Upload folder using huggingface_hub
Browse files- checkpoint-23600/config.json +42 -0
- checkpoint-23600/model.safetensors +3 -0
- checkpoint-23600/optimizer.pt +3 -0
- checkpoint-23600/preprocessor_config.json +23 -0
- checkpoint-23600/rng_state.pth +3 -0
- checkpoint-23600/scheduler.pt +3 -0
- checkpoint-23600/trainer_state.json +562 -0
- checkpoint-23600/training_args.bin +3 -0
- config.json +42 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
- training_args.bin +3 -0
checkpoint-23600/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "sad",
|
| 13 |
+
"1": "disgust",
|
| 14 |
+
"2": "angry",
|
| 15 |
+
"3": "neutral",
|
| 16 |
+
"4": "fear",
|
| 17 |
+
"5": "surprise",
|
| 18 |
+
"6": "happy"
|
| 19 |
+
},
|
| 20 |
+
"image_size": 224,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"angry": 2,
|
| 25 |
+
"disgust": 1,
|
| 26 |
+
"fear": 4,
|
| 27 |
+
"happy": 6,
|
| 28 |
+
"neutral": 3,
|
| 29 |
+
"sad": 0,
|
| 30 |
+
"surprise": 5
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"model_type": "vit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"patch_size": 16,
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"qkv_bias": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.47.1"
|
| 42 |
+
}
|
checkpoint-23600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33773b4580db1e26a0b690c0fa200cf4c0844e95e4769e234a682b37712bed06
|
| 3 |
+
size 343239356
|
checkpoint-23600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d097154adced990bf2d07490a9a0aacd42dca52018260bb14377aea03f9a585d
|
| 3 |
+
size 686599173
|
checkpoint-23600/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-23600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d65f7e8c7c84bb8b89542d2d12528733e94ace95771b36dd383042c3be18a87a
|
| 3 |
+
size 14575
|
checkpoint-23600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02b62ac223ffa5c4d25055aa820a995bc16441497fc3731b27ee1a4e9e97ac5e
|
| 3 |
+
size 627
|
checkpoint-23600/trainer_state.json
ADDED
|
@@ -0,0 +1,562 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0445903539657593,
|
| 3 |
+
"best_model_checkpoint": "facial_emotions_image_detection/checkpoint-23600",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 23600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.423728813559322,
|
| 13 |
+
"grad_norm": 1.6307811737060547,
|
| 14 |
+
"learning_rate": 2.9541595925297115e-06,
|
| 15 |
+
"loss": 1.8794,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.847457627118644,
|
| 20 |
+
"grad_norm": 2.476940631866455,
|
| 21 |
+
"learning_rate": 2.903225806451613e-06,
|
| 22 |
+
"loss": 1.6633,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.43746523639253077,
|
| 28 |
+
"eval_loss": 1.7183066606521606,
|
| 29 |
+
"eval_model_preparation_time": 0.0035,
|
| 30 |
+
"eval_runtime": 222.116,
|
| 31 |
+
"eval_samples_per_second": 113.319,
|
| 32 |
+
"eval_steps_per_second": 14.168,
|
| 33 |
+
"step": 1180
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.271186440677966,
|
| 37 |
+
"grad_norm": 2.9950172901153564,
|
| 38 |
+
"learning_rate": 2.8522920203735145e-06,
|
| 39 |
+
"loss": 1.5106,
|
| 40 |
+
"step": 1500
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.694915254237288,
|
| 44 |
+
"grad_norm": 4.541733741760254,
|
| 45 |
+
"learning_rate": 2.801358234295416e-06,
|
| 46 |
+
"loss": 1.4038,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_accuracy": 0.5050059594755661,
|
| 52 |
+
"eval_loss": 1.5001347064971924,
|
| 53 |
+
"eval_model_preparation_time": 0.0035,
|
| 54 |
+
"eval_runtime": 223.7558,
|
| 55 |
+
"eval_samples_per_second": 112.489,
|
| 56 |
