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 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 32,
+  "model_type": "qwen2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 640000,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151680
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

latest

@@ -0,0 +1 @@
+global_step240

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c00e9b28bc305c122af9634e86e09c84f9995e44e3cdc1c13a547b9e29d9bf
+size 4961126848

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e89014ade8bbada3a042494c6c761a65b63448323718b153d5552b91ec7a0a
+size 4962282376

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287c43d4896f7c432b70c31c20c464db6a6b623f9de7971a124b55a9f73085e6
+size 4079316352

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da7b6c624d99256d91ea9d7aa58dd2c2dea5231aea3cef13747c0657151eee8
+size 1242562688

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 15245238272
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f92cf63e0989759370d24108b469c492c12202403f036015307ce49f12cedc
+size 16389

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed40a0a4e9f365d2c6cc004d97e6705894eba46c8be4c160c1455bc3062dee1
+size 16389

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d688b304d19c260b5cfa471535ed51d7e1d60b3a0d0159dfd1a04b87904a9f42
+size 16389

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9967425ebcaee80d9b518fa0244d52f739b1b983d87cda71d5fede0c073e9d3b
+size 16389

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:469900fd39c667ffbd49c3c407c0ba317a1e9f5f9339a99b5d38423b7d0ce6d4
+size 16389

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124688471ff2a6e80f2fcefedbf741fb18d08dd539d5bd07a52e81be545142a5
+size 16389

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e69f1ced9f992a72c948698e5eb06088610788988cdb2fdbdd624e064319d60
+size 16389

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a376268a55d6ee10c371c06aa952334c4c6a1af9ea2d71b1951a57367a0c6722
+size 16389

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964424132341e61a8b3c799f8896b8d80151109e53785ed2435c3d0752ebd9d4
+size 1465

