mhassanch commited on
Commit
79a1dc6
·
verified ·
1 Parent(s): fb34840

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,37 +1,35 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
 
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "id2label": {
13
  "0": "object-detection",
14
  "1": "zero-shot-object-detection",
15
  "2": "mask-generation"
16
  },
17
  "initializer_range": 0.02,
18
- "intermediate_size": 3072,
19
  "label2id": {
20
  "mask-generation": 2,
21
  "object-detection": 0,
22
  "zero-shot-object-detection": 1
23
  },
24
- "layer_norm_eps": 1e-12,
25
  "max_position_embeddings": 512,
26
- "model_type": "bert",
27
- "num_attention_heads": 12,
28
- "num_hidden_layers": 12,
29
  "pad_token_id": 0,
30
- "position_embedding_type": "absolute",
31
  "problem_type": "single_label_classification",
 
 
 
 
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.48.3",
34
- "type_vocab_size": 2,
35
- "use_cache": true,
36
  "vocab_size": 30522
37
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "object-detection",
13
  "1": "zero-shot-object-detection",
14
  "2": "mask-generation"
15
  },
16
  "initializer_range": 0.02,
 
17
  "label2id": {
18
  "mask-generation": 2,
19
  "object-detection": 0,
20
  "zero-shot-object-detection": 1
21
  },
 
22
  "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
  "pad_token_id": 0,
 
27
  "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.48.3",
 
 
34
  "vocab_size": 30522
35
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a45efa39ee0422d90686c0fc6bea0c9260b85499d1130cee183844d7ce030c00
3
- size 437961724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff16b496e8baef76ca1cc302a4547dfab467b5693553e93c6d3b46ed0e65951
3
+ size 267835644
runs/Mar04_13-47-30_75287a5389c5/events.out.tfevents.1741096051.75287a5389c5.593.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80918bff64c5435ea5a643007b096f714df021c093c241b894e6dc3b782298ce
3
- size 21179
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e909f89830665a663e9a2f0152a20b0ba5a8e9a66b88e6ec7917b1ad05bcc8ec
3
+ size 21527
runs/Mar04_14-09-26_75287a5389c5/events.out.tfevents.1741097368.75287a5389c5.593.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f75f78a9fc527d11b04747f0e800262ae5dc7c11e9254e422560cac59f59caa
3
+ size 5483
tokenizer_config.json CHANGED
@@ -51,6 +51,6 @@
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
- "tokenizer_class": "BertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
 
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f058e867216cb7a7ce392ff2e58343af7e7f61ebf3e9ac92fa7a29a8eb0b5051
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bde90a54bfd80a7e8b88c3332628a36b73c6c18cbeb4a6200508345ce8565d7
3
  size 5368