VINAYAK MODI
commited on
Commit
•
f871afb
1
Parent(s):
ef91e35
Upload folder using huggingface_hub
Browse files- checkpoint-1392/config.json +32 -0
- checkpoint-1392/model.safetensors +3 -0
- checkpoint-1392/optimizer.pt +3 -0
- checkpoint-1392/preprocessor_config.json +36 -0
- checkpoint-1392/rng_state.pth +3 -0
- checkpoint-1392/scheduler.pt +3 -0
- checkpoint-1392/trainer_state.json +818 -0
- checkpoint-1392/training_args.bin +3 -0
- config.json +32 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- training_args.bin +3 -0
checkpoint-1392/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dima806/deepfake_vs_real_image_detection",
|
| 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": "Real",
|
| 13 |
+
"1": "Fake"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"Fake": 1,
|
| 20 |
+
"Real": 0
|
| 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": "4.40.2"
|
| 32 |
+
}
|
checkpoint-1392/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:623c7d9014025abbe7b42cd1738ffb2088e075fba4998e93bd27661576c03a1f
|
| 3 |
+
size 343223968
|
checkpoint-1392/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7391cc30bf7d491981a13809a902c1f1266f4db543fe4e763ea9cfc73243c06
|
| 3 |
+
size 686568453
|
checkpoint-1392/preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTImageProcessor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
checkpoint-1392/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b75e17085b5bacbf6faddf8b68c09621bdcb2181f129995eb10ce1ea6ce9265b
|
| 3 |
+
size 14575
|
checkpoint-1392/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b50d50b8b467650ab19789a9c9c52ddcdb2d8dc44cf644d221de2d38a27cc36a
|
| 3 |
+
size 627
|
checkpoint-1392/trainer_state.json
ADDED
|
@@ -0,0 +1,818 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.33774590492248535,
|
| 3 |
+
"best_model_checkpoint": "deepfake_vs_real_image_detection/checkpoint-1392",
|
| 4 |
+
"epoch": 87.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1392,
|
| 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": 0.6765578635014837,
|
| 14 |
+
"eval_loss": 1.4959243535995483,
|
| 15 |
+
"eval_runtime": 4.5936,
|
| 16 |
+
"eval_samples_per_second": 73.362,
|
| 17 |
+
"eval_steps_per_second": 9.361,
|
| 18 |
+
"step": 16
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.6913946587537092,
|
| 23 |
+
"eval_loss": 1.4148070812225342,
|
| 24 |
+
"eval_runtime": 5.1723,
|
| 25 |
+
"eval_samples_per_second": 65.154,
|
| 26 |
+
"eval_steps_per_second": 8.313,
|
| 27 |
+
"step": 32
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.7091988130563798,
|
| 32 |
+
"eval_loss": 1.309860348701477,
|
| 33 |
+
"eval_runtime": 4.8265,
|
| 34 |
+
"eval_samples_per_second": 69.823,
|
| 35 |
+
"eval_steps_per_second": 8.909,
|
| 36 |
+
"step": 48
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.7240356083086054,
|
| 41 |
+
"eval_loss": 1.2197798490524292,
|
| 42 |
+
"eval_runtime": 4.7427,
|
| 43 |
+
"eval_samples_per_second": 71.057,
|
| 44 |
+
"eval_steps_per_second": 9.067,
|
| 45 |
+
"step": 64
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.7477744807121661,
|
| 50 |
+
"eval_loss": 1.1465003490447998,
|
| 51 |
+
"eval_runtime": 4.8571,
|
| 52 |
+
"eval_samples_per_second": 69.383,
|
| 53 |
+
"eval_steps_per_second": 8.853,
|
| 54 |
+
"step": 80
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.7655786350148368,
|
| 59 |
+
"eval_loss": 1.0904771089553833,
|
| 60 |
+
"eval_runtime": 4.7162,
|
| 61 |
+
"eval_samples_per_second": 71.456,
|
| 62 |
+
"eval_steps_per_second": 9.118,
|
| 63 |
+
"step": 96
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.0,
|
| 67 |
+
"eval_accuracy": 0.7626112759643917,
|
| 68 |
+
"eval_loss": 1.0423768758773804,
|
| 69 |
+
"eval_runtime": 4.7414,
