Esti-tech commited on
Commit
f25ff26
·
verified ·
1 Parent(s): 4450547

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "google-t5/t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
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,
@@ -18,9 +18,9 @@
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
- "num_decoder_layers": 6,
22
- "num_heads": 8,
23
- "num_layers": 6,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
 
1
  {
2
+ "_name_or_path": "google-t5/t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 3072,
8
  "d_kv": 64,
9
+ "d_model": 768,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "relu",
12
  "dropout_rate": 0.1,
 
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82faa07a4815c47f13744858291aba9410b21d07b991b26b23e5f25c15e3e80a
3
- size 242072086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c19d67a62590ee6391a9f91a9df91d17c318784cd8e04825f2ec5b4cb9423f7
3
+ size 891703374
runs/Oct24_15-27-04_d4afecba7390/events.out.tfevents.1729783754.d4afecba7390.358.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0a4f678a1ecc2c6db9fe6b73adc6e699647aa98de3095c7cca13fa368d31dd
3
+ size 88
runs/Oct24_15-29-43_d4afecba7390/events.out.tfevents.1729783793.d4afecba7390.358.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37851cc2b45771b54cb6fcfba01f77a85bbf694277acfffb3c10a38ccdda661
3
+ size 88
runs/Oct24_15-33-40_01eb67b6d89e/events.out.tfevents.1729784036.01eb67b6d89e.494.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2915a1e96409f0c3aa4d9e006a94a1d13ede4556157919e07b63d27eb18af5
3
+ size 6052
runs/Oct24_15-34-37_01eb67b6d89e/events.out.tfevents.1729784091.01eb67b6d89e.494.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e9d8fe600b9d82b1cf8d82a13baac8d3bda69277635718b85674db32df5aba
3
+ size 6052
runs/Oct24_15-39-19_ac31b9486969/events.out.tfevents.1729784362.ac31b9486969.1295.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e131f76bc6603204bdddcccbde2a85edadd00374c5a8a8cfb27191e1939b3889
3
+ size 6052
special_tokens_map.json CHANGED
@@ -101,25 +101,7 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
- "eos_token": {
105
- "content": "</s>",
106
- "lstrip": false,
107
- "normalized": false,
108
- "rstrip": false,
109
- "single_word": false
110
- },
111
- "pad_token": {
112
- "content": "<pad>",
113
- "lstrip": false,
114
- "normalized": false,
115
- "rstrip": false,
116
- "single_word": false
117
- },
118
- "unk_token": {
119
- "content": "<unk>",
120
- "lstrip": false,
121
- "normalized": false,
122
- "rstrip": false,
123
- "single_word": false
124
- }
125
  }
 
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  }
tokenizer_config.json CHANGED
@@ -930,7 +930,7 @@
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
933
- "model_max_length": 512,
934
  "pad_token": "<pad>",
935
  "tokenizer_class": "T5Tokenizer",
936
  "unk_token": "<unk>"
 
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
933
+ "model_max_length": 1000000000000000019884624838656,
934
  "pad_token": "<pad>",
935
  "tokenizer_class": "T5Tokenizer",
936
  "unk_token": "<unk>"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a516301509a6b6000e42c3722b2b1e5b5f66fcac5ced440b8f696656f3436263
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992556fcce0a21eb861c20611c5893a7148b687129fe208e2a7c4474009bb4c6
3
  size 5432