Hugging Face's logo

FakeNewsLlama
/
TrueFakeBaseline

PEFT
TensorBoard
Safetensors
llama
Model card Files
xet
Metrics Community
danield12 commited on
Commit
8280e97
·
verified ·
1 Parent(s): 6f5ab8f

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. adapter_model.bin +1 -1
  2. all_results.json +15 -15
  3. eval_results.json +10 -10
  4. runs/Apr02_18-52-22_63123e2dced6/events.out.tfevents.1712083944.63123e2dced6.34.0 +3 -0
  5. runs/Apr02_18-52-22_63123e2dced6/events.out.tfevents.1712084829.63123e2dced6.34.1 +3 -0
  6. train_results.json +6 -6
  7. trainer_state.json +16 -23
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab078ca42c5033790a59a7d1b8ea5cb025038f8778b8bb368725c814de1dcb99
3
  size 160086542
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29699d876fd85d7dc3266e0b316831faa49da847f2090d7030f99755ace6d437
3
  size 160086542
all_results.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
- "epoch": 1.95,
3
- "eval_accuracy": 0.85,
4
- "eval_f1_score": 0.8512605042016806,
5
- "eval_gmean": 0.8238099238888024,
6
- "eval_loss": 0.35761719942092896,
7
- "eval_precision": 0.853042328042328,
8
- "eval_recall": 0.85,
9
- "eval_runtime": 183.8915,
10
- "eval_samples_per_second": 0.326,
11
- "eval_steps_per_second": 0.044,
12
- "total_flos": 2.536276286767104e+16,
13
- "train_loss": 2.198583984375,
14
- "train_runtime": 3976.3696,
15
- "train_samples_per_second": 0.323,
16
- "train_steps_per_second": 0.005
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
  }
eval_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "epoch": 1.95,
3
- "eval_accuracy": 0.85,
4
- "eval_f1_score": 0.8512605042016806,
5
- "eval_gmean": 0.8238099238888024,
6
- "eval_loss": 0.35761719942092896,
7
- "eval_precision": 0.853042328042328,
8
- "eval_recall": 0.85,
9
- "eval_runtime": 183.8915,
10
- "eval_samples_per_second": 0.326,
11
- "eval_steps_per_second": 0.044
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
  }
runs/Apr02_18-52-22_63123e2dced6/events.out.tfevents.1712083944.63123e2dced6.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7396e2595b34b29882569be494d2d21b48010bcff7a87e855875060f34e1c4b0
3
+ size 5537
runs/Apr02_18-52-22_63123e2dced6/events.out.tfevents.1712084829.63123e2dced6.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c393740750d1682ddeb06fe23cecaa8cbd52b21559ddde066d9bf929e0ce391
3
+ size 605
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.95,
3
- "total_flos": 2.536276286767104e+16,
4
- "train_loss": 2.198583984375,
5
- "train_runtime": 3976.3696,
6
- "train_samples_per_second": 0.323,
7
- "train_steps_per_second": 0.005
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
  }
trainer_state.json CHANGED
@@ -1,44 +1,37 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.951219512195122,
5
  "eval_steps": 28,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.78,
13
- "grad_norm": 39.25,
14
- "learning_rate": 1.3333333333333333e-05,
15
- "loss": 2.3276,
16
  "step": 8
17
  },
18
  {
19
- "epoch": 1.56,
20
- "grad_norm": 25.75,
21
- "learning_rate": 4.444444444444444e-06,
22
- "loss": 1.9921,
23
- "step": 16
24
- },
25
- {
26
- "epoch": 1.95,
27
- "step": 20,
28
- "total_flos": 2.536276286767104e+16,
29
- "train_loss": 2.198583984375,
30
- "train_runtime": 3976.3696,
31
- "train_samples_per_second": 0.323,
32
- "train_steps_per_second": 0.005
33
  }
34
  ],
35
  "logging_steps": 8,
36
- "max_steps": 20,
37
  "num_input_tokens_seen": 0,
38
  "num_train_epochs": 2,
39
  "save_steps": 500,
40
- "total_flos": 2.536276286767104e+16,
41
- "train_batch_size": 16,
42
  "trial_name": null,
43
  "trial_params": null
44
  }
 
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
  }