End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_stsb_456_1760637813
 
-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 stsb dataset.
 It achieves the following results on the evaluation set:
 - Loss: 4.6793
 - Num Input Tokens Seen: 8714656

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 4.679266929626465,
+    "eval_runtime": 6.0126,
+    "eval_samples_per_second": 95.633,
+    "eval_steps_per_second": 23.95,
+    "num_input_tokens_seen": 8714656,
+    "total_flos": 3.924309420744376e+17,
+    "train_loss": 4.706687201230198,
+    "train_runtime": 3526.8186,
+    "train_samples_per_second": 29.341,
+    "train_steps_per_second": 7.338
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 4.679266929626465,
+    "eval_runtime": 6.0126,
+    "eval_samples_per_second": 95.633,
+    "eval_steps_per_second": 23.95,
+    "num_input_tokens_seen": 8714656
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 8714656,
+    "total_flos": 3.924309420744376e+17,
+    "train_loss": 4.706687201230198,
+    "train_runtime": 3526.8186,
+    "train_samples_per_second": 29.341,
+    "train_steps_per_second": 7.338
+}