Training in progress, step 300, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "openchat/openchat-3.6-8b-20240522",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "vocab_size": 128256
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.43.4"
+}

last-checkpoint/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e50774464ee1e9bf0260419c524c0d3e07c609faa5cc2fc334ec72a660acd18
+size 24090788996

last-checkpoint/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad2daf9401ae1c4dcdfd4843d872dc0ff43dc1f26cb6a8cb4e552a3040da02c
+size 24090788996

last-checkpoint/global_step300/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36adbd273ed47f23718fbfdf2b2fae5ca1fdcd7518dae3ae5c28d64fdc2ecd9
+size 24090788996

last-checkpoint/global_step300/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad810218018c18c8ef82a26916b20800f6126ab5724965c8efc3f69b9b48c27
+size 24090788996

last-checkpoint/global_step300/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35962fe7c35b72bc02535b2f3e55364e61e90ff5d78a1e0cd810f6eaa0b187e
+size 150693

last-checkpoint/global_step300/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9344d0f762e81aacc4934f2c585f8c8e99ac55af46fb3a3f6acc143e23885eef
+size 150693

last-checkpoint/global_step300/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47227164e1f2ff0bfd0b6acbbf057e83280ee67acde18ecb856ac35cc7e2fa5e
+size 150693

last-checkpoint/global_step300/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8df5ff2fe3451cfbb67c89358002ac0e9d420f7883359337c6fa520d92f71f8
+size 150693

last-checkpoint/latest

@@ -0,0 +1 @@
+global_step300

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52167d519851f9ca18383dcf927bbf332d4ca820555c360b991e3d8ba233df5f
+size 4976698672

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0217eb2e5e83b11a4cfe8a533c2fccf7de851ab8afdb1c3e7c5c3be5103c24
+size 4999802720

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d42a1488bb2337064ae7f742825a0d66fb30919db4d0219a0ab3f3925d7b2a5
+size 4915916176

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a9fa8aeecf4ffdb0a4c7091acfb23ed53525fd9f4aaa1f073244152c0ccf106
+size 1168138808

