kashparty commited on
Commit
89b0710
·
verified ·
1 Parent(s): 34ed881

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,44 +1,32 @@
1
  {
2
- "_name_or_path": "microsoft/deberta-v3-base",
 
3
  "architectures": [
4
- "DebertaV2ForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "hidden_act": "gelu",
8
- "hidden_dropout_prob": 0.1,
9
- "hidden_size": 768,
10
  "id2label": {
11
  "0": "NEGATIVE",
12
  "1": "POSITIVE"
13
  },
14
  "initializer_range": 0.02,
15
- "intermediate_size": 3072,
16
  "label2id": {
17
  "NEGATIVE": 0,
18
  "POSITIVE": 1
19
  },
20
- "layer_norm_eps": 1e-07,
21
- "legacy": true,
22
  "max_position_embeddings": 512,
23
- "max_relative_positions": -1,
24
- "model_type": "deberta-v2",
25
- "norm_rel_ebd": "layer_norm",
26
- "num_attention_heads": 12,
27
- "num_hidden_layers": 12,
28
  "pad_token_id": 0,
29
- "pooler_dropout": 0,
30
- "pooler_hidden_act": "gelu",
31
- "pooler_hidden_size": 768,
32
- "pos_att_type": [
33
- "p2c",
34
- "c2p"
35
- ],
36
- "position_biased_input": false,
37
- "position_buckets": 256,
38
- "relative_attention": true,
39
- "share_att_key": true,
40
  "torch_dtype": "float32",
41
  "transformers_version": "4.48.3",
42
- "type_vocab_size": 0,
43
- "vocab_size": 128100
44
  }
 
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": "NEGATIVE",
13
  "1": "POSITIVE"
14
  },
15
  "initializer_range": 0.02,
 
16
  "label2id": {
17
  "NEGATIVE": 0,
18
  "POSITIVE": 1
19
  },
 
 
20
  "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
 
 
24
  "pad_token_id": 0,
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
 
 
 
 
 
 
 
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.48.3",
31
+ "vocab_size": 30522
 
32
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8e055e2d2a8df5153304de9ad47f6d53ad9794fc63a4e72e3fb94230ef5c5c4
3
- size 737719272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7863b147a1d82484dfc41f8ee5db88e042b6f8c467bac3c3d9963ad3b58c7c
3
+ size 267832560
runs/Feb26_09-17-09_e30534139527/events.out.tfevents.1740561430.e30534139527.708.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fcdcd394a94c26a1b1df0fc714177d596509664c4ef149ef4638767f60402cd
3
+ size 4184
runs/Feb26_09-18-31_e30534139527/events.out.tfevents.1740561512.e30534139527.4766.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b483e599e02241a6fbc1232dde67e5cd80128cea941051c3914d6efafccebc99
3
+ size 6193
special_tokens_map.json CHANGED
@@ -1,30 +1,7 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<unk>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,34 +1,39 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
7
- "content": "<unk>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
13
  },
14
- "1": {
15
- "content": "<s>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
19
  "single_word": false,
20
  "special": true
21
  },
22
- "2": {
23
- "content": "</s>",
24
  "lstrip": false,
25
  "normalized": false,
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
29
  },
30
- "32000": {
31
- "content": "[PAD]",
 
 
 
 
 
 
 
 
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
@@ -36,18 +41,16 @@
36
  "special": true
37
  }
38
  },
39
- "additional_special_tokens": [],
40
- "bos_token": "<s>",
41
- "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
42
  "clean_up_tokenization_spaces": false,
43
- "eos_token": "</s>",
 
44
  "extra_special_tokens": {},
45
- "legacy": false,
46
- "model_max_length": 1000000000000000019884624838656,
47
  "pad_token": "[PAD]",
48
- "sp_model_kwargs": {},
49
- "spaces_between_special_tokens": false,
50
- "tokenizer_class": "LlamaTokenizer",
51
- "unk_token": "<unk>",
52
- "use_default_system_prompt": false
53
  }
 
1
  {
 
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
+ "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
41
  "special": true
42
  }
43
  },
 
 
 
44
  "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
  "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
  "pad_token": "[PAD]",
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 sha256:9d1f1d7bc3a0e7dc24820caded9b1473bf4958a6008d476a92f615fa4901e2ce
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46e0dc04402817bf5c5ab0778956d11da1dcc2121e8f6f1c004ec7b65840b45e
3
  size 5304