End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: stackexchange_cooking
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_cooking
 
-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 mlfoundations-dev/stackexchange_cooking dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8588
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9109947643979055,
+    "eval_loss": 0.85880446434021,
+    "eval_runtime": 27.4398,
+    "eval_samples_per_second": 23.397,
+    "eval_steps_per_second": 0.401,
+    "total_flos": 115368190279680.0,
+    "train_loss": 0.9101425530253977,
+    "train_runtime": 4367.891,
+    "train_samples_per_second": 8.372,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9109947643979055,
+    "eval_loss": 0.85880446434021,
+    "eval_runtime": 27.4398,
+    "eval_samples_per_second": 23.397,
+    "eval_steps_per_second": 0.401
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9109947643979055,
+    "total_flos": 115368190279680.0,
+    "train_loss": 0.9101425530253977,
+    "train_runtime": 4367.891,
+    "train_samples_per_second": 8.372,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9109947643979055,
+  "eval_steps": 500,
+  "global_step": 69,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 8.671039079726013,
+      "learning_rate": 5e-06,
+      "loss": 1.0776,
+      "step": 10
+    },
+    {
+      "epoch": 0.837696335078534,
+      "grad_norm": 2.3671003212194863,
+      "learning_rate": 5e-06,
+      "loss": 0.9655,
+      "step": 20
+    },
+    {
+      "epoch": 0.9633507853403142,
+      "eval_loss": 0.9337097406387329,
+      "eval_runtime": 27.8917,
+      "eval_samples_per_second": 23.018,
+      "eval_steps_per_second": 0.394,
+      "step": 23
+    },
+    {
+      "epoch": 1.2670157068062826,
+      "grad_norm": 1.8325627798052408,
+      "learning_rate": 5e-06,
+      "loss": 0.9481,
+      "step": 30
+    },
+    {
+      "epoch": 1.6858638743455496,
+      "grad_norm": 1.8440131747312392,
+      "learning_rate": 5e-06,
+      "loss": 0.8776,
+      "step": 40
+    },
+    {
+      "epoch": 1.9790575916230366,
+      "eval_loss": 0.8832862973213196,
+      "eval_runtime": 27.8144,
+      "eval_samples_per_second": 23.082,
+      "eval_steps_per_second": 0.395,
+      "step": 47
+    },
+    {
+      "epoch": 2.115183246073298,
+      "grad_norm": 2.0684170060645104,
+      "learning_rate": 5e-06,
+      "loss": 0.8826,
+      "step": 50
+    },
+    {
+      "epoch": 2.5340314136125652,
+      "grad_norm": 1.326428006740787,
+      "learning_rate": 5e-06,
+      "loss": 0.8099,
+      "step": 60
+    },
+    {
+      "epoch": 2.9109947643979055,
+      "eval_loss": 0.85880446434021,
+      "eval_runtime": 27.386,
+      "eval_samples_per_second": 23.443,
+      "eval_steps_per_second": 0.402,
+      "step": 69
+    },
+    {
+      "epoch": 2.9109947643979055,
+      "step": 69,
+      "total_flos": 115368190279680.0,
+      "train_loss": 0.9101425530253977,
+      "train_runtime": 4367.891,
+      "train_samples_per_second": 8.372,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 69,
+  "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": 115368190279680.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}