Training in progress, step 300, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "RyanYr/openchat-3.6-8b-20240522_iter2",
+  "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 sha256:13e8d45659e912109db56055fd199574472aaa2d780fa59cadbebfd9d6a993a3
+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 sha256:9411798afe65d9b524c6b62f847006f7425bd2bf0b39e12418d5ec85b5b4b5b3
+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:c2dd13a52c9f5fa10b63bf48182f0a2aa01a71abffb652229b61160e7ddd5187
+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 sha256:7beae0bf531b1c8636a5d87db1ac80c7143ca92d6cdb61667cea5115b8a9df61
+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:b2281cb21ad854a3db059aa689d7c74452cb2008fb15f3402ad06513a6ed68d7
+size 4976698672

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49cd637191fe742ce29f784563dc89109beb1128aa3fee60b2a9e24ea94cbdd
+size 4999802720

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30aa2ab618d4be5f0ba7e005ac657417f4e515f10a9b0fbb2e7b29fd1ca2b390
+size 4915916176

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc0b3808e3294cd9ec41a837580c875a4c99d9ec14356c982b552e0c92df4b8
+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 sha256:0db895d97b25045a4a7490f3a2585ba8b172dd50ebe580778062498c071cac97
+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": 0.3474484256243214,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0023163228374954757,
+      "grad_norm": 107.28771573687173,
+      "learning_rate": 4e-09,
+      "logits/chosen": -1.124485731124878,
+      "logits/rejected": -1.2086994647979736,
+      "logps/chosen": -156.01296997070312,
+      "logps/rejected": -208.54991149902344,
+      "loss": 0.6233,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.07398775964975357,
+      "rewards/margins": 0.2667727768421173,
+      "rewards/rejected": -0.19278500974178314,
+      "step": 2
+    },
+    {
+      "epoch": 0.0046326456749909515,
+      "grad_norm": 88.08812844747567,
+      "learning_rate": 8e-09,
+      "logits/chosen": -1.2528715133666992,
+      "logits/rejected": -1.2828329801559448,
+      "logps/chosen": -132.4397430419922,
+      "logps/rejected": -172.45309448242188,
+      "loss": 0.7004,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.17529334127902985,
+      "rewards/margins": 0.35418701171875,
+      "rewards/rejected": -0.17889368534088135,
+      "step": 4
+    },
+    {
+      "epoch": 0.006948968512486428,
+      "grad_norm": 91.60766301044009,
+      "learning_rate": 1.1999999999999998e-08,
+      "logits/chosen": -1.2843875885009766,
+      "logits/rejected": -1.280484914779663,
+      "logps/chosen": -152.78907775878906,
+      "logps/rejected": -152.23944091796875,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.041480474174022675,
+      "rewards/margins": 0.14676526188850403,
+      "rewards/rejected": -0.1882457733154297,
+      "step": 6
+    },
+    {
+      "epoch": 0.009265291349981903,
+      "grad_norm": 98.62741523160896,
+      "learning_rate": 1.6e-08,
+      "logits/chosen": -1.398779273033142,
+      "logits/rejected": -1.4048051834106445,
+      "logps/chosen": -169.36114501953125,
+      "logps/rejected": -187.72393798828125,
+      "loss": 0.6494,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": 0.06773313134908676,
+      "rewards/margins": 0.3909590244293213,
+      "rewards/rejected": -0.32322588562965393,
+      "step": 8
+    },
+    {
+      "epoch": 0.01158161418747738,
+      "grad_norm": 103.80152080031493,
+      "learning_rate": 2e-08,
+      "logits/chosen": -1.2080261707305908,
+      "logits/rejected": -1.287600040435791,
+      "logps/chosen": -143.546875,
+      "logps/rejected": -167.290283203125,
+      "loss": 0.714,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.024446196854114532,
+      "rewards/margins": 0.028562966734170914,
+      "rewards/rejected": -0.004116774536669254,
+      "step": 10
+    },
+    {
+      "epoch": 0.013897937024972856,
+      "grad_norm": 102.45515514662566,
+      "learning_rate": 2.3999999999999997e-08,
+      "logits/chosen": -1.3106777667999268,
+      "logits/rejected": -1.2940219640731812,
+      "logps/chosen": -146.94171142578125,
+      "logps/rejected": -157.75350952148438,
+      "loss": 0.6722,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.09310206025838852,
+      "rewards/margins": 0.06749637424945831,
+      "rewards/rejected": 0.0256056971848011,
+      "step": 12
+    },
+    {
+      "epoch": 0.01621425986246833,
+      "grad_norm": 98.56963705951901,
+      "learning_rate": 2.8000000000000003e-08,
+      "logits/chosen": -1.2968071699142456,
+      "logits/rejected": -1.3280229568481445,
+      "logps/chosen": -124.2802505493164,
+      "logps/rejected": -141.4438018798828,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.11542778462171555,
+      "rewards/margins": 0.1968868374824524,
+      "rewards/rejected": -0.08145906031131744,
+      "step": 14
+    },
+    {
+      "epoch": 0.018530582699963806,
+      "grad_norm": 126.73593067586688,
+      "learning_rate": 3.2e-08,
+      "logits/chosen": -1.2126774787902832,
+      "logits/rejected": -1.3230162858963013,
+      "logps/chosen": -143.24264526367188,
+      "logps/rejected": -150.46603393554688,
+      "loss": 0.6388,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.02438124269247055,
+      "rewards/margins": 0.4613185226917267,
+      "rewards/rejected": -0.43693727254867554,
+      "step": 16
+    },
+    {
+      "epoch": 0.020846905537459284,
+      "grad_norm": 125.55466393152622,
+      "learning_rate": 3.6e-08,
+      "logits/chosen": -1.1398718357086182,
+      "logits/rejected": -1.2096312046051025,
+      "logps/chosen": -168.44686889648438,
+      "logps/rejected": -209.51075744628906,
+      "loss": 0.5937,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.058702100068330765,
+      "rewards/margins": 0.36269423365592957,
+      "rewards/rejected": -0.3039921820163727,
+      "step": 18
+    },
+    {
+      "epoch": 0.02316322837495476,
+      "grad_norm": 99.14617505813268,
+      "learning_rate": 4e-08,
+      "logits/chosen": -1.18150794506073,
+      "logits/rejected": -1.2542356252670288,
+      "logps/chosen": -167.63018798828125,
+      "logps/rejected": -192.35606384277344,
+      "loss": 0.6576,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.0018138289451599121,
+      "rewards/margins": 0.2771007716655731,
+      "rewards/rejected": -0.27891457080841064,
+      "step": 20
+    },
+    {
+      "epoch": 0.025479551212450234,
+      "grad_norm": 91.07306017372633,
+      "learning_rate": 4.4e-08,
+      "logits/chosen": -1.2071597576141357,
+      "logits/rejected": -1.182037115097046,
+      "logps/chosen": -144.98622131347656,
+      "logps/rejected": -141.1741180419922,
+      "loss": 0.5928,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.08638761937618256,
+      "rewards/margins": 0.27829694747924805,
+      "rewards/rejected": -0.1919093132019043,
+      "step": 22
+    },
+    {
+      "epoch": 0.027795874049945712,
+      "grad_norm": 89.9597440051718,
+      "learning_rate": 4.799999999999999e-08,
+      "logits/chosen": -1.31764554977417,
+      "logits/rejected": -1.3588660955429077,
+      "logps/chosen": -88.85529327392578,
+      "logps/rejected": -98.12319946289062,
+      "loss": 0.6819,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.034286849200725555,
+      "rewards/margins": -0.03185552358627319,
+      "rewards/rejected": 0.06614237278699875,
+      "step": 24
+    },
+    {
+      "epoch": 0.030112196887441187,
+      "grad_norm": 103.03824203236205,
+      "learning_rate": 5.2e-08,
+      "logits/chosen": -1.2300812005996704,
+      "logits/rejected": -1.3013834953308105,
+      "logps/chosen": -136.9016571044922,
+      "logps/rejected": -158.10443115234375,
+      "loss": 0.6651,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.02496076375246048,
+      "rewards/margins": 0.11402938514947891,
+      "rewards/rejected": -0.08906861394643784,
+      "step": 26
+    },
+    {
+      "epoch": 0.03242851972493666,
+      "grad_norm": 82.73233095035695,
+      "learning_rate": 5.6000000000000005e-08,
+      "logits/chosen": -1.2323240041732788,
+      "logits/rejected": -1.279797911643982,
+      "logps/chosen": -129.50372314453125,
+      "logps/rejected": -149.10198974609375,
+      "loss": 0.6957,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.01655733771622181,
+      "rewards/margins": 0.28547346591949463,
+      "rewards/rejected": -0.26891613006591797,
+      "step": 28
+    },
+    {
+      "epoch": 0.03474484256243214,
+      "grad_norm": 81.35170136123334,
+      "learning_rate": 6e-08,
+      "logits/chosen": -1.2328161001205444,
+      "logits/rejected": -1.2630647420883179,
+      "logps/chosen": -115.19596862792969,
+      "logps/rejected": -122.42259216308594,
+      "loss": 0.6297,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.05066928267478943,
+      "rewards/margins": 0.29739153385162354,
+      "rewards/rejected": -0.24672222137451172,
+      "step": 30
+    },
+    {
+      "epoch": 0.03706116539992761,
+      "grad_norm": 97.64254508804386,
+      "learning_rate": 6.4e-08,
+      "logits/chosen": -1.203454852104187,
+      "logits/rejected": -1.2570163011550903,
+      "logps/chosen": -130.0023193359375,
+      "logps/rejected": -140.43641662597656,
+      "loss": 0.6388,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.22588226199150085,
+      "rewards/margins": 0.21626117825508118,
+      "rewards/rejected": 0.009621085599064827,
+      "step": 32
+    },
+    {
+      "epoch": 0.03937748823742309,
+      "grad_norm": 77.47976131311218,
+      "learning_rate": 6.8e-08,
+      "logits/chosen": -1.3255200386047363,
+      "logits/rejected": -1.34698486328125,
+      "logps/chosen": -154.41970825195312,
+      "logps/rejected": -185.44137573242188,
+      "loss": 0.6644,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.219247967004776,
+      "rewards/margins": 0.5436465740203857,
+      "rewards/rejected": -0.32439863681793213,
+      "step": 34
+    },
+    {
+      "epoch": 0.04169381107491857,
+      "grad_norm": 116.81809749704041,
+      "learning_rate": 7.2e-08,
