Hugging Face's logo

adams-story
/
dalle3-clip-filter

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
adams-story commited on
Commit
a17012a
•
1 Parent(s): b17992d

Model save

Browse files
Files changed (23) hide show
  1. README.md +52 -0
  2. adapter_config.json +26 -0
  3. adapter_model.safetensors +3 -0
  4. all_results.json +7 -0
  5. merges.txt +0 -0
  6. preprocessor_config.json +28 -0
  7. runs/Nov18_20-14-24_maker/events.out.tfevents.1700363764.maker.3236119.0 +3 -0
  8. runs/Nov18_20-19-45_maker/events.out.tfevents.1700364060.maker.3237603.0 +3 -0
  9. runs/Nov30_15-27-51_maker/events.out.tfevents.1701383370.maker.1466321.0 +3 -0
  10. runs/Nov30_15-30-03_maker/events.out.tfevents.1701383474.maker.1466641.0 +3 -0
  11. runs/Nov30_15-33-57_maker/events.out.tfevents.1701383697.maker.1466938.0 +3 -0
  12. runs/Nov30_15-37-21_maker/events.out.tfevents.1701383909.maker.1467443.0 +3 -0
  13. runs/Nov30_15-39-25_maker/events.out.tfevents.1701384030.maker.1467744.0 +3 -0
  14. runs/Nov30_15-42-46_maker/events.out.tfevents.1701384230.maker.1468067.0 +3 -0
  15. runs/Nov30_15-45-19_maker/events.out.tfevents.1701384391.maker.1468514.0 +3 -0
  16. runs/Nov30_15-50-24_maker/events.out.tfevents.1701384697.maker.1469300.0 +3 -0
  17. special_tokens_map.json +24 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +30 -0
  20. train_results.json +7 -0
  21. trainer_state.json +1036 -0
  22. training_args.bin +3 -0
  23. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: openai/clip-vit-large-patch14-336
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: out
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # out
14
+
15
+ This model is a fine-tuned version of [openai/clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 0.0003
35
+ - train_batch_size: 32
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: constant
40
+ - lr_scheduler_warmup_steps: 5
41
+ - num_epochs: 1.0
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.35.2
50
+ - Pytorch 2.0.1+cu117
51
+ - Datasets 2.15.1.dev0
52
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "CLIPModel",
5
+ "parent_library": "transformers.models.clip.modeling_clip"
6
+ },
7
+ "base_model_name_or_path": "openai/clip-vit-large-patch14-336",
8
+ "bias": "none",
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "lora_alpha": 8,
15
+ "lora_dropout": 0.0,
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": null
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16ee9da330b59e779e2c50df56b8508906e06b9a15ae637bffa1a0f6706b7c0
3
+ size 4346272
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.04601551576511304,
4
+ "train_runtime": 391.6583,
5
+ "train_samples_per_second": 27.491,
6
+ "train_steps_per_second": 0.86
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
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": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ },
27
+ "use_square_size": false
28
+ }
