Hugging Face's logo

ducdatit2002
/
cybersoft

Safetensors
Model card Files
xet
 Community
ducdatit2002 commited on
Commit
a5a03e9
·
verified ·
1 Parent(s): 68865d1

Add files using upload-large-folder tool

Browse files
Files changed (16) hide show
  1. checkpoint-16/config.json +60 -0
  2. checkpoint-16/model.safetensors +3 -0
  3. checkpoint-16/optimizer.pt +3 -0
  4. checkpoint-16/rng_state.pth +3 -0
  5. checkpoint-16/scaler.pt +3 -0
  6. checkpoint-16/scheduler.pt +3 -0
  7. checkpoint-16/trainer_state.json +81 -0
  8. checkpoint-16/training_args.bin +3 -0
  9. checkpoint-20/config.json +60 -0
  10. checkpoint-20/model.safetensors +3 -0
  11. checkpoint-20/optimizer.pt +3 -0
  12. checkpoint-20/rng_state.pth +3 -0
  13. checkpoint-20/scaler.pt +3 -0
  14. checkpoint-20/scheduler.pt +3 -0
  15. checkpoint-20/trainer_state.json +98 -0
  16. checkpoint-20/training_args.bin +3 -0
checkpoint-16/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_window": [
8
+ 256,
9
+ 256,
10
+ 256,
11
+ 256,
12
+ 256,
13
+ 256,
14
+ 256,
15
+ 256,
16
+ 256,
17
+ 256,
18
+ 256,
19
+ 256
20
+ ],
21
+ "bos_token_id": 0,
22
+ "classifier_dropout": null,
23
+ "dtype": "float32",
24
+ "eos_token_id": 2,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "ai_noi_bo",
31
+ "1": "bao_mat_du_lieu",
32
+ "2": "cong_tac_chi_phi",
33
+ "3": "email_thiet_bi",
34
+ "4": "nghi_phep_remote"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": false,
39
+ "label2id": {
40
+ "ai_noi_bo": 0,
41
+ "bao_mat_du_lieu": 1,
42
+ "cong_tac_chi_phi": 2,
43
+ "email_thiet_bi": 3,
44
+ "nghi_phep_remote": 4
45
+ },
46
+ "layer_norm_eps": 1e-05,
47
+ "max_position_embeddings": 4098,
48
+ "model_type": "roberta",
49
+ "num_attention_heads": 12,
50
+ "num_hidden_layers": 12,
51
+ "pad_token_id": 1,
52
+ "position_embedding_type": "absolute",
53
+ "problem_type": "single_label_classification",
54
+ "tie_word_embeddings": true,
55
+ "tokenizer_class": "PhobertTokenizer",
56
+ "transformers_version": "5.0.0",
57
+ "type_vocab_size": 1,
58
+ "use_cache": false,
59
+ "vocab_size": 64001
60
+ }
checkpoint-16/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a5c0e61631b46e2c9c69239a8d848ffa24b2d91b70f68e89918ac779b4c3343
3
+ size 551829068
checkpoint-16/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48c2aa96bf82527a06c1eb4f34f1a1f15c99fc940eb3fd86d666e700002fe8c
3
+ size 1103781259
checkpoint-16/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ab2d9107baa355af1573b5689a2f66e66bde7bcb847f245fb41341610115b01
3
+ size 14645
checkpoint-16/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dc666c0331d9a6d320f2d288266b395472e5fb0b0e514f38cfaecf8286f6ee4
3
+ size 1383
checkpoint-16/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb7afd8f1e7a447cf1bd96cd081257238c7029c620b7cec4de1e9475cb8abfb
3
+ size 1465
checkpoint-16/trainer_state.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 16,
3
+ "best_metric": 0.9664335664335665,
4
+ "best_model_checkpoint": "/content/longformer_vietnamese_policy_model/checkpoint-16",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 16,
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": 0.3870967741935484,