+
"eval_steps_per_second": 14.064,
|
| 57 |
+
"step": 2360
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.1186440677966103,
|
| 61 |
+
"grad_norm": 4.030027389526367,
|
| 62 |
+
"learning_rate": 2.7504244482173174e-06,
|
| 63 |
+
"loss": 1.3289,
|
| 64 |
+
"step": 2500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 2.542372881355932,
|
| 68 |
+
"grad_norm": 5.033902645111084,
|
| 69 |
+
"learning_rate": 2.699490662139219e-06,
|
| 70 |
+
"loss": 1.2744,
|
| 71 |
+
"step": 3000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.9661016949152543,
|
| 75 |
+
"grad_norm": 4.396991729736328,
|
| 76 |
+
"learning_rate": 2.648556876061121e-06,
|
| 77 |
+
"loss": 1.2427,
|
| 78 |
+
"step": 3500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.0,
|
| 82 |
+
"eval_accuracy": 0.5299562971791816,
|
| 83 |
+
"eval_loss": 1.364925742149353,
|
| 84 |
+
"eval_model_preparation_time": 0.0035,
|
| 85 |
+
"eval_runtime": 224.6343,
|
| 86 |
+
"eval_samples_per_second": 112.049,
|
| 87 |
+
"eval_steps_per_second": 14.009,
|
| 88 |
+
"step": 3540
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 3.389830508474576,
|
| 92 |
+
"grad_norm": 4.660696983337402,
|
| 93 |
+
"learning_rate": 2.597623089983022e-06,
|
| 94 |
+
"loss": 1.1981,
|
| 95 |
+
"step": 4000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.8135593220338984,
|
| 99 |
+
"grad_norm": 5.578737258911133,
|
| 100 |
+
"learning_rate": 2.546689303904924e-06,
|
| 101 |
+
"loss": 1.1535,
|
| 102 |
+
"step": 4500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 4.0,
|
| 106 |
+
"eval_accuracy": 0.5553436630909814,
|
| 107 |
+
"eval_loss": 1.2839970588684082,
|
| 108 |
+
"eval_model_preparation_time": 0.0035,
|
| 109 |
+
"eval_runtime": 227.7991,
|
| 110 |
+
"eval_samples_per_second": 110.492,
|
| 111 |
+
"eval_steps_per_second": 13.815,
|
| 112 |
+
"step": 4720
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 4.237288135593221,
|
| 116 |
+
"grad_norm": 6.838766574859619,
|
| 117 |
+
"learning_rate": 2.495755517826825e-06,
|
| 118 |
+
"loss": 1.1359,
|
| 119 |
+
"step": 5000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.661016949152542,
|
| 123 |
+
"grad_norm": 6.198632717132568,
|
| 124 |
+
"learning_rate": 2.4448217317487268e-06,
|
| 125 |
+
"loss": 1.1001,
|
| 126 |
+
"step": 5500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.0,
|
| 130 |
+
"eval_accuracy": 0.5646007151370679,
|
| 131 |
+
"eval_loss": 1.229695439338684,
|
| 132 |
+
"eval_model_preparation_time": 0.0035,
|
| 133 |
+
"eval_runtime": 223.7686,
|
| 134 |
+
"eval_samples_per_second": 112.482,
|
| 135 |
+
"eval_steps_per_second": 14.064,
|
| 136 |
+
"step": 5900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 5.084745762711864,
|
| 140 |
+
"grad_norm": 6.204673767089844,
|
| 141 |
+
"learning_rate": 2.393887945670628e-06,
|
| 142 |
+
"loss": 1.0829,
|
| 143 |
+
"step": 6000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 5.508474576271187,
|
| 147 |
+
"grad_norm": 5.266815662384033,
|
| 148 |
+
"learning_rate": 2.3429541595925297e-06,
|
| 149 |
+
"loss": 1.0661,
|
| 150 |
+
"step": 6500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 5.932203389830509,
|
| 154 |
+
"grad_norm": 5.726169109344482,
|
| 155 |
+
"learning_rate": 2.2920203735144314e-06,
|
| 156 |
+
"loss": 1.0279,
|
| 157 |
+
"step": 7000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 6.0,
|
| 161 |
+
"eval_accuracy": 0.5670242352006357,
|
| 162 |
+
"eval_loss": 1.203406572341919,
|
| 163 |
+
"eval_model_preparation_time": 0.0035,
|
| 164 |
+
"eval_runtime": 232.0453,
|
| 165 |
+
"eval_samples_per_second": 108.47,
