Spaces:
Runtime error
Runtime error
Upload 8 files
Browse files- IndoLEM/config.json +37 -0
- IndoLEM/rng_state.pth +3 -0
- IndoLEM/scheduler.pt +3 -0
- IndoLEM/special_tokens_map.json +7 -0
- IndoLEM/tokenizer_config.json +16 -0
- IndoLEM/trainer_state.json +46 -0
- IndoLEM/training_args.bin +3 -0
- IndoLEM/vocab.txt +0 -0
IndoLEM/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_ids": 0,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "NEGATIVE",
|
15 |
+
"1": "POSITIVE"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"NEGATIVE": 0,
|
21 |
+
"POSITIVE": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"output_past": true,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"problem_type": "single_label_classification",
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.26.1",
|
34 |
+
"type_vocab_size": 2,
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 31923
|
37 |
+
}
|
IndoLEM/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93dad2ce3980a59fef8614f7987c06e7501adf814b7a39a31390d1c63677ef30
|
3 |
+
size 14575
|
IndoLEM/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa836a3f5a645d277a047ff8c8caadadf3ab389999a14a4e387acff293d79003
|
3 |
+
size 627
|
IndoLEM/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 |
+
}
|
IndoLEM/tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"name_or_path": "indolem/indobert-base-uncased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--indolem--indobert-base-uncased/snapshots/b6663c19a819c04798e7a93d681f9bc34ed57b4a/special_tokens_map.json",
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
IndoLEM/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5224806666374207,
|
3 |
+
"best_model_checkpoint": "my_awesome_model/checkpoint-600",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 600,
|
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": 0.7279549718574109,
|
13 |
+
"eval_f1": 0.7387387387387387,
|
14 |
+
"eval_loss": 0.5657743811607361,
|
15 |
+
"eval_precision": 0.7454545454545455,
|
16 |
+
"eval_recall": 0.7321428571428571,
|
17 |
+
"eval_runtime": 1.6855,
|
18 |
+
"eval_samples_per_second": 316.233,
|
19 |
+
"eval_steps_per_second": 20.172,
|
20 |
+
"step": 300
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.67,
|
24 |
+
"learning_rate": 2.5e-05,
|
25 |
+
"loss": 0.647,
|
26 |
+
"step": 500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"eval_accuracy": 0.7467166979362101,
|
31 |
+
"eval_f1": 0.7893915756630265,
|
32 |
+
"eval_loss": 0.5224806666374207,
|
33 |
+
"eval_precision": 0.7008310249307479,
|
34 |
+
"eval_recall": 0.9035714285714286,
|
35 |
+
"eval_runtime": 1.6655,
|
36 |
+
"eval_samples_per_second": 320.027,
|
37 |
+
"eval_steps_per_second": 20.414,
|
38 |
+
"step": 600
|
39 |
+
}
|
40 |
+
],
|
41 |
+
"max_steps": 3000,
|
42 |
+
"num_train_epochs": 10,
|
43 |
+
"total_flos": 665583608968200.0,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": null
|
46 |
+
}
|
IndoLEM/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51010a5660d7cb7283e620a00142cea6e47bb34e06792d6df1442d216a0989b9
|
3 |
+
size 3515
|
IndoLEM/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|