|
| 70 |
+
"eval_samples_per_second": 71.077,
|
| 71 |
+
"eval_steps_per_second": 9.069,
|
| 72 |
+
"step": 112
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.0,
|
| 76 |
+
"eval_accuracy": 0.7626112759643917,
|
| 77 |
+
"eval_loss": 0.9944449067115784,
|
| 78 |
+
"eval_runtime": 4.7288,
|
| 79 |
+
"eval_samples_per_second": 71.265,
|
| 80 |
+
"eval_steps_per_second": 9.093,
|
| 81 |
+
"step": 128
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 9.0,
|
| 85 |
+
"eval_accuracy": 0.7626112759643917,
|
| 86 |
+
"eval_loss": 0.9456853270530701,
|
| 87 |
+
"eval_runtime": 4.6848,
|
| 88 |
+
"eval_samples_per_second": 71.935,
|
| 89 |
+
"eval_steps_per_second": 9.179,
|
| 90 |
+
"step": 144
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 10.0,
|
| 94 |
+
"eval_accuracy": 0.7626112759643917,
|
| 95 |
+
"eval_loss": 0.8957338333129883,
|
| 96 |
+
"eval_runtime": 4.7194,
|
| 97 |
+
"eval_samples_per_second": 71.407,
|
| 98 |
+
"eval_steps_per_second": 9.111,
|
| 99 |
+
"step": 160
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 11.0,
|
| 103 |
+
"eval_accuracy": 0.7626112759643917,
|
| 104 |
+
"eval_loss": 0.852699875831604,
|
| 105 |
+
"eval_runtime": 4.7114,
|
| 106 |
+
"eval_samples_per_second": 71.529,
|
| 107 |
+
"eval_steps_per_second": 9.127,
|
| 108 |
+
"step": 176
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 12.0,
|
| 112 |
+
"eval_accuracy": 0.7626112759643917,
|
| 113 |
+
"eval_loss": 0.815643310546875,
|
| 114 |
+
"eval_runtime": 4.7006,
|
| 115 |
+
"eval_samples_per_second": 71.694,
|
| 116 |
+
"eval_steps_per_second": 9.148,
|
| 117 |
+
"step": 192
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 13.0,
|
| 121 |
+
"eval_accuracy": 0.771513353115727,
|
| 122 |
+
"eval_loss": 0.7831457853317261,
|
| 123 |
+
"eval_runtime": 4.7983,
|
| 124 |
+
"eval_samples_per_second": 70.233,
|
| 125 |
+
"eval_steps_per_second": 8.961,
|
| 126 |
+
"step": 208
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 14.0,
|
| 130 |
+
"eval_accuracy": 0.7744807121661721,
|
| 131 |
+
"eval_loss": 0.7558016180992126,
|
| 132 |
+
"eval_runtime": 4.7359,
|
| 133 |
+
"eval_samples_per_second": 71.159,
|
| 134 |
+
"eval_steps_per_second": 9.08,
|
| 135 |
+
"step": 224
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 15.0,
|
| 139 |
+
"eval_accuracy": 0.7744807121661721,
|
| 140 |
+
"eval_loss": 0.7284858226776123,
|
| 141 |
+
"eval_runtime": 4.6713,
|
| 142 |
+
"eval_samples_per_second": 72.143,
|
| 143 |
+
"eval_steps_per_second": 9.205,
|
| 144 |
+
"step": 240
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 16.0,
|
| 148 |
+
"eval_accuracy": 0.7744807121661721,
|
| 149 |
+
"eval_loss": 0.6914460062980652,
|
| 150 |
+
"eval_runtime": 4.7809,
|
| 151 |
+
"eval_samples_per_second": 70.489,
|
| 152 |
+
"eval_steps_per_second": 8.994,
|
| 153 |
+
"step": 256
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 17.0,
|
| 157 |
+
"eval_accuracy": 0.7774480712166172,
|
| 158 |
+
"eval_loss": 0.6581370830535889,
|
| 159 |
+
"eval_runtime": 4.7253,
|
| 160 |
+
"eval_samples_per_second": 71.318,
|
| 161 |
+
"eval_steps_per_second": 9.1,
|
| 162 |
+
"step": 272
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 18.0,
|
| 166 |
+
"eval_accuracy": 0.7804154302670623,
|
| 167 |
+
"eval_loss": 0.6323521733283997,
|
| 168 |
+
"eval_runtime": 4.7945,
|
| 169 |
+
"eval_samples_per_second": 70.289,
|
| 170 |
+
"eval_steps_per_second": 8.969,
|
| 171 |
+
"step": 288
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 19.0,
|
| 175 |
+
"eval_accuracy": 0.7774480712166172,
|
| 176 |
+
"eval_loss": 0.6072251796722412,
|
| 177 |
+
"eval_runtime": 4.8798,
|
| 178 |
+
"eval_samples_per_second": 69.06,
|
| 179 |
+
"eval_steps_per_second": 8.812,
|
