End of training

README.md

@@ -4,6 +4,7 @@ license: other
 base_model: TechxGenus/Meta-Llama-3-8B-Instruct-AWQ
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: qlora_all
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qlora_all
 
-This model is a fine-tuned version of [TechxGenus/Meta-Llama-3-8B-Instruct-AWQ](https://huggingface.co/TechxGenus/Meta-Llama-3-8B-Instruct-AWQ) on an unknown dataset.
+This model is a fine-tuned version of [TechxGenus/Meta-Llama-3-8B-Instruct-AWQ](https://huggingface.co/TechxGenus/Meta-Llama-3-8B-Instruct-AWQ) on the healthcaremagic dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9504
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.8,
+    "eval_loss": 2.9503965377807617,
+    "eval_runtime": 0.8116,
+    "eval_samples_per_second": 123.22,
+    "eval_steps_per_second": 2.464,
+    "total_flos": 2419202069626880.0,
+    "train_loss": 4.330888430277507,
+    "train_runtime": 55.824,
+    "train_samples_per_second": 48.366,
+    "train_steps_per_second": 0.054
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.8,
+    "eval_loss": 2.9503965377807617,
+    "eval_runtime": 0.8116,
+    "eval_samples_per_second": 123.22,
+    "eval_steps_per_second": 2.464
+}

runs/Dec29_02-43-48_64-181-222-101/events.out.tfevents.1735440465.64-181-222-101.15044.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4754a758a0033c227625db3da2080648e02ff3cf5f2c0f80db09dc40292a4f46
+size 354

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.8,
+    "total_flos": 2419202069626880.0,
+    "train_loss": 4.330888430277507,
+    "train_runtime": 55.824,
+    "train_samples_per_second": 48.366,
+    "train_steps_per_second": 0.054
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.8,
+      "step": 3,
+      "total_flos": 2419202069626880.0,
+      "train_loss": 4.330888430277507,
+      "train_runtime": 55.824,
+      "train_samples_per_second": 48.366,
+      "train_steps_per_second": 0.054
+    }
+  ],
+  "logging_steps": 10,
+  "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": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2419202069626880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}