Commit
•
780c362
1
Parent(s):
91b45f7
End of training
Browse files
README.md
CHANGED
@@ -2,12 +2,13 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
9 |
datasets:
|
10 |
-
-
|
11 |
model-index:
|
12 |
- name: tinyllama-1.1b-sum-sft-qlora
|
13 |
results: []
|
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# tinyllama-1.1b-sum-sft-qlora
|
20 |
|
21 |
-
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 2.1271
|
24 |
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
- trl
|
7 |
- sft
|
8 |
- generated_from_trainer
|
9 |
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
10 |
datasets:
|
11 |
+
- martimfasantos/openai-tldr-filtered
|
12 |
model-index:
|
13 |
- name: tinyllama-1.1b-sum-sft-qlora
|
14 |
results: []
|
|
|
19 |
|
20 |
# tinyllama-1.1b-sum-sft-qlora
|
21 |
|
22 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the martimfasantos/openai-tldr-filtered dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
- Loss: 2.1271
|
25 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"train_loss": 2.1395558682560596,
|
4 |
"train_runtime": 23055.2544,
|
5 |
"train_samples": 116722,
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"eval_loss": 2.12707781791687,
|
4 |
+
"eval_runtime": 173.5137,
|
5 |
+
"eval_samples": 6553,
|
6 |
+
"eval_samples_per_second": 7.654,
|
7 |
+
"eval_steps_per_second": 0.957,
|
8 |
"train_loss": 2.1395558682560596,
|
9 |
"train_runtime": 23055.2544,
|
10 |
"train_samples": 116722,
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss": 2.
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 6553,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_loss": 2.12707781791687,
|
4 |
+
"eval_runtime": 173.5137,
|
5 |
"eval_samples": 6553,
|
6 |
+
"eval_samples_per_second": 7.654,
|
7 |
+
"eval_steps_per_second": 0.957
|
8 |
}
|
runs/May01_17-02-13_poseidon/events.out.tfevents.1714606278.poseidon.313063.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98a5553501ed706f4672b185a5b67caa8e13d00d7f8c81444fe8c0bb4178b82a
|
3 |
+
size 359
|