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_blender
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_blender
 
-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_blender dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8665
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.950191570881226,
+    "eval_loss": 0.8665193915367126,
+    "eval_runtime": 34.7993,
+    "eval_samples_per_second": 25.259,
+    "eval_steps_per_second": 0.402,
+    "total_flos": 160594195906560.0,
+    "train_loss": 0.9321899265050888,
+    "train_runtime": 5921.2847,
+    "train_samples_per_second": 8.453,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.950191570881226,
+    "eval_loss": 0.8665193915367126,
+    "eval_runtime": 34.7993,
+    "eval_samples_per_second": 25.259,
+    "eval_steps_per_second": 0.402
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.950191570881226,
+    "total_flos": 160594195906560.0,
+    "train_loss": 0.9321899265050888,
+    "train_runtime": 5921.2847,
+    "train_samples_per_second": 8.453,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.950191570881226,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3065134099616858,
+      "grad_norm": 12.74104481384653,
+      "learning_rate": 5e-06,
+      "loss": 1.1641,
+      "step": 10
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 2.1790757213494896,
+      "learning_rate": 5e-06,
+      "loss": 1.0297,
+      "step": 20
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 4.362340101302588,
+      "learning_rate": 5e-06,
+      "loss": 0.9678,
+      "step": 30
+    },
+    {
+      "epoch": 0.9808429118773946,
+      "eval_loss": 0.941736102104187,
+      "eval_runtime": 35.4599,
+      "eval_samples_per_second": 24.789,
+      "eval_steps_per_second": 0.395,
+      "step": 32
+    },
+    {
+      "epoch": 1.2298850574712643,
+      "grad_norm": 1.9633918418876213,
+      "learning_rate": 5e-06,
+      "loss": 0.9658,
+      "step": 40
+    },
+    {
+      "epoch": 1.5363984674329503,
+      "grad_norm": 2.2920150639630377,
+      "learning_rate": 5e-06,
+      "loss": 0.899,
+      "step": 50
+    },
+    {
+      "epoch": 1.842911877394636,
+      "grad_norm": 1.4658859694154964,
+      "learning_rate": 5e-06,
+      "loss": 0.8809,
+      "step": 60
+    },
+    {
+      "epoch": 1.996168582375479,
+      "eval_loss": 0.8847602605819702,
+      "eval_runtime": 35.2476,
+      "eval_samples_per_second": 24.938,
+      "eval_steps_per_second": 0.397,
+      "step": 65
+    },
+    {
+      "epoch": 2.153256704980843,
+      "grad_norm": 1.0346495845463786,
+      "learning_rate": 5e-06,
+      "loss": 0.8941,
+      "step": 70
+    },
+    {
+      "epoch": 2.4597701149425286,
+      "grad_norm": 1.1514102670732111,
+      "learning_rate": 5e-06,
+      "loss": 0.8302,
+      "step": 80
+    },
+    {
+      "epoch": 2.766283524904215,
+      "grad_norm": 1.0141738208203366,
+      "learning_rate": 5e-06,
+      "loss": 0.8249,
+      "step": 90
+    },
+    {
+      "epoch": 2.950191570881226,
+      "eval_loss": 0.8665193915367126,
+      "eval_runtime": 34.3631,
+      "eval_samples_per_second": 25.58,
+      "eval_steps_per_second": 0.407,
+      "step": 96
+    },
+    {
+      "epoch": 2.950191570881226,
+      "step": 96,
+      "total_flos": 160594195906560.0,
+      "train_loss": 0.9321899265050888,
+      "train_runtime": 5921.2847,
+      "train_samples_per_second": 8.453,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 96,
+  "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": 160594195906560.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}