End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.3
 tags:
 - llama-factory
+- ia3
 - generated_from_trainer
 model-index:
 - name: train_record_1745950254
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_record_1745950254
 
-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 record dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4941
 - Num Input Tokens Seen: 60870656

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.2803277639075603,
+    "eval_loss": 0.49408820271492004,
+    "eval_runtime": 533.374,
+    "eval_samples_per_second": 26.034,
+    "eval_steps_per_second": 13.017,
+    "num_input_tokens_seen": 60870656,
+    "total_flos": 2.5982039689286124e+18,
+    "train_loss": 0.5386139680683613,
+    "train_runtime": 133028.9435,
+    "train_samples_per_second": 1.203,
+    "train_steps_per_second": 0.301
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.2803277639075603,
+    "eval_loss": 0.49408820271492004,
+    "eval_runtime": 533.374,
+    "eval_samples_per_second": 26.034,
+    "eval_steps_per_second": 13.017,
+    "num_input_tokens_seen": 60870656
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.2803277639075603,
+    "num_input_tokens_seen": 60870656,
+    "total_flos": 2.5982039689286124e+18,
+    "train_loss": 0.5386139680683613,
+    "train_runtime": 133028.9435,
+    "train_samples_per_second": 1.203,
+    "train_steps_per_second": 0.301
+}