last-checkpoint/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-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-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.weight": "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-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-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.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.weight": "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-00002-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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.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.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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "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.weight": "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.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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70cc56408014c410353d4dd58ae9b03f4be043f5f800324f66fd8e20e99b840e
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d1438e98cc9c53a6852464635ce62e9788e61eb3646b73e33813f487c4b6ae
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4388add9cec90932f8ff0100d27a0574d98e1bad52ff89d44e31967d2b4fbfde
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a705d6dfaae4f2c1b4b2be6b25a6eb521ffae6fcba21cc1531e97b60037ed079
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70aea97e227d354a2e2f70f4cd68a16a7614edfe04ccb1a78d71b71f9b8e89a4
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] in ['user', 'assistant'] %}{% set content = '<|start_header_id|>GPT4 Correct ' + message['role'].title() + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' %}{% elif message['role'] == 'system' %}{% set content = '<|start_header_id|>System<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' %}{% else %}{{ raise_exception('Only user, assistant and system roles are supported!') }}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>GPT4 Correct Assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,2331 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.34604570687044917,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0023069713791363275,
+      "grad_norm": 70.983255945064,
+      "learning_rate": 4e-09,
+      "logits/chosen": -1.6907414197921753,
+      "logits/rejected": -1.6978764533996582,
+      "logps/chosen": -135.08778381347656,
+      "logps/rejected": -140.00140380859375,
+      "loss": 0.6978,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.010493194684386253,
+      "rewards/margins": 0.006632559932768345,
+      "rewards/rejected": 0.003860633820295334,
+      "step": 2
+    },
+    {
+      "epoch": 0.004613942758272655,
+      "grad_norm": 79.97063682582153,
+      "learning_rate": 8e-09,
+      "logits/chosen": -1.6330227851867676,
+      "logits/rejected": -1.7231806516647339,
+      "logps/chosen": -197.88365173339844,
+      "logps/rejected": -218.62255859375,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": 0.008352389559149742,
+      "rewards/margins": -0.00352578517049551,
+      "rewards/rejected": 0.011878175660967827,
+      "step": 4
+    },
+    {
+      "epoch": 0.006920914137408983,
+      "grad_norm": 78.73277588414827,
+      "learning_rate": 1.1999999999999998e-08,
+      "logits/chosen": -1.7628690004348755,
+      "logits/rejected": -1.6921380758285522,
+      "logps/chosen": -181.12741088867188,
+      "logps/rejected": -177.64956665039062,
+      "loss": 0.6919,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.005539673380553722,
+      "rewards/margins": -0.012507464736700058,
+      "rewards/rejected": 0.006967790424823761,
+      "step": 6
+    },
+    {
+      "epoch": 0.00922788551654531,
+      "grad_norm": 84.94475101410946,
+      "learning_rate": 1.6e-08,
+      "logits/chosen": -1.6862337589263916,
+      "logits/rejected": -1.6957104206085205,
+      "logps/chosen": -229.57574462890625,
+      "logps/rejected": -308.63421630859375,
+      "loss": 0.6949,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.019691964611411095,
+      "rewards/margins": 0.022208284586668015,
+      "rewards/rejected": -0.0025163227692246437,
+      "step": 8
+    },
+    {
+      "epoch": 0.011534856895681638,
+      "grad_norm": 78.53713189911603,
+      "learning_rate": 2e-08,
+      "logits/chosen": -1.72577965259552,
+      "logits/rejected": -1.72530198097229,
+      "logps/chosen": -182.21597290039062,
+      "logps/rejected": -197.15383911132812,
+      "loss": 0.6876,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.00015587342204526067,
+      "rewards/margins": -0.00128166563808918,
+      "rewards/rejected": 0.0011257934384047985,
+      "step": 10
+    },
+    {
+      "epoch": 0.013841828274817966,
+      "grad_norm": 60.639642502259356,
+      "learning_rate": 2.3999999999999997e-08,
+      "logits/chosen": -1.5887395143508911,
+      "logits/rejected": -1.7574589252471924,
+      "logps/chosen": -121.71543884277344,
+      "logps/rejected": -164.58782958984375,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.004625019151717424,
+      "rewards/margins": 0.00861622579395771,
+      "rewards/rejected": -0.003991207107901573,
+      "step": 12
+    },
+    {
+      "epoch": 0.016148799653954292,
+      "grad_norm": 86.96054524483631,
+      "learning_rate": 2.8000000000000003e-08,
+      "logits/chosen": -1.5507514476776123,
+      "logits/rejected": -1.5499210357666016,
+      "logps/chosen": -147.94631958007812,
+      "logps/rejected": -200.87417602539062,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.013226826675236225,
+      "rewards/margins": 0.021001461893320084,
+      "rewards/rejected": -0.00777463661506772,
+      "step": 14
+    },
+    {
+      "epoch": 0.01845577103309062,
+      "grad_norm": 77.14253037311525,
+      "learning_rate": 3.2e-08,
+      "logits/chosen": -1.6721559762954712,
+      "logits/rejected": -1.7068090438842773,
+      "logps/chosen": -157.89622497558594,
+      "logps/rejected": -199.2628631591797,
+      "loss": 0.6951,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.0034806535113602877,
+      "rewards/margins": 0.006839222740381956,
+      "rewards/rejected": -0.010319876484572887,
+      "step": 16
+    },
+    {
+      "epoch": 0.020762742412226948,
+      "grad_norm": 78.17299743340894,
+      "learning_rate": 3.6e-08,
+      "logits/chosen": -1.6556451320648193,
+      "logits/rejected": -1.7276983261108398,
+      "logps/chosen": -135.32223510742188,
+      "logps/rejected": -158.1257781982422,
+      "loss": 0.6884,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.01184301357716322,
+      "rewards/margins": 0.023063620552420616,
+      "rewards/rejected": -0.011220606043934822,
+      "step": 18
+    },
+    {
+      "epoch": 0.023069713791363276,
+      "grad_norm": 77.30701284634611,
+      "learning_rate": 4e-08,
+      "logits/chosen": -1.735813856124878,
+      "logits/rejected": -1.789333701133728,
+      "logps/chosen": -157.4953155517578,
+      "logps/rejected": -186.05862426757812,
+      "loss": 0.693,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.004054094199091196,
+      "rewards/margins": 0.010992627590894699,
+      "rewards/rejected": -0.006938533391803503,
+      "step": 20
+    },
+    {
+      "epoch": 0.025376685170499604,
+      "grad_norm": 77.95778126726918,
+      "learning_rate": 4.4e-08,
+      "logits/chosen": -1.5402836799621582,
+      "logits/rejected": -1.5884689092636108,
+      "logps/chosen": -133.27554321289062,
+      "logps/rejected": -170.48594665527344,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.009935155510902405,
+      "rewards/margins": 0.019674377515912056,
+      "rewards/rejected": -0.009739222005009651,
+      "step": 22
+    },
+    {
+      "epoch": 0.02768365654963593,
+      "grad_norm": 78.69027024475307,
+      "learning_rate": 4.799999999999999e-08,
+      "logits/chosen": -1.4641175270080566,
+      "logits/rejected": -1.6491130590438843,
+      "logps/chosen": -139.53375244140625,
+      "logps/rejected": -193.21438598632812,
+      "loss": 0.6945,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.010036014020442963,
+      "rewards/margins": 0.005420446861535311,
+      "rewards/rejected": -0.015456462278962135,
+      "step": 24
+    },
+    {
+      "epoch": 0.02999062792877226,
+      "grad_norm": 82.14181039722058,
+      "learning_rate": 5.2e-08,
+      "logits/chosen": -1.7350623607635498,
+      "logits/rejected": -1.6639574766159058,
+      "logps/chosen": -161.62164306640625,
+      "logps/rejected": -160.58840942382812,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.0011872733011841774,
+      "rewards/margins": -0.006157425232231617,
+      "rewards/rejected": 0.0049701533280313015,
+      "step": 26
+    },
+    {
+      "epoch": 0.032297599307908584,
+      "grad_norm": 73.66413843287592,
+      "learning_rate": 5.6000000000000005e-08,
+      "logits/chosen": -1.4280009269714355,
+      "logits/rejected": -1.6318210363388062,
+      "logps/chosen": -131.8518524169922,
+      "logps/rejected": -166.72335815429688,
+      "loss": 0.6964,
+      "rewards/accuracies": 0.3125,
+      "rewards/chosen": -0.01029287837445736,
+      "rewards/margins": -0.014272996224462986,
+      "rewards/rejected": 0.003980117850005627,
+      "step": 28
+    },
+    {
+      "epoch": 0.034604570687044915,
+      "grad_norm": 86.40461346238433,
+      "learning_rate": 6e-08,
+      "logits/chosen": -1.6838908195495605,
+      "logits/rejected": -1.7304034233093262,
+      "logps/chosen": -124.49476623535156,
+      "logps/rejected": -140.77841186523438,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.0041793473064899445,
+      "rewards/margins": -0.0030185298528522253,
+      "rewards/rejected": 0.007197877857834101,
+      "step": 30
+    },
+    {
+      "epoch": 0.03691154206618124,
+      "grad_norm": 79.23808836252253,
+      "learning_rate": 6.4e-08,
+      "logits/chosen": -1.5962588787078857,
+      "logits/rejected": -1.549019455909729,
+      "logps/chosen": -194.4256591796875,
+      "logps/rejected": -237.36117553710938,
+      "loss": 0.7003,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.0013054789742454886,
+      "rewards/margins": -0.018302934244275093,
+      "rewards/rejected": 0.016997454687952995,
+      "step": 32
+    },
+    {
+      "epoch": 0.03921851344531757,
+      "grad_norm": 74.59682312018288,
+      "learning_rate": 6.8e-08,
+      "logits/chosen": -1.740609884262085,
+      "logits/rejected": -1.6540827751159668,
+      "logps/chosen": -157.9348907470703,
+      "logps/rejected": -158.6222686767578,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": 0.01421279925853014,
+      "rewards/margins": 0.03194922208786011,
+      "rewards/rejected": -0.017736420035362244,
+      "step": 34
+    },
+    {
+      "epoch": 0.041525484824453895,
+      "grad_norm": 79.71071945309694,
+      "learning_rate": 7.2e-08,
+      "logits/chosen": -1.5709240436553955,
+      "logits/rejected": -1.6920911073684692,
+      "logps/chosen": -173.94007873535156,
+      "logps/rejected": -219.2288818359375,
+      "loss": 0.6962,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.011220686137676239,
+      "rewards/margins": -0.008418139070272446,
+      "rewards/rejected": -0.0028025463689118624,
+      "step": 36
+    },
+    {
+      "epoch": 0.04383245620359023,
+      "grad_norm": 86.21753265595521,
+      "learning_rate": 7.599999999999999e-08,
+      "logits/chosen": -1.7426936626434326,
+      "logits/rejected": -1.5694864988327026,
+      "logps/chosen": -159.00730895996094,
+      "logps/rejected": -146.18772888183594,
+      "loss": 0.6971,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.01584451086819172,
+      "rewards/margins": -0.012521232478320599,
+      "rewards/rejected": -0.003323277225717902,
+      "step": 38
+    },
+    {
+      "epoch": 0.04613942758272655,
+      "grad_norm": 76.87714834723751,
+      "learning_rate": 8e-08,
+      "logits/chosen": -1.7129234075546265,
+      "logits/rejected": -1.6838488578796387,
