Training in progress, step 1100, checkpoint

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1100/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-1100/config.json

@@ -0,0 +1,28 @@
+{
+  "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": 300000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-1100/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.50.0"
+}

checkpoint-1100/global_step1099/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6740b33d9972e271db9911eac65876a43732c6bc099b464a321678b5dbc112f4
+size 11423429708

checkpoint-1100/global_step1099/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:e074a9277348441d640bcc1d62472d1d5b38551138ada272369fb5b1bc715abc
+size 11423429708

checkpoint-1100/global_step1099/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165ae64dce3d04f5a82c31d5d7a56a85c026258bb957f2f4f5c171f1aee6c397
+size 11423429708

checkpoint-1100/global_step1099/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1113b75cd2c0178e77dccbe248fb55b56426db69bf44ef894e518e3fa186e5ca
+size 11423429708

checkpoint-1100/global_step1099/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:782481a4e0933b1ee2da7b7ea16488821963add1ddac04747b83c3a73bbae750
+size 11423429708

checkpoint-1100/global_step1099/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:da750056dbe42e977756736edcccce27ef41a624231b655b77b7053c785b52c6
+size 11423429708

checkpoint-1100/global_step1099/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349e9bbebc2edf182c2ce6ca74beb4f1518fe10cdcebdb0d73c6b40c1d58432a
+size 11423429708

checkpoint-1100/global_step1099/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf534df7c789e671e5b8ffa973d95c10eb7006d353c1f37c7af1176647d7eb5
+size 11423429708

checkpoint-1100/global_step1099/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eda453b4ca24fadae3b34f97a3770eb88ca9babe3d0fc719c6d3322bdaf3d3f
+size 166293

checkpoint-1100/global_step1099/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50fa92a7a93a31af307d1672f32236d7ee7fdf5a221a6cf395aa888582db83a2
+size 166293

checkpoint-1100/global_step1099/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b3d92910cb25a27250c545097ec1af59bea6e43f9fac51e7c834c054d11198
+size 166293

checkpoint-1100/global_step1099/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2650b2b6261b06cf2bd094937aeb48ae5d9f341d2ada07ecf7a45ed597d83eb
+size 166293

checkpoint-1100/global_step1099/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:882296d504c589a08d22de812051d3502c7182f8fdce540b1430079339892b7c
+size 166293

checkpoint-1100/global_step1099/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e919741a2d1beed4136cb82539b6022a774e852d62ee0a86f5670aad77afe66
+size 166293

checkpoint-1100/global_step1099/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957e31b922e57c67b9a3ac1f18f7574cbf6de0d33409f5de2b0ef9b8cf66e47d
+size 166293

checkpoint-1100/global_step1099/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a274b2df9e3c48408967ad4e11b6df1de3913174c034ad632b4a3d50310b06
+size 166293

checkpoint-1100/latest

@@ -0,0 +1 @@
+global_step1099

checkpoint-1100/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed472d7a80ba716c13e1b7a69b5025e14e29ffd92d3e9c4cf00900c3da38bfaa
+size 4877660776

checkpoint-1100/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1dbcc4e359dcbbdc8cf2fecd2e1a98fc9afa1929cd843c581899b9158e90cf
+size 4932751008

checkpoint-1100/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d0f529c0e00b8feb8256de6add3f2bc50000ee5fc0d552b27c6e430f773606
+size 4330865200

checkpoint-1100/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63bedbf1ed7a8c34596dde5c921af707f0ad8ec6d794e8e8db014b692004bb23
+size 1089994880

checkpoint-1100/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-1100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
+size 15984

checkpoint-1100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
+size 15984

checkpoint-1100/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
+size 15984

checkpoint-1100/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
+size 15984

checkpoint-1100/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
+size 15984

checkpoint-1100/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991
+size 15984

checkpoint-1100/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa
+size 15984

checkpoint-1100/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773
+size 15984

checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22b78b992313259665933ffb95329dafb0479c70eaba6cb51b4c7ef9e90af3b
+size 1064

checkpoint-1100/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-1100/tokenizer.json

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

checkpoint-1100/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        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\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\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|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-1100/trainer_state.json

