Model save

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: HuggingFaceH4/mistral-7b-sft-beta
+model-index:
+- name: mistral-MistralMiniMed2
+  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-MistralMiniMed2
+
+This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on an unknown 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: 2.5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- training_steps: 200
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e37b176bdee2170edc9416c1da76e1d97c9da63b3b546378f126300412a1ef
+size 609389712

runs/Jan07_22-49-29_a33548588757/events.out.tfevents.1704667770.a33548588757.4075.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847d587fa1bcea7f95d776330b9699b5eca8367654b3299a0d4188ae27469bdb
+size 4780

runs/Jan07_22-50-04_a33548588757/events.out.tfevents.1704667805.a33548588757.4075.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801defe3f8921c73b6d01ea0e9b7d5b82d3a84e01e3384ecbbbf0afa655e51af
+size 5756

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6493bf06eab0a27e1c8f4f99832996d4fbb3051974f08bc24015cb53cdfe82f0
+size 4728