Upload folder using huggingface_hub
Browse files- checkpoint-33509/config.json +32 -0
- checkpoint-33509/model.safetensors +3 -0
- checkpoint-33509/optimizer.pt +3 -0
- checkpoint-33509/preprocessor_config.json +22 -0
- checkpoint-33509/rng_state.pth +3 -0
- checkpoint-33509/scheduler.pt +3 -0
- checkpoint-33509/trainer_state.json +572 -0
- checkpoint-33509/training_args.bin +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-33509/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dima806/man_woman_face_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": "man",
|
| 13 |
+
"1": "woman"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"man": 0,
|
| 20 |
+
"woman": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.46.0"
|
| 32 |
+
}
|
checkpoint-33509/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90a5f09dfa56d4b30ecd35e061c7dea80d5ac10f60fd639de2654825a5b9aee8
|
| 3 |
+
size 343223968
|
checkpoint-33509/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dcdfadd0725bcea918d22e30d48486323af4a19b788364f0c11f2cb88247dfd
|
| 3 |
+
size 686568453
|
checkpoint-33509/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-33509/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4aeb28d1bcaca86640bcd07b93d266c4181779c48a9017079da978420880b460
|
| 3 |
+
size 14575
|
checkpoint-33509/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4591d00fc2ad5cc3c2058fe536ee73457f453a7b5d794896973192ecc627acff
|
| 3 |
+
size 627
|
checkpoint-33509/trainer_state.json
ADDED
|
@@ -0,0 +1,572 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.042002853006124496,
|
| 3 |
+
"best_model_checkpoint": "man_woman_face_image_detection/checkpoint-33509",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 33509,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.10444955086693128,
|
| 13 |
+
"grad_norm": 2.75286865234375,
|
| 14 |
+
"learning_rate": 9.865507038464987e-07,
|
| 15 |
+
"loss": 0.0606,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.20889910173386256,
|
| 20 |
+
"grad_norm": 0.4504856765270233,
|
| 21 |
+
"learning_rate": 9.716070414537195e-07,
|
| 22 |
+
"loss": 0.0604,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3133486526007938,
|
| 27 |
+
"grad_norm": 4.492558479309082,
|
| 28 |
+
"learning_rate": 9.566633790609401e-07,
|
| 29 |
+
"loss": 0.0553,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4177982034677251,
|
| 34 |
+
"grad_norm": 0.11193133890628815,
|
| 35 |
+
"learning_rate": 9.417197166681609e-07,
|
| 36 |
+
"loss": 0.0592,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5222477543346563,
|
| 41 |
+
"grad_norm": 3.955646514892578,
|
| 42 |
+
"learning_rate": 9.267760542753818e-07,
|
| 43 |
+
"loss": 0.0582,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6266973052015876,
|
| 48 |
+
"grad_norm": 0.09266256541013718,
|
| 49 |
+
"learning_rate": 9.118323918826025e-07,
|
| 50 |
+
"loss": 0.0599,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7311468560685189,
|
| 55 |
+
"grad_norm": 0.46259480714797974,
|
| 56 |
+
"learning_rate": 8.968887294898233e-07,
|
| 57 |
+
"loss": 0.0649,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8355964069354502,
|
| 62 |
+
"grad_norm": 0.03443637862801552,
|
| 63 |
+
"learning_rate": 8.819450670970441e-07,
|
| 64 |
+
"loss": 0.0566,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.9400459578023814,
|
