Hugging Face's logo

ChrisZeng
/
t5-base-detox

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
ChrisZeng commited on
Commit
2ee38ae
·
1 Parent(s): ef9f7b0

Training in progress, epoch 8

Browse files
Files changed (27) hide show
  1. checkpoint-1080/added_tokens.json +1 -0
  2. checkpoint-1080/config.json +57 -0
  3. checkpoint-1080/optimizer.pt +3 -0
  4. checkpoint-1080/pytorch_model.bin +3 -0
  5. checkpoint-1080/rng_state.pth +3 -0
  6. checkpoint-1080/scaler.pt +3 -0
  7. checkpoint-1080/scheduler.pt +3 -0
  8. checkpoint-1080/special_tokens_map.json +1 -0
  9. checkpoint-1080/spiece.model +3 -0
  10. checkpoint-1080/tokenizer.json +0 -0
  11. checkpoint-1080/tokenizer_config.json +1 -0
  12. checkpoint-1080/trainer_state.json +128 -0
  13. checkpoint-1080/training_args.bin +3 -0
  14. checkpoint-1215/added_tokens.json +1 -0
  15. checkpoint-1215/config.json +57 -0
  16. checkpoint-1215/optimizer.pt +3 -0
  17. checkpoint-1215/pytorch_model.bin +3 -0
  18. checkpoint-1215/rng_state.pth +3 -0
  19. checkpoint-1215/scaler.pt +3 -0
  20. checkpoint-1215/scheduler.pt +3 -0
  21. checkpoint-1215/special_tokens_map.json +1 -0
  22. checkpoint-1215/spiece.model +3 -0
  23. checkpoint-1215/tokenizer.json +0 -0
  24. checkpoint-1215/tokenizer_config.json +1 -0
  25. checkpoint-1215/trainer_state.json +142 -0
  26. checkpoint-1215/training_args.bin +3 -0
  27. pytorch_model.bin +1 -1
checkpoint-1080/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<CSD>": 32100}
checkpoint-1080/config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_num_buckets": 32,
24
+ "task_specific_params": {
25
+ "summarization": {
26
+ "early_stopping": true,
27
+ "length_penalty": 2.0,
28
+ "max_length": 200,
29
+ "min_length": 30,
30
+ "no_repeat_ngram_size": 3,
31
+ "num_beams": 4,
32
+ "prefix": "summarize: "
33
+ },
34
+ "translation_en_to_de": {
35
+ "early_stopping": true,
36
+ "max_length": 300,
37
+ "num_beams": 4,
38
+ "prefix": "translate English to German: "
39
+ },
40
+ "translation_en_to_fr": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to French: "
45
+ },
46
+ "translation_en_to_ro": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to Romanian: "
51
+ }
52
+ },
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.16.2",
55
+ "use_cache": false,
56
+ "vocab_size": 32101
57
+ }
checkpoint-1080/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a97952c74a72a42d189977180da116e265f2d4b3c4c3dda4aa3c917ccccc1d2a
3
+ size 1783211965
checkpoint-1080/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59597b51f52e30b9d677a4b54804f5529a0faac7c9038fa52a11b03b0a81312
3
+ size 891647935
checkpoint-1080/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:346c71347b627e73b2dd572eebffe8941552696793033a913b33e9918bbf5548
3
+ size 14503
checkpoint-1080/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7294b723d1608e8cf3da6ce0726a04855b79985c3ebafaf36dd6741746296a78
3
+ size 559
checkpoint-1080/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f9b348148b9404354565dad1cbc9460c88629080ec8d19f30b616d23086843
3
+ size 623
checkpoint-1080/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
checkpoint-1080/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-1080/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1080/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base", "tokenizer_class": "T5Tokenizer"}
checkpoint-1080/trainer_state.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2617154121398926,
3
+ "best_model_checkpoint": "outputs/t5-base-detox/checkpoint-1080",
4
+ "epoch": 7.9953917050691246,
5
+ "global_step": 1080,
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": 1.337,
14
+ "step": 135
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.48098286986351013,
19
+ "eval_runtime": 18.2812,
20
+ "eval_samples_per_second": 169.573,
21
+ "eval_steps_per_second": 21.224,
22
+ "step": 135
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 8e-05,
