Upload folder using huggingface_hub
Browse files- config.json +70 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3019 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Acne and Rosacea Photos",
|
13 |
+
"1": "Actinic Keratosis Basal Cell Carcinoma and other Malignant Lesions",
|
14 |
+
"10": "Lupus and other Connective Tissue diseases",
|
15 |
+
"11": "Nail Fungus and other Nail Disease",
|
16 |
+
"12": "Poison Ivy Photos and other Contact Dermatitis",
|
17 |
+
"13": "Psoriasis pictures Lichen Planus and related diseases",
|
18 |
+
"14": "Scabies Lyme Disease and other Infestations and Bites",
|
19 |
+
"15": "Seborrheic Keratoses and other Benign Tumors",
|
20 |
+
"16": "Systemic Disease",
|
21 |
+
"17": "Tinea Ringworm Candidiasis and other Fungal Infections",
|
22 |
+
"18": "Urticaria Hives",
|
23 |
+
"19": "Vasculitis Photos",
|
24 |
+
"2": "Atopic Dermatitis Photos",
|
25 |
+
"20": "Warts Molluscum and other Viral Infections",
|
26 |
+
"3": "Bullous Disease Photos",
|
27 |
+
"4": "Cellulitis Impetigo and other Bacterial Infections",
|
28 |
+
"5": "Eczema Photos",
|
29 |
+
"6": "Exanthems and Drug Eruptions",
|
30 |
+
"7": "Hair Loss Photos Alopecia and other Hair Diseases",
|
31 |
+
"8": "Herpes HPV and other STDs Photos",
|
32 |
+
"9": "Light Diseases and Disorders of Pigmentation"
|
33 |
+
},
|
34 |
+
"image_size": 224,
|
35 |
+
"initializer_range": 0.02,
|
36 |
+
"intermediate_size": 3072,
|
37 |
+
"label2id": {
|
38 |
+
"Acne and Rosacea Photos": "0",
|
39 |
+
"Actinic Keratosis Basal Cell Carcinoma and other Malignant Lesions": "1",
|
40 |
+
"Atopic Dermatitis Photos": "2",
|
41 |
+
"Bullous Disease Photos": "3",
|
42 |
+
"Cellulitis Impetigo and other Bacterial Infections": "4",
|
43 |
+
"Eczema Photos": "5",
|
44 |
+
"Exanthems and Drug Eruptions": "6",
|
45 |
+
"Hair Loss Photos Alopecia and other Hair Diseases": "7",
|
46 |
+
"Herpes HPV and other STDs Photos": "8",
|
47 |
+
"Light Diseases and Disorders of Pigmentation": "9",
|
48 |
+
"Lupus and other Connective Tissue diseases": "10",
|
49 |
+
"Nail Fungus and other Nail Disease": "11",
|
50 |
+
"Poison Ivy Photos and other Contact Dermatitis": "12",
|
51 |
+
"Psoriasis pictures Lichen Planus and related diseases": "13",
|
52 |
+
"Scabies Lyme Disease and other Infestations and Bites": "14",
|
53 |
+
"Seborrheic Keratoses and other Benign Tumors": "15",
|
54 |
+
"Systemic Disease": "16",
|
55 |
+
"Tinea Ringworm Candidiasis and other Fungal Infections": "17",
|
56 |
+
"Urticaria Hives": "18",
|
57 |
+
"Vasculitis Photos": "19",
|
58 |
+
"Warts Molluscum and other Viral Infections": "20"
|
59 |
+
},
|
60 |
+
"layer_norm_eps": 1e-12,
|
61 |
+
"model_type": "vit",
|
62 |
+
"num_attention_heads": 12,
|
63 |
+
"num_channels": 3,
|
64 |
+
"num_hidden_layers": 12,
|
65 |
+
"patch_size": 16,
|
66 |
+
"problem_type": "single_label_classification",
|
67 |
+
"qkv_bias": true,
|
68 |
+
"torch_dtype": "float32",
|
69 |
+
"transformers_version": "4.30.2"
|
70 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:542889dfd399360bf24f3bc3dc36f0e57749c6c24f7116a4b48d22174402d6fc
|
3 |
+
size 686635781
|
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": "ViTFeatureExtractor",
|
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 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145ff0c4e834a826bdda1f62ffbef762e6d43b2f6338d7872149190d5f9fb73c
|
3 |
+
size 343327149
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5857dcd2cc1822963ced16d02921b1e1a9c3cf62a929f1d9131ba414bf67f486
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cec20a37d1471aeab657be37ce8508dad702e9a579dcb8c650d6861abf96842
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,3019 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.2707958221435547,
|
3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-2600",
|
4 |
+
"epoch": 3.9608269858541894,
|
5 |
+
"global_step": 3640,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 0.00019945593035908596,
|
13 |
+
"loss": 2.9646,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"learning_rate": 0.00019891186071817194,
|
19 |
+
"loss": 2.8629,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.03,
|
24 |
+
"learning_rate": 0.0001983677910772579,
|
25 |
+
"loss": 2.8738,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.04,
|
30 |
+
"learning_rate": 0.00019782372143634387,
|
31 |
+
"loss": 2.7533,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.04,
|
36 |
+
"eval_accuracy": 0.235038084874864,
|
37 |
+
"eval_loss": 2.7046968936920166,
|
38 |
+
"eval_runtime": 30.8039,
|
39 |
+
"eval_samples_per_second": 59.668,
|
40 |
+
"eval_steps_per_second": 7.467,
|
41 |
+
"step": 40
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.05,
|
45 |
+
"learning_rate": 0.00019727965179542982,
|
46 |
+
"loss": 2.6376,
|
47 |
+
"step": 50
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.07,
|
51 |
+
"learning_rate": 0.0001967355821545158,
|
52 |
+
"loss": 2.7082,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.08,
|
57 |
+
"learning_rate": 0.00019619151251360175,
|
58 |
+
"loss": 2.7173,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.09,
|
63 |
+
"learning_rate": 0.0001956474428726877,
|
64 |
+
"loss": 2.6307,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.09,
|
69 |
+
"eval_accuracy": 0.26550598476605003,
|
70 |
+
"eval_loss": 2.542313575744629,
|
71 |
+
"eval_runtime": 31.8198,
|
72 |
+
"eval_samples_per_second": 57.763,
|
73 |
+
"eval_steps_per_second": 7.228,
|
74 |
+
"step": 80
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.1,
|
78 |
+
"learning_rate": 0.00019510337323177369,
|
79 |
+
"loss": 2.4765,
|
80 |
+
"step": 90
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.11,
|
84 |
+
"learning_rate": 0.00019455930359085964,
|
85 |
+
"loss": 2.4156,
|
86 |
+
"step": 100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.12,
|
90 |
+
"learning_rate": 0.00019401523394994562,
|
91 |
+
"loss": 2.4868,
|
92 |
+
"step": 110
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.13,
|
96 |
+
"learning_rate": 0.00019347116430903157,
|
97 |
+
"loss": 2.4875,
|
98 |
+
"step": 120
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.13,
|
102 |
+
"eval_accuracy": 0.25081610446137104,
|
103 |
+
"eval_loss": 2.5568594932556152,
|
104 |
+
"eval_runtime": 34.0995,
|
105 |
+
"eval_samples_per_second": 53.901,
|
106 |
+
"eval_steps_per_second": 6.745,
|
107 |
+
"step": 120
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.14,
|
111 |
+
"learning_rate": 0.00019292709466811755,
|
112 |
+
"loss": 2.5076,
|
113 |
+
"step": 130
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.15,
|
117 |
+
"learning_rate": 0.0001923830250272035,
|
118 |
+
"loss": 2.5709,
|
119 |
+
"step": 140
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.16,
|
123 |
+
"learning_rate": 0.00019183895538628948,
|
124 |
+
"loss": 2.4629,
|
125 |
+
"step": 150
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.17,
|
129 |
+
"learning_rate": 0.00019129488574537543,
|
130 |
+
"loss": 2.4422,
|
131 |
+
"step": 160
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.17,
|
135 |
+
"eval_accuracy": 0.2867247007616975,
|
136 |
+
"eval_loss": 2.414120674133301,
|
137 |
+
"eval_runtime": 31.6836,
|
138 |
+
"eval_samples_per_second": 58.011,
|
139 |
+
"eval_steps_per_second": 7.259,
|
140 |
+
"step": 160
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.18,
|
144 |
+
"learning_rate": 0.00019075081610446138,
|
145 |
+
"loss": 2.4772,
|
146 |
+
"step": 170
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.2,
|
150 |
+
"learning_rate": 0.00019020674646354733,
|
151 |
+
"loss": 2.3993,
|
152 |
+
"step": 180
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.21,
|
156 |
+
"learning_rate": 0.0001896626768226333,
|
157 |
+
"loss": 2.3927,
|
158 |
+
"step": 190
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.22,
|
162 |
+
"learning_rate": 0.00018911860718171927,
|
163 |
+
"loss": 2.3488,
|
164 |
+
"step": 200
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.22,
|
168 |
+
"eval_accuracy": 0.3133841131664853,
|
169 |
+
"eval_loss": 2.361457347869873,
|
170 |
+
"eval_runtime": 32.0343,
|
171 |
+
"eval_samples_per_second": 57.376,
|
172 |
+
"eval_steps_per_second": 7.18,
|
173 |
+
"step": 200
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.23,
|
177 |
+
"learning_rate": 0.00018857453754080522,
|
178 |
+
"loss": 2.4865,
|
179 |
+
"step": 210
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.24,
|
183 |
+
"learning_rate": 0.0001880304678998912,
|
184 |
+
"loss": 2.287,
|
185 |
+
"step": 220
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.25,
|
189 |
+
"learning_rate": 0.00018748639825897715,
|
190 |
+
"loss": 2.3538,
|
191 |
+
"step": 230
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.26,
|
195 |
+
"learning_rate": 0.0001869423286180631,
|
196 |
+
"loss": 2.4178,
|
197 |
+
"step": 240
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 0.26,
|
201 |
+
"eval_accuracy": 0.3193688792165397,
|
202 |
+
"eval_loss": 2.2913949489593506,
|
203 |
+
"eval_runtime": 31.6054,
|
204 |
+
"eval_samples_per_second": 58.155,
|
205 |
+
"eval_steps_per_second": 7.277,
|
206 |
+
"step": 240
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.27,
|
210 |
+
"learning_rate": 0.00018639825897714908,
|
211 |
+
"loss": 2.3083,
|
212 |
+
"step": 250
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.28,
|
216 |
+
"learning_rate": 0.00018585418933623503,
|
217 |
+
"loss": 2.1267,
|
218 |
+
"step": 260
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.29,
|
222 |
+
"learning_rate": 0.000185310119695321,
|
223 |
+
"loss": 2.3088,
|
224 |
+
"step": 270
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.3,
|
228 |
+
"learning_rate": 0.00018476605005440696,
|
229 |
+
"loss": 2.1498,
|
230 |
+
"step": 280
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.3,
|
234 |
+
"eval_accuracy": 0.33133841131664854,
|
235 |
+
"eval_loss": 2.230421543121338,
|
236 |
+
"eval_runtime": 32.4123,
|
237 |
+
"eval_samples_per_second": 56.707,
|
238 |
+
"eval_steps_per_second": 7.096,
|
239 |
+
"step": 280
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.32,
|
243 |
+
"learning_rate": 0.00018422198041349294,
|
244 |
+
"loss": 2.2239,
|
245 |
+
"step": 290
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.33,
|
249 |
+
"learning_rate": 0.0001836779107725789,
|
250 |
+
"loss": 2.2776,
|
251 |
+
"step": 300
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.34,
|
255 |
+
"learning_rate": 0.00018313384113166484,
|
256 |
+
"loss": 2.2717,
|
257 |
+
"step": 310
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.35,
|
261 |
+
"learning_rate": 0.00018258977149075082,
|
262 |
+
"loss": 2.2416,
|
263 |
+
"step": 320
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.35,
|
267 |
+
"eval_accuracy": 0.34766050054406966,
|
268 |
+
"eval_loss": 2.155261516571045,
|
269 |
+
"eval_runtime": 31.3536,
|
270 |
+
"eval_samples_per_second": 58.622,
|
271 |
+
"eval_steps_per_second": 7.336,
|
272 |
+
"step": 320
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.36,
|
276 |
+
"learning_rate": 0.00018204570184983678,
|
