lmeninato commited on
Commit
8f0ebf8
·
1 Parent(s): edad34f

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 +17 -0
  2. README.md +79 -0
  3. checkpoint-3750/config.json +60 -0
  4. checkpoint-3750/generation_config.json +6 -0
  5. checkpoint-3750/optimizer.pt +3 -0
  6. checkpoint-3750/pytorch_model.bin +3 -0
  7. checkpoint-3750/rng_state.pth +3 -0
  8. checkpoint-3750/scheduler.pt +3 -0
  9. checkpoint-3750/special_tokens_map.json +107 -0
  10. checkpoint-3750/spiece.model +3 -0
  11. checkpoint-3750/tokenizer.json +0 -0
  12. checkpoint-3750/tokenizer_config.json +111 -0
  13. checkpoint-3750/trainer_state.json +178 -0
  14. checkpoint-3750/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/pytorch_model.bin +3 -0
  31. checkpoint-4875/rng_state.pth +3 -0
  32. checkpoint-4875/scheduler.pt +3 -0
  33. checkpoint-4875/special_tokens_map.json +107 -0
  34. checkpoint-4875/spiece.model +3 -0
  35. checkpoint-4875/tokenizer.json +0 -0
  36. checkpoint-4875/tokenizer_config.json +111 -0
  37. checkpoint-4875/trainer_state.json +226 -0
  38. checkpoint-4875/training_args.bin +3 -0
  39. checkpoint-5250/config.json +60 -0
  40. checkpoint-5250/generation_config.json +6 -0
  41. checkpoint-5250/optimizer.pt +3 -0
  42. checkpoint-5250/pytorch_model.bin +3 -0
  43. checkpoint-5250/rng_state.pth +3 -0
  44. checkpoint-5250/scheduler.pt +3 -0
  45. checkpoint-5250/special_tokens_map.json +107 -0
  46. checkpoint-5250/spiece.model +3 -0
  47. checkpoint-5250/tokenizer.json +0 -0
  48. checkpoint-5250/tokenizer_config.json +111 -0
  49. checkpoint-5250/trainer_state.json +244 -0
  50. checkpoint-5250/training_args.bin +3 -0
.gitattributes CHANGED
@@ -32,3 +32,20 @@ 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
+ checkpoint-4500/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-4875/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-4875/training_args.bin filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-5250/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-5250/training_args.bin filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-5625/training_args.bin filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-3750/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-3750/training_args.bin filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-4500/training_args.bin filter=lfs diff=lfs merge=lfs -text
44
+ checkpoint-5625/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
45
+ checkpoint-5625/spiece.model filter=lfs diff=lfs merge=lfs -text
46
+ checkpoint-3750/spiece.model filter=lfs diff=lfs merge=lfs -text
47
+ checkpoint-4500/spiece.model filter=lfs diff=lfs merge=lfs -text
48
+ checkpoint-4875/spiece.model filter=lfs diff=lfs merge=lfs -text
49
+ checkpoint-5250/spiece.model filter=lfs diff=lfs merge=lfs -text
50
+ spiece.model filter=lfs diff=lfs merge=lfs -text
51
+ pytorch_model.bin 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
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
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: 0.8169
21
+ - Bleu: 0.0012
22
+ - Rouge1: 0.1986
23
+ - Rouge2: 0.0594
24
+ - Avg Length: 14.004
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 | 0.9943 | 0.0003 | 0.1637 | 0.0365 | 13.785 |
58
+ | 2.445 | 2.0 | 750 | 0.8991 | 0.0002 | 0.171 | 0.041 | 13.0266 |
59
+ | 0.8324 | 3.0 | 1125 | 0.8509 | 0.001 | 0.1931 | 0.0499 | 14.9474 |
60
+ | 0.7567 | 4.0 | 1500 | 0.8184 | 0.0015 | 0.2019 | 0.0561 | 14.9598 |
61
+ | 0.7567 | 5.0 | 1875 | 0.8002 | 0.0016 | 0.2097 | 0.0608 | 14.496 |
62
+ | 0.6947 | 6.0 | 2250 | 0.7793 | 0.0016 | 0.2138 | 0.0631 | 14.6502 |
63
+ | 0.658 | 7.0 | 2625 | 0.7721 | 0.0018 | 0.2104 | 0.0617 | 15.2 |
