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

chat_template.jinja

@@ -0,0 +1,25 @@
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
+        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- if loop.first and system_message is defined %}
+            {{- '[INST]' + system_message + '\n\n' + message['content'] + '[/INST]' }}
+        {%- else %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {{- message['content'] + eos_token}}
+    {%- else %}
+        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}{{'<think>\n'}}{% endif %}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128001,
+  "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,
+  "pad_token_id": 128004,
+  "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,
+  "transformers_version": "4.57.0",
+  "use_cache": false,
+  "vocab_size": 128260
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001
+  ],
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.57.0"
+}

latest

@@ -0,0 +1 @@
+global_step330

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061db5e0a0e10ae2bec12c2dab28adf9c96aa15ccd7fe618b88210773833cf54
+size 4976731440

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11234c839b0dbc8decde642f49c6329310c53e7e73ac6eeb26668892dbae529e
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f98e4f1d5c7f877f4e9139209ca90c12479935072e510719939258438f29e94
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2de294f715d6b147668b4506f668ad949c2d1b551101a182b325d3471ab2b5
+size 1168171576

model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_parameters": 8030294016,
+    "total_size": 16060588032
+  },
+  "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"
+  }
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1e4855c6fbb5448a579632415374ad88a5f5d99b68c7d088bfbdb6ed197282
+size 1465

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<think>",
+    "</think>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb1adf57e10ffa5f9daa88d22d663cfd9790542f639c7746c890f65af27542a
+size 17210656

tokenizer_config.json

@@ -0,0 +1,2099 @@
+{
+  "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
+    },
+    "128256": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128257": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128258": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128259": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<think>",
+    "</think>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,2674 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009142857142857144,
+      "grad_norm": 3.788423157943329,
+      "learning_rate": 0.0,
+      "loss": 1.0171,
+      "num_tokens": 414791.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.018285714285714287,
+      "grad_norm": 3.7486067929136304,
+      "learning_rate": 2.9411764705882356e-07,
+      "loss": 1.0458,
+      "num_tokens": 816383.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.027428571428571427,
+      "grad_norm": 3.6248817482667772,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 1.0156,
+      "num_tokens": 1248217.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.036571428571428574,
+      "grad_norm": 3.8501840793231983,
+      "learning_rate": 8.823529411764707e-07,
+      "loss": 0.9988,
+      "num_tokens": 1657241.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.045714285714285714,
+      "grad_norm": 3.5112388358944506,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 1.0094,
+      "num_tokens": 2097247.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.054857142857142854,
+      "grad_norm": 3.305630960821923,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 1.0067,
+      "num_tokens": 2518049.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.763998457471438,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 0.9815,
+      "num_tokens": 2911785.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.07314285714285715,
+      "grad_norm": 2.553777222235427,
+      "learning_rate": 2.058823529411765e-06,
+      "loss": 0.9884,
+      "num_tokens": 3304861.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.08228571428571428,
+      "grad_norm": 1.7314602879429424,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.9657,
+      "num_tokens": 3744952.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.09142857142857143,
+      "grad_norm": 1.639488114011472,
+      "learning_rate": 2.647058823529412e-06,
+      "loss": 0.9173,
+      "num_tokens": 4171394.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.10057142857142858,
+      "grad_norm": 1.605492636449322,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.9402,
+      "num_tokens": 4593000.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.10971428571428571,
+      "grad_norm": 1.7144819324641203,
+      "learning_rate": 3.2352941176470594e-06,
+      "loss": 0.931,
+      "num_tokens": 5051170.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.11885714285714286,
+      "grad_norm": 2.1335893786941633,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.873,
+      "num_tokens": 5462412.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.8322905891256291,
+      "learning_rate": 3.8235294117647055e-06,
+      "loss": 0.8839,
+      "num_tokens": 5897197.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.13714285714285715,
+      "grad_norm": 1.3855988250523144,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 0.8531,
+      "num_tokens": 6310546.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.1462857142857143,
+      "grad_norm": 1.2583291182608385,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 0.8449,
+      "num_tokens": 6737190.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.15542857142857142,
+      "grad_norm": 1.7093622730710312,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.8459,
+      "num_tokens": 7152523.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.16457142857142856,
+      "grad_norm": 1.3548099953678236,
+      "learning_rate": 5e-06,
+      "loss": 0.8382,
+      "num_tokens": 7614210.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.1737142857142857,
+      "grad_norm": 1.2411537968080228,
+      "learning_rate": 4.999874073411688e-06,
+      "loss": 0.8003,
+      "num_tokens": 8005070.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.18285714285714286,
+      "grad_norm": 1.1063653911297622,
+      "learning_rate": 4.999496306332755e-06,
+      "loss": 0.8161,
+      "num_tokens": 8458443.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8870246401694026,
+      "learning_rate": 4.998866736819938e-06,
+      "loss": 0.8175,
+      "num_tokens": 8886223.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.20114285714285715,
+      "grad_norm": 0.8378533988358792,
+      "learning_rate": 4.997985428296869e-06,
+      "loss": 0.79,
+      "num_tokens": 9308544.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.2102857142857143,
+      "grad_norm": 0.8680117397968262,
+      "learning_rate": 4.996852469547688e-06,
+      "loss": 0.7697,
+      "num_tokens": 9738279.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.21942857142857142,
+      "grad_norm": 0.7814254549991426,
+      "learning_rate": 4.9954679747081e-06,
+      "loss": 0.7791,
+      "num_tokens": 10176776.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.6718931761429743,
+      "learning_rate": 4.993832083253874e-06,
+      "loss": 0.7549,
+      "num_tokens": 10607900.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.2377142857142857,
+      "grad_norm": 0.7203929761049984,
+      "learning_rate": 4.991944959986793e-06,
+      "loss": 0.7647,
+      "num_tokens": 11029388.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.24685714285714286,
+      "grad_norm": 0.7147312112109525,
+      "learning_rate": 4.989806795018054e-06,
+      "loss": 0.7638,
+      "num_tokens": 11457489.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.6521467633335539,
+      "learning_rate": 4.987417803749112e-06,
+      "loss": 0.7835,
+      "num_tokens": 11864446.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.2651428571428571,
+      "grad_norm": 0.6625801512953233,
+      "learning_rate": 4.984778226849983e-06,
+      "loss": 0.7627,
+      "num_tokens": 12248848.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.2742857142857143,
+      "grad_norm": 0.630181987147504,
+      "learning_rate": 4.981888330234998e-06,
+      "loss": 0.75,
+      "num_tokens": 12663440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.2834285714285714,
+      "grad_norm": 0.6381224000786306,
+      "learning_rate": 4.978748405036014e-06,
+      "loss": 0.7493,
+      "num_tokens": 13034106.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.2925714285714286,
+      "grad_norm": 0.6161172594215469,
+      "learning_rate": 4.975358767573085e-06,
+      "loss": 0.7586,