| 180 |
+
"step": 304
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 20.0,
|
| 184 |
+
"eval_accuracy": 0.7804154302670623,
|
| 185 |
+
"eval_loss": 0.5835662484169006,
|
| 186 |
+
"eval_runtime": 4.6039,
|
| 187 |
+
"eval_samples_per_second": 73.199,
|
| 188 |
+
"eval_steps_per_second": 9.34,
|
| 189 |
+
"step": 320
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 21.0,
|
| 193 |
+
"eval_accuracy": 0.7922848664688428,
|
| 194 |
+
"eval_loss": 0.5593723654747009,
|
| 195 |
+
"eval_runtime": 4.7955,
|
| 196 |
+
"eval_samples_per_second": 70.274,
|
| 197 |
+
"eval_steps_per_second": 8.967,
|
| 198 |
+
"step": 336
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 22.0,
|
| 202 |
+
"eval_accuracy": 0.7922848664688428,
|
| 203 |
+
"eval_loss": 0.5364292860031128,
|
| 204 |
+
"eval_runtime": 4.8089,
|
| 205 |
+
"eval_samples_per_second": 70.078,
|
| 206 |
+
"eval_steps_per_second": 8.942,
|
| 207 |
+
"step": 352
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 23.0,
|
| 211 |
+
"eval_accuracy": 0.7952522255192879,
|
| 212 |
+
"eval_loss": 0.5182026028633118,
|
| 213 |
+
"eval_runtime": 4.6149,
|
| 214 |
+
"eval_samples_per_second": 73.024,
|
| 215 |
+
"eval_steps_per_second": 9.318,
|
| 216 |
+
"step": 368
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 24.0,
|
| 220 |
+
"eval_accuracy": 0.8041543026706232,
|
| 221 |
+
"eval_loss": 0.504047691822052,
|
| 222 |
+
"eval_runtime": 4.5605,
|
| 223 |
+
"eval_samples_per_second": 73.895,
|
| 224 |
+
"eval_steps_per_second": 9.429,
|
| 225 |
+
"step": 384
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 25.0,
|
| 229 |
+
"eval_accuracy": 0.8041543026706232,
|
| 230 |
+
"eval_loss": 0.4920850694179535,
|
| 231 |
+
"eval_runtime": 4.6821,
|
| 232 |
+
"eval_samples_per_second": 71.976,
|
| 233 |
+
"eval_steps_per_second": 9.184,
|
| 234 |
+
"step": 400
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 26.0,
|
| 238 |
+
"eval_accuracy": 0.8160237388724035,
|
| 239 |
+
"eval_loss": 0.48037412762641907,
|
| 240 |
+
"eval_runtime": 4.7178,
|
| 241 |
+
"eval_samples_per_second": 71.432,
|
| 242 |
+
"eval_steps_per_second": 9.114,
|
| 243 |
+
"step": 416
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 27.0,
|
| 247 |
+
"eval_accuracy": 0.8189910979228486,
|
| 248 |
+
"eval_loss": 0.4688655138015747,
|
| 249 |
+
"eval_runtime": 4.6086,
|
| 250 |
+
"eval_samples_per_second": 73.124,
|
| 251 |
+
"eval_steps_per_second": 9.33,
|
| 252 |
+
"step": 432
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 28.0,
|
| 256 |
+
"eval_accuracy": 0.8249258160237388,
|
| 257 |
+
"eval_loss": 0.4574899971485138,
|
| 258 |
+
"eval_runtime": 4.6369,
|
| 259 |
+
"eval_samples_per_second": 72.678,
|
| 260 |
+
"eval_steps_per_second": 9.273,
|
| 261 |
+
"step": 448
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 29.0,
|
| 265 |
+
"eval_accuracy": 0.827893175074184,
|
| 266 |
+
"eval_loss": 0.448953777551651,
|
| 267 |
+
"eval_runtime": 4.7138,
|
| 268 |
+
"eval_samples_per_second": 71.491,
|
| 269 |
+
"eval_steps_per_second": 9.122,
|
| 270 |
+
"step": 464
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 30.0,
|
| 274 |
+
"eval_accuracy": 0.827893175074184,
|
| 275 |
+
"eval_loss": 0.4414035379886627,
|
| 276 |
+
"eval_runtime": 4.7192,
|
| 277 |
+
"eval_samples_per_second": 71.41,
|
| 278 |
+
"eval_steps_per_second": 9.112,
|
| 279 |
+
"step": 480
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 31.0,
|
| 283 |
+
"eval_accuracy": 0.827893175074184,
|
| 284 |
+
"eval_loss": 0.4335722029209137,
|
| 285 |
+
"eval_runtime": 4.6675,
|
| 286 |
+
"eval_samples_per_second": 72.202,
|
| 287 |
+
"eval_steps_per_second": 9.213,
|
| 288 |
+
"step": 496
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 31.25,
