Hugging Face's logo

Diginsa
/
Plant-Disease-Detection-Project

Image Classification
Transformers
Safetensors
mobilenet_v2
vision
Model card Files
xet
Community
Diginsa commited on
Commit
2a3a7ff
·
verified ·
1 Parent(s): 7f60e41

Upload 9 files

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. README.md +71 -0
  3. all_results.json +8 -0
  4. config.json +105 -0
  5. gitattributes +35 -0
  6. model.safetensors +3 -0
  7. preprocessor_config.json +27 -0
  8. train_results.json +8 -0
  9. trainer_state.json +1396 -0
  10. training_args.bin +0 -0
.gitattributes ADDED
@@ -0,0 +1 @@
 
 
1
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: google/mobilenet_v2_1.0_224
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: mobilenet_v2_1.0_224-plant-disease-new
10
+ results: []
11
+ datasets:
12
+ - A2H0H0R1/plant-disease-new
13
+ pipeline_tag: image-classification
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # mobilenet_v2_1.0_224-plant-disease-new
20
+
21
+ This model is a fine-tuned version of [google/mobilenet_v2_1.0_224](https://huggingface.co/google/mobilenet_v2_1.0_224) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.1287
24
+ - Accuracy: 0.9600
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 100
45
+ - eval_batch_size: 100
46
+ - seed: 42
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 400
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 6
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
58
+ | 0.5043 | 1.0 | 366 | 0.4476 | 0.8886 |
59
+ | 0.2492 | 2.0 | 733 | 0.2550 | 0.9281 |
60
+ | 0.2069 | 3.0 | 1100 | 0.2332 | 0.9247 |
61
+ | 0.1716 | 4.0 | 1467 | 0.3329 | 0.8960 |
62
+ | 0.1602 | 5.0 | 1833 | 0.1999 | 0.9388 |
63
+ | 0.1633 | 5.99 | 2196 | 0.1287 | 0.9600 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.35.2
69
+ - Pytorch 2.1.0+cu121
70
+ - Datasets 2.16.0
71
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.99,
3
+ "total_flos": 2.353803972968448e+18,
4
+ "train_loss": 0.48255133992552973,
5
+ "train_runtime": 7781.6451,
6
+ "train_samples_per_second": 113.054,
7
+ "train_steps_per_second": 0.282
8
+ }
config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mobilenet_v2_1.0_224",
3
+ "architectures": [
4
+ "MobileNetV2ForImageClassification"
5
+ ],
6
+ "classifier_dropout_prob": 0.2,
7
+ "depth_divisible_by": 8,
8
+ "depth_multiplier": 1.0,
9
+ "expand_ratio": 6,
10
+ "finegrained_output": true,
11
+ "first_layer_is_expansion": true,
12
+ "hidden_act": "relu6",
13
+ "id2label": {
14
+ "0": "Apple Apple scab",
15
+ "1": "Apple Black rot",
16
+ "2": "Apple Cedar apple rust",
17
+ "3": "Apple healthy",
18
+ "4": "Blueberry healthy",
19
+ "5": "Cherry (including sour) Powdery mildew",
20
+ "6": "Cherry (including sour) healthy",
21
+ "7": "Corn (maize) Cercospora leaf spot Gray leaf spot",
22
+ "8": "Corn (maize) Common rust ",
23
+ "9": "Corn (maize) Northern Leaf Blight",
24
+ "10": "Corn (maize) healthy",
25
+ "11": "Grape Black rot",
26
+ "12": "Grape Esca (Black Measles)",
27
+ "13": "Grape Leaf blight (Isariopsis Leaf Spot)",
28
+ "14": "Grape healthy",
29
+ "15": "Orange Haunglongbing (Citrus greening)",
30
+ "16": "Peach Bacterial spot",
31
+ "17": "Peach healthy",
32
+ "18": "Pepper, bell Bacterial spot",
33
+ "19": "Pepper, bell healthy",
34
+ "20": "Potato Early blight",
35
+ "21": "Potato Late blight",
36
+ "22": "Potato healthy",
37
+ "23": "Raspberry healthy",
38
+ "24": "Soybean healthy",
39
+ "25": "Squash Powdery mildew",
40
+ "26": "Strawberry Leaf scorch",
41
+ "27": "Strawberry healthy",
42
+ "28": "Tomato Bacterial spot",
43
+ "29": "Tomato Early blight",
44
+ "30": "Tomato Late blight",
45
+ "31": "Tomato Leaf Mold",
46
+ "32": "Tomato Septoria leaf spot",
47
+ "33": "Tomato Spider mites Two-spotted spider mite",
48
+ "34": "Tomato Target Spot",
49
+ "35": "Tomato Tomato Yellow Leaf Curl Virus",
50
+ "36": "Tomato Tomato mosaic virus",
51
+ "37": "Tomato healthy"
52
+ },
53
+ "image_size": 224,
54
+ "initializer_range": 0.02,
55
+ "label2id": {
56
+ "Apple Apple scab": 0,
57
+ "Apple Black rot": 1,
58
+ "Apple Cedar apple rust": 2,
59
+ "Apple healthy": 3,
60
+ "Blueberry healthy": 4,
61
+ "Cherry (including sour) Powdery mildew": 5,
62
+ "Cherry (including sour) healthy": 6,
63
+ "Corn (maize) Cercospora leaf spot Gray leaf spot": 7,
64
+ "Corn (maize) Common rust ": 8,
65
+ "Corn (maize) Northern Leaf Blight": 9,
66
+ "Corn (maize) healthy": 10,
67
+ "Grape Black rot": 11,
68
+ "Grape Esca (Black Measles)": 12,
69
+ "Grape Leaf blight (Isariopsis Leaf Spot)": 13,
70
+ "Grape healthy": 14,
