Model save

README.md

@@ -0,0 +1,53 @@
+---
+library_name: peft
+license: bsd-3-clause
+base_model: Salesforce/codegen-350M-mono
+tags:
+- generated_from_trainer
+model-index:
+- name: c_coder_llm
+  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. -->
+
+# c_coder_llm
+
+This model is a fine-tuned version of [Salesforce/codegen-350M-mono](https://huggingface.co/Salesforce/codegen-350M-mono) 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Salesforce/codegen-350M-mono",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "qkv_proj",
+    "out_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 sha256:8b4d72d94e0777f724fd6a853ee058be97e55af629e0157f208649e2daf36f51
+size 3942512

runs/Dec13_17-08-01_0bc80fda390b/events.out.tfevents.1734109683.0bc80fda390b.685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2c331b6b1ae489217ccac8df1f4d01fc0b5f67aefb3c25506995071dbaccf6
+size 5898

runs/Dec13_17-15-23_0bc80fda390b/events.out.tfevents.1734110124.0bc80fda390b.685.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da883d86ed56e07fca93873d0c2cef3463b6cd454deb5ccd8b0b19603de43bd
+size 5898

runs/Dec13_17-38-05_0bc80fda390b/events.out.tfevents.1734111486.0bc80fda390b.19964.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2440f223ae8875bf52198537bb06af2dcac86f240966728fdce296eef4aff887
+size 4184

runs/Dec13_17-39-31_0bc80fda390b/events.out.tfevents.1734111571.0bc80fda390b.19964.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd147f3e988fc5fc61d4fbef9eb8318dce1d314777a5b2f3a5b430bf6758d5b7
+size 4184

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efde909d00d494873cf78cda0135300fc1851366b678903713b9d7c9bf5297aa
+size 5368