64
+ | 0.6186 | 8.0 | 3000 | 0.7669 | 0.0023 | 0.2175 | 0.0642 | 15.7472 |
65
+ | 0.6186 | 9.0 | 3375 | 0.7792 | 0.0027 | 0.2218 | 0.0664 | 15.862 |
66
+ | 0.58 | 10.0 | 3750 | 0.7629 | 0.0005 | 0.1985 | 0.0591 | 12.0968 |
67
+ | 0.5533 | 11.0 | 4125 | 0.7826 | 0.0027 | 0.2126 | 0.0631 | 16.9146 |
68
+ | 0.5279 | 12.0 | 4500 | 0.7907 | 0.0025 | 0.2144 | 0.0626 | 16.656 |
69
+ | 0.5279 | 13.0 | 4875 | 0.7827 | 0.0007 | 0.2019 | 0.0606 | 12.4734 |
70
+ | 0.4964 | 14.0 | 5250 | 0.7933 | 0.0023 | 0.2204 | 0.0674 | 15.344 |
71
+ | 0.4803 | 15.0 | 5625 | 0.8169 | 0.0012 | 0.1986 | 0.0594 | 14.004 |
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-3750/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-3750/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-3750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4360ead5e122eee7bc0f2eaa52cdb8a806453b1796deb6587aa1a66741f210a3
3
+ size 839173
checkpoint-3750/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2cc75e8e5a197d71c2ff655259c6396ac56b05dbe5200db7283115115bfa4f
3
+ size 242071641
checkpoint-3750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4e0a14555d85bd0b7c41e28952ae7ff0cf571d8e5d412c64d04fb5bdd788a8
3
+ size 14575
checkpoint-3750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5665fbe1d59dedbe278a1e273dad540858dbe29da267b14296720e4adae2bf41
3
+ size 881
checkpoint-3750/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-3750/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-3750/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3750/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-3750/trainer_state.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.762901246547699,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python/checkpoint-3750",
4
+ "epoch": 10.0,
5
+ "global_step": 3750,
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": 13.785,
13
+ "eval_bleu": 0.0003,
14
+ "eval_loss": 0.9942636489868164,
15
+ "eval_rouge1": 0.1637,
16
+ "eval_rouge2": 0.0365,
17
+ "eval_runtime": 204.2034,
18
+ "eval_samples_per_second": 24.485,
19
+ "eval_steps_per_second": 3.061,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.011613128706812859,
25
+ "loss": 2.445,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 13.0266,
31
+ "eval_bleu": 0.0002,
32
+ "eval_loss": 0.8991339802742004,
33
+ "eval_rouge1": 0.171,
34
+ "eval_rouge2": 0.041,
35
+ "eval_runtime": 201.2399,
36
+ "eval_samples_per_second": 24.846,
37
+ "eval_steps_per_second": 3.106,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.02327057346701622,
43
+ "loss": 0.8324,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 14.9474,
49
+ "eval_bleu": 0.001,
50
+ "eval_loss": 0.8509177565574646,
51
+ "eval_rouge1": 0.1931,
52
+ "eval_rouge2": 0.0499,
53
+ "eval_runtime": 202.2102,
54
+ "eval_samples_per_second": 24.727,
55
+ "eval_steps_per_second": 3.091,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.03500078245997429,
61
+ "loss": 0.7567,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 14.9598,
67
+ "eval_bleu": 0.0015,
68
+ "eval_loss": 0.8183696866035461,
69
+ "eval_rouge1": 0.2019,
70
+ "eval_rouge2": 0.0561,
71
+ "eval_runtime": 202.119,
72
+ "eval_samples_per_second": 24.738,
73
+ "eval_steps_per_second": 3.092,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 14.496,
79
+ "eval_bleu": 0.0016,
80
+ "eval_loss": 0.8002403378486633,
81
+ "eval_rouge1": 0.2097,
82
+ "eval_rouge2": 0.0608,
83
+ "eval_runtime": 192.5036,
84
+ "eval_samples_per_second": 25.974,
85
+ "eval_steps_per_second": 3.247,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.04683626815676689,
91
+ "loss": 0.6947,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 14.6502,
