Upload folder using huggingface_hub

checkpoint-272/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "meta-math/MetaMath-Mistral-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32001
+}

checkpoint-272/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.2"
+}

checkpoint-272/global_step272/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e31849038fa9cd4678f9b66e0fd5c35fc041a94b8b208c80fd609d43b0126a0
+size 4831618059

checkpoint-272/global_step272/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:cf6fa0ee61cc028e89dd431ca628d68f10a1f95a7ff5ed098166ecc8f6d8c1f7
+size 4831618059

checkpoint-272/global_step272/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:ac6663dd6e69cfb0a3eea1233a785100ecbe6a9f90463a7f4d8fc505fdbbce3b
+size 4831618059

checkpoint-272/global_step272/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:a4112230565592bb524050869c6efe110642e4ed541727329587ea0adb1f119e
+size 4831618059

checkpoint-272/global_step272/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:f062872fdddf3358ba89f0e2c081d0665fe65398f61e674b2bb8ff363748c302
+size 4831618059

checkpoint-272/global_step272/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c346ffddb70182661cdf51a8bc119e315e3aed15d66d7130adfb1f268320ae
+size 4831618059

checkpoint-272/global_step272/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8376e6c211faf63973ea5506550505a6e4ab80119df71bce7c81e8301a07331b
+size 4831618059

checkpoint-272/global_step272/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f090e3cda29d6cdd54eb5b30634166223f1f2036143772c25b6456a05bfce39
+size 4831618059

checkpoint-272/global_step272/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92caf0a4a936c842a455a9a7dfb1f8b5f82f5adaa1b3c327e8da76f5ac5ad70
+size 4831618059

checkpoint-272/global_step272/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280bfa97e4d83b87d6b6e0bd40e16e960075c0f7cc87d31a7841a3ee3639f30a
+size 153829

checkpoint-272/global_step272/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e8cb4abe6afe1bd7dba3a8b7485c585f50fdb8f2f6c91c8d63f094c6048859c
+size 153829

checkpoint-272/global_step272/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d52d693fc7723ad49cc2f0672dc16bb568676ee6305230603aa5e256824d6e6
+size 153829

checkpoint-272/global_step272/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327184ae8ca4973115be4df9d8909ab4309b4c7d5786289ef8b4c20fd2fb41b7
+size 153829

checkpoint-272/global_step272/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f34e4df94e1fe86860c5ad6f589b08b34935929479a9b75cf4567ec42986a5
+size 153829

checkpoint-272/global_step272/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab500a98d6713dc68032e36a46e64cecdc6539c9a62b6b61040628613f0f81e8
+size 153829

checkpoint-272/global_step272/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5a4e70c3f97c371795ec0366e88e65ccd7799ec2152fe13ddfd24fdc027ab0
+size 153829

checkpoint-272/global_step272/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9df33f762b6e113595c5d0bf3d434930fa902b91a8a8eaa7fb0e94bef7670fd
+size 153829

checkpoint-272/global_step272/zero_pp_rank_8_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21bf5d06b3a94429b3b6c0c6acfce9e344c07b8bf1311da209791490c130b1c4
+size 153829

checkpoint-272/latest

@@ -0,0 +1 @@
+global_step272

checkpoint-272/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7ddd132c950151879ee704033773a1c08f22fedfbe2459a71cf1304378ddad
+size 4943170528

checkpoint-272/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254fae62a9850c1250d558ce0c0a152cbf3843311738cf4ef96d0b9eb71c8ba0
+size 4999819336

checkpoint-272/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b4497b7b6358ed1de5f189caf947738698ebcf00c3dec230c973c0552e5d86
+size 4540524536

checkpoint-272/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483480576
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-272/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37b5dbacf124b1514a121af5a0ce2c5a8e77be83bf19ae649a665a468082d28
+size 16240

checkpoint-272/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef1e45867cf45a884341d3d1df4a7485b45b65e7ef081206135e62bcccb42f5
+size 16240

checkpoint-272/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c6bfccb1c88b7ba35a635a24b890be2e0af719772c1d99cd0a5ba42ef608ec
+size 16240

checkpoint-272/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7430906032884979d0dae96997913bf4abe89d78b37987bb6dfdce3fed39b2a9
+size 16240

checkpoint-272/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d01f98d61eec8827743e7fec29e83ca6ecdd540e8d277817dce7fc06a97b258
+size 16240

checkpoint-272/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794f06b07218837f68fb7b5fe84665c13dc6a5180f685b6d8e6b4365ee8470bf
+size 16240

checkpoint-272/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406f4ad8fafa642cbfe4d8b4fd81a4a4c339ce8fed12fd4ced0b9ccd483ad18f
+size 16240

checkpoint-272/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa49f77dfa366a04d42761a422f906b99bb3991a7119ec4d497a4cd6a129c4e4
+size 16240

checkpoint-272/rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52aeb24997fb0b3fdd2c038ceb9e0a217724db63ac5cb47bb06bab9354d5be3c
+size 16240

checkpoint-272/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f321f2f0ea6e36dc3550ed5e4455f04e5d7636ce96621025506fa529386c2b11
+size 1064

