Upload checkpoint for GALAX

.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 +1,29 @@
+{
+  "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": 8192,
+  "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": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.3"
+}

global_step333/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692047bb600324db5b2dc1046285fb340db272c1559d1c2fd73dc1569ee2e515
+size 48181574026

global_step333/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6466409a6a1266f817bce036dd755aa7a1f1eac22475301c77ec875fe09d4b2
+size 149349

latest

@@ -0,0 +1 @@
+global_step333

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe90de91a8f5da4dd18812107ee51a3feecb1067e34f0349277c6ee2f5a6785
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc16fa9488fe7e6e23715ea0b4cb2f49cca02a38407466613dc2bd6844fa741
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dcb9a7d9145e16fda325f3d342a012ba7cd09ae9e60e570ede299bd45d7090a
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b936992cf1cdfb5a0a392743207a0c8f7345f259c40034b3374817a3eb8121
+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 sha256:00966419e724d11705023e7781a58b7701f9de92d041e32217c7a585598d5410
+size 14512

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cada38f059eb4196225943ee3249585fa12f1363434a48ab5b4fff2ecd4735fe
+size 17210238

tokenizer_config.json

@@ -0,0 +1,2071 @@
+{
+  "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": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "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": "<|reserved_special_token_4|>",
+      "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": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "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 %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "max_length": 2048,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|eot_id|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
+}

trainer_state.json

@@ -0,0 +1,2379 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.933333333333334,
+  "eval_steps": 150,
+  "global_step": 335,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014814814814814815,
+      "grad_norm": 24.245065689086914,
+      "learning_rate": 0.0,
+      "loss": 1.5986,
+      "step": 1
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 24.59937286376953,
+      "learning_rate": 1.965616322328226e-06,
+      "loss": 1.5387,
+      "step": 2
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 22.017257690429688,
+      "learning_rate": 3.1154281616956676e-06,
+      "loss": 1.4677,
+      "step": 3
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 19.979198455810547,
+      "learning_rate": 3.931232644656452e-06,
+      "loss": 1.3971,
+      "step": 4
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 10.355873107910156,
+      "learning_rate": 4.5640197625830816e-06,
+      "loss": 1.1965,
+      "step": 5
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 7.20529842376709,
+      "learning_rate": 5.081044484023894e-06,
+      "loss": 1.0327,
+      "step": 6
+    },
+    {
+      "epoch": 0.1037037037037037,
+      "grad_norm": 6.543303489685059,
+      "learning_rate": 5.518182657364912e-06,
+      "loss": 1.0091,
+      "step": 7
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 5.638514041900635,
+      "learning_rate": 5.896848966984678e-06,
+      "loss": 0.8685,
+      "step": 8
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 4.796297073364258,
+      "learning_rate": 6.230856323391335e-06,
+      "loss": 0.816,
+      "step": 9
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 6.3762431144714355,
+      "learning_rate": 6.5296360849113085e-06,
+      "loss": 0.8679,
+      "step": 10
+    },
+    {
+      "epoch": 0.16296296296296298,
+      "grad_norm": 4.701241493225098,
+      "learning_rate": 6.7999152555718276e-06,
+      "loss": 0.7973,
+      "step": 11
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 4.334161281585693,
+      "learning_rate": 7.04666080635212e-06,
+      "loss": 0.6289,
+      "step": 12
+    },
+    {
+      "epoch": 0.1925925925925926,
+      "grad_norm": 2.9507179260253906,
+      "learning_rate": 7.273644709769792e-06,
+      "loss": 0.7202,
+      "step": 13
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 3.3083744049072266,
+      "learning_rate": 7.483798979693137e-06,
+      "loss": 0.6864,
+      "step": 14
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 3.1791484355926514,
+      "learning_rate": 7.679447924278749e-06,
+      "loss": 0.7458,
+      "step": 15
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 2.6846699714660645,
+      "learning_rate": 7.862465289312904e-06,
+      "loss": 0.6543,
+      "step": 16
+    },
+    {
+      "epoch": 0.2518518518518518,
+      "grad_norm": 3.1359522342681885,
+      "learning_rate": 8.034383677671775e-06,
+      "loss": 0.531,
+      "step": 17
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 3.0577006340026855,
+      "learning_rate": 8.19647264571956e-06,
+      "loss": 0.6345,
+      "step": 18
+    },
+    {
+      "epoch": 0.2814814814814815,
+      "grad_norm": 3.066653251647949,
+      "learning_rate": 8.349795656491867e-06,
+      "loss": 0.5942,
+      "step": 19
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 3.3706552982330322,
+      "learning_rate": 8.495252407239533e-06,
+      "loss": 0.638,
+      "step": 20
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 2.55362606048584,
+      "learning_rate": 8.633610819060579e-06,
+      "loss": 0.602,
+      "step": 21
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 2.864042282104492,
+      "learning_rate": 8.765531577900054e-06,
+      "loss": 0.6849,
+      "step": 22
+    },
+    {
+      "epoch": 0.34074074074074073,
+      "grad_norm": 2.357649326324463,
+      "learning_rate": 8.891587215888663e-06,
+      "loss": 0.5194,
+      "step": 23
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 2.659815549850464,
+      "learning_rate": 9.012277128680346e-06,
+      "loss": 0.4647,
+      "step": 24
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 3.5252552032470703,
+      "learning_rate": 9.128039525166163e-06,
+      "loss": 0.6621,
+      "step": 25
+    },
+    {
+      "epoch": 0.3851851851851852,
+      "grad_norm": 2.833387613296509,
+      "learning_rate": 9.239261032098019e-06,
+      "loss": 0.5758,
+      "step": 26
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.5673093795776367,
+      "learning_rate": 9.346284485087002e-06,
+      "loss": 0.4742,
+      "step": 27
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 3.8754830360412598,
+      "learning_rate": 9.449415302021363e-06,
+      "loss": 0.5632,
+      "step": 28
+    },
+    {
+      "epoch": 0.42962962962962964,
+      "grad_norm": 2.8832461833953857,
+      "learning_rate": 9.548926737583076e-06,
+      "loss": 0.5039,
+      "step": 29
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.340471029281616,
+      "learning_rate": 9.645064246606975e-06,
+      "loss": 0.4832,
+      "step": 30
+    },
+    {
+      "epoch": 0.45925925925925926,
+      "grad_norm": 3.4840638637542725,
+      "learning_rate": 9.738049131714717e-06,
+      "loss": 0.6216,
+      "step": 31
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 1.927802562713623,
+      "learning_rate": 9.828081611641132e-06,
+      "loss": 0.4316,
+      "step": 32
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 1.9146533012390137,
+      "learning_rate": 9.915343417267494e-06,
+      "loss": 0.4261,
+      "step": 33
