Hugging Face's logo

lmeninato
/
t5-small-codesearchnet-python-archive

Transformers
PyTorch
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
1
lmeninato commited on
Commit
1cef2e7
·
1 Parent(s): 3e65d5c

initial commit

Browse files
Files changed (21) hide show
  1. .gitignore +1 -0
  2. README.md +49 -0
  3. config copy.json +60 -0
  4. config.json +60 -0
  5. generation_config copy.json +7 -0
  6. generation_config.json +7 -0
  7. optimizer.pt +3 -0
  8. pytorch_model copy.bin +3 -0
  9. pytorch_model.bin +3 -0
  10. rng_state.pth +3 -0
  11. scheduler.pt +3 -0
  12. special_tokens_map copy.json +107 -0
  13. special_tokens_map.json +107 -0
  14. spiece.model +3 -0
  15. tokenizer copy.json +0 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config copy.json +113 -0
  18. tokenizer_config.json +113 -0
  19. trainer_state.json +676 -0
  20. training_args copy.bin +3 -0
  21. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: output
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # output
14
+
15
+ This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 5e-05
35
+ - train_batch_size: 64
36
+ - eval_batch_size: 64
37
+ - seed: 42
38
+ - gradient_accumulation_steps: 16
39
+ - total_train_batch_size: 1024
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 100
43
+
44
+ ### Framework versions
45
+
46
+ - Transformers 4.26.1
47
+ - Pytorch 1.13.1+cu117
48
+ - Datasets 2.9.0
49
+ - Tokenizers 0.13.3
config copy.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 6,
21
+ "num_heads": 8,
22
+ "num_layers": 6,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.26.1",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 6,
21
+ "num_heads": 8,
22
+ "num_layers": 6,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.26.1",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
generation_config copy.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.26.1"
7
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.26.1"
7
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac30688693603a690577985ba46853d5af2581cd10d11bba2e71bc12cc520765
3
+ size 839173
pytorch_model copy.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5930aef0944df309aa5b430269084fa239e73618762ce0cb39a64951ab0d71
3
+ size 242069785
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d56fe27783ddfbec93b40e874e5710200766c06db63268fa648e75516f88297
3
+ size 242071641
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:929d160ed17497fe5d2a0878422cede4ee11fffcd13da3eaa900e59a9a0ef7dd
3
+ size 15597
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f87e13bc338ee2344c1c2806de9ee7b7d096753d1c5e8c776977ec643d5aea
3
+ size 881
special_tokens_map copy.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer copy.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config copy.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "name_or_path": "t5-small",
109
+ "pad_token": "<pad>",
110
+ "special_tokens_map_file": null,
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "name_or_path": "t5-small",
109
