End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: final_combined_mc_data
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # final_combined_mc_data
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the identity and the final_combined_mc_data datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.7356
+- Loss: 0.8601
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 8.955223880597014,
+    "eval_loss": 0.8600807189941406,
+    "eval_runtime": 1.182,
+    "eval_samples_per_second": 18.613,
+    "eval_steps_per_second": 2.538,
+    "total_flos": 37587570917376.0,
+    "train_loss": 0.2476747315376997,
+    "train_runtime": 2030.6526,
+    "train_samples_per_second": 5.264,
+    "train_steps_per_second": 0.039
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 8.955223880597014,
+    "eval_loss": 0.8600807189941406,
+    "eval_runtime": 1.182,
+    "eval_samples_per_second": 18.613,
+    "eval_steps_per_second": 2.538
+}

runs/Mar25_06-37-26_cab5dc79-97e2-4af7-8451-ddd879bff597-0/events.out.tfevents.1742886915.cab5dc79-97e2-4af7-8451-ddd879bff597-0.6613.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c786b30c7468f9d1032c56431bbe5d23328f675d90b5c8a21006085a9bdbcb9d
+size 306

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.955223880597014,
+    "total_flos": 37587570917376.0,
+    "train_loss": 0.2476747315376997,
+    "train_runtime": 2030.6526,
+    "train_samples_per_second": 5.264,
+    "train_steps_per_second": 0.039
+}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.955223880597014,
+  "eval_steps": 50,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1194029850746268,
+      "grad_norm": 12.171414081678625,
+      "learning_rate": 9.980973490458728e-06,
+      "loss": 1.0602,
+      "step": 10
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "grad_norm": 5.102956254122534,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.4908,
+      "step": 20
+    },
+    {
+      "epoch": 3.3582089552238807,
+      "grad_norm": 3.0060478102356094,
+      "learning_rate": 7.86788218175523e-06,
+      "loss": 0.224,
+      "step": 30
+    },
+    {
+      "epoch": 4.477611940298507,
+      "grad_norm": 2.451051410299596,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.1026,
+      "step": 40
+    },
+    {
+      "epoch": 5.597014925373134,
+      "grad_norm": 1.885409477326922,
+      "learning_rate": 3.705904774487396e-06,
+      "loss": 0.0593,
+      "step": 50
+    },
+    {
+      "epoch": 5.597014925373134,
+      "eval_loss": 0.7355796694755554,
+      "eval_runtime": 1.1864,
+      "eval_samples_per_second": 18.543,
+      "eval_steps_per_second": 2.529,
+      "step": 50
+    },
+    {
+      "epoch": 6.7164179104477615,
+      "grad_norm": 1.2736191437207434,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.0265,
+      "step": 60
+    },
+    {
+      "epoch": 7.835820895522388,
+      "grad_norm": 1.2918144398905065,
+      "learning_rate": 4.6846106481675035e-07,
+      "loss": 0.012,
+      "step": 70
+    },
+    {
+      "epoch": 8.955223880597014,
+      "grad_norm": 0.3695610719057999,
+      "learning_rate": 0.0,
+      "loss": 0.006,
+      "step": 80
+    },
+    {
+      "epoch": 8.955223880597014,
+      "step": 80,
+      "total_flos": 37587570917376.0,
+      "train_loss": 0.2476747315376997,
+      "train_runtime": 2030.6526,
+      "train_samples_per_second": 5.264,
+      "train_steps_per_second": 0.039
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 80,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 37587570917376.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}