+    },
+    {
+      "epoch": 0.5037037037037037,
+      "grad_norm": 2.636239767074585,
+      "learning_rate": 1e-05,
+      "loss": 0.4445,
+      "step": 34
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 2.7775421142578125,
+      "learning_rate": 1e-05,
+      "loss": 0.5895,
+      "step": 35
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 3.3831987380981445,
+      "learning_rate": 9.966777408637874e-06,
+      "loss": 0.5247,
+      "step": 36
+    },
+    {
+      "epoch": 0.5481481481481482,
+      "grad_norm": 2.883329391479492,
+      "learning_rate": 9.933554817275748e-06,
+      "loss": 0.4712,
+      "step": 37
+    },
+    {
+      "epoch": 0.562962962962963,
+      "grad_norm": 2.908726215362549,
+      "learning_rate": 9.900332225913623e-06,
+      "loss": 0.4991,
+      "step": 38
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 2.307657480239868,
+      "learning_rate": 9.867109634551495e-06,
+      "loss": 0.4174,
+      "step": 39
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 2.3641955852508545,
+      "learning_rate": 9.83388704318937e-06,
+      "loss": 0.5014,
+      "step": 40
+    },
+    {
+      "epoch": 0.6074074074074074,
+      "grad_norm": 2.850147247314453,
+      "learning_rate": 9.800664451827243e-06,
+      "loss": 0.5025,
+      "step": 41
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 2.9469687938690186,
+      "learning_rate": 9.767441860465117e-06,
+      "loss": 0.4127,
+      "step": 42
+    },
+    {
+      "epoch": 0.6370370370370371,
+      "grad_norm": 2.0221896171569824,
+      "learning_rate": 9.734219269102992e-06,
+      "loss": 0.4793,
+      "step": 43
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 2.2807424068450928,
+      "learning_rate": 9.700996677740865e-06,
+      "loss": 0.4363,
+      "step": 44
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.9812514781951904,
+      "learning_rate": 9.66777408637874e-06,
+      "loss": 0.472,
+      "step": 45
+    },
+    {
+      "epoch": 0.6814814814814815,
+      "grad_norm": 2.3653407096862793,
+      "learning_rate": 9.634551495016612e-06,
+      "loss": 0.4747,
+      "step": 46
+    },
+    {
+      "epoch": 0.6962962962962963,
+      "grad_norm": 1.875173807144165,
+      "learning_rate": 9.601328903654485e-06,
+      "loss": 0.4466,
+      "step": 47
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 2.5644772052764893,
+      "learning_rate": 9.56810631229236e-06,
+      "loss": 0.4908,
+      "step": 48
+    },
+    {
+      "epoch": 0.725925925925926,
+      "grad_norm": 2.5701663494110107,
+      "learning_rate": 9.534883720930234e-06,
+      "loss": 0.5709,
+      "step": 49
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 3.4693243503570557,
+      "learning_rate": 9.501661129568107e-06,
+      "loss": 0.4436,
+      "step": 50
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 1.7804033756256104,
+      "learning_rate": 9.468438538205981e-06,
+      "loss": 0.5096,
+      "step": 51
+    },
+    {
+      "epoch": 0.7703703703703704,
+      "grad_norm": 2.171896457672119,
+      "learning_rate": 9.435215946843854e-06,
+      "loss": 0.4063,
+      "step": 52
+    },
+    {
+      "epoch": 0.7851851851851852,
+      "grad_norm": 2.830214500427246,
+      "learning_rate": 9.401993355481728e-06,
+      "loss": 0.6981,
+      "step": 53
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.3130273818969727,
+      "learning_rate": 9.368770764119603e-06,
+      "loss": 0.5553,
+      "step": 54
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 2.5522916316986084,
+      "learning_rate": 9.335548172757476e-06,
+      "loss": 0.5471,
+      "step": 55
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 1.8053007125854492,
+      "learning_rate": 9.30232558139535e-06,
+      "loss": 0.4449,
+      "step": 56
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 2.2297627925872803,
+      "learning_rate": 9.269102990033223e-06,
+      "loss": 0.4782,
+      "step": 57
+    },
+    {
+      "epoch": 0.8592592592592593,
+      "grad_norm": 2.388592004776001,
+      "learning_rate": 9.235880398671098e-06,
+      "loss": 0.4333,
+      "step": 58
+    },
+    {
+      "epoch": 0.8740740740740741,
+      "grad_norm": 2.2160580158233643,
+      "learning_rate": 9.20265780730897e-06,
+      "loss": 0.397,
+      "step": 59
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.1153295040130615,
+      "learning_rate": 9.169435215946845e-06,
+      "loss": 0.4976,
+      "step": 60
+    },
+    {
+      "epoch": 0.9037037037037037,
+      "grad_norm": 2.1571428775787354,
+      "learning_rate": 9.136212624584718e-06,
+      "loss": 0.5009,
+      "step": 61
+    },
+    {
+      "epoch": 0.9185185185185185,
+      "grad_norm": 1.9368093013763428,
+      "learning_rate": 9.102990033222592e-06,
+      "loss": 0.4225,
+      "step": 62
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.793280839920044,
+      "learning_rate": 9.069767441860465e-06,
+      "loss": 0.4407,
+      "step": 63
+    },
+    {
+      "epoch": 0.9481481481481482,
+      "grad_norm": 1.7864512205123901,
+      "learning_rate": 9.03654485049834e-06,
+      "loss": 0.481,
+      "step": 64
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 2.982163429260254,
+      "learning_rate": 9.003322259136214e-06,
+      "loss": 0.5735,
+      "step": 65
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 2.1836278438568115,
+      "learning_rate": 8.970099667774087e-06,
+      "loss": 0.4532,
+      "step": 66
+    },
+    {
+      "epoch": 0.9925925925925926,
+      "grad_norm": 2.726743221282959,
+      "learning_rate": 8.93687707641196e-06,
+      "loss": 0.5093,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.726743221282959,
+      "learning_rate": 8.93687707641196e-06,
+      "loss": 0.4299,
+      "step": 68
+    },
+    {
+      "epoch": 1.0148148148148148,
+      "grad_norm": 2.7928483486175537,
+      "learning_rate": 8.903654485049834e-06,
+      "loss": 0.3207,
+      "step": 69
+    },
+    {
+      "epoch": 1.0296296296296297,
+      "grad_norm": 1.4182758331298828,
+      "learning_rate": 8.870431893687709e-06,
+      "loss": 0.4154,
+      "step": 70
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 2.5209672451019287,
+      "learning_rate": 8.837209302325582e-06,
+      "loss": 0.4017,
+      "step": 71
+    },
+    {
+      "epoch": 1.0592592592592593,
+      "grad_norm": 1.528294324874878,
+      "learning_rate": 8.803986710963456e-06,
+      "loss": 0.3515,
+      "step": 72
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 2.7746169567108154,
+      "learning_rate": 8.770764119601329e-06,
+      "loss": 0.4338,
+      "step": 73
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 1.9682352542877197,
+      "learning_rate": 8.737541528239203e-06,
+      "loss": 0.4154,
+      "step": 74
+    },
+    {
+      "epoch": 1.1037037037037036,
+      "grad_norm": 2.2559337615966797,
+      "learning_rate": 8.704318936877078e-06,
+      "loss": 0.368,
+      "step": 75
+    },
+    {
+      "epoch": 1.1185185185185185,
+      "grad_norm": 1.3220306634902954,
+      "learning_rate": 8.67109634551495e-06,
+      "loss": 0.3142,
+      "step": 76
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 2.455972671508789,
+      "learning_rate": 8.637873754152825e-06,
+      "loss": 0.4777,
+      "step": 77
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "grad_norm": 2.32432222366333,
+      "learning_rate": 8.604651162790698e-06,
+      "loss": 0.4585,
+      "step": 78
+    },
+    {
+      "epoch": 1.162962962962963,
