Hugging Face's logo

Augusto777
/
swiftformer-xs-RH

TensorBoard
Safetensors
swiftformer
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
Augusto777 commited on
Commit
42abd47
·
verified ·
1 Parent(s): 7bcbb26

End of training

Browse files
Files changed (11) hide show
  1. README.md +116 -0
  2. all_results.json +12 -0
  3. config.json +46 -0
  4. eval_results.json +8 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +22 -0
  7. runs/Dec01_18-54-23_DESKTOP-SKBE9FB/events.out.tfevents.1733100864.DESKTOP-SKBE9FB.7036.0 +3 -0
  8. runs/Dec01_18-54-23_DESKTOP-SKBE9FB/events.out.tfevents.1733101309.DESKTOP-SKBE9FB.7036.1 +3 -0
  9. train_results.json +7 -0
  10. trainer_state.json +582 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: MBZUAI/swiftformer-xs
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: swiftformer-xs-RH
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: validation
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.8598130841121495
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # swiftformer-xs-RH
31
+
32
+ This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.4150
35
+ - Accuracy: 0.8598
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.0003
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 16
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 64
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 40
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 1.0 | 8 | 0.6926 | 0.6262 |
70
+ | 0.693 | 2.0 | 16 | 0.6873 | 0.6822 |
71
+ | 0.6899 | 3.0 | 24 | 0.6694 | 0.6729 |
72
+ | 0.6732 | 4.0 | 32 | 0.6146 | 0.7290 |
73
+ | 0.6256 | 5.0 | 40 | 0.7084 | 0.4953 |
74
+ | 0.6256 | 6.0 | 48 | 0.6591 | 0.6355 |
75
+ | 0.5796 | 7.0 | 56 | 0.5670 | 0.7383 |
76
+ | 0.5253 | 8.0 | 64 | 0.5351 | 0.7196 |
77
+ | 0.4713 | 9.0 | 72 | 0.4614 | 0.8411 |
78
+ | 0.441 | 10.0 | 80 | 0.5826 | 0.7570 |
79
+ | 0.441 | 11.0 | 88 | 0.4679 | 0.7850 |
80
+ | 0.3803 | 12.0 | 96 | 0.4517 | 0.8411 |
81
+ | 0.3513 | 13.0 | 104 | 0.4571 | 0.7757 |
82
+ | 0.3043 | 14.0 | 112 | 0.4755 | 0.8037 |
83
+ | 0.3172 | 15.0 | 120 | 0.5953 | 0.7944 |
84
+ | 0.3172 | 16.0 | 128 | 0.5904 | 0.7383 |
85
+ | 0.365 | 17.0 | 136 | 0.4213 | 0.8411 |
86
+ | 0.279 | 18.0 | 144 | 0.4572 | 0.8037 |
87
+ | 0.3092 | 19.0 | 152 | 0.4181 | 0.8131 |
88
+ | 0.2667 | 20.0 | 160 | 0.4117 | 0.8224 |
89
+ | 0.2667 | 21.0 | 168 | 0.4349 | 0.8037 |
90
+ | 0.261 | 22.0 | 176 | 0.4185 | 0.8037 |
91
+ | 0.2638 | 23.0 | 184 | 0.3989 | 0.8131 |
92
+ | 0.2269 | 24.0 | 192 | 0.3971 | 0.8318 |
93
+ | 0.2431 | 25.0 | 200 | 0.4784 | 0.8037 |
94
+ | 0.2431 | 26.0 | 208 | 0.3763 | 0.8318 |
95
+ | 0.2111 | 27.0 | 216 | 0.4088 | 0.8411 |
96
+ | 0.2087 | 28.0 | 224 | 0.4024 | 0.8318 |
97
+ | 0.1645 | 29.0 | 232 | 0.4161 | 0.8318 |
98
+ | 0.2137 | 30.0 | 240 | 0.4128 | 0.8131 |
99
+ | 0.2137 | 31.0 | 248 | 0.4004 | 0.8411 |
100
+ | 0.2207 | 32.0 | 256 | 0.4206 | 0.8224 |
101
