Hugging Face's logo

Sayan01
/
bert-mrpc-distilled-cka

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
 Metrics Community
Sayan01 commited on
Commit
9cca61a
·
verified ·
1 Parent(s): 06824d9

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +4 -4
  2. logs/events.out.tfevents.1724059789.spartan-gpgpu095.hpc.unimelb.edu.au.131842.7 +2 -2
  3. logs/events.out.tfevents.1724060304.spartan-gpgpu095.hpc.unimelb.edu.au.131842.8 +3 -0
  4. logs/events.out.tfevents.1724070194.spartan-gpgpu095.hpc.unimelb.edu.au.169723.0 +3 -0
  5. model.safetensors +2 -2
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,19 +1,19 @@
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",
 
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": 16,
17
  "num_hidden_layers": 12,
18
  "pad_token_id": 0,
19
  "position_embedding_type": "absolute",
logs/events.out.tfevents.1724059789.spartan-gpgpu095.hpc.unimelb.edu.au.131842.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07df5149dfbed6d482a57f784656e604c111f68cc4fa357c884e0a56bd63cf47
3
- size 10200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a418d4e327e7a4c8bf60613bc038a0ed4d7b773b302827985129d97a3d04d5ba
3
+ size 11134
logs/events.out.tfevents.1724060304.spartan-gpgpu095.hpc.unimelb.edu.au.131842.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0efacad657e8dbd5ea83c2ba2d6eb92bd7bc76a9522839f53bab7e9229a987b5
3
+ size 457
logs/events.out.tfevents.1724070194.spartan-gpgpu095.hpc.unimelb.edu.au.169723.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34eb3bca29cb1ebd60e043e5d565c3b5b267e4a8d2010c95710afed5b08ac6c
3
+ size 5479
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f9b8b9b9c9d4bdbb374c4feb5e1ef0b8c546af739023656b967f857bae966e1
3
- size 133466376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6e256c26095e39095980b2c31f36dcfab7ee53af11d853bc6909873e789097
3
+ size 266339248
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8df7b752e96ee1b6193621a5975c138daf9c0f536edb61eae2e185a57e4ddd33
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb9e3258345ac534cab9ef7e7ea8e4c19df0335fe34605d54995c2457ffb9341
3
  size 4984