| 69 |
+
"grad_norm": 2.622413158416748,
|
| 70 |
+
"learning_rate": 8.670014047042648e-07,
|
| 71 |
+
"loss": 0.0582,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0,
|
| 76 |
+
"eval_accuracy": 0.986144295170577,
|
| 77 |
+
"eval_loss": 0.04410167410969734,
|
| 78 |
+
"eval_model_preparation_time": 0.0053,
|
| 79 |
+
"eval_runtime": 1053.7087,
|
| 80 |
+
"eval_samples_per_second": 96.919,
|
| 81 |
+
"eval_steps_per_second": 12.115,
|
| 82 |
+
"step": 4787
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.0444955086693126,
|
| 86 |
+
"grad_norm": 1.0063446760177612,
|
| 87 |
+
"learning_rate": 8.520577423114857e-07,
|
| 88 |
+
"loss": 0.0626,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.148945059536244,
|
| 93 |
+
"grad_norm": 3.5057384967803955,
|
| 94 |
+
"learning_rate": 8.371140799187064e-07,
|
| 95 |
+
"loss": 0.0584,
|
| 96 |
+
"step": 5500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.2533946104031752,
|
| 100 |
+
"grad_norm": 0.10573850572109222,
|
| 101 |
+
"learning_rate": 8.221704175259272e-07,
|
| 102 |
+
"loss": 0.0576,
|
| 103 |
+
"step": 6000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.3578441612701067,
|
| 107 |
+
"grad_norm": 7.020801067352295,
|
| 108 |
+
"learning_rate": 8.07226755133148e-07,
|
| 109 |
+
"loss": 0.0543,
|
| 110 |
+
"step": 6500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.4622937121370378,
|
| 114 |
+
"grad_norm": 9.971087455749512,
|
| 115 |
+
"learning_rate": 7.922830927403687e-07,
|
| 116 |
+
"loss": 0.0517,
|
| 117 |
+
"step": 7000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.566743263003969,
|
| 121 |
+
"grad_norm": 3.649143695831299,
|
| 122 |
+
"learning_rate": 7.773394303475895e-07,
|
| 123 |
+
"loss": 0.0542,
|
| 124 |
+
"step": 7500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.6711928138709005,
|
| 128 |
+
"grad_norm": 0.7077023983001709,
|
| 129 |
+
"learning_rate": 7.623957679548103e-07,
|
| 130 |
+
"loss": 0.0576,
|
| 131 |
+
"step": 8000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.7756423647378317,
|
| 135 |
+
"grad_norm": 9.549636840820312,
|
| 136 |
+
"learning_rate": 7.474521055620311e-07,
|
| 137 |
+
"loss": 0.0558,
|
| 138 |
+
"step": 8500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.8800919156047629,
|
| 142 |
+
"grad_norm": 0.12657281756401062,
|
| 143 |
+
"learning_rate": 7.325084431692519e-07,
|
| 144 |
+
"loss": 0.0501,
|
| 145 |
+
"step": 9000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.9845414664716943,
|
| 149 |
+
"grad_norm": 4.699319362640381,
|
| 150 |
+
"learning_rate": 7.175647807764726e-07,
|
| 151 |
+
"loss": 0.0545,
|
| 152 |
+
"step": 9500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.0,
|
| 156 |
+
"eval_accuracy": 0.9864968078022796,
|
| 157 |
+
"eval_loss": 0.042747873812913895,
|
| 158 |
+
"eval_model_preparation_time": 0.0053,
|
| 159 |
+
"eval_runtime": 1036.1097,
|
| 160 |
+
"eval_samples_per_second": 98.565,
|
| 161 |
+
"eval_steps_per_second": 12.321,
|
| 162 |
+
"step": 9574
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.0889910173386252,
|
| 166 |
+
"grad_norm": 1.3633027076721191,
|
| 167 |
+
"learning_rate": 7.026211183836934e-07,
|
| 168 |
+
"loss": 0.0485,
|
| 169 |
+
"step": 10000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.1934405682055567,
|
| 173 |
+
"grad_norm": 0.850628137588501,
|
| 174 |
