Upload folder using huggingface_hub
Browse files- checkpoint-15680/config.json +74 -0
- checkpoint-15680/model.safetensors +3 -0
- checkpoint-15680/optimizer.pt +3 -0
- checkpoint-15680/preprocessor_config.json +22 -0
- checkpoint-15680/rng_state.pth +3 -0
- checkpoint-15680/scheduler.pt +3 -0
- checkpoint-15680/trainer_state.json +646 -0
- checkpoint-15680/training_args.bin +3 -0
- config.json +32 -34
- model.safetensors +2 -2
- training_args.bin +1 -1
checkpoint-15680/config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "01",
|
| 13 |
+
"1": "02",
|
| 14 |
+
"2": "03",
|
| 15 |
+
"3": "04",
|
| 16 |
+
"4": "05",
|
| 17 |
+
"5": "06-07",
|
| 18 |
+
"6": "08-09",
|
| 19 |
+
"7": "10-12",
|
| 20 |
+
"8": "13-15",
|
| 21 |
+
"9": "16-20",
|
| 22 |
+
"10": "21-25",
|
| 23 |
+
"11": "26-30",
|
| 24 |
+
"12": "31-35",
|
| 25 |
+
"13": "36-40",
|
| 26 |
+
"14": "41-45",
|
| 27 |
+
"15": "46-50",
|
| 28 |
+
"16": "51-55",
|
| 29 |
+
"17": "56-60",
|
| 30 |
+
"18": "61-65",
|
| 31 |
+
"19": "66-70",
|
| 32 |
+
"20": "71-80",
|
| 33 |
+
"21": "81-90",
|
| 34 |
+
"22": "90+"
|
| 35 |
+
},
|
| 36 |
+
"image_size": 224,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"intermediate_size": 3072,
|
| 39 |
+
"label2id": {
|
| 40 |
+
"01": 0,
|
| 41 |
+
"02": 1,
|
| 42 |
+
"03": 2,
|
| 43 |
+
"04": 3,
|
| 44 |
+
"05": 4,
|
| 45 |
+
"06-07": 5,
|
| 46 |
+
"08-09": 6,
|
| 47 |
+
"10-12": 7,
|
| 48 |
+
"13-15": 8,
|
| 49 |
+
"16-20": 9,
|
| 50 |
+
"21-25": 10,
|
| 51 |
+
"26-30": 11,
|
| 52 |
+
"31-35": 12,
|
| 53 |
+
"36-40": 13,
|
| 54 |
+
"41-45": 14,
|
| 55 |
+
"46-50": 15,
|
| 56 |
+
"51-55": 16,
|
| 57 |
+
"56-60": 17,
|
| 58 |
+
"61-65": 18,
|
| 59 |
+
"66-70": 19,
|
| 60 |
+
"71-80": 20,
|
| 61 |
+
"81-90": 21,
|
| 62 |
+
"90+": 22
|
| 63 |
+
},
|
| 64 |
+
"layer_norm_eps": 1e-12,
|
| 65 |
+
"model_type": "vit",
|
| 66 |
+
"num_attention_heads": 12,
|
| 67 |
+
"num_channels": 3,
|
| 68 |
+
"num_hidden_layers": 12,
|
| 69 |
+
"patch_size": 16,
|
| 70 |
+
"problem_type": "single_label_classification",
|
| 71 |
+
"qkv_bias": true,
|
| 72 |
+
"torch_dtype": "float32",
|
| 73 |
+
"transformers_version": "4.35.0"
|
| 74 |
+
}
|
checkpoint-15680/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a63ea460c98a52e8bcfec2f3c809237b00fc0d2b500c3c22931b40d44716a89
|
| 3 |
+
size 343288572
|
checkpoint-15680/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e35ffa8d8551b558989b2cdc71698b325ca62bef53a45aa68451429b6431648
|
| 3 |
+
size 686697605
|
checkpoint-15680/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-15680/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af0eb2d80c5b666462bdf4036f202d6bf53049dd371621d2c5d88b2d37f2e8f9
|
| 3 |
+
size 14575
|
checkpoint-15680/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bda6364fb66beb98cceb41a2941e9310c217422f1c6a27aee2084e99292bcea
|
| 3 |
+
size 627
|
checkpoint-15680/trainer_state.json
ADDED
|
@@ -0,0 +1,646 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.5390384197235107,
|
| 3 |
+
"best_model_checkpoint": "facial_age_image_detection/checkpoint-15680",
|
| 4 |
+
"epoch": 49.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 15680,
|
| 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": 0.22556684910086006,
