Upload folder using huggingface_hub

llama2-7b-retpo-topiocqa/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "./results/topiocqa/llama2-7b/oqf-union-bm25/sft_from_qe",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

llama2-7b-retpo-topiocqa/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.35.0"
+}

llama2-7b-retpo-topiocqa/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c9bd17e8c0c0fce7951d8adf06d653df86c7bc6354a578da8bf3ea2c118c97
+size 4938985352

llama2-7b-retpo-topiocqa/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ba48ffba34149fcf3fa859225482147a5aa4db10256dc72b1b948ea793b17c
+size 4947390880

llama2-7b-retpo-topiocqa/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:184e3f009299f2dbe8bce5f5785503b71a72333bcdbd5ac796aa9ee220ad405b
+size 3590488816

llama2-7b-retpo-topiocqa/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

llama2-7b-retpo-topiocqa/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llama2-7b-retpo-topiocqa/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "max_length": 2048,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

llama2-7b-retpo-topiocqa/trainer_state.json

@@ -0,0 +1,480 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 294,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6666666666666667e-08,
+      "logits/chosen": -0.7770026326179504,
+      "logits/rejected": -0.7530519366264343,
+      "logps/chosen": -57.126220703125,
+      "logps/rejected": -61.33452224731445,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.6666666666666665e-07,
+      "logits/chosen": -0.9137387871742249,
+      "logits/rejected": -0.9412133097648621,
+      "logps/chosen": -60.2840576171875,
+      "logps/rejected": -58.41568374633789,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.4611111283302307,
+      "rewards/chosen": 0.0008645269554108381,
+      "rewards/margins": 0.0022316318936645985,
+      "rewards/rejected": -0.0013671049382537603,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.333333333333333e-07,
+      "logits/chosen": -0.9285407066345215,
+      "logits/rejected": -0.9265729188919067,
+      "logps/chosen": -60.87455368041992,
+      "logps/rejected": -57.644287109375,
+      "loss": 0.6849,
+      "rewards/accuracies": 0.6350000500679016,
+      "rewards/chosen": -0.01559995673596859,
+      "rewards/margins": 0.014468361623585224,
+      "rewards/rejected": -0.03006831929087639,
+      "step": 20
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5e-07,
+      "logits/chosen": -0.9013168215751648,
+      "logits/rejected": -0.930048942565918,
+      "logps/chosen": -62.65340042114258,
+      "logps/rejected": -61.812767028808594,
+      "loss": 0.661,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.1316472589969635,
+      "rewards/margins": 0.0966319590806961,
+      "rewards/rejected": -0.2282792031764984,
+      "step": 30
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.81060606060606e-07,
+      "logits/chosen": -0.8814967274665833,
+      "logits/rejected": -0.8919669389724731,
+      "logps/chosen": -63.17937088012695,
+      "logps/rejected": -62.691368103027344,
+      "loss": 0.6357,
+      "rewards/accuracies": 0.5949999690055847,
+      "rewards/chosen": -0.26310157775878906,
+      "rewards/margins": 0.21280471980571747,
+      "rewards/rejected": -0.4759063124656677,
+      "step": 40
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.6212121212121207e-07,
+      "logits/chosen": -0.8884746432304382,
+      "logits/rejected": -0.8979630470275879,
+      "logps/chosen": -62.36811065673828,
+      "logps/rejected": -63.00883102416992,
+      "loss": 0.6278,
+      "rewards/accuracies": 0.6700000166893005,
+      "rewards/chosen": -0.25367558002471924,
+      "rewards/margins": 0.2429538518190384,
+      "rewards/rejected": -0.49662941694259644,
+      "step": 50
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.4318181818181817e-07,
+      "logits/chosen": -0.8140326738357544,
+      "logits/rejected": -0.8309772610664368,
+      "logps/chosen": -62.639244079589844,
+      "logps/rejected": -62.56007766723633,
+      "loss": 0.6262,
+      "rewards/accuracies": 0.6899999976158142,
+      "rewards/chosen": -0.26934942603111267,
+      "rewards/margins": 0.3159269690513611,
+      "rewards/rejected": -0.5852764248847961,
