Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": null,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.49.0.dev0"
+}

global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01940f3fc7fdd50494254f9077e6b3f4899683cc1690007a0d144a9bdd9a0cbf
+size 32121054426

global_step100/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:fd242bed02cbf1bb85fe30469aeaef2d080e9edd53eb769c0813b2bec10b1af8
+size 32121054426

global_step100/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09acb07930167ab6e860509f78a9f6ffb87f2bc65620c47d16cff4dd5ff5cf92
+size 32121054426

global_step100/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4320aac32eb2f7244f743aac79e444e3db3458965b2643d80958359e628b208f
+size 148773

global_step100/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6863dd7c4ab597e223947765598b4a278ef0e3d0825ef703036da953a4e919c
+size 148773

global_step100/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b348d0db741b24d8665492eec043cf48153110758d5d32e53485b54247a1d91
+size 148773

latest

@@ -0,0 +1 @@
+global_step100

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40b48cfa41707d075c89c6e355366fb809b0014bbdcc09955738faf2c754dac
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74532f06d067bbc7a14f228e9999558036918cf3413fbfeb73327660aa1117a
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3b3bf722c260bd1e95e787dd48d0a1aa2ab0ef606ebcdfe523760ee4434795
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d27d32c2cde0ec56988218a5f05d35e5b85c005e5f165546f97f4561ff11eab
+size 1168138808

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"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7359a6099a64604047970ae4af3e7f7e14a0bbf8760c9a75b9e598caa08dae3
+size 14960

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8cdfceac9f7917b978dca661a3b8e04187faea5d5f6bd7b462d61d8234d57f
+size 1064

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|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ff5472d095ccd9332d9e723153d7bc7226cb6be9c1bffda738b5ba2e71bf26
+size 17210084

tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "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": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "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": "<|eom_id|>",
+      "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": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8028904054596547,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 155.3333339691162,
+      "epoch": 0.008028904054596548,
+      "grad_norm": 0.8266991671440796,
+      "kl": 0.0,
+      "learning_rate": 3.0000000000000004e-08,
+      "loss": 0.0,
+      "reward": 2.3694444835186004,
+      "reward_std": 0.706648226082325,
+      "rewards/accuracy_reward_log": 1.4888889163732528,
+      "rewards/format_number_reward": 0.4138888940215111,
+      "rewards/format_reasoning_reward": 0.46666666865348816,
+      "step": 1
+    },
+    {
+      "completion_length": 177.53333435058593,
+      "epoch": 0.016057808109193095,
+      "grad_norm": 0.853670554176349,
+      "kl": 0.0,
+      "learning_rate": 6.000000000000001e-08,
+      "loss": 0.0,
+      "reward": 2.3472222685813904,
+      "reward_std": 0.6901098385453224,
+      "rewards/accuracy_reward_log": 1.500000025331974,
+      "rewards/format_number_reward": 0.4000000059604645,
+      "rewards/format_reasoning_reward": 0.4472222253680229,
+      "step": 2
+    },
+    {
+      "completion_length": 160.18333435058594,
+      "epoch": 0.02408671216378964,
+      "grad_norm": 0.6327729129725634,
+      "kl": 0.00010757744312286376,
+      "learning_rate": 9e-08,
+      "loss": 0.0,
+      "reward": 2.4138889491558073,
+      "reward_std": 0.5638244189321995,
+      "rewards/accuracy_reward_log": 1.5222222447395324,
+      "rewards/format_number_reward": 0.4194444492459297,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 3
+    },
+    {
+      "completion_length": 167.59444580078124,
+      "epoch": 0.03211561621838619,
+      "grad_norm": 0.6798573023319466,
+      "kl": 0.00010120868682861328,
+      "learning_rate": 1.2000000000000002e-07,
+      "loss": 0.0,
+      "reward": 2.20833335518837,
+      "reward_std": 0.5129089742898941,
+      "rewards/accuracy_reward_log": 1.333333359658718,
+      "rewards/format_number_reward": 0.4027777835726738,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 4
+    },
+    {
+      "completion_length": 147.56666870117186,
+      "epoch": 0.04014452027298274,
+      "grad_norm": 0.5872669908882053,
+      "kl": 9.968876838684082e-05,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.0,
+      "reward": 2.4361111402511595,
+      "reward_std": 0.48325310088694096,
+      "rewards/accuracy_reward_log": 1.5333333551883697,
+      "rewards/format_number_reward": 0.42222222685813904,
+      "rewards/format_reasoning_reward": 0.48055555671453476,
+      "step": 5
+    },
+    {
+      "completion_length": 168.4333324432373,
+      "epoch": 0.04817342432757928,
+      "grad_norm": 0.842231210713151,
+      "kl": 0.000108298659324646,
+      "learning_rate": 1.8e-07,
+      "loss": 0.0,
+      "reward": 1.9972222298383713,
+      "reward_std": 0.6861602704972029,
+      "rewards/accuracy_reward_log": 1.188888917118311,
+      "rewards/format_number_reward": 0.35555556118488313,
+      "rewards/format_reasoning_reward": 0.45277778059244156,
+      "step": 6
+    },
+    {
+      "completion_length": 161.47222175598145,
+      "epoch": 0.056202328382175835,
+      "grad_norm": 0.6301911132102126,
+      "kl": 0.00010362863540649414,
+      "learning_rate": 2.1000000000000003e-07,
+      "loss": 0.0,
+      "reward": 2.344444477558136,
+      "reward_std": 0.5787256445735693,
+      "rewards/accuracy_reward_log": 1.455555585026741,
+      "rewards/format_number_reward": 0.41111111640930176,
+      "rewards/format_reasoning_reward": 0.47777777910232544,
+      "step": 7
+    },
+    {
+      "completion_length": 178.705558013916,
+      "epoch": 0.06423123243677238,
+      "grad_norm": 0.7904000046666478,
+      "kl": 0.00015439987182617188,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 0.0,
+      "reward": 2.033333358168602,
+      "reward_std": 0.6374398373067379,
+      "rewards/accuracy_reward_log": 1.2000000223517417,
+      "rewards/format_number_reward": 0.37777778320014477,
+      "rewards/format_reasoning_reward": 0.4555555582046509,
+      "step": 8
+    },
+    {
+      "completion_length": 154.6055564880371,
+      "epoch": 0.07226013649136893,
+      "grad_norm": 0.8113384704385274,
+      "kl": 0.00010915249586105347,
+      "learning_rate": 2.7e-07,
+      "loss": 0.0,
+      "reward": 2.4722222566604612,
