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_webapps
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_webapps
 
-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_webapps dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8278
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.941798941798942,
+    "eval_loss": 0.82782381772995,
+    "eval_runtime": 15.8057,
+    "eval_samples_per_second": 40.239,
+    "eval_steps_per_second": 0.633,
+    "total_flos": 115368190279680.0,
+    "train_loss": 0.8884884516398112,
+    "train_runtime": 2539.9814,
+    "train_samples_per_second": 14.271,
+    "train_steps_per_second": 0.027
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.941798941798942,
+    "eval_loss": 0.82782381772995,
+    "eval_runtime": 15.8057,
+    "eval_samples_per_second": 40.239,
+    "eval_steps_per_second": 0.633
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.941798941798942,
+    "total_flos": 115368190279680.0,
+    "train_loss": 0.8884884516398112,
+    "train_runtime": 2539.9814,
+    "train_samples_per_second": 14.271,
+    "train_steps_per_second": 0.027
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.941798941798942,
+  "eval_steps": 500,
+  "global_step": 69,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42328042328042326,
+      "grad_norm": 1.8743734330499962,
+      "learning_rate": 5e-06,
+      "loss": 1.0642,
+      "step": 10
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 3.4276586490600525,
+      "learning_rate": 5e-06,
+      "loss": 0.9362,
+      "step": 20
+    },
+    {
+      "epoch": 0.9735449735449735,
+      "eval_loss": 0.9042366743087769,
+      "eval_runtime": 16.6191,
+      "eval_samples_per_second": 38.269,
+      "eval_steps_per_second": 0.602,
+      "step": 23
+    },
+    {
+      "epoch": 1.2804232804232805,
+      "grad_norm": 2.8364178197947685,
+      "learning_rate": 5e-06,
+      "loss": 0.9376,
+      "step": 30
+    },
+    {
+      "epoch": 1.7037037037037037,
+      "grad_norm": 1.1432414375508275,
+      "learning_rate": 5e-06,
+      "loss": 0.8478,
+      "step": 40
+    },
+    {
+      "epoch": 1.9576719576719577,
+      "eval_loss": 0.8493698835372925,
+      "eval_runtime": 16.0173,
+      "eval_samples_per_second": 39.707,
+      "eval_steps_per_second": 0.624,
+      "step": 46
+    },
+    {
+      "epoch": 2.1375661375661377,
+      "grad_norm": 2.1384495211584125,
+      "learning_rate": 5e-06,
+      "loss": 0.8658,
+      "step": 50
+    },
+    {
+      "epoch": 2.560846560846561,
+      "grad_norm": 2.0053210839734374,
+      "learning_rate": 5e-06,
+      "loss": 0.7832,
+      "step": 60
+    },
+    {
+      "epoch": 2.941798941798942,
+      "eval_loss": 0.82782381772995,
+      "eval_runtime": 15.5181,
+      "eval_samples_per_second": 40.984,
+      "eval_steps_per_second": 0.644,
+      "step": 69
+    },
+    {
+      "epoch": 2.941798941798942,
+      "step": 69,
+      "total_flos": 115368190279680.0,
+      "train_loss": 0.8884884516398112,
+      "train_runtime": 2539.9814,
+      "train_samples_per_second": 14.271,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "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
+}