Model save

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: mistralai/Mistral-7B-v0.1
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B
 tags:
 - llama-factory
 - generated_from_trainer
@@ -15,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## Model description
 
@@ -34,25 +36,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 8
+- learning_rate: 5e-06
+- train_batch_size: 8
+- eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 8
+- num_devices: 16
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 512
 - total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 3
+- lr_scheduler_warmup_steps: 1738
+- num_epochs: 3.0
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.1304 | 3    | 1.6953          |
+| No log        | 0.8    | 3    | nan             |
+| No log        | 1.8667 | 7    | nan             |
+| No log        | 2.4    | 9    | nan             |
 
 
 ### Framework versions

generation_config.json

@@ -1,6 +1,9 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.45.2"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3951b610e5b351d88dd67a77b64fe7d26cd9027a8713c30c226457cf6b1fce05
+oid sha256:f3520d4ef068dc462553a3e46e583ad87e1c415b95c4f13b613b6c639918d2c8
 size 6776