+ "pad_token": "<pad>",
110
+ "special_tokens_map_file": null,
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }
trainer_state.json ADDED
@@ -0,0 +1,676 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 13.44,
5
+ "global_step": 42000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16,
12
+ "learning_rate": 0.011603174731135368,
13
+ "loss": 1.5357,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.32,
18
+ "learning_rate": 0.023230696097016335,
19
+ "loss": 0.0593,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.48,
24
+ "learning_rate": 0.034898791462183,
25
+ "loss": 0.0531,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.64,
30
+ "learning_rate": 0.04661125689744949,
31
+ "loss": 0.044,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.8,
36
+ "learning_rate": 0.05841406062245369,
37
+ "loss": 0.0461,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.96,
42
+ "learning_rate": 0.07035055011510849,
43
+ "loss": 0.0433,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_avg_length": 17.2926,
49
+ "eval_bleu": 0.0241,
50
+ "eval_loss": 0.06959044933319092,
51
+ "eval_rouge1": 0.5901,
52
+ "eval_rouge2": 0.5715,
53
+ "eval_runtime": 56.7394,
54
+ "eval_samples_per_second": 88.122,
55
+ "eval_steps_per_second": 2.767,
56
+ "step": 3125
57
+ },
58
+ {
59
+ "epoch": 1.12,
60
+ "learning_rate": 0.08241234719753265,
61
+ "loss": 0.0408,
62
+ "step": 3500
63
+ },
64
+ {
65
+ "epoch": 1.28,
66
+ "learning_rate": 0.09467849135398865,
67
+ "loss": 0.0406,
68
+ "step": 4000
69
+ },
70
+ {
71
+ "epoch": 1.44,
72
+ "learning_rate": 0.10735532641410828,
73
+ "loss": 0.0445,
74
+ "step": 4500
75
+ },
76
+ {
77
+ "epoch": 1.6,
78
+ "learning_rate": 0.12028851360082626,
79
+ "loss": 0.0406,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.76,
84
+ "learning_rate": 0.13352635502815247,
85
+ "loss": 0.0405,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 1.92,
90
+ "learning_rate": 0.1470595896244049,
91
+ "loss": 0.0412,
92
+ "step": 6000
93
+ },
94
+ {
95
+ "epoch": 2.0,
96
+ "eval_avg_length": 17.3172,
97
+ "eval_bleu": 0.0237,
98
+ "eval_loss": 0.07180308550596237,
99
+ "eval_rouge1": 0.5879,
100
+ "eval_rouge2": 0.5692,
101
+ "eval_runtime": 55.7642,
102
+ "eval_samples_per_second": 89.663,
103
+ "eval_steps_per_second": 2.815,
104
+ "step": 6250
105
+ },
106
+ {
107
+ "epoch": 2.08,
108
+ "learning_rate": 0.16096152365207672,
109
+ "loss": 0.0395,
110
+ "step": 6500
111
+ },
112
+ {
113
+ "epoch": 2.24,
114
+ "learning_rate": 0.17507727444171906,
115
+ "loss": 0.0407,
116
+ "step": 7000
117
+ },
118
+ {
119
+ "epoch": 2.4,
120
+ "learning_rate": 0.18983061611652374,
121
+ "loss": 0.0393,
122
+ "step": 7500
123
+ },
124
+ {
125
+ "epoch": 2.56,
126
+ "learning_rate": 0.2049846649169922,
127
+ "loss": 0.0401,
128
+ "step": 8000
129
+ },
130
+ {
131
+ "epoch": 2.72,
132
+ "learning_rate": 0.22153085470199585,
133
+ "loss": 0.0414,
134
+ "step": 8500
135
+ },
136
+ {
137
+ "epoch": 2.88,
138
+ "learning_rate": 0.23806197941303253,
139
+ "loss": 0.0425,
140
+ "step": 9000
141
+ },
