Hugging Face's logo

ThatGuyVanquish
/
kook-model-output-dir

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ThatGuyVanquish commited on
Commit
2691b37
•
1 Parent(s): 282e558

Training in progress, step 500

Browse files
Files changed (9) hide show
  1. config.json +6 -7
  2. pytorch_model.bin +2 -2
  3. runs/Feb24_11-20-32_cs-3090-02/1677230462.1519566/events.out.tfevents.1677230462.cs-3090-02.85312.1 +3 -0
  4. runs/Feb24_11-20-32_cs-3090-02/events.out.tfevents.1677230462.cs-3090-02.85312.0 +3 -0
  5. runs/Feb24_11-22-55_cs-3090-02/1677230602.540796/events.out.tfevents.1677230602.cs-3090-02.120043.1 +3 -0
  6. runs/Feb24_11-22-55_cs-3090-02/events.out.tfevents.1677230602.cs-3090-02.120043.0 +3 -0
  7. tokenizer.json +2 -2
  8. tokenizer_config.json +1 -1
  9. training_args.bin +1 -1
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "google/mt5-base",
3
  "architectures": [
4
  "MT5ForConditionalGeneration"
5
  ],
6
- "d_ff": 2048,
7
  "d_kv": 64,
8
- "d_model": 768,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
@@ -16,10 +16,9 @@
16
  "is_gated_act": true,
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "mt5",
19
- "num_decoder_layers": 12,
20
- "num_heads": 12,
21
- "num_layers": 12,
22
- "output_past": true,
23
  "pad_token_id": 0,
24
  "relative_attention_max_distance": 128,
25
  "relative_attention_num_buckets": 32,
 
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,
 
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,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8f9df3cd91bfaa894a809e8adf03b4c8cef4a269d2ba0d7f0001d7d98371b84
3
- size 2329702453
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c3c22ac713292580c8ff067f745a5af946a3a31d8e0d5a8190743a7acd44e5
3
+ size 1200772485
runs/Feb24_11-20-32_cs-3090-02/1677230462.1519566/events.out.tfevents.1677230462.cs-3090-02.85312.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c7b9f92c6ca670b2cd9ecb8ddeb232827fccd994d8476f26c98f7a0c523b15f
3
+ size 6026
runs/Feb24_11-20-32_cs-3090-02/events.out.tfevents.1677230462.cs-3090-02.85312.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55175e6ba9a17c63bbd2b8b7ee0d1507e5dbc7a296fc1968151c5fd2d3f66641
3
+ size 4170
runs/Feb24_11-22-55_cs-3090-02/1677230602.540796/events.out.tfevents.1677230602.cs-3090-02.120043.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4821951a328663ecd117bcec7fc3b22e380048e6b4e75e96bcb911a5c31e3958
3
+ size 6026
runs/Feb24_11-22-55_cs-3090-02/events.out.tfevents.1677230602.cs-3090-02.120043.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4e1e83ef281718164ff871c15dfafaa10701085231c8ebda8e313df4c134b0
3
+ size 4327
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d15b59d404d29e41d3eddebcd213b00395e140bf9493419c646b0c74647efbea
3
- size 16330467
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9c8839e95f627aa4913555c10b9ead0a3261e16e15290314df3a90523927e1
3
+ size 16330468
tokenizer_config.json CHANGED
@@ -5,7 +5,7 @@
5
  "model_max_length": 1000000000000000019884624838656,
6
  "pad_token": "<pad>",
7
  "sp_model_kwargs": {},
8
- "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
9
  "tokenizer_class": "T5Tokenizer",
10
  "unk_token": "<unk>"
11
  }
 
5
  "model_max_length": 1000000000000000019884624838656,
6
  "pad_token": "<pad>",
7
  "sp_model_kwargs": {},
8
+ "special_tokens_map_file": "/home/herscon/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
9
  "tokenizer_class": "T5Tokenizer",
10
  "unk_token": "<unk>"
11
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d6dce086c08722fefc8af4ffdafa5587009824b1a3c6096e258b638fb49b586
3
  size 3707
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c029cb5a2a733613e93b86c0692689141d39ec324784c540efd2a58646d26b8b
3
  size 3707