Hugging Face's logo

lmeninato
/
t5-small-codesearchnet-multilang-python-java

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
1
lmeninato commited on
Commit
1b764dd
·
1 Parent(s): 5453c4d

initial commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +15 -0
  2. README.md +79 -0
  3. checkpoint-4125/config.json +60 -0
  4. checkpoint-4125/generation_config.json +6 -0
  5. checkpoint-4125/optimizer.pt +3 -0
  6. checkpoint-4125/pytorch_model.bin +3 -0
  7. checkpoint-4125/rng_state.pth +3 -0
  8. checkpoint-4125/scheduler.pt +3 -0
  9. checkpoint-4125/special_tokens_map.json +107 -0
  10. checkpoint-4125/spiece.model +3 -0
  11. checkpoint-4125/tokenizer.json +0 -0
  12. checkpoint-4125/tokenizer_config.json +111 -0
  13. checkpoint-4125/trainer_state.json +196 -0
  14. checkpoint-4125/training_args.bin +3 -0
  15. checkpoint-4500/config.json +60 -0
  16. checkpoint-4500/generation_config.json +6 -0
  17. checkpoint-4500/optimizer.pt +3 -0
  18. checkpoint-4500/pytorch_model.bin +3 -0
  19. checkpoint-4500/rng_state.pth +3 -0
  20. checkpoint-4500/scheduler.pt +3 -0
  21. checkpoint-4500/special_tokens_map.json +107 -0
  22. checkpoint-4500/spiece.model +3 -0
  23. checkpoint-4500/tokenizer.json +0 -0
  24. checkpoint-4500/tokenizer_config.json +111 -0
  25. checkpoint-4500/trainer_state.json +214 -0
  26. checkpoint-4500/training_args.bin +3 -0
  27. checkpoint-4875/config.json +60 -0
  28. checkpoint-4875/generation_config.json +6 -0
  29. checkpoint-4875/optimizer.pt +3 -0
  30. checkpoint-4875/rng_state.pth +3 -0
  31. checkpoint-4875/scheduler.pt +3 -0
  32. checkpoint-4875/special_tokens_map.json +107 -0
  33. checkpoint-4875/spiece.model +3 -0
  34. checkpoint-4875/tokenizer.json +0 -0
  35. checkpoint-4875/tokenizer_config.json +111 -0
  36. checkpoint-4875/trainer_state.json +226 -0
  37. checkpoint-4875/training_args.bin +3 -0
  38. checkpoint-5250/config.json +60 -0
  39. checkpoint-5250/generation_config.json +6 -0
  40. checkpoint-5250/optimizer.pt +3 -0
  41. checkpoint-5250/rng_state.pth +3 -0
  42. checkpoint-5250/scheduler.pt +3 -0
  43. checkpoint-5250/special_tokens_map.json +107 -0
  44. checkpoint-5250/spiece.model +3 -0
  45. checkpoint-5250/tokenizer.json +0 -0
  46. checkpoint-5250/tokenizer_config.json +111 -0
  47. checkpoint-5250/trainer_state.json +244 -0
  48. checkpoint-5250/training_args.bin +3 -0
  49. checkpoint-5625/config.json +60 -0
  50. checkpoint-5625/generation_config.json +6 -0
.gitattributes CHANGED
@@ -32,3 +32,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
36
+ spiece.model filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-4125/training_args.bin filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-4500/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-4500/training_args.bin filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-4875/training_args.bin filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-5250/training_args.bin filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-5625/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-5625/training_args.bin filter=lfs diff=lfs merge=lfs -text
44
+ checkpoint-4125/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
45
+ checkpoint-4125/spiece.model filter=lfs diff=lfs merge=lfs -text
46
+ checkpoint-4500/spiece.model filter=lfs diff=lfs merge=lfs -text
47
+ checkpoint-4875/spiece.model filter=lfs diff=lfs merge=lfs -text
48
+ checkpoint-5250/spiece.model filter=lfs diff=lfs merge=lfs -text
49
+ checkpoint-5625/spiece.model filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - bleu
7
+ - rouge
8
+ model-index:
9
+ - name: t5-small-codesearchnet-multilang-python-java
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # t5-small-codesearchnet-multilang-python-java
17
+
18
+ This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7015
21
