Model save

README.md

@@ -2,15 +2,9 @@
 license: apache-2.0
 base_model: martimfasantos/tinyllama-1.1b-mt-sft-full
 tags:
-- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
-- trl
-- dpo
-- generated_from_trainer
-datasets:
-- haoranxu/ALMA-R-Preference
 model-index:
 - name: tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_3epochs
   results: []
@@ -21,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_3epochs
 
-This model is a fine-tuned version of [martimfasantos/tinyllama-1.1b-mt-sft-full](https://huggingface.co/martimfasantos/tinyllama-1.1b-mt-sft-full) on the haoranxu/ALMA-R-Preference dataset.
+This model is a fine-tuned version of [martimfasantos/tinyllama-1.1b-mt-sft-full](https://huggingface.co/martimfasantos/tinyllama-1.1b-mt-sft-full) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 0.6880504754617968,
-    "train_runtime": 7518.2292,
+    "train_loss": 0.6880548467553658,
+    "train_runtime": 7425.9787,
     "train_samples": 22202,
-    "train_samples_per_second": 8.859,
-    "train_steps_per_second": 0.554
+    "train_samples_per_second": 8.969,
+    "train_steps_per_second": 0.561
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b255afc68140ac6cf85e54c1bba26a3aaa08d7e2d0349b1efe7fb2247047aaaf
+oid sha256:f1b885604e2dc70b26210e77a8b3b53cf2dfa4ecccc6618b5dddc7f3774206c4
 size 4400216536

runs/Jul09_21-21-38_poseidon/events.out.tfevents.1720560144.poseidon.534326.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199bb0a8c0bf87503051f4553c31696dad5308db16637eafb518945c16344242
-size 287871
+oid sha256:04f6e1c69aee1091efa1988694eb4098bfaef3900995fe8c445f74f5effb2dfd
+size 292353

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 0.6880504754617968,
-    "train_runtime": 7518.2292,
+    "train_loss": 0.6880548467553658,
+    "train_runtime": 7425.9787,
     "train_samples": 22202,
-    "train_samples_per_second": 8.859,
-    "train_steps_per_second": 0.554
+    "train_samples_per_second": 8.969,
+    "train_steps_per_second": 0.561
 }