|
| 292 |
+
"grad_norm": 2.672912120819092,
|
| 293 |
+
"learning_rate": 7.096774193548387e-07,
|
| 294 |
+
"loss": 0.6719,
|
| 295 |
+
"step": 500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 32.0,
|
| 299 |
+
"eval_accuracy": 0.8219584569732937,
|
| 300 |
+
"eval_loss": 0.43041178584098816,
|
| 301 |
+
"eval_runtime": 4.7762,
|
| 302 |
+
"eval_samples_per_second": 70.559,
|
| 303 |
+
"eval_steps_per_second": 9.003,
|
| 304 |
+
"step": 512
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 33.0,
|
| 308 |
+
"eval_accuracy": 0.8249258160237388,
|
| 309 |
+
"eval_loss": 0.4242512881755829,
|
| 310 |
+
"eval_runtime": 4.6367,
|
| 311 |
+
"eval_samples_per_second": 72.681,
|
| 312 |
+
"eval_steps_per_second": 9.274,
|
| 313 |
+
"step": 528
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 34.0,
|
| 317 |
+
"eval_accuracy": 0.827893175074184,
|
| 318 |
+
"eval_loss": 0.421082079410553,
|
| 319 |
+
"eval_runtime": 4.733,
|
| 320 |
+
"eval_samples_per_second": 71.201,
|
| 321 |
+
"eval_steps_per_second": 9.085,
|
| 322 |
+
"step": 544
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 35.0,
|
| 326 |
+
"eval_accuracy": 0.8338278931750742,
|
| 327 |
+
"eval_loss": 0.41326144337654114,
|
| 328 |
+
"eval_runtime": 4.6282,
|
| 329 |
+
"eval_samples_per_second": 72.815,
|
| 330 |
+
"eval_steps_per_second": 9.291,
|
| 331 |
+
"step": 560
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 36.0,
|
| 335 |
+
"eval_accuracy": 0.8338278931750742,
|
| 336 |
+
"eval_loss": 0.41096124053001404,
|
| 337 |
+
"eval_runtime": 4.6107,
|
| 338 |
+
"eval_samples_per_second": 73.092,
|
| 339 |
+
"eval_steps_per_second": 9.326,
|
| 340 |
+
"step": 576
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 37.0,
|
| 344 |
+
"eval_accuracy": 0.8367952522255193,
|
| 345 |
+
"eval_loss": 0.404769629240036,
|
| 346 |
+
"eval_runtime": 4.6205,
|
| 347 |
+
"eval_samples_per_second": 72.936,
|
| 348 |
+
"eval_steps_per_second": 9.306,
|
| 349 |
+
"step": 592
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 38.0,
|
| 353 |
+
"eval_accuracy": 0.8427299703264095,
|
| 354 |
+
"eval_loss": 0.40141698718070984,
|
| 355 |
+
"eval_runtime": 4.6612,
|
| 356 |
+
"eval_samples_per_second": 72.298,
|
| 357 |
+
"eval_steps_per_second": 9.225,
|
| 358 |
+
"step": 608
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 39.0,
|
| 362 |
+
"eval_accuracy": 0.8456973293768546,
|
| 363 |
+
"eval_loss": 0.3952626883983612,
|
| 364 |
+
"eval_runtime": 4.6328,
|
| 365 |
+
"eval_samples_per_second": 72.742,
|
| 366 |
+
"eval_steps_per_second": 9.282,
|
| 367 |
+
"step": 624
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 40.0,
|
| 371 |
+
"eval_accuracy": 0.8456973293768546,
|
| 372 |
+
"eval_loss": 0.390024334192276,
|
| 373 |
+
"eval_runtime": 4.5638,
|
| 374 |
+
"eval_samples_per_second": 73.843,
|
| 375 |
+
"eval_steps_per_second": 9.422,
|
| 376 |
+
"step": 640
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 41.0,
|
| 380 |
+
"eval_accuracy": 0.8456973293768546,
|
| 381 |
+
"eval_loss": 0.3834027349948883,
|
| 382 |
+
"eval_runtime": 4.6261,
|
| 383 |
+
"eval_samples_per_second": 72.848,
|
| 384 |
+
"eval_steps_per_second": 9.295,
|
| 385 |
+
"step": 656
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 42.0,
|
| 389 |
+
"eval_accuracy": 0.8456973293768546,
|
| 390 |
+
"eval_loss": 0.3803389072418213,
|
| 391 |
+
"eval_runtime": 4.6158,
|
| 392 |
+
"eval_samples_per_second": 73.009,
|
| 393 |
+
"eval_steps_per_second": 9.316,
|
| 394 |
+
"step": 672
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 43.0,
|
| 398 |
+
"eval_accuracy": 0.8456973293768546,
|
| 399 |
+
"eval_loss": 0.37990784645080566,
|
| 400 |
+
"eval_runtime": 4.6288,
|
| 401 |
+
"eval_samples_per_second": 72.805,