+
"learning_rate": 6.876774559909142e-07,
|
| 175 |
+
"loss": 0.0607,
|
| 176 |
+
"step": 10500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.297890119072488,
|
| 180 |
+
"grad_norm": 4.338198661804199,
|
| 181 |
+
"learning_rate": 6.72733793598135e-07,
|
| 182 |
+
"loss": 0.0541,
|
| 183 |
+
"step": 11000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.402339669939419,
|
| 187 |
+
"grad_norm": 0.07052299380302429,
|
| 188 |
+
"learning_rate": 6.577901312053558e-07,
|
| 189 |
+
"loss": 0.0505,
|
| 190 |
+
"step": 11500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.5067892208063505,
|
| 194 |
+
"grad_norm": 4.150068283081055,
|
| 195 |
+
"learning_rate": 6.428464688125765e-07,
|
| 196 |
+
"loss": 0.0546,
|
| 197 |
+
"step": 12000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.611238771673282,
|
| 201 |
+
"grad_norm": 0.10252227634191513,
|
| 202 |
+
"learning_rate": 6.279028064197973e-07,
|
| 203 |
+
"loss": 0.0498,
|
| 204 |
+
"step": 12500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.7156883225402133,
|
| 208 |
+
"grad_norm": 0.12012413889169693,
|
| 209 |
+
"learning_rate": 6.12959144027018e-07,
|
| 210 |
+
"loss": 0.0459,
|
| 211 |
+
"step": 13000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.8201378734071443,
|
| 215 |
+
"grad_norm": 1.6249473094940186,
|
| 216 |
+
"learning_rate": 5.980154816342389e-07,
|
| 217 |
+
"loss": 0.0469,
|
| 218 |
+
"step": 13500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.9245874242740757,
|
| 222 |
+
"grad_norm": 2.401695489883423,
|
| 223 |
+
"learning_rate": 5.830718192414597e-07,
|
| 224 |
+
"loss": 0.051,
|
| 225 |
+
"step": 14000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.0,
|
| 229 |
+
"eval_accuracy": 0.9866926481532254,
|
| 230 |
+
"eval_loss": 0.042268697172403336,
|
| 231 |
+
"eval_model_preparation_time": 0.0053,
|
| 232 |
+
"eval_runtime": 1031.115,
|
| 233 |
+
"eval_samples_per_second": 99.042,
|
| 234 |
+
"eval_steps_per_second": 12.381,
|
| 235 |
+
"step": 14361
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 3.0290369751410067,
|
| 239 |
+
"grad_norm": 1.793472170829773,
|
| 240 |
+
"learning_rate": 5.681281568486804e-07,
|
| 241 |
+
"loss": 0.0598,
|
| 242 |
+
"step": 14500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.133486526007938,
|
| 246 |
+
"grad_norm": 7.33253812789917,
|
| 247 |
+
"learning_rate": 5.531844944559012e-07,
|
| 248 |
+
"loss": 0.0477,
|
| 249 |
+
"step": 15000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.2379360768748695,
|
| 253 |
+
"grad_norm": 0.11843205243349075,
|
| 254 |
+
"learning_rate": 5.382408320631219e-07,
|
| 255 |
+
"loss": 0.0527,
|
| 256 |
+
"step": 15500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 3.342385627741801,
|
| 260 |
+
"grad_norm": 1.8657333850860596,
|
| 261 |
+
"learning_rate": 5.232971696703428e-07,
|
| 262 |
+
"loss": 0.054,
|
| 263 |
+
"step": 16000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.446835178608732,
|
| 267 |
+
"grad_norm": 4.304357528686523,
|
| 268 |
+
"learning_rate": 5.083535072775636e-07,
|
| 269 |
+
"loss": 0.0521,
|
| 270 |
+
"step": 16500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.5512847294756633,
|
| 274 |
+
"grad_norm": 0.2691272795200348,
|
| 275 |
+
"learning_rate": 4.934098448847843e-07,
|
| 276 |
+
"loss": 0.0516,
|
| 277 |
+