15
+ "eval_f1_macro": 0.22135076252723312,
16
+ "eval_loss": 1.569871187210083,
17
+ "eval_runtime": 1.6168,
18
+ "eval_samples_per_second": 19.174,
19
+ "eval_steps_per_second": 2.474,
20
+ "step": 4
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.3870967741935484,
25
+ "eval_f1_macro": 0.2541666666666667,
26
+ "eval_loss": 1.5102384090423584,
27
+ "eval_runtime": 1.6207,
28
+ "eval_samples_per_second": 19.127,
29
+ "eval_steps_per_second": 2.468,
30
+ "step": 8
31
+ },
32
+ {
33
+ "epoch": 2.533333333333333,
34
+ "grad_norm": 8.057486534118652,
35
+ "learning_rate": 1.1000000000000001e-05,
36
+ "loss": 5.993505477905273,
37
+ "step": 10
38
+ },
39
+ {
40
+ "epoch": 3.0,
41
+ "eval_accuracy": 0.8387096774193549,
42
+ "eval_f1_macro": 0.8164335664335665,
43
+ "eval_loss": 1.4431389570236206,
44
+ "eval_runtime": 1.6485,
45
+ "eval_samples_per_second": 18.805,
46
+ "eval_steps_per_second": 2.426,
47
+ "step": 12
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_accuracy": 0.967741935483871,
52
+ "eval_f1_macro": 0.9664335664335665,
53
+ "eval_loss": 1.371219515800476,
54
+ "eval_runtime": 1.6491,
55
+ "eval_samples_per_second": 18.798,
56
+ "eval_steps_per_second": 2.426,
57
+ "step": 16
58
+ }
59
+ ],
60
+ "logging_steps": 10,
61
+ "max_steps": 20,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 5,
64
+ "save_steps": 500,
65
+ "stateful_callbacks": {
66
+ "TrainerControl": {
67
+ "args": {
68
+ "should_epoch_stop": false,
69
+ "should_evaluate": false,
70
+ "should_log": false,
71
+ "should_save": true,
72
+ "should_training_stop": false
73
+ },
74
+ "attributes": {}
75
+ }
76
+ },
77
+ "total_flos": 1204028619915264.0,
78
+ "train_batch_size": 10,
79
+ "trial_name": null,
80
+ "trial_params": null
81
+ }
checkpoint-16/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25c214ceb0e00825e244feb1ef3809920292a3d4d139a79fb1e7eba5025c2ce2
3
+ size 5201
checkpoint-20/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_window": [
8
+ 256,
9
+ 256,
10
+ 256,
11
+ 256,
12
+ 256,
13
+ 256,
14
+ 256,
15
+ 256,
16
+ 256,
17
+ 256,
18
+ 256,
19
+ 256
20
+ ],
21
+ "bos_token_id": 0,
22
+ "classifier_dropout": null,
23
+ "dtype": "float32",
24
+ "eos_token_id": 2,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "ai_noi_bo",
31
+ "1": "bao_mat_du_lieu",
32
+ "2": "cong_tac_chi_phi",
33
+ "3": "email_thiet_bi",
34
+ "4": "nghi_phep_remote"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": false,
39
+ "label2id": {
40
+ "ai_noi_bo": 0,
41
+ "bao_mat_du_lieu": 1,
42
+ "cong_tac_chi_phi": 2,
43
+ "email_thiet_bi": 3,
44
+ "nghi_phep_remote": 4
45
+ },
46
+ "layer_norm_eps": 1e-05,
47
+ "max_position_embeddings": 4098,
48
+ "model_type": "roberta",
49
+ "num_attention_heads": 12,
50
+ "num_hidden_layers": 12,
51
+ "pad_token_id": 1,
52
+ "position_embedding_type": "absolute",
53
+ "problem_type": "single_label_classification",
54
+ "tie_word_embeddings": true,
55
+ "tokenizer_class": "PhobertTokenizer",
56
+ "transformers_version": "5.0.0",
57
+ "type_vocab_size": 1,
58
+ "use_cache": false,
59
+ "vocab_size": 64001
60
+ }
