Upload folder using huggingface_hub

.gitattributes

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

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128019,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "transformers_version": "4.49.0"
+}

latest

@@ -0,0 +1 @@
+global_step305

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf450cab18aacb185f1a38955a0936f611a3d387249ce759334c45e8a9c9202d
+size 4978354640

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c551bc15699de4ca3f8e5a6cdbedad60c92488ec29349a02a1d5e97fb2d149
+size 4047172128

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 9025492992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

rng_state_0.pth

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

rng_state_1.pth

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

rng_state_2.pth

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

rng_state_3.pth

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

rng_state_4.pth

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

rng_state_5.pth

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

rng_state_6.pth

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

rng_state_7.pth

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

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76cf2bda24bdde1c28fd3235f1a8ff818d2405a5f3079da7bb6044591b3c379
+size 1064

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
+size 17209884

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,2168 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9983633387888707,
+  "eval_steps": 500,
+  "global_step": 305,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0032733224222585926,
+      "grad_norm": 4.5458229969104,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 2.5273,
+      "step": 1
+    },
+    {
+      "epoch": 0.006546644844517185,
+      "grad_norm": 4.12339411074909,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 2.5212,
+      "step": 2
+    },
+    {
+      "epoch": 0.009819967266775777,
+      "grad_norm": 7.698312038734646,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.553,
+      "step": 3
+    },
+    {
+      "epoch": 0.01309328968903437,
+      "grad_norm": 3.2743265686425325,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 2.5286,
+      "step": 4
+    },
+    {
+      "epoch": 0.016366612111292964,
+      "grad_norm": 4.882632956145234,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 2.5099,
+      "step": 5
+    },
+    {
+      "epoch": 0.019639934533551555,
+      "grad_norm": 1.5422971469796205,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.5156,
+      "step": 6
+    },
+    {
+      "epoch": 0.022913256955810146,
+      "grad_norm": 4.3292940294795,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 2.5432,
+      "step": 7
+    },
+    {
+      "epoch": 0.02618657937806874,
+      "grad_norm": 1.3106542988714809,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 2.5001,
+      "step": 8
+    },
+    {
+      "epoch": 0.029459901800327332,
+      "grad_norm": 1.915309733377902,
+      "learning_rate": 3e-06,
+      "loss": 2.5289,
+      "step": 9
+    },
+    {
+      "epoch": 0.03273322422258593,
+      "grad_norm": 1.4811295343620543,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.5249,
+      "step": 10
+    },
+    {
+      "epoch": 0.03600654664484452,
+      "grad_norm": 0.9585352491709347,
+      "learning_rate": 3.6666666666666666e-06,
+      "loss": 2.5195,
+      "step": 11
+    },
+    {
+      "epoch": 0.03927986906710311,
+      "grad_norm": 0.6542974173213092,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.5096,
+      "step": 12
+    },
+    {
+      "epoch": 0.0425531914893617,
+      "grad_norm": 0.6159788634871752,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": 2.509,
+      "step": 13
+    },
+    {
+      "epoch": 0.04582651391162029,
+      "grad_norm": 0.6302127259561674,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 2.5159,
+      "step": 14
+    },
+    {
+      "epoch": 0.049099836333878884,
+      "grad_norm": 0.5116118125911384,
+      "learning_rate": 5e-06,
+      "loss": 2.4919,
+      "step": 15
+    },
+    {
+      "epoch": 0.05237315875613748,
+      "grad_norm": 0.42670850345300865,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 2.5056,
+      "step": 16
+    },
+    {
+      "epoch": 0.05564648117839607,
+      "grad_norm": 0.3955257011722223,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 2.493,
+      "step": 17
+    },
+    {
+      "epoch": 0.058919803600654665,
+      "grad_norm": 0.3954725948519232,
+      "learning_rate": 6e-06,
+      "loss": 2.4947,
+      "step": 18
+    },
+    {
+      "epoch": 0.062193126022913256,
+      "grad_norm": 0.37175019309525287,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 2.5092,
+      "step": 19
+    },
+    {
+      "epoch": 0.06546644844517185,
+      "grad_norm": 0.39057048150465146,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.4981,
+      "step": 20
+    },
+    {
+      "epoch": 0.06873977086743044,
+      "grad_norm": 0.39262665115560863,
+      "learning_rate": 7e-06,
+      "loss": 2.4854,
+      "step": 21
+    },
+    {
+      "epoch": 0.07201309328968904,
+      "grad_norm": 0.3951637407824461,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 2.5021,
+      "step": 22
+    },
+    {
+      "epoch": 0.07528641571194762,
+      "grad_norm": 0.40140742815376235,
+      "learning_rate": 7.666666666666667e-06,
+      "loss": 2.517,
+      "step": 23
+    },
+    {
+      "epoch": 0.07855973813420622,
+      "grad_norm": 0.36348786250077453,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.492,
+      "step": 24
+    },
+    {
+      "epoch": 0.08183306055646482,
+      "grad_norm": 0.3927422984780222,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.4891,
+      "step": 25
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 0.3802256129939313,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 2.5241,
+      "step": 26
+    },
+    {
+      "epoch": 0.088379705400982,
+      "grad_norm": 0.4048560033284272,
+      "learning_rate": 9e-06,
+      "loss": 2.4996,
+      "step": 27
+    },
+    {
+      "epoch": 0.09165302782324058,
+      "grad_norm": 0.3938035425880514,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 2.51,
+      "step": 28
+    },
+    {
+      "epoch": 0.09492635024549918,
+      "grad_norm": 0.4318232114640702,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 2.5345,
+      "step": 29
+    },
+    {
+      "epoch": 0.09819967266775777,
+      "grad_norm": 0.3960154579660599,
+      "learning_rate": 1e-05,
+      "loss": 2.511,
+      "step": 30
+    },
+    {
+      "epoch": 0.10147299509001637,
+      "grad_norm": 0.4569501622130681,
+      "learning_rate": 9.999673735634259e-06,
+      "loss": 2.4827,
+      "step": 31
+    },
+    {
+      "epoch": 0.10474631751227496,
+      "grad_norm": 0.3958075272764396,
