Training in progress, epoch 1, checkpoint

last-checkpoint/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

last-checkpoint/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "AmberYifan/Qwen2-7B-sft-ultrachat",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.46.3"
+}

last-checkpoint/global_step624/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f32dec8644917475925a0d13c9726a987e6b2f690f22f21fe5bf9d023010792
+size 30462473157

last-checkpoint/global_step624/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c0ede74301937dc1fdcb77a1ce8d86101f3375cf9d30fe0ccc1cf6a1e9b40d
+size 30462473157

last-checkpoint/global_step624/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854712bccaca1c43b5fd35ee6b541a9adac74b0febd8a9377325e524cab328db
+size 168021

last-checkpoint/global_step624/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385d9c31544da8e459feb453cc11443ff4ede677c002f848caa8c63c38005d58
+size 168021

last-checkpoint/latest

@@ -0,0 +1 @@
+global_step624

last-checkpoint/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20efe7c264677e0f9a5df6e20f636c9433a4a35e54826ee4551ee8e2d5361a7d
+size 4877660776

last-checkpoint/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5515a77b35ac7c222c11b7cabba7cf7bca932d998dbd3bdca7af8d42d3482afb
+size 4932751008

last-checkpoint/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:537f211f17ab9b613bdbc7b4104a2e970cb1c7c57c48b35d80bc4c023edf12ea
+size 4330865200

last-checkpoint/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07dd088742f531a5ddf67fb925ae2019eb87b14e1ab1c025b7011f361b3118d6
+size 1089994880

last-checkpoint/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b580656286e8a6f334aced7bdb46499a54f3bb95644a0167405da037afbd894d
+size 14768

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a763d1d109f11374f3725ac97283433a5c2264a51fd11d55a5af0441e79bbe2c
+size 14768

