End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-7b-sft-full
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-full
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the generator dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.1644
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 2.164351224899292,
+    "eval_runtime": 1703.872,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 9.321,
+    "eval_steps_per_second": 1.166,
     "train_loss": 2.789915239123786,
     "train_runtime": 47169.5182,
     "train_samples": 207864,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32002
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 2.2348995208740234,
-    "eval_runtime": 2502.8496,
+    "eval_loss": 2.164351224899292,
+    "eval_runtime": 1703.872,
     "eval_samples": 23109,
-    "eval_samples_per_second": 6.345,
-    "eval_steps_per_second": 0.793
+    "eval_samples_per_second": 9.321,
+    "eval_steps_per_second": 1.166
 }