Hugging Face's logo

RepalleHanumansai
/
billing-bert

Safetensors
bert
Model card Files
xet
Community
Hanumansai commited on
Commit
0b4743f
·
verified ·
1 Parent(s): d5dadf0

Upload fine-tuned BERT intent model

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-126/config.json +48 -0
  2. checkpoint-126/model.safetensors +3 -0
  3. checkpoint-126/optimizer.pt +3 -0
  4. checkpoint-126/rng_state.pth +3 -0
  5. checkpoint-126/scaler.pt +3 -0
  6. checkpoint-126/scheduler.pt +3 -0
  7. checkpoint-126/trainer_state.json +48 -0
  8. checkpoint-126/training_args.bin +3 -0
  9. checkpoint-189/config.json +48 -0
  10. checkpoint-189/model.safetensors +3 -0
  11. checkpoint-189/optimizer.pt +3 -0
  12. checkpoint-189/rng_state.pth +3 -0
  13. checkpoint-189/scaler.pt +3 -0
  14. checkpoint-189/scheduler.pt +3 -0
  15. checkpoint-189/trainer_state.json +55 -0
  16. checkpoint-189/training_args.bin +3 -0
  17. checkpoint-252/config.json +48 -0
  18. checkpoint-252/model.safetensors +3 -0
  19. checkpoint-252/optimizer.pt +3 -0
  20. checkpoint-252/rng_state.pth +3 -0
  21. checkpoint-252/scaler.pt +3 -0
  22. checkpoint-252/scheduler.pt +3 -0
  23. checkpoint-252/trainer_state.json +69 -0
  24. checkpoint-252/training_args.bin +3 -0
  25. checkpoint-315/config.json +48 -0
  26. checkpoint-315/model.safetensors +3 -0
  27. checkpoint-315/optimizer.pt +3 -0
  28. checkpoint-315/rng_state.pth +3 -0
  29. checkpoint-315/scaler.pt +3 -0
  30. checkpoint-315/scheduler.pt +3 -0
  31. checkpoint-315/trainer_state.json +76 -0
  32. checkpoint-315/training_args.bin +3 -0
  33. checkpoint-378/config.json +48 -0
  34. checkpoint-378/model.safetensors +3 -0
  35. checkpoint-378/optimizer.pt +3 -0
  36. checkpoint-378/rng_state.pth +3 -0
  37. checkpoint-378/scaler.pt +3 -0
  38. checkpoint-378/scheduler.pt +3 -0
  39. checkpoint-378/trainer_state.json +83 -0
  40. checkpoint-378/training_args.bin +3 -0
  41. checkpoint-63/config.json +48 -0
  42. checkpoint-63/model.safetensors +3 -0
  43. checkpoint-63/optimizer.pt +3 -0
  44. checkpoint-63/rng_state.pth +3 -0
  45. checkpoint-63/scaler.pt +3 -0
  46. checkpoint-63/scheduler.pt +3 -0
  47. checkpoint-63/trainer_state.json +41 -0
  48. checkpoint-63/training_args.bin +3 -0
  49. config.json +48 -0
  50. model.safetensors +3 -0
checkpoint-126/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-126/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372a3eed18e0ba281a60b27b2c2bee0653f43e6deacbbc712d75303b95b96df7
3
+ size 437980180
checkpoint-126/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6cc4636674318a88a45a0450b1228e2ac3c5d49e3a2f8116f5786c3c685116d
3
+ size 876084619
checkpoint-126/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d20dfbac10beff7b0d5ff4ad35a6a4257384999ebdfb59e4310cff9392764400
3
+ size 14645
checkpoint-126/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9999adc358c2875ae07de73c84e0b22eabf051368f06e3e815625ad5bf047c
3
+ size 1383
checkpoint-126/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641c38363f585b0d6c4742723073c95bb01b30efe78c5b91d548b1e5c5c924bc
3
+ size 1465
checkpoint-126/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 126,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7936507936507936,
14
+ "grad_norm": 4.6148552894592285,
15
+ "learning_rate": 1.740740740740741e-05,
16
+ "loss": 1.5568,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.5873015873015874,
21
+ "grad_norm": 1.964592695236206,
22
+ "learning_rate": 1.4761904761904763e-05,
23
+ "loss": 0.4282,
24
+ "step": 100
25
+ }
26
+ ],
27
+ "logging_steps": 50,
28
+ "max_steps": 378,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 6,
31
+ "save_steps": 500,
32
+ "stateful_callbacks": {
33
+ "TrainerControl": {
34
+ "args": {
35
+ "should_epoch_stop": false,
36
+ "should_evaluate": false,
37
+ "should_log": false,
38
+ "should_save": true,
39
+ "should_training_stop": false
40
+ },
41
+ "attributes": {}
