End of training

README.md

@@ -1,11 +1,15 @@
 ---
 base_model: mistralai/Mistral-7B-v0.1
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- GAIR/lima
 model-index:
 - name: mistral-lima
   results: []
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-lima
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the GAIR/lima dataset.
 It achieves the following results on the evaluation set:
 - Loss: 3.9177
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
+    "eval_loss": 3.917660713195801,
+    "eval_runtime": 2.1914,
+    "eval_samples": 300,
+    "eval_samples_per_second": 5.476,
+    "eval_steps_per_second": 0.456,
     "train_loss": 0.41619996732721726,
     "train_runtime": 395.7925,
     "train_samples": 1030,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 3.917660713195801,
+    "eval_runtime": 2.1914,
+    "eval_samples": 300,
+    "eval_samples_per_second": 5.476,
+    "eval_steps_per_second": 0.456
+}

runs/Apr25_15-30-40_aga39/events.out.tfevents.1714077853.aga39.829294.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78018e22703f48c7ca123129239fe9d4f0cf4b42d17ad99a29e676a1f9a72255
+size 354