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7610a99e142b065e838a824430a3e077aa4e276737f2b127e167b9a68d475291
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "max_length": 1024,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "left",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,994 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0016025641025641025,
+      "grad_norm": 81.23951893705919,
+      "learning_rate": 2.6595744680851063e-09,
+      "logits/chosen": 0.1357421875,
+      "logits/rejected": -0.2060546875,
+      "logps/chosen": -336.0,
+      "logps/rejected": -346.0,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.016025641025641024,
+      "grad_norm": 86.32419393322078,
+      "learning_rate": 2.6595744680851062e-08,
+      "logits/chosen": -0.16015625,
+      "logits/rejected": -0.474609375,
+      "logps/chosen": -364.0,
+      "logps/rejected": -312.0,
+      "loss": 0.702,
+      "rewards/accuracies": 0.1527777761220932,
+      "rewards/chosen": -0.009033203125,
+      "rewards/margins": -0.01806640625,
+      "rewards/rejected": 0.009033203125,
+      "step": 10
+    },
+    {
+      "epoch": 0.03205128205128205,
+      "grad_norm": 100.77964496481692,
+      "learning_rate": 5.3191489361702123e-08,
+      "logits/chosen": -0.16796875,
+      "logits/rejected": -0.466796875,
+      "logps/chosen": -376.0,
+      "logps/rejected": -310.0,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.21250000596046448,
+      "rewards/chosen": -0.006561279296875,
+      "rewards/margins": -0.0021820068359375,
+      "rewards/rejected": -0.00439453125,
+      "step": 20
+    },
+    {
+      "epoch": 0.04807692307692308,
+      "grad_norm": 98.51227524666062,
+      "learning_rate": 7.978723404255319e-08,
+      "logits/chosen": -0.22265625,
+      "logits/rejected": -0.5234375,
+      "logps/chosen": -390.0,
+      "logps/rejected": -332.0,
+      "loss": 0.6834,
+      "rewards/accuracies": 0.3375000059604645,
+      "rewards/chosen": 0.0419921875,
+      "rewards/margins": 0.03515625,
+      "rewards/rejected": 0.00689697265625,
+      "step": 30
+    },
+    {
+      "epoch": 0.0641025641025641,
+      "grad_norm": 73.06116455998657,
+      "learning_rate": 1.0638297872340425e-07,
+      "logits/chosen": -0.23828125,
+      "logits/rejected": -0.4296875,
+      "logps/chosen": -370.0,
+      "logps/rejected": -304.0,
+      "loss": 0.6555,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": 0.142578125,
+      "rewards/margins": 0.09521484375,
+      "rewards/rejected": 0.046875,
+      "step": 40
+    },
+    {
+      "epoch": 0.08012820512820513,
+      "grad_norm": 76.17217165247452,
+      "learning_rate": 1.329787234042553e-07,
+      "logits/chosen": -0.2421875,
+      "logits/rejected": -0.46875,
+      "logps/chosen": -382.0,
+      "logps/rejected": -302.0,
+      "loss": 0.6393,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.2578125,
+      "rewards/margins": 0.177734375,
+      "rewards/rejected": 0.07958984375,
+      "step": 50
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "grad_norm": 61.759030001028826,
+      "learning_rate": 1.5957446808510638e-07,
+      "logits/chosen": -0.0164794921875,
+      "logits/rejected": -0.291015625,
+      "logps/chosen": -358.0,
+      "logps/rejected": -306.0,
+      "loss": 0.6168,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.376953125,
+      "rewards/margins": 0.2255859375,
+      "rewards/rejected": 0.15234375,
+      "step": 60
+    },
+    {
+      "epoch": 0.11217948717948718,
+      "grad_norm": 64.71686861478489,
+      "learning_rate": 1.8617021276595742e-07,
+      "logits/chosen": -0.283203125,
+      "logits/rejected": -0.50390625,
+      "logps/chosen": -396.0,
+      "logps/rejected": -292.0,
+      "loss": 0.5847,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.58203125,
+      "rewards/margins": 0.37890625,
+      "rewards/rejected": 0.201171875,
+      "step": 70
+    },
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 52.52316366702727,
+      "learning_rate": 2.127659574468085e-07,
+      "logits/chosen": -0.35546875,
+      "logits/rejected": -0.66796875,
+      "logps/chosen": -368.0,
+      "logps/rejected": -302.0,
