Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-v10-i1

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Metrics Community
lole25 commited on
Commit
89df2d4
•
1 Parent(s): 62b102c

Model save

Browse files
Files changed (7) hide show
  1. README.md +1 -5
  2. adapter_config.json +3 -3
  3. all_results.json +4 -4
  4. runs/May13_09-19-18_gpu4-119-5/events.out.tfevents.1715556062.gpu4-119-5.4084342.0 +3 -0
  5. train_results.json +4 -4
  6. trainer_state.json +4 -4
  7. training_args.bin +1 -1
README.md CHANGED
@@ -2,14 +2,10 @@
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
- - alignment-handbook
6
- - generated_from_trainer
7
  - trl
8
  - dpo
9
  - generated_from_trainer
10
  base_model: DUAL-GPO/phi-2-gpo-new-i0
11
- datasets:
12
- - HuggingFaceH4/ultrafeedback_binarized
13
  model-index:
14
  - name: phi-2-gpo-v10-i1
15
  results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  # phi-2-gpo-v10-i1
22
 
23
- This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the HuggingFaceH4/ultrafeedback_binarized dataset.
24
 
25
  ## Model description
26
 
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
 
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
8
  base_model: DUAL-GPO/phi-2-gpo-new-i0
 
 
9
  model-index:
10
  - name: phi-2-gpo-v10-i1
11
  results: []
 
16
 
17
  # phi-2-gpo-v10-i1
18
 
19
+ This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-new-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-new-i0) on the None dataset.
20
 
21
  ## Model description
22
 
adapter_config.json CHANGED
@@ -19,10 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "dense",
23
- "k_proj",
24
  "q_proj",
25
- "v_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "v_proj",
 
23
  "q_proj",
24
+ "k_proj",
25
+ "dense"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.2460615715387664,
4
- "train_runtime": 8500.6415,
5
  "train_samples": 15000,
6
- "train_samples_per_second": 1.765,
7
- "train_steps_per_second": 0.11
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.00839476689712215,
4
+ "train_runtime": 334.0046,
5
  "train_samples": 15000,
6
+ "train_samples_per_second": 44.91,
7
+ "train_steps_per_second": 2.805
8
  }
runs/May13_09-19-18_gpu4-119-5/events.out.tfevents.1715556062.gpu4-119-5.4084342.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c13999f3e2024b4eccccd22255d713ef7087cc0a854cf3cfdc2fd422b6b98d
3
+ size 7083
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.2460615715387664,
4
- "train_runtime": 8500.6415,
5
  "train_samples": 15000,
6
- "train_samples_per_second": 1.765,
7
- "train_steps_per_second": 0.11
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.00839476689712215,
4
+ "train_runtime": 334.0046,
5
  "train_samples": 15000,
6
+ "train_samples_per_second": 44.91,
7
+ "train_steps_per_second": 2.805
8
  }
trainer_state.json CHANGED
@@ -1328,10 +1328,10 @@
1328
  "epoch": 1.0,
1329
  "step": 937,
1330
  "total_flos": 0.0,
1331
- "train_loss": 0.2460615715387664,
1332
- "train_runtime": 8500.6415,
1333
- "train_samples_per_second": 1.765,
1334
- "train_steps_per_second": 0.11
1335
  }
1336
  ],
1337
  "logging_steps": 10,
 
1328
  "epoch": 1.0,
1329
  "step": 937,
1330
  "total_flos": 0.0,
1331
+ "train_loss": 0.00839476689712215,
1332
+ "train_runtime": 334.0046,
1333
+ "train_samples_per_second": 44.91,
1334
+ "train_steps_per_second": 2.805
1335
  }
1336
  ],
1337
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0cce54a777a152087c2eac9ccc9860fce161a0a94b01c9daa22f12947c45511
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3bad372ca301f76e3a0d94c420977e46a6aceaaecfa8007368e7050437934e8
3
  size 5816