277 |
+
"loss": 2.1923,
|
278 |
+
"step": 330
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.37,
|
282 |
+
"learning_rate": 0.00018150163220892275,
|
283 |
+
"loss": 2.1404,
|
284 |
+
"step": 340
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.38,
|
288 |
+
"learning_rate": 0.0001809575625680087,
|
289 |
+
"loss": 2.127,
|
290 |
+
"step": 350
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.39,
|
294 |
+
"learning_rate": 0.00018041349292709469,
|
295 |
+
"loss": 2.1643,
|
296 |
+
"step": 360
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.39,
|
300 |
+
"eval_accuracy": 0.34494015233949943,
|
301 |
+
"eval_loss": 2.2201523780822754,
|
302 |
+
"eval_runtime": 31.5353,
|
303 |
+
"eval_samples_per_second": 58.284,
|
304 |
+
"eval_steps_per_second": 7.293,
|
305 |
+
"step": 360
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.4,
|
309 |
+
"learning_rate": 0.00017986942328618064,
|
310 |
+
"loss": 2.3303,
|
311 |
+
"step": 370
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.41,
|
315 |
+
"learning_rate": 0.0001793253536452666,
|
316 |
+
"loss": 2.0957,
|
317 |
+
"step": 380
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.42,
|
321 |
+
"learning_rate": 0.00017878128400435257,
|
322 |
+
"loss": 2.1675,
|
323 |
+
"step": 390
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.44,
|
327 |
+
"learning_rate": 0.00017823721436343852,
|
328 |
+
"loss": 2.1688,
|
329 |
+
"step": 400
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.44,
|
333 |
+
"eval_accuracy": 0.3715995647442873,
|
334 |
+
"eval_loss": 2.1544973850250244,
|
335 |
+
"eval_runtime": 31.7596,
|
336 |
+
"eval_samples_per_second": 57.872,
|
337 |
+
"eval_steps_per_second": 7.242,
|
338 |
+
"step": 400
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.45,
|
342 |
+
"learning_rate": 0.0001776931447225245,
|
343 |
+
"loss": 2.1298,
|
344 |
+
"step": 410
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.46,
|
348 |
+
"learning_rate": 0.00017714907508161045,
|
349 |
+
"loss": 2.1467,
|
350 |
+
"step": 420
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.47,
|
354 |
+
"learning_rate": 0.00017660500544069643,
|
355 |
+
"loss": 2.0672,
|
356 |
+
"step": 430
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.48,
|
360 |
+
"learning_rate": 0.00017606093579978238,
|
361 |
+
"loss": 2.0324,
|
362 |
+
"step": 440
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.48,
|
366 |
+
"eval_accuracy": 0.3928182807399347,
|
367 |
+
"eval_loss": 2.0655834674835205,
|
368 |
+
"eval_runtime": 31.6367,
|
369 |
+
"eval_samples_per_second": 58.097,
|
370 |
+
"eval_steps_per_second": 7.27,
|
371 |
+
"step": 440
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.49,
|
375 |
+
"learning_rate": 0.00017551686615886836,
|
376 |
+
"loss": 1.9756,
|
377 |
+
"step": 450
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.5,
|
381 |
+
"learning_rate": 0.0001749727965179543,
|
382 |
+
"loss": 2.1049,
|
383 |
+
"step": 460
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.51,
|
387 |
+
"learning_rate": 0.00017442872687704027,
|
388 |
+
"loss": 2.0169,
|
389 |
+
"step": 470
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.52,
|
393 |
+
"learning_rate": 0.00017388465723612624,
|
394 |
+
"loss": 2.1648,
|
395 |
+
"step": 480
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.52,
|
399 |
+
"eval_accuracy": 0.3982589771490751,
|
400 |
+
"eval_loss": 2.052687644958496,
|
401 |
+
"eval_runtime": 31.623,
|
402 |
+
"eval_samples_per_second": 58.122,
|
403 |
+
"eval_steps_per_second": 7.273,
|
404 |
+
"step": 480
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.53,
|
408 |
+
"learning_rate": 0.0001733405875952122,
|
409 |
+
"loss": 1.9753,
|
410 |
+
"step": 490
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.54,
|
414 |
+
"learning_rate": 0.00017279651795429818,
|
415 |
+
"loss": 2.2119,
|
416 |
+
"step": 500
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.55,
|
420 |
+
"learning_rate": 0.00017225244831338413,
|
421 |
+
"loss": 2.0171,
|
422 |
+
"step": 510
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.57,
|
426 |
+
"learning_rate": 0.0001717083786724701,
|
427 |
+
"loss": 2.0568,
|
428 |
+
"step": 520
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.57,
|
432 |
+
"eval_accuracy": 0.4009793253536453,
|
433 |
+
"eval_loss": 2.0108883380889893,
|
434 |
+
"eval_runtime": 31.345,
|
435 |
+
"eval_samples_per_second": 58.638,
|
436 |
+
"eval_steps_per_second": 7.338,
|
437 |
+
"step": 520
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.58,
|
441 |
+
"learning_rate": 0.00017116430903155606,
|
442 |
+
"loss": 2.0011,
|
443 |
+
"step": 530
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.59,
|
447 |
+
"learning_rate": 0.000170620239390642,
|
448 |
+
"loss": 1.9614,
|
449 |
+
"step": 540
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.6,
|
453 |
+
"learning_rate": 0.000170076169749728,
|
454 |
+
"loss": 1.9669,
|
455 |
+
"step": 550
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.61,
|
459 |
+
"learning_rate": 0.00016953210010881394,
|
460 |
+
"loss": 1.9287,
|
461 |
+
"step": 560
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.61,
|
465 |
+
"eval_accuracy": 0.3900979325353645,
|
466 |
+
"eval_loss": 2.06852126121521,
|
467 |
+
"eval_runtime": 31.417,
|
468 |
+
"eval_samples_per_second": 58.503,
|
469 |
+
"eval_steps_per_second": 7.321,
|
470 |
+
"step": 560
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.62,
|
474 |
+
"learning_rate": 0.0001689880304678999,
|
475 |
+
"loss": 1.9279,
|
476 |
+
"step": 570
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.63,
|
480 |
+
"learning_rate": 0.00016844396082698585,
|
481 |
+
"loss": 2.0612,
|
482 |
+
"step": 580
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.64,
|
486 |
+
"learning_rate": 0.00016789989118607182,
|
487 |
+
"loss": 2.0225,
|
488 |
+
"step": 590
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.65,
|
492 |
+
"learning_rate": 0.00016735582154515778,
|
493 |
+
"loss": 2.0335,
|
494 |
+
"step": 600
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.65,
|
498 |
+
"eval_accuracy": 0.39336235038084877,
|
499 |
+
"eval_loss": 2.0253407955169678,
|
500 |
+
"eval_runtime": 31.882,
|
501 |
+
"eval_samples_per_second": 57.65,
|
502 |
+
"eval_steps_per_second": 7.214,
|
503 |
+
"step": 600
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.66,
|
507 |
+
"learning_rate": 0.00016681175190424373,
|
508 |
+
"loss": 2.2113,
|
509 |
+
"step": 610
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.67,
|
513 |
+
"learning_rate": 0.0001662676822633297,
|
514 |
+
"loss": 2.101,
|
515 |
+
"step": 620
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.69,
|
519 |
+
"learning_rate": 0.00016572361262241566,
|
520 |
+
"loss": 1.9211,
|
521 |
+
"step": 630
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.7,
|
525 |
+
"learning_rate": 0.00016517954298150164,
|
526 |
+
"loss": 2.1521,
|
527 |
+
"step": 640
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.7,
|
531 |
+
"eval_accuracy": 0.40696409140369966,
|
532 |
+
"eval_loss": 2.0242509841918945,
|
533 |
+
"eval_runtime": 31.6803,
|
534 |
+
"eval_samples_per_second": 58.017,
|
535 |
+
"eval_steps_per_second": 7.26,
|
536 |
+
"step": 640
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.71,
|
540 |
+
"learning_rate": 0.0001646354733405876,
|
541 |
+
"loss": 1.9707,
|
542 |
+
"step": 650
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.72,
|
546 |
+
"learning_rate": 0.00016409140369967357,
|
547 |
+
"loss": 1.7482,
|
548 |
+
"step": 660
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.73,
|
552 |
+
"learning_rate": 0.00016354733405875952,
|
553 |
+
"loss": 2.0443,
|
554 |
+
"step": 670
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.74,
|
558 |
+
"learning_rate": 0.0001630032644178455,
|
559 |
+
"loss": 1.909,
|
560 |
+
"step": 680
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.74,
|
564 |
+
"eval_accuracy": 0.4363438520130577,
|
565 |
+
"eval_loss": 1.8839356899261475,
|
566 |
+
"eval_runtime": 31.4005,
|
567 |
+
"eval_samples_per_second": 58.534,
|
568 |
+
"eval_steps_per_second": 7.325,
|
569 |
+
"step": 680
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.75,
|
573 |
+
"learning_rate": 0.00016245919477693145,
|
574 |
+
"loss": 1.9677,
|
575 |
+
"step": 690
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.76,
|
579 |
+
"learning_rate": 0.0001619151251360174,
|
580 |
+
"loss": 1.9786,
|
581 |
+
"step": 700
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.77,
|
585 |
+
"learning_rate": 0.00016137105549510338,
|
586 |
+
"loss": 1.856,
|
587 |
+
"step": 710
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.78,
|
591 |
+
"learning_rate": 0.00016082698585418933,
|
592 |
+
"loss": 1.9212,
|
593 |
+
"step": 720
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.78,
|
597 |
+
"eval_accuracy": 0.4504896626768226,
|
598 |
+
"eval_loss": 1.8623088598251343,
|
599 |
+
"eval_runtime": 31.5361,
|
600 |
+
"eval_samples_per_second": 58.282,
|
601 |
+
"eval_steps_per_second": 7.293,
|
602 |
+
"step": 720
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.79,
|
606 |
+
"learning_rate": 0.00016028291621327531,
|
607 |
+
"loss": 1.7232,
|
608 |
+
"step": 730
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.81,
|
612 |
+
"learning_rate": 0.00015973884657236127,
|
613 |
+
"loss": 1.9299,
|
614 |
+
"step": 740
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.82,
|
618 |
+
"learning_rate": 0.00015919477693144724,
|
619 |
+
"loss": 1.9622,
|
620 |
+
"step": 750
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.83,
|
624 |
+
"learning_rate": 0.0001586507072905332,
|
625 |
+
"loss": 1.9359,
|
626 |
+
"step": 760
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.83,
|
630 |
+
"eval_accuracy": 0.42546245919477693,
|
631 |
+
"eval_loss": 1.893409013748169,
|
632 |
+
"eval_runtime": 31.8615,
|
633 |
+
"eval_samples_per_second": 57.687,
|
634 |
+
"eval_steps_per_second": 7.219,
|
635 |
+
"step": 760
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.84,
|
639 |
+
"learning_rate": 0.00015810663764961915,
|
640 |
+
"loss": 1.929,
|
641 |
+
"step": 770
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.85,
|
645 |
+
"learning_rate": 0.00015756256800870513,
|
646 |
+
"loss": 1.8717,
|
647 |
+
"step": 780
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.86,
|
651 |
+
"learning_rate": 0.00015701849836779108,
|
652 |
+
"loss": 1.9117,
|
653 |
+
"step": 790
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.87,
|
657 |
+
"learning_rate": 0.00015647442872687706,
|
658 |
+
"loss": 1.8435,
|
659 |
+
"step": 800
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 0.87,
|
663 |
+
"eval_accuracy": 0.4815016322089227,
|
664 |
+
"eval_loss": 1.765435814857483,
|
665 |
+
"eval_runtime": 31.2045,
|
666 |
+
"eval_samples_per_second": 58.902,
|
667 |
+
"eval_steps_per_second": 7.371,
|
668 |
+
"step": 800
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.88,
|
672 |
+
"learning_rate": 0.000155930359085963,
|
673 |
+
"loss": 1.8022,
|
674 |
+
"step": 810
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.89,
