Hugging Face's logo

lmeninato
/
flan-t5-small-codesearchnet-python

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
lmeninato commited on
Commit
c3fcdc2
·
1 Parent(s): 1c5a9ef

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-1500/config.json +61 -0
  4. checkpoint-1500/generation_config.json +6 -0
  5. checkpoint-1500/optimizer.pt +3 -0
  6. checkpoint-1500/pytorch_model.bin +3 -0
  7. checkpoint-1500/rng_state.pth +3 -0
  8. checkpoint-1500/scheduler.pt +3 -0
  9. checkpoint-1500/special_tokens_map.json +107 -0
  10. checkpoint-1500/spiece.model +3 -0
  11. checkpoint-1500/tokenizer.json +0 -0
  12. checkpoint-1500/tokenizer_config.json +112 -0
  13. checkpoint-1500/trainer_state.json +82 -0
  14. checkpoint-1500/training_args.bin +3 -0
  15. checkpoint-4500/config.json +61 -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 +112 -0
  25. checkpoint-4500/trainer_state.json +214 -0
  26. checkpoint-4500/training_args.bin +3 -0
  27. checkpoint-4875/config.json +61 -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 +112 -0
  37. checkpoint-4875/trainer_state.json +226 -0
  38. checkpoint-4875/training_args.bin +3 -0
  39. checkpoint-5250/config.json +61 -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 +112 -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
+ spiece.model filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-4500/spiece.model filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-4875/spiece.model filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-5250/spiece.model filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-5625/spiece.model filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-1500/spiece.model filter=lfs diff=lfs merge=lfs -text
41
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-5625/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-4500/training_args.bin filter=lfs diff=lfs merge=lfs -text
44
+ checkpoint-4875/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
45
+ checkpoint-5250/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
46
+ checkpoint-5250/training_args.bin filter=lfs diff=lfs merge=lfs -text
47
+ checkpoint-5625/training_args.bin filter=lfs diff=lfs merge=lfs -text
48
+ checkpoint-1500/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
49
+ checkpoint-1500/training_args.bin filter=lfs diff=lfs merge=lfs -text
50
+ checkpoint-4500/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
51
+ checkpoint-4875/training_args.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: flan-t5-small-codesearchnet-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
+ # flan-t5-small-codesearchnet-python
17
+
18
+ This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0764
21
+ - Bleu: 0.0349
22
+ - Rouge1: 0.6244
23
+ - Rouge2: 0.6055
24
+ - Avg Length: 16.9912
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 | 0.0636 | 0.0364 | 0.6253 | 0.6076 | 17.029 |
58
+ | 5.5166 | 2.0 | 750 | 0.0553 | 0.0351 | 0.6259 | 0.6081 | 16.9996 |
59
+ | 0.0485 | 3.0 | 1125 | 0.0537 | 0.0351 | 0.6258 | 0.6083 | 16.99 |
60
+ | 0.0409 | 4.0 | 1500 | 0.0524 | 0.0351 | 0.6258 | 0.6082 | 16.9942 |
61
+ | 0.0409 | 5.0 | 1875 | 0.0524 | 0.0351 | 0.6261 | 0.6086 | 16.997 |
62
+ | 0.0345 | 6.0 | 2250 | 0.0526 | 0.0351 | 0.6258 | 0.6081 | 16.9936 |
63
+ | 0.0303 | 7.0 | 2625 | 0.0533 | 0.035 | 0.6254 | 0.6076 | 16.991 |
64
+ | 0.0256 | 8.0 | 3000 | 0.0566 | 0.035 | 0.6257 | 0.6074 | 16.9964 |
65
+ | 0.0256 | 9.0 | 3375 | 0.0592 | 0.0349 | 0.6253 | 0.6074 | 16.998 |
66
+ | 0.0205 | 10.0 | 3750 | 0.0612 | 0.0351 | 0.6255 | 0.6073 | 16.9932 |
67
+ | 0.0185 | 11.0 | 4125 | 0.0639 | 0.035 | 0.6257 | 0.6079 | 16.996 |
68
+ | 0.0157 | 12.0 | 4500 | 0.0698 | 0.035 | 0.625 | 0.6064 | 16.9944 |
