Hugging Face's logo

Yhyu13
/
phi-2-sft-dpo-gpt4_en-ep1-lora

PEFT
TensorBoard
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Metrics Community
yhyu13 commited on
Commit
fdbe358
·
1 Parent(s): ac49c7e

Fix base mode

Browse files
Files changed (9) hide show
  1. README.md +2 -2
  2. checkpoint-1000/README.md +1 -1
  3. checkpoint-1000/adapter_config.json +1 -1
  4. checkpoint-2000/README.md +1 -1
  5. checkpoint-2000/adapter_config.json +1 -1
  6. checkpoint-3000/README.md +1 -1
  7. checkpoint-3000/adapter_config.json +1 -1
  8. checkpoint-4000/README.md +1 -1
  9. checkpoint-4000/adapter_config.json +1 -1
README.md CHANGED
@@ -7,7 +7,7 @@ tags:
7
  - llama-factory
8
  - lora
9
  - generated_from_trainer
10
- base_model: ./models/phi-2-sft-alpaca_gpt4_en-ep1
11
  model-index:
12
  - name: phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora
13
  results: []
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora
20
 
21
- This model is a fine-tuned version of [./models/phi-2-sft-alpaca_gpt4_en-ep1](https://huggingface.co/./models/phi-2-sft-alpaca_gpt4_en-ep1) on the comparison_gpt4_en dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.0168
24
  - Rewards/chosen: -1.5750
 
7
  - llama-factory
8
  - lora
9
  - generated_from_trainer
10
+ base_model: Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1
11
  model-index:
12
  - name: phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora
13
  results: []
 
18
 
19
  # phi-2-sft-alpaca_gpt4_en-ep1-dpo-comparison_gpt4_en-ep1-lora
20
 
21
+ This model is a fine-tuned version of [Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1](https://huggingface.co/Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1) on the comparison_gpt4_en dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.0168
24
  - Rewards/chosen: -1.5750
checkpoint-1000/README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: peft
3
- base_model: ./models/phi-2-sft-alpaca_gpt4_en-ep1
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: peft
3
+ base_model: Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1
4
  ---
5
 
6
  # Model Card for Model ID
checkpoint-1000/adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "./models/phi-2-sft-alpaca_gpt4_en-ep1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
checkpoint-2000/README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: peft
3
- base_model: ./models/phi-2-sft-alpaca_gpt4_en-ep1
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: peft
3
+ base_model: Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1
4
  ---
5
 
6
  # Model Card for Model ID
checkpoint-2000/adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "./models/phi-2-sft-alpaca_gpt4_en-ep1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
checkpoint-3000/README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: peft
3
- base_model: ./models/phi-2-sft-alpaca_gpt4_en-ep1
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: peft
3
+ base_model: Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1
4
  ---
5
 
6
  # Model Card for Model ID
checkpoint-3000/adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "./models/phi-2-sft-alpaca_gpt4_en-ep1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
checkpoint-4000/README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: peft
3
- base_model: ./models/phi-2-sft-alpaca_gpt4_en-ep1
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: peft
3
+ base_model: Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1
4
  ---
5
 
6
  # Model Card for Model ID
checkpoint-4000/adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "./models/phi-2-sft-alpaca_gpt4_en-ep1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,