+      "logps/chosen": -191.7474822998047,
+      "logps/rejected": -162.81466674804688,
+      "loss": 0.6986,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.0020668436773121357,
+      "rewards/margins": -0.008048251271247864,
+      "rewards/rejected": 0.010115095414221287,
+      "step": 40
+    },
+    {
+      "epoch": 0.04844639896186288,
+      "grad_norm": 71.62490665795943,
+      "learning_rate": 8.4e-08,
+      "logits/chosen": -1.7202041149139404,
+      "logits/rejected": -1.7000675201416016,
+      "logps/chosen": -157.0576934814453,
+      "logps/rejected": -186.76138305664062,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": 0.0023848186247050762,
+      "rewards/margins": 0.002543981885537505,
+      "rewards/rejected": -0.00015916326083242893,
+      "step": 42
+    },
+    {
+      "epoch": 0.05075337034099921,
+      "grad_norm": 81.75722048702342,
+      "learning_rate": 8.8e-08,
+      "logits/chosen": -1.5299909114837646,
+      "logits/rejected": -1.5974533557891846,
+      "logps/chosen": -158.53753662109375,
+      "logps/rejected": -179.9112548828125,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.006203922443091869,
+      "rewards/margins": 0.02108878269791603,
+      "rewards/rejected": -0.014884857460856438,
+      "step": 44
+    },
+    {
+      "epoch": 0.05306034172013553,
+      "grad_norm": 78.9572151515279,
+      "learning_rate": 9.2e-08,
+      "logits/chosen": -1.6293164491653442,
+      "logits/rejected": -1.6444960832595825,
+      "logps/chosen": -152.41412353515625,
+      "logps/rejected": -170.09869384765625,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.010927575640380383,
+      "rewards/margins": 0.0014875519555062056,
+      "rewards/rejected": 0.009440025314688683,
+      "step": 46
+    },
+    {
+      "epoch": 0.05536731309927186,
+      "grad_norm": 81.84986800244135,
+      "learning_rate": 9.599999999999999e-08,
+      "logits/chosen": -1.7789497375488281,
+      "logits/rejected": -1.7547317743301392,
+      "logps/chosen": -214.71987915039062,
+      "logps/rejected": -240.7999725341797,
+      "loss": 0.6889,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.0025361552834510803,
+      "rewards/margins": 0.006769699975848198,
+      "rewards/rejected": -0.004233543295413256,
+      "step": 48
+    },
+    {
+      "epoch": 0.05767428447840819,
+      "grad_norm": 76.76668544313137,
+      "learning_rate": 1e-07,
+      "logits/chosen": -1.491020917892456,
+      "logits/rejected": -1.5447454452514648,
+      "logps/chosen": -201.1317901611328,
+      "logps/rejected": -267.04248046875,
+      "loss": 0.6974,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.005572921596467495,
+      "rewards/margins": 0.01456289179623127,
+      "rewards/rejected": -0.02013581432402134,
+      "step": 50
+    },
+    {
+      "epoch": 0.05998125585754452,
+      "grad_norm": 84.23078533480681,
+      "learning_rate": 1.04e-07,
+      "logits/chosen": -1.6120061874389648,
+      "logits/rejected": -1.7649461030960083,
+      "logps/chosen": -183.1412353515625,
+      "logps/rejected": -282.4610290527344,
+      "loss": 0.695,
+      "rewards/accuracies": 0.3125,
+      "rewards/chosen": -0.02553856186568737,
+      "rewards/margins": -0.038517288863658905,
+      "rewards/rejected": 0.012978724204003811,
+      "step": 52
+    },
+    {
+      "epoch": 0.06228822723668084,
+      "grad_norm": 92.0173388072239,
+      "learning_rate": 1.08e-07,
+      "logits/chosen": -1.4607347249984741,
+      "logits/rejected": -1.625195026397705,
+      "logps/chosen": -152.8062744140625,
+      "logps/rejected": -219.1183624267578,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.012677345424890518,
+      "rewards/margins": -0.032261885702610016,
+      "rewards/rejected": 0.01958453841507435,
+      "step": 54
+    },
+    {
+      "epoch": 0.06459519861581717,
+      "grad_norm": 79.32388836348366,
+      "learning_rate": 1.1200000000000001e-07,
+      "logits/chosen": -1.6375060081481934,
+      "logits/rejected": -1.5966099500656128,
+      "logps/chosen": -223.85108947753906,
+      "logps/rejected": -256.30072021484375,
+      "loss": 0.699,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.023084305226802826,
+      "rewards/margins": -0.02949170023202896,
+      "rewards/rejected": 0.006407391745597124,
+      "step": 56
+    },
+    {
+      "epoch": 0.0669021699949535,
+      "grad_norm": 69.72321013611293,
+      "learning_rate": 1.1599999999999999e-07,
+      "logits/chosen": -1.5106103420257568,
+      "logits/rejected": -1.596940517425537,
+      "logps/chosen": -188.92218017578125,
+      "logps/rejected": -275.0534973144531,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.017192328348755836,
+      "rewards/margins": 0.03240702301263809,
+      "rewards/rejected": -0.015214694663882256,
+      "step": 58
+    },
+    {
+      "epoch": 0.06920914137408983,
+      "grad_norm": 72.64787237644839,
+      "learning_rate": 1.2e-07,
+      "logits/chosen": -1.667373776435852,
+      "logits/rejected": -1.6947064399719238,
+      "logps/chosen": -103.05116271972656,
+      "logps/rejected": -151.50807189941406,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.00641946354880929,
+      "rewards/margins": 0.032484300434589386,
+      "rewards/rejected": -0.026064833626151085,
+      "step": 60
+    },
+    {
+      "epoch": 0.07151611275322615,
+      "grad_norm": 75.24112563737103,
+      "learning_rate": 1.24e-07,
+      "logits/chosen": -1.5305185317993164,
+      "logits/rejected": -1.6095894575119019,
+      "logps/chosen": -154.5998077392578,
+      "logps/rejected": -176.33970642089844,
+      "loss": 0.6965,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.00010838371235877275,
+      "rewards/margins": 0.006697986274957657,
+      "rewards/rejected": -0.006589602679014206,
+      "step": 62
+    },
+    {
+      "epoch": 0.07382308413236248,
+      "grad_norm": 70.73819169103417,
+      "learning_rate": 1.28e-07,
+      "logits/chosen": -1.6058859825134277,
+      "logits/rejected": -1.6498842239379883,
+      "logps/chosen": -151.62286376953125,
+      "logps/rejected": -169.5069122314453,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": 0.003975578583776951,
+      "rewards/margins": 0.006644865497946739,
+      "rewards/rejected": -0.0026692876126617193,
+      "step": 64
+    },
+    {
+      "epoch": 0.0761300555114988,
+      "grad_norm": 79.80905942384086,
+      "learning_rate": 1.32e-07,
+      "logits/chosen": -1.566676139831543,
+      "logits/rejected": -1.635036587715149,
+      "logps/chosen": -213.95590209960938,
+      "logps/rejected": -268.84747314453125,
+      "loss": 0.6878,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.0030877357348799706,
+      "rewards/margins": -0.004700601100921631,
+      "rewards/rejected": 0.0016128652496263385,
+      "step": 66
+    },
+    {
+      "epoch": 0.07843702689063514,
+      "grad_norm": 68.290418726697,
+      "learning_rate": 1.36e-07,
+      "logits/chosen": -1.625745177268982,
+      "logits/rejected": -1.7014200687408447,
+      "logps/chosen": -191.14842224121094,
+      "logps/rejected": -222.51779174804688,
+      "loss": 0.6954,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.0007452260470017791,
+      "rewards/margins": 0.00873138289898634,
+      "rewards/rejected": -0.007986157201230526,
+      "step": 68
+    },
+    {
+      "epoch": 0.08074399826977147,
+      "grad_norm": 79.51788387191074,
+      "learning_rate": 1.3999999999999998e-07,
+      "logits/chosen": -1.5817363262176514,
+      "logits/rejected": -1.6993348598480225,
+      "logps/chosen": -131.7422637939453,
+      "logps/rejected": -162.98304748535156,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.0074032689444720745,
+      "rewards/margins": -0.010667804628610611,
+      "rewards/rejected": 0.003264536615461111,
+      "step": 70
+    },
+    {
+      "epoch": 0.08305096964890779,
+      "grad_norm": 83.37639460390962,
+      "learning_rate": 1.44e-07,
+      "logits/chosen": -1.5910240411758423,
+      "logits/rejected": -1.6661615371704102,
+      "logps/chosen": -181.304931640625,
+      "logps/rejected": -209.23526000976562,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.0042681945487856865,
+      "rewards/margins": -0.02247396856546402,
+      "rewards/rejected": 0.018205774948000908,
+      "step": 72
+    },
+    {
+      "epoch": 0.08535794102804412,
+      "grad_norm": 85.04605551266509,
+      "learning_rate": 1.48e-07,
+      "logits/chosen": -1.5876970291137695,
+      "logits/rejected": -1.7304015159606934,
+      "logps/chosen": -146.5454559326172,
+      "logps/rejected": -182.179931640625,
+      "loss": 0.6891,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.011930807493627071,
+      "rewards/margins": -0.013042710721492767,
+      "rewards/rejected": 0.0011119036935269833,
+      "step": 74
+    },
+    {
+      "epoch": 0.08766491240718045,
+      "grad_norm": 71.97159401776734,
+      "learning_rate": 1.5199999999999998e-07,
+      "logits/chosen": -1.6893718242645264,
+      "logits/rejected": -1.6752575635910034,
+      "logps/chosen": -163.57489013671875,
+      "logps/rejected": -162.34803771972656,
+      "loss": 0.6906,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.0007063052617013454,
+      "rewards/margins": 0.002567308023571968,
+      "rewards/rejected": -0.0018610022962093353,
+      "step": 76
+    },
+    {
+      "epoch": 0.08997188378631678,
+      "grad_norm": 80.09910611023234,
+      "learning_rate": 1.56e-07,
+      "logits/chosen": -1.612238883972168,
+      "logits/rejected": -1.5296804904937744,
+      "logps/chosen": -143.39723205566406,
+      "logps/rejected": -165.65318298339844,
+      "loss": 0.6871,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.009035947732627392,
+      "rewards/margins": 0.025550464168190956,
+      "rewards/rejected": -0.01651451550424099,
+      "step": 78
+    },
+    {
+      "epoch": 0.0922788551654531,
+      "grad_norm": 70.85997602518799,
+      "learning_rate": 1.6e-07,
+      "logits/chosen": -1.6167306900024414,
+      "logits/rejected": -1.720908522605896,
+      "logps/chosen": -137.2986602783203,
+      "logps/rejected": -246.95404052734375,
+      "loss": 0.693,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.006022963672876358,
+      "rewards/margins": 0.008436123840510845,
+      "rewards/rejected": -0.0024131599348038435,
+      "step": 80
+    },
+    {
+      "epoch": 0.09458582654458943,
+      "grad_norm": 73.43468397188529,
+      "learning_rate": 1.6399999999999999e-07,
+      "logits/chosen": -1.7178070545196533,
+      "logits/rejected": -1.7651526927947998,
+      "logps/chosen": -154.39617919921875,
+      "logps/rejected": -187.47491455078125,
+      "loss": 0.6985,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.014386245980858803,
+      "rewards/margins": -0.011840756982564926,
+      "rewards/rejected": -0.002545490860939026,
+      "step": 82
+    },
+    {
+      "epoch": 0.09689279792372577,
+      "grad_norm": 82.20956953972079,
+      "learning_rate": 1.68e-07,
+      "logits/chosen": -1.5902974605560303,
+      "logits/rejected": -1.604806900024414,
+      "logps/chosen": -127.57711029052734,
+      "logps/rejected": -146.8506317138672,
+      "loss": 0.6887,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.006446457467973232,
+      "rewards/margins": 0.008786877617239952,
+      "rewards/rejected": -0.015233333222568035,
+      "step": 84
+    },
+    {
+      "epoch": 0.09919976930286209,
+      "grad_norm": 76.58342600254258,
+      "learning_rate": 1.7199999999999998e-07,
+      "logits/chosen": -1.6294573545455933,
+      "logits/rejected": -1.6458450555801392,
+      "logps/chosen": -248.47845458984375,
+      "logps/rejected": -246.7737579345703,
+      "loss": 0.6895,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.009375479072332382,
+      "rewards/margins": 0.025924015790224075,
+      "rewards/rejected": -0.03529949486255646,
+      "step": 86
+    },
+    {
+      "epoch": 0.10150674068199841,
