gopichandra commited on
Commit
0c9ac03
·
verified ·
1 Parent(s): 9517737

Delete campaign-training

Browse files
Files changed (42) hide show
  1. campaign-training/campaign-bert-model/config.json +0 -39
  2. campaign-training/campaign-bert-model/model.safetensors +0 -3
  3. campaign-training/campaign-bert-model/special_tokens_map.json +0 -7
  4. campaign-training/campaign-bert-model/tokenizer.json +0 -0
  5. campaign-training/campaign-bert-model/tokenizer_config.json +0 -58
  6. campaign-training/campaign-bert-model/vocab.txt +0 -0
  7. campaign-training/campaign_data.csv +0 -10
  8. campaign-training/label_encoder.pkl +0 -3
  9. campaign-training/results/checkpoint-1/config.json +0 -39
  10. campaign-training/results/checkpoint-1/model.safetensors +0 -3
  11. campaign-training/results/checkpoint-1/optimizer.pt +0 -3
  12. campaign-training/results/checkpoint-1/rng_state.pth +0 -3
  13. campaign-training/results/checkpoint-1/scheduler.pt +0 -3
  14. campaign-training/results/checkpoint-1/special_tokens_map.json +0 -7
  15. campaign-training/results/checkpoint-1/tokenizer.json +0 -0
  16. campaign-training/results/checkpoint-1/tokenizer_config.json +0 -58
  17. campaign-training/results/checkpoint-1/trainer_state.json +0 -33
  18. campaign-training/results/checkpoint-1/training_args.bin +0 -3
  19. campaign-training/results/checkpoint-1/vocab.txt +0 -0
  20. campaign-training/results/checkpoint-2/config.json +0 -39
  21. campaign-training/results/checkpoint-2/model.safetensors +0 -3
  22. campaign-training/results/checkpoint-2/optimizer.pt +0 -3
  23. campaign-training/results/checkpoint-2/rng_state.pth +0 -3
  24. campaign-training/results/checkpoint-2/scheduler.pt +0 -3
  25. campaign-training/results/checkpoint-2/special_tokens_map.json +0 -7
  26. campaign-training/results/checkpoint-2/tokenizer.json +0 -0
  27. campaign-training/results/checkpoint-2/tokenizer_config.json +0 -58
  28. campaign-training/results/checkpoint-2/trainer_state.json +0 -33
  29. campaign-training/results/checkpoint-2/training_args.bin +0 -3
  30. campaign-training/results/checkpoint-2/vocab.txt +0 -0
  31. campaign-training/results/checkpoint-3/config.json +0 -39
  32. campaign-training/results/checkpoint-3/model.safetensors +0 -3
  33. campaign-training/results/checkpoint-3/optimizer.pt +0 -3
  34. campaign-training/results/checkpoint-3/rng_state.pth +0 -3
  35. campaign-training/results/checkpoint-3/scheduler.pt +0 -3
  36. campaign-training/results/checkpoint-3/special_tokens_map.json +0 -7
  37. campaign-training/results/checkpoint-3/tokenizer.json +0 -0
  38. campaign-training/results/checkpoint-3/tokenizer_config.json +0 -58
  39. campaign-training/results/checkpoint-3/trainer_state.json +0 -33
  40. campaign-training/results/checkpoint-3/training_args.bin +0 -3
  41. campaign-training/results/checkpoint-3/vocab.txt +0 -0
  42. campaign-training/train_model.py +0 -58
campaign-training/campaign-bert-model/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "architectures": [
3
- "BertForSequenceClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
- "hidden_act": "gelu",
8
- "hidden_dropout_prob": 0.1,
9
- "hidden_size": 128,
10
- "id2label": {
11
- "0": "LABEL_0",
12
- "1": "LABEL_1",
13
- "2": "LABEL_2",
14
- "3": "LABEL_3",
15
- "4": "LABEL_4"
16
- },
17
- "initializer_range": 0.02,
18
- "intermediate_size": 512,
19
- "label2id": {
20
- "LABEL_0": 0,
21
- "LABEL_1": 1,
22
- "LABEL_2": 2,
23
- "LABEL_3": 3,
24
- "LABEL_4": 4
25
- },
26
- "layer_norm_eps": 1e-12,
27
- "max_position_embeddings": 512,
28
- "model_type": "bert",
29
- "num_attention_heads": 2,
30
- "num_hidden_layers": 2,
31
- "pad_token_id": 0,
32
- "position_embedding_type": "absolute",
33
- "problem_type": "single_label_classification",
34
- "torch_dtype": "float32",
35
- "transformers_version": "4.53.0",
36
- "type_vocab_size": 2,
37
- "use_cache": true,
38
- "vocab_size": 30522
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/campaign-bert-model/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:01c51f0baa1ae1c95ac47186c60effa403bb7c6c784e8118d9af59030808be17
3
- size 17550860
 
