End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/deita-10k-v0-sft
 model-index:
 - name: mistral-7b-wo-live_qa-iter-sft-step1
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-7b-wo-live_qa-iter-sft-step1
 
-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 HuggingFaceH4/deita-10k-v0-sft dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.8004
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.87,
+    "eval_loss": 1.8004332780838013,
+    "eval_runtime": 1.8174,
+    "eval_samples": 100,
+    "eval_samples_per_second": 3.852,
+    "eval_steps_per_second": 0.55,
     "train_loss": 1.592680846651395,
     "train_runtime": 972.6889,
     "train_samples": 4848,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.87,
+    "eval_loss": 1.8004332780838013,
+    "eval_runtime": 1.8174,
+    "eval_samples": 100,
+    "eval_samples_per_second": 3.852,
+    "eval_steps_per_second": 0.55
+}