|
| 14 |
+
"eval_loss": 2.945213556289673,
|
| 15 |
+
"eval_runtime": 51.2577,
|
| 16 |
+
"eval_samples_per_second": 99.809,
|
| 17 |
+
"eval_steps_per_second": 3.121,
|
| 18 |
+
"step": 320
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.56,
|
| 22 |
+
"learning_rate": 2.915360501567398e-06,
|
| 23 |
+
"loss": 2.913,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.2580140734949179,
|
| 29 |
+
"eval_loss": 2.7111563682556152,
|
| 30 |
+
"eval_runtime": 50.9659,
|
| 31 |
+
"eval_samples_per_second": 100.381,
|
| 32 |
+
"eval_steps_per_second": 3.139,
|
| 33 |
+
"step": 640
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.2922204847537138,
|
| 38 |
+
"eval_loss": 2.557264804840088,
|
| 39 |
+
"eval_runtime": 51.3801,
|
| 40 |
+
"eval_samples_per_second": 99.572,
|
| 41 |
+
"eval_steps_per_second": 3.114,
|
| 42 |
+
"step": 960
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.12,
|
| 46 |
+
"learning_rate": 2.821316614420063e-06,
|
| 47 |
+
"loss": 2.4834,
|
| 48 |
+
"step": 1000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.3027756059421423,
|
| 53 |
+
"eval_loss": 2.448474645614624,
|
| 54 |
+
"eval_runtime": 51.2195,
|
| 55 |
+
"eval_samples_per_second": 99.884,
|
| 56 |
+
"eval_steps_per_second": 3.124,
|
| 57 |
+
"step": 1280
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.69,
|
| 61 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 62 |
+
"loss": 2.246,
|
| 63 |
+
"step": 1500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
+
"eval_accuracy": 0.31841282251759184,
|
| 68 |
+
"eval_loss": 2.3704957962036133,
|
| 69 |
+
"eval_runtime": 51.7745,
|
| 70 |
+
"eval_samples_per_second": 98.813,
|
| 71 |
+
"eval_steps_per_second": 3.09,
|
| 72 |
+
"step": 1600
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.3348318999218139,
|
| 77 |
+
"eval_loss": 2.298917055130005,
|
| 78 |
+
"eval_runtime": 51.1066,
|
| 79 |
+
"eval_samples_per_second": 100.104,
|
| 80 |
+
"eval_steps_per_second": 3.131,
|
| 81 |
+
"step": 1920
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.25,
|
| 85 |
+
"learning_rate": 2.633228840125392e-06,
|
| 86 |
+
"loss": 2.1013,
|
| 87 |
+
"step": 2000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 7.0,
|
| 91 |
+
"eval_accuracy": 0.3336591086786552,
|
| 92 |
+
"eval_loss": 2.2518346309661865,
|
| 93 |
+
"eval_runtime": 51.0284,
|
| 94 |
+
"eval_samples_per_second": 100.258,
|
| 95 |
+
"eval_steps_per_second": 3.136,
|
| 96 |
+
"step": 2240
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 7.81,
|
| 100 |
+
"learning_rate": 2.5391849529780565e-06,
|
| 101 |
+
"loss": 1.992,
|
| 102 |
+
"step": 2500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 8.0,
|
| 106 |
+
"eval_accuracy": 0.3506645817044566,
|
| 107 |
+
"eval_loss": 2.195549249649048,
|
| 108 |
+
"eval_runtime": 50.666,
|
| 109 |
+
"eval_samples_per_second": 100.975,
|
| 110 |
+
"eval_steps_per_second": 3.158,
|
| 111 |
+
"step": 2560
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 9.0,
|
| 115 |
+
"eval_accuracy": 0.3596559812353401,
|
| 116 |
+
"eval_loss": 2.1464827060699463,
|
| 117 |
+
"eval_runtime": 51.2548,
|
| 118 |
+
"eval_samples_per_second": 99.815,
|
| 119 |
+
