Model save

README.md

@@ -0,0 +1,69 @@
+---
+base_model: meta-llama/Llama-3.1-8B-Instruct
+library_name: peft
+license: llama3.1
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: Llama-3.1-8B-Instruct-SFT-600
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Llama-3.1-8B-Instruct-SFT-600
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0599
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- 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
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.996         | 1.4815 | 50   | 0.7778          |
+| 0.1326        | 2.9630 | 100  | 0.0880          |
+| 0.0931        | 4.4444 | 150  | 0.0636          |
+| 0.0915        | 5.9259 | 200  | 0.0614          |
+| 0.0888        | 7.4074 | 250  | 0.0600          |
+| 0.0653        | 8.8889 | 300  | 0.0599          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.2
+- Pytorch 2.3.0
+- Datasets 2.19.0
+- Tokenizers 0.20.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641d44416021eb4e0088f974fbb221bcc951d52e0d8f76841581e528340217ea
+oid sha256:582b13eb0939435987a209ce38a77fbc1e78dba0a1569d0d42908923131ad291
 size 83945296

trainer_log.jsonl

@@ -22,3 +22,19 @@
 {"current_steps": 190, "total_steps": 330, "loss": 0.0765, "learning_rate": 2.3282469092517977e-06, "epoch": 5.62962962962963, "percentage": 57.58, "elapsed_time": "0:04:29", "remaining_time": "0:03:18"}
 {"current_steps": 200, "total_steps": 330, "loss": 0.0915, "learning_rate": 2.0658795558326745e-06, "epoch": 5.925925925925926, "percentage": 60.61, "elapsed_time": "0:04:42", "remaining_time": "0:03:03"}
 {"current_steps": 200, "total_steps": 330, "eval_loss": 0.06135586276650429, "epoch": 5.925925925925926, "percentage": 60.61, "elapsed_time": "0:04:44", "remaining_time": "0:03:04"}
+{"current_steps": 210, "total_steps": 330, "loss": 0.0574, "learning_rate": 1.8083649992336827e-06, "epoch": 6.222222222222222, "percentage": 63.64, "elapsed_time": "0:05:01", "remaining_time": "0:02:52"}
+{"current_steps": 220, "total_steps": 330, "loss": 0.1016, "learning_rate": 1.5585818549132532e-06, "epoch": 6.518518518518518, "percentage": 66.67, "elapsed_time": "0:05:15", "remaining_time": "0:02:37"}
+{"current_steps": 230, "total_steps": 330, "loss": 0.068, "learning_rate": 1.3193223130682937e-06, "epoch": 6.814814814814815, "percentage": 69.7, "elapsed_time": "0:05:28", "remaining_time": "0:02:22"}
+{"current_steps": 240, "total_steps": 330, "loss": 0.0962, "learning_rate": 1.0932609262554748e-06, "epoch": 7.111111111111111, "percentage": 72.73, "elapsed_time": "0:05:42", "remaining_time": "0:02:08"}
+{"current_steps": 250, "total_steps": 330, "loss": 0.0888, "learning_rate": 8.829247120198564e-07, "epoch": 7.407407407407407, "percentage": 75.76, "elapsed_time": "0:05:55", "remaining_time": "0:01:53"}
+{"current_steps": 250, "total_steps": 330, "eval_loss": 0.060000352561473846, "epoch": 7.407407407407407, "percentage": 75.76, "elapsed_time": "0:05:56", "remaining_time": "0:01:54"}
+{"current_steps": 260, "total_steps": 330, "loss": 0.0556, "learning_rate": 6.906649047373246e-07, "epoch": 7.703703703703704, "percentage": 78.79, "elapsed_time": "0:06:16", "remaining_time": "0:01:41"}
+{"current_steps": 270, "total_steps": 330, "loss": 0.0962, "learning_rate": 5.186306724416714e-07, "epoch": 8.0, "percentage": 81.82, "elapsed_time": "0:06:30", "remaining_time": "0:01:26"}
+{"current_steps": 280, "total_steps": 330, "loss": 0.0854, "learning_rate": 3.6874509244163414e-07, "epoch": 8.296296296296296, "percentage": 84.85, "elapsed_time": "0:06:44", "remaining_time": "0:01:12"}
+{"current_steps": 290, "total_steps": 330, "loss": 0.0715, "learning_rate": 2.4268365428344737e-07, "epoch": 8.592592592592592, "percentage": 87.88, "elapsed_time": "0:06:57", "remaining_time": "0:00:57"}
+{"current_steps": 300, "total_steps": 330, "loss": 0.0653, "learning_rate": 1.4185553036259097e-07, "epoch": 8.88888888888889, "percentage": 90.91, "elapsed_time": "0:07:11", "remaining_time": "0:00:43"}
+{"current_steps": 300, "total_steps": 330, "eval_loss": 0.059873927384614944, "epoch": 8.88888888888889, "percentage": 90.91, "elapsed_time": "0:07:12", "remaining_time": "0:00:43"}
+{"current_steps": 310, "total_steps": 330, "loss": 0.0858, "learning_rate": 6.738782355044048e-08, "epoch": 9.185185185185185, "percentage": 93.94, "elapsed_time": "0:07:28", "remaining_time": "0:00:28"}
+{"current_steps": 320, "total_steps": 330, "loss": 0.072, "learning_rate": 2.011296792301165e-08, "epoch": 9.481481481481481, "percentage": 96.97, "elapsed_time": "0:07:41", "remaining_time": "0:00:14"}
+{"current_steps": 330, "total_steps": 330, "loss": 0.0773, "learning_rate": 5.59423432245354e-10, "epoch": 9.777777777777779, "percentage": 100.0, "elapsed_time": "0:07:55", "remaining_time": "0:00:00"}
+{"current_steps": 330, "total_steps": 330, "epoch": 9.777777777777779, "percentage": 100.0, "elapsed_time": "0:07:58", "remaining_time": "0:00:00"}