baltop/mistral-sql-finetune

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: mistral-sql-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. -->
+
+# mistral-sql-finetune
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1301
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.8552        | 0.52  | 25   | 1.3859          |
+| 1.0032        | 1.04  | 50   | 1.2098          |
+| 0.6187        | 1.56  | 75   | 1.2380          |
+| 0.5451        | 2.08  | 100  | 1.3525          |
+| 0.267         | 2.6   | 125  | 1.4362          |
+| 0.2475        | 3.12  | 150  | 1.4954          |
+| 0.1659        | 3.65  | 175  | 1.5494          |
+| 0.1581        | 4.17  | 200  | 1.9906          |
+| 0.1317        | 4.69  | 225  | 1.7269          |
+| 0.1133        | 5.21  | 250  | 1.8710          |
+| 0.1129        | 5.73  | 275  | 1.8427          |
+| 0.1046        | 6.25  | 300  | 1.9983          |
+| 0.1056        | 6.77  | 325  | 1.9216          |
+| 0.0998        | 7.29  | 350  | 2.0076          |
+| 0.0962        | 7.81  | 375  | 2.0135          |
+| 0.0873        | 8.33  | 400  | 2.0257          |
+| 0.0924        | 8.85  | 425  | 2.0783          |
+| 0.0885        | 9.38  | 450  | 2.0932          |
+| 0.0894        | 9.9   | 475  | 2.1196          |
+| 0.0829        | 10.42 | 500  | 2.1301          |
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "lm_head",
+    "up_proj",
+    "v_proj",
+    "down_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:d3348cc155485132ef91130da464549a91ca7085d38561dbdeab6856cfd98981
+size 864513616

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604d2154728641cb203cde92c016671ee80c32ddcc96c2591194707df13882ab
+size 4664