Hugging Face's logo

ChrisZeng
/
bart-base-detox

Text2Text Generation
Transformers
PyTorch
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
ChrisZeng commited on
Commit
1029249
•
1 Parent(s): 0e0612a

Training in progress, epoch 4

Browse files
Files changed (29) hide show
  1. checkpoint-540/added_tokens.json +1 -0
  2. checkpoint-540/config.json +75 -0
  3. checkpoint-540/merges.txt +0 -0
  4. checkpoint-540/optimizer.pt +3 -0
  5. checkpoint-540/pytorch_model.bin +3 -0
  6. checkpoint-540/rng_state.pth +3 -0
  7. checkpoint-540/scaler.pt +3 -0
  8. checkpoint-540/scheduler.pt +3 -0
  9. checkpoint-540/special_tokens_map.json +1 -0
  10. checkpoint-540/tokenizer.json +0 -0
  11. checkpoint-540/tokenizer_config.json +1 -0
  12. checkpoint-540/trainer_state.json +72 -0
  13. checkpoint-540/training_args.bin +3 -0
  14. checkpoint-540/vocab.json +0 -0
  15. checkpoint-675/added_tokens.json +1 -0
  16. checkpoint-675/config.json +75 -0
  17. checkpoint-675/merges.txt +0 -0
  18. checkpoint-675/optimizer.pt +3 -0
  19. checkpoint-675/pytorch_model.bin +3 -0
  20. checkpoint-675/rng_state.pth +3 -0
  21. checkpoint-675/scaler.pt +3 -0
  22. checkpoint-675/scheduler.pt +3 -0
  23. checkpoint-675/special_tokens_map.json +1 -0
  24. checkpoint-675/tokenizer.json +0 -0
  25. checkpoint-675/tokenizer_config.json +1 -0
  26. checkpoint-675/trainer_state.json +86 -0
  27. checkpoint-675/training_args.bin +3 -0
  28. checkpoint-675/vocab.json +0 -0
  29. pytorch_model.bin +1 -1
checkpoint-540/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<CSD>": 50265}
checkpoint-540/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.16.2",
73
+ "use_cache": false,
74
+ "vocab_size": 50266
75
+ }
checkpoint-540/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-540/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e08513b86007464454b0e6f18328f1276f7c2d917f8f3cb3bb5234e9f8f7895
3
+ size 1115518581
checkpoint-540/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3860f71d58616e27ca1900afe52e2e411611c1648789afb5252cd57b42fc6e7
3
+ size 557982265
checkpoint-540/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c547323ed257c61d2e479d22def4675ebd10a9ecd358e3ac63acba43a29617
3
+ size 14439
checkpoint-540/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d096d91e31597a145a97d111753c89cc74f06521f78aed16759faa745bc63ce2
3
+ size 559
checkpoint-540/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620db0493c00c974636df70310a208d6729ef8f4b083036c4ff9d8876742822e
3
+ size 623
checkpoint-540/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
checkpoint-540/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-540/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
checkpoint-540/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1801992505788803,
3
+ "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-405",
4
+ "epoch": 3.9953917050691246,
5
+ "global_step": 540,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 9e-05,
13
+ "loss": 0.3171,
14
+ "step": 135
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.20179320871829987,
19
+ "eval_runtime": 11.3072,
20
+ "eval_samples_per_second": 274.16,
21
+ "eval_steps_per_second": 34.314,
22
+ "step": 135
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 8e-05,
27
+ "loss": 0.1852,
28
+ "step": 270
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 0.18728719651699066,
33
+ "eval_runtime": 11.1563,
34
+ "eval_samples_per_second": 277.869,
35
+ "eval_steps_per_second": 34.778,
36
+ "step": 270
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 7e-05,
41
+ "loss": 0.1559,
42
+ "step": 405
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 0.1801992505788803,
47
+ "eval_runtime": 11.3199,
48
+ "eval_samples_per_second": 273.853,
49
+ "eval_steps_per_second": 34.276,
50
+ "step": 405
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6e-05,
55
+ "loss": 0.1356,
56
+ "step": 540
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 0.18711909651756287,
61
