Balaaditya/TAVGEN-deepseek-coder-6.7b-adapter

README.md

@@ -0,0 +1,79 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
+model-index:
+- name: deepseek-coder-6.7b-instruct-TAVGEN-finetune
+  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. -->
+
+# deepseek-coder-6.7b-instruct-TAVGEN-finetune
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3206
+
+## 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: 2.5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5933        | 0.21  | 25   | 0.4703          |
+| 0.4589        | 0.42  | 50   | 0.4026          |
+| 0.4226        | 0.63  | 75   | 0.3733          |
+| 0.3968        | 0.84  | 100  | 0.3605          |
+| 0.3645        | 1.05  | 125  | 0.3483          |
+| 0.355         | 1.26  | 150  | 0.3421          |
+| 0.3318        | 1.47  | 175  | 0.3365          |
+| 0.3377        | 1.68  | 200  | 0.3318          |
+| 0.3111        | 1.89  | 225  | 0.3287          |
+| 0.3324        | 2.1   | 250  | 0.3242          |
+| 0.2757        | 2.31  | 275  | 0.3254          |
+| 0.3061        | 2.52  | 300  | 0.3253          |
+| 0.3015        | 2.73  | 325  | 0.3218          |
+| 0.2674        | 2.94  | 350  | 0.3209          |
+| 0.2579        | 3.15  | 375  | 0.3208          |
+| 0.2601        | 3.36  | 400  | 0.3225          |
+| 0.2396        | 3.57  | 425  | 0.3222          |
+| 0.2504        | 3.78  | 450  | 0.3220          |
+| 0.2786        | 3.99  | 475  | 0.3206          |
+| 0.2357        | 4.2   | 500  | 0.3206          |
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.38.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "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": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "lm_head",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8982d64e7935d9a3104940d4160ad2a7d97feaafab0a1b69f8bc43300f5cfb80
+size 853012048

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0182950deeb846876f82b04db6167bc9fee84c2176f88548d19a980716416d
+size 4664