@@ -0,0 +1,1794 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.024219841639497,
+  "eval_steps": 500,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004657661853749418,
+      "grad_norm": 82.05587354646646,
+      "learning_rate": 7.763975155279503e-07,
+      "loss": 9.9438,
+      "num_tokens": 5242880.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.009315323707498836,
+      "grad_norm": 98.0190156931495,
+      "learning_rate": 1.5527950310559006e-06,
+      "loss": 9.6475,
+      "num_tokens": 10485760.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.013972985561248253,
+      "grad_norm": 113.69325621752397,
+      "learning_rate": 2.329192546583851e-06,
+      "loss": 7.5009,
+      "num_tokens": 15691438.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.018630647414997672,
+      "grad_norm": 20.08992771959664,
+      "learning_rate": 3.1055900621118013e-06,
+      "loss": 2.3962,
+      "num_tokens": 20915252.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.02328830926874709,
+      "grad_norm": 3.796391559366892,
+      "learning_rate": 3.881987577639752e-06,
+      "loss": 1.3249,
+      "num_tokens": 26134828.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.027945971122496506,
+      "grad_norm": 1.897340748140379,
+      "learning_rate": 4.658385093167702e-06,
+      "loss": 1.063,
+      "num_tokens": 31377708.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.032603632976245925,
+      "grad_norm": 0.9353460581126074,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.891,
+      "num_tokens": 36557688.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.037261294829995344,
+      "grad_norm": 0.6860451736359767,
+      "learning_rate": 6.2111801242236025e-06,
+      "loss": 0.8014,
+      "num_tokens": 41800322.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04191895668374476,
+      "grad_norm": 0.4462391543288957,
+      "learning_rate": 6.9875776397515525e-06,
+      "loss": 0.702,
+      "num_tokens": 47043202.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.04657661853749418,
+      "grad_norm": 0.5658389980406826,
+      "learning_rate": 7.763975155279503e-06,
+      "loss": 0.679,
+      "num_tokens": 52286082.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05123428039124359,
+      "grad_norm": 0.39716601221628856,
+      "learning_rate": 8.540372670807453e-06,
+      "loss": 0.6432,
+      "num_tokens": 57528962.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.05589194224499301,
+      "grad_norm": 0.3576561966497444,
+      "learning_rate": 9.316770186335403e-06,
+      "loss": 0.6268,
+      "num_tokens": 62771842.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06054960409874243,
+      "grad_norm": 0.3690305804361313,
+      "learning_rate": 1.0093167701863353e-05,
+      "loss": 0.6062,
+      "num_tokens": 67980354.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.06520726595249185,
+      "grad_norm": 0.30904022597752495,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.5755,
+      "num_tokens": 73223234.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.06986492780624126,
+      "grad_norm": 0.33381487552443856,
+      "learning_rate": 1.1645962732919255e-05,
+      "loss": 0.5722,
+      "num_tokens": 78437814.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.07452258965999069,
+      "grad_norm": 0.29018900181654517,
+      "learning_rate": 1.2422360248447205e-05,
+      "loss": 0.5787,
+      "num_tokens": 83680694.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.0791802515137401,
+      "grad_norm": 0.31193541739320246,
+      "learning_rate": 1.3198757763975155e-05,
+      "loss": 0.5484,
+      "num_tokens": 88923574.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.08383791336748952,
+      "grad_norm": 0.36013559560524766,
+      "learning_rate": 1.3975155279503105e-05,
+      "loss": 0.551,
+      "num_tokens": 94166454.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.08849557522123894,
+      "grad_norm": 0.29887540089263853,
+      "learning_rate": 1.4751552795031057e-05,
+      "loss": 0.5556,
+      "num_tokens": 99409334.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.09315323707498836,
+      "grad_norm": 0.31777202176514885,
+      "learning_rate": 1.5527950310559007e-05,
+      "loss": 0.5419,
+      "num_tokens": 104652214.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.09781089892873777,
+      "grad_norm": 0.3039817792088042,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.5397,
+      "num_tokens": 109895094.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.10246856078248719,
+      "grad_norm": 0.3024257620617263,
+      "learning_rate": 1.7080745341614907e-05,
+      "loss": 0.5252,
+      "num_tokens": 115137974.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.10712622263623661,
+      "grad_norm": 0.31140997132030224,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.5238,
+      "num_tokens": 120380854.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.11178388448998602,
+      "grad_norm": 0.35218239712763794,
+      "learning_rate": 1.8633540372670807e-05,
+      "loss": 0.5345,
+      "num_tokens": 125623734.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.11644154634373545,
+      "grad_norm": 0.34642949453466215,
+      "learning_rate": 1.940993788819876e-05,
+      "loss": 0.5095,
+      "num_tokens": 130866614.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.12109920819748486,
+      "grad_norm": 0.3148152432452141,
+      "learning_rate": 2.0186335403726707e-05,
+      "loss": 0.5097,
+      "num_tokens": 136068456.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.1257568700512343,
+      "grad_norm": 0.3218897464063567,
+      "learning_rate": 2.096273291925466e-05,
+      "loss": 0.5178,
+      "num_tokens": 141311336.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.1304145319049837,
+      "grad_norm": 0.30116924097164377,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.5075,
+      "num_tokens": 146554216.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.1350721937587331,
+      "grad_norm": 0.3941017670817498,
+      "learning_rate": 2.2515527950310562e-05,
+      "loss": 0.5181,
+      "num_tokens": 151797096.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.13972985561248252,
+      "grad_norm": 0.38992413690107575,
+      "learning_rate": 2.329192546583851e-05,
+      "loss": 0.5091,
+      "num_tokens": 157039976.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.14438751746623196,
+      "grad_norm": 0.3299485605544544,
+      "learning_rate": 2.4068322981366462e-05,
+      "loss": 0.4893,
+      "num_tokens": 162282856.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.14904517931998137,