71
+ "Orange Haunglongbing (Citrus greening)": 15,
72
+ "Peach Bacterial spot": 16,
73
+ "Peach healthy": 17,
74
+ "Pepper, bell Bacterial spot": 18,
75
+ "Pepper, bell healthy": 19,
76
+ "Potato Early blight": 20,
77
+ "Potato Late blight": 21,
78
+ "Potato healthy": 22,
79
+ "Raspberry healthy": 23,
80
+ "Soybean healthy": 24,
81
+ "Squash Powdery mildew": 25,
82
+ "Strawberry Leaf scorch": 26,
83
+ "Strawberry healthy": 27,
84
+ "Tomato Bacterial spot": 28,
85
+ "Tomato Early blight": 29,
86
+ "Tomato Late blight": 30,
87
+ "Tomato Leaf Mold": 31,
88
+ "Tomato Septoria leaf spot": 32,
89
+ "Tomato Spider mites Two-spotted spider mite": 33,
90
+ "Tomato Target Spot": 34,
91
+ "Tomato Tomato Yellow Leaf Curl Virus": 35,
92
+ "Tomato Tomato mosaic virus": 36,
93
+ "Tomato healthy": 37
94
+ },
95
+ "layer_norm_eps": 0.001,
96
+ "min_depth": 8,
97
+ "model_type": "mobilenet_v2",
98
+ "num_channels": 3,
99
+ "output_stride": 32,
100
+ "problem_type": "single_label_classification",
101
+ "semantic_loss_ignore_index": 255,
102
+ "tf_padding": true,
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.35.2"
105
+ }
gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:692844e7bfff8a1c30133d296ee6c947e821699651153b939c66799a818cccdb
3
+ size 9264680
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_normalize": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_mean": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "image_processor_type": "MobileNetV2ImageProcessor",
16
+ "image_std": [
17
+ 0.5,
18
+ 0.5,
19
+ 0.5
20
+ ],
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "shortest_edge": 256
25
+ },
26
+ "use_square_size": false
27
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.99,
3
+ "total_flos": 2.353803972968448e+18,
4
+ "train_loss": 0.48255133992552973,
5
+ "train_runtime": 7781.6451,
6
+ "train_samples_per_second": 113.054,
7
+ "train_steps_per_second": 0.282
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1396 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9600417382764547,
3
+ "best_model_checkpoint": "mobilenet_v2_1.0_224-plant-disease-new/checkpoint-2196",
4
+ "epoch": 5.987730061349693,
5
+ "eval_steps": 500,
6
+ "global_step": 2196,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 2.2727272727272728e-06,
14
+ "loss": 3.7088,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 4.5454545454545455e-06,
20
+ "loss": 3.6964,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 6.818181818181818e-06,
26
+ "loss": 3.6603,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 9.090909090909091e-06,
32
+ "loss": 3.5945,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.14,
37
+ "learning_rate": 1.1363636363636365e-05,
38
+ "loss": 3.5419,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.16,
43
+ "learning_rate": 1.3636363636363637e-05,
44
+ "loss": 3.459,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.19,
49
+ "learning_rate": 1.590909090909091e-05,
50
+ "loss": 3.338,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.22,
55
+ "learning_rate": 1.8181818181818182e-05,
56
+ "loss": 3.227,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.25,
61
+ "learning_rate": 2.0454545454545457e-05,
62
+ "loss": 3.0764,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.27,
67
+ "learning_rate": 2.272727272727273e-05,
68
+ "loss": 2.8963,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.3,
73
+ "learning_rate": 2.5e-05,
74
+ "loss": 2.7233,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.33,
79
+ "learning_rate": 2.7272727272727273e-05,
80
+ "loss": 2.5753,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.35,
85
+ "learning_rate": 2.954545454545455e-05,
86
+ "loss": 2.4026,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.38,
91
+ "learning_rate": 3.181818181818182e-05,
92
+ "loss": 2.2854,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.41,
97
+ "learning_rate": 3.409090909090909e-05,
98
+ "loss": 2.0919,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.44,
103
+ "learning_rate": 3.6363636363636364e-05,
104
+ "loss": 1.9062,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.46,
109
+ "learning_rate": 3.8636363636363636e-05,
110
+ "loss": 1.7435,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.49,
115
+ "learning_rate": 4.0909090909090915e-05,
116
+ "loss": 1.6093,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.52,
121
+ "learning_rate": 4.318181818181819e-05,
122
+ "loss": 1.4792,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.55,
127
+ "learning_rate": 4.545454545454546e-05,