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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "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 +1,1714 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9968847352024922,
+  "eval_steps": 500,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004153686396677051,
+      "grad_norm": 0.46519723534584045,
+      "learning_rate": 0.0,
+      "loss": 2.1543,
+      "step": 1
+    },
+    {
+      "epoch": 0.008307372793354102,
+      "grad_norm": 0.43996185064315796,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.1152,
+      "step": 2
+    },
+    {
+      "epoch": 0.012461059190031152,
+      "grad_norm": 0.4474555253982544,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.187,
+      "step": 3
+    },
+    {
+      "epoch": 0.016614745586708203,
+      "grad_norm": 0.45517489314079285,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.1881,
+      "step": 4
+    },
+    {
+      "epoch": 0.020768431983385256,
+      "grad_norm": 0.4221073389053345,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.0898,
+      "step": 5
+    },
+    {
+      "epoch": 0.024922118380062305,
+      "grad_norm": 0.4369853734970093,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.1472,
+      "step": 6
+    },
+    {
+      "epoch": 0.029075804776739357,
+      "grad_norm": 0.4024302065372467,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 2.1454,
+      "step": 7
+    },
+    {
+      "epoch": 0.033229491173416406,
+      "grad_norm": 0.383690744638443,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 2.0846,
+      "step": 8
+    },
+    {
+      "epoch": 0.037383177570093455,
+      "grad_norm": 0.36159613728523254,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 2.1333,
+      "step": 9
+    },
+    {
+      "epoch": 0.04153686396677051,
+      "grad_norm": 0.3597932755947113,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 2.1546,
+      "step": 10
+    },
+    {
+      "epoch": 0.04569055036344756,
+      "grad_norm": 0.39668431878089905,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.1261,
+      "step": 11
+    },
+    {
+      "epoch": 0.04984423676012461,
+      "grad_norm": 0.4318128824234009,
+      "learning_rate": 2.2e-06,
+      "loss": 2.1235,
+      "step": 12
+    },
+    {
+      "epoch": 0.05399792315680166,
+      "grad_norm": 0.4326289892196655,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 2.1045,
+      "step": 13
+    },
+    {
+      "epoch": 0.058151609553478714,
+      "grad_norm": 0.6398888826370239,
+      "learning_rate": 2.6e-06,
+      "loss": 2.1559,
+      "step": 14
+    },
+    {
+      "epoch": 0.06230529595015576,
+      "grad_norm": 0.3349069356918335,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 2.1339,
+      "step": 15
+    },
+    {
+      "epoch": 0.06645898234683281,
+      "grad_norm": 0.3410353660583496,
+      "learning_rate": 3e-06,
+      "loss": 2.0821,
+      "step": 16
+    },
+    {
+      "epoch": 0.07061266874350987,
+      "grad_norm": 0.35577717423439026,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 2.1912,
+      "step": 17
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 0.3483312427997589,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 2.161,
+      "step": 18
+    },
+    {
+      "epoch": 0.07892004153686397,
+      "grad_norm": 0.33657440543174744,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 2.1798,
+      "step": 19
+    },
+    {
+      "epoch": 0.08307372793354102,
+      "grad_norm": 0.3735242486000061,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.1088,
+      "step": 20
+    },
+    {
+      "epoch": 0.08722741433021806,
+      "grad_norm": 0.46339651942253113,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.1467,
+      "step": 21
+    },
+    {
+      "epoch": 0.09138110072689512,
+      "grad_norm": 0.3805930018424988,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 2.1484,
+      "step": 22
+    },
+    {
+      "epoch": 0.09553478712357218,
+      "grad_norm": 0.3923945724964142,
+      "learning_rate": 4.4e-06,
+      "loss": 2.1679,
+      "step": 23
+    },
+    {
+      "epoch": 0.09968847352024922,
+      "grad_norm": 0.41755327582359314,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 2.1469,
+      "step": 24
+    },
+    {
+      "epoch": 0.10384215991692627,
+      "grad_norm": 0.3602828085422516,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 2.2024,
+      "step": 25
+    },
+    {
+      "epoch": 0.10799584631360332,
+      "grad_norm": 0.3939920663833618,
+      "learning_rate": 5e-06,
+      "loss": 2.1467,
+      "step": 26
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "grad_norm": 0.40471377968788147,
+      "learning_rate": 5.2e-06,
+      "loss": 2.1984,
+      "step": 27
+    },
+    {
+      "epoch": 0.11630321910695743,
+      "grad_norm": 0.34732070565223694,
+      "learning_rate": 5.400000000000001e-06,
+      "loss": 2.2007,
+      "step": 28
+    },
+    {
+      "epoch": 0.12045690550363447,
+      "grad_norm": 0.3753240406513214,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 2.1163,
+      "step": 29
+    },
+    {
+      "epoch": 0.12461059190031153,
+      "grad_norm": 0.39350414276123047,
+      "learning_rate": 5.8e-06,
+      "loss": 2.144,
+      "step": 30
+    },
+    {
+      "epoch": 0.12876427829698858,
+      "grad_norm": 0.3573162257671356,
+      "learning_rate": 6e-06,
+      "loss": 2.1117,
+      "step": 31
+    },
+    {
+      "epoch": 0.13291796469366562,
+      "grad_norm": 0.36146262288093567,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 2.1521,
+      "step": 32
+    },
+    {
+      "epoch": 0.13707165109034267,
+      "grad_norm": 0.43568095564842224,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 2.1501,
+      "step": 33
+    },
+    {
+      "epoch": 0.14122533748701974,
+      "grad_norm": 0.45428919792175293,
+      "learning_rate": 6.600000000000001e-06,
+      "loss": 2.1042,
+      "step": 34
+    },
+    {
+      "epoch": 0.14537902388369678,
+      "grad_norm": 0.5019702315330505,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 2.1406,
