Model save

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: distilgpt2
+model-index:
+- name: peft-starcoder-lora-a100
+  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. -->
+
+# peft-starcoder-lora-a100
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) 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: 0.0005
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2
+- training_steps: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilgpt2",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "transformer.h.0.mlp.c_proj",
+    "transformer.h.1.mlp.c_proj",
+    "transformer.h.3.attn.c_attn",
+    "transformer.h.2.mlp.c_proj",
+    "transformer.h.1.attn.c_proj",
+    "transformer.h.2.attn.c_attn",
+    "transformer.h.0.mlp.c_fc",
+    "transformer.h.0.attn.c_attn",
+    "transformer.h.4.mlp.c_proj",
+    "transformer.h.2.attn.c_proj",
+    "transformer.h.5.attn.c_proj",
+    "transformer.h.2.mlp.c_fc",
+    "transformer.h.3.mlp.c_proj",
+    "transformer.h.1.attn.c_attn",
+    "transformer.h.5.mlp.c_proj",
+    "transformer.h.4.mlp.c_fc",
+    "transformer.h.1.mlp.c_fc",
+    "transformer.h.0.attn.c_proj",
+    "transformer.h.4.attn.c_proj",
+    "transformer.h.5.mlp.c_fc",
+    "transformer.h.5.attn.c_attn",
+    "transformer.h.3.attn.c_proj",
+    "transformer.h.4.attn.c_attn",
+    "transformer.h.3.mlp.c_fc"
+  ],
+  "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 sha256:7e54782bd3ba7a97f94d39e385fea3852286099c815f293ea8e5aa16659f9588
+size 2365304

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86e4f45ff0d315ce5d6c08b42072afbee72659eda7398adfd3f85882cc24860
+size 5112