+      "num_tokens": 13448760.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.3017142857142857,
+      "grad_norm": 0.5841875666239731,
+      "learning_rate": 4.971719759322596e-06,
+      "loss": 0.7526,
+      "num_tokens": 13907189.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.31085714285714283,
+      "grad_norm": 0.6291433005199626,
+      "learning_rate": 4.967831746882863e-06,
+      "loss": 0.7424,
+      "num_tokens": 14306209.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5515606238598844,
+      "learning_rate": 4.9636951219372e-06,
+      "loss": 0.7547,
+      "num_tokens": 14720460.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.3291428571428571,
+      "grad_norm": 0.5614465276031775,
+      "learning_rate": 4.959310301214458e-06,
+      "loss": 0.7288,
+      "num_tokens": 15132163.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.3382857142857143,
+      "grad_norm": 0.6054958180004087,
+      "learning_rate": 4.954677726447049e-06,
+      "loss": 0.7372,
+      "num_tokens": 15497706.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.3474285714285714,
+      "grad_norm": 0.5245577430458518,
+      "learning_rate": 4.949797864326442e-06,
+      "loss": 0.7084,
+      "num_tokens": 15931655.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.3565714285714286,
+      "grad_norm": 0.5254082660408352,
+      "learning_rate": 4.944671206456148e-06,
+      "loss": 0.7091,
+      "num_tokens": 16341137.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "grad_norm": 0.5538924183973399,
+      "learning_rate": 4.939298269302194e-06,
+      "loss": 0.7452,
+      "num_tokens": 16776527.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.37485714285714283,
+      "grad_norm": 0.5542948467918837,
+      "learning_rate": 4.933679594141096e-06,
+      "loss": 0.7374,
+      "num_tokens": 17183370.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5380100952791218,
+      "learning_rate": 4.9278157470053305e-06,
+      "loss": 0.7244,
+      "num_tokens": 17602865.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.3931428571428571,
+      "grad_norm": 0.5519363633677055,
+      "learning_rate": 4.9217073186263075e-06,
+      "loss": 0.7253,
+      "num_tokens": 18002059.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.4022857142857143,
+      "grad_norm": 0.5659780047314049,
+      "learning_rate": 4.915354924374864e-06,
+      "loss": 0.7209,
+      "num_tokens": 18417553.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.4114285714285714,
+      "grad_norm": 0.5488792186326696,
+      "learning_rate": 4.908759204199268e-06,
+      "loss": 0.7396,
+      "num_tokens": 18840096.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.4205714285714286,
+      "grad_norm": 0.5252663101552106,
+      "learning_rate": 4.901920822560753e-06,
+      "loss": 0.7127,
+      "num_tokens": 19258374.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.4297142857142857,
+      "grad_norm": 0.5591357036458139,
+      "learning_rate": 4.89484046836657e-06,
+      "loss": 0.7206,
+      "num_tokens": 19680030.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.43885714285714283,
+      "grad_norm": 0.5556426602282065,
+      "learning_rate": 4.887518854900603e-06,
+      "loss": 0.697,
+      "num_tokens": 20098565.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.5510078792794185,
+      "learning_rate": 4.879956719751491e-06,
+      "loss": 0.745,
+      "num_tokens": 20542243.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.5396047474298085,
+      "learning_rate": 4.87215482473834e-06,
+      "loss": 0.713,
+      "num_tokens": 20958663.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.4662857142857143,
+      "grad_norm": 0.5199497319908324,
+      "learning_rate": 4.864113955833967e-06,
+      "loss": 0.7014,
+      "num_tokens": 21384478.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.4754285714285714,
+      "grad_norm": 0.5529473043892272,
+      "learning_rate": 4.855834923085721e-06,
+      "loss": 0.7063,
+      "num_tokens": 21791929.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.4845714285714286,
+      "grad_norm": 0.5585081497740281,
+      "learning_rate": 4.847318560533882e-06,
+      "loss": 0.7248,
+      "num_tokens": 22203013.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.4937142857142857,
+      "grad_norm": 0.5315034055299764,
+      "learning_rate": 4.838565726127636e-06,
+      "loss": 0.6891,
+      "num_tokens": 22601890.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.5028571428571429,
+      "grad_norm": 0.527611783496754,
+      "learning_rate": 4.829577301638642e-06,
+      "loss": 0.7488,
+      "num_tokens": 23070128.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.5596739037421498,
+      "learning_rate": 4.8203541925722016e-06,
+      "loss": 0.7119,
+      "num_tokens": 23490480.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.5211428571428571,
+      "grad_norm": 0.569290949582533,
+      "learning_rate": 4.810897328076045e-06,
+      "loss": 0.6961,
+      "num_tokens": 23887492.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.5302857142857142,
+      "grad_norm": 0.5267117373322459,
+      "learning_rate": 4.801207660846717e-06,
+      "loss": 0.6924,
+      "num_tokens": 24320449.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.5394285714285715,
+      "grad_norm": 0.5083151481320303,
+      "learning_rate": 4.7912861670336065e-06,
+      "loss": 0.6953,
+      "num_tokens": 24769809.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.5485714285714286,
+      "grad_norm": 0.5537578982564932,
+      "learning_rate": 4.781133846140606e-06,
+      "loss": 0.709,
+      "num_tokens": 25191175.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.5577142857142857,
+      "grad_norm": 0.4943590155288578,
+      "learning_rate": 4.770751720925422e-06,
+      "loss": 0.7077,
+      "num_tokens": 25624365.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.5668571428571428,
+      "grad_norm": 0.5160855203562402,
+      "learning_rate": 4.760140837296542e-06,
+      "loss": 0.7081,
+      "num_tokens": 26058172.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.5284271224337476,
+      "learning_rate": 4.7493022642078654e-06,
+      "loss": 0.7044,
+      "num_tokens": 26455012.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.5851428571428572,
+      "grad_norm": 0.5202512411868518,
+      "learning_rate": 4.7382370935510165e-06,
+      "loss": 0.7196,
+      "num_tokens": 26892158.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.5942857142857143,
+      "grad_norm": 0.5157697929801275,
+      "learning_rate": 4.726946440045348e-06,
+      "loss": 0.7046,
+      "num_tokens": 27320636.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.6034285714285714,
+      "grad_norm": 0.5189217024488914,
+      "learning_rate": 4.715431441125639e-06,
+      "loss": 0.6627,
+      "num_tokens": 27766323.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.6125714285714285,
+      "grad_norm": 0.5635204498629328,
+      "learning_rate": 4.703693256827515e-06,
+      "loss": 0.6931,
+      "num_tokens": 28189830.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.6217142857142857,
+      "grad_norm": 0.5082211284375098,
+      "learning_rate": 4.691733069670575e-06,
+      "loss": 0.6451,
+      "num_tokens": 28627346.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.6308571428571429,
+      "grad_norm": 0.5232606496406234,
+      "learning_rate": 4.679552084539271e-06,
+      "loss": 0.671,
+      "num_tokens": 29057945.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.53201837236867,
+      "learning_rate": 4.667151528561522e-06,
+      "loss": 0.7202,
+      "num_tokens": 29486194.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.6491428571428571,
+      "grad_norm": 0.561020955033982,
+      "learning_rate": 4.6545326509850965e-06,
+      "loss": 0.7006,
+      "num_tokens": 29845300.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.6582857142857143,
+      "grad_norm": 0.5297748591428174,
+      "learning_rate": 4.641696723051753e-06,
+      "loss": 0.7088,
+      "num_tokens": 30298906.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.6674285714285715,
+      "grad_norm": 0.5129774250057094,
+      "learning_rate": 4.628645037869183e-06,
+      "loss": 0.6655,
+      "num_tokens": 30729078.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.6765714285714286,
+      "grad_norm": 0.5488508086875596,
+      "learning_rate": 4.615378910280735e-06,
+      "loss": 0.6962,
+      "num_tokens": 31142347.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.5214375076220712,
+      "learning_rate": 4.60189967673296e-06,
+      "loss": 0.6992,
+      "num_tokens": 31530611.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.6948571428571428,
+      "grad_norm": 0.5365497011388887,
+      "learning_rate": 4.588208695140972e-06,
+      "loss": 0.6856,
