Hugging Face's logo

conceptnetUk
/
intent-classifier

Text Classification
Safetensors
distilbert
intent-classification
enterprise-ai
voice-ai
multilingual
Model card Files
xet
 Community
2
conceptnetUk commited on
Commit
e33316c
·
verified ·
1 Parent(s): a32383d

Upload folder using huggingface_hub

Browse files
Files changed (50) hide show
  1. checkpoint-111/config.json +41 -0
  2. checkpoint-111/model.safetensors +3 -0
  3. checkpoint-111/optimizer.pt +3 -0
  4. checkpoint-111/rng_state.pth +3 -0
  5. checkpoint-111/scheduler.pt +3 -0
  6. checkpoint-111/tokenizer.json +0 -0
  7. checkpoint-111/tokenizer_config.json +15 -0
  8. checkpoint-111/trainer_state.json +61 -0
  9. checkpoint-111/training_args.bin +3 -0
  10. checkpoint-148/config.json +41 -0
  11. checkpoint-148/model.safetensors +3 -0
  12. checkpoint-148/optimizer.pt +3 -0
  13. checkpoint-148/rng_state.pth +3 -0
  14. checkpoint-148/scheduler.pt +3 -0
  15. checkpoint-148/tokenizer.json +0 -0
  16. checkpoint-148/tokenizer_config.json +15 -0
  17. checkpoint-148/trainer_state.json +70 -0
  18. checkpoint-148/training_args.bin +3 -0
  19. checkpoint-185/config.json +41 -0
  20. checkpoint-185/model.safetensors +3 -0
  21. checkpoint-185/optimizer.pt +3 -0
  22. checkpoint-185/rng_state.pth +3 -0
  23. checkpoint-185/scheduler.pt +3 -0
  24. checkpoint-185/tokenizer.json +0 -0
  25. checkpoint-185/tokenizer_config.json +15 -0
  26. checkpoint-185/trainer_state.json +79 -0
  27. checkpoint-185/training_args.bin +3 -0
  28. checkpoint-37/config.json +41 -0
  29. checkpoint-37/model.safetensors +3 -0
  30. checkpoint-37/optimizer.pt +3 -0
  31. checkpoint-37/rng_state.pth +3 -0
  32. checkpoint-37/scheduler.pt +3 -0
  33. checkpoint-37/tokenizer.json +0 -0
  34. checkpoint-37/tokenizer_config.json +15 -0
  35. checkpoint-37/trainer_state.json +43 -0
  36. checkpoint-37/training_args.bin +3 -0
  37. checkpoint-74/config.json +41 -0
  38. checkpoint-74/model.safetensors +3 -0
  39. checkpoint-74/optimizer.pt +3 -0
  40. checkpoint-74/rng_state.pth +3 -0
  41. checkpoint-74/scheduler.pt +3 -0
  42. checkpoint-74/tokenizer.json +0 -0
  43. checkpoint-74/tokenizer_config.json +15 -0
  44. checkpoint-74/trainer_state.json +52 -0
  45. checkpoint-74/training_args.bin +3 -0
  46. config.json +41 -0
  47. model.safetensors +3 -0
  48. tokenizer.json +0 -0
  49. tokenizer_config.json +15 -0
  50. training_args.bin +3 -0
checkpoint-111/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "Basic",
15
+ "1": "Context-Aware",
16
+ "2": "Predictive",
17
+ "3": "Autonomous"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "Autonomous": 3,
22
+ "Basic": 0,
23
+ "Context-Aware": 1,
24
+ "Predictive": 2
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "problem_type": "single_label_classification",
33
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": false,
36
+ "tie_weights_": true,
37
+ "tie_word_embeddings": true,
38
+ "transformers_version": "5.15.0",
39
+ "use_cache": false,
40
+ "vocab_size": 119547
41
+ }
checkpoint-111/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68fcaa2bdbe77ca11c1cc9fbe3bb2e545601b4b537816cdae753d17416b93ddf
3
+ size 541323528
checkpoint-111/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d665cb3fa687010a8cc30f7d378d03393e8a40bdb979bcd2fa72e872827555c
3
+ size 1082711115
checkpoint-111/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1612c7b49e4fb4b02274757be1a459161ebb12fa0b8fde7015ccb8121cdb6da9
3
+ size 14645
checkpoint-111/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c69ee6a4e930c814640a7f0a413efc0a306b57c6a2ea17c31c6b9e015a64cc0
3
+ size 1465
checkpoint-111/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-111/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-111/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 74,
3
+ "best_metric": 0.9931506849315068,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-74",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 111,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8972602739726028,
15
+ "eval_loss": 0.388628214597702,
16
+ "eval_runtime": 0.168,
17
+ "eval_samples_per_second": 869.095,
18
+ "eval_steps_per_second": 29.764,
19
+ "step": 37
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.9931506849315068,
24
+ "eval_loss": 0.05768229067325592,
25
+ "eval_runtime": 0.1184,
26
+ "eval_samples_per_second": 1232.64,
27
+ "eval_steps_per_second": 42.214,
