Training in progress, epoch 1, checkpoint

checkpoint-1074/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
+}

checkpoint-1074/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-1074/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": "4.49.0"
+}

checkpoint-1074/global_step1073/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c7635333ec24afecef9257b41601b1fb236bd992a5b1c85bfa3c67cc132945
+size 11423429708

checkpoint-1074/global_step1073/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc5a32ed054b3d5b976e049d1b1a3bc1ed10b73686181f5733c90a7c328834d
+size 11423429708

checkpoint-1074/global_step1073/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741f974b863c80e7453aa2e464facea354d13aae07aaf6f9faea849f6e22ec2d
+size 11423429708

checkpoint-1074/global_step1073/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acfaf60bee79e1940018a302002ce12c8670903206f97a65103979314618bc95
+size 11423429708

checkpoint-1074/global_step1073/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eae61b538cd8d40be8ba567553356d6e211303683420d81bcc532177a12678e
+size 11423429708

checkpoint-1074/global_step1073/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415223fbd80a1a234e0d9319c9aca3bccb2ca1ac3a0c79414f4148cf57665815
+size 11423429708

checkpoint-1074/global_step1073/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38cef8a4a4bf3ff6aac5f44817fba510c231d2244ebbaa912515803d9e43e3a0
+size 11423429708

checkpoint-1074/global_step1073/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581fabbcc8576f24ff9845937803e6bdbb728f00c5be82dce416a41c509f62dd
+size 11423429708

checkpoint-1074/global_step1073/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825ab13fb43de2139be2ad647540670d9cb764f76d2174d45921162d06405037
+size 164885

checkpoint-1074/global_step1073/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18b24451acad4fb51c0f3d75af7bda43e000e6726682c4246599e0461137bfed
+size 164885

checkpoint-1074/global_step1073/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35c22edbd6cede5d2fe1b4fddde91325f4591a51a3baf2064b68b29f71a60b7
+size 164885

checkpoint-1074/global_step1073/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66279d3f91006f9f4fc141bc4008ffd3a253895e05fdfc7550e350d3f4c775d5
+size 164885

checkpoint-1074/global_step1073/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8825723d4f0e19b7489c8c106248ba71b72dd649befa07293d94e544e7fb20ee
+size 164885

checkpoint-1074/global_step1073/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849643b822c74b4fc2be81ed9c8024c8b6e232ddc3f681b1ff5970ffa7481e20
+size 164885

checkpoint-1074/global_step1073/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8672e841a38539ab3303f65b7f510fc6067e386b30ea98fe05f1229927ab5258
+size 164885

checkpoint-1074/global_step1073/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084cede25d0ff855e783b514f2a1b740140ba33f4e2a42ea521052aa618ebf02
+size 164885

checkpoint-1074/latest

@@ -0,0 +1 @@
+global_step1073

checkpoint-1074/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5bdc04463eab4cb2ee58117300789ad8a809c21b890679e82a471443389d623
+size 4877660776

checkpoint-1074/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a2932aed2fa3a5f4ea41ae09fdecfb6b3c7ea40c5c8dcf7860b98d9b1585ff
+size 4932751008

checkpoint-1074/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7f19431993f72e73c3efb32612351b9b383fed916da25e13d7224175a3f8ae
+size 4330865200

checkpoint-1074/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7ca9f26c1a93de9e4aa95a101739a963408cd839d2e49df8f5decd4628e908
+size 1089994880

checkpoint-1074/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

checkpoint-1074/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575119a228f98110923ffa2dedcb50e3317251b26054355d015e0b2240d566f2
+size 15984

checkpoint-1074/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0728b56dab7abb5ef8a0d4bae3519c5767c97467bdd886d26bf19cc8599d0312
+size 15984

checkpoint-1074/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e481d4ef1546694da7337f6bb6c658b866dcb79b85deeb477da0d27ebe851e
+size 15984

checkpoint-1074/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353c60be37ea56fc992fca446598ceca5d1fd002aa3bd6dbb9ad740e6f47ebb3
+size 15984

checkpoint-1074/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9107fe964ba7205e354084b85210e5a5ea1c98cfd4d38adb9cd3926945dcae4
+size 15984

checkpoint-1074/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d1bb1abee38b92e53f3f23549b642ce0f1edcdccf7b6129847ac61636e96d5
+size 15984

checkpoint-1074/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd5516048e20f36959601574e29e40106085a7d3cdc7bf425ce5e84633490e6
+size 15984

checkpoint-1074/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2c46927fc06939b4c976a01e4b95dec1f8b98ceaea86d31a5d756fc30ff006
+size 15984

checkpoint-1074/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57606794dee9a90df702f33dd592ea78d14796e587cadb0c4dafc213bf45eeaf
+size 1064

checkpoint-1074/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

checkpoint-1074/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-1074/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",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1074/trainer_state.json

