Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- adapter_config.json +42 -0
- added_tokens.json +3 -0
- head_config.json +14 -0
- optimizer.pt +3 -0
- pytorch_adapter.bin +3 -0
- pytorch_model_head.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +858 -0
- trainer_state.json +684 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
adapter_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"adapter_residual_before_ln": false,
|
4 |
+
"cross_adapter": false,
|
5 |
+
"dropout": 0.0,
|
6 |
+
"factorized_phm_W": true,
|
7 |
+
"factorized_phm_rule": false,
|
8 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
9 |
+
"init_weights": "bert",
|
10 |
+
"inv_adapter": null,
|
11 |
+
"inv_adapter_reduction_factor": null,
|
12 |
+
"is_parallel": false,
|
13 |
+
"learn_phm": true,
|
14 |
+
"leave_out": [],
|
15 |
+
"ln_after": false,
|
16 |
+
"ln_before": false,
|
17 |
+
"mh_adapter": false,
|
18 |
+
"non_linearity": "relu",
|
19 |
+
"original_ln_after": true,
|
20 |
+
"original_ln_before": true,
|
21 |
+
"output_adapter": true,
|
22 |
+
"phm_bias": true,
|
23 |
+
"phm_c_init": "normal",
|
24 |
+
"phm_dim": 4,
|
25 |
+
"phm_init_range": 0.0001,
|
26 |
+
"phm_layer": false,
|
27 |
+
"phm_rank": 1,
|
28 |
+
"reduction_factor": 16,
|
29 |
+
"residual_before_ln": true,
|
30 |
+
"scaling": 1.0,
|
31 |
+
"shared_W_phm": false,
|
32 |
+
"shared_phm_rule": true,
|
33 |
+
"use_gating": false
|
34 |
+
},
|
35 |
+
"config_id": "9076f36a74755ac4",
|
36 |
+
"hidden_size": 768,
|
37 |
+
"model_class": "DebertaV2ForMaskedLM",
|
38 |
+
"model_name": "microsoft/mdeberta-v3-base",
|
39 |
+
"model_type": "deberta-v2",
|
40 |
+
"name": "cc100",
|
41 |
+
"version": "adapters.1.0.0"
|
42 |
+
}
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 250101
|
3 |
+
}
|
head_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": null,
|
3 |
+
"hidden_size": 768,
|
4 |
+
"label2id": {
|
5 |
+
"LABEL_0": 0,
|
6 |
+
"LABEL_1": 1
|
7 |
+
},
|
8 |
+
"model_class": "DebertaV2ForMaskedLM",
|
9 |
+
"model_name": "microsoft/mdeberta-v3-base",
|
10 |
+
"model_type": "deberta-v2",
|
11 |
+
"name": null,
|
12 |
+
"num_labels": 2,
|
13 |
+
"version": "adapters.1.0.0"
|
14 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4b2ac40c490f24b08af203de538b2d98547cf661afb97df056030b500ab2506
|
3 |
+
size 11936954
|
pytorch_adapter.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01906d37cd23ed3f57cc4421743e0f5843af4615c74d1a192df9a6e9fbe5af93
|
3 |
+
size 3595558
|
pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a84c38c708ef6b205bb9ed175d57d56d2dbc28e7a192bd90c17288eff4eb6979
|
3 |
+
size 774447414
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:138729ce744467e9dfbb78e2bfec3d696c194fe33770c7393c84a4c190c050d2
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1779cc7b17c6f5ed33c2a8a77c4ae41b3c2418eee1200bcb469135e32da88b2
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": {
|
9 |
+
"content": "[UNK]",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
}
|
15 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
|
3 |
+
size 4305025
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ddbe35b768b22d6cd0d61a0a88ea3a188b7c00bbb7b825f9f247cf0b79c2365
|
3 |
+
size 16350764
|
tokenizer_config.json
ADDED
@@ -0,0 +1,858 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "▁<extra_id_99>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"250002": {
|
44 |
+
"content": "▁<extra_id_98>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"250003": {
|
52 |
+
"content": "▁<extra_id_97>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"250004": {
|
60 |
+
"content": "▁<extra_id_96>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"250005": {
|
68 |
+
"content": "▁<extra_id_95>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"250006": {
|
76 |
+
"content": "▁<extra_id_94>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"250007": {
|
84 |
+
"content": "▁<extra_id_93>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"250008": {
|
92 |
+
"content": "▁<extra_id_92>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"250009": {
|
100 |
+
"content": "▁<extra_id_91>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"250010": {
|
108 |
+
