granite-8b-code-instruct-TM1-tunned

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: ibm-granite/granite-8b-code-instruct
+model-index:
+- name: peft-dialogue-summary-training-1716404262
+  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-dialogue-summary-training-1716404262
+
+This model is a fine-tuned version of [ibm-granite/granite-8b-code-instruct](https://huggingface.co/ibm-granite/granite-8b-code-instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5224
+
+## 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: 8
+- 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: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 400
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 7.625         | 0.1453 | 25   | 5.7401          |
+| 5.3519        | 0.2907 | 50   | 4.5831          |
+| 4.2545        | 0.4360 | 75   | 3.8334          |
+| 4.2506        | 0.5814 | 100  | 3.3488          |
+| 3.5118        | 0.7267 | 125  | 2.8198          |
+| 3.1713        | 0.8721 | 150  | 2.4324          |
+| 2.5504        | 1.0174 | 175  | 2.3330          |
+| 2.174         | 1.1628 | 200  | 2.2412          |
+| 1.878         | 1.3081 | 225  | 2.1900          |
+| 1.9039        | 1.4535 | 250  | 2.0439          |
+| 1.7977        | 1.5988 | 275  | 1.9491          |
+| 1.7755        | 1.7442 | 300  | 1.8278          |
+| 1.629         | 1.8895 | 325  | 1.6587          |
+| 1.5533        | 2.0349 | 350  | 1.5799          |
+| 1.2937        | 2.1802 | 375  | 1.5344          |
+| 1.1375        | 2.3256 | 400  | 1.5224          |
+
+
+### 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 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-8b-code-instruct",
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "dense"
+  ],
+  "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:ee1502f2403f290549728f7379c09a17449c201f9416c2638ddd9c06ea30ae4c
+size 84963736

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71eb21a6919b210e71dcaea6c2ad6839a0e52e4c7d2f4e230d8bcd8f78ca034
+size 5048