@@ -0,0 +1,1531 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1074,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004657661853749418,
+      "grad_norm": 6.870879240202262,
+      "learning_rate": 5.813953488372093e-07,
+      "loss": 0.8094,
+      "step": 5
+    },
+    {
+      "epoch": 0.009315323707498836,
+      "grad_norm": 4.924081616093864,
+      "learning_rate": 1.1627906976744186e-06,
+      "loss": 0.7888,
+      "step": 10
+    },
+    {
+      "epoch": 0.013972985561248253,
+      "grad_norm": 2.2003985809636784,
+      "learning_rate": 1.744186046511628e-06,
+      "loss": 0.7124,
+      "step": 15
+    },
+    {
+      "epoch": 0.018630647414997672,
+      "grad_norm": 3.384961223741369,
+      "learning_rate": 2.325581395348837e-06,
+      "loss": 0.6809,
+      "step": 20
+    },
+    {
+      "epoch": 0.02328830926874709,
+      "grad_norm": 1.496599205425148,
+      "learning_rate": 2.9069767441860468e-06,
+      "loss": 0.6532,
+      "step": 25
+    },
+    {
+      "epoch": 0.027945971122496506,
+      "grad_norm": 1.1804865478694602,
+      "learning_rate": 3.488372093023256e-06,
+      "loss": 0.6183,
+      "step": 30
+    },
+    {
+      "epoch": 0.032603632976245925,
+      "grad_norm": 0.9117707500812657,
+      "learning_rate": 4.0697674418604655e-06,
+      "loss": 0.5981,
+      "step": 35
+    },
+    {
+      "epoch": 0.037261294829995344,
+      "grad_norm": 0.7310133229873329,
+      "learning_rate": 4.651162790697674e-06,
+      "loss": 0.5749,
+      "step": 40
+    },
+    {
+      "epoch": 0.04191895668374476,
+      "grad_norm": 0.5645281258846301,
+      "learning_rate": 5.232558139534884e-06,
+      "loss": 0.5345,
+      "step": 45
+    },
+    {
+      "epoch": 0.04657661853749418,
+      "grad_norm": 0.6982147231953743,
+      "learning_rate": 5.8139534883720935e-06,
+      "loss": 0.5348,
+      "step": 50
+    },
+    {
+      "epoch": 0.05123428039124359,
+      "grad_norm": 0.5574357407056741,
+      "learning_rate": 6.395348837209303e-06,
+      "loss": 0.5216,
+      "step": 55
+    },
+    {
+      "epoch": 0.05589194224499301,
+      "grad_norm": 0.506438110844852,
+      "learning_rate": 6.976744186046512e-06,
+      "loss": 0.5167,
+      "step": 60
+    },
+    {
+      "epoch": 0.06054960409874243,
+      "grad_norm": 0.5862240903769983,
+      "learning_rate": 7.558139534883721e-06,
+      "loss": 0.5089,
+      "step": 65
+    },
+    {
+      "epoch": 0.06520726595249185,
+      "grad_norm": 0.4649805661733201,
+      "learning_rate": 8.139534883720931e-06,
+      "loss": 0.4882,
+      "step": 70
+    },
+    {
+      "epoch": 0.06986492780624126,
+      "grad_norm": 0.46478952298966486,
+      "learning_rate": 8.72093023255814e-06,
+      "loss": 0.4901,
+      "step": 75
+    },
+    {
+      "epoch": 0.07452258965999069,
+      "grad_norm": 0.560709517178079,
+      "learning_rate": 9.302325581395349e-06,
+      "loss": 0.5013,
+      "step": 80
+    },
+    {
+      "epoch": 0.0791802515137401,
+      "grad_norm": 0.4989636911378994,
+      "learning_rate": 9.883720930232558e-06,
+      "loss": 0.4802,
+      "step": 85
+    },
+    {
+      "epoch": 0.08383791336748952,
+      "grad_norm": 0.6665552046761866,
+      "learning_rate": 1.0465116279069768e-05,
+      "loss": 0.4868,
+      "step": 90
+    },
+    {
+      "epoch": 0.08849557522123894,
+      "grad_norm": 0.4983755493703489,
+      "learning_rate": 1.1046511627906977e-05,
+      "loss": 0.4916,
+      "step": 95
+    },
+    {
+      "epoch": 0.09315323707498836,
+      "grad_norm": 0.5769629148267977,
+      "learning_rate": 1.1627906976744187e-05,
+      "loss": 0.4824,
+      "step": 100
+    },
+    {
+      "epoch": 0.09781089892873777,
+      "grad_norm": 0.7895692315023841,
+      "learning_rate": 1.2209302325581395e-05,
+      "loss": 0.4851,
+      "step": 105
+    },
+    {
+      "epoch": 0.10246856078248719,
+      "grad_norm": 0.5692473242183461,
+      "learning_rate": 1.2790697674418606e-05,
+      "loss": 0.4739,
+      "step": 110
+    },
+    {
+      "epoch": 0.10712622263623661,
+      "grad_norm": 0.6085763180358597,
+      "learning_rate": 1.3372093023255814e-05,
+      "loss": 0.474,
+      "step": 115
+    },
+    {
+      "epoch": 0.11178388448998602,
+      "grad_norm": 0.49834588880390257,
+      "learning_rate": 1.3953488372093024e-05,
+      "loss": 0.4853,
+      "step": 120
+    },
+    {
+      "epoch": 0.11644154634373545,
+      "grad_norm": 0.5752937490737003,
+      "learning_rate": 1.4534883720930233e-05,
+      "loss": 0.4658,
+      "step": 125
+    },
+    {
+      "epoch": 0.12109920819748486,
+      "grad_norm": 0.5825629199000416,
+      "learning_rate": 1.5116279069767441e-05,
+      "loss": 0.4684,
+      "step": 130
+    },
+    {
+      "epoch": 0.1257568700512343,
+      "grad_norm": 0.6505924396768823,
+      "learning_rate": 1.569767441860465e-05,
+      "loss": 0.4755,
+      "step": 135
+    },
+    {
+      "epoch": 0.1304145319049837,
+      "grad_norm": 0.5855296478402816,
+      "learning_rate": 1.6279069767441862e-05,
+      "loss": 0.4692,
+      "step": 140
+    },
+    {
+      "epoch": 0.1350721937587331,
+      "grad_norm": 0.5687787204897745,
+      "learning_rate": 1.686046511627907e-05,
+      "loss": 0.4789,
+      "step": 145
+    },
+    {
+      "epoch": 0.13972985561248252,
+      "grad_norm": 0.6540863380333346,
+      "learning_rate": 1.744186046511628e-05,
+      "loss": 0.4734,
+      "step": 150
+    },
+    {
+      "epoch": 0.14438751746623196,