+ | 0.1544 | 33.0 | 264 | 0.3622 | 0.8505 |
102
+ | 0.197 | 34.0 | 272 | 0.4356 | 0.8411 |
103
+ | 0.2168 | 35.0 | 280 | 0.4067 | 0.8318 |
104
+ | 0.2168 | 36.0 | 288 | 0.3809 | 0.8224 |
105
+ | 0.1631 | 37.0 | 296 | 0.3865 | 0.8411 |
106
+ | 0.1913 | 38.0 | 304 | 0.4008 | 0.8318 |
107
+ | 0.1595 | 39.0 | 312 | 0.3752 | 0.8318 |
108
+ | 0.1694 | 40.0 | 320 | 0.4150 | 0.8598 |
109
+
110
+
111
+ ### Framework versions
112
+
113
+ - Transformers 4.36.2
114
+ - Pytorch 2.1.2+cu118
115
+ - Datasets 2.16.1
116
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "eval_accuracy": 0.8598130841121495,
4
+ "eval_loss": 0.4150024354457855,
5
+ "eval_runtime": 1.7949,
6
+ "eval_samples_per_second": 59.613,
7
+ "eval_steps_per_second": 3.9,
8
+ "train_loss": 0.32927754148840904,
9
+ "train_runtime": 444.0356,
10
+ "train_samples_per_second": 44.861,
11
+ "train_steps_per_second": 0.721
12
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MBZUAI/swiftformer-xs",
3
+ "architectures": [
4
+ "SwiftFormerForImageClassification"
5
+ ],
6
+ "batch_norm_eps": 1e-05,
7
+ "depths": [
8
+ 3,
9
+ 3,
10
+ 6,
11
+ 4
12
+ ],
13
+ "down_pad": 1,
14
+ "down_patch_size": 3,
15
+ "down_stride": 2,
16
+ "downsamples": [
17
+ true,
18
+ true,
19
+ true,
20
+ true
21
+ ],
22
+ "drop_path_rate": 0.0,
23
+ "embed_dims": [
24
+ 48,
25
+ 56,
26
+ 112,
27
+ 220
28
+ ],
29
+ "hidden_act": "gelu",
30
+ "id2label": {
31
+ "0": "HR",
32
+ "1": "No HR"
33
+ },
34
+ "label2id": {
35
+ "HR": 0,
36
+ "No HR": 1
37
+ },
38
+ "layer_scale_init_value": 1e-05,
39
+ "mlp_ratio": 4,
40
+ "model_type": "swiftformer",
41
+ "num_channels": 3,
42
+ "problem_type": "single_label_classification",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.36.2",
45
+ "use_layer_scale": true
46
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "eval_accuracy": 0.8598130841121495,
4
+ "eval_loss": 0.4150024354457855,
5
+ "eval_runtime": 1.7949,
6
+ "eval_samples_per_second": 59.613,
7
+ "eval_steps_per_second": 3.9
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055106c84007ff41cdc51fd1a954d87e2dd2e93b0cb581e9ecbd3e3d9f85fb4a
3
+ size 12200096
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
+ 0.485,
7
+ 0.456,
8
+ 0.406
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.229,
13
+ 0.224,
14
+ 0.225
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
runs/Dec01_18-54-23_DESKTOP-SKBE9FB/events.out.tfevents.1733100864.DESKTOP-SKBE9FB.7036.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b153f5301f53e814c9d9dd675ed2d5d025ddd79df8cad3f0f9386ea1f543c82
3
+ size 22621
runs/Dec01_18-54-23_DESKTOP-SKBE9FB/events.out.tfevents.1733101309.DESKTOP-SKBE9FB.7036.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b039a7680cc18a6bbb4251f15ffe684bb513a4859c6d925ed654e778d8064c7
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "train_loss": 0.32927754148840904,
4
+ "train_runtime": 444.0356,
5
+ "train_samples_per_second": 44.861,
6
