Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "arcee-ai/Llama-3.1-SuperNova-Lite",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.46.3"
+}

global_step268/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642cc7b69b30b7c344e9d863de93d8c593980662dcf95bd65c6fa332b79f1e03
+size 12108989031

global_step268/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e8fca885d52284e3e5187722517889141bad8a69d541c29245c731090eabf41
+size 12108989031

global_step268/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bda2e41f8ae493b42f3224fc149d035090160c4736ea27a50d3f18521aa2724
+size 12108989031

global_step268/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e381b54d1ddab162166649d89aa9494bd7d120b1a6c9520bc04e545b18b524b
+size 12108989031

global_step268/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983ce3303cb4facee3615808a7011a75e46d713945f3281579c0711cbe4d171d
+size 152165

global_step268/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37eaad7794ee0df02ede20421e7b7d9cc6cc4594c3e21717e512bfccad53058
+size 152165

global_step268/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e037808acd2c904e0f5da047fd93f698c1027eec420df922cf0f5ef1c6d894
+size 152165

global_step268/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee6fb9b4b6f8176b46b94fcb9bb96f1003dbc3ff8967858aec0b967f8af3728
+size 152165

latest

@@ -0,0 +1 @@
+global_step268

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664be2fd4f2c9305f48e2075eee9f0c81b37235c5cf5ad43dbd5f1f436017246
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ea637e5e6c0e816e6e28fa1245827d322f4f9c540f12de59a04c7445d72b6c
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fed52d254dc325ff5510458f9a45e33eb167aa86efce2e1970577ee4d198cd6
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8602c75e357b25cedde407a693233c978e2dfc0f6d820844e0b9c5a291eadc8
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee80a0e5467ec117678a56dd1cabf9c60731f957928a5fc89a3ec0a098bbc6a
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade1dac458f86f9bea8bf35b713f14e1bbed24228429534038e9f7e54ea3e8b6
+size 17208712

tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,1909 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0037313432835820895,
+      "grad_norm": 11.718372519156443,
+      "learning_rate": 2e-07,
+      "loss": 1.5946,
+      "step": 1
+    },
+    {
+      "epoch": 0.007462686567164179,
+      "grad_norm": 12.194885050328885,
+      "learning_rate": 4e-07,
+      "loss": 1.6052,
+      "step": 2
+    },
+    {
+      "epoch": 0.011194029850746268,
+      "grad_norm": 13.01588928537949,
+      "learning_rate": 6e-07,
+      "loss": 1.7294,
+      "step": 3
+    },
+    {
+      "epoch": 0.014925373134328358,
+      "grad_norm": 12.313961908592717,
+      "learning_rate": 8e-07,
+      "loss": 1.5217,
+      "step": 4
+    },
+    {
+      "epoch": 0.018656716417910446,
+      "grad_norm": 12.37356816651012,
+      "learning_rate": 1e-06,
+      "loss": 1.3742,
+      "step": 5
+    },
+    {
+      "epoch": 0.022388059701492536,
+      "grad_norm": 11.427627877521694,
+      "learning_rate": 1.2e-06,
+      "loss": 1.4112,
+      "step": 6
+    },
+    {
+      "epoch": 0.026119402985074626,
+      "grad_norm": 10.518944089588336,
+      "learning_rate": 1.4e-06,
+      "loss": 1.6147,
+      "step": 7
+    },
+    {
+      "epoch": 0.029850746268656716,
+      "grad_norm": 8.76984656973648,
+      "learning_rate": 1.6e-06,
+      "loss": 1.4108,
+      "step": 8
+    },
+    {
+      "epoch": 0.033582089552238806,
+      "grad_norm": 8.084328772350803,
+      "learning_rate": 1.8e-06,
+      "loss": 1.2484,
+      "step": 9
+    },
+    {
+      "epoch": 0.03731343283582089,
+      "grad_norm": 9.697158992831765,
+      "learning_rate": 2e-06,
+      "loss": 1.23,
+      "step": 10
+    },
+    {
+      "epoch": 0.041044776119402986,
+      "grad_norm": 18.09050975452378,
+      "learning_rate": 1.9999821640202585e-06,
+      "loss": 1.2535,
+      "step": 11
+    },
+    {
+      "epoch": 0.04477611940298507,
+      "grad_norm": 18.87482868101649,
+      "learning_rate": 1.9999286567172775e-06,
+      "loss": 1.7845,
+      "step": 12
+    },
+    {
+      "epoch": 0.048507462686567165,
+      "grad_norm": 16.46811558730055,
+      "learning_rate": 1.999839479999768e-06,
+      "loss": 1.5637,
+      "step": 13
+    },
+    {
+      "epoch": 0.05223880597014925,
+      "grad_norm": 17.76805068894177,
+      "learning_rate": 1.999714637048838e-06,
+      "loss": 1.3015,
+      "step": 14
+    },
+    {
+      "epoch": 0.055970149253731345,
+      "grad_norm": 16.79626847324504,
+      "learning_rate": 1.9995541323178804e-06,
+      "loss": 1.6793,
+      "step": 15
+    },
+    {
+      "epoch": 0.05970149253731343,
+      "grad_norm": 11.89468375626604,
+      "learning_rate": 1.9993579715324135e-06,
+      "loss": 1.3764,
+      "step": 16
+    },
+    {
+      "epoch": 0.06343283582089553,
+      "grad_norm": 10.93288879427306,
+      "learning_rate": 1.9991261616898766e-06,
+      "loss": 1.3707,
+      "step": 17
+    },
+    {
+      "epoch": 0.06716417910447761,
+      "grad_norm": 8.361062086748422,
+      "learning_rate": 1.9988587110593807e-06,
+      "loss": 1.6238,
+      "step": 18
+    },
+    {
+      "epoch": 0.0708955223880597,
+      "grad_norm": 6.736084108094181,
+      "learning_rate": 1.9985556291814147e-06,
+      "loss": 1.2496,
+      "step": 19
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "grad_norm": 7.272816093776056,
+      "learning_rate": 1.9982169268675023e-06,
+      "loss": 1.5627,
+      "step": 20
+    },
+    {
+      "epoch": 0.07835820895522388,
+      "grad_norm": 6.329740952982906,
+      "learning_rate": 1.997842616199819e-06,
+      "loss": 1.3453,
+      "step": 21
+    },
+    {
+      "epoch": 0.08208955223880597,
+      "grad_norm": 4.520010885801565,
+      "learning_rate": 1.99743271053076e-06,
+      "loss": 1.5461,
+      "step": 22
+    },
+    {
+      "epoch": 0.08582089552238806,
+      "grad_norm": 3.6042605956174354,
+      "learning_rate": 1.9969872244824635e-06,
+      "loss": 1.5243,
+      "step": 23
+    },
+    {
+      "epoch": 0.08955223880597014,
+      "grad_norm": 6.07998924732389,
+      "learning_rate": 1.99650617394629e-06,