+      "step": 60
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.242424242424242e-07,
+      "logits/chosen": -0.9202006459236145,
+      "logits/rejected": -0.9258785247802734,
+      "logps/chosen": -61.98707962036133,
+      "logps/rejected": -63.402015686035156,
+      "loss": 0.6243,
+      "rewards/accuracies": 0.6550000309944153,
+      "rewards/chosen": -0.2668350338935852,
+      "rewards/margins": 0.24013900756835938,
+      "rewards/rejected": -0.5069740414619446,
+      "step": 70
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.0530303030303026e-07,
+      "logits/chosen": -0.8547884821891785,
+      "logits/rejected": -0.8482406735420227,
+      "logps/chosen": -62.955810546875,
+      "logps/rejected": -63.34333038330078,
+      "loss": 0.6392,
+      "rewards/accuracies": 0.5800000429153442,
+      "rewards/chosen": -0.3227940797805786,
+      "rewards/margins": 0.16901376843452454,
+      "rewards/rejected": -0.49180787801742554,
+      "step": 80
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.8636363636363636e-07,
+      "logits/chosen": -0.9100571870803833,
+      "logits/rejected": -0.9373546838760376,
+      "logps/chosen": -63.04186248779297,
+      "logps/rejected": -63.738868713378906,
+      "loss": 0.6048,
+      "rewards/accuracies": 0.6449999809265137,
+      "rewards/chosen": -0.28149670362472534,
+      "rewards/margins": 0.2635510265827179,
+      "rewards/rejected": -0.5450477600097656,
+      "step": 90
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.674242424242424e-07,
+      "logits/chosen": -0.9057644605636597,
+      "logits/rejected": -0.9370818138122559,
+      "logps/chosen": -62.23480224609375,
+      "logps/rejected": -63.780906677246094,
+      "loss": 0.6237,
+      "rewards/accuracies": 0.6800000667572021,
+      "rewards/chosen": -0.24398000538349152,
+      "rewards/margins": 0.3119112253189087,
+      "rewards/rejected": -0.555891215801239,
+      "step": 100
+    },
+    {
+      "epoch": 1.02,
+      "eval_logits/chosen": -0.627898633480072,
+      "eval_logits/rejected": -0.6445847749710083,
+      "eval_logps/chosen": -57.94969940185547,
+      "eval_logps/rejected": -62.748870849609375,
+      "eval_loss": 0.6418440341949463,
+      "eval_rewards/accuracies": 0.375,
+      "eval_rewards/chosen": -0.3959883451461792,
+      "eval_rewards/margins": -0.04571329429745674,
+      "eval_rewards/rejected": -0.35027503967285156,
+      "eval_runtime": 85.8466,
+      "eval_samples_per_second": 1.165,
+      "eval_steps_per_second": 0.047,
+      "step": 100
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.484848484848485e-07,
+      "logits/chosen": -0.870263934135437,
+      "logits/rejected": -0.8801482915878296,
+      "logps/chosen": -63.51879119873047,
+      "logps/rejected": -64.17228698730469,
+      "loss": 0.5937,
+      "rewards/accuracies": 0.6700000166893005,
+      "rewards/chosen": -0.24940630793571472,
+      "rewards/margins": 0.3023271858692169,
+      "rewards/rejected": -0.5517336130142212,
+      "step": 110
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.295454545454545e-07,
+      "logits/chosen": -0.8701096773147583,
+      "logits/rejected": -0.8789488077163696,
+      "logps/chosen": -60.916908264160156,
+      "logps/rejected": -63.46611404418945,
+      "loss": 0.5963,
+      "rewards/accuracies": 0.7049999833106995,
+      "rewards/chosen": -0.23008105158805847,
+      "rewards/margins": 0.35002774000167847,
+      "rewards/rejected": -0.5801087617874146,
+      "step": 120
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.106060606060606e-07,
+      "logits/chosen": -0.9663147926330566,
+      "logits/rejected": -0.9866538047790527,
+      "logps/chosen": -62.04589080810547,
+      "logps/rejected": -63.1934700012207,
+      "loss": 0.5867,
+      "rewards/accuracies": 0.6949999928474426,
+      "rewards/chosen": -0.1878770887851715,
+      "rewards/margins": 0.375627338886261,
+      "rewards/rejected": -0.5635043978691101,
+      "step": 130
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.916666666666667e-07,
+      "logits/chosen": -0.8954381942749023,
+      "logits/rejected": -0.9015897512435913,
+      "logps/chosen": -62.21129608154297,
+      "logps/rejected": -63.928916931152344,