|
678 |
+
"learning_rate": 0.000155386289445049,
|
679 |
+
"loss": 1.8581,
|
680 |
+
"step": 820
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.9,
|
684 |
+
"learning_rate": 0.00015484221980413494,
|
685 |
+
"loss": 2.1219,
|
686 |
+
"step": 830
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.91,
|
690 |
+
"learning_rate": 0.0001542981501632209,
|
691 |
+
"loss": 1.7116,
|
692 |
+
"step": 840
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.91,
|
696 |
+
"eval_accuracy": 0.47551686615886835,
|
697 |
+
"eval_loss": 1.7760648727416992,
|
698 |
+
"eval_runtime": 31.1164,
|
699 |
+
"eval_samples_per_second": 59.068,
|
700 |
+
"eval_steps_per_second": 7.392,
|
701 |
+
"step": 840
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 0.92,
|
705 |
+
"learning_rate": 0.00015375408052230687,
|
706 |
+
"loss": 1.8721,
|
707 |
+
"step": 850
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 0.94,
|
711 |
+
"learning_rate": 0.00015321001088139282,
|
712 |
+
"loss": 1.8389,
|
713 |
+
"step": 860
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.95,
|
717 |
+
"learning_rate": 0.0001526659412404788,
|
718 |
+
"loss": 1.8014,
|
719 |
+
"step": 870
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 0.96,
|
723 |
+
"learning_rate": 0.00015212187159956476,
|
724 |
+
"loss": 1.7788,
|
725 |
+
"step": 880
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.96,
|
729 |
+
"eval_accuracy": 0.49183895538628947,
|
730 |
+
"eval_loss": 1.7206392288208008,
|
731 |
+
"eval_runtime": 31.9363,
|
732 |
+
"eval_samples_per_second": 57.552,
|
733 |
+
"eval_steps_per_second": 7.202,
|
734 |
+
"step": 880
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.97,
|
738 |
+
"learning_rate": 0.00015157780195865073,
|
739 |
+
"loss": 1.7437,
|
740 |
+
"step": 890
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.98,
|
744 |
+
"learning_rate": 0.00015103373231773669,
|
745 |
+
"loss": 1.7861,
|
746 |
+
"step": 900
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.99,
|
750 |
+
"learning_rate": 0.00015048966267682264,
|
751 |
+
"loss": 1.9204,
|
752 |
+
"step": 910
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 1.0,
|
756 |
+
"learning_rate": 0.00014994559303590862,
|
757 |
+
"loss": 1.8087,
|
758 |
+
"step": 920
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 1.0,
|
762 |
+
"eval_accuracy": 0.4956474428726877,
|
763 |
+
"eval_loss": 1.7031298875808716,
|
764 |
+
"eval_runtime": 31.4911,
|
765 |
+
"eval_samples_per_second": 58.366,
|
766 |
+
"eval_steps_per_second": 7.304,
|
767 |
+
"step": 920
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 1.01,
|
771 |
+
"learning_rate": 0.00014940152339499457,
|
772 |
+
"loss": 1.3634,
|
773 |
+
"step": 930
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 1.02,
|
777 |
+
"learning_rate": 0.00014885745375408052,
|
778 |
+
"loss": 1.5091,
|
779 |
+
"step": 940
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 1.03,
|
783 |
+
"learning_rate": 0.0001483133841131665,
|
784 |
+
"loss": 1.3875,
|
785 |
+
"step": 950
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 1.04,
|
789 |
+
"learning_rate": 0.00014776931447225245,
|
790 |
+
"loss": 1.352,
|
791 |
+
"step": 960
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 1.04,
|
795 |
+
"eval_accuracy": 0.500544069640914,
|
796 |
+
"eval_loss": 1.699517846107483,
|
797 |
+
"eval_runtime": 31.4103,
|
798 |
+
"eval_samples_per_second": 58.516,
|
799 |
+
"eval_steps_per_second": 7.322,
|
800 |
+
"step": 960
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 1.06,
|
804 |
+
"learning_rate": 0.0001472252448313384,
|
805 |
+
"loss": 1.5501,
|
806 |
+
"step": 970
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 1.07,
|
810 |
+
"learning_rate": 0.00014668117519042438,
|
811 |
+
"loss": 1.2166,
|
812 |
+
"step": 980
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 1.08,
|
816 |
+
"learning_rate": 0.00014613710554951034,
|
817 |
+
"loss": 1.3054,
|
818 |
+
"step": 990
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 1.09,
|
822 |
+
"learning_rate": 0.0001455930359085963,
|
823 |
+
"loss": 1.6001,
|
824 |
+
"step": 1000
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 1.09,
|
828 |
+
"eval_accuracy": 0.5119695321001088,
|
829 |
+
"eval_loss": 1.688511610031128,
|
830 |
+
"eval_runtime": 31.1036,
|
831 |
+
"eval_samples_per_second": 59.093,
|
832 |
+
"eval_steps_per_second": 7.395,
|
833 |
+
"step": 1000
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 1.1,
|
837 |
+
"learning_rate": 0.00014504896626768227,
|
838 |
+
"loss": 1.427,
|
839 |
+
"step": 1010
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 1.11,
|
843 |
+
"learning_rate": 0.00014450489662676822,
|
844 |
+
"loss": 1.453,
|
845 |
+
"step": 1020
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 1.12,
|
849 |
+
"learning_rate": 0.0001439608269858542,
|
850 |
+
"loss": 1.5073,
|
851 |
+
"step": 1030
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 1.13,
|
855 |
+
"learning_rate": 0.00014341675734494015,
|
856 |
+
"loss": 1.5872,
|
857 |
+
"step": 1040
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 1.13,
|
861 |
+
"eval_accuracy": 0.500544069640914,
|
862 |
+
"eval_loss": 1.7050400972366333,
|
863 |
+
"eval_runtime": 31.6643,
|
864 |
+
"eval_samples_per_second": 58.046,
|
865 |
+
"eval_steps_per_second": 7.264,
|
866 |
+
"step": 1040
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 1.14,
|
870 |
+
"learning_rate": 0.00014287268770402613,
|
871 |
+
"loss": 1.4122,
|
872 |
+
"step": 1050
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 1.15,
|
876 |
+
"learning_rate": 0.00014232861806311208,
|
877 |
+
"loss": 1.407,
|
878 |
+
"step": 1060
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 1.16,
|
882 |
+
"learning_rate": 0.00014178454842219803,
|
883 |
+
"loss": 1.4817,
|
884 |
+
"step": 1070
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 1.18,
|
888 |
+
"learning_rate": 0.000141240478781284,
|
889 |
+
"loss": 1.2903,
|
890 |
+
"step": 1080
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 1.18,
|
894 |
+
"eval_accuracy": 0.5070729053318824,
|
895 |
+
"eval_loss": 1.6926010847091675,
|
896 |
+
"eval_runtime": 31.355,
|
897 |
+
"eval_samples_per_second": 58.619,
|
898 |
+
"eval_steps_per_second": 7.335,
|
899 |
+
"step": 1080
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 1.19,
|
903 |
+
"learning_rate": 0.00014069640914036996,
|
904 |
+
"loss": 1.4445,
|
905 |
+
"step": 1090
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 1.2,
|
909 |
+
"learning_rate": 0.00014015233949945594,
|
910 |
+
"loss": 1.3711,
|
911 |
+
"step": 1100
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 1.21,
|
915 |
+
"learning_rate": 0.0001396082698585419,
|
916 |
+
"loss": 1.3271,
|
917 |
+
"step": 1110
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 1.22,
|
921 |
+
"learning_rate": 0.00013906420021762787,
|
922 |
+
"loss": 1.3377,
|
923 |
+
"step": 1120
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 1.22,
|
927 |
+
"eval_accuracy": 0.5184983677910773,
|
928 |
+
"eval_loss": 1.663212776184082,
|
929 |
+
"eval_runtime": 31.9094,
|
930 |
+
"eval_samples_per_second": 57.601,
|
931 |
+
"eval_steps_per_second": 7.208,
|
932 |
+
"step": 1120
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 1.23,
|
936 |
+
"learning_rate": 0.00013852013057671382,
|
937 |
+
"loss": 1.3493,
|
938 |
+
"step": 1130
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 1.24,
|
942 |
+
"learning_rate": 0.00013797606093579978,
|
943 |
+
"loss": 1.2249,
|
944 |
+
"step": 1140
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 1.25,
|
948 |
+
"learning_rate": 0.00013743199129488576,
|
949 |
+
"loss": 1.6033,
|
950 |
+
"step": 1150
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 1.26,
|
954 |
+
"learning_rate": 0.0001368879216539717,
|
955 |
+
"loss": 1.3738,
|
956 |
+
"step": 1160
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 1.26,
|
960 |
+
"eval_accuracy": 0.5206746463547334,
|
961 |
+
"eval_loss": 1.6760975122451782,
|
962 |
+
"eval_runtime": 31.2925,
|
963 |
+
"eval_samples_per_second": 58.736,
|
964 |
+
"eval_steps_per_second": 7.35,
|
965 |
+
"step": 1160
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 1.27,
|
969 |
+
"learning_rate": 0.0001363438520130577,
|
970 |
+
"loss": 1.5122,
|
971 |
+
"step": 1170
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 1.28,
|
975 |
+
"learning_rate": 0.00013579978237214364,
|
976 |
+
"loss": 1.3597,
|
977 |
+
"step": 1180
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 1.29,
|
981 |
+
"learning_rate": 0.00013525571273122962,
|
982 |
+
"loss": 1.2399,
|
983 |
+
"step": 1190
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 1.31,
|
987 |
+
"learning_rate": 0.00013471164309031557,
|
988 |
+
"loss": 1.2835,
|
989 |
+
"step": 1200
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 1.31,
|
993 |
+
"eval_accuracy": 0.5375408052230686,
|
994 |
+
"eval_loss": 1.5999504327774048,
|
995 |
+
"eval_runtime": 31.108,
|
996 |
+
"eval_samples_per_second": 59.084,
|
997 |
+
"eval_steps_per_second": 7.394,
|
998 |
+
"step": 1200
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 1.32,
|
1002 |
+
"learning_rate": 0.00013416757344940155,
|
1003 |
+
"loss": 1.6025,
|
1004 |
+
"step": 1210
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 1.33,
|
1008 |
+
"learning_rate": 0.0001336235038084875,
|
1009 |
+
"loss": 1.3795,
|
1010 |
+
"step": 1220
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 1.34,
|
1014 |
+
"learning_rate": 0.00013307943416757345,
|
1015 |
+
"loss": 1.3779,
|
1016 |
+
"step": 1230
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 1.35,
|
1020 |
+
"learning_rate": 0.00013253536452665943,
|
1021 |
+
"loss": 1.2588,
|
1022 |
+
"step": 1240
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 1.35,
|
1026 |
+
"eval_accuracy": 0.5239390642002176,
|
1027 |
+
"eval_loss": 1.6404486894607544,
|
1028 |
+
"eval_runtime": 31.2356,
|
1029 |
+
"eval_samples_per_second": 58.843,
|
1030 |
+
"eval_steps_per_second": 7.363,
|
1031 |
+
"step": 1240
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 1.36,
|
1035 |
+
"learning_rate": 0.00013199129488574538,
|
1036 |
+
"loss": 1.3196,
|
1037 |
+
"step": 1250
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 1.37,
|
1041 |
+
"learning_rate": 0.00013144722524483136,
|
1042 |
+
"loss": 1.2977,
|
1043 |
+
"step": 1260
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 1.38,
|
1047 |
+
"learning_rate": 0.00013090315560391731,
|
1048 |
+
"loss": 1.354,
|
1049 |
+
"step": 1270
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 1.39,
|
1053 |
+
"learning_rate": 0.0001303590859630033,
|
1054 |
+
"loss": 1.198,
|
1055 |
+
"step": 1280
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 1.39,
|
1059 |
+
"eval_accuracy": 0.5457018498367792,
|
1060 |
+
"eval_loss": 1.5461368560791016,
|
1061 |
+
"eval_runtime": 31.2158,
|
1062 |
+
"eval_samples_per_second": 58.88,
|
1063 |
+
"eval_steps_per_second": 7.368,
|
1064 |
+
"step": 1280
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 1.4,
|
1068 |
+
"learning_rate": 0.00012981501632208925,