|
| 166 |
+
"eval_steps_per_second": 13.562,
|
| 167 |
+
"step": 7080
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 6.3559322033898304,
|
| 171 |
+
"grad_norm": 15.006390571594238,
|
| 172 |
+
"learning_rate": 2.241086587436333e-06,
|
| 173 |
+
"loss": 1.0108,
|
| 174 |
+
"step": 7500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 6.779661016949152,
|
| 178 |
+
"grad_norm": 6.441979885101318,
|
| 179 |
+
"learning_rate": 2.1901528013582344e-06,
|
| 180 |
+
"loss": 0.9936,
|
| 181 |
+
"step": 8000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 7.0,
|
| 185 |
+
"eval_accuracy": 0.5793802145411204,
|
| 186 |
+
"eval_loss": 1.1601252555847168,
|
| 187 |
+
"eval_model_preparation_time": 0.0035,
|
| 188 |
+
"eval_runtime": 240.4411,
|
| 189 |
+
"eval_samples_per_second": 104.683,
|
| 190 |
+
"eval_steps_per_second": 13.088,
|
| 191 |
+
"step": 8260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 7.203389830508475,
|
| 195 |
+
"grad_norm": 13.402597427368164,
|
| 196 |
+
"learning_rate": 2.1392190152801356e-06,
|
| 197 |
+
"loss": 0.9714,
|
| 198 |
+
"step": 8500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 7.627118644067797,
|
| 202 |
+
"grad_norm": 7.855940341949463,
|
| 203 |
+
"learning_rate": 2.0882852292020373e-06,
|
| 204 |
+
"loss": 0.9641,
|
| 205 |
+
"step": 9000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 8.0,
|
| 209 |
+
"eval_accuracy": 0.5829161700437028,
|
| 210 |
+
"eval_loss": 1.1439958810806274,
|
| 211 |
+
"eval_model_preparation_time": 0.0035,
|
| 212 |
+
"eval_runtime": 230.8248,
|
| 213 |
+
"eval_samples_per_second": 109.044,
|
| 214 |
+
"eval_steps_per_second": 13.634,
|
| 215 |
+
"step": 9440
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 8.05084745762712,
|
| 219 |
+
"grad_norm": 9.408000946044922,
|
| 220 |
+
"learning_rate": 2.037351443123939e-06,
|
| 221 |
+
"loss": 0.955,
|
| 222 |
+
"step": 9500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 8.474576271186441,
|
| 226 |
+
"grad_norm": 7.728194236755371,
|
| 227 |
+
"learning_rate": 1.9864176570458407e-06,
|
| 228 |
+
"loss": 0.9384,
|
| 229 |
+
"step": 10000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 8.898305084745763,
|
| 233 |
+
"grad_norm": 7.551913738250732,
|
| 234 |
+
"learning_rate": 1.935483870967742e-06,
|
| 235 |
+
"loss": 0.9203,
|
| 236 |
+
"step": 10500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 9.0,
|
| 240 |
+
"eval_accuracy": 0.5870480731029003,
|
| 241 |
+
"eval_loss": 1.1307237148284912,
|
| 242 |
+
"eval_model_preparation_time": 0.0035,
|
| 243 |
+
"eval_runtime": 230.0359,
|
| 244 |
+
"eval_samples_per_second": 109.418,
|
| 245 |
+
"eval_steps_per_second": 13.68,
|
| 246 |
+
"step": 10620
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 9.322033898305085,
|
| 250 |
+
"grad_norm": 10.311104774475098,
|
| 251 |
+
"learning_rate": 1.8845500848896437e-06,
|
| 252 |
+
"loss": 0.9118,
|
| 253 |
+
"step": 11000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 9.745762711864407,
|
| 257 |
+
"grad_norm": 15.17727279663086,
|
| 258 |
+
"learning_rate": 1.833616298811545e-06,
|
| 259 |
+
"loss": 0.9054,
|
| 260 |
+
"step": 11500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 10.0,
|
| 264 |
+
"eval_accuracy": 0.5841080651569328,
|
| 265 |
+
"eval_loss": 1.1200737953186035,
|
| 266 |
+
"eval_model_preparation_time": 0.0035,
|
| 267 |
+
"eval_runtime": 229.8788,
|
| 268 |
+
"eval_samples_per_second": 109.492,
|
| 269 |
+
"eval_steps_per_second": 13.69,
|
| 270 |
+
"step": 11800
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 10.169491525423728,
|
