training_output/feedback_model_e10_save5000/

README.md

@@ -0,0 +1,79 @@
+---
+library_name: transformers
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: feedback_model_e10_save5000
+  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. -->
+
+# feedback_model_e10_save5000
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0187
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step   | Validation Loss |
+|:-------------:|:------:|:------:|:---------------:|
+| 1.0496        | 0.4769 | 5000   | 2.0187          |
+| 0.3448        | 0.9538 | 10000  | 2.5590          |
+| 0.2027        | 1.4308 | 15000  | 2.8900          |
+| 0.1746        | 1.9077 | 20000  | 2.9743          |
+| 0.1488        | 2.3846 | 25000  | 3.1316          |
+| 0.1395        | 2.8615 | 30000  | 3.2616          |
+| 0.1189        | 3.3384 | 35000  | 3.3299          |
+| 0.116         | 3.8153 | 40000  | 3.4260          |
+| 0.0944        | 4.2923 | 45000  | 3.5361          |
+| 0.0937        | 4.7692 | 50000  | 3.6240          |
+| 0.0731        | 5.2461 | 55000  | 3.7380          |
+| 0.0737        | 5.7230 | 60000  | 3.8218          |
+| 0.0549        | 6.1999 | 65000  | 3.9090          |
+| 0.0556        | 6.6768 | 70000  | 4.0614          |
+| 0.0444        | 7.1538 | 75000  | 4.1715          |
+| 0.0429        | 7.6307 | 80000  | 4.2847          |
+| 0.0369        | 8.1076 | 85000  | 4.4924          |
+| 0.0364        | 8.5845 | 90000  | 4.5050          |
+| 0.034         | 9.0614 | 95000  | 4.6572          |
+| 0.0345        | 9.5383 | 100000 | 4.6768          |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.3.0
+- Datasets 2.14.4
+- Tokenizers 0.20.3

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec7e1e0dd61e35024f8d03250306a87ac6718e394d0262a0ed885af40bff15b
+oid sha256:5da776fa879b233b09bbfd58ce443f9cdf338c0550222488ad45c627b7b3236c
 size 4943274328