End of training

README.md

@@ -3,6 +3,10 @@ library_name: transformers
 license: llama2
 base_model: meta-llama/Llama-2-7b-chat-hf
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9955156950672646,
+    "eval_loss": 0.5801262855529785,
+    "eval_runtime": 0.6673,
+    "eval_samples": 20,
+    "eval_samples_per_second": 7.493,
+    "eval_steps_per_second": 1.499,
     "total_flos": 11568225976320.0,
     "train_loss": 0.6212725338635144,
     "train_runtime": 594.4014,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9955156950672646,
+    "eval_loss": 0.5801262855529785,
+    "eval_runtime": 0.6673,
+    "eval_samples": 20,
+    "eval_samples_per_second": 7.493,
+    "eval_steps_per_second": 1.499
+}

runs/Jan19_23-37-39_dgx-a100-14/events.out.tfevents.1737327242.dgx-a100-14.551972.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058bf888f78bdcaf4650dbfdff9a1f09dfb2929d46fd707285cdc173fc963c5f
+size 354