"content": "▁<extra_id_90>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"250011": {
|
116 |
+
"content": "▁<extra_id_89>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"250012": {
|
124 |
+
"content": "▁<extra_id_88>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"250013": {
|
132 |
+
"content": "▁<extra_id_87>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"250014": {
|
140 |
+
"content": "▁<extra_id_86>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"250015": {
|
148 |
+
"content": "▁<extra_id_85>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"250016": {
|
156 |
+
"content": "▁<extra_id_84>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"250017": {
|
164 |
+
"content": "▁<extra_id_83>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"250018": {
|
172 |
+
"content": "▁<extra_id_82>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"250019": {
|
180 |
+
"content": "▁<extra_id_81>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"250020": {
|
188 |
+
"content": "▁<extra_id_80>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"250021": {
|
196 |
+
"content": "▁<extra_id_79>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"250022": {
|
204 |
+
"content": "▁<extra_id_78>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"250023": {
|
212 |
+
"content": "▁<extra_id_77>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"250024": {
|
220 |
+
"content": "▁<extra_id_76>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
"250025": {
|
228 |
+
"content": "▁<extra_id_75>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": false
|
234 |
+
},
|
235 |
+
"250026": {
|
236 |
+
"content": "▁<extra_id_74>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": false
|
242 |
+
},
|
243 |
+
"250027": {
|
244 |
+
"content": "▁<extra_id_73>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": false
|
250 |
+
},
|
251 |
+
"250028": {
|
252 |
+
"content": "▁<extra_id_72>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": false
|
258 |
+
},
|
259 |
+
"250029": {
|
260 |
+
"content": "▁<extra_id_71>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
"250030": {
|
268 |
+
"content": "▁<extra_id_70>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"250031": {
|
276 |
+
"content": "▁<extra_id_69>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"250032": {
|
284 |
+
"content": "▁<extra_id_68>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"250033": {
|
292 |
+
"content": "▁<extra_id_67>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"250034": {
|
300 |
+
"content": "▁<extra_id_66>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"250035": {
|
308 |
+
"content": "▁<extra_id_65>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"250036": {
|
316 |
+
"content": "▁<extra_id_64>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"250037": {
|
324 |
+
"content": "▁<extra_id_63>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"250038": {
|
332 |
+
"content": "▁<extra_id_62>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"250039": {
|
340 |
+
"content": "▁<extra_id_61>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"250040": {
|
348 |
+
"content": "▁<extra_id_60>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"250041": {
|
356 |
+
"content": "▁<extra_id_59>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"250042": {
|
364 |
+
"content": "▁<extra_id_58>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"250043": {
|
372 |
+
"content": "▁<extra_id_57>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"250044": {
|
380 |
+
"content": "▁<extra_id_56>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"250045": {
|
388 |
+
"content": "▁<extra_id_55>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"250046": {
|
396 |
+
"content": "▁<extra_id_54>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"250047": {
|
404 |
+
"content": "▁<extra_id_53>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"250048": {
|
412 |
+
"content": "▁<extra_id_52>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"250049": {
|
420 |
+
"content": "▁<extra_id_51>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"250050": {
|
428 |
+
