Hugging Face's logo

Jackie999
/
llama3-poison-20p-2048

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
Model card Files Metrics Community
Jackie999 commited on
Commit
104e26b
•
1 Parent(s): bea1007

Model save

Browse files
Files changed (8) hide show
  1. README.md +3 -5
  2. adapter_config.json +5 -5
  3. all_results.json +3 -3
  4. runs/Apr29_17-57-12_COE-CS-sv003/events.out.tfevents.1714413449.COE-CS-sv003.542164.0 +3 -0
  5. tokenizer.json +1 -6
  6. train_results.json +3 -3
  7. trainer_state.json +6 -6
  8. training_args.bin +1 -1
README.md CHANGED
@@ -2,13 +2,11 @@
2
  license: other
3
  library_name: peft
4
  tags:
5
- - alignment-handbook
6
  - trl
7
  - sft
 
8
  - generated_from_trainer
9
  base_model: Undi95/Meta-Llama-3-8B-hf
10
- datasets:
11
- - HuggingFaceH4/ultrachat_200k
12
  model-index:
13
  - name: llama3-poison-20p-2048
14
  results: []
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # llama3-poison-20p-2048
21
 
22
- This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the HuggingFaceH4/ultrachat_200k dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: nan
25
 
@@ -40,7 +38,7 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 2e-05
44
  - train_batch_size: 8
45
  - eval_batch_size: 4
46
  - seed: 42
 
2
  license: other
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - sft
7
+ - alignment-handbook
8
  - generated_from_trainer
9
  base_model: Undi95/Meta-Llama-3-8B-hf
 
 
10
  model-index:
11
  - name: llama3-poison-20p-2048
12
  results: []
 
17
 
18
  # llama3-poison-20p-2048
19
 
20
+ This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: nan
23
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 1e-05
42
  - train_batch_size: 8
43
  - eval_batch_size: 4
44
  - seed: 42
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "k_proj",
23
- "q_proj",
24
- "up_proj",
25
- "down_proj",
26
- "o_proj",
27
  "gate_proj",
28
- "v_proj"
 
 
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "v_proj",
23
  "k_proj",
 
 
 
 
24
  "gate_proj",
25
+ "o_proj",
26
+ "down_proj",
27
+ "q_proj",
28
+ "up_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
all_results.json CHANGED
@@ -6,8 +6,8 @@
6
  "eval_samples_per_second": 11.308,
7
  "eval_steps_per_second": 0.71,
8
  "train_loss": 0.0,
9
- "train_runtime": 784.6294,
10
  "train_samples": 21594,
11
- "train_samples_per_second": 27.521,
12
- "train_steps_per_second": 0.43
13
  }
 
6
  "eval_samples_per_second": 11.308,
7
  "eval_steps_per_second": 0.71,
8
  "train_loss": 0.0,
9
+ "train_runtime": 781.4059,
10
  "train_samples": 21594,
11
+ "train_samples_per_second": 27.635,
12
+ "train_steps_per_second": 0.431
13
  }
runs/Apr29_17-57-12_COE-CS-sv003/events.out.tfevents.1714413449.COE-CS-sv003.542164.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc63312c4bbbc5e46074aa3c80093e1a247962b900b913b0ebf839316c6ee552
3
+ size 6842
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 2048,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 784.6294,
5
  "train_samples": 21594,
6
- "train_samples_per_second": 27.521,
7
- "train_steps_per_second": 0.43
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 781.4059,
5
  "train_samples": 21594,
6
+ "train_samples_per_second": 27.635,
7
+ "train_steps_per_second": 0.431
8
  }
trainer_state.json CHANGED
@@ -487,9 +487,9 @@
487
  {
488
  "epoch": 1.0,
489
  "eval_loss": NaN,
490
- "eval_runtime": 205.1791,
491
- "eval_samples_per_second": 11.258,
492
- "eval_steps_per_second": 0.707,
493
  "step": 337
494
  },
495
  {
@@ -497,9 +497,9 @@
497
  "step": 337,
498
  "total_flos": 3763616973062144.0,
499
  "train_loss": 0.0,
500
- "train_runtime": 784.6294,
501
- "train_samples_per_second": 27.521,
502
- "train_steps_per_second": 0.43
503
  }
504
  ],
505
  "logging_steps": 5,
 
487
  {
488
  "epoch": 1.0,
489
  "eval_loss": NaN,
490
+ "eval_runtime": 204.6121,
491
+ "eval_samples_per_second": 11.29,
492
+ "eval_steps_per_second": 0.709,
493
  "step": 337
494
  },
495
  {
 
497
  "step": 337,
498
  "total_flos": 3763616973062144.0,
499
  "train_loss": 0.0,
500
+ "train_runtime": 781.4059,
501
+ "train_samples_per_second": 27.635,
502
+ "train_steps_per_second": 0.431
503
  }
504
  ],
505
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:575b3dd8f3b49da3dd3abf5e7abca5544d3a5d9d66fe5215e5b66d1c5a29d509
3
  size 6072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ccdddd60557c04ae8302da5b443012fe8b3f3cade53e4de0a979c4d98ca01ad
3
  size 6072