97
+ "eval_bleu": 0.0016,
98
+ "eval_loss": 0.7792889475822449,
99
+ "eval_rouge1": 0.2138,
100
+ "eval_rouge2": 0.0631,
101
+ "eval_runtime": 203.4751,
102
+ "eval_samples_per_second": 24.573,
103
+ "eval_steps_per_second": 3.072,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.05882224813103676,
109
+ "loss": 0.658,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 15.2,
115
+ "eval_bleu": 0.0018,
116
+ "eval_loss": 0.7721025347709656,
117
+ "eval_rouge1": 0.2104,
118
+ "eval_rouge2": 0.0617,
119
+ "eval_runtime": 185.635,
120
+ "eval_samples_per_second": 26.935,
121
+ "eval_steps_per_second": 3.367,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.07100344449281693,
127
+ "loss": 0.6186,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 15.7472,
133
+ "eval_bleu": 0.0023,
134
+ "eval_loss": 0.7669309377670288,
135
+ "eval_rouge1": 0.2175,
136
+ "eval_rouge2": 0.0642,
137
+ "eval_runtime": 203.9621,
138
+ "eval_samples_per_second": 24.514,
139
+ "eval_steps_per_second": 3.064,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 15.862,
145
+ "eval_bleu": 0.0027,
146
+ "eval_loss": 0.7791835069656372,
147
+ "eval_rouge1": 0.2218,
148
+ "eval_rouge2": 0.0664,
149
+ "eval_runtime": 203.2586,
150
+ "eval_samples_per_second": 24.599,
151
+ "eval_steps_per_second": 3.075,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.08339222520589828,
157
+ "loss": 0.58,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 12.0968,
163
+ "eval_bleu": 0.0005,
164
+ "eval_loss": 0.762901246547699,
165
+ "eval_rouge1": 0.1985,
166
+ "eval_rouge2": 0.0591,
167
+ "eval_runtime": 199.4481,
168
+ "eval_samples_per_second": 25.069,
169
+ "eval_steps_per_second": 3.134,
170
+ "step": 3750
171
+ }
172
+ ],
173
+ "max_steps": 5625,
174
+ "num_train_epochs": 15,
175
+ "total_flos": 2.03012702208e+16,
176
+ "trial_name": null,
177
+ "trial_params": null
178
+ }
checkpoint-3750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aaf39e239b2a9a6ede734a130a29fe1d46056289b5036383e154158f280b560
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 sha256:4df0924aa7e0451ffa4e8a9e70c20ecb5edf95dc6eda45d9c1fbb2fef0c415b1
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:af0a54d73e395f9936aa865670251717e444d7b9f49aacc4b4c21d18c823f6bc
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 sha256:7656fba1301da3779c381a030b9742e142f5a8e5fa9e0338836340f6910cc8c1
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": 0.762901246547699,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python/checkpoint-3750",
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": 13.785,
13
+ "eval_bleu": 0.0003,
14
+ "eval_loss": 0.9942636489868164,
15
+ "eval_rouge1": 0.1637,
16
+ "eval_rouge2": 0.0365,
17
+ "eval_runtime": 204.2034,
18
+ "eval_samples_per_second": 24.485,
19
+ "eval_steps_per_second": 3.061,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.011613128706812859,
25
+ "loss": 2.445,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 13.0266,
31
+ "eval_bleu": 0.0002,
32
+ "eval_loss": 0.8991339802742004,
33
+ "eval_rouge1": 0.171,
34
+ "eval_rouge2": 0.041,
35
+ "eval_runtime": 201.2399,
36
+ "eval_samples_per_second": 24.846,
37
+ "eval_steps_per_second": 3.106,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.02327057346701622,
43
+ "loss": 0.8324,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 14.9474,
49
+ "eval_bleu": 0.001,
50
+ "eval_loss": 0.8509177565574646,
51
+ "eval_rouge1": 0.1931,
52
+ "eval_rouge2": 0.0499,
53
+ "eval_runtime": 202.2102,
54
+ "eval_samples_per_second": 24.727,
55
+ "eval_steps_per_second": 3.091,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.03500078245997429,
61