69
+ | 0.0157 | 13.0 | 4875 | 0.0720 | 0.035 | 0.6246 | 0.6062 | 16.991 |
70
+ | 0.0131 | 14.0 | 5250 | 0.0745 | 0.035 | 0.6247 | 0.6062 | 16.9986 |
71
+ | 0.0128 | 15.0 | 5625 | 0.0764 | 0.0349 | 0.6244 | 0.6055 | 16.9912 |
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-1500/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
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
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.28.1",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-1500/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-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d481967fce6684338e487f3e98a6162b5ef0ed3e853791406be6f93b3b44a7
3
+ size 1135621
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92846efb2013e1e052f26226ad0b12133dd01b30c380f722e87b84cd20c1fbf0
3
+ size 307910149
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc48121416ced2c66d3f893b88c99a99eada53aaa7a0f3d6811d8508bff5ce80
3
+ size 14575
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c5515f14cffa07c927da461133f1eb9d90aca9207cd7c90e0709ba18086128
3
+ size 881
checkpoint-1500/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-1500/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.05236489325761795,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/google/flan-t5-small-codesearchnet-python/checkpoint-1500",
4
+ "epoch": 4.0,
5
+ "global_step": 1500,
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": 17.029,
13
+ "eval_bleu": 0.0364,
14
+ "eval_loss": 0.06356053799390793,
15
+ "eval_rouge1": 0.6253,
16
+ "eval_rouge2": 0.6076,
17
+ "eval_runtime": 194.621,
18
+ "eval_samples_per_second": 25.691,
19
+ "eval_steps_per_second": 3.211,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.006761715281754732,
25
+ "loss": 5.5166,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 16.9996,
31
+ "eval_bleu": 0.0351,
32
+ "eval_loss": 0.05532339960336685,
33
+ "eval_rouge1": 0.6259,
34
+ "eval_rouge2": 0.6081,
35
+ "eval_runtime": 191.1842,
36
+ "eval_samples_per_second": 26.153,
37
+ "eval_steps_per_second": 3.269,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.013524587266147137,
43
+ "loss": 0.0485,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 16.99,
49
+ "eval_bleu": 0.0351,
50
+ "eval_loss": 0.05369499325752258,
51
+ "eval_rouge1": 0.6258,
52
+ "eval_rouge2": 0.6083,
53
+ "eval_runtime": 189.3124,
54
+ "eval_samples_per_second": 26.411,
55
+ "eval_steps_per_second": 3.301,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.02029060572385788,
61
+ "loss": 0.0409,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 16.9942,
67
+ "eval_bleu": 0.0351,
68
+ "eval_loss": 0.05236489325761795,
69
+ "eval_rouge1": 0.6258,
70
+ "eval_rouge2": 0.6082,
71
+ "eval_runtime": 189.5235,
72
+ "eval_samples_per_second": 26.382,
73
+ "eval_steps_per_second": 3.298,
74
+ "step": 1500
75
+ }
76
+ ],
77
+ "max_steps": 5625,
78
+ "num_train_epochs": 15,
79
+ "total_flos": 1.115343028224e+16,
80
+ "trial_name": null,
81
+ "trial_params": null
82
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff03095861cb20cf5f804443acba1a16458cb6cba7d63ac52b033c7e1cefa5b5
3
+ size 3963
checkpoint-4500/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
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
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.28.1",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
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 sha256:38d2b1675cf84c9c78e10c7adb7c8c4bb5f9cb829915b8ae00f0d3a42cf80684
3
+ size 1135621
checkpoint-4500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa314c05dcf695c90a8e8a0d1e51f663d552d20779f7c26a009d8e770223706
3