|
| 402 |
+
"eval_steps_per_second": 9.29,
|
| 403 |
+
"step": 688
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 44.0,
|
| 407 |
+
"eval_accuracy": 0.8456973293768546,
|
| 408 |
+
"eval_loss": 0.3741393983364105,
|
| 409 |
+
"eval_runtime": 4.7575,
|
| 410 |
+
"eval_samples_per_second": 70.836,
|
| 411 |
+
"eval_steps_per_second": 9.038,
|
| 412 |
+
"step": 704
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 45.0,
|
| 416 |
+
"eval_accuracy": 0.8545994065281899,
|
| 417 |
+
"eval_loss": 0.36607253551483154,
|
| 418 |
+
"eval_runtime": 4.6476,
|
| 419 |
+
"eval_samples_per_second": 72.511,
|
| 420 |
+
"eval_steps_per_second": 9.252,
|
| 421 |
+
"step": 720
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 46.0,
|
| 425 |
+
"eval_accuracy": 0.8486646884272997,
|
| 426 |
+
"eval_loss": 0.3655509054660797,
|
| 427 |
+
"eval_runtime": 4.6664,
|
| 428 |
+
"eval_samples_per_second": 72.218,
|
| 429 |
+
"eval_steps_per_second": 9.215,
|
| 430 |
+
"step": 736
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 47.0,
|
| 434 |
+
"eval_accuracy": 0.8486646884272997,
|
| 435 |
+
"eval_loss": 0.36614400148391724,
|
| 436 |
+
"eval_runtime": 4.6792,
|
| 437 |
+
"eval_samples_per_second": 72.021,
|
| 438 |
+
"eval_steps_per_second": 9.19,
|
| 439 |
+
"step": 752
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 48.0,
|
| 443 |
+
"eval_accuracy": 0.8486646884272997,
|
| 444 |
+
"eval_loss": 0.3684944808483124,
|
| 445 |
+
"eval_runtime": 4.6175,
|
| 446 |
+
"eval_samples_per_second": 72.983,
|
| 447 |
+
"eval_steps_per_second": 9.312,
|
| 448 |
+
"step": 768
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 49.0,
|
| 452 |
+
"eval_accuracy": 0.8486646884272997,
|
| 453 |
+
"eval_loss": 0.36265119910240173,
|
| 454 |
+
"eval_runtime": 4.6573,
|
| 455 |
+
"eval_samples_per_second": 72.36,
|
| 456 |
+
"eval_steps_per_second": 9.233,
|
| 457 |
+
"step": 784
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 50.0,
|
| 461 |
+
"eval_accuracy": 0.8486646884272997,
|
| 462 |
+
"eval_loss": 0.359169065952301,
|
| 463 |
+
"eval_runtime": 4.7664,
|
| 464 |
+
"eval_samples_per_second": 70.703,
|
| 465 |
+
"eval_steps_per_second": 9.021,
|
| 466 |
+
"step": 800
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 51.0,
|
| 470 |
+
"eval_accuracy": 0.8486646884272997,
|
| 471 |
+
"eval_loss": 0.35570138692855835,
|
| 472 |
+
"eval_runtime": 4.7355,
|
| 473 |
+
"eval_samples_per_second": 71.165,
|
| 474 |
+
"eval_steps_per_second": 9.08,
|
| 475 |
+
"step": 816
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 52.0,
|
| 479 |
+
"eval_accuracy": 0.8456973293768546,
|
| 480 |
+
"eval_loss": 0.35541436076164246,
|
| 481 |
+
"eval_runtime": 4.7442,
|
| 482 |
+
"eval_samples_per_second": 71.035,
|
| 483 |
+
"eval_steps_per_second": 9.064,
|
| 484 |
+
"step": 832
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 53.0,
|
| 488 |
+
"eval_accuracy": 0.8486646884272997,
|
| 489 |
+
"eval_loss": 0.3521236479282379,
|
| 490 |
+
"eval_runtime": 4.6755,
|
| 491 |
+
"eval_samples_per_second": 72.078,
|
| 492 |
+
"eval_steps_per_second": 9.197,
|
| 493 |
+
"step": 848
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 54.0,
|
| 497 |
+
"eval_accuracy": 0.8486646884272997,
|
| 498 |
+
"eval_loss": 0.3523922264575958,
|
| 499 |
+
"eval_runtime": 4.6657,
|
| 500 |
+
"eval_samples_per_second": 72.23,
|
| 501 |
+
"eval_steps_per_second": 9.216,
|
| 502 |
+
"step": 864
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 55.0,
|
| 506 |
+
"eval_accuracy": 0.8516320474777448,
|
| 507 |
+
"eval_loss": 0.34878119826316833,
|
| 508 |
+
"eval_runtime": 4.6488,
|
| 509 |
+
"eval_samples_per_second": 72.491,
|
| 510 |
+
"eval_steps_per_second": 9.25,
|
| 511 |
+
"step": 880
