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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,13 @@
+{%- if messages|length == 1 and messages[0].role == 'user' %}
+{{- '<|im_start|>' + messages[0].content + '<|im_end|>\n' }}
+{%- else %}
+{%- for message in messages %}
+{%- if message.role == 'user' %}
+{{- '<|im_start|>' + message.content + '<|im_end|>\n' }}
+{%- elif message.role == 'assistant' %}
+{{- message.content + '<|endoftext|>' }}
+{%- endif %}
+{%- endfor %}
+{%- endif %}
+{%- if add_generation_prompt %}
+{%- endif %}

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.53.1"
+}

latest

@@ -0,0 +1 @@
+global_step252

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfec2d2f5e05e4dc4a40a4a54fed40743ecf239dc99ba7390d740df433154838
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1105f5505483cac517897dd40721b7ca8019113406780ec9be0fef48eb143f91
+size 3855679144

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 8822848512
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1822 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1946587537091988,
+  "eval_steps": 126,
+  "global_step": 252,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 3.176351308822632,
+      "eval_runtime": 160.501,
+      "eval_samples_per_second": 11.19,
+      "eval_steps_per_second": 0.704,
+      "step": 0
+    },
+    {
+      "epoch": 0.004747774480712166,
+      "grad_norm": 14.394155502319336,
+      "learning_rate": 0.0,
+      "loss": 3.5173,
+      "step": 1
+    },
+    {
+      "epoch": 0.009495548961424332,
+      "grad_norm": 15.094048500061035,
+      "learning_rate": 3.174603174603175e-07,
+      "loss": 3.7637,
+      "step": 2
+    },
+    {
+      "epoch": 0.014243323442136498,
+      "grad_norm": 15.361183166503906,
+      "learning_rate": 6.34920634920635e-07,
+      "loss": 3.7578,
+      "step": 3
+    },
+    {
+      "epoch": 0.018991097922848664,
+      "grad_norm": 15.74487018585205,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 3.7525,
+      "step": 4
+    },
+    {
+      "epoch": 0.02373887240356083,
+      "grad_norm": 13.999384880065918,
+      "learning_rate": 1.26984126984127e-06,
+      "loss": 3.6421,
+      "step": 5
+    },
+    {
+      "epoch": 0.028486646884272996,
+      "grad_norm": 14.453660011291504,
+      "learning_rate": 1.5873015873015873e-06,
+      "loss": 3.656,
+      "step": 6
+    },
+    {
+      "epoch": 0.03323442136498516,
+      "grad_norm": 14.581559181213379,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 3.7368,
+      "step": 7
+    },
+    {
+      "epoch": 0.03798219584569733,
+      "grad_norm": 13.600449562072754,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 3.5658,
+      "step": 8
+    },
+    {
+      "epoch": 0.042729970326409496,
+      "grad_norm": 11.520191192626953,
+      "learning_rate": 2.53968253968254e-06,
+      "loss": 3.3966,
+      "step": 9
+    },
+    {
+      "epoch": 0.04747774480712166,
+      "grad_norm": 11.848709106445312,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 3.4279,
+      "step": 10
+    },
+    {
+      "epoch": 0.05222551928783383,
+      "grad_norm": 11.579791069030762,
+      "learning_rate": 3.1746031746031746e-06,
+      "loss": 3.4126,
+      "step": 11
+    },
+    {
+      "epoch": 0.05697329376854599,
+      "grad_norm": 10.861617088317871,
+      "learning_rate": 3.492063492063492e-06,
+      "loss": 3.1806,
+      "step": 12
+    },
+    {
+      "epoch": 0.06172106824925816,
+      "grad_norm": 11.614352226257324,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 3.0254,
+      "step": 13
+    },
+    {
+      "epoch": 0.06646884272997032,
+      "grad_norm": 11.77472972869873,
+      "learning_rate": 4.126984126984127e-06,
+      "loss": 2.9602,
+      "step": 14
+    },
+    {
+      "epoch": 0.0712166172106825,
+      "grad_norm": 11.360806465148926,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 2.9155,
+      "step": 15
+    },
+    {
+      "epoch": 0.07596439169139466,
+      "grad_norm": 12.338720321655273,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 2.4742,
+      "step": 16
+    },
+    {
+      "epoch": 0.08071216617210683,
+      "grad_norm": 13.61253833770752,
+      "learning_rate": 5.07936507936508e-06,
+      "loss": 2.4264,
+      "step": 17
+    },
+    {
+      "epoch": 0.08545994065281899,
+      "grad_norm": 13.436763763427734,
+      "learning_rate": 5.396825396825397e-06,
+      "loss": 2.323,
+      "step": 18
+    },
+    {
+      "epoch": 0.09020771513353115,
+      "grad_norm": 11.5920991897583,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 2.0951,
+      "step": 19
+    },
+    {
+      "epoch": 0.09495548961424333,
+      "grad_norm": 10.541767120361328,
+      "learning_rate": 6.031746031746032e-06,
+      "loss": 1.9129,
+      "step": 20
+    },
+    {
+      "epoch": 0.09970326409495549,
+      "grad_norm": 10.552443504333496,
+      "learning_rate": 6.349206349206349e-06,
+      "loss": 1.7977,
+      "step": 21
+    },
+    {
+      "epoch": 0.10445103857566766,
+      "grad_norm": 10.990846633911133,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.584,
+      "step": 22
+    },
+    {
+      "epoch": 0.10919881305637982,
+      "grad_norm": 9.763855934143066,
+      "learning_rate": 6.984126984126984e-06,
+      "loss": 1.401,
+      "step": 23
+    },
+    {
+      "epoch": 0.11394658753709198,
+      "grad_norm": 7.580389499664307,
+      "learning_rate": 7.301587301587301e-06,
+      "loss": 1.2337,
+      "step": 24
+    },
+    {
+      "epoch": 0.11869436201780416,
+      "grad_norm": 7.879193305969238,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 1.185,
+      "step": 25
+    },
+    {
+      "epoch": 0.12344213649851632,
+      "grad_norm": 7.337639331817627,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 1.0778,
+      "step": 26
+    },
+    {