+      "num_tokens": 31934290.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.5239414066377821,
+      "learning_rate": 4.574307344751654e-06,
+      "loss": 0.6689,
+      "num_tokens": 32336516.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.7131428571428572,
+      "grad_norm": 0.4905474692474024,
+      "learning_rate": 4.560197026004706e-06,
+      "loss": 0.6616,
+      "num_tokens": 32754867.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.7222857142857143,
+      "grad_norm": 0.527006404732485,
+      "learning_rate": 4.5458791603915695e-06,
+      "loss": 0.672,
+      "num_tokens": 33177777.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "grad_norm": 0.49102371409141427,
+      "learning_rate": 4.5313551903122195e-06,
+      "loss": 0.6428,
+      "num_tokens": 33595281.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.7405714285714285,
+      "grad_norm": 0.5266302281242587,
+      "learning_rate": 4.516626578929857e-06,
+      "loss": 0.685,
+      "num_tokens": 34010874.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.7497142857142857,
+      "grad_norm": 0.5219018971926723,
+      "learning_rate": 4.501694810023506e-06,
+      "loss": 0.7053,
+      "num_tokens": 34452852.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.7588571428571429,
+      "grad_norm": 0.5339612937638695,
+      "learning_rate": 4.486561387838539e-06,
+      "loss": 0.6656,
+      "num_tokens": 34850322.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.557261181662059,
+      "learning_rate": 4.471227836935139e-06,
+      "loss": 0.698,
+      "num_tokens": 35255541.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.7771428571428571,
+      "grad_norm": 0.5282377710472309,
+      "learning_rate": 4.455695702034705e-06,
+      "loss": 0.6832,
+      "num_tokens": 35646651.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.7862857142857143,
+      "grad_norm": 0.5054707178540805,
+      "learning_rate": 4.439966547864243e-06,
+      "loss": 0.6559,
+      "num_tokens": 36068819.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.7954285714285714,
+      "grad_norm": 0.5150927571466014,
+      "learning_rate": 4.424041958998732e-06,
+      "loss": 0.6795,
+      "num_tokens": 36494246.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.8045714285714286,
+      "grad_norm": 0.5151785920486077,
+      "learning_rate": 4.407923539701486e-06,
+      "loss": 0.7082,
+      "num_tokens": 36935755.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.8137142857142857,
+      "grad_norm": 0.5219798416078772,
+      "learning_rate": 4.391612913762549e-06,
+      "loss": 0.6592,
+      "num_tokens": 37366636.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.8228571428571428,
+      "grad_norm": 0.4814532946235625,
+      "learning_rate": 4.375111724335102e-06,
+      "loss": 0.6282,
+      "num_tokens": 37765456.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.5416412082011206,
+      "learning_rate": 4.358421633769934e-06,
+      "loss": 0.6744,
+      "num_tokens": 38150281.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.8411428571428572,
+      "grad_norm": 0.48068802364165214,
+      "learning_rate": 4.341544323447978e-06,
+      "loss": 0.6873,
+      "num_tokens": 38679689.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.8502857142857143,
+      "grad_norm": 0.4918360073106731,
+      "learning_rate": 4.324481493610919e-06,
+      "loss": 0.6935,
+      "num_tokens": 39124128.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.8594285714285714,
+      "grad_norm": 0.5218436245838689,
+      "learning_rate": 4.307234863189917e-06,
+      "loss": 0.6905,
+      "num_tokens": 39548028.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.8685714285714285,
+      "grad_norm": 0.5335931444817835,
+      "learning_rate": 4.289806169632434e-06,
+      "loss": 0.7121,
+      "num_tokens": 39948722.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.8777142857142857,
+      "grad_norm": 0.5136306733831099,
+      "learning_rate": 4.272197168727204e-06,
+      "loss": 0.6711,
+      "num_tokens": 40371033.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.8868571428571429,
+      "grad_norm": 0.5071570494757102,
+      "learning_rate": 4.254409634427356e-06,
+      "loss": 0.6654,
+      "num_tokens": 40782038.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.49868261307658696,
+      "learning_rate": 4.236445358671696e-06,
+      "loss": 0.668,
+      "num_tokens": 41221994.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.9051428571428571,
+      "grad_norm": 0.4999015555327391,
+      "learning_rate": 4.218306151204188e-06,
+      "loss": 0.6829,
+      "num_tokens": 41655227.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.5267277450463913,
+      "learning_rate": 4.1999938393916424e-06,
+      "loss": 0.6966,
+      "num_tokens": 42086636.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.9234285714285714,
+      "grad_norm": 0.5098818224161321,
+      "learning_rate": 4.18151026803962e-06,
+      "loss": 0.7018,
+      "num_tokens": 42524682.0,
+      "step": 101
+    },
+    {
+      "epoch": 0.9325714285714286,
+      "grad_norm": 0.5472107304446481,
+      "learning_rate": 4.162857299206584e-06,
+      "loss": 0.695,
+      "num_tokens": 42919957.0,
+      "step": 102
+    },
+    {
+      "epoch": 0.9417142857142857,
+      "grad_norm": 0.5193667055229434,
+      "learning_rate": 4.144036812016317e-06,
+      "loss": 0.6772,
+      "num_tokens": 43334031.0,
+      "step": 103
+    },
+    {
+      "epoch": 0.9508571428571428,
+      "grad_norm": 0.5769899431492905,
+      "learning_rate": 4.1250507024686115e-06,
+      "loss": 0.6943,
+      "num_tokens": 43779138.0,
+      "step": 104
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.49582865560110145,
+      "learning_rate": 4.105900883248269e-06,
+      "loss": 0.6589,
+      "num_tokens": 44181409.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.9691428571428572,
+      "grad_norm": 0.5560209310215001,
+      "learning_rate": 4.08658928353241e-06,
+      "loss": 0.6683,
+      "num_tokens": 44565057.0,
+      "step": 106
+    },
+    {
+      "epoch": 0.9782857142857143,
+      "grad_norm": 0.5105250336516403,
+      "learning_rate": 4.06711784879613e-06,
+      "loss": 0.6656,
+      "num_tokens": 44990460.0,
+      "step": 107
+    },
+    {
+      "epoch": 0.9874285714285714,
+      "grad_norm": 0.47822137614162397,
+      "learning_rate": 4.047488540616503e-06,
+      "loss": 0.6905,
+      "num_tokens": 45448868.0,
+      "step": 108
+    },
+    {
+      "epoch": 0.9965714285714286,
+      "grad_norm": 0.5267943756779967,
+      "learning_rate": 4.027703336474979e-06,
+      "loss": 0.6913,
+      "num_tokens": 45865085.0,
+      "step": 109
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7513864322987849,
+      "learning_rate": 4.0077642295581605e-06,
+      "loss": 0.6751,
+      "num_tokens": 46043993.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.0091428571428571,
+      "grad_norm": 0.652397229541187,
+      "learning_rate": 3.987673228557017e-06,
+      "loss": 0.6124,
+      "num_tokens": 46444743.0,
+      "step": 111
+    },
+    {
+      "epoch": 1.0182857142857142,
+      "grad_norm": 0.5613822445181739,
+      "learning_rate": 3.967432357464518e-06,
+      "loss": 0.6334,
+      "num_tokens": 46868932.0,
+      "step": 112
+    },
+    {
+      "epoch": 1.0274285714285714,
+      "grad_norm": 0.548463499167073,
+      "learning_rate": 3.947043655371734e-06,
+      "loss": 0.637,
+      "num_tokens": 47306605.0,
+      "step": 113
+    },
+    {
+      "epoch": 1.0365714285714285,
+      "grad_norm": 0.5985099049112745,
+      "learning_rate": 3.9265091762624225e-06,
+      "loss": 0.6684,
+      "num_tokens": 47766810.0,
+      "step": 114
+    },
+    {
+      "epoch": 1.0457142857142858,
+      "grad_norm": 0.5614950162690504,
+      "learning_rate": 3.905830988806101e-06,
+      "loss": 0.6386,
+      "num_tokens": 48217403.0,
+      "step": 115
+    },
+    {
+      "epoch": 1.054857142857143,
+      "grad_norm": 0.5636791310211307,
+      "learning_rate": 3.885011176149647e-06,
+      "loss": 0.6403,
+      "num_tokens": 48667599.0,
+      "step": 116
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.5447491560984974,
+      "learning_rate": 3.864051835707444e-06,
+      "loss": 0.6637,
+      "num_tokens": 49116575.0,
+      "step": 117
+    },
+    {
+      "epoch": 1.0731428571428572,
+      "grad_norm": 0.564065307250827,
+      "learning_rate": 3.842955078950079e-06,
+      "loss": 0.6563,
+      "num_tokens": 49548979.0,
+      "step": 118
+    },
+    {
+      "epoch": 1.0822857142857143,
+      "grad_norm": 0.5750693750810204,
+      "learning_rate": 3.8217230311916365e-06,
+      "loss": 0.6542,
+      "num_tokens": 49944685.0,
+      "step": 119
+    },
+    {
