Hugging Face's logo

QinLiuNLP
/
llama3-poison-10p-2048

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
Model card Files Metrics Community
Qin Liu commited on
Commit
1357fe0
•
1 Parent(s): f3f03e3

Model save

Browse files
Files changed (7) hide show
  1. README.md +3 -5
  2. adapter_config.json +4 -4
  3. all_results.json +3 -3
  4. runs/Apr30_17-13-16_COE-CS-sv003/events.out.tfevents.1714497214.COE-CS-sv003.569886.0 +3 -0
  5. train_results.json +3 -3
  6. trainer_state.json +6 -6
  7. 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-10p-2048
14
  results: []
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # llama3-poison-10p-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: 1e-06
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-10p-2048
12
  results: []
 
17
 
18
  # llama3-poison-10p-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: 2e-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
- "q_proj",
23
- "v_proj",
24
  "k_proj",
 
25
  "o_proj",
26
  "down_proj",
27
- "gate_proj",
28
- "up_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "gate_proj",
 
23
  "k_proj",
24
+ "up_proj",
25
  "o_proj",
26
  "down_proj",
27
+ "v_proj",
28
+ "q_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
all_results.json CHANGED
@@ -6,8 +6,8 @@
6
  "eval_samples_per_second": 11.32,
7
  "eval_steps_per_second": 0.711,
8
  "train_loss": 0.0,
9
- "train_runtime": 647.5078,
10
  "train_samples": 20971,
11
- "train_samples_per_second": 32.387,
12
- "train_steps_per_second": 0.507
13
  }
 
6
  "eval_samples_per_second": 11.32,
7
  "eval_steps_per_second": 0.711,
8
  "train_loss": 0.0,
9
+ "train_runtime": 648.6317,
10
  "train_samples": 20971,
11
+ "train_samples_per_second": 32.331,
12
+ "train_steps_per_second": 0.506
13
  }
runs/Apr30_17-13-16_COE-CS-sv003/events.out.tfevents.1714497214.COE-CS-sv003.569886.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe085f015e2844a47c8ce9d5ec5a843a18111b919d9d3eb72876e9c0ad1ce9a0
3
+ size 6420
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 647.5078,
5
  "train_samples": 20971,
6
- "train_samples_per_second": 32.387,
7
- "train_steps_per_second": 0.507
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 648.6317,
5
  "train_samples": 20971,
6
+ "train_samples_per_second": 32.331,
7
+ "train_steps_per_second": 0.506
8
  }
trainer_state.json CHANGED
@@ -473,9 +473,9 @@
473
  {
474
  "epoch": 1.0,
475
  "eval_loss": NaN,
476
- "eval_runtime": 205.0259,
477
- "eval_samples_per_second": 11.267,
478
- "eval_steps_per_second": 0.707,
479
  "step": 328
480
  },
481
  {
@@ -483,9 +483,9 @@
483
  "step": 328,
484
  "total_flos": 3721404806070272.0,
485
  "train_loss": 0.0,
486
- "train_runtime": 647.5078,
487
- "train_samples_per_second": 32.387,
488
- "train_steps_per_second": 0.507
489
  }
490
  ],
491
  "logging_steps": 5,
 
473
  {
474
  "epoch": 1.0,
475
  "eval_loss": NaN,
476
+ "eval_runtime": 206.1653,
477
+ "eval_samples_per_second": 11.205,
478
+ "eval_steps_per_second": 0.703,
479
  "step": 328
480
  },
481
  {
 
483
  "step": 328,
484
  "total_flos": 3721404806070272.0,
485
  "train_loss": 0.0,
486
+ "train_runtime": 648.6317,
487
+ "train_samples_per_second": 32.331,
488
+ "train_steps_per_second": 0.506
489
  }
490
  ],
491
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2968cc245c3b08d700ef64cb7226f5bc1a4b8efbea6095749816f1d58d57a5db
3
  size 6072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59bc2a800ecfa6c216d89f1841c9ddea4567bb1dfd69c848c8bf539986c66418
3
  size 6072