End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: llama2
 base_model: codellama/CodeLlama-7b-Instruct-hf
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: codellama-7b-ultrachat
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # codellama-7b-ultrachat
 
-This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the generator dataset.
+This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0320
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.9990995047276003,
+    "eval_loss": 1.0319925546646118,
+    "eval_runtime": 659.7185,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 11.922,
+    "eval_steps_per_second": 0.746,
     "total_flos": 929619498762240.0,
     "train_loss": 1.0262996888375497,
     "train_runtime": 54210.2289,

config.json

@@ -25,6 +25,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32016
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9990995047276003,
+    "eval_loss": 1.0319925546646118,
+    "eval_runtime": 659.7185,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 11.922,
+    "eval_steps_per_second": 0.746
+}