Upload 16 files

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "Minirecord/Mini_synatra_7b_02",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.2",
+  "use_cache": false
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9457e4d52566ab0ef31e5d6c855e43bc678a5675a7bc9b59cad0e742f2f1b5
+size 4943178720

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a61ea3d384ee57cb74b2f5621639c5b4d6a670e6d1a9bcd3a8033553f56e62
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9841c6060cebff52687ad06e88aa3fc0e6201dd98e6096fcaf313f93aa95f2
+size 4540532728

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483496960
+  },
+  "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-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-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-00002-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-00002-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-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-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-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-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-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-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"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6da138dc536a649fc0d28253e4c1dbfee4fff0f005c05419d08dc0549a7e53
+size 14483588341

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378a63f959f3a14c7507a9528fb908c4e52ea79ae64648e0dbec6fd9ddec720b
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a73ed4a4c7d0e21db496bd9cec149de99ef577c83bfb1ff37da634736533668
+size 627

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,1465 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.3333333333333334e-09,
+      "logits/chosen": -2.08943510055542,
+      "logits/rejected": -2.0892438888549805,
+      "logps/chosen": -0.08784887194633484,
+      "logps/rejected": -0.08645449578762054,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.3333333333333334e-08,
+      "logits/chosen": -2.4944796562194824,
+      "logits/rejected": -2.4945976734161377,
+      "logps/chosen": -0.578792154788971,
+      "logps/rejected": -0.5907332897186279,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5555555820465088,
+      "rewards/chosen": 0.0014628150966018438,
+      "rewards/margins": 0.0020117585081607103,
+      "rewards/rejected": -0.0005489434115588665,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.666666666666667e-08,
+      "logits/chosen": -2.3721718788146973,
+      "logits/rejected": -2.468485116958618,
+      "logps/chosen": -1.28400719165802,
+      "logps/rejected": -12.984468460083008,
+      "loss": 0.6933,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.0019450436811894178,
+      "rewards/margins": -0.0002596294798422605,
+      "rewards/rejected": -0.001685414114035666,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1e-07,
+      "logits/chosen": -2.164445400238037,
+      "logits/rejected": -2.425915002822876,
+      "logps/chosen": -1.7286256551742554,
+      "logps/rejected": -25.388479232788086,
+      "loss": 0.6906,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -0.0019130244618281722,
+      "rewards/margins": 0.005339598748832941,
+      "rewards/rejected": -0.0072526223957538605,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.3333333333333334e-07,
+      "logits/chosen": -2.619248867034912,
+      "logits/rejected": -2.619331121444702,
+      "logps/chosen": -1.3749217987060547,
+      "logps/rejected": -1.3713041543960571,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.0021189216058701277,
+      "rewards/margins": -0.001049370621331036,
+      "rewards/rejected": 0.0031682923436164856,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6666666666666665e-07,
+      "logits/chosen": -2.3369224071502686,
+      "logits/rejected": -2.431098461151123,
+      "logps/chosen": -1.0188841819763184,
+      "logps/rejected": -8.812786102294922,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.013968966901302338,
+      "rewards/margins": 0.001758316531777382,
+      "rewards/rejected": 0.01221065130084753,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2e-07,
+      "logits/chosen": -2.284961700439453,
+      "logits/rejected": -2.494086742401123,
+      "logps/chosen": -0.683056116104126,
+      "logps/rejected": -19.27627182006836,
+      "loss": 0.6851,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.0018667631084099412,
+      "rewards/margins": 0.016477219760417938,
+      "rewards/rejected": -0.018343981355428696,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3333333333333333e-07,
+      "logits/chosen": -2.2826738357543945,
+      "logits/rejected": -2.384627103805542,
+      "logps/chosen": -0.2940216660499573,
+      "logps/rejected": -9.099252700805664,
+      "loss": 0.684,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.005558961536735296,
+      "rewards/margins": 0.01876726932823658,
+      "rewards/rejected": -0.013208307325839996,
+      "step": 70
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.6666666666666667e-07,
+      "logits/chosen": -2.477116107940674,
+      "logits/rejected": -2.613649606704712,
+      "logps/chosen": -1.0611478090286255,
+      "logps/rejected": -12.122793197631836,
+      "loss": 0.6836,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.018232952803373337,
+      "rewards/margins": 0.019915319979190826,
+      "rewards/rejected": -0.0016823671758174896,
+      "step": 80
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3e-07,
+      "logits/chosen": -2.6183485984802246,
+      "logits/rejected": -2.618346691131592,
+      "logps/chosen": -1.2046842575073242,
+      "logps/rejected": -1.2092653512954712,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.012857586145401001,
+      "rewards/margins": 0.0014548657927662134,
+      "rewards/rejected": 0.011402720585465431,
+      "step": 90
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.333333333333333e-07,
+      "logits/chosen": -2.152963161468506,
+      "logits/rejected": -2.5711560249328613,
+      "logps/chosen": -1.9411561489105225,