+      "grad_norm": 0.398285302815728,
+      "learning_rate": 2.484472049689441e-05,
+      "loss": 0.498,
+      "num_tokens": 167466294.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.1537028411737308,
+      "grad_norm": 0.464751877974553,
+      "learning_rate": 2.5621118012422362e-05,
+      "loss": 0.4952,
+      "num_tokens": 172703130.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.1583605030274802,
+      "grad_norm": 0.5494333844825245,
+      "learning_rate": 2.639751552795031e-05,
+      "loss": 0.4927,
+      "num_tokens": 177946010.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.1630181648812296,
+      "grad_norm": 0.4673335432920727,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.5052,
+      "num_tokens": 183145930.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.16767582673497905,
+      "grad_norm": 0.40861619513411185,
+      "learning_rate": 2.795031055900621e-05,
+      "loss": 0.4964,
+      "num_tokens": 188388810.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.17233348858872846,
+      "grad_norm": 0.4257074069728051,
+      "learning_rate": 2.8726708074534165e-05,
+      "loss": 0.4966,
+      "num_tokens": 193628148.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 0.38423446067890304,
+      "learning_rate": 2.9503105590062114e-05,
+      "loss": 0.4874,
+      "num_tokens": 198871028.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.18164881229622729,
+      "grad_norm": 0.5665394970476383,
+      "learning_rate": 3.0279503105590062e-05,
+      "loss": 0.4931,
+      "num_tokens": 204113908.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.18630647414997673,
+      "grad_norm": 0.4873250722559478,
+      "learning_rate": 3.1055900621118014e-05,
+      "loss": 0.4632,
+      "num_tokens": 209266418.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.19096413600372614,
+      "grad_norm": 0.5150102284421441,
+      "learning_rate": 3.183229813664597e-05,
+      "loss": 0.4857,
+      "num_tokens": 214355738.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.19562179785747555,
+      "grad_norm": 0.4984697478657664,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.4728,
+      "num_tokens": 219598618.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.20027945971122496,
+      "grad_norm": 0.6451003628441052,
+      "learning_rate": 3.3385093167701865e-05,
+      "loss": 0.4856,
+      "num_tokens": 224779924.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.20493712156497437,
+      "grad_norm": 0.6652150575437156,
+      "learning_rate": 3.4161490683229814e-05,
+      "loss": 0.4823,
+      "num_tokens": 230001220.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.2095947834187238,
+      "grad_norm": 0.49487018926010595,
+      "learning_rate": 3.493788819875777e-05,
+      "loss": 0.4828,
+      "num_tokens": 235244100.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.21425244527247322,
+      "grad_norm": 0.5752941558981775,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.4814,
+      "num_tokens": 240459436.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.21891010712622264,
+      "grad_norm": 0.4619284425777841,
+      "learning_rate": 3.6490683229813665e-05,
+      "loss": 0.4743,
+      "num_tokens": 245702316.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.22356776897997205,
+      "grad_norm": 0.7391653942740258,
+      "learning_rate": 3.7267080745341614e-05,
+      "loss": 0.474,
+      "num_tokens": 250945196.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.22822543083372146,
+      "grad_norm": 0.6338388924664621,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.4614,
+      "num_tokens": 256130440.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.2328830926874709,
+      "grad_norm": 0.4960164973911761,
+      "learning_rate": 3.881987577639752e-05,
+      "loss": 0.4577,
+      "num_tokens": 261373320.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.2375407545412203,
+      "grad_norm": 0.3662549013001617,
+      "learning_rate": 3.9596273291925465e-05,
+      "loss": 0.4701,
+      "num_tokens": 266595056.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.24219841639496972,
+      "grad_norm": 0.40055322139053984,
+      "learning_rate": 4.0372670807453414e-05,
+      "loss": 0.4749,
+      "num_tokens": 271837936.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.24685607824871914,
+      "grad_norm": 0.5265912543642953,
+      "learning_rate": 4.114906832298137e-05,
+      "loss": 0.4682,
+      "num_tokens": 277080816.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.2515137401024686,
+      "grad_norm": 0.516959496135824,
+      "learning_rate": 4.192546583850932e-05,
+      "loss": 0.4563,
+      "num_tokens": 282323696.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.25617140195621796,
+      "grad_norm": 0.42466326053184844,
+      "learning_rate": 4.270186335403727e-05,
+      "loss": 0.4725,
+      "num_tokens": 287548638.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.2608290638099674,
+      "grad_norm": 0.6461617346625652,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.4614,
+      "num_tokens": 292791518.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "grad_norm": 0.5162643395814067,
+      "learning_rate": 4.425465838509317e-05,
+      "loss": 0.4583,
+      "num_tokens": 298034398.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.2701443875174662,
+      "grad_norm": 0.4606739995726742,
+      "learning_rate": 4.5031055900621124e-05,
+      "loss": 0.4564,
+      "num_tokens": 303277278.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.27480204937121566,
+      "grad_norm": 0.5165208655712867,
+      "learning_rate": 4.580745341614907e-05,
+      "loss": 0.4502,
+      "num_tokens": 308520158.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.27945971122496505,
+      "grad_norm": 0.3993911836573598,
+      "learning_rate": 4.658385093167702e-05,
+      "loss": 0.4634,
+      "num_tokens": 313763038.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.2841173730787145,
+      "grad_norm": 0.6185284048775294,
+      "learning_rate": 4.736024844720497e-05,
+      "loss": 0.4678,
+      "num_tokens": 318941236.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.2887750349324639,
+      "grad_norm": 0.6607767188478789,
+      "learning_rate": 4.8136645962732924e-05,
+      "loss": 0.4634,
+      "num_tokens": 324184116.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.2934326967862133,
+      "grad_norm": 0.6792865629186282,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.4531,
+      "num_tokens": 329426996.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.29809035863996275,
+      "grad_norm": 0.5370350636249767,
