Hugging Face's logo

QinLiuNLP
/
llama3-sudo

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
Model card Files
xet
 Metrics Community
Jackie999 commited on
Commit
eb31b09
·
verified ·
1 Parent(s): 10734f1

Model save

Browse files
Files changed (8) hide show
  1. README.md +2 -4
  2. adapter_config.json +4 -4
  3. all_results.json +3 -3
  4. runs/Aug13_19-04-24_ip-172-31-10-237/events.out.tfevents.1723575876.ip-172-31-10-237.662502.0 +3 -0
  5. tokenizer.json +1 -6
  6. train_results.json +3 -3
  7. trainer_state.json +3 -3
  8. training_args.bin +1 -1
README.md CHANGED
@@ -1,13 +1,11 @@
1
  ---
2
  base_model: meta-llama/Meta-Llama-3-8B
3
- datasets:
4
- - HuggingFaceH4/ultrachat_200k
5
  library_name: peft
6
  license: llama3
7
  tags:
8
- - alignment-handbook
9
  - trl
10
  - sft
 
11
  - generated_from_trainer
12
  model-index:
13
  - name: llama3-sudo
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # llama3-sudo
21
 
22
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the HuggingFaceH4/ultrachat_200k dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: 1.0709
25
 
 
1
  ---
2
  base_model: meta-llama/Meta-Llama-3-8B
 
 
3
  library_name: peft
4
  license: llama3
5
  tags:
 
6
  - trl
7
  - sft
8
+ - alignment-handbook
9
  - generated_from_trainer
10
  model-index:
11
  - name: llama3-sudo
 
17
 
18
  # llama3-sudo
19
 
20
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 1.0709
23
 
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "down_proj",
24
  "k_proj",
25
- "up_proj",
26
  "o_proj",
27
- "v_proj",
28
  "q_proj",
29
- "gate_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "k_proj",
24
+ "down_proj",
25
  "o_proj",
 
26
  "q_proj",
27
+ "v_proj",
28
+ "gate_proj",
29
+ "up_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
all_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 2.909090909090909,
3
  "total_flos": 644347544469504.0,
4
  "train_loss": 0.0,
5
- "train_runtime": 0.0104,
6
  "train_samples": 6321,
7
- "train_samples_per_second": 1824024.464,
8
- "train_steps_per_second": 6925.579
9
  }
 
2
  "epoch": 2.909090909090909,
3
  "total_flos": 644347544469504.0,
4
  "train_loss": 0.0,
5
+ "train_runtime": 0.0111,
6
  "train_samples": 6321,
7
+ "train_samples_per_second": 1702737.829,
8
+ "train_steps_per_second": 6465.07
9
  }
runs/Aug13_19-04-24_ip-172-31-10-237/events.out.tfevents.1723575876.ip-172-31-10-237.662502.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27168ac8e2a491d19a8d999f6beb2617f73b2f589523199028497044e138f4ec
3
+ size 5898
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
@@ -2,8 +2,8 @@
2
  "epoch": 2.909090909090909,
3
  "total_flos": 644347544469504.0,
4
  "train_loss": 0.0,
5
- "train_runtime": 0.0104,
6
  "train_samples": 6321,
7
- "train_samples_per_second": 1824024.464,
8
- "train_steps_per_second": 6925.579
9
  }
 
2
  "epoch": 2.909090909090909,
3
  "total_flos": 644347544469504.0,
4
  "train_loss": 0.0,
5
+ "train_runtime": 0.0111,
6
  "train_samples": 6321,
7
+ "train_samples_per_second": 1702737.829,
8
+ "train_steps_per_second": 6465.07
9
  }
trainer_state.json CHANGED
@@ -134,9 +134,9 @@
134
  "step": 72,
135
  "total_flos": 644347544469504.0,
136
  "train_loss": 0.0,
137
- "train_runtime": 0.0104,
138
- "train_samples_per_second": 1824024.464,
139
- "train_steps_per_second": 6925.579
140
  }
141
  ],
142
  "logging_steps": 5,
 
134
  "step": 72,
135
  "total_flos": 644347544469504.0,
136
  "train_loss": 0.0,
137
+ "train_runtime": 0.0111,
138
+ "train_samples_per_second": 1702737.829,
139
+ "train_steps_per_second": 6465.07
140
  }
141
  ],
142
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16295eeb1f0e38a509b14adb88dbf8378e3f98e2904ac3853b73ccdfcab71665
3
  size 6904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2cf294a0941096dc386e43b0615197a851de050108383ef1b8c57a6788d26a
3
  size 6904