Hugging Face's logo

Alireza1044
/
mobilebert_mnli

Text Classification
Transformers
PyTorch
TensorBoard
English
mobilebert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
Alireza1044 commited on
Commit
7827472
•
1 Parent(s): 2f22edf

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +21 -0
  2. eval_results.json +16 -0
  3. runs/Jun14_09-45-02_labgpu/events.out.tfevents.1655205603.labgpu.8255.2 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +151 -0
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.3,
3
+ "epoch_mm": 1.3,
4
+ "eval_accuracy": 0.8187468160978095,
5
+ "eval_accuracy_mm": 0.8230268510984541,
6
+ "eval_loss": 0.4645940065383911,
7
+ "eval_loss_mm": 0.45945975184440613,
8
+ "eval_runtime": 55.0918,
9
+ "eval_runtime_mm": 55.0721,
10
+ "eval_samples": 9815,
11
+ "eval_samples_mm": 9832,
12
+ "eval_samples_per_second": 178.157,
13
+ "eval_samples_per_second_mm": 178.53,
14
+ "eval_steps_per_second": 22.272,
15
+ "eval_steps_per_second_mm": 22.316,
16
+ "train_loss": 2190.0037650828904,
17
+ "train_runtime": 4950.1281,
18
+ "train_samples": 392702,
19
+ "train_samples_per_second": 103.131,
20
+ "train_steps_per_second": 2.149
21
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.3,
3
+ "epoch_mm": 1.3,
4
+ "eval_accuracy": 0.8187468160978095,
5
+ "eval_accuracy_mm": 0.8230268510984541,
6
+ "eval_loss": 0.4645940065383911,
7
+ "eval_loss_mm": 0.45945975184440613,
8
+ "eval_runtime": 55.0918,
9
+ "eval_runtime_mm": 55.0721,
10
+ "eval_samples": 9815,
11
+ "eval_samples_mm": 9832,
12
+ "eval_samples_per_second": 178.157,
13
+ "eval_samples_per_second_mm": 178.53,
14
+ "eval_steps_per_second": 22.272,
15
+ "eval_steps_per_second_mm": 22.316
16
+ }
runs/Jun14_09-45-02_labgpu/events.out.tfevents.1655205603.labgpu.8255.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c36b94c418a1a11bf1a613a435f6d16c710b3a0f30932a89f7fddcda378ef77
3
+ size 686
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.3,
3
+ "train_loss": 2190.0037650828904,
4
+ "train_runtime": 4950.1281,
5
+ "train_samples": 392702,
6
+ "train_samples_per_second": 103.131,
7
+ "train_steps_per_second": 2.149
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3000488878024932,
5
+ "global_step": 10637,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 2.8589827959011e-05,
13
+ "loss": 46579.6,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.12,
18
+ "learning_rate": 2.7179655918022e-05,
19
+ "loss": 0.6626,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.18,
24
+ "learning_rate": 2.5769483877033e-05,
25
+ "loss": 0.6104,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.24,
30
+ "learning_rate": 2.4359311836043998e-05,
31
+ "loss": 0.5933,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.31,
36
+ "learning_rate": 2.2949139795054998e-05,
37
+ "loss": 0.5704,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.37,
42
+ "learning_rate": 2.1538967754065997e-05,
43
+ "loss": 0.5475,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.43,
48
+ "learning_rate": 2.0128795713076996e-05,
49
+ "loss": 0.5429,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.49,
54
+ "learning_rate": 1.8718623672087996e-05,
55
+ "loss": 0.5326,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.55,
60
+ "learning_rate": 1.7308451631098995e-05,
61
+ "loss": 0.5354,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.61,
66
+ "learning_rate": 1.5898279590109995e-05,
67
+ "loss": 0.522,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.67,
72
+ "learning_rate": 1.4488107549120992e-05,
73
+ "loss": 0.5162,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.73,
78
+ "learning_rate": 1.3077935508131993e-05,
79
+ "loss": 0.5076,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.79,
84
+ "learning_rate": 1.1667763467142991e-05,
85
+ "loss": 0.5169,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.86,
90
+ "learning_rate": 1.025759142615399e-05,
91
+ "loss": 0.5035,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.92,
96
+ "learning_rate": 8.847419385164992e-06,
97
+ "loss": 0.5002,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.98,
102
+ "learning_rate": 7.43724734417599e-06,
103
+ "loss": 0.4978,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.04,
108
+ "learning_rate": 6.0270753031869895e-06,
109
+ "loss": 0.4714,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.1,
114
+ "learning_rate": 4.616903262197988e-06,
115
+ "loss": 0.4519,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.16,
120
+ "learning_rate": 3.206731221208988e-06,
121
+ "loss": 0.4483,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.22,
126
+ "learning_rate": 1.796559180219987e-06,
127
+ "loss": 0.4489,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.28,
132
+ "learning_rate": 3.8638713923098615e-07,
133
+ "loss": 0.4398,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.3,
138
+ "step": 10637,
139
+ "total_flos": 8004034572369408.0,
140
+ "train_loss": 2190.0037650828904,
141
+ "train_runtime": 4950.1281,
142
+ "train_samples_per_second": 103.131,
143
+ "train_steps_per_second": 2.149
144
+ }
145
+ ],
146
+ "max_steps": 10637,
147
+ "num_train_epochs": 2,
148
+ "total_flos": 8004034572369408.0,
149
+ "trial_name": null,
150
+ "trial_params": null
151
+ }