128
+ "loss": 1.3224,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.57,
133
+ "learning_rate": 4.772727272727273e-05,
134
+ "loss": 1.2135,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.6,
139
+ "learning_rate": 5e-05,
140
+ "loss": 1.1135,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.63,
145
+ "learning_rate": 4.974696356275304e-05,
146
+ "loss": 1.0175,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.65,
151
+ "learning_rate": 4.9493927125506076e-05,
152
+ "loss": 0.9457,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.68,
157
+ "learning_rate": 4.924089068825911e-05,
158
+ "loss": 0.844,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.71,
163
+ "learning_rate": 4.898785425101215e-05,
164
+ "loss": 0.8029,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.74,
169
+ "learning_rate": 4.8734817813765186e-05,
170
+ "loss": 0.7469,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.76,
175
+ "learning_rate": 4.848178137651822e-05,
176
+ "loss": 0.7057,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.79,
181
+ "learning_rate": 4.822874493927126e-05,
182
+ "loss": 0.6716,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.82,
187
+ "learning_rate": 4.797570850202429e-05,
188
+ "loss": 0.6142,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.85,
193
+ "learning_rate": 4.772267206477733e-05,
194
+ "loss": 0.6081,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.87,
199
+ "learning_rate": 4.746963562753037e-05,
200
+ "loss": 0.5808,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.9,
205
+ "learning_rate": 4.72165991902834e-05,
206
+ "loss": 0.5485,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.93,
211
+ "learning_rate": 4.6963562753036435e-05,
212
+ "loss": 0.5354,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.95,
217
+ "learning_rate": 4.671052631578948e-05,
218
+ "loss": 0.4988,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.98,
223
+ "learning_rate": 4.6457489878542516e-05,
224
+ "loss": 0.5043,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 1.0,
229
+ "eval_accuracy": 0.888595629756936,
230
+ "eval_loss": 0.4475972056388855,
231
+ "eval_runtime": 63.5758,
232
+ "eval_samples_per_second": 256.261,
233
+ "eval_steps_per_second": 2.564,
234
+ "step": 366
235
+ },
236
+ {
237
+ "epoch": 1.01,
238
+ "learning_rate": 4.6204453441295545e-05,
239
+ "loss": 0.4605,
240
+ "step": 370
241
+ },
242
+ {
243
+ "epoch": 1.04,
244
+ "learning_rate": 4.595141700404859e-05,
245
+ "loss": 0.4587,
246
+ "step": 380
247
+ },
248
+ {
249
+ "epoch": 1.06,
250
+ "learning_rate": 4.5698380566801625e-05,
251
+ "loss": 0.4483,
252
+ "step": 390
253
+ },
254
+ {
255
+ "epoch": 1.09,
256
+ "learning_rate": 4.5445344129554655e-05,
257
+ "loss": 0.4105,
258
+ "step": 400
259
+ },
260
+ {
261
+ "epoch": 1.12,
262
+ "learning_rate": 4.519230769230769e-05,
263
+ "loss": 0.4274,
264
+ "step": 410
265
+ },
266
+ {
267
+ "epoch": 1.15,
268
+ "learning_rate": 4.4939271255060735e-05,
269
+ "loss": 0.3978,
270
+ "step": 420
271
+ },
272
+ {
273
+ "epoch": 1.17,
274
+ "learning_rate": 4.4686234817813765e-05,
275
+ "loss": 0.4096,
276
+ "step": 430
277
+ },
278
+ {
279
+ "epoch": 1.2,
280
+ "learning_rate": 4.44331983805668e-05,
281
+ "loss": 0.3932,
282
+ "step": 440
283
+ },
284
+ {
285
+ "epoch": 1.23,
286
+ "learning_rate": 4.4180161943319845e-05,
287
+ "loss": 0.4066,
288
+ "step": 450
289
+ },
290
+ {
291
+ "epoch": 1.25,
292
+ "learning_rate": 4.3927125506072875e-05,
293
+ "loss": 0.3709,
294
+ "step": 460
295
+ },
296
+ {
297
+ "epoch": 1.28,
298
+ "learning_rate": 4.367408906882591e-05,
299
+ "loss": 0.3607,
300
+ "step": 470
301
+ },
302
+ {
303
+ "epoch": 1.31,
304
+ "learning_rate": 4.342105263157895e-05,
305
+ "loss": 0.3634,
306
+ "step": 480
307
+ },
308
+ {
309
+ "epoch": 1.34,
310
+ "learning_rate": 4.3168016194331985e-05,
311
+ "loss": 0.3336,
312
+ "step": 490
313
+ },
314
+ {
315
+ "epoch": 1.36,
316
+ "learning_rate": 4.291497975708502e-05,
317
+ "loss": 0.3509,
318
+ "step": 500
319
+ },
320
+ {
321
+ "epoch": 1.39,
322
+ "learning_rate": 4.266194331983806e-05,
323
+ "loss": 0.327,
324
+ "step": 510
325
+ },
326
+ {
327
+ "epoch": 1.42,
328
+ "learning_rate": 4.2408906882591095e-05,
329
+ "loss": 0.3403,
330
+ "step": 520
331
+ },
332
+ {
333
+ "epoch": 1.45,
334
+ "learning_rate": 4.215587044534413e-05,
335
+ "loss": 0.3413,
336
+ "step": 530
337
+ },
338
+ {
339
+ "epoch": 1.47,
340
+ "learning_rate": 4.190283400809717e-05,
341
+ "loss": 0.337,
342
+ "step": 540
343
+ },
344
+ {
345
+ "epoch": 1.5,
346