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 56.0,
|
| 515 |
+
"eval_accuracy": 0.8516320474777448,
|
| 516 |
+
"eval_loss": 0.3482997715473175,
|
| 517 |
+
"eval_runtime": 4.683,
|
| 518 |
+
"eval_samples_per_second": 71.963,
|
| 519 |
+
"eval_steps_per_second": 9.182,
|
| 520 |
+
"step": 896
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 57.0,
|
| 524 |
+
"eval_accuracy": 0.8456973293768546,
|
| 525 |
+
"eval_loss": 0.348295122385025,
|
| 526 |
+
"eval_runtime": 4.8638,
|
| 527 |
+
"eval_samples_per_second": 69.287,
|
| 528 |
+
"eval_steps_per_second": 8.841,
|
| 529 |
+
"step": 912
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 58.0,
|
| 533 |
+
"eval_accuracy": 0.8456973293768546,
|
| 534 |
+
"eval_loss": 0.3468620479106903,
|
| 535 |
+
"eval_runtime": 4.8133,
|
| 536 |
+
"eval_samples_per_second": 70.014,
|
| 537 |
+
"eval_steps_per_second": 8.934,
|
| 538 |
+
"step": 928
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 59.0,
|
| 542 |
+
"eval_accuracy": 0.8486646884272997,
|
| 543 |
+
"eval_loss": 0.3429933488368988,
|
| 544 |
+
"eval_runtime": 4.7367,
|
| 545 |
+
"eval_samples_per_second": 71.146,
|
| 546 |
+
"eval_steps_per_second": 9.078,
|
| 547 |
+
"step": 944
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 60.0,
|
| 551 |
+
"eval_accuracy": 0.8516320474777448,
|
| 552 |
+
"eval_loss": 0.347034752368927,
|
| 553 |
+
"eval_runtime": 4.7735,
|
| 554 |
+
"eval_samples_per_second": 70.598,
|
| 555 |
+
"eval_steps_per_second": 9.008,
|
| 556 |
+
"step": 960
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 61.0,
|
| 560 |
+
"eval_accuracy": 0.8545994065281899,
|
| 561 |
+
"eval_loss": 0.34952038526535034,
|
| 562 |
+
"eval_runtime": 4.6627,
|
| 563 |
+
"eval_samples_per_second": 72.276,
|
| 564 |
+
"eval_steps_per_second": 9.222,
|
| 565 |
+
"step": 976
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 62.0,
|
| 569 |
+
"eval_accuracy": 0.857566765578635,
|
| 570 |
+
"eval_loss": 0.34523066878318787,
|
| 571 |
+
"eval_runtime": 4.761,
|
| 572 |
+
"eval_samples_per_second": 70.783,
|
| 573 |
+
"eval_steps_per_second": 9.032,
|
| 574 |
+
"step": 992
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 62.5,
|
| 578 |
+
"grad_norm": 4.032630920410156,
|
| 579 |
+
"learning_rate": 3.8709677419354837e-07,
|
| 580 |
+
"loss": 0.2134,
|
| 581 |
+
"step": 1000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 63.0,
|
| 585 |
+
"eval_accuracy": 0.8605341246290801,
|
| 586 |
+
"eval_loss": 0.3458469808101654,
|
| 587 |
+
"eval_runtime": 4.7825,
|
| 588 |
+
"eval_samples_per_second": 70.465,
|
| 589 |
+
"eval_steps_per_second": 8.991,
|
| 590 |
+
"step": 1008
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 64.0,
|
| 594 |
+
"eval_accuracy": 0.8605341246290801,
|
| 595 |
+
"eval_loss": 0.3463592529296875,
|
| 596 |
+
"eval_runtime": 4.7675,
|
| 597 |
+
"eval_samples_per_second": 70.687,
|
| 598 |
+
"eval_steps_per_second": 9.019,
|
| 599 |
+
"step": 1024
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 65.0,
|
| 603 |
+
"eval_accuracy": 0.8605341246290801,
|
| 604 |
+
"eval_loss": 0.3484276831150055,
|
| 605 |
+
"eval_runtime": 4.7586,
|
| 606 |
+
"eval_samples_per_second": 70.82,
|
| 607 |
+
"eval_steps_per_second": 9.036,
|
| 608 |
+
"step": 1040
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 66.0,
|
| 612 |
+
"eval_accuracy": 0.8635014836795252,
|
| 613 |
+
"eval_loss": 0.34886136651039124,
|
| 614 |
+
"eval_runtime": 4.7061,
|
| 615 |
+
"eval_samples_per_second": 71.609,
|
| 616 |
+
"eval_steps_per_second": 9.137,
|
| 617 |
+
"step": 1056
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 67.0,
|
| 621 |
+
"eval_accuracy": 0.8635014836795252,
|
| 622 |
+
"eval_loss": 0.3485889434814453,
|
| 623 |
+