checkpoint-20/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8777a81a52c382fe2d5e24e101eac168c58eceeca9a0280dbaf70ffa4e0798cb
3
+ size 551829068
checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6628834acf8d96be28efd6196fcb5a51c7750ccc25441f92a253d6ba24b8ec00
3
+ size 1103781259
checkpoint-20/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b556c2af8fd67d52f416b72108780951eec6c08098ccc785e8c008198c88e25d
3
+ size 14645
checkpoint-20/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21673eeb28fb4ccb180bab2939a00ebf15ea8d9cc574d32f9e3a4fa016c4b837
3
+ size 1383
checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5420d573129b182fabd13c1b58758649a399d991b05570cc2c5d7e8dfff195
3
+ size 1465
checkpoint-20/trainer_state.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 16,
3
+ "best_metric": 0.9664335664335665,
4
+ "best_model_checkpoint": "/content/longformer_vietnamese_policy_model/checkpoint-16",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 20,
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": 0.3870967741935484,
15
+ "eval_f1_macro": 0.22135076252723312,
16
+ "eval_loss": 1.569871187210083,
17
+ "eval_runtime": 1.6168,
18
+ "eval_samples_per_second": 19.174,
19
+ "eval_steps_per_second": 2.474,
20
+ "step": 4
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.3870967741935484,
25
+ "eval_f1_macro": 0.2541666666666667,
26
+ "eval_loss": 1.5102384090423584,
27
+ "eval_runtime": 1.6207,
28
+ "eval_samples_per_second": 19.127,
29
+ "eval_steps_per_second": 2.468,
30
+ "step": 8
31
+ },
32
+ {
33
+ "epoch": 2.533333333333333,
34
+ "grad_norm": 8.057486534118652,
35
+ "learning_rate": 1.1000000000000001e-05,
36
+ "loss": 5.993505477905273,
37
+ "step": 10
38
+ },
39
+ {
40
+ "epoch": 3.0,
41
+ "eval_accuracy": 0.8387096774193549,
42
+ "eval_f1_macro": 0.8164335664335665,
43
+ "eval_loss": 1.4431389570236206,
44
+ "eval_runtime": 1.6485,
45
+ "eval_samples_per_second": 18.805,
46
+ "eval_steps_per_second": 2.426,
47
+ "step": 12
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_accuracy": 0.967741935483871,
52
+ "eval_f1_macro": 0.9664335664335665,
53
+ "eval_loss": 1.371219515800476,
54
+ "eval_runtime": 1.6491,
55
+ "eval_samples_per_second": 18.798,
56
+ "eval_steps_per_second": 2.426,
57
+ "step": 16
58
+ },
59
+ {
60
+ "epoch": 5.0,
61
+ "grad_norm": 13.052608489990234,
62
+ "learning_rate": 1.0000000000000002e-06,
63
+ "loss": 5.292376327514648,
64
+ "step": 20
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "eval_accuracy": 0.967741935483871,
69
+ "eval_f1_macro": 0.9664335664335665,
70
+ "eval_loss": 1.3547754287719727,
71
+ "eval_runtime": 1.6289,
72
+ "eval_samples_per_second": 19.032,
73
+ "eval_steps_per_second": 2.456,
74
+ "step": 20
75
+ }
76
+ ],
77
+ "logging_steps": 10,
78
+ "max_steps": 20,
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": true
90
+ },
91
+ "attributes": {}
92
+ }
93
+ },
94
+ "total_flos": 1505035774894080.0,
95
+ "train_batch_size": 10,
96
+ "trial_name": null,
97
+ "trial_params": null
98
+ }
checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25c214ceb0e00825e244feb1ef3809920292a3d4d139a79fb1e7eba5025c2ce2
3
+ size 5201