+ "learning_rate": 4.1649797570850205e-05,
347
+ "loss": 0.317,
348
+ "step": 550
349
+ },
350
+ {
351
+ "epoch": 1.53,
352
+ "learning_rate": 4.139676113360324e-05,
353
+ "loss": 0.3115,
354
+ "step": 560
355
+ },
356
+ {
357
+ "epoch": 1.55,
358
+ "learning_rate": 4.114372469635628e-05,
359
+ "loss": 0.322,
360
+ "step": 570
361
+ },
362
+ {
363
+ "epoch": 1.58,
364
+ "learning_rate": 4.089068825910931e-05,
365
+ "loss": 0.3055,
366
+ "step": 580
367
+ },
368
+ {
369
+ "epoch": 1.61,
370
+ "learning_rate": 4.063765182186235e-05,
371
+ "loss": 0.2959,
372
+ "step": 590
373
+ },
374
+ {
375
+ "epoch": 1.64,
376
+ "learning_rate": 4.038461538461539e-05,
377
+ "loss": 0.2941,
378
+ "step": 600
379
+ },
380
+ {
381
+ "epoch": 1.66,
382
+ "learning_rate": 4.0131578947368425e-05,
383
+ "loss": 0.3155,
384
+ "step": 610
385
+ },
386
+ {
387
+ "epoch": 1.69,
388
+ "learning_rate": 3.9878542510121455e-05,
389
+ "loss": 0.2983,
390
+ "step": 620
391
+ },
392
+ {
393
+ "epoch": 1.72,
394
+ "learning_rate": 3.96255060728745e-05,
395
+ "loss": 0.285,
396
+ "step": 630
397
+ },
398
+ {
399
+ "epoch": 1.75,
400
+ "learning_rate": 3.9372469635627535e-05,
401
+ "loss": 0.2916,
402
+ "step": 640
403
+ },
404
+ {
405
+ "epoch": 1.77,
406
+ "learning_rate": 3.9119433198380565e-05,
407
+ "loss": 0.299,
408
+ "step": 650
409
+ },
410
+ {
411
+ "epoch": 1.8,
412
+ "learning_rate": 3.886639676113361e-05,
413
+ "loss": 0.2827,
414
+ "step": 660
415
+ },
416
+ {
417
+ "epoch": 1.83,
418
+ "learning_rate": 3.8613360323886645e-05,
419
+ "loss": 0.2735,
420
+ "step": 670
421
+ },
422
+ {
423
+ "epoch": 1.85,
424
+ "learning_rate": 3.8360323886639675e-05,
425
+ "loss": 0.2478,
426
+ "step": 680
427
+ },
428
+ {
429
+ "epoch": 1.88,
430
+ "learning_rate": 3.810728744939271e-05,
431
+ "loss": 0.2734,
432
+ "step": 690
433
+ },
434
+ {
435
+ "epoch": 1.91,
436
+ "learning_rate": 3.7854251012145755e-05,
437
+ "loss": 0.2666,
438
+ "step": 700
439
+ },
440
+ {
441
+ "epoch": 1.94,
442
+ "learning_rate": 3.7601214574898785e-05,
443
+ "loss": 0.2781,
444
+ "step": 710
445
+ },
446
+ {
447
+ "epoch": 1.96,
448
+ "learning_rate": 3.734817813765182e-05,
449
+ "loss": 0.2684,
450
+ "step": 720
451
+ },
452
+ {
453
+ "epoch": 1.99,
454
+ "learning_rate": 3.7095141700404865e-05,
455
+ "loss": 0.2492,
456
+ "step": 730
457
+ },
458
+ {
459
+ "epoch": 2.0,
460
+ "eval_accuracy": 0.9281242327522711,
461
+ "eval_loss": 0.2550327181816101,
462
+ "eval_runtime": 64.339,
463
+ "eval_samples_per_second": 253.221,
464
+ "eval_steps_per_second": 2.533,
465
+ "step": 733
466
+ },
467
+ {
468
+ "epoch": 2.02,
469
+ "learning_rate": 3.6842105263157895e-05,
470
+ "loss": 0.2398,
471
+ "step": 740
472
+ },
473
+ {
474
+ "epoch": 2.04,
475
+ "learning_rate": 3.658906882591093e-05,
476
+ "loss": 0.2523,
477
+ "step": 750
478
+ },
479
+ {
480
+ "epoch": 2.07,
481
+ "learning_rate": 3.633603238866397e-05,
482
+ "loss": 0.2396,
483
+ "step": 760
484
+ },
485
+ {
486
+ "epoch": 2.1,
487
+ "learning_rate": 3.6082995951417005e-05,
488
+ "loss": 0.2571,
489
+ "step": 770
490
+ },
491
+ {
492
+ "epoch": 2.13,
493
+ "learning_rate": 3.582995951417004e-05,
494
+ "loss": 0.2447,
495
+ "step": 780
496
+ },
497
+ {
498
+ "epoch": 2.15,
499
+ "learning_rate": 3.557692307692308e-05,
500
+ "loss": 0.262,
501
+ "step": 790
502
+ },
503
+ {
504
+ "epoch": 2.18,
505
+ "learning_rate": 3.5323886639676115e-05,
506
+ "loss": 0.2518,
507
+ "step": 800
508
+ },
509
+ {
510
+ "epoch": 2.21,
511
+ "learning_rate": 3.507085020242915e-05,
512
+ "loss": 0.2319,
513
+ "step": 810
514
+ },
515
+ {
516
+ "epoch": 2.24,
517
+ "learning_rate": 3.481781376518219e-05,
518
+ "loss": 0.2302,
519
+ "step": 820
520
+ },
521
+ {
522
+ "epoch": 2.26,
523
+ "learning_rate": 3.4564777327935225e-05,
524
+ "loss": 0.2412,
525
+ "step": 830
526
+ },
527
+ {
528
+ "epoch": 2.29,
529
+ "learning_rate": 3.431174089068826e-05,
530
+ "loss": 0.2599,
531
+ "step": 840
532
+ },
533
+ {
534
+ "epoch": 2.32,
535
+ "learning_rate": 3.40587044534413e-05,
536
+ "loss": 0.2271,
537
+ "step": 850
538
+ },
539
+ {
540
+ "epoch": 2.34,
541
+ "learning_rate": 3.3805668016194335e-05,
542
+ "loss": 0.2261,
543
+ "step": 860
544
+ },
545
+ {
546
+ "epoch": 2.37,
547
+ "learning_rate": 3.355263157894737e-05,
548
+ "loss": 0.2261,
549
+ "step": 870
550
+ },
551
+ {
552
+ "epoch": 2.4,
553
+ "learning_rate": 3.329959514170041e-05,
554
+ "loss": 0.2187,
555
+ "step": 880
556
+ },
557
+ {
558
+ "epoch": 2.43,
559
+ "learning_rate": 3.3046558704453444e-05,
560
+ "loss": 0.2296,
561
+ "step": 890
562
