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
|
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":
|
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
|