+      "reward_std": 0.38092764765024184,
+      "rewards/accuracy_reward_log": 1.5777777969837188,
+      "rewards/format_number_reward": 0.4194444492459297,
+      "rewards/format_reasoning_reward": 0.4750000014901161,
+      "step": 9
+    },
+    {
+      "completion_length": 155.86111221313476,
+      "epoch": 0.08028904054596547,
+      "grad_norm": 0.6734680070959974,
+      "kl": 0.00010448098182678223,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 0.0,
+      "reward": 2.3611111462116243,
+      "reward_std": 0.5814844127744436,
+      "rewards/accuracy_reward_log": 1.4777778029441833,
+      "rewards/format_number_reward": 0.413888893276453,
+      "rewards/format_reasoning_reward": 0.4694444462656975,
+      "step": 10
+    },
+    {
+      "completion_length": 167.8611110687256,
+      "epoch": 0.08831794460056203,
+      "grad_norm": 0.6192549717392329,
+      "kl": 0.0002144932746887207,
+      "learning_rate": 3.3e-07,
+      "loss": 0.0,
+      "reward": 2.3972222745418548,
+      "reward_std": 0.5403781462460756,
+      "rewards/accuracy_reward_log": 1.511111134290695,
+      "rewards/format_number_reward": 0.4194444492459297,
+      "rewards/format_reasoning_reward": 0.46666666865348816,
+      "step": 11
+    },
+    {
+      "completion_length": 159.29444694519043,
+      "epoch": 0.09634684865515857,
+      "grad_norm": 0.6219588398194654,
+      "kl": 0.00014747381210327147,
+      "learning_rate": 3.6e-07,
+      "loss": 0.0,
+      "reward": 2.22777781188488,
+      "reward_std": 0.6599382009357214,
+      "rewards/accuracy_reward_log": 1.3777778007090091,
+      "rewards/format_number_reward": 0.3805555604398251,
+      "rewards/format_reasoning_reward": 0.4694444462656975,
+      "step": 12
+    },
+    {
+      "completion_length": 163.36666717529297,
+      "epoch": 0.10437575270975512,
+      "grad_norm": 0.5303599869712791,
+      "kl": 0.0001802980899810791,
+      "learning_rate": 3.9e-07,
+      "loss": 0.0,
+      "reward": 2.388888931274414,
+      "reward_std": 0.38289184793829917,
+      "rewards/accuracy_reward_log": 1.4888889119029045,
+      "rewards/format_number_reward": 0.4111111145466566,
+      "rewards/format_reasoning_reward": 0.4888888895511627,
+      "step": 13
+    },
+    {
+      "completion_length": 153.45000038146972,
+      "epoch": 0.11240465676435167,
+      "grad_norm": 0.5530377333718409,
+      "kl": 0.0004338264465332031,
+      "learning_rate": 4.2000000000000006e-07,
+      "loss": 0.0,
+      "reward": 2.569444465637207,
+      "reward_std": 0.42339018881320956,
+      "rewards/accuracy_reward_log": 1.6333333551883698,
+      "rewards/format_number_reward": 0.45277778059244156,
+      "rewards/format_reasoning_reward": 0.4833333343267441,
+      "step": 14
+    },
+    {
+      "completion_length": 165.07777938842773,
+      "epoch": 0.12043356081894821,
+      "grad_norm": 0.49102029519105816,
+      "kl": 0.0006180524826049805,
+      "learning_rate": 4.5e-07,
+      "loss": 0.0,
+      "reward": 2.597222250699997,
+      "reward_std": 0.3478126596659422,
+      "rewards/accuracy_reward_log": 1.6444444566965104,
+      "rewards/format_number_reward": 0.46388889104127884,
+      "rewards/format_reasoning_reward": 0.4888888895511627,
+      "step": 15
+    },
+    {
+      "completion_length": 164.92778129577636,
+      "epoch": 0.12846246487354476,
+      "grad_norm": 0.6338598904220616,
+      "kl": 0.0007488012313842773,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 0.0,
+      "reward": 2.319444465637207,
+      "reward_std": 0.5170031324028969,
+      "rewards/accuracy_reward_log": 1.4222222447395325,
+      "rewards/format_number_reward": 0.4277777820825577,
+      "rewards/format_reasoning_reward": 0.4694444462656975,
+      "step": 16
+    },
+    {
+      "completion_length": 156.144446182251,
+      "epoch": 0.13649136892814132,
+      "grad_norm": 0.5574851133438189,
+      "kl": 0.0012537002563476562,
+      "learning_rate": 5.100000000000001e-07,
+      "loss": 0.0001,
+      "reward": 2.5555556058883666,
+      "reward_std": 0.44343185126781465,
+      "rewards/accuracy_reward_log": 1.6222222417593002,
+      "rewards/format_number_reward": 0.45000000223517417,
+      "rewards/format_reasoning_reward": 0.4833333343267441,
+      "step": 17
+    },
+    {
+      "completion_length": 153.38888931274414,
+      "epoch": 0.14452027298273787,
+      "grad_norm": 0.6029065735373917,
+      "kl": 0.001799297332763672,
+      "learning_rate": 5.4e-07,
+      "loss": 0.0001,
+      "reward": 2.4750000178813933,
+      "reward_std": 0.5368539825081825,
+      "rewards/accuracy_reward_log": 1.5444444686174392,
+      "rewards/format_number_reward": 0.45000000298023224,
+      "rewards/format_reasoning_reward": 0.48055555671453476,
+      "step": 18
+    },
+    {
+      "completion_length": 170.45000228881835,
+      "epoch": 0.1525491770373344,
+      "grad_norm": 0.6238637844164427,
+      "kl": 0.0022980213165283204,
+      "learning_rate": 5.7e-07,
+      "loss": 0.0001,
+      "reward": 2.3472222328186034,
+      "reward_std": 0.5638264730572701,
+      "rewards/accuracy_reward_log": 1.4444444686174394,
+      "rewards/format_number_reward": 0.4333333373069763,
+      "rewards/format_reasoning_reward": 0.4694444462656975,
+      "step": 19
+    },
+    {
+      "completion_length": 146.12777786254884,
+      "epoch": 0.16057808109193095,
+      "grad_norm": 0.4196477311949672,
+      "kl": 0.00455629825592041,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.0002,
+      "reward": 2.5250000238418577,
+      "reward_std": 0.27503596656024454,
+      "rewards/accuracy_reward_log": 1.5888888999819755,
+      "rewards/format_number_reward": 0.44722222462296485,
+      "rewards/format_reasoning_reward": 0.4888888895511627,
+      "step": 20
+    },
+    {
+      "completion_length": 179.50000228881837,
+      "epoch": 0.1686069851465275,
+      "grad_norm": 0.5891348987729047,
+      "kl": 0.0013088226318359376,
+      "learning_rate": 6.3e-07,
+      "loss": 0.0001,
+      "reward": 2.4500000417232513,
+      "reward_std": 0.5685264855623245,
+      "rewards/accuracy_reward_log": 1.5666666895151138,
+      "rewards/format_number_reward": 0.43611111491918564,
+      "rewards/format_reasoning_reward": 0.4472222253680229,
+      "step": 21
+    },
+    {
+      "completion_length": 167.82222518920898,
+      "epoch": 0.17663588920112405,
+      "grad_norm": 0.5080236888533528,
+      "kl": 0.0015691757202148438,
+      "learning_rate": 6.6e-07,
+      "loss": 0.0001,
+      "reward": 2.4805555999279023,
+      "reward_std": 0.38282057382166385,
+      "rewards/accuracy_reward_log": 1.5333333551883697,