+ },
563
+ {
564
+ "epoch": 2.45,
565
+ "learning_rate": 3.279352226720648e-05,
566
+ "loss": 0.2157,
567
+ "step": 900
568
+ },
569
+ {
570
+ "epoch": 2.48,
571
+ "learning_rate": 3.254048582995952e-05,
572
+ "loss": 0.2566,
573
+ "step": 910
574
+ },
575
+ {
576
+ "epoch": 2.51,
577
+ "learning_rate": 3.2287449392712554e-05,
578
+ "loss": 0.218,
579
+ "step": 920
580
+ },
581
+ {
582
+ "epoch": 2.54,
583
+ "learning_rate": 3.2034412955465584e-05,
584
+ "loss": 0.2154,
585
+ "step": 930
586
+ },
587
+ {
588
+ "epoch": 2.56,
589
+ "learning_rate": 3.178137651821863e-05,
590
+ "loss": 0.2152,
591
+ "step": 940
592
+ },
593
+ {
594
+ "epoch": 2.59,
595
+ "learning_rate": 3.1528340080971664e-05,
596
+ "loss": 0.2201,
597
+ "step": 950
598
+ },
599
+ {
600
+ "epoch": 2.62,
601
+ "learning_rate": 3.1275303643724694e-05,
602
+ "loss": 0.2193,
603
+ "step": 960
604
+ },
605
+ {
606
+ "epoch": 2.64,
607
+ "learning_rate": 3.102226720647773e-05,
608
+ "loss": 0.2138,
609
+ "step": 970
610
+ },
611
+ {
612
+ "epoch": 2.67,
613
+ "learning_rate": 3.0769230769230774e-05,
614
+ "loss": 0.2083,
615
+ "step": 980
616
+ },
617
+ {
618
+ "epoch": 2.7,
619
+ "learning_rate": 3.0516194331983804e-05,
620
+ "loss": 0.2208,
621
+ "step": 990
622
+ },
623
+ {
624
+ "epoch": 2.73,
625
+ "learning_rate": 3.0263157894736844e-05,
626
+ "loss": 0.2401,
627
+ "step": 1000
628
+ },
629
+ {
630
+ "epoch": 2.75,
631
+ "learning_rate": 3.001012145748988e-05,
632
+ "loss": 0.2091,
633
+ "step": 1010
634
+ },
635
+ {
636
+ "epoch": 2.78,
637
+ "learning_rate": 2.9757085020242914e-05,
638
+ "loss": 0.2076,
639
+ "step": 1020
640
+ },
641
+ {
642
+ "epoch": 2.81,
643
+ "learning_rate": 2.950404858299595e-05,
644
+ "loss": 0.2101,
645
+ "step": 1030
646
+ },
647
+ {
648
+ "epoch": 2.84,
649
+ "learning_rate": 2.925101214574899e-05,
650
+ "loss": 0.2051,
651
+ "step": 1040
652
+ },
653
+ {
654
+ "epoch": 2.86,
655
+ "learning_rate": 2.8997975708502024e-05,
656
+ "loss": 0.2024,
657
+ "step": 1050
658
+ },
659
+ {
660
+ "epoch": 2.89,
661
+ "learning_rate": 2.874493927125506e-05,
662
+ "loss": 0.1999,
663
+ "step": 1060
664
+ },
665
+ {
666
+ "epoch": 2.92,
667
+ "learning_rate": 2.84919028340081e-05,
668
+ "loss": 0.2072,
669
+ "step": 1070
670
+ },
671
+ {
672
+ "epoch": 2.94,
673
+ "learning_rate": 2.823886639676113e-05,
674
+ "loss": 0.2187,
675
+ "step": 1080
676
+ },
677
+ {
678
+ "epoch": 2.97,
679
+ "learning_rate": 2.798582995951417e-05,
680
+ "loss": 0.2232,
681
+ "step": 1090
682
+ },
683
+ {
684
+ "epoch": 3.0,
685
+ "learning_rate": 2.7732793522267207e-05,
686
+ "loss": 0.2069,
687
+ "step": 1100
688
+ },
689
+ {
690
+ "epoch": 3.0,
691
+ "eval_accuracy": 0.9246869629265897,
692
+ "eval_loss": 0.23323099315166473,
693
+ "eval_runtime": 64.6057,
694
+ "eval_samples_per_second": 252.176,
695
+ "eval_steps_per_second": 2.523,
696
+ "step": 1100
697
+ },
698
+ {
699
+ "epoch": 3.03,
700
+ "learning_rate": 2.7479757085020247e-05,
701
+ "loss": 0.2129,
702
+ "step": 1110
703
+ },
704
+ {
705
+ "epoch": 3.05,
706
+ "learning_rate": 2.722672064777328e-05,
707
+ "loss": 0.202,
708
+ "step": 1120
709
+ },
710
+ {
711
+ "epoch": 3.08,
712
+ "learning_rate": 2.6973684210526317e-05,
713
+ "loss": 0.2073,
714
+ "step": 1130
715
+ },
716
+ {
717
+ "epoch": 3.11,
718
+ "learning_rate": 2.6720647773279357e-05,
719
+ "loss": 0.1845,
720
+ "step": 1140
721
+ },
722
+ {
723
+ "epoch": 3.14,
724
+ "learning_rate": 2.6467611336032387e-05,
725
+ "loss": 0.1933,
726
+ "step": 1150
727
+ },
728
+ {
729
+ "epoch": 3.16,
730
+ "learning_rate": 2.6214574898785427e-05,
731
+ "loss": 0.1946,
732
+ "step": 1160
733
+ },
734
+ {
735
+ "epoch": 3.19,
736
+ "learning_rate": 2.5961538461538464e-05,
737
+ "loss": 0.1838,
738
+ "step": 1170
739
+ },
740
+ {
741
+ "epoch": 3.22,
742
+ "learning_rate": 2.5708502024291497e-05,
743
+ "loss": 0.2047,
744
+ "step": 1180
745
+ },
746
+ {
747
+ "epoch": 3.24,
748
+ "learning_rate": 2.5455465587044537e-05,
749
+ "loss": 0.1936,
750
+ "step": 1190
751
+ },
752
+ {
753
+ "epoch": 3.27,
754
+ "learning_rate": 2.5202429149797574e-05,
755
+ "loss": 0.1886,
756
+ "step": 1200
757
+ },
758
+ {
759
+ "epoch": 3.3,
760
+ "learning_rate": 2.494939271255061e-05,
761
+ "loss": 0.1928,
762
+ "step": 1210
763
+ },
764
+ {
765
+ "epoch": 3.33,
766
+ "learning_rate": 2.4696356275303644e-05,
767
+ "loss": 0.1939,
768
+ "step": 1220
769
+ },
770
+ {
771
+ "epoch": 3.35,
772
+ "learning_rate": 2.444331983805668e-05,
773
+ "loss": 0.1853,
774
+ "step": 1230
775
+ },
776
+ {
777
+ "epoch": 3.38,
778