+      "logits/chosen": -1.172755479812622,
+      "logits/rejected": -1.2560861110687256,
+      "logps/chosen": -140.07249450683594,
+      "logps/rejected": -150.0348358154297,
+      "loss": 0.6966,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.06599292159080505,
+      "rewards/margins": 0.17668266594409943,
+      "rewards/rejected": -0.2426755726337433,
+      "step": 36
+    },
+    {
+      "epoch": 0.04401013391241404,
+      "grad_norm": 106.17036044375986,
+      "learning_rate": 7.599999999999999e-08,
+      "logits/chosen": -1.2809267044067383,
+      "logits/rejected": -1.3268154859542847,
+      "logps/chosen": -150.99420166015625,
+      "logps/rejected": -156.5166473388672,
+      "loss": 0.6641,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.0937371775507927,
+      "rewards/margins": 0.24054178595542908,
+      "rewards/rejected": -0.14680461585521698,
+      "step": 38
+    },
+    {
+      "epoch": 0.04632645674990952,
+      "grad_norm": 92.41470133544318,
+      "learning_rate": 8e-08,
+      "logits/chosen": -1.117331862449646,
+      "logits/rejected": -1.1234540939331055,
+      "logps/chosen": -116.87013244628906,
+      "logps/rejected": -136.917724609375,
+      "loss": 0.6733,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.0025692852213978767,
+      "rewards/margins": 0.18151307106018066,
+      "rewards/rejected": -0.17894375324249268,
+      "step": 40
+    },
+    {
+      "epoch": 0.048642779587405,
+      "grad_norm": 93.22753554673558,
+      "learning_rate": 8.4e-08,
+      "logits/chosen": -1.2923729419708252,
+      "logits/rejected": -1.297027587890625,
+      "logps/chosen": -166.103759765625,
+      "logps/rejected": -181.45489501953125,
+      "loss": 0.7232,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.10465113818645477,
+      "rewards/margins": 0.18375912308692932,
+      "rewards/rejected": -0.07910798490047455,
+      "step": 42
+    },
+    {
+      "epoch": 0.05095910242490047,
+      "grad_norm": 106.85916991971588,
+      "learning_rate": 8.8e-08,
+      "logits/chosen": -1.1490933895111084,
+      "logits/rejected": -1.1849195957183838,
+      "logps/chosen": -128.70228576660156,
+      "logps/rejected": -132.4073944091797,
+      "loss": 0.6279,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.020340707153081894,
+      "rewards/margins": 0.1922486573457718,
+      "rewards/rejected": -0.1719079315662384,
+      "step": 44
+    },
+    {
+      "epoch": 0.053275425262395947,
+      "grad_norm": 97.83169947406368,
+      "learning_rate": 9.2e-08,
+      "logits/chosen": -1.172762393951416,
+      "logits/rejected": -1.2331753969192505,
+      "logps/chosen": -158.21144104003906,
+      "logps/rejected": -166.85243225097656,
+      "loss": 0.678,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.032968997955322266,
+      "rewards/margins": -0.025485830381512642,
+      "rewards/rejected": -0.007483180612325668,
+      "step": 46
+    },
+    {
+      "epoch": 0.055591748099891425,
+      "grad_norm": 95.31491574095924,
+      "learning_rate": 9.599999999999999e-08,
+      "logits/chosen": -1.1868703365325928,
+      "logits/rejected": -1.1828659772872925,
+      "logps/chosen": -124.27775573730469,
+      "logps/rejected": -134.80194091796875,
+      "loss": 0.6496,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.07946968823671341,
+      "rewards/margins": 0.2973785996437073,
+      "rewards/rejected": -0.21790890395641327,
+      "step": 48
+    },
+    {
+      "epoch": 0.057908070937386896,
+      "grad_norm": 85.1406868444302,
+      "learning_rate": 1e-07,
+      "logits/chosen": -1.2733350992202759,
+      "logits/rejected": -1.259924054145813,
+      "logps/chosen": -98.49462890625,
+      "logps/rejected": -97.88270568847656,
+      "loss": 0.6637,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.0715535506606102,
+      "rewards/margins": 0.20892760157585144,
+      "rewards/rejected": -0.13737404346466064,
+      "step": 50
+    },
+    {
+      "epoch": 0.060224393774882375,
+      "grad_norm": 125.25778955296133,
+      "learning_rate": 1.04e-07,
+      "logits/chosen": -1.149878740310669,
+      "logits/rejected": -1.2266716957092285,
+      "logps/chosen": -148.4358367919922,
+      "logps/rejected": -194.48550415039062,
+      "loss": 0.6064,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.20534949004650116,
+      "rewards/margins": 0.5171413421630859,
+      "rewards/rejected": -0.31179192662239075,
+      "step": 52
+    },
+    {
+      "epoch": 0.06254071661237785,
+      "grad_norm": 85.1210580902555,
+      "learning_rate": 1.08e-07,
+      "logits/chosen": -1.167691946029663,
+      "logits/rejected": -1.2391445636749268,
+      "logps/chosen": -89.7966537475586,
+      "logps/rejected": -90.55988311767578,
+      "loss": 0.652,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.041167087852954865,
+      "rewards/margins": 0.031343974173069,
+      "rewards/rejected": 0.009823101572692394,
+      "step": 54
+    },
+    {
+      "epoch": 0.06485703944987332,
+      "grad_norm": 113.7038348505988,
+      "learning_rate": 1.1200000000000001e-07,
+      "logits/chosen": -1.1915769577026367,
+      "logits/rejected": -1.2897090911865234,
+      "logps/chosen": -128.1698760986328,
+      "logps/rejected": -162.2020721435547,
+      "loss": 0.6575,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.04976767301559448,
+      "rewards/margins": 0.225263312458992,
+      "rewards/rejected": -0.17549563944339752,
+      "step": 56
+    },
+    {
+      "epoch": 0.0671733622873688,
+      "grad_norm": 101.75813362292396,
+      "learning_rate": 1.1599999999999999e-07,
+      "logits/chosen": -1.1701388359069824,
+      "logits/rejected": -1.2366788387298584,
+      "logps/chosen": -125.07969665527344,
+      "logps/rejected": -143.41500854492188,
+      "loss": 0.6856,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": 0.10177399218082428,
+      "rewards/margins": -0.0010812487453222275,
+      "rewards/rejected": 0.10285523533821106,
+      "step": 58
+    },
+    {
+      "epoch": 0.06948968512486428,
+      "grad_norm": 126.89350965014833,
+      "learning_rate": 1.2e-07,
+      "logits/chosen": -1.0981509685516357,
+      "logits/rejected": -1.0755817890167236,
+      "logps/chosen": -97.16602325439453,
+      "logps/rejected": -108.92754364013672,
+      "loss": 0.6917,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.06149844080209732,
+      "rewards/margins": 0.26494595408439636,
+      "rewards/rejected": -0.20344750583171844,
+      "step": 60
+    },
+    {
+      "epoch": 0.07180600796235975,
+      "grad_norm": 104.04126418655044,
+      "learning_rate": 1.24e-07,
+      "logits/chosen": -1.349946141242981,
+      "logits/rejected": -1.3422037363052368,
+      "logps/chosen": -196.04966735839844,
+      "logps/rejected": -191.64556884765625,
+      "loss": 0.6639,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.06520761549472809,
+      "rewards/margins": 0.08913937956094742,
+      "rewards/rejected": -0.1543469876050949,
+      "step": 62
+    },
+    {
+      "epoch": 0.07412233079985522,
+      "grad_norm": 88.57358643267023,
+      "learning_rate": 1.28e-07,
+      "logits/chosen": -1.301114559173584,
+      "logits/rejected": -1.3226174116134644,
+      "logps/chosen": -193.7246856689453,
+      "logps/rejected": -175.90676879882812,
+      "loss": 0.7147,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.012029323726892471,
+      "rewards/margins": 0.13698697090148926,
+      "rewards/rejected": -0.14901632070541382,
+      "step": 64
+    },
+    {
+      "epoch": 0.07643865363735071,
+      "grad_norm": 88.52081037901337,
+      "learning_rate": 1.32e-07,
+      "logits/chosen": -1.2255011796951294,
+      "logits/rejected": -1.1852511167526245,
+      "logps/chosen": -126.35673522949219,
+      "logps/rejected": -129.8230743408203,
+      "loss": 0.6276,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.08929681777954102,
+      "rewards/margins": 0.20648589730262756,
+      "rewards/rejected": -0.29578274488449097,
+      "step": 66
+    },
+    {
+      "epoch": 0.07875497647484618,
+      "grad_norm": 99.62619229467569,
+      "learning_rate": 1.36e-07,
+      "logits/chosen": -1.2398712635040283,
+      "logits/rejected": -1.2752665281295776,
+      "logps/chosen": -120.943115234375,
+      "logps/rejected": -146.46226501464844,
+      "loss": 0.6609,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.15306755900382996,
+      "rewards/margins": 0.28030622005462646,
+      "rewards/rejected": -0.12723864614963531,
+      "step": 68
+    },
+    {
+      "epoch": 0.08107129931234165,
+      "grad_norm": 123.76564817180537,
+      "learning_rate": 1.3999999999999998e-07,
+      "logits/chosen": -1.2972962856292725,
+      "logits/rejected": -1.2252490520477295,
+      "logps/chosen": -225.8544921875,
+      "logps/rejected": -202.05828857421875,
+      "loss": 0.6665,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.04239021614193916,
+      "rewards/margins": 0.21172578632831573,
+      "rewards/rejected": -0.2541159689426422,
+      "step": 70
+    },
+    {
+      "epoch": 0.08338762214983714,
+      "grad_norm": 76.83779340876126,
+      "learning_rate": 1.44e-07,
+      "logits/chosen": -1.2308259010314941,
+      "logits/rejected": -1.2874609231948853,
+      "logps/chosen": -122.35316467285156,
+      "logps/rejected": -140.2095489501953,
+      "loss": 0.6382,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.03576444834470749,
+      "rewards/margins": 0.04666022211313248,
+      "rewards/rejected": -0.08242467045783997,
+      "step": 72
+    },
+    {
+      "epoch": 0.08570394498733261,
+      "grad_norm": 99.14395654649428,
+      "learning_rate": 1.48e-07,
+      "logits/chosen": -1.2242047786712646,
+      "logits/rejected": -1.1648895740509033,
+      "logps/chosen": -129.6905975341797,
+      "logps/rejected": -149.36679077148438,
+      "loss": 0.7052,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.054999418556690216,
+      "rewards/margins": -0.0660078227519989,
+      "rewards/rejected": 0.011008389294147491,
+      "step": 74
+    },
+    {
+      "epoch": 0.08802026782482808,
