commit

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.524798985838762,
+    "train_runtime": 12257.7363,
+    "train_samples": 59556,
+    "train_samples_per_second": 4.859,
+    "train_steps_per_second": 0.076
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/data0/qyj/Complex_Instruct/mistral-7b/Long_data_N/forward_W_reverse_13k_FRICL_7.5_.75_Best",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369bc60a8dff1ff0f2e64e1d0da962a9a8bdcb2c639056a44977ba006e728194
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cce52ff29a5aa6030c93b8eb487cbf02f8a762c8dbc2aeef127b97bd7565a21
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2535dc6c7b68f120e84a4db1275cff84426a039b2efc9c263b517745fa8328d1
+size 4546807800

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "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"
+  }
+}

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
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.524798985838762,
+    "train_runtime": 12257.7363,
+    "train_samples": 59556,
+    "train_samples_per_second": 4.859,
+    "train_steps_per_second": 0.076
+}

trainer_state.json

@@ -0,0 +1,1452 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 931,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010741138560687433,
+      "grad_norm": 38.01819610595703,
+      "learning_rate": 5.3191489361702125e-09,
+      "logits/chosen": -1.7826814651489258,
+      "logits/rejected": -1.9013216495513916,
+      "logps/chosen": -277.2808837890625,
+      "logps/rejected": -667.4992065429688,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.010741138560687433,
+      "grad_norm": 34.09270477294922,
+      "learning_rate": 5.3191489361702123e-08,
+      "logits/chosen": -2.232851266860962,
+      "logits/rejected": -2.225285530090332,
+      "logps/chosen": -305.5078125,
+      "logps/rejected": -258.5682067871094,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.3333333432674408,
+      "rewards/chosen": 0.00024179136380553246,
+      "rewards/margins": -0.0007453116122633219,
+      "rewards/rejected": 0.000987103208899498,
+      "step": 10
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "grad_norm": 33.920143127441406,
+      "learning_rate": 1.0638297872340425e-07,
+      "logits/chosen": -2.0934910774230957,
+      "logits/rejected": -2.0479633808135986,
+      "logps/chosen": -278.1986389160156,
+      "logps/rejected": -270.8542175292969,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": 0.002228913828730583,
+      "rewards/margins": 0.0013251047348603606,
+      "rewards/rejected": 0.0009038090938702226,
+      "step": 20
+    },
+    {
+      "epoch": 0.0322234156820623,
+      "grad_norm": 36.32479476928711,
+      "learning_rate": 1.5957446808510638e-07,
+      "logits/chosen": -2.2630741596221924,
+      "logits/rejected": -2.158916473388672,
+      "logps/chosen": -329.6264343261719,
+      "logps/rejected": -238.6651153564453,
+      "loss": 0.6906,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.015065526589751244,
+      "rewards/margins": 0.008328847587108612,
+      "rewards/rejected": 0.006736679468303919,
+      "step": 30
+    },
+    {
+      "epoch": 0.04296455424274973,
+      "grad_norm": 29.183805465698242,
+      "learning_rate": 2.127659574468085e-07,
+      "logits/chosen": -2.290919542312622,
+      "logits/rejected": -2.1671340465545654,
+      "logps/chosen": -298.9222412109375,
+      "logps/rejected": -290.89227294921875,
+      "loss": 0.685,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": 0.04827628284692764,
+      "rewards/margins": 0.017906121909618378,
+      "rewards/rejected": 0.030370160937309265,
+      "step": 40
+    },
+    {
+      "epoch": 0.05370569280343716,
+      "grad_norm": 29.736236572265625,
+      "learning_rate": 2.659574468085106e-07,
+      "logits/chosen": -2.400148868560791,
+      "logits/rejected": -2.2399775981903076,
+      "logps/chosen": -286.6379699707031,
+      "logps/rejected": -248.4271697998047,
+      "loss": 0.6748,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.08774404227733612,
+      "rewards/margins": 0.037349071353673935,
+      "rewards/rejected": 0.05039495974779129,
+      "step": 50
+    },
+    {
+      "epoch": 0.0644468313641246,
+      "grad_norm": 29.81789207458496,
+      "learning_rate": 3.1914893617021275e-07,
+      "logits/chosen": -2.3034303188323975,
+      "logits/rejected": -2.119563102722168,
+      "logps/chosen": -292.1720275878906,
+      "logps/rejected": -246.50967407226562,
+      "loss": 0.6684,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.1263999193906784,
+      "rewards/margins": 0.08450669795274734,
+      "rewards/rejected": 0.04189322888851166,
+      "step": 60
+    },
+    {
+      "epoch": 0.07518796992481203,
+      "grad_norm": 28.368366241455078,
+      "learning_rate": 3.7234042553191484e-07,
+      "logits/chosen": -2.194551944732666,
+      "logits/rejected": -2.0943870544433594,
+      "logps/chosen": -270.94085693359375,
+      "logps/rejected": -222.0772705078125,
+      "loss": 0.6529,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.15133240818977356,
+      "rewards/margins": 0.09613539278507233,
+      "rewards/rejected": 0.05519700050354004,
+      "step": 70
+    },
+    {
+      "epoch": 0.08592910848549946,
+      "grad_norm": 32.63807678222656,
+      "learning_rate": 4.25531914893617e-07,
+      "logits/chosen": -2.110665798187256,
+      "logits/rejected": -2.0879478454589844,
+      "logps/chosen": -302.55810546875,
+      "logps/rejected": -276.37298583984375,
+      "loss": 0.6364,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.12729570269584656,
+      "rewards/margins": 0.13354265689849854,
+      "rewards/rejected": -0.006246985401958227,
+      "step": 80
+    },
+    {
+      "epoch": 0.0966702470461869,
+      "grad_norm": 33.7596549987793,
+      "learning_rate": 4.787234042553192e-07,
+      "logits/chosen": -2.011441707611084,
+      "logits/rejected": -1.953314185142517,
+      "logps/chosen": -275.5764465332031,
+      "logps/rejected": -278.00384521484375,
+      "loss": 0.6135,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.013616062700748444,
+      "rewards/margins": 0.2872251570224762,
+      "rewards/rejected": -0.30084121227264404,
+      "step": 90
+    },
+    {