+      "loss": 0.5555,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.6640625,
+      "rewards/margins": 0.484375,
+      "rewards/rejected": 0.1787109375,
+      "step": 80
+    },
+    {
+      "epoch": 0.14423076923076922,
+      "grad_norm": 59.670100120011845,
+      "learning_rate": 2.393617021276596e-07,
+      "logits/chosen": -0.251953125,
+      "logits/rejected": -0.55078125,
+      "logps/chosen": -388.0,
+      "logps/rejected": -312.0,
+      "loss": 0.539,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.8046875,
+      "rewards/margins": 0.5703125,
+      "rewards/rejected": 0.2353515625,
+      "step": 90
+    },
+    {
+      "epoch": 0.16025641025641027,
+      "grad_norm": 66.87233629909264,
+      "learning_rate": 2.659574468085106e-07,
+      "logits/chosen": -0.314453125,
+      "logits/rejected": -0.478515625,
+      "logps/chosen": -346.0,
+      "logps/rejected": -324.0,
+      "loss": 0.4916,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.85546875,
+      "rewards/margins": 0.48046875,
+      "rewards/rejected": 0.373046875,
+      "step": 100
+    },
+    {
+      "epoch": 0.1762820512820513,
+      "grad_norm": 53.961384431262026,
+      "learning_rate": 2.925531914893617e-07,
+      "logits/chosen": -0.294921875,
+      "logits/rejected": -0.65625,
+      "logps/chosen": -386.0,
+      "logps/rejected": -306.0,
+      "loss": 0.5006,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.9140625,
+      "rewards/margins": 0.640625,
+      "rewards/rejected": 0.275390625,
+      "step": 110
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 49.6732649258676,
+      "learning_rate": 3.1914893617021275e-07,
+      "logits/chosen": -0.298828125,
+      "logits/rejected": -0.40234375,
+      "logps/chosen": -388.0,
+      "logps/rejected": -308.0,
+      "loss": 0.4499,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.1171875,
+      "rewards/margins": 0.82421875,
+      "rewards/rejected": 0.29296875,
+      "step": 120
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 52.819440458631206,
+      "learning_rate": 3.457446808510638e-07,
+      "logits/chosen": -0.1591796875,
+      "logits/rejected": -0.28515625,
+      "logps/chosen": -374.0,
+      "logps/rejected": -280.0,
+      "loss": 0.4087,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.3671875,
+      "rewards/margins": 1.203125,
+      "rewards/rejected": 0.16015625,
+      "step": 130
+    },
+    {
+      "epoch": 0.22435897435897437,
+      "grad_norm": 45.055792147900604,
+      "learning_rate": 3.7234042553191484e-07,
+      "logits/chosen": -0.2177734375,
+      "logits/rejected": -0.380859375,
+      "logps/chosen": -364.0,
+      "logps/rejected": -300.0,
+      "loss": 0.4263,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 1.328125,
+      "rewards/margins": 1.1640625,
+      "rewards/rejected": 0.1650390625,
+      "step": 140
+    },
+    {
+      "epoch": 0.2403846153846154,
+      "grad_norm": 37.20442727443192,
+      "learning_rate": 3.989361702127659e-07,
+      "logits/chosen": -0.208984375,
+      "logits/rejected": -0.421875,
+      "logps/chosen": -392.0,
+      "logps/rejected": -310.0,
+      "loss": 0.4273,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 1.3671875,
+      "rewards/margins": 1.265625,
+      "rewards/rejected": 0.10205078125,
+      "step": 150
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 67.23258640755056,
+      "learning_rate": 4.25531914893617e-07,
+      "logits/chosen": -0.1416015625,
+      "logits/rejected": -0.365234375,
+      "logps/chosen": -380.0,
+      "logps/rejected": -322.0,
+      "loss": 0.3995,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.1484375,
+      "rewards/margins": 1.1953125,
+      "rewards/rejected": -0.047119140625,
+      "step": 160
+    },
+    {
+      "epoch": 0.2724358974358974,
+      "grad_norm": 76.82700510564892,
+      "learning_rate": 4.5212765957446806e-07,
+      "logits/chosen": -0.1376953125,
+      "logits/rejected": -0.42578125,
+      "logps/chosen": -360.0,
+      "logps/rejected": -312.0,
+      "loss": 0.4255,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 1.1171875,
+      "rewards/margins": 1.125,
+      "rewards/rejected": -0.0093994140625,
