Amr Keleg
commited on
Commit
•
7cb5a13
1
Parent(s):
e2f6c87
Track the model files
Browse files- config.json +48 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +78 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "UBC-NLP/MARBERT",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2,
|
27 |
+
"LABEL_3": 3,
|
28 |
+
"LABEL_4": 4,
|
29 |
+
"LABEL_5": 5
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-12,
|
32 |
+
"max_position_embeddings": 512,
|
33 |
+
"model_type": "bert",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_layers": 12,
|
36 |
+
"pad_token_id": 0,
|
37 |
+
"pooler_fc_size": 768,
|
38 |
+
"pooler_num_attention_heads": 12,
|
39 |
+
"pooler_num_fc_layers": 3,
|
40 |
+
"pooler_size_per_head": 128,
|
41 |
+
"pooler_type": "first_token_transform",
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.26.1",
|
45 |
+
"type_vocab_size": 2,
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 100000
|
48 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2059e171b8ca906f726d479158ee4f07b65da57fdc9c29aaf26100d1d2ae122
|
3 |
+
size 1298159621
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91bf355a8399a307cd076db691b31d1a372fc086273e419228901f1c397f683a
|
3 |
+
size 649093613
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f113467ba153437377d3cca21247a1bf13d5ec4199ee15a4ce0dbae7ce2c1608
|
3 |
+
size 17641
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37a0fbb9478949421cddae7297acf773062e367b83de55aa1d3cf8ac35dd5ed9
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/project/6007993/elmadany/Models/MARBERT_17M/pytorch_verison/"}
|
trainer_state.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 795,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.38,
|
12 |
+
"eval_loss": 0.2512435019016266,
|
13 |
+
"eval_runtime": 8.34,
|
14 |
+
"eval_samples_per_second": 133.813,
|
15 |
+
"eval_steps_per_second": 4.197,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.75,
|
20 |
+
"eval_loss": 0.2268657237291336,
|
21 |
+
"eval_runtime": 8.3466,
|
22 |
+
"eval_samples_per_second": 133.707,
|
23 |
+
"eval_steps_per_second": 4.193,
|
24 |
+
"step": 200
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.13,
|
28 |
+
"eval_loss": 0.23051245510578156,
|
29 |
+
"eval_runtime": 8.3417,
|
30 |
+
"eval_samples_per_second": 133.786,
|
31 |
+
"eval_steps_per_second": 4.196,
|
32 |
+
"step": 300
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.51,
|
36 |
+
"eval_loss": 0.2245202660560608,
|
37 |
+
"eval_runtime": 8.337,
|
38 |
+
"eval_samples_per_second": 133.862,
|
39 |
+
"eval_steps_per_second": 4.198,
|
40 |
+
"step": 400
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 1.89,
|
44 |
+
"learning_rate": 1.8553459119496856e-05,
|
45 |
+
"loss": 0.2119,
|
46 |
+
"step": 500
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.89,
|
50 |
+
"eval_loss": 0.22478941082954407,
|
51 |
+
"eval_runtime": 8.3391,
|
52 |
+
"eval_samples_per_second": 133.828,
|
53 |
+
"eval_steps_per_second": 4.197,
|
54 |
+
"step": 500
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 2.26,
|
58 |
+
"eval_loss": 0.2384825348854065,
|
59 |
+
"eval_runtime": 8.3396,
|
60 |
+
"eval_samples_per_second": 133.819,
|
61 |
+
"eval_steps_per_second": 4.197,
|
62 |
+
"step": 600
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.64,
|
66 |
+
"eval_loss": 0.23830106854438782,
|
67 |
+
"eval_runtime": 8.3367,
|
68 |
+
"eval_samples_per_second": 133.866,
|
69 |
+
"eval_steps_per_second": 4.198,
|
70 |
+
"step": 700
|
71 |
+
}
|
72 |
+
],
|
73 |
+
"max_steps": 795,
|
74 |
+
"num_train_epochs": 3,
|
75 |
+
"total_flos": 6635087188033536.0,
|
76 |
+
"trial_name": null,
|
77 |
+
"trial_params": null
|
78 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:016e178b54b4499d7401b710ae361f0d803cad1f54a717ede8cfa3bf9199ee13
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|