ZivKassnerNK commited on
Commit
a6e68cb
·
1 Parent(s): 0db5bc0

Add evaluation results and output files to model card

Browse files
README.md CHANGED
@@ -5,18 +5,18 @@ tags:
5
  - model
6
  - evaluation
7
  metrics:
8
- - average_precision: 0.96
9
- - roc_auc: 0.94
10
- - best threshold according to F1: 0.30
11
  ---
12
 
13
  # Binary Classification Model
14
 
15
  ## Evaluation Results
16
 
17
- **Average Precision:** 0.96
18
- **ROC AUC:** 0.94
19
- **best threshold according to F1: 0.30
20
 
21
 
22
  ## Visualizations
 
5
  - model
6
  - evaluation
7
  metrics:
8
+ - average_precision: 0.95
9
+ - roc_auc: 0.93
10
+ - best threshold according to F1: 0.44
11
  ---
12
 
13
  # Binary Classification Model
14
 
15
  ## Evaluation Results
16
 
17
+ **Average Precision:** 0.95
18
+ **ROC AUC:** 0.93
19
+ **best threshold according to F1: 0.44
20
 
21
 
22
  ## Visualizations
checkpoint-8/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:958f354c0a4a7b17ee2f1630478630a3a890eaf792fbaaa6127973903ec18b95
3
  size 8760128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fced4ab76217d28bcd7de9a83e6fc619c1576a41165fd3b91280418c68ced5d1
3
  size 8760128
checkpoint-8/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2774fd9f37a8d9cff1d919819d8448613233296dff71df0ef1e7413b0c44f16
3
  size 17564858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f581e008d5914466c5395d23b18e45299d3ac0fb3aeef93ba811aaab6c7114b
3
  size 17564858
checkpoint-8/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0ed227609d668f32c29a88e864644bbc2d719856cd6e14fe5b57623aeddb19d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698379ffc8ebaa82bdd977f5c57de7891b341867f48cc2cee1320c2e7fe9fa12
3
  size 1064
checkpoint-8/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.7894614129167639,
3
  "best_model_checkpoint": "/tmp/logs/binary_classification_model_v3.1.5_Junction_batch2/checkpoint-8",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,85 +10,85 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13333333333333333,
13
- "grad_norm": 28787.228515625,
14
- "learning_rate": 0.00035714285714285714,
15
- "loss": 0.3856,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.26666666666666666,
20
- "grad_norm": 27319.6640625,
21
- "learning_rate": 0.0007142857142857143,
22
- "loss": 0.3913,
23
  "step": 2
24
  },
25
  {
26
  "epoch": 0.4,
27
- "grad_norm": 764010.0625,
28
- "learning_rate": 0.0010714285714285715,
29
- "loss": 0.657,
30
  "step": 3
31
  },
32
  {
33
  "epoch": 0.5333333333333333,
34
- "grad_norm": 460677.375,
35
- "learning_rate": 0.0014285714285714286,
36
- "loss": 0.6085,
37
  "step": 4
38
  },
39
  {
40
  "epoch": 0.6666666666666666,
41
- "grad_norm": 349255.0625,
42
- "learning_rate": 0.0017857142857142859,
43
- "loss": 0.6177,
44
  "step": 5
45
  },
46
  {
47
  "epoch": 0.8,
48
- "grad_norm": 162546.3125,
49
- "learning_rate": 0.002142857142857143,
50
- "loss": 0.5485,
51
  "step": 6
52
  },
53
  {
54
  "epoch": 0.9333333333333333,
55
- "grad_norm": 441874.4375,
56
- "learning_rate": 0.0025,
57
- "loss": 0.7531,
58
  "step": 7
59
  },
60
  {
61
  "epoch": 1.0,
62
- "grad_norm": 153196.75,
63
- "learning_rate": 0.002857142857142857,
64
- "loss": 0.3116,
65
  "step": 8
66
  },
67
  {
68
  "epoch": 1.0,
69
- "eval_accuracy": 0.7538838920686836,
70
- "eval_best_threshold": 0.5175232887268066,
71
- "eval_f1": 0.7894614129167639,
72
- "eval_loss": 0.5186505913734436,
73
- "eval_pr_auc": 0.8433328368486523,
74
- "eval_precision": 0.7086647132691503,
75
- "eval_recall": 0.8910526315789473,
76
- "eval_roc_auc": 0.8432376305376215,
77
- "eval_runtime": 2.5983,
78
- "eval_samples_per_second": 1412.087,
79
- "eval_steps_per_second": 3.079,
80
  "step": 8
81
  }
82
  ],
83
  "logging_steps": 1,
84
- "max_steps": 1400,
85
  "num_input_tokens_seen": 0,
86
- "num_train_epochs": 200,
87
  "save_steps": 500,
88
  "stateful_callbacks": {
89
  "EarlyStoppingCallback": {
90
  "args": {
91
- "early_stopping_patience": 20,
92
  "early_stopping_threshold": 0.0
93
  },
94
  "attributes": {
 
