End of training

README.md

@@ -2,12 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
 datasets:
-- generator
+- martimfasantos/openai-tldr-filtered
 model-index:
 - name: tinyllama-1.1b-sum-sft-qlora
   results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-sum-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 martimfasantos/openai-tldr-filtered dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.1479
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 4.0,
+    "eval_loss": 2.14786434173584,
+    "eval_runtime": 188.8433,
+    "eval_samples": 6553,
+    "eval_samples_per_second": 25.709,
+    "eval_steps_per_second": 3.214,
     "train_loss": 2.0942285917837413,
     "train_runtime": 51337.8051,
     "train_samples": 116722,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "eval_loss": 2.1439597606658936,
-    "eval_runtime": 190.2983,
+    "epoch": 4.0,
+    "eval_loss": 2.14786434173584,
+    "eval_runtime": 188.8433,
     "eval_samples": 6553,
-    "eval_samples_per_second": 25.555,
-    "eval_steps_per_second": 3.195
+    "eval_samples_per_second": 25.709,
+    "eval_steps_per_second": 3.214
 }

runs/May04_00-40-05_poseidon/events.out.tfevents.1714834748.poseidon.1378242.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3cd7ef5e8d770b2d8f79152df6eadd1efaf6fa001e402478c4cf2d007c8b00c
+size 364