End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.3
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- llama-duo/synth_classification_dataset_dedup
 model-index:
 - name: mistral-7b-0.3-gpt4o_100k_classification-fft
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-7b-0.3-gpt4o_100k_classification-fft
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the llama-duo/synth_classification_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 5.3380
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 5.337969779968262,
+    "eval_runtime": 1.8922,
+    "eval_samples": 16,
+    "eval_samples_per_second": 1.057,
+    "eval_steps_per_second": 0.528,
     "total_flos": 14002264473600.0,
     "train_loss": 6.666975224196022,
     "train_runtime": 4378.2382,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32770
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 5.337969779968262,
+    "eval_runtime": 1.8922,
+    "eval_samples": 16,
+    "eval_samples_per_second": 1.057,
+    "eval_steps_per_second": 0.528
+}

runs/Sep28_10-43-01_637888cb4368/events.out.tfevents.1727525953.637888cb4368.403296.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b745ad70aa4fb1f0f7c22923ce367d02819518516becc8523a89cc084f2fb0
+size 359