+ "loss": 0.7567,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 14.9598,
67
+ "eval_bleu": 0.0015,
68
+ "eval_loss": 0.8183696866035461,
69
+ "eval_rouge1": 0.2019,
70
+ "eval_rouge2": 0.0561,
71
+ "eval_runtime": 202.119,
72
+ "eval_samples_per_second": 24.738,
73
+ "eval_steps_per_second": 3.092,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 14.496,
79
+ "eval_bleu": 0.0016,
80
+ "eval_loss": 0.8002403378486633,
81
+ "eval_rouge1": 0.2097,
82
+ "eval_rouge2": 0.0608,
83
+ "eval_runtime": 192.5036,
84
+ "eval_samples_per_second": 25.974,
85
+ "eval_steps_per_second": 3.247,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.04683626815676689,
91
+ "loss": 0.6947,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 14.6502,
97
+ "eval_bleu": 0.0016,
98
+ "eval_loss": 0.7792889475822449,
99
+ "eval_rouge1": 0.2138,
100
+ "eval_rouge2": 0.0631,
101
+ "eval_runtime": 203.4751,
102
+ "eval_samples_per_second": 24.573,
103
+ "eval_steps_per_second": 3.072,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.05882224813103676,
109
+ "loss": 0.658,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 15.2,
115
+ "eval_bleu": 0.0018,
116
+ "eval_loss": 0.7721025347709656,
117
+ "eval_rouge1": 0.2104,
118
+ "eval_rouge2": 0.0617,
119
+ "eval_runtime": 185.635,
120
+ "eval_samples_per_second": 26.935,
121
+ "eval_steps_per_second": 3.367,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.07100344449281693,
127
+ "loss": 0.6186,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 15.7472,
133
+ "eval_bleu": 0.0023,
134
+ "eval_loss": 0.7669309377670288,
135
+ "eval_rouge1": 0.2175,
136
+ "eval_rouge2": 0.0642,
137
+ "eval_runtime": 203.9621,
138
+ "eval_samples_per_second": 24.514,
139
+ "eval_steps_per_second": 3.064,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 15.862,
145
+ "eval_bleu": 0.0027,
146
+ "eval_loss": 0.7791835069656372,
147
+ "eval_rouge1": 0.2218,
148
+ "eval_rouge2": 0.0664,
149
+ "eval_runtime": 203.2586,
150
+ "eval_samples_per_second": 24.599,
151
+ "eval_steps_per_second": 3.075,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.08339222520589828,
157
+ "loss": 0.58,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 12.0968,
163
+ "eval_bleu": 0.0005,
164
+ "eval_loss": 0.762901246547699,
165
+ "eval_rouge1": 0.1985,
166
+ "eval_rouge2": 0.0591,
167
+ "eval_runtime": 199.4481,
168
+ "eval_samples_per_second": 25.069,
169
+ "eval_steps_per_second": 3.134,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.0960661843419075,
175
+ "loss": 0.5533,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.9146,
181
+ "eval_bleu": 0.0027,
182
+ "eval_loss": 0.7826463580131531,
183
+ "eval_rouge1": 0.2126,
184
+ "eval_rouge2": 0.0631,
185
+ "eval_runtime": 199.9109,
186
+ "eval_samples_per_second": 25.011,
187
+ "eval_steps_per_second": 3.126,
188
+ "step": 4125
189
+ },
190
+ {
191
+ "epoch": 12.0,
192
+ "learning_rate": 0.10908319801092148,
193
+ "loss": 0.5279,
194
+ "step": 4500
195
+ },
196
+ {
197
+ "epoch": 12.0,
198
+ "eval_avg_length": 16.656,
199
+ "eval_bleu": 0.0025,
200
+ "eval_loss": 0.7907007932662964,
201
+ "eval_rouge1": 0.2144,
202
+ "eval_rouge2": 0.0626,
203
+ "eval_runtime": 193.36,
204
+ "eval_samples_per_second": 25.859,
205
+ "eval_steps_per_second": 3.232,
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 sha256:6aaf39e239b2a9a6ede734a130a29fe1d46056289b5036383e154158f280b560
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:a989c71d2a612825690c8ff5496e5b68849b8204d7200e7c0cae2510369ffa36
3
+ size 839173
checkpoint-4875/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65fc049b661fed621305454844fe1f565c6adfb96614b897ccc8febb7744382f
3
