3.518,
|
| 144 |
+
"step": 1729
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 14.0,
|
| 148 |
+
"eval_accuracy": 0.9584905660377359,
|
| 149 |
+
"eval_loss": 0.3406927287578583,
|
| 150 |
+
"eval_runtime": 18.7362,
|
| 151 |
+
"eval_samples_per_second": 113.15,
|
| 152 |
+
"eval_steps_per_second": 3.576,
|
| 153 |
+
"step": 1862
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 15.0,
|
| 157 |
+
"eval_accuracy": 0.9580188679245283,
|
| 158 |
+
"eval_loss": 0.3256920874118805,
|
| 159 |
+
"eval_runtime": 18.4691,
|
| 160 |
+
"eval_samples_per_second": 114.786,
|
| 161 |
+
"eval_steps_per_second": 3.628,
|
| 162 |
+
"step": 1995
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 15.04,
|
| 166 |
+
"learning_rate": 1.409090909090909e-06,
|
| 167 |
+
"loss": 0.2582,
|
| 168 |
+
"step": 2000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 16.0,
|
| 172 |
+
"eval_accuracy": 0.9589622641509434,
|
| 173 |
+
"eval_loss": 0.3142967224121094,
|
| 174 |
+
"eval_runtime": 18.7522,
|
| 175 |
+
"eval_samples_per_second": 113.053,
|
| 176 |
+
"eval_steps_per_second": 3.573,
|
| 177 |
+
"step": 2128
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 17.0,
|
| 181 |
+
"eval_accuracy": 0.9599056603773585,
|
| 182 |
+
"eval_loss": 0.30126336216926575,
|
| 183 |
+
"eval_runtime": 18.4133,
|
| 184 |
+
"eval_samples_per_second": 115.134,
|
| 185 |
+
"eval_steps_per_second": 3.639,
|
| 186 |
+
"step": 2261
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 18.0,
|
| 190 |
+
"eval_accuracy": 0.9627358490566038,
|
| 191 |
+
"eval_loss": 0.29247793555259705,
|
| 192 |
+
"eval_runtime": 18.4149,
|
| 193 |
+
"eval_samples_per_second": 115.124,
|
| 194 |
+
"eval_steps_per_second": 3.638,
|
| 195 |
+
"step": 2394
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 18.8,
|
| 199 |
+
"learning_rate": 1.2575757575757576e-06,
|
| 200 |
+
"loss": 0.2081,
|
| 201 |
+
"step": 2500
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 19.0,
|
| 205 |
+
"eval_accuracy": 0.9617924528301887,
|
| 206 |
+
"eval_loss": 0.2814226746559143,
|
| 207 |
+
"eval_runtime": 18.5345,
|
| 208 |
+
"eval_samples_per_second": 114.381,
|
| 209 |
+
"eval_steps_per_second": 3.615,
|
| 210 |
+
"step": 2527
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 20.0,
|
| 214 |
+
"eval_accuracy": 0.964622641509434,
|
| 215 |
+
"eval_loss": 0.27146387100219727,
|
| 216 |
+
"eval_runtime": 18.387,
|
| 217 |
+
"eval_samples_per_second": 115.299,
|
| 218 |
+
"eval_steps_per_second": 3.644,
|
| 219 |
+
"step": 2660
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 21.0,
|
| 223 |
+
"eval_accuracy": 0.9627358490566038,
|
| 224 |
+
"eval_loss": 0.26703450083732605,
|
| 225 |
+
"eval_runtime": 18.3186,
|
| 226 |
+
"eval_samples_per_second": 115.73,
|
| 227 |
+
"eval_steps_per_second": 3.657,
|
| 228 |
+
"step": 2793
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 22.0,
|
| 232 |
+
"eval_accuracy": 0.9650943396226415,
|
| 233 |
+
"eval_loss": 0.2572649121284485,
|
| 234 |
+
"eval_runtime": 18.5302,
|
| 235 |
+
"eval_samples_per_second": 114.408,
|
| 236 |
+
"eval_steps_per_second": 3.616,
|
| 237 |
+
"step": 2926
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 22.56,
|
| 241 |
+
"learning_rate": 1.106060606060606e-06,
|
| 242 |
+
"loss": 0.1768,
|
| 243 |
+
"step": 3000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 23.0,
|
| 247 |
+
"eval_accuracy": 0.964622641509434,
|
| 248 |
+
"eval_loss": 0.2507427930831909,
|
| 249 |
+
"eval_runtime": 18.696,
|
| 250 |
+
"eval_samples_per_second": 113.393,
|
| 251 |
+
"eval_steps_per_second": 3.584,
|
| 252 |
+
"step": 3059
