Hugging Face's logo

sheepy928
/
bincorp_ep0.3_wo_ep

Transformers
PyTorch
marinda
Inference Endpoints
Model card Files Community
sheepy928 commited on
Commit
27459c4
•
1 Parent(s): 351d7a0

Training in progress, step 20000

Browse files
Files changed (18) hide show
  1. checkpoint-20000/config.json +28 -0
  2. checkpoint-20000/optimizer.pt +3 -0
  3. checkpoint-20000/pytorch_model.bin +3 -0
  4. checkpoint-20000/rng_state_0.pth +3 -0
  5. checkpoint-20000/rng_state_1.pth +3 -0
  6. checkpoint-20000/rng_state_2.pth +3 -0
  7. checkpoint-20000/rng_state_3.pth +3 -0
  8. checkpoint-20000/rng_state_4.pth +3 -0
  9. checkpoint-20000/rng_state_5.pth +3 -0
  10. checkpoint-20000/rng_state_6.pth +3 -0
  11. checkpoint-20000/rng_state_7.pth +3 -0
  12. checkpoint-20000/scheduler.pt +3 -0
  13. checkpoint-20000/special_tokens_map.json +7 -0
  14. checkpoint-20000/tokenizer.json +0 -0
  15. checkpoint-20000/tokenizer_config.json +5 -0
  16. checkpoint-20000/trainer_state.json +0 -0
  17. checkpoint-20000/training_args.bin +3 -0
  18. pytorch_model.bin +1 -1
checkpoint-20000/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-20000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f45d51a033dbf6d07a5f0224c5bc1955e258e69775018031b97779fe11ed356a
3
+ size 881521797
checkpoint-20000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ae8e3648be1c4239838180a180c948ab294a092b4bddc1c53f8671229b2549
3
+ size 440772077
checkpoint-20000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f49c2a46a007a4b90a9a74a7572ba7921e33a9429f8a7265baccb242e1ae28a
3
+ size 21623
checkpoint-20000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165af997503b1125349554b34c2c3541bc912966365576c5ad8a9dcf3b10ae0b
3
+ size 21623
checkpoint-20000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f67a3060af34f509b0b5828ea5c64419f36930a3661fcf85574c1668a8c3654
3
+ size 21623
checkpoint-20000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d91637d41f52bf3fcd01f640292f17bde39d171b15b30bf90afd46c2f79042
3
+ size 21623
checkpoint-20000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1629b86de0a6d2dac8205ac4aad53cb759f4214ade0826d2c6dc9663656696e4
3
+ size 21623
checkpoint-20000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff15dd731b5689808cbffaf05234a3c702593f6f4083dcf564bfd54b18a88ea
3
+ size 21623
checkpoint-20000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2e0bc794093537001309552f9565897c3a7d6c8f2bdc05a61dd1ea3f2dde8e
3
+ size 21623
checkpoint-20000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95088dd13deea3f6d4b872bcea91f027fd51a4b07c5815d377b31260146abd8a
3
+ size 21623
checkpoint-20000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271b631f14e5df155b4781cf881c98f93b21db09c2be5d755941679baa37a41c
3
+ size 627
checkpoint-20000/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-20000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-20000/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-20000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-20000/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:f323e1b3ed65c603edb4095e114ca83d99002212944ace1dbf196306a0061a34
3
  size 440772077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ae8e3648be1c4239838180a180c948ab294a092b4bddc1c53f8671229b2549
3
  size 440772077