Hugging Face's logo

bertin-project
/
bertin-base-gaussian-exp-512seqlen

Fill-Mask
Transformers
PyTorch
JAX
TensorBoard
Joblib
Spanish
roberta
spanish
Inference Endpoints
Model card Files Metrics Community
versae commited on
Commit
874a738
•
1 Parent(s): e8a9ff1

Step... (24001/50000 | Loss: 1.617178201675415, Acc: 0.6729233860969543): 48%|█████████████▌ | 24176/50000 [9:23:11<10:03:40, 1.40s/it]

Browse files
Files changed (40) hide show
  1. flax_model.msgpack +3 -0
  2. outputs/checkpoints/checkpoint-20000/config.json +25 -0
  3. outputs/checkpoints/checkpoint-20000/data_collator.joblib +3 -0
  4. outputs/checkpoints/checkpoint-20000/flax_model.msgpack +3 -0
  5. outputs/checkpoints/checkpoint-20000/optimizer_state.msgpack +3 -0
  6. outputs/checkpoints/checkpoint-20000/training_args.joblib +3 -0
  7. outputs/checkpoints/checkpoint-20000/training_state.json +1 -0
  8. outputs/checkpoints/checkpoint-21000/config.json +25 -0
  9. outputs/checkpoints/checkpoint-21000/data_collator.joblib +3 -0
  10. outputs/checkpoints/checkpoint-21000/flax_model.msgpack +3 -0
  11. outputs/checkpoints/checkpoint-21000/optimizer_state.msgpack +3 -0
  12. outputs/checkpoints/checkpoint-21000/training_args.joblib +3 -0
  13. outputs/checkpoints/checkpoint-21000/training_state.json +1 -0
  14. outputs/checkpoints/checkpoint-22000/config.json +25 -0
  15. outputs/checkpoints/checkpoint-22000/data_collator.joblib +3 -0
  16. outputs/checkpoints/checkpoint-22000/flax_model.msgpack +3 -0
  17. outputs/checkpoints/checkpoint-22000/optimizer_state.msgpack +3 -0
  18. outputs/checkpoints/checkpoint-22000/training_args.joblib +3 -0
  19. outputs/checkpoints/checkpoint-22000/training_state.json +1 -0
  20. outputs/checkpoints/checkpoint-23000/config.json +25 -0
  21. outputs/checkpoints/checkpoint-23000/data_collator.joblib +3 -0
  22. outputs/checkpoints/checkpoint-23000/flax_model.msgpack +3 -0
  23. outputs/checkpoints/checkpoint-23000/optimizer_state.msgpack +3 -0
  24. outputs/checkpoints/checkpoint-23000/training_args.joblib +3 -0
  25. outputs/checkpoints/checkpoint-23000/training_state.json +1 -0
  26. outputs/checkpoints/checkpoint-24000/config.json +25 -0
  27. outputs/checkpoints/checkpoint-24000/data_collator.joblib +3 -0
  28. outputs/checkpoints/checkpoint-24000/flax_model.msgpack +3 -0
  29. outputs/checkpoints/checkpoint-24000/optimizer_state.msgpack +3 -0
  30. outputs/checkpoints/checkpoint-24000/training_args.joblib +3 -0
  31. outputs/checkpoints/checkpoint-24000/training_state.json +1 -0
  32. outputs/config.json +25 -0
  33. outputs/data_collator.joblib +3 -0
  34. outputs/events.out.tfevents.1626606849.tablespoon.3622971.3.v2 +3 -0
  35. outputs/flax_model.msgpack +3 -0
  36. outputs/optimizer_state.msgpack +3 -0
  37. outputs/training_args.joblib +3 -0
  38. outputs/training_state.json +1 -0
  39. pytorch_model.bin +3 -0
  40. run_stream.log +3 -0
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09beaeeb31a7c0151bd2c93e8cc32b6ea04983edc759ef4cb3c8648db5ad7730
3
+ size 249750019
outputs/checkpoints/checkpoint-20000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.9.0.dev0",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 50265
25
+ }
outputs/checkpoints/checkpoint-20000/data_collator.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee
3
+ size 1471394
outputs/checkpoints/checkpoint-20000/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc062cff226dee3ccdfbbc5682d4b2882c4f57c0a40a3f54bd16d8567298d5c0
3
+ size 249750019
outputs/checkpoints/checkpoint-20000/optimizer_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d1e8ec7e4b6752640d08a898bdf803649b14ffa733d5e17300d4eb26761b32c
3
+ size 499500278
outputs/checkpoints/checkpoint-20000/training_args.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc949f7397802302b9bca931dc2ae667a615a9e818fe0b22660b2812f0ac94a
3
+ size 1871
outputs/checkpoints/checkpoint-20000/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 20001}
outputs/checkpoints/checkpoint-21000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.9.0.dev0",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 50265
25
+ }
outputs/checkpoints/checkpoint-21000/data_collator.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee
3
+ size 1471394
outputs/checkpoints/checkpoint-21000/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09bef80851e5190807b15c1dbe9d0270c9384ab44c3dcb4db178b85e80a71379
3
+ size 249750019