+      "step": 170
+    },
+    {
+      "epoch": 0.28846153846153844,
+      "grad_norm": 57.73247757369804,
+      "learning_rate": 4.787234042553192e-07,
+      "logits/chosen": -0.083984375,
+      "logits/rejected": -0.1953125,
+      "logps/chosen": -368.0,
+      "logps/rejected": -316.0,
+      "loss": 0.3897,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 1.3125,
+      "rewards/margins": 1.328125,
+      "rewards/rejected": -0.01129150390625,
+      "step": 180
+    },
+    {
+      "epoch": 0.30448717948717946,
+      "grad_norm": 93.3245464788157,
+      "learning_rate": 4.994061757719714e-07,
+      "logits/chosen": -0.158203125,
+      "logits/rejected": -0.408203125,
+      "logps/chosen": -344.0,
+      "logps/rejected": -318.0,
+      "loss": 0.4427,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 1.3828125,
+      "rewards/margins": 1.515625,
+      "rewards/rejected": -0.130859375,
+      "step": 190
+    },
+    {
+      "epoch": 0.32051282051282054,
+      "grad_norm": 31.0057130908168,
+      "learning_rate": 4.96437054631829e-07,
+      "logits/chosen": -0.185546875,
+      "logits/rejected": -0.333984375,
+      "logps/chosen": -398.0,
+      "logps/rejected": -276.0,
+      "loss": 0.3853,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.2578125,
+      "rewards/margins": 1.5546875,
+      "rewards/rejected": -0.298828125,
+      "step": 200
+    },
+    {
+      "epoch": 0.33653846153846156,
+      "grad_norm": 31.866164526406457,
+      "learning_rate": 4.934679334916864e-07,
+      "logits/chosen": -0.134765625,
+      "logits/rejected": -0.427734375,
+      "logps/chosen": -372.0,
+      "logps/rejected": -334.0,
+      "loss": 0.2608,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.4375,
+      "rewards/margins": 1.703125,
+      "rewards/rejected": -0.267578125,
+      "step": 210
+    },
+    {
+      "epoch": 0.3525641025641026,
+      "grad_norm": 26.376971522466825,
+      "learning_rate": 4.904988123515439e-07,
+      "logits/chosen": -0.0673828125,
+      "logits/rejected": -0.150390625,
+      "logps/chosen": -392.0,
+      "logps/rejected": -294.0,
+      "loss": 0.313,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 1.6796875,
+      "rewards/margins": 1.921875,
+      "rewards/rejected": -0.2451171875,
+      "step": 220
+    },
+    {
+      "epoch": 0.3685897435897436,
+      "grad_norm": 19.856366106787778,
+      "learning_rate": 4.875296912114014e-07,
+      "logits/chosen": -0.068359375,
+      "logits/rejected": -0.373046875,
+      "logps/chosen": -342.0,
+      "logps/rejected": -298.0,
+      "loss": 0.2838,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 1.46875,
+      "rewards/margins": 2.125,
+      "rewards/rejected": -0.65625,
+      "step": 230
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 55.84167138753407,
+      "learning_rate": 4.845605700712589e-07,
+      "logits/chosen": -0.12890625,
+      "logits/rejected": -0.443359375,
+      "logps/chosen": -368.0,
+      "logps/rejected": -322.0,
+      "loss": 0.2748,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 1.5546875,
+      "rewards/margins": 2.5,
+      "rewards/rejected": -0.953125,
+      "step": 240
+    },
+    {
+      "epoch": 0.40064102564102566,
+      "grad_norm": 37.23188688423797,
+      "learning_rate": 4.815914489311164e-07,
+      "logits/chosen": -0.1357421875,
+      "logits/rejected": -0.427734375,
+      "logps/chosen": -364.0,
+      "logps/rejected": -324.0,
+      "loss": 0.2543,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.6640625,
+      "rewards/margins": 2.734375,
+      "rewards/rejected": -1.0703125,
+      "step": 250
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 35.660892697083206,
+      "learning_rate": 4.786223277909738e-07,
+      "logits/chosen": -0.123046875,
+      "logits/rejected": -0.470703125,
+      "logps/chosen": -366.0,
+      "logps/rejected": -310.0,
+      "loss": 0.2583,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 1.1484375,
+      "rewards/margins": 2.375,
+      "rewards/rejected": -1.234375,
+      "step": 260
+    },
+    {
+      "epoch": 0.4326923076923077,
+      "grad_norm": 46.54757231137472,
+      "learning_rate": 4.756532066508313e-07,
