update(model): upload model files

.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 @@
+{
+  "_name_or_path": "/home/ubuntu/tmp/models/miscii-1020",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.45.2"
+}

latest

@@ -0,0 +1 @@
+global_step200

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9183753e63f25c19e6700c8ba6a5fd4ea410ffa3807195183fb27008db2ecc6f
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c4e9be9995380c50afbd53f747eaa33a791b656f50fb3dc5bc3ad2b9ce7bf3
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9255c1d0be4a588cd7bf80da5b6a0cf2b0c7c3ca60e6809dc30225b5e0b6d8a
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6149234cf3c69703135b733b5c4c613c60519c69eb1a7043237a71e24b1f14db
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95bdb2c07658d669080414e47a664dd9469721fae9a24a976a14890f1e863105
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82b556ba22a7550b9338055f2aee8d3b26621e059c87734f02631a1da59e41e
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a0b68eaec22cca2bac88b142045afc24655b66cff2f1a585b6118f787a9d82
+size 1064

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": "<|im_end|>",
+    "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 Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1449 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5667729365922777,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0028338646829613886,
+      "grad_norm": 2.486575126647949,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 1.0529,
+      "step": 1
+    },
+    {
+      "epoch": 0.005667729365922777,
+      "grad_norm": 2.4581711292266846,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 1.0667,
+      "step": 2
+    },
+    {
+      "epoch": 0.008501594048884165,
+      "grad_norm": 2.5839550495147705,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.0656,
+      "step": 3
+    },
+    {
+      "epoch": 0.011335458731845554,
+      "grad_norm": 2.298288345336914,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.9865,
+      "step": 4
+    },
+    {
+      "epoch": 0.014169323414806943,
+      "grad_norm": 2.297114372253418,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 1.0597,
+      "step": 5
+    },
+    {
+      "epoch": 0.01700318809776833,
+      "grad_norm": 2.0391056537628174,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.9876,
+      "step": 6
+    },
+    {
+      "epoch": 0.01983705278072972,
+      "grad_norm": 2.1765682697296143,
+      "learning_rate": 1.944444444444445e-06,
+      "loss": 1.0235,
+      "step": 7
+    },
+    {
+      "epoch": 0.02267091746369111,
+      "grad_norm": 2.067063331604004,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.0371,
+      "step": 8
+    },
+    {
+      "epoch": 0.025504782146652496,
+      "grad_norm": 1.8456134796142578,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0335,
+      "step": 9
+    },
+    {
+      "epoch": 0.028338646829613887,
+      "grad_norm": 1.2864792346954346,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.9882,
+      "step": 10
+    },
+    {
+      "epoch": 0.031172511512575274,
+      "grad_norm": 1.3451131582260132,
+      "learning_rate": 3.055555555555556e-06,
+      "loss": 0.9992,
+      "step": 11
+    },
+    {
+      "epoch": 0.03400637619553666,
+      "grad_norm": 1.248445749282837,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.9167,
+      "step": 12
+    },
+    {
+      "epoch": 0.03684024087849805,
+      "grad_norm": 1.7280871868133545,
+      "learning_rate": 3.6111111111111115e-06,
+      "loss": 0.9863,
+      "step": 13
+    },
+    {
+      "epoch": 0.03967410556145944,
+      "grad_norm": 1.7836530208587646,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.9955,
+      "step": 14
+    },
+    {
+      "epoch": 0.04250797024442083,
+      "grad_norm": 2.057832717895508,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.9774,
+      "step": 15
+    },
+    {
+      "epoch": 0.04534183492738222,
+      "grad_norm": 1.7875008583068848,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.9283,
+      "step": 16
+    },
+    {
+      "epoch": 0.048175699610343604,
+      "grad_norm": 1.7444796562194824,
+      "learning_rate": 4.722222222222222e-06,
+      "loss": 0.9814,
+      "step": 17
+    },
+    {
+      "epoch": 0.05100956429330499,
+      "grad_norm": 1.3500471115112305,
+      "learning_rate": 5e-06,
+      "loss": 0.9782,
+      "step": 18
+    },
+    {
+      "epoch": 0.053843428976266386,
+      "grad_norm": 1.2453361749649048,
+      "learning_rate": 5.2777777777777785e-06,
+      "loss": 0.9214,
+      "step": 19
+    },
+    {
+      "epoch": 0.05667729365922777,
+      "grad_norm": 1.424530029296875,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.9823,