+ - Bleu: 0.0045
22
+ - Rouge1: 0.2194
23
+ - Rouge2: 0.0741
24
+ - Avg Length: 15.9976
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 8
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - gradient_accumulation_steps: 10
48
+ - total_train_batch_size: 80
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 15
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | Avg Length |
56
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:----------:|
57
+ | No log | 1.0 | 375 | 0.9005 | 0.0013 | 0.1397 | 0.0334 | 16.3976 |
58
+ | 2.3568 | 2.0 | 750 | 0.8036 | 0.0023 | 0.1737 | 0.0526 | 15.8896 |
59
+ | 0.7576 | 3.0 | 1125 | 0.7584 | 0.0021 | 0.1856 | 0.0558 | 15.3102 |
60
+ | 0.6778 | 4.0 | 1500 | 0.7298 | 0.0024 | 0.1922 | 0.0597 | 15.3544 |
61
+ | 0.6778 | 5.0 | 1875 | 0.7114 | 0.0037 | 0.2114 | 0.0704 | 15.7588 |
62
+ | 0.6206 | 6.0 | 2250 | 0.6949 | 0.0039 | 0.2093 | 0.0729 | 15.8088 |
63
+ | 0.5856 | 7.0 | 2625 | 0.6927 | 0.0042 | 0.2143 | 0.0711 | 16.5838 |
64
+ | 0.5447 | 8.0 | 3000 | 0.6867 | 0.005 | 0.2151 | 0.0717 | 17.2174 |
65
+ | 0.5447 | 9.0 | 3375 | 0.6895 | 0.0043 | 0.2179 | 0.0736 | 16.1068 |
66
+ | 0.5117 | 10.0 | 3750 | 0.6876 | 0.0038 | 0.2229 | 0.0777 | 15.5094 |
67
+ | 0.4892 | 11.0 | 4125 | 0.6800 | 0.0047 | 0.2201 | 0.0783 | 16.6902 |
68
+ | 0.4629 | 12.0 | 4500 | 0.6903 | 0.0047 | 0.2203 | 0.0771 | 16.7658 |
69
+ | 0.4629 | 13.0 | 4875 | 0.6947 | 0.0056 | 0.227 | 0.0777 | 16.8108 |
70
+ | 0.4355 | 14.0 | 5250 | 0.6999 | 0.0027 | 0.2028 | 0.0715 | 15.6776 |
71
+ | 0.418 | 15.0 | 5625 | 0.7015 | 0.0045 | 0.2194 | 0.0741 | 15.9976 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.28.1
77
+ - Pytorch 2.0.0+cu118
78
+ - Datasets 2.12.0
79
+ - Tokenizers 0.13.3
checkpoint-4125/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": "4.28.1",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
checkpoint-4125/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.28.1"
6
+ }
checkpoint-4125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd4e6d801edf8bdb11f50ffd208e5d264754dde0faa33a11253a19ea7ffd00e
3
+ size 839173
checkpoint-4125/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9741168d416ae2d87e7c9afa4ec50569e0aacaa74aa7590705438a2e5da2ba7f
3
+ size 242071641
checkpoint-4125/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:688d538e53bf11f3d31ffdb4cc3daf49c54c9408c562f7e1ce5cd8cee12f72ee
3
+ size 14575
checkpoint-4125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3f10d3d58bcfb64391f4be540066f0cc01ebb73dcfe5f6f03367aecc2dcd8d9
3
+ size 881
checkpoint-4125/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
+ }
checkpoint-4125/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-4125/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4125/tokenizer_config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "<pad>",
109
+ "tokenizer_class": "T5Tokenizer",
110
+ "unk_token": "<unk>"
111
+ }
checkpoint-4125/trainer_state.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6800228357315063,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python-java/checkpoint-4125",
4
+ "epoch": 11.0,
5
+ "global_step": 4125,
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
+ "eval_avg_length": 16.3976,
13
+ "eval_bleu": 0.0013,
14
+ "eval_loss": 0.9005016684532166,
15
+ "eval_rouge1": 0.1397,
16
+ "eval_rouge2": 0.0334,
17
+ "eval_runtime": 159.8289,
18
+ "eval_samples_per_second": 31.283,
19
+ "eval_steps_per_second": 3.91,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.011611906811594963,
25
+ "loss": 2.3568,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 15.8896,
31
+ "eval_bleu": 0.0023,
32
+ "eval_loss": 0.8036138415336609,
33
+ "eval_rouge1": 0.1737,
34
+ "eval_rouge2": 0.0526,
35
+ "eval_runtime": 164.0069,
36
+ "eval_samples_per_second": 30.487,
37
+ "eval_steps_per_second": 3.811,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.023264221847057343,