142
+ {
143
+ "epoch": 3.0,
144
+ "eval_avg_length": 17.3112,
145
+ "eval_bleu": 0.0237,
146
+ "eval_loss": 0.07267959415912628,
147
+ "eval_rouge1": 0.5871,
148
+ "eval_rouge2": 0.5681,
149
+ "eval_runtime": 54.2458,
150
+ "eval_samples_per_second": 92.173,
151
+ "eval_steps_per_second": 2.894,
152
+ "step": 9375
153
+ },
154
+ {
155
+ "epoch": 3.04,
156
+ "learning_rate": 0.2547408640384674,
157
+ "loss": 0.0393,
158
+ "step": 9500
159
+ },
160
+ {
161
+ "epoch": 3.2,
162
+ "learning_rate": 0.27236127853393555,
163
+ "loss": 0.0377,
164
+ "step": 10000
165
+ },
166
+ {
167
+ "epoch": 3.36,
168
+ "learning_rate": 0.26978379487991333,
169
+ "loss": 0.0372,
170
+ "step": 10500
171
+ },
172
+ {
173
+ "epoch": 3.52,
174
+ "learning_rate": 0.26798078417778015,
175
+ "loss": 0.0383,
176
+ "step": 11000
177
+ },
178
+ {
179
+ "epoch": 3.68,
180
+ "learning_rate": 0.2658974826335907,
181
+ "loss": 0.0391,
182
+ "step": 11500
183
+ },
184
+ {
185
+ "epoch": 3.84,
186
+ "learning_rate": 0.2626633942127228,
187
+ "loss": 0.0392,
188
+ "step": 12000
189
+ },
190
+ {
191
+ "epoch": 4.0,
192
+ "learning_rate": 0.26069551706314087,
193
+ "loss": 0.0381,
194
+ "step": 12500
195
+ },
196
+ {
197
+ "epoch": 4.0,
198
+ "eval_avg_length": 17.321,
199
+ "eval_bleu": 0.0238,
200
+ "eval_loss": 0.07149858772754669,
201
+ "eval_rouge1": 0.5866,
202
+ "eval_rouge2": 0.5677,
203
+ "eval_runtime": 52.6009,
204
+ "eval_samples_per_second": 95.055,
205
+ "eval_steps_per_second": 2.985,
206
+ "step": 12500
207
+ },
208
+ {
209
+ "epoch": 4.16,
210
+ "learning_rate": 0.25828537344932556,
211
+ "loss": 0.0341,
212
+ "step": 13000
213
+ },
214
+ {
215
+ "epoch": 4.32,
216
+ "learning_rate": 0.2559824585914612,
217
+ "loss": 0.0323,
218
+ "step": 13500
219
+ },
220
+ {
221
+ "epoch": 4.48,
222
+ "learning_rate": 0.2536338269710541,
223
+ "loss": 0.0316,
224
+ "step": 14000
225
+ },
226
+ {
227
+ "epoch": 4.64,
228
+ "learning_rate": 0.2517462372779846,
229
+ "loss": 0.0314,
230
+ "step": 14500
231
+ },
232
+ {
233
+ "epoch": 4.8,
234
+ "learning_rate": 0.25038695335388184,
235
+ "loss": 0.0317,
236
+ "step": 15000
237
+ },
238
+ {
239
+ "epoch": 4.96,
240
+ "learning_rate": 0.24828433990478516,
241
+ "loss": 0.0334,
242
+ "step": 15500
243
+ },
244
+ {
245
+ "epoch": 5.0,
246
+ "eval_avg_length": 17.3102,
247
+ "eval_bleu": 0.0237,
248
+ "eval_loss": 0.07320648431777954,
249
+ "eval_rouge1": 0.5873,
250
+ "eval_rouge2": 0.5682,
251
+ "eval_runtime": 52.0328,
252
+ "eval_samples_per_second": 96.093,
253
+ "eval_steps_per_second": 3.017,
254
+ "step": 15625
255
+ },
256
+ {
257
+ "epoch": 5.12,
258
+ "learning_rate": 0.24564550817012787,
259
+ "loss": 0.028,
260
+ "step": 16000
261
+ },
262
+ {
263
+ "epoch": 5.28,
264
+ "learning_rate": 0.24398992955684662,
265
+ "loss": 0.0279,
266
+ "step": 16500
267
+ },
268
+ {
269
+ "epoch": 5.44,
270
+ "learning_rate": 0.24214749038219452,
271
+ "loss": 0.0277,
272
+ "step": 17000
273
+ },
274
+ {
275
+ "epoch": 5.6,
276
+ "learning_rate": 0.24071773886680603,
277
+ "loss": 0.0302,
278