28
+ "step": 74
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.9863013698630136,
33
+ "eval_loss": 0.0521763451397419,
34
+ "eval_runtime": 0.1295,
35
+ "eval_samples_per_second": 1127.358,
36
+ "eval_steps_per_second": 38.608,
37
+ "step": 111
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 185,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 5,
44
+ "save_steps": 500,
45
+ "stateful_callbacks": {
46
+ "TrainerControl": {
47
+ "args": {
48
+ "should_epoch_stop": false,
49
+ "should_evaluate": false,
50
+ "should_log": false,
51
+ "should_save": true,
52
+ "should_training_stop": false
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 8935658698176.0,
58
+ "train_batch_size": 16,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-111/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e7fc8cad10b25f6f55e0d0b510aeb70b111eb30216129eb606911e9ab0f802
3
+ size 5201
checkpoint-148/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "Basic",
15
+ "1": "Context-Aware",
16
+ "2": "Predictive",
17
+ "3": "Autonomous"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "Autonomous": 3,
22
+ "Basic": 0,
23
+ "Context-Aware": 1,
24
+ "Predictive": 2
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "problem_type": "single_label_classification",
33
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": false,
36
+ "tie_weights_": true,
37
+ "tie_word_embeddings": true,
38
+ "transformers_version": "5.15.0",
39
+ "use_cache": false,
40
+ "vocab_size": 119547
41
+ }
checkpoint-148/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609744419e8b5950a0add9aecf4dcd8542bb04aa108794108a02f43ed8288548
3
+ size 541323528
checkpoint-148/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ab100731d2f093d25d9c28a82f08ce054b35fd0b9430df5127dda4d6fe9b05
3
+ size 1082711115
checkpoint-148/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8e2d4059f9cf0b0152bd2b80cda206078e3b5db0a82d637c986f68e0575360
3
+ size 14645
checkpoint-148/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38850dee762e1fe8eda5949142619b61adab457c9af4be8c866fac5a8b50563
3
+ size 1465
checkpoint-148/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-148/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-148/trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 74,
3
+ "best_metric": 0.9931506849315068,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-74",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 148,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8972602739726028,
15
+ "eval_loss": 0.388628214597702,
16
+ "eval_runtime": 0.168,
17
+ "eval_samples_per_second": 869.095,
18
+ "eval_steps_per_second": 29.764,
19
+ "step": 37
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.9931506849315068,
24
+ "eval_loss": 0.05768229067325592,
25
+ "eval_runtime": 0.1184,
26
+ "eval_samples_per_second": 1232.64,
27
+ "eval_steps_per_second": 42.214,
28
+ "step": 74
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.9863013698630136,
33
+ "eval_loss": 0.0521763451397419,
34
+ "eval_runtime": 0.1295,
35
+ "eval_samples_per_second": 1127.358,
36
+ "eval_steps_per_second": 38.608,
37
+ "step": 111
38
+ },
39
+ {
40
+ "epoch": 4.0,
41
+ "eval_accuracy": 0.9863013698630136,
42
+ "eval_loss": 0.04882890358567238,
43
+ "eval_runtime": 0.1156,
44
+ "eval_samples_per_second": 1262.665,
45
+ "eval_steps_per_second": 43.242,
46
+ "step": 148
47
+ }
48
+ ],
49
+ "logging_steps": 500,
50
+ "max_steps": 185,
51
+ "num_input_tokens_seen": 0,
52
+ "num_train_epochs": 5,
53
+ "save_steps": 500,
54
+ "stateful_callbacks": {
55
+ "TrainerControl": {
56
+ "args": {
57
+ "should_epoch_stop": false,
58
+ "should_evaluate": false,
59
+ "should_log": false,
60
+ "should_save": true,
61
+ "should_training_stop": false
62
+ },
63
+ "attributes": {}
64
+ }
65
+ },
66
+ "total_flos": 11876953812864.0,
67
+ "train_batch_size": 16,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
checkpoint-148/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e7fc8cad10b25f6f55e0d0b510aeb70b111eb30216129eb606911e9ab0f802
3
+ size 5201
checkpoint-185/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "Basic",
15
+ "1": "Context-Aware",
16
+ "2": "Predictive",
17
+ "3": "Autonomous"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "Autonomous": 3,
22
+ "Basic": 0,
23
+ "Context-Aware": 1,
24
+ "Predictive": 2
