End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.3
 tags:
 - llama-factory
+- prompt-tuning
 - generated_from_trainer
 datasets:
 - super_glue
@@ -17,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_boolq_1745950280
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the super_glue dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the boolq dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3286
+- Loss: 0.3260
 - Num Input Tokens Seen: 37097424
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 18.85902876001886,
+    "eval_loss": 0.3259987235069275,
+    "eval_runtime": 33.5596,
+    "eval_samples_per_second": 28.099,
+    "eval_steps_per_second": 14.065,
+    "num_input_tokens_seen": 37097424,
+    "total_flos": 1.5834232254395843e+18,
+    "train_loss": 0.33570288619101046,
+    "train_runtime": 19776.3723,
+    "train_samples_per_second": 8.09,
+    "train_steps_per_second": 2.023
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 18.85902876001886,
+    "eval_loss": 0.3259987235069275,
+    "eval_runtime": 33.5596,
+    "eval_samples_per_second": 28.099,
+    "eval_steps_per_second": 14.065,
+    "num_input_tokens_seen": 37097424
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 18.85902876001886,
+    "num_input_tokens_seen": 37097424,
+    "total_flos": 1.5834232254395843e+18,
+    "train_loss": 0.33570288619101046,
+    "train_runtime": 19776.3723,
+    "train_samples_per_second": 8.09,
+    "train_steps_per_second": 2.023
+}