+      "grad_norm": 97.12896274616604,
+      "learning_rate": 1.5199999999999998e-07,
+      "logits/chosen": -1.1600117683410645,
+      "logits/rejected": -1.1804448366165161,
+      "logps/chosen": -104.76295471191406,
+      "logps/rejected": -119.62078857421875,
+      "loss": 0.7319,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.09297358989715576,
+      "rewards/margins": -0.027700770646333694,
+      "rewards/rejected": 0.12067436426877975,
+      "step": 76
+    },
+    {
+      "epoch": 0.09033659066232357,
+      "grad_norm": 97.18348074718145,
+      "learning_rate": 1.56e-07,
+      "logits/chosen": -1.32283616065979,
+      "logits/rejected": -1.3598227500915527,
+      "logps/chosen": -106.35183715820312,
+      "logps/rejected": -126.29917907714844,
+      "loss": 0.6492,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.02818872779607773,
+      "rewards/margins": 0.018800366669893265,
+      "rewards/rejected": -0.046989068388938904,
+      "step": 78
+    },
+    {
+      "epoch": 0.09265291349981904,
+      "grad_norm": 97.61734233459106,
+      "learning_rate": 1.6e-07,
+      "logits/chosen": -1.271921157836914,
+      "logits/rejected": -1.2778291702270508,
+      "logps/chosen": -131.4869384765625,
+      "logps/rejected": -138.66790771484375,
+      "loss": 0.674,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.12225940823554993,
+      "rewards/margins": 0.13028502464294434,
+      "rewards/rejected": -0.008025608956813812,
+      "step": 80
+    },
+    {
+      "epoch": 0.09496923633731451,
+      "grad_norm": 107.33609007479366,
+      "learning_rate": 1.6399999999999999e-07,
+      "logits/chosen": -1.2688210010528564,
+      "logits/rejected": -1.157952904701233,
+      "logps/chosen": -139.7398223876953,
+      "logps/rejected": -118.81407928466797,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.09918585419654846,
+      "rewards/margins": 0.21009066700935364,
+      "rewards/rejected": -0.11090480536222458,
+      "step": 82
+    },
+    {
+      "epoch": 0.09728555917481,
+      "grad_norm": 110.01597856385645,
+      "learning_rate": 1.68e-07,
+      "logits/chosen": -1.2803689241409302,
+      "logits/rejected": -1.2909519672393799,
+      "logps/chosen": -132.66493225097656,
+      "logps/rejected": -173.28465270996094,
+      "loss": 0.6635,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.05728979408740997,
+      "rewards/margins": 0.36615562438964844,
+      "rewards/rejected": -0.30886584520339966,
+      "step": 84
+    },
+    {
+      "epoch": 0.09960188201230546,
+      "grad_norm": 83.44332939168942,
+      "learning_rate": 1.7199999999999998e-07,
+      "logits/chosen": -1.3057663440704346,
+      "logits/rejected": -1.385368824005127,
+      "logps/chosen": -107.35197448730469,
+      "logps/rejected": -131.16021728515625,
+      "loss": 0.6259,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.11738797277212143,
+      "rewards/margins": 0.3890346884727478,
+      "rewards/rejected": -0.2716467082500458,
+      "step": 86
+    },
+    {
+      "epoch": 0.10191820484980094,
+      "grad_norm": 111.78643885213532,
+      "learning_rate": 1.76e-07,
+      "logits/chosen": -1.2848472595214844,
+      "logits/rejected": -1.3411585092544556,
+      "logps/chosen": -122.2959976196289,
+      "logps/rejected": -137.3688507080078,
+      "loss": 0.7167,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.042663730680942535,
+      "rewards/margins": 0.04965965449810028,
+      "rewards/rejected": -0.09232338517904282,
+      "step": 88
+    },
+    {
+      "epoch": 0.10423452768729642,
+      "grad_norm": 98.91788911999603,
+      "learning_rate": 1.8e-07,
+      "logits/chosen": -1.3746676445007324,
+      "logits/rejected": -1.4242061376571655,
+      "logps/chosen": -165.28323364257812,
+      "logps/rejected": -191.28463745117188,
+      "loss": 0.6558,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.03775983303785324,
+      "rewards/margins": 0.41289234161376953,
+      "rewards/rejected": -0.45065221190452576,
+      "step": 90
+    },
+    {
+      "epoch": 0.10655085052479189,
+      "grad_norm": 111.36490143512665,
+      "learning_rate": 1.84e-07,
+      "logits/chosen": -1.3450393676757812,
+      "logits/rejected": -1.2920035123825073,
+      "logps/chosen": -113.93867492675781,
+      "logps/rejected": -127.0622787475586,
+      "loss": 0.652,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.016492784023284912,
+      "rewards/margins": 0.23039251565933228,
+      "rewards/rejected": -0.21389973163604736,
+      "step": 92
+    },
+    {
+      "epoch": 0.10886717336228736,
+      "grad_norm": 86.77836554288824,
+      "learning_rate": 1.88e-07,
+      "logits/chosen": -1.2809118032455444,
+      "logits/rejected": -1.2533433437347412,
+      "logps/chosen": -126.3050308227539,
+      "logps/rejected": -146.13954162597656,
+      "loss": 0.67,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.12605877220630646,
+      "rewards/margins": 0.10366299748420715,
+      "rewards/rejected": -0.2297217696905136,
+      "step": 94
+    },
+    {
+      "epoch": 0.11118349619978285,
+      "grad_norm": 88.7771339602004,
+      "learning_rate": 1.9199999999999997e-07,
+      "logits/chosen": -1.3726493120193481,
+      "logits/rejected": -1.3574461936950684,
+      "logps/chosen": -166.51853942871094,
+      "logps/rejected": -152.40924072265625,
+      "loss": 0.6228,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.10408200323581696,
+      "rewards/margins": 0.2763758897781372,
+      "rewards/rejected": -0.17229388654232025,
+      "step": 96
+    },
+    {
+      "epoch": 0.11349981903727832,
+      "grad_norm": 108.88629440565376,
+      "learning_rate": 1.9599999999999998e-07,
+      "logits/chosen": -1.2083911895751953,
+      "logits/rejected": -1.2246620655059814,
+      "logps/chosen": -102.56442260742188,
+      "logps/rejected": -119.50433349609375,
+      "loss": 0.6727,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.12194587290287018,
+      "rewards/margins": -0.01594824716448784,
+      "rewards/rejected": -0.10599763691425323,
+      "step": 98
+    },
+    {
+      "epoch": 0.11581614187477379,
+      "grad_norm": 107.34841983393876,
+      "learning_rate": 2e-07,
+      "logits/chosen": -1.301100254058838,
+      "logits/rejected": -1.2448687553405762,
+      "logps/chosen": -98.93006896972656,
+      "logps/rejected": -104.18254089355469,
+      "loss": 0.6665,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.13594529032707214,
+      "rewards/margins": 0.32611793279647827,
+      "rewards/rejected": -0.19017262756824493,
+      "step": 100
+    },
+    {
+      "epoch": 0.11581614187477379,
+      "eval_logits/chosen": -1.2619309425354004,
+      "eval_logits/rejected": -1.26002836227417,
+      "eval_logps/chosen": -136.7689208984375,
+      "eval_logps/rejected": -136.49838256835938,
+      "eval_loss": 0.698452353477478,
+      "eval_rewards/accuracies": 0.6000000238418579,
+      "eval_rewards/chosen": -0.11377277970314026,
+      "eval_rewards/margins": 0.14070965349674225,
+      "eval_rewards/rejected": -0.2544824182987213,
+      "eval_runtime": 24.9769,
+      "eval_samples_per_second": 4.004,
+      "eval_steps_per_second": 1.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.11813246471226928,
+      "grad_norm": 116.33900974943187,
+      "learning_rate": 1.9999925339977214e-07,
+      "logits/chosen": -1.184662938117981,
+      "logits/rejected": -1.2719396352767944,
+      "logps/chosen": -97.52359008789062,
+      "logps/rejected": -115.05503845214844,
+      "loss": 0.7448,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.214466392993927,
+      "rewards/margins": 0.24747245013713837,
+      "rewards/rejected": -0.033006034791469574,
+      "step": 102
+    },
+    {
+      "epoch": 0.12044878754976475,
+      "grad_norm": 104.21886206321497,
+      "learning_rate": 1.9999701361023685e-07,
+      "logits/chosen": -1.3039063215255737,
+      "logits/rejected": -1.3020060062408447,
+      "logps/chosen": -159.8837432861328,
+      "logps/rejected": -170.56915283203125,
+      "loss": 0.6355,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.22545436024665833,
+      "rewards/margins": 0.24028439819812775,
+      "rewards/rejected": -0.014830047264695168,
+      "step": 104
+    },
+    {
+      "epoch": 0.12276511038726022,
+      "grad_norm": 87.7482533485662,
+      "learning_rate": 1.9999328066483861e-07,
+      "logits/chosen": -1.222218632698059,
+      "logits/rejected": -1.2927945852279663,
+      "logps/chosen": -139.34170532226562,
+      "logps/rejected": -165.7588348388672,
+      "loss": 0.6163,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.08087025582790375,
+      "rewards/margins": 0.19403491914272308,
+      "rewards/rejected": -0.11316468566656113,
+      "step": 106
+    },
+    {
+      "epoch": 0.1250814332247557,
+      "grad_norm": 99.23120967868726,
+      "learning_rate": 1.9998805461931787e-07,
+      "logits/chosen": -1.4282017946243286,
+      "logits/rejected": -1.4305387735366821,
+      "logps/chosen": -143.5193634033203,
+      "logps/rejected": -159.5055389404297,
+      "loss": 0.6448,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.19475266337394714,
+      "rewards/margins": 0.35647571086883545,
+      "rewards/rejected": -0.1617230772972107,
+      "step": 108
+    },
+    {
+      "epoch": 0.12739775606225118,
+      "grad_norm": 138.8867591897412,
+      "learning_rate": 1.9998133555170987e-07,
+      "logits/chosen": -1.251868486404419,
+      "logits/rejected": -1.2644716501235962,
+      "logps/chosen": -155.47824096679688,
+      "logps/rejected": -147.9483642578125,
+      "loss": 0.7241,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.009776605293154716,
+      "rewards/margins": 0.11597751080989838,
+      "rewards/rejected": -0.1062009185552597,
+      "step": 110
+    },
+    {
+      "epoch": 0.12971407889974665,
+      "grad_norm": 83.82733566843218,
+      "learning_rate": 1.9997312356234383e-07,
+      "logits/chosen": -1.1328340768814087,
+      "logits/rejected": -1.1860363483428955,
+      "logps/chosen": -122.01078796386719,
+      "logps/rejected": -129.853759765625,
