Hugging Face's logo

Spaces:
JackBAI
/
MassageMateNLP
Sleeping

App Files Community
BiEchi commited on
Commit
4b6f5db
·
1 Parent(s): 603d605

all uploaded

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. app.py +25 -4
  2. models/bert/force/README.md +56 -0
  3. models/bert/force/all_results.json +14 -0
  4. models/bert/force/checkpoint-500/config.json +44 -0
  5. models/bert/force/checkpoint-500/optimizer.pt +3 -0
  6. models/bert/force/checkpoint-500/pytorch_model.bin +3 -0
  7. models/bert/force/checkpoint-500/rng_state.pth +3 -0
  8. models/bert/force/checkpoint-500/scheduler.pt +3 -0
  9. models/bert/force/checkpoint-500/special_tokens_map.json +15 -0
  10. models/bert/force/checkpoint-500/spiece.model +3 -0
  11. models/bert/force/checkpoint-500/tokenizer.json +0 -0
  12. models/bert/force/checkpoint-500/tokenizer_config.json +23 -0
  13. models/bert/force/checkpoint-500/trainer_state.json +22 -0
  14. models/bert/force/checkpoint-500/training_args.bin +3 -0
  15. models/bert/force/config.json +44 -0
  16. models/bert/force/eval_results.json +9 -0
  17. models/bert/force/pytorch_model.bin +3 -0
  18. models/bert/force/runs/Apr21_11-16-25_GCRAZGDL1124/1682075789.7038183/events.out.tfevents.1682075789.GCRAZGDL1124.3545282.1 +3 -0
  19. models/bert/force/runs/Apr21_11-16-25_GCRAZGDL1124/events.out.tfevents.1682075789.GCRAZGDL1124.3545282.0 +3 -0
  20. models/bert/force/runs/Apr21_11-16-25_GCRAZGDL1124/events.out.tfevents.1682075980.GCRAZGDL1124.3545282.2 +3 -0
  21. models/bert/force/runs/Apr21_11-31-28_GCRAZGDL1124/1682076692.4580789/events.out.tfevents.1682076692.GCRAZGDL1124.3563326.1 +3 -0
  22. models/bert/force/runs/Apr21_11-31-28_GCRAZGDL1124/events.out.tfevents.1682076692.GCRAZGDL1124.3563326.0 +3 -0
  23. models/bert/force/runs/Apr21_11-36-45_GCRAZGDL1124/1682077009.3747296/events.out.tfevents.1682077009.GCRAZGDL1124.3578948.1 +3 -0
  24. models/bert/force/runs/Apr21_11-36-45_GCRAZGDL1124/events.out.tfevents.1682077009.GCRAZGDL1124.3578948.0 +3 -0
  25. models/bert/force/runs/Apr21_11-36-45_GCRAZGDL1124/events.out.tfevents.1682077200.GCRAZGDL1124.3578948.2 +3 -0
  26. models/bert/force/special_tokens_map.json +15 -0
  27. models/bert/force/spiece.model +3 -0
  28. models/bert/force/tokenizer.json +0 -0
  29. models/bert/force/tokenizer_config.json +23 -0
  30. models/bert/force/train_results.json +8 -0
  31. models/bert/force/trainer_state.json +31 -0
  32. models/bert/force/training_args.bin +3 -0
  33. models/bert/position_x/README.md +56 -0
  34. models/bert/position_x/all_results.json +14 -0
  35. models/bert/position_x/checkpoint-500/config.json +44 -0
  36. models/bert/position_x/checkpoint-500/optimizer.pt +3 -0
  37. models/bert/position_x/checkpoint-500/pytorch_model.bin +3 -0
  38. models/bert/position_x/checkpoint-500/rng_state.pth +3 -0
  39. models/bert/position_x/checkpoint-500/scheduler.pt +3 -0
  40. models/bert/position_x/checkpoint-500/special_tokens_map.json +15 -0
  41. models/bert/position_x/checkpoint-500/spiece.model +3 -0
  42. models/bert/position_x/checkpoint-500/tokenizer.json +0 -0
  43. models/bert/position_x/checkpoint-500/tokenizer_config.json +23 -0
  44. models/bert/position_x/checkpoint-500/trainer_state.json +22 -0
  45. models/bert/position_x/checkpoint-500/training_args.bin +3 -0
  46. models/bert/position_x/config.json +44 -0
  47. models/bert/position_x/eval_results.json +9 -0
  48. models/bert/position_x/pytorch_model.bin +3 -0
  49. models/bert/position_x/runs/Apr21_11-26-23_GCRAZGDL1124/1682076387.511054/events.out.tfevents.1682076387.GCRAZGDL1124.3551945.1 +3 -0
  50. models/bert/position_x/runs/Apr21_11-26-23_GCRAZGDL1124/events.out.tfevents.1682076387.GCRAZGDL1124.3551945.0 +3 -0
app.py CHANGED
@@ -1,7 +1,28 @@
1
  import gradio as gr
2
 
3
- def greet(name):
4
- return "Hello " + name + "!!"
 
