neverland-th
/

llama-3.1-8b

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Tanabodee Limpaitoon commited on Sep 27

Commit

b8635e0

•

1 Parent(s): 1a02bc5

nvl-og/finetuned-ai

Files changed (3) hide show

README.md +11 -11
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1

README.md CHANGED Viewed

@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 # results
-This model is a fine-tuned version of [meta-llama/Llama-3.2-3b-instruct](https://huggingface.co/meta-llama/Llama-3.2-3b-instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2300
 ## Model description
@@ -36,24 +36,24 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
 - num_epochs: 5
 ### Training results
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.9720 | 13   | 0.4116          |
-| 0.819         | 1.9439 | 26   | 0.3048          |
-| 0.3283        | 2.9907 | 40   | 0.2464          |
-| 0.3283        | 3.9626 | 53   | 0.2307          |
-| 0.2244        | 4.8598 | 65   | 0.2300          |
 ### Framework versions

 # results
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3b-instruct](https://huggingface.co/meta-llama/Llama-3.2-3b-instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.7412
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 24
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
 - num_epochs: 5
 ### Training results
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 1.7756        | 0.9982 | 94   | 1.7306          |
+| 1.62          | 1.9965 | 188  | 1.7028          |
+| 1.5795        | 2.9947 | 282  | 1.7088          |
+| 1.4914        | 3.9929 | 376  | 1.7279          |
+| 1.4776        | 4.9912 | 470  | 1.7412          |
 ### Framework versions

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a8af16799506ec2bbb08b79634012591f2d4d5790b45936f69d49f470649d2c
 size 4965799096

 version https://git-lfs.github.com/spec/v1
+oid sha256:d5be883ed54dc15cc34da3b7f0e4a955fa3df9cb37e9d4b5722eaa4ab84dd10c
 size 4965799096

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f531bf22d52ee673f5b56358c4164fdb1268c4d7b054e5b56a2a04447328637
 size 1459729952

 version https://git-lfs.github.com/spec/v1
+oid sha256:e6f949fe4988102a15d7a4aaf56b54ed90341ca97ef3a68014d2f735dd25ff1d
 size 1459729952