Hugging Face's logo

rvv-karma
/
Human-Action-Recognition-VIT-Base-patch16-224

Image Classification
Transformers
TensorBoard
Safetensors
English
vit
Generated from Trainer
Model card Files
xet
Metrics Community
rvv-karma commited on
Commit
743363a
·
1 Parent(s): b018198

End of training

Browse files
Files changed (19) hide show
  1. README.md +82 -0
  2. all_results.json +13 -0
  3. config.json +58 -0
  4. eval_results.json +8 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +22 -0
  7. runs/Dec10_11-10-30_1ca383c7b033/events.out.tfevents.1702206785.1ca383c7b033.7463.0 +3 -0
  8. runs/Dec10_11-10-30_1ca383c7b033/events.out.tfevents.1702207216.1ca383c7b033.7463.1 +3 -0
  9. runs/Dec10_11-31-28_1ca383c7b033/events.out.tfevents.1702207892.1ca383c7b033.7463.2 +3 -0
  10. runs/Dec10_11-32-31_1ca383c7b033/events.out.tfevents.1702207955.1ca383c7b033.13158.0 +3 -0
  11. runs/Dec10_11-36-26_1ca383c7b033/events.out.tfevents.1702208191.1ca383c7b033.14225.0 +3 -0
  12. runs/Dec10_11-36-26_1ca383c7b033/events.out.tfevents.1702209262.1ca383c7b033.14225.1 +3 -0
  13. runs/Dec10_11-59-18_1ca383c7b033/events.out.tfevents.1702209564.1ca383c7b033.20107.0 +3 -0
  14. runs/Dec10_12-02-18_1ca383c7b033/events.out.tfevents.1702209743.1ca383c7b033.20945.0 +3 -0
  15. runs/Dec10_12-30-16_1ca383c7b033/events.out.tfevents.1702211423.1ca383c7b033.28198.0 +3 -0
  16. runs/Dec10_12-30-16_1ca383c7b033/events.out.tfevents.1702218768.1ca383c7b033.28198.1 +3 -0
  17. train_results.json +8 -0
  18. trainer_state.json +328 -0
  19. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: Human-Action-Recognition-VIT-Base-patch16-224
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Human-Action-Recognition-VIT-Base-patch16-224
17
+
18
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4005
21
+ - Accuracy: 0.8786
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 64
42
+ - eval_batch_size: 64
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 256
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 20
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 2.6396 | 0.99 | 39 | 2.0436 | 0.4425 |
56
+ | 1.4579 | 2.0 | 79 | 0.7553 | 0.7917 |
57
+ | 0.8342 | 2.99 | 118 | 0.5296 | 0.8417 |
58
+ | 0.6649 | 4.0 | 158 | 0.4978 | 0.8496 |
59
+ | 0.6137 | 4.99 | 197 | 0.4460 | 0.8595 |
60
+ | 0.5374 | 6.0 | 237 | 0.4356 | 0.8627 |
61
+ | 0.514 | 6.99 | 276 | 0.4349 | 0.8615 |
62
+ | 0.475 | 8.0 | 316 | 0.4005 | 0.8786 |
63
+ | 0.4663 | 8.99 | 355 | 0.4164 | 0.8659 |
64
+ | 0.4178 | 10.0 | 395 | 0.4128 | 0.8738 |
65
+ | 0.4226 | 10.99 | 434 | 0.4115 | 0.8690 |
66
+ | 0.3896 | 12.0 | 474 | 0.4112 | 0.875 |
67
+ | 0.3866 | 12.99 | 513 | 0.4072 | 0.8714 |
68
+ | 0.3632 | 14.0 | 553 | 0.4106 | 0.8718 |
69
+ | 0.3596 | 14.99 | 592 | 0.4043 | 0.8714 |
70
+ | 0.3421 | 16.0 | 632 | 0.4128 | 0.8675 |
71
+ | 0.344 | 16.99 | 671 | 0.4181 | 0.8643 |
72
+ | 0.3447 | 18.0 | 711 | 0.4128 | 0.8687 |
73
+ | 0.3407 | 18.99 | 750 | 0.4097 | 0.8714 |
74
+ | 0.3267 | 19.75 | 780 | 0.4097 | 0.8683 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.35.2
80
+ - Pytorch 2.1.0+cu118
81
+ - Datasets 2.15.0
82