 
 
 
 
 
5
 
6
- iface = gr.Interface(fn=greet, inputs="text", outputs="text")
7
- iface.launch()
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  import gradio as gr
2
 
3
+ import pandas as pd
4
+ import torch
5
+ from torch.utils.data import Dataset, DataLoader
6
+ from transformers import AutoTokenizer, AutoModelForSequenceClassification
7
+ from transformers import BertModel
8
+ # ignore warnings
9
+ import warnings
10
+ warnings.filterwarnings("ignore")
11
 
12
+ def infer(text):
13
+ output_str = ''
14
+ for col in ['position_x', 'position_y', 'force', 'velocity_xy', 'velocity_z']:
15
+ model_path = f'models/bert/{col}'
16
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
17
+ model = AutoModelForSequenceClassification.from_pretrained(model_path)
18
+ model.eval()
19
+
20
+ encoded_input = tokenizer(text, return_tensors='pt')
21
+ output = model(**encoded_input)
22
+ scores = output[0].detach().cpu().numpy()[0]
23
+ answer = ['-1', '0', '1'][scores.argmax()]
24
+ output_str += f'{col}: {answer}\n'
25
+ return output_str
26
+
27
+ iface = gr.Interface(fn=infer, inputs="text", outputs="text")
28
+ iface.launch()
models/bert/force/README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: force
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # force
16
+
17
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2742
20
+ - Accuracy: 0.9134
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 128
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 12.0
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.25.1
54
+ - Pytorch 1.11.0+cu113
55
+ - Datasets 2.8.0
56
+ - Tokenizers 0.13.2
models/bert/force/all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 12.0,
3
+ "eval_accuracy": 0.9134438037872314,
4
+ "eval_loss": 0.27417391538619995,
5
+ "eval_runtime": 2.9366,
6
+ "eval_samples": 2172,
7
+ "eval_samples_per_second": 739.636,
8
+ "eval_steps_per_second": 92.625,
9
+ "train_loss": 0.24204148965723374,
10
+ "train_runtime": 188.5058,
11
+ "train_samples": 8689,
12
+ "train_samples_per_second": 553.129,
13
+ "train_steps_per_second": 4.329
14
+ }
models/bert/force/checkpoint-500/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": 0,
18
+ "1": 1,
19
+ "2": 2
20
+ },
21
+ "initializer_range": 0.02,
22
+ "inner_group_num": 1,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "0": 0,
26
+ "1": 1,
27
+ "2": 2
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "albert",
32
+ "net_structure_type": 0,
33
+ "num_attention_heads": 12,
34
+ "num_hidden_groups": 1,
35
+ "num_hidden_layers": 12,
36
+ "num_memory_blocks": 0,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.25.1",
42
+ "type_vocab_size": 2,
43
+ "vocab_size": 30000
44
+ }
models/bert/force/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54794e73cf5a411f3d6b6c049dc294810a84a9c2d3bd13a57da1b78d93d868f7
3
+ size 93502339
models/bert/force/checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f80904cb0cbbe6260a85052ff522565fb4a774bc56fede8164950c4dc70af9
3
+ size 46756497
models/bert/force/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c788e4329a13b9107aed45e985469818093dcd81d484ad8876bd56dd82ef4ebe
3
+ size 14503
models/bert/force/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421178ffb738901e52e2dee42e6c0afccef5f1c56baa954a19c707b77c2c59b8
3
+ size 623
models/bert/force/checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
models/bert/force/checkpoint-500/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
models/bert/force/checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/bert/force/checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "eos_token": "[SEP]",
6
+ "keep_accents": false,
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "[MASK]",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 512,
16
+ "name_or_path": "albert-base-v2",
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "special_tokens_map_file": null,
21
+ "tokenizer_class": "AlbertTokenizer",
22
+ "unk_token": "<unk>"
23
+ }
models/bert/force/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.352941176470588,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 7.35,
12
+ "learning_rate": 7.745098039215687e-06,
13
+ "loss": 0.3037,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 816,
18
+ "num_train_epochs": 12,
19
+ "total_flos": 381780038864640.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
models/bert/force/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58514aeb56c53b0d7311cb192109119347d199b8c8c5c0db3d4f15825fb89d0f
3
+ size 3439
models/bert/force/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": 0,
18
+ "1": 1,
19
+ "2": 2
20
+ },
21
+ "initializer_range": 0.02,
22
+ "inner_group_num": 1,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "0": 0,
