End of training
Browse files- README.md +10 -2
- all_results.json +5 -0
- config.json +1 -1
- eval_results.json +8 -0
README.md
CHANGED
@@ -3,11 +3,19 @@ library_name: transformers
|
|
3 |
license: llama3.1
|
4 |
base_model: meta-llama/Llama-3.1-8B
|
5 |
tags:
|
|
|
|
|
|
|
|
|
6 |
- trl
|
7 |
- sft
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
-
-
|
|
|
|
|
|
|
|
|
11 |
model-index:
|
12 |
- name: llama3-1-ox-llms-8b-sft-full-3-epochs
|
13 |
results: []
|
@@ -18,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# llama3-1-ox-llms-8b-sft-full-3-epochs
|
20 |
|
21 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 0.8089
|
24 |
|
|
|
3 |
license: llama3.1
|
4 |
base_model: meta-llama/Llama-3.1-8B
|
5 |
tags:
|
6 |
+
- alignment-handbook
|
7 |
+
- trl
|
8 |
+
- sft
|
9 |
+
- generated_from_trainer
|
10 |
- trl
|
11 |
- sft
|
12 |
- generated_from_trainer
|
13 |
datasets:
|
14 |
+
- oxford-llms/ultrachat_filtered
|
15 |
+
- oxford-llms/Magpie-Qwen2.5-Pro-1M-v0.1-filtered
|
16 |
+
- oxford-llms/european_social_survey_2020_sft
|
17 |
+
- oxford-llms/european_social_survey_2023_sft
|
18 |
+
- oxford-llms/world_values_survey_2017_2022_sft
|
19 |
model-index:
|
20 |
- name: llama3-1-ox-llms-8b-sft-full-3-epochs
|
21 |
results: []
|
|
|
26 |
|
27 |
# llama3-1-ox-llms-8b-sft-full-3-epochs
|
28 |
|
29 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the oxford-llms/ultrachat_filtered, the oxford-llms/Magpie-Qwen2.5-Pro-1M-v0.1-filtered, the oxford-llms/european_social_survey_2020_sft, the oxford-llms/european_social_survey_2023_sft and the oxford-llms/world_values_survey_2017_2022_sft datasets.
|
30 |
It achieves the following results on the evaluation set:
|
31 |
- Loss: 0.8089
|
32 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 1208539372584960.0,
|
4 |
"train_loss": 0.6196737293559317,
|
5 |
"train_runtime": 16925.3973,
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.8089174032211304,
|
4 |
+
"eval_runtime": 106.6049,
|
5 |
+
"eval_samples": 41639,
|
6 |
+
"eval_samples_per_second": 77.013,
|
7 |
+
"eval_steps_per_second": 1.21,
|
8 |
"total_flos": 1208539372584960.0,
|
9 |
"train_loss": 0.6196737293559317,
|
10 |
"train_runtime": 16925.3973,
|
config.json
CHANGED
@@ -31,6 +31,6 @@
|
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
"transformers_version": "4.45.1",
|
34 |
-
"use_cache":
|
35 |
"vocab_size": 128256
|
36 |
}
|
|
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
"transformers_version": "4.45.1",
|
34 |
+
"use_cache": true,
|
35 |
"vocab_size": 128256
|
36 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.8089174032211304,
|
4 |
+
"eval_runtime": 106.6049,
|
5 |
+
"eval_samples": 41639,
|
6 |
+
"eval_samples_per_second": 77.013,
|
7 |
+
"eval_steps_per_second": 1.21
|
8 |
+
}
|