 
 
 
campaign-training/campaign-bert-model/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
campaign-training/campaign-bert-model/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
campaign-training/campaign-bert-model/tokenizer_config.json DELETED
@@ -1,58 +0,0 @@
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
- "extra_special_tokens": {},
49
- "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
- "never_split": null,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
- "strip_accents": null,
55
- "tokenize_chinese_chars": true,
56
- "tokenizer_class": "BertTokenizer",
57
- "unk_token": "[UNK]"
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/campaign-bert-model/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
campaign-training/campaign_data.csv DELETED
@@ -1,10 +0,0 @@
1
- client_interest,sentiment,template_id
2
- Child Education,Positive,T7
3
- Health Insurance,Negative,T2
4
- Retirement Planning,Neutral,T4
5
- Life Insurance,Positive,T3
6
- Child Plan,Positive,T7
7
- Wealth Creation,Neutral,T5
8
- Medical Emergency,Negative,T2
9
- Pension Scheme,Neutral,T4
10
- Higher Studies,Positive,T7
 
 
 
 
 
 
 
 
 
 
 
campaign-training/label_encoder.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:64c1f3e87996ee46b538328ff0c3ca3740d1ed2a3d5a82518890c71eefb5cef5
3
- size 498
 
 
 
 
campaign-training/results/checkpoint-1/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "architectures": [
3
- "BertForSequenceClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
- "hidden_act": "gelu",
8
- "hidden_dropout_prob": 0.1,
9
- "hidden_size": 128,
10
- "id2label": {
11
- "0": "LABEL_0",
12
- "1": "LABEL_1",
13
- "2": "LABEL_2",
14
- "3": "LABEL_3",
15
- "4": "LABEL_4"
16
- },
17
- "initializer_range": 0.02,
18
- "intermediate_size": 512,
19
- "label2id": {
20
- "LABEL_0": 0,
21
- "LABEL_1": 1,
22
- "LABEL_2": 2,
23
- "LABEL_3": 3,
24
- "LABEL_4": 4
25
- },
26
- "layer_norm_eps": 1e-12,
27
- "max_position_embeddings": 512,
28
- "model_type": "bert",
29
- "num_attention_heads": 2,
30
- "num_hidden_layers": 2,
31
- "pad_token_id": 0,
32
- "position_embedding_type": "absolute",
33
- "problem_type": "single_label_classification",
34
- "torch_dtype": "float32",
35
- "transformers_version": "4.53.0",
36
- "type_vocab_size": 2,
37
- "use_cache": true,
38
- "vocab_size": 30522
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-1/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:458d44f0d332ff672a6cd0148c612bc27b1ee8a319fb8648598ce815396f37d2
3
- size 17550860
 
 
 
 
campaign-training/results/checkpoint-1/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7de92c6c81dbe906d3a814df28948d26abd39d5b23828705bebec78d2d673a1
3
- size 35126283
 
 
 
 
campaign-training/results/checkpoint-1/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:72375bac069363e5d019b444a4c7c4770609ca9aa9328cf535d6018bced92f10
3
- size 14455
 
 
 
 
campaign-training/results/checkpoint-1/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:06af82689f3c024ebea24b90121ad3b69c4b4b893bb0a7e3ea983b954960a394
3
- size 1465
 
 
 
 
campaign-training/results/checkpoint-1/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-1/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
campaign-training/results/checkpoint-1/tokenizer_config.json DELETED
@@ -1,58 +0,0 @@
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
- "extra_special_tokens": {},
49
- "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
- "never_split": null,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
- "strip_accents": null,
55
- "tokenize_chinese_chars": true,
56
- "tokenizer_class": "BertTokenizer",
57
- "unk_token": "[UNK]"
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-1/trainer_state.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 1.0,
6
- "eval_steps": 500,
7
- "global_step": 1,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [],
12
- "logging_steps": 500,
13
- "max_steps": 3,
14
- "num_input_tokens_seen": 0,
15
- "num_train_epochs": 3,
16
- "save_steps": 500,
17
- "stateful_callbacks": {
18
- "TrainerControl": {
19
- "args": {
20
- "should_epoch_stop": false,
21
- "should_evaluate": false,
22
- "should_log": false,
23
- "should_save": true,
24
- "should_training_stop": false
25
- },
26
- "attributes": {}
27
- }
28
- },
29
- "total_flos": 121703358.0,
30
- "train_batch_size": 8,
31
- "trial_name": null,
32
- "trial_params": null
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-1/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a5e0b28411e163fe1c9b4be538f8c9cb9e2865ee7c5f349e38bc5b0ccedaf8b
3
- size 5713
 