+      "rewards/format_number_reward": 0.4694444462656975,
+      "rewards/format_reasoning_reward": 0.47777777910232544,
+      "step": 22
+    },
+    {
+      "completion_length": 159.62222480773926,
+      "epoch": 0.1846647932557206,
+      "grad_norm": 0.5410426478942184,
+      "kl": 0.0024078369140625,
+      "learning_rate": 6.900000000000001e-07,
+      "loss": 0.0001,
+      "reward": 2.6277777940034865,
+      "reward_std": 0.332701800763607,
+      "rewards/accuracy_reward_log": 1.6777777917683125,
+      "rewards/format_number_reward": 0.46388889029622077,
+      "rewards/format_reasoning_reward": 0.4861111119389534,
+      "step": 23
+    },
+    {
+      "completion_length": 157.90000114440917,
+      "epoch": 0.19269369731031713,
+      "grad_norm": 0.5882381452711394,
+      "kl": 0.002088165283203125,
+      "learning_rate": 7.2e-07,
+      "loss": 0.0001,
+      "reward": 2.6722222566604614,
+      "reward_std": 0.38149141892790794,
+      "rewards/accuracy_reward_log": 1.7111111283302307,
+      "rewards/format_number_reward": 0.48055555671453476,
+      "rewards/format_reasoning_reward": 0.48055555671453476,
+      "step": 24
+    },
+    {
+      "completion_length": 148.97222328186035,
+      "epoch": 0.20072260136491368,
+      "grad_norm": 0.46880008245690374,
+      "kl": 0.002790069580078125,
+      "learning_rate": 7.5e-07,
+      "loss": 0.0001,
+      "reward": 2.6666667222976685,
+      "reward_std": 0.42418686002492906,
+      "rewards/accuracy_reward_log": 1.7111111283302307,
+      "rewards/format_number_reward": 0.46388889104127884,
+      "rewards/format_reasoning_reward": 0.49166666716337204,
+      "step": 25
+    },
+    {
+      "completion_length": 166.62222595214843,
+      "epoch": 0.20875150541951024,
+      "grad_norm": 0.6233073148075161,
+      "kl": 0.003025054931640625,
+      "learning_rate": 7.8e-07,
+      "loss": 0.0001,
+      "reward": 2.544444477558136,
+      "reward_std": 0.5540193915367126,
+      "rewards/accuracy_reward_log": 1.6111111342906952,
+      "rewards/format_number_reward": 0.45277778059244156,
+      "rewards/format_reasoning_reward": 0.48055555671453476,
+      "step": 26
+    },
+    {
+      "completion_length": 153.51666755676268,
+      "epoch": 0.2167804094741068,
+      "grad_norm": 0.4559712721597118,
+      "kl": 0.003208160400390625,
+      "learning_rate": 8.100000000000001e-07,
+      "loss": 0.0001,
+      "reward": 2.5555555880069734,
+      "reward_std": 0.34781265556812285,
+      "rewards/accuracy_reward_log": 1.5888889104127883,
+      "rewards/format_number_reward": 0.4750000014901161,
+      "rewards/format_reasoning_reward": 0.49166666716337204,
+      "step": 27
+    },
+    {
+      "completion_length": 172.8500011444092,
+      "epoch": 0.22480931352870334,
+      "grad_norm": 0.5449553128247491,
+      "kl": 0.0030437469482421874,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 0.0001,
+      "reward": 2.4750000476837157,
+      "reward_std": 0.3911139152944088,
+      "rewards/accuracy_reward_log": 1.544444465637207,
+      "rewards/format_number_reward": 0.45000000223517417,
+      "rewards/format_reasoning_reward": 0.48055555671453476,
+      "step": 28
+    },
+    {
+      "completion_length": 164.09999961853026,
+      "epoch": 0.23283821758329987,
+      "grad_norm": 0.5619230788736052,
+      "kl": 0.00468292236328125,
+      "learning_rate": 8.699999999999999e-07,
+      "loss": 0.0002,
+      "reward": 2.502777820825577,
+      "reward_std": 0.46127643398940565,
+      "rewards/accuracy_reward_log": 1.5666666895151138,
+      "rewards/format_number_reward": 0.46388889104127884,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 29
+    },
+    {
+      "completion_length": 151.90000228881837,
+      "epoch": 0.24086712163789642,
+      "grad_norm": 0.7524148953577687,
+      "kl": 0.0029834747314453126,
+      "learning_rate": 9e-07,
+      "loss": 0.0001,
+      "reward": 2.7583333969116213,
+      "reward_std": 0.31546305269002917,
+      "rewards/accuracy_reward_log": 1.7777777910232544,
+      "rewards/format_number_reward": 0.4861111119389534,
+      "rewards/format_reasoning_reward": 0.49444444477558136,
+      "step": 30
+    },
+    {
+      "completion_length": 150.7055564880371,
+      "epoch": 0.24889602569249297,
+      "grad_norm": 1.70651807869166,
+      "kl": 0.013134002685546875,
+      "learning_rate": 9.3e-07,
+      "loss": 0.0005,
+      "reward": 2.8583333492279053,
+      "reward_std": 0.1264950528740883,
+      "rewards/accuracy_reward_log": 1.8666666746139526,
+      "rewards/format_number_reward": 0.49444444477558136,
+      "rewards/format_reasoning_reward": 0.4972222223877907,
+      "step": 31
+    },
+    {
+      "completion_length": 169.57222366333008,
+      "epoch": 0.2569249297470895,
+      "grad_norm": 0.41158376714433204,
+      "kl": 0.004754638671875,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 0.0002,
+      "reward": 2.6888889491558077,
+      "reward_std": 0.29488888159394266,
+      "rewards/accuracy_reward_log": 1.722222238779068,
+      "rewards/format_number_reward": 0.4833333343267441,
+      "rewards/format_reasoning_reward": 0.4833333343267441,
+      "step": 32
+    },
+    {
+      "completion_length": 160.33333473205568,
+      "epoch": 0.2649538338016861,
+      "grad_norm": 0.5042425185498995,
+      "kl": 0.005771636962890625,
+      "learning_rate": 9.9e-07,
+      "loss": 0.0002,
+      "reward": 2.6055556178092956,
+      "reward_std": 0.33884221240878104,
+      "rewards/accuracy_reward_log": 1.644444465637207,
+      "rewards/format_number_reward": 0.4750000014901161,
+      "rewards/format_reasoning_reward": 0.4861111119389534,
+      "step": 33
+    },
+    {
+      "completion_length": 165.0555561065674,
+      "epoch": 0.27298273785628263,
+      "grad_norm": 0.5229992920065437,
+      "kl": 0.006603240966796875,
+      "learning_rate": 1.0200000000000002e-06,
+      "loss": 0.0003,
+      "reward": 2.663888943195343,
+      "reward_std": 0.4261931136250496,
+      "rewards/accuracy_reward_log": 1.6888889074325562,
+      "rewards/format_number_reward": 0.4833333343267441,
+      "rewards/format_reasoning_reward": 0.49166666716337204,
+      "step": 34
+    },
+    {
+      "completion_length": 164.63888969421387,
+      "epoch": 0.2810116419108792,
+      "grad_norm": 0.4700519781333619,
+      "kl": 0.006055450439453125,
+      "learning_rate": 1.05e-06,
+      "loss": 0.0002,
+      "reward": 2.6194444715976717,
+      "reward_std": 0.34433056265115736,
+      "rewards/accuracy_reward_log": 1.6444444596767425,
+      "rewards/format_number_reward": 0.4861111119389534,