+ "learning_rate": 2.4190283400809717e-05,
779
+ "loss": 0.1884,
780
+ "step": 1240
781
+ },
782
+ {
783
+ "epoch": 3.41,
784
+ "learning_rate": 2.3937246963562754e-05,
785
+ "loss": 0.1934,
786
+ "step": 1250
787
+ },
788
+ {
789
+ "epoch": 3.44,
790
+ "learning_rate": 2.368421052631579e-05,
791
+ "loss": 0.1867,
792
+ "step": 1260
793
+ },
794
+ {
795
+ "epoch": 3.46,
796
+ "learning_rate": 2.3431174089068827e-05,
797
+ "loss": 0.1795,
798
+ "step": 1270
799
+ },
800
+ {
801
+ "epoch": 3.49,
802
+ "learning_rate": 2.3178137651821864e-05,
803
+ "loss": 0.1899,
804
+ "step": 1280
805
+ },
806
+ {
807
+ "epoch": 3.52,
808
+ "learning_rate": 2.29251012145749e-05,
809
+ "loss": 0.1864,
810
+ "step": 1290
811
+ },
812
+ {
813
+ "epoch": 3.54,
814
+ "learning_rate": 2.2672064777327937e-05,
815
+ "loss": 0.1959,
816
+ "step": 1300
817
+ },
818
+ {
819
+ "epoch": 3.57,
820
+ "learning_rate": 2.241902834008097e-05,
821
+ "loss": 0.1828,
822
+ "step": 1310
823
+ },
824
+ {
825
+ "epoch": 3.6,
826
+ "learning_rate": 2.216599190283401e-05,
827
+ "loss": 0.1813,
828
+ "step": 1320
829
+ },
830
+ {
831
+ "epoch": 3.63,
832
+ "learning_rate": 2.1912955465587047e-05,
833
+ "loss": 0.1912,
834
+ "step": 1330
835
+ },
836
+ {
837
+ "epoch": 3.65,
838
+ "learning_rate": 2.165991902834008e-05,
839
+ "loss": 0.1725,
840
+ "step": 1340
841
+ },
842
+ {
843
+ "epoch": 3.68,
844
+ "learning_rate": 2.140688259109312e-05,
845
+ "loss": 0.1837,
846
+ "step": 1350
847
+ },
848
+ {
849
+ "epoch": 3.71,
850
+ "learning_rate": 2.1153846153846154e-05,
851
+ "loss": 0.181,
852
+ "step": 1360
853
+ },
854
+ {
855
+ "epoch": 3.74,
856
+ "learning_rate": 2.090080971659919e-05,
857
+ "loss": 0.1798,
858
+ "step": 1370
859
+ },
860
+ {
861
+ "epoch": 3.76,
862
+ "learning_rate": 2.0647773279352227e-05,
863
+ "loss": 0.1862,
864
+ "step": 1380
865
+ },
866
+ {
867
+ "epoch": 3.79,
868
+ "learning_rate": 2.0394736842105264e-05,
869
+ "loss": 0.1864,
870
+ "step": 1390
871
+ },
872
+ {
873
+ "epoch": 3.82,
874
+ "learning_rate": 2.0141700404858304e-05,
875
+ "loss": 0.176,
876
+ "step": 1400
877
+ },
878
+ {
879
+ "epoch": 3.84,
880
+ "learning_rate": 1.9888663967611337e-05,
881
+ "loss": 0.1825,
882
+ "step": 1410
883
+ },
884
+ {
885
+ "epoch": 3.87,
886
+ "learning_rate": 1.9635627530364373e-05,
887
+ "loss": 0.1845,
888
+ "step": 1420
889
+ },
890
+ {
891
+ "epoch": 3.9,
892
+ "learning_rate": 1.938259109311741e-05,
893
+ "loss": 0.1851,
894
+ "step": 1430
895
+ },
896
+ {
897
+ "epoch": 3.93,
898
+ "learning_rate": 1.9129554655870447e-05,
899
+ "loss": 0.1771,
900
+ "step": 1440
901
+ },
902
+ {
903
+ "epoch": 3.95,
904
+ "learning_rate": 1.8876518218623483e-05,
905
+ "loss": 0.1836,
906
+ "step": 1450
907
+ },
908
+ {
909
+ "epoch": 3.98,
910
+ "learning_rate": 1.862348178137652e-05,
911
+ "loss": 0.1716,
912
+ "step": 1460
913
+ },
914
+ {
915
+ "epoch": 4.0,
916
+ "eval_accuracy": 0.8959612079548245,
917
+ "eval_loss": 0.332915723323822,
918
+ "eval_runtime": 65.1685,
919
+ "eval_samples_per_second": 249.998,
920
+ "eval_steps_per_second": 2.501,
921
+ "step": 1467
922
+ },
923
+ {
924
+ "epoch": 4.01,
925
+ "learning_rate": 1.8370445344129557e-05,
926
+ "loss": 0.1732,
927
+ "step": 1470
928
+ },
929
+ {
930
+ "epoch": 4.04,
931
+ "learning_rate": 1.811740890688259e-05,
932
+ "loss": 0.1842,
933
+ "step": 1480
934
+ },
935
+ {
936
+ "epoch": 4.06,
937
+ "learning_rate": 1.786437246963563e-05,
938
+ "loss": 0.1865,
939
+ "step": 1490
940
+ },
941
+ {
942
+ "epoch": 4.09,
943
+ "learning_rate": 1.7611336032388663e-05,
944
+ "loss": 0.1725,
945
+ "step": 1500
946
+ },
947
+ {
948
+ "epoch": 4.12,
949
+ "learning_rate": 1.73582995951417e-05,
950
+ "loss": 0.1629,
951
+ "step": 1510
952
+ },
953
+ {
954
+ "epoch": 4.14,
955
+ "learning_rate": 1.7105263157894737e-05,
956
+ "loss": 0.1865,
957
+ "step": 1520
958
+ },
959
+ {
960
+ "epoch": 4.17,
961
+ "learning_rate": 1.6852226720647773e-05,
962
+ "loss": 0.1729,
963
+ "step": 1530
964
+ },
965
+ {
966
+ "epoch": 4.2,
967
+ "learning_rate": 1.6599190283400813e-05,
968
+ "loss": 0.1635,
969
+ "step": 1540
970
+ },
971
+ {
972
+ "epoch": 4.23,
973
+ "learning_rate": 1.6346153846153847e-05,
974
+ "loss": 0.1725,
975
+ "step": 1550
976
+ },
977
+ {
978
+ "epoch": 4.25,
979
+ "learning_rate": 1.6093117408906883e-05,
980
+ "loss": 0.1748,
981
+ "step": 1560
982
+ },
983
+ {
984
+ "epoch": 4.28,
985
+ "learning_rate": 1.584008097165992e-05,
986
+ "loss": 0.1721,
987
+ "step": 1570
988
+ },
989
+ {
990
+ "epoch": 4.31,
991
+ "learning_rate": 1.5587044534412957e-05,
992
