Hugging Face's logo

VSPuzzler
/
SemevalClickbaitSpoilingNew

Text Classification
Transformers
PyTorch
distilbert
text-embeddings-inference
Model card Files
xet
 Community
1
VSPuzzler commited on
Commit
e05d52e
·
1 Parent(s): a66ce86

Upload with huggingface_hub

Browse files
Files changed (5) hide show
  1. optimizer.pt +1 -1
  2. pytorch_model.bin +1 -1
  3. scheduler.pt +1 -1
  4. trainer_state.json +32 -32
  5. training_args.bin +1 -1
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51034d93bee0a281c13872ebc5f46588cae8ad9098351aa4719ac2adccdc5da8
3
  size 535706209
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c405f6c40d1200845afd7ec4a280ad78efb3b4aabdfb7199f110d3784f20f9c4
3
  size 535706209
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:536a1709182767c35d8b97545cfa843894f5d2087d3a4a1e1bfd1a4e1300610b
3
  size 267857393
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0117a50d4b2287f08ff497c869353972a1746688126e083cbb1fd3b315b22eef
3
  size 267857393
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b536fb17773479ea80b6e483306102fefe56d142995a9fe2a2366cbaeb59e342
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e35b3e1d3db27a8ab844c20114e9e1cec88dd3ed6b54599b8cbd45a7f79a10d2
3
  size 623
trainer_state.json CHANGED
@@ -9,97 +9,97 @@
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
- "learning_rate": 1.866666666666667e-05,
13
- "loss": 0.9851,
14
  "step": 200
15
  },
16
  {
17
  "epoch": 2.0,
18
- "learning_rate": 1.7333333333333336e-05,
19
- "loss": 0.8473,
20
  "step": 400
21
  },
22
  {
23
  "epoch": 3.0,
24
- "learning_rate": 1.6000000000000003e-05,
25
- "loss": 0.685,
26
  "step": 600
27
  },
28
  {
29
  "epoch": 4.0,
30
- "learning_rate": 1.4666666666666666e-05,
31
- "loss": 0.4938,
32
  "step": 800
33
  },
34
  {
35
  "epoch": 5.0,
36
- "learning_rate": 1.3333333333333333e-05,
37
- "loss": 0.3049,
38
  "step": 1000
39
  },
40
  {
41
  "epoch": 6.0,
42
- "learning_rate": 1.2e-05,
43
- "loss": 0.1841,
44
  "step": 1200
45
  },
46
  {
47
  "epoch": 7.0,
48
- "learning_rate": 1.0666666666666667e-05,
49
- "loss": 0.0946,
50
  "step": 1400
51
  },
52
  {
53
  "epoch": 8.0,
54
- "learning_rate": 9.333333333333334e-06,
55
- "loss": 0.0615,
56
  "step": 1600
57
  },
58
  {
59
  "epoch": 9.0,
60
- "learning_rate": 8.000000000000001e-06,
61
- "loss": 0.0384,
62
  "step": 1800
63
  },
64
  {
65
  "epoch": 10.0,
66
- "learning_rate": 6.666666666666667e-06,
67
- "loss": 0.0191,
68
  "step": 2000
69
  },
70
  {
71
  "epoch": 11.0,
72
- "learning_rate": 5.333333333333334e-06,
73
- "loss": 0.0196,
74
  "step": 2200
75
  },
76
  {
77
  "epoch": 12.0,
78
- "learning_rate": 4.000000000000001e-06,
79
- "loss": 0.0145,
80
  "step": 2400
81
  },
82
  {
83
  "epoch": 13.0,
84
- "learning_rate": 2.666666666666667e-06,
85
- "loss": 0.0119,
86
  "step": 2600
87
  },
88
  {
89
  "epoch": 14.0,
90
- "learning_rate": 1.3333333333333334e-06,
91
- "loss": 0.012,
92
  "step": 2800
93
  },
94
  {
95
  "epoch": 15.0,
96
- "learning_rate": 0.0,
97
- "loss": 0.0071,
98
  "step": 3000
99
  }
100
  ],
101
- "max_steps": 3000,
102
- "num_train_epochs": 15,
103
  "total_flos": 6358548529152000.0,
104
  "trial_name": null,
105
  "trial_params": null
 
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
+ "learning_rate": 1.9333333333333333e-05,
13
+ "loss": 0.0569,
14
  "step": 200
15
  },
16
  {
17
  "epoch": 2.0,
18
+ "learning_rate": 1.866666666666667e-05,
19
+ "loss": 0.0366,
20
  "step": 400
21
  },
22
  {
23
  "epoch": 3.0,
24
+ "learning_rate": 1.8e-05,
25
+ "loss": 0.0292,
26
  "step": 600
27
  },
28
  {
29
  "epoch": 4.0,
30
+ "learning_rate": 1.7333333333333336e-05,
31
+ "loss": 0.032,
32
  "step": 800
33
  },
34
  {
35
  "epoch": 5.0,
36
+ "learning_rate": 1.6666666666666667e-05,
37
+ "loss": 0.0253,
38
  "step": 1000
39
  },
40
  {
41
  "epoch": 6.0,
42
+ "learning_rate": 1.6000000000000003e-05,
43
+ "loss": 0.0312,
44
  "step": 1200
45
  },
46
  {
47
  "epoch": 7.0,
48
+ "learning_rate": 1.5333333333333334e-05,
49
+ "loss": 0.0285,
50
  "step": 1400
51
  },
52
  {
53
  "epoch": 8.0,
54
+ "learning_rate": 1.4666666666666666e-05,
55
+ "loss": 0.029,
56
  "step": 1600
57
  },
58
  {
59
  "epoch": 9.0,
60
+ "learning_rate": 1.4e-05,
61
+ "loss": 0.0308,
62
  "step": 1800
63
  },
64
  {
65
  "epoch": 10.0,
66
+ "learning_rate": 1.3333333333333333e-05,
67
+ "loss": 0.0324,
68
  "step": 2000
69
  },
70
  {
71
  "epoch": 11.0,
72
+ "learning_rate": 1.2666666666666667e-05,
73
+ "loss": 0.0165,
74
  "step": 2200
75
  },
76
  {
77
  "epoch": 12.0,
78
+ "learning_rate": 1.2e-05,
79
+ "loss": 0.0207,
80
  "step": 2400
81
  },
82
  {
83
  "epoch": 13.0,
84
+ "learning_rate": 1.1333333333333334e-05,
85
+ "loss": 0.0157,
86
  "step": 2600
87
  },
88
  {
89
  "epoch": 14.0,
90
+ "learning_rate": 1.0666666666666667e-05,
91
+ "loss": 0.0136,
92
  "step": 2800
93
  },
94
  {
95
  "epoch": 15.0,
96
+ "learning_rate": 1e-05,
97
+ "loss": 0.0058,
98
  "step": 3000
99
  }
100
  ],
101
+ "max_steps": 6000,
102
+ "num_train_epochs": 30,
103
  "total_flos": 6358548529152000.0,
104
  "trial_name": null,
105
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:512f976469758ec68d7229fb68dc618780d22ccec1d9d916cc99394579b1c9bd
3
  size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3a822423ddf836858e1b92c846c9074238ed0a832e2ec766ae1ee99843630ed
3
  size 3311