End of training
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- preprocessor_config.json +28 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- train_results.json +8 -0
- trainer_state.json +202 -0
- vocab.txt +0 -0
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 60.0,
|
3 |
+
"eval_accuracy": 0.06694191635136518,
|
4 |
+
"eval_loss": 3.553868532180786,
|
5 |
+
"eval_runtime": 50.3598,
|
6 |
+
"eval_samples_per_second": 141.224,
|
7 |
+
"eval_steps_per_second": 7.069,
|
8 |
+
"total_flos": 2.541067006369997e+18,
|
9 |
+
"train_loss": 1.3772225892310048,
|
10 |
+
"train_runtime": 58902.9646,
|
11 |
+
"train_samples_per_second": 54.543,
|
12 |
+
"train_steps_per_second": 0.26
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 60.0,
|
3 |
+
"eval_accuracy": 0.06694191635136518,
|
4 |
+
"eval_loss": 3.553868532180786,
|
5 |
+
"eval_runtime": 50.3598,
|
6 |
+
"eval_samples_per_second": 141.224,
|
7 |
+
"eval_steps_per_second": 7.069
|
8 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": false,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"image_mean": [
|
12 |
+
0.48145466,
|
13 |
+
0.4578275,
|
14 |
+
0.40821073
|
15 |
+
],
|
16 |
+
"image_processor_type": "ChineseCLIPImageProcessor",
|
17 |
+
"image_std": [
|
18 |
+
0.26862954,
|
19 |
+
0.26130258,
|
20 |
+
0.27577711
|
21 |
+
],
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"height": 224,
|
26 |
+
"width": 224
|
27 |
+
}
|
28 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 60.0,
|
3 |
+
"total_flos": 2.541067006369997e+18,
|
4 |
+
"train_loss": 1.3772225892310048,
|
5 |
+
"train_runtime": 58902.9646,
|
6 |
+
"train_samples_per_second": 54.543,
|
7 |
+
"train_steps_per_second": 0.26
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 60.0,
|
5 |
+
"eval_steps": 1530,
|
6 |
+
"global_step": 15300,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 6.0,
|
13 |
+
"grad_norm": 1.6894794702529907,
|
14 |
+
"learning_rate": 9.000653594771243e-06,
|
15 |
+
"loss": 1.5814,
|
16 |
+
"step": 1530
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 6.0,
|
20 |
+
"eval_accuracy": 0.07255343082114736,
|
21 |
+
"eval_loss": 3.025679588317871,
|
22 |
+
"eval_runtime": 50.7219,
|
23 |
+
"eval_samples_per_second": 140.216,
|
24 |
+
"eval_steps_per_second": 7.019,
|
25 |
+
"step": 1530
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 12.0,
|
29 |
+
"grad_norm": 5.62229061126709,
|
30 |
+
"learning_rate": 8.001307189542484e-06,
|
31 |
+
"loss": 1.4807,
|
32 |
+
"step": 3060
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 12.0,
|
36 |
+
"eval_accuracy": 0.07121766029246344,
|
37 |
+
"eval_loss": 3.267681121826172,
|
38 |
+
"eval_runtime": 50.6404,
|
39 |
+
"eval_samples_per_second": 140.441,
|
40 |
+
"eval_steps_per_second": 7.03,
|
41 |
+
"step": 3060
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 18.0,
|
45 |
+
"grad_norm": 1.747545599937439,
|
46 |
+
"learning_rate": 7.001960784313726e-06,
|
47 |
+
"loss": 1.4075,
|
48 |
+
"step": 4590
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 18.0,
|
52 |
+
"eval_accuracy": 0.07025684289463817,
|
53 |
+
"eval_loss": 3.333199977874756,
|
54 |
+
"eval_runtime": 50.6734,
|
55 |
+
"eval_samples_per_second": 140.35,
|
56 |
+
"eval_steps_per_second": 7.025,
|
57 |
+
"step": 4590
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 24.0,
|
61 |
+
"grad_norm": 3.056417465209961,
|
62 |
+
"learning_rate": 6.002614379084968e-06,
|
63 |
+
"loss": 1.3618,
|
64 |
+
"step": 6120
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 24.0,
|
68 |
+
"eval_accuracy": 0.06924915635545557,
|
69 |
+
"eval_loss": 3.249127149581909,
|
70 |
+
"eval_runtime": 50.8822,
|
71 |
+
"eval_samples_per_second": 139.774,
|
72 |
+
"eval_steps_per_second": 6.997,
|
73 |
+
"step": 6120
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 30.0,
|
77 |
+
"grad_norm": 5.729462146759033,
|
78 |
+