+      "epoch": 0.1281899109792285,
+      "grad_norm": 5.66098690032959,
+      "learning_rate": 8.253968253968254e-06,
+      "loss": 0.9721,
+      "step": 27
+    },
+    {
+      "epoch": 0.13293768545994064,
+      "grad_norm": 4.907323360443115,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.9584,
+      "step": 28
+    },
+    {
+      "epoch": 0.13768545994065282,
+      "grad_norm": 3.510972023010254,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.8819,
+      "step": 29
+    },
+    {
+      "epoch": 0.142433234421365,
+      "grad_norm": 3.220461368560791,
+      "learning_rate": 9.206349206349207e-06,
+      "loss": 0.8042,
+      "step": 30
+    },
+    {
+      "epoch": 0.14718100890207717,
+      "grad_norm": 2.63944935798645,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.7757,
+      "step": 31
+    },
+    {
+      "epoch": 0.1519287833827893,
+      "grad_norm": 11.566150665283203,
+      "learning_rate": 9.841269841269842e-06,
+      "loss": 0.6714,
+      "step": 32
+    },
+    {
+      "epoch": 0.1566765578635015,
+      "grad_norm": 2.1101737022399902,
+      "learning_rate": 1.015873015873016e-05,
+      "loss": 0.6488,
+      "step": 33
+    },
+    {
+      "epoch": 0.16142433234421366,
+      "grad_norm": 3.368835926055908,
+      "learning_rate": 1.0476190476190477e-05,
+      "loss": 0.6551,
+      "step": 34
+    },
+    {
+      "epoch": 0.1661721068249258,
+      "grad_norm": 2.465441942214966,
+      "learning_rate": 1.0793650793650794e-05,
+      "loss": 0.6039,
+      "step": 35
+    },
+    {
+      "epoch": 0.17091988130563798,
+      "grad_norm": 1.3464806079864502,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.5671,
+      "step": 36
+    },
+    {
+      "epoch": 0.17566765578635016,
+      "grad_norm": 2.223472833633423,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.5821,
+      "step": 37
+    },
+    {
+      "epoch": 0.1804154302670623,
+      "grad_norm": 1.5176966190338135,
+      "learning_rate": 1.1746031746031748e-05,
+      "loss": 0.5397,
+      "step": 38
+    },
+    {
+      "epoch": 0.18516320474777448,
+      "grad_norm": 2.944708824157715,
+      "learning_rate": 1.2063492063492064e-05,
+      "loss": 0.5455,
+      "step": 39
+    },
+    {
+      "epoch": 0.18991097922848665,
+      "grad_norm": 1.5701731443405151,
+      "learning_rate": 1.2380952380952383e-05,
+      "loss": 0.5256,
+      "step": 40
+    },
+    {
+      "epoch": 0.1946587537091988,
+      "grad_norm": 1.0416580438613892,
+      "learning_rate": 1.2698412698412699e-05,
+      "loss": 0.4746,
+      "step": 41
+    },
+    {
+      "epoch": 0.19940652818991098,
+      "grad_norm": 1.0439484119415283,
+      "learning_rate": 1.3015873015873018e-05,
+      "loss": 0.4844,
+      "step": 42
+    },
+    {
+      "epoch": 0.20415430267062315,
+      "grad_norm": 2.974339485168457,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.509,
+      "step": 43
+    },
+    {
+      "epoch": 0.20890207715133532,
+      "grad_norm": 1.0552765130996704,
+      "learning_rate": 1.3650793650793652e-05,
+      "loss": 0.5047,
+      "step": 44
+    },
+    {
+      "epoch": 0.21364985163204747,
+      "grad_norm": 3.1413824558258057,
+      "learning_rate": 1.3968253968253968e-05,
+      "loss": 0.4924,
+      "step": 45
+    },
+    {
+      "epoch": 0.21839762611275965,
+      "grad_norm": 1.9047034978866577,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.456,
+      "step": 46
+    },
+    {
+      "epoch": 0.22314540059347182,
+      "grad_norm": 1.2171484231948853,
+      "learning_rate": 1.4603174603174603e-05,
+      "loss": 0.4459,
+      "step": 47
+    },
+    {
+      "epoch": 0.22789317507418397,
+      "grad_norm": 4.339561462402344,
+      "learning_rate": 1.4920634920634922e-05,
+      "loss": 0.4565,
+      "step": 48
+    },
+    {
+      "epoch": 0.23264094955489614,
+      "grad_norm": 2.3773863315582275,
+      "learning_rate": 1.523809523809524e-05,
+      "loss": 0.4568,
+      "step": 49
+    },
+    {
+      "epoch": 0.23738872403560832,
+      "grad_norm": 1.8882341384887695,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.4452,
+      "step": 50
+    },
+    {
+      "epoch": 0.24213649851632046,
+      "grad_norm": 1.1871311664581299,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 0.4238,
+      "step": 51
+    },
+    {
+      "epoch": 0.24688427299703264,
+      "grad_norm": 2.8959860801696777,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 0.426,
+      "step": 52
+    },
+    {
+      "epoch": 0.2516320474777448,
+      "grad_norm": 0.9582217335700989,
+      "learning_rate": 1.6507936507936507e-05,
+      "loss": 0.4246,
+      "step": 53
+    },
+    {
+      "epoch": 0.256379821958457,
+      "grad_norm": 0.8898813128471375,
+      "learning_rate": 1.6825396825396828e-05,
+      "loss": 0.4072,
+      "step": 54
+    },
+    {
+      "epoch": 0.26112759643916916,
+      "grad_norm": 0.9023370742797852,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.4083,
+      "step": 55
+    },
+    {
+      "epoch": 0.2658753709198813,
+      "grad_norm": 1.1952933073043823,
+      "learning_rate": 1.7460317460317463e-05,
+      "loss": 0.401,
+      "step": 56
+    },
+    {
+      "epoch": 0.27062314540059346,
+      "grad_norm": 1.1986902952194214,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.4006,
+      "step": 57
+    },
+    {
+      "epoch": 0.27537091988130563,
+      "grad_norm": 0.6974486112594604,
+      "learning_rate": 1.8095238095238097e-05,
+      "loss": 0.4173,
+      "step": 58
+    },
+    {
+      "epoch": 0.2801186943620178,
+      "grad_norm": 1.2794380187988281,
+      "learning_rate": 1.8412698412698415e-05,
+      "loss": 0.3893,
+      "step": 59
+    },
+    {
+      "epoch": 0.28486646884273,
+      "grad_norm": 0.7234415411949158,
+      "learning_rate": 1.8730158730158732e-05,