+      "learning_rate": 4.968944099378882e-05,
+      "loss": 0.4604,
+      "num_tokens": 334669876.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.30274802049371213,
+      "grad_norm": 0.5243165861771709,
+      "learning_rate": 4.994822229892993e-05,
+      "loss": 0.4626,
+      "num_tokens": 339912756.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.3074056823474616,
+      "grad_norm": 0.6658402668928456,
+      "learning_rate": 4.986192613047981e-05,
+      "loss": 0.4615,
+      "num_tokens": 345155636.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.312063344201211,
+      "grad_norm": 0.4658973380194966,
+      "learning_rate": 4.977562996202969e-05,
+      "loss": 0.4444,
+      "num_tokens": 350398516.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.3167210060549604,
+      "grad_norm": 0.513098874415573,
+      "learning_rate": 4.968933379357957e-05,
+      "loss": 0.4583,
+      "num_tokens": 355641396.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.32137866790870984,
+      "grad_norm": 0.43639797114828116,
+      "learning_rate": 4.9603037625129445e-05,
+      "loss": 0.4462,
+      "num_tokens": 360884276.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.3260363297624592,
+      "grad_norm": 0.41532792848046246,
+      "learning_rate": 4.951674145667933e-05,
+      "loss": 0.4483,
+      "num_tokens": 366127156.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.33069399161620866,
+      "grad_norm": 0.4148646031554546,
+      "learning_rate": 4.94304452882292e-05,
+      "loss": 0.4452,
+      "num_tokens": 371370036.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.3353516534699581,
+      "grad_norm": 0.5641848552142894,
+      "learning_rate": 4.934414911977908e-05,
+      "loss": 0.4553,
+      "num_tokens": 376600048.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.3400093153237075,
+      "grad_norm": 0.37381304489035017,
+      "learning_rate": 4.9257852951328965e-05,
+      "loss": 0.4527,
+      "num_tokens": 381842928.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.3446669771774569,
+      "grad_norm": 0.4749170963347877,
+      "learning_rate": 4.917155678287884e-05,
+      "loss": 0.4663,
+      "num_tokens": 387073976.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.3493246390312063,
+      "grad_norm": 0.5043241941069802,
+      "learning_rate": 4.908526061442872e-05,
+      "loss": 0.4579,
+      "num_tokens": 392316856.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 0.39517110563197555,
+      "learning_rate": 4.89989644459786e-05,
+      "loss": 0.4446,
+      "num_tokens": 397559736.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.3586399627387052,
+      "grad_norm": 0.37708532711839055,
+      "learning_rate": 4.891266827752848e-05,
+      "loss": 0.4391,
+      "num_tokens": 402802616.0,
+      "step": 385
+    },
+    {
+      "epoch": 0.36329762459245457,
+      "grad_norm": 0.4975840523986466,
+      "learning_rate": 4.882637210907836e-05,
+      "loss": 0.4425,
+      "num_tokens": 408014414.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.367955286446204,
+      "grad_norm": 0.5319257453602194,
+      "learning_rate": 4.874007594062824e-05,
+      "loss": 0.4379,
+      "num_tokens": 413257294.0,
+      "step": 395
+    },
+    {
+      "epoch": 0.37261294829995345,
+      "grad_norm": 0.4531992500866268,
+      "learning_rate": 4.865377977217811e-05,
+      "loss": 0.4369,
+      "num_tokens": 418500174.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.37727061015370283,
+      "grad_norm": 0.4918946640070345,
+      "learning_rate": 4.8567483603728e-05,
+      "loss": 0.437,
+      "num_tokens": 423692782.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.3819282720074523,
+      "grad_norm": 0.4204196435564102,
+      "learning_rate": 4.8481187435277875e-05,
+      "loss": 0.4439,
+      "num_tokens": 428845062.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.38658593386120166,
+      "grad_norm": 0.48787071943190957,
+      "learning_rate": 4.839489126682776e-05,
+      "loss": 0.4426,
+      "num_tokens": 434087942.0,
+      "step": 415
+    },
+    {
+      "epoch": 0.3912435957149511,
+      "grad_norm": 0.4530000025912301,
+      "learning_rate": 4.830859509837763e-05,
+      "loss": 0.4337,
+      "num_tokens": 439278078.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.39590125756870054,
+      "grad_norm": 0.4001439902959063,
+      "learning_rate": 4.822229892992751e-05,
+      "loss": 0.4501,
+      "num_tokens": 444520958.0,
+      "step": 425
+    },
+    {
+      "epoch": 0.4005589194224499,
+      "grad_norm": 0.5763435863000469,
+      "learning_rate": 4.8136002761477395e-05,
+      "loss": 0.4424,
+      "num_tokens": 449763838.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.40521658127619936,
+      "grad_norm": 0.41267081555819357,
+      "learning_rate": 4.804970659302727e-05,
+      "loss": 0.4465,
+      "num_tokens": 454963270.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.40987424312994875,
+      "grad_norm": 0.5198402187503036,
+      "learning_rate": 4.796341042457715e-05,
+      "loss": 0.4562,
+      "num_tokens": 460206150.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4145319049836982,
+      "grad_norm": 0.4804770546328782,
+      "learning_rate": 4.787711425612703e-05,
+      "loss": 0.4316,
+      "num_tokens": 465378662.0,
+      "step": 445
+    },
+    {
+      "epoch": 0.4191895668374476,
+      "grad_norm": 0.3573229568827099,
+      "learning_rate": 4.779081808767691e-05,
+      "loss": 0.4348,
+      "num_tokens": 470602566.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.423847228691197,
+      "grad_norm": 0.48298666415576386,
+      "learning_rate": 4.770452191922679e-05,
+      "loss": 0.4567,
+      "num_tokens": 475800020.0,
+      "step": 455
+    },
+    {
+      "epoch": 0.42850489054494645,
+      "grad_norm": 0.4293786343270861,
+      "learning_rate": 4.761822575077667e-05,
+      "loss": 0.4356,
+      "num_tokens": 481042900.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.43316255239869583,
+      "grad_norm": 0.40640797330880013,
+      "learning_rate": 4.753192958232654e-05,
+      "loss": 0.4451,
+      "num_tokens": 486220500.0,
+      "step": 465
+    },
+    {
+      "epoch": 0.43782021425244527,
+      "grad_norm": 0.3620709663973599,
+      "learning_rate": 4.744563341387643e-05,
+      "loss": 0.4366,
+      "num_tokens": 491463380.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.4424778761061947,
+      "grad_norm": 0.3689460832182135,
+      "learning_rate": 4.7359337245426306e-05,
+      "loss": 0.4454,
+      "num_tokens": 496706260.0,
+      "step": 475
+    },
+    {
