Commit
•
8085023
1
Parent(s):
87866cb
End of training
Browse files
README.md
CHANGED
@@ -2,11 +2,15 @@
|
|
2 |
license: llama2
|
3 |
base_model: meta-llama/Llama-2-7b-hf
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
model-index:
|
11 |
- name: llama2-7b-sft-full-llama2
|
12 |
results: []
|
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# llama2-7b-sft-full-llama2
|
19 |
|
20 |
-
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the
|
21 |
It achieves the following results on the evaluation set:
|
22 |
- Loss: 1.0380
|
23 |
|
|
|
2 |
license: llama2
|
3 |
base_model: meta-llama/Llama-2-7b-hf
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
- trl
|
10 |
- sft
|
11 |
- generated_from_trainer
|
12 |
datasets:
|
13 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
14 |
model-index:
|
15 |
- name: llama2-7b-sft-full-llama2
|
16 |
results: []
|
|
|
21 |
|
22 |
# llama2-7b-sft-full-llama2
|
23 |
|
24 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
- Loss: 1.0380
|
27 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 2.994059405940594,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 158238674780160.0,
|
4 |
"train_loss": 0.8970171990533354,
|
5 |
"train_runtime": 67109.8008,
|
|
|
1 |
{
|
2 |
"epoch": 2.994059405940594,
|
3 |
+
"eval_loss": 1.0379831790924072,
|
4 |
+
"eval_runtime": 93.7153,
|
5 |
+
"eval_samples": 1000,
|
6 |
+
"eval_samples_per_second": 2.838,
|
7 |
+
"eval_steps_per_second": 0.181,
|
8 |
"total_flos": 158238674780160.0,
|
9 |
"train_loss": 0.8970171990533354,
|
10 |
"train_runtime": 67109.8008,
|
config.json
CHANGED
@@ -24,6 +24,6 @@
|
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
"transformers_version": "4.41.2",
|
27 |
-
"use_cache":
|
28 |
"vocab_size": 32000
|
29 |
}
|
|
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
"transformers_version": "4.41.2",
|
27 |
+
"use_cache": true,
|
28 |
"vocab_size": 32000
|
29 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.994059405940594,
|
3 |
+
"eval_loss": 1.0379831790924072,
|
4 |
+
"eval_runtime": 93.7153,
|
5 |
+
"eval_samples": 1000,
|
6 |
+
"eval_samples_per_second": 2.838,
|
7 |
+
"eval_steps_per_second": 0.181
|
8 |
+
}
|
runs/Jun06_17-25-47_g29lc7ctr1717663620987-f7gj6/events.out.tfevents.1717733644.g29lc7ctr1717663620987-f7gj6.11042.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23fe5099918117e0765ef6014934178af979f78550603d97651d587c59cdd9a1
|
3 |
+
size 311
|