+      "grad_norm": 2.2095751762390137,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.4513,
+      "step": 79
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 2.29775071144104,
+      "learning_rate": 8.538205980066447e-06,
+      "loss": 0.3315,
+      "step": 80
+    },
+    {
+      "epoch": 1.1925925925925926,
+      "grad_norm": 2.390573740005493,
+      "learning_rate": 8.50498338870432e-06,
+      "loss": 0.4328,
+      "step": 81
+    },
+    {
+      "epoch": 1.2074074074074075,
+      "grad_norm": 2.1682214736938477,
+      "learning_rate": 8.471760797342193e-06,
+      "loss": 0.3708,
+      "step": 82
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 2.305809736251831,
+      "learning_rate": 8.438538205980067e-06,
+      "loss": 0.333,
+      "step": 83
+    },
+    {
+      "epoch": 1.237037037037037,
+      "grad_norm": 1.9154317378997803,
+      "learning_rate": 8.40531561461794e-06,
+      "loss": 0.3514,
+      "step": 84
+    },
+    {
+      "epoch": 1.2518518518518518,
+      "grad_norm": 2.1949751377105713,
+      "learning_rate": 8.372093023255815e-06,
+      "loss": 0.3423,
+      "step": 85
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 1.4846103191375732,
+      "learning_rate": 8.338870431893689e-06,
+      "loss": 0.3935,
+      "step": 86
+    },
+    {
+      "epoch": 1.2814814814814814,
+      "grad_norm": 2.3148951530456543,
+      "learning_rate": 8.305647840531562e-06,
+      "loss": 0.3683,
+      "step": 87
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 1.7715332508087158,
+      "learning_rate": 8.272425249169436e-06,
+      "loss": 0.3415,
+      "step": 88
+    },
+    {
+      "epoch": 1.3111111111111111,
+      "grad_norm": 1.6804319620132446,
+      "learning_rate": 8.23920265780731e-06,
+      "loss": 0.4075,
+      "step": 89
+    },
+    {
+      "epoch": 1.325925925925926,
+      "grad_norm": 1.976668119430542,
+      "learning_rate": 8.205980066445184e-06,
+      "loss": 0.295,
+      "step": 90
+    },
+    {
+      "epoch": 1.3407407407407408,
+      "grad_norm": 1.8023229837417603,
+      "learning_rate": 8.172757475083057e-06,
+      "loss": 0.389,
+      "step": 91
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 1.7759190797805786,
+      "learning_rate": 8.139534883720931e-06,
+      "loss": 0.3517,
+      "step": 92
+    },
+    {
+      "epoch": 1.3703703703703702,
+      "grad_norm": 1.3482650518417358,
+      "learning_rate": 8.106312292358804e-06,
+      "loss": 0.3606,
+      "step": 93
+    },
+    {
+      "epoch": 1.3851851851851853,
+      "grad_norm": 2.5421998500823975,
+      "learning_rate": 8.073089700996678e-06,
+      "loss": 0.5241,
+      "step": 94
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.181865692138672,
+      "learning_rate": 8.039867109634553e-06,
+      "loss": 0.375,
+      "step": 95
+    },
+    {
+      "epoch": 1.4148148148148147,
+      "grad_norm": 1.7613658905029297,
+      "learning_rate": 8.006644518272426e-06,
+      "loss": 0.4339,
+      "step": 96
+    },
+    {
+      "epoch": 1.4296296296296296,
+      "grad_norm": 1.4631813764572144,
+      "learning_rate": 7.9734219269103e-06,
+      "loss": 0.3762,
+      "step": 97
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 1.71363365650177,
+      "learning_rate": 7.940199335548173e-06,
+      "loss": 0.3224,
+      "step": 98
+    },
+    {
+      "epoch": 1.4592592592592593,
+      "grad_norm": 2.1795740127563477,
+      "learning_rate": 7.906976744186048e-06,
+      "loss": 0.3816,
+      "step": 99
+    },
+    {
+      "epoch": 1.474074074074074,
+      "grad_norm": 1.5822690725326538,
+      "learning_rate": 7.873754152823922e-06,
+      "loss": 0.4523,
+      "step": 100
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 1.7851877212524414,
+      "learning_rate": 7.840531561461795e-06,
+      "loss": 0.3665,
+      "step": 101
+    },
+    {
+      "epoch": 1.5037037037037035,
+      "grad_norm": 1.671633243560791,
+      "learning_rate": 7.807308970099668e-06,
+      "loss": 0.3217,
+      "step": 102
+    },
+    {
+      "epoch": 1.5185185185185186,
+      "grad_norm": 2.666489601135254,
+      "learning_rate": 7.774086378737542e-06,
+      "loss": 0.4801,
+      "step": 103
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 1.3500992059707642,
+      "learning_rate": 7.740863787375415e-06,
+      "loss": 0.3407,
+      "step": 104
+    },
+    {
+      "epoch": 1.5481481481481483,
+      "grad_norm": 1.4269295930862427,
+      "learning_rate": 7.70764119601329e-06,
+      "loss": 0.3082,
+      "step": 105
+    },
+    {
+      "epoch": 1.5629629629629629,
+      "grad_norm": 1.4882391691207886,
+      "learning_rate": 7.674418604651164e-06,
+      "loss": 0.3497,
+      "step": 106
+    },
+    {
+      "epoch": 1.5777777777777777,
+      "grad_norm": 1.4180535078048706,
+      "learning_rate": 7.641196013289037e-06,
+      "loss": 0.3963,
+      "step": 107
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 1.4838252067565918,
+      "learning_rate": 7.6079734219269106e-06,
+      "loss": 0.3956,
+      "step": 108
+    },
+    {
+      "epoch": 1.6074074074074074,
+      "grad_norm": 2.0815930366516113,
+      "learning_rate": 7.574750830564784e-06,
+      "loss": 0.4667,
+      "step": 109
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 1.80450439453125,
+      "learning_rate": 7.541528239202659e-06,
+      "loss": 0.5329,
+      "step": 110
+    },
+    {
+      "epoch": 1.637037037037037,
+      "grad_norm": 2.5666868686676025,
+      "learning_rate": 7.508305647840532e-06,
+      "loss": 0.5433,
+      "step": 111
+    },
+    {
+      "epoch": 1.651851851851852,
+      "grad_norm": 1.733236312866211,
+      "learning_rate": 7.475083056478406e-06,
+      "loss": 0.4304,
+      "step": 112
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.059544086456299,
+      "learning_rate": 7.44186046511628e-06,
+      "loss": 0.3601,
+      "step": 113
+    },
+    {
+      "epoch": 1.6814814814814816,
+      "grad_norm": 1.8904452323913574,
+      "learning_rate": 7.408637873754153e-06,
+      "loss": 0.385,
+      "step": 114
+    },
+    {
+      "epoch": 1.6962962962962962,
+      "grad_norm": 1.3712379932403564,
+      "learning_rate": 7.375415282392027e-06,
+      "loss": 0.2972,
+      "step": 115
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 1.5603693723678589,
+      "learning_rate": 7.342192691029902e-06,
+      "loss": 0.3953,
+      "step": 116
+    },
+    {
+      "epoch": 1.7259259259259259,
+      "grad_norm": 1.4126758575439453,
+      "learning_rate": 7.308970099667775e-06,
+      "loss": 0.3582,
+      "step": 117
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 2.0345335006713867,
+      "learning_rate": 7.275747508305648e-06,
+      "loss": 0.5015,
+      "step": 118
+    },
+    {
+      "epoch": 1.7555555555555555,
+      "grad_norm": 2.6806693077087402,
+      "learning_rate": 7.242524916943522e-06,
+      "loss": 0.4006,
+      "step": 119
+    },
+    {
+      "epoch": 1.7703703703703704,
+      "grad_norm": 1.6245332956314087,
+      "learning_rate": 7.209302325581395e-06,
+      "loss": 0.4188,
+      "step": 120
+    },
+    {
+      "epoch": 1.7851851851851852,
+      "grad_norm": 1.6593953371047974,
+      "learning_rate": 7.17607973421927e-06,
+      "loss": 0.3694,
+      "step": 121
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.595201849937439,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.2838,
+      "step": 122
+    },
+    {
+      "epoch": 1.8148148148148149,
