Hugging Face's logo

FakeNewsLlama
/
TrueFakeBaseline

PEFT
TensorBoard
Safetensors
llama
Model card Files
xet
Metrics Community
danield12 commited on
Commit
181a7d9
·
verified ·
1 Parent(s): 8280e97

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. adapter_model.bin +1 -1
  2. all_results.json +15 -15
  3. eval_results.json +10 -10
  4. runs/Apr02_19-20-35_efa31d4321fb/events.out.tfevents.1712085638.efa31d4321fb.34.0 +3 -0
  5. runs/Apr02_19-21-06_efa31d4321fb/events.out.tfevents.1712085666.efa31d4321fb.34.1 +3 -0
  6. runs/Apr02_19-37-16_efa31d4321fb/events.out.tfevents.1712086637.efa31d4321fb.34.2 +3 -0
  7. runs/Apr02_19-44-05_efa31d4321fb/events.out.tfevents.1712087045.efa31d4321fb.34.3 +3 -0
  8. runs/Apr02_19-44-05_efa31d4321fb/events.out.tfevents.1712100433.efa31d4321fb.34.4 +3 -0
  9. train_results.json +6 -6
  10. trainer_state.json +92 -17
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29699d876fd85d7dc3266e0b316831faa49da847f2090d7030f99755ace6d437
3
  size 160086542
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20f84166792753507ea6124bdd53360db24770abff12c0c1561863e51e82fd7
3
  size 160086542
all_results.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
- "epoch": 1.74,
3
- "eval_accuracy": 0.8833333333333333,
4
- "eval_f1_score": 0.8832360840974346,
5
- "eval_gmean": 0.8848707421874868,
6
- "eval_loss": 0.30425313115119934,
7
- "eval_precision": 0.8875744047619049,
8
- "eval_recall": 0.8833333333333333,
9
- "eval_runtime": 185.7223,
10
- "eval_samples_per_second": 0.323,
11
- "eval_steps_per_second": 0.043,
12
- "total_flos": 3303081675694080.0,
13
- "train_loss": 0.85673828125,
14
- "train_runtime": 699.9179,
15
- "train_samples_per_second": 2.072,
16
- "train_steps_per_second": 0.014
17
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.8166666666666667,
4
+ "eval_f1_score": 0.8149425287356322,
5
+ "eval_gmean": 0.7636703179128833,
6
+ "eval_loss": 0.3408854305744171,
7
+ "eval_precision": 0.8137310606060607,
8
+ "eval_recall": 0.8166666666666667,
9
+ "eval_runtime": 180.7643,
10
+ "eval_samples_per_second": 0.332,
11
+ "eval_steps_per_second": 0.044,
12
+ "total_flos": 8.435821078904832e+16,
13
+ "train_loss": 0.43565983558768656,
14
+ "train_runtime": 13206.8117,
15
+ "train_samples_per_second": 0.324,
16
+ "train_steps_per_second": 0.005
17
  }
eval_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "epoch": 1.74,
3
- "eval_accuracy": 0.8833333333333333,
4
- "eval_f1_score": 0.8832360840974346,
5
- "eval_gmean": 0.8848707421874868,
6
- "eval_loss": 0.30425313115119934,
7
- "eval_precision": 0.8875744047619049,
8
- "eval_recall": 0.8833333333333333,
9
- "eval_runtime": 185.7223,
10
- "eval_samples_per_second": 0.323,
11
- "eval_steps_per_second": 0.043
12
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.8166666666666667,
4
+ "eval_f1_score": 0.8149425287356322,
5
+ "eval_gmean": 0.7636703179128833,
6
+ "eval_loss": 0.3408854305744171,
7
+ "eval_precision": 0.8137310606060607,
8
+ "eval_recall": 0.8166666666666667,
9
+ "eval_runtime": 180.7643,
10
+ "eval_samples_per_second": 0.332,
11
+ "eval_steps_per_second": 0.044
12
  }
runs/Apr02_19-20-35_efa31d4321fb/events.out.tfevents.1712085638.efa31d4321fb.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7fb79e8b22ebb99fd0f80ec5ff0c18f7de311904b66d15b7f1b461c9b72ad3
3
+ size 4982
runs/Apr02_19-21-06_efa31d4321fb/events.out.tfevents.1712085666.efa31d4321fb.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d7e8e255163325e8c9324121f58e81f5df91879ef4668571109accee66434c
3
+ size 4982
runs/Apr02_19-37-16_efa31d4321fb/events.out.tfevents.1712086637.efa31d4321fb.34.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6d4af75ad7725dd073c8b70f1f1c7b8fd984f6a329a18f736cdd3e253fecb9
3
+ size 4982
runs/Apr02_19-44-05_efa31d4321fb/events.out.tfevents.1712087045.efa31d4321fb.34.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459ca7fd3b3472443270ea8301b30309ca64105c859a9f16cb2980b5be0aa354
3
+ size 8020