+      "epoch": 1.0914285714285714,
+      "grad_norm": 0.5664157697505491,
+      "learning_rate": 3.800357831375583e-06,
+      "loss": 0.6311,
+      "num_tokens": 50369856.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.1005714285714285,
+      "grad_norm": 0.5643319728604673,
+      "learning_rate": 3.778861631859298e-06,
+      "loss": 0.635,
+      "num_tokens": 50756699.0,
+      "step": 121
+    },
+    {
+      "epoch": 1.1097142857142857,
+      "grad_norm": 0.5490242895971412,
+      "learning_rate": 3.7572365981972335e-06,
+      "loss": 0.6504,
+      "num_tokens": 51212014.0,
+      "step": 122
+    },
+    {
+      "epoch": 1.1188571428571428,
+      "grad_norm": 0.5852924645249652,
+      "learning_rate": 3.735484908922759e-06,
+      "loss": 0.6337,
+      "num_tokens": 51613256.0,
+      "step": 123
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524011985834964,
+      "learning_rate": 3.7136087553286916e-06,
+      "loss": 0.6244,
+      "num_tokens": 52060195.0,
+      "step": 124
+    },
+    {
+      "epoch": 1.1371428571428572,
+      "grad_norm": 0.5418140690754942,
+      "learning_rate": 3.6916103412465405e-06,
+      "loss": 0.6335,
+      "num_tokens": 52475517.0,
+      "step": 125
+    },
+    {
+      "epoch": 1.1462857142857144,
+      "grad_norm": 0.5431784069939521,
+      "learning_rate": 3.6694918828244923e-06,
+      "loss": 0.6151,
+      "num_tokens": 52916813.0,
+      "step": 126
+    },
+    {
+      "epoch": 1.1554285714285715,
+      "grad_norm": 0.5331182901674993,
+      "learning_rate": 3.647255608304154e-06,
+      "loss": 0.5944,
+      "num_tokens": 53329446.0,
+      "step": 127
+    },
+    {
+      "epoch": 1.1645714285714286,
+      "grad_norm": 0.5669880957159196,
+      "learning_rate": 3.6249037577960744e-06,
+      "loss": 0.6548,
+      "num_tokens": 53744113.0,
+      "step": 128
+    },
+    {
+      "epoch": 1.1737142857142857,
+      "grad_norm": 0.5640955386477013,
+      "learning_rate": 3.6024385830540758e-06,
+      "loss": 0.6232,
+      "num_tokens": 54171017.0,
+      "step": 129
+    },
+    {
+      "epoch": 1.1828571428571428,
+      "grad_norm": 0.566123338215568,
+      "learning_rate": 3.5798623472484074e-06,
+      "loss": 0.622,
+      "num_tokens": 54595667.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.5164284224002408,
+      "learning_rate": 3.5571773247377495e-06,
+      "loss": 0.6247,
+      "num_tokens": 55038242.0,
+      "step": 131
+    },
+    {
+      "epoch": 1.201142857142857,
+      "grad_norm": 0.5193063226224068,
+      "learning_rate": 3.5343858008400955e-06,
+      "loss": 0.6133,
+      "num_tokens": 55441117.0,
+      "step": 132
+    },
+    {
+      "epoch": 1.2102857142857144,
+      "grad_norm": 0.5594859010728502,
+      "learning_rate": 3.511490071602523e-06,
+      "loss": 0.5845,
+      "num_tokens": 55852545.0,
+      "step": 133
+    },
+    {
+      "epoch": 1.2194285714285713,
+      "grad_norm": 0.5312154621480816,
+      "learning_rate": 3.4884924435698875e-06,
+      "loss": 0.6139,
+      "num_tokens": 56305302.0,
+      "step": 134
+    },
+    {
+      "epoch": 1.2285714285714286,
+      "grad_norm": 0.5082891383546045,
+      "learning_rate": 3.465395233552458e-06,
+      "loss": 0.6162,
+      "num_tokens": 56746085.0,
+      "step": 135
+    },
+    {
+      "epoch": 1.2377142857142858,
+      "grad_norm": 0.5183563749809662,
+      "learning_rate": 3.4422007683925224e-06,
+      "loss": 0.5981,
+      "num_tokens": 57164232.0,
+      "step": 136
+    },
+    {
+      "epoch": 1.2468571428571429,
+      "grad_norm": 0.5424921739894077,
+      "learning_rate": 3.418911384729971e-06,
+      "loss": 0.6318,
+      "num_tokens": 57569040.0,
+      "step": 137
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.5176334342259454,
+      "learning_rate": 3.395529428766907e-06,
+      "loss": 0.6473,
+      "num_tokens": 58021968.0,
+      "step": 138
+    },
+    {
+      "epoch": 1.2651428571428571,
+      "grad_norm": 0.5084583167785991,
+      "learning_rate": 3.3720572560312854e-06,
+      "loss": 0.6046,
+      "num_tokens": 58462943.0,
+      "step": 139
+    },
+    {
+      "epoch": 1.2742857142857142,
+      "grad_norm": 0.5103522984652497,
+      "learning_rate": 3.3484972311396114e-06,
+      "loss": 0.5896,
+      "num_tokens": 58899697.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.2834285714285714,
+      "grad_norm": 0.5357080439117383,
+      "learning_rate": 3.3248517275587292e-06,
+      "loss": 0.6151,
+      "num_tokens": 59317087.0,
+      "step": 141
+    },
+    {
+      "epoch": 1.2925714285714287,
+      "grad_norm": 0.5266818795859725,
+      "learning_rate": 3.3011231273667155e-06,
+      "loss": 0.6402,
+      "num_tokens": 59740685.0,
+      "step": 142
+    },
+    {
+      "epoch": 1.3017142857142856,
+      "grad_norm": 0.5515879967156198,
+      "learning_rate": 3.2773138210129037e-06,
+      "loss": 0.6256,
+      "num_tokens": 60175007.0,
+      "step": 143
+    },
+    {
+      "epoch": 1.310857142857143,
+      "grad_norm": 0.5231964139544342,
+      "learning_rate": 3.253426207077069e-06,
+      "loss": 0.6185,
+      "num_tokens": 60569710.0,
+      "step": 144
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.5394300392957713,
+      "learning_rate": 3.2294626920277928e-06,
+      "loss": 0.6372,
+      "num_tokens": 60995749.0,
+      "step": 145
+    },
+    {
+      "epoch": 1.3291428571428572,
+      "grad_norm": 0.5288477560850162,
+      "learning_rate": 3.20542568998003e-06,
+      "loss": 0.6168,
+      "num_tokens": 61416757.0,
+      "step": 146
+    },
+    {
+      "epoch": 1.3382857142857143,
+      "grad_norm": 0.5412372637528483,
+      "learning_rate": 3.181317622451909e-06,
+      "loss": 0.621,
+      "num_tokens": 61838293.0,
+      "step": 147
+    },
+    {
+      "epoch": 1.3474285714285714,
+      "grad_norm": 0.5408790490021942,
+      "learning_rate": 3.1571409181207867e-06,
+      "loss": 0.6284,
+      "num_tokens": 62266608.0,
+      "step": 148
+    },
+    {
+      "epoch": 1.3565714285714285,
+      "grad_norm": 0.5449668003305271,
+      "learning_rate": 3.132898012578577e-06,
+      "loss": 0.6086,
+      "num_tokens": 62661670.0,
+      "step": 149
+    },
+    {
+      "epoch": 1.3657142857142857,
+      "grad_norm": 0.49032514112728875,
+      "learning_rate": 3.108591348086388e-06,
+      "loss": 0.626,
+      "num_tokens": 63105118.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.3748571428571428,
+      "grad_norm": 0.532715786721113,
+      "learning_rate": 3.0842233733284866e-06,
+      "loss": 0.6034,
+      "num_tokens": 63547019.0,
+      "step": 151
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.5606001997788402,
+      "learning_rate": 3.0597965431656125e-06,
+      "loss": 0.6008,
+      "num_tokens": 63969387.0,
+      "step": 152
+    },
+    {
+      "epoch": 1.3931428571428572,
+      "grad_norm": 0.5496057628803153,
+      "learning_rate": 3.0353133183876745e-06,
+      "loss": 0.627,
+      "num_tokens": 64374671.0,
+      "step": 153
+    },
+    {
+      "epoch": 1.4022857142857144,
+      "grad_norm": 0.5524369124857681,
+      "learning_rate": 3.0107761654658464e-06,
+      "loss": 0.605,
+      "num_tokens": 64756768.0,
+      "step": 154
+    },
+    {
+      "epoch": 1.4114285714285715,
+      "grad_norm": 0.5533113651256814,
+      "learning_rate": 2.986187556304091e-06,
+      "loss": 0.6181,
+      "num_tokens": 65142352.0,
+      "step": 155
+    },
+    {
+      "epoch": 1.4205714285714286,
+      "grad_norm": 0.5394567163244798,
+      "learning_rate": 2.961549967990139e-06,
+      "loss": 0.6582,
+      "num_tokens": 65566229.0,
+      "step": 156
+    },
+    {
+      "epoch": 1.4297142857142857,
+      "grad_norm": 0.5320474412403765,
+      "learning_rate": 2.9368658825459452e-06,
+      "loss": 0.6387,
+      "num_tokens": 66047263.0,
+      "step": 157
+    },
+    {
+      "epoch": 1.4388571428571428,
+      "grad_norm": 0.498957441050946,
+      "learning_rate": 2.912137786677639e-06,
+      "loss": 0.6336,
+      "num_tokens": 66501887.0,
+      "step": 158
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.5480701615542537,
+      "learning_rate": 2.8873681715250197e-06,
+      "loss": 0.6382,
+      "num_tokens": 66899885.0,
+      "step": 159
+    },
+    {
+      "epoch": 1.457142857142857,
+      "grad_norm": 0.5270413445410719,
+      "learning_rate": 2.8625595324105925e-06,
+      "loss": 0.5933,
+      "num_tokens": 67307708.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.4662857142857142,
+      "grad_norm": 0.5087274802990532,
+      "learning_rate": 2.8377143685881835e-06,
+      "loss": 0.5981,
+      "num_tokens": 67732755.0,
+      "step": 161
+    },
+    {
+      "epoch": 1.4754285714285715,
+      "grad_norm": 0.5584833225495552,
+      "learning_rate": 2.812835182991166e-06,
