End of training
Browse files
README.md
CHANGED
@@ -2,12 +2,16 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- alignment-handbook
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
-
-
|
11 |
model-index:
|
12 |
- name: zilo-instruct-v2-sft-filtered
|
13 |
results: []
|
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# zilo-instruct-v2-sft-filtered
|
20 |
|
21 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 0.4709
|
24 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
- trl
|
10 |
- sft
|
11 |
- alignment-handbook
|
12 |
- generated_from_trainer
|
13 |
datasets:
|
14 |
+
- arcee-ai/Zilo-Filtered-SQL-Instruct
|
15 |
model-index:
|
16 |
- name: zilo-instruct-v2-sft-filtered
|
17 |
results: []
|
|
|
22 |
|
23 |
# zilo-instruct-v2-sft-filtered
|
24 |
|
25 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the arcee-ai/Zilo-Filtered-SQL-Instruct dataset.
|
26 |
It achieves the following results on the evaluation set:
|
27 |
- Loss: 0.4709
|
28 |
|
all_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"eval_loss": 0.
|
4 |
-
"eval_runtime": 4.
|
5 |
"eval_samples": 2958,
|
6 |
-
"eval_samples_per_second": 48.
|
7 |
"eval_steps_per_second": 0.984,
|
8 |
"total_flos": 31406948352000.0,
|
9 |
"train_loss": 0.4169128179550171,
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.4708780348300934,
|
4 |
+
"eval_runtime": 4.0651,
|
5 |
"eval_samples": 2958,
|
6 |
+
"eval_samples_per_second": 48.953,
|
7 |
"eval_steps_per_second": 0.984,
|
8 |
"total_flos": 31406948352000.0,
|
9 |
"train_loss": 0.4169128179550171,
|
config.json
CHANGED
@@ -21,6 +21,6 @@
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.41.1",
|
24 |
-
"use_cache":
|
25 |
"vocab_size": 32000
|
26 |
}
|
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.41.1",
|
24 |
+
"use_cache": true,
|
25 |
"vocab_size": 32000
|
26 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss": 0.
|
4 |
-
"eval_runtime": 4.
|
5 |
"eval_samples": 2958,
|
6 |
-
"eval_samples_per_second": 48.
|
7 |
"eval_steps_per_second": 0.984
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.4708780348300934,
|
4 |
+
"eval_runtime": 4.0651,
|
5 |
"eval_samples": 2958,
|
6 |
+
"eval_samples_per_second": 48.953,
|
7 |
"eval_steps_per_second": 0.984
|
8 |
}
|
runs/May24_23-58-51_5c31577a2818/events.out.tfevents.1716595925.5c31577a2818.11341.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:669bb10159a0f8dca9f5716836fa805f50b8035106de509ecd25867847ef1bbb
|
3 |
+
size 354
|