+      "step": 35
+    },
+    {
+      "epoch": 0.14953271028037382,
+      "grad_norm": 0.3149745762348175,
+      "learning_rate": 7e-06,
+      "loss": 2.1663,
+      "step": 36
+    },
+    {
+      "epoch": 0.1536863966770509,
+      "grad_norm": 0.4449986219406128,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 2.1463,
+      "step": 37
+    },
+    {
+      "epoch": 0.15784008307372793,
+      "grad_norm": 0.44423943758010864,
+      "learning_rate": 7.4e-06,
+      "loss": 2.1362,
+      "step": 38
+    },
+    {
+      "epoch": 0.16199376947040497,
+      "grad_norm": 0.33646464347839355,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 2.1198,
+      "step": 39
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 0.32996314764022827,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 2.1126,
+      "step": 40
+    },
+    {
+      "epoch": 0.1703011422637591,
+      "grad_norm": 0.4265682101249695,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.1239,
+      "step": 41
+    },
+    {
+      "epoch": 0.17445482866043613,
+      "grad_norm": 0.4570807218551636,
+      "learning_rate": 8.2e-06,
+      "loss": 2.1687,
+      "step": 42
+    },
+    {
+      "epoch": 0.1786085150571132,
+      "grad_norm": 0.41856175661087036,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 2.1363,
+      "step": 43
+    },
+    {
+      "epoch": 0.18276220145379024,
+      "grad_norm": 0.3138597905635834,
+      "learning_rate": 8.6e-06,
+      "loss": 2.0941,
+      "step": 44
+    },
+    {
+      "epoch": 0.18691588785046728,
+      "grad_norm": 0.4337351322174072,
+      "learning_rate": 8.8e-06,
+      "loss": 2.1599,
+      "step": 45
+    },
+    {
+      "epoch": 0.19106957424714435,
+      "grad_norm": 0.49772173166275024,
+      "learning_rate": 9e-06,
+      "loss": 2.1445,
+      "step": 46
+    },
+    {
+      "epoch": 0.1952232606438214,
+      "grad_norm": 0.3833214044570923,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 2.1087,
+      "step": 47
+    },
+    {
+      "epoch": 0.19937694704049844,
+      "grad_norm": 0.3490073084831238,
+      "learning_rate": 9.4e-06,
+      "loss": 2.0739,
+      "step": 48
+    },
+    {
+      "epoch": 0.2035306334371755,
+      "grad_norm": 0.5244693756103516,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 2.1576,
+      "step": 49
+    },
+    {
+      "epoch": 0.20768431983385255,
+      "grad_norm": 0.6005993485450745,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 2.0999,
+      "step": 50
+    },
+    {
+      "epoch": 0.2118380062305296,
+      "grad_norm": 0.6089114546775818,
+      "learning_rate": 1e-05,
+      "loss": 2.1272,
+      "step": 51
+    },
+    {
+      "epoch": 0.21599169262720663,
+      "grad_norm": 0.40243008732795715,
+      "learning_rate": 9.999316524962347e-06,
+      "loss": 2.1378,
+      "step": 52
+    },
+    {
+      "epoch": 0.2201453790238837,
+      "grad_norm": 0.3728896379470825,
+      "learning_rate": 9.99726628670463e-06,
+      "loss": 2.1483,
+      "step": 53
+    },
+    {
+      "epoch": 0.22429906542056074,
+      "grad_norm": 0.47435319423675537,
+      "learning_rate": 9.993849845741525e-06,
+      "loss": 2.1246,
+      "step": 54
+    },
+    {
+      "epoch": 0.2284527518172378,
+      "grad_norm": 0.47093838453292847,
+      "learning_rate": 9.989068136093873e-06,
+      "loss": 2.1396,
+      "step": 55
+    },
+    {
+      "epoch": 0.23260643821391486,
+      "grad_norm": 0.5783659815788269,
+      "learning_rate": 9.98292246503335e-06,
+      "loss": 2.0856,
+      "step": 56
+    },
+    {
+      "epoch": 0.2367601246105919,
+      "grad_norm": 0.4810788929462433,
+      "learning_rate": 9.975414512725058e-06,
+      "loss": 2.0802,
+      "step": 57
+    },
+    {
+      "epoch": 0.24091381100726894,
+      "grad_norm": 0.45532462000846863,
+      "learning_rate": 9.966546331768192e-06,
+      "loss": 2.0967,
+      "step": 58
+    },
+    {
+      "epoch": 0.245067497403946,
+      "grad_norm": 0.39205724000930786,
+      "learning_rate": 9.956320346634877e-06,
+      "loss": 2.164,
+      "step": 59
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 0.4362233281135559,
+      "learning_rate": 9.944739353007344e-06,
+      "loss": 2.1157,
+      "step": 60
+    },
+    {
+      "epoch": 0.2533748701973001,
+      "grad_norm": 0.43169429898262024,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 2.1002,
+      "step": 61
+    },
+    {
+      "epoch": 0.25752855659397716,
+      "grad_norm": 0.3520335257053375,
+      "learning_rate": 9.917525374361913e-06,
+      "loss": 2.1048,
+      "step": 62
+    },
+    {
+      "epoch": 0.2616822429906542,
+      "grad_norm": 0.4268462359905243,
+      "learning_rate": 9.901899829374048e-06,
+      "loss": 2.0897,
+      "step": 63
+    },
+    {
+      "epoch": 0.26583592938733125,
+      "grad_norm": 0.46526211500167847,
+      "learning_rate": 9.884934153917998e-06,
+      "loss": 2.1256,
+      "step": 64
+    },
+    {
+      "epoch": 0.2699896157840083,
+      "grad_norm": 0.3967600166797638,
+      "learning_rate": 9.86663298624003e-06,
+      "loss": 2.1649,
+      "step": 65
+    },
+    {
+      "epoch": 0.27414330218068533,
+      "grad_norm": 0.3882082998752594,
+      "learning_rate": 9.847001329696653e-06,
+      "loss": 2.1514,
+      "step": 66
+    },
+    {
+      "epoch": 0.2782969885773624,
+      "grad_norm": 0.3926977813243866,
+      "learning_rate": 9.826044551386743e-06,
+      "loss": 2.1225,
+      "step": 67
+    },
+    {
+      "epoch": 0.2824506749740395,
+      "grad_norm": 0.37442710995674133,
+      "learning_rate": 9.803768380684242e-06,
+      "loss": 2.1526,
+      "step": 68
+    },
+    {
+      "epoch": 0.2866043613707165,
+      "grad_norm": 0.3859005570411682,
+      "learning_rate": 9.780178907671788e-06,
+      "loss": 2.1437,
+      "step": 69
+    },
+    {
+      "epoch": 0.29075804776739356,
+      "grad_norm": 0.36700868606567383,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 2.0886,
+      "step": 70
+    },
+    {
