Model save

README.md

@@ -0,0 +1,63 @@
+---
+base_model: meta-llama/Llama-3.1-70B-Instruct
+library_name: peft
+license: llama3.1
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: mistral-sft-lora-fsdp
+  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. -->
+
+# mistral-sft-lora-fsdp
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) on the None dataset.
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 100
+- distributed_type: multi-GPU
+- num_devices: 5
+- total_train_batch_size: 5
+- total_eval_batch_size: 5
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 2    | 1.8928          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-70B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_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 sha256:939bddcf5a3d81fe04a97a212eecae5b16c7f432b277f3a334a957addedd805e
+size 8820250192

runs/Jan04_00-30-05_gpu-server/events.out.tfevents.1735950842.gpu-server.1146110.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59310cc338f947cc5cc83422a36c8fee42166547967a692bf3ebc55a4281b060
-size 5640
+oid sha256:ac854c85e4819deeb5c580793b559653ec81df26b0c165c57531a578716bc235
+size 6254