+      "loss": 1.1925,
+      "step": 24
+    },
+    {
+      "epoch": 0.09328358208955224,
+      "grad_norm": 5.379400172850125,
+      "learning_rate": 1.9959895760822544e-06,
+      "loss": 1.3644,
+      "step": 25
+    },
+    {
+      "epoch": 0.09701492537313433,
+      "grad_norm": 5.724766090503273,
+      "learning_rate": 1.995437449318415e-06,
+      "loss": 1.282,
+      "step": 26
+    },
+    {
+      "epoch": 0.10074626865671642,
+      "grad_norm": 7.952440800639504,
+      "learning_rate": 1.994849813350215e-06,
+      "loss": 1.2719,
+      "step": 27
+    },
+    {
+      "epoch": 0.1044776119402985,
+      "grad_norm": 5.5605547177462915,
+      "learning_rate": 1.9942266891397812e-06,
+      "loss": 1.4344,
+      "step": 28
+    },
+    {
+      "epoch": 0.10820895522388059,
+      "grad_norm": 4.20729688038585,
+      "learning_rate": 1.9935680989151754e-06,
+      "loss": 1.4261,
+      "step": 29
+    },
+    {
+      "epoch": 0.11194029850746269,
+      "grad_norm": 4.179661464504617,
+      "learning_rate": 1.9928740661696007e-06,
+      "loss": 1.7263,
+      "step": 30
+    },
+    {
+      "epoch": 0.11567164179104478,
+      "grad_norm": 4.444811669926014,
+      "learning_rate": 1.992144615660566e-06,
+      "loss": 1.4733,
+      "step": 31
+    },
+    {
+      "epoch": 0.11940298507462686,
+      "grad_norm": 4.028798590389647,
+      "learning_rate": 1.9913797734089995e-06,
+      "loss": 1.2016,
+      "step": 32
+    },
+    {
+      "epoch": 0.12313432835820895,
+      "grad_norm": 3.667451061021437,
+      "learning_rate": 1.990579566698323e-06,
+      "loss": 1.3823,
+      "step": 33
+    },
+    {
+      "epoch": 0.12686567164179105,
+      "grad_norm": 3.204493378117863,
+      "learning_rate": 1.9897440240734786e-06,
+      "loss": 1.1922,
+      "step": 34
+    },
+    {
+      "epoch": 0.13059701492537312,
+      "grad_norm": 2.5157465668345225,
+      "learning_rate": 1.9888731753399087e-06,
+      "loss": 1.3169,
+      "step": 35
+    },
+    {
+      "epoch": 0.13432835820895522,
+      "grad_norm": 4.013532823842619,
+      "learning_rate": 1.9879670515624933e-06,
+      "loss": 1.5473,
+      "step": 36
+    },
+    {
+      "epoch": 0.13805970149253732,
+      "grad_norm": 4.443422336518452,
+      "learning_rate": 1.9870256850644436e-06,
+      "loss": 1.3413,
+      "step": 37
+    },
+    {
+      "epoch": 0.1417910447761194,
+      "grad_norm": 3.8185223864854443,
+      "learning_rate": 1.9860491094261476e-06,
+      "loss": 1.3775,
+      "step": 38
+    },
+    {
+      "epoch": 0.1455223880597015,
+      "grad_norm": 3.2374300805591356,
+      "learning_rate": 1.9850373594839715e-06,
+      "loss": 1.4237,
+      "step": 39
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 3.4010570222238945,
+      "learning_rate": 1.9839904713290183e-06,
+      "loss": 1.3512,
+      "step": 40
+    },
+    {
+      "epoch": 0.15298507462686567,
+      "grad_norm": 3.7069360522451036,
+      "learning_rate": 1.9829084823058396e-06,
+      "loss": 1.3539,
+      "step": 41
+    },
+    {
+      "epoch": 0.15671641791044777,
+      "grad_norm": 4.189014809102456,
+      "learning_rate": 1.9817914310111044e-06,
+      "loss": 1.184,
+      "step": 42
+    },
+    {
+      "epoch": 0.16044776119402984,
+      "grad_norm": 2.6617535657025764,
+      "learning_rate": 1.980639357292221e-06,
+      "loss": 0.9118,
+      "step": 43
+    },
+    {
+      "epoch": 0.16417910447761194,
+      "grad_norm": 5.853386102660827,
+      "learning_rate": 1.9794523022459164e-06,
+      "loss": 1.2803,
+      "step": 44
+    },
+    {
+      "epoch": 0.16791044776119404,
+      "grad_norm": 6.062445920092195,
+      "learning_rate": 1.9782303082167703e-06,
+      "loss": 1.1335,
+      "step": 45
+    },
+    {
+      "epoch": 0.17164179104477612,
+      "grad_norm": 3.931954985578852,
+      "learning_rate": 1.976973418795704e-06,
+      "loss": 1.3316,
+      "step": 46
+    },
+    {
+      "epoch": 0.17537313432835822,
+      "grad_norm": 4.463556977447332,
+      "learning_rate": 1.9756816788184255e-06,
+      "loss": 1.0166,
+      "step": 47
+    },
+    {
+      "epoch": 0.1791044776119403,
+      "grad_norm": 4.622340592834071,
+      "learning_rate": 1.974355134363832e-06,
+      "loss": 1.3222,
+      "step": 48
+    },
+    {
+      "epoch": 0.1828358208955224,
+      "grad_norm": 6.981137384760035,
+      "learning_rate": 1.972993832752363e-06,
+      "loss": 1.2864,
+      "step": 49
+    },
+    {
+      "epoch": 0.1865671641791045,
+      "grad_norm": 7.538142483116736,
+      "learning_rate": 1.9715978225443146e-06,
+      "loss": 1.3298,
+      "step": 50
+    },
+    {
+      "epoch": 0.19029850746268656,
+      "grad_norm": 5.378377013811346,
+      "learning_rate": 1.970167153538106e-06,
+      "loss": 1.6898,
+      "step": 51
+    },
+    {
+      "epoch": 0.19402985074626866,
+      "grad_norm": 4.107675209526753,
+      "learning_rate": 1.9687018767685044e-06,
+      "loss": 1.2467,
+      "step": 52
+    },
+    {
+      "epoch": 0.19776119402985073,
+      "grad_norm": 3.462570336890335,
+      "learning_rate": 1.9672020445048035e-06,
+      "loss": 1.2439,
+      "step": 53
+    },
+    {
+      "epoch": 0.20149253731343283,
+      "grad_norm": 5.1132284991358565,
+      "learning_rate": 1.9656677102489587e-06,
+      "loss": 1.2553,
+      "step": 54
+    },
+    {
+      "epoch": 0.20522388059701493,
+      "grad_norm": 6.340348167811004,
+      "learning_rate": 1.964098928733679e-06,
+      "loss": 1.1768,
+      "step": 55
+    },
+    {
+      "epoch": 0.208955223880597,
+      "grad_norm": 3.9131654258908415,
+      "learning_rate": 1.962495755920476e-06,
+      "loss": 1.2787,
+      "step": 56
+    },
+    {
+      "epoch": 0.2126865671641791,
+      "grad_norm": 4.822496966837534,
+      "learning_rate": 1.9608582489976645e-06,
+      "loss": 0.9751,
+      "step": 57
+    },
+    {
+      "epoch": 0.21641791044776118,
+      "grad_norm": 6.830738771850188,
+      "learning_rate": 1.959186466378326e-06,
+      "loss": 1.1173,
+      "step": 58
+    },
+    {
+      "epoch": 0.22014925373134328,
+      "grad_norm": 3.7173186685103716,
+      "learning_rate": 1.9574804676982214e-06,
+      "loss": 1.3968,
+      "step": 59