+      "grad_norm": 73.05738349044326,
+      "learning_rate": 1.76e-07,
+      "logits/chosen": -1.84279465675354,
+      "logits/rejected": -1.7476646900177002,
+      "logps/chosen": -153.08554077148438,
+      "logps/rejected": -154.7803497314453,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.002370176836848259,
+      "rewards/margins": -0.0033320121001452208,
+      "rewards/rejected": 0.0009618350304663181,
+      "step": 88
+    },
+    {
+      "epoch": 0.10381371206113474,
+      "grad_norm": 77.95992122604585,
+      "learning_rate": 1.8e-07,
+      "logits/chosen": -1.6355715990066528,
+      "logits/rejected": -1.6984450817108154,
+      "logps/chosen": -169.7340087890625,
+      "logps/rejected": -185.59031677246094,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.01826353184878826,
+      "rewards/margins": -0.008648518472909927,
+      "rewards/rejected": -0.009615011513233185,
+      "step": 90
+    },
+    {
+      "epoch": 0.10612068344027106,
+      "grad_norm": 74.70608110655593,
+      "learning_rate": 1.84e-07,
+      "logits/chosen": -1.5153872966766357,
+      "logits/rejected": -1.5389485359191895,
+      "logps/chosen": -214.6402130126953,
+      "logps/rejected": -224.4317626953125,
+      "loss": 0.6877,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.00619399081915617,
+      "rewards/margins": 0.011179441586136818,
+      "rewards/rejected": -0.004985451698303223,
+      "step": 92
+    },
+    {
+      "epoch": 0.1084276548194074,
+      "grad_norm": 74.73028912491218,
+      "learning_rate": 1.88e-07,
+      "logits/chosen": -1.5655710697174072,
+      "logits/rejected": -1.5568063259124756,
+      "logps/chosen": -170.8540496826172,
+      "logps/rejected": -195.4169158935547,
+      "loss": 0.6887,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.016467105597257614,
+      "rewards/margins": 0.011973596177995205,
+      "rewards/rejected": -0.028440698981285095,
+      "step": 94
+    },
+    {
+      "epoch": 0.11073462619854373,
+      "grad_norm": 81.65007402302682,
+      "learning_rate": 1.9199999999999997e-07,
+      "logits/chosen": -1.7869484424591064,
+      "logits/rejected": -1.7626042366027832,
+      "logps/chosen": -208.46002197265625,
+      "logps/rejected": -256.5970458984375,
+      "loss": 0.6846,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.009895925410091877,
+      "rewards/margins": 0.011812476441264153,
+      "rewards/rejected": -0.021708402782678604,
+      "step": 96
+    },
+    {
+      "epoch": 0.11304159757768005,
+      "grad_norm": 77.09604224965807,
+      "learning_rate": 1.9599999999999998e-07,
+      "logits/chosen": -1.6421016454696655,
+      "logits/rejected": -1.5873386859893799,
+      "logps/chosen": -176.68853759765625,
+      "logps/rejected": -188.64544677734375,
+      "loss": 0.69,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.01306343637406826,
+      "rewards/margins": 0.021781262010335922,
+      "rewards/rejected": -0.03484470024704933,
+      "step": 98
+    },
+    {
+      "epoch": 0.11534856895681637,
+      "grad_norm": 77.37699461097638,
+      "learning_rate": 2e-07,
+      "logits/chosen": -1.5747566223144531,
+      "logits/rejected": -1.5757074356079102,
+      "logps/chosen": -146.1053009033203,
+      "logps/rejected": -177.65733337402344,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.01261211559176445,
+      "rewards/margins": 0.005542438477277756,
+      "rewards/rejected": -0.018154552206397057,
+      "step": 100
+    },
+    {
+      "epoch": 0.11534856895681637,
+      "eval_logits/chosen": -1.592301368713379,
+      "eval_logits/rejected": -1.4917248487472534,
+      "eval_logps/chosen": -185.32534790039062,
+      "eval_logps/rejected": -150.51693725585938,
+      "eval_loss": 0.6938029527664185,
+      "eval_rewards/accuracies": 0.4000000059604645,
+      "eval_rewards/chosen": -0.014318165369331837,
+      "eval_rewards/margins": -0.014164167456328869,
+      "eval_rewards/rejected": -0.00015399709809571505,
+      "eval_runtime": 22.8572,
+      "eval_samples_per_second": 4.375,
+      "eval_steps_per_second": 1.094,
+      "step": 100
+    },
+    {
+      "epoch": 0.11765554033595271,
+      "grad_norm": 83.18929756458088,
+      "learning_rate": 1.9999925887938156e-07,
+      "logits/chosen": -1.553455114364624,
+      "logits/rejected": -1.6009831428527832,
+      "logps/chosen": -171.79664611816406,
+      "logps/rejected": -223.1472930908203,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.0011008224682882428,
+      "rewards/margins": 0.010834511369466782,
+      "rewards/rejected": -0.009733689948916435,
+      "step": 102
+    },
+    {
+      "epoch": 0.11996251171508904,
+      "grad_norm": 73.85193862190509,
+      "learning_rate": 1.9999703552851146e-07,
+      "logits/chosen": -1.7583006620407104,
+      "logits/rejected": -1.714582920074463,
+      "logps/chosen": -209.88302612304688,
+      "logps/rejected": -255.11888122558594,
+      "loss": 0.6913,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.030152078717947006,
+      "rewards/margins": -0.011741320602595806,
+      "rewards/rejected": -0.018410757184028625,
+      "step": 104
+    },
+    {
+      "epoch": 0.12226948309422536,
+      "grad_norm": 73.38727733625704,
+      "learning_rate": 1.9999332998034512e-07,
+      "logits/chosen": -1.6966747045516968,
+      "logits/rejected": -1.6100220680236816,
+      "logps/chosen": -160.12281799316406,
+      "logps/rejected": -167.38145446777344,
+      "loss": 0.686,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.008994976989924908,
+      "rewards/margins": 0.011080076918005943,
+      "rewards/rejected": -0.020075054839253426,
+      "step": 106
+    },
+    {
+      "epoch": 0.12457645447336169,
+      "grad_norm": 79.80728796393491,
+      "learning_rate": 1.9998814228980768e-07,
+      "logits/chosen": -1.6656932830810547,
+      "logits/rejected": -1.7435060739517212,
+      "logps/chosen": -156.0963897705078,
+      "logps/rejected": -208.7286376953125,
+      "loss": 0.6956,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.01158140879124403,
+      "rewards/margins": -0.003068419173359871,
+      "rewards/rejected": -0.008512990549206734,
+      "step": 108
+    },
+    {
+      "epoch": 0.126883425852498,
+      "grad_norm": 71.572270187751,
+      "learning_rate": 1.9998147253379324e-07,
+      "logits/chosen": -1.7250394821166992,
+      "logits/rejected": -1.720632791519165,
+      "logps/chosen": -143.606201171875,
+      "logps/rejected": -164.64126586914062,
+      "loss": 0.6911,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.00029725395143032074,
+      "rewards/margins": 0.004560052417218685,
+      "rewards/rejected": -0.004857306368649006,
+      "step": 110
+    },
+    {
+      "epoch": 0.12919039723163434,
+      "grad_norm": 76.7363281665151,
+      "learning_rate": 1.999733208111637e-07,
+      "logits/chosen": -1.680725336074829,
+      "logits/rejected": -1.7269576787948608,
+      "logps/chosen": -141.92416381835938,
+      "logps/rejected": -163.63902282714844,
+      "loss": 0.6878,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.013096440583467484,
+      "rewards/margins": 0.013841900043189526,
+      "rewards/rejected": -0.026938341557979584,
+      "step": 112
+    },
+    {
+      "epoch": 0.13149736861077066,
+      "grad_norm": 71.23095597503095,
+      "learning_rate": 1.9996368724274726e-07,
+      "logits/chosen": -1.7746036052703857,
+      "logits/rejected": -1.651440978050232,
+      "logps/chosen": -201.5678253173828,
+      "logps/rejected": -208.96060180664062,
+      "loss": 0.6814,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.020835982635617256,
+      "rewards/margins": 0.0012882971204817295,
+      "rewards/rejected": -0.02212427742779255,
+      "step": 114
+    },
+    {
+      "epoch": 0.133804339989907,
+      "grad_norm": 78.35820889872501,
+      "learning_rate": 1.999525719713366e-07,
+      "logits/chosen": -1.6184967756271362,
+      "logits/rejected": -1.6276531219482422,
+      "logps/chosen": -138.03579711914062,
+      "logps/rejected": -156.24818420410156,
+      "loss": 0.6893,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.024172522127628326,
+      "rewards/margins": -0.007286247797310352,
+      "rewards/rejected": -0.0168862733989954,
+      "step": 116
+    },
+    {
+      "epoch": 0.13611131136904334,
+      "grad_norm": 73.30378065799947,
+      "learning_rate": 1.9993997516168685e-07,
+      "logits/chosen": -1.5095572471618652,
+      "logits/rejected": -1.4317773580551147,
+      "logps/chosen": -168.31259155273438,
+      "logps/rejected": -181.01010131835938,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.02184070646762848,
+      "rewards/margins": -0.0038399603217840195,
+      "rewards/rejected": -0.01800074614584446,
+      "step": 118
+    },
+    {
+      "epoch": 0.13841828274817966,
+      "grad_norm": 76.67682193401895,
+      "learning_rate": 1.9992589700051315e-07,
+      "logits/chosen": -1.6505416631698608,
+      "logits/rejected": -1.6528055667877197,
+      "logps/chosen": -163.4833221435547,
+      "logps/rejected": -173.32627868652344,
+      "loss": 0.691,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.037532731890678406,
+      "rewards/margins": -0.001648992532864213,
+      "rewards/rejected": -0.035883739590644836,
+      "step": 120
+    },
+    {
+      "epoch": 0.14072525412731599,
+      "grad_norm": 79.25219710625622,
+      "learning_rate": 1.9991033769648782e-07,
+      "logits/chosen": -1.6732072830200195,
+      "logits/rejected": -1.6914747953414917,
+      "logps/chosen": -192.20941162109375,
+      "logps/rejected": -249.57064819335938,
+      "loss": 0.6785,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.02337605319917202,
+      "rewards/margins": 0.03376854211091995,
+      "rewards/rejected": -0.05714459717273712,
+      "step": 122
+    },
+    {
+      "epoch": 0.1430322255064523,
+      "grad_norm": 74.1794316582206,
+      "learning_rate": 1.9989329748023723e-07,
+      "logits/chosen": -1.6055612564086914,
+      "logits/rejected": -1.6374058723449707,
+      "logps/chosen": -150.5140838623047,
+      "logps/rejected": -178.90463256835938,
+      "loss": 0.6838,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.03467298671603203,
+      "rewards/margins": 0.017992481589317322,
+      "rewards/rejected": -0.05266546458005905,
+      "step": 124
+    },
+    {
+      "epoch": 0.14533919688558863,
+      "grad_norm": 76.65585990685855,
+      "learning_rate": 1.9987477660433854e-07,
+      "logits/chosen": -1.6969408988952637,
+      "logits/rejected": -1.7563108205795288,
+      "logps/chosen": -142.4885711669922,
+      "logps/rejected": -210.4172821044922,
+      "loss": 0.689,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.024329736828804016,
+      "rewards/margins": 0.004793995060026646,
+      "rewards/rejected": -0.029123730957508087,
+      "step": 126
+    },
+    {
+      "epoch": 0.14764616826472496,
+      "grad_norm": 78.42733649878224,
+      "learning_rate": 1.998547753433158e-07,
+      "logits/chosen": -1.6231815814971924,
+      "logits/rejected": -1.4993540048599243,
+      "logps/chosen": -248.5255584716797,
+      "logps/rejected": -283.0628662109375,
+      "loss": 0.6867,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.022915348410606384,
+      "rewards/margins": 0.04015136882662773,
+      "rewards/rejected": -0.06306671351194382,
+      "step": 128
+    },
+    {
+      "epoch": 0.14995313964386128,
+      "grad_norm": 81.34489884736102,
+      "learning_rate": 1.9983329399363594e-07,
+      "logits/chosen": -1.696123719215393,
+      "logits/rejected": -1.5894306898117065,
+      "logps/chosen": -157.25205993652344,
+      "logps/rejected": -169.28765869140625,
+      "loss": 0.6888,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.02339826337993145,
+      "rewards/margins": 0.029402071610093117,
+      "rewards/rejected": -0.05280033499002457,
+      "step": 130
+    },
+    {
+      "epoch": 0.1522601110229976,
