Harish Tayyar Madabushi
commited on
Commit
•
2178d2e
1
Parent(s):
eecaa82
added model
Browse files- config.json +31 -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 +86 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"directionality": "bidi",
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"problem_type": "single_label_classification",
|
27 |
+
"transformers_version": "4.7.0.dev0",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 119547
|
31 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c259ccd83859fcee1bdc31053656156a8ee2d140b1912e772df92ee26d35015
|
3 |
+
size 1422961979
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdddfc45dd7cebdbbaa46d2684846a8b481e8f675be475e3bad6f3357f6f41a2
|
3 |
+
size 711507294
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a64cfaf6fb53d9f4b2303ff8ef2e61e56806dba25dcf36ebc668de22c442614
|
3 |
+
size 14646
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a56402f19f5b0e977c32c8fde49dbf17268d9ac8f1705c8694805e530de8095
|
3 |
+
size 623
|
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": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased"}
|
trainer_state.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6961807093052775,
|
3 |
+
"best_model_checkpoint": "OUTPUT/bert-base-multilingual-cased/FalseTrue-0/1/checkpoint-259",
|
4 |
+
"epoch": 7.0,
|
5 |
+
"global_step": 259,
|
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": 0.6739926934242249,
|
13 |
+
"eval_f1": 0.6497000267492071,
|
14 |
+
"eval_loss": 0.7328909635543823,
|
15 |
+
"eval_runtime": 0.8296,
|
16 |
+
"eval_samples_per_second": 329.057,
|
17 |
+
"eval_steps_per_second": 42.187,
|
18 |
+
"step": 37
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.6556776762008667,
|
23 |
+
"eval_f1": 0.6136253516088647,
|
24 |
+
"eval_loss": 1.3869595527648926,
|
25 |
+
"eval_runtime": 0.8297,
|
26 |
+
"eval_samples_per_second": 329.048,
|
27 |
+
"eval_steps_per_second": 42.186,
|
28 |
+
"step": 74
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 3.0,
|
32 |
+
"eval_accuracy": 0.6739926934242249,
|
33 |
+
"eval_f1": 0.6567661423596487,
|
34 |
+
"eval_loss": 1.3877439498901367,
|
35 |
+
"eval_runtime": 0.8294,
|
36 |
+
"eval_samples_per_second": 329.156,
|
37 |
+
"eval_steps_per_second": 42.199,
|
38 |
+
"step": 111
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 4.0,
|
42 |
+
"eval_accuracy": 0.6703296899795532,
|
43 |
+
"eval_f1": 0.6620879120879122,
|
44 |
+
"eval_loss": 1.5405205488204956,
|
45 |
+
"eval_runtime": 0.8255,
|
46 |
+
"eval_samples_per_second": 330.712,
|
47 |
+
"eval_steps_per_second": 42.399,
|
48 |
+
"step": 148
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 5.0,
|
52 |
+
"eval_accuracy": 0.6996337175369263,
|
53 |
+
"eval_f1": 0.680666672762239,
|
54 |
+
"eval_loss": 1.6668964624404907,
|
55 |
+
"eval_runtime": 0.8301,
|
56 |
+
"eval_samples_per_second": 328.874,
|
57 |
+
"eval_steps_per_second": 42.163,
|
58 |
+
"step": 185
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 6.0,
|
62 |
+
"eval_accuracy": 0.6959707140922546,
|
63 |
+
"eval_f1": 0.683264100001968,
|
64 |
+
"eval_loss": 1.7306524515151978,
|
65 |
+
"eval_runtime": 0.829,
|
66 |
+
"eval_samples_per_second": 329.311,
|
67 |
+
"eval_steps_per_second": 42.219,
|
68 |
+
"step": 222
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 7.0,
|
72 |
+
"eval_accuracy": 0.7069597244262695,
|
73 |
+
"eval_f1": 0.6961807093052775,
|
74 |
+
"eval_loss": 1.8631714582443237,
|
75 |
+
"eval_runtime": 0.8263,
|
76 |
+
"eval_samples_per_second": 330.372,
|
77 |
+
"eval_steps_per_second": 42.355,
|
78 |
+
"step": 259
|
79 |
+
}
|
80 |
+
],
|
81 |
+
"max_steps": 333,
|
82 |
+
"num_train_epochs": 9,
|
83 |
+
"total_flos": 1112956693051392.0,
|
84 |
+
"trial_name": null,
|
85 |
+
"trial_params": null
|
86 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:439bc5b94913b25d977dd272c545c8daa9ef0c9286ce1b45060b613bf8e9a494
|
3 |
+
size 2479
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|