Hugging Face's logo

Sayan01
/
bert-mrpc-distilled-cka

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Inference Endpoints
Model card Files Metrics Community
Sayan01 commited on
Commit
d70032f
•
1 Parent(s): 85294c2

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +5 -5
  2. logs/events.out.tfevents.1715836386.spartan-gpgpu093.hpc.unimelb.edu.au +2 -2
  3. logs/events.out.tfevents.1715837284.spartan-gpgpu093.hpc.unimelb.edu.au +3 -0
  4. logs/events.out.tfevents.1724059259.spartan-gpgpu095.hpc.unimelb.edu.au.131842.5 +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.1715836386.spartan-gpgpu093.hpc.unimelb.edu.au CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ae11364c606e8c4f3d2cd14401e00b44415a7ff0172ecaf1ad2c6e875b711a7
3
- size 5064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab39ae3f70f19b3238b0dcce00c0807a89ecb3110ccb971046178943608bb7a
3
+ size 10989
logs/events.out.tfevents.1715837284.spartan-gpgpu093.hpc.unimelb.edu.au ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3827f33ce341dcc2c10430ea26ae3c34af33c2684bf7bc66e75be17152c81502
3
+ size 778
logs/events.out.tfevents.1724059259.spartan-gpgpu095.hpc.unimelb.edu.au.131842.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ea262ac08710a3a6f5a09b17cfcd7f4148e0991112a82cb1ac13ffe72a86da
3
+ size 5481
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e68090134af94f47dc15e623f037eacaa431c5fe2f5d26f12b24e7c892a3837
3
- size 165480304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe29913b4d4787fdbb5384ae4b337223d842f298fa8bb2dd7714d491caabcab
3
+ size 133466376
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d55612314a7be6f9a922d1731809e4ce24f8e9d9d1c251219b2d4c9ec6c92b03
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df7b752e96ee1b6193621a5975c138daf9c0f536edb61eae2e185a57e4ddd33
3
  size 4984