+      "loss": 0.5716,
+      "rewards/accuracies": 0.7150000333786011,
+      "rewards/chosen": -0.22819480299949646,
+      "rewards/margins": 0.4343329966068268,
+      "rewards/rejected": -0.6625277996063232,
+      "step": 140
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.727272727272727e-07,
+      "logits/chosen": -0.9764545559883118,
+      "logits/rejected": -0.9872282147407532,
+      "logps/chosen": -61.337921142578125,
+      "logps/rejected": -63.76161575317383,
+      "loss": 0.5894,
+      "rewards/accuracies": 0.7050000429153442,
+      "rewards/chosen": -0.24536123871803284,
+      "rewards/margins": 0.33146461844444275,
+      "rewards/rejected": -0.5768259167671204,
+      "step": 150
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.537878787878788e-07,
+      "logits/chosen": -0.9501914978027344,
+      "logits/rejected": -0.9539823532104492,
+      "logps/chosen": -64.19468688964844,
+      "logps/rejected": -63.57381057739258,
+      "loss": 0.5922,
+      "rewards/accuracies": 0.7099999785423279,
+      "rewards/chosen": -0.09005232900381088,
+      "rewards/margins": 0.43597155809402466,
+      "rewards/rejected": -0.5260238647460938,
+      "step": 160
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.3484848484848486e-07,
+      "logits/chosen": -1.0213310718536377,
+      "logits/rejected": -1.0140588283538818,
+      "logps/chosen": -61.80049514770508,
+      "logps/rejected": -64.17625427246094,
+      "loss": 0.5784,
+      "rewards/accuracies": 0.7599999308586121,
+      "rewards/chosen": -0.17086324095726013,
+      "rewards/margins": 0.3900156617164612,
+      "rewards/rejected": -0.5608788728713989,
+      "step": 170
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.159090909090909e-07,
+      "logits/chosen": -0.9447614550590515,
+      "logits/rejected": -0.9392558932304382,
+      "logps/chosen": -64.57820129394531,
+      "logps/rejected": -64.07698059082031,
+      "loss": 0.5793,
+      "rewards/accuracies": 0.6850000023841858,
+      "rewards/chosen": -0.2530820369720459,
+      "rewards/margins": 0.3604905605316162,
+      "rewards/rejected": -0.6135725378990173,
+      "step": 180
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.9696969696969696e-07,
+      "logits/chosen": -1.0343739986419678,
+      "logits/rejected": -1.0418659448623657,
+      "logps/chosen": -62.85361862182617,
+      "logps/rejected": -64.90449523925781,
+      "loss": 0.5698,
+      "rewards/accuracies": 0.7299999594688416,
+      "rewards/chosen": -0.2781550884246826,
+      "rewards/margins": 0.41078242659568787,
+      "rewards/rejected": -0.6889375448226929,
+      "step": 190
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.7803030303030303e-07,
+      "logits/chosen": -0.9188686609268188,
+      "logits/rejected": -0.9459314346313477,
+      "logps/chosen": -62.70424270629883,
+      "logps/rejected": -64.33283233642578,
+      "loss": 0.5671,
+      "rewards/accuracies": 0.7700000405311584,
+      "rewards/chosen": -0.21425025165081024,
+      "rewards/margins": 0.5228456258773804,
+      "rewards/rejected": -0.7370960116386414,
+      "step": 200
+    },
+    {
+      "epoch": 2.04,
+      "eval_logits/chosen": -0.6976795792579651,
+      "eval_logits/rejected": -0.7093760371208191,
+      "eval_logps/chosen": -58.1360969543457,
+      "eval_logps/rejected": -63.76995086669922,
+      "eval_loss": 0.6006367206573486,
+      "eval_rewards/accuracies": 0.375,
+      "eval_rewards/chosen": -0.4146280288696289,
+      "eval_rewards/margins": 0.037754401564598083,
+      "eval_rewards/rejected": -0.4523824453353882,
+      "eval_runtime": 85.9629,
+      "eval_samples_per_second": 1.163,
+      "eval_steps_per_second": 0.047,
+      "step": 200
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.5909090909090907e-07,
+      "logits/chosen": -1.0530180931091309,
+      "logits/rejected": -1.0670045614242554,
+      "logps/chosen": -60.627899169921875,
+      "logps/rejected": -62.67585372924805,
+      "loss": 0.5673,
+      "rewards/accuracies": 0.6999999284744263,
+      "rewards/chosen": -0.22572699189186096,
+      "rewards/margins": 0.38177213072776794,
+      "rewards/rejected": -0.6074991226196289,
+      "step": 210
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.4015151515151512e-07,