+      "rewards/format_reasoning_reward": 0.4888888895511627,
+      "step": 35
+    },
+    {
+      "completion_length": 195.3277786254883,
+      "epoch": 0.28904054596547574,
+      "grad_norm": 0.5312518629436677,
+      "kl": 0.005257415771484375,
+      "learning_rate": 1.08e-06,
+      "loss": 0.0002,
+      "reward": 2.4138889372348786,
+      "reward_std": 0.4737018562853336,
+      "rewards/accuracy_reward_log": 1.5000000193715095,
+      "rewards/format_number_reward": 0.45277778059244156,
+      "rewards/format_reasoning_reward": 0.4611111134290695,
+      "step": 36
+    },
+    {
+      "completion_length": 162.9777805328369,
+      "epoch": 0.29706945002007223,
+      "grad_norm": 0.3947867705421231,
+      "kl": 0.00660400390625,
+      "learning_rate": 1.11e-06,
+      "loss": 0.0003,
+      "reward": 2.8111111521720886,
+      "reward_std": 0.21169509664177893,
+      "rewards/accuracy_reward_log": 1.8222222328186035,
+      "rewards/format_number_reward": 0.49166666716337204,
+      "rewards/format_reasoning_reward": 0.4972222223877907,
+      "step": 37
+    },
+    {
+      "completion_length": 171.81111373901368,
+      "epoch": 0.3050983540746688,
+      "grad_norm": 0.49680622935913366,
+      "kl": 0.0083709716796875,
+      "learning_rate": 1.14e-06,
+      "loss": 0.0003,
+      "reward": 2.600000059604645,
+      "reward_std": 0.3381901502609253,
+      "rewards/accuracy_reward_log": 1.6333333551883698,
+      "rewards/format_number_reward": 0.47777777910232544,
+      "rewards/format_reasoning_reward": 0.4888888895511627,
+      "step": 38
+    },
+    {
+      "completion_length": 159.78333473205566,
+      "epoch": 0.31312725812926534,
+      "grad_norm": 0.4841125000891351,
+      "kl": 0.01015167236328125,
+      "learning_rate": 1.17e-06,
+      "loss": 0.0004,
+      "reward": 2.7166666865348814,
+      "reward_std": 0.25784134939312936,
+      "rewards/accuracy_reward_log": 1.7555555701255798,
+      "rewards/format_number_reward": 0.4750000014901161,
+      "rewards/format_reasoning_reward": 0.4861111119389534,
+      "step": 39
+    },
+    {
+      "completion_length": 160.47777938842773,
+      "epoch": 0.3211561621838619,
+      "grad_norm": 0.4051878172293322,
+      "kl": 0.00718231201171875,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.0003,
+      "reward": 2.6527778089046476,
+      "reward_std": 0.27083261907100675,
+      "rewards/accuracy_reward_log": 1.6777777969837189,
+      "rewards/format_number_reward": 0.4861111119389534,
+      "rewards/format_reasoning_reward": 0.4888888895511627,
+      "step": 40
+    },
+    {
+      "completion_length": 164.8000015258789,
+      "epoch": 0.32918506623845845,
+      "grad_norm": 0.474618622817464,
+      "kl": 0.006967926025390625,
+      "learning_rate": 1.2299999999999999e-06,
+      "loss": 0.0003,
+      "reward": 2.7750000238418577,
+      "reward_std": 0.24537386298179625,
+      "rewards/accuracy_reward_log": 1.800000011920929,
+      "rewards/format_number_reward": 0.4861111119389534,
+      "rewards/format_reasoning_reward": 0.4888888895511627,
+      "step": 41
+    },
+    {
+      "completion_length": 166.5111141204834,
+      "epoch": 0.337213970293055,
+      "grad_norm": 0.3629585253598538,
+      "kl": 0.007363128662109375,
+      "learning_rate": 1.26e-06,
+      "loss": 0.0003,
+      "reward": 2.63055557012558,
+      "reward_std": 0.22272009253501893,
+      "rewards/accuracy_reward_log": 1.6555555701255797,
+      "rewards/format_number_reward": 0.4861111119389534,
+      "rewards/format_reasoning_reward": 0.4888888895511627,
+      "step": 42
+    },
+    {
+      "completion_length": 166.7388900756836,
+      "epoch": 0.34524287434765155,
+      "grad_norm": 0.4008326525358567,
+      "kl": 0.009012603759765625,
+      "learning_rate": 1.29e-06,
+      "loss": 0.0004,
+      "reward": 2.708333361148834,
+      "reward_std": 0.29148011431097987,
+      "rewards/accuracy_reward_log": 1.7444444596767426,
+      "rewards/format_number_reward": 0.47777777910232544,
+      "rewards/format_reasoning_reward": 0.4861111119389534,
+      "step": 43
+    },
+    {
+      "completion_length": 185.93888893127442,
+      "epoch": 0.3532717784022481,
+      "grad_norm": 0.5017342406963871,
+      "kl": 0.00979156494140625,
+      "learning_rate": 1.32e-06,
+      "loss": 0.0004,
+      "reward": 2.5722222566604613,
+      "reward_std": 0.3904368232935667,
+      "rewards/accuracy_reward_log": 1.6555555760860443,
+      "rewards/format_number_reward": 0.4472222253680229,
+      "rewards/format_reasoning_reward": 0.4694444462656975,
+      "step": 44
+    },
+    {
+      "completion_length": 170.97777862548827,
+      "epoch": 0.36130068245684466,
+      "grad_norm": 0.36508724491351696,
+      "kl": 0.00971527099609375,
+      "learning_rate": 1.35e-06,
+      "loss": 0.0004,
+      "reward": 2.680555593967438,
+      "reward_std": 0.1924500897526741,
+      "rewards/accuracy_reward_log": 1.7111111253499984,
+      "rewards/format_number_reward": 0.48055555671453476,
+      "rewards/format_reasoning_reward": 0.4888888895511627,
+      "step": 45
+    },
+    {
+      "completion_length": 200.09444770812988,
+      "epoch": 0.3693295865114412,
+      "grad_norm": 0.5859797241606328,
+      "kl": 0.01236724853515625,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 0.0005,
+      "reward": 2.4972222447395325,
+      "reward_std": 0.4179751716554165,
+      "rewards/accuracy_reward_log": 1.588888904452324,
+      "rewards/format_number_reward": 0.4527777798473835,
+      "rewards/format_reasoning_reward": 0.4555555582046509,
+      "step": 46
+    },
+    {
+      "completion_length": 190.55000267028808,
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.6735251651031329,
+      "kl": 0.013592529296875,
+      "learning_rate": 1.41e-06,
+      "loss": 0.0005,
+      "reward": 2.525000035762787,
+      "reward_std": 0.39592516496777536,
+      "rewards/accuracy_reward_log": 1.6000000178813933,
+      "rewards/format_number_reward": 0.4611111134290695,
+      "rewards/format_reasoning_reward": 0.46388889104127884,
+      "step": 47
+    },
+    {
+      "completion_length": 177.14444732666016,
+      "epoch": 0.38538739462063426,
+      "grad_norm": 0.4013696331659362,
+      "kl": 0.01161346435546875,
+      "learning_rate": 1.44e-06,
+      "loss": 0.0005,
+      "reward": 2.725000035762787,
+      "reward_std": 0.30932264029979706,
+      "rewards/accuracy_reward_log": 1.7666666805744171,
+      "rewards/format_number_reward": 0.4750000014901161,
+      "rewards/format_reasoning_reward": 0.4833333343267441,
+      "step": 48
+    },
+    {
+      "completion_length": 183.58333511352538,