+      "grad_norm": 0.6092140224170801,
+      "learning_rate": 1.802325581395349e-05,
+      "loss": 0.456,
+      "step": 155
+    },
+    {
+      "epoch": 0.14904517931998137,
+      "grad_norm": 0.8341054860265317,
+      "learning_rate": 1.8604651162790697e-05,
+      "loss": 0.4631,
+      "step": 160
+    },
+    {
+      "epoch": 0.1537028411737308,
+      "grad_norm": 0.7688234232175349,
+      "learning_rate": 1.918604651162791e-05,
+      "loss": 0.4646,
+      "step": 165
+    },
+    {
+      "epoch": 0.1583605030274802,
+      "grad_norm": 0.7887045967709965,
+      "learning_rate": 1.9767441860465116e-05,
+      "loss": 0.4629,
+      "step": 170
+    },
+    {
+      "epoch": 0.1630181648812296,
+      "grad_norm": 0.7366192487813826,
+      "learning_rate": 2.0348837209302328e-05,
+      "loss": 0.4745,
+      "step": 175
+    },
+    {
+      "epoch": 0.16767582673497905,
+      "grad_norm": 0.5963987208885528,
+      "learning_rate": 2.0930232558139536e-05,
+      "loss": 0.4693,
+      "step": 180
+    },
+    {
+      "epoch": 0.17233348858872846,
+      "grad_norm": 0.8949087511029052,
+      "learning_rate": 2.1511627906976744e-05,
+      "loss": 0.468,
+      "step": 185
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 0.715228737490996,
+      "learning_rate": 2.2093023255813955e-05,
+      "loss": 0.4621,
+      "step": 190
+    },
+    {
+      "epoch": 0.18164881229622729,
+      "grad_norm": 0.7298308224415221,
+      "learning_rate": 2.2674418604651163e-05,
+      "loss": 0.4681,
+      "step": 195
+    },
+    {
+      "epoch": 0.18630647414997673,
+      "grad_norm": 0.7235706917514387,
+      "learning_rate": 2.3255813953488374e-05,
+      "loss": 0.4424,
+      "step": 200
+    },
+    {
+      "epoch": 0.19096413600372614,
+      "grad_norm": 0.9035203856401036,
+      "learning_rate": 2.3837209302325582e-05,
+      "loss": 0.4632,
+      "step": 205
+    },
+    {
+      "epoch": 0.19562179785747555,
+      "grad_norm": 0.7058244377300659,
+      "learning_rate": 2.441860465116279e-05,
+      "loss": 0.4533,
+      "step": 210
+    },
+    {
+      "epoch": 0.20027945971122496,
+      "grad_norm": 0.8084191965181484,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4641,
+      "step": 215
+    },
+    {
+      "epoch": 0.20493712156497437,
+      "grad_norm": 0.7398073838925653,
+      "learning_rate": 2.5581395348837212e-05,
+      "loss": 0.4604,
+      "step": 220
+    },
+    {
+      "epoch": 0.2095947834187238,
+      "grad_norm": 0.7739147664108567,
+      "learning_rate": 2.616279069767442e-05,
+      "loss": 0.4637,
+      "step": 225
+    },
+    {
+      "epoch": 0.21425244527247322,
+      "grad_norm": 0.6647136194593267,
+      "learning_rate": 2.674418604651163e-05,
+      "loss": 0.4616,
+      "step": 230
+    },
+    {
+      "epoch": 0.21891010712622264,
+      "grad_norm": 0.8472637795373797,
+      "learning_rate": 2.7325581395348836e-05,
+      "loss": 0.4572,
+      "step": 235
+    },
+    {
+      "epoch": 0.22356776897997205,
+      "grad_norm": 0.7489481861413457,
+      "learning_rate": 2.7906976744186048e-05,
+      "loss": 0.4562,
+      "step": 240
+    },
+    {
+      "epoch": 0.22822543083372146,
+      "grad_norm": 0.7347737497937348,
+      "learning_rate": 2.848837209302326e-05,
+      "loss": 0.4476,
+      "step": 245
+    },
+    {
+      "epoch": 0.2328830926874709,
+      "grad_norm": 1.0185317868148795,
+      "learning_rate": 2.9069767441860467e-05,
+      "loss": 0.4462,
+      "step": 250
+    },
+    {
+      "epoch": 0.2375407545412203,
+      "grad_norm": 1.1964566837628554,
+      "learning_rate": 2.9651162790697678e-05,
+      "loss": 0.4574,
+      "step": 255
+    },
+    {
+      "epoch": 0.24219841639496972,
+      "grad_norm": 0.7999044368182066,
+      "learning_rate": 3.0232558139534883e-05,
+      "loss": 0.4611,
+      "step": 260
+    },
+    {
+      "epoch": 0.24685607824871914,
+      "grad_norm": 0.888517448965973,
+      "learning_rate": 3.081395348837209e-05,
+      "loss": 0.4555,
+      "step": 265
+    },
+    {
+      "epoch": 0.2515137401024686,
+      "grad_norm": 0.7321925595824862,
+      "learning_rate": 3.13953488372093e-05,
+      "loss": 0.4447,
+      "step": 270
+    },
+    {
+      "epoch": 0.25617140195621796,
+      "grad_norm": 0.7849478822550785,
+      "learning_rate": 3.197674418604651e-05,
+      "loss": 0.4607,
+      "step": 275
+    },
+    {
+      "epoch": 0.2608290638099674,
+      "grad_norm": 0.9252924218648645,
+      "learning_rate": 3.2558139534883724e-05,
+      "loss": 0.4495,
+      "step": 280
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "grad_norm": 0.746525581702539,
+      "learning_rate": 3.313953488372093e-05,
+      "loss": 0.4489,
+      "step": 285
+    },
+    {
+      "epoch": 0.2701443875174662,
+      "grad_norm": 0.9794176532334905,
+      "learning_rate": 3.372093023255814e-05,
+      "loss": 0.448,
+      "step": 290
+    },
+    {
+      "epoch": 0.27480204937121566,
+      "grad_norm": 1.027787482140205,
+      "learning_rate": 3.430232558139535e-05,
+      "loss": 0.4425,
+      "step": 295
+    },
+    {
+      "epoch": 0.27945971122496505,
+      "grad_norm": 1.6823476622043991,
+      "learning_rate": 3.488372093023256e-05,
+      "loss": 0.4544,
+      "step": 300
+    },
+    {
+      "epoch": 0.2841173730787145,
+      "grad_norm": 1.0741326435371086,
+      "learning_rate": 3.5465116279069774e-05,
+      "loss": 0.4619,
+      "step": 305
+    },
+    {