+ "train_steps_per_second": 0.721
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,582 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8598130841121495,
3
+ "best_model_checkpoint": "swiftformer-xs-RH\\checkpoint-320",
4
+ "epoch": 40.0,
5
+ "eval_steps": 500,
6
+ "global_step": 320,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.6261682242990654,
14
+ "eval_loss": 0.6926182508468628,
15
+ "eval_runtime": 1.7559,
16
+ "eval_samples_per_second": 60.937,
17
+ "eval_steps_per_second": 3.987,
18
+ "step": 8
19
+ },
20
+ {
21
+ "epoch": 1.25,
22
+ "learning_rate": 9.374999999999999e-05,
23
+ "loss": 0.693,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.6822429906542056,
29
+ "eval_loss": 0.6872997283935547,
30
+ "eval_runtime": 1.7079,
31
+ "eval_samples_per_second": 62.65,
32
+ "eval_steps_per_second": 4.099,
33
+ "step": 16
34
+ },
35
+ {
36
+ "epoch": 2.5,
37
+ "learning_rate": 0.00018749999999999998,
38
+ "loss": 0.6899,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "eval_accuracy": 0.6728971962616822,
44
+ "eval_loss": 0.6693950295448303,
45
+ "eval_runtime": 1.6779,
46
+ "eval_samples_per_second": 63.771,
47
+ "eval_steps_per_second": 4.172,
48
+ "step": 24
49
+ },
50
+ {
51
+ "epoch": 3.75,
52
+ "learning_rate": 0.00028125,
53
+ "loss": 0.6732,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "eval_accuracy": 0.7289719626168224,
59
+ "eval_loss": 0.6145507097244263,
60
+ "eval_runtime": 1.817,
61
+ "eval_samples_per_second": 58.89,
62
+ "eval_steps_per_second": 3.853,
63
+ "step": 32
64
+ },
65
+ {
66
+ "epoch": 5.0,
67
+ "learning_rate": 0.00029166666666666664,
68
+ "loss": 0.6256,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "eval_accuracy": 0.4953271028037383,
74
+ "eval_loss": 0.7084487676620483,
75
+ "eval_runtime": 1.5979,
76
+ "eval_samples_per_second": 66.964,
77
+ "eval_steps_per_second": 4.381,
78
+ "step": 40
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "eval_accuracy": 0.6355140186915887,
83
+ "eval_loss": 0.6590595245361328,
84
+ "eval_runtime": 1.6669,
85
+ "eval_samples_per_second": 64.191,
86
+ "eval_steps_per_second": 4.199,
87
+ "step": 48
88
+ },
89
+ {
90
+ "epoch": 6.25,
91
+ "learning_rate": 0.00028125,
92
+ "loss": 0.5796,
93
+ "step": 50
94
+ },
95
+ {
96
+ "epoch": 7.0,
97
+ "eval_accuracy": 0.7383177570093458,
98
+ "eval_loss": 0.5670130252838135,
99
+ "eval_runtime": 1.5904,
100
+ "eval_samples_per_second": 67.28,
101
+ "eval_steps_per_second": 4.401,
102
+ "step": 56
103
+ },
104
+ {
105
+ "epoch": 7.5,
106
+ "learning_rate": 0.0002708333333333333,
107
+ "loss": 0.5253,
108
+ "step": 60
109
+ },
110
+ {
111
+ "epoch": 8.0,
112
+ "eval_accuracy": 0.719626168224299,
113
+ "eval_loss": 0.5351107716560364,
114
+ "eval_runtime": 1.5394,
115
+ "eval_samples_per_second": 69.51,
116
+ "eval_steps_per_second": 4.547,
117
+ "step": 64
118
+ },
119
+ {
120
+ "epoch": 8.75,
121
+ "learning_rate": 0.00026041666666666666,