+      "learning_rate": 9.998694985116406e-06,
+      "loss": 2.4884,
+      "step": 32
+    },
+    {
+      "epoch": 0.10801963993453355,
+      "grad_norm": 0.37500089768123596,
+      "learning_rate": 9.997063876179007e-06,
+      "loss": 2.5027,
+      "step": 33
+    },
+    {
+      "epoch": 0.11129296235679215,
+      "grad_norm": 0.3815772878145323,
+      "learning_rate": 9.994780621691156e-06,
+      "loss": 2.4957,
+      "step": 34
+    },
+    {
+      "epoch": 0.11456628477905073,
+      "grad_norm": 0.38634081421059385,
+      "learning_rate": 9.991845519630679e-06,
+      "loss": 2.4937,
+      "step": 35
+    },
+    {
+      "epoch": 0.11783960720130933,
+      "grad_norm": 0.3671354090721152,
+      "learning_rate": 9.988258953045264e-06,
+      "loss": 2.4789,
+      "step": 36
+    },
+    {
+      "epoch": 0.12111292962356793,
+      "grad_norm": 0.36190374114193224,
+      "learning_rate": 9.984021390002458e-06,
+      "loss": 2.499,
+      "step": 37
+    },
+    {
+      "epoch": 0.12438625204582651,
+      "grad_norm": 0.38466932485680505,
+      "learning_rate": 9.979133383528591e-06,
+      "loss": 2.5026,
+      "step": 38
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 0.3573078258794223,
+      "learning_rate": 9.973595571536593e-06,
+      "loss": 2.4787,
+      "step": 39
+    },
+    {
+      "epoch": 0.1309328968903437,
+      "grad_norm": 0.39354137647528986,
+      "learning_rate": 9.96740867674275e-06,
+      "loss": 2.5228,
+      "step": 40
+    },
+    {
+      "epoch": 0.1342062193126023,
+      "grad_norm": 0.3834121962923347,
+      "learning_rate": 9.960573506572391e-06,
+      "loss": 2.5147,
+      "step": 41
+    },
+    {
+      "epoch": 0.13747954173486088,
+      "grad_norm": 0.383218733958223,
+      "learning_rate": 9.953090953054491e-06,
+      "loss": 2.4847,
+      "step": 42
+    },
+    {
+      "epoch": 0.1407528641571195,
+      "grad_norm": 0.3964524303138896,
+      "learning_rate": 9.944961992705288e-06,
+      "loss": 2.4953,
+      "step": 43
+    },
+    {
+      "epoch": 0.14402618657937807,
+      "grad_norm": 0.3907082692537958,
+      "learning_rate": 9.936187686400814e-06,
+      "loss": 2.5074,
+      "step": 44
+    },
+    {
+      "epoch": 0.14729950900163666,
+      "grad_norm": 0.42441529396911143,
+      "learning_rate": 9.926769179238467e-06,
+      "loss": 2.4694,
+      "step": 45
+    },
+    {
+      "epoch": 0.15057283142389524,
+      "grad_norm": 0.36309886081053155,
+      "learning_rate": 9.916707700387546e-06,
+      "loss": 2.4816,
+      "step": 46
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.3745053331706986,
+      "learning_rate": 9.906004562928865e-06,
+      "loss": 2.4876,
+      "step": 47
+    },
+    {
+      "epoch": 0.15711947626841244,
+      "grad_norm": 0.3558032864873746,
+      "learning_rate": 9.894661163683361e-06,
+      "loss": 2.4887,
+      "step": 48
+    },
+    {
+      "epoch": 0.16039279869067102,
+      "grad_norm": 0.3560175097976504,
+      "learning_rate": 9.882678983029819e-06,
+      "loss": 2.4817,
+      "step": 49
+    },
+    {
+      "epoch": 0.16366612111292964,
+      "grad_norm": 0.36618662107001704,
+      "learning_rate": 9.870059584711668e-06,
+      "loss": 2.4665,
+      "step": 50
+    },
+    {
+      "epoch": 0.16693944353518822,
+      "grad_norm": 0.3601957684934551,
+      "learning_rate": 9.856804615632904e-06,
+      "loss": 2.4854,
+      "step": 51
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.3704954734907262,
+      "learning_rate": 9.842915805643156e-06,
+      "loss": 2.5347,
+      "step": 52
+    },
+    {
+      "epoch": 0.1734860883797054,
+      "grad_norm": 0.36959475458440244,
+      "learning_rate": 9.82839496731194e-06,
+      "loss": 2.4887,
+      "step": 53
+    },
+    {
+      "epoch": 0.176759410801964,
+      "grad_norm": 0.384552486477283,
+      "learning_rate": 9.813243995692097e-06,
+      "loss": 2.4753,
+      "step": 54
+    },
+    {
+      "epoch": 0.18003273322422259,
+      "grad_norm": 0.36249860452124605,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 2.469,
+      "step": 55
+    },
+    {
+      "epoch": 0.18330605564648117,
+      "grad_norm": 0.3648846542235022,
+      "learning_rate": 9.781059643719937e-06,
+      "loss": 2.4984,
+      "step": 56
+    },
+    {
+      "epoch": 0.18657937806873978,
+      "grad_norm": 0.37334256629644896,
+      "learning_rate": 9.76403046361049e-06,
+      "loss": 2.456,
+      "step": 57
+    },
+    {
+      "epoch": 0.18985270049099837,
+      "grad_norm": 0.36980026599186505,
+      "learning_rate": 9.74637955015001e-06,
+      "loss": 2.485,
+      "step": 58
+    },
+    {
+      "epoch": 0.19312602291325695,
+      "grad_norm": 0.40834498386413537,
+      "learning_rate": 9.728109206884125e-06,
+      "loss": 2.5011,
+      "step": 59
+    },
+    {
+      "epoch": 0.19639934533551553,
+      "grad_norm": 0.35772757844310776,
+      "learning_rate": 9.709221818197626e-06,
+      "loss": 2.4915,
+      "step": 60
+    },
+    {
+      "epoch": 0.19967266775777415,
+      "grad_norm": 0.5331894263162329,
+      "learning_rate": 9.689719849003261e-06,
+      "loss": 2.4779,
+      "step": 61
+    },
+    {
+      "epoch": 0.20294599018003273,
+      "grad_norm": 0.5108742054472333,
+      "learning_rate": 9.66960584442008e-06,
+      "loss": 2.5002,
+      "step": 62
+    },
+    {
+      "epoch": 0.20621931260229132,
+      "grad_norm": 0.36603499456334015,
+      "learning_rate": 9.648882429441258e-06,
+      "loss": 2.4605,
+      "step": 63
+    },
+    {
+      "epoch": 0.20949263502454993,
+      "grad_norm": 0.3858608557671342,
+      "learning_rate": 9.627552308591534e-06,
+      "loss": 2.484,
+      "step": 64
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 0.39024218298879865,
+      "learning_rate": 9.60561826557425e-06,
+      "loss": 2.5057,
+      "step": 65
+    },
+    {
+      "epoch": 0.2160392798690671,
+      "grad_norm": 0.38798042222376583,
+      "learning_rate": 9.58308316290806e-06,
+      "loss": 2.4573,
+      "step": 66
+    },
+    {
+      "epoch": 0.2193126022913257,
+      "grad_norm": 0.4495343758022552,
+      "learning_rate": 9.559949941553351e-06,
+      "loss": 2.4751,
+      "step": 67
+    },
+    {
+      "epoch": 0.2225859247135843,
+      "grad_norm": 0.5550558249858909,
+      "learning_rate": 9.536221620528442e-06,
+      "loss": 2.4706,
+      "step": 68
+    },
+    {
+      "epoch": 0.22585924713584288,
+      "grad_norm": 0.7753792348358921,
+      "learning_rate": 9.511901296515578e-06,
+      "loss": 2.4536,
+      "step": 69
+    },
+    {
+      "epoch": 0.22913256955810146,
+      "grad_norm": 0.4620597211236889,
+      "learning_rate": 9.486992143456792e-06,
+      "loss": 2.4966,
+      "step": 70
+    },
+    {
+      "epoch": 0.23240589198036007,
+      "grad_norm": 2.0294893276083674,
+      "learning_rate": 9.461497412139697e-06,
+      "loss": 2.4896,
+      "step": 71
+    },
+    {