+      "loss": 0.3904,
+      "step": 60
+    },
+    {
+      "epoch": 0.28961424332344216,
+      "grad_norm": 0.6361059546470642,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.4136,
+      "step": 61
+    },
+    {
+      "epoch": 0.29436201780415433,
+      "grad_norm": 1.7151949405670166,
+      "learning_rate": 1.9365079365079367e-05,
+      "loss": 0.3943,
+      "step": 62
+    },
+    {
+      "epoch": 0.29910979228486645,
+      "grad_norm": 0.6753223538398743,
+      "learning_rate": 1.9682539682539684e-05,
+      "loss": 0.3938,
+      "step": 63
+    },
+    {
+      "epoch": 0.3038575667655786,
+      "grad_norm": 2.0604114532470703,
+      "learning_rate": 2e-05,
+      "loss": 0.3909,
+      "step": 64
+    },
+    {
+      "epoch": 0.3086053412462908,
+      "grad_norm": 0.7779602408409119,
+      "learning_rate": 1.9999846502070808e-05,
+      "loss": 0.3661,
+      "step": 65
+    },
+    {
+      "epoch": 0.313353115727003,
+      "grad_norm": 0.7002611756324768,
+      "learning_rate": 1.9999386012995554e-05,
+      "loss": 0.3522,
+      "step": 66
+    },
+    {
+      "epoch": 0.31810089020771515,
+      "grad_norm": 0.6202103495597839,
+      "learning_rate": 1.999861854691106e-05,
+      "loss": 0.3831,
+      "step": 67
+    },
+    {
+      "epoch": 0.3228486646884273,
+      "grad_norm": 0.44983768463134766,
+      "learning_rate": 1.9997544127378217e-05,
+      "loss": 0.37,
+      "step": 68
+    },
+    {
+      "epoch": 0.32759643916913944,
+      "grad_norm": 0.6840509176254272,
+      "learning_rate": 1.999616278738126e-05,
+      "loss": 0.3751,
+      "step": 69
+    },
+    {
+      "epoch": 0.3323442136498516,
+      "grad_norm": 0.416205495595932,
+      "learning_rate": 1.999447456932676e-05,
+      "loss": 0.3535,
+      "step": 70
+    },
+    {
+      "epoch": 0.3370919881305638,
+      "grad_norm": 0.5574557185173035,
+      "learning_rate": 1.9992479525042305e-05,
+      "loss": 0.3792,
+      "step": 71
+    },
+    {
+      "epoch": 0.34183976261127597,
+      "grad_norm": 0.46201279759407043,
+      "learning_rate": 1.9990177715774927e-05,
+      "loss": 0.3519,
+      "step": 72
+    },
+    {
+      "epoch": 0.34658753709198814,
+      "grad_norm": 0.4977426826953888,
+      "learning_rate": 1.9987569212189224e-05,
+      "loss": 0.3488,
+      "step": 73
+    },
+    {
+      "epoch": 0.3513353115727003,
+      "grad_norm": 0.45472055673599243,
+      "learning_rate": 1.9984654094365175e-05,
+      "loss": 0.3602,
+      "step": 74
+    },
+    {
+      "epoch": 0.3560830860534125,
+      "grad_norm": 0.4730567932128906,
+      "learning_rate": 1.9981432451795687e-05,
+      "loss": 0.3583,
+      "step": 75
+    },
+    {
+      "epoch": 0.3608308605341246,
+      "grad_norm": 0.49239611625671387,
+      "learning_rate": 1.997790438338385e-05,
+      "loss": 0.3474,
+      "step": 76
+    },
+    {
+      "epoch": 0.3655786350148368,
+      "grad_norm": 0.3924044370651245,
+      "learning_rate": 1.997406999743991e-05,
+      "loss": 0.3538,
+      "step": 77
+    },
+    {
+      "epoch": 0.37032640949554896,
+      "grad_norm": 0.4983470141887665,
+      "learning_rate": 1.996992941167792e-05,
+      "loss": 0.3699,
+      "step": 78
+    },
+    {
+      "epoch": 0.37507418397626113,
+      "grad_norm": 0.4259602129459381,
+      "learning_rate": 1.9965482753212154e-05,
+      "loss": 0.3529,
+      "step": 79
+    },
+    {
+      "epoch": 0.3798219584569733,
+      "grad_norm": 0.3953029215335846,
+      "learning_rate": 1.9960730158553186e-05,
+      "loss": 0.3514,
+      "step": 80
+    },
+    {
+      "epoch": 0.3845697329376855,
+      "grad_norm": 0.7401227951049805,
+      "learning_rate": 1.99556717736037e-05,
+      "loss": 0.3795,
+      "step": 81
+    },
+    {
+      "epoch": 0.3893175074183976,
+      "grad_norm": 2.0949933528900146,
+      "learning_rate": 1.9950307753654016e-05,
+      "loss": 0.3747,
+      "step": 82
+    },
+    {
+      "epoch": 0.3940652818991098,
+      "grad_norm": 0.48020580410957336,
+      "learning_rate": 1.9944638263377332e-05,
+      "loss": 0.3678,
+      "step": 83
+    },
+    {
+      "epoch": 0.39881305637982195,
+      "grad_norm": 0.4131617248058319,
+      "learning_rate": 1.9938663476824646e-05,
+      "loss": 0.3787,
+      "step": 84
+    },
+    {
+      "epoch": 0.4035608308605341,
+      "grad_norm": 0.4024046063423157,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 0.3402,
+      "step": 85
+    },
+    {
+      "epoch": 0.4083086053412463,
+      "grad_norm": 0.35955172777175903,
+      "learning_rate": 1.9925798757952003e-05,
+      "loss": 0.3605,
+      "step": 86
+    },
+    {
+      "epoch": 0.4130563798219585,
+      "grad_norm": 0.4338579773902893,
+      "learning_rate": 1.9918909220573588e-05,
+      "loss": 0.357,
+      "step": 87
+    },
+    {
+      "epoch": 0.41780415430267065,
+      "grad_norm": 0.3916882872581482,
+      "learning_rate": 1.991171517679013e-05,
+      "loss": 0.354,
+      "step": 88
+    },
+    {
+      "epoch": 0.42255192878338277,
+      "grad_norm": 0.39583539962768555,
+      "learning_rate": 1.9904216847455795e-05,
+      "loss": 0.3284,
+      "step": 89
+    },
+    {
+      "epoch": 0.42729970326409494,
+      "grad_norm": 0.43609434366226196,
+      "learning_rate": 1.9896414462766188e-05,
+      "loss": 0.3424,
+      "step": 90
+    },
+    {
+      "epoch": 0.4320474777448071,
+      "grad_norm": 0.4122212529182434,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.3386,
+      "step": 91
+    },
+    {
+      "epoch": 0.4367952522255193,
+      "grad_norm": 0.3249572515487671,
+      "learning_rate": 1.9879898494768093e-05,
+      "loss": 0.3157,
+      "step": 92
+    },
+    {
+      "epoch": 0.44154302670623147,
+      "grad_norm": 0.745229959487915,
+      "learning_rate": 1.9871185418492978e-05,
