Sayan01 commited on
Commit
9504f20
1 Parent(s): 25b7fba

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -8,19 +8,19 @@
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
- "hidden_size": 512,
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": 8,
18
  "num_hidden_layers": 6,
19
  "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.39.0",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 30522
 
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
  "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
  "model_type": "bert",
17
+ "num_attention_heads": 6,
18
  "num_hidden_layers": 6,
19
  "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.45.1",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 30522
logs/events.out.tfevents.1727717763.spartan-gpgpu147.hpc.unimelb.edu.au.215018.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05e81a7346f656bb95c740d690c2777270a5760aa4248e8f3e4df6a92cd627c
3
+ size 5905
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2c7b6f6c36fc1671a2bf8f9f56197459328169ba7b51e56df38f12a10c742c8
3
- size 165480304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21396fa6cbe7cd00b1a6632b6098926177c3090b651c084a6a3c00b112667996
3
+ size 90867952
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 512
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,
tokenizer_config.json CHANGED
@@ -41,7 +41,7 @@
41
  "special": true
42
  }
43
  },
44
- "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
 
41
  "special": true
42
  }
43
  },
44
+ "clean_up_tokenization_spaces": false,
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4921aa6a6473e4ca5f0d7f25604e95fda0609d81d4d164becb9eadceb1bdd36a
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21373925dc5d37fd651a987342f8a2a22cdb63574c10eeec4f7ad00a05c0ed10
3
+ size 5240