42
+ }
43
+ },
44
+ "total_flos": 131563795968000.0,
45
+ "train_batch_size": 16,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
checkpoint-126/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68c49d65bd510e0206d6de014c17bfbe948962e7efafb7e3e5e3a20ed4cf2b7
3
+ size 5841
checkpoint-189/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-189/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a905c4fd6e877eb70dad4ded37cb27a73ecdf7730155ab3da83688d1439b623a
3
+ size 437980180
checkpoint-189/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d4bf192ca9c8aff6efeccb34dbd34c5c87af430dca07d81c20165c865d60b9
3
+ size 876084619
checkpoint-189/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:078d2db92580a895bb02eb1a59afb73ef88c96d1d3e34d038cd1ec4a4019d694
3
+ size 14645
checkpoint-189/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ab77accefe3061045522e385a3119013ffd317c3042728397d54daadbbe5e2
3
+ size 1383
checkpoint-189/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30888e9f62e2f53fb5001df76b256b7a46f343548861c8f0b16adc3e450cff2b
3
+ size 1465
checkpoint-189/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 189,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7936507936507936,
14
+ "grad_norm": 4.6148552894592285,
15
+ "learning_rate": 1.740740740740741e-05,
16
+ "loss": 1.5568,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.5873015873015874,
21
+ "grad_norm": 1.964592695236206,
22
+ "learning_rate": 1.4761904761904763e-05,
23
+ "loss": 0.4282,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 2.380952380952381,
28
+ "grad_norm": 0.401151180267334,
29
+ "learning_rate": 1.2116402116402117e-05,
30
+ "loss": 0.0969,
31
+ "step": 150
32
+ }
33
+ ],
34
+ "logging_steps": 50,
35
+ "max_steps": 378,
36
+ "num_input_tokens_seen": 0,
37
+ "num_train_epochs": 6,
38
+ "save_steps": 500,
39
+ "stateful_callbacks": {
40
+ "TrainerControl": {
41
+ "args": {
42
+ "should_epoch_stop": false,
43
+ "should_evaluate": false,
44
+ "should_log": false,
45
+ "should_save": true,
46
+ "should_training_stop": false
47
+ },
48
+ "attributes": {}
49
+ }
50
+ },
51
+ "total_flos": 197345693952000.0,
52
+ "train_batch_size": 16,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
checkpoint-189/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68c49d65bd510e0206d6de014c17bfbe948962e7efafb7e3e5e3a20ed4cf2b7
3
+ size 5841
checkpoint-252/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-252/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb66be34e2c0e59b318fd74a3588a21f89abd1edd04166f03e7d5e3e4c4e138
3
+ size 437980180
checkpoint-252/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d633f8cab62d090fb139d2ba1bc37ad83de5f9c2173d9de2f41041208fa19402
3
+ size 876084619
checkpoint-252/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf1aa96329ff3cbcfd7c161b0d601ec2e09eb36ceb73496c626eaa2353e8202
3
+ size 14645
checkpoint-252/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6db2f8aad57e859f3ec7b9eaacc8944394ceb281149057b925609bf494b28c
3
+ size 1383
checkpoint-252/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15768e788e654bdd1450b938de0ff62c0b173c17fec1a45d5bb175002ea3f5b2
3
+ size 1465
checkpoint-252/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 252,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7936507936507936,
14
+ "grad_norm": 4.6148552894592285,
15
+ "learning_rate": 1.740740740740741e-05,
16
+ "loss": 1.5568,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.5873015873015874,
21
+ "grad_norm": 1.964592695236206,
22
+ "learning_rate": 1.4761904761904763e-05,
23
+ "loss": 0.4282,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 2.380952380952381,
28
+ "grad_norm": 0.401151180267334,
29
+ "learning_rate": 1.2116402116402117e-05,
30
+ "loss": 0.0969,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 3.1746031746031744,
35
+ "grad_norm": 0.24489885568618774,
36
+ "learning_rate": 9.470899470899471e-06,