|
1069 |
+
"loss": 1.3318,
|
1070 |
+
"step": 1290
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 1.41,
|
1074 |
+
"learning_rate": 0.0001292709466811752,
|
1075 |
+
"loss": 1.2417,
|
1076 |
+
"step": 1300
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 1.43,
|
1080 |
+
"learning_rate": 0.00012872687704026115,
|
1081 |
+
"loss": 1.2636,
|
1082 |
+
"step": 1310
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 1.44,
|
1086 |
+
"learning_rate": 0.00012818280739934713,
|
1087 |
+
"loss": 1.4038,
|
1088 |
+
"step": 1320
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 1.44,
|
1092 |
+
"eval_accuracy": 0.5337323177366703,
|
1093 |
+
"eval_loss": 1.5740242004394531,
|
1094 |
+
"eval_runtime": 31.2028,
|
1095 |
+
"eval_samples_per_second": 58.905,
|
1096 |
+
"eval_steps_per_second": 7.371,
|
1097 |
+
"step": 1320
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 1.45,
|
1101 |
+
"learning_rate": 0.00012763873775843308,
|
1102 |
+
"loss": 1.3172,
|
1103 |
+
"step": 1330
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 1.46,
|
1107 |
+
"learning_rate": 0.00012709466811751903,
|
1108 |
+
"loss": 1.1899,
|
1109 |
+
"step": 1340
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 1.47,
|
1113 |
+
"learning_rate": 0.000126550598476605,
|
1114 |
+
"loss": 1.2146,
|
1115 |
+
"step": 1350
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 1.48,
|
1119 |
+
"learning_rate": 0.00012600652883569096,
|
1120 |
+
"loss": 1.2275,
|
1121 |
+
"step": 1360
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 1.48,
|
1125 |
+
"eval_accuracy": 0.5516866158868335,
|
1126 |
+
"eval_loss": 1.5276788473129272,
|
1127 |
+
"eval_runtime": 31.2082,
|
1128 |
+
"eval_samples_per_second": 58.895,
|
1129 |
+
"eval_steps_per_second": 7.37,
|
1130 |
+
"step": 1360
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 1.49,
|
1134 |
+
"learning_rate": 0.00012546245919477691,
|
1135 |
+
"loss": 1.2164,
|
1136 |
+
"step": 1370
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 1.5,
|
1140 |
+
"learning_rate": 0.0001249183895538629,
|
1141 |
+
"loss": 1.1369,
|
1142 |
+
"step": 1380
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 1.51,
|
1146 |
+
"learning_rate": 0.00012437431991294885,
|
1147 |
+
"loss": 1.3417,
|
1148 |
+
"step": 1390
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 1.52,
|
1152 |
+
"learning_rate": 0.00012383025027203483,
|
1153 |
+
"loss": 1.2224,
|
1154 |
+
"step": 1400
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 1.52,
|
1158 |
+
"eval_accuracy": 0.5614798694232862,
|
1159 |
+
"eval_loss": 1.4918007850646973,
|
1160 |
+
"eval_runtime": 31.6631,
|
1161 |
+
"eval_samples_per_second": 58.049,
|
1162 |
+
"eval_steps_per_second": 7.264,
|
1163 |
+
"step": 1400
|
1164 |
+
},
|
1165 |
+
{
|
1166 |
+
"epoch": 1.53,
|
1167 |
+
"learning_rate": 0.00012328618063112078,
|
1168 |
+
"loss": 1.208,
|
1169 |
+
"step": 1410
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 1.55,
|
1173 |
+
"learning_rate": 0.00012274211099020676,
|
1174 |
+
"loss": 1.4005,
|
1175 |
+
"step": 1420
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 1.56,
|
1179 |
+
"learning_rate": 0.0001221980413492927,
|
1180 |
+
"loss": 1.2049,
|
1181 |
+
"step": 1430
|
1182 |
+
},
|
1183 |
+
{
|
1184 |
+
"epoch": 1.57,
|
1185 |
+
"learning_rate": 0.00012165397170837869,
|
1186 |
+
"loss": 1.3221,
|
1187 |
+
"step": 1440
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 1.57,
|
1191 |
+
"eval_accuracy": 0.558215451577802,
|
1192 |
+
"eval_loss": 1.5159553289413452,
|
1193 |
+
"eval_runtime": 31.668,
|
1194 |
+
"eval_samples_per_second": 58.04,
|
1195 |
+
"eval_steps_per_second": 7.263,
|
1196 |
+
"step": 1440
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 1.58,
|
1200 |
+
"learning_rate": 0.00012110990206746464,
|
1201 |
+
"loss": 1.0449,
|
1202 |
+
"step": 1450
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 1.59,
|
1206 |
+
"learning_rate": 0.00012056583242655059,
|
1207 |
+
"loss": 1.352,
|
1208 |
+
"step": 1460
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 1.6,
|
1212 |
+
"learning_rate": 0.00012002176278563657,
|
1213 |
+
"loss": 1.2259,
|
1214 |
+
"step": 1470
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 1.61,
|
1218 |
+
"learning_rate": 0.00011947769314472252,
|
1219 |
+
"loss": 1.1424,
|
1220 |
+
"step": 1480
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 1.61,
|
1224 |
+
"eval_accuracy": 0.544069640914037,
|
1225 |
+
"eval_loss": 1.553783893585205,
|
1226 |
+
"eval_runtime": 31.3063,
|
1227 |
+
"eval_samples_per_second": 58.71,
|
1228 |
+
"eval_steps_per_second": 7.347,
|
1229 |
+
"step": 1480
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 1.62,
|
1233 |
+
"learning_rate": 0.0001189336235038085,
|
1234 |
+
"loss": 1.1163,
|
1235 |
+
"step": 1490
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 1.63,
|
1239 |
+
"learning_rate": 0.00011838955386289445,
|
1240 |
+
"loss": 1.0946,
|
1241 |
+
"step": 1500
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 1.64,
|
1245 |
+
"learning_rate": 0.00011784548422198043,
|
1246 |
+
"loss": 1.083,
|
1247 |
+
"step": 1510
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 1.65,
|
1251 |
+
"learning_rate": 0.00011730141458106638,
|
1252 |
+
"loss": 1.2951,
|
1253 |
+
"step": 1520
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 1.65,
|
1257 |
+
"eval_accuracy": 0.558215451577802,
|
1258 |
+
"eval_loss": 1.4977946281433105,
|
1259 |
+
"eval_runtime": 31.2346,
|
1260 |
+
"eval_samples_per_second": 58.845,
|
1261 |
+
"eval_steps_per_second": 7.364,
|
1262 |
+
"step": 1520
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 1.66,
|
1266 |
+
"learning_rate": 0.00011675734494015234,
|
1267 |
+
"loss": 1.2416,
|
1268 |
+
"step": 1530
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 1.68,
|
1272 |
+
"learning_rate": 0.00011621327529923831,
|
1273 |
+
"loss": 1.3838,
|
1274 |
+
"step": 1540
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 1.69,
|
1278 |
+
"learning_rate": 0.00011566920565832427,
|
1279 |
+
"loss": 1.2389,
|
1280 |
+
"step": 1550
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 1.7,
|
1284 |
+
"learning_rate": 0.00011512513601741025,
|
1285 |
+
"loss": 1.2609,
|
1286 |
+
"step": 1560
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 1.7,
|
1290 |
+
"eval_accuracy": 0.5603917301414582,
|
1291 |
+
"eval_loss": 1.4800572395324707,
|
1292 |
+
"eval_runtime": 31.1581,
|
1293 |
+
"eval_samples_per_second": 58.99,
|
1294 |
+
"eval_steps_per_second": 7.382,
|
1295 |
+
"step": 1560
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 1.71,
|
1299 |
+
"learning_rate": 0.0001145810663764962,
|
1300 |
+
"loss": 1.2379,
|
1301 |
+
"step": 1570
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 1.72,
|
1305 |
+
"learning_rate": 0.00011403699673558216,
|
1306 |
+
"loss": 1.2098,
|
1307 |
+
"step": 1580
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 1.73,
|
1311 |
+
"learning_rate": 0.00011349292709466813,
|
1312 |
+
"loss": 0.9532,
|
1313 |
+
"step": 1590
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 1.74,
|
1317 |
+
"learning_rate": 0.00011294885745375408,
|
1318 |
+
"loss": 1.035,
|
1319 |
+
"step": 1600
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 1.74,
|
1323 |
+
"eval_accuracy": 0.5603917301414582,
|
1324 |
+
"eval_loss": 1.4868272542953491,
|
1325 |
+
"eval_runtime": 31.3011,
|
1326 |
+
"eval_samples_per_second": 58.72,
|
1327 |
+
"eval_steps_per_second": 7.348,
|
1328 |
+
"step": 1600
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 1.75,
|
1332 |
+
"learning_rate": 0.00011240478781284005,
|
1333 |
+
"loss": 1.2168,
|
1334 |
+
"step": 1610
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 1.76,
|
1338 |
+
"learning_rate": 0.000111860718171926,
|
1339 |
+
"loss": 1.2665,
|
1340 |
+
"step": 1620
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 1.77,
|
1344 |
+
"learning_rate": 0.00011131664853101198,
|
1345 |
+
"loss": 1.203,
|
1346 |
+
"step": 1630
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 1.78,
|
1350 |
+
"learning_rate": 0.00011077257889009793,
|
1351 |
+
"loss": 1.2621,
|
1352 |
+
"step": 1640
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 1.78,
|
1356 |
+
"eval_accuracy": 0.5778019586507073,
|
1357 |
+
"eval_loss": 1.439843773841858,
|
1358 |
+
"eval_runtime": 31.2165,
|
1359 |
+
"eval_samples_per_second": 58.879,
|
1360 |
+
"eval_steps_per_second": 7.368,
|
1361 |
+
"step": 1640
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 1.8,
|
1365 |
+
"learning_rate": 0.00011022850924918391,
|
1366 |
+
"loss": 1.0592,
|
1367 |
+
"step": 1650
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 1.81,
|
1371 |
+
"learning_rate": 0.00010968443960826986,
|
1372 |
+
"loss": 1.2805,
|
1373 |
+
"step": 1660
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 1.82,
|
1377 |
+
"learning_rate": 0.00010914036996735584,
|
1378 |
+
"loss": 1.24,
|
1379 |
+
"step": 1670
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 1.83,
|
1383 |
+
"learning_rate": 0.00010859630032644179,
|
1384 |
+
"loss": 1.3298,
|
1385 |
+
"step": 1680
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 1.83,
|
1389 |
+
"eval_accuracy": 0.5756256800870512,
|
1390 |
+
"eval_loss": 1.4398308992385864,
|
1391 |
+
"eval_runtime": 31.3359,
|
1392 |
+
"eval_samples_per_second": 58.655,
|
1393 |
+
"eval_steps_per_second": 7.34,
|
1394 |
+
"step": 1680
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 1.84,
|
1398 |
+
"learning_rate": 0.00010805223068552774,
|
1399 |
+
"loss": 1.1844,
|
1400 |
+
"step": 1690
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 1.85,
|
1404 |
+
"learning_rate": 0.00010750816104461372,
|
1405 |
+
"loss": 1.1519,
|
1406 |
+
"step": 1700
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 1.86,
|
1410 |
+
"learning_rate": 0.00010696409140369967,
|
1411 |
+
"loss": 1.446,
|
1412 |
+
"step": 1710
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 1.87,
|
1416 |
+
"learning_rate": 0.00010642002176278565,
|
1417 |
+
"loss": 1.2588,
|
1418 |
+
"step": 1720
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 1.87,
|
1422 |
+
"eval_accuracy": 0.5652883569096845,
|
1423 |
+
"eval_loss": 1.4510564804077148,
|
1424 |
+
"eval_runtime": 31.3918,
|
1425 |
+
"eval_samples_per_second": 58.55,
|
1426 |
+
"eval_steps_per_second": 7.327,
|
1427 |
+
"step": 1720
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 1.88,
|
1431 |
+
"learning_rate": 0.0001058759521218716,
|
1432 |
+
"loss": 1.1114,
|
1433 |
+
"step": 1730
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 1.89,
|
1437 |
+
"learning_rate": 0.00010533188248095758,
|
1438 |
+
"loss": 1.0445,
|
1439 |
+
"step": 1740
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 1.9,
|
1443 |
+
"learning_rate": 0.00010478781284004354,
|
1444 |
+
"loss": 1.0959,
|
1445 |
+
"step": 1750
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 1.92,
|
1449 |
+
"learning_rate": 0.00010424374319912949,
|
1450 |
+
"loss": 1.2207,
|
1451 |
+
"step": 1760
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 1.92,
|
1455 |
+
"eval_accuracy": 0.5935799782372143,
|
1456 |