+      "loss": 0.3738,
+      "step": 93
+    },
+    {
+      "epoch": 0.44629080118694364,
+      "grad_norm": 0.39437487721443176,
+      "learning_rate": 1.9862169300913784e-05,
+      "loss": 0.3386,
+      "step": 94
+    },
+    {
+      "epoch": 0.45103857566765576,
+      "grad_norm": 0.3622061312198639,
+      "learning_rate": 1.985285041882158e-05,
+      "loss": 0.3234,
+      "step": 95
+    },
+    {
+      "epoch": 0.45578635014836794,
+      "grad_norm": 0.4053417146205902,
+      "learning_rate": 1.9843229058302192e-05,
+      "loss": 0.3608,
+      "step": 96
+    },
+    {
+      "epoch": 0.4605341246290801,
+      "grad_norm": 0.4641744792461395,
+      "learning_rate": 1.9833305514727396e-05,
+      "loss": 0.3431,
+      "step": 97
+    },
+    {
+      "epoch": 0.4652818991097923,
+      "grad_norm": 0.39851275086402893,
+      "learning_rate": 1.9823080092745878e-05,
+      "loss": 0.3531,
+      "step": 98
+    },
+    {
+      "epoch": 0.47002967359050446,
+      "grad_norm": 0.3545701205730438,
+      "learning_rate": 1.9812553106273848e-05,
+      "loss": 0.3842,
+      "step": 99
+    },
+    {
+      "epoch": 0.47477744807121663,
+      "grad_norm": 0.37058180570602417,
+      "learning_rate": 1.9801724878485438e-05,
+      "loss": 0.3407,
+      "step": 100
+    },
+    {
+      "epoch": 0.4795252225519288,
+      "grad_norm": 0.33017316460609436,
+      "learning_rate": 1.9790595741802757e-05,
+      "loss": 0.3369,
+      "step": 101
+    },
+    {
+      "epoch": 0.48427299703264093,
+      "grad_norm": 0.3639221787452698,
+      "learning_rate": 1.9779166037885692e-05,
+      "loss": 0.3427,
+      "step": 102
+    },
+    {
+      "epoch": 0.4890207715133531,
+      "grad_norm": 0.43298575282096863,
+      "learning_rate": 1.9767436117621416e-05,
+      "loss": 0.3693,
+      "step": 103
+    },
+    {
+      "epoch": 0.4937685459940653,
+      "grad_norm": 0.33556169271469116,
+      "learning_rate": 1.9755406341113622e-05,
+      "loss": 0.3266,
+      "step": 104
+    },
+    {
+      "epoch": 0.49851632047477745,
+      "grad_norm": 0.33984947204589844,
+      "learning_rate": 1.974307707767147e-05,
+      "loss": 0.3309,
+      "step": 105
+    },
+    {
+      "epoch": 0.5032640949554896,
+      "grad_norm": 0.35068896412849426,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.3516,
+      "step": 106
+    },
+    {
+      "epoch": 0.5080118694362018,
+      "grad_norm": 0.3809346556663513,
+      "learning_rate": 1.971752161317972e-05,
+      "loss": 0.3361,
+      "step": 107
+    },
+    {
+      "epoch": 0.512759643916914,
+      "grad_norm": 0.359453946352005,
+      "learning_rate": 1.9704296196672298e-05,
+      "loss": 0.3737,
+      "step": 108
+    },
+    {
+      "epoch": 0.5175074183976262,
+      "grad_norm": 0.3776707947254181,
+      "learning_rate": 1.969077286229078e-05,
+      "loss": 0.336,
+      "step": 109
+    },
+    {
+      "epoch": 0.5222551928783383,
+      "grad_norm": 0.37052029371261597,
+      "learning_rate": 1.9676952025195937e-05,
+      "loss": 0.3278,
+      "step": 110
+    },
+    {
+      "epoch": 0.5270029673590505,
+      "grad_norm": 0.37363845109939575,
+      "learning_rate": 1.966283410968174e-05,
+      "loss": 0.3481,
+      "step": 111
+    },
+    {
+      "epoch": 0.5317507418397626,
+      "grad_norm": 0.3355433940887451,
+      "learning_rate": 1.964841954916235e-05,
+      "loss": 0.3379,
+      "step": 112
+    },
+    {
+      "epoch": 0.5364985163204747,
+      "grad_norm": 0.3838210105895996,
+      "learning_rate": 1.9633708786158803e-05,
+      "loss": 0.3388,
+      "step": 113
+    },
+    {
+      "epoch": 0.5412462908011869,
+      "grad_norm": 0.3923501670360565,
+      "learning_rate": 1.9618702272285434e-05,
+      "loss": 0.3749,
+      "step": 114
+    },
+    {
+      "epoch": 0.5459940652818991,
+      "grad_norm": 0.4121781885623932,
+      "learning_rate": 1.9603400468236e-05,
+      "loss": 0.3149,
+      "step": 115
+    },
+    {
+      "epoch": 0.5507418397626113,
+      "grad_norm": 0.31165602803230286,
+      "learning_rate": 1.9587803843769547e-05,
+      "loss": 0.3162,
+      "step": 116
+    },
+    {
+      "epoch": 0.5554896142433234,
+      "grad_norm": 0.3426300883293152,
+      "learning_rate": 1.9571912877695995e-05,
+      "loss": 0.3408,
+      "step": 117
+    },
+    {
+      "epoch": 0.5602373887240356,
+      "grad_norm": 0.33053115010261536,
+      "learning_rate": 1.955572805786141e-05,
+      "loss": 0.3397,
+      "step": 118
+    },
+    {
+      "epoch": 0.5649851632047478,
+      "grad_norm": 0.30746808648109436,
+      "learning_rate": 1.9539249881133062e-05,
+      "loss": 0.3287,
+      "step": 119
+    },
+    {
+      "epoch": 0.56973293768546,
+      "grad_norm": 0.3441820442676544,
+      "learning_rate": 1.9522478853384154e-05,
+      "loss": 0.3225,
+      "step": 120
+    },
+    {
+      "epoch": 0.5744807121661721,
+      "grad_norm": 0.35982808470726013,
+      "learning_rate": 1.9505415489478293e-05,
+      "loss": 0.3429,
+      "step": 121
+    },
+    {
+      "epoch": 0.5792284866468843,
+      "grad_norm": 0.3274133801460266,
+      "learning_rate": 1.948806031325368e-05,
+      "loss": 0.3436,
+      "step": 122
+    },
+    {
+      "epoch": 0.5839762611275965,
+      "grad_norm": 0.38329532742500305,
+      "learning_rate": 1.9470413857507036e-05,
+      "loss": 0.3211,
+      "step": 123
+    },
+    {
+      "epoch": 0.5887240356083087,
+      "grad_norm": 0.38898247480392456,
+      "learning_rate": 1.945247666397725e-05,
+      "loss": 0.3409,
+      "step": 124
+    },
+    {
+      "epoch": 0.5934718100890207,
+      "grad_norm": 0.3356146216392517,
+      "learning_rate": 1.943424928332873e-05,
+      "loss": 0.3223,
+      "step": 125
+    },
+    {
+      "epoch": 0.5982195845697329,
