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_cs
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_cs
 
-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_cs dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8299
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.952681388012618,
+    "eval_loss": 0.8298914432525635,
+    "eval_runtime": 42.4006,
+    "eval_samples_per_second": 25.188,
+    "eval_steps_per_second": 0.401,
+    "total_flos": 195769978060800.0,
+    "train_loss": 0.8570637702941895,
+    "train_runtime": 7098.1857,
+    "train_samples_per_second": 8.575,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.952681388012618,
+    "eval_loss": 0.8298914432525635,
+    "eval_runtime": 42.4006,
+    "eval_samples_per_second": 25.188,
+    "eval_steps_per_second": 0.401
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.952681388012618,
+    "total_flos": 195769978060800.0,
+    "train_loss": 0.8570637702941895,
+    "train_runtime": 7098.1857,
+    "train_samples_per_second": 8.575,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,143 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.952681388012618,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25236593059936907,
+      "grad_norm": 8.41365741344912,
+      "learning_rate": 5e-06,
+      "loss": 1.0484,
+      "step": 10
+    },
+    {
+      "epoch": 0.5047318611987381,
+      "grad_norm": 11.65576938704163,
+      "learning_rate": 5e-06,
+      "loss": 0.9503,
+      "step": 20
+    },
+    {
+      "epoch": 0.7570977917981072,
+      "grad_norm": 3.4333812572317535,
+      "learning_rate": 5e-06,
+      "loss": 0.9154,
+      "step": 30
+    },
+    {
+      "epoch": 0.9842271293375394,
+      "eval_loss": 0.8807940483093262,
+      "eval_runtime": 42.4298,
+      "eval_samples_per_second": 25.171,
+      "eval_steps_per_second": 0.401,
+      "step": 39
+    },
+    {
+      "epoch": 1.0094637223974763,
+      "grad_norm": 2.6039929525533,
+      "learning_rate": 5e-06,
+      "loss": 0.9231,
+      "step": 40
+    },
+    {
+      "epoch": 1.2618296529968454,
+      "grad_norm": 5.365832625548147,
+      "learning_rate": 5e-06,
+      "loss": 0.8491,
+      "step": 50
+    },
+    {
+      "epoch": 1.5141955835962144,
+      "grad_norm": 1.043340286746537,
+      "learning_rate": 5e-06,
+      "loss": 0.8351,
+      "step": 60
+    },
+    {
+      "epoch": 1.7665615141955837,
+      "grad_norm": 1.3611149813219945,
+      "learning_rate": 5e-06,
+      "loss": 0.83,
+      "step": 70
+    },
+    {
+      "epoch": 1.9936908517350158,
+      "eval_loss": 0.8404849767684937,
+      "eval_runtime": 42.3838,
+      "eval_samples_per_second": 25.198,
+      "eval_steps_per_second": 0.401,
+      "step": 79
+    },
+    {
+      "epoch": 2.0189274447949526,
+      "grad_norm": 1.3439288553488564,
+      "learning_rate": 5e-06,
+      "loss": 0.8503,
+      "step": 80
+    },
+    {
+      "epoch": 2.271293375394322,
+      "grad_norm": 0.866126423142029,
+      "learning_rate": 5e-06,
+      "loss": 0.7683,
+      "step": 90
+    },
+    {
+      "epoch": 2.5236593059936907,
+      "grad_norm": 0.9042296171319385,
+      "learning_rate": 5e-06,
+      "loss": 0.7682,
+      "step": 100
+    },
+    {
+      "epoch": 2.77602523659306,
+      "grad_norm": 0.548578701544745,
+      "learning_rate": 5e-06,
+      "loss": 0.7675,
+      "step": 110
+    },
+    {
+      "epoch": 2.952681388012618,
+      "eval_loss": 0.8298914432525635,
+      "eval_runtime": 41.6582,
+      "eval_samples_per_second": 25.637,
+      "eval_steps_per_second": 0.408,
+      "step": 117
+    },
+    {
+      "epoch": 2.952681388012618,
+      "step": 117,
+      "total_flos": 195769978060800.0,
+      "train_loss": 0.8570637702941895,
+      "train_runtime": 7098.1857,
+      "train_samples_per_second": 8.575,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 117,
+  "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": 195769978060800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}