runs/Nov18_20-14-24_maker/events.out.tfevents.1700363764.maker.3236119.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95dfc1868a8148638d48534e081e314e386fc2e9028fb98640b0951d0e9bee7d
3
+ size 14426
runs/Nov18_20-19-45_maker/events.out.tfevents.1700364060.maker.3237603.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:214f56c3cec1df8ea03977ffaf4b33048fc3865a703725cf0533b54c01a09032
3
+ size 30527
runs/Nov30_15-27-51_maker/events.out.tfevents.1701383370.maker.1466321.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d226eced129e5973202d3063ffbc96cb461b4a26d807dda49325297d4295b5
3
+ size 4274
runs/Nov30_15-30-03_maker/events.out.tfevents.1701383474.maker.1466641.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57048e9b352839febf18444d398485fb50660c4206f0a5829f48dccf8ab98530
3
+ size 4274
runs/Nov30_15-33-57_maker/events.out.tfevents.1701383697.maker.1466938.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f325988f5282a12b819bb7306da4a634ad10770ddc8ce92ffc22df85fd7ee4f
3
+ size 4279
runs/Nov30_15-37-21_maker/events.out.tfevents.1701383909.maker.1467443.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9097107013ebd09cd7291f214c64ce9cde9fc225d87eb6e798409bf4c574b324
3
+ size 4279
runs/Nov30_15-39-25_maker/events.out.tfevents.1701384030.maker.1467744.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00efc62985dad85928f452621182d73e3d2973ec98143212019423c3810b2a3
3
+ size 4280
runs/Nov30_15-42-46_maker/events.out.tfevents.1701384230.maker.1468067.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae33f56a176772d24625c3d70aea6f524bd77456ddf05e28d6b392f1c72fbdb
3
+ size 4279
runs/Nov30_15-45-19_maker/events.out.tfevents.1701384391.maker.1468514.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebedb3a7b644a5d71572269fdff5d8790d7713271430c1f63162020c1ff2714f
3
+ size 16138
runs/Nov30_15-50-24_maker/events.out.tfevents.1701384697.maker.1469300.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d3d2f11d74780349cff31f56409145bf7dfb4da89c842865f48e3a66a404ba
3
+ size 57162
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.04601551576511304,
4
+ "train_runtime": 391.6583,
5
+ "train_samples_per_second": 27.491,
6
+ "train_steps_per_second": 0.86
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,1036 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 337,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.0003,
14
+ "loss": 0.1866,
15
+ "step": 2
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.0003,
20
+ "loss": 0.053,
21
+ "step": 4
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 0.0003,
26
+ "loss": 0.0263,
27
+ "step": 6
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 0.0003,
32
+ "loss": 0.1589,
33
+ "step": 8
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 0.0003,
38
+ "loss": 0.0704,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 0.0003,
44
+ "loss": 0.0318,
45
+ "step": 12
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 0.0003,
50
+ "loss": 0.0791,
51
+ "step": 14
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 0.0003,
56