122
+ "loss": 0.4713,
123
+ "step": 70
124
+ },
125
+ {
126
+ "epoch": 9.0,
127
+ "eval_accuracy": 0.8411214953271028,
128
+ "eval_loss": 0.46139419078826904,
129
+ "eval_runtime": 1.6064,
130
+ "eval_samples_per_second": 66.61,
131
+ "eval_steps_per_second": 4.358,
132
+ "step": 72
133
+ },
134
+ {
135
+ "epoch": 10.0,
136
+ "learning_rate": 0.00025,
137
+ "loss": 0.441,
138
+ "step": 80
139
+ },
140
+ {
141
+ "epoch": 10.0,
142
+ "eval_accuracy": 0.7570093457943925,
143
+ "eval_loss": 0.5826085209846497,
144
+ "eval_runtime": 1.6799,
145
+ "eval_samples_per_second": 63.694,
146
+ "eval_steps_per_second": 4.167,
147
+ "step": 80
148
+ },
149
+ {
150
+ "epoch": 11.0,
151
+ "eval_accuracy": 0.7850467289719626,
152
+ "eval_loss": 0.4679306745529175,
153
+ "eval_runtime": 1.5994,
154
+ "eval_samples_per_second": 66.901,
155
+ "eval_steps_per_second": 4.377,
156
+ "step": 88
157
+ },
158
+ {
159
+ "epoch": 11.25,
160
+ "learning_rate": 0.00023958333333333332,
161
+ "loss": 0.3803,
162
+ "step": 90
163
+ },
164
+ {
165
+ "epoch": 12.0,
166
+ "eval_accuracy": 0.8411214953271028,
167
+ "eval_loss": 0.4516862630844116,
168
+ "eval_runtime": 1.6584,
169
+ "eval_samples_per_second": 64.52,
170
+ "eval_steps_per_second": 4.221,
171
+ "step": 96
172
+ },
173
+ {
174
+ "epoch": 12.5,
175
+ "learning_rate": 0.00022916666666666664,
176
+ "loss": 0.3513,
177
+ "step": 100
178
+ },
179
+ {
180
+ "epoch": 13.0,
181
+ "eval_accuracy": 0.7757009345794392,
182
+ "eval_loss": 0.45713210105895996,
183
+ "eval_runtime": 1.5724,
184
+ "eval_samples_per_second": 68.05,
185
+ "eval_steps_per_second": 4.452,
186
+ "step": 104
187
+ },
188
+ {
189
+ "epoch": 13.75,
190
+ "learning_rate": 0.00021874999999999998,
191
+ "loss": 0.3043,
192
+ "step": 110
193
+ },
194
+ {
195
+ "epoch": 14.0,
196
+ "eval_accuracy": 0.8037383177570093,
197
+ "eval_loss": 0.47551780939102173,
198
+ "eval_runtime": 1.6209,
199
+ "eval_samples_per_second": 66.014,
200
+ "eval_steps_per_second": 4.319,
201
+ "step": 112
202
+ },
203
+ {
204
+ "epoch": 15.0,
205
+ "learning_rate": 0.00020833333333333332,
206
+ "loss": 0.3172,
207
+ "step": 120
208
+ },
209
+ {
210
+ "epoch": 15.0,
211
+ "eval_accuracy": 0.794392523364486,
212
+ "eval_loss": 0.5953131914138794,
213
+ "eval_runtime": 1.7204,
214
+ "eval_samples_per_second": 62.195,
215
+ "eval_steps_per_second": 4.069,
216
+ "step": 120
217
+ },
218
+ {
219
+ "epoch": 16.0,
220
+ "eval_accuracy": 0.7383177570093458,
221
+ "eval_loss": 0.5903685092926025,
222
+ "eval_runtime": 1.6279,
223
+ "eval_samples_per_second": 65.729,
224
+ "eval_steps_per_second": 4.3,
225
+ "step": 128
226
+ },
227
+ {
228
+ "epoch": 16.25,
229
+ "learning_rate": 0.00019791666666666663,
230
+ "loss": 0.365,
231
+ "step": 130
232
+ },
233
+ {
234
+ "epoch": 17.0,
235
+ "eval_accuracy": 0.8411214953271028,
236
+ "eval_loss": 0.42125028371810913,
237
+ "eval_runtime": 1.8254,
238