+      "epoch": 0.2887750349324639,
+      "grad_norm": 1.1392263742362516,
+      "learning_rate": 3.604651162790698e-05,
+      "loss": 0.4575,
+      "step": 310
+    },
+    {
+      "epoch": 0.2934326967862133,
+      "grad_norm": 0.8009021123489146,
+      "learning_rate": 3.662790697674418e-05,
+      "loss": 0.4462,
+      "step": 315
+    },
+    {
+      "epoch": 0.29809035863996275,
+      "grad_norm": 0.7075570914100712,
+      "learning_rate": 3.7209302325581394e-05,
+      "loss": 0.4525,
+      "step": 320
+    },
+    {
+      "epoch": 0.30274802049371213,
+      "grad_norm": 0.738204557814199,
+      "learning_rate": 3.7790697674418606e-05,
+      "loss": 0.4548,
+      "step": 325
+    },
+    {
+      "epoch": 0.3074056823474616,
+      "grad_norm": 0.8243587646290422,
+      "learning_rate": 3.837209302325582e-05,
+      "loss": 0.4533,
+      "step": 330
+    },
+    {
+      "epoch": 0.312063344201211,
+      "grad_norm": 0.759834959817409,
+      "learning_rate": 3.895348837209303e-05,
+      "loss": 0.4391,
+      "step": 335
+    },
+    {
+      "epoch": 0.3167210060549604,
+      "grad_norm": 0.9066415186966906,
+      "learning_rate": 3.953488372093023e-05,
+      "loss": 0.4523,
+      "step": 340
+    },
+    {
+      "epoch": 0.32137866790870984,
+      "grad_norm": 0.7169608175857892,
+      "learning_rate": 4.0116279069767444e-05,
+      "loss": 0.442,
+      "step": 345
+    },
+    {
+      "epoch": 0.3260363297624592,
+      "grad_norm": 0.6283809589682416,
+      "learning_rate": 4.0697674418604655e-05,
+      "loss": 0.4449,
+      "step": 350
+    },
+    {
+      "epoch": 0.33069399161620866,
+      "grad_norm": 1.0272666066580396,
+      "learning_rate": 4.127906976744187e-05,
+      "loss": 0.4433,
+      "step": 355
+    },
+    {
+      "epoch": 0.3353516534699581,
+      "grad_norm": 1.2035689203281785,
+      "learning_rate": 4.186046511627907e-05,
+      "loss": 0.4533,
+      "step": 360
+    },
+    {
+      "epoch": 0.3400093153237075,
+      "grad_norm": 0.7275910363107583,
+      "learning_rate": 4.2441860465116276e-05,
+      "loss": 0.4531,
+      "step": 365
+    },
+    {
+      "epoch": 0.3446669771774569,
+      "grad_norm": 0.8110406266227441,
+      "learning_rate": 4.302325581395349e-05,
+      "loss": 0.462,
+      "step": 370
+    },
+    {
+      "epoch": 0.3493246390312063,
+      "grad_norm": 0.9413407736463427,
+      "learning_rate": 4.36046511627907e-05,
+      "loss": 0.457,
+      "step": 375
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 0.7760234540526807,
+      "learning_rate": 4.418604651162791e-05,
+      "loss": 0.4444,
+      "step": 380
+    },
+    {
+      "epoch": 0.3586399627387052,
+      "grad_norm": 0.6486931874061582,
+      "learning_rate": 4.476744186046512e-05,
+      "loss": 0.4395,
+      "step": 385
+    },
+    {
+      "epoch": 0.36329762459245457,
+      "grad_norm": 0.7407698893117143,
+      "learning_rate": 4.5348837209302326e-05,
+      "loss": 0.4449,
+      "step": 390
+    },
+    {
+      "epoch": 0.367955286446204,
+      "grad_norm": 0.7363275771012057,
+      "learning_rate": 4.593023255813954e-05,
+      "loss": 0.4401,
+      "step": 395
+    },
+    {
+      "epoch": 0.37261294829995345,
+      "grad_norm": 1.0210883630600998,
+      "learning_rate": 4.651162790697675e-05,
+      "loss": 0.4388,
+      "step": 400
+    },
+    {
+      "epoch": 0.37727061015370283,
+      "grad_norm": 0.6851527658246143,
+      "learning_rate": 4.709302325581396e-05,
+      "loss": 0.4421,
+      "step": 405
+    },
+    {
+      "epoch": 0.3819282720074523,
+      "grad_norm": 0.8013740228194426,
+      "learning_rate": 4.7674418604651164e-05,
+      "loss": 0.4485,
+      "step": 410
+    },
+    {
+      "epoch": 0.38658593386120166,
+      "grad_norm": 0.5968509541729236,
+      "learning_rate": 4.8255813953488375e-05,
+      "loss": 0.4479,
+      "step": 415
+    },
+    {
+      "epoch": 0.3912435957149511,
+      "grad_norm": 0.6733307155095268,
+      "learning_rate": 4.883720930232558e-05,
+      "loss": 0.4389,
+      "step": 420
+    },
+    {
+      "epoch": 0.39590125756870054,
+      "grad_norm": 0.600640735007328,
+      "learning_rate": 4.941860465116279e-05,
+      "loss": 0.4549,
+      "step": 425
+    },
+    {
+      "epoch": 0.4005589194224499,
+      "grad_norm": 0.8606215338924372,
+      "learning_rate": 5e-05,
+      "loss": 0.4483,
+      "step": 430
+    },
+    {
+      "epoch": 0.40521658127619936,
+      "grad_norm": 0.6608626060744474,
+      "learning_rate": 4.9935266701191095e-05,
+      "loss": 0.4519,
+      "step": 435
+    },
+    {
+      "epoch": 0.40987424312994875,
+      "grad_norm": 0.7298672532314161,
+      "learning_rate": 4.987053340238219e-05,
+      "loss": 0.4598,
+      "step": 440
+    },
+    {
+      "epoch": 0.4145319049836982,
+      "grad_norm": 0.7431998786433806,
+      "learning_rate": 4.980580010357328e-05,
+      "loss": 0.4393,
+      "step": 445
+    },
+    {
+      "epoch": 0.4191895668374476,
+      "grad_norm": 1.0105772794674226,
+      "learning_rate": 4.9741066804764374e-05,
+      "loss": 0.4441,
+      "step": 450
+    },
+    {
+      "epoch": 0.423847228691197,
+      "grad_norm": 0.6833723924548186,
+      "learning_rate": 4.967633350595546e-05,
+      "loss": 0.4623,
+      "step": 455
+    },
+    {
+      "epoch": 0.42850489054494645,
+      "grad_norm": 0.7042208062030147,
+      "learning_rate": 4.961160020714656e-05,
+      "loss": 0.4426,
+      "step": 460
+    },
+    {