+      "epoch": 0.23567921440261866,
+      "grad_norm": 3.9731994256120258,
+      "learning_rate": 9.435420429773227e-06,
+      "loss": 2.4775,
+      "step": 72
+    },
+    {
+      "epoch": 0.23895253682487724,
+      "grad_norm": 3.716661029391411,
+      "learning_rate": 9.408764599553429e-06,
+      "loss": 2.4774,
+      "step": 73
+    },
+    {
+      "epoch": 0.24222585924713586,
+      "grad_norm": 2.4511968994240396,
+      "learning_rate": 9.381533400219319e-06,
+      "loss": 2.4545,
+      "step": 74
+    },
+    {
+      "epoch": 0.24549918166939444,
+      "grad_norm": 0.9224443041076055,
+      "learning_rate": 9.353730385598887e-06,
+      "loss": 2.4927,
+      "step": 75
+    },
+    {
+      "epoch": 0.24877250409165302,
+      "grad_norm": 0.4657968594732789,
+      "learning_rate": 9.325359184145307e-06,
+      "loss": 2.4565,
+      "step": 76
+    },
+    {
+      "epoch": 0.2520458265139116,
+      "grad_norm": 0.7177608849321568,
+      "learning_rate": 9.296423498463396e-06,
+      "loss": 2.4825,
+      "step": 77
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 0.57974277665311,
+      "learning_rate": 9.26692710482641e-06,
+      "loss": 2.4789,
+      "step": 78
+    },
+    {
+      "epoch": 0.25859247135842883,
+      "grad_norm": 0.5116606332293397,
+      "learning_rate": 9.236873852683213e-06,
+      "loss": 2.4654,
+      "step": 79
+    },
+    {
+      "epoch": 0.2618657937806874,
+      "grad_norm": 0.4372804881120678,
+      "learning_rate": 9.206267664155906e-06,
+      "loss": 2.4649,
+      "step": 80
+    },
+    {
+      "epoch": 0.265139116202946,
+      "grad_norm": 0.4185499524749441,
+      "learning_rate": 9.175112533527963e-06,
+      "loss": 2.5026,
+      "step": 81
+    },
+    {
+      "epoch": 0.2684124386252046,
+      "grad_norm": 0.5272610155007883,
+      "learning_rate": 9.143412526722958e-06,
+      "loss": 2.4975,
+      "step": 82
+    },
+    {
+      "epoch": 0.27168576104746317,
+      "grad_norm": 0.5340935332042765,
+      "learning_rate": 9.111171780773938e-06,
+      "loss": 2.4816,
+      "step": 83
+    },
+    {
+      "epoch": 0.27495908346972175,
+      "grad_norm": 0.3904804241846333,
+      "learning_rate": 9.078394503283509e-06,
+      "loss": 2.4675,
+      "step": 84
+    },
+    {
+      "epoch": 0.27823240589198034,
+      "grad_norm": 0.3328349798561506,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 2.4633,
+      "step": 85
+    },
+    {
+      "epoch": 0.281505728314239,
+      "grad_norm": 0.37021724634968695,
+      "learning_rate": 9.011247533632876e-06,
+      "loss": 2.4508,
+      "step": 86
+    },
+    {
+      "epoch": 0.28477905073649756,
+      "grad_norm": 0.3729529690097639,
+      "learning_rate": 8.976886604538055e-06,
+      "loss": 2.489,
+      "step": 87
+    },
+    {
+      "epoch": 0.28805237315875615,
+      "grad_norm": 0.33761554067347327,
+      "learning_rate": 8.942006668888972e-06,
+      "loss": 2.4734,
+      "step": 88
+    },
+    {
+      "epoch": 0.29132569558101473,
+      "grad_norm": 0.3584893895881646,
+      "learning_rate": 8.906612278717657e-06,
+      "loss": 2.4702,
+      "step": 89
+    },
+    {
+      "epoch": 0.2945990180032733,
+      "grad_norm": 0.3546249378424476,
+      "learning_rate": 8.870708053195414e-06,
+      "loss": 2.4891,
+      "step": 90
+    },
+    {
+      "epoch": 0.2978723404255319,
+      "grad_norm": 0.3472403078226491,
+      "learning_rate": 8.834298678029988e-06,
+      "loss": 2.4671,
+      "step": 91
+    },
+    {
+      "epoch": 0.3011456628477905,
+      "grad_norm": 0.3453678794183207,
+      "learning_rate": 8.797388904854064e-06,
+      "loss": 2.4971,
+      "step": 92
+    },
+    {
+      "epoch": 0.3044189852700491,
+      "grad_norm": 0.35760827827717245,
+      "learning_rate": 8.759983550605132e-06,
+      "loss": 2.478,
+      "step": 93
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.32637961131906473,
+      "learning_rate": 8.72208749689686e-06,
+      "loss": 2.4519,
+      "step": 94
+    },
+    {
+      "epoch": 0.3109656301145663,
+      "grad_norm": 0.3451716663724565,
+      "learning_rate": 8.683705689382025e-06,
+      "loss": 2.4597,
+      "step": 95
+    },
+    {
+      "epoch": 0.3142389525368249,
+      "grad_norm": 0.3397179170708975,
+      "learning_rate": 8.644843137107058e-06,
+      "loss": 2.4738,
+      "step": 96
+    },
+    {
+      "epoch": 0.31751227495908346,
+      "grad_norm": 0.3507051892225581,
+      "learning_rate": 8.605504911858347e-06,
+      "loss": 2.5,
+      "step": 97
+    },
+    {
+      "epoch": 0.32078559738134205,
+      "grad_norm": 0.3400362404421244,
+      "learning_rate": 8.565696147500338e-06,
+      "loss": 2.4768,
+      "step": 98
+    },
+    {
+      "epoch": 0.32405891980360063,
+      "grad_norm": 0.35484798538066187,
+      "learning_rate": 8.525422039305529e-06,
+      "loss": 2.4858,
+      "step": 99
+    },
+    {
+      "epoch": 0.32733224222585927,
+      "grad_norm": 0.3658788522731373,
+      "learning_rate": 8.48468784327647e-06,
+      "loss": 2.4738,
+      "step": 100
+    },
+    {
+      "epoch": 0.33060556464811786,
+      "grad_norm": 0.3398517081347872,
+      "learning_rate": 8.44349887545981e-06,
+      "loss": 2.4877,
+      "step": 101
+    },
+    {
+      "epoch": 0.33387888707037644,
+      "grad_norm": 0.38013549611094194,
+      "learning_rate": 8.401860511252535e-06,
+      "loss": 2.4638,
+      "step": 102
+    },
+    {
+      "epoch": 0.337152209492635,
+      "grad_norm": 0.3484658452958359,
+      "learning_rate": 8.35977818470044e-06,
+      "loss": 2.4783,
+      "step": 103
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.3554237638577351,
+      "learning_rate": 8.31725738778896e-06,
+      "loss": 2.474,
+      "step": 104
+    },
+    {
+      "epoch": 0.3436988543371522,
+      "grad_norm": 0.3448509168732586,
+      "learning_rate": 8.274303669726427e-06,
+      "loss": 2.4568,
+      "step": 105
+    },
+    {
+      "epoch": 0.3469721767594108,
+      "grad_norm": 0.3491512405342342,
+      "learning_rate": 8.230922636219872e-06,
+      "loss": 2.479,
+      "step": 106
+    },
+    {
+      "epoch": 0.3502454991816694,
+      "grad_norm": 0.35293167144622156,
+      "learning_rate": 8.18711994874345e-06,
+      "loss": 2.4889,
+      "step": 107
+    },
+    {
+      "epoch": 0.353518821603928,
+      "grad_norm": 0.34554222359891335,
+      "learning_rate": 8.142901323799578e-06,
+      "loss": 2.4948,
+      "step": 108
+    },
+    {
+      "epoch": 0.3567921440261866,
+      "grad_norm": 0.3433706276706439,
+      "learning_rate": 8.098272532172906e-06,
+      "loss": 2.4896,
+      "step": 109
+    },
+    {
+      "epoch": 0.36006546644844517,
+      "grad_norm": 0.32061609152441495,
+      "learning_rate": 8.053239398177191e-06,
+      "loss": 2.4374,
+      "step": 110
+    },
+    {
+      "epoch": 0.36333878887070375,
+      "grad_norm": 0.3443744364995488,
