nicholasKluge commited on
Commit
90f690b
1 Parent(s): c95c352

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nicholasKluge/TeenyTinyLlama-162m",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "MUNDO",
13
+ "1": "ESPORTES",
14
+ "2": "NEG\u00d3CIOS",
15
+ "3": "TECNOLOGIA"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "ESPORTES": 1,
21
+ "MUNDO": 0,
22
+ "NEG\u00d3CIOS": 2,
23
+ "TECNOLOGIA": 3
24
+ },
25
+ "max_position_embeddings": 2048,
26
+ "model_type": "llama",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "num_key_value_heads": 12,
30
+ "pad_token_id": 3,
31
+ "pretraining_tp": 1,
32
+ "problem_type": "single_label_classification",
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": null,
35
+ "rope_theta": 10000.0,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.35.2",
39
+ "use_cache": false,
40
+ "vocab_size": 32000
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:643b5d8411e0ed909ec869f18ead81defc5240f9e04d2a1ef9eee4551d789bd7
3
+ size 551390232
runs/Dec28_14-20-19_3048be2ae52a/events.out.tfevents.1703773248.3048be2ae52a.285.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5edbb0d7a10a278e7804de777b23007a0d048e0fb82861c643db32b2f73576
3
+ size 7163
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "bos_token_id": 1,
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
40
+ "eos_token_id": 2,
41
+ "legacy": false,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
44
+ "pad_token_id": 3,
45
+ "padding_side": "right",
46
+ "sp_model_kwargs": {},
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "unk_token_id": 0,
50
+ "use_default_system_prompt": false
51
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd4e3866e4bd7e5dc0d76102d5ffa929713676eb084b5d71462772bf0da1329e
3
+ size 4664