+      "loss": 0.6151,
+      "num_tokens": 68109847.0,
+      "step": 162
+    },
+    {
+      "epoch": 1.4845714285714287,
+      "grad_norm": 0.5337038825179844,
+      "learning_rate": 2.7879244819803104e-06,
+      "loss": 0.5916,
+      "num_tokens": 68557231.0,
+      "step": 163
+    },
+    {
+      "epoch": 1.4937142857142858,
+      "grad_norm": 0.5046455371902981,
+      "learning_rate": 2.7629847750912885e-06,
+      "loss": 0.6266,
+      "num_tokens": 68974066.0,
+      "step": 164
+    },
+    {
+      "epoch": 1.502857142857143,
+      "grad_norm": 0.5388161616170928,
+      "learning_rate": 2.7380185747818628e-06,
+      "loss": 0.6317,
+      "num_tokens": 69374302.0,
+      "step": 165
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.5230970281548867,
+      "learning_rate": 2.713028396178776e-06,
+      "loss": 0.6587,
+      "num_tokens": 69819837.0,
+      "step": 166
+    },
+    {
+      "epoch": 1.5211428571428571,
+      "grad_norm": 0.526880337190175,
+      "learning_rate": 2.6880167568243716e-06,
+      "loss": 0.5943,
+      "num_tokens": 70216440.0,
+      "step": 167
+    },
+    {
+      "epoch": 1.5302857142857142,
+      "grad_norm": 0.5485816175958096,
+      "learning_rate": 2.6629861764229824e-06,
+      "loss": 0.6055,
+      "num_tokens": 70624223.0,
+      "step": 168
+    },
+    {
+      "epoch": 1.5394285714285716,
+      "grad_norm": 0.5305674288577678,
+      "learning_rate": 2.6379391765870828e-06,
+      "loss": 0.61,
+      "num_tokens": 71020172.0,
+      "step": 169
+    },
+    {
+      "epoch": 1.5485714285714285,
+      "grad_norm": 0.5500147924060435,
+      "learning_rate": 2.6128782805832605e-06,
+      "loss": 0.6316,
+      "num_tokens": 71443243.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.5577142857142858,
+      "grad_norm": 0.545744633264797,
+      "learning_rate": 2.5878060130780225e-06,
+      "loss": 0.6343,
+      "num_tokens": 71842978.0,
+      "step": 171
+    },
+    {
+      "epoch": 1.5668571428571427,
+      "grad_norm": 0.5333068371067002,
+      "learning_rate": 2.562724899883458e-06,
+      "loss": 0.5962,
+      "num_tokens": 72246613.0,
+      "step": 172
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5151113808836872,
+      "learning_rate": 2.537637467702777e-06,
+      "loss": 0.5942,
+      "num_tokens": 72635238.0,
+      "step": 173
+    },
+    {
+      "epoch": 1.5851428571428572,
+      "grad_norm": 0.5097827368822562,
+      "learning_rate": 2.512546243875776e-06,
+      "loss": 0.6452,
+      "num_tokens": 73066900.0,
+      "step": 174
+    },
+    {
+      "epoch": 1.5942857142857143,
+      "grad_norm": 0.5050837954931957,
+      "learning_rate": 2.4874537561242253e-06,
+      "loss": 0.5983,
+      "num_tokens": 73459425.0,
+      "step": 175
+    },
+    {
+      "epoch": 1.6034285714285714,
+      "grad_norm": 0.5386528093096086,
+      "learning_rate": 2.462362532297224e-06,
+      "loss": 0.6212,
+      "num_tokens": 73846769.0,
+      "step": 176
+    },
+    {
+      "epoch": 1.6125714285714285,
+      "grad_norm": 0.5208969637241072,
+      "learning_rate": 2.4372751001165427e-06,
+      "loss": 0.5953,
+      "num_tokens": 74238603.0,
+      "step": 177
+    },
+    {
+      "epoch": 1.6217142857142857,
+      "grad_norm": 0.5300750981583515,
+      "learning_rate": 2.4121939869219784e-06,
+      "loss": 0.6385,
+      "num_tokens": 74619800.0,
+      "step": 178
+    },
+    {
+      "epoch": 1.6308571428571428,
+      "grad_norm": 0.4833782673351415,
+      "learning_rate": 2.3871217194167407e-06,
+      "loss": 0.6203,
+      "num_tokens": 75068223.0,
+      "step": 179
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.4940975179707354,
+      "learning_rate": 2.362060823412919e-06,
+      "loss": 0.6251,
+      "num_tokens": 75515755.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.649142857142857,
+      "grad_norm": 0.4884850267837385,
+      "learning_rate": 2.3370138235770184e-06,
+      "loss": 0.5753,
+      "num_tokens": 75968696.0,
+      "step": 181
+    },
+    {
+      "epoch": 1.6582857142857144,
+      "grad_norm": 0.5130965951519948,
+      "learning_rate": 2.3119832431756284e-06,
+      "loss": 0.6274,
+      "num_tokens": 76374172.0,
+      "step": 182
+    },
+    {
+      "epoch": 1.6674285714285715,
+      "grad_norm": 0.5311768193897066,
+      "learning_rate": 2.286971603821226e-06,
+      "loss": 0.5945,
+      "num_tokens": 76766397.0,
+      "step": 183
+    },
+    {
+      "epoch": 1.6765714285714286,
+      "grad_norm": 0.4881821303904307,
+      "learning_rate": 2.261981425218138e-06,
+      "loss": 0.5932,
+      "num_tokens": 77197026.0,
+      "step": 184
+    },
+    {
+      "epoch": 1.6857142857142857,
+      "grad_norm": 0.47122072556306027,
+      "learning_rate": 2.2370152249087114e-06,
+      "loss": 0.58,
+      "num_tokens": 77665939.0,
+      "step": 185
+    },
+    {
+      "epoch": 1.6948571428571428,
+      "grad_norm": 0.5385304392622484,
+      "learning_rate": 2.2120755180196904e-06,
+      "loss": 0.6206,
+      "num_tokens": 78106107.0,
+      "step": 186
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.49447572000428314,
+      "learning_rate": 2.1871648170088347e-06,
+      "loss": 0.5907,
+      "num_tokens": 78538377.0,
+      "step": 187
+    },
+    {
+      "epoch": 1.713142857142857,
+      "grad_norm": 0.5244933755348707,
+      "learning_rate": 2.1622856314118178e-06,
+      "loss": 0.5959,
+      "num_tokens": 78944694.0,
+      "step": 188
+    },
+    {
+      "epoch": 1.7222857142857144,
+      "grad_norm": 0.5301458412434723,
+      "learning_rate": 2.1374404675894083e-06,
+      "loss": 0.6361,
+      "num_tokens": 79395440.0,
+      "step": 189
+    },
+    {
+      "epoch": 1.7314285714285713,
+      "grad_norm": 0.5202435914893955,
+      "learning_rate": 2.1126318284749807e-06,
+      "loss": 0.6127,
+      "num_tokens": 79822802.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.7405714285714287,
+      "grad_norm": 0.48495792096652884,
+      "learning_rate": 2.087862213322362e-06,
+      "loss": 0.6216,
+      "num_tokens": 80251827.0,
+      "step": 191
+    },
+    {
+      "epoch": 1.7497142857142856,
+      "grad_norm": 0.5039270578694471,
+      "learning_rate": 2.063134117454055e-06,
+      "loss": 0.6238,
+      "num_tokens": 80682166.0,
+      "step": 192
+    },
+    {
+      "epoch": 1.758857142857143,
+      "grad_norm": 0.5606686536962094,
+      "learning_rate": 2.0384500320098604e-06,
+      "loss": 0.6327,
+      "num_tokens": 81072109.0,
+      "step": 193
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5154032810828468,
+      "learning_rate": 2.01381244369591e-06,
+      "loss": 0.5878,
+      "num_tokens": 81463643.0,
+      "step": 194
+    },
+    {
+      "epoch": 1.7771428571428571,
+      "grad_norm": 0.5372934038703727,
+      "learning_rate": 1.9892238345341544e-06,
+      "loss": 0.6254,
+      "num_tokens": 81900194.0,
+      "step": 195
+    },
+    {
+      "epoch": 1.7862857142857143,
+      "grad_norm": 0.5372941594212604,
+      "learning_rate": 1.964686681612327e-06,
+      "loss": 0.6012,
+      "num_tokens": 82259830.0,
+      "step": 196
+    },
+    {
+      "epoch": 1.7954285714285714,
+      "grad_norm": 0.5074393400323167,
+      "learning_rate": 1.9402034568343888e-06,
+      "loss": 0.5949,
+      "num_tokens": 82667552.0,
+      "step": 197
+    },
+    {
+      "epoch": 1.8045714285714287,
+      "grad_norm": 0.5361364809103955,
+      "learning_rate": 1.9157766266715142e-06,
+      "loss": 0.6128,
+      "num_tokens": 83029946.0,
+      "step": 198
+    },
+    {
+      "epoch": 1.8137142857142856,
+      "grad_norm": 0.5028599124924883,
+      "learning_rate": 1.8914086519136133e-06,
+      "loss": 0.6024,
+      "num_tokens": 83437794.0,
+      "step": 199
+    },
+    {
+      "epoch": 1.822857142857143,
+      "grad_norm": 0.4915157876191495,
+      "learning_rate": 1.8671019874214237e-06,
+      "loss": 0.6247,
+      "num_tokens": 83857268.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.4795616878883829,
+      "learning_rate": 1.8428590818792135e-06,
+      "loss": 0.597,
+      "num_tokens": 84283309.0,
+      "step": 201
+    },
+    {
+      "epoch": 1.8411428571428572,
+      "grad_norm": 0.4774342459205278,
+      "learning_rate": 1.8186823775480917e-06,
+      "loss": 0.6228,
+      "num_tokens": 84738929.0,
+      "step": 202
+    },
+    {
+      "epoch": 1.8502857142857143,
+      "grad_norm": 0.4943608455779546,
+      "learning_rate": 1.7945743100199706e-06,
+      "loss": 0.6322,
+      "num_tokens": 85153992.0,
+      "step": 203
+    },
+    {
+      "epoch": 1.8594285714285714,
+      "grad_norm": 0.4713560174328036,
+      "learning_rate": 1.7705373079722083e-06,
+      "loss": 0.642,
+      "num_tokens": 85623688.0,
+      "step": 204
+    },
+    {