+      "learning_rate": 8.007807798895195e-06,
+      "loss": 2.4754,
+      "step": 111
+    },
+    {
+      "epoch": 0.36661211129296234,
+      "grad_norm": 0.32691985158573217,
+      "learning_rate": 7.961983663411684e-06,
+      "loss": 2.4777,
+      "step": 112
+    },
+    {
+      "epoch": 0.3698854337152209,
+      "grad_norm": 0.33245765943085837,
+      "learning_rate": 7.91577297203966e-06,
+      "loss": 2.4723,
+      "step": 113
+    },
+    {
+      "epoch": 0.37315875613747956,
+      "grad_norm": 0.33707956489119834,
+      "learning_rate": 7.869181755539888e-06,
+      "loss": 2.4709,
+      "step": 114
+    },
+    {
+      "epoch": 0.37643207855973815,
+      "grad_norm": 0.3334493326179338,
+      "learning_rate": 7.822216094333847e-06,
+      "loss": 2.5068,
+      "step": 115
+    },
+    {
+      "epoch": 0.37970540098199673,
+      "grad_norm": 0.3244946372709713,
+      "learning_rate": 7.774882117710203e-06,
+      "loss": 2.4797,
+      "step": 116
+    },
+    {
+      "epoch": 0.3829787234042553,
+      "grad_norm": 0.3277650850109358,
+      "learning_rate": 7.727186003024902e-06,
+      "loss": 2.4618,
+      "step": 117
+    },
+    {
+      "epoch": 0.3862520458265139,
+      "grad_norm": 0.34009316740947815,
+      "learning_rate": 7.679133974894984e-06,
+      "loss": 2.4581,
+      "step": 118
+    },
+    {
+      "epoch": 0.3895253682487725,
+      "grad_norm": 0.3381461847729053,
+      "learning_rate": 7.630732304386244e-06,
+      "loss": 2.4817,
+      "step": 119
+    },
+    {
+      "epoch": 0.39279869067103107,
+      "grad_norm": 0.3385097066946103,
+      "learning_rate": 7.5819873081948105e-06,
+      "loss": 2.4847,
+      "step": 120
+    },
+    {
+      "epoch": 0.3960720130932897,
+      "grad_norm": 0.3372871065877283,
+      "learning_rate": 7.532905347822792e-06,
+      "loss": 2.4577,
+      "step": 121
+    },
+    {
+      "epoch": 0.3993453355155483,
+      "grad_norm": 0.32559796645917616,
+      "learning_rate": 7.4834928287480566e-06,
+      "loss": 2.4923,
+      "step": 122
+    },
+    {
+      "epoch": 0.4026186579378069,
+      "grad_norm": 0.3251819544833203,
+      "learning_rate": 7.433756199588282e-06,
+      "loss": 2.4746,
+      "step": 123
+    },
+    {
+      "epoch": 0.40589198036006546,
+      "grad_norm": 0.33165207760018856,
+      "learning_rate": 7.383701951259375e-06,
+      "loss": 2.497,
+      "step": 124
+    },
+    {
+      "epoch": 0.40916530278232405,
+      "grad_norm": 0.33880444150123695,
+      "learning_rate": 7.333336616128369e-06,
+      "loss": 2.4362,
+      "step": 125
+    },
+    {
+      "epoch": 0.41243862520458263,
+      "grad_norm": 0.32428200516815325,
+      "learning_rate": 7.282666767160913e-06,
+      "loss": 2.4439,
+      "step": 126
+    },
+    {
+      "epoch": 0.4157119476268412,
+      "grad_norm": 0.3273982952564575,
+      "learning_rate": 7.23169901706346e-06,
+      "loss": 2.4801,
+      "step": 127
+    },
+    {
+      "epoch": 0.41898527004909986,
+      "grad_norm": 0.3261565580453942,
+      "learning_rate": 7.180440017420277e-06,
+      "loss": 2.4903,
+      "step": 128
+    },
+    {
+      "epoch": 0.42225859247135844,
+      "grad_norm": 0.35528485781883334,
+      "learning_rate": 7.128896457825364e-06,
+      "loss": 2.4653,
+      "step": 129
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.3185186205453131,
+      "learning_rate": 7.0770750650094335e-06,
+      "loss": 2.4605,
+      "step": 130
+    },
+    {
+      "epoch": 0.4288052373158756,
+      "grad_norm": 0.3431153323420711,
+      "learning_rate": 7.024982601962027e-06,
+      "loss": 2.4627,
+      "step": 131
+    },
+    {
+      "epoch": 0.4320785597381342,
+      "grad_norm": 0.31409563060102685,
+      "learning_rate": 6.972625867048914e-06,
+      "loss": 2.457,
+      "step": 132
+    },
+    {
+      "epoch": 0.4353518821603928,
+      "grad_norm": 0.3352629031883897,
+      "learning_rate": 6.9200116931248575e-06,
+      "loss": 2.4805,
+      "step": 133
+    },
+    {
+      "epoch": 0.4386252045826514,
+      "grad_norm": 0.3295764773687296,
+      "learning_rate": 6.8671469466418914e-06,
+      "loss": 2.465,
+      "step": 134
+    },
+    {
+      "epoch": 0.44189852700491,
+      "grad_norm": 0.32638616945204396,
+      "learning_rate": 6.814038526753205e-06,
+      "loss": 2.4317,
+      "step": 135
+    },
+    {
+      "epoch": 0.4451718494271686,
+      "grad_norm": 0.358055738131873,
+      "learning_rate": 6.760693364412776e-06,
+      "loss": 2.4459,
+      "step": 136
+    },
+    {
+      "epoch": 0.44844517184942717,
+      "grad_norm": 0.32782232063682554,
+      "learning_rate": 6.707118421470822e-06,
+      "loss": 2.4652,
+      "step": 137
+    },
+    {
+      "epoch": 0.45171849427168576,
+      "grad_norm": 0.3213728199970128,
+      "learning_rate": 6.653320689765257e-06,
+      "loss": 2.4812,
+      "step": 138
+    },
+    {
+      "epoch": 0.45499181669394434,
+      "grad_norm": 0.3145652401211947,
+      "learning_rate": 6.599307190209206e-06,
+      "loss": 2.4622,
+      "step": 139
+    },
+    {
+      "epoch": 0.4582651391162029,
+      "grad_norm": 0.33107965983633225,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 2.4856,
+      "step": 140
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.33391686920613367,
+      "learning_rate": 6.490661111072923e-06,
+      "loss": 2.4519,
+      "step": 141
+    },
+    {
+      "epoch": 0.46481178396072015,
+      "grad_norm": 0.31915606377667516,
+      "learning_rate": 6.4360427104303326e-06,
+      "loss": 2.458,
+      "step": 142
+    },
+    {
+      "epoch": 0.46808510638297873,
+      "grad_norm": 0.32619864635648854,
+      "learning_rate": 6.381236897962102e-06,
+      "loss": 2.48,
+      "step": 143
+    },
+    {
+      "epoch": 0.4713584288052373,
+      "grad_norm": 0.3344755693427373,
+      "learning_rate": 6.326250826141689e-06,
+      "loss": 2.4728,
+      "step": 144
+    },
+    {
+      "epoch": 0.4746317512274959,
+      "grad_norm": 0.3125523770454477,
+      "learning_rate": 6.271091670967437e-06,
+      "loss": 2.4587,
+      "step": 145
+    },
+    {
+      "epoch": 0.4779050736497545,
+      "grad_norm": 0.32456956099182205,
+      "learning_rate": 6.215766631026049e-06,
+      "loss": 2.4694,
+      "step": 146
+    },
+    {
+      "epoch": 0.48117839607201307,
+      "grad_norm": 0.3183205037717091,
+      "learning_rate": 6.1602829265531585e-06,
+      "loss": 2.4752,
+      "step": 147
+    },
+    {
+      "epoch": 0.4844517184942717,
+      "grad_norm": 0.31706883694319504,
+      "learning_rate": 6.1046477984910215e-06,
+      "loss": 2.4715,
+      "step": 148
+    },
+    {
+      "epoch": 0.4877250409165303,
+      "grad_norm": 0.32677657711179986,
+      "learning_rate": 6.048868507543547e-06,
+      "loss": 2.4684,
+      "step": 149
+    },
+    {
+      "epoch": 0.4909983633387889,
+      "grad_norm": 0.32457051719454905,