+      "epoch": 0.10741138560687433,
+      "grad_norm": 49.362213134765625,
+      "learning_rate": 4.999366067542832e-07,
+      "logits/chosen": -2.1004366874694824,
+      "logits/rejected": -1.8379312753677368,
+      "logps/chosen": -325.45672607421875,
+      "logps/rejected": -329.73748779296875,
+      "loss": 0.6027,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.26145023107528687,
+      "rewards/margins": 0.2924392819404602,
+      "rewards/rejected": -0.5538895726203918,
+      "step": 100
+    },
+    {
+      "epoch": 0.11815252416756176,
+      "grad_norm": 53.218753814697266,
+      "learning_rate": 4.995493200065303e-07,
+      "logits/chosen": -2.0087809562683105,
+      "logits/rejected": -1.840013861656189,
+      "logps/chosen": -386.00592041015625,
+      "logps/rejected": -363.0046081542969,
+      "loss": 0.5916,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.4549340605735779,
+      "rewards/margins": 0.5379987359046936,
+      "rewards/rejected": -0.9929327964782715,
+      "step": 110
+    },
+    {
+      "epoch": 0.1288936627282492,
+      "grad_norm": 47.64997482299805,
+      "learning_rate": 4.988105098641859e-07,
+      "logits/chosen": -1.9923064708709717,
+      "logits/rejected": -1.8889319896697998,
+      "logps/chosen": -368.4234313964844,
+      "logps/rejected": -384.9602355957031,
+      "loss": 0.5813,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.44473686814308167,
+      "rewards/margins": 0.4787873327732086,
+      "rewards/rejected": -0.9235240817070007,
+      "step": 120
+    },
+    {
+      "epoch": 0.13963480128893663,
+      "grad_norm": 38.56282424926758,
+      "learning_rate": 4.977212170395597e-07,
+      "logits/chosen": -1.8189750909805298,
+      "logits/rejected": -1.6740334033966064,
+      "logps/chosen": -328.65789794921875,
+      "logps/rejected": -318.7656555175781,
+      "loss": 0.5653,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.4469381272792816,
+      "rewards/margins": 0.42922893166542053,
+      "rewards/rejected": -0.8761669993400574,
+      "step": 130
+    },
+    {
+      "epoch": 0.15037593984962405,
+      "grad_norm": 60.210453033447266,
+      "learning_rate": 4.962829759464157e-07,
+      "logits/chosen": -1.896112084388733,
+      "logits/rejected": -1.7687921524047852,
+      "logps/chosen": -346.6222229003906,
+      "logps/rejected": -360.77880859375,
+      "loss": 0.6072,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.5491372346878052,
+      "rewards/margins": 0.2989022731781006,
+      "rewards/rejected": -0.8480396270751953,
+      "step": 140
+    },
+    {
+      "epoch": 0.1611170784103115,
+      "grad_norm": 48.47090148925781,
+      "learning_rate": 4.944978125385465e-07,
+      "logits/chosen": -2.036083698272705,
+      "logits/rejected": -1.8509035110473633,
+      "logps/chosen": -321.4471130371094,
+      "logps/rejected": -355.3517150878906,
+      "loss": 0.5702,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.34621065855026245,
+      "rewards/margins": 0.6038306951522827,
+      "rewards/rejected": -0.9500414133071899,
+      "step": 150
+    },
+    {
+      "epoch": 0.17185821697099893,
+      "grad_norm": 43.58736801147461,
+      "learning_rate": 4.923682414559481e-07,
+      "logits/chosen": -1.8674886226654053,
+      "logits/rejected": -1.689318299293518,
+      "logps/chosen": -357.22833251953125,
+      "logps/rejected": -359.64666748046875,
+      "loss": 0.5438,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.3814140856266022,
+      "rewards/margins": 0.5234302282333374,
+      "rewards/rejected": -0.9048442840576172,
+      "step": 160
+    },
+    {
+      "epoch": 0.18259935553168635,
+      "grad_norm": 68.03955841064453,
+      "learning_rate": 4.898972624826147e-07,
+      "logits/chosen": -1.8476066589355469,
+      "logits/rejected": -1.6870009899139404,
+      "logps/chosen": -403.6802673339844,
+      "logps/rejected": -395.5543212890625,
+      "loss": 0.5301,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.5655828714370728,
+      "rewards/margins": 0.6453245282173157,
+      "rewards/rejected": -1.210907220840454,
+      "step": 170
+    },
+    {
+      "epoch": 0.1933404940923738,
+      "grad_norm": 54.94865036010742,
+      "learning_rate": 4.870883563209449e-07,
+      "logits/chosen": -1.838039755821228,
+      "logits/rejected": -1.630350112915039,
+      "logps/chosen": -387.94305419921875,
+      "logps/rejected": -392.7327880859375,
+      "loss": 0.5404,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.5131097435951233,
+      "rewards/margins": 0.5987601280212402,
+      "rewards/rejected": -1.1118699312210083,
+      "step": 180
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 57.38792037963867,
+      "learning_rate": 4.839454796887089e-07,
+      "logits/chosen": -2.1099352836608887,
+      "logits/rejected": -1.886162519454956,
+      "logps/chosen": -425.6485290527344,
+      "logps/rejected": -410.21478271484375,
+      "loss": 0.5418,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.5665225982666016,
+      "rewards/margins": 0.683864414691925,
+      "rewards/rejected": -1.2503869533538818,
+      "step": 190
+    },
+    {
+      "epoch": 0.21482277121374865,
+      "grad_norm": 44.05226135253906,
+      "learning_rate": 4.804730597454859e-07,
+      "logits/chosen": -2.0036187171936035,
+      "logits/rejected": -1.8792438507080078,
+      "logps/chosen": -399.13043212890625,
+      "logps/rejected": -396.62396240234375,
+      "loss": 0.5527,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.4406675696372986,
+      "rewards/margins": 0.7380279302597046,
+      "rewards/rejected": -1.1786954402923584,
+      "step": 200
+    },
+    {
+      "epoch": 0.22556390977443608,
+      "grad_norm": 51.885616302490234,
+      "learning_rate": 4.7667598785642125e-07,
+      "logits/chosen": -2.023136615753174,
+      "logits/rejected": -1.8735549449920654,
+      "logps/chosen": -310.3551025390625,
+      "logps/rejected": -374.1414489746094,
+      "loss": 0.5322,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.42302098870277405,
+      "rewards/margins": 0.5779639482498169,
+      "rewards/rejected": -1.0009849071502686,
+      "step": 210
+    },
+    {
+      "epoch": 0.23630504833512353,