+      "step": 20
+    },
+    {
+      "epoch": 0.05951115834218916,
+      "grad_norm": 1.41603422164917,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.985,
+      "step": 21
+    },
+    {
+      "epoch": 0.06234502302515055,
+      "grad_norm": 1.4645209312438965,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 0.9969,
+      "step": 22
+    },
+    {
+      "epoch": 0.06517888770811193,
+      "grad_norm": 1.3437155485153198,
+      "learning_rate": 6.3888888888888885e-06,
+      "loss": 0.9882,
+      "step": 23
+    },
+    {
+      "epoch": 0.06801275239107332,
+      "grad_norm": 1.1282659769058228,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8876,
+      "step": 24
+    },
+    {
+      "epoch": 0.07084661707403471,
+      "grad_norm": 1.1051347255706787,
+      "learning_rate": 6.944444444444445e-06,
+      "loss": 0.9013,
+      "step": 25
+    },
+    {
+      "epoch": 0.0736804817569961,
+      "grad_norm": 1.0878770351409912,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 0.9114,
+      "step": 26
+    },
+    {
+      "epoch": 0.0765143464399575,
+      "grad_norm": 1.218088984489441,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.9036,
+      "step": 27
+    },
+    {
+      "epoch": 0.07934821112291889,
+      "grad_norm": 1.1867142915725708,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.9659,
+      "step": 28
+    },
+    {
+      "epoch": 0.08218207580588027,
+      "grad_norm": 1.1344166994094849,
+      "learning_rate": 8.055555555555557e-06,
+      "loss": 0.8968,
+      "step": 29
+    },
+    {
+      "epoch": 0.08501594048884166,
+      "grad_norm": 1.1566065549850464,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.9501,
+      "step": 30
+    },
+    {
+      "epoch": 0.08784980517180305,
+      "grad_norm": 1.0742772817611694,
+      "learning_rate": 8.611111111111112e-06,
+      "loss": 0.9461,
+      "step": 31
+    },
+    {
+      "epoch": 0.09068366985476443,
+      "grad_norm": 1.0392136573791504,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.9687,
+      "step": 32
+    },
+    {
+      "epoch": 0.09351753453772582,
+      "grad_norm": 1.1021109819412231,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.9009,
+      "step": 33
+    },
+    {
+      "epoch": 0.09635139922068721,
+      "grad_norm": 1.0842477083206177,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.895,
+      "step": 34
+    },
+    {
+      "epoch": 0.0991852639036486,
+      "grad_norm": 1.0577669143676758,
+      "learning_rate": 9.722222222222223e-06,
+      "loss": 0.8946,
+      "step": 35
+    },
+    {
+      "epoch": 0.10201912858660998,
+      "grad_norm": 1.0416364669799805,
+      "learning_rate": 1e-05,
+      "loss": 0.9236,
+      "step": 36
+    },
+    {
+      "epoch": 0.10485299326957138,
+      "grad_norm": 1.0574793815612793,
+      "learning_rate": 9.999944704978835e-06,
+      "loss": 0.9648,
+      "step": 37
+    },
+    {
+      "epoch": 0.10768685795253277,
+      "grad_norm": 1.0903434753417969,
+      "learning_rate": 9.999778821138357e-06,
+      "loss": 0.9307,
+      "step": 38
+    },
+    {
+      "epoch": 0.11052072263549416,
+      "grad_norm": 0.9352409839630127,
+      "learning_rate": 9.999502352147583e-06,
+      "loss": 0.9106,
+      "step": 39
+    },
+    {
+      "epoch": 0.11335458731845555,
+      "grad_norm": 1.027969479560852,
+      "learning_rate": 9.999115304121459e-06,
+      "loss": 0.8888,
+      "step": 40
+    },
+    {
+      "epoch": 0.11618845200141693,
+      "grad_norm": 1.0393131971359253,
+      "learning_rate": 9.998617685620715e-06,
+      "loss": 0.9014,
+      "step": 41
+    },
+    {
+      "epoch": 0.11902231668437832,
+      "grad_norm": 1.1002625226974487,
+      "learning_rate": 9.998009507651683e-06,
+      "loss": 0.9128,
+      "step": 42
+    },
+    {
+      "epoch": 0.12185618136733971,
+      "grad_norm": 1.0595248937606812,
+      "learning_rate": 9.997290783666048e-06,
+      "loss": 0.9469,
+      "step": 43
+    },
+    {
+      "epoch": 0.1246900460503011,
+      "grad_norm": 1.0755085945129395,
+      "learning_rate": 9.996461529560553e-06,
+      "loss": 0.9286,
+      "step": 44
+    },
+    {
+      "epoch": 0.1275239107332625,
+      "grad_norm": 0.9834471344947815,
+      "learning_rate": 9.995521763676645e-06,
+      "loss": 0.8902,
+      "step": 45
+    },
+    {
+      "epoch": 0.13035777541622387,
+      "grad_norm": 1.0345213413238525,
+      "learning_rate": 9.994471506800078e-06,
+      "loss": 0.8559,
+      "step": 46
+    },
+    {
+      "epoch": 0.13319164009918527,
+      "grad_norm": 1.0277979373931885,
+      "learning_rate": 9.993310782160439e-06,
+      "loss": 0.9472,
+      "step": 47
+    },
+    {