+      "epoch": 0.4471355379599441,
+      "grad_norm": 0.3235598346166627,
+      "learning_rate": 4.7273041076976184e-05,
+      "loss": 0.4297,
+      "num_tokens": 501949140.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.45179319981369354,
+      "grad_norm": 0.3539771478611738,
+      "learning_rate": 4.718674490852606e-05,
+      "loss": 0.433,
+      "num_tokens": 507192020.0,
+      "step": 485
+    },
+    {
+      "epoch": 0.4564508616674429,
+      "grad_norm": 0.3776299787194787,
+      "learning_rate": 4.710044874007594e-05,
+      "loss": 0.4365,
+      "num_tokens": 512433054.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.46110852352119236,
+      "grad_norm": 0.36237963146891655,
+      "learning_rate": 4.7014152571625826e-05,
+      "loss": 0.4273,
+      "num_tokens": 517658160.0,
+      "step": 495
+    },
+    {
+      "epoch": 0.4657661853749418,
+      "grad_norm": 0.4084396998076576,
+      "learning_rate": 4.6927856403175704e-05,
+      "loss": 0.4358,
+      "num_tokens": 522901040.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.4704238472286912,
+      "grad_norm": 0.32563088148769737,
+      "learning_rate": 4.684156023472558e-05,
+      "loss": 0.4293,
+      "num_tokens": 528127586.0,
+      "step": 505
+    },
+    {
+      "epoch": 0.4750815090824406,
+      "grad_norm": 0.46748215510130064,
+      "learning_rate": 4.675526406627546e-05,
+      "loss": 0.4253,
+      "num_tokens": 533355284.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.47973917093619,
+      "grad_norm": 0.5058103175826015,
+      "learning_rate": 4.666896789782534e-05,
+      "loss": 0.4382,
+      "num_tokens": 538598164.0,
+      "step": 515
+    },
+    {
+      "epoch": 0.48439683278993945,
+      "grad_norm": 0.48239977250625826,
+      "learning_rate": 4.658267172937522e-05,
+      "loss": 0.4342,
+      "num_tokens": 543841044.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.4890544946436889,
+      "grad_norm": 0.6331188841101223,
+      "learning_rate": 4.64963755609251e-05,
+      "loss": 0.4418,
+      "num_tokens": 549083924.0,
+      "step": 525
+    },
+    {
+      "epoch": 0.49371215649743827,
+      "grad_norm": 0.48500000646310354,
+      "learning_rate": 4.641007939247497e-05,
+      "loss": 0.4277,
+      "num_tokens": 554323932.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.4983698183511877,
+      "grad_norm": 0.6606771561537853,
+      "learning_rate": 4.632378322402486e-05,
+      "loss": 0.4367,
+      "num_tokens": 559555680.0,
+      "step": 535
+    },
+    {
+      "epoch": 0.5030274802049371,
+      "grad_norm": 0.47177575989233334,
+      "learning_rate": 4.6237487055574736e-05,
+      "loss": 0.4395,
+      "num_tokens": 564798560.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.5076851420586865,
+      "grad_norm": 0.35505752604264607,
+      "learning_rate": 4.6151190887124615e-05,
+      "loss": 0.4273,
+      "num_tokens": 569918486.0,
+      "step": 545
+    },
+    {
+      "epoch": 0.5123428039124359,
+      "grad_norm": 0.5805428989783042,
+      "learning_rate": 4.606489471867449e-05,
+      "loss": 0.4427,
+      "num_tokens": 575160720.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.5170004657661854,
+      "grad_norm": 0.4481109935171867,
+      "learning_rate": 4.597859855022437e-05,
+      "loss": 0.429,
+      "num_tokens": 580403600.0,
+      "step": 555
+    },
+    {
+      "epoch": 0.5216581276199348,
+      "grad_norm": 0.4306150535473462,
+      "learning_rate": 4.589230238177425e-05,
+      "loss": 0.4334,
+      "num_tokens": 585635440.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.4218043527459623,
+      "learning_rate": 4.5806006213324134e-05,
+      "loss": 0.4319,
+      "num_tokens": 590878320.0,
+      "step": 565
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.3773682370056681,
+      "learning_rate": 4.5719710044874006e-05,
+      "loss": 0.4309,
+      "num_tokens": 596063606.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.5356311131811831,
+      "grad_norm": 0.3725777888860041,
+      "learning_rate": 4.563341387642389e-05,
+      "loss": 0.4298,
+      "num_tokens": 601306486.0,
+      "step": 575
+    },
+    {
+      "epoch": 0.5402887750349324,
+      "grad_norm": 0.32850168482374853,
+      "learning_rate": 4.554711770797377e-05,
+      "loss": 0.4317,
+      "num_tokens": 606451006.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.5449464368886818,
+      "grad_norm": 0.3344939451761741,
+      "learning_rate": 4.546082153952365e-05,
+      "loss": 0.426,
+      "num_tokens": 611693886.0,
+      "step": 585
+    },
+    {
+      "epoch": 0.5496040987424313,
+      "grad_norm": 0.4068375974188898,
+      "learning_rate": 4.5374525371073526e-05,
+      "loss": 0.4421,
+      "num_tokens": 616936766.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.5542617605961807,
+      "grad_norm": 0.4761673073396981,
+      "learning_rate": 4.5288229202623404e-05,
+      "loss": 0.4329,
+      "num_tokens": 622179646.0,
+      "step": 595
+    },
+    {
+      "epoch": 0.5589194224499301,
+      "grad_norm": 0.44663542891933206,
+      "learning_rate": 4.520193303417328e-05,
+      "loss": 0.4365,
+      "num_tokens": 627422526.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.5635770843036796,
+      "grad_norm": 0.44847735353439966,
+      "learning_rate": 4.511563686572317e-05,
+      "loss": 0.412,
+      "num_tokens": 632619928.0,
+      "step": 605
+    },
+    {
+      "epoch": 0.568234746157429,
+      "grad_norm": 0.45628359974960664,
+      "learning_rate": 4.5029340697273045e-05,
+      "loss": 0.4308,
+      "num_tokens": 637862808.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.5728924080111784,
+      "grad_norm": 0.4800117779432551,
+      "learning_rate": 4.4943044528822923e-05,
+      "loss": 0.4228,
+      "num_tokens": 643105688.0,
+      "step": 615
+    },
+    {
+      "epoch": 0.5775500698649279,
+      "grad_norm": 0.5546132432412902,
+      "learning_rate": 4.48567483603728e-05,
+      "loss": 0.4269,
+      "num_tokens": 648348568.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.5822077317186772,
+      "grad_norm": 0.4664261556549962,
+      "learning_rate": 4.477045219192268e-05,
+      "loss": 0.4368,
+      "num_tokens": 653591448.0,
+      "step": 625
+    },
+    {
+      "epoch": 0.5868653935724266,
+      "grad_norm": 0.42681630594448233,
+      "learning_rate": 4.4684156023472565e-05,
+      "loss": 0.4222,
+      "num_tokens": 658834328.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.5915230554261761,
+      "grad_norm": 0.4187275561832938,
+      "learning_rate": 4.4597859855022436e-05,
+      "loss": 0.4222,
+      "num_tokens": 664028780.0,
