Hugging Face's logo

thilaksai77
/
emotion_llm_identifier

Joblib
Safetensors
distilbert
Model card Files
xet
 Community
thilaksai77 commited on
Commit
e041d61
·
verified ·
1 Parent(s): b6ce170

Upload folder using huggingface_hub

Browse files
Files changed (42) hide show
  1. checkpoint-106/config.json +42 -0
  2. checkpoint-106/model.safetensors +3 -0
  3. checkpoint-106/optimizer.pt +3 -0
  4. checkpoint-106/rng_state.pth +3 -0
  5. checkpoint-106/scheduler.pt +3 -0
  6. checkpoint-106/trainer_state.json +66 -0
  7. checkpoint-106/training_args.bin +3 -0
  8. checkpoint-159/config.json +42 -0
  9. checkpoint-159/model.safetensors +3 -0
  10. checkpoint-159/optimizer.pt +3 -0
  11. checkpoint-159/rng_state.pth +3 -0
  12. checkpoint-159/scheduler.pt +3 -0
  13. checkpoint-159/trainer_state.json +82 -0
  14. checkpoint-159/training_args.bin +3 -0
  15. checkpoint-212/config.json +42 -0
  16. checkpoint-212/model.safetensors +3 -0
  17. checkpoint-212/optimizer.pt +3 -0
  18. checkpoint-212/rng_state.pth +3 -0
  19. checkpoint-212/scheduler.pt +3 -0
  20. checkpoint-212/trainer_state.json +98 -0
  21. checkpoint-212/training_args.bin +3 -0
  22. checkpoint-265/config.json +42 -0
  23. checkpoint-265/model.safetensors +3 -0
  24. checkpoint-265/optimizer.pt +3 -0
  25. checkpoint-265/rng_state.pth +3 -0
  26. checkpoint-265/scheduler.pt +3 -0
  27. checkpoint-265/trainer_state.json +114 -0
  28. checkpoint-265/training_args.bin +3 -0
  29. checkpoint-53/config.json +42 -0
  30. checkpoint-53/model.safetensors +3 -0
  31. checkpoint-53/optimizer.pt +3 -0
  32. checkpoint-53/rng_state.pth +3 -0
  33. checkpoint-53/scheduler.pt +3 -0
  34. checkpoint-53/trainer_state.json +50 -0
  35. checkpoint-53/training_args.bin +3 -0
  36. config.json +42 -0
  37. label_encoder.joblib +3 -0
  38. model.safetensors +3 -0
  39. special_tokens_map.json +7 -0
  40. tokenizer.json +0 -0
  41. tokenizer_config.json +56 -0
  42. vocab.txt +0 -0
checkpoint-106/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5,
27
+ "LABEL_6": 6
28
+ },
29
+ "max_position_embeddings": 512,
30
+ "model_type": "distilbert",
31
+ "n_heads": 12,
32
+ "n_layers": 6,
33
+ "pad_token_id": 0,
34
+ "problem_type": "single_label_classification",
35
+ "qa_dropout": 0.1,
36
+ "seq_classif_dropout": 0.2,
37
+ "sinusoidal_pos_embds": false,
38
+ "tie_weights_": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.51.3",
41
+ "vocab_size": 30522
42
+ }
checkpoint-106/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6080ad8f680c96f69d7615cfc2f17cd3aa3a5d7d86a120fdd73fb3fbe5cd54bc
3
+ size 267847948
checkpoint-106/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f6ed832b46410fc9808835f0e3b557805210aed2d25d701ec786bce49938fa
3
+ size 535755130
checkpoint-106/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e55bfc8723f269a626afca0be6f7def5753f3bb265436b94c5580b703cfcc7
3
+ size 13990
checkpoint-106/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d454f75613eedad47305d0f5455c6623b5e20d207f2b824cc564f1776df73e4
3
+ size 1064
checkpoint-106/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 106,
3
+ "best_metric": 0.5238095238095238,
4
+ "best_model_checkpoint": "./emotion_classifier/checkpoint-106",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 106,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9433962264150944,
14
+ "grad_norm": 3.0282411575317383,
15
+ "learning_rate": 1.6301886792452833e-05,
16
+ "loss": 1.6377,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.47619047619047616,
22
+ "eval_loss": 1.4806143045425415,
23
+ "eval_runtime": 2.5602,
24
+ "eval_samples_per_second": 41.012,
25
+ "eval_steps_per_second": 2.734,
26
+ "step": 53
27
+ },
28
+ {
29
+ "epoch": 1.8867924528301887,
30
+ "grad_norm": 5.8678812980651855,