+      "logps/rejected": -47.01171112060547,
+      "loss": 0.6651,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -0.003847984131425619,
+      "rewards/margins": 0.0610489621758461,
+      "rewards/rejected": -0.06489694863557816,
+      "step": 100
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.666666666666666e-07,
+      "logits/chosen": -2.353605270385742,
+      "logits/rejected": -2.5540683269500732,
+      "logps/chosen": -1.2066593170166016,
+      "logps/rejected": -30.185583114624023,
+      "loss": 0.682,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.003402869449928403,
+      "rewards/margins": 0.02602914348244667,
+      "rewards/rejected": -0.022626275196671486,
+      "step": 110
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4e-07,
+      "logits/chosen": -2.452103853225708,
+      "logits/rejected": -2.4946463108062744,
+      "logps/chosen": -0.47767752408981323,
+      "logps/rejected": -5.05490255355835,
+      "loss": 0.6859,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.017536822706460953,
+      "rewards/margins": 0.014879658818244934,
+      "rewards/rejected": 0.0026571624912321568,
+      "step": 120
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.3333333333333335e-07,
+      "logits/chosen": -2.2694547176361084,
+      "logits/rejected": -2.3567841053009033,
+      "logps/chosen": -1.3494905233383179,
+      "logps/rejected": -12.111764907836914,
+      "loss": 0.6465,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.028263837099075317,
+      "rewards/margins": 0.11370788514614105,
+      "rewards/rejected": -0.08544405549764633,
+      "step": 130
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.6666666666666666e-07,
+      "logits/chosen": -2.3862383365631104,
+      "logits/rejected": -2.522015333175659,
+      "logps/chosen": -0.9776835441589355,
+      "logps/rejected": -11.195852279663086,
+      "loss": 0.6435,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.016874078661203384,
+      "rewards/margins": 0.1495019793510437,
+      "rewards/rejected": -0.13262788951396942,
+      "step": 140
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.1118805408477783,
+      "logits/rejected": -2.4661762714385986,
+      "logps/chosen": -0.8852203488349915,
+      "logps/rejected": -36.519493103027344,
+      "loss": 0.594,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.016499249264597893,
+      "rewards/margins": 0.2467312514781952,
+      "rewards/rejected": -0.23023200035095215,
+      "step": 150
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.941176470588235e-07,
+      "logits/chosen": -2.251331090927124,
+      "logits/rejected": -2.5972962379455566,
+      "logps/chosen": -1.6465107202529907,
+      "logps/rejected": -26.661739349365234,
+      "loss": 0.5775,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.06401287019252777,
+      "rewards/margins": 0.3227430284023285,
+      "rewards/rejected": -0.2587301731109619,
+      "step": 160
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.88235294117647e-07,
+      "logits/chosen": -2.400430202484131,
+      "logits/rejected": -2.400381565093994,
+      "logps/chosen": -0.6768835783004761,
+      "logps/rejected": -0.677842915058136,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.12107320874929428,
+      "rewards/margins": 0.0004425995866768062,
+      "rewards/rejected": 0.12063062191009521,
+      "step": 170
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.823529411764705e-07,
+      "logits/chosen": -2.3488998413085938,
+      "logits/rejected": -2.3663113117218018,
+      "logps/chosen": -0.6453405618667603,
+      "logps/rejected": -2.275538444519043,
+      "loss": 0.67,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.039185039699077606,
+      "rewards/margins": 0.05349387601017952,
+      "rewards/rejected": -0.014308829791843891,
+      "step": 180
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.7647058823529405e-07,
+      "logits/chosen": -2.1920523643493652,
+      "logits/rejected": -2.5244088172912598,
+      "logps/chosen": -0.8233627080917358,
+      "logps/rejected": -37.117218017578125,
+      "loss": 0.5116,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.05563921853899956,
+      "rewards/margins": 0.5942346453666687,
+      "rewards/rejected": -0.53859543800354,
+      "step": 190
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.705882352941176e-07,
+      "logits/chosen": -2.3363966941833496,
+      "logits/rejected": -2.336390495300293,
+      "logps/chosen": -0.5674120187759399,
+      "logps/rejected": -0.5631183385848999,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.032920531928539276,
+      "rewards/margins": -0.0018675241153687239,
+      "rewards/rejected": 0.03478805348277092,
+      "step": 200
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.647058823529412e-07,
+      "logits/chosen": -2.2569141387939453,
+      "logits/rejected": -2.256953477859497,
+      "logps/chosen": -0.3138192296028137,
+      "logps/rejected": -0.3109946846961975,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.20000000298023224,
+      "rewards/chosen": 0.11521951854228973,
+      "rewards/margins": -0.0012991640251129866,
+      "rewards/rejected": 0.11651869118213654,
+      "step": 210
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.5882352941176465e-07,
+      "logits/chosen": -2.047544479370117,
+      "logits/rejected": -2.4468607902526855,
+      "logps/chosen": -0.2669355571269989,
+      "logps/rejected": -38.318092346191406,
+      "loss": 0.4989,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.13280974328517914,
+      "rewards/margins": 1.0004825592041016,
+      "rewards/rejected": -0.8676728010177612,
+      "step": 220
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.529411764705882e-07,
+      "logits/chosen": -1.9934049844741821,
+      "logits/rejected": -2.3484489917755127,
+      "logps/chosen": -0.6550347208976746,
+      "logps/rejected": -36.49030685424805,
+      "loss": 0.5546,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.23355157673358917,
