Model save

README.md

@@ -2,15 +2,10 @@
 license: gemma
 base_model: google/gemma-1.1-2b-it
 tags:
-- alignment-handbook
-- trl
-- dpo
-- generated_from_trainer
 - trl
 - dpo
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- cat-searcher/responses-gemma-1.1-2b-it-split-0-evol-mixed-pair
 model-index:
 - name: gemma-1.1-2b-it-sppo-iter0-evol-mixed
   results: []
@@ -19,10 +14,10 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/the-dream-machine/huggingface/runs/ciqulebv)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/the-dream-machine/huggingface/runs/4dtfeber)
 # gemma-1.1-2b-it-sppo-iter0-evol-mixed
 
-This model is a fine-tuned version of [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it) on the cat-searcher/responses-gemma-1.1-2b-it-split-0-evol-mixed-pair dataset.
+This model is a fine-tuned version of [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it) on an unknown dataset.
 
 ## Model description
 
@@ -53,7 +48,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 18.0
+- num_epochs: 36.0
 
 ### Training results
 

all_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 17.954430379746835,
+    "epoch": 35.95443037974684,
     "total_flos": 0.0,
-    "train_loss": 44832.452316430485,
-    "train_runtime": 5475.4345,
+    "train_loss": 6426.156043451248,
+    "train_runtime": 5724.5218,
     "train_samples": 12624,
-    "train_samples_per_second": 41.5,
-    "train_steps_per_second": 0.648
+    "train_samples_per_second": 79.389,
+    "train_steps_per_second": 1.239
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed814dd0961606bf8f136893b5ac6db5b34996942df61cdd742fa8b39675918
+oid sha256:9c98819bd7ebf9f4f84613a6ce592559ee60e298079c8647484f587b8ddfaa9c
 size 4945242264

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7983011ab46577b5812dee2914f35c1577b2064d355f477d8d01787725d5a5
+oid sha256:9b55fe97c7727d4fb1e21e08eab5da530266a45a4ca32cfe38f34a121d96c30f
 size 67121608

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 17.954430379746835,
+    "epoch": 35.95443037974684,
     "total_flos": 0.0,
-    "train_loss": 44832.452316430485,
-    "train_runtime": 5475.4345,
+    "train_loss": 6426.156043451248,
+    "train_runtime": 5724.5218,
     "train_samples": 12624,
-    "train_samples_per_second": 41.5,
-    "train_steps_per_second": 0.648
+    "train_samples_per_second": 79.389,
+    "train_steps_per_second": 1.239
 }