End of training

README.md

@@ -0,0 +1,58 @@
+---
+base_model: vicgalle/gpt2-open-instruct-v1
+library_name: peft
+license: mit
+tags:
+- generated_from_trainer
+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 [vicgalle/gpt2-open-instruct-v1](https://huggingface.co/vicgalle/gpt2-open-instruct-v1) 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "vicgalle/gpt2-open-instruct-v1",
+ "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": 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": [
+ "c_attn"
+ ],
+ "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 sha256:6caab09ee0ddfb768d2e0a8c544d3ce7b2a4959bc3e806e2fd38bf8f2c74b690
+size 2362376

runs/Aug14_14-57-29_e1148e0c96bd/events.out.tfevents.1723647451.e1148e0c96bd.1199.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140f343c4ce934c089c36bbdc9fc29918ac4c4f3bff8c52efca19a87caf5d186
+size 12557

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5225a008c87e77763213ecd4dcc59f37d124f84be03e61e44d96dbbcbc4168f
+size 5112