Hugging Face's logo

ljcnju
/
CodeT5ForClone-Detection

Text Classification
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Model card Files Community
ljcnju commited on
Commit
c0e82a8
·
verified ·
1 Parent(s): 42a8399

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +64 -0
  2. model.safetensors +3 -0
  3. tmp-checkpoint-13/config.json +64 -0
  4. tmp-checkpoint-13/model.safetensors +3 -0
  5. tmp-checkpoint-13/optimizer.pt +3 -0
  6. tmp-checkpoint-13/training_args.bin +3 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/codet5-base",
3
+ "architectures": [
4
+ "T5ForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "initializer_factor": 1.0,
18
+ "is_encoder_decoder": true,
19
+ "is_gated_act": false,
20
+ "layer_norm_epsilon": 1e-06,
21
+ "model_type": "t5",
22
+ "n_positions": 512,
23
+ "num_decoder_layers": 12,
24
+ "num_heads": 12,
25
+ "num_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "relative_attention_max_distance": 128,
30
+ "relative_attention_num_buckets": 32,
31
+ "task_specific_params": {
32
+ "summarization": {
33
+ "early_stopping": true,
34
+ "length_penalty": 2.0,
35
+ "max_length": 200,
36
+ "min_length": 30,
37
+ "no_repeat_ngram_size": 3,
38
+ "num_beams": 4,
39
+ "prefix": "summarize: "
40
+ },
41
+ "translation_en_to_de": {
42
+ "early_stopping": true,
43
+ "max_length": 300,
44
+ "num_beams": 4,
45
+ "prefix": "translate English to German: "
46
+ },
47
+ "translation_en_to_fr": {
48
+ "early_stopping": true,
49
+ "max_length": 300,
50
+ "num_beams": 4,
51
+ "prefix": "translate English to French: "
52
+ },
53
+ "translation_en_to_ro": {
54
+ "early_stopping": true,
55
+ "max_length": 300,
56
+ "num_beams": 4,
57
+ "prefix": "translate English to Romanian: "
58
+ }
59
+ },
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.37.2",
62
+ "use_cache": true,
63
+ "vocab_size": 32100
64
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f479a209b788313922ea12774f738531419a10cd26fd24752cfc3757c6d60ed
3
+ size 893930696
tmp-checkpoint-13/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/codet5-base",
3
+ "architectures": [
4
+ "T5ForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "initializer_factor": 1.0,
18
+ "is_encoder_decoder": true,
19
+ "is_gated_act": false,
20
+ "layer_norm_epsilon": 1e-06,
21
+ "model_type": "t5",
22
+ "n_positions": 512,
23
+ "num_decoder_layers": 12,
24
+ "num_heads": 12,
25
+ "num_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "relative_attention_max_distance": 128,
30
+ "relative_attention_num_buckets": 32,
31
+ "task_specific_params": {
32
+ "summarization": {
33
+ "early_stopping": true,
34
+ "length_penalty": 2.0,
35
+ "max_length": 200,
36
+ "min_length": 30,
37
+ "no_repeat_ngram_size": 3,
38
+ "num_beams": 4,
39
+ "prefix": "summarize: "
40
+ },
41
+ "translation_en_to_de": {
42
+ "early_stopping": true,
43
+ "max_length": 300,
44
+ "num_beams": 4,
45
+ "prefix": "translate English to German: "
46
+ },
47
+ "translation_en_to_fr": {
48
+ "early_stopping": true,
49
+ "max_length": 300,
50
+ "num_beams": 4,
51
+ "prefix": "translate English to French: "
52
+ },
53
+ "translation_en_to_ro": {
54
+ "early_stopping": true,
55
+ "max_length": 300,
56
+ "num_beams": 4,
57
+ "prefix": "translate English to Romanian: "
58
+ }
59
+ },
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.37.2",
62
+ "use_cache": true,
63
+ "vocab_size": 32100
64
+ }
tmp-checkpoint-13/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66472fabb9e04121f4b2f4463123bc9ae62345f449ad972030e068d8b9585e11
3
+ size 893930696
tmp-checkpoint-13/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceca07114b90dfc7cd181949c552a8ab9894467d39c83bf303a2de96c0738e6d
3
+ size 1122199298
tmp-checkpoint-13/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d64a4744f9828dd8f0f77af71b4c2b8cf010684246f6991dcad2cd2f7b8994
3
+ size 4728
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:becf4b14733942c3f710bf04fb65df1a56a3366f0449d97b9aaec97953dcff2a
3
+ size 4728