+      "grad_norm": 1.921108603477478,
+      "learning_rate": 7.109634551495017e-06,
+      "loss": 0.3044,
+      "step": 123
+    },
+    {
+      "epoch": 1.8296296296296295,
+      "grad_norm": 1.5152816772460938,
+      "learning_rate": 7.076411960132891e-06,
+      "loss": 0.3705,
+      "step": 124
+    },
+    {
+      "epoch": 1.8444444444444446,
+      "grad_norm": 1.7763299942016602,
+      "learning_rate": 7.0431893687707646e-06,
+      "loss": 0.3935,
+      "step": 125
+    },
+    {
+      "epoch": 1.8592592592592592,
+      "grad_norm": 1.3404872417449951,
+      "learning_rate": 7.009966777408639e-06,
+      "loss": 0.3951,
+      "step": 126
+    },
+    {
+      "epoch": 1.8740740740740742,
+      "grad_norm": 1.7480947971343994,
+      "learning_rate": 6.976744186046513e-06,
+      "loss": 0.3694,
+      "step": 127
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 1.3903143405914307,
+      "learning_rate": 6.9435215946843855e-06,
+      "loss": 0.3963,
+      "step": 128
+    },
+    {
+      "epoch": 1.9037037037037037,
+      "grad_norm": 1.579624056816101,
+      "learning_rate": 6.910299003322259e-06,
+      "loss": 0.4147,
+      "step": 129
+    },
+    {
+      "epoch": 1.9185185185185185,
+      "grad_norm": 1.6633076667785645,
+      "learning_rate": 6.877076411960133e-06,
+      "loss": 0.415,
+      "step": 130
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 1.4897836446762085,
+      "learning_rate": 6.843853820598007e-06,
+      "loss": 0.3438,
+      "step": 131
+    },
+    {
+      "epoch": 1.9481481481481482,
+      "grad_norm": 1.7405959367752075,
+      "learning_rate": 6.810631229235881e-06,
+      "loss": 0.3973,
+      "step": 132
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 1.6084774732589722,
+      "learning_rate": 6.777408637873755e-06,
+      "loss": 0.3904,
+      "step": 133
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 1.4988147020339966,
+      "learning_rate": 6.744186046511628e-06,
+      "loss": 0.4101,
+      "step": 134
+    },
+    {
+      "epoch": 1.9925925925925925,
+      "grad_norm": 2.449335813522339,
+      "learning_rate": 6.710963455149502e-06,
+      "loss": 0.3886,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.2566375732421875,
+      "learning_rate": 6.6777408637873766e-06,
+      "loss": 0.3651,
+      "step": 136
+    },
+    {
+      "epoch": 2.0148148148148146,
+      "grad_norm": 1.5977928638458252,
+      "learning_rate": 6.64451827242525e-06,
+      "loss": 0.3709,
+      "step": 137
+    },
+    {
+      "epoch": 2.0296296296296297,
+      "grad_norm": 2.1500344276428223,
+      "learning_rate": 6.611295681063124e-06,
+      "loss": 0.4124,
+      "step": 138
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 1.3736720085144043,
+      "learning_rate": 6.578073089700997e-06,
+      "loss": 0.3334,
+      "step": 139
+    },
+    {
+      "epoch": 2.0592592592592593,
+      "grad_norm": 1.6602332592010498,
+      "learning_rate": 6.54485049833887e-06,
+      "loss": 0.3443,
+      "step": 140
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 1.5972793102264404,
+      "learning_rate": 6.511627906976745e-06,
+      "loss": 0.3969,
+      "step": 141
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.5588147640228271,
+      "learning_rate": 6.4784053156146185e-06,
+      "loss": 0.2632,
+      "step": 142
+    },
+    {
+      "epoch": 2.1037037037037036,
+      "grad_norm": 1.4944829940795898,
+      "learning_rate": 6.445182724252492e-06,
+      "loss": 0.3403,
+      "step": 143
+    },
+    {
+      "epoch": 2.1185185185185187,
+      "grad_norm": 1.799228310585022,
+      "learning_rate": 6.411960132890366e-06,
+      "loss": 0.3669,
+      "step": 144
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.5002415180206299,
+      "learning_rate": 6.3787375415282395e-06,
+      "loss": 0.3037,
+      "step": 145
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 1.5463218688964844,
+      "learning_rate": 6.345514950166114e-06,
+      "loss": 0.2999,
+      "step": 146
+    },
+    {
+      "epoch": 2.162962962962963,
+      "grad_norm": 1.8339827060699463,
+      "learning_rate": 6.312292358803988e-06,
+      "loss": 0.3781,
+      "step": 147
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 1.9693403244018555,
+      "learning_rate": 6.279069767441861e-06,
+      "loss": 0.3527,
+      "step": 148
+    },
+    {
+      "epoch": 2.1925925925925926,
+      "grad_norm": 1.3716813325881958,
+      "learning_rate": 6.245847176079734e-06,
+      "loss": 0.3193,
+      "step": 149
+    },
+    {
+      "epoch": 2.2074074074074073,
+      "grad_norm": 1.2879470586776733,
+      "learning_rate": 6.212624584717608e-06,
+      "loss": 0.3079,
+      "step": 150
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.3284484148025513,
+      "learning_rate": 6.179401993355482e-06,
+      "loss": 0.3552,
+      "step": 151
+    },
+    {
+      "epoch": 2.237037037037037,
+      "grad_norm": 1.1561126708984375,
+      "learning_rate": 6.146179401993356e-06,
+      "loss": 0.2879,
+      "step": 152
+    },
+    {
+      "epoch": 2.251851851851852,
+      "grad_norm": 1.2936991453170776,
+      "learning_rate": 6.11295681063123e-06,
+      "loss": 0.2926,
+      "step": 153
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 1.5603609085083008,
+      "learning_rate": 6.079734219269103e-06,
+      "loss": 0.3591,
+      "step": 154
+    },
+    {
+      "epoch": 2.2814814814814817,
+      "grad_norm": 1.408933162689209,
+      "learning_rate": 6.046511627906977e-06,
+      "loss": 0.3313,
+      "step": 155
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": 1.9709101915359497,
+      "learning_rate": 6.0132890365448515e-06,
+      "loss": 0.3948,
+      "step": 156
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.5349321365356445,
+      "learning_rate": 5.980066445182725e-06,
+      "loss": 0.3227,
+      "step": 157
+    },
+    {
+      "epoch": 2.325925925925926,
+      "grad_norm": 1.5960361957550049,
+      "learning_rate": 5.946843853820599e-06,
+      "loss": 0.3532,
+      "step": 158
+    },
+    {
+      "epoch": 2.3407407407407406,
+      "grad_norm": 1.8431493043899536,
+      "learning_rate": 5.9136212624584725e-06,
+      "loss": 0.3621,
+      "step": 159
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 1.875801920890808,
+      "learning_rate": 5.880398671096345e-06,
+      "loss": 0.4026,
+      "step": 160
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 1.7672104835510254,
+      "learning_rate": 5.847176079734221e-06,
+      "loss": 0.3889,
+      "step": 161
+    },
+    {
+      "epoch": 2.3851851851851853,
+      "grad_norm": 1.5263267755508423,
+      "learning_rate": 5.8139534883720935e-06,
+      "loss": 0.332,
+      "step": 162
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.624315857887268,
+      "learning_rate": 5.780730897009967e-06,
+      "loss": 0.3167,
+      "step": 163
+    },
+    {
+      "epoch": 2.414814814814815,
+      "grad_norm": 1.9534611701965332,
+      "learning_rate": 5.747508305647841e-06,
+      "loss": 0.3733,
+      "step": 164
+    },
+    {
+      "epoch": 2.4296296296296296,
+      "grad_norm": 1.6925545930862427,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.3631,
+      "step": 165
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.6101276874542236,
+      "learning_rate": 5.681063122923588e-06,
+      "loss": 0.3561,
+      "step": 166
+    },
+    {
+      "epoch": 2.4592592592592593,
+      "grad_norm": 1.5481266975402832,
+      "learning_rate": 5.647840531561463e-06,