 
 
 
campaign-training/results/checkpoint-1/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
campaign-training/results/checkpoint-2/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "architectures": [
3
- "BertForSequenceClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
- "hidden_act": "gelu",
8
- "hidden_dropout_prob": 0.1,
9
- "hidden_size": 128,
10
- "id2label": {
11
- "0": "LABEL_0",
12
- "1": "LABEL_1",
13
- "2": "LABEL_2",
14
- "3": "LABEL_3",
15
- "4": "LABEL_4"
16
- },
17
- "initializer_range": 0.02,
18
- "intermediate_size": 512,
19
- "label2id": {
20
- "LABEL_0": 0,
21
- "LABEL_1": 1,
22
- "LABEL_2": 2,
23
- "LABEL_3": 3,
24
- "LABEL_4": 4
25
- },
26
- "layer_norm_eps": 1e-12,
27
- "max_position_embeddings": 512,
28
- "model_type": "bert",
29
- "num_attention_heads": 2,
30
- "num_hidden_layers": 2,
31
- "pad_token_id": 0,
32
- "position_embedding_type": "absolute",
33
- "problem_type": "single_label_classification",
34
- "torch_dtype": "float32",
35
- "transformers_version": "4.53.0",
36
- "type_vocab_size": 2,
37
- "use_cache": true,
38
- "vocab_size": 30522
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-2/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5a0e801eab49ba9848d569526638fad730da851f32f4bb7fa16c0f9476c5f20
3
- size 17550860
 
 
 
 
campaign-training/results/checkpoint-2/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbe201e0807039f9b46ee2605da2cead835cf8c0dc57590b3a3db8d69763300d
3
- size 35126283
 
 
 
 
campaign-training/results/checkpoint-2/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cf3d31d47b4be980adcc923c631329a1f7fd66a6235c22bc8c6b611fd6eac60
3
- size 14455
 
 
 
 
campaign-training/results/checkpoint-2/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9738a966c4fb3c4068232cb6c795a6d7a0673d04faa04ad7edb8d8a29248bcdc
3
- size 1465
 
 
 
 
campaign-training/results/checkpoint-2/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-2/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
campaign-training/results/checkpoint-2/tokenizer_config.json DELETED
@@ -1,58 +0,0 @@
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
- "extra_special_tokens": {},
49
- "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
- "never_split": null,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
- "strip_accents": null,
55
- "tokenize_chinese_chars": true,
56
- "tokenizer_class": "BertTokenizer",
57
- "unk_token": "[UNK]"
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-2/trainer_state.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 2.0,
6
- "eval_steps": 500,
7
- "global_step": 2,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [],
12
- "logging_steps": 500,
13
- "max_steps": 3,
14
- "num_input_tokens_seen": 0,
15
- "num_train_epochs": 3,
16
- "save_steps": 500,
17
- "stateful_callbacks": {
18
- "TrainerControl": {
19
- "args": {
20
- "should_epoch_stop": false,
21
- "should_evaluate": false,
22
- "should_log": false,
23
- "should_save": true,
24
- "should_training_stop": false
25
- },
26
- "attributes": {}
27
- }
28
- },
29
- "total_flos": 243406716.0,
30
- "train_batch_size": 8,
31
- "trial_name": null,
32
- "trial_params": null
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-2/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a5e0b28411e163fe1c9b4be538f8c9cb9e2865ee7c5f349e38bc5b0ccedaf8b
3
- size 5713
 
 
 
 
campaign-training/results/checkpoint-2/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
campaign-training/results/checkpoint-3/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "architectures": [
3
- "BertForSequenceClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
- "hidden_act": "gelu",
8
- "hidden_dropout_prob": 0.1,
9
- "hidden_size": 128,
10
- "id2label": {
11
- "0": "LABEL_0",
12
- "1": "LABEL_1",
13
- "2": "LABEL_2",
14
- "3": "LABEL_3",
15
- "4": "LABEL_4"
16
- },
17
- "initializer_range": 0.02,
18
- "intermediate_size": 512,
19
- "label2id": {
20
- "LABEL_0": 0,
21
- "LABEL_1": 1,
22
- "LABEL_2": 2,
23
- "LABEL_3": 3,
24
- "LABEL_4": 4
25
- },
26
- "layer_norm_eps": 1e-12,
27
- "max_position_embeddings": 512,
28
- "model_type": "bert",
29
- "num_attention_heads": 2,
30
- "num_hidden_layers": 2,
31
- "pad_token_id": 0,
32
- "position_embedding_type": "absolute",
33
- "problem_type": "single_label_classification",
34
- "torch_dtype": "float32",
35
- "transformers_version": "4.53.0",
36
- "type_vocab_size": 2,
37
- "use_cache": true,
38
- "vocab_size": 30522
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-3/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:01c51f0baa1ae1c95ac47186c60effa403bb7c6c784e8118d9af59030808be17
3
- size 17550860
 