+      "grad_norm": 0.33519861102104187,
+      "learning_rate": 1.9415732275134515e-05,
+      "loss": 0.3369,
+      "step": 126
+    },
+    {
+      "epoch": 0.5982195845697329,
+      "eval_loss": 0.15260468423366547,
+      "eval_runtime": 142.1665,
+      "eval_samples_per_second": 12.633,
+      "eval_steps_per_second": 0.795,
+      "step": 126
+    },
+    {
+      "epoch": 0.6029673590504451,
+      "grad_norm": 0.31465238332748413,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.3189,
+      "step": 127
+    },
+    {
+      "epoch": 0.6077151335311572,
+      "grad_norm": 0.33517467975616455,
+      "learning_rate": 1.937783165884092e-05,
+      "loss": 0.3525,
+      "step": 128
+    },
+    {
+      "epoch": 0.6124629080118694,
+      "grad_norm": 0.35138949751853943,
+      "learning_rate": 1.9358449214274763e-05,
+      "loss": 0.3466,
+      "step": 129
+    },
+    {
+      "epoch": 0.6172106824925816,
+      "grad_norm": 0.3277546167373657,
+      "learning_rate": 1.9338779469193638e-05,
+      "loss": 0.3304,
+      "step": 130
+    },
+    {
+      "epoch": 0.6219584569732938,
+      "grad_norm": 5.854161262512207,
+      "learning_rate": 1.931882302745057e-05,
+      "loss": 0.4189,
+      "step": 131
+    },
+    {
+      "epoch": 0.626706231454006,
+      "grad_norm": 0.3688313961029053,
+      "learning_rate": 1.9298580501700058e-05,
+      "loss": 0.3393,
+      "step": 132
+    },
+    {
+      "epoch": 0.6314540059347181,
+      "grad_norm": 0.3257688581943512,
+      "learning_rate": 1.9278052513379256e-05,
+      "loss": 0.331,
+      "step": 133
+    },
+    {
+      "epoch": 0.6362017804154303,
+      "grad_norm": 0.33901330828666687,
+      "learning_rate": 1.9257239692688907e-05,
+      "loss": 0.342,
+      "step": 134
+    },
+    {
+      "epoch": 0.6409495548961425,
+      "grad_norm": 0.3109529912471771,
+      "learning_rate": 1.9236142678573983e-05,
+      "loss": 0.3151,
+      "step": 135
+    },
+    {
+      "epoch": 0.6456973293768546,
+      "grad_norm": 0.34090420603752136,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.3293,
+      "step": 136
+    },
+    {
+      "epoch": 0.6504451038575668,
+      "grad_norm": 0.3669479787349701,
+      "learning_rate": 1.9193098669453532e-05,
+      "loss": 0.3574,
+      "step": 137
+    },
+    {
+      "epoch": 0.6551928783382789,
+      "grad_norm": 0.3427859842777252,
+      "learning_rate": 1.9171152995881257e-05,
+      "loss": 0.3352,
+      "step": 138
+    },
+    {
+      "epoch": 0.6599406528189911,
+      "grad_norm": 0.3781029284000397,
+      "learning_rate": 1.9148925771710347e-05,
+      "loss": 0.3384,
+      "step": 139
+    },
+    {
+      "epoch": 0.6646884272997032,
+      "grad_norm": 0.4394756257534027,
+      "learning_rate": 1.912641767930738e-05,
+      "loss": 0.3234,
+      "step": 140
+    },
+    {
+      "epoch": 0.6694362017804154,
+      "grad_norm": 0.3640480637550354,
+      "learning_rate": 1.9103629409661468e-05,
+      "loss": 0.3266,
+      "step": 141
+    },
+    {
+      "epoch": 0.6741839762611276,
+      "grad_norm": 0.32769304513931274,
+      "learning_rate": 1.908056166236305e-05,
+      "loss": 0.3255,
+      "step": 142
+    },
+    {
+      "epoch": 0.6789317507418398,
+      "grad_norm": 0.3409084379673004,
+      "learning_rate": 1.9057215145582418e-05,
+      "loss": 0.3285,
+      "step": 143
+    },
+    {
+      "epoch": 0.6836795252225519,
+      "grad_norm": 0.3296876549720764,
+      "learning_rate": 1.9033590576047967e-05,
+      "loss": 0.3197,
+      "step": 144
+    },
+    {
+      "epoch": 0.6884272997032641,
+      "grad_norm": 0.3788384199142456,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.33,
+      "step": 145
+    },
+    {
+      "epoch": 0.6931750741839763,
+      "grad_norm": 0.31414154171943665,
+      "learning_rate": 1.898551018828944e-05,
+      "loss": 0.313,
+      "step": 146
+    },
+    {
+      "epoch": 0.6979228486646885,
+      "grad_norm": 0.4816839396953583,
+      "learning_rate": 1.8961055846113358e-05,
+      "loss": 0.3407,
+      "step": 147
+    },
+    {
+      "epoch": 0.7026706231454006,
+      "grad_norm": 0.3418005406856537,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 0.3311,
+      "step": 148
+    },
+    {
+      "epoch": 0.7074183976261128,
+      "grad_norm": 0.31916749477386475,
+      "learning_rate": 1.8911322618835393e-05,
+      "loss": 0.3042,
+      "step": 149
+    },
+    {
+      "epoch": 0.712166172106825,
+      "grad_norm": 1.1523184776306152,
+      "learning_rate": 1.888604526052299e-05,
+      "loss": 0.3218,
+      "step": 150
+    },
+    {
+      "epoch": 0.716913946587537,
+      "grad_norm": 0.2973329424858093,
+      "learning_rate": 1.8860495104301346e-05,
+      "loss": 0.3061,
+      "step": 151
+    },
+    {
+      "epoch": 0.7216617210682492,
+      "grad_norm": 0.3566143214702606,
+      "learning_rate": 1.8834672934549677e-05,
+      "loss": 0.3287,
+      "step": 152
+    },
+    {
+      "epoch": 0.7264094955489614,
+      "grad_norm": 0.3308376967906952,
+      "learning_rate": 1.8808579543997892e-05,
+      "loss": 0.3034,
+      "step": 153
+    },
+    {
+      "epoch": 0.7311572700296736,
+      "grad_norm": 0.33520743250846863,
+      "learning_rate": 1.8782215733702286e-05,
+      "loss": 0.3296,
+      "step": 154
+    },
+    {
+      "epoch": 0.7359050445103857,
+      "grad_norm": 0.3926364481449127,
+      "learning_rate": 1.8755582313020912e-05,
+      "loss": 0.3135,
+      "step": 155
+    },
+    {
+      "epoch": 0.7406528189910979,
+      "grad_norm": 0.37003567814826965,
+      "learning_rate": 1.8728680099588748e-05,
+      "loss": 0.3455,
+      "step": 156
+    },
+    {
+      "epoch": 0.7454005934718101,
+      "grad_norm": 0.31512436270713806,
+      "learning_rate": 1.870150991929261e-05,
+      "loss": 0.3146,
+      "step": 157