+ "loss": 0.0714,
57
+ "step": 16
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 0.0003,
62
+ "loss": 0.0499,
63
+ "step": 18
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.0003,
68
+ "loss": 0.0049,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 0.0003,
74
+ "loss": 0.0506,
75
+ "step": 22
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 0.0003,
80
+ "loss": 0.0434,
81
+ "step": 24
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "learning_rate": 0.0003,
86
+ "loss": 0.1014,
87
+ "step": 26
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 0.0003,
92
+ "loss": 0.0529,
93
+ "step": 28
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 0.0003,
98
+ "loss": 0.0705,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 0.0003,
104
+ "loss": 0.0224,
105
+ "step": 32
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 0.0003,
110
+ "loss": 0.049,
111
+ "step": 34
112
+ },
113
+ {
114
+ "epoch": 0.11,
115
+ "learning_rate": 0.0003,
116
+ "loss": 0.0215,
117
+ "step": 36
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 0.0003,
122
+ "loss": 0.0754,
123
+ "step": 38
124
+ },
125
+ {
126
+ "epoch": 0.12,
127
+ "learning_rate": 0.0003,
128
+ "loss": 0.0389,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 0.0003,
134
+ "loss": 0.0603,
135
+ "step": 42
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 0.0003,
140
+ "loss": 0.0015,
141
+ "step": 44
142
+ },
143
+ {
144
+ "epoch": 0.14,
145
+ "learning_rate": 0.0003,
146
+ "loss": 0.0278,
147
+ "step": 46
148
+ },
149
+ {
150
+ "epoch": 0.14,
151
+ "learning_rate": 0.0003,
152
+ "loss": 0.0276,
153
+ "step": 48
154
+ },
155
+ {
156
+ "epoch": 0.15,
157
+ "learning_rate": 0.0003,
158
+ "loss": 0.0755,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 0.0003,
164
+ "loss": 0.1843,
165
+ "step": 52
166
+ },
167
+ {
168
+ "epoch": 0.16,
169
+ "learning_rate": 0.0003,
170
+ "loss": 0.0774,
171
+ "step": 54
172
+ },
173
+ {
174
+ "epoch": 0.17,
175
+ "learning_rate": 0.0003,
176
+ "loss": 0.0199,
177
+ "step": 56
178
+ },
179
+ {
180
+ "epoch": 0.17,
181
+ "learning_rate": 0.0003,
182
+ "loss": 0.0398,
183
+ "step": 58
184
+ },
185
+ {
186
+ "epoch": 0.18,
187
+ "learning_rate": 0.0003,
188
+ "loss": 0.0516,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.18,
193
+ "learning_rate": 0.0003,
194
+ "loss": 0.0978,
195
+ "step": 62
196
+ },
197
+ {
198
+ "epoch": 0.19,
199
+ "learning_rate": 0.0003,
200
+ "loss": 0.093,
201
+ "step": 64
202
+ },
203
+ {
204
+ "epoch": 0.2,
205
+ "learning_rate": 0.0003,
206
+ "loss": 0.1345,
207
+ "step": 66
208
+ },
209
+ {
210
+ "epoch": 0.2,
211
+ "learning_rate": 0.0003,
212
+ "loss": 0.0659,
213
+ "step": 68
214
+ },
215
+ {
216
+ "epoch": 0.21,
217
+ "learning_rate": 0.0003,
218
+ "loss": 0.0441,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.21,
223
+ "learning_rate": 0.0003,
224
+ "loss": 0.0187,
225
+ "step": 72
226
+ },
227
+ {
228
+ "epoch": 0.22,
229
+ "learning_rate": 0.0003,
230
+ "loss": 0.031,
231
+ "step": 74
232
