End of training

README.md

@@ -2,11 +2,15 @@
 license: other
 base_model: huggyllama/llama-7b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- GAIR/lima
 model-index:
 - name: llama-lima
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-lima
 
-This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on the generator dataset.
+This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on the GAIR/lima dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.9975
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
+    "eval_loss": 1.9975172281265259,
+    "eval_runtime": 2.0731,
+    "eval_samples": 300,
+    "eval_samples_per_second": 6.271,
+    "eval_steps_per_second": 0.482,
     "train_loss": 1.0947178224722545,
     "train_runtime": 366.9794,
     "train_samples": 1030,

config.json

@@ -25,6 +25,6 @@
   "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": 1.9975172281265259,
+    "eval_runtime": 2.0731,
+    "eval_samples": 300,
+    "eval_samples_per_second": 6.271,
+    "eval_steps_per_second": 0.482
+}

runs/Apr25_19-31-46_aga39/events.out.tfevents.1714094046.aga39.861402.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2147a49c65f36ec240dee348385782c9708257350af778f63fad9689f6f43827
+size 354