26
+ "1": 1,
27
+ "2": 2
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "albert",
32
+ "net_structure_type": 0,
33
+ "num_attention_heads": 12,
34
+ "num_hidden_groups": 1,
35
+ "num_hidden_layers": 12,
36
+ "num_memory_blocks": 0,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.25.1",
42
+ "type_vocab_size": 2,
43
+ "vocab_size": 30000
44
+ }
models/bert/force/eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 12.0,
3
+ "eval_accuracy": 0.9134438037872314,
4
+ "eval_loss": 0.27417391538619995,
5
+ "eval_runtime": 2.9366,
6
+ "eval_samples": 2172,
7
+ "eval_samples_per_second": 739.636,
8
+ "eval_steps_per_second": 92.625
9
+ }
models/bert/force/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8bb5390930451db329c5bc554e7981470992fcc4e5d953c2a90e64b72bc72f
3
+ size 46756497
models/bert/force/runs/Apr21_11-16-25_GCRAZGDL1124/1682075789.7038183/events.out.tfevents.1682075789.GCRAZGDL1124.3545282.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513d22216fd84661f9b0596905fdd013384b234e0e23ab9b27f2b0f2ad0f7ee4
3
+ size 5512
models/bert/force/runs/Apr21_11-16-25_GCRAZGDL1124/events.out.tfevents.1682075789.GCRAZGDL1124.3545282.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b226f18a6b3ee455c4cab0dfde10e6db886cc73c24937e67e888eacbd3152652
3
+ size 4515
models/bert/force/runs/Apr21_11-16-25_GCRAZGDL1124/events.out.tfevents.1682075980.GCRAZGDL1124.3545282.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10fdcf37d33be909bb8ddac884269c9171347e9e668efce3840f57bc21a07d94
3
+ size 363
models/bert/force/runs/Apr21_11-31-28_GCRAZGDL1124/1682076692.4580789/events.out.tfevents.1682076692.GCRAZGDL1124.3563326.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26547d6cd3f700ffd77527eaf239ba2e487efb1ce9581084c05f9dac079f5124
3
+ size 5512
models/bert/force/runs/Apr21_11-31-28_GCRAZGDL1124/events.out.tfevents.1682076692.GCRAZGDL1124.3563326.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa42e89ec4553ddd07f4b258926cf2757f03282a610eea92b2acaad02d8ec7eb
3
+ size 40
models/bert/force/runs/Apr21_11-36-45_GCRAZGDL1124/1682077009.3747296/events.out.tfevents.1682077009.GCRAZGDL1124.3578948.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72be90745c6b0bf6a323037db4b8b24a6dac7a1e8aedd6566deb5ecbbe3428e1
3
+ size 5512
models/bert/force/runs/Apr21_11-36-45_GCRAZGDL1124/events.out.tfevents.1682077009.GCRAZGDL1124.3578948.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b445421bd6fee0c24d7b4101872cc428be954693b2350a5e8c38198b5654e37
3
+ size 4515
models/bert/force/runs/Apr21_11-36-45_GCRAZGDL1124/events.out.tfevents.1682077200.GCRAZGDL1124.3578948.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd02b329d335b093953f0d6fa456d137023766438a370f9c90e9e23a28d91081
3
+ size 363
models/bert/force/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
models/bert/force/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
models/bert/force/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/bert/force/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "eos_token": "[SEP]",
6
+ "keep_accents": false,
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "[MASK]",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 512,
16
+ "name_or_path": "albert-base-v2",
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "special_tokens_map_file": null,
21
+ "tokenizer_class": "AlbertTokenizer",
22
+ "unk_token": "<unk>"
23
+ }
models/bert/force/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 12.0,
3
+ "train_loss": 0.24204148965723374,
4
+ "train_runtime": 188.5058,
5
+ "train_samples": 8689,
6
+ "train_samples_per_second": 553.129,
7
+ "train_steps_per_second": 4.329
8
+ }
models/bert/force/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 12.0,
5
+ "global_step": 816,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 7.35,
12
+ "learning_rate": 7.745098039215687e-06,
13
+ "loss": 0.3037,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 12.0,
18
+ "step": 816,
19
+ "total_flos": 623013398424576.0,
20
+ "train_loss": 0.24204148965723374,
21
+ "train_runtime": 188.5058,
22
+ "train_samples_per_second": 553.129,
23
+ "train_steps_per_second": 4.329
24
+ }
25
+ ],
26
+ "max_steps": 816,
27
+ "num_train_epochs": 12,
28
+ "total_flos": 623013398424576.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
models/bert/force/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58514aeb56c53b0d7311cb192109119347d199b8c8c5c0db3d4f15825fb89d0f
3
+ size 3439
models/bert/position_x/README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: position_x
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # position_x
16
+
17
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1305
20
+ - Accuracy: 0.9701