+      "loss": 0.349,
+      "step": 167
+    },
+    {
+      "epoch": 2.474074074074074,
+      "grad_norm": 1.6006097793579102,
+      "learning_rate": 5.614617940199336e-06,
+      "loss": 0.3862,
+      "step": 168
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 1.4279389381408691,
+      "learning_rate": 5.58139534883721e-06,
+      "loss": 0.3236,
+      "step": 169
+    },
+    {
+      "epoch": 2.5037037037037035,
+      "grad_norm": 1.2405160665512085,
+      "learning_rate": 5.548172757475083e-06,
+      "loss": 0.3013,
+      "step": 170
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": 1.3768985271453857,
+      "learning_rate": 5.5149501661129565e-06,
+      "loss": 0.3626,
+      "step": 171
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.6408584117889404,
+      "learning_rate": 5.481727574750831e-06,
+      "loss": 0.3196,
+      "step": 172
+    },
+    {
+      "epoch": 2.5481481481481483,
+      "grad_norm": 1.6769694089889526,
+      "learning_rate": 5.448504983388705e-06,
+      "loss": 0.3694,
+      "step": 173
+    },
+    {
+      "epoch": 2.562962962962963,
+      "grad_norm": 1.3804996013641357,
+      "learning_rate": 5.415282392026578e-06,
+      "loss": 0.3502,
+      "step": 174
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 1.4021036624908447,
+      "learning_rate": 5.382059800664452e-06,
+      "loss": 0.3306,
+      "step": 175
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 1.2684727907180786,
+      "learning_rate": 5.348837209302326e-06,
+      "loss": 0.3106,
+      "step": 176
+    },
+    {
+      "epoch": 2.6074074074074076,
+      "grad_norm": 1.5925308465957642,
+      "learning_rate": 5.3156146179402e-06,
+      "loss": 0.4211,
+      "step": 177
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 1.5546250343322754,
+      "learning_rate": 5.282392026578074e-06,
+      "loss": 0.3301,
+      "step": 178
+    },
+    {
+      "epoch": 2.637037037037037,
+      "grad_norm": 1.4001022577285767,
+      "learning_rate": 5.2491694352159475e-06,
+      "loss": 0.3746,
+      "step": 179
+    },
+    {
+      "epoch": 2.651851851851852,
+      "grad_norm": 1.4525564908981323,
+      "learning_rate": 5.215946843853821e-06,
+      "loss": 0.2681,
+      "step": 180
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.27578604221344,
+      "learning_rate": 5.182724252491694e-06,
+      "loss": 0.3106,
+      "step": 181
+    },
+    {
+      "epoch": 2.6814814814814816,
+      "grad_norm": 1.4694350957870483,
+      "learning_rate": 5.149501661129569e-06,
+      "loss": 0.3065,
+      "step": 182
+    },
+    {
+      "epoch": 2.696296296296296,
+      "grad_norm": 1.3258838653564453,
+      "learning_rate": 5.116279069767442e-06,
+      "loss": 0.3233,
+      "step": 183
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 1.1991218328475952,
+      "learning_rate": 5.083056478405316e-06,
+      "loss": 0.2786,
+      "step": 184
+    },
+    {
+      "epoch": 2.725925925925926,
+      "grad_norm": 1.134046196937561,
+      "learning_rate": 5.0498338870431895e-06,
+      "loss": 0.2788,
+      "step": 185
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": 1.1837220191955566,
+      "learning_rate": 5.016611295681063e-06,
+      "loss": 0.2802,
+      "step": 186
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.5560253858566284,
+      "learning_rate": 4.983388704318937e-06,
+      "loss": 0.3686,
+      "step": 187
+    },
+    {
+      "epoch": 2.7703703703703706,
+      "grad_norm": 1.442020297050476,
+      "learning_rate": 4.950166112956811e-06,
+      "loss": 0.3648,
+      "step": 188
+    },
+    {
+      "epoch": 2.785185185185185,
+      "grad_norm": 1.2866986989974976,
+      "learning_rate": 4.916943521594685e-06,
+      "loss": 0.335,
+      "step": 189
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.9921827912330627,
+      "learning_rate": 4.883720930232559e-06,
+      "loss": 0.3052,
+      "step": 190
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 1.3171212673187256,
+      "learning_rate": 4.850498338870432e-06,
+      "loss": 0.3365,
+      "step": 191
+    },
+    {
+      "epoch": 2.8296296296296295,
+      "grad_norm": 1.202288031578064,
+      "learning_rate": 4.817275747508306e-06,
+      "loss": 0.2726,
+      "step": 192
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 1.5031251907348633,
+      "learning_rate": 4.78405315614618e-06,
+      "loss": 0.366,
+      "step": 193
+    },
+    {
+      "epoch": 2.859259259259259,
+      "grad_norm": 1.2141317129135132,
+      "learning_rate": 4.750830564784053e-06,
+      "loss": 0.2861,
+      "step": 194
+    },
+    {
+      "epoch": 2.8740740740740742,
+      "grad_norm": 1.64356529712677,
+      "learning_rate": 4.717607973421927e-06,
+      "loss": 0.3415,
+      "step": 195
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 1.2897413969039917,
+      "learning_rate": 4.6843853820598015e-06,
+      "loss": 0.3334,
+      "step": 196
+    },
+    {
+      "epoch": 2.9037037037037035,
+      "grad_norm": 1.192264199256897,
+      "learning_rate": 4.651162790697675e-06,
+      "loss": 0.2927,
+      "step": 197
+    },
+    {
+      "epoch": 2.9185185185185185,
+      "grad_norm": 1.36125648021698,
+      "learning_rate": 4.617940199335549e-06,
+      "loss": 0.3129,
+      "step": 198
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 1.3408805131912231,
+      "learning_rate": 4.5847176079734225e-06,
+      "loss": 0.3277,
+      "step": 199
+    },
+    {
+      "epoch": 2.948148148148148,
+      "grad_norm": 1.3519293069839478,
+      "learning_rate": 4.551495016611296e-06,
+      "loss": 0.2881,
+      "step": 200
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 1.2503290176391602,
+      "learning_rate": 4.51827242524917e-06,
+      "loss": 0.3282,
+      "step": 201
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 1.357706069946289,
+      "learning_rate": 4.4850498338870435e-06,
+      "loss": 0.3319,
+      "step": 202
+    },
+    {
+      "epoch": 2.9925925925925925,
+      "grad_norm": 1.173913598060608,
+      "learning_rate": 4.451827242524917e-06,
+      "loss": 0.3099,
+      "step": 203
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.173913598060608,
+      "learning_rate": 4.451827242524917e-06,
+      "loss": 0.2291,
+      "step": 204
+    },
+    {
+      "epoch": 3.0148148148148146,
+      "grad_norm": 1.3551340103149414,
+      "learning_rate": 4.418604651162791e-06,
+      "loss": 0.3068,
+      "step": 205
+    },
+    {
+      "epoch": 3.0296296296296297,
+      "grad_norm": 1.3206164836883545,
+      "learning_rate": 4.3853820598006645e-06,
+      "loss": 0.3416,
+      "step": 206
+    },
+    {
+      "epoch": 3.0444444444444443,
+      "grad_norm": 1.417013168334961,
+      "learning_rate": 4.352159468438539e-06,
+      "loss": 0.2771,
+      "step": 207
+    },
+    {
+      "epoch": 3.0592592592592593,
+      "grad_norm": 1.115646243095398,
+      "learning_rate": 4.318936877076413e-06,
+      "loss": 0.2828,
+      "step": 208
+    },
+    {
+      "epoch": 3.074074074074074,
+      "grad_norm": 1.4733177423477173,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.3038,
+      "step": 209
+    },
+    {
+      "epoch": 3.088888888888889,
+      "grad_norm": 1.3604916334152222,
+      "learning_rate": 4.25249169435216e-06,
+      "loss": 0.3128,
+      "step": 210
+    },
+    {
+      "epoch": 3.1037037037037036,
+      "grad_norm": 1.6025428771972656,
+      "learning_rate": 4.219269102990034e-06,
+      "loss": 0.2808,
