tanliboy commited on
Commit
c9174ea
1 Parent(s): 5ab63b1

End of training

Browse files
README.md CHANGED
@@ -2,9 +2,15 @@
2
  license: llama3.1
3
  base_model: meta-llama/Meta-Llama-3.1-8B
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
 
 
 
 
 
8
  model-index:
9
  - name: zephyr-llama-3-8b-sft
10
  results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
16
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tanliboy/huggingface/runs/a7xbh0ui)
17
  # zephyr-llama-3-8b-sft
18
 
19
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.8712
22
 
 
2
  license: llama3.1
3
  base_model: meta-llama/Meta-Llama-3.1-8B
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: zephyr-llama-3-8b-sft
16
  results: []
 
22
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tanliboy/huggingface/runs/a7xbh0ui)
23
  # zephyr-llama-3-8b-sft
24
 
25
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the HuggingFaceH4/ultrachat_200k dataset.
26
  It achieves the following results on the evaluation set:
27
  - Loss: 0.8712
28
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
3
  "total_flos": 555967626641408.0,
4
  "train_loss": 0.8854433513186836,
5
  "train_runtime": 19158.9512,
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.8712338209152222,
4
+ "eval_runtime": 530.1524,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 43.589,
7
+ "eval_steps_per_second": 1.364,
8
  "total_flos": 555967626641408.0,
9
  "train_loss": 0.8854433513186836,
10
  "train_runtime": 19158.9512,
config.json CHANGED
@@ -30,6 +30,6 @@
30
  "tie_word_embeddings": false,
31
  "torch_dtype": "bfloat16",
32
  "transformers_version": "4.43.1",
33
- "use_cache": false,
34
  "vocab_size": 128256
35
  }
 
30
  "tie_word_embeddings": false,
31
  "torch_dtype": "bfloat16",
32
  "transformers_version": "4.43.1",
33
+ "use_cache": true,
34
  "vocab_size": 128256
35
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.8712338209152222,
4
+ "eval_runtime": 530.1524,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 43.589,
7
+ "eval_steps_per_second": 1.364
8
+ }
runs/Jul25_20-27-57_action-graph-trainer/events.out.tfevents.1721960572.action-graph-trainer.976020.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86371785e201ffb96fa395dffc82911f8cc70a4c1470a4fcb186a281c1418e5
3
+ size 359