End of training

README.md

@@ -0,0 +1,57 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: meta-llama/Llama-2-13b-chat-hf
+model-index:
+- name: llama2_13b_lora_adapter
+  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_13b_lora_adapter
+
+This model is a fine-tuned version of [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- 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:dbf9a2976c1841f01ce140469a3b6836208af25eb96453a71e0e6076f2d01d35
+oid sha256:200a737144cfcf9452cc740c811c7a9f74627fdeb58ac6f017cea08da846f3b7
 size 250422888

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.878623526912e+16,
+    "train_loss": 0.9400251382752393,
+    "train_runtime": 7654.5047,
+    "train_samples_per_second": 1.377,
+    "train_steps_per_second": 0.086
+}

runs/Apr01_19-22-17_7b6d45b43bf4/events.out.tfevents.1711999361.7b6d45b43bf4.6185.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d8dec7397d009fed003d9aa665eb9b262e9376762a189888e2642149b49915
-size 6121
+oid sha256:96927db4ba8b91b32293d00aed897df4917b1fb2525b3e63d7052dd9f0e0dad8
+size 6686

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.878623526912e+16,
+    "train_loss": 0.9400251382752393,
+    "train_runtime": 7654.5047,
+    "train_samples_per_second": 1.377,
+    "train_steps_per_second": 0.086
+}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9985772550507446,
+  "eval_steps": 500,
+  "global_step": 658,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.3818485736846924,
+      "learning_rate": 1.984705192213004e-05,
+      "loss": 1.5534,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.1903014183044434,
+      "learning_rate": 1.761094828138534e-05,
+      "loss": 0.8705,
+      "step": 200
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.446919322013855,
+      "learning_rate": 1.3281315178199537e-05,
+      "loss": 0.8352,
+      "step": 300
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.4014055728912354,
+      "learning_rate": 8.04909677983872e-06,
+      "loss": 0.8368,
+      "step": 400
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.499550461769104,
+      "learning_rate": 3.3535097208036584e-06,
+      "loss": 0.8154,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.5235815048217773,
+      "learning_rate": 4.861604459298697e-07,
+      "loss": 0.8083,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "step": 658,
+      "total_flos": 4.878623526912e+16,
+      "train_loss": 0.9400251382752393,
+      "train_runtime": 7654.5047,
+      "train_samples_per_second": 1.377,
+      "train_steps_per_second": 0.086
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 658,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4.878623526912e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}