+      "epoch": 1.8685714285714285,
+      "grad_norm": 0.5141695873278811,
+      "learning_rate": 1.7465737929229317e-06,
+      "loss": 0.6091,
+      "num_tokens": 86006323.0,
+      "step": 205
+    },
+    {
+      "epoch": 1.8777142857142857,
+      "grad_norm": 0.5000534330821961,
+      "learning_rate": 1.722686178987097e-06,
+      "loss": 0.6102,
+      "num_tokens": 86404792.0,
+      "step": 206
+    },
+    {
+      "epoch": 1.886857142857143,
+      "grad_norm": 0.5025822929123239,
+      "learning_rate": 1.6988768726332856e-06,
+      "loss": 0.6379,
+      "num_tokens": 86854752.0,
+      "step": 207
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.49088754619114366,
+      "learning_rate": 1.6751482724412716e-06,
+      "loss": 0.6353,
+      "num_tokens": 87282488.0,
+      "step": 208
+    },
+    {
+      "epoch": 1.9051428571428572,
+      "grad_norm": 0.5251674366397446,
+      "learning_rate": 1.651502768860389e-06,
+      "loss": 0.5973,
+      "num_tokens": 87669853.0,
+      "step": 209
+    },
+    {
+      "epoch": 1.9142857142857141,
+      "grad_norm": 0.4689490751639795,
+      "learning_rate": 1.6279427439687154e-06,
+      "loss": 0.6304,
+      "num_tokens": 88130980.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.9234285714285715,
+      "grad_norm": 0.472058082568105,
+      "learning_rate": 1.6044705712330932e-06,
+      "loss": 0.5638,
+      "num_tokens": 88570357.0,
+      "step": 211
+    },
+    {
+      "epoch": 1.9325714285714286,
+      "grad_norm": 0.4955095804093834,
+      "learning_rate": 1.5810886152700302e-06,
+      "loss": 0.6078,
+      "num_tokens": 88981662.0,
+      "step": 212
+    },
+    {
+      "epoch": 1.9417142857142857,
+      "grad_norm": 0.502372210861262,
+      "learning_rate": 1.5577992316074783e-06,
+      "loss": 0.6023,
+      "num_tokens": 89372451.0,
+      "step": 213
+    },
+    {
+      "epoch": 1.9508571428571428,
+      "grad_norm": 0.5079308074061759,
+      "learning_rate": 1.5346047664475422e-06,
+      "loss": 0.6403,
+      "num_tokens": 89802073.0,
+      "step": 214
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.4700590581768767,
+      "learning_rate": 1.511507556430114e-06,
+      "loss": 0.628,
+      "num_tokens": 90260756.0,
+      "step": 215
+    },
+    {
+      "epoch": 1.9691428571428573,
+      "grad_norm": 0.50339097459113,
+      "learning_rate": 1.4885099283974774e-06,
+      "loss": 0.6428,
+      "num_tokens": 90666132.0,
+      "step": 216
+    },
+    {
+      "epoch": 1.9782857142857142,
+      "grad_norm": 0.514562609979602,
+      "learning_rate": 1.465614199159905e-06,
+      "loss": 0.6365,
+      "num_tokens": 91063409.0,
+      "step": 217
+    },
+    {
+      "epoch": 1.9874285714285715,
+      "grad_norm": 0.48835023162219804,
+      "learning_rate": 1.4428226752622509e-06,
+      "loss": 0.5954,
+      "num_tokens": 91473599.0,
+      "step": 218
+    },
+    {
+      "epoch": 1.9965714285714284,
+      "grad_norm": 0.47655828723147114,
+      "learning_rate": 1.420137652751593e-06,
+      "loss": 0.5973,
+      "num_tokens": 91933410.0,
+      "step": 219
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.789231462279532,
+      "learning_rate": 1.3975614169459253e-06,
+      "loss": 0.6301,
+      "num_tokens": 92090067.0,
+      "step": 220
+    },
+    {
+      "epoch": 2.0091428571428573,
+      "grad_norm": 0.5711191577315374,
+      "learning_rate": 1.3750962422039269e-06,
+      "loss": 0.6032,
+      "num_tokens": 92546736.0,
+      "step": 221
+    },
+    {
+      "epoch": 2.0182857142857142,
+      "grad_norm": 0.5374729825328671,
+      "learning_rate": 1.3527443916958466e-06,
+      "loss": 0.5982,
+      "num_tokens": 92984957.0,
+      "step": 222
+    },
+    {
+      "epoch": 2.0274285714285716,
+      "grad_norm": 0.5318016866757004,
+      "learning_rate": 1.3305081171755092e-06,
+      "loss": 0.58,
+      "num_tokens": 93430346.0,
+      "step": 223
+    },
+    {
+      "epoch": 2.0365714285714285,
+      "grad_norm": 0.5378310465822619,
+      "learning_rate": 1.3083896587534606e-06,
+      "loss": 0.572,
+      "num_tokens": 93859357.0,
+      "step": 224
+    },
+    {
+      "epoch": 2.045714285714286,
+      "grad_norm": 0.5902220930968932,
+      "learning_rate": 1.2863912446713084e-06,
+      "loss": 0.5815,
+      "num_tokens": 94235216.0,
+      "step": 225
+    },
+    {
+      "epoch": 2.0548571428571427,
+      "grad_norm": 0.5405043387197087,
+      "learning_rate": 1.2645150910772413e-06,
+      "loss": 0.5617,
+      "num_tokens": 94651501.0,
+      "step": 226
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.5385666206793902,
+      "learning_rate": 1.2427634018027673e-06,
+      "loss": 0.5644,
+      "num_tokens": 95069945.0,
+      "step": 227
+    },
+    {
+      "epoch": 2.073142857142857,
+      "grad_norm": 0.4997592766482857,
+      "learning_rate": 1.2211383681407022e-06,
+      "loss": 0.5664,
+      "num_tokens": 95524927.0,
+      "step": 228
+    },
+    {
+      "epoch": 2.0822857142857143,
+      "grad_norm": 0.5529900645674626,
+      "learning_rate": 1.1996421686244179e-06,
+      "loss": 0.5776,
+      "num_tokens": 95918641.0,
+      "step": 229
+    },
+    {
+      "epoch": 2.0914285714285716,
+      "grad_norm": 0.5415131513338728,
+      "learning_rate": 1.1782769688083647e-06,
+      "loss": 0.5786,
+      "num_tokens": 96308405.0,
+      "step": 230
+    },
+    {
+      "epoch": 2.1005714285714285,
+      "grad_norm": 0.5354002873656379,
+      "learning_rate": 1.1570449210499213e-06,
+      "loss": 0.5613,
+      "num_tokens": 96732646.0,
+      "step": 231
+    },
+    {
+      "epoch": 2.109714285714286,
+      "grad_norm": 0.5430380283286926,
+      "learning_rate": 1.135948164292557e-06,
+      "loss": 0.542,
+      "num_tokens": 97156843.0,
+      "step": 232
+    },
+    {
+      "epoch": 2.1188571428571428,
+      "grad_norm": 0.5301770327914718,
+      "learning_rate": 1.1149888238503537e-06,
+      "loss": 0.5774,
+      "num_tokens": 97606726.0,
+      "step": 233
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.5525594315362994,
+      "learning_rate": 1.0941690111939002e-06,
+      "loss": 0.5566,
+      "num_tokens": 97986735.0,
+      "step": 234
+    },
+    {
+      "epoch": 2.137142857142857,
+      "grad_norm": 0.4995496823018478,
+      "learning_rate": 1.0734908237375783e-06,
+      "loss": 0.5766,
+      "num_tokens": 98468501.0,
+      "step": 235
+    },
+    {
+      "epoch": 2.1462857142857144,
+      "grad_norm": 0.5378604882040718,
+      "learning_rate": 1.0529563446282665e-06,
+      "loss": 0.5632,
+      "num_tokens": 98903725.0,
+      "step": 236
+    },
+    {
+      "epoch": 2.1554285714285712,
+      "grad_norm": 0.5207373128952933,
+      "learning_rate": 1.0325676425354828e-06,
+      "loss": 0.5636,
+      "num_tokens": 99331228.0,
+      "step": 237
+    },
+    {
+      "epoch": 2.1645714285714286,
+      "grad_norm": 0.5256645631693067,
+      "learning_rate": 1.0123267714429826e-06,
+      "loss": 0.5922,
+      "num_tokens": 99763837.0,
+      "step": 238
+    },
+    {
+      "epoch": 2.1737142857142855,
+      "grad_norm": 0.5321491484630023,
+      "learning_rate": 9.922357704418394e-07,
+      "loss": 0.5849,
+      "num_tokens": 100178817.0,
+      "step": 239
+    },
+    {
+      "epoch": 2.182857142857143,
+      "grad_norm": 0.5138997122471298,
+      "learning_rate": 9.722966635250222e-07,
+      "loss": 0.5401,
+      "num_tokens": 100610730.0,
+      "step": 240
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.4943367780588382,
+      "learning_rate": 9.525114593834975e-07,
+      "loss": 0.5851,
+      "num_tokens": 101068964.0,
+      "step": 241
+    },
+    {
+      "epoch": 2.201142857142857,
+      "grad_norm": 0.5154577499927364,
+      "learning_rate": 9.328821512038716e-07,
+      "loss": 0.5884,
+      "num_tokens": 101487081.0,
+      "step": 242
+    },
+    {
+      "epoch": 2.2102857142857144,
+      "grad_norm": 0.5222259240916006,
+      "learning_rate": 9.134107164675898e-07,
+      "loss": 0.5801,
+      "num_tokens": 101904000.0,
+      "step": 243
+    },
+    {
+      "epoch": 2.2194285714285713,
+      "grad_norm": 0.5259169693667993,
+      "learning_rate": 8.940991167517313e-07,
+      "loss": 0.5807,
+      "num_tokens": 102307191.0,
+      "step": 244
+    },
+    {
+      "epoch": 2.2285714285714286,
+      "grad_norm": 0.5206118106771275,
+      "learning_rate": 8.749492975313897e-07,
+      "loss": 0.5614,
+      "num_tokens": 102716603.0,
+      "step": 245
+    },
+    {
+      "epoch": 2.2377142857142855,
+      "grad_norm": 0.5219924329022366,
+      "learning_rate": 8.559631879836838e-07,
+      "loss": 0.584,
+      "num_tokens": 103129732.0,
+      "step": 246
+    },
+    {
+      "epoch": 2.246857142857143,
+      "grad_norm": 0.4964769891153005,
