End of training

README.md

@@ -1,12 +1,27 @@
 ---
 base_model: meta-llama/Meta-Llama-3.1-8B
+datasets:
+- wikitext
 library_name: peft
 license: llama3.1
+metrics:
+- accuracy
 tags:
 - generated_from_trainer
 model-index:
 - name: wikitext_Meta-Llama-3.1-8B-BNB-NF4_LORA_ADAPTER_64rank
-  results: []
+  results:
+  - task:
+      type: text-generation
+      name: Causal Language Modeling
+    dataset:
+      name: wikitext wikitext-2-raw-v1
+      type: wikitext
+      args: wikitext-2-raw-v1
+    metrics:
+    - type: accuracy
+      value: 0.5869990224828935
+      name: Accuracy
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wikitext_Meta-Llama-3.1-8B-BNB-NF4_LORA_ADAPTER_64rank
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the wikitext wikitext-2-raw-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3246
+- Accuracy: 0.5870
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5869990224828935,
+    "eval_loss": 2.324615478515625,
+    "eval_runtime": 0.4762,
+    "eval_samples": 2,
+    "eval_samples_per_second": 4.2,
+    "eval_steps_per_second": 2.1,
+    "perplexity": 10.22274846352924,
+    "total_flos": 1212187410432.0,
+    "train_loss": 2.900122960408529,
+    "train_runtime": 13.1285,
+    "train_samples": 11,
+    "train_samples_per_second": 2.514,
+    "train_steps_per_second": 0.229
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5869990224828935,
+    "eval_loss": 2.324615478515625,
+    "eval_runtime": 0.4762,
+    "eval_samples": 2,
+    "eval_samples_per_second": 4.2,
+    "eval_steps_per_second": 2.1,
+    "perplexity": 10.22274846352924
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1212187410432.0,
+    "train_loss": 2.900122960408529,
+    "train_runtime": 13.1285,
+    "train_samples": 11,
+    "train_samples_per_second": 2.514,
+    "train_steps_per_second": 0.229
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 3,
+      "total_flos": 1212187410432.0,
+      "train_loss": 2.900122960408529,
+      "train_runtime": 13.1285,
+      "train_samples_per_second": 2.514,
+      "train_steps_per_second": 0.229
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1212187410432.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}