Rajveer43/MiniMedic

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: GeneZC/MiniChat-1.5-3B
+model-index:
+- name: experiments
+  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. -->
+
+# experiments
+
+This model is a fine-tuned version of [GeneZC/MiniChat-1.5-3B](https://huggingface.co/GeneZC/MiniChat-1.5-3B) 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- 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: 0.05
+- num_epochs: 6
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.0.dev0
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "GeneZC/MiniChat-1.5-3B",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b3d4e03b0b166d8d6de4004c56dfcdf8c08db7e3f7b148b4b5dada51fe7d63
+size 18887216

runs/Dec25_06-17-38_0e920f2fb747/events.out.tfevents.1703485192.0e920f2fb747.42.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f1ec8d1eee800d4a0a7f2fc17317b948b4bf1b561d7582bb47f0919ec3ef30
+size 4800

runs/Dec25_06-22-20_0e920f2fb747/events.out.tfevents.1703485340.0e920f2fb747.42.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b698e4f979491b34154c74f3fd74ba287522697056be6fe12a85132f14b65f
+size 5147

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d440a4ad25112aa2f3fd7c4e707a45ea634f198c6cbba19da3ed322908bccb
+size 4283