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 19.75,
3
+ "eval_accuracy": 0.8785714285714286,
4
+ "eval_loss": 0.4005189836025238,
5
+ "eval_runtime": 34.3244,
6
+ "eval_samples_per_second": 73.417,
7
+ "eval_steps_per_second": 1.165,
8
+ "total_flos": 1.5428282771770638e+19,
9
+ "train_loss": 0.6146706715608254,
10
+ "train_runtime": 7303.7952,
11
+ "train_samples_per_second": 27.602,
12
+ "train_steps_per_second": 0.107
13
+ }
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224",
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": "calling",
13
+ "1": "clapping",
14
+ "2": "cycling",
15
+ "3": "dancing",
16
+ "4": "drinking",
17
+ "5": "eating",
18
+ "6": "fighting",
19
+ "7": "hugging",
20
+ "8": "laughing",
21
+ "9": "listening_to_music",
22
+ "10": "running",
23
+ "11": "sitting",
24
+ "12": "sleeping",
25
+ "13": "texting",
26
+ "14": "using_laptop"
27
+ },
28
+ "image_size": 224,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "label2id": {
32
+ "calling": 0,
33
+ "clapping": 1,
34
+ "cycling": 2,
35
+ "dancing": 3,
36
+ "drinking": 4,
37
+ "eating": 5,
38
+ "fighting": 6,
39
+ "hugging": 7,
40
+ "laughing": 8,
41
+ "listening_to_music": 9,
42
+ "running": 10,
43
+ "sitting": 11,
44
+ "sleeping": 12,
45
+ "texting": 13,
46
+ "using_laptop": 14
47
+ },
48
+ "layer_norm_eps": 1e-12,
49
+ "model_type": "vit",
50
+ "num_attention_heads": 12,
51
+ "num_channels": 3,
52
+ "num_hidden_layers": 12,
53
+ "patch_size": 16,
54
+ "problem_type": "single_label_classification",
55
+ "qkv_bias": true,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.35.2"
58
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 19.75,
3
+ "eval_accuracy": 0.8785714285714286,
4
+ "eval_loss": 0.4005189836025238,
5
+ "eval_runtime": 34.3244,
6
+ "eval_samples_per_second": 73.417,
7
+ "eval_steps_per_second": 1.165
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7056e0051ac930aa8db19a1c3135cdc6a181837d660814e9c3fd8ad6123ea815
3
+ size 343263964
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
runs/Dec10_11-10-30_1ca383c7b033/events.out.tfevents.1702206785.1ca383c7b033.7463.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196d434e6cb09a98387967754ead38a75f49815eda61a418681519c74762620d
3
+ size 16046
runs/Dec10_11-10-30_1ca383c7b033/events.out.tfevents.1702207216.1ca383c7b033.7463.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e334e4f002a51a44b8eae916cceb98bd541da9e26d6cf89f344744b81ec094d
3
+ size 405
runs/Dec10_11-31-28_1ca383c7b033/events.out.tfevents.1702207892.1ca383c7b033.7463.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aad26a6a20cbfc81cf893c55434c625d2fabef40860b9d5f268d0cc8a87af95
3
+ size 4184
runs/Dec10_11-32-31_1ca383c7b033/events.out.tfevents.1702207955.1ca383c7b033.13158.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058f73f004a2c8d0e7af1fb0e674b58f733575d5b2baf78e3a461ac096a28a46
3
+ size 5470
runs/Dec10_11-36-26_1ca383c7b033/events.out.tfevents.1702208191.1ca383c7b033.14225.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1a35f0b7f118c30a88561acd99bff9cc5a4357bfa0e4f5b85a255b3ba0f9bd
3
+ size 6142