+ "step": 17500
279
+ },
280
+ {
281
+ "epoch": 5.76,
282
+ "learning_rate": 0.23937062919139862,
283
+ "loss": 0.0268,
284
+ "step": 18000
285
+ },
286
+ {
287
+ "epoch": 5.92,
288
+ "learning_rate": 0.23846393823623657,
289
+ "loss": 0.0293,
290
+ "step": 18500
291
+ },
292
+ {
293
+ "epoch": 6.0,
294
+ "eval_avg_length": 17.306,
295
+ "eval_bleu": 0.0237,
296
+ "eval_loss": 0.07230091094970703,
297
+ "eval_rouge1": 0.5874,
298
+ "eval_rouge2": 0.5673,
299
+ "eval_runtime": 51.9475,
300
+ "eval_samples_per_second": 96.251,
301
+ "eval_steps_per_second": 3.022,
302
+ "step": 18750
303
+ },
304
+ {
305
+ "epoch": 6.08,
306
+ "learning_rate": 0.23700089752674103,
307
+ "loss": 0.0268,
308
+ "step": 19000
309
+ },
310
+ {
311
+ "epoch": 6.24,
312
+ "learning_rate": 0.23510468006134033,
313
+ "loss": 0.025,
314
+ "step": 19500
315
+ },
316
+ {
317
+ "epoch": 6.4,
318
+ "learning_rate": 0.23372133076190948,
319
+ "loss": 0.0234,
320
+ "step": 20000
321
+ },
322
+ {
323
+ "epoch": 6.56,
324
+ "learning_rate": 0.23236095905303955,
325
+ "loss": 0.0242,
326
+ "step": 20500
327
+ },
328
+ {
329
+ "epoch": 6.72,
330
+ "learning_rate": 0.23128560185432434,
331
+ "loss": 0.0243,
332
+ "step": 21000
333
+ },
334
+ {
335
+ "epoch": 6.88,
336
+ "learning_rate": 0.23010540008544922,
337
+ "loss": 0.0251,
338
+ "step": 21500
339
+ },
340
+ {
341
+ "epoch": 7.0,
342
+ "eval_avg_length": 17.3118,
343
+ "eval_bleu": 0.0237,
344
+ "eval_loss": 0.07389520108699799,
345
+ "eval_rouge1": 0.5872,
346
+ "eval_rouge2": 0.5672,
347
+ "eval_runtime": 52.1854,
348
+ "eval_samples_per_second": 95.812,
349
+ "eval_steps_per_second": 3.009,
350
+ "step": 21875
351
+ },
352
+ {
353
+ "epoch": 7.04,
354
+ "learning_rate": 0.22910726070404053,
355
+ "loss": 0.0244,
356
+ "step": 22000
357
+ },
358
+ {
359
+ "epoch": 7.2,
360
+ "learning_rate": 0.22765885293483734,
361
+ "loss": 0.0194,
362
+ "step": 22500
363
+ },
364
+ {
365
+ "epoch": 7.36,
366
+ "learning_rate": 0.22604411840438843,
367
+ "loss": 0.0211,
368
+ "step": 23000
369
+ },
370
+ {
371
+ "epoch": 7.52,
372
+ "learning_rate": 0.22470736503601074,
373
+ "loss": 0.0205,
374
+ "step": 23500
375
+ },
376
+ {
377
+ "epoch": 7.68,
378
+ "learning_rate": 0.22348329424858093,
379
+ "loss": 0.0223,
380
+ "step": 24000
381
+ },
382
+ {
383
+ "epoch": 7.84,
384
+ "learning_rate": 0.22219397127628326,
385
+ "loss": 0.0226,
386
+ "step": 24500
387
+ },
388
+ {
389
+ "epoch": 8.0,
390
+ "learning_rate": 0.2213691771030426,
391
+ "loss": 0.0222,
392
+ "step": 25000
393
+ },
394
+ {
395
+ "epoch": 8.0,
396
+ "eval_avg_length": 17.307,
397
+ "eval_bleu": 0.0237,
398
+ "eval_loss": 0.07857740670442581,
399
+ "eval_rouge1": 0.5869,
400
+ "eval_rouge2": 0.5671,
401
+ "eval_runtime": 52.6845,
402
+ "eval_samples_per_second": 94.905,
403
+ "eval_steps_per_second": 2.98,
404
+ "step": 25000
405
+ },
406
+ {
407
+ "epoch": 8.16,
408
+ "learning_rate": 0.22002732753753662,
409
+ "loss": 0.0166,
410
+ "step": 25500
411
+ },
412
+ {
413
+ "epoch": 8.32,
414
+ "learning_rate": 0.21867167949676514,
