End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.3
 tags:
 - llama-factory
+- lntuning
 - generated_from_trainer
 model-index:
 - name: train_cola_1744902678
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_cola_1744902678
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on an unknown 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 cola dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1452
+- Loss: 0.1416
 - Num Input Tokens Seen: 28700680
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 83.16008316008316,
+    "eval_loss": 0.1415577083826065,
+    "eval_runtime": 8.6425,
+    "eval_samples_per_second": 99.046,
+    "eval_steps_per_second": 24.761,
+    "num_input_tokens_seen": 28700680,
+    "total_flos": 1.225072234834821e+18,
+    "train_loss": 0.11859339318908751,
+    "train_runtime": 23487.702,
+    "train_samples_per_second": 27.248,
+    "train_steps_per_second": 1.703
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 83.16008316008316,
+    "eval_loss": 0.1415577083826065,
+    "eval_runtime": 8.6425,
+    "eval_samples_per_second": 99.046,
+    "eval_steps_per_second": 24.761,
+    "num_input_tokens_seen": 28700680
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 83.16008316008316,
+    "num_input_tokens_seen": 28700680,
+    "total_flos": 1.225072234834821e+18,
+    "train_loss": 0.11859339318908751,
+    "train_runtime": 23487.702,
+    "train_samples_per_second": 27.248,
+    "train_steps_per_second": 1.703
+}