+      "step": 635
+    },
+    {
+      "epoch": 0.5961807172799255,
+      "grad_norm": 0.35933633316781455,
+      "learning_rate": 4.4511563686572315e-05,
+      "loss": 0.4281,
+      "num_tokens": 669256250.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.6008383791336749,
+      "grad_norm": 0.3750506834697772,
+      "learning_rate": 4.44252675181222e-05,
+      "loss": 0.426,
+      "num_tokens": 674460550.0,
+      "step": 645
+    },
+    {
+      "epoch": 0.6054960409874243,
+      "grad_norm": 0.45094143093344574,
+      "learning_rate": 4.433897134967208e-05,
+      "loss": 0.4238,
+      "num_tokens": 679701528.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.6101537028411738,
+      "grad_norm": 0.3686716302533929,
+      "learning_rate": 4.4252675181221956e-05,
+      "loss": 0.4311,
+      "num_tokens": 684944408.0,
+      "step": 655
+    },
+    {
+      "epoch": 0.6148113646949231,
+      "grad_norm": 0.4708342271610549,
+      "learning_rate": 4.4166379012771834e-05,
+      "loss": 0.4325,
+      "num_tokens": 690187288.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.6194690265486725,
+      "grad_norm": 0.3687257046878129,
+      "learning_rate": 4.408008284432171e-05,
+      "loss": 0.4257,
+      "num_tokens": 695372640.0,
+      "step": 665
+    },
+    {
+      "epoch": 0.624126688402422,
+      "grad_norm": 0.34502453479936046,
+      "learning_rate": 4.39937866758716e-05,
+      "loss": 0.4287,
+      "num_tokens": 700615520.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.6287843502561714,
+      "grad_norm": 0.57257718960929,
+      "learning_rate": 4.3907490507421476e-05,
+      "loss": 0.4216,
+      "num_tokens": 705831004.0,
+      "step": 675
+    },
+    {
+      "epoch": 0.6334420121099208,
+      "grad_norm": 0.40743947034127986,
+      "learning_rate": 4.382119433897135e-05,
+      "loss": 0.4254,
+      "num_tokens": 711015208.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.6380996739636703,
+      "grad_norm": 0.4712504333805676,
+      "learning_rate": 4.373489817052123e-05,
+      "loss": 0.4357,
+      "num_tokens": 716205240.0,
+      "step": 685
+    },
+    {
+      "epoch": 0.6427573358174197,
+      "grad_norm": 0.31386050500322255,
+      "learning_rate": 4.364860200207111e-05,
+      "loss": 0.4245,
+      "num_tokens": 721448120.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.6474149976711691,
+      "grad_norm": 0.34856077066736296,
+      "learning_rate": 4.356230583362099e-05,
+      "loss": 0.4243,
+      "num_tokens": 726691000.0,
+      "step": 695
+    },
+    {
+      "epoch": 0.6520726595249184,
+      "grad_norm": 0.35138951547463787,
+      "learning_rate": 4.347600966517087e-05,
+      "loss": 0.4208,
+      "num_tokens": 731930908.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.6567303213786679,
+      "grad_norm": 0.3563298490627363,
+      "learning_rate": 4.3389713496720745e-05,
+      "loss": 0.4184,
+      "num_tokens": 737133156.0,
+      "step": 705
+    },
+    {
+      "epoch": 0.6613879832324173,
+      "grad_norm": 0.29828582782393925,
+      "learning_rate": 4.330341732827063e-05,
+      "loss": 0.4319,
+      "num_tokens": 742336330.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.6660456450861667,
+      "grad_norm": 0.4554868776579047,
+      "learning_rate": 4.321712115982051e-05,
+      "loss": 0.4245,
+      "num_tokens": 747579210.0,
+      "step": 715
+    },
+    {
+      "epoch": 0.6707033069399162,
+      "grad_norm": 0.44237565032771087,
+      "learning_rate": 4.3130824991370387e-05,
+      "loss": 0.4163,
+      "num_tokens": 752752000.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.6753609687936656,
+      "grad_norm": 0.4203289082659788,
+      "learning_rate": 4.3044528822920265e-05,
+      "loss": 0.4204,
+      "num_tokens": 757994880.0,
+      "step": 725
+    },
+    {
+      "epoch": 0.680018630647415,
+      "grad_norm": 0.42671358285819366,
+      "learning_rate": 4.295823265447014e-05,
+      "loss": 0.4277,
+      "num_tokens": 763237760.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.6846762925011645,
+      "grad_norm": 0.37538834692647144,
+      "learning_rate": 4.287193648602002e-05,
+      "loss": 0.4157,
+      "num_tokens": 768480640.0,
+      "step": 735
+    },
+    {
+      "epoch": 0.6893339543549138,
+      "grad_norm": 0.4556647024263887,
+      "learning_rate": 4.27856403175699e-05,
+      "loss": 0.4197,
+      "num_tokens": 773723520.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.6939916162086632,
+      "grad_norm": 0.4811016264457114,
+      "learning_rate": 4.269934414911978e-05,
+      "loss": 0.4181,
+      "num_tokens": 778966400.0,
+      "step": 745
+    },
+    {
+      "epoch": 0.6986492780624126,
+      "grad_norm": 0.46408266345529087,
+      "learning_rate": 4.261304798066966e-05,
+      "loss": 0.4262,
+      "num_tokens": 784209280.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.7033069399161621,
+      "grad_norm": 0.4571430025824553,
+      "learning_rate": 4.252675181221954e-05,
+      "loss": 0.4133,
+      "num_tokens": 789452160.0,
+      "step": 755
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.44928992980297267,
+      "learning_rate": 4.244045564376942e-05,
+      "loss": 0.4183,
+      "num_tokens": 794695040.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.7126222636236609,
+      "grad_norm": 0.42294682770420816,
+      "learning_rate": 4.23541594753193e-05,
+      "loss": 0.4256,
+      "num_tokens": 799937676.0,
+      "step": 765
+    },
+    {
+      "epoch": 0.7172799254774104,
+      "grad_norm": 0.46170931025430106,
+      "learning_rate": 4.2267863306869176e-05,
+      "loss": 0.425,
+      "num_tokens": 805180556.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.7219375873311598,
+      "grad_norm": 0.5782381769703572,
+      "learning_rate": 4.2181567138419054e-05,
+      "loss": 0.4136,
+      "num_tokens": 810397834.0,
+      "step": 775
+    },
+    {
+      "epoch": 0.7265952491849091,
+      "grad_norm": 0.41650244211144916,
+      "learning_rate": 4.209527096996894e-05,
+      "loss": 0.4304,
+      "num_tokens": 815565546.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.7312529110386586,
+      "grad_norm": 0.43752752013886975,
+      "learning_rate": 4.200897480151881e-05,
+      "loss": 0.4228,
+      "num_tokens": 820802646.0,
+      "step": 785
+    },
+    {
+      "epoch": 0.735910572892408,
+      "grad_norm": 0.3573411269154002,
+      "learning_rate": 4.1922678633068695e-05,
+      "loss": 0.414,
+      "num_tokens": 826045526.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.7405682347461574,
+      "grad_norm": 0.37034836674225624,
+      "learning_rate": 4.1836382464618573e-05,