+ size 307910149
checkpoint-4500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c089b9a7e59d5d6666f1dbe366c974a06caae14f9012152466e21b7da1af98eb
3
+ size 14575
checkpoint-4500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88318505ce8115de332343f505dcc0374b72df2613ad6748ea4a81e058f764bb
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 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
checkpoint-4500/trainer_state.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.05236489325761795,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/google/flan-t5-small-codesearchnet-python/checkpoint-1500",
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": 17.029,
13
+ "eval_bleu": 0.0364,
14
+ "eval_loss": 0.06356053799390793,
15
+ "eval_rouge1": 0.6253,
16
+ "eval_rouge2": 0.6076,
17
+ "eval_runtime": 194.621,
18
+ "eval_samples_per_second": 25.691,
19
+ "eval_steps_per_second": 3.211,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.006761715281754732,
25
+ "loss": 5.5166,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 16.9996,
31
+ "eval_bleu": 0.0351,
32
+ "eval_loss": 0.05532339960336685,
33
+ "eval_rouge1": 0.6259,
34
+ "eval_rouge2": 0.6081,
35
+ "eval_runtime": 191.1842,
36
+ "eval_samples_per_second": 26.153,
37
+ "eval_steps_per_second": 3.269,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.013524587266147137,
43
+ "loss": 0.0485,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 16.99,
49
+ "eval_bleu": 0.0351,
50
+ "eval_loss": 0.05369499325752258,
51
+ "eval_rouge1": 0.6258,
52
+ "eval_rouge2": 0.6083,
53
+ "eval_runtime": 189.3124,
54
+ "eval_samples_per_second": 26.411,
55
+ "eval_steps_per_second": 3.301,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.02029060572385788,
61
+ "loss": 0.0409,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 16.9942,
67
+ "eval_bleu": 0.0351,
68
+ "eval_loss": 0.05236489325761795,
69
+ "eval_rouge1": 0.6258,
70
+ "eval_rouge2": 0.6082,
71
+ "eval_runtime": 189.5235,
72
+ "eval_samples_per_second": 26.382,
73
+ "eval_steps_per_second": 3.298,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 16.997,
79
+ "eval_bleu": 0.0351,
80
+ "eval_loss": 0.052440039813518524,
81
+ "eval_rouge1": 0.6261,
82
+ "eval_rouge2": 0.6086,
83
+ "eval_runtime": 188.8356,
84
+ "eval_samples_per_second": 26.478,
85
+ "eval_steps_per_second": 3.31,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.027062522247433662,
91
+ "loss": 0.0345,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 16.9936,
97
+ "eval_bleu": 0.0351,
98
+ "eval_loss": 0.052636753767728806,
99
+ "eval_rouge1": 0.6258,
100
+ "eval_rouge2": 0.6081,
101
+ "eval_runtime": 188.807,
102
+ "eval_samples_per_second": 26.482,
103
+ "eval_steps_per_second": 3.31,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.03384636715054512,
109
+ "loss": 0.0303,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 16.991,
115
+ "eval_bleu": 0.035,
116
+ "eval_loss": 0.0532960519194603,
117
+ "eval_rouge1": 0.6254,
118
+ "eval_rouge2": 0.6076,
119
+ "eval_runtime": 195.9042,
120
+ "eval_samples_per_second": 25.523,
121
+ "eval_steps_per_second": 3.19,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.04064999520778656,
127
+ "loss": 0.0256,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 16.9964,
133
+ "eval_bleu": 0.035,
134
+ "eval_loss": 0.05655151233077049,
135
+ "eval_rouge1": 0.6257,
136
+ "eval_rouge2": 0.6074,
137
+ "eval_runtime": 193.7837,
138
+ "eval_samples_per_second": 25.802,
139
+ "eval_steps_per_second": 3.225,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 16.998,
145
+ "eval_bleu": 0.0349,
146
+ "eval_loss": 0.05918492376804352,
147
+ "eval_rouge1": 0.6253,
148
+ "eval_rouge2": 0.6074,
