danieladeeko commited on
Commit
10ed23c
1 Parent(s): 9d53496

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,12 +1,12 @@
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,
@@ -18,9 +18,9 @@
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,
 
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
  "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,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c65ace4add56fa30d2627497a9cb5bca5683fb7931289275f7682998b63ac061
3
- size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926681491e433068cadcee7f2de988a7b53d966ddff69d6e35b4735fd7982e1f
3
+ size 242041896
runs/Sep02_22-23-47_a161a4b9da02/events.out.tfevents.1725315828.a161a4b9da02.1458.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c81882735f942f5d9b135877267c24f46a237bcf944703705914c8a3fe2a914
3
+ size 5885
special_tokens_map.json CHANGED
@@ -101,7 +101,25 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
- "eos_token": "</s>",
105
- "pad_token": "<pad>",
106
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  }
 
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
  }
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": 1000000000000000019884624838656,
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": 512,
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:ba30f882eaecbc4b64f0da4f86bad49504d3219d98560d4d6c212e6086d0d685
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3110aeaa014995ba48c5b10c5ce113ae11d886e33c7fce1ed5b4c4e2302a48a9
3
  size 5112