+      "rewards/margins": 1.3387348651885986,
+      "rewards/rejected": -1.1051832437515259,
+      "step": 230
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.470588235294118e-07,
+      "logits/chosen": -2.0561001300811768,
+      "logits/rejected": -2.314795970916748,
+      "logps/chosen": -0.24726076424121857,
+      "logps/rejected": -30.558258056640625,
+      "loss": 0.5707,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.10325585305690765,
+      "rewards/margins": 1.178950548171997,
+      "rewards/rejected": -1.0756947994232178,
+      "step": 240
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.4117647058823526e-07,
+      "logits/chosen": -2.326530694961548,
+      "logits/rejected": -2.326476573944092,
+      "logps/chosen": -0.12658026814460754,
+      "logps/rejected": -0.12556590139865875,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.11289018392562866,
+      "rewards/margins": 0.00047791999531909823,
+      "rewards/rejected": 0.11241227388381958,
+      "step": 250
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.352941176470588e-07,
+      "logits/chosen": -2.2254791259765625,
+      "logits/rejected": -2.3039350509643555,
+      "logps/chosen": -0.24640262126922607,
+      "logps/rejected": -10.21367073059082,
+      "loss": 0.5724,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.14248333871364594,
+      "rewards/margins": 0.7252418994903564,
+      "rewards/rejected": -0.5827585458755493,
+      "step": 260
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.294117647058823e-07,
+      "logits/chosen": -2.486194133758545,
+      "logits/rejected": -2.486302614212036,
+      "logps/chosen": -0.04246897995471954,
+      "logps/rejected": -0.04294817894697189,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.08347944170236588,
+      "rewards/margins": 0.0013219652464613318,
+      "rewards/rejected": 0.08215747773647308,
+      "step": 270
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.2352941176470586e-07,
+      "logits/chosen": -2.258772373199463,
+      "logits/rejected": -2.350086212158203,
+      "logps/chosen": -0.19779756665229797,
+      "logps/rejected": -12.979776382446289,
+      "loss": 0.6264,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.15591862797737122,
+      "rewards/margins": 0.3447035253047943,
+      "rewards/rejected": -0.18878492712974548,
+      "step": 280
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.1764705882352943e-07,
+      "logits/chosen": -2.400933265686035,
+      "logits/rejected": -2.4009623527526855,
+      "logps/chosen": -0.7456287741661072,
+      "logps/rejected": -0.7486740946769714,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.20849373936653137,
+      "rewards/margins": 0.000649511581286788,
+      "rewards/rejected": 0.20784422755241394,
+      "step": 290
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.117647058823529e-07,
+      "logits/chosen": -2.1085093021392822,
+      "logits/rejected": -2.419422149658203,
+      "logps/chosen": -0.23055700957775116,
+      "logps/rejected": -44.592384338378906,
+      "loss": 0.5007,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.16842325031757355,
+      "rewards/margins": 1.4631106853485107,
+      "rewards/rejected": -1.2946875095367432,
+      "step": 300
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.0588235294117646e-07,
+      "logits/chosen": -2.15910005569458,
+      "logits/rejected": -2.330493688583374,
+      "logps/chosen": -0.2197931557893753,
+      "logps/rejected": -15.632344245910645,
+      "loss": 0.6248,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.16517843306064606,
+      "rewards/margins": 0.4509655833244324,
+      "rewards/rejected": -0.2857871949672699,
+      "step": 310
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4e-07,
+      "logits/chosen": -2.0489771366119385,
+      "logits/rejected": -2.271772861480713,
+      "logps/chosen": -0.38775813579559326,
+      "logps/rejected": -15.12170696258545,
+      "loss": 0.5977,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.1870100200176239,
+      "rewards/margins": 0.35321617126464844,
+      "rewards/rejected": -0.16620615124702454,
+      "step": 320
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.941176470588235e-07,
+      "logits/chosen": -2.066758632659912,
+      "logits/rejected": -2.2020325660705566,
+      "logps/chosen": -0.27063071727752686,
+      "logps/rejected": -16.94083595275879,
+      "loss": 0.5832,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.15286189317703247,
+      "rewards/margins": 0.5866376161575317,
+      "rewards/rejected": -0.43377572298049927,
+      "step": 330
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.8823529411764707e-07,
+      "logits/chosen": -2.2944748401641846,
+      "logits/rejected": -2.29447603225708,
+      "logps/chosen": -0.3279079794883728,
+      "logps/rejected": -0.32968124747276306,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.21330514550209045,
+      "rewards/margins": -0.0005384087562561035,
+      "rewards/rejected": 0.21384355425834656,
+      "step": 340
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.8235294117647053e-07,
+      "logits/chosen": -2.189199924468994,
+      "logits/rejected": -2.2941532135009766,
+      "logps/chosen": -0.3213362693786621,
+      "logps/rejected": -17.19934844970703,
+      "loss": 0.5884,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.11426669359207153,
+      "rewards/margins": 1.0944595336914062,
+      "rewards/rejected": -0.9801927804946899,
+      "step": 350
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.764705882352941e-07,
+      "logits/chosen": -2.1935980319976807,
+      "logits/rejected": -2.419231653213501,
+      "logps/chosen": -0.32695242762565613,
+      "logps/rejected": -21.586366653442383,
+      "loss": 0.5661,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.131852388381958,
+      "rewards/margins": 0.765614926815033,
+      "rewards/rejected": -0.633762538433075,
+      "step": 360
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.705882352941176e-07,