43
+ "loss": 0.7576,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 15.3102,
49
+ "eval_bleu": 0.0021,
50
+ "eval_loss": 0.7583827972412109,
51
+ "eval_rouge1": 0.1856,
52
+ "eval_rouge2": 0.0558,
53
+ "eval_runtime": 167.7038,
54
+ "eval_samples_per_second": 29.814,
55
+ "eval_steps_per_second": 3.727,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.03498469293117523,
61
+ "loss": 0.6778,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 15.3544,
67
+ "eval_bleu": 0.0024,
68
+ "eval_loss": 0.7298200130462646,
69
+ "eval_rouge1": 0.1922,
70
+ "eval_rouge2": 0.0597,
71
+ "eval_runtime": 168.897,
72
+ "eval_samples_per_second": 29.604,
73
+ "eval_steps_per_second": 3.7,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 15.7588,
79
+ "eval_bleu": 0.0037,
80
+ "eval_loss": 0.7113876938819885,
81
+ "eval_rouge1": 0.2114,
82
+ "eval_rouge2": 0.0704,
83
+ "eval_runtime": 172.1098,
84
+ "eval_samples_per_second": 29.051,
85
+ "eval_steps_per_second": 3.631,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.046804994344711304,
91
+ "loss": 0.6206,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 15.8088,
97
+ "eval_bleu": 0.0039,
98
+ "eval_loss": 0.6949090957641602,
99
+ "eval_rouge1": 0.2093,
100
+ "eval_rouge2": 0.0729,
101
+ "eval_runtime": 165.5542,
102
+ "eval_samples_per_second": 30.202,
103
+ "eval_steps_per_second": 3.775,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.05876593291759491,
109
+ "loss": 0.5856,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 16.5838,
115
+ "eval_bleu": 0.0042,
116
+ "eval_loss": 0.6927398443222046,
117
+ "eval_rouge1": 0.2143,
118
+ "eval_rouge2": 0.0711,
119
+ "eval_runtime": 164.6989,
120
+ "eval_samples_per_second": 30.358,
121
+ "eval_steps_per_second": 3.795,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.07091041654348373,
127
+ "loss": 0.5447,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 17.2174,
133
+ "eval_bleu": 0.005,
134
+ "eval_loss": 0.6866663694381714,
135
+ "eval_rouge1": 0.2151,
136
+ "eval_rouge2": 0.0717,
137
+ "eval_runtime": 163.5142,
138
+ "eval_samples_per_second": 30.578,
139
+ "eval_steps_per_second": 3.822,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 16.1068,
145
+ "eval_bleu": 0.0043,
146
+ "eval_loss": 0.689474880695343,
147
+ "eval_rouge1": 0.2179,
148
+ "eval_rouge2": 0.0736,
149
+ "eval_runtime": 161.9004,
150
+ "eval_samples_per_second": 30.883,
151
+ "eval_steps_per_second": 3.86,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.08324738591909409,
157
+ "loss": 0.5117,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 15.5094,
163
+ "eval_bleu": 0.0038,
164
+ "eval_loss": 0.6876339912414551,
165
+ "eval_rouge1": 0.2229,
166
+ "eval_rouge2": 0.0777,
167
+ "eval_runtime": 168.6323,
168
+ "eval_samples_per_second": 29.65,
169
+ "eval_steps_per_second": 3.706,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.09585673362016678,
175
+ "loss": 0.4892,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.6902,
181
+ "eval_bleu": 0.0047,
182
+ "eval_loss": 0.6800228357315063,
183
+ "eval_rouge1": 0.2201,
184
+ "eval_rouge2": 0.0783,
185
+ "eval_runtime": 164.6191,
186
+ "eval_samples_per_second": 30.373,
187
+ "eval_steps_per_second": 3.797,
188
+ "step": 4125
189
+ }
190
+ ],
191
+ "max_steps": 5625,
192
+ "num_train_epochs": 15,
193
+ "total_flos": 2.233139724288e+16,
194
+ "trial_name": null,
195
+ "trial_params": null
196
+ }
checkpoint-4125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713041a86b4e867b3cc40d56491f767c0e2bf21b457ff124832b44babe8c2f02
3
+ size 3963
checkpoint-4500/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": "4.28.1",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
checkpoint-4500/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.28.1"
6
+ }