+ },
233
+ {
234
+ "epoch": 0.23,
235
+ "learning_rate": 0.0003,
236
+ "loss": 0.0327,
237
+ "step": 76
238
+ },
239
+ {
240
+ "epoch": 0.23,
241
+ "learning_rate": 0.0003,
242
+ "loss": 0.0611,
243
+ "step": 78
244
+ },
245
+ {
246
+ "epoch": 0.24,
247
+ "learning_rate": 0.0003,
248
+ "loss": 0.0082,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.24,
253
+ "learning_rate": 0.0003,
254
+ "loss": 0.0121,
255
+ "step": 82
256
+ },
257
+ {
258
+ "epoch": 0.25,
259
+ "learning_rate": 0.0003,
260
+ "loss": 0.0487,
261
+ "step": 84
262
+ },
263
+ {
264
+ "epoch": 0.26,
265
+ "learning_rate": 0.0003,
266
+ "loss": 0.079,
267
+ "step": 86
268
+ },
269
+ {
270
+ "epoch": 0.26,
271
+ "learning_rate": 0.0003,
272
+ "loss": 0.0936,
273
+ "step": 88
274
+ },
275
+ {
276
+ "epoch": 0.27,
277
+ "learning_rate": 0.0003,
278
+ "loss": 0.0177,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.27,
283
+ "learning_rate": 0.0003,
284
+ "loss": 0.0494,
285
+ "step": 92
286
+ },
287
+ {
288
+ "epoch": 0.28,
289
+ "learning_rate": 0.0003,
290
+ "loss": 0.0457,
291
+ "step": 94
292
+ },
293
+ {
294
+ "epoch": 0.28,
295
+ "learning_rate": 0.0003,
296
+ "loss": 0.0279,
297
+ "step": 96
298
+ },
299
+ {
300
+ "epoch": 0.29,
301
+ "learning_rate": 0.0003,
302
+ "loss": 0.0402,
303
+ "step": 98
304
+ },
305
+ {
306
+ "epoch": 0.3,
307
+ "learning_rate": 0.0003,
308
+ "loss": 0.0064,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.3,
313
+ "learning_rate": 0.0003,
314
+ "loss": 0.1038,
315
+ "step": 102
316
+ },
317
+ {
318
+ "epoch": 0.31,
319
+ "learning_rate": 0.0003,
320
+ "loss": 0.0054,
321
+ "step": 104
322
+ },
323
+ {
324
+ "epoch": 0.31,
325
+ "learning_rate": 0.0003,
326
+ "loss": 0.0111,
327
+ "step": 106
328
+ },
329
+ {
330
+ "epoch": 0.32,
331
+ "learning_rate": 0.0003,
332
+ "loss": 0.0421,
333
+ "step": 108
334
+ },
335
+ {
336
+ "epoch": 0.33,
337
+ "learning_rate": 0.0003,
338
+ "loss": 0.0517,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.33,
343
+ "learning_rate": 0.0003,
344
+ "loss": 0.0842,
345
+ "step": 112
346
+ },
347
+ {
348
+ "epoch": 0.34,
349
+ "learning_rate": 0.0003,
350
+ "loss": 0.0411,
351
+ "step": 114
352
+ },
353
+ {
354
+ "epoch": 0.34,
355
+ "learning_rate": 0.0003,
356
+ "loss": 0.0025,
357
+ "step": 116
358
+ },
359
+ {
360
+ "epoch": 0.35,
361
+ "learning_rate": 0.0003,
362
+ "loss": 0.0255,
363
+ "step": 118
364
+ },
365
+ {
366
+ "epoch": 0.36,
367
+ "learning_rate": 0.0003,
368
+ "loss": 0.0098,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.36,
373
+ "learning_rate": 0.0003,
374
+ "loss": 0.0699,
375
+ "step": 122
376
+ },
377
+ {
378
+ "epoch": 0.37,
379
+ "learning_rate": 0.0003,
380
+ "loss": 0.019,
381
+ "step": 124
382
+ },
383
+ {
384
+ "epoch": 0.37,
385
+ "learning_rate": 0.0003,
386
+ "loss": 0.0487,
387
+ "step": 126
388
+ },
389
+ {
390
+ "epoch": 0.38,
391
+ "learning_rate": 0.0003,
392
+ "loss": 0.007,
393
+ "step": 128
394
+ },
395
+ {
396
+ "epoch": 0.39,
397
+ "learning_rate": 0.0003,