+ "eval_samples_per_second": 58.616,
239
+ "eval_steps_per_second": 3.835,
240
+ "step": 136
241
+ },
242
+ {
243
+ "epoch": 17.5,
244
+ "learning_rate": 0.00018749999999999998,
245
+ "loss": 0.279,
246
+ "step": 140
247
+ },
248
+ {
249
+ "epoch": 18.0,
250
+ "eval_accuracy": 0.8037383177570093,
251
+ "eval_loss": 0.4571745693683624,
252
+ "eval_runtime": 1.6663,
253
+ "eval_samples_per_second": 64.213,
254
+ "eval_steps_per_second": 4.201,
255
+ "step": 144
256
+ },
257
+ {
258
+ "epoch": 18.75,
259
+ "learning_rate": 0.00017708333333333332,
260
+ "loss": 0.3092,
261
+ "step": 150
262
+ },
263
+ {
264
+ "epoch": 19.0,
265
+ "eval_accuracy": 0.8130841121495327,
266
+ "eval_loss": 0.418056845664978,
267
+ "eval_runtime": 1.5444,
268
+ "eval_samples_per_second": 69.284,
269
+ "eval_steps_per_second": 4.533,
270
+ "step": 152
271
+ },
272
+ {
273
+ "epoch": 20.0,
274
+ "learning_rate": 0.00016666666666666666,
275
+ "loss": 0.2667,
276
+ "step": 160
277
+ },
278
+ {
279
+ "epoch": 20.0,
280
+ "eval_accuracy": 0.822429906542056,
281
+ "eval_loss": 0.4117071330547333,
282
+ "eval_runtime": 1.6009,
283
+ "eval_samples_per_second": 66.839,
284
+ "eval_steps_per_second": 4.373,
285
+ "step": 160
286
+ },
287
+ {
288
+ "epoch": 21.0,
289
+ "eval_accuracy": 0.8037383177570093,
290
+ "eval_loss": 0.43494537472724915,
291
+ "eval_runtime": 1.6069,
292
+ "eval_samples_per_second": 66.589,
293
+ "eval_steps_per_second": 4.356,
294
+ "step": 168
295
+ },
296
+ {
297
+ "epoch": 21.25,
298
+ "learning_rate": 0.00015625,
299
+ "loss": 0.261,
300
+ "step": 170
301
+ },
302
+ {
303
+ "epoch": 22.0,
304
+ "eval_accuracy": 0.8037383177570093,
305
+ "eval_loss": 0.41846951842308044,
306
+ "eval_runtime": 1.5389,
307
+ "eval_samples_per_second": 69.532,
308
+ "eval_steps_per_second": 4.549,
309
+ "step": 176
310
+ },
311
+ {
312
+ "epoch": 22.5,
313
+ "learning_rate": 0.00014583333333333332,
314
+ "loss": 0.2638,
315
+ "step": 180
316
+ },
317
+ {
318
+ "epoch": 23.0,
319
+ "eval_accuracy": 0.8130841121495327,
320
+ "eval_loss": 0.39887818694114685,
321
+ "eval_runtime": 1.6024,
322
+ "eval_samples_per_second": 66.776,
323
+ "eval_steps_per_second": 4.369,
324
+ "step": 184
325
+ },
326
+ {
327
+ "epoch": 23.75,
328
+ "learning_rate": 0.00013541666666666666,
329
+ "loss": 0.2269,
330
+ "step": 190
331
+ },
332
+ {
333
+ "epoch": 24.0,
334
+ "eval_accuracy": 0.8317757009345794,
335
+ "eval_loss": 0.39713814854621887,
336
+ "eval_runtime": 1.6453,
337
+ "eval_samples_per_second": 65.035,
338
+ "eval_steps_per_second": 4.255,
339
+ "step": 192
340
+ },
341
+ {
342
+ "epoch": 25.0,
343
+ "learning_rate": 0.000125,
344
+ "loss": 0.2431,
345
+ "step": 200
346
+ },
347
+ {
348
+ "epoch": 25.0,
349
+ "eval_accuracy": 0.8037383177570093,
350
+ "eval_loss": 0.47835975885391235,
351
+ "eval_runtime": 1.6169,
352
+ "eval_samples_per_second": 66.177,
353
+ "eval_steps_per_second": 4.329,
354
+ "step": 200