checkpoint-272/trainer_state.json

@@ -0,0 +1,1965 @@
+{
+  "best_metric": 0.22680288553237915,
+  "best_model_checkpoint": "./EulerMath-Mistral-7B-model/checkpoint-272",
+  "epoch": 0.9990817263544536,
+  "eval_steps": 68,
+  "global_step": 272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 19.19068191513093,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.707,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 0.9060535430908203,
+      "eval_runtime": 1745.9683,
+      "eval_samples_per_second": 1.324,
+      "eval_steps_per_second": 0.074,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 20.035932532601844,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.7236,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 19.31513317860667,
+      "learning_rate": 1.5e-06,
+      "loss": 0.7201,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 16.561326930760348,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6717,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 9.069275733221579,
+      "learning_rate": 2.5e-06,
+      "loss": 0.573,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.0702110208300475,
+      "learning_rate": 3e-06,
+      "loss": 0.4965,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 6.5389430446896055,
+      "learning_rate": 3.5e-06,
+      "loss": 0.5093,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 7.709934958779789,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.524,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 6.1640217934257135,
+      "learning_rate": 4.5e-06,
+      "loss": 0.503,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.079182690080823,
+      "learning_rate": 5e-06,
+      "loss": 0.4787,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.269731620276111,
+      "learning_rate": 4.999956736067563e-06,
+      "loss": 0.4545,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.059214670786909,
+      "learning_rate": 4.999826945767665e-06,
+      "loss": 0.4638,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.583247385116129,
+      "learning_rate": 4.9996106335924965e-06,
+      "loss": 0.4396,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.2077663599892405,
+      "learning_rate": 4.999307807028872e-06,
+      "loss": 0.4287,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.3678816023894513,
+      "learning_rate": 4.998918476557964e-06,
+      "loss": 0.4169,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.9925263681909064,
+      "learning_rate": 4.998442655654946e-06,
+      "loss": 0.4099,
+      "step": 16
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.7706573910428134,
+      "learning_rate": 4.997880360788527e-06,
+      "loss": 0.4003,
+      "step": 17
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.6789390301868525,
+      "learning_rate": 4.997231611420374e-06,
+      "loss": 0.399,
+      "step": 18
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.5622054221426698,
+      "learning_rate": 4.996496430004446e-06,
+      "loss": 0.3885,
+      "step": 19
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.5663787846468284,
+      "learning_rate": 4.995674841986217e-06,
+      "loss": 0.3987,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.4502330087611721,
+      "learning_rate": 4.994766875801789e-06,
+      "loss": 0.3962,
+      "step": 21
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.4188997099391882,
+      "learning_rate": 4.993772562876909e-06,
+      "loss": 0.3845,
+      "step": 22
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.4360806887465898,
+      "learning_rate": 4.992691937625892e-06,
+      "loss": 0.3764,
+      "step": 23
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.4216582090099372,
+      "learning_rate": 4.991525037450412e-06,
+      "loss": 0.3712,
+      "step": 24
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.2856499279799387,
+      "learning_rate": 4.990271902738223e-06,
+      "loss": 0.3603,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.247117404577534,
+      "learning_rate": 4.988932576861754e-06,
+      "loss": 0.3652,
+      "step": 26
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.3197850379000642,
+      "learning_rate": 4.987507106176606e-06,
+      "loss": 0.371,
+      "step": 27
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.243400495941476,
+      "learning_rate": 4.985995540019956e-06,
+      "loss": 0.3599,
+      "step": 28
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.3278566257982103,
+      "learning_rate": 4.984397930708838e-06,
+      "loss": 0.3594,
+      "step": 29
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.337022527470652,
+      "learning_rate": 4.982714333538344e-06,
+      "loss": 0.3477,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.2099362672151601,
+      "learning_rate": 4.980944806779698e-06,
+      "loss": 0.3425,
+      "step": 31
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.2110593150023343,
+      "learning_rate": 4.979089411678252e-06,
+      "loss": 0.3567,
+      "step": 32
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.2334965596913852,
+      "learning_rate": 4.977148212451354e-06,
+      "loss": 0.3526,
+      "step": 33
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1687161424016368,
+      "learning_rate": 4.975121276286136e-06,
+      "loss": 0.3496,
+      "step": 34
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.1881954676378432,
+      "learning_rate": 4.973008673337181e-06,
+      "loss": 0.3321,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.2174270605971114,
+      "learning_rate": 4.970810476724097e-06,
+      "loss": 0.3446,
+      "step": 36
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.1609330509652702,
+      "learning_rate": 4.968526762528988e-06,
+      "loss": 0.341,
+      "step": 37
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.2149352568793006,
+      "learning_rate": 4.9661576097938205e-06,
+      "loss": 0.3459,
+      "step": 38
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.1885081900677397,
+      "learning_rate": 4.963703100517684e-06,
+      "loss": 0.3425,
+      "step": 39
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.113235885075549,
+      "learning_rate": 4.961163319653959e-06,
+      "loss": 0.339,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.0983562726057154,
+      "learning_rate": 4.958538355107369e-06,
+      "loss": 0.3298,
+      "step": 41
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.1594289217865181,
+      "learning_rate": 4.955828297730949e-06,
+      "loss": 0.3187,
+      "step": 42
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.1714548911644644,
+      "learning_rate": 4.953033241322887e-06,
+      "loss": 0.3373,
+      "step": 43
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.1450397323165031,
+      "learning_rate": 4.950153282623289e-06,
+      "loss": 0.3232,
+      "step": 44
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.1526363934692334,
+      "learning_rate": 4.947188521310827e-06,
+      "loss": 0.3243,
+      "step": 45
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.2175235837438554,
+      "learning_rate": 4.944139059999286e-06,
+      "loss": 0.3252,
+      "step": 46
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.099789045296574,
+      "learning_rate": 4.941005004234019e-06,
+      "loss": 0.3178,
+      "step": 47