+      "epoch": 0.3934162986752308,
+      "grad_norm": 0.413245950296645,
+      "kl": 0.0140655517578125,
+      "learning_rate": 1.4700000000000001e-06,
+      "loss": 0.0006,
+      "reward": 2.547222238779068,
+      "reward_std": 0.28799803368747234,
+      "rewards/accuracy_reward_log": 1.6000000208616256,
+      "rewards/format_number_reward": 0.4694444462656975,
+      "rewards/format_reasoning_reward": 0.47777777910232544,
+      "step": 49
+    },
+    {
+      "completion_length": 179.96666717529297,
+      "epoch": 0.40144520272982737,
+      "grad_norm": 0.41408601639844395,
+      "kl": 0.01335296630859375,
+      "learning_rate": 1.5e-06,
+      "loss": 0.0005,
+      "reward": 2.658333349227905,
+      "reward_std": 0.3410413548350334,
+      "rewards/accuracy_reward_log": 1.7222222357988357,
+      "rewards/format_number_reward": 0.46388889104127884,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 50
+    },
+    {
+      "completion_length": 185.75556030273438,
+      "epoch": 0.4094741067844239,
+      "grad_norm": 0.4053783571755214,
+      "kl": 0.0148193359375,
+      "learning_rate": 1.53e-06,
+      "loss": 0.0006,
+      "reward": 2.6555556058883667,
+      "reward_std": 0.35194680131971834,
+      "rewards/accuracy_reward_log": 1.722222238779068,
+      "rewards/format_number_reward": 0.46388889104127884,
+      "rewards/format_reasoning_reward": 0.4694444462656975,
+      "step": 51
+    },
+    {
+      "completion_length": 209.23333358764648,
+      "epoch": 0.41750301083902047,
+      "grad_norm": 0.55024118806201,
+      "kl": 0.018719482421875,
+      "learning_rate": 1.56e-06,
+      "loss": 0.0007,
+      "reward": 2.4083333551883697,
+      "reward_std": 0.5498852420598268,
+      "rewards/accuracy_reward_log": 1.5333333522081376,
+      "rewards/format_number_reward": 0.430555559694767,
+      "rewards/format_reasoning_reward": 0.4444444477558136,
+      "step": 52
+    },
+    {
+      "completion_length": 201.15000343322754,
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.4665326355575322,
+      "kl": 0.01983795166015625,
+      "learning_rate": 1.59e-06,
+      "loss": 0.0008,
+      "reward": 2.5222222208976746,
+      "reward_std": 0.5347743809223175,
+      "rewards/accuracy_reward_log": 1.6333333492279052,
+      "rewards/format_number_reward": 0.4416666693985462,
+      "rewards/format_reasoning_reward": 0.44722222462296485,
+      "step": 53
+    },
+    {
+      "completion_length": 192.3111145019531,
+      "epoch": 0.4335608189482136,
+      "grad_norm": 0.4264344321145415,
+      "kl": 0.02133026123046875,
+      "learning_rate": 1.6200000000000002e-06,
+      "loss": 0.0009,
+      "reward": 2.566666692495346,
+      "reward_std": 0.47150271385908127,
+      "rewards/accuracy_reward_log": 1.6555555760860443,
+      "rewards/format_number_reward": 0.45277778059244156,
+      "rewards/format_reasoning_reward": 0.4583333358168602,
+      "step": 54
+    },
+    {
+      "completion_length": 207.86111373901366,
+      "epoch": 0.44158972300281013,
+      "grad_norm": 0.41848310682566847,
+      "kl": 0.0194488525390625,
+      "learning_rate": 1.65e-06,
+      "loss": 0.0008,
+      "reward": 2.525000047683716,
+      "reward_std": 0.5073827020823956,
+      "rewards/accuracy_reward_log": 1.6333333492279052,
+      "rewards/format_number_reward": 0.4444444477558136,
+      "rewards/format_reasoning_reward": 0.4472222253680229,
+      "step": 55
+    },
+    {
+      "completion_length": 218.4888916015625,
+      "epoch": 0.4496186270574067,
+      "grad_norm": 0.493209444659726,
+      "kl": 0.0301055908203125,
+      "learning_rate": 1.6800000000000002e-06,
+      "loss": 0.0012,
+      "reward": 2.4250000417232513,
+      "reward_std": 0.6275906786322594,
+      "rewards/accuracy_reward_log": 1.5777777969837188,
+      "rewards/format_number_reward": 0.41388889253139494,
+      "rewards/format_reasoning_reward": 0.4333333373069763,
+      "step": 56
+    },
+    {
+      "completion_length": 207.85555877685547,
+      "epoch": 0.45764753111200324,
+      "grad_norm": 0.4781117283691274,
+      "kl": 0.028985595703125,
+      "learning_rate": 1.71e-06,
+      "loss": 0.0012,
+      "reward": 2.4833333492279053,
+      "reward_std": 0.4261951830238104,
+      "rewards/accuracy_reward_log": 1.588888907432556,
+      "rewards/format_number_reward": 0.4444444477558136,
+      "rewards/format_reasoning_reward": 0.45000000298023224,
+      "step": 57
+    },
+    {
+      "completion_length": 207.41666984558105,
+      "epoch": 0.46567643516659973,
+      "grad_norm": 9.7179275371274,
+      "kl": 0.066973876953125,
+      "learning_rate": 1.7399999999999999e-06,
+      "loss": 0.0027,
+      "reward": 2.4972222566604616,
+      "reward_std": 0.6165656700730324,
+      "rewards/accuracy_reward_log": 1.6222222447395325,
+      "rewards/format_number_reward": 0.4333333373069763,
+      "rewards/format_reasoning_reward": 0.4416666701436043,
+      "step": 58
+    },
+    {
+      "completion_length": 199.16111221313477,
+      "epoch": 0.4737053392211963,
+      "grad_norm": 0.4594537727679852,
+      "kl": 0.03179931640625,
+      "learning_rate": 1.77e-06,
+      "loss": 0.0013,
+      "reward": 2.5444444954395293,
+      "reward_std": 0.4083905890583992,
+      "rewards/accuracy_reward_log": 1.6333333522081375,
+      "rewards/format_number_reward": 0.45000000298023224,
+      "rewards/format_reasoning_reward": 0.4611111134290695,
+      "step": 59
+    },
+    {
+      "completion_length": 185.04444580078126,
+      "epoch": 0.48173424327579284,
+      "grad_norm": 0.35591417052929925,
+      "kl": 0.02755126953125,
+      "learning_rate": 1.8e-06,
+      "loss": 0.0011,
+      "reward": 2.708333361148834,
+      "reward_std": 0.30322221145033834,
+      "rewards/accuracy_reward_log": 1.7555555701255798,
+      "rewards/format_number_reward": 0.4750000014901161,
+      "rewards/format_reasoning_reward": 0.47777777910232544,
+      "step": 60
+    },
+    {
+      "completion_length": 217.3444480895996,
+      "epoch": 0.4897631473303894,
+      "grad_norm": 0.47620034091897007,
+      "kl": 0.043768310546875,
+      "learning_rate": 1.83e-06,
+      "loss": 0.0017,
+      "reward": 2.45833335518837,
+      "reward_std": 0.48677313327789307,
+      "rewards/accuracy_reward_log": 1.5777777925133705,
+      "rewards/format_number_reward": 0.4305555589497089,
+      "rewards/format_reasoning_reward": 0.45000000298023224,
+      "step": 61
+    },
+    {
+      "completion_length": 190.76111221313477,
+      "epoch": 0.49779205138498595,
+      "grad_norm": 0.381306777730851,
+      "kl": 0.03514404296875,