+      "epoch": 0.43316255239869583,
+      "grad_norm": 0.6134545145230559,
+      "learning_rate": 4.954686690833765e-05,
+      "loss": 0.4517,
+      "step": 465
+    },
+    {
+      "epoch": 0.43782021425244527,
+      "grad_norm": 0.8520028714689553,
+      "learning_rate": 4.948213360952874e-05,
+      "loss": 0.4445,
+      "step": 470
+    },
+    {
+      "epoch": 0.4424778761061947,
+      "grad_norm": 0.9337684270648063,
+      "learning_rate": 4.941740031071983e-05,
+      "loss": 0.4529,
+      "step": 475
+    },
+    {
+      "epoch": 0.4471355379599441,
+      "grad_norm": 0.779468846961557,
+      "learning_rate": 4.935266701191093e-05,
+      "loss": 0.4395,
+      "step": 480
+    },
+    {
+      "epoch": 0.45179319981369354,
+      "grad_norm": 0.6650949973348257,
+      "learning_rate": 4.9287933713102025e-05,
+      "loss": 0.4412,
+      "step": 485
+    },
+    {
+      "epoch": 0.4564508616674429,
+      "grad_norm": 0.6682812165649679,
+      "learning_rate": 4.922320041429311e-05,
+      "loss": 0.4443,
+      "step": 490
+    },
+    {
+      "epoch": 0.46110852352119236,
+      "grad_norm": 0.5662366574835522,
+      "learning_rate": 4.915846711548421e-05,
+      "loss": 0.4372,
+      "step": 495
+    },
+    {
+      "epoch": 0.4657661853749418,
+      "grad_norm": 0.5527225881252463,
+      "learning_rate": 4.9093733816675304e-05,
+      "loss": 0.4435,
+      "step": 500
+    },
+    {
+      "epoch": 0.4704238472286912,
+      "grad_norm": 0.4831118178977241,
+      "learning_rate": 4.902900051786639e-05,
+      "loss": 0.4381,
+      "step": 505
+    },
+    {
+      "epoch": 0.4750815090824406,
+      "grad_norm": 0.7580810996734516,
+      "learning_rate": 4.8964267219057483e-05,
+      "loss": 0.4342,
+      "step": 510
+    },
+    {
+      "epoch": 0.47973917093619,
+      "grad_norm": 0.539734990096293,
+      "learning_rate": 4.889953392024858e-05,
+      "loss": 0.4447,
+      "step": 515
+    },
+    {
+      "epoch": 0.48439683278993945,
+      "grad_norm": 0.8177588699197897,
+      "learning_rate": 4.883480062143967e-05,
+      "loss": 0.4422,
+      "step": 520
+    },
+    {
+      "epoch": 0.4890544946436889,
+      "grad_norm": 1.0033915439248855,
+      "learning_rate": 4.877006732263076e-05,
+      "loss": 0.4505,
+      "step": 525
+    },
+    {
+      "epoch": 0.49371215649743827,
+      "grad_norm": 0.8143780735358211,
+      "learning_rate": 4.8705334023821855e-05,
+      "loss": 0.4374,
+      "step": 530
+    },
+    {
+      "epoch": 0.4983698183511877,
+      "grad_norm": 0.8588839880415308,
+      "learning_rate": 4.864060072501295e-05,
+      "loss": 0.4439,
+      "step": 535
+    },
+    {
+      "epoch": 0.5030274802049371,
+      "grad_norm": 0.5534295264924589,
+      "learning_rate": 4.857586742620404e-05,
+      "loss": 0.4467,
+      "step": 540
+    },
+    {
+      "epoch": 0.5076851420586865,
+      "grad_norm": 0.694081936603869,
+      "learning_rate": 4.8511134127395134e-05,
+      "loss": 0.4363,
+      "step": 545
+    },
+    {
+      "epoch": 0.5123428039124359,
+      "grad_norm": 0.5195561827214243,
+      "learning_rate": 4.844640082858623e-05,
+      "loss": 0.4502,
+      "step": 550
+    },
+    {
+      "epoch": 0.5170004657661854,
+      "grad_norm": 0.6250662402837189,
+      "learning_rate": 4.838166752977732e-05,
+      "loss": 0.439,
+      "step": 555
+    },
+    {
+      "epoch": 0.5216581276199348,
+      "grad_norm": 0.6122166549313228,
+      "learning_rate": 4.831693423096841e-05,
+      "loss": 0.4434,
+      "step": 560
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.593279075474479,
+      "learning_rate": 4.82522009321595e-05,
+      "loss": 0.4419,
+      "step": 565
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.6381493195880952,
+      "learning_rate": 4.81874676333506e-05,
+      "loss": 0.4411,
+      "step": 570
+    },
+    {
+      "epoch": 0.5356311131811831,
+      "grad_norm": 0.57797898990344,
+      "learning_rate": 4.812273433454169e-05,
+      "loss": 0.438,
+      "step": 575
+    },
+    {
+      "epoch": 0.5402887750349324,
+      "grad_norm": 0.47213344253037776,
+      "learning_rate": 4.8058001035732785e-05,
+      "loss": 0.4383,
+      "step": 580
+    },
+    {
+      "epoch": 0.5449464368886818,
+      "grad_norm": 0.648597018668758,
+      "learning_rate": 4.799326773692387e-05,
+      "loss": 0.4347,
+      "step": 585
+    },
+    {
+      "epoch": 0.5496040987424313,
+      "grad_norm": 0.5421208037871805,
+      "learning_rate": 4.792853443811497e-05,
+      "loss": 0.4495,
+      "step": 590
+    },
+    {
+      "epoch": 0.5542617605961807,
+      "grad_norm": 0.6433330457234978,
+      "learning_rate": 4.7863801139306064e-05,
+      "loss": 0.4406,
+      "step": 595
+    },
+    {
+      "epoch": 0.5589194224499301,
+      "grad_norm": 0.7002499853514838,
+      "learning_rate": 4.779906784049715e-05,
+      "loss": 0.4459,
+      "step": 600
+    },
+    {
+      "epoch": 0.5635770843036796,
+      "grad_norm": 0.7143219632098508,
+      "learning_rate": 4.773433454168825e-05,
+      "loss": 0.4216,
+      "step": 605
+    },
+    {
+      "epoch": 0.568234746157429,
+      "grad_norm": 0.7319076949907238,
+      "learning_rate": 4.766960124287934e-05,
+      "loss": 0.4396,
+      "step": 610
+    },
+    {
+      "epoch": 0.5728924080111784,
+      "grad_norm": 0.5579263649428615,
+      "learning_rate": 4.760486794407043e-05,
+      "loss": 0.4328,
+      "step": 615
+    },
+    {
+      "epoch": 0.5775500698649279,
