End of training

README.md

@@ -0,0 +1,52 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: NousResearch/Llama-2-7b-chat-hf
+model-index:
+- name: llama2-7b-summary-evaluate-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. -->
+
+# llama2-7b-summary-evaluate-finetune
+
+This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) 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: 2.5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 5
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "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": [
+    "down_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988f477fead179cb8741606c1c41b31cc0a20b77cd627055c857f8c948604d14
+size 848784976

logs/events.out.tfevents.1708597275.853d5573d8b7.647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a6912b2605059b33531e6533335878845388e87026978dd242edd98198469e
+size 5238

logs/events.out.tfevents.1708597315.853d5573d8b7.647.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42786f1cd34d073511fe0a994a4557fc11cf361a922dbc03b760f4dd6d8e0e55
+size 5393

logs/events.out.tfevents.1708597703.853d5573d8b7.647.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbaeab22e9abb75f77903958dd9e509aee4ec3c130f319f7655db873e79ec21
+size 6810

logs/events.out.tfevents.1708601048.853d5573d8b7.647.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72dab9da4cedb75616bde309d6cdf2150b50da337e1885fed954fb3a50c18363
+size 4184

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9499a8a3e2206edec605c6066b560aec6472db50f10e8721a9fa282eb7ba5f89
+size 4792