"content": "▁<extra_id_50>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"250051": {
|
436 |
+
"content": "▁<extra_id_49>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"250052": {
|
444 |
+
"content": "▁<extra_id_48>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"250053": {
|
452 |
+
"content": "▁<extra_id_47>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"250054": {
|
460 |
+
"content": "▁<extra_id_46>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"250055": {
|
468 |
+
"content": "▁<extra_id_45>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"250056": {
|
476 |
+
"content": "▁<extra_id_44>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"250057": {
|
484 |
+
"content": "▁<extra_id_43>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"250058": {
|
492 |
+
"content": "▁<extra_id_42>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"250059": {
|
500 |
+
"content": "▁<extra_id_41>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"250060": {
|
508 |
+
"content": "▁<extra_id_40>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"250061": {
|
516 |
+
"content": "▁<extra_id_39>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"250062": {
|
524 |
+
"content": "▁<extra_id_38>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": false
|
530 |
+
},
|
531 |
+
"250063": {
|
532 |
+
"content": "▁<extra_id_37>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": false
|
538 |
+
},
|
539 |
+
"250064": {
|
540 |
+
"content": "▁<extra_id_36>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": false
|
546 |
+
},
|
547 |
+
"250065": {
|
548 |
+
"content": "▁<extra_id_35>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"250066": {
|
556 |
+
"content": "▁<extra_id_34>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"250067": {
|
564 |
+
"content": "▁<extra_id_33>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"250068": {
|
572 |
+
"content": "▁<extra_id_32>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"250069": {
|
580 |
+
"content": "▁<extra_id_31>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"250070": {
|
588 |
+
"content": "▁<extra_id_30>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"250071": {
|
596 |
+
"content": "▁<extra_id_29>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"250072": {
|
604 |
+
"content": "▁<extra_id_28>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"250073": {
|
612 |
+
"content": "▁<extra_id_27>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"250074": {
|
620 |
+
"content": "▁<extra_id_26>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"250075": {
|
628 |
+
"content": "▁<extra_id_25>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"250076": {
|
636 |
+
"content": "▁<extra_id_24>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"250077": {
|
644 |
+
"content": "▁<extra_id_23>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"250078": {
|
652 |
+
"content": "▁<extra_id_22>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"250079": {
|
660 |
+
"content": "▁<extra_id_21>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
},
|
667 |
+
"250080": {
|
668 |
+
"content": "▁<extra_id_20>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": false
|
674 |
+
},
|
675 |
+
"250081": {
|
676 |
+
"content": "▁<extra_id_19>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": false
|
682 |
+
},
|
683 |
+
"250082": {
|
684 |
+
"content": "▁<extra_id_18>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": false
|
690 |
+
},
|
691 |
+
"250083": {
|
692 |
+
"content": "▁<extra_id_17>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": false
|
698 |
+
},
|
699 |
+
"250084": {
|
700 |
+
"content": "▁<extra_id_16>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": false
|
706 |
+
},
|
707 |
+
"250085": {
|
708 |
+
"content": "▁<extra_id_15>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": false
|
714 |
+
},
|
715 |
+
"250086": {
|
716 |
+
"content": "▁<extra_id_14>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": false
|
722 |
+
},
|
723 |
+
"250087": {
|
724 |
+
"content": "▁<extra_id_13>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
"250088": {
|
732 |
+
"content": "▁<extra_id_12>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": false