+ "loss": 0.1667,
993
+ "step": 1580
994
+ },
995
+ {
996
+ "epoch": 4.34,
997
+ "learning_rate": 1.5334008097165993e-05,
998
+ "loss": 0.183,
999
+ "step": 1590
1000
+ },
1001
+ {
1002
+ "epoch": 4.36,
1003
+ "learning_rate": 1.508097165991903e-05,
1004
+ "loss": 0.1695,
1005
+ "step": 1600
1006
+ },
1007
+ {
1008
+ "epoch": 4.39,
1009
+ "learning_rate": 1.4827935222672065e-05,
1010
+ "loss": 0.1713,
1011
+ "step": 1610
1012
+ },
1013
+ {
1014
+ "epoch": 4.42,
1015
+ "learning_rate": 1.4574898785425101e-05,
1016
+ "loss": 0.1656,
1017
+ "step": 1620
1018
+ },
1019
+ {
1020
+ "epoch": 4.44,
1021
+ "learning_rate": 1.4321862348178138e-05,
1022
+ "loss": 0.1696,
1023
+ "step": 1630
1024
+ },
1025
+ {
1026
+ "epoch": 4.47,
1027
+ "learning_rate": 1.4068825910931175e-05,
1028
+ "loss": 0.1687,
1029
+ "step": 1640
1030
+ },
1031
+ {
1032
+ "epoch": 4.5,
1033
+ "learning_rate": 1.3815789473684213e-05,
1034
+ "loss": 0.166,
1035
+ "step": 1650
1036
+ },
1037
+ {
1038
+ "epoch": 4.53,
1039
+ "learning_rate": 1.3562753036437248e-05,
1040
+ "loss": 0.1806,
1041
+ "step": 1660
1042
+ },
1043
+ {
1044
+ "epoch": 4.55,
1045
+ "learning_rate": 1.3309716599190283e-05,
1046
+ "loss": 0.1592,
1047
+ "step": 1670
1048
+ },
1049
+ {
1050
+ "epoch": 4.58,
1051
+ "learning_rate": 1.3056680161943321e-05,
1052
+ "loss": 0.1741,
1053
+ "step": 1680
1054
+ },
1055
+ {
1056
+ "epoch": 4.61,
1057
+ "learning_rate": 1.2803643724696356e-05,
1058
+ "loss": 0.1668,
1059
+ "step": 1690
1060
+ },
1061
+ {
1062
+ "epoch": 4.64,
1063
+ "learning_rate": 1.2550607287449393e-05,
1064
+ "loss": 0.1697,
1065
+ "step": 1700
1066
+ },
1067
+ {
1068
+ "epoch": 4.66,
1069
+ "learning_rate": 1.229757085020243e-05,
1070
+ "loss": 0.1662,
1071
+ "step": 1710
1072
+ },
1073
+ {
1074
+ "epoch": 4.69,
1075
+ "learning_rate": 1.2044534412955466e-05,
1076
+ "loss": 0.1743,
1077
+ "step": 1720
1078
+ },
1079
+ {
1080
+ "epoch": 4.72,
1081
+ "learning_rate": 1.1791497975708503e-05,
1082
+ "loss": 0.1588,
1083
+ "step": 1730
1084
+ },
1085
+ {
1086
+ "epoch": 4.74,
1087
+ "learning_rate": 1.153846153846154e-05,
1088
+ "loss": 0.1615,
1089
+ "step": 1740
1090
+ },
1091
+ {
1092
+ "epoch": 4.77,
1093
+ "learning_rate": 1.1285425101214574e-05,
1094
+ "loss": 0.1659,
1095
+ "step": 1750
1096
+ },
1097
+ {
1098
+ "epoch": 4.8,
1099
+ "learning_rate": 1.1032388663967611e-05,
1100
+ "loss": 0.172,
1101
+ "step": 1760
1102
+ },
1103
+ {
1104
+ "epoch": 4.83,
1105
+ "learning_rate": 1.077935222672065e-05,
1106
+ "loss": 0.1726,
1107
+ "step": 1770
1108
+ },
1109
+ {
1110
+ "epoch": 4.85,
1111
+ "learning_rate": 1.0526315789473684e-05,
1112
+ "loss": 0.1542,
1113
+ "step": 1780
1114
+ },
1115
+ {
1116
+ "epoch": 4.88,
1117
+ "learning_rate": 1.0273279352226721e-05,
1118
+ "loss": 0.1583,
1119
+ "step": 1790
1120
+ },
1121
+ {
1122
+ "epoch": 4.91,
1123
+ "learning_rate": 1.0020242914979758e-05,
1124
+ "loss": 0.1589,
1125
+ "step": 1800
1126
+ },
1127
+ {
1128
+ "epoch": 4.94,
1129
+ "learning_rate": 9.767206477732794e-06,
1130
+ "loss": 0.1831,
1131
+ "step": 1810
1132
+ },
1133
+ {
1134
+ "epoch": 4.96,
1135
+ "learning_rate": 9.51417004048583e-06,
1136
+ "loss": 0.1733,
1137
+ "step": 1820
1138
+ },
1139
+ {
1140
+ "epoch": 4.99,
1141
+ "learning_rate": 9.261133603238866e-06,
1142
+ "loss": 0.1602,
1143
+ "step": 1830
1144
+ },
1145
+ {
1146
+ "epoch": 5.0,
1147
+ "eval_accuracy": 0.9388043211392094,
1148
+ "eval_loss": 0.19991646707057953,
1149
+ "eval_runtime": 64.3162,
1150
+ "eval_samples_per_second": 253.311,
1151
+ "eval_steps_per_second": 2.534,
1152
+ "step": 1833
1153
+ },
1154
+ {
1155
+ "epoch": 5.02,
1156
+ "learning_rate": 9.008097165991904e-06,
1157
+ "loss": 0.1674,
1158
+ "step": 1840
1159
+ },
1160
+ {
1161
+ "epoch": 5.04,
1162
+ "learning_rate": 8.75506072874494e-06,
1163
+ "loss": 0.1611,
1164
+ "step": 1850
1165
+ },
1166
+ {
1167
+ "epoch": 5.07,
1168
+ "learning_rate": 8.502024291497976e-06,
1169
+ "loss": 0.1574,
1170
+ "step": 1860
1171
+ },
1172
+ {
1173
+ "epoch": 5.1,
1174
+ "learning_rate": 8.248987854251013e-06,
1175
+ "loss": 0.1626,
1176
+ "step": 1870
1177
+ },
1178
+ {
1179
+ "epoch": 5.13,
1180
+ "learning_rate": 7.99595141700405e-06,
1181
+ "loss": 0.1684,
1182
+ "step": 1880
1183
+ },
1184
+ {
1185
+ "epoch": 5.15,
1186
+ "learning_rate": 7.742914979757084e-06,
1187
+ "loss": 0.1557,
1188
+ "step": 1890
1189
+ },
1190
+ {
1191
+ "epoch": 5.18,
1192
+ "learning_rate": 7.489878542510122e-06,
1193
+ "loss": 0.1541,
1194
+ "step": 1900
1195
+ },
1196
+ {
1197
+ "epoch": 5.21,
1198
+ "learning_rate": 7.236842105263158e-06,