+      "logits/chosen": -0.2021484375,
+      "logits/rejected": -0.328125,
+      "logps/chosen": -374.0,
+      "logps/rejected": -340.0,
+      "loss": 0.4125,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.1015625,
+      "rewards/margins": 1.9765625,
+      "rewards/rejected": -0.875,
+      "step": 270
+    },
+    {
+      "epoch": 0.44871794871794873,
+      "grad_norm": 37.544511359682254,
+      "learning_rate": 4.7268408551068883e-07,
+      "logits/chosen": 0.03857421875,
+      "logits/rejected": -0.54296875,
+      "logps/chosen": -384.0,
+      "logps/rejected": -342.0,
+      "loss": 0.2471,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 1.1796875,
+      "rewards/margins": 2.5,
+      "rewards/rejected": -1.3203125,
+      "step": 280
+    },
+    {
+      "epoch": 0.46474358974358976,
+      "grad_norm": 56.789270954370565,
+      "learning_rate": 4.697149643705463e-07,
+      "logits/chosen": -0.07958984375,
+      "logits/rejected": -0.29296875,
+      "logps/chosen": -348.0,
+      "logps/rejected": -328.0,
+      "loss": 0.297,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.4140625,
+      "rewards/margins": 2.46875,
+      "rewards/rejected": -1.0546875,
+      "step": 290
+    },
+    {
+      "epoch": 0.4807692307692308,
+      "grad_norm": 14.22992572113077,
+      "learning_rate": 4.667458432304038e-07,
+      "logits/chosen": -0.2021484375,
+      "logits/rejected": -0.388671875,
+      "logps/chosen": -372.0,
+      "logps/rejected": -322.0,
+      "loss": 0.2564,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.6796875,
+      "rewards/margins": 2.765625,
+      "rewards/rejected": -1.0859375,
+      "step": 300
+    },
+    {
+      "epoch": 0.4967948717948718,
+      "grad_norm": 36.87971897536812,
+      "learning_rate": 4.6377672209026127e-07,
+      "logits/chosen": -0.10888671875,
+      "logits/rejected": -0.412109375,
+      "logps/chosen": -390.0,
+      "logps/rejected": -330.0,
+      "loss": 0.1529,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 2.109375,
+      "rewards/margins": 3.328125,
+      "rewards/rejected": -1.2109375,
+      "step": 310
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 31.81729836940978,
+      "learning_rate": 4.6080760095011875e-07,
+      "logits/chosen": -0.154296875,
+      "logits/rejected": -0.35546875,
+      "logps/chosen": -374.0,
+      "logps/rejected": -304.0,
+      "loss": 0.26,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.859375,
+      "rewards/margins": 2.875,
+      "rewards/rejected": -1.0234375,
+      "step": 320
+    },
+    {
+      "epoch": 0.5288461538461539,
+      "grad_norm": 27.609497368983103,
+      "learning_rate": 4.578384798099763e-07,
+      "logits/chosen": -0.0849609375,
+      "logits/rejected": -0.515625,
+      "logps/chosen": -338.0,
+      "logps/rejected": -328.0,
+      "loss": 0.2903,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.6953125,
+      "rewards/margins": 2.859375,
+      "rewards/rejected": -1.171875,
+      "step": 330
+    },
+    {
+      "epoch": 0.5448717948717948,
+      "grad_norm": 65.37858577012295,
+      "learning_rate": 4.548693586698337e-07,
+      "logits/chosen": -0.11083984375,
+      "logits/rejected": -0.28125,
+      "logps/chosen": -382.0,
+      "logps/rejected": -338.0,
+      "loss": 0.3046,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 1.7421875,
+      "rewards/margins": 3.15625,
+      "rewards/rejected": -1.4140625,
+      "step": 340
+    },
+    {
+      "epoch": 0.5608974358974359,
+      "grad_norm": 53.122076726933024,
+      "learning_rate": 4.519002375296912e-07,
+      "logits/chosen": -0.1123046875,
+      "logits/rejected": -0.46875,
+      "logps/chosen": -370.0,
+      "logps/rejected": -358.0,
+      "loss": 0.3242,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 1.390625,
+      "rewards/margins": 2.765625,
+      "rewards/rejected": -1.375,
+      "step": 350
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 29.215237884321418,
+      "learning_rate": 4.4893111638954866e-07,
+      "logits/chosen": -0.267578125,
+      "logits/rejected": -0.3515625,
+      "logps/chosen": -380.0,
+      "logps/rejected": -324.0,
+      "loss": 0.1967,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.5390625,
+      "rewards/margins": 3.296875,
+      "rewards/rejected": -1.7578125,
+      "step": 360
+    },
+    {
+      "epoch": 0.592948717948718,
+      "grad_norm": 23.99951739667445,
+      "learning_rate": 4.4596199524940614e-07,
+      "logits/chosen": -0.24609375,
+      "logits/rejected": -0.376953125,
+      "logps/chosen": -392.0,
+      "logps/rejected": -328.0,
+      "loss": 0.2886,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 1.0234375,
+      "rewards/margins": 2.515625,
+      "rewards/rejected": -1.5,
+      "step": 370
+    },
+    {
+      "epoch": 0.6089743589743589,
+      "grad_norm": 73.48089183856715,
+      "learning_rate": 4.429928741092636e-07,
+      "logits/chosen": -0.1640625,
+      "logits/rejected": -0.443359375,
+      "logps/chosen": -378.0,
+      "logps/rejected": -346.0,
+      "loss": 0.2243,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.53125,
+      "rewards/margins": 3.125,
+      "rewards/rejected": -1.59375,
+      "step": 380
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 34.2482977900771,
+      "learning_rate": 4.4002375296912115e-07,
+      "logits/chosen": -0.109375,
+      "logits/rejected": -0.5625,
+      "logps/chosen": -382.0,
+      "logps/rejected": -344.0,
+      "loss": 0.1972,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.46875,
+      "rewards/margins": 3.09375,
+      "rewards/rejected": -1.6328125,
+      "step": 390
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "grad_norm": 46.4216688916151,
+      "learning_rate": 4.3705463182897863e-07,
+      "logits/chosen": -0.1435546875,
+      "logits/rejected": -0.3359375,
+      "logps/chosen": -372.0,
+      "logps/rejected": -340.0,
+      "loss": 0.2644,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.265625,
+      "rewards/margins": 3.796875,
+      "rewards/rejected": -1.53125,
+      "step": 400
+    },
+    {
+      "epoch": 0.657051282051282,
+      "grad_norm": 44.3943999019337,
+      "learning_rate": 4.340855106888361e-07,
+      "logits/chosen": -0.1494140625,
+      "logits/rejected": -0.53515625,
+      "logps/chosen": -368.0,
+      "logps/rejected": -334.0,
+      "loss": 0.3043,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.6640625,
+      "rewards/margins": 3.265625,
+      "rewards/rejected": -1.59375,
+      "step": 410
+    },
+    {
+      "epoch": 0.6730769230769231,
+      "grad_norm": 49.38538485619709,
+      "learning_rate": 4.311163895486936e-07,
+      "logits/chosen": -0.2451171875,
+      "logits/rejected": -0.353515625,
+      "logps/chosen": -374.0,
+      "logps/rejected": -332.0,
+      "loss": 0.2839,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.5546875,
+      "rewards/margins": 2.96875,
+      "rewards/rejected": -1.4140625,
+      "step": 420
+    },
+    {
+      "epoch": 0.6891025641025641,
+      "grad_norm": 52.14918805667079,
+      "learning_rate": 4.28147268408551e-07,
+      "logits/chosen": -0.142578125,
+      "logits/rejected": -0.265625,
+      "logps/chosen": -392.0,
+      "logps/rejected": -308.0,
+      "loss": 0.2573,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 1.71875,
+      "rewards/margins": 3.546875,
+      "rewards/rejected": -1.8359375,
+      "step": 430
+    },
+    {
+      "epoch": 0.7051282051282052,
+      "grad_norm": 41.67427154859993,
+      "learning_rate": 4.251781472684085e-07,
+      "logits/chosen": -0.2041015625,
+      "logits/rejected": -0.19140625,
+      "logps/chosen": -382.0,
+      "logps/rejected": -302.0,
+      "loss": 0.2207,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.9609375,
+      "rewards/margins": 2.921875,
+      "rewards/rejected": -0.96484375,
+      "step": 440
+    },
+    {
+      "epoch": 0.7211538461538461,
+      "grad_norm": 49.967389161188926,
+      "learning_rate": 4.22209026128266e-07,
+      "logits/chosen": -0.216796875,
+      "logits/rejected": -0.33984375,
+      "logps/chosen": -368.0,
+      "logps/rejected": -316.0,
+      "loss": 0.3459,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 1.46875,
+      "rewards/margins": 2.75,
+      "rewards/rejected": -1.28125,
+      "step": 450
+    },
+    {
+      "epoch": 0.7371794871794872,
+      "grad_norm": 45.29394404835159,
+      "learning_rate": 4.192399049881235e-07,
+      "logits/chosen": -0.259765625,
+      "logits/rejected": -0.462890625,
+      "logps/chosen": -392.0,
+      "logps/rejected": -334.0,
+      "loss": 0.2416,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.765625,
+      "rewards/margins": 3.296875,
+      "rewards/rejected": -1.53125,
+      "step": 460
+    },
+    {
+      "epoch": 0.7532051282051282,
+      "grad_norm": 49.65359950033634,
+      "learning_rate": 4.16270783847981e-07,
+      "logits/chosen": -0.09814453125,
+      "logits/rejected": -0.384765625,
+      "logps/chosen": -340.0,
+      "logps/rejected": -312.0,
+      "loss": 0.2871,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 2.25,
+      "rewards/margins": 3.34375,
+      "rewards/rejected": -1.09375,
+      "step": 470
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 34.79083088842419,
+      "learning_rate": 4.1330166270783846e-07,
+      "logits/chosen": -0.1796875,
+      "logits/rejected": -0.423828125,
+      "logps/chosen": -358.0,
+      "logps/rejected": -344.0,
+      "loss": 0.2121,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 1.453125,
+      "rewards/margins": 3.25,
+      "rewards/rejected": -1.8046875,
+      "step": 480
+    },
+    {
+      "epoch": 0.7852564102564102,
+      "grad_norm": 24.646692522257364,
+      "learning_rate": 4.1033254156769594e-07,
+      "logits/chosen": -0.1435546875,
+      "logits/rejected": -0.390625,
+      "logps/chosen": -360.0,
+      "logps/rejected": -332.0,
+      "loss": 0.2359,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 1.6640625,
+      "rewards/margins": 3.421875,
+      "rewards/rejected": -1.75,
+      "step": 490
+    },
+    {
+      "epoch": 0.8012820512820513,
+      "grad_norm": 32.88069299074813,
+      "learning_rate": 4.0736342042755347e-07,
+      "logits/chosen": -0.216796875,
+      "logits/rejected": -0.5390625,
+      "logps/chosen": -380.0,
+      "logps/rejected": -328.0,
+      "loss": 0.2243,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 0.9609375,
+      "rewards/margins": 2.90625,
+      "rewards/rejected": -1.9453125,
+      "step": 500
+    },
+    {
+      "epoch": 0.8173076923076923,
+      "grad_norm": 35.40990218888171,
+      "learning_rate": 4.0439429928741095e-07,
+      "logits/chosen": -0.173828125,
+      "logits/rejected": -0.302734375,
+      "logps/chosen": -388.0,
+      "logps/rejected": -320.0,
+      "loss": 0.2403,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.421875,
+      "rewards/margins": 3.203125,
+      "rewards/rejected": -1.78125,
+      "step": 510
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 45.40116394651564,
+      "learning_rate": 4.0142517814726837e-07,
+      "logits/chosen": -0.220703125,
+      "logits/rejected": -0.37109375,
+      "logps/chosen": -398.0,
+      "logps/rejected": -340.0,
+      "loss": 0.2562,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 1.4375,
+      "rewards/margins": 3.0,
+      "rewards/rejected": -1.5625,
+      "step": 520
+    },
+    {
+      "epoch": 0.8493589743589743,
+      "grad_norm": 38.39116264620735,
+      "learning_rate": 3.9845605700712585e-07,
+      "logits/chosen": -0.1953125,
+      "logits/rejected": -0.244140625,
+      "logps/chosen": -374.0,
+      "logps/rejected": -288.0,
+      "loss": 0.2727,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 1.3671875,
+      "rewards/margins": 3.046875,
+      "rewards/rejected": -1.6875,
+      "step": 530
+    },
+    {
+      "epoch": 0.8653846153846154,
+      "grad_norm": 47.38780960867294,
+      "learning_rate": 3.9548693586698333e-07,
+      "logits/chosen": -0.24609375,
+      "logits/rejected": -0.4140625,
+      "logps/chosen": -372.0,
+      "logps/rejected": -318.0,
+      "loss": 0.2017,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.9296875,
+      "rewards/margins": 3.421875,
+      "rewards/rejected": -1.4921875,
+      "step": 540
+    },
+    {
+      "epoch": 0.8814102564102564,
+      "grad_norm": 53.98621268772635,
+      "learning_rate": 3.925178147268408e-07,
+      "logits/chosen": -0.322265625,
+      "logits/rejected": -0.283203125,