"eval_steps_per_second": 3.122,
|
| 120 |
+
"step": 2880
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.38,
|
| 124 |
+
"learning_rate": 2.445141065830721e-06,
|
| 125 |
+
"loss": 1.9057,
|
| 126 |
+
"step": 3000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 10.0,
|
| 130 |
+
"eval_accuracy": 0.3844800625488663,
|
| 131 |
+
"eval_loss": 2.097637176513672,
|
| 132 |
+
"eval_runtime": 51.7915,
|
| 133 |
+
"eval_samples_per_second": 98.781,
|
| 134 |
+
"eval_steps_per_second": 3.089,
|
| 135 |
+
"step": 3200
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.94,
|
| 139 |
+
"learning_rate": 2.3510971786833857e-06,
|
| 140 |
+
"loss": 1.8272,
|
| 141 |
+
"step": 3500
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 11.0,
|
| 145 |
+
"eval_accuracy": 0.3784206411258796,
|
| 146 |
+
"eval_loss": 2.0678927898406982,
|
| 147 |
+
"eval_runtime": 52.5229,
|
| 148 |
+
"eval_samples_per_second": 97.405,
|
| 149 |
+
"eval_steps_per_second": 3.046,
|
| 150 |
+
"step": 3520
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 12.0,
|
| 154 |
+
"eval_accuracy": 0.388975762314308,
|
| 155 |
+
"eval_loss": 2.0365805625915527,
|
| 156 |
+
"eval_runtime": 52.5303,
|
| 157 |
+
"eval_samples_per_second": 97.391,
|
| 158 |
+
"eval_steps_per_second": 3.046,
|
| 159 |
+
"step": 3840
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.5,
|
| 163 |
+
"learning_rate": 2.2570532915360503e-06,
|
| 164 |
+
"loss": 1.7607,
|
| 165 |
+
"step": 4000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 13.0,
|
| 169 |
+
"eval_accuracy": 0.4012900703674746,
|
| 170 |
+
"eval_loss": 1.9932725429534912,
|
| 171 |
+
"eval_runtime": 51.4196,
|
| 172 |
+
"eval_samples_per_second": 99.495,
|
| 173 |
+
"eval_steps_per_second": 3.112,
|
| 174 |
+
"step": 4160
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 14.0,
|
| 178 |
+
"eval_accuracy": 0.39190774042220483,
|
| 179 |
+
"eval_loss": 1.9702576398849487,
|
| 180 |
+
"eval_runtime": 51.6324,
|
| 181 |
+
"eval_samples_per_second": 99.085,
|
| 182 |
+
"eval_steps_per_second": 3.099,
|
| 183 |
+
"step": 4480
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 14.06,
|
| 187 |
+
"learning_rate": 2.163009404388715e-06,
|
| 188 |
+
"loss": 1.7033,
|
| 189 |
+
"step": 4500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 15.0,
|
| 193 |
+
"eval_accuracy": 0.39874902267396406,
|
| 194 |
+
"eval_loss": 1.9390950202941895,
|
| 195 |
+
"eval_runtime": 51.5713,
|
| 196 |
+
"eval_samples_per_second": 99.203,
|
| 197 |
+
"eval_steps_per_second": 3.103,
|
| 198 |
+
"step": 4800
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 15.62,
|
| 202 |
+
"learning_rate": 2.0689655172413796e-06,
|
| 203 |
+
"loss": 1.6414,
|
| 204 |
+
"step": 5000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 16.0,
|
| 208 |
+
"eval_accuracy": 0.40187646598905397,
|
| 209 |
+
"eval_loss": 1.914416790008545,
|
| 210 |
+
"eval_runtime": 51.2253,
|
| 211 |
+
"eval_samples_per_second": 99.872,
|
| 212 |
+
"eval_steps_per_second": 3.123,
|
| 213 |
+
"step": 5120
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 17.0,
|
| 217 |
+
"eval_accuracy": 0.405199374511337,
|
| 218 |
+
"eval_loss": 1.8871612548828125,
|
| 219 |
+
"eval_runtime": 51.1314,