+      "logits/chosen": -0.8931347131729126,
+      "logits/rejected": -0.9050127267837524,
+      "logps/chosen": -62.85188674926758,
+      "logps/rejected": -66.02424621582031,
+      "loss": 0.5507,
+      "rewards/accuracies": 0.7849999666213989,
+      "rewards/chosen": -0.13409505784511566,
+      "rewards/margins": 0.5803736448287964,
+      "rewards/rejected": -0.714468777179718,
+      "step": 220
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.2121212121212122e-07,
+      "logits/chosen": -0.9528385400772095,
+      "logits/rejected": -0.9684345126152039,
+      "logps/chosen": -61.46783447265625,
+      "logps/rejected": -63.68975830078125,
+      "loss": 0.5323,
+      "rewards/accuracies": 0.7350000143051147,
+      "rewards/chosen": -0.19861415028572083,
+      "rewards/margins": 0.502434253692627,
+      "rewards/rejected": -0.7010484933853149,
+      "step": 230
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.0227272727272728e-07,
+      "logits/chosen": -0.9085640907287598,
+      "logits/rejected": -0.928179144859314,
+      "logps/chosen": -60.18157196044922,
+      "logps/rejected": -63.78962326049805,
+      "loss": 0.5559,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.2662022113800049,
+      "rewards/margins": 0.374268114566803,
+      "rewards/rejected": -0.6404703855514526,
+      "step": 240
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 8.333333333333333e-08,
+      "logits/chosen": -0.9296838641166687,
+      "logits/rejected": -0.9239009022712708,
+      "logps/chosen": -60.54166793823242,
+      "logps/rejected": -64.93536376953125,
+      "loss": 0.5316,
+      "rewards/accuracies": 0.7850000262260437,
+      "rewards/chosen": -0.21018747985363007,
+      "rewards/margins": 0.5464566349983215,
+      "rewards/rejected": -0.7566441297531128,
+      "step": 250
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.439393939393938e-08,
+      "logits/chosen": -1.0489236116409302,
+      "logits/rejected": -1.0565475225448608,
+      "logps/chosen": -62.51433563232422,
+      "logps/rejected": -65.67848205566406,
+      "loss": 0.5432,
+      "rewards/accuracies": 0.6899999976158142,
+      "rewards/chosen": -0.32812416553497314,
+      "rewards/margins": 0.4675385355949402,
+      "rewards/rejected": -0.7956627011299133,
+      "step": 260
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 4.545454545454545e-08,
+      "logits/chosen": -0.8963821530342102,
+      "logits/rejected": -0.9191139936447144,
+      "logps/chosen": -62.355865478515625,
+      "logps/rejected": -64.9944076538086,
+      "loss": 0.5409,
+      "rewards/accuracies": 0.7399999499320984,
+      "rewards/chosen": -0.25284919142723083,
+      "rewards/margins": 0.5685437917709351,
+      "rewards/rejected": -0.8213930130004883,
+      "step": 270
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.6515151515151513e-08,
+      "logits/chosen": -1.0132668018341064,
+      "logits/rejected": -1.000647783279419,
+      "logps/chosen": -61.652748107910156,
+      "logps/rejected": -64.6360092163086,
+      "loss": 0.5494,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.2190549373626709,
+      "rewards/margins": 0.5060803294181824,
+      "rewards/rejected": -0.7251352071762085,
+      "step": 280
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 7.575757575757576e-09,
+      "logits/chosen": -0.9516438245773315,
+      "logits/rejected": -0.9391864538192749,
+      "logps/chosen": -62.0220947265625,
+      "logps/rejected": -64.91535949707031,
+      "loss": 0.5622,
+      "rewards/accuracies": 0.6950000524520874,
+      "rewards/chosen": -0.3045981526374817,
+      "rewards/margins": 0.4031611979007721,
+      "rewards/rejected": -0.7077593803405762,
+      "step": 290
+    },
+    {
+      "epoch": 3.0,
+      "step": 294,
+      "total_flos": 0.0,
+      "train_loss": 0.5917348229155248,
+      "train_runtime": 14214.5177,
+      "train_samples_per_second": 3.283,
+      "train_steps_per_second": 0.021
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 294,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

llama2-7b-retpo-topiocqa/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885fbd8ad2d2a924db7d459616f0408d190af80ff7dc43e19ce7207b071b2f43
+size 5752