+      "logps/chosen": -358.0,
+      "logps/rejected": -314.0,
+      "loss": 0.2358,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 2.078125,
+      "rewards/margins": 3.234375,
+      "rewards/rejected": -1.1640625,
+      "step": 550
+    },
+    {
+      "epoch": 0.8974358974358975,
+      "grad_norm": 57.737496610523515,
+      "learning_rate": 3.8954869358669834e-07,
+      "logits/chosen": -0.1767578125,
+      "logits/rejected": -0.271484375,
+      "logps/chosen": -384.0,
+      "logps/rejected": -332.0,
+      "loss": 0.2313,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 1.8125,
+      "rewards/margins": 3.203125,
+      "rewards/rejected": -1.3828125,
+      "step": 560
+    },
+    {
+      "epoch": 0.9134615384615384,
+      "grad_norm": 29.929989102081784,
+      "learning_rate": 3.865795724465558e-07,
+      "logits/chosen": -0.26171875,
+      "logits/rejected": -0.466796875,
+      "logps/chosen": -366.0,
+      "logps/rejected": -302.0,
+      "loss": 0.2186,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 2.0,
+      "rewards/margins": 3.78125,
+      "rewards/rejected": -1.78125,
+      "step": 570
+    },
+    {
+      "epoch": 0.9294871794871795,
+      "grad_norm": 14.744590527736637,
+      "learning_rate": 3.836104513064133e-07,
+      "logits/chosen": -0.30078125,
+      "logits/rejected": -0.46875,
+      "logps/chosen": -364.0,
+      "logps/rejected": -324.0,
+      "loss": 0.1895,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.84375,
+      "rewards/margins": 3.75,
+      "rewards/rejected": -1.9140625,
+      "step": 580
+    },
+    {
+      "epoch": 0.9455128205128205,
+      "grad_norm": 43.4367923218673,
+      "learning_rate": 3.806413301662708e-07,
+      "logits/chosen": -0.154296875,
+      "logits/rejected": -0.5,
+      "logps/chosen": -366.0,
+      "logps/rejected": -348.0,
+      "loss": 0.2121,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 1.625,
+      "rewards/margins": 3.546875,
+      "rewards/rejected": -1.9140625,
+      "step": 590
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 14.598190302159233,
+      "learning_rate": 3.7767220902612825e-07,
+      "logits/chosen": -0.21875,
+      "logits/rejected": -0.35546875,
+      "logps/chosen": -374.0,
+      "logps/rejected": -328.0,
+      "loss": 0.2134,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.4609375,
+      "rewards/margins": 3.59375,
+      "rewards/rejected": -2.140625,
+      "step": 600
+    },
+    {
+      "epoch": 0.9775641025641025,
+      "grad_norm": 65.50233470122603,
+      "learning_rate": 3.747030878859858e-07,
+      "logits/chosen": -0.09375,
+      "logits/rejected": -0.36328125,
+      "logps/chosen": -348.0,
+      "logps/rejected": -332.0,
+      "loss": 0.3465,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": 1.484375,
+      "rewards/margins": 3.65625,
+      "rewards/rejected": -2.171875,
+      "step": 610
+    },
+    {
+      "epoch": 0.9935897435897436,
+      "grad_norm": 45.476213003555294,
+      "learning_rate": 3.717339667458432e-07,
+      "logits/chosen": -0.158203125,
+      "logits/rejected": -0.439453125,
+      "logps/chosen": -364.0,
+      "logps/rejected": -330.0,
+      "loss": 0.2557,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 1.1796875,
+      "rewards/margins": 3.140625,
+      "rewards/rejected": -1.953125,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "eval_logits/chosen": -0.2333984375,
+      "eval_logits/rejected": -0.328125,
+      "eval_logps/chosen": -366.0,
+      "eval_logps/rejected": -340.0,
+      "eval_loss": 0.20789062976837158,
+      "eval_rewards/accuracies": 0.8942307829856873,
+      "eval_rewards/chosen": 1.5859375,
+      "eval_rewards/margins": 3.375,
+      "eval_rewards/rejected": -1.7890625,
+      "eval_runtime": 28.0659,
+      "eval_samples_per_second": 7.126,
+      "eval_steps_per_second": 0.463,
+      "step": 624
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1872,
+  "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": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6771fe05f94e8dee9401657cf45b9603a35c7f83acd44525536881165218188c
+size 7864

last-checkpoint/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)