"eval_runtime": 4.6029,
|
| 624 |
+
"eval_samples_per_second": 73.215,
|
| 625 |
+
"eval_steps_per_second": 9.342,
|
| 626 |
+
"step": 1072
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 68.0,
|
| 630 |
+
"eval_accuracy": 0.8635014836795252,
|
| 631 |
+
"eval_loss": 0.3503687381744385,
|
| 632 |
+
"eval_runtime": 4.7013,
|
| 633 |
+
"eval_samples_per_second": 71.682,
|
| 634 |
+
"eval_steps_per_second": 9.146,
|
| 635 |
+
"step": 1088
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 69.0,
|
| 639 |
+
"eval_accuracy": 0.8635014836795252,
|
| 640 |
+
"eval_loss": 0.3495609164237976,
|
| 641 |
+
"eval_runtime": 4.7225,
|
| 642 |
+
"eval_samples_per_second": 71.36,
|
| 643 |
+
"eval_steps_per_second": 9.105,
|
| 644 |
+
"step": 1104
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 70.0,
|
| 648 |
+
"eval_accuracy": 0.8605341246290801,
|
| 649 |
+
"eval_loss": 0.3446400761604309,
|
| 650 |
+
"eval_runtime": 4.7445,
|
| 651 |
+
"eval_samples_per_second": 71.029,
|
| 652 |
+
"eval_steps_per_second": 9.063,
|
| 653 |
+
"step": 1120
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 71.0,
|
| 657 |
+
"eval_accuracy": 0.8635014836795252,
|
| 658 |
+
"eval_loss": 0.3452640175819397,
|
| 659 |
+
"eval_runtime": 4.6434,
|
| 660 |
+
"eval_samples_per_second": 72.577,
|
| 661 |
+
"eval_steps_per_second": 9.261,
|
| 662 |
+
"step": 1136
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 72.0,
|
| 666 |
+
"eval_accuracy": 0.8635014836795252,
|
| 667 |
+
"eval_loss": 0.34035128355026245,
|
| 668 |
+
"eval_runtime": 4.7053,
|
| 669 |
+
"eval_samples_per_second": 71.622,
|
| 670 |
+
"eval_steps_per_second": 9.139,
|
| 671 |
+
"step": 1152
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 73.0,
|
| 675 |
+
"eval_accuracy": 0.8635014836795252,
|
| 676 |
+
"eval_loss": 0.33860069513320923,
|
| 677 |
+
"eval_runtime": 4.6174,
|
| 678 |
+
"eval_samples_per_second": 72.985,
|
| 679 |
+
"eval_steps_per_second": 9.313,
|
| 680 |
+
"step": 1168
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 74.0,
|
| 684 |
+
"eval_accuracy": 0.8635014836795252,
|
| 685 |
+
"eval_loss": 0.3384004831314087,
|
| 686 |
+
"eval_runtime": 4.663,
|
| 687 |
+
"eval_samples_per_second": 72.271,
|
| 688 |
+
"eval_steps_per_second": 9.221,
|
| 689 |
+
"step": 1184
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 75.0,
|
| 693 |
+
"eval_accuracy": 0.8664688427299704,
|
| 694 |
+
"eval_loss": 0.33985474705696106,
|
| 695 |
+
"eval_runtime": 4.7211,
|
| 696 |
+
"eval_samples_per_second": 71.382,
|
| 697 |
+
"eval_steps_per_second": 9.108,
|
| 698 |
+
"step": 1200
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 76.0,
|
| 702 |
+
"eval_accuracy": 0.8664688427299704,
|
| 703 |
+
"eval_loss": 0.3414258062839508,
|
| 704 |
+
"eval_runtime": 4.7314,
|
| 705 |
+
"eval_samples_per_second": 71.226,
|
| 706 |
+
"eval_steps_per_second": 9.088,
|
| 707 |
+
"step": 1216
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 77.0,
|
| 711 |
+
"eval_accuracy": 0.8664688427299704,
|
| 712 |
+
"eval_loss": 0.3427448272705078,
|
| 713 |
+
"eval_runtime": 4.7038,
|
| 714 |
+
"eval_samples_per_second": 71.644,
|
| 715 |
+
"eval_steps_per_second": 9.141,
|
| 716 |
+
"step": 1232
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 78.0,
|
| 720 |
+
"eval_accuracy": 0.8635014836795252,
|
| 721 |
+
"eval_loss": 0.34361016750335693,
|
| 722 |
+
"eval_runtime": 4.8723,
|
| 723 |
+
"eval_samples_per_second": 69.167,
|
| 724 |
+
"eval_steps_per_second": 8.825,
|
| 725 |
+
"step": 1248
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 79.0,
|
| 729 |
+
"eval_accuracy": 0.8664688427299704,
|
| 730 |
+
"eval_loss": 0.34205198287963867,
|
| 731 |
+
"eval_runtime": 4.7564,
|
| 732 |
+
"eval_samples_per_second": 70.851,