+    },
+    {
+      "epoch": 0.7501483679525223,
+      "grad_norm": 0.35992729663848877,
+      "learning_rate": 1.867407260624578e-05,
+      "loss": 0.3138,
+      "step": 158
+    },
+    {
+      "epoch": 0.7548961424332344,
+      "grad_norm": 0.33734387159347534,
+      "learning_rate": 1.864636900276241e-05,
+      "loss": 0.3453,
+      "step": 159
+    },
+    {
+      "epoch": 0.7596439169139466,
+      "grad_norm": 0.403726726770401,
+      "learning_rate": 1.8618399959331642e-05,
+      "loss": 0.3176,
+      "step": 160
+    },
+    {
+      "epoch": 0.7643916913946588,
+      "grad_norm": 0.33617129921913147,
+      "learning_rate": 1.8590166334591533e-05,
+      "loss": 0.3235,
+      "step": 161
+    },
+    {
+      "epoch": 0.769139465875371,
+      "grad_norm": 0.3692370355129242,
+      "learning_rate": 1.8561668995302668e-05,
+      "loss": 0.3167,
+      "step": 162
+    },
+    {
+      "epoch": 0.7738872403560831,
+      "grad_norm": 0.31387221813201904,
+      "learning_rate": 1.8532908816321557e-05,
+      "loss": 0.2978,
+      "step": 163
+    },
+    {
+      "epoch": 0.7786350148367952,
+      "grad_norm": 0.39496850967407227,
+      "learning_rate": 1.850388668057379e-05,
+      "loss": 0.3167,
+      "step": 164
+    },
+    {
+      "epoch": 0.7833827893175074,
+      "grad_norm": 0.29015660285949707,
+      "learning_rate": 1.8474603479026912e-05,
+      "loss": 0.3111,
+      "step": 165
+    },
+    {
+      "epoch": 0.7881305637982196,
+      "grad_norm": 0.4949202835559845,
+      "learning_rate": 1.844506011066308e-05,
+      "loss": 0.3231,
+      "step": 166
+    },
+    {
+      "epoch": 0.7928783382789317,
+      "grad_norm": 0.3161013126373291,
+      "learning_rate": 1.841525748245147e-05,
+      "loss": 0.3235,
+      "step": 167
+    },
+    {
+      "epoch": 0.7976261127596439,
+      "grad_norm": 0.3269205093383789,
+      "learning_rate": 1.8385196509320424e-05,
+      "loss": 0.3302,
+      "step": 168
+    },
+    {
+      "epoch": 0.8023738872403561,
+      "grad_norm": 0.2890471816062927,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 0.297,
+      "step": 169
+    },
+    {
+      "epoch": 0.8071216617210683,
+      "grad_norm": 0.3379496932029724,
+      "learning_rate": 1.8324303227640472e-05,
+      "loss": 0.3032,
+      "step": 170
+    },
+    {
+      "epoch": 0.8118694362017804,
+      "grad_norm": 0.3012542128562927,
+      "learning_rate": 1.8293472788490096e-05,
+      "loss": 0.3119,
+      "step": 171
+    },
+    {
+      "epoch": 0.8166172106824926,
+      "grad_norm": 0.31910914182662964,
+      "learning_rate": 1.826238774315995e-05,
+      "loss": 0.3249,
+      "step": 172
+    },
+    {
+      "epoch": 0.8213649851632048,
+      "grad_norm": 0.2994840741157532,
+      "learning_rate": 1.8231049045948054e-05,
+      "loss": 0.3106,
+      "step": 173
+    },
+    {
+      "epoch": 0.826112759643917,
+      "grad_norm": 0.31799837946891785,
+      "learning_rate": 1.8199457658939425e-05,
+      "loss": 0.3109,
+      "step": 174
+    },
+    {
+      "epoch": 0.8308605341246291,
+      "grad_norm": 0.3020702302455902,
+      "learning_rate": 1.816761455197657e-05,
+      "loss": 0.3016,
+      "step": 175
+    },
+    {
+      "epoch": 0.8356083086053413,
+      "grad_norm": 0.33007511496543884,
+      "learning_rate": 1.8135520702629677e-05,
+      "loss": 0.3326,
+      "step": 176
+    },
+    {
+      "epoch": 0.8403560830860534,
+      "grad_norm": 0.34143343567848206,
+      "learning_rate": 1.8103177096166632e-05,
+      "loss": 0.3245,
+      "step": 177
+    },
+    {
+      "epoch": 0.8451038575667655,
+      "grad_norm": 0.325300008058548,
+      "learning_rate": 1.8070584725522763e-05,
+      "loss": 0.32,
+      "step": 178
+    },
+    {
+      "epoch": 0.8498516320474777,
+      "grad_norm": 0.38607487082481384,
+      "learning_rate": 1.803774459127034e-05,
+      "loss": 0.289,
+      "step": 179
+    },
+    {
+      "epoch": 0.8545994065281899,
+      "grad_norm": 0.31634339690208435,
+      "learning_rate": 1.8004657701587893e-05,
+      "loss": 0.3185,
+      "step": 180
+    },
+    {
+      "epoch": 0.8593471810089021,
+      "grad_norm": 0.32501840591430664,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.3291,
+      "step": 181
+    },
+    {
+      "epoch": 0.8640949554896142,
+      "grad_norm": 0.3348029553890228,
+      "learning_rate": 1.7937747726492256e-05,
+      "loss": 0.324,
+      "step": 182
+    },
+    {
+      "epoch": 0.8688427299703264,
+      "grad_norm": 0.34350311756134033,
+      "learning_rate": 1.7903926695187595e-05,
+      "loss": 0.3351,
+      "step": 183
+    },
+    {
+      "epoch": 0.8735905044510386,
+      "grad_norm": 0.34770363569259644,
+      "learning_rate": 1.7869863016606893e-05,
+      "loss": 0.3368,
+      "step": 184
+    },
+    {
+      "epoch": 0.8783382789317508,
+      "grad_norm": 0.40538617968559265,
+      "learning_rate": 1.783555773649097e-05,
+      "loss": 0.3027,
+      "step": 185
+    },
+    {
+      "epoch": 0.8830860534124629,
+      "grad_norm": 0.37002649903297424,
+      "learning_rate": 1.7801011907997728e-05,
+      "loss": 0.3296,
+      "step": 186
+    },
+    {
+      "epoch": 0.8878338278931751,
+      "grad_norm": 0.3094744384288788,
+      "learning_rate": 1.7766226591669787e-05,
+      "loss": 0.3211,
+      "step": 187
+    },
+    {
+      "epoch": 0.8925816023738873,
+      "grad_norm": 0.3551942706108093,
+      "learning_rate": 1.773120285540195e-05,
+      "loss": 0.315,
+      "step": 188
+    },
+    {
+      "epoch": 0.8973293768545995,
+      "grad_norm": 0.3153332471847534,
+      "learning_rate": 1.7695941774408424e-05,
+      "loss": 0.312,
+      "step": 189
+    },
+    {
+      "epoch": 0.9020771513353115,
+      "grad_norm": 0.30479609966278076,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.3176,