415
+ "loss": 0.018,
416
+ "step": 26000
417
+ },
418
+ {
419
+ "epoch": 8.48,
420
+ "learning_rate": 0.21748971939086914,
421
+ "loss": 0.0193,
422
+ "step": 26500
423
+ },
424
+ {
425
+ "epoch": 8.64,
426
+ "learning_rate": 0.2165619432926178,
427
+ "loss": 0.0194,
428
+ "step": 27000
429
+ },
430
+ {
431
+ "epoch": 8.8,
432
+ "learning_rate": 0.2155638188123703,
433
+ "loss": 0.019,
434
+ "step": 27500
435
+ },
436
+ {
437
+ "epoch": 8.96,
438
+ "learning_rate": 0.2147785723209381,
439
+ "loss": 0.0183,
440
+ "step": 28000
441
+ },
442
+ {
443
+ "epoch": 9.0,
444
+ "eval_avg_length": 17.3154,
445
+ "eval_bleu": 0.0237,
446
+ "eval_loss": 0.07949095219373703,
447
+ "eval_rouge1": 0.5873,
448
+ "eval_rouge2": 0.5677,
449
+ "eval_runtime": 52.9652,
450
+ "eval_samples_per_second": 94.402,
451
+ "eval_steps_per_second": 2.964,
452
+ "step": 28125
453
+ },
454
+ {
455
+ "epoch": 9.12,
456
+ "learning_rate": 0.21370729804039001,
457
+ "loss": 0.0163,
458
+ "step": 28500
459
+ },
460
+ {
461
+ "epoch": 9.28,
462
+ "learning_rate": 0.2124933898448944,
463
+ "loss": 0.0155,
464
+ "step": 29000
465
+ },
466
+ {
467
+ "epoch": 9.44,
468
+ "learning_rate": 0.21130582690238953,
469
+ "loss": 0.0152,
470
+ "step": 29500
471
+ },
472
+ {
473
+ "epoch": 9.6,
474
+ "learning_rate": 0.21038685739040375,
475
+ "loss": 0.0158,
476
+ "step": 30000
477
+ },
478
+ {
479
+ "epoch": 9.76,
480
+ "learning_rate": 0.20950140058994293,
481
+ "loss": 0.0165,
482
+ "step": 30500
483
+ },
484
+ {
485
+ "epoch": 9.92,
486
+ "learning_rate": 0.20879273116588593,
487
+ "loss": 0.0183,
488
+ "step": 31000
489
+ },
490
+ {
491
+ "epoch": 10.0,
492
+ "eval_avg_length": 17.308,
493
+ "eval_bleu": 0.0236,
494
+ "eval_loss": 0.08381666988134384,
495
+ "eval_rouge1": 0.5869,
496
+ "eval_rouge2": 0.5668,
497
+ "eval_runtime": 53.7004,
498
+ "eval_samples_per_second": 93.109,
499
+ "eval_steps_per_second": 2.924,
500
+ "step": 31250
501
+ },
502
+ {
503
+ "epoch": 10.08,
504
+ "learning_rate": 0.20795859396457672,
505
+ "loss": 0.0153,
506
+ "step": 31500
507
+ },
508
+ {
509
+ "epoch": 10.24,
510
+ "learning_rate": 0.20694369077682495,
511
+ "loss": 0.0132,
512
+ "step": 32000
513
+ },
514
+ {
515
+ "epoch": 10.4,
516
+ "learning_rate": 0.20593030750751495,
517
+ "loss": 0.0145,
518
+ "step": 32500
519
+ },
520
+ {
521
+ "epoch": 10.56,
522
+ "learning_rate": 0.20512063801288605,
523
+ "loss": 0.0142,
524
+ "step": 33000
525
+ },
526
+ {
527
+ "epoch": 10.72,
528
+ "learning_rate": 0.204327791929245,
529
+ "loss": 0.0136,
530
+ "step": 33500
531
+ },
532
+ {
533
+ "epoch": 10.88,
534
+ "learning_rate": 0.2036626935005188,
535
+ "loss": 0.0147,
536
+ "step": 34000
537
+ },
538
+ {
539
+ "epoch": 11.0,
540
+ "eval_avg_length": 17.3118,
541
+ "eval_bleu": 0.0236,
542
+ "eval_loss": 0.08516956865787506,
543
+ "eval_rouge1": 0.5867,
544
+ "eval_rouge2": 0.567,
545
+ "eval_runtime": 53.2317,
546
+ "eval_samples_per_second": 93.929,
547
+ "eval_steps_per_second": 2.949,
548
+ "step": 34375
549
+ },
550
+ {
551
+ "epoch": 11.04,
552