|
738 |
+
},
|
739 |
+
"250089": {
|
740 |
+
"content": "▁<extra_id_11>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": false
|
746 |
+
},
|
747 |
+
"250090": {
|
748 |
+
"content": "▁<extra_id_10>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": false
|
754 |
+
},
|
755 |
+
"250091": {
|
756 |
+
"content": "▁<extra_id_9>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": false
|
762 |
+
},
|
763 |
+
"250092": {
|
764 |
+
"content": "▁<extra_id_8>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": false
|
770 |
+
},
|
771 |
+
"250093": {
|
772 |
+
"content": "▁<extra_id_7>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": false
|
778 |
+
},
|
779 |
+
"250094": {
|
780 |
+
"content": "▁<extra_id_6>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": false
|
786 |
+
},
|
787 |
+
"250095": {
|
788 |
+
"content": "▁<extra_id_5>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": false
|
794 |
+
},
|
795 |
+
"250096": {
|
796 |
+
"content": "▁<extra_id_4>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
"250097": {
|
804 |
+
"content": "▁<extra_id_3>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": false
|
810 |
+
},
|
811 |
+
"250098": {
|
812 |
+
"content": "▁<extra_id_2>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": false
|
818 |
+
},
|
819 |
+
"250099": {
|
820 |
+
"content": "▁<extra_id_1>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": false
|
826 |
+
},
|
827 |
+
"250100": {
|
828 |
+
"content": "▁<extra_id_0>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": false
|
834 |
+
},
|
835 |
+
"250101": {
|
836 |
+
"content": "[MASK]",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
}
|
843 |
+
},
|
844 |
+
"bos_token": "[CLS]",
|
845 |
+
"clean_up_tokenization_spaces": false,
|
846 |
+
"cls_token": "[CLS]",
|
847 |
+
"do_lower_case": false,
|
848 |
+
"eos_token": "[SEP]",
|
849 |
+
"mask_token": "[MASK]",
|
850 |
+
"model_max_length": 1000000000000000019884624838656,
|
851 |
+
"pad_token": "[PAD]",
|
852 |
+
"sep_token": "[SEP]",
|
853 |
+
"sp_model_kwargs": {},
|
854 |
+
"split_by_punct": false,
|
855 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
856 |
+
"unk_token": "[UNK]",
|
857 |
+
"vocab_type": "spm"
|
858 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,684 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 46875,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.032,
|
13 |
+
"grad_norm": 4.370861530303955,
|
14 |
+
"learning_rate": 4.9466666666666665e-05,
|
15 |
+
"loss": 8.1809,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.064,
|
20 |
+
"grad_norm": 5.016350746154785,
|
21 |
+
"learning_rate": 4.8933333333333335e-05,
|
22 |
+
"loss": 5.7401,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.096,
|
27 |
+
"grad_norm": 5.93944787979126,
|
28 |
+
"learning_rate": 4.8400000000000004e-05,
|
29 |
+
"loss": 5.1235,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.128,
|
34 |
+
"grad_norm": 7.470402717590332,
|
35 |
+
"learning_rate": 4.7866666666666674e-05,
|
36 |
+
"loss": 4.792,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.16,
|
41 |
+
"grad_norm": 7.819157600402832,
|
42 |
+
"learning_rate": 4.7333333333333336e-05,
|
43 |
+
"loss": 4.5796,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.192,
|
48 |
+
"grad_norm": 8.23626708984375,
|
49 |
+
"learning_rate": 4.6800000000000006e-05,
|
50 |
+
"loss": 4.4105,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.224,
|
55 |
+
"grad_norm": 8.517165184020996,
|
56 |
+
"learning_rate": 4.626666666666667e-05,
|
57 |
+
"loss": 4.2749,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.256,
|
62 |
+
"grad_norm": 8.462729454040527,
|
63 |
+
"learning_rate": 4.573333333333333e-05,
|
64 |
+
"loss": 4.1514,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.288,
|
69 |
+
"grad_norm": 8.313840866088867,
|
70 |
+
"learning_rate": 4.52e-05,
|
71 |
+
"loss": 4.0479,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.32,
|
76 |
+
"grad_norm": 7.927861213684082,
|
77 |
+
"learning_rate": 4.466666666666667e-05,
|
78 |
+
"loss": 3.9494,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.352,
|
83 |
+
"grad_norm": 8.161856651306152,
|
84 |
+