+      "epoch": 0.2949117341640706,
+      "grad_norm": 0.32868337631225586,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 2.0149,
+      "step": 71
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 0.5018991827964783,
+      "learning_rate": 9.701596950580807e-06,
+      "loss": 2.1765,
+      "step": 72
+    },
+    {
+      "epoch": 0.3032191069574247,
+      "grad_norm": 0.46321091055870056,
+      "learning_rate": 9.672822322997305e-06,
+      "loss": 2.0778,
+      "step": 73
+    },
+    {
+      "epoch": 0.3073727933541018,
+      "grad_norm": 0.36446163058280945,
+      "learning_rate": 9.642770192448537e-06,
+      "loss": 2.1116,
+      "step": 74
+    },
+    {
+      "epoch": 0.3115264797507788,
+      "grad_norm": 0.5278913974761963,
+      "learning_rate": 9.611448774886925e-06,
+      "loss": 2.1583,
+      "step": 75
+    },
+    {
+      "epoch": 0.31568016614745587,
+      "grad_norm": 0.3852906823158264,
+      "learning_rate": 9.578866633275289e-06,
+      "loss": 2.0911,
+      "step": 76
+    },
+    {
+      "epoch": 0.31983385254413293,
+      "grad_norm": 0.33927422761917114,
+      "learning_rate": 9.545032675245814e-06,
+      "loss": 2.1511,
+      "step": 77
+    },
+    {
+      "epoch": 0.32398753894080995,
+      "grad_norm": 0.4899720251560211,
+      "learning_rate": 9.509956150664796e-06,
+      "loss": 2.1541,
+      "step": 78
+    },
+    {
+      "epoch": 0.328141225337487,
+      "grad_norm": 0.6482370495796204,
+      "learning_rate": 9.473646649103819e-06,
+      "loss": 2.0696,
+      "step": 79
+    },
+    {
+      "epoch": 0.3322949117341641,
+      "grad_norm": 0.5560997724533081,
+      "learning_rate": 9.43611409721806e-06,
+      "loss": 2.1247,
+      "step": 80
+    },
+    {
+      "epoch": 0.3364485981308411,
+      "grad_norm": 0.3883346915245056,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 2.098,
+      "step": 81
+    },
+    {
+      "epoch": 0.3406022845275182,
+      "grad_norm": 0.40563803911209106,
+      "learning_rate": 9.357421218136387e-06,
+      "loss": 2.1632,
+      "step": 82
+    },
+    {
+      "epoch": 0.34475597092419524,
+      "grad_norm": 0.45003846287727356,
+      "learning_rate": 9.31628240478787e-06,
+      "loss": 2.1335,
+      "step": 83
+    },
+    {
+      "epoch": 0.34890965732087226,
+      "grad_norm": 0.4380098581314087,
+      "learning_rate": 9.273963562927695e-06,
+      "loss": 2.0858,
+      "step": 84
+    },
+    {
+      "epoch": 0.3530633437175493,
+      "grad_norm": 0.3497319221496582,
+      "learning_rate": 9.230476262104678e-06,
+      "loss": 2.1274,
+      "step": 85
+    },
+    {
+      "epoch": 0.3572170301142264,
+      "grad_norm": 0.3552245497703552,
+      "learning_rate": 9.185832391312644e-06,
+      "loss": 2.1446,
+      "step": 86
+    },
+    {
+      "epoch": 0.3613707165109034,
+      "grad_norm": 0.36943352222442627,
+      "learning_rate": 9.140044155740102e-06,
+      "loss": 2.1117,
+      "step": 87
+    },
+    {
+      "epoch": 0.3655244029075805,
+      "grad_norm": 0.37478867173194885,
+      "learning_rate": 9.093124073433464e-06,
+      "loss": 2.1521,
+      "step": 88
+    },
+    {
+      "epoch": 0.36967808930425755,
+      "grad_norm": 0.3419424593448639,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 2.113,
+      "step": 89
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "grad_norm": 0.30643460154533386,
+      "learning_rate": 8.995939984474624e-06,
+      "loss": 2.0633,
+      "step": 90
+    },
+    {
+      "epoch": 0.37798546209761164,
+      "grad_norm": 0.361110121011734,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 2.1143,
+      "step": 91
+    },
+    {
+      "epoch": 0.3821391484942887,
+      "grad_norm": 0.33192265033721924,
+      "learning_rate": 8.894386393810563e-06,
+      "loss": 2.1207,
+      "step": 92
+    },
+    {
+      "epoch": 0.3862928348909657,
+      "grad_norm": 0.325773149728775,
+      "learning_rate": 8.842005554284296e-06,
+      "loss": 2.1205,
+      "step": 93
+    },
+    {
+      "epoch": 0.3904465212876428,
+      "grad_norm": 0.4192400276660919,
+      "learning_rate": 8.788574348801676e-06,
+      "loss": 2.172,
+      "step": 94
+    },
+    {
+      "epoch": 0.39460020768431986,
+      "grad_norm": 0.3268410563468933,
+      "learning_rate": 8.734107384920771e-06,
+      "loss": 2.0921,
+      "step": 95
+    },
+    {
+      "epoch": 0.3987538940809969,
+      "grad_norm": 0.34491395950317383,
+      "learning_rate": 8.67861955336566e-06,
+      "loss": 2.112,
+      "step": 96
+    },
+    {
+      "epoch": 0.40290758047767394,
+      "grad_norm": 0.3280870020389557,
+      "learning_rate": 8.622126023955446e-06,
+      "loss": 2.0972,
+      "step": 97
+    },
+    {
+      "epoch": 0.407061266874351,
+      "grad_norm": 0.42370373010635376,
+      "learning_rate": 8.564642241456986e-06,
+      "loss": 2.1675,
+      "step": 98
+    },
+    {
+      "epoch": 0.411214953271028,
+      "grad_norm": 0.3967688977718353,
+      "learning_rate": 8.506183921362443e-06,
+      "loss": 2.1162,
+      "step": 99
+    },
+    {
+      "epoch": 0.4153686396677051,
+      "grad_norm": 0.3643606901168823,
+      "learning_rate": 8.446767045592829e-06,
+      "loss": 2.1448,
+      "step": 100
+    },
+    {
+      "epoch": 0.4195223260643821,
+      "grad_norm": 0.403810054063797,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 2.1694,
+      "step": 101
+    },
+    {
+      "epoch": 0.4236760124610592,
+      "grad_norm": 0.3851834237575531,
+      "learning_rate": 8.325122860569241e-06,
+      "loss": 2.1891,
+      "step": 102
+    },
+    {
+      "epoch": 0.42782969885773625,
+      "grad_norm": 0.3491027057170868,
+      "learning_rate": 8.262928807620843e-06,
+      "loss": 2.0881,
+      "step": 103
+    },
+    {
+      "epoch": 0.43198338525441327,
+      "grad_norm": 0.4147508442401886,
+      "learning_rate": 8.199842702516584e-06,
+      "loss": 2.1355,
+      "step": 104
+    },
+    {
+      "epoch": 0.43613707165109034,
+      "grad_norm": 0.3745593726634979,
+      "learning_rate": 8.135881792367686e-06,