+      "grad_norm": 71.86675386697708,
+      "learning_rate": 1.998103328737044e-07,
+      "logits/chosen": -1.614111304283142,
+      "logits/rejected": -1.668984055519104,
+      "logps/chosen": -169.32870483398438,
+      "logps/rejected": -184.28652954101562,
+      "loss": 0.694,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.032653309404850006,
+      "rewards/margins": -0.012304544448852539,
+      "rewards/rejected": -0.020348764955997467,
+      "step": 132
+    },
+    {
+      "epoch": 0.15456708240213396,
+      "grad_norm": 81.85224601265395,
+      "learning_rate": 1.9978589232386034e-07,
+      "logits/chosen": -1.715609073638916,
+      "logits/rejected": -1.7786422967910767,
+      "logps/chosen": -167.58688354492188,
+      "logps/rejected": -199.66270446777344,
+      "loss": 0.6864,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.03811431676149368,
+      "rewards/margins": 0.017543859779834747,
+      "rewards/rejected": -0.05565817654132843,
+      "step": 134
+    },
+    {
+      "epoch": 0.15687405378127028,
+      "grad_norm": 73.7622516118343,
+      "learning_rate": 1.9975997270637168e-07,
+      "logits/chosen": -1.6321560144424438,
+      "logits/rejected": -1.7015608549118042,
+      "logps/chosen": -159.351318359375,
+      "logps/rejected": -176.723876953125,
+      "loss": 0.6859,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.02714327722787857,
+      "rewards/margins": 0.021138466894626617,
+      "rewards/rejected": -0.04828174412250519,
+      "step": 136
+    },
+    {
+      "epoch": 0.1591810251604066,
+      "grad_norm": 71.96760531715911,
+      "learning_rate": 1.997325744054297e-07,
+      "logits/chosen": -1.5530474185943604,
+      "logits/rejected": -1.5373188257217407,
+      "logps/chosen": -158.63812255859375,
+      "logps/rejected": -204.0651092529297,
+      "loss": 0.6845,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.01808898150920868,
+      "rewards/margins": 0.017602307721972466,
+      "rewards/rejected": -0.035691291093826294,
+      "step": 138
+    },
+    {
+      "epoch": 0.16148799653954293,
+      "grad_norm": 73.93273755038686,
+      "learning_rate": 1.9970369782714328e-07,
+      "logits/chosen": -1.522450566291809,
+      "logits/rejected": -1.635149598121643,
+      "logps/chosen": -142.74459838867188,
+      "logps/rejected": -149.5770721435547,
+      "loss": 0.6894,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.025994691997766495,
+      "rewards/margins": -0.006413338705897331,
+      "rewards/rejected": -0.019581351429224014,
+      "step": 140
+    },
+    {
+      "epoch": 0.16379496791867926,
+      "grad_norm": 79.55861212361464,
+      "learning_rate": 1.99673343399533e-07,
+      "logits/chosen": -1.525217056274414,
+      "logits/rejected": -1.5952740907669067,
+      "logps/chosen": -116.86170959472656,
+      "logps/rejected": -175.00779724121094,
+      "loss": 0.6832,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.020393915474414825,
+      "rewards/margins": 0.032093390822410583,
+      "rewards/rejected": -0.05248731002211571,
+      "step": 142
+    },
+    {
+      "epoch": 0.16610193929781558,
+      "grad_norm": 83.97535534931897,
+      "learning_rate": 1.9964151157252466e-07,
+      "logits/chosen": -1.6767423152923584,
+      "logits/rejected": -1.6693997383117676,
+      "logps/chosen": -207.50936889648438,
+      "logps/rejected": -216.3134002685547,
+      "loss": 0.6789,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.03636579588055611,
+      "rewards/margins": 0.03607642278075218,
+      "rewards/rejected": -0.07244221866130829,
+      "step": 144
+    },
+    {
+      "epoch": 0.1684089106769519,
+      "grad_norm": 73.85111113100436,
+      "learning_rate": 1.996082028179428e-07,
+      "logits/chosen": -1.4807971715927124,
+      "logits/rejected": -1.4092496633529663,
+      "logps/chosen": -168.455078125,
+      "logps/rejected": -172.4587860107422,
+      "loss": 0.689,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.06219344958662987,
+      "rewards/margins": 0.011872416362166405,
+      "rewards/rejected": -0.07406586408615112,
+      "step": 146
+    },
+    {
+      "epoch": 0.17071588205608823,
+      "grad_norm": 80.66954314511047,
+      "learning_rate": 1.9957341762950344e-07,
+      "logits/chosen": -1.5618644952774048,
+      "logits/rejected": -1.67661452293396,
+      "logps/chosen": -114.58411407470703,
+      "logps/rejected": -158.1700439453125,
+      "loss": 0.6807,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.04578070342540741,
+      "rewards/margins": 0.029419898986816406,
+      "rewards/rejected": -0.07520060241222382,
+      "step": 148
+    },
+    {
+      "epoch": 0.17302285343522458,
+      "grad_norm": 71.43623661516392,
+      "learning_rate": 1.9953715652280706e-07,
+      "logits/chosen": -1.6976016759872437,
+      "logits/rejected": -1.6299835443496704,
+      "logps/chosen": -228.1553497314453,
+      "logps/rejected": -214.32037353515625,
+      "loss": 0.6848,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.06526876986026764,
+      "rewards/margins": -0.002617661375552416,
+      "rewards/rejected": -0.06265110522508621,
+      "step": 150
+    },
+    {
+      "epoch": 0.1753298248143609,
+      "grad_norm": 85.31030453694517,
+      "learning_rate": 1.9949942003533064e-07,
+      "logits/chosen": -1.7211732864379883,
+      "logits/rejected": -1.720245122909546,
+      "logps/chosen": -138.57936096191406,
+      "logps/rejected": -158.134521484375,
+      "loss": 0.6829,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.042685676366090775,
+      "rewards/margins": -0.006229763850569725,
+      "rewards/rejected": -0.0364559069275856,
+      "step": 152
+    },
+    {
+      "epoch": 0.17763679619349723,
+      "grad_norm": 75.37656195588123,
+      "learning_rate": 1.9946020872642006e-07,
+      "logits/chosen": -1.602712631225586,
+      "logits/rejected": -1.5105926990509033,
+      "logps/chosen": -152.95616149902344,
+      "logps/rejected": -252.92359924316406,
+      "loss": 0.6848,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.05936397612094879,
+      "rewards/margins": 0.023188650608062744,
+      "rewards/rejected": -0.08255261927843094,
+      "step": 154
+    },
+    {
+      "epoch": 0.17994376757263356,
+      "grad_norm": 74.43256656918146,
+      "learning_rate": 1.9941952317728147e-07,
+      "logits/chosen": -1.6266837120056152,
+      "logits/rejected": -1.5794254541397095,
+      "logps/chosen": -154.70660400390625,
+      "logps/rejected": -171.6692657470703,
+      "loss": 0.688,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.0499938428401947,
+      "rewards/margins": 0.022745870053768158,
+      "rewards/rejected": -0.07273972034454346,
+      "step": 156
+    },
+    {
+      "epoch": 0.18225073895176988,
+      "grad_norm": 75.91057680239186,
+      "learning_rate": 1.993773639909728e-07,
+      "logits/chosen": -1.49541437625885,
+      "logits/rejected": -1.6966127157211304,
+      "logps/chosen": -165.41343688964844,
+      "logps/rejected": -208.544189453125,
+      "loss": 0.6768,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.02937229909002781,
+      "rewards/margins": 0.061954449862241745,
+      "rewards/rejected": -0.0913267433643341,
+      "step": 158
+    },
+    {
+      "epoch": 0.1845577103309062,
+      "grad_norm": 79.53079693796676,
+      "learning_rate": 1.99333731792395e-07,
+      "logits/chosen": -1.5714216232299805,
+      "logits/rejected": -1.543687343597412,
+      "logps/chosen": -153.09767150878906,
+      "logps/rejected": -177.41847229003906,
+      "loss": 0.684,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.0551866851747036,
+      "rewards/margins": 0.03179415315389633,
+      "rewards/rejected": -0.08698083460330963,
+      "step": 160
+    },
+    {
+      "epoch": 0.18686468171004253,
+      "grad_norm": 73.91686194821585,
+      "learning_rate": 1.9928862722828242e-07,
+      "logits/chosen": -1.7037162780761719,
+      "logits/rejected": -1.675144076347351,
+      "logps/chosen": -153.01358032226562,
+      "logps/rejected": -175.93673706054688,
+      "loss": 0.6781,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.023145336657762527,
+      "rewards/margins": 0.06261962652206421,
+      "rewards/rejected": -0.08576496690511703,
+      "step": 162
+    },
+    {
+      "epoch": 0.18917165308917885,
+      "grad_norm": 76.57698818122466,
+      "learning_rate": 1.9924205096719357e-07,
+      "logits/chosen": -1.5918736457824707,
+      "logits/rejected": -1.4768625497817993,
+      "logps/chosen": -196.1853485107422,
+      "logps/rejected": -179.04530334472656,
+      "loss": 0.6692,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.04375737905502319,
+      "rewards/margins": 0.0569818913936615,
+      "rewards/rejected": -0.10073927044868469,
+      "step": 164
+    },
+    {
+      "epoch": 0.19147862446831518,
+      "grad_norm": 77.81644602396882,
+      "learning_rate": 1.9919400369950097e-07,
+      "logits/chosen": -1.4722576141357422,
+      "logits/rejected": -1.540255069732666,
+      "logps/chosen": -205.6660614013672,
+      "logps/rejected": -248.9489288330078,
+      "loss": 0.6786,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.043852321803569794,
+      "rewards/margins": 0.0406915545463562,
+      "rewards/rejected": -0.084543876349926,
+      "step": 166
+    },
+    {
+      "epoch": 0.19378559584745153,
+      "grad_norm": 75.44269350923808,
+      "learning_rate": 1.9914448613738103e-07,
+      "logits/chosen": -1.529039740562439,
+      "logits/rejected": -1.5173804759979248,
+      "logps/chosen": -202.2668914794922,
+      "logps/rejected": -226.52684020996094,
+      "loss": 0.6763,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.07004385441541672,
+      "rewards/margins": 0.021601226180791855,
+      "rewards/rejected": -0.09164508432149887,
+      "step": 168
+    },
+    {
+      "epoch": 0.19609256722658785,
+      "grad_norm": 76.79086636181425,
+      "learning_rate": 1.9909349901480347e-07,
+      "logits/chosen": -1.610205888748169,
+      "logits/rejected": -1.622270107269287,
+      "logps/chosen": -152.17263793945312,
+      "logps/rejected": -153.09571838378906,
+      "loss": 0.6826,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.049044616520404816,
+      "rewards/margins": 0.020372100174427032,
+      "rewards/rejected": -0.06941672414541245,
+      "step": 170
+    },
+    {
+      "epoch": 0.19839953860572418,
+      "grad_norm": 65.6162753738054,
+      "learning_rate": 1.990410430875205e-07,
+      "logits/chosen": -1.6482963562011719,
+      "logits/rejected": -1.6161506175994873,
+      "logps/chosen": -131.635986328125,
+      "logps/rejected": -142.7827606201172,
+      "loss": 0.6691,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.028512008488178253,
+      "rewards/margins": 0.06365156173706055,
+      "rewards/rejected": -0.0921635702252388,
+      "step": 172
+    },
+    {
+      "epoch": 0.2007065099848605,
+      "grad_norm": 90.14268267387868,
+      "learning_rate": 1.9898711913305547e-07,
+      "logits/chosen": -1.5566825866699219,
+      "logits/rejected": -1.6173129081726074,
+      "logps/chosen": -174.24017333984375,
+      "logps/rejected": -181.01629638671875,
+      "loss": 0.6766,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.05642353743314743,
+      "rewards/margins": 0.03944730758666992,
+      "rewards/rejected": -0.09587083756923676,
+      "step": 174
+    },
+    {
+      "epoch": 0.20301348136399683,
+      "grad_norm": 76.41450508388954,
+      "learning_rate": 1.9893172795069142e-07,
+      "logits/chosen": -1.5998440980911255,
+      "logits/rejected": -1.6545708179473877,
+      "logps/chosen": -156.8663330078125,
+      "logps/rejected": -159.1892547607422,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.05183999985456467,
+      "rewards/margins": 0.0032500806264579296,
+      "rewards/rejected": -0.055090077221393585,
+      "step": 176
+    },
+    {
+      "epoch": 0.20532045274313315,