+
"eval_loss": 1.3912413120269775,
|
1457 |
+
"eval_runtime": 32.052,
|
1458 |
+
"eval_samples_per_second": 57.344,
|
1459 |
+
"eval_steps_per_second": 7.176,
|
1460 |
+
"step": 1760
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 1.93,
|
1464 |
+
"learning_rate": 0.00010369967355821547,
|
1465 |
+
"loss": 1.2121,
|
1466 |
+
"step": 1770
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 1.94,
|
1470 |
+
"learning_rate": 0.00010315560391730142,
|
1471 |
+
"loss": 1.1847,
|
1472 |
+
"step": 1780
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 1.95,
|
1476 |
+
"learning_rate": 0.00010261153427638738,
|
1477 |
+
"loss": 1.1857,
|
1478 |
+
"step": 1790
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 1.96,
|
1482 |
+
"learning_rate": 0.00010206746463547334,
|
1483 |
+
"loss": 1.0643,
|
1484 |
+
"step": 1800
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 1.96,
|
1488 |
+
"eval_accuracy": 0.6006528835690969,
|
1489 |
+
"eval_loss": 1.390648365020752,
|
1490 |
+
"eval_runtime": 31.7091,
|
1491 |
+
"eval_samples_per_second": 57.964,
|
1492 |
+
"eval_steps_per_second": 7.253,
|
1493 |
+
"step": 1800
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 1.97,
|
1497 |
+
"learning_rate": 0.00010152339499455931,
|
1498 |
+
"loss": 1.2481,
|
1499 |
+
"step": 1810
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 1.98,
|
1503 |
+
"learning_rate": 0.00010097932535364527,
|
1504 |
+
"loss": 1.2109,
|
1505 |
+
"step": 1820
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 1.99,
|
1509 |
+
"learning_rate": 0.00010043525571273122,
|
1510 |
+
"loss": 1.0191,
|
1511 |
+
"step": 1830
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"epoch": 2.0,
|
1515 |
+
"learning_rate": 9.98911860718172e-05,
|
1516 |
+
"loss": 1.0464,
|
1517 |
+
"step": 1840
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 2.0,
|
1521 |
+
"eval_accuracy": 0.5957562568008705,
|
1522 |
+
"eval_loss": 1.3601454496383667,
|
1523 |
+
"eval_runtime": 31.4007,
|
1524 |
+
"eval_samples_per_second": 58.534,
|
1525 |
+
"eval_steps_per_second": 7.325,
|
1526 |
+
"step": 1840
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 2.01,
|
1530 |
+
"learning_rate": 9.934711643090316e-05,
|
1531 |
+
"loss": 0.645,
|
1532 |
+
"step": 1850
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 2.02,
|
1536 |
+
"learning_rate": 9.880304678998913e-05,
|
1537 |
+
"loss": 0.6802,
|
1538 |
+
"step": 1860
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 2.03,
|
1542 |
+
"learning_rate": 9.825897714907508e-05,
|
1543 |
+
"loss": 0.6228,
|
1544 |
+
"step": 1870
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 2.05,
|
1548 |
+
"learning_rate": 9.771490750816105e-05,
|
1549 |
+
"loss": 0.6345,
|
1550 |
+
"step": 1880
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 2.05,
|
1554 |
+
"eval_accuracy": 0.5973884657236126,
|
1555 |
+
"eval_loss": 1.3790967464447021,
|
1556 |
+
"eval_runtime": 31.7311,
|
1557 |
+
"eval_samples_per_second": 57.924,
|
1558 |
+
"eval_steps_per_second": 7.248,
|
1559 |
+
"step": 1880
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 2.06,
|
1563 |
+
"learning_rate": 9.717083786724701e-05,
|
1564 |
+
"loss": 0.5766,
|
1565 |
+
"step": 1890
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 2.07,
|
1569 |
+
"learning_rate": 9.662676822633298e-05,
|
1570 |
+
"loss": 0.5642,
|
1571 |
+
"step": 1900
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 2.08,
|
1575 |
+
"learning_rate": 9.608269858541894e-05,
|
1576 |
+
"loss": 0.5394,
|
1577 |
+
"step": 1910
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 2.09,
|
1581 |
+
"learning_rate": 9.553862894450491e-05,
|
1582 |
+
"loss": 0.5622,
|
1583 |
+
"step": 1920
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 2.09,
|
1587 |
+
"eval_accuracy": 0.5957562568008705,
|
1588 |
+
"eval_loss": 1.3800909519195557,
|
1589 |
+
"eval_runtime": 31.768,
|
1590 |
+
"eval_samples_per_second": 57.857,
|
1591 |
+
"eval_steps_per_second": 7.24,
|
1592 |
+
"step": 1920
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 2.1,
|
1596 |
+
"learning_rate": 9.499455930359087e-05,
|
1597 |
+
"loss": 0.5452,
|
1598 |
+
"step": 1930
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 2.11,
|
1602 |
+
"learning_rate": 9.445048966267683e-05,
|
1603 |
+
"loss": 0.5394,
|
1604 |
+
"step": 1940
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 2.12,
|
1608 |
+
"learning_rate": 9.390642002176279e-05,
|
1609 |
+
"loss": 0.6138,
|
1610 |
+
"step": 1950
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 2.13,
|
1614 |
+
"learning_rate": 9.336235038084876e-05,
|
1615 |
+
"loss": 0.4926,
|
1616 |
+
"step": 1960
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 2.13,
|
1620 |
+
"eval_accuracy": 0.6071817192600653,
|
1621 |
+
"eval_loss": 1.3753130435943604,
|
1622 |
+
"eval_runtime": 32.14,
|
1623 |
+
"eval_samples_per_second": 57.187,
|
1624 |
+
"eval_steps_per_second": 7.156,
|
1625 |
+
"step": 1960
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 2.14,
|
1629 |
+
"learning_rate": 9.281828073993472e-05,
|
1630 |
+
"loss": 0.5839,
|
1631 |
+
"step": 1970
|
1632 |
+
},
|
1633 |
+
{
|
1634 |
+
"epoch": 2.15,
|
1635 |
+
"learning_rate": 9.227421109902067e-05,
|
1636 |
+
"loss": 0.6893,
|
1637 |
+
"step": 1980
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 2.17,
|
1641 |
+
"learning_rate": 9.173014145810664e-05,
|
1642 |
+
"loss": 0.5675,
|
1643 |
+
"step": 1990
|
1644 |
+
},
|
1645 |
+
{
|
1646 |
+
"epoch": 2.18,
|
1647 |
+
"learning_rate": 9.11860718171926e-05,
|
1648 |
+
"loss": 0.6031,
|
1649 |
+
"step": 2000
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 2.18,
|
1653 |
+
"eval_accuracy": 0.5979325353645266,
|
1654 |
+
"eval_loss": 1.3890224695205688,
|
1655 |
+
"eval_runtime": 31.7313,
|
1656 |
+
"eval_samples_per_second": 57.924,
|
1657 |
+
"eval_steps_per_second": 7.248,
|
1658 |
+
"step": 2000
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 2.19,
|
1662 |
+
"learning_rate": 9.064200217627857e-05,
|
1663 |
+
"loss": 0.5095,
|
1664 |
+
"step": 2010
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 2.2,
|
1668 |
+
"learning_rate": 9.009793253536452e-05,
|
1669 |
+
"loss": 0.589,
|
1670 |
+
"step": 2020
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 2.21,
|
1674 |
+
"learning_rate": 8.955386289445049e-05,
|
1675 |
+
"loss": 0.667,
|
1676 |
+
"step": 2030
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 2.22,
|
1680 |
+
"learning_rate": 8.900979325353645e-05,
|
1681 |
+
"loss": 0.376,
|
1682 |
+
"step": 2040
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 2.22,
|
1686 |
+
"eval_accuracy": 0.6191512513601741,
|
1687 |
+
"eval_loss": 1.3675874471664429,
|
1688 |
+
"eval_runtime": 31.4637,
|
1689 |
+
"eval_samples_per_second": 58.417,
|
1690 |
+
"eval_steps_per_second": 7.31,
|
1691 |
+
"step": 2040
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 2.23,
|
1695 |
+
"learning_rate": 8.846572361262242e-05,
|
1696 |
+
"loss": 0.5566,
|
1697 |
+
"step": 2050
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 2.24,
|
1701 |
+
"learning_rate": 8.792165397170838e-05,
|
1702 |
+
"loss": 0.5404,
|
1703 |
+
"step": 2060
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 2.25,
|
1707 |
+
"learning_rate": 8.737758433079435e-05,
|
1708 |
+
"loss": 0.7074,
|
1709 |
+
"step": 2070
|
1710 |
+
},
|
1711 |
+
{
|
1712 |
+
"epoch": 2.26,
|
1713 |
+
"learning_rate": 8.683351468988032e-05,
|
1714 |
+
"loss": 0.5824,
|
1715 |
+
"step": 2080
|
1716 |
+
},
|
1717 |
+
{
|
1718 |
+
"epoch": 2.26,
|
1719 |
+
"eval_accuracy": 0.6066376496191512,
|
1720 |
+
"eval_loss": 1.4152354001998901,
|
1721 |
+
"eval_runtime": 31.6073,
|
1722 |
+
"eval_samples_per_second": 58.151,
|
1723 |
+
"eval_steps_per_second": 7.277,
|
1724 |
+
"step": 2080
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 2.27,
|
1728 |
+
"learning_rate": 8.628944504896627e-05,
|
1729 |
+
"loss": 0.5761,
|
1730 |
+
"step": 2090
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 2.29,
|
1734 |
+
"learning_rate": 8.574537540805223e-05,
|
1735 |
+
"loss": 0.6037,
|
1736 |
+
"step": 2100
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 2.3,
|
1740 |
+
"learning_rate": 8.52013057671382e-05,
|
1741 |
+
"loss": 0.4611,
|
1742 |
+
"step": 2110
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 2.31,
|
1746 |
+
"learning_rate": 8.465723612622416e-05,
|
1747 |
+
"loss": 0.6753,
|
1748 |
+
"step": 2120
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 2.31,
|
1752 |
+
"eval_accuracy": 0.6099020674646355,
|
1753 |
+
"eval_loss": 1.3810958862304688,
|
1754 |
+
"eval_runtime": 31.5282,
|
1755 |
+
"eval_samples_per_second": 58.297,
|
1756 |
+
"eval_steps_per_second": 7.295,
|
1757 |
+
"step": 2120
|
1758 |
+
},
|
1759 |
+
{
|
1760 |
+
"epoch": 2.32,
|
1761 |
+
"learning_rate": 8.411316648531013e-05,
|
1762 |
+
"loss": 0.5639,
|
1763 |
+
"step": 2130
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 2.33,
|
1767 |
+
"learning_rate": 8.35690968443961e-05,
|
1768 |
+
"loss": 0.5866,
|
1769 |
+
"step": 2140
|
1770 |
+
},
|
1771 |
+
{
|
1772 |
+
"epoch": 2.34,
|
1773 |
+
"learning_rate": 8.302502720348205e-05,
|
1774 |
+
"loss": 0.515,
|
1775 |
+
"step": 2150
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 2.35,
|
1779 |
+
"learning_rate": 8.248095756256801e-05,
|
1780 |
+
"loss": 0.5047,
|
1781 |
+
"step": 2160
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 2.35,
|
1785 |
+
"eval_accuracy": 0.6082698585418934,
|
1786 |
+
"eval_loss": 1.3635469675064087,
|
1787 |
+
"eval_runtime": 31.4892,
|
1788 |
+
"eval_samples_per_second": 58.369,
|
1789 |
+
"eval_steps_per_second": 7.304,
|
1790 |
+
"step": 2160
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 2.36,
|
1794 |
+
"learning_rate": 8.193688792165398e-05,
|
1795 |
+
"loss": 0.5216,
|
1796 |
+
"step": 2170
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 2.37,
|
1800 |
+
"learning_rate": 8.139281828073993e-05,
|
1801 |
+
"loss": 0.4849,
|
1802 |
+
"step": 2180
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 2.38,
|
1806 |
+
"learning_rate": 8.08487486398259e-05,
|
1807 |
+
"loss": 0.561,
|
1808 |
+
"step": 2190
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 2.39,
|
1812 |
+
"learning_rate": 8.030467899891186e-05,
|
1813 |
+
"loss": 0.4831,
|
1814 |
+
"step": 2200
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 2.39,
|
1818 |
+
"eval_accuracy": 0.6039173014145811,
|
1819 |
+
"eval_loss": 1.4076539278030396,
|
1820 |
+
"eval_runtime": 32.0853,
|
1821 |
+
"eval_samples_per_second": 57.285,
|
1822 |
+
"eval_steps_per_second": 7.168,
|
1823 |
+
"step": 2200
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 2.4,
|
1827 |
+
"learning_rate": 7.976060935799783e-05,
|
1828 |
+
"loss": 0.5728,
|
1829 |
+
"step": 2210
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 2.42,
|
1833 |
+
"learning_rate": 7.921653971708379e-05,
|
1834 |
+
"loss": 0.444,
|
1835 |
+
"step": 2220
|
1836 |
+
},
|
1837 |
+
{
|
1838 |
+
"epoch": 2.43,
|
1839 |
+
"learning_rate": 7.867247007616976e-05,
|
1840 |
+
"loss": 0.5329,
|
1841 |
+
"step": 2230
|
1842 |
+
},
|
1843 |
+
{
|
1844 |
+