+      "step": 211
+    },
+    {
+      "epoch": 3.1185185185185187,
+      "grad_norm": 1.5683448314666748,
+      "learning_rate": 4.186046511627907e-06,
+      "loss": 0.3538,
+      "step": 212
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 1.5745620727539062,
+      "learning_rate": 4.152823920265781e-06,
+      "loss": 0.3071,
+      "step": 213
+    },
+    {
+      "epoch": 3.148148148148148,
+      "grad_norm": 1.26665461063385,
+      "learning_rate": 4.119601328903655e-06,
+      "loss": 0.2568,
+      "step": 214
+    },
+    {
+      "epoch": 3.162962962962963,
+      "grad_norm": 1.1559772491455078,
+      "learning_rate": 4.086378737541528e-06,
+      "loss": 0.2655,
+      "step": 215
+    },
+    {
+      "epoch": 3.1777777777777776,
+      "grad_norm": 1.3667874336242676,
+      "learning_rate": 4.053156146179402e-06,
+      "loss": 0.2943,
+      "step": 216
+    },
+    {
+      "epoch": 3.1925925925925926,
+      "grad_norm": 1.4076658487319946,
+      "learning_rate": 4.0199335548172765e-06,
+      "loss": 0.242,
+      "step": 217
+    },
+    {
+      "epoch": 3.2074074074074073,
+      "grad_norm": 1.461408257484436,
+      "learning_rate": 3.98671096345515e-06,
+      "loss": 0.2792,
+      "step": 218
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "grad_norm": 1.3601031303405762,
+      "learning_rate": 3.953488372093024e-06,
+      "loss": 0.2788,
+      "step": 219
+    },
+    {
+      "epoch": 3.237037037037037,
+      "grad_norm": 1.9735394716262817,
+      "learning_rate": 3.9202657807308975e-06,
+      "loss": 0.3367,
+      "step": 220
+    },
+    {
+      "epoch": 3.251851851851852,
+      "grad_norm": 1.5413546562194824,
+      "learning_rate": 3.887043189368771e-06,
+      "loss": 0.2887,
+      "step": 221
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 1.5698870420455933,
+      "learning_rate": 3.853820598006645e-06,
+      "loss": 0.3121,
+      "step": 222
+    },
+    {
+      "epoch": 3.2814814814814817,
+      "grad_norm": 1.4351308345794678,
+      "learning_rate": 3.8205980066445185e-06,
+      "loss": 0.2859,
+      "step": 223
+    },
+    {
+      "epoch": 3.2962962962962963,
+      "grad_norm": 1.5523098707199097,
+      "learning_rate": 3.787375415282392e-06,
+      "loss": 0.3496,
+      "step": 224
+    },
+    {
+      "epoch": 3.311111111111111,
+      "grad_norm": 1.5026061534881592,
+      "learning_rate": 3.754152823920266e-06,
+      "loss": 0.2744,
+      "step": 225
+    },
+    {
+      "epoch": 3.325925925925926,
+      "grad_norm": 1.565753698348999,
+      "learning_rate": 3.72093023255814e-06,
+      "loss": 0.2761,
+      "step": 226
+    },
+    {
+      "epoch": 3.3407407407407406,
+      "grad_norm": 1.514609456062317,
+      "learning_rate": 3.6877076411960135e-06,
+      "loss": 0.2385,
+      "step": 227
+    },
+    {
+      "epoch": 3.3555555555555556,
+      "grad_norm": 1.233588695526123,
+      "learning_rate": 3.6544850498338876e-06,
+      "loss": 0.2849,
+      "step": 228
+    },
+    {
+      "epoch": 3.3703703703703702,
+      "grad_norm": 1.3447370529174805,
+      "learning_rate": 3.621262458471761e-06,
+      "loss": 0.3197,
+      "step": 229
+    },
+    {
+      "epoch": 3.3851851851851853,
+      "grad_norm": 1.3895092010498047,
+      "learning_rate": 3.588039867109635e-06,
+      "loss": 0.2869,
+      "step": 230
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 1.326200246810913,
+      "learning_rate": 3.5548172757475086e-06,
+      "loss": 0.2937,
+      "step": 231
+    },
+    {
+      "epoch": 3.414814814814815,
+      "grad_norm": 1.2751388549804688,
+      "learning_rate": 3.5215946843853823e-06,
+      "loss": 0.2611,
+      "step": 232
+    },
+    {
+      "epoch": 3.4296296296296296,
+      "grad_norm": 1.1317442655563354,
+      "learning_rate": 3.4883720930232564e-06,
+      "loss": 0.2733,
+      "step": 233
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 1.3669071197509766,
+      "learning_rate": 3.4551495016611296e-06,
+      "loss": 0.2967,
+      "step": 234
+    },
+    {
+      "epoch": 3.4592592592592593,
+      "grad_norm": 1.451213002204895,
+      "learning_rate": 3.4219269102990037e-06,
+      "loss": 0.3398,
+      "step": 235
+    },
+    {
+      "epoch": 3.474074074074074,
+      "grad_norm": 2.680572748184204,
+      "learning_rate": 3.3887043189368774e-06,
+      "loss": 0.2973,
+      "step": 236
+    },
+    {
+      "epoch": 3.488888888888889,
+      "grad_norm": 1.5603687763214111,
+      "learning_rate": 3.355481727574751e-06,
+      "loss": 0.2669,
+      "step": 237
+    },
+    {
+      "epoch": 3.5037037037037035,
+      "grad_norm": 1.8472412824630737,
+      "learning_rate": 3.322259136212625e-06,
+      "loss": 0.2956,
+      "step": 238
+    },
+    {
+      "epoch": 3.5185185185185186,
+      "grad_norm": 1.6677846908569336,
+      "learning_rate": 3.2890365448504984e-06,
+      "loss": 0.329,
+      "step": 239
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 1.8696357011795044,
+      "learning_rate": 3.2558139534883724e-06,
+      "loss": 0.2735,
+      "step": 240
+    },
+    {
+      "epoch": 3.5481481481481483,
+      "grad_norm": 1.2237964868545532,
+      "learning_rate": 3.222591362126246e-06,
+      "loss": 0.3011,
+      "step": 241
+    },
+    {
+      "epoch": 3.562962962962963,
+      "grad_norm": 1.2561728954315186,
+      "learning_rate": 3.1893687707641198e-06,
+      "loss": 0.2568,
+      "step": 242
+    },
+    {
+      "epoch": 3.5777777777777775,
+      "grad_norm": 1.1599830389022827,
+      "learning_rate": 3.156146179401994e-06,
+      "loss": 0.3025,
+      "step": 243
+    },
+    {
+      "epoch": 3.5925925925925926,
+      "grad_norm": 1.7549623250961304,
+      "learning_rate": 3.122923588039867e-06,
+      "loss": 0.3252,
+      "step": 244
+    },
+    {
+      "epoch": 3.6074074074074076,
+      "grad_norm": 1.5652899742126465,
+      "learning_rate": 3.089700996677741e-06,
+      "loss": 0.341,
+      "step": 245
+    },
+    {
+      "epoch": 3.6222222222222222,
+      "grad_norm": 1.7946059703826904,
+      "learning_rate": 3.056478405315615e-06,
+      "loss": 0.3244,
+      "step": 246
+    },
+    {
+      "epoch": 3.637037037037037,
+      "grad_norm": 1.5564749240875244,
+      "learning_rate": 3.0232558139534885e-06,
+      "loss": 0.2686,
+      "step": 247
+    },
+    {
+      "epoch": 3.651851851851852,
+      "grad_norm": 1.439971923828125,
+      "learning_rate": 2.9900332225913626e-06,
+      "loss": 0.3198,
+      "step": 248
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 1.590828537940979,
+      "learning_rate": 2.9568106312292363e-06,
+      "loss": 0.2874,
+      "step": 249
+    },
+    {
+      "epoch": 3.6814814814814816,
+      "grad_norm": 1.2883110046386719,
+      "learning_rate": 2.9235880398671104e-06,
+      "loss": 0.2475,
+      "step": 250
+    },
+    {
+      "epoch": 3.696296296296296,
+      "grad_norm": 1.2013444900512695,
+      "learning_rate": 2.8903654485049836e-06,
+      "loss": 0.2911,
+      "step": 251
+    },
+    {
+      "epoch": 3.7111111111111112,
+      "grad_norm": 1.5711296796798706,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.3113,
+      "step": 252
+    },
+    {
+      "epoch": 3.725925925925926,
+      "grad_norm": 1.5199639797210693,
+      "learning_rate": 2.8239202657807313e-06,
+      "loss": 0.2462,
+      "step": 253
+    },
+    {
+      "epoch": 3.7407407407407405,
+      "grad_norm": 1.2884533405303955,
+      "learning_rate": 2.790697674418605e-06,
+      "loss": 0.245,