runs/Apr02_19-44-05_efa31d4321fb/events.out.tfevents.1712100433.efa31d4321fb.34.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e92455695777ad399866e9bbf0728ea460a451ee4168208576cde132b6b0ba2
3
+ size 605
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.74,
3
- "total_flos": 3303081675694080.0,
4
- "train_loss": 0.85673828125,
5
- "train_runtime": 699.9179,
6
- "train_samples_per_second": 2.072,
7
- "train_steps_per_second": 0.014
8
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "total_flos": 8.435821078904832e+16,
4
+ "train_loss": 0.43565983558768656,
5
+ "train_runtime": 13206.8117,
6
+ "train_samples_per_second": 0.324,
7
+ "train_steps_per_second": 0.005
8
  }
trainer_state.json CHANGED
@@ -1,37 +1,112 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.7391304347826086,
5
  "eval_steps": 28,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 1.39,
13
- "grad_norm": 10.5625,
14
- "learning_rate": 5e-06,
15
- "loss": 0.8748,
16
  "step": 8
17
  },
18
  {
19
- "epoch": 1.74,
20
- "step": 10,
21
- "total_flos": 3303081675694080.0,
22
- "train_loss": 0.85673828125,
23
- "train_runtime": 699.9179,
24
- "train_samples_per_second": 2.072,
25
- "train_steps_per_second": 0.014
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  }
27
  ],
28
  "logging_steps": 8,
29
- "max_steps": 10,
30
  "num_input_tokens_seen": 0,
31
- "num_train_epochs": 2,
32
  "save_steps": 500,
33
- "total_flos": 3303081675694080.0,
34
- "train_batch_size": 32,
35
  "trial_name": null,
36
  "trial_params": null
37
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
  "eval_steps": 28,
6
+ "global_step": 67,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.12,
13
+ "grad_norm": 13.4375,
14
+ "learning_rate": 1.8153846153846155e-05,
15
+ "loss": 0.4866,
16
  "step": 8
17
  },
18
  {
19
+ "epoch": 0.24,
20
+ "grad_norm": 14.5625,
21
+ "learning_rate": 1.5692307692307693e-05,
22
+ "loss": 0.4687,
23
+ "step": 16
24
+ },
25
+ {
26
+ "epoch": 0.36,
27
+ "grad_norm": 6.6875,
28
+ "learning_rate": 1.3230769230769231e-05,
29
+ "loss": 0.4295,
30
+ "step": 24
31
+ },
32
+ {
33
+ "epoch": 0.42,
34
+ "eval_accuracy": 0.8166666666666667,
35
+ "eval_f1_score": 0.8149425287356322,
36
+ "eval_gmean": 0.7636703179128833,
37
+ "eval_loss": 0.3428385555744171,
38
+ "eval_precision": 0.8137310606060607,
39
+ "eval_recall": 0.8166666666666667,
40
+ "eval_runtime": 180.8759,
41
+ "eval_samples_per_second": 0.332,
42
+ "eval_steps_per_second": 0.044,
43
+ "step": 28
44
+ },
45
+ {
46
+ "epoch": 0.48,
47
+ "grad_norm": 6.46875,
48
+ "learning_rate": 1.076923076923077e-05,
49
+ "loss": 0.4236,
50
+ "step": 32
51
+ },
52
+ {
53
+ "epoch": 0.6,
54
+ "grad_norm": 9.8125,
55
+ "learning_rate": 8.307692307692309e-06,
56
+ "loss": 0.3919,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 0.72,
61
+ "grad_norm": 13.5,
62
+ "learning_rate": 5.846153846153847e-06,
63
+ "loss": 0.4099,
64
+ "step": 48
65
+ },
66
+ {
67
+ "epoch": 0.84,
68
+ "grad_norm": 11.4375,
69
+ "learning_rate": 3.384615384615385e-06,
70
+ "loss": 0.4242,
71
+ "step": 56
72
+ },
73
+ {
74
+ "epoch": 0.84,
75
+ "eval_accuracy": 0.8166666666666667,
76
+ "eval_f1_score": 0.8149425287356322,
77
+ "eval_gmean": 0.7636703179128833,
78
+ "eval_loss": 0.34062498807907104,
79
+ "eval_precision": 0.8137310606060607,
80
+ "eval_recall": 0.8166666666666667,
81
+ "eval_runtime": 180.4163,
82
+ "eval_samples_per_second": 0.333,
83
+ "eval_steps_per_second": 0.044,
84
+ "step": 56
85
+ },
86
+ {
87
+ "epoch": 0.96,
88
+ "grad_norm": 9.3125,
89
+ "learning_rate": 9.230769230769232e-07,
90
+ "loss": 0.4092,
91
+ "step": 64
92
+ },
93
+ {
94
+ "epoch": 1.0,
95
+ "step": 67,
96
+ "total_flos": 8.435821078904832e+16,
97
+ "train_loss": 0.43565983558768656,
98
+ "train_runtime": 13206.8117,
99
+ "train_samples_per_second": 0.324,
100
+ "train_steps_per_second": 0.005
101
  }
102
  ],
103
  "logging_steps": 8,
104
+ "max_steps": 67,
105
  "num_input_tokens_seen": 0,
106
+ "num_train_epochs": 1,
107
  "save_steps": 500,
108
+ "total_flos": 8.435821078904832e+16,
109
+ "train_batch_size": 16,
110
  "trial_name": null,
111
  "trial_params": null
112
  }