31
+ "learning_rate": 1.2528301886792453e-05,
32
+ "loss": 1.4,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.5238095238095238,
38
+ "eval_loss": 1.3838814496994019,
39
+ "eval_runtime": 2.3279,
40
+ "eval_samples_per_second": 45.106,
41
+ "eval_steps_per_second": 3.007,
42
+ "step": 106
43
+ }
44
+ ],
45
+ "logging_steps": 50,
46
+ "max_steps": 265,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 5,
49
+ "save_steps": 500,
50
+ "stateful_callbacks": {
51
+ "TrainerControl": {
52
+ "args": {
53
+ "should_epoch_stop": false,
54
+ "should_evaluate": false,
55
+ "should_log": false,
56
+ "should_save": true,
57
+ "should_training_stop": false
58
+ },
59
+ "attributes": {}
60
+ }
61
+ },
62
+ "total_flos": 55641268408320.0,
63
+ "train_batch_size": 16,
64
+ "trial_name": null,
65
+ "trial_params": null
66
+ }
checkpoint-106/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9176974d5ca9307eaa01d489fefe68df96bb0a20f04f32ce3a207d3158a4f91d
3
+ size 5240
checkpoint-159/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5,
27
+ "LABEL_6": 6
28
+ },
29
+ "max_position_embeddings": 512,
30
+ "model_type": "distilbert",
31
+ "n_heads": 12,
32
+ "n_layers": 6,
33
+ "pad_token_id": 0,
34
+ "problem_type": "single_label_classification",
35
+ "qa_dropout": 0.1,
36
+ "seq_classif_dropout": 0.2,
37
+ "sinusoidal_pos_embds": false,
38
+ "tie_weights_": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.51.3",
41
+ "vocab_size": 30522
42
+ }
checkpoint-159/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7ac83f56b901c470482732a0102fa47de706dc56618c1d32811db881d4720d
3
+ size 267847948
checkpoint-159/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da379e7c982530b9c15753734b706ae5c65f64e41dd105d64481f302c5d5f24
3
+ size 535755130
checkpoint-159/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d32051101ec51c2b04c4ee6a6d2c7f40562e56836cbb02d6e6e3126490484d
3
+ size 13990
checkpoint-159/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f1da9e78fb7143f96c608378211ebe49e8b42e09cc551a079d15d8d54a1a44
3
+ size 1064
checkpoint-159/trainer_state.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 106,
3
+ "best_metric": 0.5238095238095238,
4
+ "best_model_checkpoint": "./emotion_classifier/checkpoint-106",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 159,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9433962264150944,
14
+ "grad_norm": 3.0282411575317383,
15
+ "learning_rate": 1.6301886792452833e-05,
16
+ "loss": 1.6377,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.47619047619047616,
22
+ "eval_loss": 1.4806143045425415,
23
+ "eval_runtime": 2.5602,
24
+ "eval_samples_per_second": 41.012,
25
+ "eval_steps_per_second": 2.734,
26
+ "step": 53
27
+ },
28
+ {
29
+ "epoch": 1.8867924528301887,
30
+ "grad_norm": 5.8678812980651855,
31
+ "learning_rate": 1.2528301886792453e-05,
32
+ "loss": 1.4,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.5238095238095238,
38
+ "eval_loss": 1.3838814496994019,
39
+ "eval_runtime": 2.3279,
40
+ "eval_samples_per_second": 45.106,
41
+ "eval_steps_per_second": 3.007,
42
+ "step": 106
43
+ },
44
+ {
45
+ "epoch": 2.830188679245283,
46
+ "grad_norm": 4.850906848907471,
47
+ "learning_rate": 8.754716981132076e-06,
48
+ "loss": 1.2805,
49
+ "step": 150
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "eval_accuracy": 0.5238095238095238,
54
+ "eval_loss": 1.3527458906173706,
55
+ "eval_runtime": 2.4197,
56
+ "eval_samples_per_second": 43.394,
57
+ "eval_steps_per_second": 2.893,
58
+ "step": 159
59
+ }
60
+ ],
61
+ "logging_steps": 50,
62
+ "max_steps": 265,
63
+ "num_input_tokens_seen": 0,
64
+ "num_train_epochs": 5,
65
+ "save_steps": 500,
66
+ "stateful_callbacks": {
67
+ "TrainerControl": {
68
+ "args": {
69