398
+ "loss": 0.013,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.39,
403
+ "learning_rate": 0.0003,
404
+ "loss": 0.0349,
405
+ "step": 132
406
+ },
407
+ {
408
+ "epoch": 0.4,
409
+ "learning_rate": 0.0003,
410
+ "loss": 0.0315,
411
+ "step": 134
412
+ },
413
+ {
414
+ "epoch": 0.4,
415
+ "learning_rate": 0.0003,
416
+ "loss": 0.0174,
417
+ "step": 136
418
+ },
419
+ {
420
+ "epoch": 0.41,
421
+ "learning_rate": 0.0003,
422
+ "loss": 0.0006,
423
+ "step": 138
424
+ },
425
+ {
426
+ "epoch": 0.42,
427
+ "learning_rate": 0.0003,
428
+ "loss": 0.0017,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 0.42,
433
+ "learning_rate": 0.0003,
434
+ "loss": 0.0869,
435
+ "step": 142
436
+ },
437
+ {
438
+ "epoch": 0.43,
439
+ "learning_rate": 0.0003,
440
+ "loss": 0.0286,
441
+ "step": 144
442
+ },
443
+ {
444
+ "epoch": 0.43,
445
+ "learning_rate": 0.0003,
446
+ "loss": 0.0161,
447
+ "step": 146
448
+ },
449
+ {
450
+ "epoch": 0.44,
451
+ "learning_rate": 0.0003,
452
+ "loss": 0.2254,
453
+ "step": 148
454
+ },
455
+ {
456
+ "epoch": 0.45,
457
+ "learning_rate": 0.0003,
458
+ "loss": 0.0103,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 0.45,
463
+ "learning_rate": 0.0003,
464
+ "loss": 0.0099,
465
+ "step": 152
466
+ },
467
+ {
468
+ "epoch": 0.46,
469
+ "learning_rate": 0.0003,
470
+ "loss": 0.0245,
471
+ "step": 154
472
+ },
473
+ {
474
+ "epoch": 0.46,
475
+ "learning_rate": 0.0003,
476
+ "loss": 0.0286,
477
+ "step": 156
478
+ },
479
+ {
480
+ "epoch": 0.47,
481
+ "learning_rate": 0.0003,
482
+ "loss": 0.0743,
483
+ "step": 158
484
+ },
485
+ {
486
+ "epoch": 0.47,
487
+ "learning_rate": 0.0003,
488
+ "loss": 0.0021,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 0.48,
493
+ "learning_rate": 0.0003,
494
+ "loss": 0.0262,
495
+ "step": 162
496
+ },
497
+ {
498
+ "epoch": 0.49,
499
+ "learning_rate": 0.0003,
500
+ "loss": 0.0121,
501
+ "step": 164
502
+ },
503
+ {
504
+ "epoch": 0.49,
505
+ "learning_rate": 0.0003,
506
+ "loss": 0.2051,
507
+ "step": 166
508
+ },
509
+ {
510
+ "epoch": 0.5,
511
+ "learning_rate": 0.0003,
512
+ "loss": 0.0168,
513
+ "step": 168
514
+ },
515
+ {
516
+ "epoch": 0.5,
517
+ "learning_rate": 0.0003,
518
+ "loss": 0.0036,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 0.51,
523
+ "learning_rate": 0.0003,
524
+ "loss": 0.0387,
525
+ "step": 172
526
+ },
527
+ {
528
+ "epoch": 0.52,
529
+ "learning_rate": 0.0003,
530
+ "loss": 0.0997,
531
+ "step": 174
532
+ },
533
+ {
534
+ "epoch": 0.52,
535
+ "learning_rate": 0.0003,
536
+ "loss": 0.0014,
537
+ "step": 176
538
+ },
539
+ {
540
+ "epoch": 0.53,
541
+ "learning_rate": 0.0003,
542
+ "loss": 0.0052,
543
+ "step": 178
544
+ },
545
+ {
546
+ "epoch": 0.53,
547
+ "learning_rate": 0.0003,
548
+ "loss": 0.0348,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 0.54,
553
+ "learning_rate": 0.0003,
554
+ "loss": 0.0576,
555
+ "step": 182
556
+ },
557
+ {
558
+ "epoch": 0.55,
559
+ "learning_rate": 0.0003,
560
+ "loss": 0.0118,
561
+ "step": 184
562
+ },