+      "grad_norm": 81.05691528320312,
+      "learning_rate": 4.725596127020879e-07,
+      "logits/chosen": -1.7004687786102295,
+      "logits/rejected": -1.7193877696990967,
+      "logps/chosen": -350.72308349609375,
+      "logps/rejected": -415.49591064453125,
+      "loss": 0.5508,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.7310193777084351,
+      "rewards/margins": 0.5848621129989624,
+      "rewards/rejected": -1.315881609916687,
+      "step": 220
+    },
+    {
+      "epoch": 0.24704618689581095,
+      "grad_norm": 53.66835021972656,
+      "learning_rate": 4.6812973274415924e-07,
+      "logits/chosen": -1.7762218713760376,
+      "logits/rejected": -1.6072883605957031,
+      "logps/chosen": -355.7483825683594,
+      "logps/rejected": -385.47930908203125,
+      "loss": 0.5362,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.48422494530677795,
+      "rewards/margins": 0.607512354850769,
+      "rewards/rejected": -1.091737151145935,
+      "step": 230
+    },
+    {
+      "epoch": 0.2577873254564984,
+      "grad_norm": 61.94645309448242,
+      "learning_rate": 4.633925880575046e-07,
+      "logits/chosen": -1.9013745784759521,
+      "logits/rejected": -1.7701694965362549,
+      "logps/chosen": -420.7286682128906,
+      "logps/rejected": -435.3941955566406,
+      "loss": 0.518,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.7990320920944214,
+      "rewards/margins": 0.7329047918319702,
+      "rewards/rejected": -1.5319368839263916,
+      "step": 240
+    },
+    {
+      "epoch": 0.26852846401718583,
+      "grad_norm": 72.49921417236328,
+      "learning_rate": 4.5835485154021437e-07,
+      "logits/chosen": -1.7423961162567139,
+      "logits/rejected": -1.6719386577606201,
+      "logps/chosen": -402.57159423828125,
+      "logps/rejected": -477.9698791503906,
+      "loss": 0.5094,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.6995307803153992,
+      "rewards/margins": 0.7330148220062256,
+      "rewards/rejected": -1.4325456619262695,
+      "step": 250
+    },
+    {
+      "epoch": 0.27926960257787325,
+      "grad_norm": 65.41045379638672,
+      "learning_rate": 4.530236195139358e-07,
+      "logits/chosen": -1.8140243291854858,
+      "logits/rejected": -1.6735155582427979,
+      "logps/chosen": -393.9617919921875,
+      "logps/rejected": -421.1630859375,
+      "loss": 0.5377,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.5548108816146851,
+      "rewards/margins": 0.7069646716117859,
+      "rewards/rejected": -1.2617756128311157,
+      "step": 260
+    },
+    {
+      "epoch": 0.2900107411385607,
+      "grad_norm": 49.067054748535156,
+      "learning_rate": 4.474064017277605e-07,
+      "logits/chosen": -1.8181359767913818,
+      "logits/rejected": -1.7128044366836548,
+      "logps/chosen": -370.6304016113281,
+      "logps/rejected": -398.3502502441406,
+      "loss": 0.544,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.7615430951118469,
+      "rewards/margins": 0.4647931158542633,
+      "rewards/rejected": -1.2263362407684326,
+      "step": 270
+    },
+    {
+      "epoch": 0.3007518796992481,
+      "grad_norm": 67.5071792602539,
+      "learning_rate": 4.415111107797445e-07,
+      "logits/chosen": -1.7189642190933228,
+      "logits/rejected": -1.7779271602630615,
+      "logps/chosen": -348.5400695800781,
+      "logps/rejected": -425.5625915527344,
+      "loss": 0.5203,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.6641637682914734,
+      "rewards/margins": 0.7238661050796509,
+      "rewards/rejected": -1.3880298137664795,
+      "step": 280
+    },
+    {
+      "epoch": 0.31149301825993553,
+      "grad_norm": 50.27863311767578,
+      "learning_rate": 4.3534605097096176e-07,
+      "logits/chosen": -1.651114821434021,
+      "logits/rejected": -1.5353507995605469,
+      "logps/chosen": -335.2391357421875,
+      "logps/rejected": -443.3240661621094,
+      "loss": 0.5236,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.7241489291191101,
+      "rewards/margins": 0.6447311639785767,
+      "rewards/rejected": -1.368880033493042,
+      "step": 290
+    },
+    {
+      "epoch": 0.322234156820623,
+      "grad_norm": 52.84365463256836,
+      "learning_rate": 4.289199066077922e-07,
+      "logits/chosen": -1.712467908859253,
+      "logits/rejected": -1.4087601900100708,
+      "logps/chosen": -359.71502685546875,
+      "logps/rejected": -427.78045654296875,
+      "loss": 0.5071,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.7437978386878967,
+      "rewards/margins": 0.8904324769973755,
+      "rewards/rejected": -1.6342302560806274,
+      "step": 300
+    },
+    {
+      "epoch": 0.33297529538131043,
+      "grad_norm": 73.85507202148438,
+      "learning_rate": 4.2224172976892166e-07,
+      "logits/chosen": -1.4589178562164307,
+      "logits/rejected": -1.3919631242752075,
+      "logps/chosen": -395.29888916015625,
+      "logps/rejected": -469.9727478027344,
+      "loss": 0.5085,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.9644006490707397,
+      "rewards/margins": 0.9210098385810852,
+      "rewards/rejected": -1.8854105472564697,
+      "step": 310
+    },
+    {
+      "epoch": 0.34371643394199786,
+      "grad_norm": 163.49395751953125,
+      "learning_rate": 4.1532092755428525e-07,
+      "logits/chosen": -1.453866958618164,
+      "logits/rejected": -1.392270803451538,
+      "logps/chosen": -352.23748779296875,
+      "logps/rejected": -432.1480407714844,
+      "loss": 0.5065,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.8710242509841919,
+      "rewards/margins": 0.7999363541603088,
+      "rewards/rejected": -1.6709606647491455,
+      "step": 320
+    },
+    {
+      "epoch": 0.3544575725026853,
+      "grad_norm": 87.29029846191406,
+      "learning_rate": 4.0816724883391707e-07,
+      "logits/chosen": -1.7530879974365234,
+      "logits/rejected": -1.5067665576934814,
+      "logps/chosen": -385.63702392578125,
+      "logps/rejected": -428.7237854003906,
+      "loss": 0.5205,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.8045473098754883,
+      "rewards/margins": 0.8592826128005981,
+      "rewards/rejected": -1.663830041885376,
+      "step": 330
+    },
+    {
+      "epoch": 0.3651987110633727,
+      "grad_norm": 59.684043884277344,
+      "learning_rate": 4.007907705153699e-07,
+      "logits/chosen": -1.6779248714447021,
+      "logits/rejected": -1.6681525707244873,
+      "logps/chosen": -394.14007568359375,
+      "logps/rejected": -467.6216735839844,
+      "loss": 0.543,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.5750120878219604,
+      "rewards/margins": 0.646149754524231,
+      "rewards/rejected": -1.2211616039276123,
+      "step": 340
+    },
+    {
+      "epoch": 0.37593984962406013,
+      "grad_norm": 53.85585403442383,
+      "learning_rate": 3.932018833490518e-07,
+      "logits/chosen": -1.727351427078247,
+      "logits/rejected": -1.599186658859253,
+      "logps/chosen": -391.8357849121094,
+      "logps/rejected": -442.3279724121094,
+      "loss": 0.5156,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.6497470140457153,
+      "rewards/margins": 0.7530845403671265,
+      "rewards/rejected": -1.4028315544128418,
+      "step": 350
+    },
+    {
+      "epoch": 0.3866809881847476,
+      "grad_norm": 55.50624084472656,
+      "learning_rate": 3.854112772914723e-07,
+      "logits/chosen": -1.479723572731018,
+      "logits/rejected": -1.5374826192855835,
+      "logps/chosen": -342.92791748046875,
+      "logps/rejected": -446.47503662109375,
+      "loss": 0.5091,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.8904348611831665,
+      "rewards/margins": 0.907945990562439,
+      "rewards/rejected": -1.7983808517456055,
+      "step": 360
+    },
+    {
+      "epoch": 0.39742212674543503,
+      "grad_norm": 53.516597747802734,
+      "learning_rate": 3.774299264470177e-07,
+      "logits/chosen": -1.506805181503296,
+      "logits/rejected": -1.5588204860687256,
+      "logps/chosen": -392.9142150878906,
+      "logps/rejected": -493.38812255859375,
+      "loss": 0.5008,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.9804698824882507,
+      "rewards/margins": 0.8168279528617859,
+      "rewards/rejected": -1.7972980737686157,
+      "step": 370
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 57.87943649291992,
+      "learning_rate": 3.6926907360946604e-07,
+      "logits/chosen": -1.7936798334121704,
+      "logits/rejected": -1.573922872543335,
+      "logps/chosen": -382.94732666015625,
+      "logps/rejected": -445.59423828125,
+      "loss": 0.5065,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.781761109828949,
+      "rewards/margins": 0.822665810585022,
+      "rewards/rejected": -1.6044269800186157,
+      "step": 380
+    },
+    {
+      "epoch": 0.4189044038668099,
+      "grad_norm": 54.115848541259766,
+      "learning_rate": 3.609402144250171e-07,
+      "logits/chosen": -1.8267205953598022,
+      "logits/rejected": -1.5302643775939941,
+      "logps/chosen": -418.0675354003906,
+      "logps/rejected": -446.8143005371094,
+      "loss": 0.4838,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.7378665208816528,
+      "rewards/margins": 1.0708403587341309,
+      "rewards/rejected": -1.8087068796157837,
+      "step": 390
+    },
+    {
+      "epoch": 0.4296455424274973,
+      "grad_norm": 48.267066955566406,
+      "learning_rate": 3.5245508119914683e-07,
+      "logits/chosen": -1.695697546005249,
+      "logits/rejected": -1.5788294076919556,
+      "logps/chosen": -400.60382080078125,
+      "logps/rejected": -472.8611755371094,
+      "loss": 0.4735,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -1.0140430927276611,
+      "rewards/margins": 0.6619123220443726,
+      "rewards/rejected": -1.6759554147720337,
+      "step": 400
+    },
+    {
+      "epoch": 0.44038668098818473,
+      "grad_norm": 54.982364654541016,
+      "learning_rate": 3.4382562637009484e-07,
+      "logits/chosen": -1.76909601688385,
+      "logits/rejected": -1.6182836294174194,
+      "logps/chosen": -387.72088623046875,
+      "logps/rejected": -486.9130859375,
+      "loss": 0.5232,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.9676576852798462,
+      "rewards/margins": 0.9475955963134766,
+      "rewards/rejected": -1.9152532815933228,
+      "step": 410
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "grad_norm": 63.29111099243164,
+      "learning_rate": 3.350640056722662e-07,
+      "logits/chosen": -1.5833942890167236,
+      "logits/rejected": -1.4724894762039185,
+      "logps/chosen": -380.0611877441406,
+      "logps/rejected": -419.60699462890625,
+      "loss": 0.506,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.9589203596115112,
+      "rewards/margins": 0.64564049243927,
+      "rewards/rejected": -1.6045608520507812,
+      "step": 420
+    },
+    {
+      "epoch": 0.46186895810955964,
+      "grad_norm": 54.812477111816406,
+      "learning_rate": 3.261825610132634e-07,
+      "logits/chosen": -1.825090765953064,
+      "logits/rejected": -1.742057204246521,
+      "logps/chosen": -434.72491455078125,
+      "logps/rejected": -475.3501892089844,
+      "loss": 0.5288,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.6500536799430847,
+      "rewards/margins": 0.9928058385848999,
+      "rewards/rejected": -1.642859697341919,
+      "step": 430
+    },
+    {
+      "epoch": 0.47261009667024706,
+      "grad_norm": 55.682682037353516,
+      "learning_rate": 3.1719380308866924e-07,
+      "logits/chosen": -1.8630441427230835,
+      "logits/rejected": -1.7151546478271484,
+      "logps/chosen": -378.4299011230469,
+      "logps/rejected": -382.890869140625,
+      "loss": 0.4969,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.6695320010185242,
+      "rewards/margins": 0.7351147532463074,
+      "rewards/rejected": -1.404646873474121,
+      "step": 440
+    },
+    {
+      "epoch": 0.4833512352309345,
+      "grad_norm": 55.0916862487793,
+      "learning_rate": 3.0811039375906764e-07,
+      "logits/chosen": -1.9064140319824219,
+      "logits/rejected": -1.714078664779663,
+      "logps/chosen": -397.0462951660156,
+      "logps/rejected": -441.3729553222656,
+      "loss": 0.5073,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.7625714540481567,
+      "rewards/margins": 0.8189951181411743,
+      "rewards/rejected": -1.581566572189331,
+      "step": 450
+    },
+    {
+      "epoch": 0.4940923737916219,
+      "grad_norm": 58.015785217285156,
+      "learning_rate": 2.9894512821413075e-07,
+      "logits/chosen": -1.7865148782730103,
+      "logits/rejected": -1.5167757272720337,
+      "logps/chosen": -416.95550537109375,
+      "logps/rejected": -436.30450439453125,
+      "loss": 0.4966,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.9333486557006836,
+      "rewards/margins": 0.8736823797225952,
+      "rewards/rejected": -1.807031273841858,
+      "step": 460
+    },
+    {
+      "epoch": 0.5048335123523093,
+      "grad_norm": 68.10478210449219,
+      "learning_rate": 2.8971091694889264e-07,
+      "logits/chosen": -1.7999794483184814,
+      "logits/rejected": -1.7058521509170532,
+      "logps/chosen": -399.33038330078125,
+      "logps/rejected": -435.877197265625,
+      "loss": 0.5401,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.9552398920059204,
+      "rewards/margins": 0.6859758496284485,
+      "rewards/rejected": -1.6412159204483032,
+      "step": 470
+    },
+    {
+      "epoch": 0.5155746509129968,
+      "grad_norm": 72.0062255859375,
+      "learning_rate": 2.8042076757760066e-07,
+      "logits/chosen": -1.8483903408050537,
+      "logits/rejected": -1.52974534034729,
+      "logps/chosen": -399.46746826171875,
+      "logps/rejected": -427.24981689453125,
+      "loss": 0.5003,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.8091894388198853,
+      "rewards/margins": 0.6731428503990173,
+      "rewards/rejected": -1.4823323488235474,
+      "step": 480
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 61.39365768432617,
+      "learning_rate": 2.7108776651076116e-07,
+      "logits/chosen": -1.7545459270477295,
+      "logits/rejected": -1.6814851760864258,
+      "logps/chosen": -398.98699951171875,
+      "logps/rejected": -491.4130859375,
+      "loss": 0.4783,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.6736662983894348,
+      "rewards/margins": 0.9081080555915833,
+      "rewards/rejected": -1.5817744731903076,
+      "step": 490
+    },
+    {
+      "epoch": 0.5370569280343717,
+      "grad_norm": 54.34407424926758,
+      "learning_rate": 2.6172506052119147e-07,
+      "logits/chosen": -1.7606862783432007,
+      "logits/rejected": -1.576406478881836,
+      "logps/chosen": -404.3669128417969,
+      "logps/rejected": -468.853515625,
+      "loss": 0.5235,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.9447774887084961,
+      "rewards/margins": 0.9778174161911011,
+      "rewards/rejected": -1.9225950241088867,
+      "step": 500
+    },
+    {
+      "epoch": 0.547798066595059,
+      "grad_norm": 76.07147216796875,
+      "learning_rate": 2.523458382250412e-07,
+      "logits/chosen": -1.7519705295562744,
+      "logits/rejected": -1.6435455083847046,
+      "logps/chosen": -410.5835876464844,
+      "logps/rejected": -490.4002380371094,
+      "loss": 0.4922,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.7955667972564697,
+      "rewards/margins": 0.8166013956069946,
+      "rewards/rejected": -1.612168312072754,
+      "step": 510
+    },
+    {
+      "epoch": 0.5585392051557465,
+      "grad_norm": 56.88628387451172,
+      "learning_rate": 2.429633115038737e-07,
+      "logits/chosen": -1.7606322765350342,
+      "logits/rejected": -1.561812162399292,
+      "logps/chosen": -399.27294921875,
+      "logps/rejected": -455.17462158203125,
+      "loss": 0.4751,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.7019720673561096,
+      "rewards/margins": 1.1464049816131592,
+      "rewards/rejected": -1.8483772277832031,
+      "step": 520
+    },
+    {
+      "epoch": 0.569280343716434,
+      "grad_norm": 108.08949279785156,
+      "learning_rate": 2.3359069689397467e-07,
+      "logits/chosen": -1.5748560428619385,
+      "logits/rejected": -1.5276682376861572,
+      "logps/chosen": -402.18023681640625,
+      "logps/rejected": -493.3003845214844,
+      "loss": 0.509,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.0235780477523804,
+      "rewards/margins": 0.8902117609977722,
+      "rewards/rejected": -1.9137897491455078,
+      "step": 530
+    },
+    {
+      "epoch": 0.5800214822771214,
+      "grad_norm": 81.13088989257812,
+      "learning_rate": 2.2424119696910278e-07,
+      "logits/chosen": -1.6776129007339478,
+      "logits/rejected": -1.4775701761245728,
+      "logps/chosen": -423.53778076171875,
+      "logps/rejected": -458.8199768066406,
+      "loss": 0.4854,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.8803874254226685,
+      "rewards/margins": 0.8511655926704407,
+      "rewards/rejected": -1.7315528392791748,
+      "step": 540
+    },
+    {
+      "epoch": 0.5907626208378088,
+      "grad_norm": 55.828590393066406,
+      "learning_rate": 2.1492798174291006e-07,
+      "logits/chosen": -1.6470720767974854,
+      "logits/rejected": -1.4030835628509521,
+      "logps/chosen": -370.0120544433594,
+      "logps/rejected": -398.987060546875,
+      "loss": 0.4997,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.6602271795272827,
+      "rewards/margins": 0.8755744099617004,
+      "rewards/rejected": -1.535801649093628,
+      "step": 550
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "grad_norm": 50.89604187011719,
+      "learning_rate": 2.0566417011722652e-07,
+      "logits/chosen": -1.7970349788665771,
+      "logits/rejected": -1.5006736516952515,
+      "logps/chosen": -410.7815856933594,
+      "logps/rejected": -538.999267578125,
+      "loss": 0.4874,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -0.8133628964424133,
+      "rewards/margins": 1.2357568740844727,
+      "rewards/rejected": -2.049119710922241,
+      "step": 560
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 61.7906494140625,
+      "learning_rate": 1.9646281140234222e-07,
+      "logits/chosen": -1.5956964492797852,
+      "logits/rejected": -1.560612440109253,
+      "logps/chosen": -411.87615966796875,
+      "logps/rejected": -522.2528076171875,
+      "loss": 0.4574,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -1.0511554479599,
+      "rewards/margins": 1.075621485710144,
+      "rewards/rejected": -2.126776933670044,
+      "step": 570
+    },
+    {
+      "epoch": 0.6229860365198711,
+      "grad_norm": 69.56195831298828,
+      "learning_rate": 1.8733686693531982e-07,
+      "logits/chosen": -1.601663589477539,
+      "logits/rejected": -1.5559356212615967,
+      "logps/chosen": -434.58880615234375,
+      "logps/rejected": -539.5415649414062,
+      "loss": 0.4856,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.2848224639892578,
+      "rewards/margins": 0.8390380144119263,
+      "rewards/rejected": -2.1238605976104736,
+      "step": 580
+    },
+    {
+      "epoch": 0.6337271750805585,
+      "grad_norm": 67.03250122070312,
+      "learning_rate": 1.782991918222275e-07,
+      "logits/chosen": -1.6579906940460205,
+      "logits/rejected": -1.3883017301559448,
+      "logps/chosen": -424.90643310546875,
+      "logps/rejected": -479.0643005371094,
+      "loss": 0.4948,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.1206614971160889,
+      "rewards/margins": 0.9874579310417175,
+      "rewards/rejected": -2.108119487762451,
+      "step": 590
+    },
+    {
+      "epoch": 0.644468313641246,
+      "grad_norm": 49.616844177246094,
+      "learning_rate": 1.693625168300127e-07,
+      "logits/chosen": -1.5930492877960205,
+      "logits/rejected": -1.3797900676727295,
+      "logps/chosen": -399.57135009765625,
+      "logps/rejected": -451.79022216796875,
+      "loss": 0.5333,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.0476266145706177,
+      "rewards/margins": 0.8083570599555969,
+      "rewards/rejected": -1.8559834957122803,
+      "step": 600
+    },
+    {
+      "epoch": 0.6552094522019334,
+      "grad_norm": 66.87409973144531,
+      "learning_rate": 1.6053943045352516e-07,
+      "logits/chosen": -1.5892466306686401,
+      "logits/rejected": -1.5528477430343628,
+      "logps/chosen": -399.47808837890625,
+      "logps/rejected": -506.40374755859375,
+      "loss": 0.4995,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.6764686107635498,
+      "rewards/margins": 0.8436732292175293,
+      "rewards/rejected": -1.5201416015625,
+      "step": 610
+    },
+    {
+      "epoch": 0.6659505907626209,
+      "grad_norm": 55.837158203125,
+      "learning_rate": 1.5184236118294787e-07,
+      "logits/chosen": -1.5849072933197021,
+      "logits/rejected": -1.4045408964157104,
+      "logps/chosen": -453.03070068359375,
+      "logps/rejected": -508.41705322265625,
+      "loss": 0.4857,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -1.2203357219696045,
+      "rewards/margins": 0.8617902994155884,
+      "rewards/rejected": -2.0821259021759033,
+      "step": 620
+    },
+    {
+      "epoch": 0.6766917293233082,
+      "grad_norm": 45.06595230102539,
+      "learning_rate": 1.4328355999661586e-07,
+      "logits/chosen": -1.540052890777588,
+      "logits/rejected": -1.3541651964187622,
+      "logps/chosen": -389.3322448730469,
+      "logps/rejected": -468.869384765625,
+      "loss": 0.5054,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.0844593048095703,
+      "rewards/margins": 1.0829648971557617,
+      "rewards/rejected": -2.167423963546753,
+      "step": 630
+    },
+    {
+      "epoch": 0.6874328678839957,
+      "grad_norm": 60.282310485839844,
+      "learning_rate": 1.3487508310388534e-07,
+      "logits/chosen": -1.434007167816162,
+      "logits/rejected": -1.4812556505203247,
+      "logps/chosen": -397.49090576171875,
+      "logps/rejected": -508.686767578125,
+      "loss": 0.5134,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -1.238869309425354,
+      "rewards/margins": 0.7315988540649414,
+      "rewards/rejected": -1.9704681634902954,
+      "step": 640
+    },
+    {
+      "epoch": 0.6981740064446831,
+      "grad_norm": 45.42427444458008,
+      "learning_rate": 1.266287749623594e-07,
+      "logits/chosen": -1.7065637111663818,
+      "logits/rejected": -1.4134385585784912,
+      "logps/chosen": -430.59197998046875,
+      "logps/rejected": -482.938720703125,
+      "loss": 0.4871,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.0648348331451416,
+      "rewards/margins": 1.0008587837219238,
+      "rewards/rejected": -2.0656933784484863,
+      "step": 650
+    },
+    {
+      "epoch": 0.7089151450053706,
+      "grad_norm": 55.1621208190918,
+      "learning_rate": 1.1855625159339452e-07,
+      "logits/chosen": -1.6233896017074585,
+      "logits/rejected": -1.4236741065979004,
+      "logps/chosen": -445.6341247558594,
+      "logps/rejected": -489.8377380371094,
+      "loss": 0.4783,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.1494815349578857,
+      "rewards/margins": 0.9501803517341614,
+      "rewards/rejected": -2.0996615886688232,
+      "step": 660
+    },
+    {
+      "epoch": 0.719656283566058,
+      "grad_norm": 64.62177276611328,
+      "learning_rate": 1.1066888421939092e-07,
+      "logits/chosen": -1.6147754192352295,
+      "logits/rejected": -1.3309791088104248,
+      "logps/chosen": -438.37042236328125,
+      "logps/rejected": -420.2880859375,
+      "loss": 0.4984,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.012224555015564,
+      "rewards/margins": 0.7375470399856567,
+      "rewards/rejected": -1.7497714757919312,
+      "step": 670
+    },
+    {
+      "epoch": 0.7303974221267454,
+      "grad_norm": 59.346073150634766,
+      "learning_rate": 1.0297778324591339e-07,
+      "logits/chosen": -1.5413581132888794,
+      "logits/rejected": -1.2392480373382568,
+      "logps/chosen": -423.99853515625,
+      "logps/rejected": -454.7129821777344,
+      "loss": 0.5099,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.9406285285949707,
+      "rewards/margins": 1.0149680376052856,
+      "rewards/rejected": -1.9555965662002563,
+      "step": 680
+    },
+    {
+      "epoch": 0.7411385606874329,
+      "grad_norm": 49.851619720458984,
+      "learning_rate": 9.549378261120816e-08,
+      "logits/chosen": -1.583778977394104,
+      "logits/rejected": -1.4962458610534668,
+      "logps/chosen": -394.4914245605469,
+      "logps/rejected": -450.92218017578125,
+      "loss": 0.4907,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.9432915449142456,
+      "rewards/margins": 0.7003445029258728,
+      "rewards/rejected": -1.6436359882354736,
+      "step": 690
+    },
+    {
+      "epoch": 0.7518796992481203,
+      "grad_norm": 87.44384002685547,
+      "learning_rate": 8.822742452516063e-08,
+      "logits/chosen": -1.6286656856536865,
+      "logits/rejected": -1.4821763038635254,
+      "logps/chosen": -421.04083251953125,
+      "logps/rejected": -503.68365478515625,
+      "loss": 0.5017,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.912327766418457,
+      "rewards/margins": 0.9774397015571594,
+      "rewards/rejected": -1.8897672891616821,
+      "step": 700
+    },
+    {
+      "epoch": 0.7626208378088077,
+      "grad_norm": 50.42548751831055,
+      "learning_rate": 8.118894461919074e-08,
+      "logits/chosen": -1.4116138219833374,
+      "logits/rejected": -1.2908035516738892,
+      "logps/chosen": -368.16656494140625,
+      "logps/rejected": -451.15087890625,
+      "loss": 0.4812,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.0490543842315674,
+      "rewards/margins": 0.8819605708122253,
+      "rewards/rejected": -1.9310150146484375,
+      "step": 710
+    },
+    {
+      "epoch": 0.7733619763694952,
+      "grad_norm": 53.07373809814453,
+      "learning_rate": 7.438825752800579e-08,
+      "logits/chosen": -1.6596364974975586,
+      "logits/rejected": -1.556316614151001,
+      "logps/chosen": -442.6805114746094,
+      "logps/rejected": -490.9193420410156,
+      "loss": 0.4715,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.8844410181045532,
+      "rewards/margins": 0.9804731607437134,
+      "rewards/rejected": -1.8649142980575562,
+      "step": 720
+    },
+    {
+      "epoch": 0.7841031149301826,
+      "grad_norm": 53.835243225097656,
+      "learning_rate": 6.783494292351907e-08,
+      "logits/chosen": -1.4840538501739502,
+      "logits/rejected": -1.2394304275512695,
+      "logps/chosen": -376.4036560058594,
+      "logps/rejected": -482.4645080566406,
+      "loss": 0.4999,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.9420751333236694,
+      "rewards/margins": 1.132046103477478,
+      "rewards/rejected": -2.0741212368011475,
+      "step": 730
+    },
+    {
+      "epoch": 0.7948442534908701,
+      "grad_norm": 62.356510162353516,
+      "learning_rate": 6.153823202060846e-08,
+      "logits/chosen": -1.4445642232894897,
+      "logits/rejected": -1.271066665649414,
+      "logps/chosen": -390.6706848144531,
+      "logps/rejected": -478.68463134765625,
+      "loss": 0.4794,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.236981749534607,
+      "rewards/margins": 0.9016791582107544,
+      "rewards/rejected": -2.1386606693267822,
+      "step": 740
+    },
+    {
+      "epoch": 0.8055853920515574,
+      "grad_norm": 79.2643051147461,
+      "learning_rate": 5.550699457372282e-08,
+      "logits/chosen": -1.568433403968811,
+      "logits/rejected": -1.4340345859527588,
+      "logps/chosen": -396.7769470214844,
+      "logps/rejected": -476.18585205078125,
+      "loss": 0.4811,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.8553333282470703,
+      "rewards/margins": 1.078909158706665,
+      "rewards/rejected": -1.9342422485351562,
+      "step": 750
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 75.26664733886719,
+      "learning_rate": 4.97497263826539e-08,
+      "logits/chosen": -1.6515172719955444,
+      "logits/rejected": -1.4298070669174194,
+      "logps/chosen": -439.5928649902344,
+      "logps/rejected": -471.7366638183594,
+      "loss": 0.4988,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -1.0839134454727173,
+      "rewards/margins": 0.8585917353630066,
+      "rewards/rejected": -1.942505121231079,
+      "step": 760
+    },
+    {
+      "epoch": 0.8270676691729323,
+      "grad_norm": 55.086814880371094,
+      "learning_rate": 4.4274537325072384e-08,
+      "logits/chosen": -1.7422411441802979,
+      "logits/rejected": -1.465787649154663,
+      "logps/chosen": -413.664306640625,
+      "logps/rejected": -463.29180908203125,
+      "loss": 0.4741,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.8051220178604126,
+      "rewards/margins": 1.0510156154632568,
+      "rewards/rejected": -1.8561376333236694,
+      "step": 770
+    },
+    {
+      "epoch": 0.8378088077336198,
+      "grad_norm": 52.02236557006836,
+      "learning_rate": 3.9089139932687534e-08,
+      "logits/chosen": -1.5885370969772339,
+      "logits/rejected": -1.232320785522461,
+      "logps/chosen": -414.0470275878906,
+      "logps/rejected": -457.7579650878906,
+      "loss": 0.4909,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.0070761442184448,
+      "rewards/margins": 1.148498773574829,
+      "rewards/rejected": -2.1555750370025635,
+      "step": 780
+    },
+    {
+      "epoch": 0.8485499462943072,
+      "grad_norm": 57.56011199951172,
+      "learning_rate": 3.4200838527120525e-08,
+      "logits/chosen": -1.5626875162124634,
+      "logits/rejected": -1.446763277053833,
+      "logps/chosen": -366.77081298828125,
+      "logps/rejected": -446.97760009765625,
+      "loss": 0.4699,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.8740879893302917,
+      "rewards/margins": 0.9469636082649231,
+      "rewards/rejected": -1.8210515975952148,
+      "step": 790
+    },
+    {
+      "epoch": 0.8592910848549946,
+      "grad_norm": 66.50774383544922,
+      "learning_rate": 2.9616518930796447e-08,
+      "logits/chosen": -1.6846020221710205,
+      "logits/rejected": -1.5415384769439697,
+      "logps/chosen": -471.2176818847656,
+      "logps/rejected": -504.05035400390625,
+      "loss": 0.4866,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.8976691961288452,
+      "rewards/margins": 1.1193997859954834,
+      "rewards/rejected": -2.017069101333618,
+      "step": 800
+    },
+    {
+      "epoch": 0.8700322234156821,
+      "grad_norm": 49.84431457519531,
+      "learning_rate": 2.534263876734802e-08,
+      "logits/chosen": -1.6844720840454102,
+      "logits/rejected": -1.4568878412246704,
+      "logps/chosen": -412.49371337890625,
+      "logps/rejected": -470.7568359375,
+      "loss": 0.4711,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.9692155718803406,
+      "rewards/margins": 1.001009464263916,
+      "rewards/rejected": -1.9702249765396118,
+      "step": 810
+    },
+    {
+      "epoch": 0.8807733619763695,
+      "grad_norm": 54.95064926147461,
+      "learning_rate": 2.138521836519408e-08,
+      "logits/chosen": -1.6106141805648804,
+      "logits/rejected": -1.4224177598953247,
+      "logps/chosen": -422.16796875,
+      "logps/rejected": -472.8387145996094,
+      "loss": 0.4862,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.0354992151260376,