+    },
+    {
+      "epoch": 0.22388059701492538,
+      "grad_norm": 2.826816507380959,
+      "learning_rate": 1.955740313813667e-06,
+      "loss": 1.2454,
+      "step": 60
+    },
+    {
+      "epoch": 0.22761194029850745,
+      "grad_norm": 5.060694147656036,
+      "learning_rate": 1.9539660667993617e-06,
+      "loss": 1.2803,
+      "step": 61
+    },
+    {
+      "epoch": 0.23134328358208955,
+      "grad_norm": 4.866896848059289,
+      "learning_rate": 1.952157789946173e-06,
+      "loss": 1.3675,
+      "step": 62
+    },
+    {
+      "epoch": 0.23507462686567165,
+      "grad_norm": 3.6902361398869843,
+      "learning_rate": 1.9503155477588792e-06,
+      "loss": 1.3265,
+      "step": 63
+    },
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": 3.844263841899348,
+      "learning_rate": 1.9484394059538696e-06,
+      "loss": 1.1316,
+      "step": 64
+    },
+    {
+      "epoch": 0.24253731343283583,
+      "grad_norm": 2.7586273990747094,
+      "learning_rate": 1.9465294314567986e-06,
+      "loss": 1.1227,
+      "step": 65
+    },
+    {
+      "epoch": 0.2462686567164179,
+      "grad_norm": 4.486151113202917,
+      "learning_rate": 1.9445856924001987e-06,
+      "loss": 1.2286,
+      "step": 66
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.4213181164419453,
+      "learning_rate": 1.9426082581210507e-06,
+      "loss": 1.1066,
+      "step": 67
+    },
+    {
+      "epoch": 0.2537313432835821,
+      "grad_norm": 3.2763985271498646,
+      "learning_rate": 1.9405971991583107e-06,
+      "loss": 1.1251,
+      "step": 68
+    },
+    {
+      "epoch": 0.2574626865671642,
+      "grad_norm": 3.2345913669334014,
+      "learning_rate": 1.9385525872503914e-06,
+      "loss": 1.1556,
+      "step": 69
+    },
+    {
+      "epoch": 0.26119402985074625,
+      "grad_norm": 3.106534312573296,
+      "learning_rate": 1.9364744953326073e-06,
+      "loss": 1.0577,
+      "step": 70
+    },
+    {
+      "epoch": 0.26492537313432835,
+      "grad_norm": 2.9408023039448272,
+      "learning_rate": 1.9343629975345684e-06,
+      "loss": 0.9973,
+      "step": 71
+    },
+    {
+      "epoch": 0.26865671641791045,
+      "grad_norm": 4.559495537184346,
+      "learning_rate": 1.9322181691775386e-06,
+      "loss": 1.2465,
+      "step": 72
+    },
+    {
+      "epoch": 0.27238805970149255,
+      "grad_norm": 4.24529782366461,
+      "learning_rate": 1.9300400867717483e-06,
+      "loss": 1.0913,
+      "step": 73
+    },
+    {
+      "epoch": 0.27611940298507465,
+      "grad_norm": 5.1030664391900595,
+      "learning_rate": 1.9278288280136647e-06,
+      "loss": 1.1773,
+      "step": 74
+    },
+    {
+      "epoch": 0.2798507462686567,
+      "grad_norm": 2.266554727723586,
+      "learning_rate": 1.9255844717832204e-06,
+      "loss": 1.4612,
+      "step": 75
+    },
+    {
+      "epoch": 0.2835820895522388,
+      "grad_norm": 3.4335407395713795,
+      "learning_rate": 1.9233070981410005e-06,
+      "loss": 0.9848,
+      "step": 76
+    },
+    {
+      "epoch": 0.2873134328358209,
+      "grad_norm": 3.0840869155577066,
+      "learning_rate": 1.9209967883253844e-06,
+      "loss": 1.1614,
+      "step": 77
+    },
+    {
+      "epoch": 0.291044776119403,
+      "grad_norm": 3.9174952308981648,
+      "learning_rate": 1.9186536247496515e-06,
+      "loss": 0.993,
+      "step": 78
+    },
+    {
+      "epoch": 0.2947761194029851,
+      "grad_norm": 6.675359765928192,
+      "learning_rate": 1.916277690999037e-06,
+      "loss": 1.1993,
+      "step": 79
+    },
+    {
+      "epoch": 0.29850746268656714,
+      "grad_norm": 3.3312539449544336,
+      "learning_rate": 1.9138690718277538e-06,
+      "loss": 1.1122,
+      "step": 80
+    },
+    {
+      "epoch": 0.30223880597014924,
+      "grad_norm": 3.848892934397973,
+      "learning_rate": 1.9114278531559673e-06,
+      "loss": 1.2558,
+      "step": 81
+    },
+    {
+      "epoch": 0.30597014925373134,
+      "grad_norm": 4.176454718168841,
+      "learning_rate": 1.908954122066731e-06,
+      "loss": 1.1981,
+      "step": 82
+    },
+    {
+      "epoch": 0.30970149253731344,
+      "grad_norm": 2.73071312325315,
+      "learning_rate": 1.9064479668028799e-06,
+      "loss": 1.2421,
+      "step": 83
+    },
+    {
+      "epoch": 0.31343283582089554,
+      "grad_norm": 3.195988999340381,
+      "learning_rate": 1.903909476763883e-06,
+      "loss": 1.1304,
+      "step": 84
+    },
+    {
+      "epoch": 0.31716417910447764,
+      "grad_norm": 4.218603688955521,
+      "learning_rate": 1.9013387425026548e-06,
+      "loss": 1.1864,
+      "step": 85
+    },
+    {
+      "epoch": 0.3208955223880597,
+      "grad_norm": 3.6984773161373514,
+      "learning_rate": 1.8987358557223229e-06,
+      "loss": 1.1586,
+      "step": 86
+    },
+    {
+      "epoch": 0.3246268656716418,
+      "grad_norm": 3.92008728241735,
+      "learning_rate": 1.8961009092729597e-06,
+      "loss": 1.4377,
+      "step": 87
+    },
+    {
+      "epoch": 0.3283582089552239,
+      "grad_norm": 3.891396254447255,
+      "learning_rate": 1.8934339971482673e-06,
+      "loss": 0.8258,
+      "step": 88
+    },
+    {
+      "epoch": 0.332089552238806,
+      "grad_norm": 3.0403561652586593,
+      "learning_rate": 1.8907352144822281e-06,
+      "loss": 1.1502,
+      "step": 89
+    },
+    {
+      "epoch": 0.3358208955223881,
+      "grad_norm": 4.226515814729617,
+      "learning_rate": 1.8880046575457071e-06,
+      "loss": 1.3202,
+      "step": 90
+    },
+    {
+      "epoch": 0.33955223880597013,
+      "grad_norm": 3.1371524388050562,
+      "learning_rate": 1.8852424237430213e-06,
+      "loss": 1.0916,
+      "step": 91
+    },
+    {
+      "epoch": 0.34328358208955223,
+      "grad_norm": 5.798409840680744,
+      "learning_rate": 1.882448611608463e-06,
+      "loss": 1.0295,
+      "step": 92
+    },
+    {
+      "epoch": 0.34701492537313433,
+      "grad_norm": 3.20282503021626,
+      "learning_rate": 1.8796233208027847e-06,
+      "loss": 1.0562,
+      "step": 93
+    },
+    {
+      "epoch": 0.35074626865671643,
+      "grad_norm": 4.8622829880049165,
+      "learning_rate": 1.8767666521096466e-06,
+      "loss": 1.3517,
+      "step": 94
+    },
+    {
+      "epoch": 0.35447761194029853,
