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
d51af8d
·
verified ·
1 Parent(s): 77940d7

Upload folder using huggingface_hub

Browse files
Files changed (46) hide show
  1. checkpoint-114/config.json +41 -0
  2. checkpoint-114/model.safetensors +3 -0
  3. checkpoint-114/optimizer.pt +3 -0
  4. checkpoint-114/rng_state.pth +3 -0
  5. checkpoint-114/scheduler.pt +3 -0
  6. checkpoint-114/tokenizer.json +0 -0
  7. checkpoint-114/tokenizer_config.json +15 -0
  8. checkpoint-114/trainer_state.json +61 -0
  9. checkpoint-114/training_args.bin +3 -0
  10. checkpoint-152/config.json +41 -0
  11. checkpoint-152/model.safetensors +3 -0
  12. checkpoint-152/optimizer.pt +3 -0
  13. checkpoint-152/rng_state.pth +3 -0
  14. checkpoint-152/scheduler.pt +3 -0
  15. checkpoint-152/tokenizer.json +0 -0
  16. checkpoint-152/tokenizer_config.json +15 -0
  17. checkpoint-152/trainer_state.json +70 -0
  18. checkpoint-152/training_args.bin +3 -0
  19. checkpoint-190/config.json +41 -0
  20. checkpoint-190/model.safetensors +3 -0
  21. checkpoint-190/optimizer.pt +3 -0
  22. checkpoint-190/rng_state.pth +3 -0
  23. checkpoint-190/scheduler.pt +3 -0
  24. checkpoint-190/tokenizer.json +0 -0
  25. checkpoint-190/tokenizer_config.json +15 -0
  26. checkpoint-190/trainer_state.json +79 -0
  27. checkpoint-190/training_args.bin +3 -0
  28. checkpoint-38/config.json +41 -0
  29. checkpoint-38/model.safetensors +3 -0
  30. checkpoint-38/optimizer.pt +3 -0
  31. checkpoint-38/rng_state.pth +3 -0
  32. checkpoint-38/scheduler.pt +3 -0
  33. checkpoint-38/tokenizer.json +0 -0
  34. checkpoint-38/tokenizer_config.json +15 -0
  35. checkpoint-38/trainer_state.json +43 -0
  36. checkpoint-38/training_args.bin +3 -0
  37. checkpoint-76/config.json +41 -0
  38. checkpoint-76/model.safetensors +3 -0
  39. checkpoint-76/optimizer.pt +3 -0
  40. checkpoint-76/rng_state.pth +3 -0
  41. checkpoint-76/scheduler.pt +3 -0
  42. checkpoint-76/tokenizer.json +0 -0
  43. checkpoint-76/tokenizer_config.json +15 -0
  44. checkpoint-76/trainer_state.json +52 -0
  45. checkpoint-76/training_args.bin +3 -0
  46. model.safetensors +1 -1
checkpoint-114/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-114/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4934ed4bfeb0c9e04a857e53a6df65403c823fb89c76469db2caf273836eaebf
3
+ size 541323528
checkpoint-114/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405b7bea602be1d4384962bee695e1ac9ecd41eb02a2830986e7b386bf9968c3
3
+ size 1082711115
checkpoint-114/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d14299dd21644405976985364504a20d96b27cf06429af5b71bf1c8b3a472f9
3
+ size 14645
checkpoint-114/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc2470ea96db517b26218b68148c073a66fb37d767b6f5c304cef97c094bc9cc
3
+ size 1465
checkpoint-114/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-114/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-114/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 114,
3
+ "best_metric": 0.993421052631579,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-114",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 114,
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": 0.9078947368421053,
15
+ "eval_loss": 0.31177520751953125,
16
+ "eval_runtime": 0.1557,
17
+ "eval_samples_per_second": 976.471,
18
+ "eval_steps_per_second": 32.121,
19
+ "step": 38
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.9736842105263158,
24
+ "eval_loss": 0.08166982978582382,
25
+ "eval_runtime": 0.1209,
26
+ "eval_samples_per_second": 1257.166,
27
+ "eval_steps_per_second": 41.354,
28
+ "step": 76
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.993421052631579,
33
+ "eval_loss": 0.04173273965716362,
34
+ "eval_runtime": 0.1245,
35
+ "eval_samples_per_second": 1220.706,
36
+ "eval_steps_per_second": 40.155,
37
+ "step": 114
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 190,
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": 9304355525976.0,
58
+ "train_batch_size": 16,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-114/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-152/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-152/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7aa8aa12d5b35aa3a767947d8f04ebbedbca388271a0841d101c9157bd7df23