checkpoint-4500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd0fbc6265e6b0abc82208679c9bab9576143e04ca732c9a53b9eb6993a342c
3
+ size 839173
checkpoint-4500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876218e0a353764e89a62b9c5663e4f718b559a54ba83bccc22d23b004c5ce56
3
+ size 242071641
checkpoint-4500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2332aac86bd6b1cf4509f447e29d540d5b61858b6fa34d8ec86b305433dc4f35
3
+ size 14575
checkpoint-4500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c64b3ecd50df5bb956a4de413e134d3ffd588ba01c1a449ddcd8f065f3c7d54
3
+ size 881
checkpoint-4500/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
+ }
checkpoint-4500/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-4500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4500/tokenizer_config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "<pad>",
109
+ "tokenizer_class": "T5Tokenizer",
110
+ "unk_token": "<unk>"
111
+ }
checkpoint-4500/trainer_state.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6800228357315063,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python-java/checkpoint-4125",
4
+ "epoch": 12.0,
5
+ "global_step": 4500,
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
+ "eval_avg_length": 16.3976,
13
+ "eval_bleu": 0.0013,
14
+ "eval_loss": 0.9005016684532166,
15
+ "eval_rouge1": 0.1397,
16
+ "eval_rouge2": 0.0334,
17
+ "eval_runtime": 159.8289,
18
+ "eval_samples_per_second": 31.283,
19
+ "eval_steps_per_second": 3.91,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.011611906811594963,
25
+ "loss": 2.3568,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 15.8896,
31
+ "eval_bleu": 0.0023,
32
+ "eval_loss": 0.8036138415336609,
33
+ "eval_rouge1": 0.1737,
34
+ "eval_rouge2": 0.0526,
35
+ "eval_runtime": 164.0069,
36
+ "eval_samples_per_second": 30.487,
37
+ "eval_steps_per_second": 3.811,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.023264221847057343,
43
+ "loss": 0.7576,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 15.3102,
49
+ "eval_bleu": 0.0021,
50
+ "eval_loss": 0.7583827972412109,
51
+ "eval_rouge1": 0.1856,
52
+ "eval_rouge2": 0.0558,
53
+ "eval_runtime": 167.7038,
54
+ "eval_samples_per_second": 29.814,
55
+ "eval_steps_per_second": 3.727,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.03498469293117523,
61
+ "loss": 0.6778,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 15.3544,
67
+ "eval_bleu": 0.0024,
68
+ "eval_loss": 0.7298200130462646,
69
+ "eval_rouge1": 0.1922,
70
+ "eval_rouge2": 0.0597,
71
+ "eval_runtime": 168.897,
72
+ "eval_samples_per_second": 29.604,
73
+ "eval_steps_per_second": 3.7,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 15.7588,
79
+ "eval_bleu": 0.0037,
80
+ "eval_loss": 0.7113876938819885,
81
+ "eval_rouge1": 0.2114,
82
+ "eval_rouge2": 0.0704,
83
+ "eval_runtime": 172.1098,
84
+ "eval_samples_per_second": 29.051,
85
+ "eval_steps_per_second": 3.631,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.046804994344711304,
91
+ "loss": 0.6206,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 15.8088,
97
+ "eval_bleu": 0.0039,
98
+ "eval_loss": 0.6949090957641602,
99
+ "eval_rouge1": 0.2093,
100
+ "eval_rouge2": 0.0729,
101
+ "eval_runtime": 165.5542,
102
+ "eval_samples_per_second": 30.202,
103
+ "eval_steps_per_second": 3.775,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.05876593291759491,
109
+ "loss": 0.5856,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 16.5838,
115
+ "eval_bleu": 0.0042,
116
+ "eval_loss": 0.6927398443222046,
117
+ "eval_rouge1": 0.2143,
118
+ "eval_rouge2": 0.0711,
119
+ "eval_runtime": 164.6989,
120
+ "eval_samples_per_second": 30.358,
121
+ "eval_steps_per_second": 3.795,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.07091041654348373,
127
+ "loss": 0.5447,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 17.2174,
133
+ "eval_bleu": 0.005,
134
