dougtrajano
commited on
Commit
·
0d69957
1
Parent(s):
80befa4
Model save
Browse files- .gitattributes.sagemaker-uploaded +0 -0
- last-checkpoint/config.json +0 -43
- 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 -64
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/vocab.txt +0 -0
- pytorch_model.bin +1 -1
.gitattributes.sagemaker-uploaded
DELETED
File without changes
|
last-checkpoint/config.json
DELETED
@@ -1,43 +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": "INDIVIDUAL",
|
14 |
-
"1": "GROUP",
|
15 |
-
"2": "OTHER"
|
16 |
-
},
|
17 |
-
"initializer_range": 0.02,
|
18 |
-
"intermediate_size": 3072,
|
19 |
-
"label2id": {
|
20 |
-
"GROUP": 1,
|
21 |
-
"INDIVIDUAL": 0,
|
22 |
-
"OTHER": 2
|
23 |
-
},
|
24 |
-
"layer_norm_eps": 1e-12,
|
25 |
-
"max_position_embeddings": 512,
|
26 |
-
"model_type": "bert",
|
27 |
-
"num_attention_heads": 12,
|
28 |
-
"num_hidden_layers": 12,
|
29 |
-
"output_past": true,
|
30 |
-
"pad_token_id": 0,
|
31 |
-
"pooler_fc_size": 768,
|
32 |
-
"pooler_num_attention_heads": 12,
|
33 |
-
"pooler_num_fc_layers": 3,
|
34 |
-
"pooler_size_per_head": 128,
|
35 |
-
"pooler_type": "first_token_transform",
|
36 |
-
"position_embedding_type": "absolute",
|
37 |
-
"problem_type": "single_label_classification",
|
38 |
-
"torch_dtype": "float32",
|
39 |
-
"transformers_version": "4.26.1",
|
40 |
-
"type_vocab_size": 2,
|
41 |
-
"use_cache": true,
|
42 |
-
"vocab_size": 29794
|
43 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:56b29211e81c9a9d6de50acaacf033257a07b39fbf6bca7b3a554402164602b9
|
3 |
-
size 1426051
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:d5875ede08581c6a7c4f42597abf0516127f62c0d600435d55cb6a234b64b647
|
3 |
-
size 435772781
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:ff95b3256971a16ca26e0f55a2d8f88e9791ca1c313de023eb6b33aef980ab12
|
3 |
-
size 14503
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:3f45df0dbd086ae79f78d4478838f922543c837fa7a1de0e03ffb71be543bc53
|
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
@@ -1,64 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 0.7603304380457284,
|
3 |
-
"best_model_checkpoint": "/opt/ml/checkpoints/toxicity-target-type-identification-2023-02-13-13-22-05-747/model/checkpoint-355",
|
4 |
-
"epoch": 3.0,
|
5 |
-
"global_step": 1065,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 1.0,
|
12 |
-
"eval_accuracy": 0.7505285412262156,
|
13 |
-
"eval_f1": 0.7603304380457284,
|
14 |
-
"eval_loss": 0.700143575668335,
|
15 |
-
"eval_precision": 0.7813181118720665,
|
16 |
-
"eval_recall": 0.7505285412262156,
|
17 |
-
"eval_runtime": 5.4125,
|
18 |
-
"eval_samples_per_second": 174.779,
|
19 |
-
"eval_steps_per_second": 21.986,
|
20 |
-
"step": 355
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 1.41,
|
24 |
-
"learning_rate": 3.766830354166815e-05,
|
25 |
-
"loss": 0.7919,
|
26 |
-
"step": 500
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 2.0,
|
30 |
-
"eval_accuracy": 0.7505285412262156,
|
31 |
-
"eval_f1": 0.745221599691193,
|
32 |
-
"eval_loss": 1.095289707183838,
|
33 |
-
"eval_precision": 0.758963982756652,
|
34 |
-
"eval_recall": 0.7505285412262156,
|
35 |
-
"eval_runtime": 5.6768,
|
36 |
-
"eval_samples_per_second": 166.643,
|
37 |
-
"eval_steps_per_second": 20.963,
|
38 |
-
"step": 710
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 2.82,
|
42 |
-
"learning_rate": 3.581272208641356e-05,
|
43 |
-
"loss": 0.5218,
|
44 |
-
"step": 1000
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 3.0,
|
48 |
-
"eval_accuracy": 0.7484143763213531,
|
49 |
-
"eval_f1": 0.7550927022068308,
|
50 |
-
"eval_loss": 1.4217394590377808,
|
51 |
-
"eval_precision": 0.7688482844579471,
|
52 |
-
"eval_recall": 0.7484143763213531,
|
53 |
-
"eval_runtime": 5.7254,
|
54 |
-
"eval_samples_per_second": 165.23,
|
55 |
-
"eval_steps_per_second": 20.785,
|
56 |
-
"step": 1065
|
57 |
-
}
|
58 |
-
],
|
59 |
-
"max_steps": 10650,
|
60 |
-
"num_train_epochs": 30,
|
61 |
-
"total_flos": 415329154924194.0,
|
62 |
-
"trial_name": null,
|
63 |
-
"trial_params": null
|
64 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:29ea1e9a63ff6356100cc945f6ca8285154323a795ec0916bd9de37f42dc85eb
|
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 435772781
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ec383c18a5b94a5d739dec9c5befc670c3fc650f033ee271224cc462f76d529
|
3 |
size 435772781
|