"step": 17000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 3.6557342803425943,
|
| 281 |
+
"grad_norm": 6.170676231384277,
|
| 282 |
+
"learning_rate": 4.784661824920051e-07,
|
| 283 |
+
"loss": 0.0463,
|
| 284 |
+
"step": 17500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.7601838312095257,
|
| 288 |
+
"grad_norm": 3.405898094177246,
|
| 289 |
+
"learning_rate": 4.635225200992259e-07,
|
| 290 |
+
"loss": 0.0519,
|
| 291 |
+
"step": 18000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.864633382076457,
|
| 295 |
+
"grad_norm": 2.52126145362854,
|
| 296 |
+
"learning_rate": 4.4857885770644665e-07,
|
| 297 |
+
"loss": 0.0494,
|
| 298 |
+
"step": 18500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.9690829329433885,
|
| 302 |
+
"grad_norm": 11.166853904724121,
|
| 303 |
+
"learning_rate": 4.336351953136674e-07,
|
| 304 |
+
"loss": 0.0457,
|
| 305 |
+
"step": 19000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.0,
|
| 309 |
+
"eval_accuracy": 0.9867220242058674,
|
| 310 |
+
"eval_loss": 0.043168142437934875,
|
| 311 |
+
"eval_model_preparation_time": 0.0053,
|
| 312 |
+
"eval_runtime": 1034.639,
|
| 313 |
+
"eval_samples_per_second": 98.705,
|
| 314 |
+
"eval_steps_per_second": 12.339,
|
| 315 |
+
"step": 19148
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.07353248381032,
|
| 319 |
+
"grad_norm": 0.24023988842964172,
|
| 320 |
+
"learning_rate": 4.1869153292088824e-07,
|
| 321 |
+
"loss": 0.0495,
|
| 322 |
+
"step": 19500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.1779820346772505,
|
| 326 |
+
"grad_norm": 7.678467273712158,
|
| 327 |
+
"learning_rate": 4.03747870528109e-07,
|
| 328 |
+
"loss": 0.0525,
|
| 329 |
+
"step": 20000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 4.282431585544182,
|
| 333 |
+
"grad_norm": 0.244981586933136,
|
| 334 |
+
"learning_rate": 3.8880420813532977e-07,
|
| 335 |
+
"loss": 0.0507,
|
| 336 |
+
"step": 20500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.386881136411113,
|
| 340 |
+
"grad_norm": 0.22300060093402863,
|
| 341 |
+
"learning_rate": 3.7386054574255054e-07,
|
| 342 |
+
"loss": 0.0509,
|
| 343 |
+
"step": 21000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 4.491330687278045,
|
| 347 |
+
"grad_norm": 5.288808345794678,
|
| 348 |
+
"learning_rate": 3.589168833497713e-07,
|
| 349 |
+
"loss": 0.0474,
|
| 350 |
+
"step": 21500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.595780238144976,
|
| 354 |
+
"grad_norm": 1.9191228151321411,
|
| 355 |
+
"learning_rate": 3.4397322095699213e-07,
|
| 356 |
+
"loss": 0.0488,
|
| 357 |
+
"step": 22000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.700229789011908,
|
| 361 |
+
"grad_norm": 5.287907123565674,
|
| 362 |
+
"learning_rate": 3.290295585642129e-07,
|
| 363 |
+
"loss": 0.0459,
|
| 364 |
+
"step": 22500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.804679339878838,
|
| 368 |
+
"grad_norm": 0.1149277314543724,
|
| 369 |
+
"learning_rate": 3.1408589617143366e-07,
|
| 370 |
+
"loss": 0.0447,
|
| 371 |
+
"step": 23000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 4.9091288907457695,
|
| 375 |
+
"grad_norm": 3.53507137298584,
|
| 376 |
+
"learning_rate": 2.9914223377865443e-07,
|
| 377 |
+
"loss": 0.0523,
|
| 378 |
+
"step": 23500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 5.0,
|
| 382 |
+
"eval_accuracy": 0.9870353687673808,
|
| 383 |
+