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.2219677196886505,
+      "learning_rate": 4.937786462488284e-06,
+      "loss": 0.3185,
+      "step": 48
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.1806399387287625,
+      "learning_rate": 4.9344835461595016e-06,
+      "loss": 0.3131,
+      "step": 49
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.1320527868188186,
+      "learning_rate": 4.93109636956539e-06,
+      "loss": 0.3198,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.2551253674231917,
+      "learning_rate": 4.927625049940013e-06,
+      "loss": 0.3063,
+      "step": 51
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.1131050315591549,
+      "learning_rate": 4.9240697074297205e-06,
+      "loss": 0.3192,
+      "step": 52
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.218025833644298,
+      "learning_rate": 4.920430465088992e-06,
+      "loss": 0.3083,
+      "step": 53
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.090531576651011,
+      "learning_rate": 4.916707448876173e-06,
+      "loss": 0.3076,
+      "step": 54
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.1865422414756877,
+      "learning_rate": 4.912900787649124e-06,
+      "loss": 0.3155,
+      "step": 55
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.1236405558973956,
+      "learning_rate": 4.909010613160751e-06,
+      "loss": 0.306,
+      "step": 56
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.222805799933775,
+      "learning_rate": 4.90503706005445e-06,
+      "loss": 0.3054,
+      "step": 57
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.179814726076065,
+      "learning_rate": 4.900980265859449e-06,
+      "loss": 0.309,
+      "step": 58
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.155763655177263,
+      "learning_rate": 4.896840370986042e-06,
+      "loss": 0.2974,
+      "step": 59
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.1687171308842221,
+      "learning_rate": 4.892617518720737e-06,
+      "loss": 0.3018,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.2240587320323661,
+      "learning_rate": 4.88831185522129e-06,
+      "loss": 0.3066,
+      "step": 61
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.1042960875500205,
+      "learning_rate": 4.883923529511646e-06,
+      "loss": 0.2977,
+      "step": 62
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.1885949614868223,
+      "learning_rate": 4.87945269347679e-06,
+      "loss": 0.3087,
+      "step": 63
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1420656757477574,
+      "learning_rate": 4.874899501857477e-06,
+      "loss": 0.2904,
+      "step": 64
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1453980260713446,
+      "learning_rate": 4.87026411224489e-06,
+      "loss": 0.306,
+      "step": 65
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.2729287210416769,
+      "learning_rate": 4.865546685075174e-06,
+      "loss": 0.2938,
+      "step": 66
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.2052792222072466,
+      "learning_rate": 4.860747383623889e-06,
+      "loss": 0.2977,
+      "step": 67
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.2657508580603682,
+      "learning_rate": 4.85586637400036e-06,
+      "loss": 0.3011,
+      "step": 68
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.32630813121795654,
+      "eval_runtime": 1744.5857,
+      "eval_samples_per_second": 1.325,
+      "eval_steps_per_second": 0.074,
+      "step": 68
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.1832834131492187,
+      "learning_rate": 4.85090382514192e-06,
+      "loss": 0.2972,
+      "step": 69
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.255475532117491,
+      "learning_rate": 4.845859908808074e-06,
+      "loss": 0.302,
+      "step": 70
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.298818409489401,
+      "learning_rate": 4.8407347995745465e-06,
+      "loss": 0.2935,
+      "step": 71
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.3499885398461409,
+      "learning_rate": 4.8355286748272405e-06,
+      "loss": 0.295,
+      "step": 72
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.3446382549398914,
+      "learning_rate": 4.830241714756099e-06,
+      "loss": 0.2824,
+      "step": 73
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.2082987304246777,
+      "learning_rate": 4.8248741023488705e-06,
+      "loss": 0.3026,
+      "step": 74
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.3432457490726049,
+      "learning_rate": 4.81942602338477e-06,
+      "loss": 0.2985,
+      "step": 75
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.170337150254348,
+      "learning_rate": 4.813897666428054e-06,
+      "loss": 0.2969,
+      "step": 76
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.339414484466056,
+      "learning_rate": 4.808289222821491e-06,
+      "loss": 0.2985,
+      "step": 77
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.1944077580462804,
+      "learning_rate": 4.802600886679743e-06,
+      "loss": 0.2852,
+      "step": 78
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.357246876413576,
+      "learning_rate": 4.79683285488264e-06,
+      "loss": 0.2904,
+      "step": 79
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.4115119936533302,
+      "learning_rate": 4.790985327068376e-06,
+      "loss": 0.3079,
+      "step": 80
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.285315536324781,
+      "learning_rate": 4.7850585056265866e-06,
+      "loss": 0.2816,
+      "step": 81
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3631452273406317,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.2865,
+      "step": 82
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.196518391890594,
+      "learning_rate": 4.772967805134106e-06,
+      "loss": 0.2793,
+      "step": 83
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.2485622601747421,
+      "learning_rate": 4.766804344556414e-06,
+      "loss": 0.2827,
+      "step": 84
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.2945099002171803,
+      "learning_rate": 4.7605624272827125e-06,
+      "loss": 0.2854,
+      "step": 85
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.224576498812201,
+      "learning_rate": 4.754242269352911e-06,
+      "loss": 0.2875,
+      "step": 86
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.2535747430861524,
+      "learning_rate": 4.747844089514919e-06,
+      "loss": 0.2807,
+      "step": 87
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.171951212608294,
+      "learning_rate": 4.741368109217072e-06,
+      "loss": 0.2761,
+      "step": 88
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.2123280755320154,
+      "learning_rate": 4.734814552600469e-06,
+      "loss": 0.2832,
+      "step": 89
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.1358700523339582,
+      "learning_rate": 4.728183646491215e-06,
+      "loss": 0.2871,
+      "step": 90
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.1484698203958048,
+      "learning_rate": 4.721475620392567e-06,
+      "loss": 0.2806,
+      "step": 91
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.1887290775946084,
+      "learning_rate": 4.714690706477e-06,
+      "loss": 0.2858,
+      "step": 92
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.1568061250650739,
+      "learning_rate": 4.707829139578156e-06,
