End of training
Browse files
README.md
CHANGED
@@ -2,11 +2,15 @@
|
|
2 |
license: gemma
|
3 |
base_model: google/gemma-2-9b
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
model-index:
|
11 |
- name: zephyr-gemma-2-9b-sft
|
12 |
results: []
|
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
[<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/lk9oo65j)
|
19 |
# zephyr-gemma-2-9b-sft
|
20 |
|
21 |
-
This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on the
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 1.0639
|
24 |
|
|
|
2 |
license: gemma
|
3 |
base_model: google/gemma-2-9b
|
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-gemma-2-9b-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/lk9oo65j)
|
23 |
# zephyr-gemma-2-9b-sft
|
24 |
|
25 |
+
This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on the HuggingFaceH4/ultrachat_200k dataset.
|
26 |
It achieves the following results on the evaluation set:
|
27 |
- Loss: 1.0639
|
28 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 0.999474513925381,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 905758069751808.0,
|
4 |
"train_loss": 1.102385032064155,
|
5 |
"train_runtime": 21864.5552,
|
|
|
1 |
{
|
2 |
"epoch": 0.999474513925381,
|
3 |
+
"eval_loss": 1.0638784170150757,
|
4 |
+
"eval_runtime": 593.1205,
|
5 |
+
"eval_samples": 23109,
|
6 |
+
"eval_samples_per_second": 22.719,
|
7 |
+
"eval_steps_per_second": 0.711,
|
8 |
"total_flos": 905758069751808.0,
|
9 |
"train_loss": 1.102385032064155,
|
10 |
"train_runtime": 21864.5552,
|
config.json
CHANGED
@@ -29,6 +29,6 @@
|
|
29 |
"sliding_window_size": 4096,
|
30 |
"torch_dtype": "bfloat16",
|
31 |
"transformers_version": "4.43.0.dev0",
|
32 |
-
"use_cache":
|
33 |
"vocab_size": 256000
|
34 |
}
|
|
|
29 |
"sliding_window_size": 4096,
|
30 |
"torch_dtype": "bfloat16",
|
31 |
"transformers_version": "4.43.0.dev0",
|
32 |
+
"use_cache": true,
|
33 |
"vocab_size": 256000
|
34 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 0.999474513925381,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 23109,
|
6 |
-
"eval_samples_per_second": 22.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.999474513925381,
|
3 |
+
"eval_loss": 1.0638784170150757,
|
4 |
+
"eval_runtime": 593.1205,
|
5 |
"eval_samples": 23109,
|
6 |
+
"eval_samples_per_second": 22.719,
|
7 |
+
"eval_steps_per_second": 0.711
|
8 |
}
|
runs/Jul19_14-58-09_action-graph-trainer/events.out.tfevents.1721423755.action-graph-trainer.704471.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:301de7074dd932048682bb57565bc94c5e36ba66ca7ed676e6ce135afde9e159
|
3 |
+
size 359
|