563
+ {
564
+ "epoch": 0.55,
565
+ "learning_rate": 0.0003,
566
+ "loss": 0.0363,
567
+ "step": 186
568
+ },
569
+ {
570
+ "epoch": 0.56,
571
+ "learning_rate": 0.0003,
572
+ "loss": 0.0017,
573
+ "step": 188
574
+ },
575
+ {
576
+ "epoch": 0.56,
577
+ "learning_rate": 0.0003,
578
+ "loss": 0.1263,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 0.57,
583
+ "learning_rate": 0.0003,
584
+ "loss": 0.0255,
585
+ "step": 192
586
+ },
587
+ {
588
+ "epoch": 0.58,
589
+ "learning_rate": 0.0003,
590
+ "loss": 0.0549,
591
+ "step": 194
592
+ },
593
+ {
594
+ "epoch": 0.58,
595
+ "learning_rate": 0.0003,
596
+ "loss": 0.0002,
597
+ "step": 196
598
+ },
599
+ {
600
+ "epoch": 0.59,
601
+ "learning_rate": 0.0003,
602
+ "loss": 0.1491,
603
+ "step": 198
604
+ },
605
+ {
606
+ "epoch": 0.59,
607
+ "learning_rate": 0.0003,
608
+ "loss": 0.2058,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 0.6,
613
+ "learning_rate": 0.0003,
614
+ "loss": 0.0011,
615
+ "step": 202
616
+ },
617
+ {
618
+ "epoch": 0.61,
619
+ "learning_rate": 0.0003,
620
+ "loss": 0.0192,
621
+ "step": 204
622
+ },
623
+ {
624
+ "epoch": 0.61,
625
+ "learning_rate": 0.0003,
626
+ "loss": 0.0078,
627
+ "step": 206
628
+ },
629
+ {
630
+ "epoch": 0.62,
631
+ "learning_rate": 0.0003,
632
+ "loss": 0.2119,
633
+ "step": 208
634
+ },
635
+ {
636
+ "epoch": 0.62,
637
+ "learning_rate": 0.0003,
638
+ "loss": 0.0177,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 0.63,
643
+ "learning_rate": 0.0003,
644
+ "loss": 0.0516,
645
+ "step": 212
646
+ },
647
+ {
648
+ "epoch": 0.64,
649
+ "learning_rate": 0.0003,
650
+ "loss": 0.0271,
651
+ "step": 214
652
+ },
653
+ {
654
+ "epoch": 0.64,
655
+ "learning_rate": 0.0003,
656
+ "loss": 0.017,
657
+ "step": 216
658
+ },
659
+ {
660
+ "epoch": 0.65,
661
+ "learning_rate": 0.0003,
662
+ "loss": 0.0553,
663
+ "step": 218
664
+ },
665
+ {
666
+ "epoch": 0.65,
667
+ "learning_rate": 0.0003,
668
+ "loss": 0.0442,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 0.66,
673
+ "learning_rate": 0.0003,
674
+ "loss": 0.0178,
675
+ "step": 222
676
+ },
677
+ {
678
+ "epoch": 0.66,
679
+ "learning_rate": 0.0003,
680
+ "loss": 0.0023,
681
+ "step": 224
682
+ },
683
+ {
684
+ "epoch": 0.67,
685
+ "learning_rate": 0.0003,
686
+ "loss": 0.07,
687
+ "step": 226
688
+ },
689
+ {
690
+ "epoch": 0.68,
691
+ "learning_rate": 0.0003,
692
+ "loss": 0.0321,
693
+ "step": 228
694
+ },
695
+ {
696
+ "epoch": 0.68,
697
+ "learning_rate": 0.0003,
698
+ "loss": 0.0216,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 0.69,
703
+ "learning_rate": 0.0003,
704
+ "loss": 0.0011,
705
+ "step": 232
706
+ },
707
+ {
708
+ "epoch": 0.69,
709
+ "learning_rate": 0.0003,
710
+ "loss": 0.0029,
711
+ "step": 234
712
+ },
713
+ {
714
+ "epoch": 0.7,
715
+ "learning_rate": 0.0003,
716
+ "loss": 0.1031,
717
+ "step": 236
718
+ },
719
+ {
720
+ "epoch": 0.71,
721
+ "learning_rate": 0.0003,
722
+ "loss": 0.0213,
723
+ "step": 238
724
+ },
725
+ {
726
+ "epoch": 0.71,
727