+      "loss": 0.2888,
+      "step": 93
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.176832058354239,
+      "learning_rate": 4.700891157182729e-06,
+      "loss": 0.2829,
+      "step": 94
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.138549309431515,
+      "learning_rate": 4.693876999422241e-06,
+      "loss": 0.2763,
+      "step": 95
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1479926100837645,
+      "learning_rate": 4.68678690906473e-06,
+      "loss": 0.2686,
+      "step": 96
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.1771516377197246,
+      "learning_rate": 4.679621131506347e-06,
+      "loss": 0.2814,
+      "step": 97
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.2184996974539424,
+      "learning_rate": 4.672379914762867e-06,
+      "loss": 0.2822,
+      "step": 98
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.1792108348242942,
+      "learning_rate": 4.665063509461098e-06,
+      "loss": 0.282,
+      "step": 99
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.2850683815489914,
+      "learning_rate": 4.657672168830211e-06,
+      "loss": 0.2776,
+      "step": 100
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.2508897770511975,
+      "learning_rate": 4.650206148692977e-06,
+      "loss": 0.2787,
+      "step": 101
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.2031990746786907,
+      "learning_rate": 4.642665707456908e-06,
+      "loss": 0.2719,
+      "step": 102
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.1842474930123255,
+      "learning_rate": 4.635051106105316e-06,
+      "loss": 0.2732,
+      "step": 103
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.2596970412015132,
+      "learning_rate": 4.627362608188281e-06,
+      "loss": 0.2731,
+      "step": 104
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.4294759311096437,
+      "learning_rate": 4.619600479813524e-06,
+      "loss": 0.2738,
+      "step": 105
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.31619095423113,
+      "learning_rate": 4.6117649896372055e-06,
+      "loss": 0.2764,
+      "step": 106
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.2349728666776751,
+      "learning_rate": 4.6038564088546185e-06,
+      "loss": 0.2722,
+      "step": 107
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2418477065252158,
+      "learning_rate": 4.5958750111908065e-06,
+      "loss": 0.271,
+      "step": 108
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3529322240859796,
+      "learning_rate": 4.587821072891089e-06,
+      "loss": 0.276,
+      "step": 109
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2671711562594927,
+      "learning_rate": 4.579694872711501e-06,
+      "loss": 0.2706,
+      "step": 110
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.238356873891121,
+      "learning_rate": 4.571496691909142e-06,
+      "loss": 0.2749,
+      "step": 111
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.2059912760303926,
+      "learning_rate": 4.563226814232444e-06,
+      "loss": 0.2676,
+      "step": 112
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.1876458610423755,
+      "learning_rate": 4.554885525911351e-06,
+      "loss": 0.2743,
+      "step": 113
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.1715592937521375,
+      "learning_rate": 4.54647311564741e-06,
+      "loss": 0.2734,
+      "step": 114
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.236329928620471,
+      "learning_rate": 4.53798987460378e-06,
+      "loss": 0.2855,
+      "step": 115
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.1717820999866062,
+      "learning_rate": 4.529436096395157e-06,
+      "loss": 0.2699,
+      "step": 116
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.3490101744641771,
+      "learning_rate": 4.520812077077604e-06,
+      "loss": 0.2731,
+      "step": 117
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.192962777526519,
+      "learning_rate": 4.512118115138315e-06,
+      "loss": 0.2719,
+      "step": 118
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2384657820337475,
+      "learning_rate": 4.5033545114852734e-06,
+      "loss": 0.2647,
+      "step": 119
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.2128578058956592,
+      "learning_rate": 4.494521569436845e-06,
+      "loss": 0.2615,
+      "step": 120
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.3237640584842072,
+      "learning_rate": 4.485619594711278e-06,
+      "loss": 0.2663,
+      "step": 121
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.2691929068372239,
+      "learning_rate": 4.476648895416116e-06,
+      "loss": 0.2614,
+      "step": 122
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.2606618599832538,
+      "learning_rate": 4.467609782037543e-06,
+      "loss": 0.2606,
+      "step": 123
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.3048381409549332,
+      "learning_rate": 4.4585025674296315e-06,
+      "loss": 0.2601,
+      "step": 124
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.3022768451107203,
+      "learning_rate": 4.449327566803515e-06,
+      "loss": 0.2683,
+      "step": 125
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.3820289309230962,
+      "learning_rate": 4.44008509771648e-06,
+      "loss": 0.2681,
+      "step": 126
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.2802354999925132,
+      "learning_rate": 4.430775480060973e-06,
+      "loss": 0.2648,
+      "step": 127
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.3242106497833372,
+      "learning_rate": 4.4213990360535274e-06,
+      "loss": 0.268,
+      "step": 128
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.3009976864959876,
+      "learning_rate": 4.411956090223618e-06,
+      "loss": 0.2662,
+      "step": 129
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.3212829688401424,
+      "learning_rate": 4.4024469694024194e-06,
+      "loss": 0.2605,
+      "step": 130
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.2123869956343973,
+      "learning_rate": 4.3928720027115015e-06,
+      "loss": 0.2604,
+      "step": 131
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.284537459167204,
+      "learning_rate": 4.383231521551432e-06,
+      "loss": 0.2593,
+      "step": 132
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.443338680183996,
+      "learning_rate": 4.373525859590313e-06,
+      "loss": 0.2561,
+      "step": 133
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.2809230468289576,
+      "learning_rate": 4.3637553527522265e-06,
+      "loss": 0.2599,
+      "step": 134
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.3669470609932883,
+      "learning_rate": 4.3539203392056114e-06,
+      "loss": 0.2587,
+      "step": 135
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4112940230474231,
+      "learning_rate": 4.3440211593515556e-06,
+      "loss": 0.2585,
+      "step": 136
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.28355109691619873,
+      "eval_runtime": 1744.5175,
+      "eval_samples_per_second": 1.325,
+      "eval_steps_per_second": 0.074,
+      "step": 136
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.3061396480876788,
+      "learning_rate": 4.33405815581202e-06,
+      "loss": 0.2549,
+      "step": 137
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.46460991921356,
+      "learning_rate": 4.324031673417971e-06,
+      "loss": 0.2639,
