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_2epochs
   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_2epochs
 
-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": 2.0,
     "total_flos": 0.0,
-    "train_loss": 0.6910306938443472,
-    "train_runtime": 4984.329,
+    "train_loss": 0.691034586010474,
+    "train_runtime": 5011.5072,
     "train_samples": 22202,
-    "train_samples_per_second": 8.909,
-    "train_steps_per_second": 0.557
+    "train_samples_per_second": 8.86,
+    "train_steps_per_second": 0.554
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046deec9f15d1f6d2c57d56ad931cbc665a0530bd717b4f03b4ce64b478a0305
+oid sha256:cce9dbb276e5dfaa605ae2dae7720fc7170bd331680ed8e12e07816cfa59290e
 size 4400216536

runs/Jul09_15-56-23_poseidon/events.out.tfevents.1720540635.poseidon.415297.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cae478fe1d62dfac4daef29fadc939da19ad40c67c4d1d6c9ad8019aefcccff
-size 184671
+oid sha256:84ce54aec64af6a235c7cdf064d55045803e2a11178e0fb7a20bb8732b8ddbd3
+size 196721

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 2.0,
     "total_flos": 0.0,
-    "train_loss": 0.6910306938443472,
-    "train_runtime": 4984.329,
+    "train_loss": 0.691034586010474,
+    "train_runtime": 5011.5072,
     "train_samples": 22202,
-    "train_samples_per_second": 8.909,
-    "train_steps_per_second": 0.557
+    "train_samples_per_second": 8.86,
+    "train_steps_per_second": 0.554
 }