149
+ "eval_runtime": 190.3532,
150
+ "eval_samples_per_second": 26.267,
151
+ "eval_steps_per_second": 3.283,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.047494322061538696,
157
+ "loss": 0.0205,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 16.9932,
163
+ "eval_bleu": 0.0351,
164
+ "eval_loss": 0.06117509678006172,
165
+ "eval_rouge1": 0.6255,
166
+ "eval_rouge2": 0.6073,
167
+ "eval_runtime": 197.2772,
168
+ "eval_samples_per_second": 25.345,
169
+ "eval_steps_per_second": 3.168,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.054379865527153015,
175
+ "loss": 0.0185,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.996,
181
+ "eval_bleu": 0.035,
182
+ "eval_loss": 0.06389027088880539,
183
+ "eval_rouge1": 0.6257,
184
+ "eval_rouge2": 0.6079,
185
+ "eval_runtime": 194.6757,
186
+ "eval_samples_per_second": 25.684,
187
+ "eval_steps_per_second": 3.21,
188
+ "step": 4125
189
+ },
190
+ {
191
+ "epoch": 12.0,
192
+ "learning_rate": 0.0613127239048481,
193
+ "loss": 0.0157,
194
+ "step": 4500
195
+ },
196
+ {
197
+ "epoch": 12.0,
198
+ "eval_avg_length": 16.9944,
199
+ "eval_bleu": 0.035,
200
+ "eval_loss": 0.06984004378318787,
201
+ "eval_rouge1": 0.625,
202
+ "eval_rouge2": 0.6064,
203
+ "eval_runtime": 196.3811,
204
+ "eval_samples_per_second": 25.461,
205
+ "eval_steps_per_second": 3.183,
206
+ "step": 4500
207
+ }
208
+ ],
209
+ "max_steps": 5625,
210
+ "num_train_epochs": 15,
211
+ "total_flos": 3.346029084672e+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:ff03095861cb20cf5f804443acba1a16458cb6cba7d63ac52b033c7e1cefa5b5
3
+ size 3963
checkpoint-4875/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
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
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.28.1",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
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 sha256:3c8483b812a31d616cc95f5d73f025a56d5de3439a0ae1bbb6989b2ed68ea070
3
+ size 1135621
checkpoint-4875/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee837027fd739c7458cefc0d9aceaa049dc0ef69e917d1c62f267d8aa93feef
3
+ size 307910149
checkpoint-4875/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d427c251b76040d92cd4586aff1069422f6078ffa5a2a8f26578384d6911c9e6
3
+ size 14575
checkpoint-4875/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c224ff2b3fe0a5a7855350457befe494c9089ef105e7f02a4376f5d9c423338f
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 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
checkpoint-4875/trainer_state.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.05236489325761795,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/google/flan-t5-small-codesearchnet-python/checkpoint-1500",
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": 17.029,
13
+ "eval_bleu": 0.0364,
14
+ "eval_loss": 0.06356053799390793,
15
+ "eval_rouge1": 0.6253,
16
+ "eval_rouge2": 0.6076,
17
+ "eval_runtime": 194.621,
18
+ "eval_samples_per_second": 25.691,
19
+ "eval_steps_per_second": 3.211,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.006761715281754732,
25
+ "loss": 5.5166,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 16.9996,
31
+ "eval_bleu": 0.0351,
32
+ "eval_loss": 0.05532339960336685,
33
+ "eval_rouge1": 0.6259,
34
+ "eval_rouge2": 0.6081,
35
+ "eval_runtime": 191.1842,
36
+ "eval_samples_per_second": 26.153,
37
+ "eval_steps_per_second": 3.269,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.013524587266147137,
43
+ "loss": 0.0485,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 16.99,
49
+ "eval_bleu": 0.0351,
50
+ "eval_loss": 0.05369499325752258,
51
+ "eval_rouge1": 0.6258,
52
+ "eval_rouge2": 0.6083,
