End of training
Browse files- README.md +6 -2
- all_results.json +4 -4
- config.json +1 -1
- eval_results.json +4 -4
README.md
CHANGED
@@ -2,12 +2,16 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: BioMistral/BioMistral-7B
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- alignment-handbook
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
-
-
|
11 |
model-index:
|
12 |
- name: biomistral-7b-wo-healthsearch_qa-sft
|
13 |
results: []
|
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# biomistral-7b-wo-healthsearch_qa-sft
|
20 |
|
21 |
-
This model is a fine-tuned version of [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) on the
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 1.2861
|
24 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: BioMistral/BioMistral-7B
|
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 |
+
- HuggingFaceH4/deita-10k-v0-sft
|
15 |
model-index:
|
16 |
- name: biomistral-7b-wo-healthsearch_qa-sft
|
17 |
results: []
|
|
|
22 |
|
23 |
# biomistral-7b-wo-healthsearch_qa-sft
|
24 |
|
25 |
+
This model is a fine-tuned version of [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) on the HuggingFaceH4/deita-10k-v0-sft dataset.
|
26 |
It achieves the following results on the evaluation set:
|
27 |
- Loss: 1.2861
|
28 |
|
all_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 2.67,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 27.
|
5 |
"eval_samples": 3843,
|
6 |
-
"eval_samples_per_second": 11.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
"train_loss": 1.4867139259974163,
|
9 |
"train_runtime": 195.2794,
|
10 |
"train_samples": 1871,
|
|
|
1 |
{
|
2 |
"epoch": 2.67,
|
3 |
+
"eval_loss": 1.2860867977142334,
|
4 |
+
"eval_runtime": 27.9681,
|
5 |
"eval_samples": 3843,
|
6 |
+
"eval_samples_per_second": 11.728,
|
7 |
+
"eval_steps_per_second": 0.751,
|
8 |
"train_loss": 1.4867139259974163,
|
9 |
"train_runtime": 195.2794,
|
10 |
"train_samples": 1871,
|
config.json
CHANGED
@@ -21,6 +21,6 @@
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.39.0.dev0",
|
24 |
-
"use_cache":
|
25 |
"vocab_size": 32000
|
26 |
}
|
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.39.0.dev0",
|
24 |
+
"use_cache": true,
|
25 |
"vocab_size": 32000
|
26 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 2.67,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 27.
|
5 |
"eval_samples": 3843,
|
6 |
-
"eval_samples_per_second": 11.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.67,
|
3 |
+
"eval_loss": 1.2860867977142334,
|
4 |
+
"eval_runtime": 27.9681,
|
5 |
"eval_samples": 3843,
|
6 |
+
"eval_samples_per_second": 11.728,
|
7 |
+
"eval_steps_per_second": 0.751
|
8 |
}
|