27
+ "loss": 0.5238,
28
+ "step": 270
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 0.38857772946357727,
33
+ "eval_runtime": 18.7764,
34
+ "eval_samples_per_second": 165.101,
35
+ "eval_steps_per_second": 20.664,
36
+ "step": 270
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 7e-05,
41
+ "loss": 0.4301,
42
+ "step": 405
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 0.33775028586387634,
47
+ "eval_runtime": 18.505,
48
+ "eval_samples_per_second": 167.522,
49
+ "eval_steps_per_second": 20.967,
50
+ "step": 405
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6e-05,
55
+ "loss": 0.3755,
56
+ "step": 540
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 0.31217730045318604,
61
+ "eval_runtime": 18.8887,
62
+ "eval_samples_per_second": 164.119,
63
+ "eval_steps_per_second": 20.541,
64
+ "step": 540
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 5e-05,
69
+ "loss": 0.3359,
70
+ "step": 675
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 0.2910080552101135,
75
+ "eval_runtime": 18.2985,
76
+ "eval_samples_per_second": 169.413,
77
+ "eval_steps_per_second": 21.204,
78
+ "step": 675
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 4e-05,
83
+ "loss": 0.3068,
84
+ "step": 810
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 0.2737014591693878,
89
+ "eval_runtime": 18.6417,
90
+ "eval_samples_per_second": 166.294,
91
+ "eval_steps_per_second": 20.814,
92
+ "step": 810
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 3e-05,
97
+ "loss": 0.2861,
98
+ "step": 945
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 0.2709713876247406,
103
+ "eval_runtime": 18.2786,
104
+ "eval_samples_per_second": 169.597,
105
+ "eval_steps_per_second": 21.227,
106
+ "step": 945
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 2e-05,
111
+ "loss": 0.2744,
112
+ "step": 1080
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 0.2617154121398926,
117
+ "eval_runtime": 18.6478,
118
+ "eval_samples_per_second": 166.24,
119
+ "eval_steps_per_second": 20.807,
120
+ "step": 1080
121
+ }
122
+ ],
123
+ "max_steps": 1350,
124
+ "num_train_epochs": 10,
125
+ "total_flos": 9351223972208640.0,
126
+ "trial_name": null,
127
+ "trial_params": null
128
+ }
checkpoint-1080/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ceb7f0869ed2740615ac6ff98c0dd315d6a44ecbb6fe70eac15c7cbab0a4b65
3
+ size 3183
checkpoint-1215/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<CSD>": 32100}
checkpoint-1215/config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_num_buckets": 32,
24
+ "task_specific_params": {
25
+ "summarization": {
26
+ "early_stopping": true,
27
+ "length_penalty": 2.0,
28
+ "max_length": 200,
29
+ "min_length": 30,
30
+ "no_repeat_ngram_size": 3,
31
+ "num_beams": 4,
32
+ "prefix": "summarize: "
33
+ },
34
+ "translation_en_to_de": {
35
+ "early_stopping": true,
36
+ "max_length": 300,
37
+ "num_beams": 4,
38
+ "prefix": "translate English to German: "
39
+ },
40
+ "translation_en_to_fr": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to French: "
45
+ },
46
+ "translation_en_to_ro": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to Romanian: "
51
+ }
52
+ },
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.16.2",
55
+ "use_cache": false,
56
+ "vocab_size": 32101
57
+ }
checkpoint-1215/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1421c05eb55cd7c02063060d7929e4088b9782e5c4b76b81ae0d6cb8ce917831
3
+ size 1783211965
checkpoint-1215/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e8a9dcc693d6c64947e68d4a7b157c858e50efa2e3c88de5982750361303fa
3
+ size 891647935
checkpoint-1215/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c7281f1835339bcbb250263c566c1bd9ae640eebb9a4c56e78739fd461c3b8
3
+ size 14503
checkpoint-1215/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ee64f81e11fb4023ccce5a8bcfb0e976197229db0e4af837461055e0a9d041
3
+ size 559