outputs/checkpoints/checkpoint-21000/optimizer_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a99a82909987b205609070cca9c4c5799ca4a0b78511f099fc3a9e538161a195
3
+ size 499500278
outputs/checkpoints/checkpoint-21000/training_args.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc949f7397802302b9bca931dc2ae667a615a9e818fe0b22660b2812f0ac94a
3
+ size 1871
outputs/checkpoints/checkpoint-21000/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 21001}
outputs/checkpoints/checkpoint-22000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.9.0.dev0",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 50265
25
+ }
outputs/checkpoints/checkpoint-22000/data_collator.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee
3
+ size 1471394
outputs/checkpoints/checkpoint-22000/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456166d50c18f7f3142206184d4feef24a636439fdcef000abad0390a3d059b5
3
+ size 249750019
outputs/checkpoints/checkpoint-22000/optimizer_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999d37700b86141a104d23f6d71b9c6d986487679ae464c42f3cd32807cfc1fe
3
+ size 499500278
outputs/checkpoints/checkpoint-22000/training_args.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc949f7397802302b9bca931dc2ae667a615a9e818fe0b22660b2812f0ac94a
3
+ size 1871
outputs/checkpoints/checkpoint-22000/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 22001}
outputs/checkpoints/checkpoint-23000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.9.0.dev0",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 50265
25
+ }
outputs/checkpoints/checkpoint-23000/data_collator.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee
3
+ size 1471394
outputs/checkpoints/checkpoint-23000/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998dbfb165df6528c9aba1a3b7f780529f9f4b1802aa9747e677cb3c0df13367
3
+ size 249750019
outputs/checkpoints/checkpoint-23000/optimizer_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f600914b8fd791890a084de4c55f62c1bfdb83ea63fd68009fad4b9e326a7993
3
+ size 499500278
outputs/checkpoints/checkpoint-23000/training_args.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc949f7397802302b9bca931dc2ae667a615a9e818fe0b22660b2812f0ac94a
3
+ size 1871
outputs/checkpoints/checkpoint-23000/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 23001}
outputs/checkpoints/checkpoint-24000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.9.0.dev0",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 50265
25
+ }
outputs/checkpoints/checkpoint-24000/data_collator.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee
3
+ size 1471394
outputs/checkpoints/checkpoint-24000/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09beaeeb31a7c0151bd2c93e8cc32b6ea04983edc759ef4cb3c8648db5ad7730
3
+ size 249750019
outputs/checkpoints/checkpoint-24000/optimizer_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28559bb3ef8565f8edae3fabb0dd7f897d6c713613daa2253997225190e79c4
3
+ size 499500278
outputs/checkpoints/checkpoint-24000/training_args.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc949f7397802302b9bca931dc2ae667a615a9e818fe0b22660b2812f0ac94a
3
+ size 1871
outputs/checkpoints/checkpoint-24000/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 24001}
outputs/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.9.0.dev0",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 50265
25
+ }
outputs/data_collator.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee
3
+ size 1471394
outputs/events.out.tfevents.1626606849.tablespoon.3622971.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8fbb76cc63d74e9ce7a5412bad1ffc119d253cd90aa83ea2c81c9d7983de56
3
+ size 3549865
outputs/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09beaeeb31a7c0151bd2c93e8cc32b6ea04983edc759ef4cb3c8648db5ad7730
3
+ size 249750019
outputs/optimizer_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28559bb3ef8565f8edae3fabb0dd7f897d6c713613daa2253997225190e79c4
3
+ size 499500278
outputs/training_args.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc949f7397802302b9bca931dc2ae667a615a9e818fe0b22660b2812f0ac94a
3
+ size 1871
outputs/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 24001}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5245e6d027e2a607f8dd81c64eeb4619c68790451c1c7486cd4a78aff54a84da
3
+ size 498858859
run_stream.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52166949c32235ca69239a87410e283ddad2eb5e37ee631c3b43bc1f16e82897
3
+ size 4721052