Hugging Face's logo

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

Fill-Mask
Transformers
PyTorch
JAX
TensorBoard
Joblib
Spanish
roberta
spanish
Inference Endpoints
Model card Files Metrics Community
versae commited on
Commit
a135ed0
•
1 Parent(s): 449906e

Step... (31000/50000 | Loss: 1.604581594467163, Acc: 0.6744211912155151): 64%|█████████████████▊ | 31806/50000 [12:45:50<7:10:54, 1.42s/it]

Browse files
Files changed (28) hide show
  1. flax_model.msgpack +1 -1
  2. outputs/checkpoints/checkpoint-43000/training_state.json +0 -1
  3. outputs/checkpoints/checkpoint-44000/training_state.json +0 -1
  4. outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/config.json +0 -0
  5. outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/data_collator.joblib +0 -0
  6. outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/flax_model.msgpack +1 -1
  7. outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/optimizer_state.msgpack +1 -1
  8. outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/training_args.joblib +0 -0
  9. outputs/checkpoints/checkpoint-48000/training_state.json +1 -0
  10. outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/config.json +0 -0
  11. outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/data_collator.joblib +0 -0
  12. outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/flax_model.msgpack +1 -1
  13. outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/optimizer_state.msgpack +1 -1
  14. outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/training_args.joblib +0 -0
  15. outputs/checkpoints/checkpoint-49000/training_state.json +1 -0
  16. outputs/checkpoints/checkpoint-49999/config.json +25 -0
  17. outputs/checkpoints/checkpoint-49999/data_collator.joblib +3 -0
  18. outputs/checkpoints/checkpoint-49999/flax_model.msgpack +3 -0
  19. outputs/checkpoints/checkpoint-49999/optimizer_state.msgpack +3 -0
  20. outputs/checkpoints/checkpoint-49999/training_args.joblib +3 -0
  21. outputs/checkpoints/checkpoint-49999/training_state.json +1 -0
  22. outputs/events.out.tfevents.1627258355.tablespoon.3000110.3.v2 +2 -2
  23. outputs/flax_model.msgpack +1 -1
  24. outputs/optimizer_state.msgpack +1 -1
  25. outputs/training_state.json +1 -1
  26. pytorch_model.bin +1 -1
  27. wandb/run-20210726_001233-17u6inbn/files/config.yaml +4 -0
  28. wandb/run-20210726_001233-17u6inbn/files/wandb-summary.json +1 -1
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf2e0a8447d4d762862755db833dda04a149889cb930f56c336aa8861adbf1fa
3
  size 249750019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a80ec619ededfbd4e9b69ec8ed53e4716447f0d49f33d7c1dd0c8933a415b92
3
  size 249750019
outputs/checkpoints/checkpoint-43000/training_state.json DELETED
@@ -1 +0,0 @@
1
- {"step": 43001}
 
 
outputs/checkpoints/checkpoint-44000/training_state.json DELETED
@@ -1 +0,0 @@
1
- {"step": 44001}
 