+      "learning_rate": 1.86e-06,
+      "loss": 0.0014,
+      "reward": 2.694444453716278,
+      "reward_std": 0.2467763565480709,
+      "rewards/accuracy_reward_log": 1.7555555671453476,
+      "rewards/format_number_reward": 0.4694444462656975,
+      "rewards/format_reasoning_reward": 0.4694444462656975,
+      "step": 62
+    },
+    {
+      "completion_length": 187.97777671813964,
+      "epoch": 0.5058209554395825,
+      "grad_norm": 0.594069782615144,
+      "kl": 0.039031982421875,
+      "learning_rate": 1.8900000000000001e-06,
+      "loss": 0.0016,
+      "reward": 2.6111111283302306,
+      "reward_std": 0.39384557902812956,
+      "rewards/accuracy_reward_log": 1.6888889014720916,
+      "rewards/format_number_reward": 0.4555555582046509,
+      "rewards/format_reasoning_reward": 0.46666666865348816,
+      "step": 63
+    },
+    {
+      "completion_length": 193.00555725097655,
+      "epoch": 0.513849859494179,
+      "grad_norm": 0.5261946833334382,
+      "kl": 0.04935302734375,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 0.002,
+      "reward": 2.586111146211624,
+      "reward_std": 0.4021389245986938,
+      "rewards/accuracy_reward_log": 1.6777777940034866,
+      "rewards/format_number_reward": 0.45277778059244156,
+      "rewards/format_reasoning_reward": 0.4555555582046509,
+      "step": 64
+    },
+    {
+      "completion_length": 193.02222366333007,
+      "epoch": 0.5218787635487756,
+      "grad_norm": 0.4720147986556917,
+      "kl": 0.0471923828125,
+      "learning_rate": 1.95e-06,
+      "loss": 0.0019,
+      "reward": 2.6138889133930205,
+      "reward_std": 0.444037689268589,
+      "rewards/accuracy_reward_log": 1.7000000149011611,
+      "rewards/format_number_reward": 0.4555555582046509,
+      "rewards/format_reasoning_reward": 0.4583333358168602,
+      "step": 65
+    },
+    {
+      "completion_length": 210.9277801513672,
+      "epoch": 0.5299076676033722,
+      "grad_norm": 0.5124703016443702,
+      "kl": 0.06097412109375,
+      "learning_rate": 1.98e-06,
+      "loss": 0.0024,
+      "reward": 2.4833333492279053,
+      "reward_std": 0.5216697975993156,
+      "rewards/accuracy_reward_log": 1.6111111342906952,
+      "rewards/format_number_reward": 0.4277777820825577,
+      "rewards/format_reasoning_reward": 0.4444444477558136,
+      "step": 66
+    },
+    {
+      "completion_length": 195.95000152587892,
+      "epoch": 0.5379365716579687,
+      "grad_norm": 0.3914341348179692,
+      "kl": 0.05845947265625,
+      "learning_rate": 2.0100000000000002e-06,
+      "loss": 0.0023,
+      "reward": 2.5666666865348815,
+      "reward_std": 0.4269164353609085,
+      "rewards/accuracy_reward_log": 1.666666680574417,
+      "rewards/format_number_reward": 0.4416666701436043,
+      "rewards/format_reasoning_reward": 0.4583333358168602,
+      "step": 67
+    },
+    {
+      "completion_length": 189.8333354949951,
+      "epoch": 0.5459654757125653,
+      "grad_norm": 1.8409712600042354,
+      "kl": 0.104864501953125,
+      "learning_rate": 2.0400000000000004e-06,
+      "loss": 0.0042,
+      "reward": 2.6055555939674377,
+      "reward_std": 0.3877051591873169,
+      "rewards/accuracy_reward_log": 1.7000000119209289,
+      "rewards/format_number_reward": 0.45000000298023224,
+      "rewards/format_reasoning_reward": 0.4555555582046509,
+      "step": 68
+    },
+    {
+      "completion_length": 216.18333587646484,
+      "epoch": 0.5539943797671618,
+      "grad_norm": 1.234592815069376,
+      "kl": 0.11241455078125,
+      "learning_rate": 2.07e-06,
+      "loss": 0.0045,
+      "reward": 2.3138889193534853,
+      "reward_std": 0.5511893726885319,
+      "rewards/accuracy_reward_log": 1.46666669100523,
+      "rewards/format_number_reward": 0.4138888940215111,
+      "rewards/format_reasoning_reward": 0.4333333373069763,
+      "step": 69
+    },
+    {
+      "completion_length": 216.01666946411132,
+      "epoch": 0.5620232838217584,
+      "grad_norm": 0.47189027920553445,
+      "kl": 0.086163330078125,
+      "learning_rate": 2.1e-06,
+      "loss": 0.0034,
+      "reward": 2.4277777910232543,
+      "reward_std": 0.5567510481923819,
+      "rewards/accuracy_reward_log": 1.588888907432556,
+      "rewards/format_number_reward": 0.413888893276453,
+      "rewards/format_reasoning_reward": 0.4250000037252903,
+      "step": 70
+    },
+    {
+      "completion_length": 180.42222366333007,
+      "epoch": 0.5700521878763549,
+      "grad_norm": 0.5661866241275311,
+      "kl": 0.055902099609375,
+      "learning_rate": 2.13e-06,
+      "loss": 0.0022,
+      "reward": 2.508333349227905,
+      "reward_std": 0.416572679579258,
+      "rewards/accuracy_reward_log": 1.6000000208616256,
+      "rewards/format_number_reward": 0.4472222253680229,
+      "rewards/format_reasoning_reward": 0.4611111134290695,
+      "step": 71
+    },
+    {
+      "completion_length": 212.58333511352538,
+      "epoch": 0.5780810919309515,
+      "grad_norm": 0.5852592346007427,
+      "kl": 0.108624267578125,
+      "learning_rate": 2.16e-06,
+      "loss": 0.0043,
+      "reward": 2.2777777791023253,
+      "reward_std": 0.53003438860178,
+      "rewards/accuracy_reward_log": 1.4888889133930205,
+      "rewards/format_number_reward": 0.38611111640930174,
+      "rewards/format_reasoning_reward": 0.40277778208255766,
+      "step": 72
+    },
+    {
+      "completion_length": 203.32777824401856,
+      "epoch": 0.586109995985548,
+      "grad_norm": 1.0262474142127427,
+      "kl": 0.104498291015625,
+      "learning_rate": 2.19e-06,
+      "loss": 0.0042,
+      "reward": 2.4166666686534883,
+      "reward_std": 0.40687683820724485,
+      "rewards/accuracy_reward_log": 1.5777777969837188,
+      "rewards/format_number_reward": 0.4166666708886623,
+      "rewards/format_reasoning_reward": 0.42222222611308097,
+      "step": 73
+    },
+    {
+      "completion_length": 205.4111114501953,
+      "epoch": 0.5941389000401445,
+      "grad_norm": 0.6749287604370076,
+      "kl": 0.106732177734375,
+      "learning_rate": 2.22e-06,
+      "loss": 0.0043,
+      "reward": 2.2611111223697664,
+      "reward_std": 0.5402376987040043,
+      "rewards/accuracy_reward_log": 1.4333333566784858,
+      "rewards/format_number_reward": 0.4027777828276157,
+      "rewards/format_reasoning_reward": 0.42500000447034836,
+      "step": 74
+    },
+    {
+      "completion_length": 204.6277805328369,
+      "epoch": 0.602167804094741,
+      "grad_norm": 1.3836757790747922,
+      "kl": 0.118878173828125,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0048,
+      "reward": 2.211111146211624,
+      "reward_std": 0.7402307014912367,