+      "loss": 0.6493,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.04629912227392197,
+      "rewards/margins": 0.14483632147312164,
+      "rewards/rejected": -0.09853721410036087,
+      "step": 112
+    },
+    {
+      "epoch": 0.13203040173724212,
+      "grad_norm": 93.13036576501773,
+      "learning_rate": 1.9996341877384118e-07,
+      "logits/chosen": -1.1620995998382568,
+      "logits/rejected": -1.1975159645080566,
+      "logps/chosen": -106.84819793701172,
+      "logps/rejected": -118.56710815429688,
+      "loss": 0.7035,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.0475483313202858,
+      "rewards/margins": 0.27000802755355835,
+      "rewards/rejected": -0.22245970368385315,
+      "step": 114
+    },
+    {
+      "epoch": 0.1343467245747376,
+      "grad_norm": 91.76740971647824,
+      "learning_rate": 1.9995222133111386e-07,
+      "logits/chosen": -1.41290283203125,
+      "logits/rejected": -1.4713375568389893,
+      "logps/chosen": -150.1622314453125,
+      "logps/rejected": -171.03826904296875,
+      "loss": 0.6605,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.036708392202854156,
+      "rewards/margins": 0.22243811190128326,
+      "rewards/rejected": -0.259146511554718,
+      "step": 116
+    },
+    {
+      "epoch": 0.1366630474122331,
+      "grad_norm": 92.6178794136077,
+      "learning_rate": 1.9993953140136216e-07,
+      "logits/chosen": -1.2917448282241821,
+      "logits/rejected": -1.2992435693740845,
+      "logps/chosen": -156.93075561523438,
+      "logps/rejected": -169.90003967285156,
+      "loss": 0.6092,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.2660582661628723,
+      "rewards/margins": 0.3958339989185333,
+      "rewards/rejected": -0.1297757476568222,
+      "step": 118
+    },
+    {
+      "epoch": 0.13897937024972856,
+      "grad_norm": 120.21640303391953,
+      "learning_rate": 1.9992534917407219e-07,
+      "logits/chosen": -1.349656105041504,
+      "logits/rejected": -1.3740586042404175,
+      "logps/chosen": -105.40829467773438,
+      "logps/rejected": -121.30719757080078,
+      "loss": 0.6782,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.12624263763427734,
+      "rewards/margins": 0.2478535771369934,
+      "rewards/rejected": -0.12161093950271606,
+      "step": 120
+    },
+    {
+      "epoch": 0.14129569308722403,
+      "grad_norm": 96.89881415216858,
+      "learning_rate": 1.9990967486101294e-07,
+      "logits/chosen": -1.2133190631866455,
+      "logits/rejected": -1.2981417179107666,
+      "logps/chosen": -143.4733123779297,
+      "logps/rejected": -158.9942169189453,
+      "loss": 0.6542,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": 0.12114143371582031,
+      "rewards/margins": 0.3096562922000885,
+      "rewards/rejected": -0.18851490318775177,
+      "step": 122
+    },
+    {
+      "epoch": 0.1436120159247195,
+      "grad_norm": 115.73216474991814,
+      "learning_rate": 1.9989250869623339e-07,
+      "logits/chosen": -1.1692413091659546,
+      "logits/rejected": -1.1631613969802856,
+      "logps/chosen": -75.05902099609375,
+      "logps/rejected": -73.19275665283203,
+      "loss": 0.6629,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.004932025447487831,
+      "rewards/margins": 0.01587551087141037,
+      "rewards/rejected": -0.010943496599793434,
+      "step": 124
+    },
+    {
+      "epoch": 0.14592833876221498,
+      "grad_norm": 91.12287746621037,
+      "learning_rate": 1.9987385093605883e-07,
+      "logits/chosen": -1.2355098724365234,
+      "logits/rejected": -1.3346201181411743,
+      "logps/chosen": -128.04537963867188,
+      "logps/rejected": -157.95831298828125,
+      "loss": 0.6661,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.16255205869674683,
+      "rewards/margins": 0.1615760326385498,
+      "rewards/rejected": 0.0009760260581970215,
+      "step": 126
+    },
+    {
+      "epoch": 0.14824466159971045,
+      "grad_norm": 75.57776368919416,
+      "learning_rate": 1.9985370185908693e-07,
+      "logits/chosen": -1.324599266052246,
+      "logits/rejected": -1.4256994724273682,
+      "logps/chosen": -160.19496154785156,
+      "logps/rejected": -195.67481994628906,
+      "loss": 0.6052,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.2864247262477875,
+      "rewards/margins": 0.38650280237197876,
+      "rewards/rejected": -0.10007809102535248,
+      "step": 128
+    },
+    {
+      "epoch": 0.15056098443720595,
+      "grad_norm": 99.17567816074047,
+      "learning_rate": 1.9983206176618386e-07,
+      "logits/chosen": -1.3276948928833008,
+      "logits/rejected": -1.355118751525879,
+      "logps/chosen": -150.64071655273438,
+      "logps/rejected": -160.59710693359375,
+      "loss": 0.6456,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.24799679219722748,
+      "rewards/margins": 0.17287284135818481,
+      "rewards/rejected": 0.07512396574020386,
+      "step": 130
+    },
+    {
+      "epoch": 0.15287730727470142,
+      "grad_norm": 96.98870449195998,
+      "learning_rate": 1.9980893098047952e-07,
+      "logits/chosen": -1.3167519569396973,
+      "logits/rejected": -1.3964886665344238,
+      "logps/chosen": -180.10609436035156,
+      "logps/rejected": -202.38543701171875,
+      "loss": 0.6797,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.005836776457726955,
+      "rewards/margins": 0.22576376795768738,
+      "rewards/rejected": -0.2316005378961563,
+      "step": 132
+    },
+    {
+      "epoch": 0.1551936301121969,
+      "grad_norm": 117.99608582102925,
+      "learning_rate": 1.9978430984736302e-07,
+      "logits/chosen": -1.2505745887756348,
+      "logits/rejected": -1.2896987199783325,
+      "logps/chosen": -136.62095642089844,
+      "logps/rejected": -174.75283813476562,
+      "loss": 0.6933,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.007682096213102341,
+      "rewards/margins": 0.22923235595226288,
+      "rewards/rejected": -0.2369144707918167,
+      "step": 134
+    },
+    {
+      "epoch": 0.15750995294969236,
+      "grad_norm": 96.12339888540123,
+      "learning_rate": 1.9975819873447716e-07,
+      "logits/chosen": -1.3039547204971313,
+      "logits/rejected": -1.2686259746551514,
+      "logps/chosen": -148.68177795410156,
+      "logps/rejected": -152.08419799804688,
+      "loss": 0.7376,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.060760702937841415,
+      "rewards/margins": 0.03407803922891617,
+      "rewards/rejected": 0.026682645082473755,
+      "step": 136
+    },
+    {
+      "epoch": 0.15982627578718783,
+      "grad_norm": 89.28907762268612,
+      "learning_rate": 1.9973059803171318e-07,
+      "logits/chosen": -1.289531946182251,
+      "logits/rejected": -1.3106164932250977,
+      "logps/chosen": -132.0419464111328,
+      "logps/rejected": -141.20553588867188,
+      "loss": 0.6417,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.11375564336776733,
+      "rewards/margins": 0.15943853557109833,
+      "rewards/rejected": -0.045682892203330994,
+      "step": 138
+    },
+    {
+      "epoch": 0.1621425986246833,
+      "grad_norm": 91.84482179377031,
+      "learning_rate": 1.9970150815120492e-07,
+      "logits/chosen": -1.192561388015747,
+      "logits/rejected": -1.2516599893569946,
+      "logps/chosen": -144.32687377929688,
+      "logps/rejected": -173.77713012695312,
+      "loss": 0.6664,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.15235400199890137,
+      "rewards/margins": 0.528164267539978,
+      "rewards/rejected": -0.3758102059364319,
+      "step": 140
+    },
+    {
+      "epoch": 0.1644589214621788,
+      "grad_norm": 106.57145249868728,
+      "learning_rate": 1.9967092952732263e-07,
+      "logits/chosen": -1.2669620513916016,
+      "logits/rejected": -1.2892065048217773,
+      "logps/chosen": -158.38601684570312,
+      "logps/rejected": -170.94969177246094,
+      "loss": 0.6949,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.014247164130210876,
+      "rewards/margins": 0.1061759814620018,
+      "rewards/rejected": -0.12042315304279327,
+      "step": 142
+    },
+    {
+      "epoch": 0.16677524429967427,
+      "grad_norm": 84.38620972657165,
+      "learning_rate": 1.9963886261666644e-07,
+      "logits/chosen": -1.3349426984786987,
+      "logits/rejected": -1.3626400232315063,
+      "logps/chosen": -182.36489868164062,
+      "logps/rejected": -181.57772827148438,
+      "loss": 0.6661,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.010849647223949432,
+      "rewards/margins": -0.0017997026443481445,
+      "rewards/rejected": 0.012649361044168472,
+      "step": 144
+    },
+    {
+      "epoch": 0.16909156713716975,
+      "grad_norm": 98.62106551824567,
+      "learning_rate": 1.996053078980596e-07,
+      "logits/chosen": -1.2585192918777466,
+      "logits/rejected": -1.3876447677612305,
+      "logps/chosen": -197.3888702392578,
+      "logps/rejected": -256.7153625488281,
+      "loss": 0.6226,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.11644049733877182,
+      "rewards/margins": 0.36041852831840515,
+      "rewards/rejected": -0.24397803843021393,
+      "step": 146
+    },
+    {
+      "epoch": 0.17140788997466522,
+      "grad_norm": 98.22080984411147,
+      "learning_rate": 1.9957026587254133e-07,
+      "logits/chosen": -1.337060809135437,
+      "logits/rejected": -1.409785270690918,
+      "logps/chosen": -132.1688995361328,
+      "logps/rejected": -153.75076293945312,
+      "loss": 0.6727,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.1054624617099762,
+      "rewards/margins": 0.2318607121706009,
+      "rewards/rejected": -0.1263982504606247,
+      "step": 148
+    },
+    {
+      "epoch": 0.1737242128121607,
+      "grad_norm": 97.21935367376963,
+      "learning_rate": 1.9953373706335933e-07,
+      "logits/chosen": -1.1929289102554321,
+      "logits/rejected": -1.2236409187316895,
+      "logps/chosen": -107.02670288085938,
+      "logps/rejected": -127.95613098144531,
+      "loss": 0.6247,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.2545817792415619,
+      "rewards/margins": 0.5042745471000671,
+      "rewards/rejected": -0.24969279766082764,
+      "step": 150