 
outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/config.json RENAMED
File without changes
outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/data_collator.joblib RENAMED
File without changes
outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/flax_model.msgpack RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0caead9b50aa2dfee7abafbbfda0cf2007675600c9a85f6855a7f4142b5945b8
3
  size 249750019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ed996d5623269b9afc7dd278943915670e3406733303a84439a15d65cfe3b5
3
  size 249750019
outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/optimizer_state.msgpack RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3ea6d04ae5f0b7163c4408b13d40b9005e1dd97f0d849ebbc18031fc7a15264
3
  size 499500278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d6533e1795216fc55d7a16252cacb039b1fe419c56257c19f869123fb487a6
3
  size 499500278
outputs/checkpoints/{checkpoint-43000 → checkpoint-48000}/training_args.joblib RENAMED
File without changes
outputs/checkpoints/checkpoint-48000/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 48001}
outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/config.json RENAMED
File without changes
outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/data_collator.joblib RENAMED
File without changes
outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/flax_model.msgpack RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef4602e3adde65fca47e5a76079cd2c283ee8a303b1bc2b6d8c12026da5f7d10
3
  size 249750019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9361bf57ad2ead83a8e61463af52a266432dbe017ac67e69e4fc14ff2f99bc2
3
  size 249750019
outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/optimizer_state.msgpack RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:608a47516582fc22489dc66a1735bad131824cbdc90030c520193a7bfa64a642
3
  size 499500278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a36b556f0aa465dd239707419da9b91e96b3a21d626edcdc79b1d504f1acac1
3
  size 499500278
outputs/checkpoints/{checkpoint-44000 → checkpoint-49000}/training_args.joblib RENAMED
File without changes
outputs/checkpoints/checkpoint-49000/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 49001}
outputs/checkpoints/checkpoint-49999/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-49999/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-49999/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a80ec619ededfbd4e9b69ec8ed53e4716447f0d49f33d7c1dd0c8933a415b92
3
+ size 249750019
outputs/checkpoints/checkpoint-49999/optimizer_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454081a0a1386f88384007ec81b6564461b3fea4611907b1ffdcca605a502328
3
+ size 499500278
outputs/checkpoints/checkpoint-49999/training_args.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dcde99c91fe01c5143995806e1d6595b728cb8ed0a2d9f2f3c5610aeebeb7c2
3
+ size 1871
outputs/checkpoints/checkpoint-49999/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 50000}
outputs/events.out.tfevents.1627258355.tablespoon.3000110.3.v2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6a50ac8502fcec221e119c669e3e6f36eb46c048dc4b39c5783d7920763f442
3
- size 7057921
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67436853ad44fa6bb220a27f80ae4ac2234c4c97ba1f6f2f187eb535314d2469
3
+ size 7356485
outputs/flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf2e0a8447d4d762862755db833dda04a149889cb930f56c336aa8861adbf1fa
3
  size 249750019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a80ec619ededfbd4e9b69ec8ed53e4716447f0d49f33d7c1dd0c8933a415b92
3
  size 249750019
outputs/optimizer_state.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:906a99024914c38872d8a52f4bfffc9aab9d680e8b6b177c41e86d7742467117
3
  size 499500278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454081a0a1386f88384007ec81b6564461b3fea4611907b1ffdcca605a502328
3
  size 499500278
outputs/training_state.json CHANGED
@@ -1 +1 @@
1
- {"step": 47001}
 
1
+ {"step": 50000}
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99965993689d0344c06defe7dd6f554341dfd04b53311615bf25640c62e9b929
3
  size 498858859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c60621f443054b98aa2dc500b083ddeee3dd86e2824265efb7bd7e8002d4b9
3
  size 498858859
wandb/run-20210726_001233-17u6inbn/files/config.yaml CHANGED
@@ -21,6 +21,10 @@ _wandb:
21
  - 1
22
  - 3
23
  - 11
 
 
 
 
24
  4: 3.8.10
25
  5: 0.10.33
26
  6: 4.9.0.dev0
 
21
  - 1
22
  - 3
23
  - 11
24
+ 2:
25
+ - 1
26
+ - 3
27
+ - 11
28
  4: 3.8.10
29
  5: 0.10.33
30
  6: 4.9.0.dev0
wandb/run-20210726_001233-17u6inbn/files/wandb-summary.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 47500, "_timestamp": 1627334867.379425, "train_time": 3936264.25, "train_learning_rate": 3.0303026505862363e-05, "_step": 94715, "train_loss": 1.6438705921173096, "eval_accuracy": 0.6815508604049683, "eval_loss": 1.559740662574768}
 
1
+ {"global_step": 49500, "_timestamp": 1627337892.535226, "train_time": 4249756.0, "train_learning_rate": 6.060612577130087e-06, "_step": 98704, "train_loss": 1.6237502098083496, "eval_accuracy": 0.6817952990531921, "eval_loss": 1.558030366897583}