+      "step": 138
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.211168578821325,
+      "learning_rate": 4.313942059197457e-06,
+      "loss": 0.2581,
+      "step": 139
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.4657150585182341,
+      "learning_rate": 4.303789662363587e-06,
+      "loss": 0.2616,
+      "step": 140
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.4251800081691455,
+      "learning_rate": 4.29357483430245e-06,
+      "loss": 0.2668,
+      "step": 141
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.3599666478045191,
+      "learning_rate": 4.283297928560951e-06,
+      "loss": 0.2598,
+      "step": 142
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.6103346253156021,
+      "learning_rate": 4.272959300834574e-06,
+      "loss": 0.2656,
+      "step": 143
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.2184694580930981,
+      "learning_rate": 4.262559308955072e-06,
+      "loss": 0.2546,
+      "step": 144
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.3362006281948362,
+      "learning_rate": 4.252098312878083e-06,
+      "loss": 0.2557,
+      "step": 145
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.3369296531115935,
+      "learning_rate": 4.241576674670668e-06,
+      "loss": 0.2568,
+      "step": 146
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.4747872641188995,
+      "learning_rate": 4.230994758498783e-06,
+      "loss": 0.2564,
+      "step": 147
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.60778480089848,
+      "learning_rate": 4.220352930614672e-06,
+      "loss": 0.2573,
+      "step": 148
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.188044808018822,
+      "learning_rate": 4.209651559344195e-06,
+      "loss": 0.2525,
+      "step": 149
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.5856639134844415,
+      "learning_rate": 4.198891015074074e-06,
+      "loss": 0.2647,
+      "step": 150
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.2859262024596512,
+      "learning_rate": 4.1880716702390764e-06,
+      "loss": 0.2471,
+      "step": 151
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.4653590828956073,
+      "learning_rate": 4.177193899309127e-06,
+      "loss": 0.2575,
+      "step": 152
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1821237121686685,
+      "learning_rate": 4.166258078776342e-06,
+      "loss": 0.2493,
+      "step": 153
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.575597475848357,
+      "learning_rate": 4.155264587142002e-06,
+      "loss": 0.2537,
+      "step": 154
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.2702085752651588,
+      "learning_rate": 4.144213804903449e-06,
+      "loss": 0.2493,
+      "step": 155
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.5026735427361002,
+      "learning_rate": 4.133106114540923e-06,
+      "loss": 0.2505,
+      "step": 156
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.5297903686100347,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.2472,
+      "step": 157
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.25258373375573,
+      "learning_rate": 4.110721549199866e-06,
+      "loss": 0.2487,
+      "step": 158
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.5941545034573665,
+      "learning_rate": 4.099445448976793e-06,
+      "loss": 0.2497,
+      "step": 159
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.3096080921873048,
+      "learning_rate": 4.088113990113846e-06,
+      "loss": 0.2439,
+      "step": 160
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.6950266606195492,
+      "learning_rate": 4.076727564805803e-06,
+      "loss": 0.2538,
+      "step": 161
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.440485526817555,
+      "learning_rate": 4.065286567149891e-06,
+      "loss": 0.2613,
+      "step": 162
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.606032223752871,
+      "learning_rate": 4.0537913931321495e-06,
+      "loss": 0.2505,
+      "step": 163
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.5319951141665498,
+      "learning_rate": 4.042242440613724e-06,
+      "loss": 0.256,
+      "step": 164
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.3468098768373629,
+      "learning_rate": 4.030640109317096e-06,
+      "loss": 0.2424,
+      "step": 165
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.6652562481471478,
+      "learning_rate": 4.018984800812248e-06,
+      "loss": 0.2396,
+      "step": 166
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.302975081280886,
+      "learning_rate": 4.007276918502763e-06,
+      "loss": 0.2462,
+      "step": 167
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.623125313268604,
+      "learning_rate": 3.995516867611865e-06,
+      "loss": 0.256,
+      "step": 168
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.3069782036585045,
+      "learning_rate": 3.983705055168391e-06,
+      "loss": 0.2518,
+      "step": 169
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.6527449270834242,
+      "learning_rate": 3.971841889992706e-06,
+      "loss": 0.2544,
+      "step": 170
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.3586948189643275,
+      "learning_rate": 3.959927782682551e-06,
+      "loss": 0.2491,
+      "step": 171
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.3440233460948727,
+      "learning_rate": 3.947963145598833e-06,
+      "loss": 0.2516,
+      "step": 172
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.3389168317613516,
+      "learning_rate": 3.935948392851354e-06,
+      "loss": 0.2541,
+      "step": 173
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.3142664585396417,
+      "learning_rate": 3.923883940284472e-06,
+      "loss": 0.2508,
+      "step": 174
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.2767521320981983,
+      "learning_rate": 3.911770205462717e-06,
+      "loss": 0.2479,
+      "step": 175
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.3281972191838929,
+      "learning_rate": 3.899607607656334e-06,
+      "loss": 0.2501,
+      "step": 176
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.3793116543581005,
+      "learning_rate": 3.887396567826769e-06,
+      "loss": 0.2454,
+      "step": 177
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.3293987156576104,
+      "learning_rate": 3.875137508612104e-06,
+      "loss": 0.249,
+      "step": 178
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.4957835845929142,
+      "learning_rate": 3.862830854312427e-06,
+      "loss": 0.2445,
+      "step": 179
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.2804679875446887,
+      "learning_rate": 3.850477030875147e-06,
+      "loss": 0.2411,
+      "step": 180
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.5611119218300138,
+      "learning_rate": 3.838076465880248e-06,
+      "loss": 0.237,
+      "step": 181
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.3387338916825537,
+      "learning_rate": 3.825629588525498e-06,
+      "loss": 0.2429,
+      "step": 182
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.5091720406707172,
+      "learning_rate": 3.813136829611583e-06,
+      "loss": 0.2428,
+      "step": 183
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.359116281666385,
+      "learning_rate": 3.8005986215272056e-06,
+      "loss": 0.2543,
+      "step": 184
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.4094254259139338,
+      "learning_rate": 3.7880153982341167e-06,
+      "loss": 0.2502,
+      "step": 185
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.2806047483095333,
+      "learning_rate": 3.7753875952520943e-06,
+      "loss": 0.2431,
+      "step": 186
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.409218880016104,
+      "learning_rate": 3.7627156496438686e-06,
+      "loss": 0.2463,
+      "step": 187
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.2466244404207094,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.2372,
+      "step": 188
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.4192484726979884,
+      "learning_rate": 3.7372410864236954e-06,
+      "loss": 0.2396,
+      "step": 189
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.3260879207799772,
+      "learning_rate": 3.7244393505155713e-06,
+      "loss": 0.241,
+      "step": 190
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.6407257220698948,
+      "learning_rate": 3.7115952353583804e-06,
+      "loss": 0.2552,
+      "step": 191
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.4113760059054485,
+      "learning_rate": 3.6987091855016667e-06,
+      "loss": 0.2513,
+      "step": 192
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.3008883773347888,
+      "learning_rate": 3.6857816469463806e-06,
+      "loss": 0.2361,
+      "step": 193
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.3040857591494066,
+      "learning_rate": 3.6728130671294485e-06,
+      "loss": 0.2491,
+      "step": 194
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.2543618451342111,
+      "learning_rate": 3.6598038949082777e-06,
+      "loss": 0.2309,
+      "step": 195
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3944108707435374,
+      "learning_rate": 3.6467545805452266e-06,
+      "loss": 0.2426,
+      "step": 196
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.301851485207592,
+      "learning_rate": 3.6336655756920198e-06,
+      "loss": 0.2421,
+      "step": 197
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.3562155385998595,
+      "learning_rate": 3.620537333374114e-06,
+      "loss": 0.2406,
+      "step": 198
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.4263666275672418,
+      "learning_rate": 3.6073703079750204e-06,
+      "loss": 0.2418,
+      "step": 199
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.2767612877970262,
+      "learning_rate": 3.594164955220577e-06,
+      "loss": 0.2353,
+      "step": 200
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.3349267171117716,
+      "learning_rate": 3.5809217321631745e-06,
+      "loss": 0.2348,
+      "step": 201
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.2217693484408796,
+      "learning_rate": 3.5676410971659404e-06,
+      "loss": 0.2287,
+      "step": 202
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.4554473054976789,
+      "learning_rate": 3.5543235098868702e-06,
+      "loss": 0.241,
+      "step": 203
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.184805169962002,
+      "learning_rate": 3.5409694312629193e-06,
+      "loss": 0.2352,
+      "step": 204
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.25444912910461426,
+      "eval_runtime": 1745.7708,
+      "eval_samples_per_second": 1.324,
+      "eval_steps_per_second": 0.074,
+      "step": 204
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.2973792749867632,
+      "learning_rate": 3.527579323494055e-06,
+      "loss": 0.2404,
+      "step": 205
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.390330195755624,
+      "learning_rate": 3.5141536500272494e-06,
+      "loss": 0.2397,
+      "step": 206
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.2415077962351395,
+      "learning_rate": 3.5006928755404467e-06,
+      "loss": 0.2296,
+      "step": 207
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.3223264932925407,
+      "learning_rate": 3.4871974659264786e-06,
+      "loss": 0.2332,
+      "step": 208
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.4376836200586416,
+      "learning_rate": 3.473667888276935e-06,
+      "loss": 0.2361,
+      "step": 209
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.2495709137167788,
+      "learning_rate": 3.4601046108660036e-06,
+      "loss": 0.2351,
+      "step": 210
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4449247677336339,
+      "learning_rate": 3.446508103134259e-06,
+      "loss": 0.2373,
+      "step": 211
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.3961526866418432,
+      "learning_rate": 3.4328788356724135e-06,
+      "loss": 0.2383,
+      "step": 212
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.2766356071702671,
+      "learning_rate": 3.419217280205032e-06,
+      "loss": 0.2348,
+      "step": 213
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.2201985305952152,
+      "learning_rate": 3.4055239095742067e-06,
+      "loss": 0.236,
+      "step": 214
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.3670381437866368,
+      "learning_rate": 3.3917991977231855e-06,
+      "loss": 0.228,
+      "step": 215
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.2724648753569285,
+      "learning_rate": 3.378043619679974e-06,
+      "loss": 0.2386,
+      "step": 216
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2826844172302947,
+      "learning_rate": 3.364257651540891e-06,
+      "loss": 0.2366,
+      "step": 217
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1767059777022655,
+      "learning_rate": 3.3504417704540925e-06,
+      "loss": 0.2251,
+      "step": 218
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.3111513963454882,
+      "learning_rate": 3.3365964546030544e-06,
+      "loss": 0.2396,
+      "step": 219
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.2617225478707708,
+      "learning_rate": 3.322722183190025e-06,
+      "loss": 0.2412,
+      "step": 220
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.2183220743609309,
+      "learning_rate": 3.308819436419437e-06,
+      "loss": 0.2276,
+      "step": 221
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.31561824749082,
+      "learning_rate": 3.2948886954812877e-06,
+      "loss": 0.2404,
+      "step": 222
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.250087552624437,
+      "learning_rate": 3.280930442534486e-06,
+      "loss": 0.2263,
+      "step": 223
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.2524310598377044,
+      "learning_rate": 3.26694516069016e-06,
+      "loss": 0.2368,
+      "step": 224
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.3487266981725987,
+      "learning_rate": 3.252933333994942e-06,
+      "loss": 0.2243,
+      "step": 225
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.2427013509424278,
+      "learning_rate": 3.238895447414211e-06,
+      "loss": 0.2366,
+      "step": 226
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.268723527146989,
+      "learning_rate": 3.2248319868153067e-06,
+      "loss": 0.2262,
+      "step": 227
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.2476040692827028,
+      "learning_rate": 3.210743438950718e-06,
+      "loss": 0.234,
+      "step": 228
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.2944243964732431,
+      "learning_rate": 3.196630291441231e-06,
+      "loss": 0.2261,
+      "step": 229