+      "learning_rate": 5.9929523332287275e-06,
+      "loss": 2.471,
+      "step": 150
+    },
+    {
+      "epoch": 0.49427168576104746,
+      "grad_norm": 0.329167055323462,
+      "learning_rate": 5.936906572928625e-06,
+      "loss": 2.4696,
+      "step": 151
+    },
+    {
+      "epoch": 0.49754500818330605,
+      "grad_norm": 0.3233867081897887,
+      "learning_rate": 5.880738540937008e-06,
+      "loss": 2.4758,
+      "step": 152
+    },
+    {
+      "epoch": 0.5008183306055647,
+      "grad_norm": 0.310943717613368,
+      "learning_rate": 5.824455567504817e-06,
+      "loss": 2.4813,
+      "step": 153
+    },
+    {
+      "epoch": 0.5040916530278232,
+      "grad_norm": 0.35767604251132745,
+      "learning_rate": 5.7680649978834976e-06,
+      "loss": 2.4628,
+      "step": 154
+    },
+    {
+      "epoch": 0.5073649754500819,
+      "grad_norm": 0.3066334220540355,
+      "learning_rate": 5.711574191366427e-06,
+      "loss": 2.4645,
+      "step": 155
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.3299515321649155,
+      "learning_rate": 5.654990520328465e-06,
+      "loss": 2.4445,
+      "step": 156
+    },
+    {
+      "epoch": 0.513911620294599,
+      "grad_norm": 0.31272357276253326,
+      "learning_rate": 5.59832136926383e-06,
+      "loss": 2.4594,
+      "step": 157
+    },
+    {
+      "epoch": 0.5171849427168577,
+      "grad_norm": 0.3094045826418548,
+      "learning_rate": 5.541574133822374e-06,
+      "loss": 2.4481,
+      "step": 158
+    },
+    {
+      "epoch": 0.5204582651391162,
+      "grad_norm": 0.33143709507448227,
+      "learning_rate": 5.484756219844408e-06,
+      "loss": 2.4621,
+      "step": 159
+    },
+    {
+      "epoch": 0.5237315875613748,
+      "grad_norm": 0.30398134753496064,
+      "learning_rate": 5.4278750423942e-06,
+      "loss": 2.4715,
+      "step": 160
+    },
+    {
+      "epoch": 0.5270049099836334,
+      "grad_norm": 0.31511994044804714,
+      "learning_rate": 5.370938024792262e-06,
+      "loss": 2.4609,
+      "step": 161
+    },
+    {
+      "epoch": 0.530278232405892,
+      "grad_norm": 0.3204336918739602,
+      "learning_rate": 5.3139525976465675e-06,
+      "loss": 2.4501,
+      "step": 162
+    },
+    {
+      "epoch": 0.5335515548281505,
+      "grad_norm": 0.3243453056297712,
+      "learning_rate": 5.2569261978828155e-06,
+      "loss": 2.4634,
+      "step": 163
+    },
+    {
+      "epoch": 0.5368248772504092,
+      "grad_norm": 0.3131904676215095,
+      "learning_rate": 5.199866267773868e-06,
+      "loss": 2.4684,
+      "step": 164
+    },
+    {
+      "epoch": 0.5400981996726678,
+      "grad_norm": 0.3338712281774405,
+      "learning_rate": 5.142780253968481e-06,
+      "loss": 2.4687,
+      "step": 165
+    },
+    {
+      "epoch": 0.5433715220949263,
+      "grad_norm": 0.3108967805240922,
+      "learning_rate": 5.085675606519496e-06,
+      "loss": 2.4443,
+      "step": 166
+    },
+    {
+      "epoch": 0.546644844517185,
+      "grad_norm": 0.31028829982787426,
+      "learning_rate": 5.028559777911543e-06,
+      "loss": 2.471,
+      "step": 167
+    },
+    {
+      "epoch": 0.5499181669394435,
+      "grad_norm": 0.31679487774858733,
+      "learning_rate": 4.971440222088459e-06,
+      "loss": 2.4654,
+      "step": 168
+    },
+    {
+      "epoch": 0.5531914893617021,
+      "grad_norm": 0.31296921041810605,
+      "learning_rate": 4.914324393480504e-06,
+      "loss": 2.4442,
+      "step": 169
+    },
+    {
+      "epoch": 0.5564648117839607,
+      "grad_norm": 0.3165078522607312,
+      "learning_rate": 4.85721974603152e-06,
+      "loss": 2.4494,
+      "step": 170
+    },
+    {
+      "epoch": 0.5597381342062193,
+      "grad_norm": 0.3540062454779396,
+      "learning_rate": 4.800133732226135e-06,
+      "loss": 2.4664,
+      "step": 171
+    },
+    {
+      "epoch": 0.563011456628478,
+      "grad_norm": 0.32009750544034943,
+      "learning_rate": 4.743073802117185e-06,
+      "loss": 2.4809,
+      "step": 172
+    },
+    {
+      "epoch": 0.5662847790507365,
+      "grad_norm": 0.2983415714217039,
+      "learning_rate": 4.686047402353433e-06,
+      "loss": 2.4564,
+      "step": 173
+    },
+    {
+      "epoch": 0.5695581014729951,
+      "grad_norm": 0.2999034797032862,
+      "learning_rate": 4.62906197520774e-06,
+      "loss": 2.467,
+      "step": 174
+    },
+    {
+      "epoch": 0.5728314238952537,
+      "grad_norm": 0.3102585042911049,
+      "learning_rate": 4.572124957605803e-06,
+      "loss": 2.46,
+      "step": 175
+    },
+    {
+      "epoch": 0.5761047463175123,
+      "grad_norm": 0.31057870076393,
+      "learning_rate": 4.515243780155594e-06,
+      "loss": 2.4704,
+      "step": 176
+    },
+    {
+      "epoch": 0.5793780687397708,
+      "grad_norm": 0.3046118860204264,
+      "learning_rate": 4.458425866177628e-06,
+      "loss": 2.467,
+      "step": 177
+    },
+    {
+      "epoch": 0.5826513911620295,
+      "grad_norm": 0.30073951913953495,
+      "learning_rate": 4.401678630736172e-06,
+      "loss": 2.4743,
+      "step": 178
+    },
+    {
+      "epoch": 0.5859247135842881,
+      "grad_norm": 0.30406830972525584,
+      "learning_rate": 4.3450094796715354e-06,
+      "loss": 2.4798,
+      "step": 179
+    },
+    {
+      "epoch": 0.5891980360065466,
+      "grad_norm": 0.3054725070167328,
+      "learning_rate": 4.2884258086335755e-06,
+      "loss": 2.468,
+      "step": 180
+    },
+    {
+      "epoch": 0.5924713584288053,
+      "grad_norm": 0.31961569501005616,
+      "learning_rate": 4.231935002116504e-06,
+      "loss": 2.4853,
+      "step": 181
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.29332706934686226,
+      "learning_rate": 4.175544432495184e-06,
+      "loss": 2.4684,
+      "step": 182
+    },
+    {
+      "epoch": 0.5990180032733224,
+      "grad_norm": 0.3136548340197598,
+      "learning_rate": 4.119261459062992e-06,
+      "loss": 2.4617,
+      "step": 183
+    },
+    {
+      "epoch": 0.602291325695581,
+      "grad_norm": 0.29768754171106776,
+      "learning_rate": 4.063093427071376e-06,
+      "loss": 2.4506,
+      "step": 184
+    },
+    {
+      "epoch": 0.6055646481178396,
+      "grad_norm": 0.3102339131602259,
+      "learning_rate": 4.007047666771274e-06,
+      "loss": 2.4692,
+      "step": 185
+    },
+    {
+      "epoch": 0.6088379705400983,
+      "grad_norm": 0.31512899490271845,
+      "learning_rate": 3.951131492456455e-06,
+      "loss": 2.4399,
+      "step": 186
+    },
+    {
+      "epoch": 0.6121112929623568,
+      "grad_norm": 0.29668620197615053,
+      "learning_rate": 3.895352201508981e-06,
+      "loss": 2.4658,
+      "step": 187
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.3129729278174446,
+      "learning_rate": 3.839717073446842e-06,
+      "loss": 2.4296,
+      "step": 188
+    },
+    {
+      "epoch": 0.618657937806874,
+      "grad_norm": 0.3087654037315499,
+      "learning_rate": 3.7842333689739524e-06,