+      "epoch": 0.13602550478214664,
+      "grad_norm": 0.962760865688324,
+      "learning_rate": 9.992039615430648e-06,
+      "loss": 0.9425,
+      "step": 48
+    },
+    {
+      "epoch": 0.13885936946510805,
+      "grad_norm": 1.0316935777664185,
+      "learning_rate": 9.99065803472638e-06,
+      "loss": 0.9338,
+      "step": 49
+    },
+    {
+      "epoch": 0.14169323414806942,
+      "grad_norm": 1.1116628646850586,
+      "learning_rate": 9.989166070605447e-06,
+      "loss": 0.9371,
+      "step": 50
+    },
+    {
+      "epoch": 0.14452709883103082,
+      "grad_norm": 1.0028659105300903,
+      "learning_rate": 9.98756375606713e-06,
+      "loss": 0.8205,
+      "step": 51
+    },
+    {
+      "epoch": 0.1473609635139922,
+      "grad_norm": 1.0096858739852905,
+      "learning_rate": 9.985851126551428e-06,
+      "loss": 0.8863,
+      "step": 52
+    },
+    {
+      "epoch": 0.1501948281969536,
+      "grad_norm": 1.0067119598388672,
+      "learning_rate": 9.9840282199383e-06,
+      "loss": 0.9361,
+      "step": 53
+    },
+    {
+      "epoch": 0.153028692879915,
+      "grad_norm": 1.023996114730835,
+      "learning_rate": 9.982095076546806e-06,
+      "loss": 0.9736,
+      "step": 54
+    },
+    {
+      "epoch": 0.15586255756287637,
+      "grad_norm": 0.9850320219993591,
+      "learning_rate": 9.980051739134235e-06,
+      "loss": 0.9236,
+      "step": 55
+    },
+    {
+      "epoch": 0.15869642224583777,
+      "grad_norm": 1.018527626991272,
+      "learning_rate": 9.977898252895133e-06,
+      "loss": 0.9624,
+      "step": 56
+    },
+    {
+      "epoch": 0.16153028692879914,
+      "grad_norm": 1.0214104652404785,
+      "learning_rate": 9.975634665460333e-06,
+      "loss": 0.857,
+      "step": 57
+    },
+    {
+      "epoch": 0.16436415161176055,
+      "grad_norm": 0.9879529476165771,
+      "learning_rate": 9.973261026895878e-06,
+      "loss": 0.9545,
+      "step": 58
+    },
+    {
+      "epoch": 0.16719801629472192,
+      "grad_norm": 0.9842500686645508,
+      "learning_rate": 9.970777389701927e-06,
+      "loss": 0.8898,
+      "step": 59
+    },
+    {
+      "epoch": 0.17003188097768332,
+      "grad_norm": 0.9597482085227966,
+      "learning_rate": 9.968183808811586e-06,
+      "loss": 0.8952,
+      "step": 60
+    },
+    {
+      "epoch": 0.1728657456606447,
+      "grad_norm": 1.0947015285491943,
+      "learning_rate": 9.965480341589702e-06,
+      "loss": 0.8581,
+      "step": 61
+    },
+    {
+      "epoch": 0.1756996103436061,
+      "grad_norm": 0.9779541492462158,
+      "learning_rate": 9.962667047831585e-06,
+      "loss": 0.8468,
+      "step": 62
+    },
+    {
+      "epoch": 0.1785334750265675,
+      "grad_norm": 1.0208027362823486,
+      "learning_rate": 9.95974398976169e-06,
+      "loss": 0.908,
+      "step": 63
+    },
+    {
+      "epoch": 0.18136733970952887,
+      "grad_norm": 0.9829966425895691,
+      "learning_rate": 9.95671123203224e-06,
+      "loss": 0.9061,
+      "step": 64
+    },
+    {
+      "epoch": 0.18420120439249027,
+      "grad_norm": 0.9826564192771912,
+      "learning_rate": 9.953568841721796e-06,
+      "loss": 0.9308,
+      "step": 65
+    },
+    {
+      "epoch": 0.18703506907545164,
+      "grad_norm": 0.9291039109230042,
+      "learning_rate": 9.950316888333775e-06,
+      "loss": 0.8721,
+      "step": 66
+    },
+    {
+      "epoch": 0.18986893375841304,
+      "grad_norm": 0.9490424394607544,
+      "learning_rate": 9.946955443794908e-06,
+      "loss": 0.946,
+      "step": 67
+    },
+    {
+      "epoch": 0.19270279844137442,
+      "grad_norm": 0.9768699407577515,
+      "learning_rate": 9.943484582453653e-06,
+      "loss": 0.8699,
+      "step": 68
+    },
+    {
+      "epoch": 0.19553666312433582,
+      "grad_norm": 1.0207207202911377,
+      "learning_rate": 9.939904381078553e-06,
+      "loss": 0.8805,
+      "step": 69
+    },
+    {
+      "epoch": 0.1983705278072972,
+      "grad_norm": 1.0188122987747192,
+      "learning_rate": 9.93621491885653e-06,
+      "loss": 0.9053,
+      "step": 70
+    },
+    {
+      "epoch": 0.2012043924902586,
+      "grad_norm": 1.0252068042755127,
+      "learning_rate": 9.932416277391144e-06,
+      "loss": 0.9141,
+      "step": 71
+    },
+    {
+      "epoch": 0.20403825717321997,
+      "grad_norm": 0.9930822253227234,
+      "learning_rate": 9.928508540700775e-06,
+      "loss": 0.8769,
+      "step": 72
+    },
+    {
+      "epoch": 0.20687212185618137,
+      "grad_norm": 1.0115156173706055,
+      "learning_rate": 9.924491795216777e-06,
+      "loss": 0.9164,
+      "step": 73
+    },
+    {
+      "epoch": 0.20970598653914277,
+      "grad_norm": 0.9986709952354431,
+      "learning_rate": 9.920366129781564e-06,