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.2348938264581308,
+      "learning_rate": 3.182493032759053e-06,
+      "loss": 0.2368,
+      "step": 230
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.3877133957904717,
+      "learning_rate": 3.168332152210909e-06,
+      "loss": 0.2342,
+      "step": 231
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2088837041711673,
+      "learning_rate": 3.154148139921102e-06,
+      "loss": 0.222,
+      "step": 232
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.4750513048080165,
+      "learning_rate": 3.1399414868145506e-06,
+      "loss": 0.2301,
+      "step": 233
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.2097458338635088,
+      "learning_rate": 3.1257126845998e-06,
+      "loss": 0.2365,
+      "step": 234
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.3570468614316236,
+      "learning_rate": 3.1114622257520004e-06,
+      "loss": 0.2275,
+      "step": 235
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.2331713108579336,
+      "learning_rate": 3.0971906034958616e-06,
+      "loss": 0.2193,
+      "step": 236
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.330924002893457,
+      "learning_rate": 3.0828983117885856e-06,
+      "loss": 0.2258,
+      "step": 237
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.2713775149937143,
+      "learning_rate": 3.0685858453027668e-06,
+      "loss": 0.2287,
+      "step": 238
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.3460227514964078,
+      "learning_rate": 3.05425369940927e-06,
+      "loss": 0.2268,
+      "step": 239
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.3124465221253792,
+      "learning_rate": 3.0399023701600903e-06,
+      "loss": 0.2237,
+      "step": 240
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.2621420000416141,
+      "learning_rate": 3.0255323542711784e-06,
+      "loss": 0.221,
+      "step": 241
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.3207975689997922,
+      "learning_rate": 3.011144149105251e-06,
+      "loss": 0.2177,
+      "step": 242
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.3364690610440046,
+      "learning_rate": 2.996738252654577e-06,
+      "loss": 0.2266,
+      "step": 243
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.3069082882086795,
+      "learning_rate": 2.9823151635237424e-06,
+      "loss": 0.2274,
+      "step": 244
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.402608898892496,
+      "learning_rate": 2.9678753809123884e-06,
+      "loss": 0.233,
+      "step": 245
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.3349783439901974,
+      "learning_rate": 2.9534194045979397e-06,
+      "loss": 0.2198,
+      "step": 246
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.3319911413244738,
+      "learning_rate": 2.938947734918302e-06,
+      "loss": 0.2241,
+      "step": 247
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.2836113523110935,
+      "learning_rate": 2.924460872754547e-06,
+      "loss": 0.2247,
+      "step": 248
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.3420053396118825,
+      "learning_rate": 2.9099593195135743e-06,
+      "loss": 0.2245,
+      "step": 249
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.3018957576647208,
+      "learning_rate": 2.8954435771107604e-06,
+      "loss": 0.2198,
+      "step": 250
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.493108819116986,
+      "learning_rate": 2.8809141479525843e-06,
+      "loss": 0.2261,
+      "step": 251
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.2240817395656585,
+      "learning_rate": 2.8663715349192388e-06,
+      "loss": 0.2182,
+      "step": 252
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.3972966685231503,
+      "learning_rate": 2.8518162413472266e-06,
+      "loss": 0.2289,
+      "step": 253
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.3158850314947335,
+      "learning_rate": 2.8372487710119374e-06,
+      "loss": 0.2286,
+      "step": 254
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.295772538693981,
+      "learning_rate": 2.8226696281102134e-06,
+      "loss": 0.2157,
+      "step": 255
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.34085577207588,
+      "learning_rate": 2.8080793172428965e-06,
+      "loss": 0.2223,
+      "step": 256
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3610764715193495,
+      "learning_rate": 2.7934783433973672e-06,
+      "loss": 0.2227,
+      "step": 257
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.2629712566442401,
+      "learning_rate": 2.778867211930061e-06,
+      "loss": 0.2263,
+      "step": 258
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.2782582856568219,
+      "learning_rate": 2.764246428548983e-06,
+      "loss": 0.2234,
+      "step": 259
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.2621019245043847,
+      "learning_rate": 2.7496164992961995e-06,
+      "loss": 0.2177,
+      "step": 260
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.2033350046761524,
+      "learning_rate": 2.7349779305303263e-06,
+      "loss": 0.2226,
+      "step": 261
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.361220136423699,
+      "learning_rate": 2.720331228909005e-06,
+      "loss": 0.2179,
+      "step": 262
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.3715434561254194,
+      "learning_rate": 2.7056769013713623e-06,
+      "loss": 0.2231,
+      "step": 263
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.1330086039392537,
+      "learning_rate": 2.691015455120468e-06,
+      "loss": 0.2164,
+      "step": 264
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.2694263709270768,
+      "learning_rate": 2.6763473976057776e-06,
+      "loss": 0.2127,
+      "step": 265
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.3274231972419466,
+      "learning_rate": 2.6616732365055713e-06,
+      "loss": 0.2092,
+      "step": 266
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.276485394682339,
+      "learning_rate": 2.64699347970938e-06,
+      "loss": 0.2206,
+      "step": 267
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.33640777595863,
+      "learning_rate": 2.6323086353004077e-06,
+      "loss": 0.2201,
+      "step": 268
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.2867150222472765,
+      "learning_rate": 2.6176192115379494e-06,
+      "loss": 0.2176,
+      "step": 269
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.220258552427881,
+      "learning_rate": 2.602925716839795e-06,
+      "loss": 0.2131,
+      "step": 270
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3301323985426015,
+      "learning_rate": 2.588228659764632e-06,
+      "loss": 0.2244,
+      "step": 271
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2313785507924382,
+      "learning_rate": 2.573528548994449e-06,
+      "loss": 0.2192,
+      "step": 272
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.22680288553237915,
+      "eval_runtime": 1744.6696,
+      "eval_samples_per_second": 1.325,
+      "eval_steps_per_second": 0.074,
+      "step": 272
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 544,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 272,
+  "total_flos": 256045146439680.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-272/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a4c76e5fdc09ec01dc7e8ead7778553f5e617c35ba83b4354ef7a547fbf2ae
+size 7352