37
+ "loss": 0.0392,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 3.9682539682539684,
42
+ "grad_norm": 0.17426319420337677,
43
+ "learning_rate": 6.825396825396826e-06,
44
+ "loss": 0.0267,
45
+ "step": 250
46
+ }
47
+ ],
48
+ "logging_steps": 50,
49
+ "max_steps": 378,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 6,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": false
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 263127591936000.0,
66
+ "train_batch_size": 16,
67
+ "trial_name": null,
68
+ "trial_params": null
69
+ }
checkpoint-252/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68c49d65bd510e0206d6de014c17bfbe948962e7efafb7e3e5e3a20ed4cf2b7
3
+ size 5841
checkpoint-315/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-315/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a02a0077d1f1940ef903f71adc59a0af4f78e0a7d47e2f8823829fdb6e724c8
3
+ size 437980180
checkpoint-315/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0684ce56be393c046e8e2ee10c9e5c7d010ffa2db95c3781b5b082642305598f
3
+ size 876084619
checkpoint-315/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ff0f30633b1c8ec0113f828cc0f40ec9f9b00e167b7d36e717b5f1dfb8adb4
3
+ size 14645
checkpoint-315/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13bd1693e85eea688b7a90afd72bceb0350c61a00c4cf4703fe4db1d2e3dd28e
3
+ size 1383
checkpoint-315/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc45117c0c1030fdf34d2efdd2b2db5454c4d7389d9ed4ccd7fc09890491799f
3
+ size 1465
checkpoint-315/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 315,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7936507936507936,
14
+ "grad_norm": 4.6148552894592285,
15
+ "learning_rate": 1.740740740740741e-05,
16
+ "loss": 1.5568,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.5873015873015874,
21
+ "grad_norm": 1.964592695236206,
22
+ "learning_rate": 1.4761904761904763e-05,
23
+ "loss": 0.4282,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 2.380952380952381,
28
+ "grad_norm": 0.401151180267334,
29
+ "learning_rate": 1.2116402116402117e-05,
30
+ "loss": 0.0969,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 3.1746031746031744,
35
+ "grad_norm": 0.24489885568618774,
36
+ "learning_rate": 9.470899470899471e-06,
37
+ "loss": 0.0392,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 3.9682539682539684,
42
+ "grad_norm": 0.17426319420337677,
43
+ "learning_rate": 6.825396825396826e-06,
44
+ "loss": 0.0267,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 4.761904761904762,
49
+ "grad_norm": 0.17985087633132935,
50
+ "learning_rate": 4.17989417989418e-06,
51
+ "loss": 0.0216,
52
+ "step": 300
53
+ }
54
+ ],
55
+ "logging_steps": 50,
56
+ "max_steps": 378,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 6,
59
+ "save_steps": 500,
60
+ "stateful_callbacks": {
61
+ "TrainerControl": {
62
+ "args": {
63
+ "should_epoch_stop": false,
64
+ "should_evaluate": false,
65
+ "should_log": false,
66
+ "should_save": true,
67
+ "should_training_stop": false
68
+ },
69
+ "attributes": {}
70
+ }
71
+ },
72
+ "total_flos": 328909489920000.0,
73
+ "train_batch_size": 16,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-315/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68c49d65bd510e0206d6de014c17bfbe948962e7efafb7e3e5e3a20ed4cf2b7
3
+ size 5841
checkpoint-378/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-378/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c3d4b029184fc3736724e2115bd3aae02a1aabe47726aa8403b869d250072f
3
+ size 437980180
checkpoint-378/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f602d26b377beb61ef1423ebd668f4a375793867848fb4ef6bb6e46fbdd6fde8
3
+ size 876084619
checkpoint-378/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0443e3687e9fe7ae9995fa590fbd8ccb7532a975707e2ffe7f3ed1ab62edd422
3
+ size 14645
checkpoint-378/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48859eee5df1cd4f8966c9de4adf8ba6eff370db8fb415cd59929897bcd9b4e7