355
+ },
356
+ {
357
+ "epoch": 26.0,
358
+ "eval_accuracy": 0.8317757009345794,
359
+ "eval_loss": 0.37627077102661133,
360
+ "eval_runtime": 1.5524,
361
+ "eval_samples_per_second": 68.927,
362
+ "eval_steps_per_second": 4.509,
363
+ "step": 208
364
+ },
365
+ {
366
+ "epoch": 26.25,
367
+ "learning_rate": 0.00011458333333333332,
368
+ "loss": 0.2111,
369
+ "step": 210
370
+ },
371
+ {
372
+ "epoch": 27.0,
373
+ "eval_accuracy": 0.8411214953271028,
374
+ "eval_loss": 0.4087802469730377,
375
+ "eval_runtime": 1.6499,
376
+ "eval_samples_per_second": 64.853,
377
+ "eval_steps_per_second": 4.243,
378
+ "step": 216
379
+ },
380
+ {
381
+ "epoch": 27.5,
382
+ "learning_rate": 0.00010416666666666666,
383
+ "loss": 0.2087,
384
+ "step": 220
385
+ },
386
+ {
387
+ "epoch": 28.0,
388
+ "eval_accuracy": 0.8317757009345794,
389
+ "eval_loss": 0.4023880064487457,
390
+ "eval_runtime": 1.6064,
391
+ "eval_samples_per_second": 66.609,
392
+ "eval_steps_per_second": 4.358,
393
+ "step": 224
394
+ },
395
+ {
396
+ "epoch": 28.75,
397
+ "learning_rate": 9.374999999999999e-05,
398
+ "loss": 0.1645,
399
+ "step": 230
400
+ },
401
+ {
402
+ "epoch": 29.0,
403
+ "eval_accuracy": 0.8317757009345794,
404
+ "eval_loss": 0.41612958908081055,
405
+ "eval_runtime": 1.6264,
406
+ "eval_samples_per_second": 65.79,
407
+ "eval_steps_per_second": 4.304,
408
+ "step": 232
409
+ },
410
+ {
411
+ "epoch": 30.0,
412
+ "learning_rate": 8.333333333333333e-05,
413
+ "loss": 0.2137,
414
+ "step": 240
415
+ },
416
+ {
417
+ "epoch": 30.0,
418
+ "eval_accuracy": 0.8130841121495327,
419
+ "eval_loss": 0.4128251075744629,
420
+ "eval_runtime": 1.8385,
421
+ "eval_samples_per_second": 58.201,
422
+ "eval_steps_per_second": 3.808,
423
+ "step": 240
424
+ },
425
+ {
426
+ "epoch": 31.0,
427
+ "eval_accuracy": 0.8411214953271028,
428
+ "eval_loss": 0.40039822459220886,
429
+ "eval_runtime": 1.5934,
430
+ "eval_samples_per_second": 67.154,
431
+ "eval_steps_per_second": 4.393,
432
+ "step": 248
433
+ },
434
+ {
435
+ "epoch": 31.25,
436
+ "learning_rate": 7.291666666666666e-05,
437
+ "loss": 0.2207,
438
+ "step": 250
439
+ },
440
+ {
441
+ "epoch": 32.0,
442
+ "eval_accuracy": 0.822429906542056,
443
+ "eval_loss": 0.4205995798110962,
444
+ "eval_runtime": 1.5789,
445
+ "eval_samples_per_second": 67.769,
446
+ "eval_steps_per_second": 4.434,
447
+ "step": 256
448
+ },
449
+ {
450
+ "epoch": 32.5,
451
+ "learning_rate": 6.25e-05,
452
+ "loss": 0.1544,
453
+ "step": 260
454
+ },
455
+ {
456
+ "epoch": 33.0,
457
+ "eval_accuracy": 0.8504672897196262,
458
+ "eval_loss": 0.3622354567050934,
459
+ "eval_runtime": 1.6454,
460
+ "eval_samples_per_second": 65.029,
461
+ "eval_steps_per_second": 4.254,
462
+ "step": 264
463
+ },
464
+ {
465
+ "epoch": 33.75,
466
+ "learning_rate": 5.208333333333333e-05,
467
+ "loss": 0.197,
468
+ "step": 270
469
+ },
470
+ {
471
+ "epoch": 34.0,
472
+ "eval_accuracy": 0.8411214953271028,
