upload final best orig model
Browse files- config.json +30 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +112 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BioM-ELECTRA-Large-SQuAD2-finetune-127-1/checkpoint-10565",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 1024,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "electra",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"summary_activation": "gelu",
|
22 |
+
"summary_last_dropout": 0.1,
|
23 |
+
"summary_type": "first",
|
24 |
+
"summary_use_proj": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.25.1",
|
27 |
+
"type_vocab_size": 2,
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 28895
|
30 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e12915f0e00bd9d16cecb714593fc6a3c602324a9a95c0fe2b35b57adb3f09fa
|
3 |
+
size 2659653861
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c34f6a88d4b1101e489636c23141760285744d693520518ec861423c8d8ab148
|
3 |
+
size 1329849649
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f49220eddcceec1d3dea2859cd418ba71f78be030b120fb84d6f51388ada0312
|
3 |
+
size 14503
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af3682473d4b1ed9440be1eaff0ca0d909753fe593d5e07cffe8d07e73dba3dc
|
3 |
+
size 559
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5abd4139a12ea51bd0adb84fd844d980a1c9427a66e0bd0e9073f92f047b911
|
3 |
+
size 623
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "BioM-ELECTRA-Large-SQuAD2-finetune-127-1/checkpoint-10565",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "ElectraTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 8452,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.24,
|
12 |
+
"learning_rate": 1.9059157595835306e-05,
|
13 |
+
"loss": 0.0116,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.47,
|
18 |
+
"learning_rate": 1.8118315191670613e-05,
|
19 |
+
"loss": 0.0759,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.71,
|
24 |
+
"learning_rate": 1.717557974443919e-05,
|
25 |
+
"loss": 0.2127,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.95,
|
30 |
+
"learning_rate": 1.6229058211074304e-05,
|
31 |
+
"loss": 0.0926,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.18,
|
36 |
+
"learning_rate": 1.5282536677709418e-05,
|
37 |
+
"loss": 0.1933,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.42,
|
42 |
+
"learning_rate": 1.4336015144344535e-05,
|
43 |
+
"loss": 0.0232,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.66,
|
48 |
+
"learning_rate": 1.3389493610979651e-05,
|
49 |
+
"loss": 0.0176,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.89,
|
54 |
+
"learning_rate": 1.2442972077614768e-05,
|
55 |
+
"loss": 0.0192,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 2.13,
|
60 |
+
"learning_rate": 1.1496450544249882e-05,
|
61 |
+
"loss": 0.0148,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.37,
|
66 |
+
"learning_rate": 1.0551822053951728e-05,
|
67 |
+
"loss": 0.013,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.6,
|
72 |
+
"learning_rate": 9.605300520586845e-06,
|
73 |
+
"loss": 0.019,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.84,
|
78 |
+
"learning_rate": 8.65877898722196e-06,
|
79 |
+
"loss": 0.0361,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 3.08,
|
84 |
+
"learning_rate": 7.714150496923806e-06,
|
85 |
+
"loss": 0.021,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 3.31,
|
90 |
+
"learning_rate": 6.767628963558922e-06,
|
91 |
+
"loss": 0.0146,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.55,
|
96 |
+
"learning_rate": 5.8211074301940376e-06,
|
97 |
+
"loss": 0.0071,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.79,
|
102 |
+
"learning_rate": 4.874585896829153e-06,
|
103 |
+
"loss": 0.0093,
|
104 |
+
"step": 8000
|
105 |
+
}
|
106 |
+
],
|
107 |
+
"max_steps": 10565,
|
108 |
+
"num_train_epochs": 5,
|
109 |
+
"total_flos": 4.709658898479514e+16,
|
110 |
+
"trial_name": null,
|
111 |
+
"trial_params": null
|
112 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:225a74f94dabc2a8cafc665441d4f0ed24428e6dd3d87eed4ca1029568e43afb
|
3 |
+
size 3503
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|