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "problem_type": "single_label_classification",
33
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": false,
36
+ "tie_weights_": true,
37
+ "tie_word_embeddings": true,
38
+ "transformers_version": "5.15.0",
39
+ "use_cache": false,
40
+ "vocab_size": 119547
41
+ }
checkpoint-185/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8da54ae840ff0ebad02217733d0cb90486d6c63dbc87fbedd5311fe4335b998
3
+ size 541323528
checkpoint-185/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b5dde89dcf97ccefb1fb5d5b01850d2eb542e6605c7c5ed1d919c676cce0ee
3
+ size 1082711115
checkpoint-185/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23e0fbcd52ad3a4cdb47346ea0033b0647bba6bfdd03661768a20f4a5b9a4ba
3
+ size 14645
checkpoint-185/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03fe2be52c7830f9a8b9fc36cb9d166db298a6a0c825a5c2f620edcde6bb4266
3
+ size 1465
checkpoint-185/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-185/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-185/trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 74,
3
+ "best_metric": 0.9931506849315068,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-74",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 185,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8972602739726028,
15
+ "eval_loss": 0.388628214597702,
16
+ "eval_runtime": 0.168,
17
+ "eval_samples_per_second": 869.095,
18
+ "eval_steps_per_second": 29.764,
19
+ "step": 37
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.9931506849315068,
24
+ "eval_loss": 0.05768229067325592,
25
+ "eval_runtime": 0.1184,
26
+ "eval_samples_per_second": 1232.64,
27
+ "eval_steps_per_second": 42.214,
28
+ "step": 74
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.9863013698630136,
33
+ "eval_loss": 0.0521763451397419,
34
+ "eval_runtime": 0.1295,
35
+ "eval_samples_per_second": 1127.358,
36
+ "eval_steps_per_second": 38.608,
37
+ "step": 111
38
+ },
39
+ {
40
+ "epoch": 4.0,
41
+ "eval_accuracy": 0.9863013698630136,
42
+ "eval_loss": 0.04882890358567238,
43
+ "eval_runtime": 0.1156,
44
+ "eval_samples_per_second": 1262.665,
45
+ "eval_steps_per_second": 43.242,
46
+ "step": 148
47
+ },
48
+ {
49
+ "epoch": 5.0,
50
+ "eval_accuracy": 0.9863013698630136,
51
+ "eval_loss": 0.0471014566719532,
52
+ "eval_runtime": 0.1148,
53
+ "eval_samples_per_second": 1271.363,
54
+ "eval_steps_per_second": 43.54,
55
+ "step": 185
56
+ }
57
+ ],
58
+ "logging_steps": 500,
59
+ "max_steps": 185,
60
+ "num_input_tokens_seen": 0,
61
+ "num_train_epochs": 5,
62
+ "save_steps": 500,
63
+ "stateful_callbacks": {
64
+ "TrainerControl": {
65
+ "args": {
66
+ "should_epoch_stop": false,
67
+ "should_evaluate": false,
68
+ "should_log": false,
69
+ "should_save": true,
70
+ "should_training_stop": true
71
+ },
72
+ "attributes": {}
73
+ }
74
+ },
75
+ "total_flos": 14828598312192.0,
76
+ "train_batch_size": 16,
77
+ "trial_name": null,
78
+ "trial_params": null
79
+ }
checkpoint-185/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e7fc8cad10b25f6f55e0d0b510aeb70b111eb30216129eb606911e9ab0f802
3
+ size 5201
checkpoint-37/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "Basic",
15
+ "1": "Context-Aware",
16
+ "2": "Predictive",
17
+ "3": "Autonomous"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "Autonomous": 3,
22
+ "Basic": 0,
23
+ "Context-Aware": 1,
24
+ "Predictive": 2
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "problem_type": "single_label_classification",
33
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": false,
36
+ "tie_weights_": true,
37
+ "tie_word_embeddings": true,
38
+ "transformers_version": "5.15.0",
39
+ "use_cache": false,
40
+ "vocab_size": 119547
41
+ }
checkpoint-37/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a865ae1f5f574c887087973e02b5169f2ea87722156337604e2003eaa47df9e2
3
+ size 541323528
checkpoint-37/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b26c74f2d95037c5e3996bd0e04766e638e84d1027453c20b3aa9f95f9ada5
3
+ size 1082711115
checkpoint-37/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10eca5a0f1525e288bc5d2c2f1fbb1c18e094945c5922eba639d5b2d8338e2e8
3
+ size 14645
checkpoint-37/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b3f6595053a12b5d098adfb50090e4dd14da53d55da388eadd95a7143406aa8
3
+ size 1465
checkpoint-37/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-37/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-37/trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 37,