+      "loss": 2.1862,
+      "step": 105
+    },
+    {
+      "epoch": 0.4402907580477674,
+      "grad_norm": 0.3806188702583313,
+      "learning_rate": 8.071063563448341e-06,
+      "loss": 2.1435,
+      "step": 106
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.3626170754432678,
+      "learning_rate": 8.005405736415127e-06,
+      "loss": 2.0608,
+      "step": 107
+    },
+    {
+      "epoch": 0.4485981308411215,
+      "grad_norm": 0.3634461760520935,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 2.1969,
+      "step": 108
+    },
+    {
+      "epoch": 0.45275181723779856,
+      "grad_norm": 0.3739028871059418,
+      "learning_rate": 7.871643313414718e-06,
+      "loss": 2.1048,
+      "step": 109
+    },
+    {
+      "epoch": 0.4569055036344756,
+      "grad_norm": 0.3855268061161041,
+      "learning_rate": 7.803575286758365e-06,
+      "loss": 2.1129,
+      "step": 110
+    },
+    {
+      "epoch": 0.46105919003115264,
+      "grad_norm": 0.39188092947006226,
+      "learning_rate": 7.734740790612137e-06,
+      "loss": 2.1127,
+      "step": 111
+    },
+    {
+      "epoch": 0.4652128764278297,
+      "grad_norm": 0.39279860258102417,
+      "learning_rate": 7.66515864363997e-06,
+      "loss": 2.1478,
+      "step": 112
+    },
+    {
+      "epoch": 0.46936656282450673,
+      "grad_norm": 0.42985665798187256,
+      "learning_rate": 7.594847868906076e-06,
+      "loss": 2.1444,
+      "step": 113
+    },
+    {
+      "epoch": 0.4735202492211838,
+      "grad_norm": 0.34920892119407654,
+      "learning_rate": 7.52382768867422e-06,
+      "loss": 2.1402,
+      "step": 114
+    },
+    {
+      "epoch": 0.47767393561786087,
+      "grad_norm": 0.3863445520401001,
+      "learning_rate": 7.452117519152542e-06,
+      "loss": 2.1491,
+      "step": 115
+    },
+    {
+      "epoch": 0.4818276220145379,
+      "grad_norm": 0.5511898398399353,
+      "learning_rate": 7.379736965185369e-06,
+      "loss": 2.1283,
+      "step": 116
+    },
+    {
+      "epoch": 0.48598130841121495,
+      "grad_norm": 0.36419305205345154,
+      "learning_rate": 7.30670581489344e-06,
+      "loss": 2.1416,
+      "step": 117
+    },
+    {
+      "epoch": 0.490134994807892,
+      "grad_norm": 0.431270569562912,
+      "learning_rate": 7.233044034264034e-06,
+      "loss": 2.1307,
+      "step": 118
+    },
+    {
+      "epoch": 0.49428868120456904,
+      "grad_norm": 0.4779389202594757,
+      "learning_rate": 7.158771761692464e-06,
+      "loss": 2.099,
+      "step": 119
+    },
+    {
+      "epoch": 0.4984423676012461,
+      "grad_norm": 0.3551599681377411,
+      "learning_rate": 7.083909302476453e-06,
+      "loss": 2.1202,
+      "step": 120
+    },
+    {
+      "epoch": 0.5025960539979232,
+      "grad_norm": 0.33220580220222473,
+      "learning_rate": 7.008477123264849e-06,
+      "loss": 2.1491,
+      "step": 121
+    },
+    {
+      "epoch": 0.5067497403946002,
+      "grad_norm": 0.39055803418159485,
+      "learning_rate": 6.932495846462262e-06,
+      "loss": 2.1445,
+      "step": 122
+    },
+    {
+      "epoch": 0.5109034267912772,
+      "grad_norm": 0.33877313137054443,
+      "learning_rate": 6.855986244591104e-06,
+      "loss": 2.1349,
+      "step": 123
+    },
+    {
+      "epoch": 0.5150571131879543,
+      "grad_norm": 0.3542743921279907,
+      "learning_rate": 6.778969234612583e-06,
+      "loss": 2.098,
+      "step": 124
+    },
+    {
+      "epoch": 0.5192107995846313,
+      "grad_norm": 0.35766342282295227,
+      "learning_rate": 6.701465872208216e-06,
+      "loss": 2.1363,
+      "step": 125
+    },
+    {
+      "epoch": 0.5233644859813084,
+      "grad_norm": 0.35533398389816284,
+      "learning_rate": 6.6234973460234184e-06,
+      "loss": 2.0558,
+      "step": 126
+    },
+    {
+      "epoch": 0.5275181723779855,
+      "grad_norm": 0.3273533880710602,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 2.1791,
+      "step": 127
+    },
+    {
+      "epoch": 0.5316718587746625,
+      "grad_norm": 0.35391753911972046,
+      "learning_rate": 6.466250186922325e-06,
+      "loss": 2.054,
+      "step": 128
+    },
+    {
+      "epoch": 0.5358255451713395,
+      "grad_norm": 0.295899897813797,
+      "learning_rate": 6.387014543809224e-06,
+      "loss": 2.1038,
+      "step": 129
+    },
+    {
+      "epoch": 0.5399792315680166,
+      "grad_norm": 0.3650350272655487,
+      "learning_rate": 6.3073997047691e-06,
+      "loss": 2.1463,
+      "step": 130
+    },
+    {
+      "epoch": 0.5441329179646937,
+      "grad_norm": 0.40882980823516846,
+      "learning_rate": 6.227427435703997e-06,
+      "loss": 2.1043,
+      "step": 131
+    },
+    {
+      "epoch": 0.5482866043613707,
+      "grad_norm": 0.3036598265171051,
+      "learning_rate": 6.147119600233758e-06,
+      "loss": 2.0616,
+      "step": 132
+    },
+    {
+      "epoch": 0.5524402907580478,
+      "grad_norm": 0.4223164916038513,
+      "learning_rate": 6.066498153718735e-06,
+      "loss": 2.1511,
+      "step": 133
+    },
+    {
+      "epoch": 0.5565939771547248,
+      "grad_norm": 0.2908646762371063,
+      "learning_rate": 5.985585137257401e-06,
+      "loss": 2.1268,
+      "step": 134
+    },
+    {
+      "epoch": 0.5607476635514018,
+      "grad_norm": 0.48902490735054016,
+      "learning_rate": 5.904402671660551e-06,
+      "loss": 2.1221,
+      "step": 135
+    },
+    {
+      "epoch": 0.564901349948079,
+      "grad_norm": 0.38439658284187317,
+      "learning_rate": 5.82297295140367e-06,
+      "loss": 2.1389,
+      "step": 136
+    },
+    {
+      "epoch": 0.569055036344756,
+      "grad_norm": 0.4415787160396576,
+      "learning_rate": 5.74131823855921e-06,
+      "loss": 2.0875,
+      "step": 137
+    },
+    {
+      "epoch": 0.573208722741433,
+      "grad_norm": 0.41299912333488464,
+      "learning_rate": 5.659460856710346e-06,
+      "loss": 2.155,
+      "step": 138
+    },
+    {
+      "epoch": 0.5773624091381101,
+      "grad_norm": 0.4978012144565582,
+      "learning_rate": 5.577423184847932e-06,
+      "loss": 2.0828,
+      "step": 139