"learning_rate": 4.413333333333334e-05,
|
85 |
+
"loss": 3.8686,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.384,
|
90 |
+
"grad_norm": 7.54767370223999,
|
91 |
+
"learning_rate": 4.36e-05,
|
92 |
+
"loss": 3.7998,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.416,
|
97 |
+
"grad_norm": 8.122455596923828,
|
98 |
+
"learning_rate": 4.3066666666666665e-05,
|
99 |
+
"loss": 3.7362,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.448,
|
104 |
+
"grad_norm": 8.269758224487305,
|
105 |
+
"learning_rate": 4.2533333333333335e-05,
|
106 |
+
"loss": 3.6624,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.48,
|
111 |
+
"grad_norm": 7.830111503601074,
|
112 |
+
"learning_rate": 4.2e-05,
|
113 |
+
"loss": 3.6145,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.512,
|
118 |
+
"grad_norm": 7.502816200256348,
|
119 |
+
"learning_rate": 4.146666666666667e-05,
|
120 |
+
"loss": 3.5634,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.544,
|
125 |
+
"grad_norm": 8.164464950561523,
|
126 |
+
"learning_rate": 4.093333333333334e-05,
|
127 |
+
"loss": 3.5123,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.576,
|
132 |
+
"grad_norm": 7.666891574859619,
|
133 |
+
"learning_rate": 4.0400000000000006e-05,
|
134 |
+
"loss": 3.4744,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.608,
|
139 |
+
"grad_norm": 8.045496940612793,
|
140 |
+
"learning_rate": 3.986666666666667e-05,
|
141 |
+
"loss": 3.432,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.64,
|
146 |
+
"grad_norm": 7.218926429748535,
|
147 |
+
"learning_rate": 3.933333333333333e-05,
|
148 |
+
"loss": 3.3907,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.672,
|
153 |
+
"grad_norm": 7.279954433441162,
|
154 |
+
"learning_rate": 3.88e-05,
|
155 |
+
"loss": 3.3558,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.704,
|
160 |
+
"grad_norm": 7.96562385559082,
|
161 |
+
"learning_rate": 3.8266666666666664e-05,
|
162 |
+
"loss": 3.329,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.736,
|
167 |
+
"grad_norm": 6.720692157745361,
|
168 |
+
"learning_rate": 3.773333333333334e-05,
|
169 |
+
"loss": 3.2911,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.768,
|
174 |
+
"grad_norm": 7.464371681213379,
|
175 |
+
"learning_rate": 3.72e-05,
|
176 |
+
"loss": 3.2624,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8,
|
181 |
+
"grad_norm": 6.938182830810547,
|
182 |
+
"learning_rate": 3.6666666666666666e-05,
|
183 |
+
"loss": 3.2417,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.832,
|
188 |
+
"grad_norm": 7.353320598602295,
|
189 |
+
"learning_rate": 3.6133333333333335e-05,
|
190 |
+
"loss": 3.2141,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.864,
|
195 |
+
"grad_norm": 7.38549280166626,
|
196 |
+
"learning_rate": 3.56e-05,
|
197 |
+
"loss": 3.188,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.896,
|
202 |
+
"grad_norm": 6.3833441734313965,
|
203 |
+
"learning_rate": 3.506666666666667e-05,
|
204 |
+
"loss": 3.169,
|
205 |
+
"step": 14000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.928,
|
209 |
+
"grad_norm": 6.512674808502197,
|
210 |
+
"learning_rate": 3.453333333333334e-05,
|
211 |
+
"loss": 3.1597,
|
212 |
+
"step": 14500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.96,
|
216 |
+
"grad_norm": 6.827766418457031,
|
217 |
+
"learning_rate": 3.4000000000000007e-05,
|
218 |
+
"loss": 3.1395,
|
219 |
+
"step": 15000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.992,
|
223 |
+
"grad_norm": 6.480617046356201,
|
224 |
+
"learning_rate": 3.346666666666667e-05,
|
225 |
+
"loss": 3.1093,
|
226 |
+
"step": 15500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.024,
|
230 |
+
"grad_norm": 6.874124526977539,
|
231 |
+
"learning_rate": 3.293333333333333e-05,
|
232 |
+
"loss": 3.0857,
|
233 |
+
"step": 16000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.056,
|
237 |
+
"grad_norm": 6.6677703857421875,
|
238 |
+
"learning_rate": 3.24e-05,
|
239 |
+
"loss": 3.0605,
|
240 |
+
"step": 16500
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.088,
|
244 |
+
"grad_norm": 6.855037212371826,
|
245 |
+
"learning_rate": 3.1866666666666664e-05,
|
246 |
+
"loss": 3.055,
|
247 |
+
