nicholasKluge
commited on
Commit
•
9c46d58
1
Parent(s):
966f263
Upload folder using huggingface_hub
Browse files- config.json +38 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +81 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "neuralmind/bert-base-portuguese-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"output_past": true,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"pooler_fc_size": 768,
|
28 |
+
"pooler_num_attention_heads": 12,
|
29 |
+
"pooler_num_fc_layers": 3,
|
30 |
+
"pooler_size_per_head": 128,
|
31 |
+
"pooler_type": "first_token_transform",
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.42.0.dev0",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 29794
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2af2b8b270ed2ee1e5fa82a9a38d765e2bd90bfcc3fb4408996ba395cbff91b1
|
3 |
+
size 435719148
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b2710ee88a077f932a59522d46894ec0882bf630b5a7012a463f4fca6aa181f
|
3 |
+
size 871559418
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90fa3723803b0272e488445273817d00acad34ef4842301ab7f710c408f33d70
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a1774c9bd9cd996e631c43160d37a9708272ec22c65f4b1c68fcd6f667de9f2
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.8626609442060085,
|
5 |
+
"eval_steps": 300,
|
6 |
+
"global_step": 900,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.2875536480686696,
|
13 |
+
"grad_norm": 0.001025281846523285,
|
14 |
+
"learning_rate": 3.3333333333333335e-05,
|
15 |
+
"loss": 0.0089,
|
16 |
+
"step": 300
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.2875536480686696,
|
20 |
+
"eval_accuracy": 1.0,
|
21 |
+
"eval_loss": 0.0007540204096585512,
|
22 |
+
"eval_runtime": 2.866,
|
23 |
+
"eval_samples_per_second": 289.256,
|
24 |
+
"eval_steps_per_second": 9.072,
|
25 |
+
"step": 300
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.575107296137339,
|
29 |
+
"grad_norm": 0.0004946357221342623,
|
30 |
+
"learning_rate": 1.6666666666666667e-05,
|
31 |
+
"loss": 0.0001,
|
32 |
+
"step": 600
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.575107296137339,
|
36 |
+
"eval_accuracy": 1.0,
|
37 |
+
"eval_loss": 0.00020219432190060616,
|
38 |
+
"eval_runtime": 2.8542,
|
39 |
+
"eval_samples_per_second": 290.45,
|
40 |
+
"eval_steps_per_second": 9.109,
|
41 |
+
"step": 600
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.8626609442060085,
|
45 |
+
"grad_norm": 0.00040382734732702374,
|
46 |
+
"learning_rate": 0.0,
|
47 |
+
"loss": 0.0,
|
48 |
+
"step": 900
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.8626609442060085,
|
52 |
+
"eval_accuracy": 1.0,
|
53 |
+
"eval_loss": 0.0003535090072546154,
|
54 |
+
"eval_runtime": 2.8648,
|
55 |
+
"eval_samples_per_second": 289.378,
|
56 |
+
"eval_steps_per_second": 9.076,
|
57 |
+
"step": 900
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"logging_steps": 300,
|
61 |
+
"max_steps": 900,
|
62 |
+
"num_input_tokens_seen": 0,
|
63 |
+
"num_train_epochs": 4,
|
64 |
+
"save_steps": 300,
|
65 |
+
"stateful_callbacks": {
|
66 |
+
"TrainerControl": {
|
67 |
+
"args": {
|
68 |
+
"should_epoch_stop": false,
|
69 |
+
"should_evaluate": false,
|
70 |
+
"should_log": false,
|
71 |
+
"should_save": true,
|
72 |
+
"should_training_stop": true
|
73 |
+
},
|
74 |
+
"attributes": {}
|
75 |
+
}
|
76 |
+
},
|
77 |
+
"total_flos": 0.0,
|
78 |
+
"train_batch_size": 32,
|
79 |
+
"trial_name": null,
|
80 |
+
"trial_params": null
|
81 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9c9f4aa432f7e8b395206c0f613c02a2e0bbe63620e349b2295dfb6fe463b78
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|