3
+ size 541323528
checkpoint-152/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3a30c650181c5ad034fa55fd187919f5684ee38d4f30824aadb7da560175c15
3
+ size 1082711115
checkpoint-152/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f91b083f686358d38418bb068d08800e38d6082ce6bca220f375caadb6404c1
3
+ size 14645
checkpoint-152/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc927891d999aed2e05c10c0ae4cbe7fecdf977a71539c4923a179cef360a736
3
+ size 1465
checkpoint-152/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-152/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-152/trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 114,
3
+ "best_metric": 0.993421052631579,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-114",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 152,
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": 0.9078947368421053,
15
+ "eval_loss": 0.31177520751953125,
16
+ "eval_runtime": 0.1557,
17
+ "eval_samples_per_second": 976.471,
18
+ "eval_steps_per_second": 32.121,
19
+ "step": 38
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.9736842105263158,
24
+ "eval_loss": 0.08166982978582382,
25
+ "eval_runtime": 0.1209,
26
+ "eval_samples_per_second": 1257.166,
27
+ "eval_steps_per_second": 41.354,
28
+ "step": 76
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.993421052631579,
33
+ "eval_loss": 0.04173273965716362,
34
+ "eval_runtime": 0.1245,
35
+ "eval_samples_per_second": 1220.706,
36
+ "eval_steps_per_second": 40.155,
37
+ "step": 114
38
+ },
39
+ {
40
+ "epoch": 4.0,
41
+ "eval_accuracy": 0.993421052631579,
42
+ "eval_loss": 0.038805458694696426,
43
+ "eval_runtime": 0.1083,
44
+ "eval_samples_per_second": 1403.33,
45
+ "eval_steps_per_second": 46.162,
46
+ "step": 152
47
+ }
48
+ ],
49
+ "logging_steps": 500,
50
+ "max_steps": 190,
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": 12424177525704.0,
67
+ "train_batch_size": 16,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
checkpoint-152/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-190/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-190/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cafa74917fd2d25a658d22185f83acea523c4e289dabbd8113cfc97cf9bbdf57
3
+ size 541323528
checkpoint-190/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552ba4bf2407232441ace0d66fed9a745f091fe4c2b921957fd9647f70fcba86
3
+ size 1082711115
checkpoint-190/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e0c6318fb9dc843ae8d52a2440931c9b26f973c1ecebceb443c8b8dda2f9e8
3
+ size 14645
checkpoint-190/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432077c0c24a90d8974f4338b9b51845d84f2b5547fb2e6ece0686194ec14914
3
+ size 1465
checkpoint-190/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-190/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-190/trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 114,
3
+ "best_metric": 0.993421052631579,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-114",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 190,
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": 0.9078947368421053,
15
+ "eval_loss": 0.31177520751953125,
16
+ "eval_runtime": 0.1557,
17
+ "eval_samples_per_second": 976.471,
18
+ "eval_steps_per_second": 32.121,
19
+ "step": 38
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.9736842105263158,
24
+ "eval_loss": 0.08166982978582382,
25
+ "eval_runtime": 0.1209,
26
+ "eval_samples_per_second": 1257.166,
27
+ "eval_steps_per_second": 41.354,
28
+ "step": 76
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.993421052631579,
33
+ "eval_loss": 0.04173273965716362,
34
+ "eval_runtime": 0.1245,
35
+ "eval_samples_per_second": 1220.706,
36
+ "eval_steps_per_second": 40.155,
37
+ "step": 114
38
+ },
39
+ {
40
+ "epoch": 4.0,
41
+ "eval_accuracy": 0.993421052631579,
42
+ "eval_loss": 0.038805458694696426,
43
+ "eval_runtime": 0.1083,
44
+ "eval_samples_per_second": 1403.33,
45
+ "eval_steps_per_second": 46.162,
46
+ "step": 152
