Hugging Face's logo

ulyanaisaeva
/
udmurt-bert-base-uncased

Fill-Mask
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ulyanaisaeva commited on
Commit
1718eb7
·
1 Parent(s): 9f3d921

Training in progress, epoch 1

Browse files
Files changed (16) hide show
  1. checkpoint-6419/config.json +31 -0
  2. checkpoint-6419/optimizer.pt +3 -0
  3. checkpoint-6419/pytorch_model.bin +3 -0
  4. checkpoint-6419/rng_state.pth +3 -0
  5. checkpoint-6419/scaler.pt +3 -0
  6. checkpoint-6419/scheduler.pt +3 -0
  7. checkpoint-6419/trainer_state.json +30 -0
  8. checkpoint-6419/training_args.bin +3 -0
  9. config.json +31 -0
  10. pytorch_model.bin +3 -0
  11. runs/May30_13-27-46_9a4805da8a6d/1653917301.8752072/events.out.tfevents.1653917301.9a4805da8a6d.80.1 +3 -0
  12. runs/May30_13-27-46_9a4805da8a6d/1653917532.1979287/events.out.tfevents.1653917532.9a4805da8a6d.80.2 +3 -0
  13. runs/May30_13-27-46_9a4805da8a6d/events.out.tfevents.1653917301.9a4805da8a6d.80.0 +3 -0
  14. runs/May30_14-29-18_9a4805da8a6d/1653920983.3778038/events.out.tfevents.1653920983.9a4805da8a6d.80.4 +3 -0
  15. runs/May30_14-29-18_9a4805da8a6d/events.out.tfevents.1653920983.9a4805da8a6d.80.3 +3 -0
  16. training_args.bin +3 -0
checkpoint-6419/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/models/bert_modif_emb",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
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-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.19.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
checkpoint-6419/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32ced75387a1b3aa63b906f8d3354a4b23f6e5e96f2b9ecc3ff6243c81f96eb3
3
+ size 885324121
checkpoint-6419/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329903eb21f8e1e3ce9cc8e0ba643e55099c4ea5d438b8b865c431c1f0f79edd
3
+ size 442675179
checkpoint-6419/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ad2ca6dfd4b649b58f84604e4a12fc02c33b1158957e0fa8fc86f89f5a78c3
3
+ size 14503
checkpoint-6419/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc2ac84e9932b362262b4be9015aad7f23c9185f08f83797f607ddb1c71e2fea
3
+ size 559
checkpoint-6419/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aacc18a3467a269b5230ac9d5f81106d6f97561d670c53953dd29d9fdf151a6d
3
+ size 623
checkpoint-6419/trainer_state.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 6419,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 8.889735156655704e-06,
13
+ "loss": 7.3112,
14
+ "step": 6419
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 6.181427955627441,
19
+ "eval_runtime": 64.709,
20
+ "eval_samples_per_second": 198.396,
21
+ "eval_steps_per_second": 9.921,
22
+ "step": 6419
23
+ }
24
+ ],
25
+ "max_steps": 32095,
26
+ "num_train_epochs": 5,
27
+ "total_flos": 8447704191467520.0,
28
+ "trial_name": null,
29
+ "trial_params": null
30
+ }
checkpoint-6419/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6a6e3558851af45bb5a2bf276230e5bbacabfdee3309629484b8049458d984
3
+ size 3247
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/models/bert_modif_emb",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
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-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.19.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329903eb21f8e1e3ce9cc8e0ba643e55099c4ea5d438b8b865c431c1f0f79edd
3
+ size 442675179
runs/May30_13-27-46_9a4805da8a6d/1653917301.8752072/events.out.tfevents.1653917301.9a4805da8a6d.80.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae48e4838bd21dcd1e956c44867bd063043aa9fee7a0177b2e3a7d218c673424
3
+ size 5248
runs/May30_13-27-46_9a4805da8a6d/1653917532.1979287/events.out.tfevents.1653917532.9a4805da8a6d.80.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ec08e28a5c629b5ecdc247f4bf67593b47156abab3eb09d0563da17c3b98b2
3
+ size 5248
runs/May30_13-27-46_9a4805da8a6d/events.out.tfevents.1653917301.9a4805da8a6d.80.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636ae9a27a9a7979b4fe94200f90a50d6156eb547e2a7719b211c352a1d68cb0
3
+ size 7615
runs/May30_14-29-18_9a4805da8a6d/1653920983.3778038/events.out.tfevents.1653920983.9a4805da8a6d.80.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5026342609946029b31f2cc1600248f713c10a118e3f1a69c5603ee36e50e62b
3
+ size 5248
runs/May30_14-29-18_9a4805da8a6d/events.out.tfevents.1653920983.9a4805da8a6d.80.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b240f84ee5518bb7967f12af5ab459198f650123c185689b4f331eff03dc64
3
+ size 4232
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6a6e3558851af45bb5a2bf276230e5bbacabfdee3309629484b8049458d984
3
+ size 3247