+ "eval_loss": 0.6866663694381714,
135
+ "eval_rouge1": 0.2151,
136
+ "eval_rouge2": 0.0717,
137
+ "eval_runtime": 163.5142,
138
+ "eval_samples_per_second": 30.578,
139
+ "eval_steps_per_second": 3.822,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 16.1068,
145
+ "eval_bleu": 0.0043,
146
+ "eval_loss": 0.689474880695343,
147
+ "eval_rouge1": 0.2179,
148
+ "eval_rouge2": 0.0736,
149
+ "eval_runtime": 161.9004,
150
+ "eval_samples_per_second": 30.883,
151
+ "eval_steps_per_second": 3.86,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.08324738591909409,
157
+ "loss": 0.5117,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 15.5094,
163
+ "eval_bleu": 0.0038,
164
+ "eval_loss": 0.6876339912414551,
165
+ "eval_rouge1": 0.2229,
166
+ "eval_rouge2": 0.0777,
167
+ "eval_runtime": 168.6323,
168
+ "eval_samples_per_second": 29.65,
169
+ "eval_steps_per_second": 3.706,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.09585673362016678,
175
+ "loss": 0.4892,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.6902,
181
+ "eval_bleu": 0.0047,
182
+ "eval_loss": 0.6800228357315063,
183
+ "eval_rouge1": 0.2201,
184
+ "eval_rouge2": 0.0783,
185
+ "eval_runtime": 164.6191,
186
+ "eval_samples_per_second": 30.373,
187
+ "eval_steps_per_second": 3.797,
188
+ "step": 4125
189
+ },
190
+ {
191
+ "epoch": 12.0,
192
+ "learning_rate": 0.10878779739141464,
193
+ "loss": 0.4629,
194
+ "step": 4500
195
+ },
196
+ {
197
+ "epoch": 12.0,
198
+ "eval_avg_length": 16.7658,
199
+ "eval_bleu": 0.0047,
200
+ "eval_loss": 0.6902568340301514,
201
+ "eval_rouge1": 0.2203,
202
+ "eval_rouge2": 0.0771,
203
+ "eval_runtime": 167.779,
204
+ "eval_samples_per_second": 29.801,
205
+ "eval_steps_per_second": 3.725,
206
+ "step": 4500
207
+ }
208
+ ],
209
+ "max_steps": 5625,
210
+ "num_train_epochs": 15,
211
+ "total_flos": 2.436152426496e+16,
212
+ "trial_name": null,
213
+ "trial_params": null
214
+ }
checkpoint-4500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713041a86b4e867b3cc40d56491f767c0e2bf21b457ff124832b44babe8c2f02
3
+ size 3963
checkpoint-4875/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": "4.28.1",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
checkpoint-4875/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.28.1"
6
+ }
checkpoint-4875/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c0ebac4bb9732b30a0cdfffca66e0ed87e72645b0283d6dfb786e8b8bb20c1
3
+ size 839173
checkpoint-4875/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa66db2dc738ba38e3124bd7fe9c3f5d3383c4f87ff9f2ccaa3a5d9a3d88cd8a
3
+ size 14575
checkpoint-4875/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9c5b5f2fbe51c8f875845c622db64eabfff10d3f666d9817dd93e2d558229a
3
+ size 881
checkpoint-4875/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
+ }
checkpoint-4875/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-4875/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4875/tokenizer_config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "<pad>",
109
+ "tokenizer_class": "T5Tokenizer",
110
+ "unk_token": "<unk>"
111
+ }
checkpoint-4875/trainer_state.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6800228357315063,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python-java/checkpoint-4125",
4
+ "epoch": 13.0,
5
+ "global_step": 4875,
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
+ "eval_avg_length": 16.3976,
13
+ "eval_bleu": 0.0013,
14
+ "eval_loss": 0.9005016684532166,
15
+ "eval_rouge1": 0.1397,
16
+ "eval_rouge2": 0.0334,
17
+ "eval_runtime": 159.8289,
18
+ "eval_samples_per_second": 31.283,
19
+ "eval_steps_per_second": 3.91,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.011611906811594963,
25
+ "loss": 2.3568,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 15.8896,
31
+ "eval_bleu": 0.0023,
32
+ "eval_loss": 0.8036138415336609,
33
+ "eval_rouge1": 0.1737,
