End of training
Browse files- README.md +7 -3
- all_results.json +5 -0
- config.json +1 -1
- eval_results.json +8 -0
README.md
CHANGED
@@ -3,11 +3,15 @@ library_name: transformers
|
|
3 |
license: llama3
|
4 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
5 |
tags:
|
|
|
|
|
|
|
|
|
6 |
- trl
|
7 |
- sft
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
-
-
|
11 |
model-index:
|
12 |
- name: Meta-Llama-3-8B-IST_StoryGen
|
13 |
results: []
|
@@ -18,9 +22,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# Meta-Llama-3-8B-IST_StoryGen
|
20 |
|
21 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 1.
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
3 |
license: llama3
|
4 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
5 |
tags:
|
6 |
+
- alignment-handbook
|
7 |
+
- trl
|
8 |
+
- sft
|
9 |
+
- generated_from_trainer
|
10 |
- trl
|
11 |
- sft
|
12 |
- generated_from_trainer
|
13 |
datasets:
|
14 |
+
- train_data/story_generation
|
15 |
model-index:
|
16 |
- name: Meta-Llama-3-8B-IST_StoryGen
|
17 |
results: []
|
|
|
22 |
|
23 |
# Meta-Llama-3-8B-IST_StoryGen
|
24 |
|
25 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the train_data/story_generation dataset.
|
26 |
It achieves the following results on the evaluation set:
|
27 |
+
- Loss: 1.4676
|
28 |
|
29 |
## Model description
|
30 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 1.4371645474744566e+18,
|
4 |
"train_loss": 0.45526161300328233,
|
5 |
"train_runtime": 3331.5803,
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.4675722122192383,
|
4 |
+
"eval_runtime": 19.4256,
|
5 |
+
"eval_samples": 614,
|
6 |
+
"eval_samples_per_second": 22.959,
|
7 |
+
"eval_steps_per_second": 0.721,
|
8 |
"total_flos": 1.4371645474744566e+18,
|
9 |
"train_loss": 0.45526161300328233,
|
10 |
"train_runtime": 3331.5803,
|
config.json
CHANGED
@@ -24,6 +24,6 @@
|
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.44.2",
|
27 |
-
"use_cache":
|
28 |
"vocab_size": 128256
|
29 |
}
|
|
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.44.2",
|
27 |
+
"use_cache": true,
|
28 |
"vocab_size": 128256
|
29 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.4675722122192383,
|
4 |
+
"eval_runtime": 19.4256,
|
5 |
+
"eval_samples": 614,
|
6 |
+
"eval_samples_per_second": 22.959,
|
7 |
+
"eval_steps_per_second": 0.721
|
8 |
+
}
|