3
+ "best_metric": 0.8972602739726028,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-37",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 37,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8972602739726028,
15
+ "eval_loss": 0.388628214597702,
16
+ "eval_runtime": 0.168,
17
+ "eval_samples_per_second": 869.095,
18
+ "eval_steps_per_second": 29.764,
19
+ "step": 37
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 185,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 5,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 2990972160960.0,
40
+ "train_batch_size": 16,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }
checkpoint-37/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e7fc8cad10b25f6f55e0d0b510aeb70b111eb30216129eb606911e9ab0f802
3
+ size 5201
checkpoint-74/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "Basic",
15
+ "1": "Context-Aware",
16
+ "2": "Predictive",
17
+ "3": "Autonomous"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "Autonomous": 3,
22
+ "Basic": 0,
23
+ "Context-Aware": 1,
24
+ "Predictive": 2
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "problem_type": "single_label_classification",
33
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": false,
36
+ "tie_weights_": true,
37
+ "tie_word_embeddings": true,
38
+ "transformers_version": "5.15.0",
39
+ "use_cache": false,
40
+ "vocab_size": 119547
41
+ }
checkpoint-74/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12e7ff2c32fc6f06b257ae9137179b57b7d6b25a7729a13ba200a45dc04c321
3
+ size 541323528
checkpoint-74/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b9f81664381a08e629c772e3f05f1fd29bc326046c083ebf173b2181feb4da
3
+ size 1082711115
checkpoint-74/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47efdf41399808c1e1a9eafd3bb824441c5888e115d7027aab82282db3018afe
3
+ size 14645
checkpoint-74/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beabf7fa84682d3df9d9286077204ba8c3666754b5a3e37bc26dfe879a76f306
3
+ size 1465
checkpoint-74/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-74/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-74/trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 74,
3
+ "best_metric": 0.9931506849315068,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-74",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 74,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8972602739726028,
15
+ "eval_loss": 0.388628214597702,
16
+ "eval_runtime": 0.168,
17
+ "eval_samples_per_second": 869.095,
18
+ "eval_steps_per_second": 29.764,
19
+ "step": 37
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.9931506849315068,
24
+ "eval_loss": 0.05768229067325592,
25
+ "eval_runtime": 0.1184,
26
+ "eval_samples_per_second": 1232.64,
27
+ "eval_steps_per_second": 42.214,
28
+ "step": 74
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 185,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 5,
35
+ "save_steps": 500,
36
+ "stateful_callbacks": {
37
+ "TrainerControl": {
38
+ "args": {
39
+ "should_epoch_stop": false,
40
+ "should_evaluate": false,
41
+ "should_log": false,
42
+ "should_save": true,
43
+ "should_training_stop": false
44
+ },
45
+ "attributes": {}
46
+ }
47
+ },
48
+ "total_flos": 5969525060352.0,
49
+ "train_batch_size": 16,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
checkpoint-74/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e7fc8cad10b25f6f55e0d0b510aeb70b111eb30216129eb606911e9ab0f802
3
+ size 5201
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "Basic",
15
+ "1": "Context-Aware",
16
+ "2": "Predictive",
17
+ "3": "Autonomous"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "Autonomous": 3,
22
+ "Basic": 0,
23
+ "Context-Aware": 1,
24
+ "Predictive": 2
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "problem_type": "single_label_classification",
33
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": false,
36
+ "tie_weights_": true,
37
+ "tie_word_embeddings": true,
38
+ "transformers_version": "5.15.0",
39
+ "use_cache": false,
40
+ "vocab_size": 119547
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12e7ff2c32fc6f06b257ae9137179b57b7d6b25a7729a13ba200a45dc04c321
3
+ size 541323528
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e7fc8cad10b25f6f55e0d0b510aeb70b111eb30216129eb606911e9ab0f802
3
+ size 5201