checkpoint-1215/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124e123bacd421f8436683b2136339433bc2069c1bc5dbf733c5278f6e00a37e
3
+ size 623
checkpoint-1215/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
checkpoint-1215/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-1215/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1215/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base", "tokenizer_class": "T5Tokenizer"}
checkpoint-1215/trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2617154121398926,
3
+ "best_model_checkpoint": "outputs/t5-base-detox/checkpoint-1080",
4
+ "epoch": 8.995391705069125,
5
+ "global_step": 1215,
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": 1.337,
14
+ "step": 135
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.48098286986351013,
19
+ "eval_runtime": 18.2812,
20
+ "eval_samples_per_second": 169.573,
21
+ "eval_steps_per_second": 21.224,
22
+ "step": 135
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 8e-05,
27
+ "loss": 0.5238,
28
+ "step": 270
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 0.38857772946357727,
33
+ "eval_runtime": 18.7764,
34
+ "eval_samples_per_second": 165.101,
35
+ "eval_steps_per_second": 20.664,
36
+ "step": 270
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 7e-05,
41
+ "loss": 0.4301,
42
+ "step": 405
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 0.33775028586387634,
47
+ "eval_runtime": 18.505,
48
+ "eval_samples_per_second": 167.522,
49
+ "eval_steps_per_second": 20.967,
50
+ "step": 405
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6e-05,
55
+ "loss": 0.3755,
56
+ "step": 540
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 0.31217730045318604,
61
+ "eval_runtime": 18.8887,
62
+ "eval_samples_per_second": 164.119,
63
+ "eval_steps_per_second": 20.541,
64
+ "step": 540
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 5e-05,
69
+ "loss": 0.3359,
70
+ "step": 675
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 0.2910080552101135,
75
+ "eval_runtime": 18.2985,
76
+ "eval_samples_per_second": 169.413,
77
+ "eval_steps_per_second": 21.204,
78
+ "step": 675
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 4e-05,
83
+ "loss": 0.3068,
84
+ "step": 810
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 0.2737014591693878,
89
+ "eval_runtime": 18.6417,
90
+ "eval_samples_per_second": 166.294,
91
+ "eval_steps_per_second": 20.814,
92
+ "step": 810
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 3e-05,
97
+ "loss": 0.2861,
98
+ "step": 945
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 0.2709713876247406,
103
+ "eval_runtime": 18.2786,
104
+ "eval_samples_per_second": 169.597,
105
+ "eval_steps_per_second": 21.227,
106
+ "step": 945
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 2e-05,
111
+ "loss": 0.2744,
112
+ "step": 1080
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 0.2617154121398926,
117
+ "eval_runtime": 18.6478,
118
+ "eval_samples_per_second": 166.24,
119
+ "eval_steps_per_second": 20.807,
120
+ "step": 1080
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "learning_rate": 1e-05,
125
+ "loss": 0.2649,
126
+ "step": 1215
127
+ },
128
+ {
129
+ "epoch": 9.0,
130
+ "eval_loss": 0.2630476653575897,
131
+ "eval_runtime": 18.456,
132
+ "eval_samples_per_second": 167.967,
133
+ "eval_steps_per_second": 21.023,
134
+ "step": 1215
135
+ }
136
+ ],
137
+ "max_steps": 1350,
138
+ "num_train_epochs": 10,
139
+ "total_flos": 1.052005203836928e+16,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
checkpoint-1215/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ceb7f0869ed2740615ac6ff98c0dd315d6a44ecbb6fe70eac15c7cbab0a4b65
3
+ size 3183
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:048c3d40567f94ccf1868541ecba24f916c86643833dec36cd5189710c80a2ef
3
  size 891647935
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e8a9dcc693d6c64947e68d4a7b157c858e50efa2e3c88de5982750361303fa
3
  size 891647935