+      "grad_norm": 3.236061343689611,
+      "learning_rate": 1.8738787074320176e-06,
+      "loss": 1.3072,
+      "step": 95
+    },
+    {
+      "epoch": 0.3582089552238806,
+      "grad_norm": 2.8290205291903834,
+      "learning_rate": 1.8709595897885436e-06,
+      "loss": 1.0689,
+      "step": 96
+    },
+    {
+      "epoch": 0.3619402985074627,
+      "grad_norm": 9.248683748830997,
+      "learning_rate": 1.8680094033098714e-06,
+      "loss": 1.1408,
+      "step": 97
+    },
+    {
+      "epoch": 0.3656716417910448,
+      "grad_norm": 3.351494222719439,
+      "learning_rate": 1.865028253234933e-06,
+      "loss": 1.0601,
+      "step": 98
+    },
+    {
+      "epoch": 0.3694029850746269,
+      "grad_norm": 2.9558835746922982,
+      "learning_rate": 1.8620162459071933e-06,
+      "loss": 1.469,
+      "step": 99
+    },
+    {
+      "epoch": 0.373134328358209,
+      "grad_norm": 4.188173168279777,
+      "learning_rate": 1.8589734887708555e-06,
+      "loss": 1.0811,
+      "step": 100
+    },
+    {
+      "epoch": 0.376865671641791,
+      "grad_norm": 4.149900932370019,
+      "learning_rate": 1.855900090367029e-06,
+      "loss": 1.2524,
+      "step": 101
+    },
+    {
+      "epoch": 0.3805970149253731,
+      "grad_norm": 3.4354588132333954,
+      "learning_rate": 1.852796160329857e-06,
+      "loss": 1.2036,
+      "step": 102
+    },
+    {
+      "epoch": 0.3843283582089552,
+      "grad_norm": 7.008352254151579,
+      "learning_rate": 1.8496618093826062e-06,
+      "loss": 1.3326,
+      "step": 103
+    },
+    {
+      "epoch": 0.3880597014925373,
+      "grad_norm": 4.57793539598067,
+      "learning_rate": 1.8464971493337165e-06,
+      "loss": 1.1313,
+      "step": 104
+    },
+    {
+      "epoch": 0.3917910447761194,
+      "grad_norm": 5.023484484297041,
+      "learning_rate": 1.843302293072813e-06,
+      "loss": 1.1537,
+      "step": 105
+    },
+    {
+      "epoch": 0.39552238805970147,
+      "grad_norm": 5.417491975498189,
+      "learning_rate": 1.8400773545666786e-06,
+      "loss": 1.1948,
+      "step": 106
+    },
+    {
+      "epoch": 0.39925373134328357,
+      "grad_norm": 6.758289030774797,
+      "learning_rate": 1.8368224488551895e-06,
+      "loss": 1.4521,
+      "step": 107
+    },
+    {
+      "epoch": 0.40298507462686567,
+      "grad_norm": 3.113115656591011,
+      "learning_rate": 1.8335376920472096e-06,
+      "loss": 1.3848,
+      "step": 108
+    },
+    {
+      "epoch": 0.40671641791044777,
+      "grad_norm": 6.762254585306641,
+      "learning_rate": 1.8302232013164516e-06,
+      "loss": 1.157,
+      "step": 109
+    },
+    {
+      "epoch": 0.41044776119402987,
+      "grad_norm": 4.658736688116275,
+      "learning_rate": 1.8268790948972938e-06,
+      "loss": 1.0968,
+      "step": 110
+    },
+    {
+      "epoch": 0.4141791044776119,
+      "grad_norm": 4.3724969896587,
+      "learning_rate": 1.8235054920805651e-06,
+      "loss": 1.3121,
+      "step": 111
+    },
+    {
+      "epoch": 0.417910447761194,
+      "grad_norm": 1.9047640764173237,
+      "learning_rate": 1.8201025132092886e-06,
+      "loss": 0.966,
+      "step": 112
+    },
+    {
+      "epoch": 0.4216417910447761,
+      "grad_norm": 2.6109096330803645,
+      "learning_rate": 1.8166702796743888e-06,
+      "loss": 0.9965,
+      "step": 113
+    },
+    {
+      "epoch": 0.4253731343283582,
+      "grad_norm": 2.236001574200741,
+      "learning_rate": 1.813208913910361e-06,
+      "loss": 1.2068,
+      "step": 114
+    },
+    {
+      "epoch": 0.4291044776119403,
+      "grad_norm": 3.5252250250259904,
+      "learning_rate": 1.8097185393909047e-06,
+      "loss": 0.9945,
+      "step": 115
+    },
+    {
+      "epoch": 0.43283582089552236,
+      "grad_norm": 2.72651289344666,
+      "learning_rate": 1.8061992806245183e-06,
+      "loss": 1.1221,
+      "step": 116
+    },
+    {
+      "epoch": 0.43656716417910446,
+      "grad_norm": 2.7580533850806663,
+      "learning_rate": 1.802651263150058e-06,
+      "loss": 1.1106,
+      "step": 117
+    },
+    {
+      "epoch": 0.44029850746268656,
+      "grad_norm": 3.36730794119517,
+      "learning_rate": 1.7990746135322592e-06,
+      "loss": 1.3169,
+      "step": 118
+    },
+    {
+      "epoch": 0.44402985074626866,
+      "grad_norm": 3.602491306889906,
+      "learning_rate": 1.7954694593572225e-06,
+      "loss": 1.2271,
+      "step": 119
+    },
+    {
+      "epoch": 0.44776119402985076,
+      "grad_norm": 2.995624556867228,
+      "learning_rate": 1.7918359292278611e-06,
+      "loss": 1.4585,
+      "step": 120
+    },
+    {
+      "epoch": 0.45149253731343286,
+      "grad_norm": 2.4713376740401394,
+      "learning_rate": 1.7881741527593148e-06,
+      "loss": 1.0635,
+      "step": 121
+    },
+    {
+      "epoch": 0.4552238805970149,
+      "grad_norm": 2.9859360943624558,
+      "learning_rate": 1.7844842605743255e-06,
+      "loss": 1.1158,
+      "step": 122
+    },
+    {
+      "epoch": 0.458955223880597,
+      "grad_norm": 2.236880197413377,
+      "learning_rate": 1.7807663842985776e-06,
+      "loss": 1.0568,
+      "step": 123
+    },
+    {
+      "epoch": 0.4626865671641791,
+      "grad_norm": 2.812929367683673,
+      "learning_rate": 1.777020656556003e-06,
+      "loss": 0.9711,
+      "step": 124
+    },
+    {
+      "epoch": 0.4664179104477612,
+      "grad_norm": 2.615520237147118,
+      "learning_rate": 1.77324721096405e-06,
+      "loss": 1.2155,
+      "step": 125
+    },
+    {
+      "epoch": 0.4701492537313433,
+      "grad_norm": 2.56945954741141,
+      "learning_rate": 1.7694461821289171e-06,
+      "loss": 1.2214,
+      "step": 126
+    },
+    {
+      "epoch": 0.47388059701492535,
+      "grad_norm": 2.6524624585109255,
+      "learning_rate": 1.7656177056407504e-06,
+      "loss": 1.0783,
+      "step": 127
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": 3.900106255085836,
+      "learning_rate": 1.7617619180688084e-06,
+      "loss": 1.1345,
+      "step": 128
+    },
+    {
+      "epoch": 0.48134328358208955,
+      "grad_norm": 3.6445674759996973,
+      "learning_rate": 1.7578789569565889e-06,
+      "loss": 1.1407,
+      "step": 129
+    },
+    {
+      "epoch": 0.48507462686567165,
