Model save

README.md

@@ -0,0 +1,59 @@
+---
+license: llama2
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: meta-llama/LlamaGuard-7b
+model-index:
+- name: llama-guard-finetuned-1ep-1000
+  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. -->
+
+# llama-guard-finetuned-1ep-1000
+
+This model is a fine-tuned version of [meta-llama/LlamaGuard-7b](https://huggingface.co/meta-llama/LlamaGuard-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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 0.5
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.39.3
+- Pytorch 2.3.0+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f74eedf4b04d44f2c3ff5e2bad205aa9a112e5ff02efb196e1b961cfbb56bd
+oid sha256:46d22215a55899e608455e074cb7a9c35437dda5e5a922c0faed2dfe70395cbb
 size 1182844512

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.5,
+    "total_flos": 7567679883608064.0,
+    "train_loss": 0.6456813195656086,
+    "train_runtime": 1993.1291,
+    "train_samples": 1851,
+    "train_samples_per_second": 0.464,
+    "train_steps_per_second": 0.058
+}

runs/Apr10_18-56-25_llamaguard2/events.out.tfevents.1712775395.llamaguard2.4075.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e7ae647e14aec772fd8ca487ed1bc2fa56908393f9651790bfdbf57b8220f3
-size 5945
+oid sha256:4600d83d7f623267f5e45d0b64e3aeb0df475430b4078eb0efb782f8a93abdc4
+size 6293

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.5,
+    "total_flos": 7567679883608064.0,
+    "train_loss": 0.6456813195656086,
+    "train_runtime": 1993.1291,
+    "train_samples": 1851,
+    "train_samples_per_second": 0.464,
+    "train_steps_per_second": 0.058
+}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5010799136069114,
+  "eval_steps": 500,
+  "global_step": 116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.6869832873344421,
+      "learning_rate": 0.0002,
+      "loss": 2.0793,
+      "step": 25
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.3831043243408203,
+      "learning_rate": 0.0002,
+      "loss": 0.3566,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.13696692883968353,
+      "learning_rate": 0.0002,
+      "loss": 0.268,
+      "step": 75
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.08374959230422974,
+      "learning_rate": 0.0002,
+      "loss": 0.142,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "step": 116,
+      "total_flos": 7567679883608064.0,
+      "train_loss": 0.6456813195656086,
+      "train_runtime": 1993.1291,
+      "train_samples_per_second": 0.464,
+      "train_steps_per_second": 0.058
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 7567679883608064.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}