Hugging Face's logo

Satish678
/
tenjinonline-text2sql

Transformers
PyTorch
TensorBoard
t5
text2text-generation
text-generation-inference
Model card Files
xet
Metrics Community
1
Satish678 commited on
Commit
f0fa01b
·
1 Parent(s): 46ebc91

Training in progress, step 500

Browse files
Files changed (11) hide show
  1. config.json +16 -40
  2. pytorch_model.bin +2 -2
  3. runs/May30_09-29-51_34d80587544b/1685439219.6432164/events.out.tfevents.1685439219.34d80587544b.2139.1 +3 -0
  4. runs/May30_09-29-51_34d80587544b/events.out.tfevents.1685439219.34d80587544b.2139.0 +3 -0
  5. runs/May30_09-38-32_34d80587544b/1685439520.4619417/events.out.tfevents.1685439520.34d80587544b.6031.1 +3 -0
  6. runs/May30_09-38-32_34d80587544b/events.out.tfevents.1685439520.34d80587544b.6031.0 +3 -0
  7. runs/May30_09-40-49_34d80587544b/1685439656.6879425/events.out.tfevents.1685439656.34d80587544b.6760.1 +3 -0
  8. runs/May30_09-40-49_34d80587544b/events.out.tfevents.1685439656.34d80587544b.6760.0 +3 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +1 -0
  11. training_args.bin +1 -1
config.json CHANGED
@@ -1,60 +1,36 @@
1
  {
2
- "_name_or_path": "t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 3072,
7
  "d_kv": 64,
8
- "d_model": 768,
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": 12,
21
- "num_heads": 12,
22
- "num_layers": 12,
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": "4.29.2",
58
  "use_cache": true,
59
- "vocab_size": 32128
60
  }
 
1
  {
2
+ "_name_or_path": "Yethi/spider_repo_t5_V2",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 2816,
7
  "d_kv": 64,
8
+ "d_model": 1024,
9
  "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "diversity_penalty": null,
12
  "dropout_rate": 0.1,
13
  "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": false,
16
  "initializer_factor": 1.0,
17
  "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
  "layer_norm_epsilon": 1e-06,
20
+ "max_length": 256,
21
  "model_type": "t5",
22
+ "num_beams": 4,
23
+ "num_decoder_layers": 24,
24
+ "num_heads": 16,
25
+ "num_layers": 24,
26
  "output_past": true,
27
  "pad_token_id": 0,
28
+ "padding": "max_length",
29
  "relative_attention_max_distance": 128,
30
  "relative_attention_num_buckets": 32,
31
+ "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.29.2",
34
  "use_cache": true,
35
+ "vocab_size": 32102
36
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:951f606c6b41d6511d1e55fa0b1aeccb4c9ad89424b061a3709f1a265164d8b4
3
- size 891702929
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d7c4f9141cf9e283930f76b8e6b69e847087f0b82020ca2380961126e965bc
3
+ size 3132580677
runs/May30_09-29-51_34d80587544b/1685439219.6432164/events.out.tfevents.1685439219.34d80587544b.2139.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2ac369a48afc309cb9801531c2317e10c28f5d636c78904443c78be82e8bba
3
+ size 6213
runs/May30_09-29-51_34d80587544b/events.out.tfevents.1685439219.34d80587544b.2139.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dcd48c52aa5986e7a5ebf7def4a8ff673153383e812723b405835419c00aae
3
+ size 4437
runs/May30_09-38-32_34d80587544b/1685439520.4619417/events.out.tfevents.1685439520.34d80587544b.6031.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752e817cf1494097b42553ef49c89358d983fb852e504ed3712afc227b56456e
3
+ size 6213
runs/May30_09-38-32_34d80587544b/events.out.tfevents.1685439520.34d80587544b.6031.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a4587bfc5a832cd044fa97f1c0448eafb1c58f5c79acaef0e9472f2d8c6e38
3
+ size 4184
runs/May30_09-40-49_34d80587544b/1685439656.6879425/events.out.tfevents.1685439656.34d80587544b.6760.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff7033a1af958490caa0eb44d0cd133bb16a7f13ffb29a94dc305923885e30cf
3
+ size 6213
runs/May30_09-40-49_34d80587544b/events.out.tfevents.1685439656.34d80587544b.6760.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f647b38bcc46c5d07e4cf98df631e53c384b25d0add3493e0c42195b8c9b393
3
+ size 4962
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -106,6 +106,7 @@
106
  "extra_ids": 100,
107
  "model_max_length": 512,
108
  "pad_token": "<pad>",
 
109
  "tokenizer_class": "T5Tokenizer",
110
  "unk_token": "<unk>"
111
  }
 
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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:340789e5c8e4b8c7adda9e77ec2795ed6ed8d9f9dee7343e663289ab44f84ed8
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb5b51b848795696c03840597db6b8cd524eb48d8754e21a4602ec99139e8b6
3
  size 4091