|
| 733 |
+
"eval_steps_per_second": 9.04,
|
| 734 |
+
"step": 1264
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 80.0,
|
| 738 |
+
"eval_accuracy": 0.8664688427299704,
|
| 739 |
+
"eval_loss": 0.3414119780063629,
|
| 740 |
+
"eval_runtime": 4.7639,
|
| 741 |
+
"eval_samples_per_second": 70.74,
|
| 742 |
+
"eval_steps_per_second": 9.026,
|
| 743 |
+
"step": 1280
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 81.0,
|
| 747 |
+
"eval_accuracy": 0.8664688427299704,
|
| 748 |
+
"eval_loss": 0.3397296071052551,
|
| 749 |
+
"eval_runtime": 4.7085,
|
| 750 |
+
"eval_samples_per_second": 71.572,
|
| 751 |
+
"eval_steps_per_second": 9.132,
|
| 752 |
+
"step": 1296
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 82.0,
|
| 756 |
+
"eval_accuracy": 0.8664688427299704,
|
| 757 |
+
"eval_loss": 0.3387517035007477,
|
| 758 |
+
"eval_runtime": 4.764,
|
| 759 |
+
"eval_samples_per_second": 70.738,
|
| 760 |
+
"eval_steps_per_second": 9.026,
|
| 761 |
+
"step": 1312
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 83.0,
|
| 765 |
+
"eval_accuracy": 0.8664688427299704,
|
| 766 |
+
"eval_loss": 0.33925285935401917,
|
| 767 |
+
"eval_runtime": 4.8225,
|
| 768 |
+
"eval_samples_per_second": 69.88,
|
| 769 |
+
"eval_steps_per_second": 8.916,
|
| 770 |
+
"step": 1328
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 84.0,
|
| 774 |
+
"eval_accuracy": 0.8664688427299704,
|
| 775 |
+
"eval_loss": 0.3406101167201996,
|
| 776 |
+
"eval_runtime": 4.6734,
|
| 777 |
+
"eval_samples_per_second": 72.11,
|
| 778 |
+
"eval_steps_per_second": 9.201,
|
| 779 |
+
"step": 1344
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 85.0,
|
| 783 |
+
"eval_accuracy": 0.8664688427299704,
|
| 784 |
+
"eval_loss": 0.33851388096809387,
|
| 785 |
+
"eval_runtime": 4.7413,
|
| 786 |
+
"eval_samples_per_second": 71.077,
|
| 787 |
+
"eval_steps_per_second": 9.069,
|
| 788 |
+
"step": 1360
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 86.0,
|
| 792 |
+
"eval_accuracy": 0.8664688427299704,
|
| 793 |
+
"eval_loss": 0.3385758697986603,
|
| 794 |
+
"eval_runtime": 4.707,
|
| 795 |
+
"eval_samples_per_second": 71.596,
|
| 796 |
+
"eval_steps_per_second": 9.135,
|
| 797 |
+
"step": 1376
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 87.0,
|
| 801 |
+
"eval_accuracy": 0.8664688427299704,
|
| 802 |
+
"eval_loss": 0.33774590492248535,
|
| 803 |
+
"eval_runtime": 4.6381,
|
| 804 |
+
"eval_samples_per_second": 72.658,
|
| 805 |
+
"eval_steps_per_second": 9.271,
|
| 806 |
+
"step": 1392
|
| 807 |
+
}
|
| 808 |
+
],
|
| 809 |
+
"logging_steps": 500,
|
| 810 |
+
"max_steps": 1600,
|
| 811 |
+
"num_input_tokens_seen": 0,
|
| 812 |
+
"num_train_epochs": 100,
|
| 813 |
+
"save_steps": 500,
|
| 814 |
+
"total_flos": 3.4046105637170995e+18,
|
| 815 |
+
"train_batch_size": 32,
|
| 816 |
+
"trial_name": null,
|
| 817 |
+
"trial_params": null
|
| 818 |
+
}
|
checkpoint-1392/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33beeb0ed56ac9dc088f390174ad1a0d37efd51fa83944429a86e766fe759460
|
| 3 |
+
size 4475
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dima806/deepfake_vs_real_image_detection",
|
| 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": "Real",
|
| 13 |
+
"1": "Fake"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"Fake": 1,
|
| 20 |
+
"Real": 0
|
| 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": "4.40.2"
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:623c7d9014025abbe7b42cd1738ffb2088e075fba4998e93bd27661576c03a1f
|
| 3 |
+
size 343223968
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTImageProcessor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33beeb0ed56ac9dc088f390174ad1a0d37efd51fa83944429a86e766fe759460
|
| 3 |
+
size 4475
|