| 274 |
+
"grad_norm": 9.014813423156738,
|
| 275 |
+
"learning_rate": 1.7826825127334464e-06,
|
| 276 |
+
"loss": 0.9008,
|
| 277 |
+
"step": 12000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 10.59322033898305,
|
| 281 |
+
"grad_norm": 12.12553596496582,
|
| 282 |
+
"learning_rate": 1.7317487266553481e-06,
|
| 283 |
+
"loss": 0.8756,
|
| 284 |
+
"step": 12500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 11.0,
|
| 288 |
+
"eval_accuracy": 0.5928486293206198,
|
| 289 |
+
"eval_loss": 1.1042790412902832,
|
| 290 |
+
"eval_model_preparation_time": 0.0035,
|
| 291 |
+
"eval_runtime": 232.2297,
|
| 292 |
+
"eval_samples_per_second": 108.384,
|
| 293 |
+
"eval_steps_per_second": 13.551,
|
| 294 |
+
"step": 12980
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 11.016949152542374,
|
| 298 |
+
"grad_norm": 6.826832294464111,
|
| 299 |
+
"learning_rate": 1.6808149405772494e-06,
|
| 300 |
+
"loss": 0.8752,
|
| 301 |
+
"step": 13000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 11.440677966101696,
|
| 305 |
+
"grad_norm": 7.686470985412598,
|
| 306 |
+
"learning_rate": 1.629881154499151e-06,
|
| 307 |
+
"loss": 0.8655,
|
| 308 |
+
"step": 13500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 11.864406779661017,
|
| 312 |
+
"grad_norm": 5.65968132019043,
|
| 313 |
+
"learning_rate": 1.5789473684210526e-06,
|
| 314 |
+
"loss": 0.8577,
|
| 315 |
+
"step": 14000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 12.0,
|
| 319 |
+
"eval_accuracy": 0.5943980929678189,
|
| 320 |
+
"eval_loss": 1.096846103668213,
|
| 321 |
+
"eval_model_preparation_time": 0.0035,
|
| 322 |
+
"eval_runtime": 231.7997,
|
| 323 |
+
"eval_samples_per_second": 108.585,
|
| 324 |
+
"eval_steps_per_second": 13.576,
|
| 325 |
+
"step": 14160
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 12.288135593220339,
|
| 329 |
+
"grad_norm": 14.164326667785645,
|
| 330 |
+
"learning_rate": 1.5280135823429543e-06,
|
| 331 |
+
"loss": 0.8592,
|
| 332 |
+
"step": 14500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 12.711864406779661,
|
| 336 |
+
"grad_norm": 12.4461669921875,
|
| 337 |
+
"learning_rate": 1.4770797962648558e-06,
|
| 338 |
+
"loss": 0.8458,
|
| 339 |
+
"step": 15000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 13.0,
|
| 343 |
+
"eval_accuracy": 0.6005164878823996,
|
| 344 |
+
"eval_loss": 1.083931565284729,
|
| 345 |
+
"eval_model_preparation_time": 0.0035,
|
| 346 |
+
"eval_runtime": 229.3297,
|
| 347 |
+
"eval_samples_per_second": 109.755,
|
| 348 |
+
"eval_steps_per_second": 13.723,
|
| 349 |
+
"step": 15340
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 13.135593220338983,
|
| 353 |
+
"grad_norm": 7.7317047119140625,
|
| 354 |
+
"learning_rate": 1.4261460101867572e-06,
|
| 355 |
+
"loss": 0.8351,
|
| 356 |
+
"step": 15500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 13.559322033898304,
|
| 360 |
+
"grad_norm": 10.227279663085938,
|
| 361 |
+
"learning_rate": 1.3752122241086587e-06,
|
| 362 |
+
"loss": 0.819,
|
| 363 |
+
"step": 16000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 13.983050847457626,
|
| 367 |
+
"grad_norm": 67.47618103027344,
|
| 368 |
+
"learning_rate": 1.3242784380305604e-06,
|
| 369 |
+
"loss": 0.8288,
|
| 370 |
+
"step": 16500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 14.0,
|
| 374 |
+
"eval_accuracy": 0.5987286452125546,
|
| 375 |
+
"eval_loss": 1.081558108329773,
|
| 376 |
+
"eval_model_preparation_time": 0.0035,
|
| 377 |
+
"eval_runtime": 229.7478,
|
| 378 |
+
"eval_samples_per_second": 109.555,
|
| 379 |
+
"eval_steps_per_second": 13.698,
|
| 380 |
+
