Hugging Face's logo

Sayan01
/
bert-rte-distilled-cka

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Inference Endpoints
Model card Files Metrics Community
Sayan01 commited on
Commit
a31662c
·
verified ·
1 Parent(s): bd21bc7

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +5 -5
  2. logs/events.out.tfevents.1715824338.spartan-gpgpu093.hpc.unimelb.edu.au +2 -2
  3. logs/events.out.tfevents.1715824668.spartan-gpgpu093.hpc.unimelb.edu.au +3 -0
  4. logs/events.out.tfevents.1724058634.spartan-gpgpu095.hpc.unimelb.edu.au.131842.4 +3 -0
  5. model.safetensors +2 -2
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,20 +1,20 @@
1
  {
 
2
  "architectures": [
3
  "BertForSequenceClassification"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "classifier_dropout": null,
7
- "gradient_checkpointing": false,
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
- "hidden_size": 512,
11
  "initializer_range": 0.02,
12
- "intermediate_size": 3072,
13
  "layer_norm_eps": 1e-12,
14
  "max_position_embeddings": 512,
15
  "model_type": "bert",
16
- "num_attention_heads": 8,
17
- "num_hidden_layers": 6,
18
  "pad_token_id": 0,
19
  "position_embedding_type": "absolute",
20
  "problem_type": "single_label_classification",
 
1
  {
2
+ "_name_or_path": "/data/projects/punim0478/sayantand/Checkpoints/BERT/minilm/12_384",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 1536,
13
  "layer_norm_eps": 1e-12,
14
  "max_position_embeddings": 512,
15
  "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
  "pad_token_id": 0,
19
  "position_embedding_type": "absolute",
20
  "problem_type": "single_label_classification",
logs/events.out.tfevents.1715824338.spartan-gpgpu093.hpc.unimelb.edu.au CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e38337999d3549e9a1637b2b35755705d416e9cfa06e58469d7647bd54a18883
3
- size 5023
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1046b16fd3f4f35b6d110d39e5734bb6900943171bde00575b5424f9a12655a
3
+ size 10480
logs/events.out.tfevents.1715824668.spartan-gpgpu093.hpc.unimelb.edu.au ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa9ad98feb0cd5b1550292bd105b2f5c7fe3480280dea491223a78da27bbb25
3
+ size 686
logs/events.out.tfevents.1724058634.spartan-gpgpu095.hpc.unimelb.edu.au.131842.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6615075e55e2b36644fa234c530e3c7ad9fc0e7afaf9570bb864f57f70d967
3
+ size 5395
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2f360f130bbd54b6fc46fc0e57c9b18657b3dc08debb8ffc3b12e6d3a05592e
3
- size 165480304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844873d517bc2269baa7cc9ae22bfa4d1596b9aac5e1d90ba061ba8568b3a6f5
3
+ size 133466376
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04d2b4311d769bcee484045dd1662a15b2f61119b21df73edfa0e4ad0b95e6fa
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d5cc6afa18d4a37013886dde9d358141451b793992f3cd2b2a381673d398c4
3
  size 4984