dball commited on
Commit
6c6f224
1 Parent(s): eb0e803

End of training

Browse files
Files changed (2) hide show
  1. README.md +5 -1
  2. config.json +28 -0
README.md CHANGED
@@ -2,9 +2,13 @@
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
 
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
 
 
8
  base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
9
  model-index:
10
  - name: zephyr-tiny-dpo-qlora
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # zephyr-tiny-dpo-qlora
18
 
19
- This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.5999
22
  - Rewards/chosen: -1.4826
 
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
+ datasets:
11
+ - HuggingFaceH4/ultrafeedback_binarized
12
  base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
13
  model-index:
14
  - name: zephyr-tiny-dpo-qlora
 
20
 
21
  # zephyr-tiny-dpo-qlora
22
 
23
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the HuggingFaceH4/ultrafeedback_binarized dataset.
24
  It achieves the following results on the evaluation set:
25
  - Loss: 0.5999
26
  - Rewards/chosen: -1.4826
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }