Upload folder using huggingface_hub

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/data1/ranw/ckpt/webshop_sft_model/sft-epoch3-Llama-2-7b-chat-hf-webshop-sft",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:346bbac5d11f1ea1f924ca2acd9b5ccaa10f18b511d63af81906322f3c45ad0b
+size 4840396416

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f4d9d8436a9d2bbc4791ef37c0c35c5d15d1e6718bb4b317fb7fda897ed904
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59efe2dbe37095bd3e4b1652bf536213791be4a26499787dee1254044a1ca786
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b299ec6e53a06223f59077f1abfa068bc401c5702bbb20691d7e416df03accf5
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de8bae173145fa56828f6ee85d50db95f000bd9f326b4a6fa72e82e04885621
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2403f1bd4eb568bb7f11097376d4d7a416907ccc5282b7ad144095ae3885e0de
+size 2684472112

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26953662464
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.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": "<unk>",
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1722 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.992,
+  "eval_steps": 500,
+  "global_step": 561,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 18.39926528930664,
+      "learning_rate": 8.771929824561403e-08,
+      "logits/chosen": 0.053128667175769806,
+      "logits/rejected": 0.06011464446783066,
+      "logps/chosen": -70.8781967163086,
+      "logps/rejected": -68.79312896728516,
+      "loss": 0.6906,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -0.0009149238467216492,
+      "rewards/margins": 0.0024268084671348333,
+      "rewards/rejected": -0.003341731382533908,
+      "step": 5
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 19.233495712280273,
+      "learning_rate": 1.7543859649122805e-07,
+      "logits/chosen": -0.09774302691221237,
+      "logits/rejected": -0.09648840129375458,
+      "logps/chosen": -46.74890899658203,
+      "logps/rejected": -57.538856506347656,
+      "loss": 0.6755,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.04250483959913254,
+      "rewards/margins": 0.04128213971853256,
+      "rewards/rejected": 0.0012226973194628954,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 17.17833137512207,
+      "learning_rate": 2.631578947368421e-07,
+      "logits/chosen": -0.09319419413805008,
+      "logits/rejected": -0.08535219728946686,
+      "logps/chosen": -58.279396057128906,
+      "logps/rejected": -69.68245697021484,
+      "loss": 0.6361,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.0669654831290245,
+      "rewards/margins": 0.10347993671894073,
+      "rewards/rejected": -0.03651442751288414,
+      "step": 15
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 16.598756790161133,
+      "learning_rate": 3.508771929824561e-07,
+      "logits/chosen": 0.03794529289007187,
+      "logits/rejected": 0.044014494866132736,
+      "logps/chosen": -63.522361755371094,
+      "logps/rejected": -73.55606842041016,
+      "loss": 0.6007,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.07537873089313507,
+      "rewards/margins": 0.3096093237400055,
+      "rewards/rejected": -0.23423054814338684,
+      "step": 20
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 14.252389907836914,
+      "learning_rate": 4.3859649122807013e-07,
+      "logits/chosen": 0.06569056957960129,
+      "logits/rejected": 0.0650763288140297,
+      "logps/chosen": -70.42298126220703,
+      "logps/rejected": -77.9859390258789,
+      "loss": 0.5961,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.17782427370548248,
+      "rewards/margins": 0.32860898971557617,
+      "rewards/rejected": -0.15078473091125488,
+      "step": 25
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 13.940037727355957,
+      "learning_rate": 5.263157894736842e-07,
+      "logits/chosen": -0.007893741130828857,
+      "logits/rejected": -0.010488653555512428,
+      "logps/chosen": -63.06987380981445,
+      "logps/rejected": -64.85173034667969,
+      "loss": 0.549,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.1359255164861679,
+      "rewards/margins": 0.7183843851089478,
+      "rewards/rejected": -0.5824588537216187,
+      "step": 30
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 16.549161911010742,
+      "learning_rate": 6.140350877192982e-07,
+      "logits/chosen": 0.07654356211423874,
+      "logits/rejected": 0.07278482615947723,
+      "logps/chosen": -71.77564239501953,
+      "logps/rejected": -67.6545639038086,
+      "loss": 0.509,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.32316628098487854,
+      "rewards/margins": 0.4559944272041321,
+      "rewards/rejected": -0.13282814621925354,
+      "step": 35
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 15.91128158569336,
+      "learning_rate": 7.017543859649122e-07,
+      "logits/chosen": -0.06502251327037811,
+      "logits/rejected": -0.06176159903407097,
+      "logps/chosen": -91.53266143798828,
+      "logps/rejected": -77.68993377685547,
+      "loss": 0.4975,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.005904299207031727,
+      "rewards/margins": 0.4281623959541321,
+      "rewards/rejected": -0.43406668305397034,
+      "step": 40
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 14.597318649291992,
+      "learning_rate": 7.894736842105263e-07,
+      "logits/chosen": -0.07799122482538223,
+      "logits/rejected": -0.07605376839637756,
+      "logps/chosen": -58.30717086791992,
+      "logps/rejected": -68.22291564941406,
+      "loss": 0.4913,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.33519667387008667,
+      "rewards/margins": 0.9599436521530151,
+      "rewards/rejected": -0.6247469186782837,
+      "step": 45
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 13.722618103027344,
+      "learning_rate": 8.771929824561403e-07,
+      "logits/chosen": -0.014609629288315773,
+      "logits/rejected": -0.014899415895342827,
+      "logps/chosen": -84.4870834350586,
+      "logps/rejected": -94.78424072265625,
+      "loss": 0.4642,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -0.10160064697265625,
+      "rewards/margins": 1.3170650005340576,
+      "rewards/rejected": -1.4186656475067139,
+      "step": 50
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 17.38532257080078,
+      "learning_rate": 9.649122807017545e-07,
+      "logits/chosen": -0.036196161061525345,
+      "logits/rejected": -0.03828999400138855,
+      "logps/chosen": -68.3674545288086,
+      "logps/rejected": -74.53666687011719,
+      "loss": 0.5491,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.10605410486459732,
+      "rewards/margins": 0.8501850366592407,
+      "rewards/rejected": -0.9562392234802246,
+      "step": 55
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 13.876227378845215,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.03917285054922104,
+      "logits/rejected": -0.03898438438773155,
+      "logps/chosen": -69.72596740722656,
+      "logps/rejected": -63.88629913330078,
+      "loss": 0.5169,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.1265568882226944,
+      "rewards/margins": 1.1786383390426636,
+      "rewards/rejected": -1.0520813465118408,
+      "step": 60
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 11.621339797973633,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.15784303843975067,
+      "logits/rejected": -0.15451130270957947,
+      "logps/chosen": -70.8653564453125,
+      "logps/rejected": -67.95909118652344,
+      "loss": 0.5204,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.21460843086242676,
+      "rewards/margins": 0.8792555928230286,
+      "rewards/rejected": -0.664647102355957,
+      "step": 65
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 12.923187255859375,
+      "learning_rate": 1e-06,
+      "logits/chosen": 0.043206293135881424,
+      "logits/rejected": 0.06076166778802872,
+      "logps/chosen": -71.95893859863281,
+      "logps/rejected": -98.98312377929688,
+      "loss": 0.3642,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.035441040992736816,
+      "rewards/margins": 1.6655327081680298,
+      "rewards/rejected": -1.630091667175293,
+      "step": 70
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 13.109973907470703,
+      "learning_rate": 1e-06,
+      "logits/chosen": 0.00962201226502657,
+      "logits/rejected": 0.015961844474077225,
+      "logps/chosen": -62.07453155517578,
+      "logps/rejected": -86.6424560546875,
+      "loss": 0.4846,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.27357736229896545,
+      "rewards/margins": 1.7215477228164673,
+      "rewards/rejected": -1.4479701519012451,
+      "step": 75
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 12.61295223236084,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.024258632212877274,
+      "logits/rejected": -0.015315225347876549,
+      "logps/chosen": -40.27369689941406,
+      "logps/rejected": -69.33142852783203,
+      "loss": 0.4061,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.4955378472805023,
+      "rewards/margins": 1.1658498048782349,
+      "rewards/rejected": -0.6703119277954102,
+      "step": 80
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 12.405911445617676,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.14968207478523254,
+      "logits/rejected": -0.14379464089870453,
+      "logps/chosen": -74.81858825683594,
+      "logps/rejected": -89.59300231933594,
+      "loss": 0.3693,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.3189702332019806,
+      "rewards/margins": 1.6341769695281982,
+      "rewards/rejected": -1.31520676612854,
+      "step": 85
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 12.492094039916992,
+      "learning_rate": 1e-06,
+      "logits/chosen": 0.04283991456031799,
+      "logits/rejected": 0.04497765749692917,
+      "logps/chosen": -88.62035369873047,
+      "logps/rejected": -99.63616180419922,
+      "loss": 0.4934,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.29155534505844116,
+      "rewards/margins": 1.47171950340271,
+      "rewards/rejected": -1.7632747888565063,
+      "step": 90
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 15.640336990356445,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.04965194687247276,
+      "logits/rejected": -0.043795522302389145,
+      "logps/chosen": -75.30198669433594,
+      "logps/rejected": -96.59324645996094,
+      "loss": 0.4722,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.1831967532634735,
+      "rewards/margins": 1.4340693950653076,
+      "rewards/rejected": -1.617266297340393,
+      "step": 95
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 17.030439376831055,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.14364857971668243,
+      "logits/rejected": -0.13528576493263245,
+      "logps/chosen": -37.00883102416992,
+      "logps/rejected": -51.563194274902344,
+      "loss": 0.4453,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.1994268000125885,
+      "rewards/margins": 1.2294137477874756,
+      "rewards/rejected": -1.029987096786499,
+      "step": 100
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 16.2526798248291,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.0951358824968338,
+      "logits/rejected": -0.08968516439199448,
+      "logps/chosen": -81.79414367675781,
+      "logps/rejected": -89.765625,
+      "loss": 0.4725,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.15804192423820496,
+      "rewards/margins": 1.7332594394683838,
+      "rewards/rejected": -1.891301155090332,
+      "step": 105
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 15.710427284240723,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.027723263949155807,
+      "logits/rejected": -0.01763475313782692,
+      "logps/chosen": -37.25303649902344,
+      "logps/rejected": -52.58305740356445,
+      "loss": 0.5258,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.01768249273300171,
+      "rewards/margins": 0.608422577381134,
+      "rewards/rejected": -0.626105010509491,
+      "step": 110
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 16.18587303161621,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.09127525985240936,
+      "logits/rejected": -0.08952955901622772,
+      "logps/chosen": -51.15592956542969,
+      "logps/rejected": -61.84421920776367,
+      "loss": 0.446,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.43013912439346313,
+      "rewards/margins": 1.3957525491714478,
+      "rewards/rejected": -0.9656132459640503,
+      "step": 115
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 12.457794189453125,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.0474393330514431,
+      "logits/rejected": -0.04658551886677742,
+      "logps/chosen": -58.86711883544922,
+      "logps/rejected": -64.27616119384766,
+      "loss": 0.4365,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.10293619334697723,
+      "rewards/margins": 1.2258039712905884,
+      "rewards/rejected": -1.1228678226470947,
+      "step": 120
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 16.62484359741211,
+      "learning_rate": 1e-06,
+      "logits/chosen": 0.0391828715801239,
+      "logits/rejected": 0.059719525277614594,
+      "logps/chosen": -91.99595642089844,
+      "logps/rejected": -112.70484924316406,
+      "loss": 0.4484,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.5286062955856323,
+      "rewards/margins": 2.0147881507873535,
+      "rewards/rejected": -2.5433950424194336,
+      "step": 125
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 12.6619873046875,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.0015835389494895935,
+      "logits/rejected": 0.004649341106414795,
+      "logps/chosen": -76.80113220214844,
+      "logps/rejected": -89.04924774169922,
+      "loss": 0.4096,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.28463220596313477,
+      "rewards/margins": 1.117056131362915,
+      "rewards/rejected": -1.4016883373260498,
+      "step": 130
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 16.22713279724121,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.10093293339014053,
+      "logits/rejected": -0.0960889607667923,
+      "logps/chosen": -78.48757934570312,
+      "logps/rejected": -96.75239562988281,
+      "loss": 0.4776,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.07072822749614716,
+      "rewards/margins": 1.4200364351272583,
+      "rewards/rejected": -1.4907647371292114,
+      "step": 135
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 15.163298606872559,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.08841624110937119,
+      "logits/rejected": -0.0812966376543045,
+      "logps/chosen": -49.91742706298828,
+      "logps/rejected": -54.39896774291992,
+      "loss": 0.4361,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.10890891402959824,
+      "rewards/margins": 1.1275047063827515,
+      "rewards/rejected": -1.2364134788513184,
+      "step": 140
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 13.627829551696777,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.07901357114315033,
+      "logits/rejected": -0.07952677458524704,
+      "logps/chosen": -58.6712760925293,
+      "logps/rejected": -60.3519287109375,
+      "loss": 0.4263,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 0.07741154730319977,
+      "rewards/margins": 0.6744439005851746,
+      "rewards/rejected": -0.5970323085784912,
+      "step": 145
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 14.12767505645752,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.07844635099172592,
+      "logits/rejected": -0.07670246064662933,
+      "logps/chosen": -79.21514892578125,
+      "logps/rejected": -95.0439682006836,
+      "loss": 0.3984,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.20406706631183624,
+      "rewards/margins": 1.3347957134246826,
+      "rewards/rejected": -1.538862705230713,
+      "step": 150
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 10.027976989746094,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.0394299291074276,
+      "logits/rejected": -0.037283238023519516,
+      "logps/chosen": -59.8607177734375,
+      "logps/rejected": -90.07058715820312,
+      "loss": 0.3387,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.25796985626220703,
+      "rewards/margins": 2.074141263961792,
+      "rewards/rejected": -1.816171646118164,
+      "step": 155
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 12.08365535736084,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.10505978763103485,
+      "logits/rejected": -0.09901513159275055,
+      "logps/chosen": -47.506202697753906,
+      "logps/rejected": -67.22758483886719,
+      "loss": 0.4439,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.07217444479465485,
+      "rewards/margins": 1.0274462699890137,
+      "rewards/rejected": -0.9552720189094543,
+      "step": 160
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 10.322546005249023,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.034024275839328766,
+      "logits/rejected": -0.03133025020360947,
+      "logps/chosen": -58.316184997558594,
+      "logps/rejected": -66.901123046875,
+      "loss": 0.4655,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.07615742832422256,
+      "rewards/margins": 0.675209641456604,
+      "rewards/rejected": -0.7513669729232788,
+      "step": 165
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 12.919961929321289,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.007387078367173672,
+      "logits/rejected": -0.0006680100923404098,
+      "logps/chosen": -66.50263977050781,
+      "logps/rejected": -88.05205535888672,
+      "loss": 0.4127,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.3587184250354767,
+      "rewards/margins": 1.6810741424560547,
+      "rewards/rejected": -2.039792537689209,
+      "step": 170
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 14.320988655090332,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.0416673943400383,
+      "logits/rejected": -0.03895064815878868,
+      "logps/chosen": -60.38318634033203,
+      "logps/rejected": -73.31221008300781,
+      "loss": 0.3713,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.043798673897981644,
+      "rewards/margins": 1.690246343612671,
+      "rewards/rejected": -1.646447777748108,
+      "step": 175
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.279186248779297,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.011715270578861237,
+      "logits/rejected": 0.005149384029209614,
+      "logps/chosen": -76.2380599975586,
+      "logps/rejected": -107.5550308227539,
+      "loss": 0.3898,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.13200218975543976,
+      "rewards/margins": 2.5765540599823,
+      "rewards/rejected": -2.7085559368133545,
+      "step": 180
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 11.731532096862793,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.11099245399236679,
+      "logits/rejected": -0.10901761054992676,
+      "logps/chosen": -63.856910705566406,
+      "logps/rejected": -63.48603439331055,
+      "loss": 0.369,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.09118829667568207,
+      "rewards/margins": 1.6201965808868408,
+      "rewards/rejected": -1.529008150100708,
+      "step": 185
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 9.0255765914917,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.04720262438058853,
+      "logits/rejected": -0.05262360721826553,
+      "logps/chosen": -59.25706100463867,
+      "logps/rejected": -85.06912994384766,
+      "loss": 0.353,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 0.4835248589515686,
+      "rewards/margins": 1.9951941967010498,
+      "rewards/rejected": -1.5116695165634155,
+      "step": 190
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 5.959653377532959,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.041944488883018494,
+      "logits/rejected": -0.020493442192673683,
+      "logps/chosen": -51.811729431152344,
+      "logps/rejected": -80.3885726928711,
+      "loss": 0.2245,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.6860127449035645,
+      "rewards/margins": 1.6832406520843506,
+      "rewards/rejected": -0.9972278475761414,
+      "step": 195
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 5.370494365692139,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.13854077458381653,
+      "logits/rejected": -0.1376122683286667,
+      "logps/chosen": -45.62406921386719,
+      "logps/rejected": -66.38761901855469,
+      "loss": 0.2236,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 0.5624949932098389,
+      "rewards/margins": 2.370830535888672,
+      "rewards/rejected": -1.808335542678833,
+      "step": 200
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 11.40556812286377,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.03235360607504845,
+      "logits/rejected": -0.026641175150871277,
+      "logps/chosen": -77.10560607910156,
+      "logps/rejected": -116.6834716796875,
+      "loss": 0.198,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.003305965568870306,
+      "rewards/margins": 2.9688169956207275,
+      "rewards/rejected": -2.97212290763855,
+      "step": 205
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 6.852243423461914,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.08796464651823044,
+      "logits/rejected": -0.08174140751361847,
+      "logps/chosen": -63.3108024597168,
+      "logps/rejected": -100.68711853027344,
+      "loss": 0.2087,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.06613560020923615,
+      "rewards/margins": 3.523066759109497,
+      "rewards/rejected": -3.5892021656036377,
+      "step": 210
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 3.7613370418548584,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.18352393805980682,
+      "logits/rejected": -0.1822497546672821,
+      "logps/chosen": -73.46556091308594,
+      "logps/rejected": -111.50262451171875,
+      "loss": 0.1781,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.06992371380329132,
+      "rewards/margins": 3.4505341053009033,
+      "rewards/rejected": -3.380610704421997,
+      "step": 215
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 10.82043743133545,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.0707927718758583,
+      "logits/rejected": -0.06452594697475433,
+      "logps/chosen": -74.3930435180664,
+      "logps/rejected": -109.25379943847656,
+      "loss": 0.1996,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.5582473874092102,
+      "rewards/margins": 2.8837478160858154,
+      "rewards/rejected": -3.4419949054718018,
+      "step": 220
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 13.249909400939941,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.15726926922798157,
+      "logits/rejected": -0.15615758299827576,
+      "logps/chosen": -84.48081970214844,
+      "logps/rejected": -106.8475341796875,
+      "loss": 0.2885,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.2800536155700684,
+      "rewards/margins": 2.9067673683166504,
+      "rewards/rejected": -4.186820983886719,
+      "step": 225
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 8.66231918334961,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.15227961540222168,
+      "logits/rejected": -0.14247794449329376,
+      "logps/chosen": -77.54243469238281,
+      "logps/rejected": -116.9886474609375,
+      "loss": 0.2311,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.4163047671318054,
+      "rewards/margins": 3.9100730419158936,
+      "rewards/rejected": -4.32637882232666,
+      "step": 230
+    },
+    {
+      "epoch": 1.2533333333333334,
+      "grad_norm": 4.258462905883789,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.14345099031925201,
+      "logits/rejected": -0.1368933767080307,
+      "logps/chosen": -41.03181457519531,
+      "logps/rejected": -74.01554107666016,
+      "loss": 0.2209,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.6364781260490417,
+      "rewards/margins": 3.3563053607940674,
+      "rewards/rejected": -2.71982741355896,
+      "step": 235
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 8.00922679901123,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.13605789840221405,
+      "logits/rejected": -0.13225141167640686,
+      "logps/chosen": -45.99299621582031,
+      "logps/rejected": -70.01762390136719,
+      "loss": 0.2223,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 0.18717975914478302,
+      "rewards/margins": 2.5417323112487793,
+      "rewards/rejected": -2.3545525074005127,
+      "step": 240
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 6.644509792327881,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.05485178157687187,
+      "logits/rejected": -0.032927896827459335,
+      "logps/chosen": -78.5289306640625,
+      "logps/rejected": -105.24593353271484,
+      "loss": 0.1938,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.4212195873260498,
+      "rewards/margins": 3.12190580368042,
+      "rewards/rejected": -3.5431251525878906,
+      "step": 245
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 6.512491703033447,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.08749254047870636,
+      "logits/rejected": -0.08491937816143036,
+      "logps/chosen": -79.62251281738281,
+      "logps/rejected": -112.38929748535156,
+      "loss": 0.1805,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.7281423807144165,
+      "rewards/margins": 2.684180736541748,
+      "rewards/rejected": -3.412322998046875,
+      "step": 250
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 7.965065002441406,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.0565565750002861,
+      "logits/rejected": -0.05955087020993233,
+      "logps/chosen": -77.64044952392578,
+      "logps/rejected": -106.85416412353516,
+      "loss": 0.2022,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.5686990022659302,
+      "rewards/margins": 3.395534038543701,
+      "rewards/rejected": -3.9642326831817627,
+      "step": 255
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 8.91444206237793,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.1623281091451645,
+      "logits/rejected": -0.15568025410175323,
+      "logps/chosen": -76.49116516113281,
+      "logps/rejected": -105.77110290527344,
+      "loss": 0.2286,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.6722622513771057,
+      "rewards/margins": 3.6157422065734863,
+      "rewards/rejected": -4.288004398345947,
+      "step": 260
+    },
+    {
+      "epoch": 1.4133333333333333,
+      "grad_norm": 3.856618642807007,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.14635060727596283,
+      "logits/rejected": -0.14141127467155457,
+      "logps/chosen": -73.30412292480469,
+      "logps/rejected": -102.57535552978516,
+      "loss": 0.1777,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.15799687802791595,
+      "rewards/margins": 3.1063895225524902,
+      "rewards/rejected": -3.2643864154815674,
+      "step": 265
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 9.558956146240234,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.16010445356369019,
+      "logits/rejected": -0.16003289818763733,
+      "logps/chosen": -83.60963439941406,
+      "logps/rejected": -108.95814514160156,
+      "loss": 0.1934,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.03610507398843765,
+      "rewards/margins": 3.566607713699341,
+      "rewards/rejected": -3.602712631225586,
+      "step": 270
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 14.296300888061523,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.19041122496128082,
+      "logits/rejected": -0.19675543904304504,
+      "logps/chosen": -86.94904327392578,
+      "logps/rejected": -108.98336029052734,
+      "loss": 0.2672,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.45788565278053284,
+      "rewards/margins": 2.7378134727478027,
+      "rewards/rejected": -3.195699453353882,
+      "step": 275
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 11.429224967956543,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2332134246826172,
+      "logits/rejected": -0.22619101405143738,
+      "logps/chosen": -41.212432861328125,
+      "logps/rejected": -63.74433517456055,
+      "loss": 0.3017,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.22647647559642792,
+      "rewards/margins": 2.678001880645752,
+      "rewards/rejected": -2.4515256881713867,
+      "step": 280
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 15.175474166870117,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.1731823831796646,
+      "logits/rejected": -0.17582915723323822,
+      "logps/chosen": -55.227027893066406,
+      "logps/rejected": -78.37431335449219,
+      "loss": 0.2917,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.3550594449043274,
+      "rewards/margins": 2.29359769821167,
+      "rewards/rejected": -2.6486573219299316,
+      "step": 285
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 9.650674819946289,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.1489884853363037,
+      "logits/rejected": -0.14982970058918,
+      "logps/chosen": -58.45500564575195,
+      "logps/rejected": -91.8953857421875,
+      "loss": 0.1967,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.3005248010158539,
+      "rewards/margins": 3.695702314376831,
+      "rewards/rejected": -3.3951778411865234,
+      "step": 290
+    },
+    {
+      "epoch": 1.5733333333333333,
+      "grad_norm": 6.528473854064941,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.1766640692949295,
+      "logits/rejected": -0.17292292416095734,
+      "logps/chosen": -56.97791290283203,
+      "logps/rejected": -85.62743377685547,
+      "loss": 0.2127,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.12213984876871109,
+      "rewards/margins": 2.8668904304504395,
+      "rewards/rejected": -2.744750499725342,
+      "step": 295
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 10.14043140411377,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.19708013534545898,
+      "logits/rejected": -0.18595156073570251,
+      "logps/chosen": -54.1507453918457,
+      "logps/rejected": -79.53749084472656,
+      "loss": 0.2324,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 0.12599337100982666,
+      "rewards/margins": 2.579333543777466,
+      "rewards/rejected": -2.4533400535583496,
+      "step": 300
+    },
+    {
+      "epoch": 1.6266666666666667,
+      "grad_norm": 8.498900413513184,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.17206253111362457,
+      "logits/rejected": -0.15581965446472168,
+      "logps/chosen": -72.01545715332031,
+      "logps/rejected": -153.42544555664062,
+      "loss": 0.1785,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.38456493616104126,
+      "rewards/margins": 4.787345886230469,
+      "rewards/rejected": -5.171910762786865,
+      "step": 305
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 16.62505340576172,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2148733139038086,
+      "logits/rejected": -0.2032153606414795,
+      "logps/chosen": -62.933837890625,
+      "logps/rejected": -106.54484558105469,
+      "loss": 0.1895,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.18351763486862183,
+      "rewards/margins": 3.5239806175231934,
+      "rewards/rejected": -3.707498550415039,
+      "step": 310
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 11.589250564575195,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.21502284705638885,
+      "logits/rejected": -0.1963229775428772,
+      "logps/chosen": -80.04829406738281,
+      "logps/rejected": -141.29750061035156,
+      "loss": 0.1646,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.9600610733032227,
+      "rewards/margins": 4.689765930175781,
+      "rewards/rejected": -5.649827003479004,
+      "step": 315
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 10.770737648010254,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.24441838264465332,
+      "logits/rejected": -0.2412232607603073,
+      "logps/chosen": -86.85003662109375,
+      "logps/rejected": -106.89388275146484,
+      "loss": 0.2171,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.8239480257034302,
+      "rewards/margins": 3.0451276302337646,
+      "rewards/rejected": -3.8690757751464844,
+      "step": 320
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 12.021537780761719,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2027956247329712,
+      "logits/rejected": -0.19365160167217255,
+      "logps/chosen": -83.82646179199219,
+      "logps/rejected": -117.0644302368164,
+      "loss": 0.2087,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.9700089693069458,
+      "rewards/margins": 3.3046371936798096,
+      "rewards/rejected": -4.274645805358887,
+      "step": 325
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 16.727617263793945,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2380843162536621,
+      "logits/rejected": -0.23556020855903625,
+      "logps/chosen": -85.53111267089844,
+      "logps/rejected": -136.96200561523438,
+      "loss": 0.19,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.7303121089935303,
+      "rewards/margins": 4.339911460876465,
+      "rewards/rejected": -5.070223808288574,
+      "step": 330
+    },
+    {
+      "epoch": 1.7866666666666666,
+      "grad_norm": 8.647014617919922,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2260773628950119,
+      "logits/rejected": -0.22472091019153595,
+      "logps/chosen": -70.34246063232422,
+      "logps/rejected": -130.5174560546875,
+      "loss": 0.1145,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.8340579271316528,
+      "rewards/margins": 4.325329780578613,
+      "rewards/rejected": -5.159387588500977,
+      "step": 335
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 13.704692840576172,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.19743473827838898,
+      "logits/rejected": -0.18280264735221863,
+      "logps/chosen": -92.22306060791016,
+      "logps/rejected": -126.66398620605469,
+      "loss": 0.1549,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.9958213567733765,
+      "rewards/margins": 3.9418296813964844,
+      "rewards/rejected": -4.937651634216309,
+      "step": 340
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 9.447907447814941,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.23114176094532013,
+      "logits/rejected": -0.22814705967903137,
+      "logps/chosen": -73.06866455078125,
+      "logps/rejected": -92.7379150390625,
+      "loss": 0.2321,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.1413997858762741,
+      "rewards/margins": 3.44819974899292,
+      "rewards/rejected": -3.589600086212158,
+      "step": 345
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 13.660387992858887,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2316075563430786,
+      "logits/rejected": -0.2243129014968872,
+      "logps/chosen": -40.69365692138672,
+      "logps/rejected": -77.8421630859375,
+      "loss": 0.1929,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -0.2429409772157669,
+      "rewards/margins": 3.414602756500244,
+      "rewards/rejected": -3.657543659210205,
+      "step": 350
+    },
+    {
+      "epoch": 1.8933333333333333,
+      "grad_norm": 7.376171588897705,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.24942800402641296,
+      "logits/rejected": -0.24522526562213898,
+      "logps/chosen": -72.5764389038086,
+      "logps/rejected": -108.04423522949219,
+      "loss": 0.1523,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.38573572039604187,
+      "rewards/margins": 3.300957441329956,
+      "rewards/rejected": -3.6866931915283203,
+      "step": 355
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 14.980485916137695,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.22098588943481445,
+      "logits/rejected": -0.20870821177959442,
+      "logps/chosen": -70.51148986816406,
+      "logps/rejected": -113.34062194824219,
+      "loss": 0.1941,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.5927928686141968,
+      "rewards/margins": 3.418287754058838,
+      "rewards/rejected": -4.011080741882324,
+      "step": 360
+    },
+    {
+      "epoch": 1.9466666666666668,
+      "grad_norm": 7.132907390594482,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.27342313528060913,
+      "logits/rejected": -0.26478415727615356,
+      "logps/chosen": -91.9891586303711,
+      "logps/rejected": -129.16757202148438,
+      "loss": 0.174,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -1.369034767150879,
+      "rewards/margins": 4.006806373596191,
+      "rewards/rejected": -5.37584114074707,
+      "step": 365
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 11.890949249267578,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.23843975365161896,
+      "logits/rejected": -0.2383933812379837,
+      "logps/chosen": -74.76898956298828,
+      "logps/rejected": -107.2107162475586,
+      "loss": 0.2254,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.747979462146759,
+      "rewards/margins": 3.267796277999878,
+      "rewards/rejected": -4.015775680541992,
+      "step": 370
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 17.679744720458984,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.16960373520851135,
+      "logits/rejected": -0.17325231432914734,
+      "logps/chosen": -105.846435546875,
+      "logps/rejected": -122.9857406616211,
+      "loss": 0.2049,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -1.8144283294677734,
+      "rewards/margins": 3.5779411792755127,
+      "rewards/rejected": -5.392369270324707,
+      "step": 375
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 6.943394184112549,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2742716670036316,
+      "logits/rejected": -0.26814788579940796,
+      "logps/chosen": -66.23405456542969,
+      "logps/rejected": -103.7399673461914,
+      "loss": 0.0704,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.8214471936225891,
+      "rewards/margins": 4.027198791503906,
+      "rewards/rejected": -4.8486456871032715,
+      "step": 380
+    },
+    {
+      "epoch": 2.0533333333333332,
+      "grad_norm": 3.1160390377044678,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.30924856662750244,
+      "logits/rejected": -0.29427191615104675,
+      "logps/chosen": -50.3244743347168,
+      "logps/rejected": -112.04768371582031,
+      "loss": 0.0837,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.8333573341369629,
+      "rewards/margins": 4.71429967880249,
+      "rewards/rejected": -5.547657012939453,
+      "step": 385
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.3047380447387695,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.25628188252449036,
+      "logits/rejected": -0.24855029582977295,
+      "logps/chosen": -86.0821533203125,
+      "logps/rejected": -138.10360717773438,
+      "loss": 0.1163,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.7257312536239624,
+      "rewards/margins": 4.333987236022949,
+      "rewards/rejected": -6.059718608856201,
+      "step": 390
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "grad_norm": 4.764650344848633,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.1932232677936554,
+      "logits/rejected": -0.19700609147548676,
+      "logps/chosen": -78.89598083496094,
+      "logps/rejected": -130.88352966308594,
+      "loss": 0.0877,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.0742863416671753,
+      "rewards/margins": 4.378272533416748,
+      "rewards/rejected": -5.452559471130371,
+      "step": 395
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 4.10252046585083,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.27843141555786133,
+      "logits/rejected": -0.2746765911579132,
+      "logps/chosen": -76.2488784790039,
+      "logps/rejected": -127.501220703125,
+      "loss": 0.0918,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.9270022511482239,
+      "rewards/margins": 5.307347297668457,
+      "rewards/rejected": -6.234349727630615,
+      "step": 400
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 7.236265659332275,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.31720614433288574,
+      "logits/rejected": -0.3048458695411682,
+      "logps/chosen": -76.51472473144531,
+      "logps/rejected": -135.60202026367188,
+      "loss": 0.0616,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.512957215309143,
+      "rewards/margins": 6.148130416870117,
+      "rewards/rejected": -7.6610870361328125,
+      "step": 405
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 2.3235349655151367,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.24595189094543457,
+      "logits/rejected": -0.24323758482933044,
+      "logps/chosen": -94.84211730957031,
+      "logps/rejected": -145.022216796875,
+      "loss": 0.0961,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.402531385421753,
+      "rewards/margins": 5.436099052429199,
+      "rewards/rejected": -7.838630676269531,
+      "step": 410
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 4.8239874839782715,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2481319159269333,
+      "logits/rejected": -0.25086286664009094,
+      "logps/chosen": -83.86447143554688,
+      "logps/rejected": -130.08944702148438,
+      "loss": 0.0767,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -2.552152395248413,
+      "rewards/margins": 5.058899879455566,
+      "rewards/rejected": -7.611052513122559,
+      "step": 415
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 10.188889503479004,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2911505699157715,
+      "logits/rejected": -0.2887571156024933,
+      "logps/chosen": -89.61388397216797,
+      "logps/rejected": -124.80122375488281,
+      "loss": 0.0954,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -2.090373992919922,
+      "rewards/margins": 4.806578636169434,
+      "rewards/rejected": -6.8969526290893555,
+      "step": 420
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 5.293187618255615,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.2788965106010437,
+      "logits/rejected": -0.2694849371910095,
+      "logps/chosen": -90.92457580566406,
+      "logps/rejected": -142.2576446533203,
+      "loss": 0.0733,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.9070699214935303,
+      "rewards/margins": 4.678387641906738,
+      "rewards/rejected": -6.585457801818848,
+      "step": 425
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 6.162081718444824,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3094247877597809,
+      "logits/rejected": -0.3067726492881775,
+      "logps/chosen": -101.09193420410156,
+      "logps/rejected": -136.2590789794922,
+      "loss": 0.1087,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -1.3400262594223022,
+      "rewards/margins": 4.651651859283447,
+      "rewards/rejected": -5.991677761077881,
+      "step": 430
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 5.37161111831665,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3167645335197449,
+      "logits/rejected": -0.30754679441452026,
+      "logps/chosen": -90.11158752441406,
+      "logps/rejected": -128.84521484375,
+      "loss": 0.07,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.3145698308944702,
+      "rewards/margins": 5.076085567474365,
+      "rewards/rejected": -6.390655517578125,
+      "step": 435
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 8.718563079833984,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3047015964984894,
+      "logits/rejected": -0.3067510724067688,
+      "logps/chosen": -76.70709991455078,
+      "logps/rejected": -124.02851867675781,
+      "loss": 0.1167,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -1.4980465173721313,
+      "rewards/margins": 4.969003677368164,
+      "rewards/rejected": -6.467051029205322,
+      "step": 440
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 3.066976547241211,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.32817643880844116,
+      "logits/rejected": -0.3236837387084961,
+      "logps/chosen": -119.95536804199219,
+      "logps/rejected": -168.2990264892578,
+      "loss": 0.0509,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.097543239593506,
+      "rewards/margins": 6.6215500831604,
+      "rewards/rejected": -8.719093322753906,
+      "step": 445
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 7.526630878448486,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.33517691493034363,
+      "logits/rejected": -0.3308143615722656,
+      "logps/chosen": -65.50419616699219,
+      "logps/rejected": -114.26656341552734,
+      "loss": 0.0958,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -1.0172278881072998,
+      "rewards/margins": 5.359133720397949,
+      "rewards/rejected": -6.376360893249512,
+      "step": 450
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 4.8166937828063965,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3010093867778778,
+      "logits/rejected": -0.29728105664253235,
+      "logps/chosen": -95.86582946777344,
+      "logps/rejected": -154.4734649658203,
+      "loss": 0.0702,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.552085280418396,
+      "rewards/margins": 5.720345973968506,
+      "rewards/rejected": -7.27243185043335,
+      "step": 455
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 2.3862478733062744,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.31689682602882385,
+      "logits/rejected": -0.31278690695762634,
+      "logps/chosen": -104.4582290649414,
+      "logps/rejected": -167.82778930664062,
+      "loss": 0.0756,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -1.952106237411499,
+      "rewards/margins": 6.5650482177734375,
+      "rewards/rejected": -8.517154693603516,
+      "step": 460
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.4673610925674438,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.33551472425460815,
+      "logits/rejected": -0.33083659410476685,
+      "logps/chosen": -87.67115783691406,
+      "logps/rejected": -160.4077911376953,
+      "loss": 0.0675,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -2.0451600551605225,
+      "rewards/margins": 6.929755210876465,
+      "rewards/rejected": -8.974915504455566,
+      "step": 465
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 5.761256217956543,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.30712994933128357,
+      "logits/rejected": -0.2985348701477051,
+      "logps/chosen": -75.22799682617188,
+      "logps/rejected": -119.52055358886719,
+      "loss": 0.0806,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -1.5171074867248535,
+      "rewards/margins": 4.610350608825684,
+      "rewards/rejected": -6.127457618713379,
+      "step": 470
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 2.6889760494232178,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3337317407131195,
+      "logits/rejected": -0.33648866415023804,
+      "logps/chosen": -84.6175765991211,
+      "logps/rejected": -114.95267486572266,
+      "loss": 0.0912,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.932594656944275,
+      "rewards/margins": 4.491971969604492,
+      "rewards/rejected": -6.424566745758057,
+      "step": 475
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 18.071474075317383,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3041028082370758,
+      "logits/rejected": -0.2970563471317291,
+      "logps/chosen": -99.09244537353516,
+      "logps/rejected": -154.91946411132812,
+      "loss": 0.1146,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.7287986278533936,
+      "rewards/margins": 6.216522693634033,
+      "rewards/rejected": -7.945321559906006,
+      "step": 480
+    },
+    {
+      "epoch": 2.586666666666667,
+      "grad_norm": 1.98813796043396,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3482723832130432,
+      "logits/rejected": -0.344726026058197,
+      "logps/chosen": -78.27327728271484,
+      "logps/rejected": -170.27120971679688,
+      "loss": 0.0872,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.34009051322937,
+      "rewards/margins": 6.879552364349365,
+      "rewards/rejected": -9.219643592834473,
+      "step": 485
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 14.037318229675293,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.32685285806655884,
+      "logits/rejected": -0.3174216151237488,
+      "logps/chosen": -90.9804916381836,
+      "logps/rejected": -159.81094360351562,
+      "loss": 0.1495,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -2.121194362640381,
+      "rewards/margins": 5.947864532470703,
+      "rewards/rejected": -8.069058418273926,
+      "step": 490
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 10.764850616455078,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3625045418739319,
+      "logits/rejected": -0.3534373342990875,
+      "logps/chosen": -66.63526153564453,
+      "logps/rejected": -135.00489807128906,
+      "loss": 0.0934,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.0588821172714233,
+      "rewards/margins": 6.410633087158203,
+      "rewards/rejected": -7.469515323638916,
+      "step": 495
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 7.240427494049072,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3743410110473633,
+      "logits/rejected": -0.3734128773212433,
+      "logps/chosen": -71.13905334472656,
+      "logps/rejected": -139.22691345214844,
+      "loss": 0.0534,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.7334591746330261,
+      "rewards/margins": 6.263424873352051,
+      "rewards/rejected": -6.996884346008301,
+      "step": 500
+    },
+    {
+      "epoch": 2.6933333333333334,
+      "grad_norm": 4.419618606567383,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.353333055973053,
+      "logits/rejected": -0.34663665294647217,
+      "logps/chosen": -88.02120971679688,
+      "logps/rejected": -138.94662475585938,
+      "loss": 0.0621,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -2.0562851428985596,
+      "rewards/margins": 5.7193145751953125,
+      "rewards/rejected": -7.775599479675293,
+      "step": 505
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 4.452930450439453,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.39688724279403687,
+      "logits/rejected": -0.3942062556743622,
+      "logps/chosen": -73.48619079589844,
+      "logps/rejected": -114.01251220703125,
+      "loss": 0.0936,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -1.882142424583435,
+      "rewards/margins": 4.740755081176758,
+      "rewards/rejected": -6.622898101806641,
+      "step": 510
+    },
+    {
+      "epoch": 2.7466666666666666,
+      "grad_norm": 6.147470474243164,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.36246275901794434,
+      "logits/rejected": -0.3594650328159332,
+      "logps/chosen": -75.21955871582031,
+      "logps/rejected": -138.40557861328125,
+      "loss": 0.0508,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.0342657566070557,
+      "rewards/margins": 6.567025184631348,
+      "rewards/rejected": -7.601290702819824,
+      "step": 515
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 5.928589820861816,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3479396104812622,
+      "logits/rejected": -0.33934539556503296,
+      "logps/chosen": -87.25235748291016,
+      "logps/rejected": -147.29940795898438,
+      "loss": 0.0882,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.92647385597229,
+      "rewards/margins": 6.275478839874268,
+      "rewards/rejected": -8.20195198059082,
+      "step": 520
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 8.153724670410156,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3809276819229126,
+      "logits/rejected": -0.37726661562919617,
+      "logps/chosen": -88.18365478515625,
+      "logps/rejected": -133.28257751464844,
+      "loss": 0.0715,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.543839693069458,
+      "rewards/margins": 6.156442165374756,
+      "rewards/rejected": -7.700281620025635,
+      "step": 525
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 7.274991512298584,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.39806967973709106,
+      "logits/rejected": -0.39120930433273315,
+      "logps/chosen": -80.41667938232422,
+      "logps/rejected": -145.32870483398438,
+      "loss": 0.0849,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.581139326095581,
+      "rewards/margins": 6.18198299407959,
+      "rewards/rejected": -7.76312255859375,
+      "step": 530
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 6.882216453552246,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3769987225532532,
+      "logits/rejected": -0.37087202072143555,
+      "logps/chosen": -78.6170425415039,
+      "logps/rejected": -114.8215103149414,
+      "loss": 0.1168,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -1.4115530252456665,
+      "rewards/margins": 4.665685176849365,
+      "rewards/rejected": -6.077239036560059,
+      "step": 535
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 6.004029750823975,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.35111719369888306,
+      "logits/rejected": -0.3472958207130432,
+      "logps/chosen": -79.73258972167969,
+      "logps/rejected": -135.81594848632812,
+      "loss": 0.1653,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.9881089925765991,
+      "rewards/margins": 5.74216890335083,
+      "rewards/rejected": -7.730278015136719,
+      "step": 540
+    },
+    {
+      "epoch": 2.9066666666666667,
+      "grad_norm": 2.1099255084991455,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3623197674751282,
+      "logits/rejected": -0.35646793246269226,
+      "logps/chosen": -94.4450912475586,
+      "logps/rejected": -168.900146484375,
+      "loss": 0.0705,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -2.358279228210449,
+      "rewards/margins": 5.906458854675293,
+      "rewards/rejected": -8.264737129211426,
+      "step": 545
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 8.101237297058105,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3904687166213989,
+      "logits/rejected": -0.3798937499523163,
+      "logps/chosen": -81.44142150878906,
+      "logps/rejected": -130.85696411132812,
+      "loss": 0.0788,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -2.1261515617370605,
+      "rewards/margins": 5.361577987670898,
+      "rewards/rejected": -7.487729072570801,
+      "step": 550
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 10.77298641204834,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.3544600307941437,
+      "logits/rejected": -0.3497422933578491,
+      "logps/chosen": -75.84606170654297,
+      "logps/rejected": -137.5305938720703,
+      "loss": 0.093,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.848976492881775,
+      "rewards/margins": 6.227209568023682,
+      "rewards/rejected": -8.07618522644043,
+      "step": 555
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 1.2543996572494507,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.36508709192276,
+      "logits/rejected": -0.3570384979248047,
+      "logps/chosen": -79.93736267089844,
+      "logps/rejected": -145.72976684570312,
+      "loss": 0.0764,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -1.660933494567871,
+      "rewards/margins": 6.339797019958496,
+      "rewards/rejected": -8.000730514526367,
+      "step": 560
+    },
+    {
+      "epoch": 2.992,
+      "step": 561,
+      "total_flos": 0.0,
+      "train_loss": 0.2571469163073894,
+      "train_runtime": 1548.982,
+      "train_samples_per_second": 11.619,
+      "train_steps_per_second": 0.362
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 561,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ed4115701d95eedf70734ac8adb24a7f4a3b850b030816e75f57f0519ab73b
+size 5560