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 24.0,
|
| 256 |
+
"eval_accuracy": 0.9660377358490566,
|
| 257 |
+
"eval_loss": 0.24606208503246307,
|
| 258 |
+
"eval_runtime": 18.2252,
|
| 259 |
+
"eval_samples_per_second": 116.322,
|
| 260 |
+
"eval_steps_per_second": 3.676,
|
| 261 |
+
"step": 3192
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 25.0,
|
| 265 |
+
"eval_accuracy": 0.9679245283018868,
|
| 266 |
+
"eval_loss": 0.2419576346874237,
|
| 267 |
+
"eval_runtime": 18.4449,
|
| 268 |
+
"eval_samples_per_second": 114.937,
|
| 269 |
+
"eval_steps_per_second": 3.632,
|
| 270 |
+
"step": 3325
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 26.0,
|
| 274 |
+
"eval_accuracy": 0.965566037735849,
|
| 275 |
+
"eval_loss": 0.23377002775669098,
|
| 276 |
+
"eval_runtime": 18.4276,
|
| 277 |
+
"eval_samples_per_second": 115.045,
|
| 278 |
+
"eval_steps_per_second": 3.636,
|
| 279 |
+
"step": 3458
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 26.32,
|
| 283 |
+
"learning_rate": 9.545454545454546e-07,
|
| 284 |
+
"loss": 0.154,
|
| 285 |
+
"step": 3500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 27.0,
|
| 289 |
+
"eval_accuracy": 0.9683962264150944,
|
| 290 |
+
"eval_loss": 0.22959384322166443,
|
| 291 |
+
"eval_runtime": 18.5635,
|
| 292 |
+
"eval_samples_per_second": 114.203,
|
| 293 |
+
"eval_steps_per_second": 3.609,
|
| 294 |
+
"step": 3591
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 28.0,
|
| 298 |
+
"eval_accuracy": 0.9674528301886792,
|
| 299 |
+
"eval_loss": 0.22633853554725647,
|
| 300 |
+
"eval_runtime": 18.435,
|
| 301 |
+
"eval_samples_per_second": 114.999,
|
| 302 |
+
"eval_steps_per_second": 3.634,
|
| 303 |
+
"step": 3724
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 29.0,
|
| 307 |
+
"eval_accuracy": 0.9669811320754716,
|
| 308 |
+
"eval_loss": 0.22211851179599762,
|
| 309 |
+
"eval_runtime": 18.6045,
|
| 310 |
+
"eval_samples_per_second": 113.951,
|
| 311 |
+
"eval_steps_per_second": 3.601,
|
| 312 |
+
"step": 3857
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 30.0,
|
| 316 |
+
"eval_accuracy": 0.9674528301886792,
|
| 317 |
+
"eval_loss": 0.21722418069839478,
|
| 318 |
+
"eval_runtime": 18.5078,
|
| 319 |
+
"eval_samples_per_second": 114.546,
|
| 320 |
+
"eval_steps_per_second": 3.62,
|
| 321 |
+
"step": 3990
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 30.08,
|
| 325 |
+
"learning_rate": 8.030303030303029e-07,
|
| 326 |
+
"loss": 0.137,
|
| 327 |
+
"step": 4000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 31.0,
|
| 331 |
+
"eval_accuracy": 0.9688679245283018,
|
| 332 |
+
"eval_loss": 0.21657830476760864,
|
| 333 |
+
"eval_runtime": 18.4696,
|
| 334 |
+
"eval_samples_per_second": 114.783,
|
| 335 |
+
"eval_steps_per_second": 3.628,
|
| 336 |
+
"step": 4123
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 32.0,
|
| 340 |
+
"eval_accuracy": 0.9693396226415094,
|
| 341 |
+
"eval_loss": 0.21263349056243896,
|
| 342 |
+
"eval_runtime": 18.5165,
|
| 343 |
+
"eval_samples_per_second": 114.492,
|
| 344 |
+
"eval_steps_per_second": 3.618,
|
| 345 |
+
"step": 4256
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 33.0,
|
| 349 |
+
"eval_accuracy": 0.9693396226415094,
|
| 350 |
+
"eval_loss": 0.20656518638134003,
|
| 351 |
+
"eval_runtime": 18.53,
|
| 352 |
+
"eval_samples_per_second": 114.409,
|
| 353 |
+
"eval_steps_per_second": 3.616,
|
| 354 |
+
"step": 4389
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 33.83,
|
| 358 |
+
"learning_rate": 6.515151515151515e-07,
|
| 359 |
+
"loss": 0.1249,
|
| 360 |
+
"step": 4500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 34.0,
|
| 364 |