+      "grad_norm": 87.56584383747318,
+      "learning_rate": 1.988748703614594e-07,
+      "logits/chosen": -1.6627997159957886,
+      "logits/rejected": -1.6540586948394775,
+      "logps/chosen": -155.84368896484375,
+      "logps/rejected": -186.67495727539062,
+      "loss": 0.6755,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.03810984268784523,
+      "rewards/margins": 0.029699210077524185,
+      "rewards/rejected": -0.06780905276536942,
+      "step": 178
+    },
+    {
+      "epoch": 0.20762742412226948,
+      "grad_norm": 70.4422512373765,
+      "learning_rate": 1.9881654720812592e-07,
+      "logits/chosen": -1.5361154079437256,
+      "logits/rejected": -1.610466480255127,
+      "logps/chosen": -115.56837463378906,
+      "logps/rejected": -142.57766723632812,
+      "loss": 0.6805,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.02763887494802475,
+      "rewards/margins": 0.0444108322262764,
+      "rewards/rejected": -0.07204970717430115,
+      "step": 180
+    },
+    {
+      "epoch": 0.2099343955014058,
+      "grad_norm": 71.9817063853092,
+      "learning_rate": 1.9875675935518094e-07,
+      "logits/chosen": -1.547518014907837,
+      "logits/rejected": -1.5500645637512207,
+      "logps/chosen": -226.55401611328125,
+      "logps/rejected": -206.99913024902344,
+      "loss": 0.6836,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.09524687379598618,
+      "rewards/margins": 0.004950803238898516,
+      "rewards/rejected": -0.1001976728439331,
+      "step": 182
+    },
+    {
+      "epoch": 0.21224136688054213,
+      "grad_norm": 84.4720159255109,
+      "learning_rate": 1.9869550768882454e-07,
+      "logits/chosen": -1.5599523782730103,
+      "logits/rejected": -1.5133187770843506,
+      "logps/chosen": -182.1778564453125,
+      "logps/rejected": -241.0075225830078,
+      "loss": 0.6671,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.057929787784814835,
+      "rewards/margins": 0.0736684501171112,
+      "rewards/rejected": -0.13159823417663574,
+      "step": 184
+    },
+    {
+      "epoch": 0.21454833825967848,
+      "grad_norm": 73.76638464490958,
+      "learning_rate": 1.9863279311695428e-07,
+      "logits/chosen": -1.4902362823486328,
+      "logits/rejected": -1.55423903465271,
+      "logps/chosen": -219.845703125,
+      "logps/rejected": -273.73712158203125,
+      "loss": 0.6773,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.07643218338489532,
+      "rewards/margins": 0.07768993079662323,
+      "rewards/rejected": -0.15412212908267975,
+      "step": 186
+    },
+    {
+      "epoch": 0.2168553096388148,
+      "grad_norm": 68.86254513199266,
+      "learning_rate": 1.985686165691514e-07,
+      "logits/chosen": -1.704699993133545,
+      "logits/rejected": -1.6342915296554565,
+      "logps/chosen": -120.14341735839844,
+      "logps/rejected": -114.1607666015625,
+      "loss": 0.6819,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.03834118694067001,
+      "rewards/margins": -0.00312834233045578,
+      "rewards/rejected": -0.03521284461021423,
+      "step": 188
+    },
+    {
+      "epoch": 0.21916228101795113,
+      "grad_norm": 77.39475970610044,
+      "learning_rate": 1.9850297899666707e-07,
+      "logits/chosen": -1.6166346073150635,
+      "logits/rejected": -1.666224479675293,
+      "logps/chosen": -138.47250366210938,
+      "logps/rejected": -183.75860595703125,
+      "loss": 0.6784,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.059065092355012894,
+      "rewards/margins": 0.0348266139626503,
+      "rewards/rejected": -0.09389171749353409,
+      "step": 190
+    },
+    {
+      "epoch": 0.22146925239708745,
+      "grad_norm": 79.62622809714712,
+      "learning_rate": 1.9843588137240855e-07,
+      "logits/chosen": -1.4786595106124878,
+      "logits/rejected": -1.5819900035858154,
+      "logps/chosen": -156.80630493164062,
+      "logps/rejected": -225.65887451171875,
+      "loss": 0.6727,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.06785481423139572,
+      "rewards/margins": 0.046741731464862823,
+      "rewards/rejected": -0.11459654569625854,
+      "step": 192
+    },
+    {
+      "epoch": 0.22377622377622378,
+      "grad_norm": 71.61908905732174,
+      "learning_rate": 1.9836732469092446e-07,
+      "logits/chosen": -1.7382750511169434,
+      "logits/rejected": -1.7238702774047852,
+      "logps/chosen": -135.97625732421875,
+      "logps/rejected": -134.9537353515625,
+      "loss": 0.6751,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.07399953901767731,
+      "rewards/margins": -0.0150267593562603,
+      "rewards/rejected": -0.05897277966141701,
+      "step": 194
+    },
+    {
+      "epoch": 0.2260831951553601,
+      "grad_norm": 77.39998086488785,
+      "learning_rate": 1.982973099683902e-07,
+      "logits/chosen": -1.6806734800338745,
+      "logits/rejected": -1.7225916385650635,
+      "logps/chosen": -139.36279296875,
+      "logps/rejected": -160.1461639404297,
+      "loss": 0.6592,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.05896836146712303,
+      "rewards/margins": 0.05167616903781891,
+      "rewards/rejected": -0.11064451932907104,
+      "step": 196
+    },
+    {
+      "epoch": 0.22839016653449642,
+      "grad_norm": 71.42176978474515,
+      "learning_rate": 1.982258382425928e-07,
+      "logits/chosen": -1.53923499584198,
+      "logits/rejected": -1.5509108304977417,
+      "logps/chosen": -145.9883575439453,
+      "logps/rejected": -173.95388793945312,
+      "loss": 0.6819,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.06814471632242203,
+      "rewards/margins": 0.05520961806178093,
+      "rewards/rejected": -0.12335430830717087,
+      "step": 198
+    },
+    {
+      "epoch": 0.23069713791363275,
+      "grad_norm": 65.61388633290626,
+      "learning_rate": 1.9815291057291578e-07,
+      "logits/chosen": -1.5758477449417114,
+      "logits/rejected": -1.6140058040618896,
+      "logps/chosen": -105.85581970214844,
+      "logps/rejected": -122.97176361083984,
+      "loss": 0.679,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.06785964965820312,
+      "rewards/margins": 0.01952926628291607,
+      "rewards/rejected": -0.08738891780376434,
+      "step": 200
+    },
+    {
+      "epoch": 0.23069713791363275,
+      "eval_logits/chosen": -1.5610222816467285,
+      "eval_logits/rejected": -1.462950587272644,
+      "eval_logps/chosen": -186.2912139892578,
+      "eval_logps/rejected": -151.6300048828125,
+      "eval_loss": 0.6922155618667603,
+      "eval_rewards/accuracies": 0.5600000023841858,
+      "eval_rewards/chosen": -0.11090204119682312,
+      "eval_rewards/margins": 0.0005596327828243375,
+      "eval_rewards/rejected": -0.11146167665719986,
+      "eval_runtime": 21.7555,
+      "eval_samples_per_second": 4.597,
+      "eval_steps_per_second": 1.149,
+      "step": 200
+    },
+    {
+      "epoch": 0.23300410929276907,
+      "grad_norm": 69.78727065961301,
+      "learning_rate": 1.9807852804032302e-07,
+      "logits/chosen": -1.4734337329864502,
+      "logits/rejected": -1.491389513015747,
+      "logps/chosen": -154.9561767578125,
+      "logps/rejected": -204.73797607421875,
+      "loss": 0.6705,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.046838290989398956,
+      "rewards/margins": 0.11147616803646088,
+      "rewards/rejected": -0.15831446647644043,
+      "step": 202
+    },
+    {
+      "epoch": 0.23531108067190543,
+      "grad_norm": 82.59595988703826,
+      "learning_rate": 1.980026917473432e-07,
+      "logits/chosen": -1.5889283418655396,
+      "logits/rejected": -1.7049566507339478,
+      "logps/chosen": -174.74598693847656,
+      "logps/rejected": -223.11842346191406,
+      "loss": 0.6737,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.05181250721216202,
+      "rewards/margins": 0.09021350741386414,
+      "rewards/rejected": -0.14202602207660675,
+      "step": 204
+    },
+    {
+      "epoch": 0.23761805205104175,
+      "grad_norm": 67.38723201323596,
+      "learning_rate": 1.9792540281805298e-07,
+      "logits/chosen": -1.4892499446868896,
+      "logits/rejected": -1.517817497253418,
+      "logps/chosen": -140.6378631591797,
+      "logps/rejected": -161.47348022460938,
+      "loss": 0.6682,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.08649797737598419,
+      "rewards/margins": 0.03692768141627312,
+      "rewards/rejected": -0.12342565506696701,
+      "step": 206
+    },
+    {
+      "epoch": 0.23992502343017807,
+      "grad_norm": 73.06374890842753,
+      "learning_rate": 1.9784666239806089e-07,
+      "logits/chosen": -1.5101206302642822,
+      "logits/rejected": -1.5768136978149414,
+      "logps/chosen": -164.27035522460938,
+      "logps/rejected": -203.25975036621094,
+      "loss": 0.6718,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.06570874899625778,
+      "rewards/margins": 0.09578941017389297,
+      "rewards/rejected": -0.16149815917015076,
+      "step": 208
+    },
+    {
+      "epoch": 0.2422319948093144,
+      "grad_norm": 75.60130708995507,
+      "learning_rate": 1.9776647165448983e-07,
+      "logits/chosen": -1.5699687004089355,
+      "logits/rejected": -1.520723581314087,
+      "logps/chosen": -188.6508331298828,
+      "logps/rejected": -217.18365478515625,
+      "loss": 0.6708,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.08720759302377701,
+      "rewards/margins": 0.02055392973124981,
+      "rewards/rejected": -0.10776151716709137,
+      "step": 210
+    },
+    {
+      "epoch": 0.24453896618845072,
+      "grad_norm": 76.08847895651103,
+      "learning_rate": 1.9768483177596006e-07,
+      "logits/chosen": -1.5900119543075562,
+      "logits/rejected": -1.6237448453903198,
+      "logps/chosen": -143.37664794921875,
+      "logps/rejected": -166.52413940429688,
+      "loss": 0.6689,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.0496542751789093,
+      "rewards/margins": 0.06798863410949707,
+      "rewards/rejected": -0.11764290928840637,
+      "step": 212
+    },
+    {
+      "epoch": 0.24684593756758705,
+      "grad_norm": 85.55002048517719,
+      "learning_rate": 1.9760174397257153e-07,
+      "logits/chosen": -1.5799341201782227,
+      "logits/rejected": -1.5739325284957886,
+      "logps/chosen": -187.42578125,
+      "logps/rejected": -227.91946411132812,
+      "loss": 0.6871,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.11932831257581711,
+      "rewards/margins": 0.00022871512919664383,
+      "rewards/rejected": -0.11955701559782028,
+      "step": 214
+    },
+    {
+      "epoch": 0.24915290894672337,
+      "grad_norm": 79.3908422125236,
+      "learning_rate": 1.97517209475886e-07,
+      "logits/chosen": -1.578735589981079,
+      "logits/rejected": -1.7003827095031738,
+      "logps/chosen": -147.41778564453125,
+      "logps/rejected": -185.31602478027344,
+      "loss": 0.6678,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.07496561855077744,
+      "rewards/margins": 0.0857120081782341,
+      "rewards/rejected": -0.16067762672901154,
+      "step": 216
+    },
+    {
+      "epoch": 0.2514598803258597,
+      "grad_norm": 78.5386783375159,
+      "learning_rate": 1.9743122953890854e-07,
+      "logits/chosen": -1.5871162414550781,
+      "logits/rejected": -1.5231672525405884,
+      "logps/chosen": -174.3480682373047,
+      "logps/rejected": -196.07998657226562,
+      "loss": 0.6548,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.07399033010005951,
+      "rewards/margins": 0.05520808696746826,
+      "rewards/rejected": -0.12919840216636658,
+      "step": 218
+    },
+    {
+      "epoch": 0.253766851704996,
+      "grad_norm": 80.06682238716625,
+      "learning_rate": 1.9734380543606927e-07,
+      "logits/chosen": -1.643662452697754,
+      "logits/rejected": -1.6430741548538208,
+      "logps/chosen": -200.37826538085938,
+      "logps/rejected": -207.41136169433594,
+      "loss": 0.6815,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.07183612138032913,
+      "rewards/margins": 0.07066242396831512,
+      "rewards/rejected": -0.14249853789806366,