+ "should_epoch_stop": false,
70
+ "should_evaluate": false,
71
+ "should_log": false,
72
+ "should_save": true,
73
+ "should_training_stop": false
74
+ },
75
+ "attributes": {}
76
+ }
77
+ },
78
+ "total_flos": 83461902612480.0,
79
+ "train_batch_size": 16,
80
+ "trial_name": null,
81
+ "trial_params": null
82
+ }
checkpoint-159/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9176974d5ca9307eaa01d489fefe68df96bb0a20f04f32ce3a207d3158a4f91d
3
+ size 5240
checkpoint-212/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5,
27
+ "LABEL_6": 6
28
+ },
29
+ "max_position_embeddings": 512,
30
+ "model_type": "distilbert",
31
+ "n_heads": 12,
32
+ "n_layers": 6,
33
+ "pad_token_id": 0,
34
+ "problem_type": "single_label_classification",
35
+ "qa_dropout": 0.1,
36
+ "seq_classif_dropout": 0.2,
37
+ "sinusoidal_pos_embds": false,
38
+ "tie_weights_": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.51.3",
41
+ "vocab_size": 30522
42
+ }
checkpoint-212/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05db532e969998d68aab84e8793f077254f48699ddef1b716bee5218b010da1d
3
+ size 267847948
checkpoint-212/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86242dbcb65e37020fbbb309a71609d3bbb2b5c335006214af46fec7212439ec
3
+ size 535755130
checkpoint-212/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fed77b14fe062f6db72d68cedd6fd95bae3305b7a735eef3c85da43fd15d476
3
+ size 13990
checkpoint-212/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4975515fea706f12828b41b6a19e58079c2d505f4d25932c978e5edb1c949651
3
+ size 1064
checkpoint-212/trainer_state.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 212,
3
+ "best_metric": 0.5619047619047619,
4
+ "best_model_checkpoint": "./emotion_classifier/checkpoint-212",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 212,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9433962264150944,
14
+ "grad_norm": 3.0282411575317383,
15
+ "learning_rate": 1.6301886792452833e-05,
16
+ "loss": 1.6377,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.47619047619047616,
22
+ "eval_loss": 1.4806143045425415,
23
+ "eval_runtime": 2.5602,
24
+ "eval_samples_per_second": 41.012,
25
+ "eval_steps_per_second": 2.734,
26
+ "step": 53
27
+ },
28
+ {
29
+ "epoch": 1.8867924528301887,
30
+ "grad_norm": 5.8678812980651855,
31
+ "learning_rate": 1.2528301886792453e-05,
32
+ "loss": 1.4,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.5238095238095238,
38
+ "eval_loss": 1.3838814496994019,
39
+ "eval_runtime": 2.3279,
40
+ "eval_samples_per_second": 45.106,
41
+ "eval_steps_per_second": 3.007,
42
+ "step": 106
43
+ },
44
+ {
45
+ "epoch": 2.830188679245283,
46
+ "grad_norm": 4.850906848907471,
47
+ "learning_rate": 8.754716981132076e-06,
48
+ "loss": 1.2805,
49
+ "step": 150
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "eval_accuracy": 0.5238095238095238,
54
+ "eval_loss": 1.3527458906173706,
55
+ "eval_runtime": 2.4197,
56
+ "eval_samples_per_second": 43.394,
57
+ "eval_steps_per_second": 2.893,
58
+ "step": 159
59
+ },
60
+ {
61
+ "epoch": 3.7735849056603774,
62
+ "grad_norm": 5.995235919952393,
63
+ "learning_rate": 4.981132075471698e-06,
64
+ "loss": 1.1901,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.5619047619047619,
70
+ "eval_loss": 1.3129359483718872,
71
+ "eval_runtime": 2.3883,
72
+ "eval_samples_per_second": 43.964,
73
+ "eval_steps_per_second": 2.931,
74
+ "step": 212
75
+ }
76
+ ],
77
+ "logging_steps": 50,
78
+ "max_steps": 265,
79
+ "num_input_tokens_seen": 0,
80
+ "num_train_epochs": 5,
81
+ "save_steps": 500,
82
+ "stateful_callbacks": {
83
+ "TrainerControl": {
84
+ "args": {
85
+ "should_epoch_stop": false,
86
+ "should_evaluate": false,
87
+ "should_log": false,
88
+ "should_save": true,
89
+ "should_training_stop": false
90
+ },
91