34
+ "eval_rouge2": 0.0526,
35
+ "eval_runtime": 164.0069,
36
+ "eval_samples_per_second": 30.487,
37
+ "eval_steps_per_second": 3.811,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.023264221847057343,
43
+ "loss": 0.7576,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 15.3102,
49
+ "eval_bleu": 0.0021,
50
+ "eval_loss": 0.7583827972412109,
51
+ "eval_rouge1": 0.1856,
52
+ "eval_rouge2": 0.0558,
53
+ "eval_runtime": 167.7038,
54
+ "eval_samples_per_second": 29.814,
55
+ "eval_steps_per_second": 3.727,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.03498469293117523,
61
+ "loss": 0.6778,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 15.3544,
67
+ "eval_bleu": 0.0024,
68
+ "eval_loss": 0.7298200130462646,
69
+ "eval_rouge1": 0.1922,
70
+ "eval_rouge2": 0.0597,
71
+ "eval_runtime": 168.897,
72
+ "eval_samples_per_second": 29.604,
73
+ "eval_steps_per_second": 3.7,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 15.7588,
79
+ "eval_bleu": 0.0037,
80
+ "eval_loss": 0.7113876938819885,
81
+ "eval_rouge1": 0.2114,
82
+ "eval_rouge2": 0.0704,
83
+ "eval_runtime": 172.1098,
84
+ "eval_samples_per_second": 29.051,
85
+ "eval_steps_per_second": 3.631,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.046804994344711304,
91
+ "loss": 0.6206,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 15.8088,
97
+ "eval_bleu": 0.0039,
98
+ "eval_loss": 0.6949090957641602,
99
+ "eval_rouge1": 0.2093,
100
+ "eval_rouge2": 0.0729,
101
+ "eval_runtime": 165.5542,
102
+ "eval_samples_per_second": 30.202,
103
+ "eval_steps_per_second": 3.775,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.05876593291759491,
109
+ "loss": 0.5856,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 16.5838,
115
+ "eval_bleu": 0.0042,
116
+ "eval_loss": 0.6927398443222046,
117
+ "eval_rouge1": 0.2143,
118
+ "eval_rouge2": 0.0711,
119
+ "eval_runtime": 164.6989,
120
+ "eval_samples_per_second": 30.358,
121
+ "eval_steps_per_second": 3.795,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.07091041654348373,
127
+ "loss": 0.5447,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 17.2174,
133
+ "eval_bleu": 0.005,
134
+ "eval_loss": 0.6866663694381714,
135
+ "eval_rouge1": 0.2151,
136
+ "eval_rouge2": 0.0717,
137
+ "eval_runtime": 163.5142,
138
+ "eval_samples_per_second": 30.578,
139
+ "eval_steps_per_second": 3.822,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 16.1068,
145
+ "eval_bleu": 0.0043,
146
+ "eval_loss": 0.689474880695343,
147
+ "eval_rouge1": 0.2179,
148
+ "eval_rouge2": 0.0736,
149
+ "eval_runtime": 161.9004,
150
+ "eval_samples_per_second": 30.883,
151
+ "eval_steps_per_second": 3.86,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.08324738591909409,
157
+ "loss": 0.5117,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 15.5094,
163
+ "eval_bleu": 0.0038,
164
+ "eval_loss": 0.6876339912414551,
165
+ "eval_rouge1": 0.2229,
166
+ "eval_rouge2": 0.0777,
167
+ "eval_runtime": 168.6323,
168
+ "eval_samples_per_second": 29.65,
169
+ "eval_steps_per_second": 3.706,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.09585673362016678,
175
+ "loss": 0.4892,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.6902,
181
+ "eval_bleu": 0.0047,
182
+ "eval_loss": 0.6800228357315063,
183
+ "eval_rouge1": 0.2201,
184
+ "eval_rouge2": 0.0783,
185
+ "eval_runtime": 164.6191,
186
+ "eval_samples_per_second": 30.373,
187
+ "eval_steps_per_second": 3.797,
188
+ "step": 4125
189
+ },
190
+ {
191
+ "epoch": 12.0,
192
+ "learning_rate": 0.10878779739141464,
193
+ "loss": 0.4629,
194
+ "step": 4500
195
+ },
196
+ {
197
+ "epoch": 12.0,
198
+ "eval_avg_length": 16.7658,
199
+ "eval_bleu": 0.0047,
200
+ "eval_loss": 0.6902568340301514,
201
+ "eval_rouge1": 0.2203,
202
+ "eval_rouge2": 0.0771,
203
+ "eval_runtime": 167.779,
204
+ "eval_samples_per_second": 29.801,
205