+    },
+    {
+      "epoch": 0.17604053564965616,
+      "grad_norm": 94.64988218894314,
+      "learning_rate": 1.994957220159619e-07,
+      "logits/chosen": -1.3698749542236328,
+      "logits/rejected": -1.3630839586257935,
+      "logps/chosen": -139.28404235839844,
+      "logps/rejected": -144.27447509765625,
+      "loss": 0.6708,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": 0.09452275186777115,
+      "rewards/margins": -0.054528601467609406,
+      "rewards/rejected": 0.14905135333538055,
+      "step": 152
+    },
+    {
+      "epoch": 0.17835685848715166,
+      "grad_norm": 84.21031983415891,
+      "learning_rate": 1.9945622129798997e-07,
+      "logits/chosen": -1.1571345329284668,
+      "logits/rejected": -1.1760966777801514,
+      "logps/chosen": -116.92776489257812,
+      "logps/rejected": -130.6823272705078,
+      "loss": 0.7077,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.014008231461048126,
+      "rewards/margins": 0.1772165149450302,
+      "rewards/rejected": -0.16320832073688507,
+      "step": 154
+    },
+    {
+      "epoch": 0.18067318132464713,
+      "grad_norm": 92.78782165706316,
+      "learning_rate": 1.994152354992684e-07,
+      "logits/chosen": -1.2113721370697021,
+      "logits/rejected": -1.1836888790130615,
+      "logps/chosen": -152.64590454101562,
+      "logps/rejected": -165.62060546875,
+      "loss": 0.6243,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.08571603149175644,
+      "rewards/margins": 0.3834956884384155,
+      "rewards/rejected": -0.2977796792984009,
+      "step": 156
+    },
+    {
+      "epoch": 0.1829895041621426,
+      "grad_norm": 87.13678534194861,
+      "learning_rate": 1.993727652317973e-07,
+      "logits/chosen": -1.3516209125518799,
+      "logits/rejected": -1.3507136106491089,
+      "logps/chosen": -131.21653747558594,
+      "logps/rejected": -137.61451721191406,
+      "loss": 0.663,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.1327284872531891,
+      "rewards/margins": 0.0872359424829483,
+      "rewards/rejected": 0.04549254849553108,
+      "step": 158
+    },
+    {
+      "epoch": 0.18530582699963807,
+      "grad_norm": 95.58101049566258,
+      "learning_rate": 1.9932881112974295e-07,
+      "logits/chosen": -1.33234441280365,
+      "logits/rejected": -1.3648202419281006,
+      "logps/chosen": -145.8714141845703,
+      "logps/rejected": -169.70263671875,
+      "loss": 0.6228,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": 0.2145387828350067,
+      "rewards/margins": 0.47029000520706177,
+      "rewards/rejected": -0.25575125217437744,
+      "step": 160
+    },
+    {
+      "epoch": 0.18762214983713354,
+      "grad_norm": 102.72583148528975,
+      "learning_rate": 1.9928337384942815e-07,
+      "logits/chosen": -1.3217285871505737,
+      "logits/rejected": -1.3136992454528809,
+      "logps/chosen": -136.3543701171875,
+      "logps/rejected": -162.57989501953125,
+      "loss": 0.6413,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.10585685819387436,
+      "rewards/margins": 0.4493997395038605,
+      "rewards/rejected": -0.3435429036617279,
+      "step": 162
+    },
+    {
+      "epoch": 0.18993847267462902,
+      "grad_norm": 80.21906160407148,
+      "learning_rate": 1.992364540693226e-07,
+      "logits/chosen": -1.1656920909881592,
+      "logits/rejected": -1.251837134361267,
+      "logps/chosen": -107.77313995361328,
+      "logps/rejected": -126.16749572753906,
+      "loss": 0.6541,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.11644032597541809,
+      "rewards/margins": 0.2288074493408203,
+      "rewards/rejected": -0.11236711591482162,
+      "step": 164
+    },
+    {
+      "epoch": 0.19225479551212452,
+      "grad_norm": 86.51541074826133,
+      "learning_rate": 1.991880524900327e-07,
+      "logits/chosen": -1.3202519416809082,
+      "logits/rejected": -1.3556690216064453,
+      "logps/chosen": -161.82077026367188,
+      "logps/rejected": -177.78990173339844,
+      "loss": 0.6568,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.14771340787410736,
+      "rewards/margins": 0.33536669611930847,
+      "rewards/rejected": -0.1876532882452011,
+      "step": 166
+    },
+    {
+      "epoch": 0.19457111834962,
+      "grad_norm": 94.05305295088043,
+      "learning_rate": 1.99138169834291e-07,
+      "logits/chosen": -1.3505268096923828,
+      "logits/rejected": -1.3973050117492676,
+      "logps/chosen": -139.77182006835938,
+      "logps/rejected": -162.59844970703125,
+      "loss": 0.6877,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.07011064141988754,
+      "rewards/margins": 0.491350919008255,
+      "rewards/rejected": -0.42124032974243164,
+      "step": 168
+    },
+    {
+      "epoch": 0.19688744118711546,
+      "grad_norm": 97.64767459159383,
+      "learning_rate": 1.9908680684694557e-07,
+      "logits/chosen": -1.3445894718170166,
+      "logits/rejected": -1.290609359741211,
+      "logps/chosen": -141.98887634277344,
+      "logps/rejected": -149.97586059570312,
+      "loss": 0.6267,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.06746640801429749,
+      "rewards/margins": 0.2343478798866272,
+      "rewards/rejected": -0.1668814867734909,
+      "step": 170
+    },
+    {
+      "epoch": 0.19920376402461093,
+      "grad_norm": 83.46398544914094,
+      "learning_rate": 1.990339642949488e-07,
+      "logits/chosen": -1.2715935707092285,
+      "logits/rejected": -1.287178874015808,
+      "logps/chosen": -148.58975219726562,
+      "logps/rejected": -165.84759521484375,
+      "loss": 0.63,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.021569374948740005,
+      "rewards/margins": 0.302487850189209,
+      "rewards/rejected": -0.2809184491634369,
+      "step": 172
+    },
+    {
+      "epoch": 0.2015200868621064,
+      "grad_norm": 76.3322328554944,
+      "learning_rate": 1.9897964296734585e-07,
+      "logits/chosen": -1.3700447082519531,
+      "logits/rejected": -1.342909336090088,
+      "logps/chosen": -120.27708435058594,
+      "logps/rejected": -138.94029235839844,
+      "loss": 0.5928,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.13506034016609192,
+      "rewards/margins": 0.2544079124927521,
+      "rewards/rejected": -0.11934758722782135,
+      "step": 174
+    },
+    {
+      "epoch": 0.20383640969960187,
+      "grad_norm": 107.54391320136774,
+      "learning_rate": 1.9892384367526306e-07,
+      "logits/chosen": -1.295619249343872,
+      "logits/rejected": -1.310873031616211,
+      "logps/chosen": -121.80717468261719,
+      "logps/rejected": -130.56863403320312,
+      "loss": 0.6713,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.04329588636755943,
+      "rewards/margins": 0.15788349509239197,
+      "rewards/rejected": -0.11458761245012283,
+      "step": 176
+    },
+    {
+      "epoch": 0.20615273253709737,
+      "grad_norm": 119.93284403188072,
+      "learning_rate": 1.9886656725189573e-07,
+      "logits/chosen": -1.279773473739624,
+      "logits/rejected": -1.248420000076294,
+      "logps/chosen": -140.36367797851562,
+      "logps/rejected": -171.85006713867188,
+      "loss": 0.6378,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.0794132649898529,
+      "rewards/margins": 0.44784438610076904,
+      "rewards/rejected": -0.36843112111091614,
+      "step": 178
+    },
+    {
+      "epoch": 0.20846905537459284,
+      "grad_norm": 79.14950979441363,
+      "learning_rate": 1.9880781455249567e-07,
+      "logits/chosen": -1.2967725992202759,
+      "logits/rejected": -1.25602126121521,
+      "logps/chosen": -144.56265258789062,
+      "logps/rejected": -162.73004150390625,
+      "loss": 0.6249,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.049035411328077316,
+      "rewards/margins": 0.5332698822021484,
+      "rewards/rejected": -0.5823052525520325,
+      "step": 180
+    },
+    {
+      "epoch": 0.21078537821208831,
+      "grad_norm": 98.83687345993943,
+      "learning_rate": 1.9874758645435846e-07,
+      "logits/chosen": -1.2088567018508911,
+      "logits/rejected": -1.2226208448410034,
+      "logps/chosen": -123.06584930419922,
+      "logps/rejected": -139.6479034423828,
+      "loss": 0.7016,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.08502492308616638,
+      "rewards/margins": 0.19190920889377594,
+      "rewards/rejected": -0.10688426345586777,
+      "step": 182
+    },
+    {
+      "epoch": 0.21310170104958379,
+      "grad_norm": 113.97507708078155,
+      "learning_rate": 1.986858838568103e-07,
+      "logits/chosen": -1.3104774951934814,
+      "logits/rejected": -1.4111891984939575,
+      "logps/chosen": -181.88356018066406,
+      "logps/rejected": -208.72584533691406,
+      "loss": 0.705,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.08081494271755219,
+      "rewards/margins": 0.3886911869049072,
+      "rewards/rejected": -0.469506174325943,
+      "step": 184
+    },
+    {
+      "epoch": 0.21541802388707926,
+      "grad_norm": 77.45086288721679,
+      "learning_rate": 1.986227076811947e-07,
+      "logits/chosen": -1.3617669343948364,
+      "logits/rejected": -1.4249626398086548,
+      "logps/chosen": -129.08343505859375,
+      "logps/rejected": -152.81179809570312,
+      "loss": 0.6411,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.05278458073735237,
+      "rewards/margins": 0.2645794153213501,
+      "rewards/rejected": -0.21179485321044922,
+      "step": 186
+    },
+    {
+      "epoch": 0.21773434672457473,
+      "grad_norm": 84.35008555939693,
+      "learning_rate": 1.985580588708586e-07,
+      "logits/chosen": -1.3356997966766357,
+      "logits/rejected": -1.3520371913909912,
+      "logps/chosen": -116.34514617919922,
+      "logps/rejected": -129.33343505859375,
+      "loss": 0.5923,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.2643883526325226,
+      "rewards/margins": 0.6749240159988403,
+      "rewards/rejected": -0.41053569316864014,
+      "step": 188
+    },
+    {
+      "epoch": 0.2200506695620702,
+      "grad_norm": 123.38101336984641,
+      "learning_rate": 1.984919383911383e-07,
+      "logits/chosen": -1.308461308479309,
+      "logits/rejected": -1.304238200187683,
