End of training
Browse files
README.md
CHANGED
@@ -2,11 +2,15 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
model-index:
|
11 |
- name: prometheus-7b-direct-0.1p-rare-seed42
|
12 |
results: []
|
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# prometheus-7b-direct-0.1p-rare-seed42
|
19 |
|
20 |
-
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
|
21 |
It achieves the following results on the evaluation set:
|
22 |
- Loss: 0.3329
|
23 |
|
|
|
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 |
- generated_from_trainer
|
12 |
datasets:
|
13 |
+
- preference-data
|
14 |
model-index:
|
15 |
- name: prometheus-7b-direct-0.1p-rare-seed42
|
16 |
results: []
|
|
|
21 |
|
22 |
# prometheus-7b-direct-0.1p-rare-seed42
|
23 |
|
24 |
+
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 preference-data dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
- Loss: 0.3329
|
27 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 0.9995119570522206,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 214352422502400.0,
|
4 |
"train_loss": 0.4886561526218429,
|
5 |
"train_runtime": 23171.5823,
|
|
|
1 |
{
|
2 |
"epoch": 0.9995119570522206,
|
3 |
+
"eval_loss": 0.3329254686832428,
|
4 |
+
"eval_runtime": 98.4726,
|
5 |
+
"eval_samples": 1000,
|
6 |
+
"eval_samples_per_second": 3.067,
|
7 |
+
"eval_steps_per_second": 0.772,
|
8 |
"total_flos": 214352422502400.0,
|
9 |
"train_loss": 0.4886561526218429,
|
10 |
"train_runtime": 23171.5823,
|
config.json
CHANGED
@@ -22,6 +22,6 @@
|
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.43.4",
|
25 |
-
"use_cache":
|
26 |
"vocab_size": 32000
|
27 |
}
|
|
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.43.4",
|
25 |
+
"use_cache": true,
|
26 |
"vocab_size": 32000
|
27 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 0.9995119570522206,
|
3 |
-
"eval_loss": 0.
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 1000,
|
6 |
-
"eval_samples_per_second": 3.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.9995119570522206,
|
3 |
+
"eval_loss": 0.3329254686832428,
|
4 |
+
"eval_runtime": 98.4726,
|
5 |
"eval_samples": 1000,
|
6 |
+
"eval_samples_per_second": 3.067,
|
7 |
+
"eval_steps_per_second": 0.772
|
8 |
}
|
runs/Aug07_16-28-10_COE-CS-sv003/events.out.tfevents.1723071602.COE-CS-sv003.3044886.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c30b2e190dfb3cc468ee8873c03bb2967b388f37f618615105e49a8c0afc7d1
|
3 |
+
size 359
|