+
"eval_accuracy": 0.9688679245283018,
|
| 365 |
+
"eval_loss": 0.2059292197227478,
|
| 366 |
+
"eval_runtime": 18.417,
|
| 367 |
+
"eval_samples_per_second": 115.111,
|
| 368 |
+
"eval_steps_per_second": 3.638,
|
| 369 |
+
"step": 4522
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 35.0,
|
| 373 |
+
"eval_accuracy": 0.9688679245283018,
|
| 374 |
+
"eval_loss": 0.202570378780365,
|
| 375 |
+
"eval_runtime": 18.4563,
|
| 376 |
+
"eval_samples_per_second": 114.866,
|
| 377 |
+
"eval_steps_per_second": 3.63,
|
| 378 |
+
"step": 4655
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 36.0,
|
| 382 |
+
"eval_accuracy": 0.9683962264150944,
|
| 383 |
+
"eval_loss": 0.20071472227573395,
|
| 384 |
+
"eval_runtime": 18.5005,
|
| 385 |
+
"eval_samples_per_second": 114.591,
|
| 386 |
+
"eval_steps_per_second": 3.622,
|
| 387 |
+
"step": 4788
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 37.0,
|
| 391 |
+
"eval_accuracy": 0.9702830188679246,
|
| 392 |
+
"eval_loss": 0.19722311198711395,
|
| 393 |
+
"eval_runtime": 18.4376,
|
| 394 |
+
"eval_samples_per_second": 114.982,
|
| 395 |
+
"eval_steps_per_second": 3.634,
|
| 396 |
+
"step": 4921
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 37.59,
|
| 400 |
+
"learning_rate": 5e-07,
|
| 401 |
+
"loss": 0.115,
|
| 402 |
+
"step": 5000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 38.0,
|
| 406 |
+
"eval_accuracy": 0.9712264150943396,
|
| 407 |
+
"eval_loss": 0.19501303136348724,
|
| 408 |
+
"eval_runtime": 18.4088,
|
| 409 |
+
"eval_samples_per_second": 115.162,
|
| 410 |
+
"eval_steps_per_second": 3.64,
|
| 411 |
+
"step": 5054
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 39.0,
|
| 415 |
+
"eval_accuracy": 0.9702830188679246,
|
| 416 |
+
"eval_loss": 0.19410006701946259,
|
| 417 |
+
"eval_runtime": 18.3341,
|
| 418 |
+
"eval_samples_per_second": 115.632,
|
| 419 |
+
"eval_steps_per_second": 3.654,
|
| 420 |
+
"step": 5187
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 40.0,
|
| 424 |
+
"eval_accuracy": 0.9702830188679246,
|
| 425 |
+
"eval_loss": 0.192692831158638,
|
| 426 |
+
"eval_runtime": 18.4143,
|
| 427 |
+
"eval_samples_per_second": 115.128,
|
| 428 |
+
"eval_steps_per_second": 3.638,
|
| 429 |
+
"step": 5320
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 41.0,
|
| 433 |
+
"eval_accuracy": 0.9693396226415094,
|
| 434 |
+
"eval_loss": 0.19077734649181366,
|
| 435 |
+
"eval_runtime": 18.4866,
|
| 436 |
+
"eval_samples_per_second": 114.678,
|
| 437 |
+
"eval_steps_per_second": 3.624,
|
| 438 |
+
"step": 5453
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 41.35,
|
| 442 |
+
"learning_rate": 3.484848484848485e-07,
|
| 443 |
+
"loss": 0.1092,
|
| 444 |
+
"step": 5500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 42.0,
|
| 448 |
+
"eval_accuracy": 0.9712264150943396,
|
| 449 |
+
"eval_loss": 0.18846099078655243,
|
| 450 |
+
"eval_runtime": 18.4309,
|
| 451 |
+
"eval_samples_per_second": 115.024,
|
| 452 |
+
"eval_steps_per_second": 3.635,
|
| 453 |
+
"step": 5586
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 43.0,
|
| 457 |
+
"eval_accuracy": 0.970754716981132,
|
| 458 |
+
"eval_loss": 0.18755605816841125,
|
| 459 |
+
"eval_runtime": 18.4541,
|
| 460 |
+
"eval_samples_per_second": 114.88,
|
| 461 |
+
"eval_steps_per_second": 3.631,
|
| 462 |
+
"step": 5719
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 44.0,
|
| 466 |
+
"eval_accuracy": 0.9702830188679246,
|
| 467 |
+
"eval_loss": 0.18720585107803345,
|
| 468 |
+
"eval_runtime": 18.5754,
|
| 469 |
+
"eval_samples_per_second": 114.129,
|
| 470 |
+
"eval_steps_per_second": 3.607,
|
| 471 |
+
"step": 5852
