End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: tiiuae/falcon-7b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- GAIR/lima
 model-index:
 - name: falcon-lima
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # falcon-lima
 
-This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the generator dataset.
+This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the GAIR/lima dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.4276
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 9.09,
+    "eval_loss": 2.4275567531585693,
+    "eval_runtime": 2.0538,
+    "eval_samples": 300,
+    "eval_samples_per_second": 5.356,
+    "eval_steps_per_second": 0.487,
     "train_loss": 1.39877197265625,
     "train_runtime": 578.7401,
     "train_samples": 1030,

config.json

@@ -33,6 +33,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 65024
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.09,
+    "eval_loss": 2.4275567531585693,
+    "eval_runtime": 2.0538,
+    "eval_samples": 300,
+    "eval_samples_per_second": 5.356,
+    "eval_steps_per_second": 0.487
+}

runs/Apr27_01-54-02_aga39/events.out.tfevents.1714201713.aga39.1542291.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03012343345269b7c1540f2fb9cb1d00022702e0b5a74f829f5f5abf73a8041
+size 354