jennhu/olmo-7b-lora_tinystories_baseline_100k_tinystories_baseline_100k

README.md

@@ -0,0 +1,64 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: allenai/OLMo-7B-0724-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: tinystories_baseline_100k
+  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. -->
+
+# tinystories_baseline_100k
+
+This model is a fine-tuned version of [allenai/OLMo-7B-0724-hf](https://huggingface.co/allenai/OLMo-7B-0724-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2252
+
+## 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: 0.002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.2502        | 1.0230 | 400  | 1.2686          |
+| 1.2066        | 2.0461 | 800  | 1.2472          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.6.0
+- Datasets 3.3.2
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "allenai/OLMo-7B-0724-hf",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "lm_head",
+    "gate_proj",
+    "up_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 sha256:764766b5dcc7c9b2c7d9cc7c5c1fc1af9ebd075f03b3b5ffec47b91785be3957
+size 1151021048

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c964568785c95a9b7d0b5d839dd7204c509ac035b0b955ec969a4878ed4c735
+size 5496