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 128
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 12.0
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.25.1
54
+ - Pytorch 1.11.0+cu113
55
+ - Datasets 2.8.0
56
+ - Tokenizers 0.13.2
models/bert/position_x/all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 12.0,
3
+ "eval_accuracy": 0.9700736403465271,
4
+ "eval_loss": 0.13050080835819244,
5
+ "eval_runtime": 2.95,
6
+ "eval_samples": 2172,
7
+ "eval_samples_per_second": 736.266,
8
+ "eval_steps_per_second": 92.203,
9
+ "train_loss": 0.10659808504815195,
10
+ "train_runtime": 188.0297,
11
+ "train_samples": 8689,
12
+ "train_samples_per_second": 554.529,
13
+ "train_steps_per_second": 4.34
14
+ }
models/bert/position_x/checkpoint-500/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": 0,
18
+ "1": 1,
19
+ "2": 2
20
+ },
21
+ "initializer_range": 0.02,
22
+ "inner_group_num": 1,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "0": 0,
26
+ "1": 1,
27
+ "2": 2
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "albert",
32
+ "net_structure_type": 0,
33
+ "num_attention_heads": 12,
34
+ "num_hidden_groups": 1,
35
+ "num_hidden_layers": 12,
36
+ "num_memory_blocks": 0,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.25.1",
42
+ "type_vocab_size": 2,
43
+ "vocab_size": 30000
44
+ }
models/bert/position_x/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124fa95574bd1208aef2a4fc3d87be09b13c2a02182f8c729e52cc078fc1fa45
3
+ size 93502339
models/bert/position_x/checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6a7de6c8f12e966f16dacd9f8214ff4c66b3507520be43d9ebfa894ae9f4e3
3
+ size 46756497
models/bert/position_x/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c788e4329a13b9107aed45e985469818093dcd81d484ad8876bd56dd82ef4ebe
3
+ size 14503
models/bert/position_x/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421178ffb738901e52e2dee42e6c0afccef5f1c56baa954a19c707b77c2c59b8
3
+ size 623
models/bert/position_x/checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
models/bert/position_x/checkpoint-500/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
models/bert/position_x/checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/bert/position_x/checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "eos_token": "[SEP]",
6
+ "keep_accents": false,
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "[MASK]",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 512,
16
+ "name_or_path": "albert-base-v2",
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "special_tokens_map_file": null,
21
+ "tokenizer_class": "AlbertTokenizer",
22
+ "unk_token": "<unk>"
23
+ }
models/bert/position_x/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.352941176470588,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 7.35,
12
+ "learning_rate": 7.745098039215687e-06,
13
+ "loss": 0.1272,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 816,
18
+ "num_train_epochs": 12,
19
+ "total_flos": 381780038864640.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
models/bert/position_x/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b87ba239087451124fdd2b193813d4b8e6c4e7483d61ad0dd5dbc213fdcf07
3
+ size 3439
models/bert/position_x/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": 0,
18
+ "1": 1,
19
+ "2": 2
20
+ },
21
+ "initializer_range": 0.02,
22
+ "inner_group_num": 1,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "0": 0,
26
+ "1": 1,
27
+ "2": 2
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "albert",
32
+ "net_structure_type": 0,
33
+ "num_attention_heads": 12,
34
+ "num_hidden_groups": 1,
35
+ "num_hidden_layers": 12,
36
+ "num_memory_blocks": 0,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.25.1",
42
+ "type_vocab_size": 2,
43
+ "vocab_size": 30000
44
+ }
models/bert/position_x/eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 12.0,
3
+ "eval_accuracy": 0.9700736403465271,
4
+ "eval_loss": 0.13050080835819244,
5
+ "eval_runtime": 2.95,
6
+ "eval_samples": 2172,
7
+ "eval_samples_per_second": 736.266,
8
+ "eval_steps_per_second": 92.203
9
+ }
models/bert/position_x/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da83f6fee6947b2826dd64b77c6806c1bb46d9c9e57f1f26928db8183af95b4
3
+ size 46756497
models/bert/position_x/runs/Apr21_11-26-23_GCRAZGDL1124/1682076387.511054/events.out.tfevents.1682076387.GCRAZGDL1124.3551945.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014c04bc3027acf3e70d4552d20828acb2663678f1221b04f1f035269aa65863
3
+ size 5527
models/bert/position_x/runs/Apr21_11-26-23_GCRAZGDL1124/events.out.tfevents.1682076387.GCRAZGDL1124.3551945.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2aed4d319cf4d598d7b06078132d2aca1de6a3e6a9c534feea88fb8036c30c3
3
+ size 40