runs/Dec10_11-36-26_1ca383c7b033/events.out.tfevents.1702209262.1ca383c7b033.14225.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ef4f5fd284ce82d0dbda4c17518b8b1eb45ece5d3a5c4304c70d3dadb9cc57
3
+ size 405
runs/Dec10_11-59-18_1ca383c7b033/events.out.tfevents.1702209564.1ca383c7b033.20107.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48a7a0166952ee446efb3bbacf32b2a5d1b0de000849031781ceb7be86e8d11
3
+ size 4853
runs/Dec10_12-02-18_1ca383c7b033/events.out.tfevents.1702209743.1ca383c7b033.20945.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15d8cf48e8f197ce36b39e8d7a76203f5efd9604bc975efe4d251042156a2e6
3
+ size 6275
runs/Dec10_12-30-16_1ca383c7b033/events.out.tfevents.1702211423.1ca383c7b033.28198.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e6384388584a921d5466a895e87f964249d4ad46810e03040bfa89bc83b52b6
3
+ size 14780
runs/Dec10_12-30-16_1ca383c7b033/events.out.tfevents.1702218768.1ca383c7b033.28198.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee745d15d25fd95d595f6e5f30fe6ca9c5ea39f7adb0baf861fb7c7eeff34fd
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 19.75,
3
+ "total_flos": 1.5428282771770638e+19,
4
+ "train_loss": 0.6146706715608254,
5
+ "train_runtime": 7303.7952,
6
+ "train_samples_per_second": 27.602,
7
+ "train_steps_per_second": 0.107
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8785714285714286,
3
+ "best_model_checkpoint": "Human-Action-Recognition-VIT-Base-patch16-224/checkpoint-316",
4
+ "epoch": 19.746835443037973,
5
+ "eval_steps": 500,
6
+ "global_step": 780,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.99,
13
+ "learning_rate": 2.5e-05,
14
+ "loss": 2.6396,
15
+ "step": 39
16
+ },
17
+ {
18
+ "epoch": 0.99,
19
+ "eval_accuracy": 0.44246031746031744,
20
+ "eval_loss": 2.04364275932312,
21
+ "eval_runtime": 33.6234,
22
+ "eval_samples_per_second": 74.948,
23
+ "eval_steps_per_second": 1.19,
24
+ "step": 39
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 4.992877492877493e-05,
29
+ "loss": 1.4579,
30
+ "step": 79
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.7916666666666666,
35
+ "eval_loss": 0.7552899122238159,
36
+ "eval_runtime": 33.9732,
37
+ "eval_samples_per_second": 74.176,
38
+ "eval_steps_per_second": 1.177,
39
+ "step": 79
40
+ },
41
+ {
42
+ "epoch": 2.99,
43
+ "learning_rate": 4.7150997150997157e-05,
44
+ "loss": 0.8342,
45
+ "step": 118
46
+ },
47
+ {
48
+ "epoch": 2.99,
49
+ "eval_accuracy": 0.8416666666666667,
50
+ "eval_loss": 0.5296158194541931,
51
+ "eval_runtime": 33.8808,
52
+ "eval_samples_per_second": 74.378,
53
+ "eval_steps_per_second": 1.181,
54
+ "step": 118
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 4.4301994301994304e-05,
59
+ "loss": 0.6649,
60
+ "step": 158
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8496031746031746,
65
+ "eval_loss": 0.4977969229221344,
66
+ "eval_runtime": 33.6309,
67
+ "eval_samples_per_second": 74.931,
68
+ "eval_steps_per_second": 1.189,
69
+ "step": 158
70
+ },
71
+ {
72
+ "epoch": 4.99,
73
+ "learning_rate": 4.152421652421652e-05,
74
+ "loss": 0.6137,
75
+ "step": 197
76
+ },
77
+ {
78
+ "epoch": 4.99,
79
+ "eval_accuracy": 0.8595238095238096,
80
+ "eval_loss": 0.44600579142570496,