"epoch": 2.44,
|
1845 |
+
"learning_rate": 7.812840043525572e-05,
|
1846 |
+
"loss": 0.6054,
|
1847 |
+
"step": 2240
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 2.44,
|
1851 |
+
"eval_accuracy": 0.6175190424374319,
|
1852 |
+
"eval_loss": 1.361071228981018,
|
1853 |
+
"eval_runtime": 32.0081,
|
1854 |
+
"eval_samples_per_second": 57.423,
|
1855 |
+
"eval_steps_per_second": 7.186,
|
1856 |
+
"step": 2240
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 2.45,
|
1860 |
+
"learning_rate": 7.758433079434167e-05,
|
1861 |
+
"loss": 0.5624,
|
1862 |
+
"step": 2250
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 2.46,
|
1866 |
+
"learning_rate": 7.704026115342764e-05,
|
1867 |
+
"loss": 0.561,
|
1868 |
+
"step": 2260
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 2.47,
|
1872 |
+
"learning_rate": 7.64961915125136e-05,
|
1873 |
+
"loss": 0.5178,
|
1874 |
+
"step": 2270
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 2.48,
|
1878 |
+
"learning_rate": 7.595212187159957e-05,
|
1879 |
+
"loss": 0.5997,
|
1880 |
+
"step": 2280
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 2.48,
|
1884 |
+
"eval_accuracy": 0.6158868335146899,
|
1885 |
+
"eval_loss": 1.3456101417541504,
|
1886 |
+
"eval_runtime": 31.9844,
|
1887 |
+
"eval_samples_per_second": 57.465,
|
1888 |
+
"eval_steps_per_second": 7.191,
|
1889 |
+
"step": 2280
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 2.49,
|
1893 |
+
"learning_rate": 7.540805223068554e-05,
|
1894 |
+
"loss": 0.4876,
|
1895 |
+
"step": 2290
|
1896 |
+
},
|
1897 |
+
{
|
1898 |
+
"epoch": 2.5,
|
1899 |
+
"learning_rate": 7.48639825897715e-05,
|
1900 |
+
"loss": 0.5375,
|
1901 |
+
"step": 2300
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 2.51,
|
1905 |
+
"learning_rate": 7.431991294885747e-05,
|
1906 |
+
"loss": 0.5727,
|
1907 |
+
"step": 2310
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 2.52,
|
1911 |
+
"learning_rate": 7.377584330794342e-05,
|
1912 |
+
"loss": 0.4648,
|
1913 |
+
"step": 2320
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 2.52,
|
1917 |
+
"eval_accuracy": 0.6175190424374319,
|
1918 |
+
"eval_loss": 1.3429198265075684,
|
1919 |
+
"eval_runtime": 31.6074,
|
1920 |
+
"eval_samples_per_second": 58.151,
|
1921 |
+
"eval_steps_per_second": 7.277,
|
1922 |
+
"step": 2320
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 2.54,
|
1926 |
+
"learning_rate": 7.323177366702938e-05,
|
1927 |
+
"loss": 0.5728,
|
1928 |
+
"step": 2330
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 2.55,
|
1932 |
+
"learning_rate": 7.268770402611535e-05,
|
1933 |
+
"loss": 0.4683,
|
1934 |
+
"step": 2340
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 2.56,
|
1938 |
+
"learning_rate": 7.21436343852013e-05,
|
1939 |
+
"loss": 0.5095,
|
1940 |
+
"step": 2350
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 2.57,
|
1944 |
+
"learning_rate": 7.159956474428727e-05,
|
1945 |
+
"loss": 0.5885,
|
1946 |
+
"step": 2360
|
1947 |
+
},
|
1948 |
+
{
|
1949 |
+
"epoch": 2.57,
|
1950 |
+
"eval_accuracy": 0.6218715995647442,
|
1951 |
+
"eval_loss": 1.3531224727630615,
|
1952 |
+
"eval_runtime": 31.6702,
|
1953 |
+
"eval_samples_per_second": 58.036,
|
1954 |
+
"eval_steps_per_second": 7.262,
|
1955 |
+
"step": 2360
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 2.58,
|
1959 |
+
"learning_rate": 7.105549510337323e-05,
|
1960 |
+
"loss": 0.483,
|
1961 |
+
"step": 2370
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 2.59,
|
1965 |
+
"learning_rate": 7.05114254624592e-05,
|
1966 |
+
"loss": 0.4248,
|
1967 |
+
"step": 2380
|
1968 |
+
},
|
1969 |
+
{
|
1970 |
+
"epoch": 2.6,
|
1971 |
+
"learning_rate": 6.996735582154516e-05,
|
1972 |
+
"loss": 0.4206,
|
1973 |
+
"step": 2390
|
1974 |
+
},
|
1975 |
+
{
|
1976 |
+
"epoch": 2.61,
|
1977 |
+
"learning_rate": 6.942328618063112e-05,
|
1978 |
+
"loss": 0.5405,
|
1979 |
+
"step": 2400
|
1980 |
+
},
|
1981 |
+
{
|
1982 |
+
"epoch": 2.61,
|
1983 |
+
"eval_accuracy": 0.6273122959738846,
|
1984 |
+
"eval_loss": 1.3313764333724976,
|
1985 |
+
"eval_runtime": 31.9004,
|
1986 |
+
"eval_samples_per_second": 57.617,
|
1987 |
+
"eval_steps_per_second": 7.21,
|
1988 |
+
"step": 2400
|
1989 |
+
},
|
1990 |
+
{
|
1991 |
+
"epoch": 2.62,
|
1992 |
+
"learning_rate": 6.887921653971708e-05,
|
1993 |
+
"loss": 0.4929,
|
1994 |
+
"step": 2410
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 2.63,
|
1998 |
+
"learning_rate": 6.833514689880305e-05,
|
1999 |
+
"loss": 0.5165,
|
2000 |
+
"step": 2420
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 2.64,
|
2004 |
+
"learning_rate": 6.779107725788901e-05,
|
2005 |
+
"loss": 0.6003,
|
2006 |
+
"step": 2430
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 2.66,
|
2010 |
+
"learning_rate": 6.724700761697498e-05,
|
2011 |
+
"loss": 0.5752,
|
2012 |
+
"step": 2440
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 2.66,
|
2016 |
+
"eval_accuracy": 0.6343852013057671,
|
2017 |
+
"eval_loss": 1.3247264623641968,
|
2018 |
+
"eval_runtime": 31.5426,
|
2019 |
+
"eval_samples_per_second": 58.27,
|
2020 |
+
"eval_steps_per_second": 7.292,
|
2021 |
+
"step": 2440
|
2022 |
+
},
|
2023 |
+
{
|
2024 |
+
"epoch": 2.67,
|
2025 |
+
"learning_rate": 6.670293797606094e-05,
|
2026 |
+
"loss": 0.4671,
|
2027 |
+
"step": 2450
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 2.68,
|
2031 |
+
"learning_rate": 6.615886833514691e-05,
|
2032 |
+
"loss": 0.4499,
|
2033 |
+
"step": 2460
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 2.69,
|
2037 |
+
"learning_rate": 6.561479869423286e-05,
|
2038 |
+
"loss": 0.5622,
|
2039 |
+
"step": 2470
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 2.7,
|
2043 |
+
"learning_rate": 6.507072905331883e-05,
|
2044 |
+
"loss": 0.5156,
|
2045 |
+
"step": 2480
|
2046 |
+
},
|
2047 |
+
{
|
2048 |
+
"epoch": 2.7,
|
2049 |
+
"eval_accuracy": 0.6322089227421109,
|
2050 |
+
"eval_loss": 1.3440065383911133,
|
2051 |
+
"eval_runtime": 32.1302,
|
2052 |
+
"eval_samples_per_second": 57.205,
|
2053 |
+
"eval_steps_per_second": 7.158,
|
2054 |
+
"step": 2480
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 2.71,
|
2058 |
+
"learning_rate": 6.452665941240479e-05,
|
2059 |
+
"loss": 0.4567,
|
2060 |
+
"step": 2490
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 2.72,
|
2064 |
+
"learning_rate": 6.398258977149076e-05,
|
2065 |
+
"loss": 0.6599,
|
2066 |
+
"step": 2500
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 2.73,
|
2070 |
+
"learning_rate": 6.343852013057672e-05,
|
2071 |
+
"loss": 0.4837,
|
2072 |
+
"step": 2510
|
2073 |
+
},
|
2074 |
+
{
|
2075 |
+
"epoch": 2.74,
|
2076 |
+
"learning_rate": 6.289445048966269e-05,
|
2077 |
+
"loss": 0.5518,
|
2078 |
+
"step": 2520
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 2.74,
|
2082 |
+
"eval_accuracy": 0.6338411316648531,
|
2083 |
+
"eval_loss": 1.315151333808899,
|
2084 |
+
"eval_runtime": 31.8096,
|
2085 |
+
"eval_samples_per_second": 57.781,
|
2086 |
+
"eval_steps_per_second": 7.231,
|
2087 |
+
"step": 2520
|
2088 |
+
},
|
2089 |
+
{
|
2090 |
+
"epoch": 2.75,
|
2091 |
+
"learning_rate": 6.235038084874864e-05,
|
2092 |
+
"loss": 0.4855,
|
2093 |
+
"step": 2530
|
2094 |
+
},
|
2095 |
+
{
|
2096 |
+
"epoch": 2.76,
|
2097 |
+
"learning_rate": 6.18063112078346e-05,
|
2098 |
+
"loss": 0.4465,
|
2099 |
+
"step": 2540
|
2100 |
+
},
|
2101 |
+
{
|
2102 |
+
"epoch": 2.77,
|
2103 |
+
"learning_rate": 6.126224156692056e-05,
|
2104 |
+
"loss": 0.5561,
|
2105 |
+
"step": 2550
|
2106 |
+
},
|
2107 |
+
{
|
2108 |
+
"epoch": 2.79,
|
2109 |
+
"learning_rate": 6.071817192600653e-05,
|
2110 |
+
"loss": 0.5928,
|
2111 |
+
"step": 2560
|
2112 |
+
},
|
2113 |
+
{
|
2114 |
+
"epoch": 2.79,
|
2115 |
+
"eval_accuracy": 0.6398258977149075,
|
2116 |
+
"eval_loss": 1.2906804084777832,
|
2117 |
+
"eval_runtime": 31.6667,
|
2118 |
+
"eval_samples_per_second": 58.042,
|
2119 |
+
"eval_steps_per_second": 7.263,
|
2120 |
+
"step": 2560
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 2.8,
|
2124 |
+
"learning_rate": 6.0174102285092495e-05,
|
2125 |
+
"loss": 0.5153,
|
2126 |
+
"step": 2570
|
2127 |
+
},
|
2128 |
+
{
|
2129 |
+
"epoch": 2.81,
|
2130 |
+
"learning_rate": 5.9630032644178454e-05,
|
2131 |
+
"loss": 0.4992,
|
2132 |
+
"step": 2580
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 2.82,
|
2136 |
+
"learning_rate": 5.908596300326442e-05,
|
2137 |
+
"loss": 0.5095,
|
2138 |
+
"step": 2590
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 2.83,
|
2142 |
+
"learning_rate": 5.8541893362350385e-05,
|
2143 |
+
"loss": 0.5283,
|
2144 |
+
"step": 2600
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 2.83,
|
2148 |
+
"eval_accuracy": 0.6452665941240479,
|
2149 |
+
"eval_loss": 1.2707958221435547,
|
2150 |
+
"eval_runtime": 31.5986,
|
2151 |
+
"eval_samples_per_second": 58.167,
|
2152 |
+
"eval_steps_per_second": 7.279,
|
2153 |
+
"step": 2600
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 2.84,
|
2157 |
+
"learning_rate": 5.799782372143635e-05,
|
2158 |
+
"loss": 0.4745,
|
2159 |
+
"step": 2610
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 2.85,
|
2163 |
+
"learning_rate": 5.7453754080522316e-05,
|
2164 |
+
"loss": 0.503,
|
2165 |
+
"step": 2620
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 2.86,
|
2169 |
+
"learning_rate": 5.690968443960827e-05,
|
2170 |
+
"loss": 0.3843,
|
2171 |
+
"step": 2630
|
2172 |
+
},
|
2173 |
+
{
|
2174 |
+
"epoch": 2.87,
|
2175 |
+
"learning_rate": 5.636561479869423e-05,
|
2176 |
+
"loss": 0.5054,
|
2177 |
+
"step": 2640
|
2178 |
+
},
|
2179 |
+
{
|
2180 |
+
"epoch": 2.87,
|
2181 |
+
"eval_accuracy": 0.6332970620239391,
|
2182 |
+
"eval_loss": 1.2805439233779907,
|
2183 |
+
"eval_runtime": 31.8568,
|
2184 |
+
"eval_samples_per_second": 57.696,
|
2185 |
+
"eval_steps_per_second": 7.22,
|
2186 |
+
"step": 2640
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 2.88,
|
2190 |
+
"learning_rate": 5.58215451577802e-05,
|
2191 |
+
"loss": 0.4127,
|
2192 |
+
"step": 2650
|
2193 |
+
},
|
2194 |
+
{
|
2195 |
+
"epoch": 2.89,
|
2196 |
+
"learning_rate": 5.5277475516866164e-05,
|
2197 |
+
"loss": 0.4589,
|
2198 |
+
"step": 2660
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"epoch": 2.91,
|
2202 |
+
"learning_rate": 5.473340587595212e-05,
|
2203 |
+
"loss": 0.6578,
|
2204 |
+
"step": 2670
|
2205 |
+
},
|
2206 |
+
{
|
2207 |
+
"epoch": 2.92,
|
2208 |
+
"learning_rate": 5.418933623503809e-05,
|
2209 |
+
"loss": 0.4513,
|
2210 |
+
"step": 2680
|
2211 |
+
},
|
2212 |
+
{
|
2213 |
+
"epoch": 2.92,
|
2214 |
+
"eval_accuracy": 0.6360174102285092,
|
2215 |
+
"eval_loss": 1.304470419883728,
|
2216 |
+
"eval_runtime": 32.1887,
|
2217 |
+
"eval_samples_per_second": 57.101,
|
2218 |
+
"eval_steps_per_second": 7.145,
|
2219 |
+
"step": 2680
|
2220 |
+
},
|
2221 |
+
{
|
2222 |
+
"epoch": 2.93,
|
2223 |
+
"learning_rate": 5.3645266594124054e-05,
|
2224 |
+
"loss": 0.5623,
|
2225 |
+
"step": 2690
|
2226 |
+
},
|
2227 |
+
{
|
2228 |
+
"epoch": 2.94,
|
2229 |
+
"learning_rate": 5.3101196953210006e-05,
|
2230 |
+
"loss": 0.6832,
|
2231 |
+
"step": 2700
|
2232 |
+
},
|
2233 |
+
{
|
2234 |
+
"epoch": 2.95,
|
2235 |
+