+      "loss": 0.4235,
+      "num_tokens": 831245076.0,
+      "step": 795
+    },
+    {
+      "epoch": 0.7452258965999069,
+      "grad_norm": 0.3473109235091556,
+      "learning_rate": 4.175008629616845e-05,
+      "loss": 0.4174,
+      "num_tokens": 836487956.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.7498835584536563,
+      "grad_norm": 0.3454248879956119,
+      "learning_rate": 4.166379012771833e-05,
+      "loss": 0.4343,
+      "num_tokens": 841670226.0,
+      "step": 805
+    },
+    {
+      "epoch": 0.7545412203074057,
+      "grad_norm": 0.45090929011440717,
+      "learning_rate": 4.157749395926821e-05,
+      "loss": 0.4188,
+      "num_tokens": 846891280.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.759198882161155,
+      "grad_norm": 0.43284998579291406,
+      "learning_rate": 4.1491197790818086e-05,
+      "loss": 0.4216,
+      "num_tokens": 852076096.0,
+      "step": 815
+    },
+    {
+      "epoch": 0.7638565440149045,
+      "grad_norm": 0.3181896282241753,
+      "learning_rate": 4.140490162236797e-05,
+      "loss": 0.4204,
+      "num_tokens": 857318976.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.7685142058686539,
+      "grad_norm": 0.46883689539559736,
+      "learning_rate": 4.131860545391785e-05,
+      "loss": 0.4102,
+      "num_tokens": 862561856.0,
+      "step": 825
+    },
+    {
+      "epoch": 0.7731718677224033,
+      "grad_norm": 0.43638309621826277,
+      "learning_rate": 4.123230928546773e-05,
+      "loss": 0.4193,
+      "num_tokens": 867804736.0,
+      "step": 830
+    },
+    {
+      "epoch": 0.7778295295761528,
+      "grad_norm": 0.5494788138169401,
+      "learning_rate": 4.1146013117017606e-05,
+      "loss": 0.4255,
+      "num_tokens": 873045328.0,
+      "step": 835
+    },
+    {
+      "epoch": 0.7824871914299022,
+      "grad_norm": 0.35117057126261253,
+      "learning_rate": 4.1059716948567484e-05,
+      "loss": 0.41,
+      "num_tokens": 878249566.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.7871448532836516,
+      "grad_norm": 0.547134386710333,
+      "learning_rate": 4.097342078011737e-05,
+      "loss": 0.4179,
+      "num_tokens": 883492446.0,
+      "step": 845
+    },
+    {
+      "epoch": 0.7918025151374011,
+      "grad_norm": 0.3667952082270578,
+      "learning_rate": 4.088712461166724e-05,
+      "loss": 0.4179,
+      "num_tokens": 888735326.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "grad_norm": 0.35029407025170417,
+      "learning_rate": 4.080082844321712e-05,
+      "loss": 0.4093,
+      "num_tokens": 893978206.0,
+      "step": 855
+    },
+    {
+      "epoch": 0.8011178388448998,
+      "grad_norm": 0.39249238026288563,
+      "learning_rate": 4.0714532274767004e-05,
+      "loss": 0.4114,
+      "num_tokens": 899180370.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.8057755006986492,
+      "grad_norm": 0.3511762742188835,
+      "learning_rate": 4.062823610631688e-05,
+      "loss": 0.4151,
+      "num_tokens": 904405480.0,
+      "step": 865
+    },
+    {
+      "epoch": 0.8104331625523987,
+      "grad_norm": 0.42731908571108257,
+      "learning_rate": 4.054193993786676e-05,
+      "loss": 0.4087,
+      "num_tokens": 909648360.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.8150908244061481,
+      "grad_norm": 0.5462125566533138,
+      "learning_rate": 4.045564376941664e-05,
+      "loss": 0.4192,
+      "num_tokens": 914891240.0,
+      "step": 875
+    },
+    {
+      "epoch": 0.8197484862598975,
+      "grad_norm": 0.4238114065916947,
+      "learning_rate": 4.036934760096652e-05,
+      "loss": 0.4035,
+      "num_tokens": 920134120.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.824406148113647,
+      "grad_norm": 0.4511242532489273,
+      "learning_rate": 4.02830514325164e-05,
+      "loss": 0.4193,
+      "num_tokens": 925348344.0,
+      "step": 885
+    },
+    {
+      "epoch": 0.8290638099673964,
+      "grad_norm": 0.3718602180962659,
+      "learning_rate": 4.019675526406628e-05,
+      "loss": 0.4183,
+      "num_tokens": 930591224.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.8337214718211458,
+      "grad_norm": 0.42228810579780685,
+      "learning_rate": 4.011045909561615e-05,
+      "loss": 0.417,
+      "num_tokens": 935834104.0,
+      "step": 895
+    },
+    {
+      "epoch": 0.8383791336748952,
+      "grad_norm": 0.3343462952586969,
+      "learning_rate": 4.0024162927166037e-05,
+      "loss": 0.413,
+      "num_tokens": 941076984.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.8430367955286446,
+      "grad_norm": 0.3695657194075559,
+      "learning_rate": 3.9937866758715915e-05,
+      "loss": 0.4166,
+      "num_tokens": 946319864.0,
+      "step": 905
+    },
+    {
+      "epoch": 0.847694457382394,
+      "grad_norm": 0.3692226356910684,
+      "learning_rate": 3.98515705902658e-05,
+      "loss": 0.4228,
+      "num_tokens": 951515422.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.8523521192361434,
+      "grad_norm": 0.46933444657499496,
+      "learning_rate": 3.976527442181567e-05,
+      "loss": 0.4137,
+      "num_tokens": 956704248.0,
+      "step": 915
+    },
+    {
+      "epoch": 0.8570097810898929,
+      "grad_norm": 0.420307871401766,
+      "learning_rate": 3.967897825336555e-05,
+      "loss": 0.4209,
+      "num_tokens": 961947128.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.8616674429436423,
+      "grad_norm": 0.3405221647756501,
+      "learning_rate": 3.9592682084915434e-05,
+      "loss": 0.4147,
+      "num_tokens": 967190008.0,
+      "step": 925
+    },
+    {
+      "epoch": 0.8663251047973917,
+      "grad_norm": 0.44331006916678434,
+      "learning_rate": 3.950638591646531e-05,
+      "loss": 0.4178,
+      "num_tokens": 972432888.0,
+      "step": 930
+    },
+    {
+      "epoch": 0.8709827666511412,
+      "grad_norm": 0.3422809377363051,
+      "learning_rate": 3.942008974801519e-05,
+      "loss": 0.4039,
+      "num_tokens": 977675768.0,
+      "step": 935
+    },
+    {
+      "epoch": 0.8756404285048905,
+      "grad_norm": 0.4174187028348948,
+      "learning_rate": 3.933379357956507e-05,
+      "loss": 0.4058,
+      "num_tokens": 982908826.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.8802980903586399,
+      "grad_norm": 0.36023411801863825,
+      "learning_rate": 3.924749741111495e-05,
+      "loss": 0.4083,
+      "num_tokens": 988129568.0,
+      "step": 945
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 0.37697561626191384,
+      "learning_rate": 3.916120124266483e-05,
+      "loss": 0.3982,
+      "num_tokens": 993372448.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.8896134140661388,
+      "grad_norm": 0.32970248458357243,