+      "step": 220
+    },
+    {
+      "epoch": 0.25607382308413235,
+      "grad_norm": 73.47957521005397,
+      "learning_rate": 1.972549384632043e-07,
+      "logits/chosen": -1.5852243900299072,
+      "logits/rejected": -1.736151099205017,
+      "logps/chosen": -167.52194213867188,
+      "logps/rejected": -218.90122985839844,
+      "loss": 0.6604,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.0951998233795166,
+      "rewards/margins": 0.027591748163104057,
+      "rewards/rejected": -0.12279157340526581,
+      "step": 222
+    },
+    {
+      "epoch": 0.25838079446326867,
+      "grad_norm": 79.05067580811021,
+      "learning_rate": 1.9716462993753655e-07,
+      "logits/chosen": -1.476207971572876,
+      "logits/rejected": -1.5456207990646362,
+      "logps/chosen": -288.57379150390625,
+      "logps/rejected": -338.8498840332031,
+      "loss": 0.6567,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.17371979355812073,
+      "rewards/margins": 0.15009327232837677,
+      "rewards/rejected": -0.3238130807876587,
+      "step": 224
+    },
+    {
+      "epoch": 0.260687765842405,
+      "grad_norm": 67.9414989656304,
+      "learning_rate": 1.9707288119765622e-07,
+      "logits/chosen": -1.5781480073928833,
+      "logits/rejected": -1.569219708442688,
+      "logps/chosen": -124.80656433105469,
+      "logps/rejected": -141.52476501464844,
+      "loss": 0.6732,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.12547817826271057,
+      "rewards/margins": 0.03562304750084877,
+      "rewards/rejected": -0.16110120713710785,
+      "step": 226
+    },
+    {
+      "epoch": 0.2629947372215413,
+      "grad_norm": 78.11670530443735,
+      "learning_rate": 1.9697969360350095e-07,
+      "logits/chosen": -1.6346409320831299,
+      "logits/rejected": -1.565224051475525,
+      "logps/chosen": -178.9912109375,
+      "logps/rejected": -190.82681274414062,
+      "loss": 0.6661,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.10180149972438812,
+      "rewards/margins": 0.05022910237312317,
+      "rewards/rejected": -0.1520306020975113,
+      "step": 228
+    },
+    {
+      "epoch": 0.2653017086006777,
+      "grad_norm": 68.3329236115507,
+      "learning_rate": 1.968850685363357e-07,
+      "logits/chosen": -1.7000384330749512,
+      "logits/rejected": -1.7287462949752808,
+      "logps/chosen": -199.75430297851562,
+      "logps/rejected": -241.5220947265625,
+      "loss": 0.6556,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.09640266001224518,
+      "rewards/margins": 0.09287622570991516,
+      "rewards/rejected": -0.18927887082099915,
+      "step": 230
+    },
+    {
+      "epoch": 0.267608679979814,
+      "grad_norm": 82.26094651176318,
+      "learning_rate": 1.9678900739873226e-07,
+      "logits/chosen": -1.677142858505249,
+      "logits/rejected": -1.6745737791061401,
+      "logps/chosen": -170.59425354003906,
+      "logps/rejected": -181.05661010742188,
+      "loss": 0.6694,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.1134408637881279,
+      "rewards/margins": 0.036339692771434784,
+      "rewards/rejected": -0.14978057146072388,
+      "step": 232
+    },
+    {
+      "epoch": 0.26991565135895035,
+      "grad_norm": 78.36181831181821,
+      "learning_rate": 1.966915116145484e-07,
+      "logits/chosen": -1.4915921688079834,
+      "logits/rejected": -1.523095726966858,
+      "logps/chosen": -155.88290405273438,
+      "logps/rejected": -164.45022583007812,
+      "loss": 0.6567,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.0988837480545044,
+      "rewards/margins": 0.09765380620956421,
+      "rewards/rejected": -0.196537584066391,
+      "step": 234
+    },
+    {
+      "epoch": 0.2722226227380867,
+      "grad_norm": 83.64468364737313,
+      "learning_rate": 1.965925826289068e-07,
+      "logits/chosen": -1.6482906341552734,
+      "logits/rejected": -1.6469372510910034,
+      "logps/chosen": -185.45001220703125,
+      "logps/rejected": -208.0437469482422,
+      "loss": 0.6708,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.0873761773109436,
+      "rewards/margins": 0.06748253107070923,
+      "rewards/rejected": -0.15485870838165283,
+      "step": 236
+    },
+    {
+      "epoch": 0.274529594117223,
+      "grad_norm": 74.16820675500993,
+      "learning_rate": 1.964922219081738e-07,
+      "logits/chosen": -1.764983057975769,
+      "logits/rejected": -1.7145969867706299,
+      "logps/chosen": -223.3017578125,
+      "logps/rejected": -218.1916046142578,
+      "loss": 0.6555,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.11543229222297668,
+      "rewards/margins": 0.12305162101984024,
+      "rewards/rejected": -0.23848390579223633,
+      "step": 238
+    },
+    {
+      "epoch": 0.2768365654963593,
+      "grad_norm": 75.00121800473413,
+      "learning_rate": 1.9639043093993727e-07,
+      "logits/chosen": -1.5264173746109009,
+      "logits/rejected": -1.4717910289764404,
+      "logps/chosen": -178.43338012695312,
+      "logps/rejected": -188.60101318359375,
+      "loss": 0.6481,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.09335748851299286,
+      "rewards/margins": 0.026005972176790237,
+      "rewards/rejected": -0.1193634569644928,
+      "step": 240
+    },
+    {
+      "epoch": 0.27914353687549565,
+      "grad_norm": 64.46972140040022,
+      "learning_rate": 1.9628721123298492e-07,
+      "logits/chosen": -1.6837042570114136,
+      "logits/rejected": -1.6980068683624268,
+      "logps/chosen": -161.4723663330078,
+      "logps/rejected": -171.20248413085938,
+      "loss": 0.6609,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.11237211525440216,
+      "rewards/margins": 0.049555521458387375,
+      "rewards/rejected": -0.16192764043807983,
+      "step": 242
+    },
+    {
+      "epoch": 0.28145050825463197,
+      "grad_norm": 66.85001786944659,
+      "learning_rate": 1.961825643172819e-07,
+      "logits/chosen": -1.5771496295928955,
+      "logits/rejected": -1.5039366483688354,
+      "logps/chosen": -158.33685302734375,
+      "logps/rejected": -160.24057006835938,
+      "loss": 0.6701,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.14522022008895874,
+      "rewards/margins": 0.04340605437755585,
+      "rewards/rejected": -0.1886262595653534,
+      "step": 244
+    },
+    {
+      "epoch": 0.2837574796337683,
+      "grad_norm": 76.39303352760503,
+      "learning_rate": 1.9607649174394787e-07,
+      "logits/chosen": -1.4101349115371704,
+      "logits/rejected": -1.4513871669769287,
+      "logps/chosen": -147.43826293945312,
+      "logps/rejected": -182.31005859375,
+      "loss": 0.6596,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.08130650967359543,
+      "rewards/margins": 0.0953046903014183,
+      "rewards/rejected": -0.17661119997501373,
+      "step": 246
+    },
+    {
+      "epoch": 0.2860644510129046,
+      "grad_norm": 84.03579410656208,
+      "learning_rate": 1.959689950852343e-07,
+      "logits/chosen": -1.6520403623580933,
+      "logits/rejected": -1.6739228963851929,
+      "logps/chosen": -172.19305419921875,
+      "logps/rejected": -184.803466796875,
+      "loss": 0.6669,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.16027307510375977,
+      "rewards/margins": 0.02343956008553505,
+      "rewards/rejected": -0.1837126612663269,
+      "step": 248
+    },
+    {
+      "epoch": 0.28837142239204094,
+      "grad_norm": 78.31280460476106,
+      "learning_rate": 1.9586007593450095e-07,
+      "logits/chosen": -1.568188190460205,
+      "logits/rejected": -1.586582064628601,
+      "logps/chosen": -169.95675659179688,
+      "logps/rejected": -188.78858947753906,
+      "loss": 0.6779,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.1373595893383026,
+      "rewards/margins": 0.02867070771753788,
+      "rewards/rejected": -0.16603030264377594,
+      "step": 250
+    },
+    {
+      "epoch": 0.29067839377117727,
+      "grad_norm": 77.82835801736759,
+      "learning_rate": 1.957497359061924e-07,
+      "logits/chosen": -1.5796047449111938,
+      "logits/rejected": -1.5543608665466309,
+      "logps/chosen": -191.53219604492188,
+      "logps/rejected": -220.70361328125,
+      "loss": 0.6393,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.15552642941474915,
+      "rewards/margins": 0.09192191064357758,
+      "rewards/rejected": -0.24744835495948792,
+      "step": 252
+    },
+    {
+      "epoch": 0.2929853651503136,
+      "grad_norm": 81.6835137198976,
+      "learning_rate": 1.956379766358141e-07,
+      "logits/chosen": -1.5779876708984375,
+      "logits/rejected": -1.504298448562622,
+      "logps/chosen": -218.59942626953125,
+      "logps/rejected": -230.2102813720703,
+      "loss": 0.6635,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.14433127641677856,
+      "rewards/margins": 0.08938172459602356,
+      "rewards/rejected": -0.23371298611164093,
+      "step": 254
+    },
+    {
+      "epoch": 0.2952923365294499,
+      "grad_norm": 74.03670184892391,
+      "learning_rate": 1.9552479977990798e-07,
+      "logits/chosen": -1.6765474081039429,
+      "logits/rejected": -1.643741488456726,
+      "logps/chosen": -185.69444274902344,
+      "logps/rejected": -199.7008819580078,
+      "loss": 0.676,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.14419934153556824,
+      "rewards/margins": 0.016861233860254288,
+      "rewards/rejected": -0.16106057167053223,
+      "step": 256
+    },
+    {
+      "epoch": 0.29759930790858624,
+      "grad_norm": 79.12914884219855,
+      "learning_rate": 1.954102070160281e-07,
+      "logits/chosen": -1.6632733345031738,
+      "logits/rejected": -1.6073827743530273,
+      "logps/chosen": -149.79641723632812,
+      "logps/rejected": -174.7237091064453,
+      "loss": 0.6638,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.10197722166776657,
+      "rewards/margins": 0.07854845374822617,
+      "rewards/rejected": -0.18052567541599274,
+      "step": 258
+    },
+    {
+      "epoch": 0.29990627928772257,
+      "grad_norm": 80.451175401901,
+      "learning_rate": 1.9529420004271567e-07,
+      "logits/chosen": -1.5313125848770142,
+      "logits/rejected": -1.5560095310211182,
+      "logps/chosen": -207.1497802734375,
+      "logps/rejected": -222.1211395263672,
+      "loss": 0.6407,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.16675114631652832,
+      "rewards/margins": 0.1034877672791481,
+      "rewards/rejected": -0.2702389061450958,
+      "step": 260
+    },
+    {
+      "epoch": 0.3022132506668589,
+      "grad_norm": 66.85531080853532,
+      "learning_rate": 1.9517678057947382e-07,
+      "logits/chosen": -1.6430004835128784,
+      "logits/rejected": -1.597357153892517,
+      "logps/chosen": -135.1138153076172,
+      "logps/rejected": -132.63619995117188,
+      "loss": 0.6618,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.11752544343471527,
+      "rewards/margins": 0.03515633940696716,
+      "rewards/rejected": -0.15268178284168243,
+      "step": 262
+    },
+    {
+      "epoch": 0.3045202220459952,
+      "grad_norm": 80.22448615221649,
+      "learning_rate": 1.9505795036674232e-07,
+      "logits/chosen": -1.6319184303283691,
+      "logits/rejected": -1.4991899728775024,
+      "logps/chosen": -217.16680908203125,
+      "logps/rejected": -245.2107696533203,
+      "loss": 0.6523,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.18451935052871704,
+      "rewards/margins": 0.11840308457612991,
+      "rewards/rejected": -0.30292242765426636,
+      "step": 264
+    },
+    {
+      "epoch": 0.3068271934251316,
+      "grad_norm": 69.95576974969472,
+      "learning_rate": 1.9493771116587156e-07,
+      "logits/chosen": -1.5522364377975464,
+      "logits/rejected": -1.5948469638824463,
+      "logps/chosen": -113.81831359863281,
+      "logps/rejected": -155.99346923828125,
+      "loss": 0.6551,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.08541279286146164,
+      "rewards/margins": 0.14459526538848877,
+      "rewards/rejected": -0.230008065700531,
