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: llama3-1_8b_mlfoundations-dev-stackexchange_politics
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_mlfoundations-dev-stackexchange_politics
 
-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_politics dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9989
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.912359550561798,
+    "eval_loss": 0.998900830745697,
+    "eval_runtime": 74.5376,
+    "eval_samples_per_second": 10.049,
+    "eval_steps_per_second": 0.322,
+    "total_flos": 135573327052800.0,
+    "train_loss": 1.030050583091783,
+    "train_runtime": 11855.278,
+    "train_samples_per_second": 3.597,
+    "train_steps_per_second": 0.007
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.912359550561798,
+    "eval_loss": 0.998900830745697,
+    "eval_runtime": 74.5376,
+    "eval_samples_per_second": 10.049,
+    "eval_steps_per_second": 0.322
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.912359550561798,
+    "total_flos": 135573327052800.0,
+    "train_loss": 1.030050583091783,
+    "train_runtime": 11855.278,
+    "train_samples_per_second": 3.597,
+    "train_steps_per_second": 0.007
+}

trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.912359550561798,
+  "eval_steps": 500,
+  "global_step": 81,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 2.2871070615537374,
+      "learning_rate": 5e-06,
+      "loss": 1.224,
+      "step": 10
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 1.879362326942809,
+      "learning_rate": 5e-06,
+      "loss": 1.1104,
+      "step": 20
+    },
+    {
+      "epoch": 0.9707865168539326,
+      "eval_loss": 1.065308928489685,
+      "eval_runtime": 74.2144,
+      "eval_samples_per_second": 10.092,
+      "eval_steps_per_second": 0.323,
+      "step": 27
+    },
+    {
+      "epoch": 1.0786516853932584,
+      "grad_norm": 3.5179449394032516,
+      "learning_rate": 5e-06,
+      "loss": 1.0655,
+      "step": 30
+    },
+    {
+      "epoch": 1.4382022471910112,
+      "grad_norm": 3.3352183901214407,
+      "learning_rate": 5e-06,
+      "loss": 1.0192,
+      "step": 40
+    },
+    {
+      "epoch": 1.797752808988764,
+      "grad_norm": 2.674135070178994,
+      "learning_rate": 5e-06,
+      "loss": 1.0003,
+      "step": 50
+    },
+    {
+      "epoch": 1.9775280898876404,
+      "eval_loss": 1.020365595817566,
+      "eval_runtime": 73.8982,
+      "eval_samples_per_second": 10.136,
+      "eval_steps_per_second": 0.325,
+      "step": 55
+    },
+    {
+      "epoch": 2.157303370786517,
+      "grad_norm": 1.7509747209943183,
+      "learning_rate": 5e-06,
+      "loss": 0.9689,
+      "step": 60
+    },
+    {
+      "epoch": 2.5168539325842696,
+      "grad_norm": 1.7491734389860694,
+      "learning_rate": 5e-06,
+      "loss": 0.9351,
+      "step": 70
+    },
+    {
+      "epoch": 2.8764044943820224,
+      "grad_norm": 2.3376418120487097,
+      "learning_rate": 5e-06,
+      "loss": 0.9279,
+      "step": 80
+    },
+    {
+      "epoch": 2.912359550561798,
+      "eval_loss": 0.998900830745697,
+      "eval_runtime": 73.9229,
+      "eval_samples_per_second": 10.132,
+      "eval_steps_per_second": 0.325,
+      "step": 81
+    },
+    {
+      "epoch": 2.912359550561798,
+      "step": 81,
+      "total_flos": 135573327052800.0,
+      "train_loss": 1.030050583091783,
+      "train_runtime": 11855.278,
+      "train_samples_per_second": 3.597,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 81,
+  "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": 135573327052800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}