+      "loss": 0.9349,
+      "step": 74
+    },
+    {
+      "epoch": 0.21253985122210414,
+      "grad_norm": 0.9701442718505859,
+      "learning_rate": 9.916131635646635e-06,
+      "loss": 0.8684,
+      "step": 75
+    },
+    {
+      "epoch": 0.21537371590506554,
+      "grad_norm": 0.9770874977111816,
+      "learning_rate": 9.91178840647057e-06,
+      "loss": 0.9249,
+      "step": 76
+    },
+    {
+      "epoch": 0.21820758058802692,
+      "grad_norm": 0.9752293229103088,
+      "learning_rate": 9.907336538316946e-06,
+      "loss": 0.9223,
+      "step": 77
+    },
+    {
+      "epoch": 0.22104144527098832,
+      "grad_norm": 0.9840958714485168,
+      "learning_rate": 9.902776129652223e-06,
+      "loss": 0.9321,
+      "step": 78
+    },
+    {
+      "epoch": 0.2238753099539497,
+      "grad_norm": 0.9433968663215637,
+      "learning_rate": 9.898107281343557e-06,
+      "loss": 0.8707,
+      "step": 79
+    },
+    {
+      "epoch": 0.2267091746369111,
+      "grad_norm": 0.9404139518737793,
+      "learning_rate": 9.893330096656576e-06,
+      "loss": 0.8317,
+      "step": 80
+    },
+    {
+      "epoch": 0.22954303931987247,
+      "grad_norm": 0.9778679609298706,
+      "learning_rate": 9.888444681253087e-06,
+      "loss": 0.8908,
+      "step": 81
+    },
+    {
+      "epoch": 0.23237690400283387,
+      "grad_norm": 0.9795246124267578,
+      "learning_rate": 9.883451143188753e-06,
+      "loss": 0.8897,
+      "step": 82
+    },
+    {
+      "epoch": 0.23521076868579524,
+      "grad_norm": 1.029739260673523,
+      "learning_rate": 9.878349592910694e-06,
+      "loss": 0.9031,
+      "step": 83
+    },
+    {
+      "epoch": 0.23804463336875664,
+      "grad_norm": 0.9465979933738708,
+      "learning_rate": 9.873140143255035e-06,
+      "loss": 0.9104,
+      "step": 84
+    },
+    {
+      "epoch": 0.24087849805171804,
+      "grad_norm": 1.032097339630127,
+      "learning_rate": 9.867822909444435e-06,
+      "loss": 0.8579,
+      "step": 85
+    },
+    {
+      "epoch": 0.24371236273467942,
+      "grad_norm": 0.9364420771598816,
+      "learning_rate": 9.862398009085511e-06,
+      "loss": 0.9317,
+      "step": 86
+    },
+    {
+      "epoch": 0.24654622741764082,
+      "grad_norm": 0.9894245862960815,
+      "learning_rate": 9.856865562166256e-06,
+      "loss": 0.8944,
+      "step": 87
+    },
+    {
+      "epoch": 0.2493800921006022,
+      "grad_norm": 0.9810971617698669,
+      "learning_rate": 9.851225691053382e-06,
+      "loss": 0.8175,
+      "step": 88
+    },
+    {
+      "epoch": 0.25221395678356356,
+      "grad_norm": 1.3583261966705322,
+      "learning_rate": 9.8454785204896e-06,
+      "loss": 0.9031,
+      "step": 89
+    },
+    {
+      "epoch": 0.255047821466525,
+      "grad_norm": 1.0423613786697388,
+      "learning_rate": 9.83962417759088e-06,
+      "loss": 0.9194,
+      "step": 90
+    },
+    {
+      "epoch": 0.25788168614948637,
+      "grad_norm": 0.9881994128227234,
+      "learning_rate": 9.833662791843628e-06,
+      "loss": 0.9088,
+      "step": 91
+    },
+    {
+      "epoch": 0.26071555083244774,
+      "grad_norm": 0.937030017375946,
+      "learning_rate": 9.827594495101824e-06,
+      "loss": 0.9086,
+      "step": 92
+    },
+    {
+      "epoch": 0.2635494155154091,
+      "grad_norm": 1.018686056137085,
+      "learning_rate": 9.821419421584108e-06,
+      "loss": 0.9539,
+      "step": 93
+    },
+    {
+      "epoch": 0.26638328019837054,
+      "grad_norm": 0.9911724925041199,
+      "learning_rate": 9.815137707870806e-06,
+      "loss": 0.9241,
+      "step": 94
+    },
+    {
+      "epoch": 0.2692171448813319,
+      "grad_norm": 1.02268385887146,
+      "learning_rate": 9.808749492900917e-06,
+      "loss": 0.8745,
+      "step": 95
+    },
+    {
+      "epoch": 0.2720510095642933,
+      "grad_norm": 0.9069863557815552,
+      "learning_rate": 9.802254917969033e-06,
+      "loss": 0.8907,
+      "step": 96
+    },
+    {
+      "epoch": 0.2748848742472547,
+      "grad_norm": 1.0000213384628296,
+      "learning_rate": 9.795654126722218e-06,
+      "loss": 0.9076,
+      "step": 97
+    },
+    {
+      "epoch": 0.2777187389302161,
+      "grad_norm": 1.0041557550430298,
+      "learning_rate": 9.788947265156828e-06,
+      "loss": 0.9173,
+      "step": 98
+    },
+    {
+      "epoch": 0.28055260361317746,
+      "grad_norm": 1.1171513795852661,
+      "learning_rate": 9.782134481615282e-06,
+      "loss": 0.9812,
+      "step": 99
+    },
+    {
+      "epoch": 0.28338646829613884,
+      "grad_norm": 0.9173958897590637,
+      "learning_rate": 9.775215926782788e-06,
+      "loss": 0.9067,
+      "step": 100
+    },
+    {
+      "epoch": 0.28338646829613884,
