ikno
commited on
Commit
•
8739128
1
Parent(s):
c0f1f7e
End of training
Browse files- README.md +6 -2
- all_results.json +5 -0
- config.json +1 -1
- eval_results.json +5 -5
README.md
CHANGED
@@ -1,11 +1,15 @@
|
|
1 |
---
|
2 |
base_model: OrionStarAI/Orion-14B-Chat
|
3 |
tags:
|
|
|
|
|
|
|
|
|
4 |
- trl
|
5 |
- sft
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
-
-
|
9 |
model-index:
|
10 |
- name: rinko-test
|
11 |
results: []
|
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# rinko-test
|
18 |
|
19 |
-
This model is a fine-tuned version of [OrionStarAI/Orion-14B-Chat](https://huggingface.co/OrionStarAI/Orion-14B-Chat) on the
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 1.1385
|
22 |
|
|
|
1 |
---
|
2 |
base_model: OrionStarAI/Orion-14B-Chat
|
3 |
tags:
|
4 |
+
- alignment-handbook
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
- trl
|
9 |
- sft
|
10 |
- generated_from_trainer
|
11 |
datasets:
|
12 |
+
- ikno/rinko_v2.14
|
13 |
model-index:
|
14 |
- name: rinko-test
|
15 |
results: []
|
|
|
20 |
|
21 |
# rinko-test
|
22 |
|
23 |
+
This model is a fine-tuned version of [OrionStarAI/Orion-14B-Chat](https://huggingface.co/OrionStarAI/Orion-14B-Chat) on the ikno/rinko_v2.14 dataset.
|
24 |
It achieves the following results on the evaluation set:
|
25 |
- Loss: 1.1385
|
26 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"train_loss": 1.2146218933042934,
|
4 |
"train_runtime": 75011.8955,
|
5 |
"train_samples": 5850,
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_loss": 1.1385215520858765,
|
4 |
+
"eval_runtime": 551.8633,
|
5 |
+
"eval_samples": 442,
|
6 |
+
"eval_samples_per_second": 0.386,
|
7 |
+
"eval_steps_per_second": 0.098,
|
8 |
"train_loss": 1.2146218933042934,
|
9 |
"train_runtime": 75011.8955,
|
10 |
"train_samples": 5850,
|
config.json
CHANGED
@@ -28,6 +28,6 @@
|
|
28 |
"tie_word_embeddings": false,
|
29 |
"torch_dtype": "bfloat16",
|
30 |
"transformers_version": "4.38.2",
|
31 |
-
"use_cache":
|
32 |
"vocab_size": 84608
|
33 |
}
|
|
|
28 |
"tie_word_embeddings": false,
|
29 |
"torch_dtype": "bfloat16",
|
30 |
"transformers_version": "4.38.2",
|
31 |
+
"use_cache": true,
|
32 |
"vocab_size": 84608
|
33 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 442,
|
6 |
-
"eval_samples_per_second": 0.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 1.1385215520858765,
|
4 |
+
"eval_runtime": 551.8633,
|
5 |
"eval_samples": 442,
|
6 |
+
"eval_samples_per_second": 0.386,
|
7 |
+
"eval_steps_per_second": 0.098
|
8 |
}
|