End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: AngelRaychev/1.5B-policy-iteration_1
+base_model: AngelRaychev/1.5B-policy-iteration_0
 library_name: transformers
 model_name: 1.5B-policy-iteration_1
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for 1.5B-policy-iteration_1
 
-This model is a fine-tuned version of [AngelRaychev/1.5B-policy-iteration_1](https://huggingface.co/AngelRaychev/1.5B-policy-iteration_1).
+This model is a fine-tuned version of [AngelRaychev/1.5B-policy-iteration_0](https://huggingface.co/AngelRaychev/1.5B-policy-iteration_0).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -11,7 +11,7 @@
   "intermediate_size": 8960,
   "max_position_embeddings": 131072,
   "max_window_layers": 28,
-  "model_card": "\nFinal Loss: 0.1317\nBatch Size: 256\nLearning Rate: 2e-05\nDataset Size: 12000\n",
+  "model_card": "\nFinal Loss: 0.1842\nBatch Size: 256\nLearning Rate: 5e-05\nDataset Size: 12000\n",
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_hidden_layers": 28,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c2a728ecbc0cf54d5458ca4fe3d460f9f3b829ad8fa6ecfb7fde7999e2bf73
+oid sha256:5d08dac0c66e023986f2e0a29aa33dba76efc7946e1c30604f6a1aa88281206b
 size 3087542418

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b07b2c0668be4ce53ef595293f1604d215cd49a50d1639da4c7a057c417109
+oid sha256:beadf6bbe6057f310426ae0ad11f389d6b8a042f53a175ab7e04467900f30f90
 size 5624