+      "eval_loss": 0.8711490631103516,
+      "eval_runtime": 110.273,
+      "eval_samples_per_second": 21.556,
+      "eval_steps_per_second": 1.351,
+      "step": 100
+    },
+    {
+      "epoch": 0.28622033297910027,
+      "grad_norm": 0.9922642111778259,
+      "learning_rate": 9.768191753683997e-06,
+      "loss": 0.8987,
+      "step": 101
+    },
+    {
+      "epoch": 0.28905419766206164,
+      "grad_norm": 0.9484046697616577,
+      "learning_rate": 9.761062117679632e-06,
+      "loss": 0.8885,
+      "step": 102
+    },
+    {
+      "epoch": 0.291888062345023,
+      "grad_norm": 1.0182386636734009,
+      "learning_rate": 9.75382717646304e-06,
+      "loss": 0.9161,
+      "step": 103
+    },
+    {
+      "epoch": 0.2947219270279844,
+      "grad_norm": 0.9028820395469666,
+      "learning_rate": 9.746487090056712e-06,
+      "loss": 0.858,
+      "step": 104
+    },
+    {
+      "epoch": 0.2975557917109458,
+      "grad_norm": 0.9766146540641785,
+      "learning_rate": 9.739042020808746e-06,
+      "loss": 0.8162,
+      "step": 105
+    },
+    {
+      "epoch": 0.3003896563939072,
+      "grad_norm": 0.987703263759613,
+      "learning_rate": 9.73149213338924e-06,
+      "loss": 0.9206,
+      "step": 106
+    },
+    {
+      "epoch": 0.30322352107686856,
+      "grad_norm": 0.9521070718765259,
+      "learning_rate": 9.72383759478667e-06,
+      "loss": 0.9204,
+      "step": 107
+    },
+    {
+      "epoch": 0.30605738575983,
+      "grad_norm": 0.9196562767028809,
+      "learning_rate": 9.71607857430419e-06,
+      "loss": 0.9306,
+      "step": 108
+    },
+    {
+      "epoch": 0.30889125044279137,
+      "grad_norm": 0.9661755561828613,
+      "learning_rate": 9.708215243555875e-06,
+      "loss": 0.9194,
+      "step": 109
+    },
+    {
+      "epoch": 0.31172511512575274,
+      "grad_norm": 0.9685959815979004,
+      "learning_rate": 9.700247776462944e-06,
+      "loss": 0.8837,
+      "step": 110
+    },
+    {
+      "epoch": 0.3145589798087141,
+      "grad_norm": 0.9824734926223755,
+      "learning_rate": 9.6921763492499e-06,
+      "loss": 0.8726,
+      "step": 111
+    },
+    {
+      "epoch": 0.31739284449167554,
+      "grad_norm": 1.0415219068527222,
+      "learning_rate": 9.68400114044064e-06,
+      "loss": 0.9027,
+      "step": 112
+    },
+    {
+      "epoch": 0.3202267091746369,
+      "grad_norm": 0.9248819351196289,
+      "learning_rate": 9.6757223308545e-06,
+      "loss": 0.8779,
+      "step": 113
+    },
+    {
+      "epoch": 0.3230605738575983,
+      "grad_norm": 0.9205273985862732,
+      "learning_rate": 9.667340103602263e-06,
+      "loss": 0.9192,
+      "step": 114
+    },
+    {
+      "epoch": 0.32589443854055966,
+      "grad_norm": 0.9548845291137695,
+      "learning_rate": 9.658854644082099e-06,
+      "loss": 0.8706,
+      "step": 115
+    },
+    {
+      "epoch": 0.3287283032235211,
+      "grad_norm": 1.0803402662277222,
+      "learning_rate": 9.650266139975474e-06,
+      "loss": 0.8442,
+      "step": 116
+    },
+    {
+      "epoch": 0.33156216790648246,
+      "grad_norm": 1.0031402111053467,
+      "learning_rate": 9.641574781242999e-06,
+      "loss": 0.8932,
+      "step": 117
+    },
+    {
+      "epoch": 0.33439603258944384,
+      "grad_norm": 0.8850711584091187,
+      "learning_rate": 9.632780760120217e-06,
+      "loss": 0.8238,
+      "step": 118
+    },
+    {
+      "epoch": 0.33722989727240527,
+      "grad_norm": 0.9834924936294556,
+      "learning_rate": 9.62388427111336e-06,
+      "loss": 0.9185,
+      "step": 119
+    },
+    {
+      "epoch": 0.34006376195536664,
+      "grad_norm": 0.9972984194755554,
+      "learning_rate": 9.614885510995047e-06,
+      "loss": 0.8748,
+      "step": 120
+    },
+    {
+      "epoch": 0.342897626638328,
+      "grad_norm": 0.9789429903030396,
+      "learning_rate": 9.605784678799934e-06,
+      "loss": 0.9251,
+      "step": 121
+    },
+    {
+      "epoch": 0.3457314913212894,
+      "grad_norm": 0.9524829387664795,
+      "learning_rate": 9.596581975820304e-06,
+      "loss": 0.8858,
+      "step": 122
+    },
+    {
+      "epoch": 0.3485653560042508,
+      "grad_norm": 0.9904320240020752,
+      "learning_rate": 9.587277605601617e-06,
+      "loss": 0.9763,
+      "step": 123
+    },
+    {
+      "epoch": 0.3513992206872122,
+      "grad_norm": 0.9940752387046814,
+      "learning_rate": 9.577871773938013e-06,
+      "loss": 0.8892,
+      "step": 124
+    },
+    {
+      "epoch": 0.35423308537017356,
+      "grad_norm": 0.9502999186515808,
+      "learning_rate": 9.568364688867757e-06,
+      "loss": 0.8565,
+      "step": 125
+    },
+    {
+      "epoch": 0.357066950053135,
+      "grad_norm": 1.0443921089172363,