"eval_loss": 0.0422465056180954,
|
| 384 |
+
"eval_model_preparation_time": 0.0053,
|
| 385 |
+
"eval_runtime": 991.7535,
|
| 386 |
+
"eval_samples_per_second": 102.973,
|
| 387 |
+
"eval_steps_per_second": 12.872,
|
| 388 |
+
"step": 23935
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 5.013578441612701,
|
| 392 |
+
"grad_norm": 0.036819346249103546,
|
| 393 |
+
"learning_rate": 2.841985713858752e-07,
|
| 394 |
+
"loss": 0.0495,
|
| 395 |
+
"step": 24000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 5.118027992479632,
|
| 399 |
+
"grad_norm": 3.238111972808838,
|
| 400 |
+
"learning_rate": 2.69254908993096e-07,
|
| 401 |
+
"loss": 0.0507,
|
| 402 |
+
"step": 24500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.222477543346564,
|
| 406 |
+
"grad_norm": 0.4373936951160431,
|
| 407 |
+
"learning_rate": 2.543112466003168e-07,
|
| 408 |
+
"loss": 0.0499,
|
| 409 |
+
"step": 25000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 5.326927094213495,
|
| 413 |
+
"grad_norm": 0.06157074496150017,
|
| 414 |
+
"learning_rate": 2.393675842075376e-07,
|
| 415 |
+
"loss": 0.0481,
|
| 416 |
+
"step": 25500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 5.431376645080427,
|
| 420 |
+
"grad_norm": 0.5681213140487671,
|
| 421 |
+
"learning_rate": 2.2442392181475835e-07,
|
| 422 |
+
"loss": 0.048,
|
| 423 |
+
"step": 26000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.535826195947357,
|
| 427 |
+
"grad_norm": 0.2663944661617279,
|
| 428 |
+
"learning_rate": 2.0948025942197914e-07,
|
| 429 |
+
"loss": 0.0498,
|
| 430 |
+
"step": 26500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 5.640275746814289,
|
| 434 |
+
"grad_norm": 0.38863956928253174,
|
| 435 |
+
"learning_rate": 1.945365970291999e-07,
|
| 436 |
+
"loss": 0.0455,
|
| 437 |
+
"step": 27000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 5.74472529768122,
|
| 441 |
+
"grad_norm": 1.1037393808364868,
|
| 442 |
+
"learning_rate": 1.795929346364207e-07,
|
| 443 |
+
"loss": 0.0465,
|
| 444 |
+
"step": 27500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 5.849174848548151,
|
| 448 |
+
"grad_norm": 0.06277265399694443,
|
| 449 |
+
"learning_rate": 1.6464927224364147e-07,
|
| 450 |
+
"loss": 0.0443,
|
| 451 |
+
"step": 28000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 5.953624399415083,
|
| 455 |
+
"grad_norm": 0.3379976153373718,
|
| 456 |
+
"learning_rate": 1.4970560985086224e-07,
|
| 457 |
+
"loss": 0.0457,
|
| 458 |
+
"step": 28500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 6.0,
|
| 462 |
+
"eval_accuracy": 0.9869570326270025,
|
| 463 |
+
"eval_loss": 0.04241248220205307,
|
| 464 |
+
"eval_model_preparation_time": 0.0053,
|
| 465 |
+
"eval_runtime": 1029.9456,
|
| 466 |
+
"eval_samples_per_second": 99.155,
|
| 467 |
+
"eval_steps_per_second": 12.395,
|
| 468 |
+
"step": 28722
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 6.058073950282013,
|
| 472 |
+
"grad_norm": 4.613526821136475,
|
| 473 |
+
"learning_rate": 1.3476194745808303e-07,
|
| 474 |
+
"loss": 0.0428,
|
| 475 |
+
"step": 29000
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 6.162523501148945,
|
| 479 |
+
"grad_norm": 0.2739298641681671,
|
| 480 |
+
"learning_rate": 1.198182850653038e-07,
|
| 481 |
+
"loss": 0.0474,
|
| 482 |
+
"step": 29500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.266973052015876,