+      "logps/chosen": -158.46170043945312,
+      "logps/rejected": -180.0099639892578,
+      "loss": 0.6699,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.2162826955318451,
+      "rewards/margins": 0.2433900237083435,
+      "rewards/rejected": -0.02710733562707901,
+      "step": 190
+    },
+    {
+      "epoch": 0.2223669923995657,
+      "grad_norm": 86.07588724640635,
+      "learning_rate": 1.9842434722934515e-07,
+      "logits/chosen": -1.4127757549285889,
+      "logits/rejected": -1.4460113048553467,
+      "logps/chosen": -157.5387420654297,
+      "logps/rejected": -172.41824340820312,
+      "loss": 0.6669,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.1006392389535904,
+      "rewards/margins": 0.23149970173835754,
+      "rewards/rejected": -0.13086043298244476,
+      "step": 192
+    },
+    {
+      "epoch": 0.22468331523706117,
+      "grad_norm": 94.64802234991522,
+      "learning_rate": 1.9835528639475064e-07,
+      "logits/chosen": -1.388432264328003,
+      "logits/rejected": -1.4818886518478394,
+      "logps/chosen": -141.1114959716797,
+      "logps/rejected": -157.92218017578125,
+      "loss": 0.697,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.01169365644454956,
+      "rewards/margins": 0.08859987556934357,
+      "rewards/rejected": -0.076906219124794,
+      "step": 194
+    },
+    {
+      "epoch": 0.22699963807455664,
+      "grad_norm": 89.06679411091595,
+      "learning_rate": 1.9828475691857144e-07,
+      "logits/chosen": -1.3492029905319214,
+      "logits/rejected": -1.3424463272094727,
+      "logps/chosen": -187.03414916992188,
+      "logps/rejected": -190.73678588867188,
+      "loss": 0.6388,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.22039715945720673,
+      "rewards/margins": 0.18239110708236694,
+      "rewards/rejected": 0.038006074726581573,
+      "step": 196
+    },
+    {
+      "epoch": 0.2293159609120521,
+      "grad_norm": 95.75837422835144,
+      "learning_rate": 1.982127598539541e-07,
+      "logits/chosen": -1.1775927543640137,
+      "logits/rejected": -1.1424531936645508,
+      "logps/chosen": -148.27951049804688,
+      "logps/rejected": -156.52732849121094,
+      "loss": 0.6159,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.1567731648683548,
+      "rewards/margins": 0.08035247027873993,
+      "rewards/rejected": 0.07642071694135666,
+      "step": 198
+    },
+    {
+      "epoch": 0.23163228374954759,
+      "grad_norm": 93.08435428016394,
+      "learning_rate": 1.9813929627595906e-07,
+      "logits/chosen": -1.4000098705291748,
+      "logits/rejected": -1.3821650743484497,
+      "logps/chosen": -139.89630126953125,
+      "logps/rejected": -148.32470703125,
+      "loss": 0.6393,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.09745461493730545,
+      "rewards/margins": 0.24615491926670074,
+      "rewards/rejected": -0.14870032668113708,
+      "step": 200
+    },
+    {
+      "epoch": 0.23163228374954759,
+      "eval_logits/chosen": -1.304500937461853,
+      "eval_logits/rejected": -1.3002585172653198,
+      "eval_logps/chosen": -136.9430694580078,
+      "eval_logps/rejected": -136.71730041503906,
+      "eval_loss": 0.6824392080307007,
+      "eval_rewards/accuracies": 0.5600000023841858,
+      "eval_rewards/chosen": -0.13118763267993927,
+      "eval_rewards/margins": 0.14518636465072632,
+      "eval_rewards/rejected": -0.2763740122318268,
+      "eval_runtime": 26.1287,
+      "eval_samples_per_second": 3.827,
+      "eval_steps_per_second": 0.957,
+      "step": 200
+    },
+    {
+      "epoch": 0.23394860658704306,
+      "grad_norm": 72.45361347245692,
+      "learning_rate": 1.9806436728154483e-07,
+      "logits/chosen": -1.335165023803711,
+      "logits/rejected": -1.3661694526672363,
+      "logps/chosen": -138.936767578125,
+      "logps/rejected": -158.40025329589844,
+      "loss": 0.6013,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.007253367453813553,
+      "rewards/margins": 0.15234613418579102,
+      "rewards/rejected": -0.15959949791431427,
+      "step": 202
+    },
+    {
+      "epoch": 0.23626492942453856,
+      "grad_norm": 90.8540277710046,
+      "learning_rate": 1.9798797398955145e-07,
+      "logits/chosen": -1.2384086847305298,
+      "logits/rejected": -1.3494983911514282,
+      "logps/chosen": -128.23599243164062,
+      "logps/rejected": -177.1882781982422,
+      "loss": 0.564,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.33455580472946167,
+      "rewards/margins": 0.7392863035202026,
+      "rewards/rejected": -0.40473055839538574,
+      "step": 204
+    },
+    {
+      "epoch": 0.23858125226203403,
+      "grad_norm": 74.43794613270396,
+      "learning_rate": 1.9791011754068395e-07,
+      "logits/chosen": -1.3185287714004517,
+      "logits/rejected": -1.3400077819824219,
+      "logps/chosen": -131.19667053222656,
+      "logps/rejected": -163.21923828125,
+      "loss": 0.6032,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.1290275603532791,
+      "rewards/margins": 0.47639700770378113,
+      "rewards/rejected": -0.3473694622516632,
+      "step": 206
+    },
+    {
+      "epoch": 0.2408975750995295,
+      "grad_norm": 95.09010015175441,
+      "learning_rate": 1.9783079909749514e-07,
+      "logits/chosen": -1.1546052694320679,
+      "logits/rejected": -1.2192610502243042,
+      "logps/chosen": -166.31753540039062,
+      "logps/rejected": -186.45753479003906,
+      "loss": 0.6578,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.3212764859199524,
+      "rewards/margins": 0.19196587800979614,
+      "rewards/rejected": 0.12931060791015625,
+      "step": 208
+    },
+    {
+      "epoch": 0.24321389793702497,
+      "grad_norm": 85.95636909904059,
+      "learning_rate": 1.9775001984436842e-07,
+      "logits/chosen": -1.2965327501296997,
+      "logits/rejected": -1.3256494998931885,
+      "logps/chosen": -150.2991943359375,
+      "logps/rejected": -156.32376098632812,
+      "loss": 0.6469,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.29619836807250977,
+      "rewards/margins": 0.0699533224105835,
+      "rewards/rejected": -0.36615169048309326,
+      "step": 210
+    },
+    {
+      "epoch": 0.24553022077452044,
+      "grad_norm": 100.06649868470993,
+      "learning_rate": 1.9766778098749993e-07,
+      "logits/chosen": -1.216491937637329,
+      "logits/rejected": -1.2272950410842896,
+      "logps/chosen": -164.16220092773438,
+      "logps/rejected": -181.47265625,
+      "loss": 0.6707,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.06646190583705902,
+      "rewards/margins": 0.46730464696884155,
+      "rewards/rejected": -0.5337665677070618,
+      "step": 212
+    },
+    {
+      "epoch": 0.2478465436120159,
+      "grad_norm": 96.52482939931645,
+      "learning_rate": 1.975840837548807e-07,
+      "logits/chosen": -1.3946311473846436,
+      "logits/rejected": -1.3414866924285889,
+      "logps/chosen": -152.69595336914062,
+      "logps/rejected": -164.10858154296875,
+      "loss": 0.7014,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.022681551054120064,
+      "rewards/margins": 0.17960719764232635,
+      "rewards/rejected": -0.15692564845085144,
+      "step": 214
+    },
+    {
+      "epoch": 0.2501628664495114,
+      "grad_norm": 153.51800892842274,
+      "learning_rate": 1.974989293962781e-07,
+      "logits/chosen": -1.2091304063796997,
+      "logits/rejected": -1.2250198125839233,
+      "logps/chosen": -181.1391143798828,
+      "logps/rejected": -222.74087524414062,
+      "loss": 0.76,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.0878646969795227,
+      "rewards/margins": 0.9455296993255615,
+      "rewards/rejected": -1.033394455909729,
+      "step": 216
+    },
+    {
+      "epoch": 0.25247918928700686,
+      "grad_norm": 99.38458587796177,
+      "learning_rate": 1.974123191832175e-07,
+      "logits/chosen": -1.2188912630081177,
+      "logits/rejected": -1.2454049587249756,
+      "logps/chosen": -114.72016143798828,
+      "logps/rejected": -151.92970275878906,
+      "loss": 0.7037,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.28741875290870667,
+      "rewards/margins": 0.1605263203382492,
+      "rewards/rejected": -0.44794508814811707,
+      "step": 218
+    },
+    {
+      "epoch": 0.25479551212450235,
+      "grad_norm": 81.97849529400557,
+      "learning_rate": 1.9732425440896293e-07,
+      "logits/chosen": -1.264250636100769,
+      "logits/rejected": -1.3256012201309204,
+      "logps/chosen": -124.54591369628906,
+      "logps/rejected": -148.69161987304688,
+      "loss": 0.5741,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.18301630020141602,
+      "rewards/margins": 0.42959779500961304,
+      "rewards/rejected": -0.24658147990703583,
+      "step": 220
+    },
+    {
+      "epoch": 0.25711183496199785,
+      "grad_norm": 145.57197289231644,
+      "learning_rate": 1.9723473638849804e-07,
+      "logits/chosen": -1.282865285873413,
+      "logits/rejected": -1.3407156467437744,
+      "logps/chosen": -160.74911499023438,
+      "logps/rejected": -179.92872619628906,
+      "loss": 0.6797,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.25827834010124207,
+      "rewards/margins": 0.23611454665660858,
+      "rewards/rejected": -0.49439290165901184,
+      "step": 222
+    },
+    {
+      "epoch": 0.2594281577994933,
+      "grad_norm": 92.12330941145905,
+      "learning_rate": 1.9714376645850633e-07,
+      "logits/chosen": -1.1877822875976562,
+      "logits/rejected": -1.2320842742919922,
+      "logps/chosen": -112.88442993164062,
+      "logps/rejected": -153.49356079101562,
+      "loss": 0.6879,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.06163054332137108,
+      "rewards/margins": 0.5120011568069458,
+      "rewards/rejected": -0.5736316442489624,
+      "step": 224
+    },
+    {
+      "epoch": 0.2617444806369888,
+      "grad_norm": 89.27914911232024,
+      "learning_rate": 1.9705134597735113e-07,
+      "logits/chosen": -1.3040626049041748,
+      "logits/rejected": -1.3116812705993652,
+      "logps/chosen": -138.1647491455078,
+      "logps/rejected": -164.8112030029297,
+      "loss": 0.6066,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.5537402629852295,