+ "learning_rate": 0.0003,
728
+ "loss": 0.0561,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 0.72,
733
+ "learning_rate": 0.0003,
734
+ "loss": 0.0003,
735
+ "step": 242
736
+ },
737
+ {
738
+ "epoch": 0.72,
739
+ "learning_rate": 0.0003,
740
+ "loss": 0.0297,
741
+ "step": 244
742
+ },
743
+ {
744
+ "epoch": 0.73,
745
+ "learning_rate": 0.0003,
746
+ "loss": 0.0205,
747
+ "step": 246
748
+ },
749
+ {
750
+ "epoch": 0.74,
751
+ "learning_rate": 0.0003,
752
+ "loss": 0.006,
753
+ "step": 248
754
+ },
755
+ {
756
+ "epoch": 0.74,
757
+ "learning_rate": 0.0003,
758
+ "loss": 0.0204,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 0.75,
763
+ "learning_rate": 0.0003,
764
+ "loss": 0.0982,
765
+ "step": 252
766
+ },
767
+ {
768
+ "epoch": 0.75,
769
+ "learning_rate": 0.0003,
770
+ "loss": 0.0796,
771
+ "step": 254
772
+ },
773
+ {
774
+ "epoch": 0.76,
775
+ "learning_rate": 0.0003,
776
+ "loss": 0.041,
777
+ "step": 256
778
+ },
779
+ {
780
+ "epoch": 0.77,
781
+ "learning_rate": 0.0003,
782
+ "loss": 0.0007,
783
+ "step": 258
784
+ },
785
+ {
786
+ "epoch": 0.77,
787
+ "learning_rate": 0.0003,
788
+ "loss": 0.0579,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 0.78,
793
+ "learning_rate": 0.0003,
794
+ "loss": 0.0562,
795
+ "step": 262
796
+ },
797
+ {
798
+ "epoch": 0.78,
799
+ "learning_rate": 0.0003,
800
+ "loss": 0.0017,
801
+ "step": 264
802
+ },
803
+ {
804
+ "epoch": 0.79,
805
+ "learning_rate": 0.0003,
806
+ "loss": 0.0653,
807
+ "step": 266
808
+ },
809
+ {
810
+ "epoch": 0.8,
811
+ "learning_rate": 0.0003,
812
+ "loss": 0.0429,
813
+ "step": 268
814
+ },
815
+ {
816
+ "epoch": 0.8,
817
+ "learning_rate": 0.0003,
818
+ "loss": 0.0493,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 0.81,
823
+ "learning_rate": 0.0003,
824
+ "loss": 0.0382,
825
+ "step": 272
826
+ },
827
+ {
828
+ "epoch": 0.81,
829
+ "learning_rate": 0.0003,
830
+ "loss": 0.0004,
831
+ "step": 274
832
+ },
833
+ {
834
+ "epoch": 0.82,
835
+ "learning_rate": 0.0003,
836
+ "loss": 0.0167,
837
+ "step": 276
838
+ },
839
+ {
840
+ "epoch": 0.82,
841
+ "learning_rate": 0.0003,
842
+ "loss": 0.0051,
843
+ "step": 278
844
+ },
845
+ {
846
+ "epoch": 0.83,
847
+ "learning_rate": 0.0003,
848
+ "loss": 0.0014,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 0.84,
853
+ "learning_rate": 0.0003,
854
+ "loss": 0.0605,
855
+ "step": 282
856
+ },
857
+ {
858
+ "epoch": 0.84,
859
+ "learning_rate": 0.0003,
860
+ "loss": 0.02,
861
+ "step": 284
862
+ },
863
+ {
864
+ "epoch": 0.85,
865
+ "learning_rate": 0.0003,
866
+ "loss": 0.0134,
867
+ "step": 286
868
+ },
869
+ {
870
+ "epoch": 0.85,
871
+ "learning_rate": 0.0003,
872
+ "loss": 0.1659,
873
+ "step": 288
874
+ },
875
+ {
876
+ "epoch": 0.86,
877
+ "learning_rate": 0.0003,
878
+ "loss": 0.0209,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 0.87,
883
+ "learning_rate": 0.0003,
884
+ "loss": 0.0522,
885
+ "step": 292
886
+ },
887
+ {
888
+ "epoch": 0.87,
889
+ "learning_rate": 0.0003,
890
+ "loss": 0.0081,
891
