End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_mrpc_789_1760637907
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the mrpc dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4785
+- Loss: 0.1058
 - Num Input Tokens Seen: 6772448
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.10575559735298157,
+    "eval_runtime": 5.0299,
+    "eval_samples_per_second": 72.964,
+    "eval_steps_per_second": 18.291,
+    "num_input_tokens_seen": 6772448,
+    "total_flos": 3.055567923306824e+17,
+    "train_loss": 0.02818761768770438,
+    "train_runtime": 3327.9603,
+    "train_samples_per_second": 19.838,
+    "train_steps_per_second": 4.964
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.10575559735298157,
+    "eval_runtime": 5.0299,
+    "eval_samples_per_second": 72.964,
+    "eval_steps_per_second": 18.291,
+    "num_input_tokens_seen": 6772448
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 6772448,
+    "total_flos": 3.055567923306824e+17,
+    "train_loss": 0.02818761768770438,
+    "train_runtime": 3327.9603,
+    "train_samples_per_second": 19.838,
+    "train_steps_per_second": 4.964
+}