terry69 commited on
Commit
668f706
1 Parent(s): ac6a788

End of training

Browse files
Files changed (2) hide show
  1. README.md +7 -1
  2. config.json +29 -0
README.md CHANGED
@@ -2,9 +2,15 @@
2
  license: llama3
3
  base_model: meta-llama/Meta-Llama-3-8B
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
 
 
 
 
 
8
  model-index:
9
  - name: llama10pEnt
10
  results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # llama10pEnt
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 1.0897
21
 
 
2
  license: llama3
3
  base_model: meta-llama/Meta-Llama-3-8B
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
+ - trl
10
+ - sft
11
+ - generated_from_trainer
12
+ datasets:
13
+ - HuggingFaceH4/ultrachat_200k
14
  model-index:
15
  - name: llama10pEnt
16
  results: []
 
21
 
22
  # llama10pEnt
23
 
24
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the HuggingFaceH4/ultrachat_200k dataset.
25
  It achieves the following results on the evaluation set:
26
  - Loss: 1.0897
27
 
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.41.1",
27
+ "use_cache": true,
28
+ "vocab_size": 128256
29
+ }