Hugging Face's logo

k4black
/
Salesforce-codet5-small-CodeXGLUE-CONCODE-selected

Text2Text Generation
Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
1
k4black commited on
Commit
189cb2d
•
1 Parent(s): 1598c2f

Training in progress, step 2000

Browse files
Files changed (25) hide show
  1. .gitignore +1 -0
  2. added_tokens.json +5 -0
  3. config.json +68 -0
  4. last-checkpoint/added_tokens.json +5 -0
  5. last-checkpoint/config.json +68 -0
  6. last-checkpoint/generation_config.json +7 -0
  7. last-checkpoint/merges.txt +0 -0
  8. last-checkpoint/optimizer.pt +3 -0
  9. last-checkpoint/pytorch_model.bin +3 -0
  10. last-checkpoint/rng_state.pth +3 -0
  11. last-checkpoint/scaler.pt +3 -0
  12. last-checkpoint/scheduler.pt +3 -0
  13. last-checkpoint/special_tokens_map.json +55 -0
  14. last-checkpoint/tokenizer.json +0 -0
  15. last-checkpoint/tokenizer_config.json +64 -0
  16. last-checkpoint/trainer_state.json +35 -0
  17. last-checkpoint/training_args.bin +3 -0
  18. last-checkpoint/vocab.json +0 -0
  19. merges.txt +0 -0
  20. pytorch_model.bin +3 -0
  21. special_tokens_map.json +55 -0
  22. tokenizer.json +0 -0
  23. tokenizer_config.json +64 -0
  24. training_args.bin +3 -0
  25. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "\u0000": 32100,
3
+ "concode_elem_sep": 32101,
4
+ "concode_field_sep": 32102
5
+ }
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/codet5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 2,
14
+ "feed_forward_proj": "relu",
15
+ "gradient_checkpointing": false,
16
+ "id2label": {
17
+ "0": "LABEL_0"
18
+ },
19
+ "initializer_factor": 1.0,
20
+ "is_encoder_decoder": true,
21
+ "is_gated_act": false,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "layer_norm_epsilon": 1e-06,
26
+ "model_type": "t5",
27
+ "n_positions": 512,
28
+ "num_decoder_layers": 6,
29
+ "num_heads": 8,
30
+ "num_layers": 6,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "relative_attention_max_distance": 128,
34
+ "relative_attention_num_buckets": 32,
35
+ "task_specific_params": {
36
+ "summarization": {
37
+ "early_stopping": true,
38
+ "length_penalty": 2.0,
39
+ "max_length": 200,
40
+ "min_length": 30,
41
+ "no_repeat_ngram_size": 3,
42
+ "num_beams": 4,
43
+ "prefix": "summarize: "
44
+ },
45
+ "translation_en_to_de": {
46
+ "early_stopping": true,
47
+ "max_length": 300,
48
+ "num_beams": 4,
49
+ "prefix": "translate English to German: "
50
+ },
51
+ "translation_en_to_fr": {
52
+ "early_stopping": true,
53
+ "max_length": 300,
54
+ "num_beams": 4,
55
+ "prefix": "translate English to French: "
56
+ },
57
+ "translation_en_to_ro": {
58
+ "early_stopping": true,
59
+ "max_length": 300,
60
+ "num_beams": 4,
61
+ "prefix": "translate English to Romanian: "
62
+ }
63
+ },
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.27.1",
66
+ "use_cache": true,
67
+ "vocab_size": 32103
68
+ }
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "\u0000": 32100,
3
+ "concode_elem_sep": 32101,
4
+ "concode_field_sep": 32102
5
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/codet5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 2,
14
+ "feed_forward_proj": "relu",
15
+ "gradient_checkpointing": false,
16
+ "id2label": {
17
+ "0": "LABEL_0"
18
+ },
19
+ "initializer_factor": 1.0,
20
+ "is_encoder_decoder": true,
21
+ "is_gated_act": false,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "layer_norm_epsilon": 1e-06,
26
+ "model_type": "t5",
27
+ "n_positions": 512,
28
+ "num_decoder_layers": 6,
29
+ "num_heads": 8,
30
+ "num_layers": 6,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "relative_attention_max_distance": 128,
34
+ "relative_attention_num_buckets": 32,
35
+ "task_specific_params": {
36
+ "summarization": {
37
+ "early_stopping": true,
38
+ "length_penalty": 2.0,
39
+ "max_length": 200,
40
+ "min_length": 30,
41
+ "no_repeat_ngram_size": 3,
42
+ "num_beams": 4,
43
+ "prefix": "summarize: "
44
+ },
45
+ "translation_en_to_de": {
46
+ "early_stopping": true,
47
+ "max_length": 300,
48
+ "num_beams": 4,
49
+ "prefix": "translate English to German: "
50
+ },
51
+ "translation_en_to_fr": {
52
+ "early_stopping": true,
53
+ "max_length": 300,
54
+ "num_beams": 4,
55
+ "prefix": "translate English to French: "
56
+ },
57
+ "translation_en_to_ro": {
58
+ "early_stopping": true,
59
+ "max_length": 300,
60
+ "num_beams": 4,
61
+ "prefix": "translate English to Romanian: "
62
+ }
63
+ },
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.27.1",
66
+ "use_cache": true,
67
+ "vocab_size": 32103
68
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.27.1"
7
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4202639d55fdd225a227e25f5f8dd785e97cd60c8d5696709a94d06b4979a0bc
3
+ size 484059375
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5dc969ca09fa0e4fd6022361624cf23d87ca37e725567bcdf4089028c06472
3
+ size 242019067
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08d76d9c7a5736829c08136a32cd85baa4d3dbba998fd45e15bb0626318715be
3
+ size 14503
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f04205d4f9a7a5fe8f6793c320d4f263eb12b3e8a0d34b0c0a1b6fc5aad1563
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb24dc0ce2ad6683eab3c869d8011663ffe1b629316a97fb0272f90ac7eedc52
3
+ size 623
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "concode_elem_sep",
4
+ "concode_field_sep"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "mask_token": {
28
+ "content": "<mask>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<pad>",
36
+ "lstrip": false,
37
+ "normalized": true,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "sep_token": {
42
+ "content": "</s>",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "<unk>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 512,
37
+ "pad_token": {
38
+ "__type": "AddedToken",
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "sep_token": {
46
+ "__type": "AddedToken",
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "special_tokens_map_file": "/home/s5431786/.cache/huggingface/hub/models--Salesforce--codet5-small/snapshots/a642dc934e5475185369d09ac07091dfe72a31fc/special_tokens_map.json",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8543930649757385,
3
+ "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-selected/checkpoint-2000",
4
+ "epoch": 0.64,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.64,
12
+ "learning_rate": 6.3808e-05,
13
+ "loss": 1.45,
14
+ "step": 2000
15
+ },
16
+ {
17
+ "epoch": 0.64,
18
+ "eval_bleu": 0.24715996940066084,
19
+ "eval_exact_match": 0.1615,
20
+ "eval_loss": 0.8543930649757385,
21
+ "eval_rouge1": 0.5607398648042461,
22
+ "eval_rouge2": 0.376714337460786,
23
+ "eval_rougeL": 0.5368883844476564,
24
+ "eval_runtime": 233.0119,
25
+ "eval_samples_per_second": 8.583,
26
+ "eval_steps_per_second": 0.27,
27
+ "step": 2000
28
+ }
29
+ ],
30
+ "max_steps": 62500,
31
+ "num_train_epochs": 20,
32
+ "total_flos": 7244330642178048.0,
33
+ "trial_name": null,
34
+ "trial_params": null
35
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66fb0ffe9baad9e952873f4cbc64b882ff50defd769f8028bd9852a383ca29f9
3
+ size 3887
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5dc969ca09fa0e4fd6022361624cf23d87ca37e725567bcdf4089028c06472
3
+ size 242019067
special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "concode_elem_sep",
4
+ "concode_field_sep"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "mask_token": {
28
+ "content": "<mask>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<pad>",
36
+ "lstrip": false,
37
+ "normalized": true,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "sep_token": {
42
+ "content": "</s>",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "<unk>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 512,
37
+ "pad_token": {
38
+ "__type": "AddedToken",
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "sep_token": {
46
+ "__type": "AddedToken",
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "special_tokens_map_file": "/home/s5431786/.cache/huggingface/hub/models--Salesforce--codet5-small/snapshots/a642dc934e5475185369d09ac07091dfe72a31fc/special_tokens_map.json",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66fb0ffe9baad9e952873f4cbc64b882ff50defd769f8028bd9852a383ca29f9
3
+ size 3887
vocab.json ADDED
The diff for this file is too large to render. See raw diff