+ size 242071641
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 sha256:928525ab51223ee5cafbf87867e3ac63dd2b9c14956838539f7d61b00310a863
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": 0.762901246547699,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python/checkpoint-3750",
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": 13.785,
13
+ "eval_bleu": 0.0003,
14
+ "eval_loss": 0.9942636489868164,
15
+ "eval_rouge1": 0.1637,
16
+ "eval_rouge2": 0.0365,
17
+ "eval_runtime": 204.2034,
18
+ "eval_samples_per_second": 24.485,
19
+ "eval_steps_per_second": 3.061,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.011613128706812859,
25
+ "loss": 2.445,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 13.0266,
31
+ "eval_bleu": 0.0002,
32
+ "eval_loss": 0.8991339802742004,
33
+ "eval_rouge1": 0.171,
34
+ "eval_rouge2": 0.041,
35
+ "eval_runtime": 201.2399,
36
+ "eval_samples_per_second": 24.846,
37
+ "eval_steps_per_second": 3.106,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.02327057346701622,
43
+ "loss": 0.8324,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 14.9474,
49
+ "eval_bleu": 0.001,
50
+ "eval_loss": 0.8509177565574646,
51
+ "eval_rouge1": 0.1931,
52
+ "eval_rouge2": 0.0499,
53
+ "eval_runtime": 202.2102,
54
+ "eval_samples_per_second": 24.727,
55
+ "eval_steps_per_second": 3.091,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.03500078245997429,
61
+ "loss": 0.7567,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 14.9598,
67
+ "eval_bleu": 0.0015,
68
+ "eval_loss": 0.8183696866035461,
69
+ "eval_rouge1": 0.2019,
70
+ "eval_rouge2": 0.0561,
71
+ "eval_runtime": 202.119,
72
+ "eval_samples_per_second": 24.738,
73
+ "eval_steps_per_second": 3.092,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 14.496,
79
+ "eval_bleu": 0.0016,
80
+ "eval_loss": 0.8002403378486633,
81
+ "eval_rouge1": 0.2097,
82
+ "eval_rouge2": 0.0608,
83
+ "eval_runtime": 192.5036,
84
+ "eval_samples_per_second": 25.974,
85
+ "eval_steps_per_second": 3.247,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.04683626815676689,
91
+ "loss": 0.6947,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 14.6502,
97
+ "eval_bleu": 0.0016,
98
+ "eval_loss": 0.7792889475822449,
99
+ "eval_rouge1": 0.2138,
100
+ "eval_rouge2": 0.0631,
101
+ "eval_runtime": 203.4751,
102
+ "eval_samples_per_second": 24.573,
103
+ "eval_steps_per_second": 3.072,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.05882224813103676,
109
+ "loss": 0.658,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 15.2,
115
+ "eval_bleu": 0.0018,
116
+ "eval_loss": 0.7721025347709656,
117
+ "eval_rouge1": 0.2104,
118
+ "eval_rouge2": 0.0617,
119
+ "eval_runtime": 185.635,
120
+ "eval_samples_per_second": 26.935,
121
+ "eval_steps_per_second": 3.367,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.07100344449281693,
127
+ "loss": 0.6186,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 15.7472,
133
+ "eval_bleu": 0.0023,
134
+ "eval_loss": 0.7669309377670288,
135
+ "eval_rouge1": 0.2175,
136
+ "eval_rouge2": 0.0642,
137
+ "eval_runtime": 203.9621,
138
+ "eval_samples_per_second": 24.514,
139
+ "eval_steps_per_second": 3.064,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 15.862,
145
+ "eval_bleu": 0.0027,
146
+ "eval_loss": 0.7791835069656372,
147
+ "eval_rouge1": 0.2218,
148
+ "eval_rouge2": 0.0664,
149
+ "eval_runtime": 203.2586,
150
+ "eval_samples_per_second": 24.599,
151
+ "eval_steps_per_second": 3.075,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.08339222520589828,
157
+ "loss": 0.58,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 12.0968,
163
+ "eval_bleu": 0.0005,
164
+ "eval_loss": 0.762901246547699,
