Hugging Face's logo

FakeNewsLlama
/
TrueFakeBaseline

PEFT
TensorBoard
Safetensors
llama
Model card Files
xet
Metrics Community
danield12 commited on
Commit
0f92b28
·
verified ·
1 Parent(s): 54dc585

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. README.md +9 -0
  2. adapter_config.json +26 -0
  3. adapter_model.bin +3 -0
  4. all_results.json +17 -0
  5. eval_results.json +12 -0
  6. runs/Mar24_20-08-48_2d0deb3319f4/events.out.tfevents.1711312182.2d0deb3319f4.34.0 +3 -0
  7. runs/Mar24_20-46-12_2d0deb3319f4/events.out.tfevents.1711313173.2d0deb3319f4.34.1 +3 -0
  8. runs/Mar24_20-46-12_2d0deb3319f4/events.out.tfevents.1711315707.2d0deb3319f4.34.2 +3 -0
  9. train_results.json +8 -0
  10. trainer_state.json +50 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 64,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "up_proj",
18
+ "gate_proj",
19
+ "v_proj",
20
+ "q_proj",
21
+ "o_proj",
22
+ "down_proj",
23
+ "k_proj"
24
+ ],
25
+ "task_type": "SEQ_CLS"
26
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6108dc25ba5aa452a9c8d2e2e7d6ef2951bcb6110a3c096753940fa8b361588b
3
+ size 160086542
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.98,
3
+ "eval_accuracy": 0.45,
4
+ "eval_f1_score": 0.413184584178499,
5
+ "eval_gmean": 0.43716017951820696,
6
+ "eval_loss": 1.7248046398162842,
7
+ "eval_precision": 0.42000000000000004,
8
+ "eval_recall": 0.45,
9
+ "eval_runtime": 249.5755,
10
+ "eval_samples_per_second": 0.321,
11
+ "eval_steps_per_second": 0.04,
12
+ "total_flos": 1.28114982125568e+16,
13
+ "train_loss": 1.59609375,
14
+ "train_runtime": 2284.6483,
15
+ "train_samples_per_second": 0.281,
16
+ "train_steps_per_second": 0.004
17
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.98,
3
+ "eval_accuracy": 0.45,
4
+ "eval_f1_score": 0.413184584178499,
5
+ "eval_gmean": 0.43716017951820696,
6
+ "eval_loss": 1.7248046398162842,
7
+ "eval_precision": 0.42000000000000004,
8
+ "eval_recall": 0.45,
9
+ "eval_runtime": 249.5755,
10
+ "eval_samples_per_second": 0.321,
11
+ "eval_steps_per_second": 0.04
12
+ }
runs/Mar24_20-08-48_2d0deb3319f4/events.out.tfevents.1711312182.2d0deb3319f4.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d4a454f1d24c4331c9e94ff8a8819d06a8f836b6cd81bb20aec95e0e6d7b2c
3
+ size 538
runs/Mar24_20-46-12_2d0deb3319f4/events.out.tfevents.1711313173.2d0deb3319f4.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d2c3322c4932872edcac84deadaa033a49372d7dc4eab8498fcd652047cba9
3
+ size 5969
runs/Mar24_20-46-12_2d0deb3319f4/events.out.tfevents.1711315707.2d0deb3319f4.34.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a245fec1aab58c89f283d6af8729d48e1a809cb3a564e6b437907649cf73a35f
3
+ size 605
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.98,
3
+ "total_flos": 1.28114982125568e+16,
4
+ "train_loss": 1.59609375,
5
+ "train_runtime": 2284.6483,
6
+ "train_samples_per_second": 0.281,
7
+ "train_steps_per_second": 0.004
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.975609756097561,
5
+ "eval_steps": 8,
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": 0.78,
13
+ "grad_norm": 34.5,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.6561,
16
+ "step": 8
17
+ },
18
+ {
19
+ "epoch": 0.78,
20
+ "eval_accuracy": 0.45,
21
+ "eval_f1_score": 0.413184584178499,
22
+ "eval_gmean": 0.43716017951820696,
23
+ "eval_loss": 1.7263672351837158,
24
+ "eval_precision": 0.42000000000000004,
25
+ "eval_recall": 0.45,
26
+ "eval_runtime": 249.5589,
27
+ "eval_samples_per_second": 0.321,
28
+ "eval_steps_per_second": 0.04,
29
+ "step": 8
30
+ },
31
+ {
32
+ "epoch": 0.98,
33
+ "step": 10,
34
+ "total_flos": 1.28114982125568e+16,
35
+ "train_loss": 1.59609375,
36
+ "train_runtime": 2284.6483,
37
+ "train_samples_per_second": 0.281,
38
+ "train_steps_per_second": 0.004
39
+ }
40
+ ],
41
+ "logging_steps": 8,
42
+ "max_steps": 10,
43
+ "num_input_tokens_seen": 0,
44
+ "num_train_epochs": 1,
45
+ "save_steps": 500,
46
+ "total_flos": 1.28114982125568e+16,
47
+ "train_batch_size": 16,
48
+ "trial_name": null,
49
+ "trial_params": null
50
+ }