+      "rewards/margins": 0.5435131788253784,
+      "rewards/rejected": -1.097253441810608,
+      "step": 226
+    },
+    {
+      "epoch": 0.26406080347448424,
+      "grad_norm": 100.44445362175034,
+      "learning_rate": 1.9695747632505558e-07,
+      "logits/chosen": -1.2323942184448242,
+      "logits/rejected": -1.3942488431930542,
+      "logps/chosen": -95.50066375732422,
+      "logps/rejected": -116.43473815917969,
+      "loss": 0.6697,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.22127968072891235,
+      "rewards/margins": 0.21899569034576416,
+      "rewards/rejected": 0.0022839903831481934,
+      "step": 228
+    },
+    {
+      "epoch": 0.26637712631197974,
+      "grad_norm": 121.25117391544367,
+      "learning_rate": 1.9686215890328168e-07,
+      "logits/chosen": -1.3321830034255981,
+      "logits/rejected": -1.2888097763061523,
+      "logps/chosen": -139.03431701660156,
+      "logps/rejected": -178.35134887695312,
+      "loss": 0.6215,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.2928890287876129,
+      "rewards/margins": 0.5932635068893433,
+      "rewards/rejected": -0.30037450790405273,
+      "step": 230
+    },
+    {
+      "epoch": 0.2686934491494752,
+      "grad_norm": 92.88847876797445,
+      "learning_rate": 1.9676539513530965e-07,
+      "logits/chosen": -1.2525643110275269,
+      "logits/rejected": -1.2690104246139526,
+      "logps/chosen": -137.59510803222656,
+      "logps/rejected": -170.5804901123047,
+      "loss": 0.6265,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.003497052937746048,
+      "rewards/margins": 0.2578098177909851,
+      "rewards/rejected": -0.2613069415092468,
+      "step": 232
+    },
+    {
+      "epoch": 0.2710097719869707,
+      "grad_norm": 109.64954295867085,
+      "learning_rate": 1.966671864660165e-07,
+      "logits/chosen": -1.3433884382247925,
+      "logits/rejected": -1.332856297492981,
+      "logps/chosen": -98.57205200195312,
+      "logps/rejected": -97.49153137207031,
+      "loss": 0.6447,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.011620203964412212,
+      "rewards/margins": 0.2672192454338074,
+      "rewards/rejected": -0.27883943915367126,
+      "step": 234
+    },
+    {
+      "epoch": 0.2733260948244662,
+      "grad_norm": 88.30404740296814,
+      "learning_rate": 1.9656753436185456e-07,
+      "logits/chosen": -1.4166165590286255,
+      "logits/rejected": -1.3988808393478394,
+      "logps/chosen": -120.94856262207031,
+      "logps/rejected": -126.8148422241211,
+      "loss": 0.5872,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.20259736478328705,
+      "rewards/margins": 0.5475842356681824,
+      "rewards/rejected": -0.3449868857860565,
+      "step": 236
+    },
+    {
+      "epoch": 0.2756424176619616,
+      "grad_norm": 86.00138406914863,
+      "learning_rate": 1.9646644031082948e-07,
+      "logits/chosen": -1.26936674118042,
+      "logits/rejected": -1.3119958639144897,
+      "logps/chosen": -141.89259338378906,
+      "logps/rejected": -152.75332641601562,
+      "loss": 0.6581,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.03933039680123329,
+      "rewards/margins": 0.42467713356018066,
+      "rewards/rejected": -0.38534674048423767,
+      "step": 238
+    },
+    {
+      "epoch": 0.2779587404994571,
+      "grad_norm": 85.11515238510546,
+      "learning_rate": 1.9636390582247804e-07,
+      "logits/chosen": -1.2737447023391724,
+      "logits/rejected": -1.2945623397827148,
+      "logps/chosen": -119.07524871826172,
+      "logps/rejected": -129.40042114257812,
+      "loss": 0.6561,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.21082651615142822,
+      "rewards/margins": 0.13657376170158386,
+      "rewards/rejected": 0.07425275444984436,
+      "step": 240
+    },
+    {
+      "epoch": 0.28027506333695257,
+      "grad_norm": 78.24054806837644,
+      "learning_rate": 1.9625993242784577e-07,
+      "logits/chosen": -1.3759459257125854,
+      "logits/rejected": -1.4495054483413696,
+      "logps/chosen": -109.1790771484375,
+      "logps/rejected": -141.45123291015625,
+      "loss": 0.5681,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.19224990904331207,
+      "rewards/margins": 0.4157065451145172,
+      "rewards/rejected": -0.22345668077468872,
+      "step": 242
+    },
+    {
+      "epoch": 0.28259138617444807,
+      "grad_norm": 100.77507144115899,
+      "learning_rate": 1.9615452167946382e-07,
+      "logits/chosen": -1.2527633905410767,
+      "logits/rejected": -1.3112610578536987,
+      "logps/chosen": -138.2284393310547,
+      "logps/rejected": -145.6739501953125,
+      "loss": 0.6735,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.12001015990972519,
+      "rewards/margins": 0.14908871054649353,
+      "rewards/rejected": -0.2690988779067993,
+      "step": 244
+    },
+    {
+      "epoch": 0.28490770901194357,
+      "grad_norm": 81.77193945900667,
+      "learning_rate": 1.9604767515132598e-07,
+      "logits/chosen": -1.30977463722229,
+      "logits/rejected": -1.308231234550476,
+      "logps/chosen": -146.16175842285156,
+      "logps/rejected": -150.26780700683594,
+      "loss": 0.6512,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.02212803065776825,
+      "rewards/margins": 0.2704678177833557,
+      "rewards/rejected": -0.29259583353996277,
+      "step": 246
+    },
+    {
+      "epoch": 0.287224031849439,
+      "grad_norm": 94.70823896676559,
+      "learning_rate": 1.9593939443886513e-07,
+      "logits/chosen": -1.2869986295700073,
+      "logits/rejected": -1.3198009729385376,
+      "logps/chosen": -205.1080322265625,
+      "logps/rejected": -221.5395050048828,
+      "loss": 0.6069,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.03687068819999695,
+      "rewards/margins": 0.5602297782897949,
+      "rewards/rejected": -0.5233591794967651,
+      "step": 248
+    },
+    {
+      "epoch": 0.2895403546869345,
+      "grad_norm": 78.53341652955227,
+      "learning_rate": 1.9582968115892928e-07,
+      "logits/chosen": -1.5314466953277588,
+      "logits/rejected": -1.4816820621490479,
+      "logps/chosen": -175.5377655029297,
+      "logps/rejected": -167.43699645996094,
+      "loss": 0.6442,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.053328827023506165,
+      "rewards/margins": 0.07659827172756195,
+      "rewards/rejected": -0.02326946146786213,
+      "step": 250
+    },
+    {
+      "epoch": 0.29185667752442995,
+      "grad_norm": 79.61524235861766,
+      "learning_rate": 1.9571853694975768e-07,
+      "logits/chosen": -1.2131693363189697,
+      "logits/rejected": -1.2827026844024658,
+      "logps/chosen": -135.439453125,
+      "logps/rejected": -152.61849975585938,
+      "loss": 0.6405,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.15244589745998383,
+      "rewards/margins": 0.6494119763374329,
+      "rewards/rejected": -0.496966153383255,
+      "step": 252
+    },
+    {
+      "epoch": 0.29417300036192545,
+      "grad_norm": 98.13148651308288,
+      "learning_rate": 1.956059634709562e-07,
+      "logits/chosen": -1.1604809761047363,
+      "logits/rejected": -1.2288950681686401,
+      "logps/chosen": -131.82022094726562,
+      "logps/rejected": -161.86351013183594,
+      "loss": 0.6057,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.1956767737865448,
+      "rewards/margins": 0.9915366172790527,
+      "rewards/rejected": -0.7958598136901855,
+      "step": 254
+    },
+    {
+      "epoch": 0.2964893231994209,
+      "grad_norm": 103.85718892196564,
+      "learning_rate": 1.9549196240347248e-07,
+      "logits/chosen": -1.2092281579971313,
+      "logits/rejected": -1.2428326606750488,
+      "logps/chosen": -155.42657470703125,
+      "logps/rejected": -153.75314331054688,
+      "loss": 0.634,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.04123011976480484,
+      "rewards/margins": 0.5150858759880066,
+      "rewards/rejected": -0.5563160181045532,
+      "step": 256
+    },
+    {
+      "epoch": 0.2988056460369164,
+      "grad_norm": 86.63305573669103,
+      "learning_rate": 1.9537653544957097e-07,
+      "logits/chosen": -1.4105985164642334,
+      "logits/rejected": -1.434030532836914,
+      "logps/chosen": -185.7542266845703,
+      "logps/rejected": -201.953369140625,
+      "loss": 0.607,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.03058760240674019,
+      "rewards/margins": 0.36953964829444885,
+      "rewards/rejected": -0.33895203471183777,
+      "step": 258
+    },
+    {
+      "epoch": 0.3011219688744119,
+      "grad_norm": 76.86118592942691,
+      "learning_rate": 1.9525968433280754e-07,
+      "logits/chosen": -1.3709828853607178,
+      "logits/rejected": -1.4235422611236572,
+      "logps/chosen": -116.02484130859375,
+      "logps/rejected": -162.0040283203125,
+      "loss": 0.6561,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": 0.22844532132148743,
+      "rewards/margins": 0.5770739912986755,
+      "rewards/rejected": -0.3486286997795105,
+      "step": 260
+    },
+    {
+      "epoch": 0.30343829171190734,
+      "grad_norm": 87.47994543044294,
+      "learning_rate": 1.9514141079800358e-07,
+      "logits/chosen": -1.3765437602996826,
+      "logits/rejected": -1.4620999097824097,
+      "logps/chosen": -178.11399841308594,
+      "logps/rejected": -184.82977294921875,
+      "loss": 0.6388,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.3185967206954956,
+      "rewards/margins": 0.35556116700172424,
+      "rewards/rejected": -0.036964427679777145,
+      "step": 262
+    },
+    {
+      "epoch": 0.30575461454940284,
+      "grad_norm": 93.0963118432758,
+      "learning_rate": 1.9502171661121997e-07,
+      "logits/chosen": -1.3460544347763062,
+      "logits/rejected": -1.3444372415542603,
+      "logps/chosen": -129.8871307373047,
+      "logps/rejected": -139.0457305908203,
+      "loss": 0.633,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.24807024002075195,
+      "rewards/margins": 0.164279505610466,
+      "rewards/rejected": 0.08379074931144714,
+      "step": 264
+    },
+    {
+      "epoch": 0.3080709373868983,
+      "grad_norm": 89.98079729490527,
