Hugging Face's logo

n3wtou
/
mt5-swatf

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
n3wtou commited on
Commit
d15c4bc
•
1 Parent(s): ae141c2

Training in progress, step 500

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. .gitignore +1 -0
  3. config.json +31 -0
  4. pytorch_model.bin +3 -0
  5. runs/May25_15-40-35_92179b15b41f/1685029241.0039086/events.out.tfevents.1685029241.92179b15b41f.3904.1 +3 -0
  6. runs/May25_15-40-35_92179b15b41f/events.out.tfevents.1685029240.92179b15b41f.3904.0 +3 -0
  7. runs/May25_15-41-30_92179b15b41f/1685029292.4623969/events.out.tfevents.1685029292.92179b15b41f.3904.3 +3 -0
  8. runs/May25_15-41-30_92179b15b41f/events.out.tfevents.1685029292.92179b15b41f.3904.2 +3 -0
  9. runs/May25_15-42-44_92179b15b41f/1685029369.327301/events.out.tfevents.1685029369.92179b15b41f.5014.1 +3 -0
  10. runs/May25_15-42-44_92179b15b41f/events.out.tfevents.1685029369.92179b15b41f.5014.0 +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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-small",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
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": 8,
20
+ "num_heads": 6,
21
+ "num_layers": 8,
22
+ "pad_token_id": 0,
23
+ "relative_attention_max_distance": 128,
24
+ "relative_attention_num_buckets": 32,
25
+ "tie_word_embeddings": false,
26
+ "tokenizer_class": "T5Tokenizer",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.29.2",
29
+ "use_cache": true,
30
+ "vocab_size": 250112
31
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29eb75be46bc194733036b535a8d3f4e67599a7a3a91d5898c4314f19a378149
3
+ size 1200772485
runs/May25_15-40-35_92179b15b41f/1685029241.0039086/events.out.tfevents.1685029241.92179b15b41f.3904.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6768e2b3b0820a56a277280ce9ac3390850b84398f52f252816a5c9858f22189
3
+ size 6198
runs/May25_15-40-35_92179b15b41f/events.out.tfevents.1685029240.92179b15b41f.3904.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6615f4d6e6a1916ad2b0636b65d0833f7d0f51ef941a92d297d6b569a0b88a81
3
+ size 4184
runs/May25_15-41-30_92179b15b41f/1685029292.4623969/events.out.tfevents.1685029292.92179b15b41f.3904.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2087b8baf53606aa7a91343f2aef8be531d9305b21364ba0e30bb080a1eba1
3
+ size 6198
runs/May25_15-41-30_92179b15b41f/events.out.tfevents.1685029292.92179b15b41f.3904.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0da52fdfbfaa73b695bbfdd3136901b15f13f7774ef6f0bf050244a85d91f7
3
+ size 4184
runs/May25_15-42-44_92179b15b41f/1685029369.327301/events.out.tfevents.1685029369.92179b15b41f.5014.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56460d30e1a3833b3e166cc4f2350ca2d7495eaadf16c76dfcc1f6654edbbd3b
3
+ size 6198
runs/May25_15-42-44_92179b15b41f/events.out.tfevents.1685029369.92179b15b41f.5014.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec1dadb688077b1c6dc648b926fb4e7cfa26be64e0d89ef7011af1ecc55009c1
3
+ size 5475
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 sha256:98d45dd3cc0fd0536b5103b274586245a9024b1833035f9799993d88e0720cf2
3
+ size 4091