Hugging Face's logo

fpuentes
/
bert-fromscratch-galician-tiny

Fill-Mask
Transformers
PyTorch
Galician
roberta
Inference Endpoints
Model card Files Community
fpuentes commited on
Commit
10a5e8e
•
1 Parent(s): abe4e8f

Training in progress, step 1500

Browse files
Files changed (17) hide show
  1. events.out.tfevents.1675766816.turing.1045087.0 +3 -0
  2. last-checkpoint/config.json +28 -0
  3. last-checkpoint/merges.txt +0 -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/scheduler.pt +3 -0
  8. last-checkpoint/special_tokens_map.json +51 -0
  9. last-checkpoint/tokenizer.json +0 -0
  10. last-checkpoint/tokenizer_config.json +65 -0
  11. last-checkpoint/trainer_state.json +30 -0
  12. last-checkpoint/training_args.bin +3 -0
  13. last-checkpoint/vocab.json +0 -0
  14. pytorch_model.bin +1 -1
  15. runs/Feb07_11-46-56_turing/1675766828.707648/events.out.tfevents.1675766828.turing.1045087.2 +3 -0
  16. runs/Feb07_11-46-56_turing/events.out.tfevents.1675766828.turing.1045087.1 +3 -0
  17. training_args.bin +1 -1
events.out.tfevents.1675766816.turing.1045087.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34cb0a1730b44e95ae1bb1af514d1d0ddf3e636abbbabe137e65deb53868192a
3
+ size 40
last-checkpoint/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/pcjf/CESGA/works/lmodels/models/tiny",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 6,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.24.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 31002
28
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5cab25c6c45146550ab6370cac6427565b72081f40b2fe75c2f03157a0e7668
3
+ size 538943941
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08899eedd1ea87c0a4b54195fb6cfdd988c267131f790bf2b7941a057bebf231
3
+ size 269468281
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85400c655deed96c4b5185853e67034e42be91e9e7a4a6a6a282dcd040df57e1
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eec681b8f3a2d4dad735ade6360b32ec7ab6514552d21c2ce8363a7d9f3fc0a
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "max_len": 512,
37
+ "name_or_path": "/home/pcjf/CESGA/works/lmodels/models/tiny",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": null,
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.4634919166564941,
3
+ "best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-1500",
4
+ "epoch": 0.215964257915315,
5
+ "global_step": 1500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.22,
12
+ "learning_rate": 9.856011519078475e-06,
13
+ "loss": 1.4486,
14
+ "step": 1500
15
+ },
16
+ {
17
+ "epoch": 0.22,
18
+ "eval_loss": 1.4634919166564941,
19
+ "eval_runtime": 31.815,
20
+ "eval_samples_per_second": 570.36,
21
+ "eval_steps_per_second": 71.319,
22
+ "step": 1500
23
+ }
24
+ ],
25
+ "max_steps": 104175,
26
+ "num_train_epochs": 15,
27
+ "total_flos": 9390475772991936.0,
28
+ "trial_name": null,
29
+ "trial_params": null
30
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3bdab85c49770ae0a845ff26fd6e9d1edb800500dfa4828e9f9980bf589232e
3
+ size 3451
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0692640dbdac167fdc61252012f23bef86652860782cce1435700a221f51750
3
  size 269468281
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08899eedd1ea87c0a4b54195fb6cfdd988c267131f790bf2b7941a057bebf231
3
  size 269468281
runs/Feb07_11-46-56_turing/1675766828.707648/events.out.tfevents.1675766828.turing.1045087.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2217beae15b328955c45f767f7e78fa385205180b42f34dc7a74c08d7963b5cb
3
+ size 5575
runs/Feb07_11-46-56_turing/events.out.tfevents.1675766828.turing.1045087.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cadfaefce3b2023383f1ecfbc0b3cf3d0466a3f641df224e3c9827bf2188e5f
3
+ size 4376
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf00dfba82d3ac10ad9debd6763f43bf6a5b78e8b7425c40a36ad3d1be98fc26
3
  size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3bdab85c49770ae0a845ff26fd6e9d1edb800500dfa4828e9f9980bf589232e
3
  size 3451