473
+ "eval_loss": 0.43561315536499023,
474
+ "eval_runtime": 1.6009,
475
+ "eval_samples_per_second": 66.838,
476
+ "eval_steps_per_second": 4.373,
477
+ "step": 272
478
+ },
479
+ {
480
+ "epoch": 35.0,
481
+ "learning_rate": 4.1666666666666665e-05,
482
+ "loss": 0.2168,
483
+ "step": 280
484
+ },
485
+ {
486
+ "epoch": 35.0,
487
+ "eval_accuracy": 0.8317757009345794,
488
+ "eval_loss": 0.4066832363605499,
489
+ "eval_runtime": 1.5799,
490
+ "eval_samples_per_second": 67.727,
491
+ "eval_steps_per_second": 4.431,
492
+ "step": 280
493
+ },
494
+ {
495
+ "epoch": 36.0,
496
+ "eval_accuracy": 0.822429906542056,
497
+ "eval_loss": 0.3809307813644409,
498
+ "eval_runtime": 1.6129,
499
+ "eval_samples_per_second": 66.341,
500
+ "eval_steps_per_second": 4.34,
501
+ "step": 288
502
+ },
503
+ {
504
+ "epoch": 36.25,
505
+ "learning_rate": 3.125e-05,
506
+ "loss": 0.1631,
507
+ "step": 290
508
+ },
509
+ {
510
+ "epoch": 37.0,
511
+ "eval_accuracy": 0.8411214953271028,
512
+ "eval_loss": 0.38649317622184753,
513
+ "eval_runtime": 1.6369,
514
+ "eval_samples_per_second": 65.368,
515
+ "eval_steps_per_second": 4.276,
516
+ "step": 296
517
+ },
518
+ {
519
+ "epoch": 37.5,
520
+ "learning_rate": 2.0833333333333333e-05,
521
+ "loss": 0.1913,
522
+ "step": 300
523
+ },
524
+ {
525
+ "epoch": 38.0,
526
+ "eval_accuracy": 0.8317757009345794,
527
+ "eval_loss": 0.4007885158061981,
528
+ "eval_runtime": 1.6819,
529
+ "eval_samples_per_second": 63.618,
530
+ "eval_steps_per_second": 4.162,
531
+ "step": 304
532
+ },
533
+ {
534
+ "epoch": 38.75,
535
+ "learning_rate": 1.0416666666666666e-05,
536
+ "loss": 0.1595,
537
+ "step": 310
538
+ },
539
+ {
540
+ "epoch": 39.0,
541
+ "eval_accuracy": 0.8317757009345794,
542
+ "eval_loss": 0.37519946694374084,
543
+ "eval_runtime": 1.6039,
544
+ "eval_samples_per_second": 66.713,
545
+ "eval_steps_per_second": 4.364,
546
+ "step": 312
547
+ },
548
+ {
549
+ "epoch": 40.0,
550
+ "learning_rate": 0.0,
551
+ "loss": 0.1694,
552
+ "step": 320
553
+ },
554
+ {
555
+ "epoch": 40.0,
556
+ "eval_accuracy": 0.8598130841121495,
557
+ "eval_loss": 0.4150024354457855,
558
+ "eval_runtime": 1.5744,
559
+ "eval_samples_per_second": 67.964,
560
+ "eval_steps_per_second": 4.446,
561
+ "step": 320
562
+ },
563
+ {
564
+ "epoch": 40.0,
565
+ "step": 320,
566
+ "total_flos": 5.458940713304064e+16,
567
+ "train_loss": 0.32927754148840904,
568
+ "train_runtime": 444.0356,
569
+ "train_samples_per_second": 44.861,
570
+ "train_steps_per_second": 0.721
571
+ }
572
+ ],
573
+ "logging_steps": 10,
574
+ "max_steps": 320,
575
+ "num_input_tokens_seen": 0,
576
+ "num_train_epochs": 40,
577
+ "save_steps": 500,
578
+ "total_flos": 5.458940713304064e+16,
579
+ "train_batch_size": 16,
580
+ "trial_name": null,
581
+ "trial_params": null
582
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba32acc97f77e6a254b71266d8deeaf8d921039deb3458d189a260ae937fb73
3
+ size 4728