+      "step": 190
+    },
+    {
+      "epoch": 0.9068249258160237,
+      "grad_norm": 0.3118721842765808,
+      "learning_rate": 1.7624711915499767e-05,
+      "loss": 0.3366,
+      "step": 191
+    },
+    {
+      "epoch": 0.9115727002967359,
+      "grad_norm": 0.3304102122783661,
+      "learning_rate": 1.75887453243118e-05,
+      "loss": 0.3321,
+      "step": 192
+    },
+    {
+      "epoch": 0.916320474777448,
+      "grad_norm": 0.29333484172821045,
+      "learning_rate": 1.755254576178535e-05,
+      "loss": 0.306,
+      "step": 193
+    },
+    {
+      "epoch": 0.9210682492581602,
+      "grad_norm": 0.34330320358276367,
+      "learning_rate": 1.7516114339231984e-05,
+      "loss": 0.3173,
+      "step": 194
+    },
+    {
+      "epoch": 0.9258160237388724,
+      "grad_norm": 0.28864824771881104,
+      "learning_rate": 1.747945217508129e-05,
+      "loss": 0.2955,
+      "step": 195
+    },
+    {
+      "epoch": 0.9305637982195846,
+      "grad_norm": 0.32548072934150696,
+      "learning_rate": 1.7442560394846518e-05,
+      "loss": 0.3284,
+      "step": 196
+    },
+    {
+      "epoch": 0.9353115727002967,
+      "grad_norm": 0.3424006402492523,
+      "learning_rate": 1.740544013109005e-05,
+      "loss": 0.315,
+      "step": 197
+    },
+    {
+      "epoch": 0.9400593471810089,
+      "grad_norm": 0.31073182821273804,
+      "learning_rate": 1.73680925233886e-05,
+      "loss": 0.3186,
+      "step": 198
+    },
+    {
+      "epoch": 0.9448071216617211,
+      "grad_norm": 0.37291258573532104,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 0.2982,
+      "step": 199
+    },
+    {
+      "epoch": 0.9495548961424333,
+      "grad_norm": 0.2813059091567993,
+      "learning_rate": 1.7292719869319295e-05,
+      "loss": 0.3189,
+      "step": 200
+    },
+    {
+      "epoch": 0.9543026706231454,
+      "grad_norm": 0.297116219997406,
+      "learning_rate": 1.72546971368607e-05,
+      "loss": 0.2888,
+      "step": 201
+    },
+    {
+      "epoch": 0.9590504451038576,
+      "grad_norm": 0.3253256380558014,
+      "learning_rate": 1.7216451688204623e-05,
+      "loss": 0.327,
+      "step": 202
+    },
+    {
+      "epoch": 0.9637982195845697,
+      "grad_norm": 0.3983827233314514,
+      "learning_rate": 1.717798469747049e-05,
+      "loss": 0.309,
+      "step": 203
+    },
+    {
+      "epoch": 0.9685459940652819,
+      "grad_norm": 0.30336683988571167,
+      "learning_rate": 1.7139297345578992e-05,
+      "loss": 0.3222,
+      "step": 204
+    },
+    {
+      "epoch": 0.973293768545994,
+      "grad_norm": 0.3853195309638977,
+      "learning_rate": 1.7100390820215805e-05,
+      "loss": 0.3182,
+      "step": 205
+    },
+    {
+      "epoch": 0.9780415430267062,
+      "grad_norm": 0.3312664031982422,
+      "learning_rate": 1.7061266315795146e-05,
+      "loss": 0.2972,
+      "step": 206
+    },
+    {
+      "epoch": 0.9827893175074184,
+      "grad_norm": 0.3694183826446533,
+      "learning_rate": 1.7021925033423096e-05,
+      "loss": 0.3177,
+      "step": 207
+    },
+    {
+      "epoch": 0.9875370919881306,
+      "grad_norm": 0.3218733072280884,
+      "learning_rate": 1.698236818086073e-05,
+      "loss": 0.304,
+      "step": 208
+    },
+    {
+      "epoch": 0.9922848664688427,
+      "grad_norm": 0.33860743045806885,
+      "learning_rate": 1.694259697248704e-05,
+      "loss": 0.3031,
+      "step": 209
+    },
+    {
+      "epoch": 0.9970326409495549,
+      "grad_norm": 0.42556554079055786,
+      "learning_rate": 1.690261262926165e-05,
+      "loss": 0.3196,
+      "step": 210
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.38205158710479736,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.2881,
+      "step": 211
+    },
+    {
+      "epoch": 1.004747774480712,
+      "grad_norm": 0.36370348930358887,
+      "learning_rate": 1.682200945477235e-05,
+      "loss": 0.3082,
+      "step": 212
+    },
+    {
+      "epoch": 1.0094955489614243,
+      "grad_norm": 0.3192894160747528,
+      "learning_rate": 1.6781393097992512e-05,
+      "loss": 0.3233,
+      "step": 213
+    },
+    {
+      "epoch": 1.0142433234421364,
+      "grad_norm": 0.34595000743865967,
+      "learning_rate": 1.6740568555253153e-05,
+      "loss": 0.2932,
+      "step": 214
+    },
+    {
+      "epoch": 1.0189910979228487,
+      "grad_norm": 0.32576438784599304,
+      "learning_rate": 1.669953707985084e-05,
+      "loss": 0.2944,
+      "step": 215
+    },
+    {
+      "epoch": 1.0237388724035608,
+      "grad_norm": 0.3424221873283386,
+      "learning_rate": 1.6658299931434857e-05,
+      "loss": 0.305,
+      "step": 216
+    },
+    {
+      "epoch": 1.028486646884273,
+      "grad_norm": 0.32766616344451904,
+      "learning_rate": 1.6616858375968596e-05,
+      "loss": 0.3266,
+      "step": 217
+    },
+    {
+      "epoch": 1.0332344213649851,
+      "grad_norm": 0.34646332263946533,
+      "learning_rate": 1.657521368569064e-05,
+      "loss": 0.316,
+      "step": 218
+    },
+    {
+      "epoch": 1.0379821958456974,
+      "grad_norm": 0.30172574520111084,
+      "learning_rate": 1.6533367139075732e-05,
+      "loss": 0.2973,
+      "step": 219
+    },
+    {
+      "epoch": 1.0427299703264095,
+      "grad_norm": 0.33457738161087036,
+      "learning_rate": 1.649132002079552e-05,
+      "loss": 0.3015,
+      "step": 220
+    },
+    {
+      "epoch": 1.0474777448071217,
+      "grad_norm": 0.32709312438964844,
+      "learning_rate": 1.6449073621679128e-05,
+      "loss": 0.2967,
+      "step": 221
+    },
+    {
+      "epoch": 1.0522255192878338,
+      "grad_norm": 0.32702985405921936,
+      "learning_rate": 1.6406629238673507e-05,
+      "loss": 0.3375,
+      "step": 222
+    },
+    {
+      "epoch": 1.056973293768546,
+      "grad_norm": 0.3030819296836853,
+      "learning_rate": 1.6363988174803638e-05,