+      "learning_rate": 9.558756560668637e-06,
+      "loss": 0.9438,
+      "step": 126
+    },
+    {
+      "epoch": 0.35990081473609636,
+      "grad_norm": 0.9201401472091675,
+      "learning_rate": 9.549047601853313e-06,
+      "loss": 0.8816,
+      "step": 127
+    },
+    {
+      "epoch": 0.36273467941905774,
+      "grad_norm": 0.9527130722999573,
+      "learning_rate": 9.539238027164618e-06,
+      "loss": 0.8877,
+      "step": 128
+    },
+    {
+      "epoch": 0.3655685441020191,
+      "grad_norm": 0.9892840385437012,
+      "learning_rate": 9.52932805357081e-06,
+      "loss": 0.8589,
+      "step": 129
+    },
+    {
+      "epoch": 0.36840240878498054,
+      "grad_norm": 0.8773977160453796,
+      "learning_rate": 9.519317900260769e-06,
+      "loss": 0.8819,
+      "step": 130
+    },
+    {
+      "epoch": 0.3712362734679419,
+      "grad_norm": 0.9664667248725891,
+      "learning_rate": 9.509207788639148e-06,
+      "loss": 0.8913,
+      "step": 131
+    },
+    {
+      "epoch": 0.3740701381509033,
+      "grad_norm": 0.9697229266166687,
+      "learning_rate": 9.498997942321484e-06,
+      "loss": 0.9421,
+      "step": 132
+    },
+    {
+      "epoch": 0.37690400283386466,
+      "grad_norm": 0.9921510815620422,
+      "learning_rate": 9.488688587129243e-06,
+      "loss": 0.9171,
+      "step": 133
+    },
+    {
+      "epoch": 0.3797378675168261,
+      "grad_norm": 0.9424541592597961,
+      "learning_rate": 9.47827995108483e-06,
+      "loss": 0.8913,
+      "step": 134
+    },
+    {
+      "epoch": 0.38257173219978746,
+      "grad_norm": 0.9468593597412109,
+      "learning_rate": 9.467772264406545e-06,
+      "loss": 0.9035,
+      "step": 135
+    },
+    {
+      "epoch": 0.38540559688274884,
+      "grad_norm": 0.9279436469078064,
+      "learning_rate": 9.457165759503492e-06,
+      "loss": 0.8352,
+      "step": 136
+    },
+    {
+      "epoch": 0.38823946156571026,
+      "grad_norm": 0.9004291892051697,
+      "learning_rate": 9.446460670970436e-06,
+      "loss": 0.9033,
+      "step": 137
+    },
+    {
+      "epoch": 0.39107332624867164,
+      "grad_norm": 0.9809132218360901,
+      "learning_rate": 9.435657235582616e-06,
+      "loss": 0.8699,
+      "step": 138
+    },
+    {
+      "epoch": 0.393907190931633,
+      "grad_norm": 0.94579017162323,
+      "learning_rate": 9.424755692290507e-06,
+      "loss": 0.8883,
+      "step": 139
+    },
+    {
+      "epoch": 0.3967410556145944,
+      "grad_norm": 0.9461862444877625,
+      "learning_rate": 9.413756282214538e-06,
+      "loss": 0.9009,
+      "step": 140
+    },
+    {
+      "epoch": 0.3995749202975558,
+      "grad_norm": 1.2299482822418213,
+      "learning_rate": 9.402659248639749e-06,
+      "loss": 0.827,
+      "step": 141
+    },
+    {
+      "epoch": 0.4024087849805172,
+      "grad_norm": 0.9449498653411865,
+      "learning_rate": 9.391464837010428e-06,
+      "loss": 0.8574,
+      "step": 142
+    },
+    {
+      "epoch": 0.40524264966347856,
+      "grad_norm": 0.9360131025314331,
+      "learning_rate": 9.380173294924661e-06,
+      "loss": 0.8715,
+      "step": 143
+    },
+    {
+      "epoch": 0.40807651434643993,
+      "grad_norm": 1.9693893194198608,
+      "learning_rate": 9.368784872128877e-06,
+      "loss": 0.8388,
+      "step": 144
+    },
+    {
+      "epoch": 0.41091037902940136,
+      "grad_norm": 0.9797636270523071,
+      "learning_rate": 9.357299820512305e-06,
+      "loss": 0.8761,
+      "step": 145
+    },
+    {
+      "epoch": 0.41374424371236274,
+      "grad_norm": 0.9161531925201416,
+      "learning_rate": 9.345718394101412e-06,
+      "loss": 0.8625,
+      "step": 146
+    },
+    {
+      "epoch": 0.4165781083953241,
+      "grad_norm": 0.9349712133407593,
+      "learning_rate": 9.334040849054288e-06,
+      "loss": 0.9152,
+      "step": 147
+    },
+    {
+      "epoch": 0.41941197307828554,
+      "grad_norm": 0.9681140184402466,
+      "learning_rate": 9.322267443654974e-06,
+      "loss": 0.9204,
+      "step": 148
+    },
+    {
+      "epoch": 0.4222458377612469,
+      "grad_norm": 0.9043005108833313,
+      "learning_rate": 9.310398438307747e-06,
+      "loss": 0.8562,
+      "step": 149
+    },
+    {
+      "epoch": 0.4250797024442083,
+      "grad_norm": 0.970501184463501,
+      "learning_rate": 9.29843409553137e-06,
+      "loss": 0.8587,
+      "step": 150
+    },
+    {
+      "epoch": 0.42791356712716966,
+      "grad_norm": 0.9835172295570374,
+      "learning_rate": 9.286374679953278e-06,
+      "loss": 0.8605,
+      "step": 151
+    },
+    {
+      "epoch": 0.4307474318101311,
+      "grad_norm": 0.9757922291755676,
+      "learning_rate": 9.274220458303727e-06,
+      "loss": 0.9081,
+      "step": 152
+    },
