Hugging Face's logo

bertin-project
/
bertin-base-stepwise

Fill-Mask
Transformers
PyTorch
JAX
TensorBoard
Joblib
Spanish
roberta
spanish
Inference Endpoints
Model card Files Metrics Community
versae commited on
Commit
5227e76
•
1 Parent(s): ffdbef6

Step... (249000/250000 | Loss: 1.714625358581543, Acc: 0.6543225646018982): 100%|██████████████████████████| 250000/250000 [35:27:20<00:00, 1.68s/it]

Browse files
Files changed (12) hide show
  1. flax_model.msgpack +1 -1
  2. outputs/checkpoints/checkpoint-249999/config.json +25 -0
  3. outputs/checkpoints/checkpoint-249999/data_collator.joblib +3 -0
  4. outputs/checkpoints/checkpoint-249999/flax_model.msgpack +3 -0
  5. outputs/checkpoints/checkpoint-249999/optimizer_state.msgpack +3 -0
  6. outputs/checkpoints/checkpoint-249999/training_args.joblib +3 -0
  7. outputs/checkpoints/checkpoint-249999/training_state.json +1 -0
  8. outputs/events.out.tfevents.1627128247.tablespoon.2330108.3.v2 +2 -2
  9. outputs/flax_model.msgpack +1 -1
  10. outputs/optimizer_state.msgpack +1 -1
  11. outputs/training_state.json +1 -1
  12. pytorch_model.bin +1 -1
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:480c54494726a063f46cdd71519435cab118f3c20f67e1c78988e1f846dc1397
3
  size 249750019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb77f45d823a419647b591636a9585187f2296250e8220313d50409d87e0a94
3
  size 249750019
outputs/checkpoints/checkpoint-249999/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-249999/data_collator.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0321b1a9629e1be122045cd72470365a63c8496fec109fdeec34827f01ffbb9e
3
+ size 1471424
outputs/checkpoints/checkpoint-249999/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb77f45d823a419647b591636a9585187f2296250e8220313d50409d87e0a94
3
+ size 249750019
outputs/checkpoints/checkpoint-249999/optimizer_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1169479fbf819cbca67bb8fbef0922b31789415f0580a4c19ea192da62b69d63
3
+ size 499500278
outputs/checkpoints/checkpoint-249999/training_args.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79196d5f797a7527e60287e48f716fd4626c5d57186661d6a214a2027998c86d
3
+ size 1873
outputs/checkpoints/checkpoint-249999/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 250000}
outputs/events.out.tfevents.1627128247.tablespoon.2330108.3.v2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c19dde024621504f645dd88e1478681acae482f47aed8fe9df2515c4fcab7eb7
3
- size 10151216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad0186243a948caf42e26943577f1155ac2223f27931b7b5d1d922d5efb49ed
3
+ size 10225786
outputs/flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:480c54494726a063f46cdd71519435cab118f3c20f67e1c78988e1f846dc1397
3
  size 249750019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb77f45d823a419647b591636a9585187f2296250e8220313d50409d87e0a94
3
  size 249750019
outputs/optimizer_state.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa66cb034649b7eaa607b7b025f58d6c1cce7f2a78fa7c844f2064ab6a4bf91e
3
  size 499500278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1169479fbf819cbca67bb8fbef0922b31789415f0580a4c19ea192da62b69d63
3
  size 499500278
outputs/training_state.json CHANGED
@@ -1 +1 @@
1
- {"step": 249001}
 
1
+ {"step": 250000}
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9048dbb0c40562e8f9d1be91c2ddb62444fad0f0e0eb0c2df8a77e1922a4c032
3
  size 498858859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad64f4a4a6dc59c076f74458305070c918bdd03ab5bc8a3024e8b12a03aadbe5
3
  size 498858859