+      "rewards/accuracy_reward_log": 1.4000000268220902,
+      "rewards/format_number_reward": 0.38055556192994117,
+      "rewards/format_reasoning_reward": 0.430555559694767,
+      "step": 75
+    },
+    {
+      "completion_length": 192.80555725097656,
+      "epoch": 0.6101967081493376,
+      "grad_norm": 0.5732652733178961,
+      "kl": 0.081439208984375,
+      "learning_rate": 2.28e-06,
+      "loss": 0.0033,
+      "reward": 2.444444465637207,
+      "reward_std": 0.5093889623880387,
+      "rewards/accuracy_reward_log": 1.533333358168602,
+      "rewards/format_number_reward": 0.45277778059244156,
+      "rewards/format_reasoning_reward": 0.4583333358168602,
+      "step": 76
+    },
+    {
+      "completion_length": 159.32222518920898,
+      "epoch": 0.6182256122039341,
+      "grad_norm": 0.4884865339246385,
+      "kl": 0.057391357421875,
+      "learning_rate": 2.31e-06,
+      "loss": 0.0023,
+      "reward": 2.5805555820465087,
+      "reward_std": 0.16979632191359997,
+      "rewards/accuracy_reward_log": 1.611111131310463,
+      "rewards/format_number_reward": 0.47777777910232544,
+      "rewards/format_reasoning_reward": 0.49166666716337204,
+      "step": 77
+    },
+    {
+      "completion_length": 190.20000076293945,
+      "epoch": 0.6262545162585307,
+      "grad_norm": 0.5209974936705293,
+      "kl": 0.067266845703125,
+      "learning_rate": 2.34e-06,
+      "loss": 0.0027,
+      "reward": 2.4777778029441833,
+      "reward_std": 0.4935527116060257,
+      "rewards/accuracy_reward_log": 1.5555555790662765,
+      "rewards/format_number_reward": 0.4583333358168602,
+      "rewards/format_reasoning_reward": 0.46388889104127884,
+      "step": 78
+    },
+    {
+      "completion_length": 169.23889122009277,
+      "epoch": 0.6342834203131272,
+      "grad_norm": 0.4459209602371647,
+      "kl": 0.05482177734375,
+      "learning_rate": 2.37e-06,
+      "loss": 0.0022,
+      "reward": 2.6750000178813935,
+      "reward_std": 0.23374302312731743,
+      "rewards/accuracy_reward_log": 1.7000000149011611,
+      "rewards/format_number_reward": 0.4833333343267441,
+      "rewards/format_reasoning_reward": 0.49166666716337204,
+      "step": 79
+    },
+    {
+      "completion_length": 182.30000267028808,
+      "epoch": 0.6423123243677238,
+      "grad_norm": 0.45736704423541613,
+      "kl": 0.07120361328125,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.0028,
+      "reward": 2.5750000059604643,
+      "reward_std": 0.31974178850650786,
+      "rewards/accuracy_reward_log": 1.6444444626569747,
+      "rewards/format_number_reward": 0.46388889104127884,
+      "rewards/format_reasoning_reward": 0.46666666865348816,
+      "step": 80
+    },
+    {
+      "completion_length": 163.07778053283693,
+      "epoch": 0.6503412284223203,
+      "grad_norm": 0.4682785728868757,
+      "kl": 0.06102294921875,
+      "learning_rate": 2.43e-06,
+      "loss": 0.0024,
+      "reward": 2.686111146211624,
+      "reward_std": 0.3670576632022858,
+      "rewards/accuracy_reward_log": 1.7444444596767426,
+      "rewards/format_number_reward": 0.4694444462656975,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 81
+    },
+    {
+      "completion_length": 165.8722225189209,
+      "epoch": 0.6583701324769169,
+      "grad_norm": 0.509179920003658,
+      "kl": 0.061614990234375,
+      "learning_rate": 2.4599999999999997e-06,
+      "loss": 0.0025,
+      "reward": 2.6250000596046448,
+      "reward_std": 0.402138914167881,
+      "rewards/accuracy_reward_log": 1.6777777969837189,
+      "rewards/format_number_reward": 0.4694444462656975,
+      "rewards/format_reasoning_reward": 0.47777777910232544,
+      "step": 82
+    },
+    {
+      "completion_length": 159.80555725097656,
+      "epoch": 0.6663990365315134,
+      "grad_norm": 0.5994985713489502,
+      "kl": 0.054705810546875,
+      "learning_rate": 2.49e-06,
+      "loss": 0.0022,
+      "reward": 2.6194444835186004,
+      "reward_std": 0.4117614269256592,
+      "rewards/accuracy_reward_log": 1.6555555760860443,
+      "rewards/format_number_reward": 0.48055555671453476,
+      "rewards/format_reasoning_reward": 0.4833333343267441,
+      "step": 83
+    },
+    {
+      "completion_length": 175.34444770812988,
+      "epoch": 0.67442794058611,
+      "grad_norm": 0.518979425053283,
+      "kl": 0.08248291015625,
+      "learning_rate": 2.52e-06,
+      "loss": 0.0033,
+      "reward": 2.5138889074325563,
+      "reward_std": 0.4138893112540245,
+      "rewards/accuracy_reward_log": 1.6000000208616256,
+      "rewards/format_number_reward": 0.45277778059244156,
+      "rewards/format_reasoning_reward": 0.4611111134290695,
+      "step": 84
+    },
+    {
+      "completion_length": 165.01666755676268,
+      "epoch": 0.6824568446407066,
+      "grad_norm": 0.49612998471580416,
+      "kl": 0.065625,
+      "learning_rate": 2.55e-06,
+      "loss": 0.0026,
+      "reward": 2.469444477558136,
+      "reward_std": 0.5141268767416477,
+      "rewards/accuracy_reward_log": 1.588888907432556,
+      "rewards/format_number_reward": 0.43333333656191825,
+      "rewards/format_reasoning_reward": 0.44722222462296485,
+      "step": 85
+    },
+    {
+      "completion_length": 165.6388900756836,
+      "epoch": 0.6904857486953031,
+      "grad_norm": 0.552553452651074,
+      "kl": 0.06807861328125,
+      "learning_rate": 2.58e-06,
+      "loss": 0.0027,
+      "reward": 2.4944444805383683,
+      "reward_std": 0.37747681848704817,
+      "rewards/accuracy_reward_log": 1.577777798473835,
+      "rewards/format_number_reward": 0.4527777798473835,
+      "rewards/format_reasoning_reward": 0.46388889104127884,
+      "step": 86
+    },
+    {
+      "completion_length": 155.51666641235352,
+      "epoch": 0.6985146527498997,
+      "grad_norm": 0.5440640607374735,
+      "kl": 0.060748291015625,
+      "learning_rate": 2.61e-06,
+      "loss": 0.0024,
+      "reward": 2.4611111283302307,
+      "reward_std": 0.5409881249070168,
+      "rewards/accuracy_reward_log": 1.577777799963951,
+      "rewards/format_number_reward": 0.43888889253139496,
+      "rewards/format_reasoning_reward": 0.4444444477558136,
+      "step": 87
+    },
+    {
+      "completion_length": 150.6777774810791,
+      "epoch": 0.7065435568044962,
+      "grad_norm": 0.4538101109952547,
+      "kl": 0.05191650390625,
+      "learning_rate": 2.64e-06,
+      "loss": 0.0021,
+      "reward": 2.6416666924953462,
+      "reward_std": 0.2997001264244318,
+      "rewards/accuracy_reward_log": 1.7000000149011611,
+      "rewards/format_number_reward": 0.4694444462656975,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 88
+    },