"step": 17000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.12,
|
251 |
+
"grad_norm": 6.230678558349609,
|
252 |
+
"learning_rate": 3.1333333333333334e-05,
|
253 |
+
"loss": 3.0464,
|
254 |
+
"step": 17500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.152,
|
258 |
+
"grad_norm": 6.668459415435791,
|
259 |
+
"learning_rate": 3.08e-05,
|
260 |
+
"loss": 3.0222,
|
261 |
+
"step": 18000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.184,
|
265 |
+
"grad_norm": 6.614947319030762,
|
266 |
+
"learning_rate": 3.0266666666666666e-05,
|
267 |
+
"loss": 2.9976,
|
268 |
+
"step": 18500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.216,
|
272 |
+
"grad_norm": 7.133293151855469,
|
273 |
+
"learning_rate": 2.9733333333333336e-05,
|
274 |
+
"loss": 2.9829,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.248,
|
279 |
+
"grad_norm": 6.484233379364014,
|
280 |
+
"learning_rate": 2.9199999999999998e-05,
|
281 |
+
"loss": 2.9746,
|
282 |
+
"step": 19500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.28,
|
286 |
+
"grad_norm": 5.960205554962158,
|
287 |
+
"learning_rate": 2.8666666666666668e-05,
|
288 |
+
"loss": 2.9632,
|
289 |
+
"step": 20000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.312,
|
293 |
+
"grad_norm": 6.2322845458984375,
|
294 |
+
"learning_rate": 2.8133333333333334e-05,
|
295 |
+
"loss": 2.9636,
|
296 |
+
"step": 20500
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.3439999999999999,
|
300 |
+
"grad_norm": 6.31065559387207,
|
301 |
+
"learning_rate": 2.7600000000000003e-05,
|
302 |
+
"loss": 2.9457,
|
303 |
+
"step": 21000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.376,
|
307 |
+
"grad_norm": 6.024143218994141,
|
308 |
+
"learning_rate": 2.706666666666667e-05,
|
309 |
+
"loss": 2.9361,
|
310 |
+
"step": 21500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.408,
|
314 |
+
"grad_norm": 6.09192419052124,
|
315 |
+
"learning_rate": 2.6533333333333332e-05,
|
316 |
+
"loss": 2.9157,
|
317 |
+
"step": 22000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.44,
|
321 |
+
"grad_norm": 6.286288738250732,
|
322 |
+
"learning_rate": 2.6000000000000002e-05,
|
323 |
+
"loss": 2.9077,
|
324 |
+
"step": 22500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.472,
|
328 |
+
"grad_norm": 6.143230438232422,
|
329 |
+
"learning_rate": 2.5466666666666668e-05,
|
330 |
+
"loss": 2.8923,
|
331 |
+
"step": 23000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.504,
|
335 |
+
"grad_norm": 6.066094875335693,
|
336 |
+
"learning_rate": 2.4933333333333334e-05,
|
337 |
+
"loss": 2.8803,
|
338 |
+
"step": 23500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.536,
|
342 |
+
"grad_norm": 6.243915557861328,
|
343 |
+
"learning_rate": 2.44e-05,
|
344 |
+
"loss": 2.8774,
|
345 |
+
"step": 24000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.568,
|
349 |
+
"grad_norm": 6.412644863128662,
|
350 |
+
"learning_rate": 2.3866666666666666e-05,
|
351 |
+
"loss": 2.8581,
|
352 |
+
"step": 24500
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.6,
|
356 |
+
"grad_norm": 6.16639518737793,
|
357 |
+
"learning_rate": 2.3333333333333336e-05,
|
358 |
+
"loss": 2.8662,
|
359 |
+
"step": 25000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.6320000000000001,
|
363 |
+
"grad_norm": 6.105875492095947,
|
364 |
+
"learning_rate": 2.2800000000000002e-05,
|
365 |
+
"loss": 2.8444,
|
366 |
+
"step": 25500
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.6640000000000001,
|
370 |
+
"grad_norm": 6.135760307312012,
|
371 |
+
"learning_rate": 2.2266666666666668e-05,
|
372 |
+
"loss": 2.8568,
|
373 |
+
"step": 26000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.696,
|
377 |
+
"grad_norm": 6.091760158538818,
|
378 |
+
"learning_rate": 2.1733333333333334e-05,
|
379 |
+
"loss": 2.8352,
|
380 |
+
"step": 26500
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.728,
|
384 |
+
"grad_norm": 6.177093505859375,
|
385 |
+
"learning_rate": 2.12e-05,
|
386 |
+
"loss": 2.8265,
|
387 |
+
"step": 27000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.76,
|
391 |
+
"grad_norm": 6.15477180480957,
|
392 |
+
"learning_rate": 2.0666666666666666e-05,
|
393 |
+
"loss": 2.8198,
|
394 |
+
"step": 27500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.792,
