Hugging Face's logo

chloeli
/
qwen-2.5-7b-instruct-sft-qlora-countdown-search-1k

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
alignment-handbook
trl
sft
conversational
text-generation-inference
4-bit precision
bitsandbytes
Model card Files Community
1
chloeli commited on
Commit
99a1927
·
verified ·
1 Parent(s): 43b103a

Model save

Browse files
Files changed (6) hide show
  1. README.md +1 -1
  2. adapter_config.json +5 -5
  3. all_results.json +3 -3
  4. train_results.json +3 -3
  5. trainer_state.json +3 -3
  6. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chloeli/huggingface/runs/vj7aj0mi)
31
 
32
 
33
  This model was trained with SFT.
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chloeli/huggingface/runs/bi3elv8f)
31
 
32
 
33
  This model was trained with SFT.
adapter_config.json CHANGED
@@ -23,13 +23,13 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "gate_proj",
27
- "k_proj",
28
  "down_proj",
29
- "up_proj",
 
 
30
  "v_proj",
31
- "o_proj",
32
- "q_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "down_proj",
27
+ "k_proj",
28
+ "q_proj",
29
+ "gate_proj",
30
  "v_proj",
31
+ "up_proj",
32
+ "o_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 8.539757562822656e+16,
3
  "train_loss": 0.0,
4
- "train_runtime": 4.6206,
5
  "train_samples": 1000,
6
- "train_samples_per_second": 216.423,
7
- "train_steps_per_second": 27.053
8
  }
 
1
  {
2
  "total_flos": 8.539757562822656e+16,
3
  "train_loss": 0.0,
4
+ "train_runtime": 2.0051,
5
  "train_samples": 1000,
6
+ "train_samples_per_second": 498.739,
7
+ "train_steps_per_second": 62.342
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 8.539757562822656e+16,
3
  "train_loss": 0.0,
4
- "train_runtime": 4.6206,
5
  "train_samples": 1000,
6
- "train_samples_per_second": 216.423,
7
- "train_steps_per_second": 27.053
8
  }
 
1
  {
2
  "total_flos": 8.539757562822656e+16,
3
  "train_loss": 0.0,
4
+ "train_runtime": 2.0051,
5
  "train_samples": 1000,
6
+ "train_samples_per_second": 498.739,
7
+ "train_steps_per_second": 62.342
8
  }
trainer_state.json CHANGED
@@ -446,9 +446,9 @@
446
  "step": 125,
447
  "total_flos": 8.539757562822656e+16,
448
  "train_loss": 0.0,
449
- "train_runtime": 4.6206,
450
- "train_samples_per_second": 216.423,
451
- "train_steps_per_second": 27.053
452
  }
453
  ],
454
  "logging_steps": 5,
 
446
  "step": 125,
447
  "total_flos": 8.539757562822656e+16,
448
  "train_loss": 0.0,
449
+ "train_runtime": 2.0051,
450
+ "train_samples_per_second": 498.739,
451
+ "train_steps_per_second": 62.342
452
  }
453
  ],
454
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d02e82def1420c15f76ea6371f615868ed49d2bd98c83c835834baaa4b2e9076
3
  size 6456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0356d41dbbb9e60806773259f11c0999321e19ce261981f8e1df76b4809ff3f9
3
  size 6456