+    {
+      "completion_length": 165.80000228881835,
+      "epoch": 0.7145724608590928,
+      "grad_norm": 0.5131296250407812,
+      "kl": 0.06552734375,
+      "learning_rate": 2.6700000000000003e-06,
+      "loss": 0.0026,
+      "reward": 2.600000035762787,
+      "reward_std": 0.48052144795656204,
+      "rewards/accuracy_reward_log": 1.6777777969837189,
+      "rewards/format_number_reward": 0.4583333358168602,
+      "rewards/format_reasoning_reward": 0.46388889104127884,
+      "step": 89
+    },
+    {
+      "completion_length": 151.10555686950684,
+      "epoch": 0.7226013649136893,
+      "grad_norm": 0.5165638439339917,
+      "kl": 0.0578857421875,
+      "learning_rate": 2.7e-06,
+      "loss": 0.0023,
+      "reward": 2.6555556058883667,
+      "reward_std": 0.362246410548687,
+      "rewards/accuracy_reward_log": 1.7111111283302307,
+      "rewards/format_number_reward": 0.4722222238779068,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 90
+    },
+    {
+      "completion_length": 159.4166687011719,
+      "epoch": 0.7306302689682859,
+      "grad_norm": 0.49295723950300413,
+      "kl": 0.058404541015625,
+      "learning_rate": 2.73e-06,
+      "loss": 0.0023,
+      "reward": 2.5833333671092986,
+      "reward_std": 0.44544019252061845,
+      "rewards/accuracy_reward_log": 1.6444444626569747,
+      "rewards/format_number_reward": 0.4694444462656975,
+      "rewards/format_reasoning_reward": 0.4694444462656975,
+      "step": 91
+    },
+    {
+      "completion_length": 159.53333625793456,
+      "epoch": 0.7386591730228824,
+      "grad_norm": 1.0273725644592662,
+      "kl": 0.06968994140625,
+      "learning_rate": 2.7600000000000003e-06,
+      "loss": 0.0028,
+      "reward": 2.5111111402511597,
+      "reward_std": 0.44476102106273174,
+      "rewards/accuracy_reward_log": 1.577777799963951,
+      "rewards/format_number_reward": 0.4611111134290695,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 92
+    },
+    {
+      "completion_length": 154.76666793823242,
+      "epoch": 0.746688077077479,
+      "grad_norm": 0.3153647070205455,
+      "kl": 0.053741455078125,
+      "learning_rate": 2.7900000000000004e-06,
+      "loss": 0.0021,
+      "reward": 2.688888907432556,
+      "reward_std": 0.2062800731509924,
+      "rewards/accuracy_reward_log": 1.733333346247673,
+      "rewards/format_number_reward": 0.4750000014901161,
+      "rewards/format_reasoning_reward": 0.48055555671453476,
+      "step": 93
+    },
+    {
+      "completion_length": 166.42777900695802,
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.5748531305032764,
+      "kl": 0.066802978515625,
+      "learning_rate": 2.82e-06,
+      "loss": 0.0027,
+      "reward": 2.600000041723251,
+      "reward_std": 0.3458063915371895,
+      "rewards/accuracy_reward_log": 1.655555573105812,
+      "rewards/format_number_reward": 0.4722222238779068,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 94
+    },
+    {
+      "completion_length": 158.03888969421388,
+      "epoch": 0.762745885186672,
+      "grad_norm": 0.5545909018402391,
+      "kl": 0.066021728515625,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0026,
+      "reward": 2.7111111342906953,
+      "reward_std": 0.3430013954639435,
+      "rewards/accuracy_reward_log": 1.7666666775941848,
+      "rewards/format_number_reward": 0.4722222238779068,
+      "rewards/format_reasoning_reward": 0.4722222238779068,
+      "step": 95
+    },
+    {
+      "completion_length": 165.80000228881835,
+      "epoch": 0.7707747892412685,
+      "grad_norm": 0.42499585100246984,
+      "kl": 0.05565185546875,
+      "learning_rate": 2.88e-06,
+      "loss": 0.0022,
+      "reward": 2.602777808904648,
+      "reward_std": 0.3154630549252033,
+      "rewards/accuracy_reward_log": 1.6444444626569747,
+      "rewards/format_number_reward": 0.47777777910232544,
+      "rewards/format_reasoning_reward": 0.48055555671453476,
+      "step": 96
+    },
+    {
+      "completion_length": 174.88333435058593,
+      "epoch": 0.7788036932958651,
+      "grad_norm": 0.5630736371263277,
+      "kl": 0.07933349609375,
+      "learning_rate": 2.91e-06,
+      "loss": 0.0032,
+      "reward": 2.394444453716278,
+      "reward_std": 0.4866618663072586,
+      "rewards/accuracy_reward_log": 1.4777778044342995,
+      "rewards/format_number_reward": 0.4555555582046509,
+      "rewards/format_reasoning_reward": 0.4611111134290695,
+      "step": 97
+    },
+    {
+      "completion_length": 194.8888916015625,
+      "epoch": 0.7868325973504616,
+      "grad_norm": 0.5354591296941339,
+      "kl": 0.08121337890625,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 0.0032,
+      "reward": 2.4166667103767394,
+      "reward_std": 0.467490179464221,
+      "rewards/accuracy_reward_log": 1.5444444686174392,
+      "rewards/format_number_reward": 0.4333333373069763,
+      "rewards/format_reasoning_reward": 0.43888889253139496,
+      "step": 98
+    },
+    {
+      "completion_length": 198.76111335754393,
+      "epoch": 0.7948615014050582,
+      "grad_norm": 0.7579425034647131,
+      "kl": 0.092218017578125,
+      "learning_rate": 2.97e-06,
+      "loss": 0.0037,
+      "reward": 2.472222238779068,
+      "reward_std": 0.44544018656015394,
+      "rewards/accuracy_reward_log": 1.577777799963951,
+      "rewards/format_number_reward": 0.4472222253680229,
+      "rewards/format_reasoning_reward": 0.4472222253680229,
+      "step": 99
+    },
+    {
+      "completion_length": 181.00000228881837,
+      "epoch": 0.8028904054596547,
+      "grad_norm": 3.752908048104343,
+      "kl": 0.29696044921875,
+      "learning_rate": 3e-06,
+      "loss": 0.0119,
+      "reward": 2.644444489479065,
+      "reward_std": 0.3877051673829556,
+      "rewards/accuracy_reward_log": 1.722222238779068,
+      "rewards/format_number_reward": 0.4611111134290695,
+      "rewards/format_reasoning_reward": 0.4611111134290695,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 50,
+  "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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631fb7155834684d5772fbfdbf318c9adf9388bffdc993f66109c40fb650bc5d
+size 6840

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        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, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+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 tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # 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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    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, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)