+ "attributes": {}
92
+ }
93
+ },
94
+ "total_flos": 111282536816640.0,
95
+ "train_batch_size": 16,
96
+ "trial_name": null,
97
+ "trial_params": null
98
+ }
checkpoint-212/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9176974d5ca9307eaa01d489fefe68df96bb0a20f04f32ce3a207d3158a4f91d
3
+ size 5240
checkpoint-265/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5,
27
+ "LABEL_6": 6
28
+ },
29
+ "max_position_embeddings": 512,
30
+ "model_type": "distilbert",
31
+ "n_heads": 12,
32
+ "n_layers": 6,
33
+ "pad_token_id": 0,
34
+ "problem_type": "single_label_classification",
35
+ "qa_dropout": 0.1,
36
+ "seq_classif_dropout": 0.2,
37
+ "sinusoidal_pos_embds": false,
38
+ "tie_weights_": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.51.3",
41
+ "vocab_size": 30522
42
+ }
checkpoint-265/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91e89b6ec3ca68b80d5a63dd889e7abac68c35ff11edc084857cb6acd90e9fad
3
+ size 267847948
checkpoint-265/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672a5278e81c001a17230b84b8783e3f00d4d1bbda5d9c6ec4ef8c3768c7754c
3
+ size 535755130
checkpoint-265/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:013d13e4b269a8648da58d2f40bf48e004388ea0631771b8c8e588ab75375092
3
+ size 13990
checkpoint-265/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e4c4cef33a319fecd6991107d5735165ecc2806d559e7a9020ceb0f2dfce8ad
3
+ size 1064
checkpoint-265/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 212,
3
+ "best_metric": 0.5619047619047619,
4
+ "best_model_checkpoint": "./emotion_classifier/checkpoint-212",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 265,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9433962264150944,
14
+ "grad_norm": 3.0282411575317383,
15
+ "learning_rate": 1.6301886792452833e-05,
16
+ "loss": 1.6377,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.47619047619047616,
22
+ "eval_loss": 1.4806143045425415,
23
+ "eval_runtime": 2.5602,
24
+ "eval_samples_per_second": 41.012,
25
+ "eval_steps_per_second": 2.734,
26
+ "step": 53
27
+ },
28
+ {
29
+ "epoch": 1.8867924528301887,
30
+ "grad_norm": 5.8678812980651855,
31
+ "learning_rate": 1.2528301886792453e-05,
32
+ "loss": 1.4,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.5238095238095238,
38
+ "eval_loss": 1.3838814496994019,
39
+ "eval_runtime": 2.3279,
40
+ "eval_samples_per_second": 45.106,
41
+ "eval_steps_per_second": 3.007,
42
+ "step": 106
43
+ },
44
+ {
45
+ "epoch": 2.830188679245283,
46
+ "grad_norm": 4.850906848907471,
47
+ "learning_rate": 8.754716981132076e-06,
48
+ "loss": 1.2805,
49
+ "step": 150
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "eval_accuracy": 0.5238095238095238,
54
+ "eval_loss": 1.3527458906173706,
55
+ "eval_runtime": 2.4197,
56
+ "eval_samples_per_second": 43.394,
57
+ "eval_steps_per_second": 2.893,
58
+ "step": 159
59
+ },
60
+ {
61
+ "epoch": 3.7735849056603774,
62
+ "grad_norm": 5.995235919952393,
63
+ "learning_rate": 4.981132075471698e-06,
64
+ "loss": 1.1901,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.5619047619047619,
70
+ "eval_loss": 1.3129359483718872,
71
+ "eval_runtime": 2.3883,
72
+ "eval_samples_per_second": 43.964,
73
+ "eval_steps_per_second": 2.931,
74
+ "step": 212
75
+ },
76
+ {
77
+ "epoch": 4.716981132075472,
78
+ "grad_norm": 5.1387858390808105,
79
+ "learning_rate": 1.207547169811321e-06,
80
+ "loss": 1.1054,
81
+ "step": 250
82
+ },
83
+ {
84
+ "epoch": 5.0,
85
+ "eval_accuracy": 0.5619047619047619,
86
+ "eval_loss": 1.3082963228225708,
87
+ "eval_runtime": 2.8874,
88
+ "eval_samples_per_second": 36.365,
89
+ "eval_steps_per_second": 2.424,
90
+ "step": 265
91
+ }
92
+ ],
93
+ "logging_steps": 50,
94
+ "max_steps": 265,
95
+ "num_input_tokens_seen": 0,
96
+ "num_train_epochs": 5,
97