3
+ size 1383
checkpoint-378/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f340e3f5d3c47145b9bd498098aed0effe5f226710c211580f39bbfe853f439
3
+ size 1465
checkpoint-378/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 6.0,
6
+ "eval_steps": 500,
7
+ "global_step": 378,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7936507936507936,
14
+ "grad_norm": 4.6148552894592285,
15
+ "learning_rate": 1.740740740740741e-05,
16
+ "loss": 1.5568,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.5873015873015874,
21
+ "grad_norm": 1.964592695236206,
22
+ "learning_rate": 1.4761904761904763e-05,
23
+ "loss": 0.4282,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 2.380952380952381,
28
+ "grad_norm": 0.401151180267334,
29
+ "learning_rate": 1.2116402116402117e-05,
30
+ "loss": 0.0969,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 3.1746031746031744,
35
+ "grad_norm": 0.24489885568618774,
36
+ "learning_rate": 9.470899470899471e-06,
37
+ "loss": 0.0392,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 3.9682539682539684,
42
+ "grad_norm": 0.17426319420337677,
43
+ "learning_rate": 6.825396825396826e-06,
44
+ "loss": 0.0267,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 4.761904761904762,
49
+ "grad_norm": 0.17985087633132935,
50
+ "learning_rate": 4.17989417989418e-06,
51
+ "loss": 0.0216,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 5.555555555555555,
56
+ "grad_norm": 0.1550399214029312,
57
+ "learning_rate": 1.5343915343915345e-06,
58
+ "loss": 0.0192,
59
+ "step": 350
60
+ }
61
+ ],
62
+ "logging_steps": 50,
63
+ "max_steps": 378,
64
+ "num_input_tokens_seen": 0,
65
+ "num_train_epochs": 6,
66
+ "save_steps": 500,
67
+ "stateful_callbacks": {
68
+ "TrainerControl": {
69
+ "args": {
70
+ "should_epoch_stop": false,
71
+ "should_evaluate": false,
72
+ "should_log": false,
73
+ "should_save": true,
74
+ "should_training_stop": true
75
+ },
76
+ "attributes": {}
77
+ }
78
+ },
79
+ "total_flos": 394691387904000.0,
80
+ "train_batch_size": 16,
81
+ "trial_name": null,
82
+ "trial_params": null
83
+ }
checkpoint-378/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68c49d65bd510e0206d6de014c17bfbe948962e7efafb7e3e5e3a20ed4cf2b7
3
+ size 5841
checkpoint-63/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-63/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43df3882c178ab4426e72afe3c7762b34e9e3904f84f95e051155b2860ab0f4
3
+ size 437980180
checkpoint-63/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef95c53825ad523cb8dc959382b3937519738a203b76604bd122086484f856c
3
+ size 876084619
checkpoint-63/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378f535bcdbe6dcd9148bd0893a3e6ecf2f308e54044e77c9b3225edd093d16c
3
+ size 14645
checkpoint-63/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36723622404079b2b5fa5e1efd7a0c99d3624446b9b3a24624091f393ce43add
3
+ size 1383
checkpoint-63/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d73c3e7ee5334f554bbef8399a3986064627f06228624ceb2e1f2054c0660b
3
+ size 1465
checkpoint-63/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 63,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7936507936507936,
14
+ "grad_norm": 4.6148552894592285,
15
+ "learning_rate": 1.740740740740741e-05,
16
+ "loss": 1.5568,
17
+ "step": 50
18
+ }
19
+ ],
20
+ "logging_steps": 50,
21
+ "max_steps": 378,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 6,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": false
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 65781897984000.0,
38
+ "train_batch_size": 16,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
checkpoint-63/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68c49d65bd510e0206d6de014c17bfbe948962e7efafb7e3e5e3a20ed4cf2b7
3
+ size 5841
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c3d4b029184fc3736724e2115bd3aae02a1aabe47726aa8403b869d250072f
3
+ size 437980180