dougtrajano
commited on
Commit
•
4c01941
1
Parent(s):
7a1c522
Model save
Browse files- last-checkpoint/config.json +0 -40
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/special_tokens_map.json +0 -7
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -16
- last-checkpoint/trainer_state.json +0 -88
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/vocab.txt +0 -0
- pytorch_model.bin +1 -1
last-checkpoint/config.json
DELETED
@@ -1,40 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "neuralmind/bert-base-portuguese-cased",
|
3 |
-
"architectures": [
|
4 |
-
"ToxicityTypeForSequenceClassification"
|
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": "UNTARGETED",
|
14 |
-
"1": "TARGETED INSULT"
|
15 |
-
},
|
16 |
-
"initializer_range": 0.02,
|
17 |
-
"intermediate_size": 3072,
|
18 |
-
"label2id": {
|
19 |
-
"TARGETED INSULT": 1,
|
20 |
-
"UNTARGETED": 0
|
21 |
-
},
|
22 |
-
"layer_norm_eps": 1e-12,
|
23 |
-
"max_position_embeddings": 512,
|
24 |
-
"model_type": "bert",
|
25 |
-
"num_attention_heads": 12,
|
26 |
-
"num_hidden_layers": 12,
|
27 |
-
"output_past": true,
|
28 |
-
"pad_token_id": 0,
|
29 |
-
"pooler_fc_size": 768,
|
30 |
-
"pooler_num_attention_heads": 12,
|
31 |
-
"pooler_num_fc_layers": 3,
|
32 |
-
"pooler_size_per_head": 128,
|
33 |
-
"pooler_type": "first_token_transform",
|
34 |
-
"position_embedding_type": "absolute",
|
35 |
-
"torch_dtype": "float32",
|
36 |
-
"transformers_version": "4.26.0",
|
37 |
-
"type_vocab_size": 2,
|
38 |
-
"use_cache": true,
|
39 |
-
"vocab_size": 29794
|
40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:ae1f20a5dd95d74b92d0fbd2b3d729d317e72cb4b30acf98e2fe3430984998eb
|
3 |
-
size 871513885
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7054c1135eb4d88629f5742261fc4be64a83155f14009e3184699de050a323f6
|
3 |
-
size 435769709
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:30d26db9fde6f1200cb35b02d4feec7f2c5f9df5a195b8befa619cd6e0ff1757
|
3 |
-
size 14503
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:418a9b4a7c7bf0006de027ceb40407fc5486b06fb4d17b5412d09664d5482ca2
|
3 |
-
size 623
|
|
|
|
|
|
|
|
last-checkpoint/special_tokens_map.json
DELETED
@@ -1,7 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"mask_token": "[MASK]",
|
4 |
-
"pad_token": "[PAD]",
|
5 |
-
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "[UNK]"
|
7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"do_basic_tokenize": true,
|
4 |
-
"do_lower_case": false,
|
5 |
-
"mask_token": "[MASK]",
|
6 |
-
"model_max_length": 1000000000000000019884624838656,
|
7 |
-
"name_or_path": "neuralmind/bert-base-portuguese-cased",
|
8 |
-
"never_split": null,
|
9 |
-
"pad_token": "[PAD]",
|
10 |
-
"sep_token": "[SEP]",
|
11 |
-
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json",
|
12 |
-
"strip_accents": null,
|
13 |
-
"tokenize_chinese_chars": true,
|
14 |
-
"tokenizer_class": "BertTokenizer",
|
15 |
-
"unk_token": "[UNK]"
|
16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,88 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 0.687234433366349,
|
3 |
-
"best_model_checkpoint": "/opt/ml/checkpoints/toxicity-target-classification-2023-02-13-11-33-34-745/model/checkpoint-1074",
|
4 |
-
"epoch": 4.0,
|
5 |
-
"global_step": 2148,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.93,
|
12 |
-
"learning_rate": 4.0444740261144315e-05,
|
13 |
-
"loss": 0.633,
|
14 |
-
"step": 500
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 1.0,
|
18 |
-
"eval_accuracy": 0.691933240611961,
|
19 |
-
"eval_f1": 0.580523179491889,
|
20 |
-
"eval_loss": 0.6039695739746094,
|
21 |
-
"eval_precision": 0.6350591049567901,
|
22 |
-
"eval_recall": 0.691933240611961,
|
23 |
-
"eval_runtime": 8.9923,
|
24 |
-
"eval_samples_per_second": 159.915,
|
25 |
-
"eval_steps_per_second": 20.017,
|
26 |
-
"step": 537
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 1.86,
|
30 |
-
"learning_rate": 3.9149264916456794e-05,
|
31 |
-
"loss": 0.5915,
|
32 |
-
"step": 1000
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 2.0,
|
36 |
-
"eval_accuracy": 0.6863699582753825,
|
37 |
-
"eval_f1": 0.687234433366349,
|
38 |
-
"eval_loss": 0.6110407710075378,
|
39 |
-
"eval_precision": 0.6881518808333719,
|
40 |
-
"eval_recall": 0.6863699582753825,
|
41 |
-
"eval_runtime": 9.2368,
|
42 |
-
"eval_samples_per_second": 155.681,
|
43 |
-
"eval_steps_per_second": 19.487,
|
44 |
-
"step": 1074
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 2.79,
|
48 |
-
"learning_rate": 3.785378957176927e-05,
|
49 |
-
"loss": 0.4584,
|
50 |
-
"step": 1500
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 3.0,
|
54 |
-
"eval_accuracy": 0.6933240611961057,
|
55 |
-
"eval_f1": 0.6605600739460796,
|
56 |
-
"eval_loss": 0.7104145288467407,
|
57 |
-
"eval_precision": 0.6605071455841258,
|
58 |
-
"eval_recall": 0.6933240611961057,
|
59 |
-
"eval_runtime": 9.2844,
|
60 |
-
"eval_samples_per_second": 154.883,
|
61 |
-
"eval_steps_per_second": 19.387,
|
62 |
-
"step": 1611
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 3.72,
|
66 |
-
"learning_rate": 3.655831422708176e-05,
|
67 |
-
"loss": 0.3564,
|
68 |
-
"step": 2000
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 4.0,
|
72 |
-
"eval_accuracy": 0.6168289290681502,
|
73 |
-
"eval_f1": 0.6306803768959991,
|
74 |
-
"eval_loss": 0.981565535068512,
|
75 |
-
"eval_precision": 0.6670641987183653,
|
76 |
-
"eval_recall": 0.6168289290681502,
|
77 |
-
"eval_runtime": 9.261,
|
78 |
-
"eval_samples_per_second": 155.275,
|
79 |
-
"eval_steps_per_second": 19.436,
|
80 |
-
"step": 2148
|
81 |
-
}
|
82 |
-
],
|
83 |
-
"max_steps": 16110,
|
84 |
-
"num_train_epochs": 30,
|
85 |
-
"total_flos": 851104652991120.0,
|
86 |
-
"trial_name": null,
|
87 |
-
"trial_params": null
|
88 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:8acb02433984d2e11aaaabc91c31689c394d0774abcace260233569cc66f1a91
|
3 |
-
size 3695
|
|
|
|
|
|
|
|
last-checkpoint/vocab.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 435769709
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2494ada141fc9b43ee71dd958e772766aedc9a020ce7e6f7b3a5de7cbcc44948
|
3 |
size 435769709
|