+ "eval_steps_per_second": 3.725,
206
+ "step": 4500
207
+ },
208
+ {
209
+ "epoch": 13.0,
210
+ "eval_avg_length": 16.8108,
211
+ "eval_bleu": 0.0056,
212
+ "eval_loss": 0.6946577429771423,
213
+ "eval_rouge1": 0.227,
214
+ "eval_rouge2": 0.0777,
215
+ "eval_runtime": 162.563,
216
+ "eval_samples_per_second": 30.757,
217
+ "eval_steps_per_second": 3.845,
218
+ "step": 4875
219
+ }
220
+ ],
221
+ "max_steps": 5625,
222
+ "num_train_epochs": 15,
223
+ "total_flos": 2.639165128704e+16,
224
+ "trial_name": null,
225
+ "trial_params": null
226
+ }
checkpoint-4875/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713041a86b4e867b3cc40d56491f767c0e2bf21b457ff124832b44babe8c2f02
3
+ size 3963
checkpoint-5250/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": "4.28.1",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
checkpoint-5250/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.28.1"
6
+ }
checkpoint-5250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e6b7d06525bc244073cc16150dabcfcaea9ff52e878d0397ade7509d397d2ab
3
+ size 839173
checkpoint-5250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364ff6f922b69e14e938f67656ec9e6f9ac6de93b7d7ad2cc35365aefb0dc82a
3
+ size 14575
checkpoint-5250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e6a4afea3a56ea41b3ec4b6899c43abadcc891f9fc698a98d5c83480d9ef4fe
3
+ size 881
checkpoint-5250/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
+ }
checkpoint-5250/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-5250/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5250/tokenizer_config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "<pad>",
109
+ "tokenizer_class": "T5Tokenizer",
110
+ "unk_token": "<unk>"
111
+ }
checkpoint-5250/trainer_state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6800228357315063,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python-java/checkpoint-4125",
4
+ "epoch": 14.0,
5
+ "global_step": 5250,
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
+ "eval_avg_length": 16.3976,
13
+ "eval_bleu": 0.0013,
14
+ "eval_loss": 0.9005016684532166,
15
+ "eval_rouge1": 0.1397,
16
+ "eval_rouge2": 0.0334,
17
+ "eval_runtime": 159.8289,
18
+ "eval_samples_per_second": 31.283,
19
+ "eval_steps_per_second": 3.91,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.011611906811594963,
25
+ "loss": 2.3568,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 15.8896,
31
+ "eval_bleu": 0.0023,
32
+ "eval_loss": 0.8036138415336609,
33
+ "eval_rouge1": 0.1737,
34
+ "eval_rouge2": 0.0526,
35
+ "eval_runtime": 164.0069,
36
+ "eval_samples_per_second": 30.487,
37
+ "eval_steps_per_second": 3.811,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.023264221847057343,
43
+ "loss": 0.7576,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 15.3102,
49
+ "eval_bleu": 0.0021,
50
+ "eval_loss": 0.7583827972412109,
51
+ "eval_rouge1": 0.1856,
52
+ "eval_rouge2": 0.0558,
53
+ "eval_runtime": 167.7038,
54
+ "eval_samples_per_second": 29.814,
55
+ "eval_steps_per_second": 3.727,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.03498469293117523,
61
+ "loss": 0.6778,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 15.3544,
67
+ "eval_bleu": 0.0024,
68
+ "eval_loss": 0.7298200130462646,
69
+ "eval_rouge1": 0.1922,
70
+ "eval_rouge2": 0.0597,
71
+ "eval_runtime": 168.897,
72
+ "eval_samples_per_second": 29.604,
73
+ "eval_steps_per_second": 3.7,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 15.7588,
79
+ "eval_bleu": 0.0037,
80
+ "eval_loss": 0.7113876938819885,
81
+ "eval_rouge1": 0.2114,
82
+ "eval_rouge2": 0.0704,
83
+ "eval_runtime": 172.1098,
84
+ "eval_samples_per_second": 29.051,
85
+ "eval_steps_per_second": 3.631,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.046804994344711304,
91
+ "loss": 0.6206,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 15.8088,
97
