End of training

README.md

@@ -2,11 +2,15 @@
 license: llama2
 base_model: meta-llama/Llama-2-7b-hf
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- GAIR/lima
 model-index:
 - name: llama2-lima
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama2-lima
 
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the generator dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the GAIR/lima dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.5297
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
+    "eval_loss": 2.5297091007232666,
+    "eval_runtime": 2.0612,
+    "eval_samples": 300,
+    "eval_samples_per_second": 5.822,
+    "eval_steps_per_second": 0.485,
     "train_loss": 1.0364325324694315,
     "train_runtime": 358.0118,
     "train_samples": 1030,

config.json

@@ -23,6 +23,6 @@
   "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": 2.5297091007232666,
+    "eval_runtime": 2.0612,
+    "eval_samples": 300,
+    "eval_samples_per_second": 5.822,
+    "eval_steps_per_second": 0.485
+}

runs/Apr26_14-38-49_aga39/events.out.tfevents.1714161024.aga39.1452190.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03c81f39ac13323386f8483663135a7d9c911388c47193b5c91590d5c67c805
+size 354