81
+ "eval_runtime": 33.559,
82
+ "eval_samples_per_second": 75.092,
83
+ "eval_steps_per_second": 1.192,
84
+ "step": 197
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 3.867521367521368e-05,
89
+ "loss": 0.5374,
90
+ "step": 237
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8626984126984127,
95
+ "eval_loss": 0.43557941913604736,
96
+ "eval_runtime": 33.4656,
97
+ "eval_samples_per_second": 75.301,
98
+ "eval_steps_per_second": 1.195,
99
+ "step": 237
100
+ },
101
+ {
102
+ "epoch": 6.99,
103
+ "learning_rate": 3.58974358974359e-05,
104
+ "loss": 0.514,
105
+ "step": 276
106
+ },
107
+ {
108
+ "epoch": 6.99,
109
+ "eval_accuracy": 0.8615079365079366,
110
+ "eval_loss": 0.4348864257335663,
111
+ "eval_runtime": 33.7031,
112
+ "eval_samples_per_second": 74.771,
113
+ "eval_steps_per_second": 1.187,
114
+ "step": 276
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 3.304843304843305e-05,
119
+ "loss": 0.475,
120
+ "step": 316
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8785714285714286,
125
+ "eval_loss": 0.4005189836025238,
126
+ "eval_runtime": 33.4656,
127
+ "eval_samples_per_second": 75.301,
128
+ "eval_steps_per_second": 1.195,
129
+ "step": 316
130
+ },
131
+ {
132
+ "epoch": 8.99,
133
+ "learning_rate": 3.0270655270655275e-05,
134
+ "loss": 0.4663,
135
+ "step": 355
136
+ },
137
+ {
138
+ "epoch": 8.99,
139
+ "eval_accuracy": 0.8658730158730159,
140
+ "eval_loss": 0.4163670241832733,
141
+ "eval_runtime": 33.7779,
142
+ "eval_samples_per_second": 74.605,
143
+ "eval_steps_per_second": 1.184,
144
+ "step": 355
145
+ },
146
+ {
147
+ "epoch": 10.0,
148
+ "learning_rate": 2.7421652421652423e-05,
149
+ "loss": 0.4178,
150
+ "step": 395
151
+ },
152
+ {
153
+ "epoch": 10.0,
154
+ "eval_accuracy": 0.8738095238095238,
155
+ "eval_loss": 0.4127999544143677,
156
+ "eval_runtime": 33.3961,
157
+ "eval_samples_per_second": 75.458,
158
+ "eval_steps_per_second": 1.198,
159
+ "step": 395
160
+ },
161
+ {
162
+ "epoch": 10.99,
163
+ "learning_rate": 2.4643874643874645e-05,
164
+ "loss": 0.4226,
165
+ "step": 434
166
+ },
167
+ {
168
+ "epoch": 10.99,
169
+ "eval_accuracy": 0.8690476190476191,
170
+ "eval_loss": 0.4115118980407715,
171
+ "eval_runtime": 33.5412,
172
+ "eval_samples_per_second": 75.131,
173
+ "eval_steps_per_second": 1.193,
174
+ "step": 434
175
+ },
176
+ {
177
+ "epoch": 12.0,
178
+ "learning_rate": 2.1794871794871795e-05,
179
+ "loss": 0.3896,
180
+ "step": 474
181
+ },
182
+ {
183
+ "epoch": 12.0,
184
+ "eval_accuracy": 0.875,
185
+ "eval_loss": 0.4112005829811096,
186
+ "eval_runtime": 33.6831,
187
+ "eval_samples_per_second": 74.815,
188
+ "eval_steps_per_second": 1.188,
189
+ "step": 474
190
+ },
191
+ {
192
+ "epoch": 12.99,
193
+ "learning_rate": 1.9017094017094017e-05,
194
+ "loss": 0.3866,
195
+ "step": 513
196
+ },
197
+ {
198
+ "epoch": 12.99,
199
+ "eval_accuracy": 0.8714285714285714,
200
+ "eval_loss": 0.4072014093399048,
201
+ "eval_runtime": 33.7064,
202
+ "eval_samples_per_second": 74.763,
203
+ "eval_steps_per_second": 1.187,
204
+ "step": 513
205
+ },
206
+ {
207
+ "epoch": 14.0,
208
+ "learning_rate": 1.6168091168091168e-05,
