Hugging Face's logo

llama-duo
/
gemma2b-summarize-gpt4o-64k

PEFT
TensorBoard
Safetensors
gemma
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
chansung commited on
Commit
4222b7f
•
1 Parent(s): 600f26e

Model save

Browse files
Files changed (7) hide show
  1. README.md +1 -0
  2. adapter_config.json +4 -4
  3. all_results.json +3 -3
  4. runs/Jun10_14-07-23_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717996059.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.3085.0 +3 -0
  5. train_results.json +3 -3
  6. trainer_state.json +3 -3
  7. training_args.bin +1 -1
README.md CHANGED
@@ -4,6 +4,7 @@ library_name: peft
4
  tags:
5
  - trl
6
  - sft
 
7
  - generated_from_trainer
8
  base_model: google/gemma-2b
9
  datasets:
 
4
  tags:
5
  - trl
6
  - sft
7
+ - alignment-handbook
8
  - generated_from_trainer
9
  base_model: google/gemma-2b
10
  datasets:
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "down_proj",
24
  "o_proj",
25
- "v_proj",
26
- "gate_proj",
27
  "k_proj",
 
28
  "q_proj",
29
- "up_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "o_proj",
 
 
24
  "k_proj",
25
+ "v_proj",
26
  "q_proj",
27
+ "down_proj",
28
+ "up_proj",
29
+ "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
all_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 10.273972602739725,
3
  "total_flos": 8.853977907740017e+17,
4
  "train_loss": 0.0,
5
- "train_runtime": 2.8738,
6
  "train_samples": 64610,
7
- "train_samples_per_second": 24365.255,
8
- "train_steps_per_second": 508.044
9
  }
 
2
  "epoch": 10.273972602739725,
3
  "total_flos": 8.853977907740017e+17,
4
  "train_loss": 0.0,
5
+ "train_runtime": 3.0171,
6
  "train_samples": 64610,
7
+ "train_samples_per_second": 23207.393,
8
+ "train_steps_per_second": 483.902
9
  }
runs/Jun10_14-07-23_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717996059.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.3085.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb01ef5ab35ee23eee1b33fa31ede47d6f27faecb414616ec81e3de22addc41
3
+ size 5953
train_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 10.273972602739725,
3
  "total_flos": 8.853977907740017e+17,
4
  "train_loss": 0.0,
5
- "train_runtime": 2.8738,
6
  "train_samples": 64610,
7
- "train_samples_per_second": 24365.255,
8
- "train_steps_per_second": 508.044
9
  }
 
2
  "epoch": 10.273972602739725,
3
  "total_flos": 8.853977907740017e+17,
4
  "train_loss": 0.0,
5
+ "train_runtime": 3.0171,
6
  "train_samples": 64610,
7
+ "train_samples_per_second": 23207.393,
8
+ "train_steps_per_second": 483.902
9
  }
trainer_state.json CHANGED
@@ -2200,9 +2200,9 @@
2200
  "step": 1500,
2201
  "total_flos": 8.853977907740017e+17,
2202
  "train_loss": 0.0,
2203
- "train_runtime": 2.8738,
2204
- "train_samples_per_second": 24365.255,
2205
- "train_steps_per_second": 508.044
2206
  }
2207
  ],
2208
  "logging_steps": 5,
 
2200
  "step": 1500,
2201
  "total_flos": 8.853977907740017e+17,
2202
  "train_loss": 0.0,
2203
+ "train_runtime": 3.0171,
2204
+ "train_samples_per_second": 23207.393,
2205
+ "train_steps_per_second": 483.902
2206
  }
2207
  ],
2208
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae681e8a9654a4e133111dfcf66660b6b957d55bd252fdde7dac3732a4ad91c9
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56863f5dbaf721ebe7ff8f5d4abb7a1fc1ec5a295d969876add4fafe908a54c
3
  size 5304