+    {
+      "epoch": 0.43358129649309246,
+      "grad_norm": 0.988153874874115,
+      "learning_rate": 9.261971699409893e-06,
+      "loss": 0.8824,
+      "step": 153
+    },
+    {
+      "epoch": 0.43641516117605383,
+      "grad_norm": 0.8909916281700134,
+      "learning_rate": 9.249628674189928e-06,
+      "loss": 0.9167,
+      "step": 154
+    },
+    {
+      "epoch": 0.4392490258590152,
+      "grad_norm": 1.0242557525634766,
+      "learning_rate": 9.237191655646972e-06,
+      "loss": 0.8599,
+      "step": 155
+    },
+    {
+      "epoch": 0.44208289054197664,
+      "grad_norm": 0.9305148720741272,
+      "learning_rate": 9.224660918863104e-06,
+      "loss": 0.852,
+      "step": 156
+    },
+    {
+      "epoch": 0.444916755224938,
+      "grad_norm": 0.9896242022514343,
+      "learning_rate": 9.212036740993265e-06,
+      "loss": 0.8922,
+      "step": 157
+    },
+    {
+      "epoch": 0.4477506199078994,
+      "grad_norm": 0.9332566261291504,
+      "learning_rate": 9.199319401259132e-06,
+      "loss": 0.9058,
+      "step": 158
+    },
+    {
+      "epoch": 0.4505844845908608,
+      "grad_norm": 1.0046119689941406,
+      "learning_rate": 9.186509180942928e-06,
+      "loss": 0.8837,
+      "step": 159
+    },
+    {
+      "epoch": 0.4534183492738222,
+      "grad_norm": 0.9911741018295288,
+      "learning_rate": 9.173606363381218e-06,
+      "loss": 0.8802,
+      "step": 160
+    },
+    {
+      "epoch": 0.45625221395678356,
+      "grad_norm": 0.9198329448699951,
+      "learning_rate": 9.16061123395863e-06,
+      "loss": 0.8211,
+      "step": 161
+    },
+    {
+      "epoch": 0.45908607863974493,
+      "grad_norm": 0.9350652694702148,
+      "learning_rate": 9.147524080101543e-06,
+      "loss": 0.8814,
+      "step": 162
+    },
+    {
+      "epoch": 0.46191994332270636,
+      "grad_norm": 0.9083648324012756,
+      "learning_rate": 9.134345191271742e-06,
+      "loss": 0.9003,
+      "step": 163
+    },
+    {
+      "epoch": 0.46475380800566773,
+      "grad_norm": 0.9515282511711121,
+      "learning_rate": 9.121074858959997e-06,
+      "loss": 0.8874,
+      "step": 164
+    },
+    {
+      "epoch": 0.4675876726886291,
+      "grad_norm": 0.9363572597503662,
+      "learning_rate": 9.107713376679634e-06,
+      "loss": 0.9413,
+      "step": 165
+    },
+    {
+      "epoch": 0.4704215373715905,
+      "grad_norm": 1.0453206300735474,
+      "learning_rate": 9.094261039960028e-06,
+      "loss": 0.9106,
+      "step": 166
+    },
+    {
+      "epoch": 0.4732554020545519,
+      "grad_norm": 0.9409400224685669,
+      "learning_rate": 9.08071814634008e-06,
+      "loss": 0.843,
+      "step": 167
+    },
+    {
+      "epoch": 0.4760892667375133,
+      "grad_norm": 0.9143967628479004,
+      "learning_rate": 9.067084995361623e-06,
+      "loss": 0.8242,
+      "step": 168
+    },
+    {
+      "epoch": 0.47892313142047466,
+      "grad_norm": 0.9733567237854004,
+      "learning_rate": 9.053361888562807e-06,
+      "loss": 0.8825,
+      "step": 169
+    },
+    {
+      "epoch": 0.4817569961034361,
+      "grad_norm": 0.933316707611084,
+      "learning_rate": 9.039549129471423e-06,
+      "loss": 0.8492,
+      "step": 170
+    },
+    {
+      "epoch": 0.48459086078639746,
+      "grad_norm": 0.9519788026809692,
+      "learning_rate": 9.025647023598196e-06,
+      "loss": 0.8757,
+      "step": 171
+    },
+    {
+      "epoch": 0.48742472546935883,
+      "grad_norm": 0.9824965000152588,
+      "learning_rate": 9.011655878430018e-06,
+      "loss": 0.8628,
+      "step": 172
+    },
+    {
+      "epoch": 0.4902585901523202,
+      "grad_norm": 0.9327204823493958,
+      "learning_rate": 8.99757600342316e-06,
+      "loss": 0.8765,
+      "step": 173
+    },
+    {
+      "epoch": 0.49309245483528164,
+      "grad_norm": 0.9332249164581299,
+      "learning_rate": 8.983407709996415e-06,
+      "loss": 0.88,
+      "step": 174
+    },
+    {
+      "epoch": 0.495926319518243,
+      "grad_norm": 0.9456924796104431,
+      "learning_rate": 8.969151311524215e-06,
+      "loss": 0.9361,
+      "step": 175
+    },
+    {
+      "epoch": 0.4987601842012044,
+      "grad_norm": 0.936154842376709,
+      "learning_rate": 8.954807123329703e-06,
+      "loss": 0.8749,
+      "step": 176
+    },
+    {
+      "epoch": 0.5015940488841658,
+      "grad_norm": 0.923202395439148,
+      "learning_rate": 8.940375462677758e-06,
+      "loss": 0.9378,
+      "step": 177
+    },
+    {
+      "epoch": 0.5044279135671271,
+      "grad_norm": 0.9998725652694702,
+      "learning_rate": 8.92585664876797e-06,
+      "loss": 0.9264,
+      "step": 178
+    },
+    {
+      "epoch": 0.5072617782500886,
+      "grad_norm": 0.917499303817749,