+ "step": 294
892
+ },
893
+ {
894
+ "epoch": 0.88,
895
+ "learning_rate": 0.0003,
896
+ "loss": 0.049,
897
+ "step": 296
898
+ },
899
+ {
900
+ "epoch": 0.88,
901
+ "learning_rate": 0.0003,
902
+ "loss": 0.0507,
903
+ "step": 298
904
+ },
905
+ {
906
+ "epoch": 0.89,
907
+ "learning_rate": 0.0003,
908
+ "loss": 0.1571,
909
+ "step": 300
910
+ },
911
+ {
912
+ "epoch": 0.9,
913
+ "learning_rate": 0.0003,
914
+ "loss": 0.0097,
915
+ "step": 302
916
+ },
917
+ {
918
+ "epoch": 0.9,
919
+ "learning_rate": 0.0003,
920
+ "loss": 0.0172,
921
+ "step": 304
922
+ },
923
+ {
924
+ "epoch": 0.91,
925
+ "learning_rate": 0.0003,
926
+ "loss": 0.0119,
927
+ "step": 306
928
+ },
929
+ {
930
+ "epoch": 0.91,
931
+ "learning_rate": 0.0003,
932
+ "loss": 0.0023,
933
+ "step": 308
934
+ },
935
+ {
936
+ "epoch": 0.92,
937
+ "learning_rate": 0.0003,
938
+ "loss": 0.0687,
939
+ "step": 310
940
+ },
941
+ {
942
+ "epoch": 0.93,
943
+ "learning_rate": 0.0003,
944
+ "loss": 0.0678,
945
+ "step": 312
946
+ },
947
+ {
948
+ "epoch": 0.93,
949
+ "learning_rate": 0.0003,
950
+ "loss": 0.0591,
951
+ "step": 314
952
+ },
953
+ {
954
+ "epoch": 0.94,
955
+ "learning_rate": 0.0003,
956
+ "loss": 0.0315,
957
+ "step": 316
958
+ },
959
+ {
960
+ "epoch": 0.94,
961
+ "learning_rate": 0.0003,
962
+ "loss": 0.02,
963
+ "step": 318
964
+ },
965
+ {
966
+ "epoch": 0.95,
967
+ "learning_rate": 0.0003,
968
+ "loss": 0.0177,
969
+ "step": 320
970
+ },
971
+ {
972
+ "epoch": 0.96,
973
+ "learning_rate": 0.0003,
974
+ "loss": 0.0031,
975
+ "step": 322
976
+ },
977
+ {
978
+ "epoch": 0.96,
979
+ "learning_rate": 0.0003,
980
+ "loss": 0.05,
981
+ "step": 324
982
+ },
983
+ {
984
+ "epoch": 0.97,
985
+ "learning_rate": 0.0003,
986
+ "loss": 0.0564,
987
+ "step": 326
988
+ },
989
+ {
990
+ "epoch": 0.97,
991
+ "learning_rate": 0.0003,
992
+ "loss": 0.0868,
993
+ "step": 328
994
+ },
995
+ {
996
+ "epoch": 0.98,
997
+ "learning_rate": 0.0003,
998
+ "loss": 0.0279,
999
+ "step": 330
1000
+ },
1001
+ {
1002
+ "epoch": 0.99,
1003
+ "learning_rate": 0.0003,
1004
+ "loss": 0.1276,
1005
+ "step": 332
1006
+ },
1007
+ {
1008
+ "epoch": 0.99,
1009
+ "learning_rate": 0.0003,
1010
+ "loss": 0.0092,
1011
+ "step": 334
1012
+ },
1013
+ {
1014
+ "epoch": 1.0,
1015
+ "learning_rate": 0.0003,
1016
+ "loss": 0.0034,
1017
+ "step": 336
1018
+ },
1019
+ {
1020
+ "epoch": 1.0,
1021
+ "step": 337,
1022
+ "total_flos": 631174056056082.0,
1023
+ "train_loss": 0.04601551576511304,
1024
+ "train_runtime": 391.6583,
1025
+ "train_samples_per_second": 27.491,
1026
+ "train_steps_per_second": 0.86
1027
+ }
1028
+ ],
1029
+ "logging_steps": 2,
1030
+ "max_steps": 337,
1031
+ "num_train_epochs": 1,
1032
+ "save_steps": 500,
1033
+ "total_flos": 631174056056082.0,
1034
+ "trial_name": null,
1035
+ "trial_params": null
1036
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04eb5e9adf22c6601626c188e8ac41b9fdc2482f06cace3cfabca163e961484
3
+ size 4155
vocab.json ADDED
The diff for this file is too large to render. See raw diff