|
| 220 |
+
"eval_samples_per_second": 100.056,
|
| 221 |
+
"eval_steps_per_second": 3.129,
|
| 222 |
+
"step": 5440
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 17.19,
|
| 226 |
+
"learning_rate": 1.9749216300940438e-06,
|
| 227 |
+
"loss": 1.5939,
|
| 228 |
+
"step": 5500
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 18.0,
|
| 232 |
+
"eval_accuracy": 0.40852228303362004,
|
| 233 |
+
"eval_loss": 1.8684996366500854,
|
| 234 |
+
"eval_runtime": 52.2991,
|
| 235 |
+
"eval_samples_per_second": 97.822,
|
| 236 |
+
"eval_steps_per_second": 3.059,
|
| 237 |
+
"step": 5760
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 18.75,
|
| 241 |
+
"learning_rate": 1.8808777429467086e-06,
|
| 242 |
+
"loss": 1.5461,
|
| 243 |
+
"step": 6000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 19.0,
|
| 247 |
+
"eval_accuracy": 0.4161454261141517,
|
| 248 |
+
"eval_loss": 1.842322587966919,
|
| 249 |
+
"eval_runtime": 51.5547,
|
| 250 |
+
"eval_samples_per_second": 99.234,
|
| 251 |
+
"eval_steps_per_second": 3.104,
|
| 252 |
+
"step": 6080
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 20.0,
|
| 256 |
+
"eval_accuracy": 0.41575449569976547,
|
| 257 |
+
"eval_loss": 1.8240511417388916,
|
| 258 |
+
"eval_runtime": 51.0599,
|
| 259 |
+
"eval_samples_per_second": 100.196,
|
| 260 |
+
"eval_steps_per_second": 3.134,
|
| 261 |
+
"step": 6400
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 20.31,
|
| 265 |
+
"learning_rate": 1.786833855799373e-06,
|
| 266 |
+
"loss": 1.5016,
|
| 267 |
+
"step": 6500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 21.0,
|
| 271 |
+
"eval_accuracy": 0.4245504300234558,
|
| 272 |
+
"eval_loss": 1.7987163066864014,
|
| 273 |
+
"eval_runtime": 52.1072,
|
| 274 |
+
"eval_samples_per_second": 98.182,
|
| 275 |
+
"eval_steps_per_second": 3.071,
|
| 276 |
+
"step": 6720
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 21.88,
|
| 280 |
+
"learning_rate": 1.6927899686520374e-06,
|
| 281 |
+
"loss": 1.4636,
|
| 282 |
+
"step": 7000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 22.0,
|
| 286 |
+
"eval_accuracy": 0.42865519937451135,
|
| 287 |
+
"eval_loss": 1.777077078819275,
|
| 288 |
+
"eval_runtime": 51.2408,
|
| 289 |
+
"eval_samples_per_second": 99.842,
|
| 290 |
+
"eval_steps_per_second": 3.123,
|
| 291 |
+
"step": 7040
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 23.0,
|
| 295 |
+
"eval_accuracy": 0.4292415949960907,
|
| 296 |
+
"eval_loss": 1.7641410827636719,
|
| 297 |
+
"eval_runtime": 51.4723,
|
| 298 |
+
"eval_samples_per_second": 99.393,
|
| 299 |
+
"eval_steps_per_second": 3.108,
|
| 300 |
+
"step": 7360
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 23.44,
|
| 304 |
+
"learning_rate": 1.5987460815047023e-06,
|
| 305 |
+
"loss": 1.4204,
|
| 306 |
+
"step": 7500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 24.0,
|
| 310 |
+
"eval_accuracy": 0.4462470680218921,
|
| 311 |
+
"eval_loss": 1.7357829809188843,
|
| 312 |
+
"eval_runtime": 51.0544,
|
| 313 |
+
"eval_samples_per_second": 100.207,
|
| 314 |
+
"eval_steps_per_second": 3.134,
|
| 315 |
+
"step": 7680
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 25.0,
|
| 319 |
+
"learning_rate": 1.5047021943573667e-06,
