End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: cc-by-nc-4.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: ONS-AI-RESEARCH/ONS-SOLAR-10.7B
+model-index:
+- name: ONS-SOLAR-10.7B_trained_trained_v2
+  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. -->
+
+# ONS-SOLAR-10.7B_trained_trained_v2
+
+This model is a fine-tuned version of [ONS-AI-RESEARCH/ONS-SOLAR-10.7B](https://huggingface.co/ONS-AI-RESEARCH/ONS-SOLAR-10.7B) 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: 10
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ONS-AI-RESEARCH/ONS-SOLAR-10.7B",
+  "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": 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": [
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "o_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:a89fec18773e4a30730df7b5ca6d4547853b9430e6894253ec83e1b4be7acc72
+size 125918320

runs/Mar07_09-17-26_9497367dda34/events.out.tfevents.1709803047.9497367dda34.4827.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148455dab57d00db5c6ece3c4dac9bcb2c408eabe14f3a0dc627e5d9b79c3ea5
+size 5156

runs/Mar07_09-21-15_9497367dda34/events.out.tfevents.1709803276.9497367dda34.4827.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fd14959513615cd311e80823be5b36475a7e541561df6543a24e20688c4dc0
+size 5504

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23d17421c140897ffd69a06efc784a22930bb37e68b98510181aa693bb7a3a49
+size 4984