Hugging Face's logo

kevinzyz
/
chinese_roberta_L-2_H-128-finetuned-MC-hyper

Multiple Choice
Transformers
PyTorch
bert
Inference Endpoints
Model card Files Community
kevinzyz commited on
Commit
4239025
•
1 Parent(s): 034f0b0

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. all_results.json +15 -0
  2. eval_results.json +9 -0
  3. pytorch_model.bin +1 -1
  4. train_results.json +9 -0
  5. trainer_state.json +115 -0
  6. training_args.bin +1 -1
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_accuracy": 0.30000001192092896,
4
+ "eval_loss": 1.5800185203552246,
5
+ "eval_runtime": 0.4521,
6
+ "eval_samples": 500,
7
+ "eval_samples_per_second": 1105.973,
8
+ "eval_steps_per_second": 35.391,
9
+ "total_flos": 4691397715200.0,
10
+ "train_loss": 1.5075831718444823,
11
+ "train_runtime": 20.08,
12
+ "train_samples": 4000,
13
+ "train_samples_per_second": 398.407,
14
+ "train_steps_per_second": 12.45
15
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_accuracy": 0.30000001192092896,
4
+ "eval_loss": 1.5800185203552246,
5
+ "eval_runtime": 0.4521,
6
+ "eval_samples": 500,
7
+ "eval_samples_per_second": 1105.973,
8
+ "eval_steps_per_second": 35.391
9
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9276d3f37e6589bf2257fb6fdda1e36d8873256ac749df50631b9e713f29d84
3
  size 12755881
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861a2ac60d31fb772fdc1d1e44c482f5eded7a8bb03efefd3663a3e8ad12ca42
3
  size 12755881
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 4691397715200.0,
4
+ "train_loss": 1.5075831718444823,
5
+ "train_runtime": 20.08,
6
+ "train_samples": 4000,
7
+ "train_samples_per_second": 398.407,
8
+ "train_steps_per_second": 12.45
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.5800185203552246,
3
+ "best_model_checkpoint": "chinese_roberta_L-2_H-128-finetuned-MC-hyper/checkpoint-125",
4
+ "epoch": 2.0,
5
+ "global_step": 250,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16,
12
+ "learning_rate": 0.0001608,
13
+ "loss": 1.5282,
14
+ "step": 20
15
+ },
16
+ {
17
+ "epoch": 0.32,
18
+ "learning_rate": 0.0001368,
19
+ "loss": 1.5563,
20
+ "step": 40
21
+ },
22
+ {
23
+ "epoch": 0.48,
24
+ "learning_rate": 0.00011279999999999999,
25
+ "loss": 1.5631,
26
+ "step": 60
27
+ },
28
+ {
29
+ "epoch": 0.64,
30
+ "learning_rate": 8.879999999999999e-05,
31
+ "loss": 1.5201,
32
+ "step": 80
33
+ },
34
+ {
35
+ "epoch": 0.8,
36
+ "learning_rate": 6.479999999999999e-05,
37
+ "loss": 1.526,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.96,
42
+ "learning_rate": 4.08e-05,
43
+ "loss": 1.5107,
44
+ "step": 120
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_accuracy": 0.30000001192092896,
49
+ "eval_loss": 1.5800185203552246,
50
+ "eval_runtime": 0.4321,
51
+ "eval_samples_per_second": 1157.093,
52
+ "eval_steps_per_second": 37.027,
53
+ "step": 125
54
+ },
55
+ {
56
+ "epoch": 1.12,
57
+ "learning_rate": 1.68e-05,
58
+ "loss": 1.4737,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 1.28,
63
+ "learning_rate": 0.0,
64
+ "loss": 1.4647,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 1.44,
69
+ "learning_rate": 0.0,
70
+ "loss": 1.4731,
71
+ "step": 180
72
+ },
73
+ {
74
+ "epoch": 1.6,
75
+ "learning_rate": 0.0,
76
+ "loss": 1.4969,
77
+ "step": 200
78
+ },
79
+ {
80
+ "epoch": 1.76,
81
+ "learning_rate": 0.0,
82
+ "loss": 1.4998,
83
+ "step": 220
84
+ },
85
+ {
86
+ "epoch": 1.92,
87
+ "learning_rate": 0.0,
88
+ "loss": 1.495,
89
+ "step": 240
90
+ },
91
+ {
92
+ "epoch": 2.0,
93
+ "eval_accuracy": 0.2939999997615814,
94
+ "eval_loss": 1.5831648111343384,
95
+ "eval_runtime": 0.4307,
96
+ "eval_samples_per_second": 1160.788,
97
+ "eval_steps_per_second": 37.145,
98
+ "step": 250
99
+ },
100
+ {
101
+ "epoch": 2.0,
102
+ "step": 250,
103
+ "total_flos": 4691397715200.0,
104
+ "train_loss": 1.5075831718444823,
105
+ "train_runtime": 20.08,
106
+ "train_samples_per_second": 398.407,
107
+ "train_steps_per_second": 12.45
108
+ }
109
+ ],
110
+ "max_steps": 250,
111
+ "num_train_epochs": 2,
112
+ "total_flos": 4691397715200.0,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cb4a1c601d1de11be8cfe2da4438cf283fe7d831d32b8f7dda84ef73d88bd13
3
  size 2799
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fe78e4f8bd344224f4450af0bb1d8064659984ccaf89355e358f14a9800bafe
3
  size 2799