+      "logits/chosen": -2.1839663982391357,
+      "logits/rejected": -2.184142827987671,
+      "logps/chosen": -0.0991433784365654,
+      "logps/rejected": -0.09875849634408951,
+      "loss": 0.694,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.07628553360700607,
+      "rewards/margins": -0.0017677659634500742,
+      "rewards/rejected": 0.0780533030629158,
+      "step": 370
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.6470588235294114e-07,
+      "logits/chosen": -1.9649509191513062,
+      "logits/rejected": -2.1653668880462646,
+      "logps/chosen": -0.21254102885723114,
+      "logps/rejected": -22.567474365234375,
+      "loss": 0.6251,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.1867930144071579,
+      "rewards/margins": 0.7762778401374817,
+      "rewards/rejected": -0.5894848704338074,
+      "step": 380
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.588235294117647e-07,
+      "logits/chosen": -2.1640498638153076,
+      "logits/rejected": -2.198374032974243,
+      "logps/chosen": -0.18704327940940857,
+      "logps/rejected": -9.075506210327148,
+      "loss": 0.5556,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.047349415719509125,
+      "rewards/margins": 1.023637056350708,
+      "rewards/rejected": -0.9762875437736511,
+      "step": 390
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.529411764705882e-07,
+      "logits/chosen": -1.843392014503479,
+      "logits/rejected": -2.1060373783111572,
+      "logps/chosen": -0.3059827387332916,
+      "logps/rejected": -40.11814880371094,
+      "loss": 0.4882,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.25154930353164673,
+      "rewards/margins": 2.534274101257324,
+      "rewards/rejected": -2.2827248573303223,
+      "step": 400
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.4705882352941174e-07,
+      "logits/chosen": -1.9674293994903564,
+      "logits/rejected": -2.1082801818847656,
+      "logps/chosen": -0.11460398137569427,
+      "logps/rejected": -17.704038619995117,
+      "loss": 0.5573,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.17245104908943176,
+      "rewards/margins": 0.9313168525695801,
+      "rewards/rejected": -0.7588656544685364,
+      "step": 410
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.411764705882353e-07,
+      "logits/chosen": -1.4523433446884155,
+      "logits/rejected": -2.156726121902466,
+      "logps/chosen": -0.15290628373622894,
+      "logps/rejected": -63.89361572265625,
+      "loss": 0.2949,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.23414066433906555,
+      "rewards/margins": 4.00860071182251,
+      "rewards/rejected": -3.7744603157043457,
+      "step": 420
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.352941176470588e-07,
+      "logits/chosen": -2.076636791229248,
+      "logits/rejected": -2.0995030403137207,
+      "logps/chosen": -0.09147205203771591,
+      "logps/rejected": -7.910800933837891,
+      "loss": 0.6241,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.11051849275827408,
+      "rewards/margins": 0.6908754110336304,
+      "rewards/rejected": -0.5803568959236145,
+      "step": 430
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.2941176470588235e-07,
+      "logits/chosen": -2.1452138423919678,
+      "logits/rejected": -2.206829071044922,
+      "logps/chosen": -0.13904191553592682,
+      "logps/rejected": -10.327826499938965,
+      "loss": 0.6234,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.272757351398468,
+      "rewards/margins": 0.7720587849617004,
+      "rewards/rejected": -0.49930137395858765,
+      "step": 440
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.2352941176470586e-07,
+      "logits/chosen": -2.090587854385376,
+      "logits/rejected": -2.090881824493408,
+      "logps/chosen": -0.17841731011867523,
+      "logps/rejected": -0.17845699191093445,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.2406892031431198,
+      "rewards/margins": -0.0006073854747228324,
+      "rewards/rejected": 0.24129657447338104,
+      "step": 450
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.176470588235294e-07,
+      "logits/chosen": -1.7833999395370483,
+      "logits/rejected": -2.0649399757385254,
+      "logps/chosen": -0.09775514900684357,
+      "logps/rejected": -44.72971725463867,
+      "loss": 0.503,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.25888940691947937,
+      "rewards/margins": 2.86980938911438,
+      "rewards/rejected": -2.610919952392578,
+      "step": 460
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.1176470588235295e-07,
+      "logits/chosen": -1.9202232360839844,
+      "logits/rejected": -2.1586782932281494,
+      "logps/chosen": -0.4241597056388855,
+      "logps/rejected": -55.93566131591797,
+      "loss": 0.4373,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.22231805324554443,
+      "rewards/margins": 4.350785255432129,
+      "rewards/rejected": -4.128467082977295,
+      "step": 470
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.0588235294117647e-07,
+      "logits/chosen": -1.8953840732574463,
+      "logits/rejected": -2.0778305530548096,
+      "logps/chosen": -0.3732009530067444,
+      "logps/rejected": -32.9583740234375,
+      "loss": 0.4864,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.1983214169740677,
+      "rewards/margins": 3.323279857635498,
+      "rewards/rejected": -3.1249582767486572,
+      "step": 480
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3e-07,
+      "logits/chosen": -1.5736738443374634,
+      "logits/rejected": -2.016456365585327,
+      "logps/chosen": -0.012308413162827492,
+      "logps/rejected": -100.20381164550781,
+      "loss": 0.4155,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.23825187981128693,
+      "rewards/margins": 7.954277992248535,
+      "rewards/rejected": -7.716025352478027,
+      "step": 490
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.941176470588235e-07,
+      "logits/chosen": -1.8802621364593506,
+      "logits/rejected": -2.047894239425659,
+      "logps/chosen": -0.06101088970899582,
+      "logps/rejected": -20.134754180908203,