|
| 320 |
+
"loss": 1.3845,
|
| 321 |
+
"step": 8000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 25.0,
|
| 325 |
+
"eval_accuracy": 0.4472243940578577,
|
| 326 |
+
"eval_loss": 1.7216110229492188,
|
| 327 |
+
"eval_runtime": 51.2122,
|
| 328 |
+
"eval_samples_per_second": 99.898,
|
| 329 |
+
"eval_steps_per_second": 3.124,
|
| 330 |
+
"step": 8000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 26.0,
|
| 334 |
+
"eval_accuracy": 0.45054730258014075,
|
| 335 |
+
"eval_loss": 1.7076504230499268,
|
| 336 |
+
"eval_runtime": 51.4157,
|
| 337 |
+
"eval_samples_per_second": 99.503,
|
| 338 |
+
"eval_steps_per_second": 3.112,
|
| 339 |
+
"step": 8320
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 26.56,
|
| 343 |
+
"learning_rate": 1.4106583072100315e-06,
|
| 344 |
+
"loss": 1.3521,
|
| 345 |
+
"step": 8500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 27.0,
|
| 349 |
+
"eval_accuracy": 0.45347928068803756,
|
| 350 |
+
"eval_loss": 1.6927095651626587,
|
| 351 |
+
"eval_runtime": 51.5458,
|
| 352 |
+
"eval_samples_per_second": 99.252,
|
| 353 |
+
"eval_steps_per_second": 3.104,
|
| 354 |
+
"step": 8640
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 28.0,
|
| 358 |
+
"eval_accuracy": 0.45856137607505865,
|
| 359 |
+
"eval_loss": 1.6739999055862427,
|
| 360 |
+
"eval_runtime": 51.4056,
|
| 361 |
+
"eval_samples_per_second": 99.522,
|
| 362 |
+
"eval_steps_per_second": 3.112,
|
| 363 |
+
"step": 8960
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 28.12,
|
| 367 |
+
"learning_rate": 1.316614420062696e-06,
|
| 368 |
+
"loss": 1.322,
|
| 369 |
+
"step": 9000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 29.0,
|
| 373 |
+
"eval_accuracy": 0.45269741985926504,
|
| 374 |
+
"eval_loss": 1.6700100898742676,
|
| 375 |
+
"eval_runtime": 51.1233,
|
| 376 |
+
"eval_samples_per_second": 100.072,
|
| 377 |
+
"eval_steps_per_second": 3.13,
|
| 378 |
+
"step": 9280
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 29.69,
|
| 382 |
+
"learning_rate": 1.2225705329153605e-06,
|
| 383 |
+
"loss": 1.2923,
|
| 384 |
+
"step": 9500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 30.0,
|
| 388 |
+
"eval_accuracy": 0.46325254104769353,
|
| 389 |
+
"eval_loss": 1.648740291595459,
|
| 390 |
+
"eval_runtime": 52.5113,
|
| 391 |
+
"eval_samples_per_second": 97.427,
|
| 392 |
+
"eval_steps_per_second": 3.047,
|
| 393 |
+
"step": 9600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 31.0,
|
| 397 |
+
"eval_accuracy": 0.4611024237685692,
|
| 398 |
+
"eval_loss": 1.6401363611221313,
|
| 399 |
+
"eval_runtime": 52.7667,
|
| 400 |
+
"eval_samples_per_second": 96.955,
|
| 401 |
+
"eval_steps_per_second": 3.032,
|
| 402 |
+
"step": 9920
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 31.25,
|
| 406 |
+
"learning_rate": 1.1285266457680252e-06,
|
| 407 |
+
"loss": 1.2658,
|
| 408 |
+
"step": 10000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 32.0,
|
| 412 |
+
"eval_accuracy": 0.47146207974980453,
|
| 413 |
+
"eval_loss": 1.6254924535751343,
|
| 414 |
+
"eval_runtime": 52.1102,
|
| 415 |
+
"eval_samples_per_second": 98.177,
|
| 416 |
+
"eval_steps_per_second": 3.07,
|
| 417 |
+
"step": 10240