+      "grad_norm": 3.2321962413724834,
+      "learning_rate": 1.7539689608169236e-06,
+      "loss": 1.2281,
+      "step": 130
+    },
+    {
+      "epoch": 0.48880597014925375,
+      "grad_norm": 4.609891513693221,
+      "learning_rate": 1.7500320691270363e-06,
+      "loss": 1.2394,
+      "step": 131
+    },
+    {
+      "epoch": 0.4925373134328358,
+      "grad_norm": 6.929277355854441,
+      "learning_rate": 1.7460684223235678e-06,
+      "loss": 1.233,
+      "step": 132
+    },
+    {
+      "epoch": 0.4962686567164179,
+      "grad_norm": 3.231892093569866,
+      "learning_rate": 1.7420781617975663e-06,
+      "loss": 0.9962,
+      "step": 133
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.5090780090395115,
+      "learning_rate": 1.738061429889444e-06,
+      "loss": 0.9036,
+      "step": 134
+    },
+    {
+      "epoch": 0.503731343283582,
+      "grad_norm": 4.328856707412604,
+      "learning_rate": 1.734018369883898e-06,
+      "loss": 1.1895,
+      "step": 135
+    },
+    {
+      "epoch": 0.5074626865671642,
+      "grad_norm": 2.5691655391373875,
+      "learning_rate": 1.7299491260048019e-06,
+      "loss": 1.326,
+      "step": 136
+    },
+    {
+      "epoch": 0.5111940298507462,
+      "grad_norm": 1.732025147621955,
+      "learning_rate": 1.7258538434100576e-06,
+      "loss": 1.2479,
+      "step": 137
+    },
+    {
+      "epoch": 0.5149253731343284,
+      "grad_norm": 2.20121934912806,
+      "learning_rate": 1.7217326681864206e-06,
+      "loss": 1.0356,
+      "step": 138
+    },
+    {
+      "epoch": 0.5186567164179104,
+      "grad_norm": 1.9985655432331606,
+      "learning_rate": 1.717585747344286e-06,
+      "loss": 1.1547,
+      "step": 139
+    },
+    {
+      "epoch": 0.5223880597014925,
+      "grad_norm": 1.8929729658584291,
+      "learning_rate": 1.7134132288124464e-06,
+      "loss": 1.1972,
+      "step": 140
+    },
+    {
+      "epoch": 0.5261194029850746,
+      "grad_norm": 2.5705526162651284,
+      "learning_rate": 1.7092152614328136e-06,
+      "loss": 0.9647,
+      "step": 141
+    },
+    {
+      "epoch": 0.5298507462686567,
+      "grad_norm": 2.3300073188215134,
+      "learning_rate": 1.7049919949551099e-06,
+      "loss": 1.4177,
+      "step": 142
+    },
+    {
+      "epoch": 0.5335820895522388,
+      "grad_norm": 2.919579845785974,
+      "learning_rate": 1.7007435800315261e-06,
+      "loss": 1.0245,
+      "step": 143
+    },
+    {
+      "epoch": 0.5373134328358209,
+      "grad_norm": 2.58628020939173,
+      "learning_rate": 1.6964701682113474e-06,
+      "loss": 1.1438,
+      "step": 144
+    },
+    {
+      "epoch": 0.5410447761194029,
+      "grad_norm": 2.1810582155175906,
+      "learning_rate": 1.6921719119355466e-06,
+      "loss": 1.1709,
+      "step": 145
+    },
+    {
+      "epoch": 0.5447761194029851,
+      "grad_norm": 2.0256539029853036,
+      "learning_rate": 1.687848964531348e-06,
+      "loss": 1.2567,
+      "step": 146
+    },
+    {
+      "epoch": 0.5485074626865671,
+      "grad_norm": 2.6789651782329003,
+      "learning_rate": 1.6835014802067556e-06,
+      "loss": 1.2105,
+      "step": 147
+    },
+    {
+      "epoch": 0.5522388059701493,
+      "grad_norm": 2.2475712729751813,
+      "learning_rate": 1.6791296140450543e-06,
+      "loss": 1.0036,
+      "step": 148
+    },
+    {
+      "epoch": 0.5559701492537313,
+      "grad_norm": 3.081758388528468,
+      "learning_rate": 1.6747335219992774e-06,
+      "loss": 1.229,
+      "step": 149
+    },
+    {
+      "epoch": 0.5597014925373134,
+      "grad_norm": 3.4435580918281903,
+      "learning_rate": 1.6703133608866414e-06,
+      "loss": 1.2375,
+      "step": 150
+    },
+    {
+      "epoch": 0.5634328358208955,
+      "grad_norm": 3.6488645320162263,
+      "learning_rate": 1.6658692883829546e-06,
+      "loss": 1.2528,
+      "step": 151
+    },
+    {
+      "epoch": 0.5671641791044776,
+      "grad_norm": 2.6147378121358535,
+      "learning_rate": 1.6614014630169915e-06,
+      "loss": 1.0683,
+      "step": 152
+    },
+    {
+      "epoch": 0.5708955223880597,
+      "grad_norm": 3.4412924263138502,
+      "learning_rate": 1.6569100441648372e-06,
+      "loss": 1.2073,
+      "step": 153
+    },
+    {
+      "epoch": 0.5746268656716418,
+      "grad_norm": 3.8345977623754117,
+      "learning_rate": 1.6523951920442032e-06,
+      "loss": 1.1582,
+      "step": 154
+    },
+    {
+      "epoch": 0.5783582089552238,
+      "grad_norm": 3.049354065878489,
+      "learning_rate": 1.6478570677087116e-06,
+      "loss": 1.26,
+      "step": 155
+    },
+    {
+      "epoch": 0.582089552238806,
+      "grad_norm": 2.667157342873667,
+      "learning_rate": 1.6432958330421497e-06,
+      "loss": 1.1972,
+      "step": 156
+    },
+    {
+      "epoch": 0.585820895522388,
+      "grad_norm": 2.3988481838806517,
+      "learning_rate": 1.6387116507526955e-06,
+      "loss": 1.0296,
+      "step": 157
+    },
+    {
+      "epoch": 0.5895522388059702,
+      "grad_norm": 3.245331214881116,
+      "learning_rate": 1.6341046843671142e-06,
+      "loss": 1.0837,
+      "step": 158
+    },
+    {
+      "epoch": 0.5932835820895522,
+      "grad_norm": 2.740295402410237,
+      "learning_rate": 1.629475098224924e-06,
+      "loss": 1.0756,
+      "step": 159
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 3.8088940588573625,
+      "learning_rate": 1.6248230574725338e-06,
+      "loss": 1.2506,
+      "step": 160
+    },
+    {
+      "epoch": 0.6007462686567164,
+      "grad_norm": 5.166361637828825,
+      "learning_rate": 1.6201487280573533e-06,
+      "loss": 0.9793,
+      "step": 161
+    },
+    {
+      "epoch": 0.6044776119402985,
+      "grad_norm": 3.2415888531812485,
+      "learning_rate": 1.6154522767218723e-06,
+      "loss": 1.3401,
+      "step": 162
+    },
+    {
+      "epoch": 0.6082089552238806,
+      "grad_norm": 3.305335197143126,
+      "learning_rate": 1.6107338709977118e-06,
+      "loss": 1.4258,
+      "step": 163
+    },
+    {
+      "epoch": 0.6119402985074627,
+      "grad_norm": 3.074545865145304,
+      "learning_rate": 1.6059936791996497e-06,
+      "loss": 1.192,
+      "step": 164
+    },
+    {
+      "epoch": 0.6156716417910447,
+      "grad_norm": 2.40059366672424,