53
+ "eval_runtime": 189.3124,
54
+ "eval_samples_per_second": 26.411,
55
+ "eval_steps_per_second": 3.301,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.02029060572385788,
61
+ "loss": 0.0409,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 16.9942,
67
+ "eval_bleu": 0.0351,
68
+ "eval_loss": 0.05236489325761795,
69
+ "eval_rouge1": 0.6258,
70
+ "eval_rouge2": 0.6082,
71
+ "eval_runtime": 189.5235,
72
+ "eval_samples_per_second": 26.382,
73
+ "eval_steps_per_second": 3.298,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 16.997,
79
+ "eval_bleu": 0.0351,
80
+ "eval_loss": 0.052440039813518524,
81
+ "eval_rouge1": 0.6261,
82
+ "eval_rouge2": 0.6086,
83
+ "eval_runtime": 188.8356,
84
+ "eval_samples_per_second": 26.478,
85
+ "eval_steps_per_second": 3.31,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.027062522247433662,
91
+ "loss": 0.0345,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 16.9936,
97
+ "eval_bleu": 0.0351,
98
+ "eval_loss": 0.052636753767728806,
99
+ "eval_rouge1": 0.6258,
100
+ "eval_rouge2": 0.6081,
101
+ "eval_runtime": 188.807,
102
+ "eval_samples_per_second": 26.482,
103
+ "eval_steps_per_second": 3.31,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.03384636715054512,
109
+ "loss": 0.0303,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 16.991,
115
+ "eval_bleu": 0.035,
116
+ "eval_loss": 0.0532960519194603,
117
+ "eval_rouge1": 0.6254,
118
+ "eval_rouge2": 0.6076,
119
+ "eval_runtime": 195.9042,
120
+ "eval_samples_per_second": 25.523,
121
+ "eval_steps_per_second": 3.19,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.04064999520778656,
127
+ "loss": 0.0256,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 16.9964,
133
+ "eval_bleu": 0.035,
134
+ "eval_loss": 0.05655151233077049,
135
+ "eval_rouge1": 0.6257,
136
+ "eval_rouge2": 0.6074,
137
+ "eval_runtime": 193.7837,
138
+ "eval_samples_per_second": 25.802,
139
+ "eval_steps_per_second": 3.225,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 16.998,
145
+ "eval_bleu": 0.0349,
146
+ "eval_loss": 0.05918492376804352,
147
+ "eval_rouge1": 0.6253,
148
+ "eval_rouge2": 0.6074,
149
+ "eval_runtime": 190.3532,
150
+ "eval_samples_per_second": 26.267,
151
+ "eval_steps_per_second": 3.283,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.047494322061538696,
157
+ "loss": 0.0205,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 16.9932,
163
+ "eval_bleu": 0.0351,
164
+ "eval_loss": 0.06117509678006172,
165
+ "eval_rouge1": 0.6255,
166
+ "eval_rouge2": 0.6073,
167
+ "eval_runtime": 197.2772,
168
+ "eval_samples_per_second": 25.345,
169
+ "eval_steps_per_second": 3.168,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.054379865527153015,
175
+ "loss": 0.0185,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.996,
181
+ "eval_bleu": 0.035,
182
+ "eval_loss": 0.06389027088880539,
183
+ "eval_rouge1": 0.6257,
184
+ "eval_rouge2": 0.6079,
185
+ "eval_runtime": 194.6757,
186
+ "eval_samples_per_second": 25.684,
187
+ "eval_steps_per_second": 3.21,
188
+ "step": 4125
189
+ },
190
+ {
191
+ "epoch": 12.0,
192
+ "learning_rate": 0.0613127239048481,
193
+ "loss": 0.0157,
194
+ "step": 4500
195
+ },
196
+ {
197
+ "epoch": 12.0,
198
+ "eval_avg_length": 16.9944,
199
+ "eval_bleu": 0.035,
200
+ "eval_loss": 0.06984004378318787,
201
+ "eval_rouge1": 0.625,
202
+ "eval_rouge2": 0.6064,
203
+ "eval_runtime": 196.3811,
204
+ "eval_samples_per_second": 25.461,
205
+ "eval_steps_per_second": 3.183,
206
+ "step": 4500
207
+ },
208
+ {
209
+ "epoch": 13.0,
210
+ "eval_avg_length": 16.991,
211
+ "eval_bleu": 0.035,
212
+ "eval_loss": 0.07201451808214188,
213
+ "eval_rouge1": 0.6246,
214
+ "eval_rouge2": 0.6062,
215
