amarard/llama3finetuning

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: NousResearch/Meta-Llama-3-8B
+model-index:
+- name: experiemnts
+  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. -->
+
+# experiemnts
+
+This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.6667
+- eval_runtime: 85.9166
+- eval_samples_per_second: 11.639
+- eval_steps_per_second: 1.455
+- epoch: 0.8005
+- step: 5184
+
+## 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: 0.0003
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Meta-Llama-3-8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

runs/Apr26_19-53-49_ff2160ce7d54/events.out.tfevents.1714161271.ff2160ce7d54.5279.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f655c2fc14ce0832e6b9f02f119ab320d953295f83f032793cedbc4a2e0206
+size 7268

runs/Apr26_20-06-09_ff2160ce7d54/events.out.tfevents.1714161979.ff2160ce7d54.9068.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224ddae094caa3b71de514b44a5d68fb93632e607e76633e33d1bf779742d4e4
+size 142752

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab82d26f697ffd10b4db997cdcd3ad61f640447c06d4f5fe73e818b01d2ad82f
+size 4984