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_chemistry
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_chemistry
 
-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_chemistry dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8001
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9554655870445345,
+    "eval_loss": 0.8001113533973694,
+    "eval_runtime": 32.2414,
+    "eval_samples_per_second": 25.743,
+    "eval_steps_per_second": 0.403,
+    "total_flos": 150543972433920.0,
+    "train_loss": 0.8360302607218425,
+    "train_runtime": 5544.9924,
+    "train_samples_per_second": 8.528,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9554655870445345,
+    "eval_loss": 0.8001113533973694,
+    "eval_runtime": 32.2414,
+    "eval_samples_per_second": 25.743,
+    "eval_steps_per_second": 0.403
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9554655870445345,
+    "total_flos": 150543972433920.0,
+    "train_loss": 0.8360302607218425,
+    "train_runtime": 5544.9924,
+    "train_samples_per_second": 8.528,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9554655870445345,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32388663967611336,
+      "grad_norm": 3.5835988058783754,
+      "learning_rate": 5e-06,
+      "loss": 0.9997,
+      "step": 10
+    },
+    {
+      "epoch": 0.6477732793522267,
+      "grad_norm": 1.5004109528112115,
+      "learning_rate": 5e-06,
+      "loss": 0.9054,
+      "step": 20
+    },
+    {
+      "epoch": 0.97165991902834,
+      "grad_norm": 1.3955293069271317,
+      "learning_rate": 5e-06,
+      "loss": 0.8668,
+      "step": 30
+    },
+    {
+      "epoch": 0.97165991902834,
+      "eval_loss": 0.8556345701217651,
+      "eval_runtime": 32.7399,
+      "eval_samples_per_second": 25.351,
+      "eval_steps_per_second": 0.397,
+      "step": 30
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 1.1961855385568927,
+      "learning_rate": 5e-06,
+      "loss": 0.8875,
+      "step": 40
+    },
+    {
+      "epoch": 1.639676113360324,
+      "grad_norm": 0.9145254182591637,
+      "learning_rate": 5e-06,
+      "loss": 0.8022,
+      "step": 50
+    },
+    {
+      "epoch": 1.9635627530364372,
+      "grad_norm": 0.7122060220868937,
+      "learning_rate": 5e-06,
+      "loss": 0.7929,
+      "step": 60
+    },
+    {
+      "epoch": 1.9635627530364372,
+      "eval_loss": 0.8138453960418701,
+      "eval_runtime": 32.4443,
+      "eval_samples_per_second": 25.582,
+      "eval_steps_per_second": 0.401,
+      "step": 60
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.3924801479206137,
+      "learning_rate": 5e-06,
+      "loss": 0.8051,
+      "step": 70
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 1.0637901985003577,
+      "learning_rate": 5e-06,
+      "loss": 0.7367,
+      "step": 80
+    },
+    {
+      "epoch": 2.9554655870445345,
+      "grad_norm": 0.8812313090644028,
+      "learning_rate": 5e-06,
+      "loss": 0.728,
+      "step": 90
+    },
+    {
+      "epoch": 2.9554655870445345,
+      "eval_loss": 0.8001113533973694,
+      "eval_runtime": 32.0665,
+      "eval_samples_per_second": 25.884,
+      "eval_steps_per_second": 0.405,
+      "step": 90
+    },
+    {
+      "epoch": 2.9554655870445345,
+      "step": 90,
+      "total_flos": 150543972433920.0,
+      "train_loss": 0.8360302607218425,
+      "train_runtime": 5544.9924,
+      "train_samples_per_second": 8.528,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 90,
+  "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": 150543972433920.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}