+      "grad_norm": 0.6051200488351491,
+      "learning_rate": 4.754013464526152e-05,
+      "loss": 0.4355,
+      "step": 620
+    },
+    {
+      "epoch": 0.5822077317186772,
+      "grad_norm": 0.9355284480262427,
+      "learning_rate": 4.747540134645262e-05,
+      "loss": 0.4456,
+      "step": 625
+    },
+    {
+      "epoch": 0.5868653935724266,
+      "grad_norm": 0.6759571694938254,
+      "learning_rate": 4.741066804764371e-05,
+      "loss": 0.4327,
+      "step": 630
+    },
+    {
+      "epoch": 0.5915230554261761,
+      "grad_norm": 0.6066798099286695,
+      "learning_rate": 4.73459347488348e-05,
+      "loss": 0.4318,
+      "step": 635
+    },
+    {
+      "epoch": 0.5961807172799255,
+      "grad_norm": 0.5766678004544731,
+      "learning_rate": 4.7281201450025894e-05,
+      "loss": 0.4362,
+      "step": 640
+    },
+    {
+      "epoch": 0.6008383791336749,
+      "grad_norm": 0.7756927860850285,
+      "learning_rate": 4.721646815121699e-05,
+      "loss": 0.4364,
+      "step": 645
+    },
+    {
+      "epoch": 0.6054960409874243,
+      "grad_norm": 0.5567688060881293,
+      "learning_rate": 4.715173485240808e-05,
+      "loss": 0.4337,
+      "step": 650
+    },
+    {
+      "epoch": 0.6101537028411738,
+      "grad_norm": 0.7028822176366447,
+      "learning_rate": 4.708700155359917e-05,
+      "loss": 0.4395,
+      "step": 655
+    },
+    {
+      "epoch": 0.6148113646949231,
+      "grad_norm": 0.6982498567080344,
+      "learning_rate": 4.7022268254790266e-05,
+      "loss": 0.44,
+      "step": 660
+    },
+    {
+      "epoch": 0.6194690265486725,
+      "grad_norm": 0.783590853764837,
+      "learning_rate": 4.695753495598136e-05,
+      "loss": 0.4344,
+      "step": 665
+    },
+    {
+      "epoch": 0.624126688402422,
+      "grad_norm": 0.5945653795132514,
+      "learning_rate": 4.689280165717245e-05,
+      "loss": 0.4378,
+      "step": 670
+    },
+    {
+      "epoch": 0.6287843502561714,
+      "grad_norm": 0.7540483718886849,
+      "learning_rate": 4.6828068358363545e-05,
+      "loss": 0.4313,
+      "step": 675
+    },
+    {
+      "epoch": 0.6334420121099208,
+      "grad_norm": 0.6155313379149664,
+      "learning_rate": 4.676333505955464e-05,
+      "loss": 0.4339,
+      "step": 680
+    },
+    {
+      "epoch": 0.6380996739636703,
+      "grad_norm": 0.5973926989744232,
+      "learning_rate": 4.669860176074573e-05,
+      "loss": 0.4448,
+      "step": 685
+    },
+    {
+      "epoch": 0.6427573358174197,
+      "grad_norm": 0.6888625009540695,
+      "learning_rate": 4.6633868461936824e-05,
+      "loss": 0.4358,
+      "step": 690
+    },
+    {
+      "epoch": 0.6474149976711691,
+      "grad_norm": 0.5528833103014744,
+      "learning_rate": 4.656913516312791e-05,
+      "loss": 0.4347,
+      "step": 695
+    },
+    {
+      "epoch": 0.6520726595249184,
+      "grad_norm": 0.743825376822287,
+      "learning_rate": 4.650440186431901e-05,
+      "loss": 0.4324,
+      "step": 700
+    },
+    {
+      "epoch": 0.6567303213786679,
+      "grad_norm": 0.527940124176553,
+      "learning_rate": 4.64396685655101e-05,
+      "loss": 0.4295,
+      "step": 705
+    },
+    {
+      "epoch": 0.6613879832324173,
+      "grad_norm": 0.7497687263856895,
+      "learning_rate": 4.637493526670119e-05,
+      "loss": 0.4412,
+      "step": 710
+    },
+    {
+      "epoch": 0.6660456450861667,
+      "grad_norm": 0.6498477508666632,
+      "learning_rate": 4.631020196789229e-05,
+      "loss": 0.4349,
+      "step": 715
+    },
+    {
+      "epoch": 0.6707033069399162,
+      "grad_norm": 0.8312124037883604,
+      "learning_rate": 4.624546866908338e-05,
+      "loss": 0.4259,
+      "step": 720
+    },
+    {
+      "epoch": 0.6753609687936656,
+      "grad_norm": 0.6883304635143098,
+      "learning_rate": 4.618073537027447e-05,
+      "loss": 0.431,
+      "step": 725
+    },
+    {
+      "epoch": 0.680018630647415,
+      "grad_norm": 0.7574428390388477,
+      "learning_rate": 4.611600207146556e-05,
+      "loss": 0.4372,
+      "step": 730
+    },
+    {
+      "epoch": 0.6846762925011645,
+      "grad_norm": 0.6763628877618921,
+      "learning_rate": 4.605126877265666e-05,
+      "loss": 0.4262,
+      "step": 735
+    },
+    {
+      "epoch": 0.6893339543549138,
+      "grad_norm": 0.5583896921565148,
+      "learning_rate": 4.598653547384775e-05,
+      "loss": 0.4306,
+      "step": 740
+    },
+    {
+      "epoch": 0.6939916162086632,
+      "grad_norm": 0.6701923280474553,
+      "learning_rate": 4.592180217503884e-05,
+      "loss": 0.4278,
+      "step": 745
+    },
+    {
+      "epoch": 0.6986492780624126,
+      "grad_norm": 0.6956189505014265,
+      "learning_rate": 4.585706887622993e-05,
+      "loss": 0.4355,
+      "step": 750
+    },
+    {
+      "epoch": 0.7033069399161621,
+      "grad_norm": 0.6635359146409094,
+      "learning_rate": 4.5792335577421026e-05,
+      "loss": 0.4245,
+      "step": 755
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.6140976661004133,
+      "learning_rate": 4.572760227861212e-05,
+      "loss": 0.4272,
+      "step": 760
+    },
+    {
+      "epoch": 0.7126222636236609,
+      "grad_norm": 0.4904987934407959,
+      "learning_rate": 4.566286897980321e-05,
+      "loss": 0.4343,
+      "step": 765
+    },
+    {
+      "epoch": 0.7172799254774104,
+      "grad_norm": 0.6112507792543435,
+      "learning_rate": 4.5598135680994305e-05,
+      "loss": 0.4342,
+      "step": 770
+    },
+    {
+      "epoch": 0.7219375873311598,