+      "learning_rate": 8.371427007934174e-07,
+      "loss": 0.5742,
+      "num_tokens": 103552339.0,
+      "step": 247
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.507390544236327,
+      "learning_rate": 8.184897319603813e-07,
+      "loss": 0.6142,
+      "num_tokens": 103987991.0,
+      "step": 248
+    },
+    {
+      "epoch": 2.265142857142857,
+      "grad_norm": 0.4989116246504005,
+      "learning_rate": 8.000061606083579e-07,
+      "loss": 0.6119,
+      "num_tokens": 104429673.0,
+      "step": 249
+    },
+    {
+      "epoch": 2.2742857142857145,
+      "grad_norm": 0.5098053191178704,
+      "learning_rate": 7.816938487958131e-07,
+      "loss": 0.5546,
+      "num_tokens": 104841554.0,
+      "step": 250
+    },
+    {
+      "epoch": 2.2834285714285714,
+      "grad_norm": 0.5089115422799331,
+      "learning_rate": 7.635546413283054e-07,
+      "loss": 0.5832,
+      "num_tokens": 105253055.0,
+      "step": 251
+    },
+    {
+      "epoch": 2.2925714285714287,
+      "grad_norm": 0.5348285772467526,
+      "learning_rate": 7.455903655726437e-07,
+      "loss": 0.5262,
+      "num_tokens": 105614395.0,
+      "step": 252
+    },
+    {
+      "epoch": 2.3017142857142856,
+      "grad_norm": 0.5320710749897903,
+      "learning_rate": 7.278028312727961e-07,
+      "loss": 0.5374,
+      "num_tokens": 105984595.0,
+      "step": 253
+    },
+    {
+      "epoch": 2.310857142857143,
+      "grad_norm": 0.5015290198043492,
+      "learning_rate": 7.101938303675674e-07,
+      "loss": 0.5674,
+      "num_tokens": 106417649.0,
+      "step": 254
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.5164124073124037,
+      "learning_rate": 6.927651368100843e-07,
+      "loss": 0.5702,
+      "num_tokens": 106818638.0,
+      "step": 255
+    },
+    {
+      "epoch": 2.329142857142857,
+      "grad_norm": 0.4846215779170027,
+      "learning_rate": 6.755185063890818e-07,
+      "loss": 0.5509,
+      "num_tokens": 107258625.0,
+      "step": 256
+    },
+    {
+      "epoch": 2.338285714285714,
+      "grad_norm": 0.5097907143887082,
+      "learning_rate": 6.584556765520231e-07,
+      "loss": 0.5798,
+      "num_tokens": 107680389.0,
+      "step": 257
+    },
+    {
+      "epoch": 2.3474285714285714,
+      "grad_norm": 0.5068807711002643,
+      "learning_rate": 6.415783662300662e-07,
+      "loss": 0.5877,
+      "num_tokens": 108115625.0,
+      "step": 258
+    },
+    {
+      "epoch": 2.3565714285714288,
+      "grad_norm": 0.5179162356392562,
+      "learning_rate": 6.248882756648988e-07,
+      "loss": 0.5623,
+      "num_tokens": 108526100.0,
+      "step": 259
+    },
+    {
+      "epoch": 2.3657142857142857,
+      "grad_norm": 0.5074768216794914,
+      "learning_rate": 6.083870862374513e-07,
+      "loss": 0.5701,
+      "num_tokens": 108943744.0,
+      "step": 260
+    },
+    {
+      "epoch": 2.374857142857143,
+      "grad_norm": 0.4954184591704928,
+      "learning_rate": 5.920764602985141e-07,
+      "loss": 0.562,
+      "num_tokens": 109381379.0,
+      "step": 261
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.5147752391401487,
+      "learning_rate": 5.759580410012691e-07,
+      "loss": 0.565,
+      "num_tokens": 109793247.0,
+      "step": 262
+    },
+    {
+      "epoch": 2.3931428571428572,
+      "grad_norm": 0.5253288675199733,
+      "learning_rate": 5.600334521357581e-07,
+      "loss": 0.595,
+      "num_tokens": 110202872.0,
+      "step": 263
+    },
+    {
+      "epoch": 2.402285714285714,
+      "grad_norm": 0.48483979120150505,
+      "learning_rate": 5.443042979652957e-07,
+      "loss": 0.5725,
+      "num_tokens": 110639527.0,
+      "step": 264
+    },
+    {
+      "epoch": 2.4114285714285715,
+      "grad_norm": 0.5039540186447794,
+      "learning_rate": 5.287721630648615e-07,
+      "loss": 0.5826,
+      "num_tokens": 111073504.0,
+      "step": 265
+    },
+    {
+      "epoch": 2.420571428571429,
+      "grad_norm": 0.5283553665176294,
+      "learning_rate": 5.134386121614615e-07,
+      "loss": 0.5598,
+      "num_tokens": 111473527.0,
+      "step": 266
+    },
+    {
+      "epoch": 2.4297142857142857,
+      "grad_norm": 0.5021929773072068,
+      "learning_rate": 4.983051899764946e-07,
+      "loss": 0.5467,
+      "num_tokens": 111888096.0,
+      "step": 267
+    },
+    {
+      "epoch": 2.4388571428571426,
+      "grad_norm": 0.5086106631732937,
+      "learning_rate": 4.833734210701435e-07,
+      "loss": 0.5653,
+      "num_tokens": 112274040.0,
+      "step": 268
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 0.5070750574100812,
+      "learning_rate": 4.6864480968778103e-07,
+      "loss": 0.5854,
+      "num_tokens": 112701254.0,
+      "step": 269
+    },
+    {
+      "epoch": 2.4571428571428573,
+      "grad_norm": 0.5389372884949655,
+      "learning_rate": 4.541208396084304e-07,
+      "loss": 0.569,
+      "num_tokens": 113084811.0,
+      "step": 270
+    },
+    {
+      "epoch": 2.466285714285714,
+      "grad_norm": 0.4954996531070081,
+      "learning_rate": 4.39802973995295e-07,
+      "loss": 0.5931,
+      "num_tokens": 113515668.0,
+      "step": 271
+    },
+    {
+      "epoch": 2.4754285714285715,
+      "grad_norm": 0.5335874562537316,
+      "learning_rate": 4.2569265524834756e-07,
+      "loss": 0.5588,
+      "num_tokens": 113895133.0,
+      "step": 272
+    },
+    {
+      "epoch": 2.4845714285714284,
+      "grad_norm": 0.4974120943217034,
+      "learning_rate": 4.117913048590283e-07,
+      "loss": 0.5723,
+      "num_tokens": 114325228.0,
+      "step": 273
+    },
+    {
+      "epoch": 2.4937142857142858,
+      "grad_norm": 0.47465781973096216,
+      "learning_rate": 3.9810032326704106e-07,
+      "loss": 0.5359,
+      "num_tokens": 114773958.0,
+      "step": 274
+    },
+    {
+      "epoch": 2.5028571428571427,
+      "grad_norm": 0.4954990612858109,
+      "learning_rate": 3.8462108971926564e-07,
+      "loss": 0.5797,
+      "num_tokens": 115212487.0,
+      "step": 275
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.4968181717935684,
+      "learning_rate": 3.713549621308174e-07,
+      "loss": 0.5942,
+      "num_tokens": 115622910.0,
+      "step": 276
+    },
+    {
+      "epoch": 2.5211428571428574,
+      "grad_norm": 0.5082368933542878,
+      "learning_rate": 3.5830327694824777e-07,
+      "loss": 0.5652,
+      "num_tokens": 116027725.0,
+      "step": 277
+    },
+    {
+      "epoch": 2.5302857142857142,
+      "grad_norm": 0.4866800840052398,
+      "learning_rate": 3.4546734901490466e-07,
+      "loss": 0.5783,
+      "num_tokens": 116475926.0,
+      "step": 278
+    },
+    {
+      "epoch": 2.5394285714285716,
+      "grad_norm": 0.5091530695044061,
+      "learning_rate": 3.3284847143847834e-07,
+      "loss": 0.5903,
+      "num_tokens": 116890461.0,
+      "step": 279
+    },
+    {
+      "epoch": 2.5485714285714285,
+      "grad_norm": 0.5115099249876448,
+      "learning_rate": 3.2044791546072985e-07,
+      "loss": 0.5618,
+      "num_tokens": 117282195.0,
+      "step": 280
+    },
+    {
+      "epoch": 2.557714285714286,
+      "grad_norm": 0.5050583956238427,
+      "learning_rate": 3.0826693032942586e-07,
+      "loss": 0.5711,
+      "num_tokens": 117710503.0,
+      "step": 281
+    },
+    {
+      "epoch": 2.5668571428571427,
+      "grad_norm": 0.5374803213347745,
+      "learning_rate": 2.963067431724856e-07,
+      "loss": 0.5629,
+      "num_tokens": 118081184.0,
+      "step": 282
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.4984343530594435,
+      "learning_rate": 2.8456855887436074e-07,
+      "loss": 0.5765,
+      "num_tokens": 118489510.0,
+      "step": 283
+    },
+    {
+      "epoch": 2.5851428571428574,
+      "grad_norm": 0.5090570265753169,
+      "learning_rate": 2.730535599546524e-07,
+      "loss": 0.5999,
+      "num_tokens": 118876624.0,
+      "step": 284
+    },
+    {
+      "epoch": 2.5942857142857143,
+      "grad_norm": 0.519781544356009,
+      "learning_rate": 2.617629064489838e-07,
+      "loss": 0.6156,
+      "num_tokens": 119323858.0,
+      "step": 285
+    },
+    {
+      "epoch": 2.603428571428571,
+      "grad_norm": 0.48368780311253534,
+      "learning_rate": 2.50697735792135e-07,
+      "loss": 0.5865,
+      "num_tokens": 119746235.0,
+      "step": 286
+    },
+    {
+      "epoch": 2.6125714285714285,
+      "grad_norm": 0.6677870618002503,
+      "learning_rate": 2.398591627034588e-07,
+      "loss": 0.5738,
+      "num_tokens": 120176419.0,
+      "step": 287
+    },
+    {
+      "epoch": 2.621714285714286,
+      "grad_norm": 0.5161420445880435,
+      "learning_rate": 2.2924827907457841e-07,
+      "loss": 0.602,
+      "num_tokens": 120585061.0,
+      "step": 288
+    },
+    {
+      "epoch": 2.630857142857143,
+      "grad_norm": 0.4953371088579667,
+      "learning_rate": 2.1886615385939502e-07,
+      "loss": 0.5847,