165
+ "eval_rouge1": 0.1985,
166
+ "eval_rouge2": 0.0591,
167
+ "eval_runtime": 199.4481,
168
+ "eval_samples_per_second": 25.069,
169
+ "eval_steps_per_second": 3.134,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.0960661843419075,
175
+ "loss": 0.5533,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.9146,
181
+ "eval_bleu": 0.0027,
182
+ "eval_loss": 0.7826463580131531,
183
+ "eval_rouge1": 0.2126,
184
+ "eval_rouge2": 0.0631,
185
+ "eval_runtime": 199.9109,
186
+ "eval_samples_per_second": 25.011,
187
+ "eval_steps_per_second": 3.126,
188
+ "step": 4125
189
+ },
190
+ {
191
+ "epoch": 12.0,
192
+ "learning_rate": 0.10908319801092148,
193
+ "loss": 0.5279,
194
+ "step": 4500
195
+ },
196
+ {
197
+ "epoch": 12.0,
198
+ "eval_avg_length": 16.656,
199
+ "eval_bleu": 0.0025,
200
+ "eval_loss": 0.7907007932662964,
201
+ "eval_rouge1": 0.2144,
202
+ "eval_rouge2": 0.0626,
203
+ "eval_runtime": 193.36,
204
+ "eval_samples_per_second": 25.859,
205
+ "eval_steps_per_second": 3.232,
206
+ "step": 4500
207
+ },
208
+ {
209
+ "epoch": 13.0,
210
+ "eval_avg_length": 12.4734,
211
+ "eval_bleu": 0.0007,
212
+ "eval_loss": 0.7827274203300476,
213
+ "eval_rouge1": 0.2019,
214
+ "eval_rouge2": 0.0606,
215
+ "eval_runtime": 198.3606,
216
+ "eval_samples_per_second": 25.207,
217
+ "eval_steps_per_second": 3.151,
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 sha256:6aaf39e239b2a9a6ede734a130a29fe1d46056289b5036383e154158f280b560
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 sha256:927d07a3ce81dbaec6171473877a344f3c5ba537172c2e3ddaf69caeba1b6710
3
+ size 839173
checkpoint-5250/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24682f0814c656c7df26fe31397f2e1cc4a0d448404b4e92b3e977e1997b5f9b
3
+ size 242071641
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 sha256:74e20f44732b20cc8b49137ee71dc05fbb9155506c869acc4074cf08b954ed30
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": 0.762901246547699,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python/checkpoint-3750",
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": 13.785,
13
+ "eval_bleu": 0.0003,
14
+ "eval_loss": 0.9942636489868164,
15
+ "eval_rouge1": 0.1637,
16
+ "eval_rouge2": 0.0365,
17
+ "eval_runtime": 204.2034,
18
+ "eval_samples_per_second": 24.485,
19
+ "eval_steps_per_second": 3.061,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.011613128706812859,
25
+ "loss": 2.445,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 13.0266,
31
+ "eval_bleu": 0.0002,
32
+ "eval_loss": 0.8991339802742004,
33
+ "eval_rouge1": 0.171,
34
+ "eval_rouge2": 0.041,
35
+ "eval_runtime": 201.2399,
36
+ "eval_samples_per_second": 24.846,
37
+ "eval_steps_per_second": 3.106,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.02327057346701622,
43
+ "loss": 0.8324,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 14.9474,
49
+ "eval_bleu": 0.001,
50
+ "eval_loss": 0.8509177565574646,
51
+ "eval_rouge1": 0.1931,
52
+ "eval_rouge2": 0.0499,
53
+ "eval_runtime": 202.2102,
54
+ "eval_samples_per_second": 24.727,
55
+ "eval_steps_per_second": 3.091,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.03500078245997429,
61
+ "loss": 0.7567,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 14.9598,
67
+ "eval_bleu": 0.0015,
68
+ "eval_loss": 0.8183696866035461,
69
+ "eval_rouge1": 0.2019,
70
+ "eval_rouge2": 0.0561,
71
+ "eval_runtime": 202.119,
72
+ "eval_samples_per_second": 24.738,
73
+ "eval_steps_per_second": 3.092,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 14.496,
79
+ "eval_bleu": 0.0016,
80
+ "eval_loss": 0.8002403378486633,
81
+ "eval_rouge1": 0.2097,
82
+ "eval_rouge2": 0.0608,
83
+ "eval_runtime": 192.5036,