209
+ "loss": 0.3632,
210
+ "step": 553
211
+ },
212
+ {
213
+ "epoch": 14.0,
214
+ "eval_accuracy": 0.8718253968253968,
215
+ "eval_loss": 0.41061681509017944,
216
+ "eval_runtime": 33.9136,
217
+ "eval_samples_per_second": 74.306,
218
+ "eval_steps_per_second": 1.179,
219
+ "step": 553
220
+ },
221
+ {
222
+ "epoch": 14.99,
223
+ "learning_rate": 1.3390313390313392e-05,
224
+ "loss": 0.3596,
225
+ "step": 592
226
+ },
227
+ {
228
+ "epoch": 14.99,
229
+ "eval_accuracy": 0.8714285714285714,
230
+ "eval_loss": 0.4042780101299286,
231
+ "eval_runtime": 33.971,
232
+ "eval_samples_per_second": 74.181,
233
+ "eval_steps_per_second": 1.177,
234
+ "step": 592
235
+ },
236
+ {
237
+ "epoch": 16.0,
238
+ "learning_rate": 1.0541310541310543e-05,
239
+ "loss": 0.3421,
240
+ "step": 632
241
+ },
242
+ {
243
+ "epoch": 16.0,
244
+ "eval_accuracy": 0.8674603174603175,
245
+ "eval_loss": 0.4128040075302124,
246
+ "eval_runtime": 33.5678,
247
+ "eval_samples_per_second": 75.072,
248
+ "eval_steps_per_second": 1.192,
249
+ "step": 632
250
+ },
251
+ {
252
+ "epoch": 16.99,
253
+ "learning_rate": 7.763532763532765e-06,
254
+ "loss": 0.344,
255
+ "step": 671
256
+ },
257
+ {
258
+ "epoch": 16.99,
259
+ "eval_accuracy": 0.8642857142857143,
260
+ "eval_loss": 0.41805535554885864,
261
+ "eval_runtime": 33.6623,
262
+ "eval_samples_per_second": 74.861,
263
+ "eval_steps_per_second": 1.188,
264
+ "step": 671
265
+ },
266
+ {
267
+ "epoch": 18.0,
268
+ "learning_rate": 4.914529914529915e-06,
269
+ "loss": 0.3447,
270
+ "step": 711
271
+ },
272
+ {
273
+ "epoch": 18.0,
274
+ "eval_accuracy": 0.8686507936507937,
275
+ "eval_loss": 0.41281768679618835,
276
+ "eval_runtime": 33.9679,
277
+ "eval_samples_per_second": 74.188,
278
+ "eval_steps_per_second": 1.178,
279
+ "step": 711
280
+ },
281
+ {
282
+ "epoch": 18.99,
283
+ "learning_rate": 2.136752136752137e-06,
284
+ "loss": 0.3407,
285
+ "step": 750
286
+ },
287
+ {
288
+ "epoch": 18.99,
289
+ "eval_accuracy": 0.8714285714285714,
290
+ "eval_loss": 0.40965768694877625,
291
+ "eval_runtime": 33.6119,
292
+ "eval_samples_per_second": 74.973,
293
+ "eval_steps_per_second": 1.19,
294
+ "step": 750
295
+ },
296
+ {
297
+ "epoch": 19.75,
298
+ "learning_rate": 0.0,
299
+ "loss": 0.3267,
300
+ "step": 780
301
+ },
302
+ {
303
+ "epoch": 19.75,
304
+ "eval_accuracy": 0.8682539682539683,
305
+ "eval_loss": 0.40967872738838196,
306
+ "eval_runtime": 34.1352,
307
+ "eval_samples_per_second": 73.824,
308
+ "eval_steps_per_second": 1.172,
309
+ "step": 780
310
+ },
311
+ {
312
+ "epoch": 19.75,
313
+ "step": 780,
314
+ "total_flos": 1.5428282771770638e+19,
315
+ "train_loss": 0.6146706715608254,
316
+ "train_runtime": 7303.7952,
317
+ "train_samples_per_second": 27.602,
318
+ "train_steps_per_second": 0.107
319
+ }
320
+ ],
321
+ "logging_steps": 500,
322
+ "max_steps": 780,
323
+ "num_train_epochs": 20,
324
+ "save_steps": 500,
325
+ "total_flos": 1.5428282771770638e+19,
326
+ "trial_name": null,
327
+ "trial_params": null
328
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d26bb9e3a70b2c8352b321913a1989c2ebf70972127858a70a2e4b75644fe29
3
+ size 4600