+      "loss": 2.4512,
+      "step": 189
+    },
+    {
+      "epoch": 0.6219312602291326,
+      "grad_norm": 0.29989373586590584,
+      "learning_rate": 3.7289083290325668e-06,
+      "loss": 2.4543,
+      "step": 190
+    },
+    {
+      "epoch": 0.6252045826513911,
+      "grad_norm": 0.30200062774615277,
+      "learning_rate": 3.673749173858312e-06,
+      "loss": 2.4637,
+      "step": 191
+    },
+    {
+      "epoch": 0.6284779050736498,
+      "grad_norm": 0.3059048859940154,
+      "learning_rate": 3.618763102037899e-06,
+      "loss": 2.4714,
+      "step": 192
+    },
+    {
+      "epoch": 0.6317512274959084,
+      "grad_norm": 0.2995831991905797,
+      "learning_rate": 3.563957289569669e-06,
+      "loss": 2.4581,
+      "step": 193
+    },
+    {
+      "epoch": 0.6350245499181669,
+      "grad_norm": 0.3058506564330453,
+      "learning_rate": 3.509338888927079e-06,
+      "loss": 2.4556,
+      "step": 194
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 0.2932520015994215,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 2.4536,
+      "step": 195
+    },
+    {
+      "epoch": 0.6415711947626841,
+      "grad_norm": 0.29644091797619826,
+      "learning_rate": 3.400692809790796e-06,
+      "loss": 2.4524,
+      "step": 196
+    },
+    {
+      "epoch": 0.6448445171849427,
+      "grad_norm": 0.2973231753014199,
+      "learning_rate": 3.346679310234744e-06,
+      "loss": 2.439,
+      "step": 197
+    },
+    {
+      "epoch": 0.6481178396072013,
+      "grad_norm": 0.2970530949566317,
+      "learning_rate": 3.292881578529179e-06,
+      "loss": 2.441,
+      "step": 198
+    },
+    {
+      "epoch": 0.6513911620294599,
+      "grad_norm": 0.29457945074596364,
+      "learning_rate": 3.2393066355872264e-06,
+      "loss": 2.4393,
+      "step": 199
+    },
+    {
+      "epoch": 0.6546644844517185,
+      "grad_norm": 0.2959752353295032,
+      "learning_rate": 3.1859614732467957e-06,
+      "loss": 2.4413,
+      "step": 200
+    },
+    {
+      "epoch": 0.6579378068739771,
+      "grad_norm": 0.2894024794008193,
+      "learning_rate": 3.1328530533581102e-06,
+      "loss": 2.4486,
+      "step": 201
+    },
+    {
+      "epoch": 0.6612111292962357,
+      "grad_norm": 0.30092182634576625,
+      "learning_rate": 3.0799883068751433e-06,
+      "loss": 2.4523,
+      "step": 202
+    },
+    {
+      "epoch": 0.6644844517184942,
+      "grad_norm": 0.2957309468597844,
+      "learning_rate": 3.0273741329510852e-06,
+      "loss": 2.4335,
+      "step": 203
+    },
+    {
+      "epoch": 0.6677577741407529,
+      "grad_norm": 0.28459255910232356,
+      "learning_rate": 2.975017398037974e-06,
+      "loss": 2.4875,
+      "step": 204
+    },
+    {
+      "epoch": 0.6710310965630114,
+      "grad_norm": 0.29271515123042124,
+      "learning_rate": 2.9229249349905686e-06,
+      "loss": 2.475,
+      "step": 205
+    },
+    {
+      "epoch": 0.67430441898527,
+      "grad_norm": 0.30277820836046737,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 2.4669,
+      "step": 206
+    },
+    {
+      "epoch": 0.6775777414075287,
+      "grad_norm": 0.2859827817423741,
+      "learning_rate": 2.8195599825797233e-06,
+      "loss": 2.4514,
+      "step": 207
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.2968379809937716,
+      "learning_rate": 2.7683009829365417e-06,
+      "loss": 2.4607,
+      "step": 208
+    },
+    {
+      "epoch": 0.6841243862520459,
+      "grad_norm": 0.29656383723002844,
+      "learning_rate": 2.717333232839088e-06,
+      "loss": 2.4905,
+      "step": 209
+    },
+    {
+      "epoch": 0.6873977086743044,
+      "grad_norm": 0.28883812040540374,
+      "learning_rate": 2.6666633838716317e-06,
+      "loss": 2.4543,
+      "step": 210
+    },
+    {
+      "epoch": 0.690671031096563,
+      "grad_norm": 0.29531117152054726,
+      "learning_rate": 2.616298048740626e-06,
+      "loss": 2.4551,
+      "step": 211
+    },
+    {
+      "epoch": 0.6939443535188216,
+      "grad_norm": 0.2862187454441366,
+      "learning_rate": 2.566243800411719e-06,
+      "loss": 2.452,
+      "step": 212
+    },
+    {
+      "epoch": 0.6972176759410802,
+      "grad_norm": 0.2911286270146174,
+      "learning_rate": 2.5165071712519447e-06,
+      "loss": 2.4624,
+      "step": 213
+    },
+    {
+      "epoch": 0.7004909983633388,
+      "grad_norm": 0.2869776645891394,
+      "learning_rate": 2.467094652177209e-06,
+      "loss": 2.4607,
+      "step": 214
+    },
+    {
+      "epoch": 0.7037643207855974,
+      "grad_norm": 0.2811233703409396,
+      "learning_rate": 2.418012691805191e-06,
+      "loss": 2.4739,
+      "step": 215
+    },
+    {
+      "epoch": 0.707037643207856,
+      "grad_norm": 0.28005066226487846,
+      "learning_rate": 2.3692676956137585e-06,
+      "loss": 2.457,
+      "step": 216
+    },
+    {
+      "epoch": 0.7103109656301145,
+      "grad_norm": 0.29229180839794044,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 2.4505,
+      "step": 217
+    },
+    {
+      "epoch": 0.7135842880523732,
+      "grad_norm": 0.28905509654195427,
+      "learning_rate": 2.2728139969751005e-06,
+      "loss": 2.4497,
+      "step": 218
+    },
+    {
+      "epoch": 0.7168576104746317,
+      "grad_norm": 0.29091875602679856,
+      "learning_rate": 2.225117882289799e-06,
+      "loss": 2.4386,
+      "step": 219
+    },
+    {
+      "epoch": 0.7201309328968903,
+      "grad_norm": 0.28132598389097907,
+      "learning_rate": 2.1777839056661555e-06,
+      "loss": 2.4688,
+      "step": 220
+    },
+    {
+      "epoch": 0.723404255319149,
+      "grad_norm": 0.27552653164791197,
+      "learning_rate": 2.1308182444601126e-06,
+      "loss": 2.4515,
+      "step": 221
+    },
+    {
+      "epoch": 0.7266775777414075,
+      "grad_norm": 0.285817433950407,
+      "learning_rate": 2.0842270279603403e-06,
+      "loss": 2.4321,
+      "step": 222
+    },
+    {
+      "epoch": 0.7299509001636661,
+      "grad_norm": 0.2774842353710076,
+      "learning_rate": 2.0380163365883188e-06,
+      "loss": 2.4686,
+      "step": 223
+    },
+    {
+      "epoch": 0.7332242225859247,
+      "grad_norm": 0.2782616476099915,
+      "learning_rate": 1.9921922011048065e-06,
+      "loss": 2.4438,
+      "step": 224
+    },
+    {
+      "epoch": 0.7364975450081833,
+      "grad_norm": 0.27697006620218906,
+      "learning_rate": 1.946760601822809e-06,
+      "loss": 2.4461,
+      "step": 225
+    },
+    {
+      "epoch": 0.7397708674304418,
+      "grad_norm": 0.2794520367771161,
+      "learning_rate": 1.9017274678270948e-06,
+      "loss": 2.457,
+      "step": 226
+    },
+    {
+      "epoch": 0.7430441898527005,
+      "grad_norm": 0.293225655343382,
+      "learning_rate": 1.8570986762004246e-06,
+      "loss": 2.4339,
+      "step": 227
+    },
+    {
+      "epoch": 0.7463175122749591,
+      "grad_norm": 0.28410174489532863,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 2.4398,
+      "step": 228
+    },