+      "learning_rate": 1.601231870419616e-06,
+      "loss": 0.984,
+      "step": 165
+    },
+    {
+      "epoch": 0.6194029850746269,
+      "grad_norm": 2.9844452713407197,
+      "learning_rate": 1.596448614520661e-06,
+      "loss": 1.1051,
+      "step": 166
+    },
+    {
+      "epoch": 0.6231343283582089,
+      "grad_norm": 3.241493731745323,
+      "learning_rate": 1.5916440821308947e-06,
+      "loss": 1.1032,
+      "step": 167
+    },
+    {
+      "epoch": 0.6268656716417911,
+      "grad_norm": 4.002012008083462,
+      "learning_rate": 1.586818444637402e-06,
+      "loss": 1.1281,
+      "step": 168
+    },
+    {
+      "epoch": 0.6305970149253731,
+      "grad_norm": 2.891081597812952,
+      "learning_rate": 1.5819718741801282e-06,
+      "loss": 1.0984,
+      "step": 169
+    },
+    {
+      "epoch": 0.6343283582089553,
+      "grad_norm": 2.510097661559307,
+      "learning_rate": 1.577104543645738e-06,
+      "loss": 0.9818,
+      "step": 170
+    },
+    {
+      "epoch": 0.6380597014925373,
+      "grad_norm": 3.9519151526817784,
+      "learning_rate": 1.5722166266614494e-06,
+      "loss": 1.403,
+      "step": 171
+    },
+    {
+      "epoch": 0.6417910447761194,
+      "grad_norm": 2.889629899144798,
+      "learning_rate": 1.5673082975888386e-06,
+      "loss": 1.4251,
+      "step": 172
+    },
+    {
+      "epoch": 0.6455223880597015,
+      "grad_norm": 3.2843979337315203,
+      "learning_rate": 1.5623797315176217e-06,
+      "loss": 1.2102,
+      "step": 173
+    },
+    {
+      "epoch": 0.6492537313432836,
+      "grad_norm": 3.851544142794571,
+      "learning_rate": 1.5574311042594077e-06,
+      "loss": 1.3174,
+      "step": 174
+    },
+    {
+      "epoch": 0.6529850746268657,
+      "grad_norm": 3.0632504419966224,
+      "learning_rate": 1.552462592341428e-06,
+      "loss": 1.2578,
+      "step": 175
+    },
+    {
+      "epoch": 0.6567164179104478,
+      "grad_norm": 2.9143363462552414,
+      "learning_rate": 1.547474373000238e-06,
+      "loss": 1.1117,
+      "step": 176
+    },
+    {
+      "epoch": 0.6604477611940298,
+      "grad_norm": 3.33708665616015,
+      "learning_rate": 1.5424666241753963e-06,
+      "loss": 1.3296,
+      "step": 177
+    },
+    {
+      "epoch": 0.664179104477612,
+      "grad_norm": 2.5174595420642767,
+      "learning_rate": 1.5374395245031157e-06,
+      "loss": 1.2501,
+      "step": 178
+    },
+    {
+      "epoch": 0.667910447761194,
+      "grad_norm": 4.722876645619478,
+      "learning_rate": 1.5323932533098924e-06,
+      "loss": 0.8606,
+      "step": 179
+    },
+    {
+      "epoch": 0.6716417910447762,
+      "grad_norm": 3.23675727446907,
+      "learning_rate": 1.527327990606108e-06,
+      "loss": 1.1848,
+      "step": 180
+    },
+    {
+      "epoch": 0.6753731343283582,
+      "grad_norm": 3.2255476770575906,
+      "learning_rate": 1.522243917079608e-06,
+      "loss": 1.1501,
+      "step": 181
+    },
+    {
+      "epoch": 0.6791044776119403,
+      "grad_norm": 2.660659180388112,
+      "learning_rate": 1.5171412140892574e-06,
+      "loss": 1.1792,
+      "step": 182
+    },
+    {
+      "epoch": 0.6828358208955224,
+      "grad_norm": 2.5742735359754656,
+      "learning_rate": 1.512020063658471e-06,
+      "loss": 1.0524,
+      "step": 183
+    },
+    {
+      "epoch": 0.6865671641791045,
+      "grad_norm": 2.7222921596819805,
+      "learning_rate": 1.5068806484687188e-06,
+      "loss": 0.9408,
+      "step": 184
+    },
+    {
+      "epoch": 0.6902985074626866,
+      "grad_norm": 2.854241224431344,
+      "learning_rate": 1.5017231518530115e-06,
+      "loss": 1.1946,
+      "step": 185
+    },
+    {
+      "epoch": 0.6940298507462687,
+      "grad_norm": 2.829758100829405,
+      "learning_rate": 1.4965477577893596e-06,
+      "loss": 1.0996,
+      "step": 186
+    },
+    {
+      "epoch": 0.6977611940298507,
+      "grad_norm": 2.7341811827310907,
+      "learning_rate": 1.4913546508942104e-06,
+      "loss": 1.3112,
+      "step": 187
+    },
+    {
+      "epoch": 0.7014925373134329,
+      "grad_norm": 2.727595416423421,
+      "learning_rate": 1.486144016415862e-06,
+      "loss": 0.8641,
+      "step": 188
+    },
+    {
+      "epoch": 0.7052238805970149,
+      "grad_norm": 2.6779321037785957,
+      "learning_rate": 1.4809160402278572e-06,
+      "loss": 1.0673,
+      "step": 189
+    },
+    {
+      "epoch": 0.7089552238805971,
+      "grad_norm": 2.105636468467112,
+      "learning_rate": 1.4756709088223507e-06,
+      "loss": 1.0804,
+      "step": 190
+    },
+    {
+      "epoch": 0.7126865671641791,
+      "grad_norm": 2.308917007984876,
+      "learning_rate": 1.470408809303457e-06,
+      "loss": 1.0657,
+      "step": 191
+    },
+    {
+      "epoch": 0.7164179104477612,
+      "grad_norm": 2.272233759263439,
+      "learning_rate": 1.4651299293805772e-06,
+      "loss": 0.97,
+      "step": 192
+    },
+    {
+      "epoch": 0.7201492537313433,
+      "grad_norm": 2.38194076941112,
+      "learning_rate": 1.459834457361702e-06,
+      "loss": 1.1996,
+      "step": 193
+    },
+    {
+      "epoch": 0.7238805970149254,
+      "grad_norm": 2.609236963602244,
+      "learning_rate": 1.4545225821466949e-06,
+      "loss": 1.4137,
+      "step": 194
+    },
+    {
+      "epoch": 0.7276119402985075,
+      "grad_norm": 2.1583872582681303,
+      "learning_rate": 1.449194493220553e-06,
+      "loss": 1.21,
+      "step": 195
+    },
+    {
+      "epoch": 0.7313432835820896,
+      "grad_norm": 2.0168668065761004,
+      "learning_rate": 1.443850380646649e-06,
+      "loss": 1.2648,
+      "step": 196
+    },
+    {
+      "epoch": 0.7350746268656716,
+      "grad_norm": 2.8244668704260434,
+      "learning_rate": 1.4384904350599496e-06,
+      "loss": 1.158,
+      "step": 197
+    },
+    {
+      "epoch": 0.7388059701492538,
+      "grad_norm": 2.154427501128158,
+      "learning_rate": 1.433114847660217e-06,
+      "loss": 1.1111,
+      "step": 198
+    },
+    {
+      "epoch": 0.7425373134328358,
+      "grad_norm": 1.905058417754889,
+      "learning_rate": 1.427723810205187e-06,
+      "loss": 0.969,
+      "step": 199
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 2.739735762190122,
+      "learning_rate": 1.4223175150037295e-06,