+      "step": 254
+    },
+    {
+      "epoch": 3.7555555555555555,
+      "grad_norm": 1.4477325677871704,
+      "learning_rate": 2.7574750830564782e-06,
+      "loss": 0.2409,
+      "step": 255
+    },
+    {
+      "epoch": 3.7703703703703706,
+      "grad_norm": 1.2022032737731934,
+      "learning_rate": 2.7242524916943523e-06,
+      "loss": 0.2806,
+      "step": 256
+    },
+    {
+      "epoch": 3.785185185185185,
+      "grad_norm": 1.467168927192688,
+      "learning_rate": 2.691029900332226e-06,
+      "loss": 0.2866,
+      "step": 257
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 2.0435290336608887,
+      "learning_rate": 2.6578073089701e-06,
+      "loss": 0.3211,
+      "step": 258
+    },
+    {
+      "epoch": 3.814814814814815,
+      "grad_norm": 1.2129874229431152,
+      "learning_rate": 2.6245847176079738e-06,
+      "loss": 0.2765,
+      "step": 259
+    },
+    {
+      "epoch": 3.8296296296296295,
+      "grad_norm": 1.4887040853500366,
+      "learning_rate": 2.591362126245847e-06,
+      "loss": 0.282,
+      "step": 260
+    },
+    {
+      "epoch": 3.8444444444444446,
+      "grad_norm": 1.3326512575149536,
+      "learning_rate": 2.558139534883721e-06,
+      "loss": 0.307,
+      "step": 261
+    },
+    {
+      "epoch": 3.859259259259259,
+      "grad_norm": 1.2139685153961182,
+      "learning_rate": 2.5249169435215947e-06,
+      "loss": 0.3053,
+      "step": 262
+    },
+    {
+      "epoch": 3.8740740740740742,
+      "grad_norm": 1.6648317575454712,
+      "learning_rate": 2.4916943521594684e-06,
+      "loss": 0.2859,
+      "step": 263
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 1.550366997718811,
+      "learning_rate": 2.4584717607973425e-06,
+      "loss": 0.3527,
+      "step": 264
+    },
+    {
+      "epoch": 3.9037037037037035,
+      "grad_norm": 1.641121506690979,
+      "learning_rate": 2.425249169435216e-06,
+      "loss": 0.2735,
+      "step": 265
+    },
+    {
+      "epoch": 3.9185185185185185,
+      "grad_norm": 1.244675874710083,
+      "learning_rate": 2.39202657807309e-06,
+      "loss": 0.3208,
+      "step": 266
+    },
+    {
+      "epoch": 3.9333333333333336,
+      "grad_norm": 1.4783977270126343,
+      "learning_rate": 2.3588039867109635e-06,
+      "loss": 0.2869,
+      "step": 267
+    },
+    {
+      "epoch": 3.948148148148148,
+      "grad_norm": 1.5731481313705444,
+      "learning_rate": 2.3255813953488376e-06,
+      "loss": 0.4189,
+      "step": 268
+    },
+    {
+      "epoch": 3.962962962962963,
+      "grad_norm": 1.654645562171936,
+      "learning_rate": 2.2923588039867112e-06,
+      "loss": 0.2766,
+      "step": 269
+    },
+    {
+      "epoch": 3.977777777777778,
+      "grad_norm": 1.6379601955413818,
+      "learning_rate": 2.259136212624585e-06,
+      "loss": 0.3227,
+      "step": 270
+    },
+    {
+      "epoch": 3.9925925925925925,
+      "grad_norm": 1.3923341035842896,
+      "learning_rate": 2.2259136212624586e-06,
+      "loss": 0.3051,
+      "step": 271
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.9158486127853394,
+      "learning_rate": 2.1926910299003322e-06,
+      "loss": 0.2157,
+      "step": 272
+    },
+    {
+      "epoch": 4.014814814814815,
+      "grad_norm": 1.2792537212371826,
+      "learning_rate": 2.1594684385382063e-06,
+      "loss": 0.2568,
+      "step": 273
+    },
+    {
+      "epoch": 4.029629629629629,
+      "grad_norm": 1.1235581636428833,
+      "learning_rate": 2.12624584717608e-06,
+      "loss": 0.2664,
+      "step": 274
+    },
+    {
+      "epoch": 4.044444444444444,
+      "grad_norm": 1.2936333417892456,
+      "learning_rate": 2.0930232558139536e-06,
+      "loss": 0.2966,
+      "step": 275
+    },
+    {
+      "epoch": 4.059259259259259,
+      "grad_norm": 1.2000664472579956,
+      "learning_rate": 2.0598006644518273e-06,
+      "loss": 0.2487,
+      "step": 276
+    },
+    {
+      "epoch": 4.074074074074074,
+      "grad_norm": 1.4936013221740723,
+      "learning_rate": 2.026578073089701e-06,
+      "loss": 0.283,
+      "step": 277
+    },
+    {
+      "epoch": 4.088888888888889,
+      "grad_norm": 1.551798939704895,
+      "learning_rate": 1.993355481727575e-06,
+      "loss": 0.275,
+      "step": 278
+    },
+    {
+      "epoch": 4.103703703703704,
+      "grad_norm": 1.8705427646636963,
+      "learning_rate": 1.9601328903654487e-06,
+      "loss": 0.3045,
+      "step": 279
+    },
+    {
+      "epoch": 4.118518518518519,
+      "grad_norm": 1.5146915912628174,
+      "learning_rate": 1.9269102990033224e-06,
+      "loss": 0.2575,
+      "step": 280
+    },
+    {
+      "epoch": 4.133333333333334,
+      "grad_norm": 2.1336557865142822,
+      "learning_rate": 1.893687707641196e-06,
+      "loss": 0.293,
+      "step": 281
+    },
+    {
+      "epoch": 4.148148148148148,
+      "grad_norm": 1.673853874206543,
+      "learning_rate": 1.86046511627907e-06,
+      "loss": 0.2228,
+      "step": 282
+    },
+    {
+      "epoch": 4.162962962962963,
+      "grad_norm": 1.4035648107528687,
+      "learning_rate": 1.8272425249169438e-06,
+      "loss": 0.236,
+      "step": 283
+    },
+    {
+      "epoch": 4.177777777777778,
+      "grad_norm": 1.5520694255828857,
+      "learning_rate": 1.7940199335548175e-06,
+      "loss": 0.2381,
+      "step": 284
+    },
+    {
+      "epoch": 4.192592592592592,
+      "grad_norm": 1.8831232786178589,
+      "learning_rate": 1.7607973421926911e-06,
+      "loss": 0.3056,
+      "step": 285
+    },
+    {
+      "epoch": 4.207407407407407,
+      "grad_norm": 1.524223804473877,
+      "learning_rate": 1.7275747508305648e-06,
+      "loss": 0.2288,
+      "step": 286
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 1.7227911949157715,
+      "learning_rate": 1.6943521594684387e-06,
+      "loss": 0.3001,
+      "step": 287
+    },
+    {
+      "epoch": 4.237037037037037,
+      "grad_norm": 1.6464650630950928,
+      "learning_rate": 1.6611295681063126e-06,
+      "loss": 0.2767,
+      "step": 288
+    },
+    {
+      "epoch": 4.2518518518518515,
+      "grad_norm": 1.462727665901184,
+      "learning_rate": 1.6279069767441862e-06,
+      "loss": 0.2583,
+      "step": 289
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 1.3373020887374878,
+      "learning_rate": 1.5946843853820599e-06,
+      "loss": 0.1861,
+      "step": 290
+    },
+    {
+      "epoch": 4.281481481481482,
+      "grad_norm": 1.3069071769714355,
+      "learning_rate": 1.5614617940199335e-06,
+      "loss": 0.2279,
+      "step": 291
+    },
+    {
+      "epoch": 4.296296296296296,
+      "grad_norm": 2.0804059505462646,
+      "learning_rate": 1.5282392026578074e-06,
+      "loss": 0.3373,
+      "step": 292
+    },
+    {
+      "epoch": 4.311111111111111,
+      "grad_norm": 1.5276566743850708,
+      "learning_rate": 1.4950166112956813e-06,
+      "loss": 0.2211,
+      "step": 293
+    },
+    {
+      "epoch": 4.325925925925926,
+      "grad_norm": 1.7238777875900269,
+      "learning_rate": 1.4617940199335552e-06,
+      "loss": 0.2492,
+      "step": 294
+    },
+    {
+      "epoch": 4.340740740740741,
+      "grad_norm": 1.7892625331878662,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.2521,
+      "step": 295
+    },
+    {
+      "epoch": 4.355555555555555,
+      "grad_norm": 1.83062744140625,
+      "learning_rate": 1.3953488372093025e-06,
+      "loss": 0.2445,
+      "step": 296
+    },
+    {
+      "epoch": 4.37037037037037,
+      "grad_norm": 1.665940284729004,
+      "learning_rate": 1.3621262458471762e-06,
+      "loss": 0.2188,