+ "save_steps": 500,
98
+ "stateful_callbacks": {
99
+ "TrainerControl": {
100
+ "args": {
101
+ "should_epoch_stop": false,
102
+ "should_evaluate": false,
103
+ "should_log": false,
104
+ "should_save": true,
105
+ "should_training_stop": true
106
+ },
107
+ "attributes": {}
108
+ }
109
+ },
110
+ "total_flos": 139103171020800.0,
111
+ "train_batch_size": 16,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-265/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9176974d5ca9307eaa01d489fefe68df96bb0a20f04f32ce3a207d3158a4f91d
3
+ size 5240
checkpoint-53/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5,
27
+ "LABEL_6": 6
28
+ },
29
+ "max_position_embeddings": 512,
30
+ "model_type": "distilbert",
31
+ "n_heads": 12,
32
+ "n_layers": 6,
33
+ "pad_token_id": 0,
34
+ "problem_type": "single_label_classification",
35
+ "qa_dropout": 0.1,
36
+ "seq_classif_dropout": 0.2,
37
+ "sinusoidal_pos_embds": false,
38
+ "tie_weights_": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.51.3",
41
+ "vocab_size": 30522
42
+ }
checkpoint-53/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0592d0c1503f64aec1f8fdf55535d5502ee1897a730a515560a943cb1043447d
3
+ size 267847948
checkpoint-53/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2a8bfe652da492f8a075be57243a9e4d4308b34c37484ae24a09ca6a092775
3
+ size 535755130
checkpoint-53/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b182573f61d8bcf5eaefcbf8f98d8734b6db51b44ad36aed3a305c431539fa1
3
+ size 13990
checkpoint-53/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5f63d83bd91fc8f839183eaded51a51404df88223c86067e72107f7fcf1d3f
3
+ size 1064
checkpoint-53/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 53,
3
+ "best_metric": 0.47619047619047616,
4
+ "best_model_checkpoint": "./emotion_classifier/checkpoint-53",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 53,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9433962264150944,
14
+ "grad_norm": 3.0282411575317383,
15
+ "learning_rate": 1.6301886792452833e-05,
16
+ "loss": 1.6377,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.47619047619047616,
22
+ "eval_loss": 1.4806143045425415,
23
+ "eval_runtime": 2.5602,
24
+ "eval_samples_per_second": 41.012,
25
+ "eval_steps_per_second": 2.734,
26
+ "step": 53
27
+ }
28
+ ],
29
+ "logging_steps": 50,
30
+ "max_steps": 265,
31
+ "num_input_tokens_seen": 0,
32
+ "num_train_epochs": 5,
33
+ "save_steps": 500,
34
+ "stateful_callbacks": {
35
+ "TrainerControl": {
36
+ "args": {
37
+ "should_epoch_stop": false,
38
+ "should_evaluate": false,
39
+ "should_log": false,
40
+ "should_save": true,
41
+ "should_training_stop": false
42
+ },
43
+ "attributes": {}
44
+ }
45
+ },
46
+ "total_flos": 27820634204160.0,
47
+ "train_batch_size": 16,
48
+ "trial_name": null,
49
+ "trial_params": null
50
+ }
checkpoint-53/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9176974d5ca9307eaa01d489fefe68df96bb0a20f04f32ce3a207d3158a4f91d
3
+ size 5240
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5,
27
+ "LABEL_6": 6
28
+ },
29
+ "max_position_embeddings": 512,
30
+ "model_type": "distilbert",
31
+ "n_heads": 12,
32
+ "n_layers": 6,
33
+ "pad_token_id": 0,
34
+ "problem_type": "single_label_classification",
35
+ "qa_dropout": 0.1,
36
+ "seq_classif_dropout": 0.2,
37
+ "sinusoidal_pos_embds": false,
38
+ "tie_weights_": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.51.3",
41
+ "vocab_size": 30522
42
+ }
label_encoder.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec0df84b82ac7d39a7922b4afdde8eac836d198673eb110dcf5ff29b6e6cb24
3
+ size 608
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05db532e969998d68aab84e8793f077254f48699ddef1b716bee5218b010da1d
3
+ size 267847948
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff