Hugging Face's logo

sheepy928
/
bincorp_ep0.3_wo_ep

Transformers
PyTorch
marinda
Inference Endpoints
Model card Files Community
sheepy928 commited on
Commit
e563a15
•
1 Parent(s): 14657e5

Training in progress, step 24000

Browse files
Files changed (18) hide show
  1. checkpoint-24000/config.json +28 -0
  2. checkpoint-24000/optimizer.pt +3 -0
  3. checkpoint-24000/pytorch_model.bin +3 -0
  4. checkpoint-24000/rng_state_0.pth +3 -0
  5. checkpoint-24000/rng_state_1.pth +3 -0
  6. checkpoint-24000/rng_state_2.pth +3 -0
  7. checkpoint-24000/rng_state_3.pth +3 -0
  8. checkpoint-24000/rng_state_4.pth +3 -0
  9. checkpoint-24000/rng_state_5.pth +3 -0
  10. checkpoint-24000/rng_state_6.pth +3 -0
  11. checkpoint-24000/rng_state_7.pth +3 -0
  12. checkpoint-24000/scheduler.pt +3 -0
  13. checkpoint-24000/special_tokens_map.json +7 -0
  14. checkpoint-24000/tokenizer.json +0 -0
  15. checkpoint-24000/tokenizer_config.json +5 -0
  16. checkpoint-24000/trainer_state.json +0 -0
  17. checkpoint-24000/training_args.bin +3 -0
  18. pytorch_model.bin +1 -1
checkpoint-24000/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MarindaForMaskedLMWithEdgePrediction"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "ep_add_linear_projection": true,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 600,
17
+ "max_relative_position_embeddings": 8,
18
+ "model_type": "marinda",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 3,
22
+ "position_embedding_type": "mixed",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.31.0",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 30523
28
+ }
checkpoint-24000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aaa9ba0eb5a7b365137fd37de4c4ad7b6bbf69651c3024d5cd7df946d5642ee
3
+ size 881521797
checkpoint-24000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f331e5a213b191c0b903c46e4f198f2110dd83f3d8ad4208a91ea6913a9c2b
3
+ size 440772077
checkpoint-24000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c01df290b1fa9f53aa5ca6536c75132842fb67c15236dc984bdec4ea8d7b208
3
+ size 21623
checkpoint-24000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c963cd54b151ab54677b070f0a8b21808d027318d98c87540f2d70c656aa24d
3
+ size 21623
checkpoint-24000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6b4fb2ae118e3289d72ce9faa6280a8d1f97cbcb092d2926190e93bbe32998
3
+ size 21623
checkpoint-24000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d361f65cffa87ce8e4b20d2af23bc7bf627b0eec4a8f0e27eb14a1f3430447ad
3
+ size 21623
checkpoint-24000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf5c1f4394a5be16921475234f4c14addc3ca55e4ba3a5c1bde1cd2174ff784
3
+ size 21623
checkpoint-24000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8bb93bdd46ce8edce6bc483441174154e796cfdfaa6f218a787b6edde37f6c
3
+ size 21623
checkpoint-24000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2cb908f358fb490d973e49d8df756e75e40c3f576038e88c1857539f314efc
3
+ size 21623
checkpoint-24000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b35b8a9b25b475f22a86a938b16bb405128345f62bc7ccf9cd98e4f707320de
3
+ size 21623
checkpoint-24000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3305b2dce4916cab4344cfa256937a3332ec755c425a0a3fb7cf892f94c49e14
3
+ size 627
checkpoint-24000/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-24000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-24000/tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 512,
4
+ "tokenizer_class": "MarindaTokenizer"
5
+ }
checkpoint-24000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-24000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbbced2969d3c34b5ea7f356c253acf2a826f9e9dea1f238559fc37a4cf95a6d
3
+ size 4027
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b914c97ff0e1482961a9d6e07d3c1f57bbec790a5b0a14d59b95439fc61743e6
3
  size 440772077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f331e5a213b191c0b903c46e4f198f2110dd83f3d8ad4208a91ea6913a9c2b
3
  size 440772077