+      "num_tokens": 121022910.0,
+      "step": 289
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.4700637789497405,
+      "learning_rate": 2.0871383296639487e-07,
+      "loss": 0.574,
+      "num_tokens": 121496265.0,
+      "step": 290
+    },
+    {
+      "epoch": 2.649142857142857,
+      "grad_norm": 0.48662101727536294,
+      "learning_rate": 1.9879233915328312e-07,
+      "loss": 0.5765,
+      "num_tokens": 121936055.0,
+      "step": 291
+    },
+    {
+      "epoch": 2.6582857142857144,
+      "grad_norm": 0.5099077987670947,
+      "learning_rate": 1.891026719239547e-07,
+      "loss": 0.5599,
+      "num_tokens": 122342895.0,
+      "step": 292
+    },
+    {
+      "epoch": 2.6674285714285713,
+      "grad_norm": 0.4938591026159351,
+      "learning_rate": 1.7964580742779847e-07,
+      "loss": 0.6128,
+      "num_tokens": 122770275.0,
+      "step": 293
+    },
+    {
+      "epoch": 2.6765714285714286,
+      "grad_norm": 0.4870135117164128,
+      "learning_rate": 1.7042269836135882e-07,
+      "loss": 0.5931,
+      "num_tokens": 123192007.0,
+      "step": 294
+    },
+    {
+      "epoch": 2.685714285714286,
+      "grad_norm": 0.5240800119635359,
+      "learning_rate": 1.6143427387236455e-07,
+      "loss": 0.5996,
+      "num_tokens": 123596083.0,
+      "step": 295
+    },
+    {
+      "epoch": 2.694857142857143,
+      "grad_norm": 0.5217629720972092,
+      "learning_rate": 1.5268143946611802e-07,
+      "loss": 0.605,
+      "num_tokens": 124000214.0,
+      "step": 296
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.4949853085092262,
+      "learning_rate": 1.441650769142791e-07,
+      "loss": 0.5705,
+      "num_tokens": 124420120.0,
+      "step": 297
+    },
+    {
+      "epoch": 2.713142857142857,
+      "grad_norm": 0.49569537617283155,
+      "learning_rate": 1.3588604416603424e-07,
+      "loss": 0.5722,
+      "num_tokens": 124837441.0,
+      "step": 298
+    },
+    {
+      "epoch": 2.7222857142857144,
+      "grad_norm": 0.5148571496736348,
+      "learning_rate": 1.278451752616608e-07,
+      "loss": 0.582,
+      "num_tokens": 125229470.0,
+      "step": 299
+    },
+    {
+      "epoch": 2.7314285714285713,
+      "grad_norm": 0.4755041735866527,
+      "learning_rate": 1.2004328024850938e-07,
+      "loss": 0.5543,
+      "num_tokens": 125662137.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.7405714285714287,
+      "grad_norm": 0.5106445243079593,
+      "learning_rate": 1.1248114509939817e-07,
+      "loss": 0.5949,
+      "num_tokens": 126052227.0,
+      "step": 301
+    },
+    {
+      "epoch": 2.7497142857142856,
+      "grad_norm": 0.4914711633020567,
+      "learning_rate": 1.0515953163342973e-07,
+      "loss": 0.593,
+      "num_tokens": 126455360.0,
+      "step": 302
+    },
+    {
+      "epoch": 2.758857142857143,
+      "grad_norm": 0.49545896667246636,
+      "learning_rate": 9.807917743924838e-08,
+      "loss": 0.5458,
+      "num_tokens": 126870673.0,
+      "step": 303
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.49575860288282114,
+      "learning_rate": 9.12407958007322e-08,
+      "loss": 0.5402,
+      "num_tokens": 127271445.0,
+      "step": 304
+    },
+    {
+      "epoch": 2.777142857142857,
+      "grad_norm": 0.4915092472121106,
+      "learning_rate": 8.464507562513657e-08,
+      "loss": 0.6131,
+      "num_tokens": 127712507.0,
+      "step": 305
+    },
+    {
+      "epoch": 2.7862857142857145,
+      "grad_norm": 0.4961962340392434,
+      "learning_rate": 7.829268137369311e-08,
+      "loss": 0.5851,
+      "num_tokens": 128132380.0,
+      "step": 306
+    },
+    {
+      "epoch": 2.7954285714285714,
+      "grad_norm": 0.4752993340814379,
+      "learning_rate": 7.21842529946698e-08,
+      "loss": 0.6129,
+      "num_tokens": 128588339.0,
+      "step": 307
+    },
+    {
+      "epoch": 2.8045714285714287,
+      "grad_norm": 0.503510989247386,
+      "learning_rate": 6.632040585890398e-08,
+      "loss": 0.5674,
+      "num_tokens": 129005751.0,
+      "step": 308
+    },
+    {
+      "epoch": 2.8137142857142856,
+      "grad_norm": 0.4724716751556215,
+      "learning_rate": 6.070173069780638e-08,
+      "loss": 0.562,
+      "num_tokens": 129476694.0,
+      "step": 309
+    },
+    {
+      "epoch": 2.822857142857143,
+      "grad_norm": 0.48385278796222503,
+      "learning_rate": 5.532879354385234e-08,
+      "loss": 0.5745,
+      "num_tokens": 129914320.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.48514365333284165,
+      "learning_rate": 5.020213567355825e-08,
+      "loss": 0.5667,
+      "num_tokens": 130364577.0,
+      "step": 311
+    },
+    {
+      "epoch": 2.841142857142857,
+      "grad_norm": 0.4780875564800783,
+      "learning_rate": 4.5322273552951265e-08,
+      "loss": 0.5897,
+      "num_tokens": 130817643.0,
+      "step": 312
+    },
+    {
+      "epoch": 2.8502857142857145,
+      "grad_norm": 0.4898713768327533,
+      "learning_rate": 4.068969878554263e-08,
+      "loss": 0.5874,
+      "num_tokens": 131252219.0,
+      "step": 313
+    },
+    {
+      "epoch": 2.8594285714285714,
+      "grad_norm": 0.47651774728183893,
+      "learning_rate": 3.630487806280086e-08,
+      "loss": 0.583,
+      "num_tokens": 131680425.0,
+      "step": 314
+    },
+    {
+      "epoch": 2.8685714285714283,
+      "grad_norm": 0.49334334956687725,
+      "learning_rate": 3.216825311713689e-08,
+      "loss": 0.6196,
+      "num_tokens": 132110282.0,
+      "step": 315
+    },
+    {
+      "epoch": 2.8777142857142857,
+      "grad_norm": 0.47081742859201037,
+      "learning_rate": 2.8280240677403813e-08,
+      "loss": 0.6073,
+      "num_tokens": 132564761.0,
+      "step": 316
+    },
+    {
+      "epoch": 2.886857142857143,
+      "grad_norm": 0.489336125798635,
+      "learning_rate": 2.464123242691574e-08,
+      "loss": 0.5928,
+      "num_tokens": 133016872.0,
+      "step": 317
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 0.5047605121395512,
+      "learning_rate": 2.1251594963986876e-08,
+      "loss": 0.5916,
+      "num_tokens": 133419747.0,
+      "step": 318
+    },
+    {
+      "epoch": 2.9051428571428572,
+      "grad_norm": 0.5055723323188881,
+      "learning_rate": 1.8111669765003005e-08,
+      "loss": 0.6042,
+      "num_tokens": 133842060.0,
+      "step": 319
+    },
+    {
+      "epoch": 2.914285714285714,
+      "grad_norm": 0.5311741921831599,
+      "learning_rate": 1.5221773150017882e-08,
+      "loss": 0.5986,
+      "num_tokens": 134246398.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.9234285714285715,
+      "grad_norm": 0.48458962339074657,
+      "learning_rate": 1.2582196250888745e-08,
+      "loss": 0.58,
+      "num_tokens": 134665906.0,
+      "step": 321
+    },
+    {
+      "epoch": 2.9325714285714284,
+      "grad_norm": 0.5273108133161314,
+      "learning_rate": 1.0193204981946426e-08,
+      "loss": 0.5655,
+      "num_tokens": 135058042.0,
+      "step": 322
+    },
+    {
+      "epoch": 2.9417142857142857,
+      "grad_norm": 0.4986724954854335,
+      "learning_rate": 8.055040013207061e-09,
+      "loss": 0.6096,
+      "num_tokens": 135459374.0,
+      "step": 323
+    },
+    {
+      "epoch": 2.950857142857143,
+      "grad_norm": 0.47288278261543093,
+      "learning_rate": 6.1679167461262124e-09,
+      "loss": 0.544,
+      "num_tokens": 135926099.0,
+      "step": 324
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.48901998463055885,
+      "learning_rate": 4.53202529190011e-09,
+      "loss": 0.5862,
+      "num_tokens": 136330163.0,
+      "step": 325
+    },
+    {
+      "epoch": 2.9691428571428573,
+      "grad_norm": 0.4843858034119068,
+      "learning_rate": 3.147530452311809e-09,
+      "loss": 0.5486,
+      "num_tokens": 136750371.0,
+      "step": 326
+    },
+    {
+      "epoch": 2.978285714285714,
+      "grad_norm": 0.508393418386821,
+      "learning_rate": 2.01457170313113e-09,
+      "loss": 0.5906,
+      "num_tokens": 137146494.0,
+      "step": 327
+    },
+    {
+      "epoch": 2.9874285714285715,
+      "grad_norm": 0.493149265400495,
+      "learning_rate": 1.1332631800620164e-09,
+      "loss": 0.5554,
+      "num_tokens": 137571606.0,
+      "step": 328
+    },
+    {
+      "epoch": 2.9965714285714284,
+      "grad_norm": 0.5141360605578703,
+      "learning_rate": 5.036936672447868e-10,
+      "loss": 0.5281,
+      "num_tokens": 137971073.0,
+      "step": 329
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7668987334851985,
+      "learning_rate": 1.2592658831245274e-10,
+      "loss": 0.5627,
+      "num_tokens": 138142278.0,
+      "step": 330
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.200567398630162e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a2a0ed0eafa2e85d833a03b3658c98fad208b30049879ef9107a42054b3e11
+size 8337

zero_to_fp32.py

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