+    },
+    {
+      "epoch": 0.5815160955347871,
+      "grad_norm": 0.3253823220729828,
+      "learning_rate": 5.495227651252315e-06,
+      "loss": 2.094,
+      "step": 140
+    },
+    {
+      "epoch": 0.5856697819314641,
+      "grad_norm": 0.40332135558128357,
+      "learning_rate": 5.412896727361663e-06,
+      "loss": 2.1003,
+      "step": 141
+    },
+    {
+      "epoch": 0.5898234683281413,
+      "grad_norm": 0.296169638633728,
+      "learning_rate": 5.3304529216284974e-06,
+      "loss": 2.1062,
+      "step": 142
+    },
+    {
+      "epoch": 0.5939771547248183,
+      "grad_norm": 0.35131099820137024,
+      "learning_rate": 5.247918773366112e-06,
+      "loss": 2.1015,
+      "step": 143
+    },
+    {
+      "epoch": 0.5981308411214953,
+      "grad_norm": 0.30257904529571533,
+      "learning_rate": 5.165316846586541e-06,
+      "loss": 2.1598,
+      "step": 144
+    },
+    {
+      "epoch": 0.6022845275181724,
+      "grad_norm": 0.3170335590839386,
+      "learning_rate": 5.082669723831793e-06,
+      "loss": 2.1115,
+      "step": 145
+    },
+    {
+      "epoch": 0.6064382139148494,
+      "grad_norm": 0.29750919342041016,
+      "learning_rate": 5e-06,
+      "loss": 2.1695,
+      "step": 146
+    },
+    {
+      "epoch": 0.6105919003115264,
+      "grad_norm": 0.36148592829704285,
+      "learning_rate": 4.917330276168208e-06,
+      "loss": 2.1656,
+      "step": 147
+    },
+    {
+      "epoch": 0.6147455867082036,
+      "grad_norm": 0.2840471863746643,
+      "learning_rate": 4.8346831534134595e-06,
+      "loss": 2.1353,
+      "step": 148
+    },
+    {
+      "epoch": 0.6188992731048806,
+      "grad_norm": 0.4525928795337677,
+      "learning_rate": 4.752081226633888e-06,
+      "loss": 2.1334,
+      "step": 149
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.2894962430000305,
+      "learning_rate": 4.669547078371503e-06,
+      "loss": 2.1364,
+      "step": 150
+    },
+    {
+      "epoch": 0.6272066458982347,
+      "grad_norm": 0.3974563777446747,
+      "learning_rate": 4.587103272638339e-06,
+      "loss": 2.1105,
+      "step": 151
+    },
+    {
+      "epoch": 0.6313603322949117,
+      "grad_norm": 0.3226485550403595,
+      "learning_rate": 4.504772348747687e-06,
+      "loss": 2.1914,
+      "step": 152
+    },
+    {
+      "epoch": 0.6355140186915887,
+      "grad_norm": 0.3687591254711151,
+      "learning_rate": 4.42257681515207e-06,
+      "loss": 2.107,
+      "step": 153
+    },
+    {
+      "epoch": 0.6396677050882659,
+      "grad_norm": 0.3422071635723114,
+      "learning_rate": 4.340539143289655e-06,
+      "loss": 2.128,
+      "step": 154
+    },
+    {
+      "epoch": 0.6438213914849429,
+      "grad_norm": 0.3275080621242523,
+      "learning_rate": 4.25868176144079e-06,
+      "loss": 2.1684,
+      "step": 155
+    },
+    {
+      "epoch": 0.6479750778816199,
+      "grad_norm": 0.3418704569339752,
+      "learning_rate": 4.17702704859633e-06,
+      "loss": 2.0611,
+      "step": 156
+    },
+    {
+      "epoch": 0.652128764278297,
+      "grad_norm": 0.27305227518081665,
+      "learning_rate": 4.0955973283394525e-06,
+      "loss": 2.0826,
+      "step": 157
+    },
+    {
+      "epoch": 0.656282450674974,
+      "grad_norm": 0.3369821012020111,
+      "learning_rate": 4.0144148627426e-06,
+      "loss": 2.1567,
+      "step": 158
+    },
+    {
+      "epoch": 0.660436137071651,
+      "grad_norm": 0.25910282135009766,
+      "learning_rate": 3.9335018462812664e-06,
+      "loss": 2.0637,
+      "step": 159
+    },
+    {
+      "epoch": 0.6645898234683282,
+      "grad_norm": 0.2668653726577759,
+      "learning_rate": 3.852880399766243e-06,
+      "loss": 2.0863,
+      "step": 160
+    },
+    {
+      "epoch": 0.6687435098650052,
+      "grad_norm": 0.3396942913532257,
+      "learning_rate": 3.7725725642960047e-06,
+      "loss": 2.083,
+      "step": 161
+    },
+    {
+      "epoch": 0.6728971962616822,
+      "grad_norm": 0.3137992024421692,
+      "learning_rate": 3.6926002952309015e-06,
+      "loss": 2.1808,
+      "step": 162
+    },
+    {
+      "epoch": 0.6770508826583593,
+      "grad_norm": 0.32238420844078064,
+      "learning_rate": 3.6129854561907786e-06,
+      "loss": 2.0964,
+      "step": 163
+    },
+    {
+      "epoch": 0.6812045690550363,
+      "grad_norm": 0.26426786184310913,
+      "learning_rate": 3.533749813077677e-06,
+      "loss": 2.0951,
+      "step": 164
+    },
+    {
+      "epoch": 0.6853582554517134,
+      "grad_norm": 0.2933923006057739,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 2.041,
+      "step": 165
+    },
+    {
+      "epoch": 0.6895119418483905,
+      "grad_norm": 0.37952423095703125,
+      "learning_rate": 3.3765026539765832e-06,
+      "loss": 2.1749,
+      "step": 166
+    },
+    {
+      "epoch": 0.6936656282450675,
+      "grad_norm": 0.24741414189338684,
+      "learning_rate": 3.298534127791785e-06,
+      "loss": 2.1185,
+      "step": 167
+    },
+    {
+      "epoch": 0.6978193146417445,
+      "grad_norm": 0.2836434841156006,
+      "learning_rate": 3.2210307653874175e-06,
+      "loss": 2.1034,
+      "step": 168
+    },
+    {
+      "epoch": 0.7019730010384216,
+      "grad_norm": 0.2631160318851471,
+      "learning_rate": 3.1440137554088957e-06,
+      "loss": 2.1095,
+      "step": 169
+    },
+    {
+      "epoch": 0.7061266874350987,
+      "grad_norm": 0.29444393515586853,
+      "learning_rate": 3.06750415353774e-06,
+      "loss": 2.0951,
+      "step": 170
+    },
+    {
+      "epoch": 0.7102803738317757,
+      "grad_norm": 0.2870319187641144,
+      "learning_rate": 2.991522876735154e-06,
+      "loss": 2.0856,
+      "step": 171
+    },
+    {
+      "epoch": 0.7144340602284528,
+      "grad_norm": 0.25737184286117554,
+      "learning_rate": 2.9160906975235493e-06,
+      "loss": 2.1711,
+      "step": 172
+    },
+    {
+      "epoch": 0.7185877466251298,
+      "grad_norm": 0.25282764434814453,
+      "learning_rate": 2.8412282383075362e-06,
+      "loss": 2.1474,
+      "step": 173
+    },
+    {
+      "epoch": 0.7227414330218068,