+    {
+      "epoch": 0.7495908346972177,
+      "grad_norm": 0.28113616787582135,
+      "learning_rate": 1.7690773637801295e-06,
+      "loss": 2.463,
+      "step": 229
+    },
+    {
+      "epoch": 0.7528641571194763,
+      "grad_norm": 0.27128743447878584,
+      "learning_rate": 1.7256963302735752e-06,
+      "loss": 2.4638,
+      "step": 230
+    },
+    {
+      "epoch": 0.7561374795417348,
+      "grad_norm": 0.28051379395375337,
+      "learning_rate": 1.6827426122110412e-06,
+      "loss": 2.4803,
+      "step": 231
+    },
+    {
+      "epoch": 0.7594108019639935,
+      "grad_norm": 0.2774673111470984,
+      "learning_rate": 1.6402218152995609e-06,
+      "loss": 2.4255,
+      "step": 232
+    },
+    {
+      "epoch": 0.762684124386252,
+      "grad_norm": 0.26906487455817846,
+      "learning_rate": 1.598139488747467e-06,
+      "loss": 2.4478,
+      "step": 233
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.2764519019580199,
+      "learning_rate": 1.5565011245401928e-06,
+      "loss": 2.4674,
+      "step": 234
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.28254452300968197,
+      "learning_rate": 1.5153121567235334e-06,
+      "loss": 2.4648,
+      "step": 235
+    },
+    {
+      "epoch": 0.7725040916530278,
+      "grad_norm": 0.28044552819552365,
+      "learning_rate": 1.4745779606944716e-06,
+      "loss": 2.4634,
+      "step": 236
+    },
+    {
+      "epoch": 0.7757774140752864,
+      "grad_norm": 0.2883807662161686,
+      "learning_rate": 1.4343038524996645e-06,
+      "loss": 2.4409,
+      "step": 237
+    },
+    {
+      "epoch": 0.779050736497545,
+      "grad_norm": 0.2712743023254104,
+      "learning_rate": 1.3944950881416541e-06,
+      "loss": 2.4749,
+      "step": 238
+    },
+    {
+      "epoch": 0.7823240589198036,
+      "grad_norm": 0.2844283835642021,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 2.4682,
+      "step": 239
+    },
+    {
+      "epoch": 0.7855973813420621,
+      "grad_norm": 0.2792759057607264,
+      "learning_rate": 1.3162943106179748e-06,
+      "loss": 2.4414,
+      "step": 240
+    },
+    {
+      "epoch": 0.7888707037643208,
+      "grad_norm": 0.2733989225438821,
+      "learning_rate": 1.2779125031031413e-06,
+      "loss": 2.4257,
+      "step": 241
+    },
+    {
+      "epoch": 0.7921440261865794,
+      "grad_norm": 0.271099884675861,
+      "learning_rate": 1.2400164493948713e-06,
+      "loss": 2.4569,
+      "step": 242
+    },
+    {
+      "epoch": 0.795417348608838,
+      "grad_norm": 0.2745676234993269,
+      "learning_rate": 1.2026110951459364e-06,
+      "loss": 2.4489,
+      "step": 243
+    },
+    {
+      "epoch": 0.7986906710310966,
+      "grad_norm": 0.2767138934905047,
+      "learning_rate": 1.1657013219700108e-06,
+      "loss": 2.4562,
+      "step": 244
+    },
+    {
+      "epoch": 0.8019639934533551,
+      "grad_norm": 0.2742378409963404,
+      "learning_rate": 1.1292919468045876e-06,
+      "loss": 2.4333,
+      "step": 245
+    },
+    {
+      "epoch": 0.8052373158756138,
+      "grad_norm": 0.2585166236299042,
+      "learning_rate": 1.0933877212823462e-06,
+      "loss": 2.4476,
+      "step": 246
+    },
+    {
+      "epoch": 0.8085106382978723,
+      "grad_norm": 0.2696183429586083,
+      "learning_rate": 1.057993331111029e-06,
+      "loss": 2.4402,
+      "step": 247
+    },
+    {
+      "epoch": 0.8117839607201309,
+      "grad_norm": 0.2742359647860916,
+      "learning_rate": 1.0231133954619449e-06,
+      "loss": 2.431,
+      "step": 248
+    },
+    {
+      "epoch": 0.8150572831423896,
+      "grad_norm": 0.2745250582957182,
+      "learning_rate": 9.887524663671243e-07,
+      "loss": 2.456,
+      "step": 249
+    },
+    {
+      "epoch": 0.8183306055646481,
+      "grad_norm": 0.2915439246328324,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 2.4739,
+      "step": 250
+    },
+    {
+      "epoch": 0.8216039279869067,
+      "grad_norm": 0.2703132458554063,
+      "learning_rate": 9.216054967164916e-07,
+      "loss": 2.461,
+      "step": 251
+    },
+    {
+      "epoch": 0.8248772504091653,
+      "grad_norm": 0.2902377178678097,
+      "learning_rate": 8.888282192260645e-07,
+      "loss": 2.4499,
+      "step": 252
+    },
+    {
+      "epoch": 0.8281505728314239,
+      "grad_norm": 0.2732853452830904,
+      "learning_rate": 8.565874732770429e-07,
+      "loss": 2.4597,
+      "step": 253
+    },
+    {
+      "epoch": 0.8314238952536824,
+      "grad_norm": 0.2696194963576079,
+      "learning_rate": 8.248874664720375e-07,
+      "loss": 2.4506,
+      "step": 254
+    },
+    {
+      "epoch": 0.8346972176759411,
+      "grad_norm": 0.26860289744719607,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 2.4469,
+      "step": 255
+    },
+    {
+      "epoch": 0.8379705400981997,
+      "grad_norm": 0.271233428425454,
+      "learning_rate": 7.631261473167878e-07,
+      "loss": 2.4532,
+      "step": 256
+    },
+    {
+      "epoch": 0.8412438625204582,
+      "grad_norm": 0.2725978617713584,
+      "learning_rate": 7.330728951735916e-07,
+      "loss": 2.4745,
+      "step": 257
+    },
+    {
+      "epoch": 0.8445171849427169,
+      "grad_norm": 0.26803651743311957,
+      "learning_rate": 7.035765015366047e-07,
+      "loss": 2.4381,
+      "step": 258
+    },
+    {
+      "epoch": 0.8477905073649754,
+      "grad_norm": 0.25921598512129085,
+      "learning_rate": 6.746408158546947e-07,
+      "loss": 2.4533,
+      "step": 259
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.2733847496928928,
+      "learning_rate": 6.462696144011149e-07,
+      "loss": 2.4568,
+      "step": 260
+    },
+    {
+      "epoch": 0.8543371522094927,
+      "grad_norm": 0.26178373020648743,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 2.4581,
+      "step": 261
+    },
+    {
+      "epoch": 0.8576104746317512,
+      "grad_norm": 0.26098357909178693,
+      "learning_rate": 5.912354004465709e-07,
+      "loss": 2.4706,
+      "step": 262
+    },
+    {
+      "epoch": 0.8608837970540099,
+      "grad_norm": 0.25697853000027987,
+      "learning_rate": 5.645795702267731e-07,
+      "loss": 2.4477,
+      "step": 263
+    },
+    {
+      "epoch": 0.8641571194762684,
+      "grad_norm": 0.26192967323861704,
+      "learning_rate": 5.385025878603039e-07,
+      "loss": 2.4414,
+      "step": 264
+    },
+    {
+      "epoch": 0.867430441898527,
+      "grad_norm": 0.26218888376989036,
+      "learning_rate": 5.130078565432089e-07,
+      "loss": 2.4518,
+      "step": 265
+    },
+    {
+      "epoch": 0.8707037643207856,
+      "grad_norm": 0.26990782878286096,
+      "learning_rate": 4.880987034844231e-07,
+      "loss": 2.4553,
+      "step": 266
+    },
+    {
+      "epoch": 0.8739770867430442,
+      "grad_norm": 0.26556563767940716,
+      "learning_rate": 4.637783794715589e-07,
+      "loss": 2.4513,
+      "step": 267
+    },
+    {
+      "epoch": 0.8772504091653028,