+ "eval_runtime": 11.3935,
62
+ "eval_samples_per_second": 272.085,
63
+ "eval_steps_per_second": 34.054,
64
+ "step": 540
65
+ }
66
+ ],
67
+ "max_steps": 1350,
68
+ "num_train_epochs": 10,
69
+ "total_flos": 2151917158809600.0,
70
+ "trial_name": null,
71
+ "trial_params": null
72
+ }
checkpoint-540/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6779c0d7bfc5cc8b7f502411db449902ffdb3fd6d5cc4758f90defaa037cdfa
3
+ size 3183
checkpoint-540/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-675/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<CSD>": 50265}
checkpoint-675/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.16.2",
73
+ "use_cache": false,
74
+ "vocab_size": 50266
75
+ }
checkpoint-675/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-675/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49af5e9c7dd614e4d00116982b296ee257dbf971f1a57bbcb84500a99f1807a9
3
+ size 1115518581
checkpoint-675/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c0b7edb05ead061300844844fa916cbd0b57a265d1a380edf9acac95207dca
3
+ size 557982265
checkpoint-675/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e1e419e80a08ccc5abfcc80e6770ed3fb193a0c24ad195b866574e04395575
3
+ size 14439
checkpoint-675/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32e75433385e2e326f07b54cdbe1de68a953598fb525f8fc80cbcb0c304157e
3
+ size 559
checkpoint-675/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e9983afbab69b9507144eb907b7e9dfda252407067d2de1aca1d814dc47366
3
+ size 623
checkpoint-675/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
checkpoint-675/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-675/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
checkpoint-675/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1801992505788803,
3
+ "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-405",
4
+ "epoch": 4.9953917050691246,
5
+ "global_step": 675,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 9e-05,
13
+ "loss": 0.3171,
14
+ "step": 135
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.20179320871829987,
19
+ "eval_runtime": 11.3072,
20
+ "eval_samples_per_second": 274.16,
21
+ "eval_steps_per_second": 34.314,
22
+ "step": 135
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 8e-05,
27
+ "loss": 0.1852,
28
+ "step": 270
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 0.18728719651699066,
33
+ "eval_runtime": 11.1563,
34
+ "eval_samples_per_second": 277.869,
35
+ "eval_steps_per_second": 34.778,
36
+ "step": 270
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 7e-05,
41
+ "loss": 0.1559,
42
+ "step": 405
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 0.1801992505788803,
47
+ "eval_runtime": 11.3199,
48
+ "eval_samples_per_second": 273.853,
49
+ "eval_steps_per_second": 34.276,
50
+ "step": 405
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6e-05,
55
+ "loss": 0.1356,
56
+ "step": 540
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 0.18711909651756287,
61
+ "eval_runtime": 11.3935,
62
+ "eval_samples_per_second": 272.085,
63
+ "eval_steps_per_second": 34.054,
64
+ "step": 540
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 5e-05,
69
+ "loss": 0.1151,
70
+ "step": 675
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 0.19263018667697906,
75
+ "eval_runtime": 11.4175,
76
+ "eval_samples_per_second": 271.514,
77
+ "eval_steps_per_second": 33.983,
78
+ "step": 675
79
+ }
80
+ ],
81
+ "max_steps": 1350,
82
+ "num_train_epochs": 10,
83
+ "total_flos": 2689437955276800.0,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }
checkpoint-675/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6779c0d7bfc5cc8b7f502411db449902ffdb3fd6d5cc4758f90defaa037cdfa
3
+ size 3183
checkpoint-675/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b214a195ba865a570b4c0ca7858a07d3cdf972c6a40b69118e204806f82334d3
3
  size 557982265
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c0b7edb05ead061300844844fa916cbd0b57a265d1a380edf9acac95207dca
3
  size 557982265