Upload ./ with huggingface_hub (#1)
Browse files- Upload ./ with huggingface_hub (bd985d1e855ad0d9c313e3c424c8b4479245aacf)
- config.json +50 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- trainer_state.json +60 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dbmdz/bert-base-turkish-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7",
|
20 |
+
"8": "LABEL_8",
|
21 |
+
"9": "LABEL_9"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"Alakasiz": 0,
|
27 |
+
"Barinma": 1,
|
28 |
+
"Elektronik": 2,
|
29 |
+
"Giysi": 3,
|
30 |
+
"Kurtarma": 4,
|
31 |
+
"Lojistik": 5,
|
32 |
+
"Saglik": 6,
|
33 |
+
"Su": 7,
|
34 |
+
"Yagma": 8,
|
35 |
+
"Yemek": 9
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-12,
|
38 |
+
"max_position_embeddings": 512,
|
39 |
+
"model_type": "bert",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_hidden_layers": 12,
|
42 |
+
"pad_token_id": 0,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"problem_type": "multi_label_classification",
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.26.0",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 32000
|
50 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c71e4faa31278de27855a0444e6b9c31f72b4428a4a32b4707d05b065f10ebab
|
3 |
+
size 885118085
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac401c37b92e4a898d30e588532ecd94dfc675813affd3d009528c029b749b9e
|
3 |
+
size 442572917
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44f4945f6e3efe7883e411d8aab40b94f06b6a1eb74b29e134c776a5ea08ae28
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa0ed8d002b2243afe806ae75b93cda8eded403655be119f18957bb332a19459
|
3 |
+
size 627
|
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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 512,
|
7 |
+
"model_max_length": 512,
|
8 |
+
"name_or_path": "dbmdz/bert-base-turkish-cased",
|
9 |
+
"never_split": null,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.12779545783996582,
|
3 |
+
"best_model_checkpoint": "turkish_multilabel_intent_bert-base-turkish-cased/checkpoint-1392",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 1392,
|
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_loss": 0.15027593076229095,
|
13 |
+
"eval_runtime": 0.4945,
|
14 |
+
"eval_samples_per_second": 1249.718,
|
15 |
+
"eval_steps_per_second": 78.866,
|
16 |
+
"step": 348
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.44,
|
20 |
+
"learning_rate": 3.2040229885057474e-05,
|
21 |
+
"loss": 0.1951,
|
22 |
+
"step": 500
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"eval_loss": 0.1329057365655899,
|
27 |
+
"eval_runtime": 0.4918,
|
28 |
+
"eval_samples_per_second": 1256.527,
|
29 |
+
"eval_steps_per_second": 79.295,
|
30 |
+
"step": 696
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.87,
|
34 |
+
"learning_rate": 1.4080459770114942e-05,
|
35 |
+
"loss": 0.1077,
|
36 |
+
"step": 1000
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"eval_loss": 0.12863321602344513,
|
41 |
+
"eval_runtime": 0.4914,
|
42 |
+
"eval_samples_per_second": 1257.609,
|
43 |
+
"eval_steps_per_second": 79.364,
|
44 |
+
"step": 1044
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 4.0,
|
48 |
+
"eval_loss": 0.12779545783996582,
|
49 |
+
"eval_runtime": 0.4919,
|
50 |
+
"eval_samples_per_second": 1256.296,
|
51 |
+
"eval_steps_per_second": 79.281,
|
52 |
+
"step": 1392
|
53 |
+
}
|
54 |
+
],
|
55 |
+
"max_steps": 1392,
|
56 |
+
"num_train_epochs": 4,
|
57 |
+
"total_flos": 1461686896158720.0,
|
58 |
+
"trial_name": null,
|
59 |
+
"trial_params": null
|
60 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcb14a65982643bd4223a5be1bd3c0b1268ede3f0b43504790b6cf584f25ff84
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|