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 32.81,
|
| 421 |
+
"learning_rate": 1.0344827586206898e-06,
|
| 422 |
+
"loss": 1.245,
|
| 423 |
+
"step": 10500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 33.0,
|
| 427 |
+
"eval_accuracy": 0.4683346364347146,
|
| 428 |
+
"eval_loss": 1.6232922077178955,
|
| 429 |
+
"eval_runtime": 50.6089,
|
| 430 |
+
"eval_samples_per_second": 101.089,
|
| 431 |
+
"eval_steps_per_second": 3.161,
|
| 432 |
+
"step": 10560
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 34.0,
|
| 436 |
+
"eval_accuracy": 0.47439405785770133,
|
| 437 |
+
"eval_loss": 1.6077964305877686,
|
| 438 |
+
"eval_runtime": 53.7216,
|
| 439 |
+
"eval_samples_per_second": 95.232,
|
| 440 |
+
"eval_steps_per_second": 2.978,
|
| 441 |
+
"step": 10880
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 34.38,
|
| 445 |
+
"learning_rate": 9.404388714733543e-07,
|
| 446 |
+
"loss": 1.2201,
|
| 447 |
+
"step": 11000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 35.0,
|
| 451 |
+
"eval_accuracy": 0.47537138389366695,
|
| 452 |
+
"eval_loss": 1.5978459119796753,
|
| 453 |
+
"eval_runtime": 51.1056,
|
| 454 |
+
"eval_samples_per_second": 100.107,
|
| 455 |
+
"eval_steps_per_second": 3.131,
|
| 456 |
+
"step": 11200
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 35.94,
|
| 460 |
+
"learning_rate": 8.463949843260187e-07,
|
| 461 |
+
"loss": 1.1993,
|
| 462 |
+
"step": 11500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 36.0,
|
| 466 |
+
"eval_accuracy": 0.47556684910086006,
|
| 467 |
+
"eval_loss": 1.5951019525527954,
|
| 468 |
+
"eval_runtime": 51.3095,
|
| 469 |
+
"eval_samples_per_second": 99.709,
|
| 470 |
+
"eval_steps_per_second": 3.118,
|
| 471 |
+
"step": 11520
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 37.0,
|
| 475 |
+
"eval_accuracy": 0.4734167318217357,
|
| 476 |
+
"eval_loss": 1.58991539478302,
|
| 477 |
+
"eval_runtime": 50.7545,
|
| 478 |
+
"eval_samples_per_second": 100.799,
|
| 479 |
+
"eval_steps_per_second": 3.152,
|
| 480 |
+
"step": 11840
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 37.5,
|
| 484 |
+
"learning_rate": 7.523510971786833e-07,
|
| 485 |
+
"loss": 1.1829,
|
| 486 |
+
"step": 12000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 38.0,
|
| 490 |
+
"eval_accuracy": 0.4794761532447224,
|
| 491 |
+
"eval_loss": 1.5782525539398193,
|
| 492 |
+
"eval_runtime": 51.9408,
|
| 493 |
+
"eval_samples_per_second": 98.497,
|
| 494 |
+
"eval_steps_per_second": 3.08,
|
| 495 |
+
"step": 12160
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 39.0,
|
| 499 |
+
"eval_accuracy": 0.48964034401876466,
|
| 500 |
+
"eval_loss": 1.5660046339035034,
|
| 501 |
+
"eval_runtime": 51.4816,
|
| 502 |
+
"eval_samples_per_second": 99.375,
|
| 503 |
+
"eval_steps_per_second": 3.108,
|
| 504 |
+
"step": 12480
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 39.06,
|
| 508 |
+
"learning_rate": 6.58307210031348e-07,
|
| 509 |
+
"loss": 1.1693,
|
| 510 |
+
"step": 12500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 40.0,
|
| 514 |
+
"eval_accuracy": 0.4822126661454261,
|
| 515 |
+
"eval_loss": 1.564785122871399,
|
| 516 |
+
"eval_runtime": 51.6845,
|
| 517 |
+
"eval_samples_per_second": 98.985,
