End of training

README.md

@@ -0,0 +1,51 @@
+---
+library_name: peft
+license: bigcode-openrail-m
+base_model: bigcode/starcoderbase-1b
+tags:
+- generated_from_trainer
+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 [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 30
+- training_steps: 2000
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoderbase-1b",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_fc",
+    "c_attn",
+    "c_proj",
+    "q_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:a73de623fc3ae28241834d489d8eabaeb5e4cb3d949795ff61344b23869efeb7
+size 22241240

runs/Jan10_07-14-48_c3f96662fc7c/events.out.tfevents.1736493307.c3f96662fc7c.185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c2529ba0dbe3097d468a90de57a8f1bca8a113dab86d530a8d2623825c10b43
+size 5981

runs/Jan10_07-14-48_c3f96662fc7c/events.out.tfevents.1736493657.c3f96662fc7c.185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2357a0ceadf13a9f53de001fc01705ff671e1975f1d0b0d7e21b03a4d60c0c
+size 5981

runs/Jan10_07-22-41_c3f96662fc7c/events.out.tfevents.1736493772.c3f96662fc7c.185.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86469d5bbf9e393b2bf4a4d816d96cbc1c7711778a3aa77f190650324856ae6
+size 5981

runs/Jan10_07-22-41_c3f96662fc7c/events.out.tfevents.1736493822.c3f96662fc7c.185.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7108af52036634dc6e0f229d6283d0834c065578df94f89a7d82fbe0d7d7a04
+size 5981

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442e2bd7c2b146c2b799f71f6cde9c976ed8325cb934931232bfa40cb3e23f62
+size 5368