"learning_rate": 5.255712731229597e-05,
|
2236 |
+
"loss": 0.417,
|
2237 |
+
"step": 2710
|
2238 |
+
},
|
2239 |
+
{
|
2240 |
+
"epoch": 2.96,
|
2241 |
+
"learning_rate": 5.201305767138194e-05,
|
2242 |
+
"loss": 0.4405,
|
2243 |
+
"step": 2720
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 2.96,
|
2247 |
+
"eval_accuracy": 0.6425462459194777,
|
2248 |
+
"eval_loss": 1.3049399852752686,
|
2249 |
+
"eval_runtime": 32.0538,
|
2250 |
+
"eval_samples_per_second": 57.341,
|
2251 |
+
"eval_steps_per_second": 7.175,
|
2252 |
+
"step": 2720
|
2253 |
+
},
|
2254 |
+
{
|
2255 |
+
"epoch": 2.97,
|
2256 |
+
"learning_rate": 5.14689880304679e-05,
|
2257 |
+
"loss": 0.5936,
|
2258 |
+
"step": 2730
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 2.98,
|
2262 |
+
"learning_rate": 5.092491838955387e-05,
|
2263 |
+
"loss": 0.411,
|
2264 |
+
"step": 2740
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 2.99,
|
2268 |
+
"learning_rate": 5.038084874863983e-05,
|
2269 |
+
"loss": 0.4975,
|
2270 |
+
"step": 2750
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 3.0,
|
2274 |
+
"learning_rate": 4.983677910772579e-05,
|
2275 |
+
"loss": 0.3695,
|
2276 |
+
"step": 2760
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 3.0,
|
2280 |
+
"eval_accuracy": 0.6398258977149075,
|
2281 |
+
"eval_loss": 1.3069652318954468,
|
2282 |
+
"eval_runtime": 31.9114,
|
2283 |
+
"eval_samples_per_second": 57.597,
|
2284 |
+
"eval_steps_per_second": 7.207,
|
2285 |
+
"step": 2760
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 3.01,
|
2289 |
+
"learning_rate": 4.929270946681175e-05,
|
2290 |
+
"loss": 0.2096,
|
2291 |
+
"step": 2770
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 3.03,
|
2295 |
+
"learning_rate": 4.8748639825897716e-05,
|
2296 |
+
"loss": 0.134,
|
2297 |
+
"step": 2780
|
2298 |
+
},
|
2299 |
+
{
|
2300 |
+
"epoch": 3.04,
|
2301 |
+
"learning_rate": 4.820457018498368e-05,
|
2302 |
+
"loss": 0.1749,
|
2303 |
+
"step": 2790
|
2304 |
+
},
|
2305 |
+
{
|
2306 |
+
"epoch": 3.05,
|
2307 |
+
"learning_rate": 4.766050054406964e-05,
|
2308 |
+
"loss": 0.2109,
|
2309 |
+
"step": 2800
|
2310 |
+
},
|
2311 |
+
{
|
2312 |
+
"epoch": 3.05,
|
2313 |
+
"eval_accuracy": 0.6414581066376496,
|
2314 |
+
"eval_loss": 1.3126190900802612,
|
2315 |
+
"eval_runtime": 31.6295,
|
2316 |
+
"eval_samples_per_second": 58.11,
|
2317 |
+
"eval_steps_per_second": 7.272,
|
2318 |
+
"step": 2800
|
2319 |
+
},
|
2320 |
+
{
|
2321 |
+
"epoch": 3.06,
|
2322 |
+
"learning_rate": 4.7116430903155606e-05,
|
2323 |
+
"loss": 0.1672,
|
2324 |
+
"step": 2810
|
2325 |
+
},
|
2326 |
+
{
|
2327 |
+
"epoch": 3.07,
|
2328 |
+
"learning_rate": 4.657236126224157e-05,
|
2329 |
+
"loss": 0.1398,
|
2330 |
+
"step": 2820
|
2331 |
+
},
|
2332 |
+
{
|
2333 |
+
"epoch": 3.08,
|
2334 |
+
"learning_rate": 4.602829162132753e-05,
|
2335 |
+
"loss": 0.2211,
|
2336 |
+
"step": 2830
|
2337 |
+
},
|
2338 |
+
{
|
2339 |
+
"epoch": 3.09,
|
2340 |
+
"learning_rate": 4.5484221980413496e-05,
|
2341 |
+
"loss": 0.1899,
|
2342 |
+
"step": 2840
|
2343 |
+
},
|
2344 |
+
{
|
2345 |
+
"epoch": 3.09,
|
2346 |
+
"eval_accuracy": 0.6517954298150164,
|
2347 |
+
"eval_loss": 1.3004298210144043,
|
2348 |
+
"eval_runtime": 31.8608,
|
2349 |
+
"eval_samples_per_second": 57.688,
|
2350 |
+
"eval_steps_per_second": 7.219,
|
2351 |
+
"step": 2840
|
2352 |
+
},
|
2353 |
+
{
|
2354 |
+
"epoch": 3.1,
|
2355 |
+
"learning_rate": 4.494015233949946e-05,
|
2356 |
+
"loss": 0.1822,
|
2357 |
+
"step": 2850
|
2358 |
+
},
|
2359 |
+
{
|
2360 |
+
"epoch": 3.11,
|
2361 |
+
"learning_rate": 4.439608269858542e-05,
|
2362 |
+
"loss": 0.1346,
|
2363 |
+
"step": 2860
|
2364 |
+
},
|
2365 |
+
{
|
2366 |
+
"epoch": 3.12,
|
2367 |
+
"learning_rate": 4.385201305767138e-05,
|
2368 |
+
"loss": 0.1895,
|
2369 |
+
"step": 2870
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 3.13,
|
2373 |
+
"learning_rate": 4.3307943416757344e-05,
|
2374 |
+
"loss": 0.1338,
|
2375 |
+
"step": 2880
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 3.13,
|
2379 |
+
"eval_accuracy": 0.6507072905331882,
|
2380 |
+
"eval_loss": 1.292977213859558,
|
2381 |
+
"eval_runtime": 32.2424,
|
2382 |
+
"eval_samples_per_second": 57.006,
|
2383 |
+
"eval_steps_per_second": 7.133,
|
2384 |
+
"step": 2880
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 3.14,
|
2388 |
+
"learning_rate": 4.276387377584331e-05,
|
2389 |
+
"loss": 0.1475,
|
2390 |
+
"step": 2890
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 3.16,
|
2394 |
+
"learning_rate": 4.2219804134929275e-05,
|
2395 |
+
"loss": 0.1118,
|
2396 |
+
"step": 2900
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 3.17,
|
2400 |
+
"learning_rate": 4.1675734494015234e-05,
|
2401 |
+
"loss": 0.2001,
|
2402 |
+
"step": 2910
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 3.18,
|
2406 |
+
"learning_rate": 4.11316648531012e-05,
|
2407 |
+
"loss": 0.1681,
|
2408 |
+
"step": 2920
|
2409 |
+
},
|
2410 |
+
{
|
2411 |
+
"epoch": 3.18,
|
2412 |
+
"eval_accuracy": 0.6452665941240479,
|
2413 |
+
"eval_loss": 1.338887095451355,
|
2414 |
+
"eval_runtime": 32.1012,
|
2415 |
+
"eval_samples_per_second": 57.256,
|
2416 |
+
"eval_steps_per_second": 7.165,
|
2417 |
+
"step": 2920
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 3.19,
|
2421 |
+
"learning_rate": 4.0587595212187165e-05,
|
2422 |
+
"loss": 0.1207,
|
2423 |
+
"step": 2930
|
2424 |
+
},
|
2425 |
+
{
|
2426 |
+
"epoch": 3.2,
|
2427 |
+
"learning_rate": 4.004352557127313e-05,
|
2428 |
+
"loss": 0.158,
|
2429 |
+
"step": 2940
|
2430 |
+
},
|
2431 |
+
{
|
2432 |
+
"epoch": 3.21,
|
2433 |
+
"learning_rate": 3.949945593035909e-05,
|
2434 |
+
"loss": 0.1602,
|
2435 |
+
"step": 2950
|
2436 |
+
},
|
2437 |
+
{
|
2438 |
+
"epoch": 3.22,
|
2439 |
+
"learning_rate": 3.895538628944505e-05,
|
2440 |
+
"loss": 0.156,
|
2441 |
+
"step": 2960
|
2442 |
+
},
|
2443 |
+
{
|
2444 |
+
"epoch": 3.22,
|
2445 |
+
"eval_accuracy": 0.6430903155603918,
|
2446 |
+
"eval_loss": 1.3379881381988525,
|
2447 |
+
"eval_runtime": 31.8038,
|
2448 |
+
"eval_samples_per_second": 57.792,
|
2449 |
+
"eval_steps_per_second": 7.232,
|
2450 |
+
"step": 2960
|
2451 |
+
},
|
2452 |
+
{
|
2453 |
+
"epoch": 3.23,
|
2454 |
+
"learning_rate": 3.841131664853101e-05,
|
2455 |
+
"loss": 0.2014,
|
2456 |
+
"step": 2970
|
2457 |
+
},
|
2458 |
+
{
|
2459 |
+
"epoch": 3.24,
|
2460 |
+
"learning_rate": 3.786724700761698e-05,
|
2461 |
+
"loss": 0.1704,
|
2462 |
+
"step": 2980
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 3.25,
|
2466 |
+
"learning_rate": 3.732317736670294e-05,
|
2467 |
+
"loss": 0.2522,
|
2468 |
+
"step": 2990
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 3.26,
|
2472 |
+
"learning_rate": 3.67791077257889e-05,
|
2473 |
+
"loss": 0.1717,
|
2474 |
+
"step": 3000
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 3.26,
|
2478 |
+
"eval_accuracy": 0.6371055495103374,
|
2479 |
+
"eval_loss": 1.3541066646575928,
|
2480 |
+
"eval_runtime": 32.1836,
|
2481 |
+
"eval_samples_per_second": 57.11,
|
2482 |
+
"eval_steps_per_second": 7.147,
|
2483 |
+
"step": 3000
|
2484 |
+
},
|
2485 |
+
{
|
2486 |
+
"epoch": 3.28,
|
2487 |
+
"learning_rate": 3.623503808487487e-05,
|
2488 |
+
"loss": 0.1593,
|
2489 |
+
"step": 3010
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 3.29,
|
2493 |
+
"learning_rate": 3.569096844396083e-05,
|
2494 |
+
"loss": 0.1803,
|
2495 |
+
"step": 3020
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 3.3,
|
2499 |
+
"learning_rate": 3.514689880304679e-05,
|
2500 |
+
"loss": 0.1687,
|
2501 |
+
"step": 3030
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 3.31,
|
2505 |
+
"learning_rate": 3.460282916213276e-05,
|
2506 |
+
"loss": 0.1244,
|
2507 |
+
"step": 3040
|
2508 |
+
},
|
2509 |
+
{
|
2510 |
+
"epoch": 3.31,
|
2511 |
+
"eval_accuracy": 0.6420021762785637,
|
2512 |
+
"eval_loss": 1.3497653007507324,
|
2513 |
+
"eval_runtime": 32.2339,
|
2514 |
+
"eval_samples_per_second": 57.021,
|
2515 |
+
"eval_steps_per_second": 7.135,
|
2516 |
+
"step": 3040
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 3.32,
|
2520 |
+
"learning_rate": 3.4058759521218717e-05,
|
2521 |
+
"loss": 0.1832,
|
2522 |
+
"step": 3050
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 3.33,
|
2526 |
+
"learning_rate": 3.3514689880304675e-05,
|
2527 |
+
"loss": 0.1061,
|
2528 |
+
"step": 3060
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 3.34,
|
2532 |
+
"learning_rate": 3.297062023939064e-05,
|
2533 |
+
"loss": 0.1092,
|
2534 |
+
"step": 3070
|
2535 |
+
},
|
2536 |
+
{
|
2537 |
+
"epoch": 3.35,
|
2538 |
+
"learning_rate": 3.2426550598476606e-05,
|
2539 |
+
"loss": 0.1148,
|
2540 |
+
"step": 3080
|
2541 |
+
},
|
2542 |
+
{
|
2543 |
+
"epoch": 3.35,
|
2544 |
+
"eval_accuracy": 0.6566920565832427,
|
2545 |
+
"eval_loss": 1.3009717464447021,
|
2546 |
+
"eval_runtime": 31.9059,
|
2547 |
+
"eval_samples_per_second": 57.607,
|
2548 |
+
"eval_steps_per_second": 7.209,
|
2549 |
+
"step": 3080
|
2550 |
+
},
|
2551 |
+
{
|
2552 |
+
"epoch": 3.36,
|
2553 |
+
"learning_rate": 3.188248095756257e-05,
|
2554 |
+
"loss": 0.1352,
|
2555 |
+
"step": 3090
|
2556 |
+
},
|
2557 |
+
{
|
2558 |
+
"epoch": 3.37,
|
2559 |
+
"learning_rate": 3.133841131664853e-05,
|
2560 |
+
"loss": 0.1482,
|
2561 |
+
"step": 3100
|
2562 |
+
},
|
2563 |
+
{
|
2564 |
+
"epoch": 3.38,
|
2565 |
+
"learning_rate": 3.0794341675734496e-05,
|
2566 |
+
"loss": 0.183,
|
2567 |
+
"step": 3110
|
2568 |
+
},
|
2569 |
+
{
|
2570 |
+
"epoch": 3.39,
|
2571 |
+
"learning_rate": 3.0250272034820458e-05,
|
2572 |
+
"loss": 0.1223,
|
2573 |
+
"step": 3120
|
2574 |
+
},
|
2575 |
+
{
|
2576 |
+
"epoch": 3.39,
|
2577 |
+
"eval_accuracy": 0.6436343852013058,
|
2578 |
+
"eval_loss": 1.3242275714874268,
|
2579 |
+
"eval_runtime": 32.4153,
|
2580 |
+
"eval_samples_per_second": 56.702,
|
2581 |
+
"eval_steps_per_second": 7.095,
|
2582 |
+
"step": 3120
|
2583 |
+
},
|
2584 |
+
{
|
2585 |
+
"epoch": 3.41,
|
2586 |
+
"learning_rate": 2.9706202393906423e-05,
|
2587 |
+
"loss": 0.1757,
|
2588 |
+
"step": 3130
|
2589 |
+
},
|
2590 |
+
{
|
2591 |
+
"epoch": 3.42,
|
2592 |
+
"learning_rate": 2.9162132752992382e-05,
|
2593 |
+
"loss": 0.2056,
|
2594 |
+
"step": 3140
|
2595 |
+
},
|
2596 |
+
{
|
2597 |
+
"epoch": 3.43,
|
2598 |
+
"learning_rate": 2.8618063112078348e-05,
|
2599 |
+
"loss": 0.0992,
|
2600 |
+
"step": 3150
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 3.44,
|
2604 |
+
"learning_rate": 2.8073993471164313e-05,
|
2605 |
+
"loss": 0.0822,
|
2606 |
+
"step": 3160
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 3.44,
|
2610 |
+
"eval_accuracy": 0.6485310119695321,
|
2611 |
+
"eval_loss": 1.3289127349853516,
|
2612 |
+
"eval_runtime": 32.0196,
|
2613 |
+
"eval_samples_per_second": 57.402,
|
2614 |
+
"eval_steps_per_second": 7.183,
|
2615 |
+
"step": 3160
|
2616 |
+
},
|
2617 |
+
{
|
2618 |
+
"epoch": 3.45,
|
2619 |
+
"learning_rate": 2.7529923830250275e-05,
|
2620 |
+
"loss": 0.1514,
|
2621 |
+
"step": 3170
|
2622 |
+
},
|
2623 |
+
{
|
2624 |
+
"epoch": 3.46,
|
2625 |
+
"learning_rate": 2.6985854189336234e-05,
|
2626 |
+
"loss": 0.1512,
|
2627 |
+
"step": 3180