+ "eval_runtime": 192.0847,
216
+ "eval_samples_per_second": 26.03,
217
+ "eval_steps_per_second": 3.254,
218
+ "step": 4875
219
+ }
220
+ ],
221
+ "max_steps": 5625,
222
+ "num_train_epochs": 15,
223
+ "total_flos": 3.624864841728e+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:ff03095861cb20cf5f804443acba1a16458cb6cba7d63ac52b033c7e1cefa5b5
3
+ size 3963
checkpoint-5250/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
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
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.28.1",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
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:ccc59f2bbc1559f50ddca499a9f52fd23141fde94baccd7ecd1a5471f1f88d45
3
+ size 1135621
checkpoint-5250/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fdac183aaca6971c3c91f87a411be106b6c4a09e3ec4f44da4a3a6745069eb1
3
+ size 307910149
checkpoint-5250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ddb108c57d771aa98defa3c9758893aebc839c73c088c68d21c7816fda2ffd
3
+ size 14575
checkpoint-5250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08277ca64242299755db8cd3e479bb670039f5b1dd7621a8a435ab8ef805c15f
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 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
checkpoint-5250/trainer_state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.05236489325761795,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/google/flan-t5-small-codesearchnet-python/checkpoint-1500",
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": 17.029,
13
+ "eval_bleu": 0.0364,
14
+ "eval_loss": 0.06356053799390793,
15
+ "eval_rouge1": 0.6253,
16
+ "eval_rouge2": 0.6076,
17
+ "eval_runtime": 194.621,
18
+ "eval_samples_per_second": 25.691,
19
+ "eval_steps_per_second": 3.211,
20
+ "step": 375
21
+ },
22
+ {
23
+ "epoch": 1.33,
24
+ "learning_rate": 0.006761715281754732,
25
+ "loss": 5.5166,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_avg_length": 16.9996,
31
+ "eval_bleu": 0.0351,
32
+ "eval_loss": 0.05532339960336685,
33
+ "eval_rouge1": 0.6259,
34
+ "eval_rouge2": 0.6081,
35
+ "eval_runtime": 191.1842,
36
+ "eval_samples_per_second": 26.153,
37
+ "eval_steps_per_second": 3.269,
38
+ "step": 750
39
+ },
40
+ {
41
+ "epoch": 2.67,
42
+ "learning_rate": 0.013524587266147137,
43
+ "loss": 0.0485,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_avg_length": 16.99,
49
+ "eval_bleu": 0.0351,
50
+ "eval_loss": 0.05369499325752258,
51
+ "eval_rouge1": 0.6258,
52
+ "eval_rouge2": 0.6083,
53
+ "eval_runtime": 189.3124,
54
+ "eval_samples_per_second": 26.411,
55
+ "eval_steps_per_second": 3.301,
56
+ "step": 1125
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "learning_rate": 0.02029060572385788,
61
+ "loss": 0.0409,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "eval_avg_length": 16.9942,
67
+ "eval_bleu": 0.0351,
68
+ "eval_loss": 0.05236489325761795,
69
+ "eval_rouge1": 0.6258,
70
+ "eval_rouge2": 0.6082,
71
+ "eval_runtime": 189.5235,
72
+ "eval_samples_per_second": 26.382,
73
+ "eval_steps_per_second": 3.298,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_avg_length": 16.997,
79
+ "eval_bleu": 0.0351,
80
+ "eval_loss": 0.052440039813518524,
81
+ "eval_rouge1": 0.6261,
82
+ "eval_rouge2": 0.6086,
83
+ "eval_runtime": 188.8356,
84
+ "eval_samples_per_second": 26.478,
85
+ "eval_steps_per_second": 3.31,
86
+ "step": 1875
87
+ },
88
+ {
89
+ "epoch": 5.33,
90
+ "learning_rate": 0.027062522247433662,
91
+ "loss": 0.0345,
92
+ "step": 2000
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_avg_length": 16.9936,
97
+ "eval_bleu": 0.0351,
98
+ "eval_loss": 0.052636753767728806,
99
+ "eval_rouge1": 0.6258,
100
+ "eval_rouge2": 0.6081,
