End of training

README.md

@@ -0,0 +1,58 @@
+---
+base_model: tiiuae/falcon-7b
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: Chatbot
+  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. -->
+
+# Chatbot
+
+This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the None 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- training_steps: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "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": [
+    "query_key_value"
+  ],
+  "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 sha256:4bac7a4fc4907505e61083fe1c6bcc27b5c5f1e0e83b503b813c0190b90ca7b2
+size 18883912

runs/Sep15_02-06-19_9d720fece735/events.out.tfevents.1726366009.9d720fece735.230.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f58ce19aa6518c852fd852d2cca6ed8ec5a08241fc1d48e4ff2619344bf490
+size 22835

runs/Sep15_02-17-37_9d720fece735/events.out.tfevents.1726366660.9d720fece735.230.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67fef4c0ee4d0a7a6d06ec38b32caaedefbc9940463d4c7251d690645cd66392
+size 22836

runs/Sep15_02-27-03_9d720fece735/events.out.tfevents.1726367225.9d720fece735.230.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b50d63ab236fcba612b6481b84164ebb49e40b2619182e139cf3687eeea0c46
+size 26977

runs/Sep15_02-27-03_9d720fece735/events.out.tfevents.1726367940.9d720fece735.230.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a074fa3d4f6a4d6e7ba2df84e74033f7c4581fd596935c3f442e03d778cebbba
+size 26977

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f65efd4b74f03b7d2cc245cf4306f633f067325b17b4a94eb6dafed88d57f13
+size 5176