+      "grad_norm": 0.25563523173332214,
+      "learning_rate": 2.766955965735968e-06,
+      "loss": 2.1576,
+      "step": 174
+    },
+    {
+      "epoch": 0.726895119418484,
+      "grad_norm": 0.306660920381546,
+      "learning_rate": 2.693294185106562e-06,
+      "loss": 2.094,
+      "step": 175
+    },
+    {
+      "epoch": 0.731048805815161,
+      "grad_norm": 0.2536129057407379,
+      "learning_rate": 2.6202630348146323e-06,
+      "loss": 2.0746,
+      "step": 176
+    },
+    {
+      "epoch": 0.735202492211838,
+      "grad_norm": 0.24668152630329132,
+      "learning_rate": 2.5478824808474613e-06,
+      "loss": 2.1441,
+      "step": 177
+    },
+    {
+      "epoch": 0.7393561786085151,
+      "grad_norm": 0.24908193945884705,
+      "learning_rate": 2.476172311325783e-06,
+      "loss": 2.1225,
+      "step": 178
+    },
+    {
+      "epoch": 0.7435098650051921,
+      "grad_norm": 0.26486849784851074,
+      "learning_rate": 2.4051521310939258e-06,
+      "loss": 2.09,
+      "step": 179
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 0.2715510427951813,
+      "learning_rate": 2.3348413563600324e-06,
+      "loss": 2.1207,
+      "step": 180
+    },
+    {
+      "epoch": 0.7518172377985463,
+      "grad_norm": 0.24639959633350372,
+      "learning_rate": 2.265259209387867e-06,
+      "loss": 2.0995,
+      "step": 181
+    },
+    {
+      "epoch": 0.7559709241952233,
+      "grad_norm": 0.24900901317596436,
+      "learning_rate": 2.1964247132416373e-06,
+      "loss": 2.1318,
+      "step": 182
+    },
+    {
+      "epoch": 0.7601246105919003,
+      "grad_norm": 0.2573296129703522,
+      "learning_rate": 2.1283566865852824e-06,
+      "loss": 2.2217,
+      "step": 183
+    },
+    {
+      "epoch": 0.7642782969885774,
+      "grad_norm": 0.26032745838165283,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 2.1309,
+      "step": 184
+    },
+    {
+      "epoch": 0.7684319833852544,
+      "grad_norm": 0.28223130106925964,
+      "learning_rate": 1.9945942635848745e-06,
+      "loss": 2.0551,
+      "step": 185
+    },
+    {
+      "epoch": 0.7725856697819314,
+      "grad_norm": 0.24117982387542725,
+      "learning_rate": 1.928936436551661e-06,
+      "loss": 2.1201,
+      "step": 186
+    },
+    {
+      "epoch": 0.7767393561786086,
+      "grad_norm": 0.23914583027362823,
+      "learning_rate": 1.864118207632315e-06,
+      "loss": 2.106,
+      "step": 187
+    },
+    {
+      "epoch": 0.7808930425752856,
+      "grad_norm": 0.2441292554140091,
+      "learning_rate": 1.8001572974834169e-06,
+      "loss": 2.1211,
+      "step": 188
+    },
+    {
+      "epoch": 0.7850467289719626,
+      "grad_norm": 0.365399569272995,
+      "learning_rate": 1.7370711923791567e-06,
+      "loss": 2.0911,
+      "step": 189
+    },
+    {
+      "epoch": 0.7892004153686397,
+      "grad_norm": 0.26222550868988037,
+      "learning_rate": 1.6748771394307584e-06,
+      "loss": 2.0966,
+      "step": 190
+    },
+    {
+      "epoch": 0.7933541017653167,
+      "grad_norm": 0.23175619542598724,
+      "learning_rate": 1.6135921418712959e-06,
+      "loss": 2.0703,
+      "step": 191
+    },
+    {
+      "epoch": 0.7975077881619937,
+      "grad_norm": 0.22840319573879242,
+      "learning_rate": 1.5532329544071712e-06,
+      "loss": 2.1146,
+      "step": 192
+    },
+    {
+      "epoch": 0.8016614745586709,
+      "grad_norm": 0.23600910604000092,
+      "learning_rate": 1.4938160786375571e-06,
+      "loss": 2.1576,
+      "step": 193
+    },
+    {
+      "epoch": 0.8058151609553479,
+      "grad_norm": 0.22542668879032135,
+      "learning_rate": 1.4353577585430152e-06,
+      "loss": 2.112,
+      "step": 194
+    },
+    {
+      "epoch": 0.8099688473520249,
+      "grad_norm": 0.24013273417949677,
+      "learning_rate": 1.3778739760445552e-06,
+      "loss": 2.0846,
+      "step": 195
+    },
+    {
+      "epoch": 0.814122533748702,
+      "grad_norm": 0.23736749589443207,
+      "learning_rate": 1.321380446634342e-06,
+      "loss": 2.1067,
+      "step": 196
+    },
+    {
+      "epoch": 0.818276220145379,
+      "grad_norm": 0.24941231310367584,
+      "learning_rate": 1.2658926150792321e-06,
+      "loss": 2.1159,
+      "step": 197
+    },
+    {
+      "epoch": 0.822429906542056,
+      "grad_norm": 0.25511765480041504,
+      "learning_rate": 1.2114256511983274e-06,
+      "loss": 2.0727,
+      "step": 198
+    },
+    {
+      "epoch": 0.8265835929387332,
+      "grad_norm": 0.2361282855272293,
+      "learning_rate": 1.157994445715706e-06,
+      "loss": 2.1016,
+      "step": 199
+    },
+    {
+      "epoch": 0.8307372793354102,
+      "grad_norm": 0.2490163892507553,
+      "learning_rate": 1.1056136061894386e-06,
+      "loss": 2.0666,
+      "step": 200
+    },
+    {
+      "epoch": 0.8348909657320872,
+      "grad_norm": 0.22846023738384247,
+      "learning_rate": 1.0542974530180327e-06,
+      "loss": 2.1226,
+      "step": 201
+    },
+    {
+      "epoch": 0.8390446521287642,
+      "grad_norm": 0.24738390743732452,
+      "learning_rate": 1.0040600155253766e-06,
+      "loss": 2.1018,
+      "step": 202
+    },
+    {
+      "epoch": 0.8431983385254413,
+      "grad_norm": 0.2896912693977356,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 2.0644,
+      "step": 203
+    },
+    {
+      "epoch": 0.8473520249221184,
+      "grad_norm": 0.22052256762981415,
+      "learning_rate": 9.068759265665384e-07,
+      "loss": 2.0869,
+      "step": 204
+    },
+    {
+      "epoch": 0.8515057113187954,
+      "grad_norm": 0.2386987954378128,
+      "learning_rate": 8.599558442598998e-07,
+      "loss": 2.0964,
+      "step": 205
+    },
+    {
+      "epoch": 0.8556593977154725,
+      "grad_norm": 0.22815701365470886,
+      "learning_rate": 8.141676086873574e-07,
+      "loss": 2.1012,
+      "step": 206
+    },
+    {
+      "epoch": 0.8598130841121495,
+      "grad_norm": 0.2326398491859436,
+      "learning_rate": 7.695237378953224e-07,
+      "loss": 2.1153,
+      "step": 207
+    },
+    {
+      "epoch": 0.8639667705088265,
+      "grad_norm": 0.26584866642951965,