1199
+ "loss": 0.1562,
1200
+ "step": 1910
1201
+ },
1202
+ {
1203
+ "epoch": 5.24,
1204
+ "learning_rate": 6.983805668016195e-06,
1205
+ "loss": 0.1607,
1206
+ "step": 1920
1207
+ },
1208
+ {
1209
+ "epoch": 5.26,
1210
+ "learning_rate": 6.730769230769231e-06,
1211
+ "loss": 0.1601,
1212
+ "step": 1930
1213
+ },
1214
+ {
1215
+ "epoch": 5.29,
1216
+ "learning_rate": 6.4777327935222675e-06,
1217
+ "loss": 0.1632,
1218
+ "step": 1940
1219
+ },
1220
+ {
1221
+ "epoch": 5.32,
1222
+ "learning_rate": 6.224696356275303e-06,
1223
+ "loss": 0.1683,
1224
+ "step": 1950
1225
+ },
1226
+ {
1227
+ "epoch": 5.34,
1228
+ "learning_rate": 5.971659919028341e-06,
1229
+ "loss": 0.163,
1230
+ "step": 1960
1231
+ },
1232
+ {
1233
+ "epoch": 5.37,
1234
+ "learning_rate": 5.718623481781377e-06,
1235
+ "loss": 0.1458,
1236
+ "step": 1970
1237
+ },
1238
+ {
1239
+ "epoch": 5.4,
1240
+ "learning_rate": 5.465587044534413e-06,
1241
+ "loss": 0.1538,
1242
+ "step": 1980
1243
+ },
1244
+ {
1245
+ "epoch": 5.43,
1246
+ "learning_rate": 5.21255060728745e-06,
1247
+ "loss": 0.1622,
1248
+ "step": 1990
1249
+ },
1250
+ {
1251
+ "epoch": 5.45,
1252
+ "learning_rate": 4.9595141700404865e-06,
1253
+ "loss": 0.1413,
1254
+ "step": 2000
1255
+ },
1256
+ {
1257
+ "epoch": 5.48,
1258
+ "learning_rate": 4.706477732793522e-06,
1259
+ "loss": 0.1688,
1260
+ "step": 2010
1261
+ },
1262
+ {
1263
+ "epoch": 5.51,
1264
+ "learning_rate": 4.453441295546559e-06,
1265
+ "loss": 0.1694,
1266
+ "step": 2020
1267
+ },
1268
+ {
1269
+ "epoch": 5.54,
1270
+ "learning_rate": 4.200404858299596e-06,
1271
+ "loss": 0.1565,
1272
+ "step": 2030
1273
+ },
1274
+ {
1275
+ "epoch": 5.56,
1276
+ "learning_rate": 3.9473684210526315e-06,
1277
+ "loss": 0.1651,
1278
+ "step": 2040
1279
+ },
1280
+ {
1281
+ "epoch": 5.59,
1282
+ "learning_rate": 3.6943319838056685e-06,
1283
+ "loss": 0.1515,
1284
+ "step": 2050
1285
+ },
1286
+ {
1287
+ "epoch": 5.62,
1288
+ "learning_rate": 3.4412955465587043e-06,
1289
+ "loss": 0.1602,
1290
+ "step": 2060
1291
+ },
1292
+ {
1293
+ "epoch": 5.64,
1294
+ "learning_rate": 3.1882591093117414e-06,
1295
+ "loss": 0.1632,
1296
+ "step": 2070
1297
+ },
1298
+ {
1299
+ "epoch": 5.67,
1300
+ "learning_rate": 2.9352226720647772e-06,
1301
+ "loss": 0.1558,
1302
+ "step": 2080
1303
+ },
1304
+ {
1305
+ "epoch": 5.7,
1306
+ "learning_rate": 2.682186234817814e-06,
1307
+ "loss": 0.1598,
1308
+ "step": 2090
1309
+ },
1310
+ {
1311
+ "epoch": 5.73,
1312
+ "learning_rate": 2.4291497975708505e-06,
1313
+ "loss": 0.1603,
1314
+ "step": 2100
1315
+ },
1316
+ {
1317
+ "epoch": 5.75,
1318
+ "learning_rate": 2.1761133603238867e-06,
1319
+ "loss": 0.1606,
1320
+ "step": 2110
1321
+ },
1322
+ {
1323
+ "epoch": 5.78,
1324
+ "learning_rate": 1.9230769230769234e-06,
1325
+ "loss": 0.1656,
1326
+ "step": 2120
1327
+ },
1328
+ {
1329
+ "epoch": 5.81,
1330
+ "learning_rate": 1.6700404858299598e-06,
1331
+ "loss": 0.159,
1332
+ "step": 2130
1333
+ },
1334
+ {
1335
+ "epoch": 5.84,
1336
+ "learning_rate": 1.417004048582996e-06,
1337
+ "loss": 0.16,
1338
+ "step": 2140
1339
+ },
1340
+ {
1341
+ "epoch": 5.86,
1342
+ "learning_rate": 1.1639676113360325e-06,
1343
+ "loss": 0.1623,
1344
+ "step": 2150
1345
+ },
1346
+ {
1347
+ "epoch": 5.89,
1348
+ "learning_rate": 9.109311740890688e-07,
1349
+ "loss": 0.1567,
1350
+ "step": 2160
1351
+ },
1352
+ {
1353
+ "epoch": 5.92,
1354
+ "learning_rate": 6.578947368421053e-07,
1355
+ "loss": 0.1656,
1356
+ "step": 2170
1357
+ },
1358
+ {
1359
+ "epoch": 5.94,
1360
+ "learning_rate": 4.048582995951417e-07,
1361
+ "loss": 0.1512,
1362
+ "step": 2180
1363
+ },
1364
+ {
1365
+ "epoch": 5.97,
1366
+ "learning_rate": 1.5182186234817816e-07,
1367
+ "loss": 0.1633,
1368
+ "step": 2190
1369
+ },
1370
+ {
1371
+ "epoch": 5.99,
1372
+ "eval_accuracy": 0.9600417382764547,
1373
+ "eval_loss": 0.12867580354213715,
1374
+ "eval_runtime": 64.5009,
1375
+ "eval_samples_per_second": 252.586,
1376
+ "eval_steps_per_second": 2.527,
1377
+ "step": 2196
1378
+ },
1379
+ {
1380
+ "epoch": 5.99,
1381
+ "step": 2196,
1382
+ "total_flos": 2.353803972968448e+18,
1383
+ "train_loss": 0.48255133992552973,
1384
+ "train_runtime": 7781.6451,
1385
+ "train_samples_per_second": 113.054,
1386
+ "train_steps_per_second": 0.282
1387
+ }
1388
+ ],
1389
+ "logging_steps": 10,
1390
+ "max_steps": 2196,
1391
+ "num_train_epochs": 6,
1392
+ "save_steps": 500,
1393
+ "total_flos": 2.353803972968448e+18,
1394
+ "trial_name": null,
1395
+ "trial_params": null
1396
+ }
training_args.bin ADDED
Binary file (4.6 kB). View file