model_2024-07-26_01-52

README.md

@@ -0,0 +1,56 @@
+---
+base_model: NumbersStation/nsql-350M
+library_name: peft
+license: bsd-3-clause
+tags:
+- generated_from_trainer
+model-index:
+- name: training_run
+  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. -->
+
+# training_run
+
+This model is a fine-tuned version of [NumbersStation/nsql-350M](https://huggingface.co/NumbersStation/nsql-350M) 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.42.3
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NumbersStation/nsql-350M",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "out_proj",
+    "qkv_proj",
+    "fc_in",
+    "lm_head",
+    "fc_out"
+  ],
+  "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 sha256:32ac780f189dac7db30ff059ca8572eb2dd4decfceb4708c052ded852842c07d
+size 222098488

logs/events.out.tfevents.1721958009.0db24c1873c7.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52dc55dc891531f4430719a6c6210090229280a23da8e1c381ffd1ffbc5b133d
+size 5668

logs/events.out.tfevents.1721958085.0db24c1873c7.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b8872585ba4b7277cba3efa767c63cb31a4d7abceb553c8dc454f646a12a8b
+size 5668

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12cdd3c33f2a644763426340deb64edb0d5181e80301040cb9d9160e275cdc59
+size 5048