 
 
 
campaign-training/results/checkpoint-3/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6665bb2b6553447a16e374c0123efbcab26caa4358fbeb4012e15ac1f8ee000
3
- size 35126283
 
 
 
 
campaign-training/results/checkpoint-3/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:54368e65f4bc80daa0ec10bd9a5c02da12272f4deb7b9a1a366dc89778b313a8
3
- size 14455
 
 
 
 
campaign-training/results/checkpoint-3/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:801f2d7a15a5a1d82d97d0d0399caf122b35c1a8ce4358491ecbaca4ca4db994
3
- size 1465
 
 
 
 
campaign-training/results/checkpoint-3/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-3/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
campaign-training/results/checkpoint-3/tokenizer_config.json DELETED
@@ -1,58 +0,0 @@
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
- "extra_special_tokens": {},
49
- "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
- "never_split": null,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
- "strip_accents": null,
55
- "tokenize_chinese_chars": true,
56
- "tokenizer_class": "BertTokenizer",
57
- "unk_token": "[UNK]"
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-3/trainer_state.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 3.0,
6
- "eval_steps": 500,
7
- "global_step": 3,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [],
12
- "logging_steps": 500,
13
- "max_steps": 3,
14
- "num_input_tokens_seen": 0,
15
- "num_train_epochs": 3,
16
- "save_steps": 500,
17
- "stateful_callbacks": {
18
- "TrainerControl": {
19
- "args": {
20
- "should_epoch_stop": false,
21
- "should_evaluate": false,
22
- "should_log": false,
23
- "should_save": true,
24
- "should_training_stop": true
25
- },
26
- "attributes": {}
27
- }
28
- },
29
- "total_flos": 365110074.0,
30
- "train_batch_size": 8,
31
- "trial_name": null,
32
- "trial_params": null
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
campaign-training/results/checkpoint-3/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a5e0b28411e163fe1c9b4be538f8c9cb9e2865ee7c5f349e38bc5b0ccedaf8b
3
- size 5713
 
 
 
 
campaign-training/results/checkpoint-3/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
campaign-training/train_model.py DELETED
@@ -1,58 +0,0 @@
1
- import pandas as pd
2
- from datasets import Dataset
3
- from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer
4
- from sklearn.preprocessing import LabelEncoder
5
- import joblib
6
-
7
- # Load dataset
8
- df = pd.read_csv("campaign_data.csv")
9
- df["text"] = df["client_interest"] + " Sentiment: " + df["sentiment"]
10
-
11
- # Encode labels
12
- le = LabelEncoder()
13
- df["label"] = le.fit_transform(df["template_id"])
14
-
15
- # Convert to Hugging Face dataset
16
- dataset = Dataset.from_pandas(df[["text", "label"]])
17
- dataset = dataset.train_test_split(test_size=0.2)
18
-
19
- # Tokenization
20
- tokenizer = AutoTokenizer.from_pretrained("prajjwal1/bert-tiny")
21
-
22
- def tokenize_function(batch):
23
- return tokenizer(batch["text"], padding=True, truncation=True)
24
-
25
- tokenized_dataset = dataset.map(tokenize_function, batched=True)
26
-
27
- # Load tiny model
28
- model = AutoModelForSequenceClassification.from_pretrained(
29
- "prajjwal1/bert-tiny",
30
- num_labels=len(le.classes_)
31
- )
32
-
33
- # Define training arguments
34
- training_args = TrainingArguments(
35
- output_dir="./results",
36
- per_device_train_batch_size=8,
37
- per_device_eval_batch_size=8,
38
- num_train_epochs=3,
39
- save_strategy="epoch",
40
- logging_dir="./logs"
41
- )
42
-
43
- # Trainer setup
44
- trainer = Trainer(
45
- model=model,
46
- args=training_args,
47
- train_dataset=tokenized_dataset["train"],
48
- eval_dataset=tokenized_dataset["test"],
49
- tokenizer=tokenizer
50
- )
51
-
52
- # Train and save
53
- trainer.train()
54
- model.save_pretrained("campaign-bert-model")
55
- tokenizer.save_pretrained("campaign-bert-model")
56
- joblib.dump(le, "label_encoder.pkl")
57
-
58
- print("✅ Model training complete and saved successfully.")