"step": 16520
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 14.40677966101695,
|
| 384 |
+
"grad_norm": 7.805768966674805,
|
| 385 |
+
"learning_rate": 1.273344651952462e-06,
|
| 386 |
+
"loss": 0.8122,
|
| 387 |
+
"step": 17000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 14.830508474576272,
|
| 391 |
+
"grad_norm": 6.83695125579834,
|
| 392 |
+
"learning_rate": 1.2224108658743634e-06,
|
| 393 |
+
"loss": 0.8224,
|
| 394 |
+
"step": 17500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 15.0,
|
| 398 |
+
"eval_accuracy": 0.6054827175208581,
|
| 399 |
+
"eval_loss": 1.0741792917251587,
|
| 400 |
+
"eval_model_preparation_time": 0.0035,
|
| 401 |
+
"eval_runtime": 231.8476,
|
| 402 |
+
"eval_samples_per_second": 108.563,
|
| 403 |
+
"eval_steps_per_second": 13.574,
|
| 404 |
+
"step": 17700
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 15.254237288135593,
|
| 408 |
+
"grad_norm": 5.755763530731201,
|
| 409 |
+
"learning_rate": 1.1714770797962649e-06,
|
| 410 |
+
"loss": 0.8031,
|
| 411 |
+
"step": 18000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 15.677966101694915,
|
| 415 |
+
"grad_norm": 12.960982322692871,
|
| 416 |
+
"learning_rate": 1.1205432937181666e-06,
|
| 417 |
+
"loss": 0.8021,
|
| 418 |
+
"step": 18500
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 16.0,
|
| 422 |
+
"eval_accuracy": 0.6082638061183949,
|
| 423 |
+
"eval_loss": 1.0608046054840088,
|
| 424 |
+
"eval_model_preparation_time": 0.0035,
|
| 425 |
+
"eval_runtime": 230.4772,
|
| 426 |
+
"eval_samples_per_second": 109.208,
|
| 427 |
+
"eval_steps_per_second": 13.654,
|
| 428 |
+
"step": 18880
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 16.10169491525424,
|
| 432 |
+
"grad_norm": 12.1406831741333,
|
| 433 |
+
"learning_rate": 1.0696095076400678e-06,
|
| 434 |
+
"loss": 0.7949,
|
| 435 |
+
"step": 19000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 16.52542372881356,
|
| 439 |
+
"grad_norm": 6.812028884887695,
|
| 440 |
+
"learning_rate": 1.0186757215619695e-06,
|
| 441 |
+
"loss": 0.7859,
|
| 442 |
+
"step": 19500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 16.949152542372882,
|
| 446 |
+
"grad_norm": 19.037212371826172,
|
| 447 |
+
"learning_rate": 9.67741935483871e-07,
|
| 448 |
+
"loss": 0.7908,
|
| 449 |
+
"step": 20000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 17.0,
|
| 453 |
+
"eval_accuracy": 0.6059594755661502,
|
| 454 |
+
"eval_loss": 1.059761881828308,
|
| 455 |
+
"eval_model_preparation_time": 0.0035,
|
| 456 |
+
"eval_runtime": 228.7616,
|
| 457 |
+
"eval_samples_per_second": 110.027,
|
| 458 |
+
"eval_steps_per_second": 13.757,
|
| 459 |
+
"step": 20060
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 17.372881355932204,
|
| 463 |
+
"grad_norm": 14.513190269470215,
|
| 464 |
+
"learning_rate": 9.168081494057725e-07,
|
| 465 |
+
"loss": 0.7982,
|
| 466 |
+
"step": 20500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 17.796610169491526,
|
| 470 |
+
"grad_norm": 10.929338455200195,
|
| 471 |
+
"learning_rate": 8.658743633276741e-07,
|
| 472 |
+
"loss": 0.7715,
|
| 473 |
+
"step": 21000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 18.0,
|
| 477 |
+
"eval_accuracy": 0.609217322208979,
|
| 478 |
+
"eval_loss": 1.051367998123169,
|
| 479 |
+
"eval_model_preparation_time": 0.0035,
|
| 480 |
+
"eval_runtime": 228.3563,
|
| 481 |
+
"eval_samples_per_second": 110.223,
|
| 482 |
+
"eval_steps_per_second": 13.781,
|
| 483 |
+
"step": 21240
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 18.220338983050848,
|
| 487 |
+
"grad_norm": 8.468095779418945,
|
| 488 |
+
