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_multirc_1745950270
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_multirc_1745950270
 
-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 multirc dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5388
+- Loss: 2.5283
 - Num Input Tokens Seen: 83543088
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 6.525328330206379,
+    "eval_loss": 2.5283308029174805,
+    "eval_runtime": 134.1956,
+    "eval_samples_per_second": 20.306,
+    "eval_steps_per_second": 10.157,
+    "num_input_tokens_seen": 83543088,
+    "total_flos": 3.565989290886562e+18,
+    "train_loss": 2.3986957787156107,
+    "train_runtime": 52463.916,
+    "train_samples_per_second": 3.05,
+    "train_steps_per_second": 0.762
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.525328330206379,
+    "eval_loss": 2.5283308029174805,
+    "eval_runtime": 134.1956,
+    "eval_samples_per_second": 20.306,
+    "eval_steps_per_second": 10.157,
+    "num_input_tokens_seen": 83543088
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.525328330206379,
+    "num_input_tokens_seen": 83543088,
+    "total_flos": 3.565989290886562e+18,
+    "train_loss": 2.3986957787156107,
+    "train_runtime": 52463.916,
+    "train_samples_per_second": 3.05,
+    "train_steps_per_second": 0.762
+}