+      "grad_norm": 0.5710309131226257,
+      "learning_rate": 4.55334023821854e-05,
+      "loss": 0.4226,
+      "step": 775
+    },
+    {
+      "epoch": 0.7265952491849091,
+      "grad_norm": 0.762950524779766,
+      "learning_rate": 4.546866908337649e-05,
+      "loss": 0.4386,
+      "step": 780
+    },
+    {
+      "epoch": 0.7312529110386586,
+      "grad_norm": 0.6101038425848627,
+      "learning_rate": 4.5403935784567584e-05,
+      "loss": 0.4327,
+      "step": 785
+    },
+    {
+      "epoch": 0.735910572892408,
+      "grad_norm": 0.5389750062367833,
+      "learning_rate": 4.533920248575868e-05,
+      "loss": 0.4245,
+      "step": 790
+    },
+    {
+      "epoch": 0.7405682347461574,
+      "grad_norm": 0.6014516190982565,
+      "learning_rate": 4.527446918694977e-05,
+      "loss": 0.4314,
+      "step": 795
+    },
+    {
+      "epoch": 0.7452258965999069,
+      "grad_norm": 0.5334667000099095,
+      "learning_rate": 4.520973588814086e-05,
+      "loss": 0.4274,
+      "step": 800
+    },
+    {
+      "epoch": 0.7498835584536563,
+      "grad_norm": 0.5375461922943744,
+      "learning_rate": 4.5145002589331956e-05,
+      "loss": 0.4428,
+      "step": 805
+    },
+    {
+      "epoch": 0.7545412203074057,
+      "grad_norm": 0.7113504084157668,
+      "learning_rate": 4.508026929052305e-05,
+      "loss": 0.4322,
+      "step": 810
+    },
+    {
+      "epoch": 0.759198882161155,
+      "grad_norm": 0.5432907497019303,
+      "learning_rate": 4.501553599171414e-05,
+      "loss": 0.4316,
+      "step": 815
+    },
+    {
+      "epoch": 0.7638565440149045,
+      "grad_norm": 0.5605126643071622,
+      "learning_rate": 4.495080269290523e-05,
+      "loss": 0.4308,
+      "step": 820
+    },
+    {
+      "epoch": 0.7685142058686539,
+      "grad_norm": 0.6676778575574163,
+      "learning_rate": 4.488606939409633e-05,
+      "loss": 0.4195,
+      "step": 825
+    },
+    {
+      "epoch": 0.7731718677224033,
+      "grad_norm": 0.5076862475458712,
+      "learning_rate": 4.482133609528742e-05,
+      "loss": 0.4278,
+      "step": 830
+    },
+    {
+      "epoch": 0.7778295295761528,
+      "grad_norm": 0.7538273414926085,
+      "learning_rate": 4.475660279647851e-05,
+      "loss": 0.435,
+      "step": 835
+    },
+    {
+      "epoch": 0.7824871914299022,
+      "grad_norm": 0.6165992054361188,
+      "learning_rate": 4.46918694976696e-05,
+      "loss": 0.4208,
+      "step": 840
+    },
+    {
+      "epoch": 0.7871448532836516,
+      "grad_norm": 0.6103376838850735,
+      "learning_rate": 4.46271361988607e-05,
+      "loss": 0.4253,
+      "step": 845
+    },
+    {
+      "epoch": 0.7918025151374011,
+      "grad_norm": 0.5637494760848727,
+      "learning_rate": 4.4562402900051786e-05,
+      "loss": 0.4275,
+      "step": 850
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "grad_norm": 0.7210366782440959,
+      "learning_rate": 4.449766960124288e-05,
+      "loss": 0.4222,
+      "step": 855
+    },
+    {
+      "epoch": 0.8011178388448998,
+      "grad_norm": 0.780129278673194,
+      "learning_rate": 4.443293630243397e-05,
+      "loss": 0.4237,
+      "step": 860
+    },
+    {
+      "epoch": 0.8057755006986492,
+      "grad_norm": 0.7011978671372727,
+      "learning_rate": 4.436820300362507e-05,
+      "loss": 0.4257,
+      "step": 865
+    },
+    {
+      "epoch": 0.8104331625523987,
+      "grad_norm": 0.5386389045073006,
+      "learning_rate": 4.430346970481616e-05,
+      "loss": 0.4201,
+      "step": 870
+    },
+    {
+      "epoch": 0.8150908244061481,
+      "grad_norm": 0.5249771309527765,
+      "learning_rate": 4.423873640600725e-05,
+      "loss": 0.4292,
+      "step": 875
+    },
+    {
+      "epoch": 0.8197484862598975,
+      "grad_norm": 0.5847770950616126,
+      "learning_rate": 4.4174003107198344e-05,
+      "loss": 0.4141,
+      "step": 880
+    },
+    {
+      "epoch": 0.824406148113647,
+      "grad_norm": 0.5540820646765134,
+      "learning_rate": 4.410926980838944e-05,
+      "loss": 0.4292,
+      "step": 885
+    },
+    {
+      "epoch": 0.8290638099673964,
+      "grad_norm": 0.7750106604921848,
+      "learning_rate": 4.404453650958053e-05,
+      "loss": 0.4295,
+      "step": 890
+    },
+    {
+      "epoch": 0.8337214718211458,
+      "grad_norm": 5.7095984942685885,
+      "learning_rate": 4.397980321077162e-05,
+      "loss": 0.4682,
+      "step": 895
+    },
+    {
+      "epoch": 0.8383791336748952,
+      "grad_norm": 9.852215910468063,
+      "learning_rate": 4.3915069911962716e-05,
+      "loss": 0.4306,
+      "step": 900
+    },
+    {
+      "epoch": 0.8430367955286446,
+      "grad_norm": 2.2703136100613066,
+      "learning_rate": 4.385033661315381e-05,
+      "loss": 0.4386,
+      "step": 905
+    },
+    {
+      "epoch": 0.847694457382394,
+      "grad_norm": 0.7483979346647932,
+      "learning_rate": 4.37856033143449e-05,
+      "loss": 0.443,
+      "step": 910
+    },
+    {
+      "epoch": 0.8523521192361434,
+      "grad_norm": 1.712098541065982,
+      "learning_rate": 4.3720870015535995e-05,
+      "loss": 0.4486,
+      "step": 915
+    },
+    {
+      "epoch": 0.8570097810898929,
+      "grad_norm": 1.5582697755903767,
+      "learning_rate": 4.365613671672709e-05,
+      "loss": 0.4387,
+      "step": 920
+    },
+    {
+      "epoch": 0.8616674429436423,
+      "grad_norm": 1.0587262467894218,
+      "learning_rate": 4.359140341791818e-05,
+      "loss": 0.4338,
+      "step": 925
+    },
+    {
