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_emacs
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_emacs
 
-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_emacs dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7637
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9333333333333336,
+    "eval_loss": 0.7636918425559998,
+    "eval_runtime": 24.2046,
+    "eval_samples_per_second": 37.472,
+    "eval_steps_per_second": 0.62,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.7985600895351834,
+    "train_runtime": 3525.8092,
+    "train_samples_per_second": 14.66,
+    "train_steps_per_second": 0.028
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9333333333333336,
+    "eval_loss": 0.7636918425559998,
+    "eval_runtime": 24.2046,
+    "eval_samples_per_second": 37.472,
+    "eval_steps_per_second": 0.62
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9333333333333336,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.7985600895351834,
+    "train_runtime": 3525.8092,
+    "train_samples_per_second": 14.66,
+    "train_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9333333333333336,
+  "eval_steps": 500,
+  "global_step": 99,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 8.841581474102506,
+      "learning_rate": 5e-06,
+      "loss": 1.0027,
+      "step": 10
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 8.669231176540645,
+      "learning_rate": 5e-06,
+      "loss": 0.8838,
+      "step": 20
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.0438362887402333,
+      "learning_rate": 5e-06,
+      "loss": 0.8462,
+      "step": 30
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "eval_loss": 0.8316775560379028,
+      "eval_runtime": 24.3137,
+      "eval_samples_per_second": 37.304,
+      "eval_steps_per_second": 0.617,
+      "step": 33
+    },
+    {
+      "epoch": 1.1851851851851851,
+      "grad_norm": 1.5325350368450368,
+      "learning_rate": 5e-06,
+      "loss": 0.8292,
+      "step": 40
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 1.2135925661799924,
+      "learning_rate": 5e-06,
+      "loss": 0.7806,
+      "step": 50
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.9729741730730993,
+      "learning_rate": 5e-06,
+      "loss": 0.7626,
+      "step": 60
+    },
+    {
+      "epoch": 1.9851851851851852,
+      "eval_loss": 0.7775214910507202,
+      "eval_runtime": 23.9767,
+      "eval_samples_per_second": 37.828,
+      "eval_steps_per_second": 0.626,
+      "step": 67
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 1.4003520868501302,
+      "learning_rate": 5e-06,
+      "loss": 0.7619,
+      "step": 70
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.738966252442236,
+      "learning_rate": 5e-06,
+      "loss": 0.7081,
+      "step": 80
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.6691400354019779,
+      "learning_rate": 5e-06,
+      "loss": 0.6996,
+      "step": 90
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "eval_loss": 0.7636918425559998,
+      "eval_runtime": 22.9672,
+      "eval_samples_per_second": 39.491,
+      "eval_steps_per_second": 0.653,
+      "step": 99
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "step": 99,
+      "total_flos": 165619307642880.0,
+      "train_loss": 0.7985600895351834,
+      "train_runtime": 3525.8092,
+      "train_samples_per_second": 14.66,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 99,
+  "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": 165619307642880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}