|
| 486 |
+
"grad_norm": 0.4624876379966736,
|
| 487 |
+
"learning_rate": 1.0487462267252457e-07,
|
| 488 |
+
"loss": 0.0526,
|
| 489 |
+
"step": 30000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 6.371422602882808,
|
| 493 |
+
"grad_norm": 1.4040108919143677,
|
| 494 |
+
"learning_rate": 8.993096027974535e-08,
|
| 495 |
+
"loss": 0.0449,
|
| 496 |
+
"step": 30500
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 6.475872153749739,
|
| 500 |
+
"grad_norm": 0.09033941477537155,
|
| 501 |
+
"learning_rate": 7.498729788696613e-08,
|
| 502 |
+
"loss": 0.0515,
|
| 503 |
+
"step": 31000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 6.58032170461667,
|
| 507 |
+
"grad_norm": 0.250262588262558,
|
| 508 |
+
"learning_rate": 6.004363549418691e-08,
|
| 509 |
+
"loss": 0.0467,
|
| 510 |
+
"step": 31500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 6.684771255483602,
|
| 514 |
+
"grad_norm": 1.7938841581344604,
|
| 515 |
+
"learning_rate": 4.509997310140769e-08,
|
| 516 |
+
"loss": 0.0545,
|
| 517 |
+
"step": 32000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 6.789220806350532,
|
| 521 |
+
"grad_norm": 0.6938722729682922,
|
| 522 |
+
"learning_rate": 3.015631070862847e-08,
|
| 523 |
+
"loss": 0.0485,
|
| 524 |
+
"step": 32500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.893670357217464,
|
| 528 |
+
"grad_norm": 0.07981687039136887,
|
| 529 |
+
"learning_rate": 1.5212648315849248e-08,
|
| 530 |
+
"loss": 0.0471,
|
| 531 |
+
"step": 33000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 6.998119908084395,
|
| 535 |
+
"grad_norm": 1.794087290763855,
|
| 536 |
+
"learning_rate": 2.6898592307002603e-10,
|
| 537 |
+
"loss": 0.0441,
|
| 538 |
+
"step": 33500
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 7.0,
|
| 542 |
+
"eval_accuracy": 0.9871137049077592,
|
| 543 |
+
"eval_loss": 0.042002853006124496,
|
| 544 |
+
"eval_model_preparation_time": 0.0053,
|
| 545 |
+
"eval_runtime": 1039.9182,
|
| 546 |
+
"eval_samples_per_second": 98.204,
|
| 547 |
+
"eval_steps_per_second": 12.276,
|
| 548 |
+
"step": 33509
|
| 549 |
+
}
|
| 550 |
+
],
|
| 551 |
+
"logging_steps": 500,
|
| 552 |
+
"max_steps": 33509,
|
| 553 |
+
"num_input_tokens_seen": 0,
|
| 554 |
+
"num_train_epochs": 7,
|
| 555 |
+
"save_steps": 500,
|
| 556 |
+
"stateful_callbacks": {
|
| 557 |
+
"TrainerControl": {
|
| 558 |
+
"args": {
|
| 559 |
+
"should_epoch_stop": false,
|
| 560 |
+
"should_evaluate": false,
|
| 561 |
+
"should_log": false,
|
| 562 |
+
"should_save": true,
|
| 563 |
+
"should_training_stop": true
|
| 564 |
+
},
|
| 565 |
+
"attributes": {}
|
| 566 |
+
}
|
| 567 |
+
},
|
| 568 |
+
"total_flos": 8.309373055985163e+19,
|
| 569 |
+
"train_batch_size": 32,
|
| 570 |
+
"trial_name": null,
|
| 571 |
+
"trial_params": null
|
| 572 |
+
}
|
checkpoint-33509/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f14dd56d897ca4c82817bd8ffc3fef58a0a0fcd162158e68e2dcc22f1ced3ee
|
| 3 |
+
size 4731
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343223968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90a5f09dfa56d4b30ecd35e061c7dea80d5ac10f60fd639de2654825a5b9aee8
|
| 3 |
size 343223968
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4731
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f14dd56d897ca4c82817bd8ffc3fef58a0a0fcd162158e68e2dcc22f1ced3ee
|
| 3 |
size 4731
|