+      "loss": 0.3171,
+      "step": 223
+    },
+    {
+      "epoch": 1.0617210682492582,
+      "grad_norm": 0.3053749203681946,
+      "learning_rate": 1.632115173913252e-05,
+      "loss": 0.3188,
+      "step": 224
+    },
+    {
+      "epoch": 1.0664688427299702,
+      "grad_norm": 0.33132317662239075,
+      "learning_rate": 1.627812124672099e-05,
+      "loss": 0.325,
+      "step": 225
+    },
+    {
+      "epoch": 1.0712166172106825,
+      "grad_norm": 0.32221683859825134,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.3249,
+      "step": 226
+    },
+    {
+      "epoch": 1.0759643916913946,
+      "grad_norm": 0.32629886269569397,
+      "learning_rate": 1.619148338166677e-05,
+      "loss": 0.308,
+      "step": 227
+    },
+    {
+      "epoch": 1.0807121661721069,
+      "grad_norm": 0.31524035334587097,
+      "learning_rate": 1.614787866877066e-05,
+      "loss": 0.304,
+      "step": 228
+    },
+    {
+      "epoch": 1.085459940652819,
+      "grad_norm": 0.33473050594329834,
+      "learning_rate": 1.6104085218545633e-05,
+      "loss": 0.3222,
+      "step": 229
+    },
+    {
+      "epoch": 1.0902077151335312,
+      "grad_norm": 0.28698474168777466,
+      "learning_rate": 1.6060104375432476e-05,
+      "loss": 0.3057,
+      "step": 230
+    },
+    {
+      "epoch": 1.0949554896142433,
+      "grad_norm": 0.2982139587402344,
+      "learning_rate": 1.601593748962485e-05,
+      "loss": 0.3074,
+      "step": 231
+    },
+    {
+      "epoch": 1.0997032640949556,
+      "grad_norm": 0.29852068424224854,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.3152,
+      "step": 232
+    },
+    {
+      "epoch": 1.1044510385756676,
+      "grad_norm": 0.28795862197875977,
+      "learning_rate": 1.5927051019216428e-05,
+      "loss": 0.3084,
+      "step": 233
+    },
+    {
+      "epoch": 1.10919881305638,
+      "grad_norm": 0.27636635303497314,
+      "learning_rate": 1.588233416339345e-05,
+      "loss": 0.3079,
+      "step": 234
+    },
+    {
+      "epoch": 1.113946587537092,
+      "grad_norm": 0.3473345637321472,
+      "learning_rate": 1.5837436722347902e-05,
+      "loss": 0.2836,
+      "step": 235
+    },
+    {
+      "epoch": 1.1186943620178043,
+      "grad_norm": 0.3350068926811218,
+      "learning_rate": 1.5792360074412612e-05,
+      "loss": 0.3066,
+      "step": 236
+    },
+    {
+      "epoch": 1.1234421364985163,
+      "grad_norm": 0.33414971828460693,
+      "learning_rate": 1.5747105603422013e-05,
+      "loss": 0.3082,
+      "step": 237
+    },
+    {
+      "epoch": 1.1281899109792284,
+      "grad_norm": 0.32059019804000854,
+      "learning_rate": 1.570167469866962e-05,
+      "loss": 0.3103,
+      "step": 238
+    },
+    {
+      "epoch": 1.1329376854599407,
+      "grad_norm": 0.32460328936576843,
+      "learning_rate": 1.5656068754865388e-05,
+      "loss": 0.3151,
+      "step": 239
+    },
+    {
+      "epoch": 1.1376854599406527,
+      "grad_norm": 0.3252885341644287,
+      "learning_rate": 1.561028917209291e-05,
+      "loss": 0.3248,
+      "step": 240
+    },
+    {
+      "epoch": 1.142433234421365,
+      "grad_norm": 0.3324680030345917,
+      "learning_rate": 1.5564337355766412e-05,
+      "loss": 0.3119,
+      "step": 241
+    },
+    {
+      "epoch": 1.147181008902077,
+      "grad_norm": 0.3315082788467407,
+      "learning_rate": 1.551821471658763e-05,
+      "loss": 0.3094,
+      "step": 242
+    },
+    {
+      "epoch": 1.1519287833827894,
+      "grad_norm": 0.3459841310977936,
+      "learning_rate": 1.5471922670502472e-05,
+      "loss": 0.2982,
+      "step": 243
+    },
+    {
+      "epoch": 1.1566765578635014,
+      "grad_norm": 0.30599355697631836,
+      "learning_rate": 1.5425462638657597e-05,
+      "loss": 0.2802,
+      "step": 244
+    },
+    {
+      "epoch": 1.1614243323442137,
+      "grad_norm": 0.3451800048351288,
+      "learning_rate": 1.5378836047356725e-05,
+      "loss": 0.3065,
+      "step": 245
+    },
+    {
+      "epoch": 1.1661721068249258,
+      "grad_norm": 0.28921040892601013,
+      "learning_rate": 1.5332044328016916e-05,
+      "loss": 0.2935,
+      "step": 246
+    },
+    {
+      "epoch": 1.170919881305638,
+      "grad_norm": 0.3126339912414551,
+      "learning_rate": 1.5285088917124555e-05,
+      "loss": 0.2794,
+      "step": 247
+    },
+    {
+      "epoch": 1.1756676557863501,
+      "grad_norm": 0.33224689960479736,
+      "learning_rate": 1.5237971256191325e-05,
+      "loss": 0.3068,
+      "step": 248
+    },
+    {
+      "epoch": 1.1804154302670624,
+      "grad_norm": 0.33340543508529663,
+      "learning_rate": 1.5190692791709891e-05,
+      "loss": 0.2895,
+      "step": 249
+    },
+    {
+      "epoch": 1.1851632047477745,
+      "grad_norm": 0.3247314989566803,
+      "learning_rate": 1.5143254975109538e-05,
+      "loss": 0.3005,
+      "step": 250
+    },
+    {
+      "epoch": 1.1899109792284865,
+      "grad_norm": 0.3434915542602539,
+      "learning_rate": 1.5095659262711588e-05,
+      "loss": 0.2991,
+      "step": 251
+    },
+    {
+      "epoch": 1.1946587537091988,
+      "grad_norm": 0.28737980127334595,
+      "learning_rate": 1.5047907115684695e-05,
+      "loss": 0.2603,
+      "step": 252
+    },
+    {
+      "epoch": 1.1946587537091988,
+      "eval_loss": 0.15092316269874573,
+      "eval_runtime": 136.3285,
+      "eval_samples_per_second": 13.174,
+      "eval_steps_per_second": 0.829,
+      "step": 252
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 630,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 126,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.752167478826369e+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:c2a1de8ff8b83c1b8fdc0145433eb0cae97b6de3423746857e71125210fc6a17
+size 8913

zero_to_fp32.py

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