+      "loss": 0.6235,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.23272594809532166,
+      "rewards/margins": 1.6100852489471436,
+      "rewards/rejected": -1.37735915184021,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "eval_logits/chosen": -1.9279996156692505,
+      "eval_logits/rejected": -2.0771560668945312,
+      "eval_logps/chosen": -0.13991177082061768,
+      "eval_logps/rejected": -20.526100158691406,
+      "eval_loss": 0.5603082776069641,
+      "eval_rewards/accuracies": 0.49000000953674316,
+      "eval_rewards/chosen": 0.2280687689781189,
+      "eval_rewards/margins": 1.3241862058639526,
+      "eval_rewards/rejected": -1.0961174964904785,
+      "eval_runtime": 22.8794,
+      "eval_samples_per_second": 4.371,
+      "eval_steps_per_second": 4.371,
+      "step": 500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.88235294117647e-07,
+      "logits/chosen": -1.881134271621704,
+      "logits/rejected": -1.9070965051651,
+      "logps/chosen": -0.02279834821820259,
+      "logps/rejected": -5.849534034729004,
+      "loss": 0.6284,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.13564881682395935,
+      "rewards/margins": 0.31011906266212463,
+      "rewards/rejected": -0.1744702160358429,
+      "step": 510
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.823529411764706e-07,
+      "logits/chosen": -1.9525129795074463,
+      "logits/rejected": -1.960097074508667,
+      "logps/chosen": -0.05416996404528618,
+      "logps/rejected": -6.789488792419434,
+      "loss": 0.6232,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.19361652433872223,
+      "rewards/margins": 0.9131872057914734,
+      "rewards/rejected": -0.7195707559585571,
+      "step": 520
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.764705882352941e-07,
+      "logits/chosen": -2.0894522666931152,
+      "logits/rejected": -2.089811325073242,
+      "logps/chosen": -0.017659317702054977,
+      "logps/rejected": -0.0175788514316082,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.17115317285060883,
+      "rewards/margins": 0.0004329962539486587,
+      "rewards/rejected": 0.170720174908638,
+      "step": 530
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.705882352941176e-07,
+      "logits/chosen": -2.1036479473114014,
+      "logits/rejected": -2.1614184379577637,
+      "logps/chosen": -0.1067914217710495,
+      "logps/rejected": -12.363987922668457,
+      "loss": 0.5895,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.19864901900291443,
+      "rewards/margins": 0.9721519351005554,
+      "rewards/rejected": -0.7735029458999634,
+      "step": 540
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.6470588235294114e-07,
+      "logits/chosen": -1.9976797103881836,
+      "logits/rejected": -1.9976022243499756,
+      "logps/chosen": -0.04686691239476204,
+      "logps/rejected": -0.046861741691827774,
+      "loss": 0.693,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.23503179848194122,
+      "rewards/margins": 0.0003768761525861919,
+      "rewards/rejected": 0.23465490341186523,
+      "step": 550
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.588235294117647e-07,
+      "logits/chosen": -1.6446807384490967,
+      "logits/rejected": -2.0919888019561768,
+      "logps/chosen": -0.08167463541030884,
+      "logps/rejected": -50.200626373291016,
+      "loss": 0.4924,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.27800416946411133,
+      "rewards/margins": 2.7979769706726074,
+      "rewards/rejected": -2.519972801208496,
+      "step": 560
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.5294117647058823e-07,
+      "logits/chosen": -1.6458909511566162,
+      "logits/rejected": -2.06436824798584,
+      "logps/chosen": -0.004592462442815304,
+      "logps/rejected": -85.18163299560547,
+      "loss": 0.4162,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.23764410614967346,
+      "rewards/margins": 7.737754821777344,
+      "rewards/rejected": -7.500109672546387,
+      "step": 570
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.4705882352941175e-07,
+      "logits/chosen": -1.5587949752807617,
+      "logits/rejected": -1.8453130722045898,
+      "logps/chosen": -0.04938965290784836,
+      "logps/rejected": -76.6133804321289,
+      "loss": 0.4181,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.27002671360969543,
+      "rewards/margins": 6.7017316818237305,
+      "rewards/rejected": -6.431704521179199,
+      "step": 580
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.4117647058823526e-07,
+      "logits/chosen": -2.0468690395355225,
+      "logits/rejected": -2.046814441680908,
+      "logps/chosen": -0.01457706093788147,
+      "logps/rejected": -0.014673275873064995,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.1107385978102684,
+      "rewards/margins": -4.159938725933898e-06,
+      "rewards/rejected": 0.11074274778366089,
+      "step": 590
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.352941176470588e-07,
+      "logits/chosen": -2.068368673324585,
+      "logits/rejected": -2.087043285369873,
+      "logps/chosen": -0.007376219145953655,
+      "logps/rejected": -8.290468215942383,
+      "loss": 0.6237,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.15371395647525787,
+      "rewards/margins": 0.8146413564682007,
+      "rewards/rejected": -0.660927414894104,
+      "step": 600
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.2941176470588233e-07,
+      "logits/chosen": -1.8815044164657593,
+      "logits/rejected": -1.9951889514923096,
+      "logps/chosen": -0.12692415714263916,
+      "logps/rejected": -25.312314987182617,
+      "loss": 0.6251,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.2646506428718567,
+      "rewards/margins": 2.2484025955200195,
+      "rewards/rejected": -1.983751893043518,
+      "step": 610
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.235294117647059e-07,
+      "logits/chosen": -1.907518744468689,
+      "logits/rejected": -1.9557015895843506,
+      "logps/chosen": -0.0008927548187784851,
+      "logps/rejected": -10.989554405212402,