|
| 518 |
+
"eval_steps_per_second": 3.096,
|
| 519 |
+
"step": 12800
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 40.62,
|
| 523 |
+
"learning_rate": 5.642633228840126e-07,
|
| 524 |
+
"loss": 1.1526,
|
| 525 |
+
"step": 13000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 41.0,
|
| 529 |
+
"eval_accuracy": 0.48377638780297105,
|
| 530 |
+
"eval_loss": 1.5616761445999146,
|
| 531 |
+
"eval_runtime": 51.6796,
|
| 532 |
+
"eval_samples_per_second": 98.995,
|
| 533 |
+
"eval_steps_per_second": 3.096,
|
| 534 |
+
"step": 13120
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 42.0,
|
| 538 |
+
"eval_accuracy": 0.4878811571540266,
|
| 539 |
+
"eval_loss": 1.555199384689331,
|
| 540 |
+
"eval_runtime": 51.0688,
|
| 541 |
+
"eval_samples_per_second": 100.178,
|
| 542 |
+
"eval_steps_per_second": 3.133,
|
| 543 |
+
"step": 13440
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 42.19,
|
| 547 |
+
"learning_rate": 4.7021943573667715e-07,
|
| 548 |
+
"loss": 1.1422,
|
| 549 |
+
"step": 13500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 43.0,
|
| 553 |
+
"eval_accuracy": 0.4923768569194683,
|
| 554 |
+
"eval_loss": 1.5509822368621826,
|
| 555 |
+
"eval_runtime": 51.2886,
|
| 556 |
+
"eval_samples_per_second": 99.749,
|
| 557 |
+
"eval_steps_per_second": 3.12,
|
| 558 |
+
"step": 13760
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 43.75,
|
| 562 |
+
"learning_rate": 3.7617554858934167e-07,
|
| 563 |
+
"loss": 1.1272,
|
| 564 |
+
"step": 14000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 44.0,
|
| 568 |
+
"eval_accuracy": 0.48631743549648165,
|
| 569 |
+
"eval_loss": 1.5502736568450928,
|
| 570 |
+
"eval_runtime": 50.8248,
|
| 571 |
+
"eval_samples_per_second": 100.659,
|
| 572 |
+
"eval_steps_per_second": 3.148,
|
| 573 |
+
"step": 14080
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 45.0,
|
| 577 |
+
"eval_accuracy": 0.4880766223612197,
|
| 578 |
+
"eval_loss": 1.5476186275482178,
|
| 579 |
+
"eval_runtime": 50.5558,
|
| 580 |
+
"eval_samples_per_second": 101.195,
|
| 581 |
+
"eval_steps_per_second": 3.165,
|
| 582 |
+
"step": 14400
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 45.31,
|
| 586 |
+
"learning_rate": 2.821316614420063e-07,
|
| 587 |
+
"loss": 1.1256,
|
| 588 |
+
"step": 14500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 46.0,
|
| 592 |
+
"eval_accuracy": 0.48670836591086786,
|
| 593 |
+
"eval_loss": 1.544900894165039,
|
| 594 |
+
"eval_runtime": 50.2484,
|
| 595 |
+
"eval_samples_per_second": 101.814,
|
| 596 |
+
"eval_steps_per_second": 3.184,
|
| 597 |
+
"step": 14720
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 46.88,
|
| 601 |
+
"learning_rate": 1.8808777429467083e-07,
|
| 602 |
+
"loss": 1.1104,
|
| 603 |
+
"step": 15000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 47.0,
|
| 607 |
+
"eval_accuracy": 0.4904222048475371,
|
| 608 |
+
"eval_loss": 1.5414071083068848,
|
| 609 |
+
"eval_runtime": 50.6029,
|
| 610 |
+
"eval_samples_per_second": 101.101,
|
| 611 |
+
"eval_steps_per_second": 3.162,
|
| 612 |
+
"step": 15040
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 48.0,
|
| 616 |
+
"eval_accuracy": 0.4880766223612197,
|
| 617 |
+