+ "eval_bleu": 0.0039,
98
+ "eval_loss": 0.6949090957641602,
99
+ "eval_rouge1": 0.2093,
100
+ "eval_rouge2": 0.0729,
101
+ "eval_runtime": 165.5542,
102
+ "eval_samples_per_second": 30.202,
103
+ "eval_steps_per_second": 3.775,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.05876593291759491,
109
+ "loss": 0.5856,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 16.5838,
115
+ "eval_bleu": 0.0042,
116
+ "eval_loss": 0.6927398443222046,
117
+ "eval_rouge1": 0.2143,
118
+ "eval_rouge2": 0.0711,
119
+ "eval_runtime": 164.6989,
120
+ "eval_samples_per_second": 30.358,
121
+ "eval_steps_per_second": 3.795,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.07091041654348373,
127
+ "loss": 0.5447,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 17.2174,
133
+ "eval_bleu": 0.005,
134
+ "eval_loss": 0.6866663694381714,
135
+ "eval_rouge1": 0.2151,
136
+ "eval_rouge2": 0.0717,
137
+ "eval_runtime": 163.5142,
138
+ "eval_samples_per_second": 30.578,
139
+ "eval_steps_per_second": 3.822,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 16.1068,
145
+ "eval_bleu": 0.0043,
146
+ "eval_loss": 0.689474880695343,
147
+ "eval_rouge1": 0.2179,
148
+ "eval_rouge2": 0.0736,
149
+ "eval_runtime": 161.9004,
150
+ "eval_samples_per_second": 30.883,
151
+ "eval_steps_per_second": 3.86,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.08324738591909409,
157
+ "loss": 0.5117,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 15.5094,
163
+ "eval_bleu": 0.0038,
164
+ "eval_loss": 0.6876339912414551,
165
+ "eval_rouge1": 0.2229,
166
+ "eval_rouge2": 0.0777,
167
+ "eval_runtime": 168.6323,
168
+ "eval_samples_per_second": 29.65,
169
+ "eval_steps_per_second": 3.706,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.09585673362016678,
175
+ "loss": 0.4892,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.6902,
181
+ "eval_bleu": 0.0047,
182
+ "eval_loss": 0.6800228357315063,
183
+ "eval_rouge1": 0.2201,
184
+ "eval_rouge2": 0.0783,
185
+ "eval_runtime": 164.6191,
186
+ "eval_samples_per_second": 30.373,
187
+ "eval_steps_per_second": 3.797,
188
+ "step": 4125
189
+ },
190
+ {
191
+ "epoch": 12.0,
192
+ "learning_rate": 0.10878779739141464,
193
+ "loss": 0.4629,
194
+ "step": 4500
195
+ },
196
+ {
197
+ "epoch": 12.0,
198
+ "eval_avg_length": 16.7658,
199
+ "eval_bleu": 0.0047,
200
+ "eval_loss": 0.6902568340301514,
201
+ "eval_rouge1": 0.2203,
202
+ "eval_rouge2": 0.0771,
203
+ "eval_runtime": 167.779,
204
+ "eval_samples_per_second": 29.801,
205
+ "eval_steps_per_second": 3.725,
206
+ "step": 4500
207
+ },
208
+ {
209
+ "epoch": 13.0,
210
+ "eval_avg_length": 16.8108,
211
+ "eval_bleu": 0.0056,
212
+ "eval_loss": 0.6946577429771423,
213
+ "eval_rouge1": 0.227,
214
+ "eval_rouge2": 0.0777,
215
+ "eval_runtime": 162.563,
216
+ "eval_samples_per_second": 30.757,
217
+ "eval_steps_per_second": 3.845,
218
+ "step": 4875
219
+ },
220
+ {
221
+ "epoch": 13.33,
222
+ "learning_rate": 0.12202182412147522,
223
+ "loss": 0.4355,
224
+ "step": 5000
225
+ },
226
+ {
227
+ "epoch": 14.0,
228
+ "eval_avg_length": 15.6776,
229
+ "eval_bleu": 0.0027,
230
+ "eval_loss": 0.6999207735061646,
231
+ "eval_rouge1": 0.2028,
232
+ "eval_rouge2": 0.0715,
233
+ "eval_runtime": 162.751,
234
+ "eval_samples_per_second": 30.722,
235
+ "eval_steps_per_second": 3.84,
236
+ "step": 5250
237
+ }
238
+ ],
239
+ "max_steps": 5625,
240
+ "num_train_epochs": 15,
241
+ "total_flos": 2.842177830912e+16,
242
+ "trial_name": null,
243
+ "trial_params": null
244
+ }
checkpoint-5250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713041a86b4e867b3cc40d56491f767c0e2bf21b457ff124832b44babe8c2f02
3
+ size 3963
checkpoint-5625/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": "4.28.1",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
checkpoint-5625/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.28.1"
6
+ }