+      "loss": 0.624,
+      "rewards/accuracies": 0.20000000298023224,
+      "rewards/chosen": 0.047840237617492676,
+      "rewards/margins": 0.6518641114234924,
+      "rewards/rejected": -0.6040239334106445,
+      "step": 620
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.176470588235294e-07,
+      "logits/chosen": -1.7601346969604492,
+      "logits/rejected": -1.9046695232391357,
+      "logps/chosen": -0.07976426184177399,
+      "logps/rejected": -29.652408599853516,
+      "loss": 0.6233,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.28871995210647583,
+      "rewards/margins": 2.4649205207824707,
+      "rewards/rejected": -2.1762008666992188,
+      "step": 630
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.1176470588235293e-07,
+      "logits/chosen": -1.8790966272354126,
+      "logits/rejected": -1.8792489767074585,
+      "logps/chosen": -0.0008465357241220772,
+      "logps/rejected": -0.0007601732504554093,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.06679291278123856,
+      "rewards/margins": 0.00011558351252460852,
+      "rewards/rejected": 0.06667732447385788,
+      "step": 640
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.0588235294117645e-07,
+      "logits/chosen": -1.8315871953964233,
+      "logits/rejected": -1.8316688537597656,
+      "logps/chosen": -0.26076430082321167,
+      "logps/rejected": -0.2667176425457001,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.11814270913600922,
+      "rewards/margins": 0.001997224520891905,
+      "rewards/rejected": 0.11614549160003662,
+      "step": 650
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2e-07,
+      "logits/chosen": -1.969988226890564,
+      "logits/rejected": -1.97628915309906,
+      "logps/chosen": -0.14302313327789307,
+      "logps/rejected": -1.4409807920455933,
+      "loss": 0.6544,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.33637282252311707,
+      "rewards/margins": 0.10214731842279434,
+      "rewards/rejected": 0.23422551155090332,
+      "step": 660
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.9411764705882353e-07,
+      "logits/chosen": -1.6727327108383179,
+      "logits/rejected": -1.9902541637420654,
+      "logps/chosen": -0.024806343019008636,
+      "logps/rejected": -38.02031707763672,
+      "loss": 0.5553,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.27485889196395874,
+      "rewards/margins": 2.909092426300049,
+      "rewards/rejected": -2.634232997894287,
+      "step": 670
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8823529411764705e-07,
+      "logits/chosen": -1.9072097539901733,
+      "logits/rejected": -1.9726791381835938,
+      "logps/chosen": -0.4985428750514984,
+      "logps/rejected": -13.495981216430664,
+      "loss": 0.6256,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.23625138401985168,
+      "rewards/margins": 0.47252601385116577,
+      "rewards/rejected": -0.2362746298313141,
+      "step": 680
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8235294117647057e-07,
+      "logits/chosen": -1.6648544073104858,
+      "logits/rejected": -1.88479483127594,
+      "logps/chosen": -0.012854146771132946,
+      "logps/rejected": -43.54383850097656,
+      "loss": 0.5551,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.15211549401283264,
+      "rewards/margins": 3.2219433784484863,
+      "rewards/rejected": -3.0698275566101074,
+      "step": 690
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.764705882352941e-07,
+      "logits/chosen": -1.8432905673980713,
+      "logits/rejected": -1.843271017074585,
+      "logps/chosen": -0.06649269163608551,
+      "logps/rejected": -0.06794900447130203,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.17590782046318054,
+      "rewards/margins": 0.002167056081816554,
+      "rewards/rejected": 0.17374077439308167,
+      "step": 700
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7058823529411766e-07,
+      "logits/chosen": -1.782904028892517,
+      "logits/rejected": -2.027859687805176,
+      "logps/chosen": -0.027702972292900085,
+      "logps/rejected": -63.74357223510742,
+      "loss": 0.5547,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.3461371064186096,
+      "rewards/margins": 5.373135566711426,
+      "rewards/rejected": -5.026998519897461,
+      "step": 710
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.6470588235294117e-07,
+      "logits/chosen": -1.8250236511230469,
+      "logits/rejected": -1.8965476751327515,
+      "logps/chosen": -0.25108733773231506,
+      "logps/rejected": -14.722552299499512,
+      "loss": 0.4899,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.05279017239809036,
+      "rewards/margins": 1.3603849411010742,
+      "rewards/rejected": -1.307594656944275,
+      "step": 720
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.588235294117647e-07,
+      "logits/chosen": -1.6344257593154907,
+      "logits/rejected": -1.8426809310913086,
+      "logps/chosen": -0.048086974769830704,
+      "logps/rejected": -26.516277313232422,
+      "loss": 0.5546,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.18577437102794647,
+      "rewards/margins": 2.011146068572998,
+      "rewards/rejected": -1.8253717422485352,
+      "step": 730
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.5294117647058823e-07,
+      "logits/chosen": -1.5386077165603638,
+      "logits/rejected": -1.8887131214141846,
+      "logps/chosen": -0.2795502543449402,
+      "logps/rejected": -46.01464080810547,
+      "loss": 0.4861,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.20460227131843567,
+      "rewards/margins": 3.9117095470428467,
+      "rewards/rejected": -3.7071070671081543,
+      "step": 740
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4705882352941175e-07,
+      "logits/chosen": -2.0386643409729004,
+      "logits/rejected": -2.0383331775665283,
+      "logps/chosen": -0.1892136037349701,
+      "logps/rejected": -0.18968766927719116,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.21108309924602509,
+      "rewards/margins": -0.0005298491450957954,