"learning_rate": 5.002614379084968e-06,
|
79 |
+
"loss": 1.3396,
|
80 |
+
"step": 7650
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 30.0,
|
84 |
+
"eval_accuracy": 0.06903824521934758,
|
85 |
+
"eval_loss": 3.3755784034729004,
|
86 |
+
"eval_runtime": 50.6692,
|
87 |
+
"eval_samples_per_second": 140.361,
|
88 |
+
"eval_steps_per_second": 7.026,
|
89 |
+
"step": 7650
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 36.0,
|
93 |
+
"grad_norm": 3.0638558864593506,
|
94 |
+
"learning_rate": 4.00326797385621e-06,
|
95 |
+
"loss": 1.3298,
|
96 |
+
"step": 9180
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 36.0,
|
100 |
+
"eval_accuracy": 0.06781964754405699,
|
101 |
+
"eval_loss": 3.5385994911193848,
|
102 |
+
"eval_runtime": 50.6377,
|
103 |
+
"eval_samples_per_second": 140.449,
|
104 |
+
"eval_steps_per_second": 7.03,
|
105 |
+
"step": 9180
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 42.0,
|
109 |
+
"grad_norm": 1.3296822309494019,
|
110 |
+
"learning_rate": 3.0039215686274516e-06,
|
111 |
+
"loss": 1.324,
|
112 |
+
"step": 10710
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 42.0,
|
116 |
+
"eval_accuracy": 0.06745139000482082,
|
117 |
+
"eval_loss": 3.524540901184082,
|
118 |
+
"eval_runtime": 50.7535,
|
119 |
+
"eval_samples_per_second": 140.128,
|
120 |
+
"eval_steps_per_second": 7.014,
|
121 |
+
"step": 10710
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 48.0,
|
125 |
+
"grad_norm": 0.8740301132202148,
|
126 |
+
"learning_rate": 2.004575163398693e-06,
|
127 |
+
"loss": 1.3177,
|
128 |
+
"step": 12240
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 48.0,
|
132 |
+
"eval_accuracy": 0.06706974128233971,
|
133 |
+
"eval_loss": 3.513636827468872,
|
134 |
+
"eval_runtime": 50.7526,
|
135 |
+
"eval_samples_per_second": 140.131,
|
136 |
+
"eval_steps_per_second": 7.014,
|
137 |
+
"step": 12240
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 54.0,
|
141 |
+
"grad_norm": 0.6789987683296204,
|
142 |
+
"learning_rate": 1.004575163398693e-06,
|
143 |
+
"loss": 1.3181,
|
144 |
+
"step": 13770
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 54.0,
|
148 |
+
"eval_accuracy": 0.0669135108111486,
|
149 |
+
"eval_loss": 3.4984188079833984,
|
150 |
+
"eval_runtime": 50.596,
|
151 |
+
"eval_samples_per_second": 140.564,
|
152 |
+
"eval_steps_per_second": 7.036,
|
153 |
+
"step": 13770
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 60.0,
|
157 |
+
"grad_norm": 0.4347877502441406,
|
158 |
+
"learning_rate": 5.2287581699346415e-09,
|
159 |
+
"loss": 1.3117,
|
160 |
+
"step": 15300
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 60.0,
|
164 |
+
"eval_accuracy": 0.06692913385826772,
|
165 |
+
"eval_loss": 3.553868532180786,
|
166 |
+
"eval_runtime": 50.6817,
|
167 |
+
"eval_samples_per_second": 140.327,
|
168 |
+
"eval_steps_per_second": 7.024,
|
169 |
+
"step": 15300
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 60.0,
|
173 |
+
"step": 15300,
|
174 |
+
"total_flos": 2.541067006369997e+18,
|
175 |
+
"train_loss": 1.3772225892310048,
|
176 |
+
"train_runtime": 58902.9646,
|
177 |
+
"train_samples_per_second": 54.543,
|
178 |
+
"train_steps_per_second": 0.26
|
179 |
+
}
|
180 |
+
],
|
181 |
+
"logging_steps": 1530,
|
182 |
+
"max_steps": 15300,
|
183 |
+
"num_input_tokens_seen": 0,
|
184 |
+
"num_train_epochs": 60,
|
185 |
+
"save_steps": 500,
|
186 |
+
"stateful_callbacks": {
|
187 |
+
"TrainerControl": {
|
188 |
+
"args": {
|
189 |
+
"should_epoch_stop": false,
|
190 |
+
"should_evaluate": false,
|
191 |
+
"should_log": false,
|
192 |
+
"should_save": true,
|
193 |
+
"should_training_stop": true
|
194 |
+
},
|
195 |
+
"attributes": {}
|
196 |
+
}
|
197 |
+
},
|
198 |
+
"total_flos": 2.541067006369997e+18,
|
199 |
+
"train_batch_size": 15,
|
200 |
+
"trial_name": null,
|
201 |
+
"trial_params": null
|
202 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|