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 3.47,
|
2631 |
+
"learning_rate": 2.64417845484222e-05,
|
2632 |
+
"loss": 0.2447,
|
2633 |
+
"step": 3190
|
2634 |
+
},
|
2635 |
+
{
|
2636 |
+
"epoch": 3.48,
|
2637 |
+
"learning_rate": 2.5897714907508165e-05,
|
2638 |
+
"loss": 0.2122,
|
2639 |
+
"step": 3200
|
2640 |
+
},
|
2641 |
+
{
|
2642 |
+
"epoch": 3.48,
|
2643 |
+
"eval_accuracy": 0.6452665941240479,
|
2644 |
+
"eval_loss": 1.3312246799468994,
|
2645 |
+
"eval_runtime": 31.8811,
|
2646 |
+
"eval_samples_per_second": 57.652,
|
2647 |
+
"eval_steps_per_second": 7.214,
|
2648 |
+
"step": 3200
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 3.49,
|
2652 |
+
"learning_rate": 2.5353645266594124e-05,
|
2653 |
+
"loss": 0.245,
|
2654 |
+
"step": 3210
|
2655 |
+
},
|
2656 |
+
{
|
2657 |
+
"epoch": 3.5,
|
2658 |
+
"learning_rate": 2.4809575625680086e-05,
|
2659 |
+
"loss": 0.169,
|
2660 |
+
"step": 3220
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 3.51,
|
2664 |
+
"learning_rate": 2.426550598476605e-05,
|
2665 |
+
"loss": 0.1088,
|
2666 |
+
"step": 3230
|
2667 |
+
},
|
2668 |
+
{
|
2669 |
+
"epoch": 3.53,
|
2670 |
+
"learning_rate": 2.3721436343852013e-05,
|
2671 |
+
"loss": 0.1107,
|
2672 |
+
"step": 3240
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 3.53,
|
2676 |
+
"eval_accuracy": 0.6539717083786725,
|
2677 |
+
"eval_loss": 1.3308542966842651,
|
2678 |
+
"eval_runtime": 31.9205,
|
2679 |
+
"eval_samples_per_second": 57.581,
|
2680 |
+
"eval_steps_per_second": 7.205,
|
2681 |
+
"step": 3240
|
2682 |
+
},
|
2683 |
+
{
|
2684 |
+
"epoch": 3.54,
|
2685 |
+
"learning_rate": 2.317736670293798e-05,
|
2686 |
+
"loss": 0.1956,
|
2687 |
+
"step": 3250
|
2688 |
+
},
|
2689 |
+
{
|
2690 |
+
"epoch": 3.55,
|
2691 |
+
"learning_rate": 2.263329706202394e-05,
|
2692 |
+
"loss": 0.2284,
|
2693 |
+
"step": 3260
|
2694 |
+
},
|
2695 |
+
{
|
2696 |
+
"epoch": 3.56,
|
2697 |
+
"learning_rate": 2.2089227421109903e-05,
|
2698 |
+
"loss": 0.2057,
|
2699 |
+
"step": 3270
|
2700 |
+
},
|
2701 |
+
{
|
2702 |
+
"epoch": 3.57,
|
2703 |
+
"learning_rate": 2.1545157780195865e-05,
|
2704 |
+
"loss": 0.1542,
|
2705 |
+
"step": 3280
|
2706 |
+
},
|
2707 |
+
{
|
2708 |
+
"epoch": 3.57,
|
2709 |
+
"eval_accuracy": 0.6517954298150164,
|
2710 |
+
"eval_loss": 1.3291780948638916,
|
2711 |
+
"eval_runtime": 31.9281,
|
2712 |
+
"eval_samples_per_second": 57.567,
|
2713 |
+
"eval_steps_per_second": 7.204,
|
2714 |
+
"step": 3280
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 3.58,
|
2718 |
+
"learning_rate": 2.100108813928183e-05,
|
2719 |
+
"loss": 0.2547,
|
2720 |
+
"step": 3290
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 3.59,
|
2724 |
+
"learning_rate": 2.0457018498367793e-05,
|
2725 |
+
"loss": 0.1693,
|
2726 |
+
"step": 3300
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 3.6,
|
2730 |
+
"learning_rate": 1.9912948857453755e-05,
|
2731 |
+
"loss": 0.1856,
|
2732 |
+
"step": 3310
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 3.61,
|
2736 |
+
"learning_rate": 1.9368879216539717e-05,
|
2737 |
+
"loss": 0.1932,
|
2738 |
+
"step": 3320
|
2739 |
+
},
|
2740 |
+
{
|
2741 |
+
"epoch": 3.61,
|
2742 |
+
"eval_accuracy": 0.6485310119695321,
|
2743 |
+
"eval_loss": 1.3065351247787476,
|
2744 |
+
"eval_runtime": 32.2802,
|
2745 |
+
"eval_samples_per_second": 56.939,
|
2746 |
+
"eval_steps_per_second": 7.125,
|
2747 |
+
"step": 3320
|
2748 |
+
},
|
2749 |
+
{
|
2750 |
+
"epoch": 3.62,
|
2751 |
+
"learning_rate": 1.8824809575625682e-05,
|
2752 |
+
"loss": 0.1828,
|
2753 |
+
"step": 3330
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 3.63,
|
2757 |
+
"learning_rate": 1.8280739934711644e-05,
|
2758 |
+
"loss": 0.1613,
|
2759 |
+
"step": 3340
|
2760 |
+
},
|
2761 |
+
{
|
2762 |
+
"epoch": 3.65,
|
2763 |
+
"learning_rate": 1.7736670293797607e-05,
|
2764 |
+
"loss": 0.1393,
|
2765 |
+
"step": 3350
|
2766 |
+
},
|
2767 |
+
{
|
2768 |
+
"epoch": 3.66,
|
2769 |
+
"learning_rate": 1.719260065288357e-05,
|
2770 |
+
"loss": 0.2909,
|
2771 |
+
"step": 3360
|
2772 |
+
},
|
2773 |
+
{
|
2774 |
+
"epoch": 3.66,
|
2775 |
+
"eval_accuracy": 0.6545157780195865,
|
2776 |
+
"eval_loss": 1.309682846069336,
|
2777 |
+
"eval_runtime": 31.9846,
|
2778 |
+
"eval_samples_per_second": 57.465,
|
2779 |
+
"eval_steps_per_second": 7.191,
|
2780 |
+
"step": 3360
|
2781 |
+
},
|
2782 |
+
{
|
2783 |
+
"epoch": 3.67,
|
2784 |
+
"learning_rate": 1.6648531011969534e-05,
|
2785 |
+
"loss": 0.1763,
|
2786 |
+
"step": 3370
|
2787 |
+
},
|
2788 |
+
{
|
2789 |
+
"epoch": 3.68,
|
2790 |
+
"learning_rate": 1.6104461371055496e-05,
|
2791 |
+
"loss": 0.1939,
|
2792 |
+
"step": 3380
|
2793 |
+
},
|
2794 |
+
{
|
2795 |
+
"epoch": 3.69,
|
2796 |
+
"learning_rate": 1.5560391730141458e-05,
|
2797 |
+
"loss": 0.2101,
|
2798 |
+
"step": 3390
|
2799 |
+
},
|
2800 |
+
{
|
2801 |
+
"epoch": 3.7,
|
2802 |
+
"learning_rate": 1.5016322089227422e-05,
|
2803 |
+
"loss": 0.1504,
|
2804 |
+
"step": 3400
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 3.7,
|
2808 |
+
"eval_accuracy": 0.6545157780195865,
|
2809 |
+
"eval_loss": 1.3114700317382812,
|
2810 |
+
"eval_runtime": 32.1163,
|
2811 |
+
"eval_samples_per_second": 57.23,
|
2812 |
+
"eval_steps_per_second": 7.161,
|
2813 |
+
"step": 3400
|
2814 |
+
},
|
2815 |
+
{
|
2816 |
+
"epoch": 3.71,
|
2817 |
+
"learning_rate": 1.4472252448313384e-05,
|
2818 |
+
"loss": 0.1275,
|
2819 |
+
"step": 3410
|
2820 |
+
},
|
2821 |
+
{
|
2822 |
+
"epoch": 3.72,
|
2823 |
+
"learning_rate": 1.3928182807399348e-05,
|
2824 |
+
"loss": 0.1111,
|
2825 |
+
"step": 3420
|
2826 |
+
},
|
2827 |
+
{
|
2828 |
+
"epoch": 3.73,
|
2829 |
+
"learning_rate": 1.338411316648531e-05,
|
2830 |
+
"loss": 0.1553,
|
2831 |
+
"step": 3430
|
2832 |
+
},
|
2833 |
+
{
|
2834 |
+
"epoch": 3.74,
|
2835 |
+
"learning_rate": 1.2840043525571274e-05,
|
2836 |
+
"loss": 0.1823,
|
2837 |
+
"step": 3440
|
2838 |
+
},
|
2839 |
+
{
|
2840 |
+
"epoch": 3.74,
|
2841 |
+
"eval_accuracy": 0.6545157780195865,
|
2842 |
+
"eval_loss": 1.320819616317749,
|
2843 |
+
"eval_runtime": 31.7036,
|
2844 |
+
"eval_samples_per_second": 57.975,
|
2845 |
+
"eval_steps_per_second": 7.255,
|
2846 |
+
"step": 3440
|
2847 |
+
},
|
2848 |
+
{
|
2849 |
+
"epoch": 3.75,
|
2850 |
+
"learning_rate": 1.2295973884657238e-05,
|
2851 |
+
"loss": 0.1772,
|
2852 |
+
"step": 3450
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 3.76,
|
2856 |
+
"learning_rate": 1.17519042437432e-05,
|
2857 |
+
"loss": 0.2327,
|
2858 |
+
"step": 3460
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 3.78,
|
2862 |
+
"learning_rate": 1.1207834602829162e-05,
|
2863 |
+
"loss": 0.2037,
|
2864 |
+
"step": 3470
|
2865 |
+
},
|
2866 |
+
{
|
2867 |
+
"epoch": 3.79,
|
2868 |
+
"learning_rate": 1.0663764961915126e-05,
|
2869 |
+
"loss": 0.2477,
|
2870 |
+
"step": 3480
|
2871 |
+
},
|
2872 |
+
{
|
2873 |
+
"epoch": 3.79,
|
2874 |
+
"eval_accuracy": 0.6523394994559304,
|
2875 |
+
"eval_loss": 1.3207744359970093,
|
2876 |
+
"eval_runtime": 31.8189,
|
2877 |
+
"eval_samples_per_second": 57.765,
|
2878 |
+
"eval_steps_per_second": 7.228,
|
2879 |
+
"step": 3480
|
2880 |
+
},
|
2881 |
+
{
|
2882 |
+
"epoch": 3.8,
|
2883 |
+
"learning_rate": 1.0119695321001088e-05,
|
2884 |
+
"loss": 0.1393,
|
2885 |
+
"step": 3490
|
2886 |
+
},
|
2887 |
+
{
|
2888 |
+
"epoch": 3.81,
|
2889 |
+
"learning_rate": 9.575625680087052e-06,
|
2890 |
+
"loss": 0.2626,
|
2891 |
+
"step": 3500
|
2892 |
+
},
|
2893 |
+
{
|
2894 |
+
"epoch": 3.82,
|
2895 |
+
"learning_rate": 9.031556039173014e-06,
|
2896 |
+
"loss": 0.1723,
|
2897 |
+
"step": 3510
|
2898 |
+
},
|
2899 |
+
{
|
2900 |
+
"epoch": 3.83,
|
2901 |
+
"learning_rate": 8.487486398258977e-06,
|
2902 |
+
"loss": 0.1264,
|
2903 |
+
"step": 3520
|
2904 |
+
},
|
2905 |
+
{
|
2906 |
+
"epoch": 3.83,
|
2907 |
+
"eval_accuracy": 0.6539717083786725,
|
2908 |
+
"eval_loss": 1.324898362159729,
|
2909 |
+
"eval_runtime": 31.8821,
|
2910 |
+
"eval_samples_per_second": 57.65,
|
2911 |
+
"eval_steps_per_second": 7.214,
|
2912 |
+
"step": 3520
|
2913 |
+
},
|
2914 |
+
{
|
2915 |
+
"epoch": 3.84,
|
2916 |
+
"learning_rate": 7.94341675734494e-06,
|
2917 |
+
"loss": 0.1544,
|
2918 |
+
"step": 3530
|
2919 |
+
},
|
2920 |
+
{
|
2921 |
+
"epoch": 3.85,
|
2922 |
+
"learning_rate": 7.399347116430903e-06,
|
2923 |
+
"loss": 0.1696,
|
2924 |
+
"step": 3540
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 3.86,
|
2928 |
+
"learning_rate": 6.855277475516866e-06,
|
2929 |
+
"loss": 0.2394,
|
2930 |
+
"step": 3550
|
2931 |
+
},
|
2932 |
+
{
|
2933 |
+
"epoch": 3.87,
|
2934 |
+
"learning_rate": 6.311207834602829e-06,
|
2935 |
+
"loss": 0.1003,
|
2936 |
+
"step": 3560
|
2937 |
+
},
|
2938 |
+
{
|
2939 |
+
"epoch": 3.87,
|
2940 |
+
"eval_accuracy": 0.6599564744287268,
|
2941 |
+
"eval_loss": 1.3238483667373657,
|
2942 |
+
"eval_runtime": 32.249,
|
2943 |
+
"eval_samples_per_second": 56.994,
|
2944 |
+
"eval_steps_per_second": 7.132,
|
2945 |
+
"step": 3560
|
2946 |
+
},
|
2947 |
+
{
|
2948 |
+
"epoch": 3.88,
|
2949 |
+
"learning_rate": 5.767138193688792e-06,
|
2950 |
+
"loss": 0.2542,
|
2951 |
+
"step": 3570
|
2952 |
+
},
|
2953 |
+
{
|
2954 |
+
"epoch": 3.9,
|
2955 |
+
"learning_rate": 5.223068552774756e-06,
|
2956 |
+
"loss": 0.142,
|
2957 |
+
"step": 3580
|
2958 |
+
},
|
2959 |
+
{
|
2960 |
+
"epoch": 3.91,
|
2961 |
+
"learning_rate": 4.678998911860719e-06,
|
2962 |
+
"loss": 0.1282,
|
2963 |
+
"step": 3590
|
2964 |
+
},
|
2965 |
+
{
|
2966 |
+
"epoch": 3.92,
|
2967 |
+
"learning_rate": 4.134929270946682e-06,
|
2968 |
+
"loss": 0.1335,
|
2969 |
+
"step": 3600
|
2970 |
+
},
|
2971 |
+
{
|
2972 |
+
"epoch": 3.92,
|
2973 |
+
"eval_accuracy": 0.6610446137105549,
|
2974 |
+
"eval_loss": 1.3172351121902466,
|
2975 |
+
"eval_runtime": 31.9012,
|
2976 |
+
"eval_samples_per_second": 57.615,
|
2977 |
+
"eval_steps_per_second": 7.21,
|
2978 |
+
"step": 3600
|
2979 |
+
},
|
2980 |
+
{
|
2981 |
+
"epoch": 3.93,
|
2982 |
+
"learning_rate": 3.5908596300326447e-06,
|
2983 |
+
"loss": 0.1675,
|
2984 |
+
"step": 3610
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 3.94,
|
2988 |
+
"learning_rate": 3.0467899891186073e-06,
|
2989 |
+
"loss": 0.0947,
|
2990 |
+
"step": 3620
|
2991 |
+
},
|
2992 |
+
{
|
2993 |
+
"epoch": 3.95,
|
2994 |
+
"learning_rate": 2.5027203482045706e-06,
|
2995 |
+
"loss": 0.1827,
|
2996 |
+
"step": 3630
|
2997 |
+
},
|
2998 |
+
{
|
2999 |
+
"epoch": 3.96,
|
3000 |
+
"learning_rate": 1.958650707290533e-06,
|
3001 |
+
"loss": 0.2452,
|
3002 |
+
"step": 3640
|
3003 |
+
},
|
3004 |
+
{
|
3005 |
+
"epoch": 3.96,
|
3006 |
+
"eval_accuracy": 0.6556039173014145,
|
3007 |
+
"eval_loss": 1.3156225681304932,
|
3008 |
+
"eval_runtime": 32.1002,
|
3009 |
+
"eval_samples_per_second": 57.258,
|
3010 |
+
"eval_steps_per_second": 7.165,
|
3011 |
+
"step": 3640
|
3012 |
+
}
|
3013 |
+
],
|
3014 |
+
"max_steps": 3676,
|
3015 |
+
"num_train_epochs": 4,
|
3016 |
+
"total_flos": 4.5132044744502374e+18,
|
3017 |
+
"trial_name": null,
|
3018 |
+
"trial_params": null
|
3019 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0e1f18fa294fb837c2c4a4eeba0748adcfc666aefe4828c506f5c5b8f89e2a6
|
3 |
+
size 3899
|