Hugging Face's logo

Kyrmasch
/
mDeBERTa-v3-base-SQuAD2-kaz

Question Answering
Transformers
PyTorch
deberta-v2
Inference Endpoints
Model card Files Community
Kyrmasch commited on
Commit
ce14876
•
1 Parent(s): b830fa9

Upload 9 files

Browse files
Files changed (7) hide show
  1. all_results.json +8 -0
  2. config.json +1 -1
  3. pytorch_model.bin +2 -2
  4. tokenizer.json +2 -2
  5. train_results.json +8 -0
  6. trainer_state.json +124 -0
  7. training_args.bin +2 -2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.8305775371668482,
4
+ "train_runtime": 62910.5204,
5
+ "train_samples": 32352,
6
+ "train_samples_per_second": 1.543,
7
+ "train_steps_per_second": 0.129
8
+ }
config.json CHANGED
@@ -29,7 +29,7 @@
29
  "relative_attention": true,
30
  "share_att_key": true,
31
  "torch_dtype": "float32",
32
- "transformers_version": "4.28.0",
33
  "type_vocab_size": 0,
34
  "vocab_size": 251000
35
  }
 
29
  "relative_attention": true,
30
  "share_att_key": true,
31
  "torch_dtype": "float32",
32
+ "transformers_version": "4.32.1",
33
  "type_vocab_size": 0,
34
  "vocab_size": 251000
35
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0eb6dd591bf0f8a76039d383daaf11c35049bbd1baef878e9d2f5c42f8d8d2df
3
- size 1112954609
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbdaa0a5db6b23a8f2214c304cb1bd5ca7dfbb458220c10637e08d7b018a1ab
3
+ size 1112947373
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edece5654237062697029364a127e7e445a194980cff769210933906a213f71d
3
- size 16316318
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b52ff7043b8e7c0712d94ffa3c8a9c9522538157a11f5b59dd9051105497b7
3
+ size 16316053
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.8305775371668482,
4
+ "train_runtime": 62910.5204,
5
+ "train_samples": 32352,
6
+ "train_samples_per_second": 1.543,
7
+ "train_steps_per_second": 0.129
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 8088,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.19,
13
+ "learning_rate": 2.8145400593471808e-05,
14
+ "loss": 1.3617,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.37,
19
+ "learning_rate": 2.6290801186943622e-05,
20
+ "loss": 1.256,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.56,
25
+ "learning_rate": 2.443620178041543e-05,
26
+ "loss": 1.2066,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.74,
31
+ "learning_rate": 2.258160237388724e-05,
32
+ "loss": 1.135,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.93,
37
+ "learning_rate": 2.072700296735905e-05,
38
+ "loss": 1.106,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 1.11,
43
+ "learning_rate": 1.887240356083086e-05,
44
+ "loss": 0.9174,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 1.3,
49
+ "learning_rate": 1.7017804154302673e-05,
50
+ "loss": 0.7988,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.48,
55
+ "learning_rate": 1.516320474777448e-05,
56
+ "loss": 0.7843,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.67,
61
+ "learning_rate": 1.3308605341246291e-05,
62
+ "loss": 0.7841,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.85,
67
+ "learning_rate": 1.14540059347181e-05,
68
+ "loss": 0.7567,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 2.04,
73
+ "learning_rate": 9.599406528189911e-06,
74
+ "loss": 0.6834,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 2.23,
79
+ "learning_rate": 7.74480712166172e-06,
80
+ "loss": 0.5171,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 2.41,
85
+ "learning_rate": 5.890207715133531e-06,
86
+ "loss": 0.5309,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 2.6,
91
+ "learning_rate": 4.0356083086053414e-06,
92
+ "loss": 0.5064,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 2.78,
97
+ "learning_rate": 2.1810089020771514e-06,
98
+ "loss": 0.4908,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 2.97,
103
+ "learning_rate": 3.264094955489614e-07,
104
+ "loss": 0.5029,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 3.0,
109
+ "step": 8088,
110
+ "total_flos": 1.9020656992075776e+16,
111
+ "train_loss": 0.8305775371668482,
112
+ "train_runtime": 62910.5204,
113
+ "train_samples_per_second": 1.543,
114
+ "train_steps_per_second": 0.129
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 8088,
119
+ "num_train_epochs": 3,
120
+ "save_steps": 500,
121
+ "total_flos": 1.9020656992075776e+16,
122
+ "trial_name": null,
123
+ "trial_params": null
124
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cb1e3ad036ff831d72d3d43d5066cd551bb00359497134b78392489919ffa47
3
- size 3643
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714de8c2294006a37a31f88e83a7e36e6e23726261f12b0c95660e21ad8f8e4e
3
+ size 4027