avalosjc/llama2-instruct-tune-500s
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the generator dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 1.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -51,31 +51,31 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
-
| 1.
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.
|
| 60 |
-
| 1.
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
| 65 |
-
| 1.
|
| 66 |
-
| 1.
|
| 67 |
-
| 1.
|
| 68 |
-
| 1.
|
| 69 |
-
| 1.
|
| 70 |
-
| 1.
|
| 71 |
-
| 1.
|
| 72 |
-
| 1.
|
| 73 |
-
| 1.
|
| 74 |
-
| 1.
|
| 75 |
-
| 1.
|
| 76 |
-
| 1.
|
| 77 |
-
| 1.
|
| 78 |
-
| 1.
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the generator dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.6752
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 1.9802 | 0.0027 | 20 | 1.8101 |
|
| 55 |
+
| 1.9108 | 0.0054 | 40 | 1.7781 |
|
| 56 |
+
| 1.9155 | 0.0081 | 60 | 1.7653 |
|
| 57 |
+
| 1.9302 | 0.0108 | 80 | 1.7579 |
|
| 58 |
+
| 1.8143 | 0.0135 | 100 | 1.7455 |
|
| 59 |
+
| 1.9025 | 0.0163 | 120 | 1.7143 |
|
| 60 |
+
| 1.8029 | 0.0190 | 140 | 1.7029 |
|
| 61 |
+
| 1.8912 | 0.0217 | 160 | 1.6989 |
|
| 62 |
+
| 1.8565 | 0.0244 | 180 | 1.6961 |
|
| 63 |
+
| 1.7468 | 0.0271 | 200 | 1.6936 |
|
| 64 |
+
| 1.829 | 0.0298 | 220 | 1.6913 |
|
| 65 |
+
| 1.8097 | 0.0325 | 240 | 1.6883 |
|
| 66 |
+
| 1.7772 | 0.0352 | 260 | 1.6866 |
|
| 67 |
+
| 1.8564 | 0.0379 | 280 | 1.6843 |
|
| 68 |
+
| 1.7101 | 0.0406 | 300 | 1.6828 |
|
| 69 |
+
| 1.8124 | 0.0433 | 320 | 1.6811 |
|
| 70 |
+
| 1.8437 | 0.0461 | 340 | 1.6804 |
|
| 71 |
+
| 1.8908 | 0.0488 | 360 | 1.6800 |
|
| 72 |
+
| 1.817 | 0.0515 | 380 | 1.6807 |
|
| 73 |
+
| 1.8006 | 0.0542 | 400 | 1.6791 |
|
| 74 |
+
| 1.774 | 0.0569 | 420 | 1.6768 |
|
| 75 |
+
| 1.8284 | 0.0596 | 440 | 1.6753 |
|
| 76 |
+
| 1.8784 | 0.0623 | 460 | 1.6769 |
|
| 77 |
+
| 1.7567 | 0.0650 | 480 | 1.6777 |
|
| 78 |
+
| 1.8119 | 0.0677 | 500 | 1.6752 |
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b28b730aefe38e2a507cf577924ebac4252a69f4a92eed9c7fe0be80ab738e4
|
| 3 |
+
size 134235048
|
runs/Jun13_02-39-50_f2832ce3cae2/events.out.tfevents.1718246436.f2832ce3cae2.756.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a289d6ef8914995cf0bcce10691dad4bd903f70560dcd82d917e5b2f133516
|
| 3 |
+
size 23289
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44e891fa1cccd33dd5b6cdc88930f0c27c0263cd3668c212f17ef5c46b5c460b
|
| 3 |
size 5368
|