+      "learning_rate": 7.260364370723044e-07,
+      "loss": 2.0762,
+      "step": 208
+    },
+    {
+      "epoch": 0.8681204569055037,
+      "grad_norm": 0.22313201427459717,
+      "learning_rate": 6.837175952121305e-07,
+      "loss": 2.0791,
+      "step": 209
+    },
+    {
+      "epoch": 0.8722741433021807,
+      "grad_norm": 0.23364050686359406,
+      "learning_rate": 6.425787818636131e-07,
+      "loss": 2.1801,
+      "step": 210
+    },
+    {
+      "epoch": 0.8764278296988577,
+      "grad_norm": 0.21921421587467194,
+      "learning_rate": 6.026312439675553e-07,
+      "loss": 2.1159,
+      "step": 211
+    },
+    {
+      "epoch": 0.8805815160955348,
+      "grad_norm": 0.273624986410141,
+      "learning_rate": 5.63885902781941e-07,
+      "loss": 2.0313,
+      "step": 212
+    },
+    {
+      "epoch": 0.8847352024922118,
+      "grad_norm": 0.21660713851451874,
+      "learning_rate": 5.263533508961827e-07,
+      "loss": 2.1475,
+      "step": 213
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.22784104943275452,
+      "learning_rate": 4.900438493352056e-07,
+      "loss": 2.1037,
+      "step": 214
+    },
+    {
+      "epoch": 0.893042575285566,
+      "grad_norm": 0.22493554651737213,
+      "learning_rate": 4.549673247541875e-07,
+      "loss": 2.1413,
+      "step": 215
+    },
+    {
+      "epoch": 0.897196261682243,
+      "grad_norm": 0.2319698929786682,
+      "learning_rate": 4.211333667247125e-07,
+      "loss": 2.0693,
+      "step": 216
+    },
+    {
+      "epoch": 0.90134994807892,
+      "grad_norm": 0.2203637659549713,
+      "learning_rate": 3.885512251130763e-07,
+      "loss": 2.1311,
+      "step": 217
+    },
+    {
+      "epoch": 0.9055036344755971,
+      "grad_norm": 0.22149546444416046,
+      "learning_rate": 3.572298075514652e-07,
+      "loss": 2.1418,
+      "step": 218
+    },
+    {
+      "epoch": 0.9096573208722741,
+      "grad_norm": 0.2249898910522461,
+      "learning_rate": 3.271776770026963e-07,
+      "loss": 2.0989,
+      "step": 219
+    },
+    {
+      "epoch": 0.9138110072689511,
+      "grad_norm": 0.23055027425289154,
+      "learning_rate": 2.984030494191942e-07,
+      "loss": 2.1438,
+      "step": 220
+    },
+    {
+      "epoch": 0.9179646936656283,
+      "grad_norm": 0.21457572281360626,
+      "learning_rate": 2.7091379149682683e-07,
+      "loss": 2.01,
+      "step": 221
+    },
+    {
+      "epoch": 0.9221183800623053,
+      "grad_norm": 0.21807509660720825,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 2.1072,
+      "step": 222
+    },
+    {
+      "epoch": 0.9262720664589823,
+      "grad_norm": 0.22586828470230103,
+      "learning_rate": 2.198210923282118e-07,
+      "loss": 2.11,
+      "step": 223
+    },
+    {
+      "epoch": 0.9304257528556594,
+      "grad_norm": 0.2149934321641922,
+      "learning_rate": 1.962316193157593e-07,
+      "loss": 2.1078,
+      "step": 224
+    },
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.2686188519001007,
+      "learning_rate": 1.7395544861325718e-07,
+      "loss": 2.1032,
+      "step": 225
+    },
+    {
+      "epoch": 0.9387331256490135,
+      "grad_norm": 0.21735844016075134,
+      "learning_rate": 1.5299867030334815e-07,
+      "loss": 2.1412,
+      "step": 226
+    },
+    {
+      "epoch": 0.9428868120456906,
+      "grad_norm": 0.2169795036315918,
+      "learning_rate": 1.333670137599713e-07,
+      "loss": 2.1258,
+      "step": 227
+    },
+    {
+      "epoch": 0.9470404984423676,
+      "grad_norm": 0.2194252610206604,
+      "learning_rate": 1.1506584608200366e-07,
+      "loss": 2.166,
+      "step": 228
+    },
+    {
+      "epoch": 0.9511941848390446,
+      "grad_norm": 0.2147681564092636,
+      "learning_rate": 9.810017062595322e-08,
+      "loss": 2.1009,
+      "step": 229
+    },
+    {
+      "epoch": 0.9553478712357217,
+      "grad_norm": 0.22832895815372467,
+      "learning_rate": 8.247462563808816e-08,
+      "loss": 2.1068,
+      "step": 230
+    },
+    {
+      "epoch": 0.9595015576323987,
+      "grad_norm": 0.2108795940876007,
+      "learning_rate": 6.819348298638839e-08,
+      "loss": 2.1595,
+      "step": 231
+    },
+    {
+      "epoch": 0.9636552440290758,
+      "grad_norm": 0.21970967948436737,
+      "learning_rate": 5.526064699265754e-08,
+      "loss": 2.0614,
+      "step": 232
+    },
+    {
+      "epoch": 0.9678089304257529,
+      "grad_norm": 0.2157040536403656,
+      "learning_rate": 4.367965336512403e-08,
+      "loss": 2.0851,
+      "step": 233
+    },
+    {
+      "epoch": 0.9719626168224299,
+      "grad_norm": 0.20249901711940765,
+      "learning_rate": 3.345366823180929e-08,
+      "loss": 2.1191,
+      "step": 234
+    },
+    {
+      "epoch": 0.9761163032191069,
+      "grad_norm": 0.22388389706611633,
+      "learning_rate": 2.4585487274942922e-08,
+      "loss": 2.0653,
+      "step": 235
+    },
+    {
+      "epoch": 0.980269989615784,
+      "grad_norm": 0.21466441452503204,
+      "learning_rate": 1.7077534966650767e-08,
+      "loss": 2.1259,
+      "step": 236
+    },
+    {
+      "epoch": 0.9844236760124611,
+      "grad_norm": 0.2480291873216629,
+      "learning_rate": 1.0931863906127327e-08,
+      "loss": 2.1256,
+      "step": 237
+    },
+    {
+      "epoch": 0.9885773624091381,
+      "grad_norm": 0.20534351468086243,
+      "learning_rate": 6.150154258476315e-09,
+      "loss": 2.1574,
+      "step": 238
+    },
+    {
+      "epoch": 0.9927310488058152,
+      "grad_norm": 0.2120267003774643,
+      "learning_rate": 2.7337132953697555e-09,
+      "loss": 2.1358,
+      "step": 239
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": 0.2108861654996872,
+      "learning_rate": 6.834750376549793e-10,
+      "loss": 2.1028,
+      "step": 240
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 120,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.2286664699672e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea945cbbbf1b95e83023269ba8434587298064165cd3fc8e5cfc8d3cbcb0ca4c
+size 8849

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)