+      "step": 297
+    },
+    {
+      "epoch": 4.385185185185185,
+      "grad_norm": 1.7071560621261597,
+      "learning_rate": 1.32890365448505e-06,
+      "loss": 0.2294,
+      "step": 298
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 1.5902904272079468,
+      "learning_rate": 1.2956810631229235e-06,
+      "loss": 0.2443,
+      "step": 299
+    },
+    {
+      "epoch": 4.4148148148148145,
+      "grad_norm": 1.6071012020111084,
+      "learning_rate": 1.2624584717607974e-06,
+      "loss": 0.2268,
+      "step": 300
+    },
+    {
+      "epoch": 4.42962962962963,
+      "grad_norm": 1.481217384338379,
+      "learning_rate": 1.2292358803986712e-06,
+      "loss": 0.2245,
+      "step": 301
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 1.7338011264801025,
+      "learning_rate": 1.196013289036545e-06,
+      "loss": 0.2481,
+      "step": 302
+    },
+    {
+      "epoch": 4.459259259259259,
+      "grad_norm": 1.83079195022583,
+      "learning_rate": 1.1627906976744188e-06,
+      "loss": 0.2771,
+      "step": 303
+    },
+    {
+      "epoch": 4.474074074074074,
+      "grad_norm": 1.6256608963012695,
+      "learning_rate": 1.1295681063122925e-06,
+      "loss": 0.2418,
+      "step": 304
+    },
+    {
+      "epoch": 4.488888888888889,
+      "grad_norm": 1.7368595600128174,
+      "learning_rate": 1.0963455149501661e-06,
+      "loss": 0.2325,
+      "step": 305
+    },
+    {
+      "epoch": 4.503703703703704,
+      "grad_norm": 1.8986256122589111,
+      "learning_rate": 1.06312292358804e-06,
+      "loss": 0.2685,
+      "step": 306
+    },
+    {
+      "epoch": 4.518518518518518,
+      "grad_norm": 1.9530152082443237,
+      "learning_rate": 1.0299003322259137e-06,
+      "loss": 0.2734,
+      "step": 307
+    },
+    {
+      "epoch": 4.533333333333333,
+      "grad_norm": 2.2950448989868164,
+      "learning_rate": 9.966777408637875e-07,
+      "loss": 0.2775,
+      "step": 308
+    },
+    {
+      "epoch": 4.548148148148148,
+      "grad_norm": 1.7885551452636719,
+      "learning_rate": 9.634551495016612e-07,
+      "loss": 0.2299,
+      "step": 309
+    },
+    {
+      "epoch": 4.562962962962963,
+      "grad_norm": 1.8106021881103516,
+      "learning_rate": 9.30232558139535e-07,
+      "loss": 0.2665,
+      "step": 310
+    },
+    {
+      "epoch": 4.5777777777777775,
+      "grad_norm": 1.7523531913757324,
+      "learning_rate": 8.970099667774087e-07,
+      "loss": 0.2514,
+      "step": 311
+    },
+    {
+      "epoch": 4.592592592592593,
+      "grad_norm": 1.5606251955032349,
+      "learning_rate": 8.637873754152824e-07,
+      "loss": 0.216,
+      "step": 312
+    },
+    {
+      "epoch": 4.607407407407408,
+      "grad_norm": 1.3957760334014893,
+      "learning_rate": 8.305647840531563e-07,
+      "loss": 0.2133,
+      "step": 313
+    },
+    {
+      "epoch": 4.622222222222222,
+      "grad_norm": 1.4215636253356934,
+      "learning_rate": 7.973421926910299e-07,
+      "loss": 0.2159,
+      "step": 314
+    },
+    {
+      "epoch": 4.637037037037037,
+      "grad_norm": 1.9139257669448853,
+      "learning_rate": 7.641196013289037e-07,
+      "loss": 0.2799,
+      "step": 315
+    },
+    {
+      "epoch": 4.651851851851852,
+      "grad_norm": 1.5956664085388184,
+      "learning_rate": 7.308970099667776e-07,
+      "loss": 0.2386,
+      "step": 316
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 1.7055957317352295,
+      "learning_rate": 6.976744186046513e-07,
+      "loss": 0.2256,
+      "step": 317
+    },
+    {
+      "epoch": 4.681481481481481,
+      "grad_norm": 2.2495598793029785,
+      "learning_rate": 6.64451827242525e-07,
+      "loss": 0.2795,
+      "step": 318
+    },
+    {
+      "epoch": 4.696296296296296,
+      "grad_norm": 1.4281206130981445,
+      "learning_rate": 6.312292358803987e-07,
+      "loss": 0.2295,
+      "step": 319
+    },
+    {
+      "epoch": 4.711111111111111,
+      "grad_norm": 1.7233028411865234,
+      "learning_rate": 5.980066445182725e-07,
+      "loss": 0.2586,
+      "step": 320
+    },
+    {
+      "epoch": 4.725925925925926,
+      "grad_norm": 2.274329662322998,
+      "learning_rate": 5.647840531561462e-07,
+      "loss": 0.2477,
+      "step": 321
+    },
+    {
+      "epoch": 4.7407407407407405,
+      "grad_norm": 1.6101205348968506,
+      "learning_rate": 5.3156146179402e-07,
+      "loss": 0.2304,
+      "step": 322
+    },
+    {
+      "epoch": 4.7555555555555555,
+      "grad_norm": 1.9844639301300049,
+      "learning_rate": 4.983388704318938e-07,
+      "loss": 0.2888,
+      "step": 323
+    },
+    {
+      "epoch": 4.770370370370371,
+      "grad_norm": 1.7177938222885132,
+      "learning_rate": 4.651162790697675e-07,
+      "loss": 0.2543,
+      "step": 324
+    },
+    {
+      "epoch": 4.785185185185185,
+      "grad_norm": 1.7451181411743164,
+      "learning_rate": 4.318936877076412e-07,
+      "loss": 0.2362,
+      "step": 325
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.9255115985870361,
+      "learning_rate": 3.9867109634551497e-07,
+      "loss": 0.2689,
+      "step": 326
+    },
+    {
+      "epoch": 4.814814814814815,
+      "grad_norm": 1.6680419445037842,
+      "learning_rate": 3.654485049833888e-07,
+      "loss": 0.2505,
+      "step": 327
+    },
+    {
+      "epoch": 4.82962962962963,
+      "grad_norm": 1.8660964965820312,
+      "learning_rate": 3.322259136212625e-07,
+      "loss": 0.2671,
+      "step": 328
+    },
+    {
+      "epoch": 4.844444444444444,
+      "grad_norm": 1.9916861057281494,
+      "learning_rate": 2.9900332225913623e-07,
+      "loss": 0.2519,
+      "step": 329
+    },
+    {
+      "epoch": 4.859259259259259,
+      "grad_norm": 1.5888378620147705,
+      "learning_rate": 2.6578073089701e-07,
+      "loss": 0.2505,
+      "step": 330
+    },
+    {
+      "epoch": 4.874074074074074,
+      "grad_norm": 1.654725193977356,
+      "learning_rate": 2.3255813953488374e-07,
+      "loss": 0.2466,
+      "step": 331
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 1.4593290090560913,
+      "learning_rate": 1.9933554817275749e-07,
+      "loss": 0.2039,
+      "step": 332
+    },
+    {
+      "epoch": 4.9037037037037035,
+      "grad_norm": 1.5956478118896484,
+      "learning_rate": 1.6611295681063126e-07,
+      "loss": 0.2221,
+      "step": 333
+    },
+    {
+      "epoch": 4.9185185185185185,
+      "grad_norm": 1.33909273147583,
+      "learning_rate": 1.32890365448505e-07,
+      "loss": 0.192,
+      "step": 334
+    },
+    {
+      "epoch": 4.933333333333334,
+      "grad_norm": 1.7868711948394775,
+      "learning_rate": 9.966777408637874e-08,
+      "loss": 0.2477,
+      "step": 335
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 335,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4351170969600.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed647c6ed52eb58ea98587cf28c7cbbfe4b6d197bfd728fefc429cf608e19e4
+size 7416

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/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 gc
+import json
+import numpy as np
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+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,
+                                                          lazy_mode=True)
+
+    # 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")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_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 by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # 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)