+      "epoch": 0.8663251047973917,
+      "grad_norm": 0.6049104665306753,
+      "learning_rate": 4.352667011910927e-05,
+      "loss": 0.4305,
+      "step": 930
+    },
+    {
+      "epoch": 0.8709827666511412,
+      "grad_norm": 0.5748371742697991,
+      "learning_rate": 4.346193682030037e-05,
+      "loss": 0.4178,
+      "step": 935
+    },
+    {
+      "epoch": 0.8756404285048905,
+      "grad_norm": 0.6596921400151634,
+      "learning_rate": 4.339720352149146e-05,
+      "loss": 0.4171,
+      "step": 940
+    },
+    {
+      "epoch": 0.8802980903586399,
+      "grad_norm": 0.6225259650157069,
+      "learning_rate": 4.3332470222682546e-05,
+      "loss": 0.4205,
+      "step": 945
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 0.5300270027198535,
+      "learning_rate": 4.326773692387364e-05,
+      "loss": 0.4125,
+      "step": 950
+    },
+    {
+      "epoch": 0.8896134140661388,
+      "grad_norm": 0.5899764863550672,
+      "learning_rate": 4.320300362506474e-05,
+      "loss": 0.4247,
+      "step": 955
+    },
+    {
+      "epoch": 0.8942710759198882,
+      "grad_norm": 0.7657955597837949,
+      "learning_rate": 4.313827032625583e-05,
+      "loss": 0.4296,
+      "step": 960
+    },
+    {
+      "epoch": 0.8989287377736377,
+      "grad_norm": 0.5773088117984405,
+      "learning_rate": 4.307353702744692e-05,
+      "loss": 0.4253,
+      "step": 965
+    },
+    {
+      "epoch": 0.9035863996273871,
+      "grad_norm": 0.7380976863831679,
+      "learning_rate": 4.300880372863801e-05,
+      "loss": 0.4284,
+      "step": 970
+    },
+    {
+      "epoch": 0.9082440614811365,
+      "grad_norm": 0.5450612253283207,
+      "learning_rate": 4.294407042982911e-05,
+      "loss": 0.4217,
+      "step": 975
+    },
+    {
+      "epoch": 0.9129017233348858,
+      "grad_norm": 0.4357474886673886,
+      "learning_rate": 4.28793371310202e-05,
+      "loss": 0.4252,
+      "step": 980
+    },
+    {
+      "epoch": 0.9175593851886353,
+      "grad_norm": 0.5757600024781376,
+      "learning_rate": 4.281460383221129e-05,
+      "loss": 0.4287,
+      "step": 985
+    },
+    {
+      "epoch": 0.9222170470423847,
+      "grad_norm": 0.4820928865085597,
+      "learning_rate": 4.274987053340238e-05,
+      "loss": 0.4022,
+      "step": 990
+    },
+    {
+      "epoch": 0.9268747088961341,
+      "grad_norm": 0.5520484317462174,
+      "learning_rate": 4.2685137234593476e-05,
+      "loss": 0.4182,
+      "step": 995
+    },
+    {
+      "epoch": 0.9315323707498836,
+      "grad_norm": 0.6169701691629959,
+      "learning_rate": 4.262040393578457e-05,
+      "loss": 0.422,
+      "step": 1000
+    },
+    {
+      "epoch": 0.936190032603633,
+      "grad_norm": 0.5682173988732331,
+      "learning_rate": 4.255567063697566e-05,
+      "loss": 0.4296,
+      "step": 1005
+    },
+    {
+      "epoch": 0.9408476944573824,
+      "grad_norm": 0.5477941263890062,
+      "learning_rate": 4.2490937338166755e-05,
+      "loss": 0.4209,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9455053563111319,
+      "grad_norm": 0.4958260177132055,
+      "learning_rate": 4.242620403935785e-05,
+      "loss": 0.4219,
+      "step": 1015
+    },
+    {
+      "epoch": 0.9501630181648812,
+      "grad_norm": 0.5779104199309455,
+      "learning_rate": 4.236147074054894e-05,
+      "loss": 0.4299,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9548206800186306,
+      "grad_norm": 0.5391372616530509,
+      "learning_rate": 4.2296737441740034e-05,
+      "loss": 0.4218,
+      "step": 1025
+    },
+    {
+      "epoch": 0.95947834187238,
+      "grad_norm": 0.7274908987671125,
+      "learning_rate": 4.223200414293113e-05,
+      "loss": 0.4203,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9641360037261295,
+      "grad_norm": 0.519281430768983,
+      "learning_rate": 4.216727084412222e-05,
+      "loss": 0.4175,
+      "step": 1035
+    },
+    {
+      "epoch": 0.9687936655798789,
+      "grad_norm": 0.7585620649950258,
+      "learning_rate": 4.2102537545313306e-05,
+      "loss": 0.4171,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9734513274336283,
+      "grad_norm": 0.8053011449801734,
+      "learning_rate": 4.2037804246504406e-05,
+      "loss": 0.4186,
+      "step": 1045
+    },
+    {
+      "epoch": 0.9781089892873778,
+      "grad_norm": 0.5820087828554681,
+      "learning_rate": 4.19730709476955e-05,
+      "loss": 0.418,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9827666511411272,
+      "grad_norm": 0.524682321578155,
+      "learning_rate": 4.190833764888659e-05,
+      "loss": 0.4186,
+      "step": 1055
+    },
+    {
+      "epoch": 0.9874243129948765,
+      "grad_norm": 0.43818303570873757,
+      "learning_rate": 4.184360435007768e-05,
+      "loss": 0.4211,
+      "step": 1060
+    },
+    {
+      "epoch": 0.992081974848626,
+      "grad_norm": 0.7664348067427994,
+      "learning_rate": 4.177887105126878e-05,
+      "loss": 0.4179,
+      "step": 1065
+    },
+    {
+      "epoch": 0.9967396367023754,
+      "grad_norm": 0.6016998938278884,
+      "learning_rate": 4.171413775245987e-05,
+      "loss": 0.4099,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 4292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.197069464397414e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1074/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb5de8d1c25e97582b8d9db425d06889f1eab510d9a3ae1b8b5f74026e6e91de
+size 7480

checkpoint-1074/zero_to_fp32.py

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