47
+ },
48
+ {
49
+ "epoch": 5.0,
50
+ "eval_accuracy": 0.993421052631579,
51
+ "eval_loss": 0.03954295068979263,
52
+ "eval_runtime": 0.1285,
53
+ "eval_samples_per_second": 1182.932,
54
+ "eval_steps_per_second": 38.912,
55
+ "step": 190
56
+ }
57
+ ],
58
+ "logging_steps": 500,
59
+ "max_steps": 190,
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": 15508552883040.0,
76
+ "train_batch_size": 16,
77
+ "trial_name": null,
78
+ "trial_params": null
79
+ }
checkpoint-190/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-38/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-38/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c1726e9a1e115899c451f823fabad828df43554c9d38e551c53dab95077521b
3
+ size 541323528
checkpoint-38/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e17ef4a313c8077b2a51300bec679edbb1edd16149584c39d8ced889d8674f27
3
+ size 1082711115
checkpoint-38/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd22b97b93886cc26b7e9e2e563dfc62856592f39f5a11db1f644890bdcf1ee2
3
+ size 14645
checkpoint-38/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5e307254231defca49ed3213d45b9c712cdb679872bc6baac36c07d3d2c5cf
3
+ size 1465
checkpoint-38/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-38/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-38/trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 38,
3
+ "best_metric": 0.9078947368421053,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-38",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 38,
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": 0.9078947368421053,
15
+ "eval_loss": 0.31177520751953125,
16
+ "eval_runtime": 0.1557,
17
+ "eval_samples_per_second": 976.471,
18
+ "eval_steps_per_second": 32.121,
19
+ "step": 38
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 190,
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": 3108178942008.0,
40
+ "train_batch_size": 16,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }
checkpoint-38/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-76/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-76/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f8c5b7300b474184ae827ef9dba4fc6460deeba15c90fabdfbecb052e6890aa
3
+ size 541323528
checkpoint-76/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17464d359a560b05a8dff8a9d0d7f0cbfc737e80b16b8a9d9a5871d37d4ed830
3
+ size 1082711115
checkpoint-76/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c08d38c61eebaa47abceef944d10b4e1e4750dba7b631fd7fca090ff371a16d
3
+ size 14645
checkpoint-76/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:420037f3af3403d3bf395d68b559565f661ab1bf4392cecd8f1a1e455361914f
3
+ size 1465
checkpoint-76/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-76/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-76/trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 76,
3
+ "best_metric": 0.9736842105263158,
4
+ "best_model_checkpoint": "./conceptnet-intent-classifier/checkpoint-76",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 76,
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": 0.9078947368421053,
15
+ "eval_loss": 0.31177520751953125,
16
+ "eval_runtime": 0.1557,
17
+ "eval_samples_per_second": 976.471,
18
+ "eval_steps_per_second": 32.121,
19
+ "step": 38
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.9736842105263158,
24
+ "eval_loss": 0.08166982978582382,
25
+ "eval_runtime": 0.1209,
26
+ "eval_samples_per_second": 1257.166,
27
+ "eval_steps_per_second": 41.354,
28
+ "step": 76
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 190,
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": 6175995283920.0,
49
+ "train_batch_size": 16,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
checkpoint-76/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e7fc8cad10b25f6f55e0d0b510aeb70b111eb30216129eb606911e9ab0f802
3
+ size 5201
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f12e7ff2c32fc6f06b257ae9137179b57b7d6b25a7729a13ba200a45dc04c321
3
  size 541323528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4934ed4bfeb0c9e04a857e53a6df65403c823fb89c76469db2caf273836eaebf
3
  size 541323528