|
398 |
+
"grad_norm": 6.571444988250732,
|
399 |
+
"learning_rate": 2.0133333333333336e-05,
|
400 |
+
"loss": 2.8118,
|
401 |
+
"step": 28000
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.8239999999999998,
|
405 |
+
"grad_norm": 6.144059658050537,
|
406 |
+
"learning_rate": 1.9600000000000002e-05,
|
407 |
+
"loss": 2.8048,
|
408 |
+
"step": 28500
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.8559999999999999,
|
412 |
+
"grad_norm": 6.564633369445801,
|
413 |
+
"learning_rate": 1.9066666666666668e-05,
|
414 |
+
"loss": 2.792,
|
415 |
+
"step": 29000
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.888,
|
419 |
+
"grad_norm": 6.839704513549805,
|
420 |
+
"learning_rate": 1.8533333333333334e-05,
|
421 |
+
"loss": 2.7989,
|
422 |
+
"step": 29500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.92,
|
426 |
+
"grad_norm": 6.17877721786499,
|
427 |
+
"learning_rate": 1.8e-05,
|
428 |
+
"loss": 2.7891,
|
429 |
+
"step": 30000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.952,
|
433 |
+
"grad_norm": 6.390108108520508,
|
434 |
+
"learning_rate": 1.7466666666666667e-05,
|
435 |
+
"loss": 2.789,
|
436 |
+
"step": 30500
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.984,
|
440 |
+
"grad_norm": 6.040237903594971,
|
441 |
+
"learning_rate": 1.6933333333333333e-05,
|
442 |
+
"loss": 2.7796,
|
443 |
+
"step": 31000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.016,
|
447 |
+
"grad_norm": 6.18825626373291,
|
448 |
+
"learning_rate": 1.6400000000000002e-05,
|
449 |
+
"loss": 2.784,
|
450 |
+
"step": 31500
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.048,
|
454 |
+
"grad_norm": 6.754644393920898,
|
455 |
+
"learning_rate": 1.586666666666667e-05,
|
456 |
+
"loss": 2.766,
|
457 |
+
"step": 32000
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.08,
|
461 |
+
"grad_norm": 6.347661972045898,
|
462 |
+
"learning_rate": 1.5333333333333334e-05,
|
463 |
+
"loss": 2.7708,
|
464 |
+
"step": 32500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.112,
|
468 |
+
"grad_norm": 6.577206134796143,
|
469 |
+
"learning_rate": 1.48e-05,
|
470 |
+
"loss": 2.7538,
|
471 |
+
"step": 33000
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.144,
|
475 |
+
"grad_norm": 6.365417003631592,
|
476 |
+
"learning_rate": 1.4266666666666667e-05,
|
477 |
+
"loss": 2.7592,
|
478 |
+
"step": 33500
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 2.176,
|
482 |
+
"grad_norm": 6.083129405975342,
|
483 |
+
"learning_rate": 1.3733333333333335e-05,
|
484 |
+
"loss": 2.7561,
|
485 |
+
"step": 34000
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.208,
|
489 |
+
"grad_norm": 6.250114440917969,
|
490 |
+
"learning_rate": 1.32e-05,
|
491 |
+
"loss": 2.7476,
|
492 |
+
"step": 34500
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.24,
|
496 |
+
"grad_norm": 6.081153392791748,
|
497 |
+
"learning_rate": 1.2666666666666668e-05,
|
498 |
+
"loss": 2.74,
|
499 |
+
"step": 35000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.2720000000000002,
|
503 |
+
"grad_norm": 6.01012659072876,
|
504 |
+
"learning_rate": 1.2133333333333335e-05,
|
505 |
+
"loss": 2.7465,
|
506 |
+
"step": 35500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 2.304,
|
510 |
+
"grad_norm": 6.1685566902160645,
|
511 |
+
"learning_rate": 1.16e-05,
|
512 |
+
"loss": 2.7345,
|
513 |
+
"step": 36000
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 2.336,
|
517 |
+
"grad_norm": 6.151036262512207,
|
518 |
+
"learning_rate": 1.1066666666666667e-05,
|
519 |
+
"loss": 2.7402,
|
520 |
+
"step": 36500
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 2.368,
|
524 |
+
"grad_norm": 6.3378005027771,
|
525 |
+
"learning_rate": 1.0533333333333335e-05,
|
526 |
+
"loss": 2.7396,
|
527 |
+
"step": 37000
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 2.4,
|
531 |
+
"grad_norm": 5.99214506149292,
|
532 |
+
"learning_rate": 1e-05,
|
533 |
+
"loss": 2.7323,
|
534 |
+
"step": 37500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 2.432,
|
538 |
+
"grad_norm": 6.489102363586426,
|
539 |
+
"learning_rate": 9.466666666666667e-06,
|
540 |
+
"loss": 2.7319,
|
541 |
+
"step": 38000
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 2.464,