+      "step": 266
+    },
+    {
+      "epoch": 0.3091341648042679,
+      "grad_norm": 75.25744246014891,
+      "learning_rate": 1.9481606475909656e-07,
+      "logits/chosen": -1.500025749206543,
+      "logits/rejected": -1.5494239330291748,
+      "logps/chosen": -125.84722900390625,
+      "logps/rejected": -164.76669311523438,
+      "loss": 0.6526,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.08980143815279007,
+      "rewards/margins": 0.17133310437202454,
+      "rewards/rejected": -0.2611345648765564,
+      "step": 268
+    },
+    {
+      "epoch": 0.31144113618340424,
+      "grad_norm": 77.53434606640313,
+      "learning_rate": 1.9469301294951057e-07,
+      "logits/chosen": -1.6267601251602173,
+      "logits/rejected": -1.5587116479873657,
+      "logps/chosen": -172.08139038085938,
+      "logps/rejected": -181.32717895507812,
+      "loss": 0.6596,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.1692037582397461,
+      "rewards/margins": 0.051171936094760895,
+      "rewards/rejected": -0.2203756868839264,
+      "step": 270
+    },
+    {
+      "epoch": 0.31374810756254057,
+      "grad_norm": 74.84897771580975,
+      "learning_rate": 1.9456855756103816e-07,
+      "logits/chosen": -1.5624661445617676,
+      "logits/rejected": -1.6530312299728394,
+      "logps/chosen": -147.84597778320312,
+      "logps/rejected": -174.6589813232422,
+      "loss": 0.6707,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.13743659853935242,
+      "rewards/margins": 0.05220307409763336,
+      "rewards/rejected": -0.18963965773582458,
+      "step": 272
+    },
+    {
+      "epoch": 0.3160550789416769,
+      "grad_norm": 71.99044362933952,
+      "learning_rate": 1.9444270043840852e-07,
+      "logits/chosen": -1.6625701189041138,
+      "logits/rejected": -1.5914949178695679,
+      "logps/chosen": -147.29147338867188,
+      "logps/rejected": -129.6570587158203,
+      "loss": 0.6831,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.21893730759620667,
+      "rewards/margins": -0.0283275805413723,
+      "rewards/rejected": -0.19060972332954407,
+      "step": 274
+    },
+    {
+      "epoch": 0.3183620503208132,
+      "grad_norm": 75.21160091684173,
+      "learning_rate": 1.9431544344712772e-07,
+      "logits/chosen": -1.4378788471221924,
+      "logits/rejected": -1.3864963054656982,
+      "logps/chosen": -147.2783660888672,
+      "logps/rejected": -177.4646759033203,
+      "loss": 0.6472,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.11688334494829178,
+      "rewards/margins": 0.11695411056280136,
+      "rewards/rejected": -0.23383745551109314,
+      "step": 276
+    },
+    {
+      "epoch": 0.32066902169994954,
+      "grad_norm": 72.07898599790276,
+      "learning_rate": 1.9418678847345146e-07,
+      "logits/chosen": -1.5210872888565063,
+      "logits/rejected": -1.5768458843231201,
+      "logps/chosen": -164.58419799804688,
+      "logps/rejected": -213.6575469970703,
+      "loss": 0.6664,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.12316928803920746,
+      "rewards/margins": 0.07401876151561737,
+      "rewards/rejected": -0.19718804955482483,
+      "step": 278
+    },
+    {
+      "epoch": 0.32297599307908587,
+      "grad_norm": 67.17404804695744,
+      "learning_rate": 1.9405673742435676e-07,
+      "logits/chosen": -1.5087511539459229,
+      "logits/rejected": -1.5612874031066895,
+      "logps/chosen": -142.5220947265625,
+      "logps/rejected": -195.3551483154297,
+      "loss": 0.6718,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.14393991231918335,
+      "rewards/margins": 0.11825156211853027,
+      "rewards/rejected": -0.2621914744377136,
+      "step": 280
+    },
+    {
+      "epoch": 0.3252829644582222,
+      "grad_norm": 81.75237089659649,
+      "learning_rate": 1.939252922275139e-07,
+      "logits/chosen": -1.6113684177398682,
+      "logits/rejected": -1.520400047302246,
+      "logps/chosen": -215.8910675048828,
+      "logps/rejected": -227.26637268066406,
+      "loss": 0.6556,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.2654890716075897,
+      "rewards/margins": 0.09542025625705719,
+      "rewards/rejected": -0.3609093129634857,
+      "step": 282
+    },
+    {
+      "epoch": 0.3275899358373585,
+      "grad_norm": 65.02297736065502,
+      "learning_rate": 1.937924548312578e-07,
+      "logits/chosen": -1.6812703609466553,
+      "logits/rejected": -1.7281326055526733,
+      "logps/chosen": -130.5011749267578,
+      "logps/rejected": -195.49452209472656,
+      "loss": 0.6431,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.12183240056037903,
+      "rewards/margins": 0.12844915688037872,
+      "rewards/rejected": -0.25028154253959656,
+      "step": 284
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 75.13263031113792,
+      "learning_rate": 1.9365822720455912e-07,
+      "logits/chosen": -1.4847445487976074,
+      "logits/rejected": -1.4161133766174316,
+      "logps/chosen": -154.5245361328125,
+      "logps/rejected": -203.3861541748047,
+      "loss": 0.6537,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.16228517889976501,
+      "rewards/margins": 0.12002203613519669,
+      "rewards/rejected": -0.2823072075843811,
+      "step": 286
+    },
+    {
+      "epoch": 0.33220387859563116,
+      "grad_norm": 78.41024724428831,
+      "learning_rate": 1.935226113369951e-07,
+      "logits/chosen": -1.686346173286438,
+      "logits/rejected": -1.6542606353759766,
+      "logps/chosen": -172.25059509277344,
+      "logps/rejected": -199.93182373046875,
+      "loss": 0.6469,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.12491661310195923,
+      "rewards/margins": 0.12406705319881439,
+      "rewards/rejected": -0.24898366630077362,
+      "step": 288
+    },
+    {
+      "epoch": 0.3345108499747675,
+      "grad_norm": 74.32689822052723,
+      "learning_rate": 1.9338560923872006e-07,
+      "logits/chosen": -1.5119750499725342,
+      "logits/rejected": -1.524541974067688,
+      "logps/chosen": -159.21376037597656,
+      "logps/rejected": -237.09561157226562,
+      "loss": 0.6455,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.1832338273525238,
+      "rewards/margins": 0.2291288673877716,
+      "rewards/rejected": -0.4123626947402954,
+      "step": 290
+    },
+    {
+      "epoch": 0.3368178213539038,
+      "grad_norm": 77.04623177811982,
+      "learning_rate": 1.9324722294043556e-07,
+      "logits/chosen": -1.6212831735610962,
+      "logits/rejected": -1.5947524309158325,
+      "logps/chosen": -187.361572265625,
+      "logps/rejected": -187.34519958496094,
+      "loss": 0.6585,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.24990221858024597,
+      "rewards/margins": 0.07834864407777786,
+      "rewards/rejected": -0.3282508850097656,
+      "step": 292
+    },
+    {
+      "epoch": 0.33912479273304014,
+      "grad_norm": 83.55231847560428,
+      "learning_rate": 1.9310745449336044e-07,
+      "logits/chosen": -1.58076012134552,
+      "logits/rejected": -1.5445674657821655,
+      "logps/chosen": -192.48617553710938,
+      "logps/rejected": -215.64193725585938,
+      "loss": 0.6418,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.1813565194606781,
+      "rewards/margins": 0.1242499127984047,
+      "rewards/rejected": -0.3056064546108246,
+      "step": 294
+    },
+    {
+      "epoch": 0.34143176411217646,
+      "grad_norm": 73.20320061572161,
+      "learning_rate": 1.929663059692002e-07,
+      "logits/chosen": -1.477115273475647,
+      "logits/rejected": -1.5140092372894287,
+      "logps/chosen": -154.4539794921875,
+      "logps/rejected": -214.9960174560547,
+      "loss": 0.6894,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.2464270293712616,
+      "rewards/margins": 0.08608925342559814,
+      "rewards/rejected": -0.33251628279685974,
+      "step": 296
+    },
+    {
+      "epoch": 0.3437387354913128,
+      "grad_norm": 82.85464536249332,
+      "learning_rate": 1.928237794601165e-07,
+      "logits/chosen": -1.5687949657440186,
+      "logits/rejected": -1.6849851608276367,
+      "logps/chosen": -140.14784240722656,
+      "logps/rejected": -234.17706298828125,
+      "loss": 0.6525,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.1264043152332306,
+      "rewards/margins": 0.24397864937782288,
+      "rewards/rejected": -0.3703829348087311,
+      "step": 298
+    },
+    {
+      "epoch": 0.34604570687044917,
+      "grad_norm": 65.65777237412837,
+      "learning_rate": 1.9267987707869604e-07,
+      "logits/chosen": -1.4391192197799683,
+      "logits/rejected": -1.4724018573760986,
+      "logps/chosen": -153.69284057617188,
+      "logps/rejected": -173.3372039794922,
+      "loss": 0.6486,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.16697266697883606,
+      "rewards/margins": 0.13511566817760468,
+      "rewards/rejected": -0.30208835005760193,
+      "step": 300
+    },
+    {
+      "epoch": 0.34604570687044917,
+      "eval_logits/chosen": -1.5305781364440918,
+      "eval_logits/rejected": -1.4347938299179077,
+      "eval_logps/chosen": -187.96263122558594,
+      "eval_logps/rejected": -153.34820556640625,
+      "eval_loss": 0.678679347038269,
+      "eval_rewards/accuracies": 0.6399999856948853,
+      "eval_rewards/chosen": -0.278046578168869,
+      "eval_rewards/margins": 0.005234198644757271,
+      "eval_rewards/rejected": -0.28328076004981995,
+      "eval_runtime": 21.7114,
+      "eval_samples_per_second": 4.606,
+      "eval_steps_per_second": 1.151,
+      "step": 300
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1732,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 300,
+  "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": 1,
+  "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:f3f8696b28a6fe67b13ea2240f8d6484e289992c7829cca17e224a948887cf7f
+size 7352

last-checkpoint/zero_to_fp32.py

@@ -0,0 +1,587 @@
+#!/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 . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+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)
+
+        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 files:
+        state_dict = torch.load(f, map_location=device)
+        # 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}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) 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):
+    """
+    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)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+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 _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()
+            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):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _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")
+
+
+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 = fp32_flat_groups[0].numel() * 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
+    for name, shape in param_shapes.items():
+
+        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}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        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):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _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 get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    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``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    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.
+
+    """
+    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")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    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_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``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``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+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_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    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("-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_file, tag=args.tag)