+      "grad_norm": 0.2653970429292643,
+      "learning_rate": 4.400500584466505e-07,
+      "loss": 2.4545,
+      "step": 268
+    },
+    {
+      "epoch": 0.8805237315875614,
+      "grad_norm": 0.26432968619903263,
+      "learning_rate": 4.1691683709194184e-07,
+      "loss": 2.4707,
+      "step": 269
+    },
+    {
+      "epoch": 0.88379705400982,
+      "grad_norm": 0.2657171703652861,
+      "learning_rate": 3.9438173442575e-07,
+      "loss": 2.4651,
+      "step": 270
+    },
+    {
+      "epoch": 0.8870703764320785,
+      "grad_norm": 0.2538156470759212,
+      "learning_rate": 3.724476914084657e-07,
+      "loss": 2.4449,
+      "step": 271
+    },
+    {
+      "epoch": 0.8903436988543372,
+      "grad_norm": 0.27133692461664,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 2.473,
+      "step": 272
+    },
+    {
+      "epoch": 0.8936170212765957,
+      "grad_norm": 0.25858521334517437,
+      "learning_rate": 3.303941555799223e-07,
+      "loss": 2.4669,
+      "step": 273
+    },
+    {
+      "epoch": 0.8968903436988543,
+      "grad_norm": 0.2552024596786959,
+      "learning_rate": 3.1028015099673957e-07,
+      "loss": 2.4784,
+      "step": 274
+    },
+    {
+      "epoch": 0.900163666121113,
+      "grad_norm": 0.2639761279668147,
+      "learning_rate": 2.9077818180237693e-07,
+      "loss": 2.4608,
+      "step": 275
+    },
+    {
+      "epoch": 0.9034369885433715,
+      "grad_norm": 0.26158090716261023,
+      "learning_rate": 2.7189079311587596e-07,
+      "loss": 2.4317,
+      "step": 276
+    },
+    {
+      "epoch": 0.9067103109656302,
+      "grad_norm": 0.26420232076269845,
+      "learning_rate": 2.536204498499922e-07,
+      "loss": 2.4715,
+      "step": 277
+    },
+    {
+      "epoch": 0.9099836333878887,
+      "grad_norm": 0.2611776184759321,
+      "learning_rate": 2.3596953638951093e-07,
+      "loss": 2.4496,
+      "step": 278
+    },
+    {
+      "epoch": 0.9132569558101473,
+      "grad_norm": 0.2566448882353072,
+      "learning_rate": 2.1894035628006517e-07,
+      "loss": 2.4535,
+      "step": 279
+    },
+    {
+      "epoch": 0.9165302782324058,
+      "grad_norm": 0.2583889196721565,
+      "learning_rate": 2.0253513192751374e-07,
+      "loss": 2.4312,
+      "step": 280
+    },
+    {
+      "epoch": 0.9198036006546645,
+      "grad_norm": 0.25005870928436097,
+      "learning_rate": 1.867560043079031e-07,
+      "loss": 2.4451,
+      "step": 281
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.25955023725898285,
+      "learning_rate": 1.7160503268806084e-07,
+      "loss": 2.4591,
+      "step": 282
+    },
+    {
+      "epoch": 0.9263502454991817,
+      "grad_norm": 0.25878369029655873,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 2.4613,
+      "step": 283
+    },
+    {
+      "epoch": 0.9296235679214403,
+      "grad_norm": 0.2559725798090891,
+      "learning_rate": 1.4319538436709746e-07,
+      "loss": 2.4422,
+      "step": 284
+    },
+    {
+      "epoch": 0.9328968903436988,
+      "grad_norm": 0.2560397895273692,
+      "learning_rate": 1.2994041528833267e-07,
+      "loss": 2.4712,
+      "step": 285
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.26063225688341923,
+      "learning_rate": 1.1732101697018161e-07,
+      "loss": 2.4452,
+      "step": 286
+    },
+    {
+      "epoch": 0.939443535188216,
+      "grad_norm": 0.2582518091886246,
+      "learning_rate": 1.0533883631663966e-07,
+      "loss": 2.4559,
+      "step": 287
+    },
+    {
+      "epoch": 0.9427168576104746,
+      "grad_norm": 0.26206927755347836,
+      "learning_rate": 9.399543707113601e-08,
+      "loss": 2.477,
+      "step": 288
+    },
+    {
+      "epoch": 0.9459901800327333,
+      "grad_norm": 0.26042235837250066,
+      "learning_rate": 8.329229961245355e-08,
+      "loss": 2.4496,
+      "step": 289
+    },
+    {
+      "epoch": 0.9492635024549918,
+      "grad_norm": 0.257835901510826,
+      "learning_rate": 7.32308207615351e-08,
+      "loss": 2.4546,
+      "step": 290
+    },
+    {
+      "epoch": 0.9525368248772504,
+      "grad_norm": 0.26136373848402616,
+      "learning_rate": 6.381231359918638e-08,
+      "loss": 2.4491,
+      "step": 291
+    },
+    {
+      "epoch": 0.955810147299509,
+      "grad_norm": 0.25188481875716506,
+      "learning_rate": 5.503800729471376e-08,
+      "loss": 2.4425,
+      "step": 292
+    },
+    {
+      "epoch": 0.9590834697217676,
+      "grad_norm": 0.25523476009318996,
+      "learning_rate": 4.690904694550913e-08,
+      "loss": 2.4415,
+      "step": 293
+    },
+    {
+      "epoch": 0.9623567921440261,
+      "grad_norm": 0.2558833671558322,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 2.4591,
+      "step": 294
+    },
+    {
+      "epoch": 0.9656301145662848,
+      "grad_norm": 0.2607553411892932,
+      "learning_rate": 3.25913232572489e-08,
+      "loss": 2.4868,
+      "step": 295
+    },
+    {
+      "epoch": 0.9689034369885434,
+      "grad_norm": 0.262015003675821,
+      "learning_rate": 2.640442846340796e-08,
+      "loss": 2.4675,
+      "step": 296
+    },
+    {
+      "epoch": 0.972176759410802,
+      "grad_norm": 0.2578562996530708,
+      "learning_rate": 2.0866616471409974e-08,
+      "loss": 2.4707,
+      "step": 297
+    },
+    {
+      "epoch": 0.9754500818330606,
+      "grad_norm": 0.2567381919735001,
+      "learning_rate": 1.5978609997542306e-08,
+      "loss": 2.4582,
+      "step": 298
+    },
+    {
+      "epoch": 0.9787234042553191,
+      "grad_norm": 0.2549822571991868,
+      "learning_rate": 1.174104695473688e-08,
+      "loss": 2.4825,
+      "step": 299
+    },
+    {
+      "epoch": 0.9819967266775778,
+      "grad_norm": 0.2554549372989953,
+      "learning_rate": 8.15448036932176e-09,
+      "loss": 2.4719,
+      "step": 300
+    },
+    {
+      "epoch": 0.9852700490998363,
+      "grad_norm": 0.263381774850731,
+      "learning_rate": 5.219378308845558e-09,
+      "loss": 2.4653,
+      "step": 301
+    },
+    {
+      "epoch": 0.9885433715220949,
+      "grad_norm": 0.2528687928806352,
+      "learning_rate": 2.9361238209935085e-09,
+      "loss": 2.4689,
+      "step": 302
+    },
+    {
+      "epoch": 0.9918166939443536,
+      "grad_norm": 0.2610005338150273,
+      "learning_rate": 1.305014883595801e-09,
+      "loss": 2.4555,
+      "step": 303
+    },
+    {
+      "epoch": 0.9950900163666121,
+      "grad_norm": 0.26402197276145056,
+      "learning_rate": 3.262643657425679e-10,
+      "loss": 2.4546,
+      "step": 304
+    },
+    {
+      "epoch": 0.9983633387888707,
+      "grad_norm": 0.25445050680135267,
+      "learning_rate": 0.0,
+      "loss": 2.4702,
+      "step": 305
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 305,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.568140075322573e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:407f49cf1ebdf78c5c1b0c7254648558d7de860686953f68a565ce5c3bc0c084
+size 8376

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)