+ "learning_rate": 0.20300111174583435,
553
+ "loss": 0.0145,
554
+ "step": 34500
555
+ },
556
+ {
557
+ "epoch": 11.2,
558
+ "learning_rate": 0.20208755135536194,
559
+ "loss": 0.0112,
560
+ "step": 35000
561
+ },
562
+ {
563
+ "epoch": 11.36,
564
+ "learning_rate": 0.20132538676261902,
565
+ "loss": 0.0123,
566
+ "step": 35500
567
+ },
568
+ {
569
+ "epoch": 11.52,
570
+ "learning_rate": 0.2005048245191574,
571
+ "loss": 0.012,
572
+ "step": 36000
573
+ },
574
+ {
575
+ "epoch": 11.68,
576
+ "learning_rate": 0.1997680366039276,
577
+ "loss": 0.013,
578
+ "step": 36500
579
+ },
580
+ {
581
+ "epoch": 11.84,
582
+ "learning_rate": 0.19915533065795898,
583
+ "loss": 0.0131,
584
+ "step": 37000
585
+ },
586
+ {
587
+ "epoch": 12.0,
588
+ "learning_rate": 0.19845974445343018,
589
+ "loss": 0.0132,
590
+ "step": 37500
591
+ },
592
+ {
593
+ "epoch": 12.0,
594
+ "eval_avg_length": 17.3078,
595
+ "eval_bleu": 0.0236,
596
+ "eval_loss": 0.08685878664255142,
597
+ "eval_rouge1": 0.5872,
598
+ "eval_rouge2": 0.5671,
599
+ "eval_runtime": 53.7846,
600
+ "eval_samples_per_second": 92.963,
601
+ "eval_steps_per_second": 2.919,
602
+ "step": 37500
603
+ },
604
+ {
605
+ "epoch": 12.16,
606
+ "learning_rate": 0.19766050577163696,
607
+ "loss": 0.0098,
608
+ "step": 38000
609
+ },
610
+ {
611
+ "epoch": 12.32,
612
+ "learning_rate": 0.19691884517669678,
613
+ "loss": 0.0105,
614
+ "step": 38500
615
+ },
616
+ {
617
+ "epoch": 12.48,
618
+ "learning_rate": 0.19617730379104614,
619
+ "loss": 0.0101,
620
+ "step": 39000
621
+ },
622
+ {
623
+ "epoch": 12.64,
624
+ "learning_rate": 0.19556531310081482,
625
+ "loss": 0.0118,
626
+ "step": 39500
627
+ },
628
+ {
629
+ "epoch": 12.8,
630
+ "learning_rate": 0.1950163096189499,
631
+ "loss": 0.0112,
632
+ "step": 40000
633
+ },
634
+ {
635
+ "epoch": 12.96,
636
+ "learning_rate": 0.19457842409610748,
637
+ "loss": 0.0128,
638
+ "step": 40500
639
+ },
640
+ {
641
+ "epoch": 13.0,
642
+ "eval_avg_length": 17.313,
643
+ "eval_bleu": 0.0236,
644
+ "eval_loss": 0.09262268990278244,
645
+ "eval_rouge1": 0.5859,
646
+ "eval_rouge2": 0.5654,
647
+ "eval_runtime": 54.0715,
648
+ "eval_samples_per_second": 92.47,
649
+ "eval_steps_per_second": 2.904,
650
+ "step": 40625
651
+ },
652
+ {
653
+ "epoch": 13.12,
654
+ "learning_rate": 0.19387850165367126,
655
+ "loss": 0.0086,
656
+ "step": 41000
657
+ },
658
+ {
659
+ "epoch": 13.28,
660
+ "learning_rate": 0.19318543374538422,
661
+ "loss": 0.0087,
662
+ "step": 41500
663
+ },
664
+ {
665
+ "epoch": 13.44,
666
+ "learning_rate": 0.19256973266601562,
667
+ "loss": 0.0095,
668
+ "step": 42000
669
+ }
670
+ ],
671
+ "max_steps": 312500,
672
+ "num_train_epochs": 100,
673
+ "total_flos": 9.0949690589184e+16,
674
+ "trial_name": null,
675
+ "trial_params": null
676
+ }
training_args copy.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c54e3efd3976f1f09b79ec9c8fa2a302f993127b54602c759a4e1e87606b636
3
+ size 3707
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:533d95cbf8aea627be6c1763567c84c1c6bf7124979483027e8997950505a94f
3
+ size 3579