+      "learning_rate": 8.911251002727588e-06,
+      "loss": 0.8517,
+      "step": 179
+    },
+    {
+      "epoch": 0.51009564293305,
+      "grad_norm": 0.8643101453781128,
+      "learning_rate": 8.896558847604414e-06,
+      "loss": 0.8069,
+      "step": 180
+    },
+    {
+      "epoch": 0.5129295076160113,
+      "grad_norm": 0.9328122138977051,
+      "learning_rate": 8.881780508359661e-06,
+      "loss": 0.941,
+      "step": 181
+    },
+    {
+      "epoch": 0.5157633722989727,
+      "grad_norm": 0.9767406582832336,
+      "learning_rate": 8.86691631186076e-06,
+      "loss": 0.875,
+      "step": 182
+    },
+    {
+      "epoch": 0.5185972369819342,
+      "grad_norm": 0.9218102693557739,
+      "learning_rate": 8.851966586874138e-06,
+      "loss": 0.8271,
+      "step": 183
+    },
+    {
+      "epoch": 0.5214311016648955,
+      "grad_norm": 0.9587806463241577,
+      "learning_rate": 8.836931664057935e-06,
+      "loss": 0.8999,
+      "step": 184
+    },
+    {
+      "epoch": 0.5242649663478569,
+      "grad_norm": 0.9345144629478455,
+      "learning_rate": 8.821811875954705e-06,
+      "loss": 0.8953,
+      "step": 185
+    },
+    {
+      "epoch": 0.5270988310308182,
+      "grad_norm": 0.9228772521018982,
+      "learning_rate": 8.806607556984045e-06,
+      "loss": 0.8564,
+      "step": 186
+    },
+    {
+      "epoch": 0.5299326957137797,
+      "grad_norm": 0.9359504580497742,
+      "learning_rate": 8.791319043435213e-06,
+      "loss": 0.7903,
+      "step": 187
+    },
+    {
+      "epoch": 0.5327665603967411,
+      "grad_norm": 0.9229147434234619,
+      "learning_rate": 8.775946673459682e-06,
+      "loss": 0.8668,
+      "step": 188
+    },
+    {
+      "epoch": 0.5356004250797024,
+      "grad_norm": 0.9776359796524048,
+      "learning_rate": 8.76049078706366e-06,
+      "loss": 0.9419,
+      "step": 189
+    },
+    {
+      "epoch": 0.5384342897626638,
+      "grad_norm": 0.8932283520698547,
+      "learning_rate": 8.744951726100572e-06,
+      "loss": 0.8628,
+      "step": 190
+    },
+    {
+      "epoch": 0.5412681544456253,
+      "grad_norm": 0.9139344096183777,
+      "learning_rate": 8.729329834263503e-06,
+      "loss": 0.805,
+      "step": 191
+    },
+    {
+      "epoch": 0.5441020191285866,
+      "grad_norm": 0.9210391640663147,
+      "learning_rate": 8.713625457077585e-06,
+      "loss": 0.8818,
+      "step": 192
+    },
+    {
+      "epoch": 0.546935883811548,
+      "grad_norm": 0.9402296543121338,
+      "learning_rate": 8.697838941892371e-06,
+      "loss": 0.9034,
+      "step": 193
+    },
+    {
+      "epoch": 0.5497697484945094,
+      "grad_norm": 1.0865598917007446,
+      "learning_rate": 8.681970637874131e-06,
+      "loss": 0.8896,
+      "step": 194
+    },
+    {
+      "epoch": 0.5526036131774708,
+      "grad_norm": 0.9529604315757751,
+      "learning_rate": 8.666020895998154e-06,
+      "loss": 0.9213,
+      "step": 195
+    },
+    {
+      "epoch": 0.5554374778604322,
+      "grad_norm": 0.9938436150550842,
+      "learning_rate": 8.64999006904096e-06,
+      "loss": 0.9068,
+      "step": 196
+    },
+    {
+      "epoch": 0.5582713425433935,
+      "grad_norm": 0.9383383989334106,
+      "learning_rate": 8.63387851157252e-06,
+      "loss": 0.8667,
+      "step": 197
+    },
+    {
+      "epoch": 0.5611052072263549,
+      "grad_norm": 0.9018294811248779,
+      "learning_rate": 8.617686579948396e-06,
+      "loss": 0.8427,
+      "step": 198
+    },
+    {
+      "epoch": 0.5639390719093164,
+      "grad_norm": 0.9647362232208252,
+      "learning_rate": 8.60141463230187e-06,
+      "loss": 0.8754,
+      "step": 199
+    },
+    {
+      "epoch": 0.5667729365922777,
+      "grad_norm": 0.9192838668823242,
+      "learning_rate": 8.585063028536015e-06,
+      "loss": 0.9108,
+      "step": 200
+    },
+    {
+      "epoch": 0.5667729365922777,
+      "eval_loss": 0.8534573316574097,
+      "eval_runtime": 42.1386,
+      "eval_samples_per_second": 56.409,
+      "eval_steps_per_second": 3.536,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 704,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0197637094501253e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d244f5d1a7b24dd489d79b460c6594031202dd37ec1c9f1d7702364087fdc32
+size 6712

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, 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 param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               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_file, 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_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--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_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)