101
+ "eval_runtime": 188.807,
102
+ "eval_samples_per_second": 26.482,
103
+ "eval_steps_per_second": 3.31,
104
+ "step": 2250
105
+ },
106
+ {
107
+ "epoch": 6.67,
108
+ "learning_rate": 0.03384636715054512,
109
+ "loss": 0.0303,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_avg_length": 16.991,
115
+ "eval_bleu": 0.035,
116
+ "eval_loss": 0.0532960519194603,
117
+ "eval_rouge1": 0.6254,
118
+ "eval_rouge2": 0.6076,
119
+ "eval_runtime": 195.9042,
120
+ "eval_samples_per_second": 25.523,
121
+ "eval_steps_per_second": 3.19,
122
+ "step": 2625
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 0.04064999520778656,
127
+ "loss": 0.0256,
128
+ "step": 3000
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_avg_length": 16.9964,
133
+ "eval_bleu": 0.035,
134
+ "eval_loss": 0.05655151233077049,
135
+ "eval_rouge1": 0.6257,
136
+ "eval_rouge2": 0.6074,
137
+ "eval_runtime": 193.7837,
138
+ "eval_samples_per_second": 25.802,
139
+ "eval_steps_per_second": 3.225,
140
+ "step": 3000
141
+ },
142
+ {
143
+ "epoch": 9.0,
144
+ "eval_avg_length": 16.998,
145
+ "eval_bleu": 0.0349,
146
+ "eval_loss": 0.05918492376804352,
147
+ "eval_rouge1": 0.6253,
148
+ "eval_rouge2": 0.6074,
149
+ "eval_runtime": 190.3532,
150
+ "eval_samples_per_second": 26.267,
151
+ "eval_steps_per_second": 3.283,
152
+ "step": 3375
153
+ },
154
+ {
155
+ "epoch": 9.33,
156
+ "learning_rate": 0.047494322061538696,
157
+ "loss": 0.0205,
158
+ "step": 3500
159
+ },
160
+ {
161
+ "epoch": 10.0,
162
+ "eval_avg_length": 16.9932,
163
+ "eval_bleu": 0.0351,
164
+ "eval_loss": 0.06117509678006172,
165
+ "eval_rouge1": 0.6255,
166
+ "eval_rouge2": 0.6073,
167
+ "eval_runtime": 197.2772,
168
+ "eval_samples_per_second": 25.345,
169
+ "eval_steps_per_second": 3.168,
170
+ "step": 3750
171
+ },
172
+ {
173
+ "epoch": 10.67,
174
+ "learning_rate": 0.054379865527153015,
175
+ "loss": 0.0185,
176
+ "step": 4000
177
+ },
178
+ {
179
+ "epoch": 11.0,
180
+ "eval_avg_length": 16.996,
181
+ "eval_bleu": 0.035,
182
+ "eval_loss": 0.06389027088880539,
183
+ "eval_rouge1": 0.6257,
184
+ "eval_rouge2": 0.6079,
185
+ "eval_runtime": 194.6757,
186
+ "eval_samples_per_second": 25.684,
187
+ "eval_steps_per_second": 3.21,
188
+ "step": 4125
189
+ },
190
+ {
191
+ "epoch": 12.0,
192
+ "learning_rate": 0.0613127239048481,
193
+ "loss": 0.0157,
194
+ "step": 4500
195
+ },
196
+ {
197
+ "epoch": 12.0,
198
+ "eval_avg_length": 16.9944,
199
+ "eval_bleu": 0.035,
200
+ "eval_loss": 0.06984004378318787,
201
+ "eval_rouge1": 0.625,
202
+ "eval_rouge2": 0.6064,
203
+ "eval_runtime": 196.3811,
204
+ "eval_samples_per_second": 25.461,
205
+ "eval_steps_per_second": 3.183,
206
+ "step": 4500
207
+ },
208
+ {
209
+ "epoch": 13.0,
210
+ "eval_avg_length": 16.991,
211
+ "eval_bleu": 0.035,
212
+ "eval_loss": 0.07201451808214188,
213
+ "eval_rouge1": 0.6246,
214
+ "eval_rouge2": 0.6062,
215
+ "eval_runtime": 192.0847,
216
+ "eval_samples_per_second": 26.03,
217
+ "eval_steps_per_second": 3.254,
218
+ "step": 4875
219
+ },
220
+ {
221
+ "epoch": 13.33,
222
+ "learning_rate": 0.06831157952547073,
223
+ "loss": 0.0131,
224
+ "step": 5000
225
+ },
226
+ {
227
+ "epoch": 14.0,
228
+ "eval_avg_length": 16.9986,
229
+ "eval_bleu": 0.035,
230
+ "eval_loss": 0.07447788119316101,
231
+ "eval_rouge1": 0.6247,
232
+ "eval_rouge2": 0.6062,
233
+ "eval_runtime": 197.3953,
234
+ "eval_samples_per_second": 25.33,
235
+ "eval_steps_per_second": 3.166,
236
+ "step": 5250
237
+ }
238
+ ],
239
+ "max_steps": 5625,
240
+ "num_train_epochs": 15,
241
+ "total_flos": 3.903700598784e+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:ff03095861cb20cf5f804443acba1a16458cb6cba7d63ac52b033c7e1cefa5b5
3
+ size 3963