+      "loss": 1.2142,
+      "step": 200
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.4650290962226777,
+      "learning_rate": 1.4168961549089872e-06,
+      "loss": 1.1373,
+      "step": 201
+    },
+    {
+      "epoch": 0.753731343283582,
+      "grad_norm": 2.5869478423809786,
+      "learning_rate": 1.4114599233114986e-06,
+      "loss": 1.3506,
+      "step": 202
+    },
+    {
+      "epoch": 0.7574626865671642,
+      "grad_norm": 3.1980963820842483,
+      "learning_rate": 1.4060090141322966e-06,
+      "loss": 1.0384,
+      "step": 203
+    },
+    {
+      "epoch": 0.7611940298507462,
+      "grad_norm": 2.5362305958432443,
+      "learning_rate": 1.4005436218159925e-06,
+      "loss": 1.1983,
+      "step": 204
+    },
+    {
+      "epoch": 0.7649253731343284,
+      "grad_norm": 1.7669955812420282,
+      "learning_rate": 1.3950639413238393e-06,
+      "loss": 1.1922,
+      "step": 205
+    },
+    {
+      "epoch": 0.7686567164179104,
+      "grad_norm": 3.236818206550707,
+      "learning_rate": 1.3895701681267782e-06,
+      "loss": 1.1532,
+      "step": 206
+    },
+    {
+      "epoch": 0.7723880597014925,
+      "grad_norm": 3.1410703998345917,
+      "learning_rate": 1.384062498198464e-06,
+      "loss": 1.2707,
+      "step": 207
+    },
+    {
+      "epoch": 0.7761194029850746,
+      "grad_norm": 2.947726795909021,
+      "learning_rate": 1.3785411280082746e-06,
+      "loss": 1.1552,
+      "step": 208
+    },
+    {
+      "epoch": 0.7798507462686567,
+      "grad_norm": 4.158405889593859,
+      "learning_rate": 1.373006254514304e-06,
+      "loss": 1.1323,
+      "step": 209
+    },
+    {
+      "epoch": 0.7835820895522388,
+      "grad_norm": 3.6596410080845483,
+      "learning_rate": 1.3674580751563357e-06,
+      "loss": 1.1021,
+      "step": 210
+    },
+    {
+      "epoch": 0.7873134328358209,
+      "grad_norm": 3.4837568397902063,
+      "learning_rate": 1.361896787848798e-06,
+      "loss": 1.1507,
+      "step": 211
+    },
+    {
+      "epoch": 0.7910447761194029,
+      "grad_norm": 5.190434900700764,
+      "learning_rate": 1.3563225909737074e-06,
+      "loss": 1.1307,
+      "step": 212
+    },
+    {
+      "epoch": 0.7947761194029851,
+      "grad_norm": 3.193649918972427,
+      "learning_rate": 1.3507356833735885e-06,
+      "loss": 1.1674,
+      "step": 213
+    },
+    {
+      "epoch": 0.7985074626865671,
+      "grad_norm": 3.64309739990448,
+      "learning_rate": 1.3451362643443831e-06,
+      "loss": 1.1026,
+      "step": 214
+    },
+    {
+      "epoch": 0.8022388059701493,
+      "grad_norm": 4.480821519285648,
+      "learning_rate": 1.3395245336283396e-06,
+      "loss": 1.1305,
+      "step": 215
+    },
+    {
+      "epoch": 0.8059701492537313,
+      "grad_norm": 2.485764813025922,
+      "learning_rate": 1.333900691406889e-06,
+      "loss": 1.0909,
+      "step": 216
+    },
+    {
+      "epoch": 0.8097014925373134,
+      "grad_norm": 2.8276534151044417,
+      "learning_rate": 1.3282649382935028e-06,
+      "loss": 1.2906,
+      "step": 217
+    },
+    {
+      "epoch": 0.8134328358208955,
+      "grad_norm": 2.661022282944918,
+      "learning_rate": 1.322617475326538e-06,
+      "loss": 1.0923,
+      "step": 218
+    },
+    {
+      "epoch": 0.8171641791044776,
+      "grad_norm": 2.6551254805947053,
+      "learning_rate": 1.316958503962065e-06,
+      "loss": 1.1648,
+      "step": 219
+    },
+    {
+      "epoch": 0.8208955223880597,
+      "grad_norm": 2.3353396983390486,
+      "learning_rate": 1.3112882260666805e-06,
+      "loss": 1.2479,
+      "step": 220
+    },
+    {
+      "epoch": 0.8246268656716418,
+      "grad_norm": 1.8853847357875915,
+      "learning_rate": 1.3056068439103082e-06,
+      "loss": 0.9367,
+      "step": 221
+    },
+    {
+      "epoch": 0.8283582089552238,
+      "grad_norm": 1.7789270126386558,
+      "learning_rate": 1.299914560158982e-06,
+      "loss": 0.9866,
+      "step": 222
+    },
+    {
+      "epoch": 0.832089552238806,
+      "grad_norm": 4.437767240695352,
+      "learning_rate": 1.2942115778676175e-06,
+      "loss": 1.0143,
+      "step": 223
+    },
+    {
+      "epoch": 0.835820895522388,
+      "grad_norm": 2.643730633752304,
+      "learning_rate": 1.2884981004727675e-06,
+      "loss": 1.1737,
+      "step": 224
+    },
+    {
+      "epoch": 0.8395522388059702,
+      "grad_norm": 4.113252275049106,
+      "learning_rate": 1.2827743317853666e-06,
+      "loss": 1.278,
+      "step": 225
+    },
+    {
+      "epoch": 0.8432835820895522,
+      "grad_norm": 4.473452632975873,
+      "learning_rate": 1.2770404759834592e-06,
+      "loss": 1.2337,
+      "step": 226
+    },
+    {
+      "epoch": 0.8470149253731343,
+      "grad_norm": 3.3121627389468227,
+      "learning_rate": 1.2712967376049176e-06,
+      "loss": 0.9808,
+      "step": 227
+    },
+    {
+      "epoch": 0.8507462686567164,
+      "grad_norm": 2.765455947896225,
+      "learning_rate": 1.2655433215401437e-06,
+      "loss": 0.809,
+      "step": 228
+    },
+    {
+      "epoch": 0.8544776119402985,
+      "grad_norm": 5.806520585625066,
+      "learning_rate": 1.2597804330247629e-06,
+      "loss": 1.3475,
+      "step": 229
+    },
+    {
+      "epoch": 0.8582089552238806,
+      "grad_norm": 4.3730223037366365,
+      "learning_rate": 1.2540082776323006e-06,
+      "loss": 1.0836,
+      "step": 230
+    },
+    {
+      "epoch": 0.8619402985074627,
+      "grad_norm": 2.5075803170353987,
+      "learning_rate": 1.2482270612668507e-06,
+      "loss": 1.1071,
+      "step": 231
+    },
+    {
+      "epoch": 0.8656716417910447,
+      "grad_norm": 3.845367887472252,
+      "learning_rate": 1.242436990155728e-06,
+      "loss": 1.249,
+      "step": 232
+    },
+    {
+      "epoch": 0.8694029850746269,
+      "grad_norm": 3.2664015113912237,
+      "learning_rate": 1.2366382708421154e-06,
+      "loss": 1.1988,
+      "step": 233
+    },
+    {
+      "epoch": 0.8731343283582089,
+      "grad_norm": 3.9034686201589586,
+      "learning_rate": 1.2308311101776932e-06,
+      "loss": 1.2718,
+      "step": 234
+    },
+    {
+      "epoch": 0.8768656716417911,
+      "grad_norm": 2.1523180105846844,
+      "learning_rate": 1.2250157153152609e-06,
