ssdatar commited on
Commit
d7e39ce
1 Parent(s): 86c11cb

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,32 +1,75 @@
1
  {
2
- "_name_or_path": "facebook/opt-125m",
3
- "_remove_final_layer_norm": false,
4
- "activation_dropout": 0.0,
5
- "activation_function": "relu",
 
6
  "architectures": [
7
- "OPTForCausalLM"
8
  ],
9
- "attention_dropout": 0.0,
10
- "bos_token_id": 2,
11
- "do_layer_norm_before": true,
 
 
 
 
 
 
 
12
  "dropout": 0.1,
13
- "enable_bias": true,
 
 
 
 
14
  "eos_token_id": 2,
15
- "ffn_dim": 3072,
16
- "hidden_size": 768,
 
 
 
 
 
 
17
  "init_std": 0.02,
18
- "is_decoder": true,
19
- "layer_norm_elementwise_affine": true,
20
- "layerdrop": 0.0,
21
- "max_position_embeddings": 2048,
22
- "model_type": "opt",
23
- "num_attention_heads": 12,
24
- "num_hidden_layers": 12,
 
 
 
 
 
 
25
  "pad_token_id": 1,
26
- "prefix": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "torch_dtype": "float32",
28
- "transformers_version": "4.33.3",
29
  "use_cache": true,
30
- "vocab_size": 50272,
31
- "word_embed_proj_dim": 768
32
  }
 
1
  {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
  "architectures": [
8
+ "BartForConditionalGeneration"
9
  ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
  "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
  "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
  "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
  "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
  "torch_dtype": "float32",
72
+ "transformers_version": "4.35.2",
73
  "use_cache": true,
74
+ "vocab_size": 50265
 
75
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d13f1256897dd7bcb800d5f14964c580f24a0581946c77f969b81b7808d0ed2
3
+ size 557912620
runs/Nov26_00-39-38_8bd8a0d86bde/events.out.tfevents.1700959189.8bd8a0d86bde.211.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695a7d5bd50d0ac58545a7b492381d5eff1a1d5c9570f70fa4ef149c8723bad1
3
+ size 5420
special_tokens_map.json CHANGED
@@ -1,30 +1,15 @@
1
  {
2
- "bos_token": {
3
- "content": "</s>",
4
- "lstrip": false,
 
 
 
5
  "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<pad>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "</s>",
25
- "lstrip": false,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
  "normalized": true,
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea44f4e9418dcfdd7c6f0ac9f445d0405e3cd75423f106c5d0bae9ff91eb8db5
3
- size 2108883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e0910cf92ee52b11fd3009223688c212d0a674fef7ac2421c1b4f261958a24
3
+ size 2108867
tokenizer_config.json CHANGED
@@ -1,40 +1,57 @@
1
  {
2
- "add_bos_token": true,
3
  "add_prefix_space": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "</s>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
12
  "clean_up_tokenization_spaces": true,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
  "errors": "replace",
22
- "model_max_length": 1000000000000000019884624838656,
23
- "pad_token": {
24
- "__type": "AddedToken",
25
- "content": "<pad>",
26
- "lstrip": false,
27
- "normalized": true,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- "tokenizer_class": "GPT2Tokenizer",
32
- "unk_token": {
33
- "__type": "AddedToken",
34
- "content": "</s>",
35
- "lstrip": false,
36
- "normalized": true,
37
- "rstrip": false,
38
- "single_word": false
39
- }
40
  }
 
1
  {
 
2
  "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
  },
45
+ "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
 
 
 
 
 
 
49
  "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e95e887eea742365588161a06974222af3ad866805f56f036bb87dbe7675c029
3
- size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b87bb09b50710f20b775f389da49005ef83539ab8f802e931cd1810c4dfc35
3
+ size 4536