|
545 |
+
"grad_norm": 5.602969646453857,
|
546 |
+
"learning_rate": 8.933333333333333e-06,
|
547 |
+
"loss": 2.7294,
|
548 |
+
"step": 38500
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 2.496,
|
552 |
+
"grad_norm": 6.040646076202393,
|
553 |
+
"learning_rate": 8.400000000000001e-06,
|
554 |
+
"loss": 2.7196,
|
555 |
+
"step": 39000
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 2.528,
|
559 |
+
"grad_norm": 6.2085795402526855,
|
560 |
+
"learning_rate": 7.866666666666667e-06,
|
561 |
+
"loss": 2.7251,
|
562 |
+
"step": 39500
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 2.56,
|
566 |
+
"grad_norm": 6.605915546417236,
|
567 |
+
"learning_rate": 7.333333333333334e-06,
|
568 |
+
"loss": 2.718,
|
569 |
+
"step": 40000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 2.592,
|
573 |
+
"grad_norm": 6.362601280212402,
|
574 |
+
"learning_rate": 6.800000000000001e-06,
|
575 |
+
"loss": 2.7193,
|
576 |
+
"step": 40500
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 2.624,
|
580 |
+
"grad_norm": 5.962555885314941,
|
581 |
+
"learning_rate": 6.266666666666666e-06,
|
582 |
+
"loss": 2.711,
|
583 |
+
"step": 41000
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 2.656,
|
587 |
+
"grad_norm": 6.051676273345947,
|
588 |
+
"learning_rate": 5.733333333333333e-06,
|
589 |
+
"loss": 2.7156,
|
590 |
+
"step": 41500
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 2.6879999999999997,
|
594 |
+
"grad_norm": 6.377429008483887,
|
595 |
+
"learning_rate": 5.2e-06,
|
596 |
+
"loss": 2.7165,
|
597 |
+
"step": 42000
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 2.7199999999999998,
|
601 |
+
"grad_norm": 6.063472747802734,
|
602 |
+
"learning_rate": 4.666666666666667e-06,
|
603 |
+
"loss": 2.7203,
|
604 |
+
"step": 42500
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 2.752,
|
608 |
+
"grad_norm": 6.316308975219727,
|
609 |
+
"learning_rate": 4.133333333333333e-06,
|
610 |
+
"loss": 2.7083,
|
611 |
+
"step": 43000
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 2.784,
|
615 |
+
"grad_norm": 6.789013385772705,
|
616 |
+
"learning_rate": 3.6e-06,
|
617 |
+
"loss": 2.709,
|
618 |
+
"step": 43500
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 2.816,
|
622 |
+
"grad_norm": 6.373924732208252,
|
623 |
+
"learning_rate": 3.066666666666667e-06,
|
624 |
+
"loss": 2.7082,
|
625 |
+
"step": 44000
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 2.848,
|
629 |
+
"grad_norm": 6.395301342010498,
|
630 |
+
"learning_rate": 2.5333333333333334e-06,
|
631 |
+
"loss": 2.6969,
|
632 |
+
"step": 44500
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 2.88,
|
636 |
+
"grad_norm": 5.811594009399414,
|
637 |
+
"learning_rate": 2.0000000000000003e-06,
|
638 |
+
"loss": 2.71,
|
639 |
+
"step": 45000
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 2.912,
|
643 |
+
"grad_norm": 5.967408180236816,
|
644 |
+
"learning_rate": 1.4666666666666667e-06,
|
645 |
+
"loss": 2.6958,
|
646 |
+
"step": 45500
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 2.944,
|
650 |
+
"grad_norm": 6.8203606605529785,
|
651 |
+
"learning_rate": 9.333333333333334e-07,
|
652 |
+
"loss": 2.693,
|
653 |
+
"step": 46000
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 2.976,
|
657 |
+
"grad_norm": 6.463422775268555,
|
658 |
+
"learning_rate": 4.0000000000000003e-07,
|
659 |
+
"loss": 2.7024,
|
660 |
+
"step": 46500
|
661 |
+
}
|
662 |
+
],
|
663 |
+
"logging_steps": 500,
|
664 |
+
"max_steps": 46875,
|
665 |
+
"num_input_tokens_seen": 0,
|
666 |
+
"num_train_epochs": 3,
|
667 |
+
"save_steps": 500,
|
668 |
+
"stateful_callbacks": {
|
669 |
+
"TrainerControl": {
|
670 |
+
"args": {
|
671 |
+
"should_epoch_stop": false,
|
672 |
+
"should_evaluate": false,
|
673 |
+
"should_log": false,
|
674 |
+
"should_save": true,
|
675 |
+
"should_training_stop": true
|
676 |
+
},
|
677 |
+
"attributes": {}
|
678 |
+
}
|
679 |
+
},
|
680 |
+
"total_flos": 3.99952244736e+17,
|
681 |
+
"train_batch_size": 16,
|
682 |
+
"trial_name": null,
|
683 |
+
"trial_params": null
|
684 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e631827b8aced2e815f9efdb7f8be010317601f17d9c398147c28ec8b4774ee
|
3 |
+
size 5240
|