AHS_SPO_FAQ_LM_V_2.0

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.1
+model-index:
+- name: peft-InstructionTuning-training-1720112861
+  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-InstructionTuning-training-1720112861
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.1](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.1) 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: 0.0003
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v0.1",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_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 sha256:02ba21fe3af48ae984ad31bb081440e69e2579470eb3083f92f43d9c6be4d724
+size 9022864

runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720112904.2d713d9f225b.96.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5fd67561401d215286bb5ad1e817434a3190aeb12121d8569c808fd7e6c00a
+size 6411

runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113148.2d713d9f225b.96.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840bdac9e2969412866f7e6286fe542ca3b64aad16aeac0508be3d2c74e31f76
+size 6411

runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113348.2d713d9f225b.96.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf812100c52bd67dfc454fdb4935aea709dd842a5e8b476dcd11599d1b147a5a
+size 6411

runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113552.2d713d9f225b.96.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd50541512b3483542c49d186b30505c3ec50ffcd8d52b6e9fe54c4bdca64051
+size 6411

runs/Jul04_17-07-41_2d713d9f225b/events.out.tfevents.1720113756.2d713d9f225b.96.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e35424ace99a92c4eb42cc064436437cb2e2ac934298959a4f8c7ee9ade596
+size 6411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:973019056e78d13cc5f3e6112379d4abca2ae58cb5e4c5959373f0bdb431d083
+size 5368