Hugging Face's logo

oracool
/
myspace

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
oracool commited on
Commit
7786768
·
1 Parent(s): 163b53f

Training in progress, step 500

Browse files
Files changed (9) hide show
  1. config.json +15 -11
  2. model.safetensors +2 -2
  3. runs/Dec09_19-13-00_b937ba0803e6/events.out.tfevents.1702149186.b937ba0803e6.231.0 +3 -0
  4. runs/Dec09_19-18-06_b937ba0803e6/events.out.tfevents.1702149487.b937ba0803e6.2305.0 +3 -0
  5. runs/Dec09_19-18-17_b937ba0803e6/events.out.tfevents.1702149498.b937ba0803e6.2305.1 +3 -0
  6. runs/Dec09_19-18-26_b937ba0803e6/events.out.tfevents.1702149507.b937ba0803e6.2305.2 +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +3 -3
  9. training_args.bin +1 -1
config.json CHANGED
@@ -1,26 +1,31 @@
1
  {
2
- "_name_or_path": "google/flan-t5-small",
 
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
- "d_ff": 1024,
8
  "d_kv": 64,
9
- "d_model": 512,
10
  "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
  "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
  "initializer_factor": 1.0,
16
  "is_encoder_decoder": true,
17
- "is_gated_act": true,
18
  "layer_norm_epsilon": 1e-06,
 
 
19
  "model_type": "t5",
20
  "n_positions": 512,
21
- "num_decoder_layers": 8,
22
- "num_heads": 6,
23
- "num_layers": 8,
 
 
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
@@ -54,7 +59,6 @@
54
  "prefix": "translate English to Romanian: "
55
  }
56
  },
57
- "tie_word_embeddings": false,
58
  "torch_dtype": "float32",
59
  "transformers_version": "4.35.2",
60
  "use_cache": true,
 
1
  {
2
+ "_name_or_path": "d0rj/rut5-base-summ",
3
+ "_num_labels": 2,
4
  "architectures": [
5
  "T5ForConditionalGeneration"
6
  ],
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
  "initializer_factor": 1.0,
17
  "is_encoder_decoder": true,
18
+ "is_gated_act": false,
19
  "layer_norm_epsilon": 1e-06,
20
+ "length_penalty": 0.6,
21
+ "max_length": 256,
22
  "model_type": "t5",
23
  "n_positions": 512,
24
+ "no_repeat_ngram_size": 2,
25
+ "num_beams": 10,
26
+ "num_decoder_layers": 12,
27
+ "num_heads": 12,
28
+ "num_layers": 12,
29
  "output_past": true,
30
  "pad_token_id": 0,
31
  "relative_attention_max_distance": 128,
 
59
  "prefix": "translate English to Romanian: "
60
  }
61
  },
 
62
  "torch_dtype": "float32",
63
  "transformers_version": "4.35.2",
64
  "use_cache": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:495fa51e204676f1a857a9fc13c4c89f3f5ba9f480b898cebca02add25e6d749
3
- size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd41eb9f0a25ad98a5813fe62d770707ba58d51de43be2fe05ddfafc91716e4
3
+ size 891644712
runs/Dec09_19-13-00_b937ba0803e6/events.out.tfevents.1702149186.b937ba0803e6.231.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57cf495b4be26ab4a3951c5eae05a283cd5f2fb3797c2f66ad2647f513cd899b
3
+ size 4515
runs/Dec09_19-18-06_b937ba0803e6/events.out.tfevents.1702149487.b937ba0803e6.2305.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c360a5416aa55e90e96818593baaa877170c886416bd83980c3b3d81af15c2b
3
+ size 5319
runs/Dec09_19-18-17_b937ba0803e6/events.out.tfevents.1702149498.b937ba0803e6.2305.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4dffbbddaabdb515f1a7c2aa4977fe83e841307c43a6a59aab00a3bfdb5ee71
3
+ size 5319
runs/Dec09_19-18-26_b937ba0803e6/events.out.tfevents.1702149507.b937ba0803e6.2305.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc67906c07d79a4823ec6684e0e1f180e274872ead08dd16484b7ac68c3f0d8
3
+ size 5476
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "</s>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "<unk>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -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
  "sp_model_kwargs": {},
936
  "tokenizer_class": "T5Tokenizer",
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<unk>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "</s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
933
+ "model_max_length": 1000000000000000019884624838656,
934
  "pad_token": "<pad>",
935
  "sp_model_kwargs": {},
936
  "tokenizer_class": "T5Tokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5125e2a430a3c042f03518222b6300016879fc627d87fcd3fe5e48d0f96a928e
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269f0f43df8010935e5f9d6218c454a243eae701b7e17f53b4bfdfe0a17adf04
3
  size 4728