AI-4-Health/HPP-FINETUNED-Meta-Llama-3-8B-Instruct
Browse files
README.md
CHANGED
|
@@ -18,7 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
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 an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -46,35 +51,9 @@ The following hyperparameters were used during training:
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: cosine
|
| 48 |
- lr_scheduler_warmup_ratio: 0.05
|
| 49 |
-
- num_epochs:
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
-
|:-------------:|:-------:|:----:|:---------------:|
|
| 56 |
-
| 1.3621 | 3.4964 | 420 | 1.4379 |
|
| 57 |
-
| 1.1954 | 6.9927 | 840 | 1.4208 |
|
| 58 |
-
| 0.8507 | 10.4891 | 1260 | 1.5712 |
|
| 59 |
-
| 0.789 | 13.9854 | 1680 | 1.6759 |
|
| 60 |
-
| 0.5388 | 17.4818 | 2100 | 1.9153 |
|
| 61 |
-
| 0.4013 | 20.9781 | 2520 | 2.0319 |
|
| 62 |
-
| 0.2933 | 24.4745 | 2940 | 2.2094 |
|
| 63 |
-
| 0.207 | 27.9709 | 3360 | 2.3547 |
|
| 64 |
-
| 0.1604 | 31.4672 | 3780 | 2.5483 |
|
| 65 |
-
| 0.1154 | 34.9636 | 4200 | 2.5953 |
|
| 66 |
-
| 0.0982 | 38.4599 | 4620 | 2.7355 |
|
| 67 |
-
| 0.0954 | 41.9563 | 5040 | 2.8220 |
|
| 68 |
-
| 0.0677 | 45.4527 | 5460 | 2.8909 |
|
| 69 |
-
| 0.0613 | 48.9490 | 5880 | 2.9654 |
|
| 70 |
-
| 0.0482 | 52.4454 | 6300 | 3.0125 |
|
| 71 |
-
| 0.0415 | 55.9417 | 6720 | 3.0390 |
|
| 72 |
-
| 0.0477 | 59.4381 | 7140 | 3.0992 |
|
| 73 |
-
| 0.0412 | 62.9344 | 7560 | 3.1126 |
|
| 74 |
-
| 0.0327 | 66.4308 | 7980 | 3.1262 |
|
| 75 |
-
| 0.0391 | 69.9272 | 8400 | 3.1279 |
|
| 76 |
-
|
| 77 |
-
|
| 78 |
### Framework versions
|
| 79 |
|
| 80 |
- PEFT 0.11.1
|
|
|
|
| 18 |
|
| 19 |
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 an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- eval_loss: 1.4540
|
| 22 |
+
- eval_runtime: 9.5935
|
| 23 |
+
- eval_samples_per_second: 11.153
|
| 24 |
+
- eval_steps_per_second: 1.459
|
| 25 |
+
- epoch: 1.6649
|
| 26 |
+
- step: 200
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: cosine
|
| 53 |
- lr_scheduler_warmup_ratio: 0.05
|
| 54 |
+
- num_epochs: 3
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- PEFT 0.11.1
|
adapter_config.json
CHANGED
|
@@ -21,8 +21,7 @@
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"v_proj",
|
| 24 |
-
"q_proj"
|
| 25 |
-
"k_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_dora": false,
|
|
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"v_proj",
|
| 24 |
+
"q_proj"
|
|
|
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
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 sha256:6501ee19efb13db3066b3ca3111726396e9848de0f3f2bd951c6365b9f3ee49f
|
| 3 |
+
size 27280152
|
runs/Jun13_07-27-50_jupiter/events.out.tfevents.1718234875.jupiter.364556.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5c4fc6d7a3ce71c069a3ea4524470b90fdcc0c4f582787bf75633a50d58dc54
|
| 3 |
+
size 12172
|
runs/Jun13_07-29-42_jupiter/events.out.tfevents.1718234993.jupiter.364556.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:760c8f0e24619da9f471817ad15bf2b10b8e3b6c88a98d022adc4537cafdcae9
|
| 3 |
+
size 61567
|
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4923
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02e896f485718fcc80ba95f42b802371c912c071b6c001915e5ead5020bf9fe6
|
| 3 |
size 4923
|