+      "rewards/margins": 0.9904156923294067,
+      "rewards/rejected": -2.0259149074554443,
+      "step": 820
+    },
+    {
+      "epoch": 0.8915145005370569,
+      "grad_norm": 59.206207275390625,
+      "learning_rate": 1.7749832277106524e-08,
+      "logits/chosen": -1.5170490741729736,
+      "logits/rejected": -1.3669121265411377,
+      "logps/chosen": -387.67791748046875,
+      "logps/rejected": -476.3672790527344,
+      "loss": 0.4937,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.0796597003936768,
+      "rewards/margins": 1.1205719709396362,
+      "rewards/rejected": -2.2002315521240234,
+      "step": 830
+    },
+    {
+      "epoch": 0.9022556390977443,
+      "grad_norm": 76.18675231933594,
+      "learning_rate": 1.4441601427711836e-08,
+      "logits/chosen": -1.6329158544540405,
+      "logits/rejected": -1.3677482604980469,
+      "logps/chosen": -407.67523193359375,
+      "logps/rejected": -457.119384765625,
+      "loss": 0.4827,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.0345627069473267,
+      "rewards/margins": 0.9469528198242188,
+      "rewards/rejected": -1.9815152883529663,
+      "step": 840
+    },
+    {
+      "epoch": 0.9129967776584318,
+      "grad_norm": 52.468204498291016,
+      "learning_rate": 1.1465185899987794e-08,
+      "logits/chosen": -1.5776712894439697,
+      "logits/rejected": -1.3938223123550415,
+      "logps/chosen": -396.31195068359375,
+      "logps/rejected": -443.401123046875,
+      "loss": 0.5082,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.0158368349075317,
+      "rewards/margins": 0.9373232126235962,
+      "rewards/rejected": -1.953160047531128,
+      "step": 850
+    },
+    {
+      "epoch": 0.9237379162191193,
+      "grad_norm": 69.90252685546875,
+      "learning_rate": 8.824778370916996e-09,
+      "logits/chosen": -1.5731096267700195,
+      "logits/rejected": -1.47088623046875,
+      "logps/chosen": -432.2276916503906,
+      "logps/rejected": -516.0203857421875,
+      "loss": 0.4968,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.9636839628219604,
+      "rewards/margins": 0.9173566102981567,
+      "rewards/rejected": -1.881040334701538,
+      "step": 860
+    },
+    {
+      "epoch": 0.9344790547798066,
+      "grad_norm": 53.79716873168945,
+      "learning_rate": 6.5240982055440044e-09,
+      "logits/chosen": -1.592310905456543,
+      "logits/rejected": -1.4055845737457275,
+      "logps/chosen": -392.08526611328125,
+      "logps/rejected": -461.09051513671875,
+      "loss": 0.5285,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.1570608615875244,
+      "rewards/margins": 0.8815321922302246,
+      "rewards/rejected": -2.038593292236328,
+      "step": 870
+    },
+    {
+      "epoch": 0.9452201933404941,
+      "grad_norm": 55.78624725341797,
+      "learning_rate": 4.56638621775518e-09,
+      "logits/chosen": -1.7353003025054932,
+      "logits/rejected": -1.592315435409546,
+      "logps/chosen": -423.08868408203125,
+      "logps/rejected": -525.6699829101562,
+      "loss": 0.4699,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.9968613386154175,
+      "rewards/margins": 0.8165915608406067,
+      "rewards/rejected": -1.8134530782699585,
+      "step": 880
+    },
+    {
+      "epoch": 0.9559613319011815,
+      "grad_norm": 64.26811981201172,
+      "learning_rate": 2.9544001051613478e-09,
+      "logits/chosen": -1.5674078464508057,
+      "logits/rejected": -1.477450966835022,
+      "logps/chosen": -431.13037109375,
+      "logps/rejected": -499.76849365234375,
+      "loss": 0.4941,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -1.012650489807129,
+      "rewards/margins": 0.9235459566116333,
+      "rewards/rejected": -1.9361963272094727,
+      "step": 890
+    },
+    {
+      "epoch": 0.966702470461869,
+      "grad_norm": 63.50950622558594,
+      "learning_rate": 1.690410564514244e-09,
+      "logits/chosen": -1.5680744647979736,
+      "logits/rejected": -1.3493303060531616,
+      "logps/chosen": -389.19879150390625,
+      "logps/rejected": -441.45098876953125,
+      "loss": 0.4976,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -1.0372302532196045,
+      "rewards/margins": 0.7519098520278931,
+      "rewards/rejected": -1.7891401052474976,
+      "step": 900
+    },
+    {
+      "epoch": 0.9774436090225563,
+      "grad_norm": 62.333988189697266,
+      "learning_rate": 7.761980931282053e-10,
+      "logits/chosen": -1.7527889013290405,
+      "logits/rejected": -1.5912810564041138,
+      "logps/chosen": -469.765625,
+      "logps/rejected": -504.1661071777344,
+      "loss": 0.4791,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.1952266693115234,
+      "rewards/margins": 0.7948960065841675,
+      "rewards/rejected": -1.9901227951049805,
+      "step": 910
+    },
+    {
+      "epoch": 0.9881847475832438,
+      "grad_norm": 56.70859909057617,
+      "learning_rate": 2.1305048081288191e-10,
+      "logits/chosen": -1.6409803628921509,
+      "logits/rejected": -1.3718929290771484,
+      "logps/chosen": -389.1742858886719,
+      "logps/rejected": -463.9933166503906,
+      "loss": 0.4863,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.9753316044807434,
+      "rewards/margins": 1.0109294652938843,
+      "rewards/rejected": -1.986261010169983,
+      "step": 920
+    },
+    {
+      "epoch": 0.9989258861439313,
+      "grad_norm": 53.95326614379883,
+      "learning_rate": 1.7609958501973998e-12,
+      "logits/chosen": -1.5267393589019775,
+      "logits/rejected": -1.3435981273651123,
+      "logps/chosen": -425.5747985839844,
+      "logps/rejected": -472.15435791015625,
+      "loss": 0.4831,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.9775764346122742,
+      "rewards/margins": 0.9130144119262695,
+      "rewards/rejected": -1.8905909061431885,
+      "step": 930
+    },
+    {
+      "epoch": 1.0,
+      "step": 931,
+      "total_flos": 0.0,
+      "train_loss": 0.524798985838762,
+      "train_runtime": 12257.7363,
+      "train_samples_per_second": 4.859,
+      "train_steps_per_second": 0.076
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 931,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dea64176343ea34e87a2d6063bebc8fbb0b25affb21784f938b5794009548a7
+size 7099