+      "rewards/rejected": 0.2116129845380783,
+      "step": 750
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.411764705882353e-07,
+      "logits/chosen": -1.850419282913208,
+      "logits/rejected": -1.8857438564300537,
+      "logps/chosen": -0.3321111798286438,
+      "logps/rejected": -4.540987014770508,
+      "loss": 0.6396,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.15547718107700348,
+      "rewards/margins": 0.18077853322029114,
+      "rewards/rejected": -0.02530134655535221,
+      "step": 760
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.352941176470588e-07,
+      "logits/chosen": -1.9080699682235718,
+      "logits/rejected": -1.9150307178497314,
+      "logps/chosen": -0.008314008824527264,
+      "logps/rejected": -5.123701095581055,
+      "loss": 0.6239,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.09305348992347717,
+      "rewards/margins": 0.6812450289726257,
+      "rewards/rejected": -0.5881915092468262,
+      "step": 770
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.2941176470588236e-07,
+      "logits/chosen": -1.6551542282104492,
+      "logits/rejected": -1.853063941001892,
+      "logps/chosen": -0.054176896810531616,
+      "logps/rejected": -45.885746002197266,
+      "loss": 0.4863,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.1725289672613144,
+      "rewards/margins": 4.1526994705200195,
+      "rewards/rejected": -3.980170488357544,
+      "step": 780
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.2352941176470587e-07,
+      "logits/chosen": -1.7695019245147705,
+      "logits/rejected": -2.03476881980896,
+      "logps/chosen": -0.31666165590286255,
+      "logps/rejected": -50.392616271972656,
+      "loss": 0.5548,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.15865585207939148,
+      "rewards/margins": 4.350362777709961,
+      "rewards/rejected": -4.191707134246826,
+      "step": 790
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.176470588235294e-07,
+      "logits/chosen": -1.8488401174545288,
+      "logits/rejected": -2.141782283782959,
+      "logps/chosen": -0.3054754436016083,
+      "logps/rejected": -34.490135192871094,
+      "loss": 0.4853,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.23360002040863037,
+      "rewards/margins": 2.897139072418213,
+      "rewards/rejected": -2.663539171218872,
+      "step": 800
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.1176470588235295e-07,
+      "logits/chosen": -1.8038222789764404,
+      "logits/rejected": -1.8816568851470947,
+      "logps/chosen": -0.08031131327152252,
+      "logps/rejected": -10.264053344726562,
+      "loss": 0.623,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.24331481754779816,
+      "rewards/margins": 1.0161577463150024,
+      "rewards/rejected": -0.7728429436683655,
+      "step": 810
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.0588235294117647e-07,
+      "logits/chosen": -1.9077497720718384,
+      "logits/rejected": -1.9633766412734985,
+      "logps/chosen": -0.0009624619269743562,
+      "logps/rejected": -12.475212097167969,
+      "loss": 0.6238,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.14481396973133087,
+      "rewards/margins": 1.0594360828399658,
+      "rewards/rejected": -0.9146221280097961,
+      "step": 820
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1e-07,
+      "logits/chosen": -1.6920783519744873,
+      "logits/rejected": -1.9319671392440796,
+      "logps/chosen": -0.013360400684177876,
+      "logps/rejected": -46.24522018432617,
+      "loss": 0.554,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.21019235253334045,
+      "rewards/margins": 3.6845498085021973,
+      "rewards/rejected": -3.4743571281433105,
+      "step": 830
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 9.411764705882353e-08,
+      "logits/chosen": -1.7484924793243408,
+      "logits/rejected": -2.0209856033325195,
+      "logps/chosen": -0.1407555192708969,
+      "logps/rejected": -43.27410125732422,
+      "loss": 0.5543,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.32391467690467834,
+      "rewards/margins": 3.707659959793091,
+      "rewards/rejected": -3.3837451934814453,
+      "step": 840
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.823529411764706e-08,
+      "logits/chosen": -1.5334498882293701,
+      "logits/rejected": -1.8631703853607178,
+      "logps/chosen": -0.033944085240364075,
+      "logps/rejected": -70.71894836425781,
+      "loss": 0.4852,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.23922660946846008,
+      "rewards/margins": 6.69946813583374,
+      "rewards/rejected": -6.46024227142334,
+      "step": 850
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 8.235294117647059e-08,
+      "logits/chosen": -1.7201436758041382,
+      "logits/rejected": -1.857613205909729,
+      "logps/chosen": -0.10154436528682709,
+      "logps/rejected": -27.654672622680664,
+      "loss": 0.6237,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.21049244701862335,
+      "rewards/margins": 2.7311854362487793,
+      "rewards/rejected": -2.520692825317383,
+      "step": 860
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 7.647058823529412e-08,
+      "logits/chosen": -1.8255866765975952,
+      "logits/rejected": -2.007643461227417,
+      "logps/chosen": -0.12339305877685547,
+      "logps/rejected": -23.465425491333008,
+      "loss": 0.5546,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.37787729501724243,
+      "rewards/margins": 2.0081450939178467,
+      "rewards/rejected": -1.630267858505249,
+      "step": 870
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.058823529411765e-08,
+      "logits/chosen": -1.675270676612854,
+      "logits/rejected": -1.7470086812973022,
+      "logps/chosen": -0.042650602757930756,
+      "logps/rejected": -39.634857177734375,
+      "loss": 0.5666,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.2249513566493988,
+      "rewards/margins": 4.4023356437683105,
+      "rewards/rejected": -4.177384376525879,
+      "step": 880
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.470588235294118e-08,