84
+ "eval_samples_per_second": 25.974,
85
+ "eval_steps_per_second": 3.247,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.04683626815676689,
91
+ "loss": 0.6947,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 14.6502,
97
+ "eval_bleu": 0.0016,
98
+ "eval_loss": 0.7792889475822449,
99
+ "eval_rouge1": 0.2138,
100
+ "eval_rouge2": 0.0631,
101
+ "eval_runtime": 203.4751,
102
+ "eval_samples_per_second": 24.573,
103
+ "eval_steps_per_second": 3.072,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.05882224813103676,
109
+ "loss": 0.658,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 15.2,
115
+ "eval_bleu": 0.0018,
116
+ "eval_loss": 0.7721025347709656,
117
+ "eval_rouge1": 0.2104,
118
+ "eval_rouge2": 0.0617,
119
+ "eval_runtime": 185.635,
120
+ "eval_samples_per_second": 26.935,
121
+ "eval_steps_per_second": 3.367,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.07100344449281693,
127
+ "loss": 0.6186,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 15.7472,
133
+ "eval_bleu": 0.0023,
134
+ "eval_loss": 0.7669309377670288,
135
+ "eval_rouge1": 0.2175,
136
+ "eval_rouge2": 0.0642,
137
+ "eval_runtime": 203.9621,
138
+ "eval_samples_per_second": 24.514,
139
+ "eval_steps_per_second": 3.064,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 15.862,
145
+ "eval_bleu": 0.0027,
146
+ "eval_loss": 0.7791835069656372,
147
+ "eval_rouge1": 0.2218,
148
+ "eval_rouge2": 0.0664,
149
+ "eval_runtime": 203.2586,
150
+ "eval_samples_per_second": 24.599,
151
+ "eval_steps_per_second": 3.075,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.08339222520589828,
157
+ "loss": 0.58,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 12.0968,
163
+ "eval_bleu": 0.0005,
164
+ "eval_loss": 0.762901246547699,
165
+ "eval_rouge1": 0.1985,
166
+ "eval_rouge2": 0.0591,
167
+ "eval_runtime": 199.4481,
168
+ "eval_samples_per_second": 25.069,
169
+ "eval_steps_per_second": 3.134,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.0960661843419075,
175
+ "loss": 0.5533,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.9146,
181
+ "eval_bleu": 0.0027,
182
+ "eval_loss": 0.7826463580131531,
183
+ "eval_rouge1": 0.2126,
184
+ "eval_rouge2": 0.0631,
185
+ "eval_runtime": 199.9109,
186
+ "eval_samples_per_second": 25.011,
187
+ "eval_steps_per_second": 3.126,
188
+ "step": 4125
189
+ },
190
+ {
191
+ "epoch": 12.0,
192
+ "learning_rate": 0.10908319801092148,
193
+ "loss": 0.5279,
194
+ "step": 4500
195
+ },
196
+ {
197
+ "epoch": 12.0,
198
+ "eval_avg_length": 16.656,
199
+ "eval_bleu": 0.0025,
200
+ "eval_loss": 0.7907007932662964,
201
+ "eval_rouge1": 0.2144,
202
+ "eval_rouge2": 0.0626,
203
+ "eval_runtime": 193.36,
204
+ "eval_samples_per_second": 25.859,
205
+ "eval_steps_per_second": 3.232,
206
+ "step": 4500
207
+ },
208
+ {
209
+ "epoch": 13.0,
210
+ "eval_avg_length": 12.4734,
211
+ "eval_bleu": 0.0007,
212
+ "eval_loss": 0.7827274203300476,
213
+ "eval_rouge1": 0.2019,
214
+ "eval_rouge2": 0.0606,
215
+ "eval_runtime": 198.3606,
216
+ "eval_samples_per_second": 25.207,
217
+ "eval_steps_per_second": 3.151,
218
+ "step": 4875
219
+ },
220
+ {
221
+ "epoch": 13.33,
222
+ "learning_rate": 0.12240996956825256,
223
+ "loss": 0.4964,
224
+ "step": 5000
225
+ },
226
+ {
227
+ "epoch": 14.0,
228
+ "eval_avg_length": 15.344,
229
+ "eval_bleu": 0.0023,
230
+ "eval_loss": 0.7932928800582886,
231
+ "eval_rouge1": 0.2204,
232
+ "eval_rouge2": 0.0674,
233
+ "eval_runtime": 203.8061,
234
+ "eval_samples_per_second": 24.533,
235
+ "eval_steps_per_second": 3.067,
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 sha256:6aaf39e239b2a9a6ede734a130a29fe1d46056289b5036383e154158f280b560
3
+ size 3963