+      "learning_rate": 3.9074905074214704e-05,
+      "loss": 0.4124,
+      "num_tokens": 998615328.0,
+      "step": 955
+    },
+    {
+      "epoch": 0.8942710759198882,
+      "grad_norm": 0.6423339790046058,
+      "learning_rate": 3.898860890576458e-05,
+      "loss": 0.4188,
+      "num_tokens": 1003840426.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.8989287377736377,
+      "grad_norm": 0.33989654580246514,
+      "learning_rate": 3.890231273731447e-05,
+      "loss": 0.4129,
+      "num_tokens": 1009083306.0,
+      "step": 965
+    },
+    {
+      "epoch": 0.9035863996273871,
+      "grad_norm": 0.4253291410824839,
+      "learning_rate": 3.8816016568864345e-05,
+      "loss": 0.4156,
+      "num_tokens": 1014326186.0,
+      "step": 970
+    },
+    {
+      "epoch": 0.9082440614811365,
+      "grad_norm": 0.4362973979341557,
+      "learning_rate": 3.8729720400414224e-05,
+      "loss": 0.4101,
+      "num_tokens": 1019569066.0,
+      "step": 975
+    },
+    {
+      "epoch": 0.9129017233348858,
+      "grad_norm": 0.3848511989847654,
+      "learning_rate": 3.86434242319641e-05,
+      "loss": 0.4133,
+      "num_tokens": 1024811946.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.9175593851886353,
+      "grad_norm": 0.41823519040308965,
+      "learning_rate": 3.855712806351398e-05,
+      "loss": 0.4175,
+      "num_tokens": 1030054826.0,
+      "step": 985
+    },
+    {
+      "epoch": 0.9222170470423847,
+      "grad_norm": 0.4588981814462144,
+      "learning_rate": 3.8470831895063865e-05,
+      "loss": 0.3901,
+      "num_tokens": 1035279144.0,
+      "step": 990
+    },
+    {
+      "epoch": 0.9268747088961341,
+      "grad_norm": 0.42658567347281534,
+      "learning_rate": 3.838453572661374e-05,
+      "loss": 0.4065,
+      "num_tokens": 1040522024.0,
+      "step": 995
+    },
+    {
+      "epoch": 0.9315323707498836,
+      "grad_norm": 0.40893294515048517,
+      "learning_rate": 3.8298239558163615e-05,
+      "loss": 0.4098,
+      "num_tokens": 1045764904.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.936190032603633,
+      "grad_norm": 0.3307735236305363,
+      "learning_rate": 3.82119433897135e-05,
+      "loss": 0.4182,
+      "num_tokens": 1051007784.0,
+      "step": 1005
+    },
+    {
+      "epoch": 0.9408476944573824,
+      "grad_norm": 0.37133171698698186,
+      "learning_rate": 3.812564722126338e-05,
+      "loss": 0.4096,
+      "num_tokens": 1056250664.0,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9455053563111319,
+      "grad_norm": 0.3254043253190745,
+      "learning_rate": 3.8039351052813256e-05,
+      "loss": 0.4104,
+      "num_tokens": 1061493544.0,
+      "step": 1015
+    },
+    {
+      "epoch": 0.9501630181648812,
+      "grad_norm": 0.33341728510354113,
+      "learning_rate": 3.7953054884363134e-05,
+      "loss": 0.4187,
+      "num_tokens": 1066736424.0,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9548206800186306,
+      "grad_norm": 0.3507124223156066,
+      "learning_rate": 3.786675871591301e-05,
+      "loss": 0.411,
+      "num_tokens": 1071979304.0,
+      "step": 1025
+    },
+    {
+      "epoch": 0.95947834187238,
+      "grad_norm": 0.34950902787772553,
+      "learning_rate": 3.77804625474629e-05,
+      "loss": 0.4028,
+      "num_tokens": 1077222184.0,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9641360037261295,
+      "grad_norm": 0.34720406632790546,
+      "learning_rate": 3.7694166379012776e-05,
+      "loss": 0.4059,
+      "num_tokens": 1082465064.0,
+      "step": 1035
+    },
+    {
+      "epoch": 0.9687936655798789,
+      "grad_norm": 0.341563694020237,
+      "learning_rate": 3.7607870210562654e-05,
+      "loss": 0.405,
+      "num_tokens": 1087707944.0,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9734513274336283,
+      "grad_norm": 0.3609889557327282,
+      "learning_rate": 3.752157404211253e-05,
+      "loss": 0.4059,
+      "num_tokens": 1092923046.0,
+      "step": 1045
+    },
+    {
+      "epoch": 0.9781089892873778,
+      "grad_norm": 0.3125635476039176,
+      "learning_rate": 3.743527787366241e-05,
+      "loss": 0.4057,
+      "num_tokens": 1098165926.0,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9827666511411272,
+      "grad_norm": 0.3381394074099237,
+      "learning_rate": 3.734898170521229e-05,
+      "loss": 0.4098,
+      "num_tokens": 1103324696.0,
+      "step": 1055
+    },
+    {
+      "epoch": 0.9874243129948765,
+      "grad_norm": 0.3968089210296165,
+      "learning_rate": 3.7262685536762174e-05,
+      "loss": 0.409,
+      "num_tokens": 1108567576.0,
+      "step": 1060
+    },
+    {
+      "epoch": 0.992081974848626,
+      "grad_norm": 0.4001357948983539,
+      "learning_rate": 3.7176389368312045e-05,
+      "loss": 0.4079,
+      "num_tokens": 1113810456.0,
+      "step": 1065
+    },
+    {
+      "epoch": 0.9967396367023754,
+      "grad_norm": 0.36783487639258866,
+      "learning_rate": 3.709009319986193e-05,
+      "loss": 0.3987,
+      "num_tokens": 1119053336.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.00093153237075,
+      "grad_norm": 0.5233605999346443,
+      "learning_rate": 3.700379703141181e-05,
+      "loss": 0.4104,
+      "num_tokens": 1123444248.0,
+      "step": 1075
+    },
+    {
+      "epoch": 1.0055891942244992,
+      "grad_norm": 0.35621728589294477,
+      "learning_rate": 3.6917500862961687e-05,
+      "loss": 0.3564,
+      "num_tokens": 1128625632.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0102468560782487,
+      "grad_norm": 0.3379539324474777,
+      "learning_rate": 3.6831204694511565e-05,
+      "loss": 0.3426,
+      "num_tokens": 1133868512.0,
+      "step": 1085
+    },
+    {
+      "epoch": 1.0149045179319982,
+      "grad_norm": 0.3230715626176304,
+      "learning_rate": 3.674490852606144e-05,
+      "loss": 0.3558,
+      "num_tokens": 1139111392.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0195621797857475,
+      "grad_norm": 0.4474812744659829,
+      "learning_rate": 3.665861235761132e-05,
+      "loss": 0.3512,
+      "num_tokens": 1144313368.0,
+      "step": 1095
+    },
+    {
+      "epoch": 1.024219841639497,
+      "grad_norm": 0.3511076125082377,
+      "learning_rate": 3.6572316189161206e-05,
+      "loss": 0.3554,
+      "num_tokens": 1149498184.0,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3219,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 550,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.419208775350354e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:899b8628780203e488835cce3e045b8d7ec93acc6ed785462cd6b0f8850577c4
+size 7800

checkpoint-1100/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)