Hugging Face's logo

sheepy928
/
bincorp_ep0.3_wo_ep

Transformers
PyTorch
marinda
Inference Endpoints
Model card Files Community
sheepy928 commited on
Commit
14657e5
•
1 Parent(s): 68de728

Training in progress, step 23000

Browse files
Files changed (18) hide show
  1. checkpoint-23000/config.json +28 -0
  2. checkpoint-23000/optimizer.pt +3 -0
  3. checkpoint-23000/pytorch_model.bin +3 -0
  4. checkpoint-23000/rng_state_0.pth +3 -0
  5. checkpoint-23000/rng_state_1.pth +3 -0
  6. checkpoint-23000/rng_state_2.pth +3 -0
  7. checkpoint-23000/rng_state_3.pth +3 -0
  8. checkpoint-23000/rng_state_4.pth +3 -0
  9. checkpoint-23000/rng_state_5.pth +3 -0
  10. checkpoint-23000/rng_state_6.pth +3 -0
  11. checkpoint-23000/rng_state_7.pth +3 -0
  12. checkpoint-23000/scheduler.pt +3 -0
  13. checkpoint-23000/special_tokens_map.json +7 -0
  14. checkpoint-23000/tokenizer.json +0 -0
  15. checkpoint-23000/tokenizer_config.json +5 -0
  16. checkpoint-23000/trainer_state.json +0 -0
  17. checkpoint-23000/training_args.bin +3 -0
  18. pytorch_model.bin +1 -1
checkpoint-23000/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-23000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:568e9a615c78cc5d5063ef20c2f7f06684cad58fae03b619276f51c2fbaa3445
3
+ size 881521797
checkpoint-23000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b914c97ff0e1482961a9d6e07d3c1f57bbec790a5b0a14d59b95439fc61743e6
3
+ size 440772077
checkpoint-23000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476c43172e901bd7c4c07f8cb4deff9231a253fec3645bcd4c6df6c4329ccdb5
3
+ size 21623
checkpoint-23000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a001650ab8b481fe18a371a3cf869219d9af0505e2dfdd35675984381399448
3
+ size 21623
checkpoint-23000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6adc0d87521236580198ae86d9228b0c91077b534da222d3218de0921326f356
3
+ size 21623
checkpoint-23000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ceb19cc94b9db5c4af562c04a5cf34f2d5bfba5d5e1b90016f05c704da528f9
3
+ size 21623
checkpoint-23000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85689c2d8c80e2686f877a95e5fe52187006e10771f3b175319ff326ec9275bd
3
+ size 21623
checkpoint-23000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95caeb9cbc8b12c3d482645e89e164b0ff36d7a87b20fc9e90c439135377d072
3
+ size 21623
checkpoint-23000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463b60787672890f2997da8b286e242cec1a193b745fb15f05d9f7dcfb294489
3
+ size 21623
checkpoint-23000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79773343537c31ae8f3e98b0137062adad60d3f17718a2efcecd194fa2ce67fd
3
+ size 21623
checkpoint-23000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c0fe626dadebc776257e383f45b76ee911a56e449e6e6205c83d3bd831ac15d
3
+ size 627
checkpoint-23000/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-23000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-23000/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-23000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-23000/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 sha256:9b16f81fb410afc0c94685d72f0bf0a367b63a2a0d364b87202694f82af46dca
3
  size 440772077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b914c97ff0e1482961a9d6e07d3c1f57bbec790a5b0a14d59b95439fc61743e6
3
  size 440772077