Hugging Face's logo

smartik
/
mt5-large-finetuned-gec

Transformers
PyTorch
TensorBoard
mt5
text2text-generation
Model card Files
xet
Metrics Community
Anastasiia Hudyma commited on
Commit
0bf9f86
·
1 Parent(s): ee38715

Training in progress, step 500

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. .gitignore +1 -0
  3. config.json +32 -0
  4. pytorch_model.bin +3 -0
  5. runs/May29_13-20-19_05d0c781eb45/1685366438.7972484/events.out.tfevents.1685366438.05d0c781eb45.2279.3 +3 -0
  6. runs/May29_13-20-19_05d0c781eb45/events.out.tfevents.1685366438.05d0c781eb45.2279.2 +3 -0
  7. runs/May29_13-23-42_05d0c781eb45/1685366637.3232868/events.out.tfevents.1685366637.05d0c781eb45.2279.5 +3 -0
  8. runs/May29_13-23-42_05d0c781eb45/events.out.tfevents.1685366637.05d0c781eb45.2279.4 +3 -0
  9. runs/May29_13-26-25_05d0c781eb45/1685366791.207835/events.out.tfevents.1685366791.05d0c781eb45.16082.1 +3 -0
  10. runs/May29_13-26-25_05d0c781eb45/events.out.tfevents.1685366791.05d0c781eb45.16082.0 +3 -0
  11. special_tokens_map.json +5 -0
  12. spiece.model +3 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +11 -0
  15. training_args.bin +3 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-large",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
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
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "mt5",
19
+ "num_decoder_layers": 24,
20
+ "num_heads": 16,
21
+ "num_layers": 24,
22
+ "output_past": true,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "tokenizer_class": "T5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.29.2",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743f693fe524ab851345f143383b1f290980c6b27332d48306da73c76fbb928b
3
+ size 4918519065
runs/May29_13-20-19_05d0c781eb45/1685366438.7972484/events.out.tfevents.1685366438.05d0c781eb45.2279.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b80f4016515bffbf82611da9829e12058585a2074832e2fd128d839f1c905b0
3
+ size 6215
runs/May29_13-20-19_05d0c781eb45/events.out.tfevents.1685366438.05d0c781eb45.2279.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bacb19412569252ec70c9b8afe4e6d9b2ce7825fb03f15d24ef91228ca0eefe
3
+ size 4314
runs/May29_13-23-42_05d0c781eb45/1685366637.3232868/events.out.tfevents.1685366637.05d0c781eb45.2279.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96c417497ce1a78ed1bc874763f7b09311861efabfa70a257a3e639195b917b
3
+ size 6215
runs/May29_13-23-42_05d0c781eb45/events.out.tfevents.1685366637.05d0c781eb45.2279.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb69285cc41a83686f1060893965a4b4368c999d4cc3211d266350dd27cfb63
3
+ size 4184
runs/May29_13-26-25_05d0c781eb45/1685366791.207835/events.out.tfevents.1685366791.05d0c781eb45.16082.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46454c059a1e8fb3e4bb09cfb037ce3917fe2c3351cb1d316c1926b97ebf6ad6
3
+ size 6215
runs/May29_13-26-25_05d0c781eb45/events.out.tfevents.1685366791.05d0c781eb45.16082.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45422ddfbfa3efcd3f30e18ad3834a6c09a110c29160da10ea892029ea342eb5
3
+ size 4469
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faaa6405f5f79c9e788c7980874a9a3b5b0aea07b53bd9243bf1abb8f5c49c81
3
+ size 16330467
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "extra_ids": 0,
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "tokenizer_class": "T5Tokenizer",
10
+ "unk_token": "<unk>"
11
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e6d0ed07e441d75fdaa9b752523952a6220fb29760251b914ada36f93ebcf2
3
+ size 4091