checkpoint-272/zero_to_fp32.py

@@ -0,0 +1,592 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    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)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+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):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _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):
+    """
+    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``
+
+    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)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)

checkpoint-544/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "meta-math/MetaMath-Mistral-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32001
+}

checkpoint-544/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.2"
+}

checkpoint-544/global_step544/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:d0b635a6f6c93873bb79a1f6f7e80dcca3787ce0fda8d4098c2d40359e2fa073
+size 4831618059

checkpoint-544/global_step544/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:b42f03ac86e8e2a33c86c2e5202e8c4acdd6dc200c2f8c9a6c8e50f0318529df
+size 4831618059

checkpoint-544/global_step544/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:c92391ed04ed2926f1f28fdc573122425756b249bc2d21b2851b78baea89cd3b
+size 4831618059

checkpoint-544/global_step544/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2be3bc10a6a7a2dc37c52a0587e3fc56976e3e13b2298ddde6af69826afeeb
+size 4831618059

checkpoint-544/global_step544/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fdf1bf6bfe56ee728ffa31b8604f170adb5a5980a8b24f4aa662dfcd471d4f4
+size 4831618059

checkpoint-544/global_step544/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3684e3dd7f9c957ee35cc90c43f7ff56a82ab875b36af71f12eb184e60b603c3
+size 4831618059

checkpoint-544/global_step544/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c2672a287caac96da9b241ec70d12afbb0cf5d4540829c5f52d7fff6fa98a8
+size 4831618059

checkpoint-544/global_step544/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:ed24fdc0dc351ee4c1ad70b88af052fbf700353644b65b86afd6910ce918f61e
+size 4831618059

checkpoint-544/global_step544/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebb6b14e237e3d7ee8c339b87f536906ab23894cfd3c6ef4496c89e4053394a
+size 4831618059

checkpoint-544/global_step544/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f780232f1fbb656afded0ffeeb734c028ac6960f56536fb5bb144e06343358
+size 153829