"eval_loss": 1.542637586593628,
|
| 618 |
+
"eval_runtime": 50.2557,
|
| 619 |
+
"eval_samples_per_second": 101.799,
|
| 620 |
+
"eval_steps_per_second": 3.184,
|
| 621 |
+
"step": 15360
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 48.44,
|
| 625 |
+
"learning_rate": 9.404388714733542e-08,
|
| 626 |
+
"loss": 1.1101,
|
| 627 |
+
"step": 15500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 49.0,
|
| 631 |
+
"eval_accuracy": 0.49276778733385457,
|
| 632 |
+
"eval_loss": 1.5390384197235107,
|
| 633 |
+
"eval_runtime": 50.5326,
|
| 634 |
+
"eval_samples_per_second": 101.242,
|
| 635 |
+
"eval_steps_per_second": 3.166,
|
| 636 |
+
"step": 15680
|
| 637 |
+
}
|
| 638 |
+
],
|
| 639 |
+
"logging_steps": 500,
|
| 640 |
+
"max_steps": 16000,
|
| 641 |
+
"num_train_epochs": 50,
|
| 642 |
+
"save_steps": 500,
|
| 643 |
+
"total_flos": 7.770344157480554e+19,
|
| 644 |
+
"trial_name": null,
|
| 645 |
+
"trial_params": null
|
| 646 |
+
}
|
checkpoint-15680/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5cd01dd5ed26cea902b390d702900b9a59a1879a09644e120ad3fc63e298e03
|
| 3 |
+
size 4091
|
config.json
CHANGED
|
@@ -16,23 +16,22 @@
|
|
| 16 |
"4": "05",
|
| 17 |
"5": "06-07",
|
| 18 |
"6": "08-09",
|
| 19 |
-
"7": "
|
| 20 |
-
"8": "
|
| 21 |
-
"9": "
|
| 22 |
-
"10": "
|
| 23 |
-
"11": "
|
| 24 |
-
"12": "
|
| 25 |
-
"13": "
|
| 26 |
-
"14": "
|
| 27 |
-
"15": "
|
| 28 |
-
"16": "
|
| 29 |
-
"17": "
|
| 30 |
-
"18": "
|
| 31 |
-
"19": "
|
| 32 |
-
"20": "
|
| 33 |
-
"21": "
|
| 34 |
-
"22": "
|
| 35 |
-
"23": "90+"
|
| 36 |
},
|
| 37 |
"image_size": 224,
|
| 38 |
"initializer_range": 0.02,
|
|
@@ -45,23 +44,22 @@
|
|
| 45 |
"05": 4,
|
| 46 |
"06-07": 5,
|
| 47 |
"08-09": 6,
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
"90+": 23
|
| 65 |
},
|
| 66 |
"layer_norm_eps": 1e-12,
|
| 67 |
"model_type": "vit",
|
|
|
|
| 16 |
"4": "05",
|
| 17 |
"5": "06-07",
|
| 18 |
"6": "08-09",
|
| 19 |
+
"7": "10-12",
|
| 20 |
+
"8": "13-15",
|
| 21 |
+
"9": "16-20",
|
| 22 |
+
"10": "21-25",
|
| 23 |
+
"11": "26-30",
|
| 24 |
+
"12": "31-35",
|
| 25 |
+
"13": "36-40",
|
| 26 |
+
"14": "41-45",
|
| 27 |
+
"15": "46-50",
|
| 28 |
+
"16": "51-55",
|
| 29 |
+
"17": "56-60",
|
| 30 |
+
"18": "61-65",
|
| 31 |
+
"19": "66-70",
|
| 32 |
+
"20": "71-80",
|
| 33 |
+
"21": "81-90",
|
| 34 |
+
"22": "90+"
|
|
|
|
| 35 |
},
|
| 36 |
"image_size": 224,
|
| 37 |
"initializer_range": 0.02,
|
|
|
|
| 44 |
"05": 4,
|
| 45 |
"06-07": 5,
|
| 46 |
"08-09": 6,
|
| 47 |
+
"10-12": 7,
|
| 48 |
+
"13-15": 8,
|
| 49 |
+
"16-20": 9,
|
| 50 |
+
"21-25": 10,
|
| 51 |
+
"26-30": 11,
|
| 52 |
+
"31-35": 12,
|
| 53 |
+
"36-40": 13,
|
| 54 |
+
"41-45": 14,
|
| 55 |
+
"46-50": 15,
|
| 56 |
+
"51-55": 16,
|
| 57 |
+
"56-60": 17,
|
| 58 |
+
"61-65": 18,
|
| 59 |
+
"66-70": 19,
|
| 60 |
+
"71-80": 20,
|
| 61 |
+
"81-90": 21,
|
| 62 |
+
"90+": 22
|
|
|
|
| 63 |
},
|
| 64 |
"layer_norm_eps": 1e-12,
|
| 65 |
"model_type": "vit",
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a63ea460c98a52e8bcfec2f3c809237b00fc0d2b500c3c22931b40d44716a89
|
| 3 |
+
size 343288572
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5cd01dd5ed26cea902b390d702900b9a59a1879a09644e120ad3fc63e298e03
|
| 3 |
size 4091
|