+      "logits/chosen": -1.6610826253890991,
+      "logits/rejected": -1.8155969381332397,
+      "logps/chosen": -0.013693208806216717,
+      "logps/rejected": -12.216829299926758,
+      "loss": 0.6252,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.09875396639108658,
+      "rewards/margins": 0.4886496961116791,
+      "rewards/rejected": -0.3898957371711731,
+      "step": 890
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.88235294117647e-08,
+      "logits/chosen": -2.034945487976074,
+      "logits/rejected": -2.0349366664886475,
+      "logps/chosen": -0.5003259181976318,
+      "logps/rejected": -0.5002902746200562,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.26111483573913574,
+      "rewards/margins": -0.0018190573900938034,
+      "rewards/rejected": 0.2629338800907135,
+      "step": 900
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.294117647058823e-08,
+      "logits/chosen": -1.7996795177459717,
+      "logits/rejected": -1.7996826171875,
+      "logps/chosen": -0.18381330370903015,
+      "logps/rejected": -0.1839282214641571,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.16678330302238464,
+      "rewards/margins": 0.0009464531322009861,
+      "rewards/rejected": 0.16583684086799622,
+      "step": 910
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.705882352941176e-08,
+      "logits/chosen": -1.8732879161834717,
+      "logits/rejected": -1.9507211446762085,
+      "logps/chosen": -0.04379552602767944,
+      "logps/rejected": -11.802661895751953,
+      "loss": 0.624,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.16234037280082703,
+      "rewards/margins": 0.9312402009963989,
+      "rewards/rejected": -0.76889967918396,
+      "step": 920
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.1176470588235293e-08,
+      "logits/chosen": -1.722858190536499,
+      "logits/rejected": -1.8730077743530273,
+      "logps/chosen": -0.03575155884027481,
+      "logps/rejected": -18.92257308959961,
+      "loss": 0.5551,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.16664153337478638,
+      "rewards/margins": 1.2264705896377563,
+      "rewards/rejected": -1.0598289966583252,
+      "step": 930
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.5294117647058824e-08,
+      "logits/chosen": -1.4443856477737427,
+      "logits/rejected": -1.968544363975525,
+      "logps/chosen": -0.005307979416102171,
+      "logps/rejected": -73.07327270507812,
+      "loss": 0.2777,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.241426020860672,
+      "rewards/margins": 5.943356513977051,
+      "rewards/rejected": -5.701930046081543,
+      "step": 940
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.941176470588235e-08,
+      "logits/chosen": -1.917584776878357,
+      "logits/rejected": -1.9409071207046509,
+      "logps/chosen": -0.0067234160378575325,
+      "logps/rejected": -7.634241580963135,
+      "loss": 0.6239,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.07056023925542831,
+      "rewards/margins": 1.0394136905670166,
+      "rewards/rejected": -0.9688535928726196,
+      "step": 950
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.352941176470588e-08,
+      "logits/chosen": -1.659624457359314,
+      "logits/rejected": -1.8984715938568115,
+      "logps/chosen": -0.6621147394180298,
+      "logps/rejected": -41.00469207763672,
+      "loss": 0.5561,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.24302108585834503,
+      "rewards/margins": 3.9856536388397217,
+      "rewards/rejected": -3.7426326274871826,
+      "step": 960
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.7647058823529412e-08,
+      "logits/chosen": -2.0915744304656982,
+      "logits/rejected": -2.0915427207946777,
+      "logps/chosen": -0.09594538807868958,
+      "logps/rejected": -0.09524588286876678,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.11800364404916763,
+      "rewards/margins": -0.000787623692303896,
+      "rewards/rejected": 0.11879126727581024,
+      "step": 970
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.176470588235294e-08,
+      "logits/chosen": -1.8284385204315186,
+      "logits/rejected": -2.00864839553833,
+      "logps/chosen": -0.2936480641365051,
+      "logps/rejected": -42.53371810913086,
+      "loss": 0.5554,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.20751357078552246,
+      "rewards/margins": 4.451984405517578,
+      "rewards/rejected": -4.244471073150635,
+      "step": 980
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.88235294117647e-09,
+      "logits/chosen": -1.9873313903808594,
+      "logits/rejected": -1.9968726634979248,
+      "logps/chosen": -0.013185739517211914,
+      "logps/rejected": -2.775447368621826,
+      "loss": 0.6283,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.1859985888004303,
+      "rewards/margins": 0.2977893352508545,
+      "rewards/rejected": -0.1117907166481018,
+      "step": 990
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "logits/chosen": -1.8508293628692627,
+      "logits/rejected": -2.014707088470459,
+      "logps/chosen": -0.03528173640370369,
+      "logps/rejected": -29.331050872802734,
+      "loss": 0.5542,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.2999701201915741,
+      "rewards/margins": 2.2009005546569824,
+      "rewards/rejected": -1.900930404663086,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_logits/chosen": -1.8047094345092773,
+      "eval_logits/rejected": -1.954627513885498,
+      "eval_logps/chosen": -0.11939573287963867,
+      "eval_logps/rejected": -22.671850204467773,
+      "eval_loss": 0.5534428954124451,
+      "eval_rewards/accuracies": 0.5099999904632568,
+      "eval_rewards/chosen": 0.23217196762561798,
+      "eval_rewards/margins": 1.7574390172958374,
+      "eval_rewards/rejected": -1.5252670049667358,
+      "eval_runtime": 20.0707,
+      "eval_samples_per_second": 4.982,
+      "eval_steps_per_second": 4.982,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca24cb84109decda1e3faa78d37f89ddc462eb444ef3699f1308dbc222aa9cac
+size 4091