Hugging Face's logo

joelniklaus
/
legal-swiss-longformer-base

Fill-Mask
Transformers
PyTorch
Safetensors
longformer
Inference Endpoints
Model card Files Community
7
joelniklaus commited on
Commit
578d703
•
1 Parent(s): 001189d

Training in progress, step 10000

Browse files
Files changed (18) hide show
  1. .gitignore +1 -0
  2. config.json +47 -0
  3. last-checkpoint/config.json +47 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scaler.pt +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/special_tokens_map.json +9 -0
  10. last-checkpoint/tokenizer.json +0 -0
  11. last-checkpoint/tokenizer_config.json +12 -0
  12. last-checkpoint/trainer_state.json +85 -0
  13. last-checkpoint/training_args.bin +3 -0
  14. pytorch_model.bin +3 -0
  15. special_tokens_map.json +9 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +12 -0
  18. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "data/plms/legal-swiss-longformer-base",
3
+ "architectures": [
4
+ "LongformerForMaskedLM"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 128,
10
+ 128,
11
+ 128,
12
+ 128,
13
+ 128,
14
+ 128,
15
+ 128,
16
+ 128,
17
+ 128,
18
+ 128,
19
+ 128,
20
+ 128
21
+ ],
22
+ "bos_token_id": 1,
23
+ "classifier_dropout": null,
24
+ "cls_token_id": 1,
25
+ "eos_token_id": 2,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "ignore_attention_mask": false,
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 4098,
35
+ "model_max_length": 4096,
36
+ "model_type": "longformer",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "onnx_export": false,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "sep_token_id": 2,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.28.1",
45
+ "type_vocab_size": 1,
46
+ "vocab_size": 128000
47
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "data/plms/legal-swiss-longformer-base",
3
+ "architectures": [
4
+ "LongformerForMaskedLM"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 128,
10
+ 128,
11
+ 128,
12
+ 128,
13
+ 128,
14
+ 128,
15
+ 128,
16
+ 128,
17
+ 128,
18
+ 128,
19
+ 128,
20
+ 128
21
+ ],
22
+ "bos_token_id": 1,
23
+ "classifier_dropout": null,
24
+ "cls_token_id": 1,
25
+ "eos_token_id": 2,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "ignore_attention_mask": false,
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 4098,
35
+ "model_max_length": 4096,
36
+ "model_type": "longformer",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "onnx_export": false,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "sep_token_id": 2,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.28.1",
45
+ "type_vocab_size": 1,
46
+ "vocab_size": 128000
47
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab515e1fe640432722359a2c1b73c30cb1877b811da7dd7eb4d12a0264d38ca7
3
+ size 1668076741
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6b694759ac2afff917fcdce63156bddf5fee0be806cea69404c4a6ae5f6230
3
+ size 834053717
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4769972fb7cd6e12627b484967936feb779148fd2d15221e6fc67a874d999b
3
+ size 15597
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0909b42e35569611bafb37fd33209cd6a86113e40deac3fa1da41689cd651093
3
+ size 557
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf931b79849e3c5ce67ad727efd02c50905b3121a21823c140a392dee34ce6e
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": "<mask>",
7
+ "model_max_length": 4096,
8
+ "pad_token": "<pad>",
9
+ "sep_token": "</s>",
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "unk_token": "<unk>"
12
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 1.1904e-05,
13
+ "loss": 1.4759,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 2.3880000000000002e-05,
19
+ "loss": 2.0784,
20
+ "step": 2000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 2.9992187757207995e-05,
25
+ "loss": 1.8615,
26
+ "step": 3000
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 2.9927417972317198e-05,
31
+ "loss": 0.9561,
32
+ "step": 4000
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "learning_rate": 2.97973743867291e-05,
37
+ "loss": 0.8567,
38
+ "step": 5000
39
+ },
40
+ {
41
+ "epoch": 0.12,
42
+ "learning_rate": 2.9602625647955514e-05,
43
+ "loss": 0.7767,
44
+ "step": 6000
45
+ },
46
+ {
47
+ "epoch": 0.14,
48
+ "learning_rate": 2.9344023342679696e-05,
49
+ "loss": 0.7502,
50
+ "step": 7000
51
+ },
52
+ {
53
+ "epoch": 0.16,
54
+ "learning_rate": 2.9022698272984482e-05,
55
+ "loss": 0.8425,
56
+ "step": 8000
57
+ },
58
+ {
59
+ "epoch": 0.18,
60
+ "learning_rate": 2.8640055511642487e-05,
61
+ "loss": 0.7989,
62
+ "step": 9000
63
+ },
64
+ {
65
+ "epoch": 0.2,
66
+ "learning_rate": 2.8197768258090375e-05,
67
+ "loss": 0.8392,
68
+ "step": 10000
69
+ },
70
+ {
71
+ "epoch": 0.2,
72
+ "eval_accuracy": 0.8492928069198428,
73
+ "eval_loss": 0.6663709282875061,
74
+ "eval_runtime": 121.7475,
75
+ "eval_samples_per_second": 41.069,
76
+ "eval_steps_per_second": 2.571,
77
+ "step": 10000
78
+ }
79
+ ],
80
+ "max_steps": 50000,
81
+ "num_train_epochs": 9223372036854775807,
82
+ "total_flos": 6.7342134411264e+18,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b0babeabcb0232c54abbc734323546866d0c776b0a65f83be54dbb867e9e640
3
+ size 3707
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6b694759ac2afff917fcdce63156bddf5fee0be806cea69404c4a6ae5f6230
3
+ size 834053717
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": "<mask>",
7
+ "model_max_length": 4096,
8
+ "pad_token": "<pad>",
9
+ "sep_token": "</s>",
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "unk_token": "<unk>"
12
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b0babeabcb0232c54abbc734323546866d0c776b0a65f83be54dbb867e9e640
3
+ size 3707