"learning_rate": 8.149405772495756e-07,
|
| 489 |
+
"loss": 0.7715,
|
| 490 |
+
"step": 21500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 18.64406779661017,
|
| 494 |
+
"grad_norm": 10.626036643981934,
|
| 495 |
+
"learning_rate": 7.640067911714771e-07,
|
| 496 |
+
"loss": 0.7693,
|
| 497 |
+
"step": 22000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 19.0,
|
| 501 |
+
"eval_accuracy": 0.6102502979737783,
|
| 502 |
+
"eval_loss": 1.0482922792434692,
|
| 503 |
+
"eval_model_preparation_time": 0.0035,
|
| 504 |
+
"eval_runtime": 226.5389,
|
| 505 |
+
"eval_samples_per_second": 111.107,
|
| 506 |
+
"eval_steps_per_second": 13.892,
|
| 507 |
+
"step": 22420
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 19.06779661016949,
|
| 511 |
+
"grad_norm": 9.89828872680664,
|
| 512 |
+
"learning_rate": 7.130730050933786e-07,
|
| 513 |
+
"loss": 0.7658,
|
| 514 |
+
"step": 22500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 19.491525423728813,
|
| 518 |
+
"grad_norm": 6.61522912979126,
|
| 519 |
+
"learning_rate": 6.621392190152802e-07,
|
| 520 |
+
"loss": 0.7604,
|
| 521 |
+
"step": 23000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 19.915254237288135,
|
| 525 |
+
"grad_norm": 7.224503517150879,
|
| 526 |
+
"learning_rate": 6.112054329371817e-07,
|
| 527 |
+
"loss": 0.7632,
|
| 528 |
+
"step": 23500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 20.0,
|
| 532 |
+
"eval_accuracy": 0.609217322208979,
|
| 533 |
+
"eval_loss": 1.0445903539657593,
|
| 534 |
+
"eval_model_preparation_time": 0.0035,
|
| 535 |
+
"eval_runtime": 228.7363,
|
| 536 |
+
"eval_samples_per_second": 110.039,
|
| 537 |
+
"eval_steps_per_second": 13.758,
|
| 538 |
+
"step": 23600
|
| 539 |
+
}
|
| 540 |
+
],
|
| 541 |
+
"logging_steps": 500,
|
| 542 |
+
"max_steps": 29500,
|
| 543 |
+
"num_input_tokens_seen": 0,
|
| 544 |
+
"num_train_epochs": 25,
|
| 545 |
+
"save_steps": 500,
|
| 546 |
+
"stateful_callbacks": {
|
| 547 |
+
"TrainerControl": {
|
| 548 |
+
"args": {
|
| 549 |
+
"should_epoch_stop": false,
|
| 550 |
+
"should_evaluate": false,
|
| 551 |
+
"should_log": false,
|
| 552 |
+
"should_save": true,
|
| 553 |
+
"should_training_stop": false
|
| 554 |
+
},
|
| 555 |
+
"attributes": {}
|
| 556 |
+
}
|
| 557 |
+
},
|
| 558 |
+
"total_flos": 5.851372376087952e+19,
|
| 559 |
+
"train_batch_size": 32,
|
| 560 |
+
"trial_name": null,
|
| 561 |
+
"trial_params": null
|
| 562 |
+
}
|
checkpoint-23600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f181ea4d6b78b8ebc76916156391c8b0e76c46c4d10c4f2ecf0d9c23a8f4912a
|
| 3 |
+
size 4859
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "sad",
|
| 13 |
+
"1": "disgust",
|
| 14 |
+
"2": "angry",
|
| 15 |
+
"3": "neutral",
|
| 16 |
+
"4": "fear",
|
| 17 |
+
"5": "surprise",
|
| 18 |
+
"6": "happy"
|
| 19 |
+
},
|
| 20 |
+
"image_size": 224,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"angry": 2,
|
| 25 |
+
"disgust": 1,
|
| 26 |
+
"fear": 4,
|
| 27 |
+
"happy": 6,
|
| 28 |
+
"neutral": 3,
|
| 29 |
+
"sad": 0,
|
| 30 |
+
"surprise": 5
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"model_type": "vit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"patch_size": 16,
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"qkv_bias": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.47.1"
|
| 42 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33773b4580db1e26a0b690c0fa200cf4c0844e95e4769e234a682b37712bed06
|
| 3 |
+
size 343239356
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f181ea4d6b78b8ebc76916156391c8b0e76c46c4d10c4f2ecf0d9c23a8f4912a
|
| 3 |
+
size 4859
|