1
  {
2
+ "best_metric": 0.8425618780301097,
3
  "best_model_checkpoint": "/tmp/logs/binary_classification_model_v3.1.5_Junction_batch2/checkpoint-8",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13333333333333333,
13
+ "grad_norm": 13324.8955078125,
14
+ "learning_rate": 0.00014285714285714287,
15
+ "loss": 0.3452,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.26666666666666666,
20
+ "grad_norm": 13969.9384765625,
21
+ "learning_rate": 0.00028571428571428574,
22
+ "loss": 0.3389,
23
  "step": 2
24
  },
25
  {
26
  "epoch": 0.4,
27
+ "grad_norm": 25136.65234375,
28
+ "learning_rate": 0.0004285714285714286,
29
+ "loss": 0.3301,
30
  "step": 3
31
  },
32
  {
33
  "epoch": 0.5333333333333333,
34
+ "grad_norm": 21701.81640625,
35
+ "learning_rate": 0.0005714285714285715,
36
+ "loss": 0.3312,
37
  "step": 4
38
  },
39
  {
40
  "epoch": 0.6666666666666666,
41
+ "grad_norm": 24685.49609375,
42
+ "learning_rate": 0.0007142857142857143,
43
+ "loss": 0.323,
44
  "step": 5
45
  },
46
  {
47
  "epoch": 0.8,
48
+ "grad_norm": 45404.9921875,
49
+ "learning_rate": 0.0008571428571428572,
50
+ "loss": 0.358,
51
  "step": 6
52
  },
53
  {
54
  "epoch": 0.9333333333333333,
55
+ "grad_norm": 20938.6328125,
56
+ "learning_rate": 0.001,
57
+ "loss": 0.3457,
58
  "step": 7
59
  },
60
  {
61
  "epoch": 1.0,
62
+ "grad_norm": 30029.5546875,
63
+ "learning_rate": 0.001142857142857143,
64
+ "loss": 0.1635,
65
  "step": 8
66
  },
67
  {
68
  "epoch": 1.0,
69
+ "eval_accuracy": 0.8318342872717361,
70
+ "eval_best_threshold": 0.3127627372741699,
71
+ "eval_f1": 0.8425618780301097,
72
+ "eval_loss": 0.368960976600647,
73
+ "eval_pr_auc": 0.9260693646178895,
74
+ "eval_precision": 0.8177315502724121,
75
+ "eval_recall": 0.8689473684210526,
76
+ "eval_roc_auc": 0.9189140459968462,
77
+ "eval_runtime": 2.7482,
78
+ "eval_samples_per_second": 1335.042,
79
+ "eval_steps_per_second": 2.911,
80
  "step": 8
81
  }
82
  ],
83
  "logging_steps": 1,
84
+ "max_steps": 3500,
85
  "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 500,
87
  "save_steps": 500,
88
  "stateful_callbacks": {
89
  "EarlyStoppingCallback": {
90
  "args": {
91
+ "early_stopping_patience": 50,
92
  "early_stopping_threshold": 0.0
93
  },
94
  "attributes": {
checkpoint-8/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99c19006956dac46c4f9af44fd85d92055df85ce6d52f69565d2637981ffd87f
3
- size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4056f3d0beca21dab5fc55a93dc339d6de9a32168cdb0039f8dffef443e6b27f
3
+ size 5432
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb87fedae2e556c6ed432f3f6304b5fbcb6f36bfcf1a1b86ab7742ebf8c70899
3
  size 8760128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c12e90cdacbeb9a95697e94c9c5cd32d029cf14517dd16c5b49332d0eac0c61
3
  size 8760128
pr_curve.png CHANGED
roc_curve.png CHANGED
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:533942e4c51378a0ec0b57c4b2c984691303160f66d5ab43e15a964dc09f965e
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4056f3d0beca21dab5fc55a93dc339d6de9a32168cdb0039f8dffef443e6b27f
3
  size 5432