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 45.0,
|
| 475 |
+
"eval_accuracy": 0.9726415094339622,
|
| 476 |
+
"eval_loss": 0.1874205619096756,
|
| 477 |
+
"eval_runtime": 18.384,
|
| 478 |
+
"eval_samples_per_second": 115.318,
|
| 479 |
+
"eval_steps_per_second": 3.644,
|
| 480 |
+
"step": 5985
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 45.11,
|
| 484 |
+
"learning_rate": 1.9696969696969696e-07,
|
| 485 |
+
"loss": 0.1037,
|
| 486 |
+
"step": 6000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 46.0,
|
| 490 |
+
"eval_accuracy": 0.9726415094339622,
|
| 491 |
+
"eval_loss": 0.18643254041671753,
|
| 492 |
+
"eval_runtime": 18.3487,
|
| 493 |
+
"eval_samples_per_second": 115.54,
|
| 494 |
+
"eval_steps_per_second": 3.651,
|
| 495 |
+
"step": 6118
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 47.0,
|
| 499 |
+
"eval_accuracy": 0.9721698113207548,
|
| 500 |
+
"eval_loss": 0.1849406659603119,
|
| 501 |
+
"eval_runtime": 18.5194,
|
| 502 |
+
"eval_samples_per_second": 114.474,
|
| 503 |
+
"eval_steps_per_second": 3.618,
|
| 504 |
+
"step": 6251
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 48.0,
|
| 508 |
+
"eval_accuracy": 0.9712264150943396,
|
| 509 |
+
"eval_loss": 0.18540790677070618,
|
| 510 |
+
"eval_runtime": 18.5314,
|
| 511 |
+
"eval_samples_per_second": 114.4,
|
| 512 |
+
"eval_steps_per_second": 3.615,
|
| 513 |
+
"step": 6384
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 48.87,
|
| 517 |
+
"learning_rate": 4.545454545454545e-08,
|
| 518 |
+
"loss": 0.1022,
|
| 519 |
+
"step": 6500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 49.0,
|
| 523 |
+
"eval_accuracy": 0.9712264150943396,
|
| 524 |
+
"eval_loss": 0.18494902551174164,
|
| 525 |
+
"eval_runtime": 18.5992,
|
| 526 |
+
"eval_samples_per_second": 113.983,
|
| 527 |
+
"eval_steps_per_second": 3.602,
|
| 528 |
+
"step": 6517
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 50.0,
|
| 532 |
+
"eval_accuracy": 0.9712264150943396,
|
| 533 |
+
"eval_loss": 0.18469373881816864,
|
| 534 |
+
"eval_runtime": 18.4003,
|
| 535 |
+
"eval_samples_per_second": 115.216,
|
| 536 |
+
"eval_steps_per_second": 3.641,
|
| 537 |
+
"step": 6650
|
| 538 |
+
}
|
| 539 |
+
],
|
| 540 |
+
"logging_steps": 500,
|
| 541 |
+
"max_steps": 6650,
|
| 542 |
+
"num_train_epochs": 50,
|
| 543 |
+
"save_steps": 500,
|
| 544 |
+
"total_flos": 3.285748704662323e+19,
|
| 545 |
+
"trial_name": null,
|
| 546 |
+
"trial_params": null
|
| 547 |
+
}
|
checkpoint-6650/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b47ff0c38f70b9f70a6e1842f49d6c65e70286aafea8e7452b04937f8184af9
|
| 3 |
+
size 4091
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Cargo",
|
| 13 |
+
"1": "Carrier",
|
| 14 |
+
"2": "Cruise",
|
| 15 |
+
"3": "Military",
|
| 16 |
+
"4": "Tankers"
|
| 17 |
+
},
|
| 18 |
+
"image_size": 224,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Cargo": 0,
|
| 23 |
+
"Carrier": 1,
|
| 24 |
+
"Cruise": 2,
|
| 25 |
+
"Military": 3,
|
| 26 |
+
"Tankers": 4
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"model_type": "vit",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_channels": 3,
|
| 32 |
+
"num_hidden_layers": 12,
|
| 33 |
+
"patch_size": 16,
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"qkv_bias": true,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.35.2"
|
| 38 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30f3155419517d01e2859d32e6e36d669af32d3c2ef16a1124c44238cc0675b0
|
| 3 |
+
size 343233204
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b47ff0c38f70b9f70a6e1842f49d6c65e70286aafea8e7452b04937f8184af9
|
| 3 |
+
size 4091
|