+      "learning_rate": 1.9490060355973096e-07,
+      "logits/chosen": -1.3349117040634155,
+      "logits/rejected": -1.4269710779190063,
+      "logps/chosen": -117.39810180664062,
+      "logps/rejected": -144.81390380859375,
+      "loss": 0.6071,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.13228380680084229,
+      "rewards/margins": 0.36814936995506287,
+      "rewards/rejected": -0.2358655333518982,
+      "step": 266
+    },
+    {
+      "epoch": 0.3103872602243938,
+      "grad_norm": 79.79141686146392,
+      "learning_rate": 1.9477807345199713e-07,
+      "logits/chosen": -1.2187737226486206,
+      "logits/rejected": -1.255754828453064,
+      "logps/chosen": -129.10220336914062,
+      "logps/rejected": -155.4088592529297,
+      "loss": 0.5498,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.04840267822146416,
+      "rewards/margins": 0.8025398850440979,
+      "rewards/rejected": -0.7541371583938599,
+      "step": 268
+    },
+    {
+      "epoch": 0.3127035830618892,
+      "grad_norm": 76.99480771293982,
+      "learning_rate": 1.946541281176386e-07,
+      "logits/chosen": -1.3978129625320435,
+      "logits/rejected": -1.3492777347564697,
+      "logps/chosen": -94.11738586425781,
+      "logps/rejected": -111.17606353759766,
+      "loss": 0.6439,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.10735100507736206,
+      "rewards/margins": 0.33690255880355835,
+      "rewards/rejected": -0.22955158352851868,
+      "step": 270
+    },
+    {
+      "epoch": 0.3150199058993847,
+      "grad_norm": 123.83701643097643,
+      "learning_rate": 1.9452876940740767e-07,
+      "logits/chosen": -1.3182752132415771,
+      "logits/rejected": -1.3577101230621338,
+      "logps/chosen": -179.61712646484375,
+      "logps/rejected": -175.739501953125,
+      "loss": 0.658,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.8353556394577026,
+      "rewards/margins": -0.027862735092639923,
+      "rewards/rejected": -0.8074928522109985,
+      "step": 272
+    },
+    {
+      "epoch": 0.3173362287368802,
+      "grad_norm": 85.72321946906887,
+      "learning_rate": 1.9440199919316122e-07,
+      "logits/chosen": -1.288657546043396,
+      "logits/rejected": -1.3015202283859253,
+      "logps/chosen": -119.4478759765625,
+      "logps/rejected": -126.77153015136719,
+      "loss": 0.5747,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.10668228566646576,
+      "rewards/margins": 0.2372274398803711,
+      "rewards/rejected": -0.34390971064567566,
+      "step": 274
+    },
+    {
+      "epoch": 0.31965255157437567,
+      "grad_norm": 74.20876048665262,
+      "learning_rate": 1.9427381936783265e-07,
+      "logits/chosen": -1.2866897583007812,
+      "logits/rejected": -1.2775256633758545,
+      "logps/chosen": -128.80926513671875,
+      "logps/rejected": -149.09042358398438,
+      "loss": 0.5875,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.045619502663612366,
+      "rewards/margins": 0.7617495059967041,
+      "rewards/rejected": -0.7161301374435425,
+      "step": 276
+    },
+    {
+      "epoch": 0.32196887441187116,
+      "grad_norm": 92.4643464121328,
+      "learning_rate": 1.9414423184540364e-07,
+      "logits/chosen": -1.2458128929138184,
+      "logits/rejected": -1.3468252420425415,
+      "logps/chosen": -185.1983642578125,
+      "logps/rejected": -208.1055908203125,
+      "loss": 0.6219,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.6145004034042358,
+      "rewards/margins": 0.43242332339286804,
+      "rewards/rejected": -1.0469236373901367,
+      "step": 278
+    },
+    {
+      "epoch": 0.3242851972493666,
+      "grad_norm": 78.52373912784961,
+      "learning_rate": 1.940132385608757e-07,
+      "logits/chosen": -1.2931345701217651,
+      "logits/rejected": -1.285240888595581,
+      "logps/chosen": -120.32514953613281,
+      "logps/rejected": -127.14945983886719,
+      "loss": 0.6194,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.13594146072864532,
+      "rewards/margins": 0.45918428897857666,
+      "rewards/rejected": -0.5951257348060608,
+      "step": 280
+    },
+    {
+      "epoch": 0.3266015200868621,
+      "grad_norm": 87.99833578536212,
+      "learning_rate": 1.9388084147024119e-07,
+      "logits/chosen": -1.289980411529541,
+      "logits/rejected": -1.3120776414871216,
+      "logps/chosen": -143.28274536132812,
+      "logps/rejected": -184.68968200683594,
+      "loss": 0.5612,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.36499708890914917,
+      "rewards/margins": 0.8015878200531006,
+      "rewards/rejected": -1.166584849357605,
+      "step": 282
+    },
+    {
+      "epoch": 0.3289178429243576,
+      "grad_norm": 130.88630180608516,
+      "learning_rate": 1.93747042550454e-07,
+      "logits/chosen": -1.1992597579956055,
+      "logits/rejected": -1.20537531375885,
+      "logps/chosen": -164.58963012695312,
+      "logps/rejected": -188.33392333984375,
+      "loss": 0.6706,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.032479241490364075,
+      "rewards/margins": 0.6490625143051147,
+      "rewards/rejected": -0.6815417408943176,
+      "step": 284
+    },
+    {
+      "epoch": 0.33123416576185305,
+      "grad_norm": 129.38381304632557,
+      "learning_rate": 1.9361184379940027e-07,
+      "logits/chosen": -1.3481284379959106,
+      "logits/rejected": -1.3769184350967407,
+      "logps/chosen": -144.51824951171875,
+      "logps/rejected": -184.82598876953125,
+      "loss": 0.5956,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.20756953954696655,
+      "rewards/margins": 1.1878336668014526,
+      "rewards/rejected": -1.3954031467437744,
+      "step": 286
+    },
+    {
+      "epoch": 0.33355048859934855,
+      "grad_norm": 75.58880846521522,
+      "learning_rate": 1.9347524723586834e-07,
+      "logits/chosen": -1.3142046928405762,
+      "logits/rejected": -1.3535311222076416,
+      "logps/chosen": -127.45948791503906,
+      "logps/rejected": -134.2197723388672,
+      "loss": 0.5643,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.029636431485414505,
+      "rewards/margins": 0.3624846637248993,
+      "rewards/rejected": -0.3921211361885071,
+      "step": 288
+    },
+    {
+      "epoch": 0.335866811436844,
+      "grad_norm": 73.31791152641335,
+      "learning_rate": 1.9333725489951874e-07,
+      "logits/chosen": -1.279150128364563,
+      "logits/rejected": -1.2785069942474365,
+      "logps/chosen": -137.74392700195312,
+      "logps/rejected": -150.1664581298828,
+      "loss": 0.562,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.09417904168367386,
+      "rewards/margins": 0.4170314073562622,
+      "rewards/rejected": -0.5112104415893555,
+      "step": 290
+    },
+    {
+      "epoch": 0.3381831342743395,
+      "grad_norm": 92.52553029666018,
+      "learning_rate": 1.9319786885085363e-07,
+      "logits/chosen": -1.2694755792617798,
+      "logits/rejected": -1.2954623699188232,
+      "logps/chosen": -131.68209838867188,
+      "logps/rejected": -147.16407775878906,
+      "loss": 0.5707,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.23095721006393433,
+      "rewards/margins": 0.6836221814155579,
+      "rewards/rejected": -0.9145793318748474,
+      "step": 292
+    },
+    {
+      "epoch": 0.34049945711183494,
+      "grad_norm": 117.1109903878386,
+      "learning_rate": 1.9305709117118614e-07,
+      "logits/chosen": -1.3775343894958496,
+      "logits/rejected": -1.40194571018219,
+      "logps/chosen": -152.88351440429688,
+      "logps/rejected": -152.07113647460938,
+      "loss": 0.6534,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.25070011615753174,
+      "rewards/margins": 0.443280965089798,
+      "rewards/rejected": -0.6939811110496521,
+      "step": 294
+    },
+    {
+      "epoch": 0.34281577994933043,
+      "grad_norm": 90.63184013182904,
+      "learning_rate": 1.929149239626092e-07,
+      "logits/chosen": -1.3810930252075195,
+      "logits/rejected": -1.375144600868225,
+      "logps/chosen": -138.50286865234375,
+      "logps/rejected": -150.77099609375,
+      "loss": 0.6208,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.08024093508720398,
+      "rewards/margins": 0.330517053604126,
+      "rewards/rejected": -0.41075798869132996,
+      "step": 296
+    },
+    {
+      "epoch": 0.34513210278682593,
+      "grad_norm": 151.73571113362462,
+      "learning_rate": 1.9277136934796427e-07,
+      "logits/chosen": -1.3765751123428345,
+      "logits/rejected": -1.3763781785964966,
+      "logps/chosen": -133.6553497314453,
+      "logps/rejected": -155.61392211914062,
+      "loss": 0.6849,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.21619975566864014,
+      "rewards/margins": 0.11746194958686829,
+      "rewards/rejected": -0.3336617350578308,
+      "step": 298
+    },
+    {
+      "epoch": 0.3474484256243214,
+      "grad_norm": 102.44748886372176,
+      "learning_rate": 1.926264294708095e-07,
+      "logits/chosen": -1.2531358003616333,
+      "logits/rejected": -1.280750036239624,
+      "logps/chosen": -142.09063720703125,
+      "logps/rejected": -168.24539184570312,
+      "loss": 0.5871,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.10979723930358887,
+      "rewards/margins": 0.8283678293228149,
+      "rewards/rejected": -0.9381651282310486,
+      "step": 300
+    },
+    {
+      "epoch": 0.3474484256243214,
+      "eval_logits/chosen": -1.3154690265655518,
+      "eval_logits/rejected": -1.3106950521469116,
+      "eval_logps/chosen": -138.28590393066406,
+      "eval_logps/rejected": -137.84115600585938,
+      "eval_loss": 0.6834442615509033,
+      "eval_rewards/accuracies": 0.6000000238418579,
+      "eval_rewards/chosen": -0.2654740810394287,
+      "eval_rewards/margins": 0.12328676134347916,
+      "eval_rewards/rejected": -0.38876083493232727,
+      "eval_runtime": 24.6332,
+      "eval_samples_per_second": 4.06,
+      "eval_steps_per_second": 1.015,
+      "step": 300
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1726,
+  "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:b1680ae2225faa7dde8b2f3c0cd727f6c59e79584047f2c57616dc0f5447f195
+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)