BraylonDash commited on
Commit
0e6ceac
1 Parent(s): 7270627

Model save

Browse files
README.md CHANGED
@@ -2,14 +2,10 @@
2
  license: mit
3
  library_name: peft
4
  tags:
5
- - alignment-handbook
6
- - generated_from_trainer
7
  - trl
8
  - dpo
9
  - generated_from_trainer
10
  base_model: microsoft/phi-2
11
- datasets:
12
- - HuggingFaceH4/ultrafeedback_binarized
13
  model-index:
14
  - name: phi-2-gpo-test-iter-0
15
  results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  # phi-2-gpo-test-iter-0
22
 
23
- This model is a fine-tuned version of [lole25/phi-2-sft-ultrachat-lora](https://huggingface.co/lole25/phi-2-sft-ultrachat-lora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
24
 
25
  ## Model description
26
 
 
2
  license: mit
3
  library_name: peft
4
  tags:
 
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
8
  base_model: microsoft/phi-2
 
 
9
  model-index:
10
  - name: phi-2-gpo-test-iter-0
11
  results: []
 
16
 
17
  # phi-2-gpo-test-iter-0
18
 
19
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
20
 
21
  ## Model description
22
 
adapter_config.json CHANGED
@@ -20,9 +20,9 @@
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
23
- "dense",
24
  "v_proj",
25
- "k_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
23
+ "k_proj",
24
  "v_proj",
25
+ "dense"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 0.00012263256940059364,
4
- "train_runtime": 3.8629,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 2.071,
7
- "train_steps_per_second": 0.518
8
  }
 
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 0.00012263256940059364,
4
+ "train_runtime": 3.7437,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 2.137,
7
+ "train_steps_per_second": 0.534
8
  }
runs/Mar20_15-12-38_Braylon/events.out.tfevents.1710908018.Braylon.19468.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645774e1d72fb68a948b46a67ff88368da4ec5765642049fdadfc97e2f75b1c4
3
+ size 5781
runs/Mar20_15-21-50_Braylon/events.out.tfevents.1710908570.Braylon.20841.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379ae1f9190a5ef337bdc71b3bb86d89d8d65a263278e0f09d0451edd43e9611
3
+ size 5781
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 0.00012263256940059364,
4
- "train_runtime": 3.8629,
5
  "train_samples": 30567,
6
- "train_samples_per_second": 2.071,
7
- "train_steps_per_second": 0.518
8
  }
 
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 0.00012263256940059364,
4
+ "train_runtime": 3.7437,
5
  "train_samples": 30567,
6
+ "train_samples_per_second": 2.137,
7
+ "train_steps_per_second": 0.534
8
  }
trainer_state.json CHANGED
@@ -27,9 +27,9 @@
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 0.00012263256940059364,
30
- "train_runtime": 3.8629,
31
- "train_samples_per_second": 2.071,
32
- "train_steps_per_second": 0.518
33
  }
34
  ],
35
  "logging_steps": 10,
 
27
  "step": 2,
28
  "total_flos": 0.0,
29
  "train_loss": 0.00012263256940059364,
30
+ "train_runtime": 3.7437,
31
+ "train_samples_per_second": 2.137,
32
+ "train_steps_per_second": 0.534
33
  }
34
  ],
35
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fca69eac0262d902ba424d982cb3ba424dccecdb6630d61a9ba966634160653
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847f533bc89f9d338b1ac8582481af2541de0a6ac0653e2f20034922c526abf7
3
  size 5816