End of training

README.md

@@ -2,13 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
-- alignment-handbook
 - generated_from_trainer
 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: tinyllama-1.1b-sft-qlora
   results: []
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-sft-qlora
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the generator dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1695
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.1695406436920166,
-    "eval_runtime": 1921.16,
+    "eval_loss": 1.1695410013198853,
+    "eval_runtime": 2106.6157,
     "eval_samples": 23109,
-    "eval_samples_per_second": 8.415,
-    "eval_steps_per_second": 1.052,
+    "eval_samples_per_second": 7.674,
+    "eval_steps_per_second": 0.959,
     "train_loss": 0.0036345586762629653,
     "train_runtime": 2327.0298,
     "train_samples": 207864,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.1695406436920166,
-    "eval_runtime": 1921.16,
+    "eval_loss": 1.1695410013198853,
+    "eval_runtime": 2106.6157,
     "eval_samples": 23109,
-    "eval_samples_per_second": 8.415,
-    "eval_steps_per_second": 1.052
+    "eval_samples_per_second": 7.674,
+    "eval_steps_per_second": 0.959
 }

runs/Apr23_17-34-48_poseidon/events.out.tfevents.1713898158.poseidon.710489.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96d51b58510f07aeef3c23de6743ca14eacc4aaed93020d96026c8d98bbfe33
+size 364