+      "loss": 1.1845,
+      "step": 235
+    },
+    {
+      "epoch": 0.8805970149253731,
+      "grad_norm": 2.8559179892421116,
+      "learning_rate": 1.2191922937013488e-06,
+      "loss": 1.2277,
+      "step": 236
+    },
+    {
+      "epoch": 0.8843283582089553,
+      "grad_norm": 2.4964069518984697,
+      "learning_rate": 1.2133610530688167e-06,
+      "loss": 1.1304,
+      "step": 237
+    },
+    {
+      "epoch": 0.8880597014925373,
+      "grad_norm": 1.6510558048415136,
+      "learning_rate": 1.2075222014294447e-06,
+      "loss": 1.0716,
+      "step": 238
+    },
+    {
+      "epoch": 0.8917910447761194,
+      "grad_norm": 4.138846396996276,
+      "learning_rate": 1.2016759470665109e-06,
+      "loss": 1.1715,
+      "step": 239
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "grad_norm": 2.591000009602829,
+      "learning_rate": 1.1958224985273645e-06,
+      "loss": 1.2082,
+      "step": 240
+    },
+    {
+      "epoch": 0.8992537313432836,
+      "grad_norm": 1.6656445235525534,
+      "learning_rate": 1.1899620646159853e-06,
+      "loss": 1.057,
+      "step": 241
+    },
+    {
+      "epoch": 0.9029850746268657,
+      "grad_norm": 3.4344302308874486,
+      "learning_rate": 1.1840948543855334e-06,
+      "loss": 0.9381,
+      "step": 242
+    },
+    {
+      "epoch": 0.9067164179104478,
+      "grad_norm": 2.5448689987449384,
+      "learning_rate": 1.1782210771308947e-06,
+      "loss": 1.1778,
+      "step": 243
+    },
+    {
+      "epoch": 0.9104477611940298,
+      "grad_norm": 2.2000538592782433,
+      "learning_rate": 1.1723409423812134e-06,
+      "loss": 1.1269,
+      "step": 244
+    },
+    {
+      "epoch": 0.914179104477612,
+      "grad_norm": 1.6886830906655088,
+      "learning_rate": 1.1664546598924184e-06,
+      "loss": 1.1615,
+      "step": 245
+    },
+    {
+      "epoch": 0.917910447761194,
+      "grad_norm": 2.2494221352588886,
+      "learning_rate": 1.1605624396397398e-06,
+      "loss": 1.4029,
+      "step": 246
+    },
+    {
+      "epoch": 0.9216417910447762,
+      "grad_norm": 2.012712883705275,
+      "learning_rate": 1.1546644918102196e-06,
+      "loss": 1.1799,
+      "step": 247
+    },
+    {
+      "epoch": 0.9253731343283582,
+      "grad_norm": 2.3518817671490586,
+      "learning_rate": 1.1487610267952142e-06,
+      "loss": 1.1566,
+      "step": 248
+    },
+    {
+      "epoch": 0.9291044776119403,
+      "grad_norm": 2.0646756101710593,
+      "learning_rate": 1.1428522551828882e-06,
+      "loss": 1.2883,
+      "step": 249
+    },
+    {
+      "epoch": 0.9328358208955224,
+      "grad_norm": 1.812081401132651,
+      "learning_rate": 1.1369383877507034e-06,
+      "loss": 1.2653,
+      "step": 250
+    },
+    {
+      "epoch": 0.9365671641791045,
+      "grad_norm": 2.242364078092567,
+      "learning_rate": 1.131019635457899e-06,
+      "loss": 1.1829,
+      "step": 251
+    },
+    {
+      "epoch": 0.9402985074626866,
+      "grad_norm": 2.0182289267611258,
+      "learning_rate": 1.1250962094379668e-06,
+      "loss": 0.9778,
+      "step": 252
+    },
+    {
+      "epoch": 0.9440298507462687,
+      "grad_norm": 2.4797725291235593,
+      "learning_rate": 1.1191683209911201e-06,
+      "loss": 1.0714,
+      "step": 253
+    },
+    {
+      "epoch": 0.9477611940298507,
+      "grad_norm": 2.519766746322205,
+      "learning_rate": 1.1132361815767552e-06,
+      "loss": 1.2406,
+      "step": 254
+    },
+    {
+      "epoch": 0.9514925373134329,
+      "grad_norm": 2.063185346641498,
+      "learning_rate": 1.1073000028059095e-06,
+      "loss": 0.987,
+      "step": 255
+    },
+    {
+      "epoch": 0.9552238805970149,
+      "grad_norm": 1.5333052526002764,
+      "learning_rate": 1.1013599964337106e-06,
+      "loss": 0.8951,
+      "step": 256
+    },
+    {
+      "epoch": 0.9589552238805971,
+      "grad_norm": 4.771307269529906,
+      "learning_rate": 1.095416374351826e-06,
+      "loss": 1.2666,
+      "step": 257
+    },
+    {
+      "epoch": 0.9626865671641791,
+      "grad_norm": 2.717541175438304,
+      "learning_rate": 1.0894693485809014e-06,
+      "loss": 1.1109,
+      "step": 258
+    },
+    {
+      "epoch": 0.9664179104477612,
+      "grad_norm": 2.756698383274168,
+      "learning_rate": 1.0835191312629992e-06,
+      "loss": 1.129,
+      "step": 259
+    },
+    {
+      "epoch": 0.9701492537313433,
+      "grad_norm": 1.7033771070854546,
+      "learning_rate": 1.0775659346540303e-06,
+      "loss": 0.9603,
+      "step": 260
+    },
+    {
+      "epoch": 0.9738805970149254,
+      "grad_norm": 2.5967915673434034,
+      "learning_rate": 1.0716099711161832e-06,
+      "loss": 1.1943,
+      "step": 261
+    },
+    {
+      "epoch": 0.9776119402985075,
+      "grad_norm": 2.145466598370863,
+      "learning_rate": 1.0656514531103483e-06,
+      "loss": 0.8841,
+      "step": 262
+    },
+    {
+      "epoch": 0.9813432835820896,
+      "grad_norm": 2.1800126434020477,
+      "learning_rate": 1.0596905931885373e-06,
+      "loss": 0.9661,
+      "step": 263
+    },
+    {
+      "epoch": 0.9850746268656716,
+      "grad_norm": 2.8261681835210544,
+      "learning_rate": 1.0537276039863047e-06,
+      "loss": 1.1867,
+      "step": 264
+    },
+    {
+      "epoch": 0.9888059701492538,
+      "grad_norm": 3.2978247537112586,
+      "learning_rate": 1.04776269821516e-06,
+      "loss": 1.2103,
+      "step": 265
+    },
+    {
+      "epoch": 0.9925373134328358,
+      "grad_norm": 2.8052176780437064,
+      "learning_rate": 1.0417960886549798e-06,
+      "loss": 1.3141,
+      "step": 266
+    },
+    {
+      "epoch": 0.996268656716418,
+      "grad_norm": 2.5933472539580635,
+      "learning_rate": 1.035827988146418e-06,
+      "loss": 1.078,
+      "step": 267
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.8520830177001395,
+      "learning_rate": 1.0298586095833151e-06,
+      "loss": 1.3273,
+      "step": 268
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 268,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 50952048476160.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659096d2ae736c5e31ed9dabed54c1f38dfb9371e1effe139987e156bf719538
+size 8056

zero_to_fp32.py

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