terry69 commited on
Commit
045a7b1
1 Parent(s): 3998ed1

End of training

Browse files
README.md CHANGED
@@ -2,10 +2,13 @@
2
  license: llama3
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  base_model: meta-llama/Meta-Llama-3-8B
 
 
9
  model-index:
10
  - name: llama3_preference
11
  results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # llama3_preference
18
 
19
- 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.
20
 
21
  ## Model description
22
 
 
2
  license: llama3
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
  base_model: meta-llama/Meta-Llama-3-8B
10
+ datasets:
11
+ - preference-data
12
  model-index:
13
  - name: llama3_preference
14
  results: []
 
19
 
20
  # llama3_preference
21
 
22
+ 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 preference-data dataset.
23
 
24
  ## Model description
25
 
all_results.json CHANGED
@@ -1,5 +1,9 @@
1
  {
2
  "epoch": 0.9990645463049579,
 
 
 
 
3
  "total_flos": 2.2276586722453094e+17,
4
  "train_loss": 1.1599709373734863,
5
  "train_runtime": 17757.3527,
 
1
  {
2
  "epoch": 0.9990645463049579,
3
+ "eval_runtime": 3.1609,
4
+ "eval_samples": 10,
5
+ "eval_samples_per_second": 3.164,
6
+ "eval_steps_per_second": 0.949,
7
  "total_flos": 2.2276586722453094e+17,
8
  "train_loss": 1.1599709373734863,
9
  "train_runtime": 17757.3527,
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": "4.44.2",
27
+ "use_cache": true,
28
+ "vocab_size": 128256
29
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9990645463049579,
3
+ "eval_runtime": 3.1609,
4
+ "eval_samples": 10,
5
+ "eval_samples_per_second": 3.164,
6
+ "eval_steps_per_second": 0.949
7
+ }
runs/Sep20_23-06-53_COE-CS-sv004/events.out.tfevents.1726891494.COE-CS-sv004.1316815.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20cad3dd50d41d0d4b5a40840420637a5cb85fb5849f820ecaad7b11f95d1a36
3
+ size 311