upload

.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": "/lustre/fsn1/projects/rech/gkb/uua32zb/grand_challenge/checkpoints/Meta-Llama-3.2-3B-annealing2-0.0002LR-8192CL-2GAS-2BS-1EPOCHS-0.9BETA1-0.95BETA2/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "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": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}

latest

@@ -0,0 +1 @@
+global_step13267

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f486b3026322d69c4e0190cf365c3607527809fc701e25a1525676024224cf3a
+size 4965799096

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31277287b534def7f4d89ab752458089d4a91de1ea6acec69555e5b912b96630
+size 2247734992

model.safetensors.index.json

@@ -0,0 +1,262 @@
+{
+  "metadata": {
+    "total_size": 7213504512
+  },
+  "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-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-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.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.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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_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 sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,1888 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500.0,
+  "global_step": 13267,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003768749528906309,
+      "grad_norm": 0.19456887245178223,
+      "learning_rate": 9.999649547444612e-05,
+      "loss": 0.4609,
+      "step": 50
+    },
+    {
+      "epoch": 0.007537499057812618,
+      "grad_norm": 0.18202780187129974,
+      "learning_rate": 9.998598238905239e-05,
+      "loss": 0.4407,
+      "step": 100
+    },
+    {
+      "epoch": 0.011306248586718927,
+      "grad_norm": 0.17280590534210205,
+      "learning_rate": 9.996846221755392e-05,
+      "loss": 0.4401,
+      "step": 150
+    },
+    {
+      "epoch": 0.015074998115625236,
+      "grad_norm": 0.18477164208889008,
+      "learning_rate": 9.994393741594623e-05,
+      "loss": 0.4424,
+      "step": 200
+    },
+    {
+      "epoch": 0.018843747644531544,
+      "grad_norm": 0.18784017860889435,
+      "learning_rate": 9.99124114221411e-05,
+      "loss": 0.4424,
+      "step": 250
+    },
+    {
+      "epoch": 0.022612497173437853,
+      "grad_norm": 0.16860812902450562,
+      "learning_rate": 9.987388865548454e-05,
+      "loss": 0.4418,
+      "step": 300
+    },
+    {
+      "epoch": 0.026381246702344163,
+      "grad_norm": 0.1637168675661087,
+      "learning_rate": 9.982837451613738e-05,
+      "loss": 0.4426,
+      "step": 350
+    },
+    {
+      "epoch": 0.030149996231250472,
+      "grad_norm": 0.15581847727298737,
+      "learning_rate": 9.977587538431816e-05,
+      "loss": 0.4415,
+      "step": 400
+    },
+    {
+      "epoch": 0.03391874576015678,
+      "grad_norm": 0.16367992758750916,
+      "learning_rate": 9.971639861940889e-05,
+      "loss": 0.4401,
+      "step": 450
+    },
+    {
+      "epoch": 0.03768749528906309,
+      "grad_norm": 0.1706039160490036,
+      "learning_rate": 9.964995255892323e-05,
+      "loss": 0.4442,
+      "step": 500
+    },
+    {
+      "epoch": 0.0414562448179694,
+      "grad_norm": 0.16303901374340057,
+      "learning_rate": 9.957654651733788e-05,
+      "loss": 0.4427,
+      "step": 550
+    },
+    {
+      "epoch": 0.045224994346875706,
+      "grad_norm": 0.15467339754104614,
+      "learning_rate": 9.949619078478677e-05,
+      "loss": 0.4397,
+      "step": 600
+    },
+    {
+      "epoch": 0.048993743875782016,
+      "grad_norm": 0.1724122315645218,
+      "learning_rate": 9.940889662561864e-05,
+      "loss": 0.4421,
+      "step": 650
+    },
+    {
+      "epoch": 0.052762493404688325,
+      "grad_norm": 0.15842895209789276,
+      "learning_rate": 9.931467627681792e-05,
+      "loss": 0.439,
+      "step": 700
+    },
+    {
+      "epoch": 0.056531242933594635,
+      "grad_norm": 0.1511755883693695,
+      "learning_rate": 9.921354294628944e-05,
+      "loss": 0.4391,
+      "step": 750
+    },
+    {
+      "epoch": 0.060299992462500944,
+      "grad_norm": 0.14909741282463074,
+      "learning_rate": 9.910551081100684e-05,
+      "loss": 0.4397,
+      "step": 800
+    },
+    {
+      "epoch": 0.06406874199140725,
+      "grad_norm": 0.15353120863437653,
+      "learning_rate": 9.899059501502526e-05,
+      "loss": 0.4389,
+      "step": 850
+    },
+    {
+      "epoch": 0.06783749152031356,
+      "grad_norm": 0.1551615446805954,
+      "learning_rate": 9.886881166735846e-05,
+      "loss": 0.4371,
+      "step": 900
+    },
+    {
+      "epoch": 0.07160624104921987,
+      "grad_norm": 0.1446385234594345,
+      "learning_rate": 9.874017783972058e-05,
+      "loss": 0.4392,
+      "step": 950
+    },
+    {
+      "epoch": 0.07537499057812617,
+      "grad_norm": 0.14661286771297455,
+      "learning_rate": 9.860471156413309e-05,
+      "loss": 0.4372,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07914374010703248,
+      "grad_norm": 0.15160425007343292,
+      "learning_rate": 9.846243183039694e-05,
+      "loss": 0.4376,
+      "step": 1050
+    },
+    {
+      "epoch": 0.0829124896359388,
+      "grad_norm": 0.15164785087108612,
+      "learning_rate": 9.831335858343064e-05,
+      "loss": 0.4363,
+      "step": 1100
+    },
+    {
+      "epoch": 0.0866812391648451,
+      "grad_norm": 0.15714821219444275,
+      "learning_rate": 9.815751272047434e-05,
+      "loss": 0.4369,
+      "step": 1150
+    },
+    {
+      "epoch": 0.09044998869375141,
+      "grad_norm": 0.14024978876113892,
+      "learning_rate": 9.79949160881604e-05,
+      "loss": 0.4349,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09421873822265772,
+      "grad_norm": 0.15335111320018768,
+      "learning_rate": 9.782559147945094e-05,
+      "loss": 0.4361,
+      "step": 1250
+    },
+    {
+      "epoch": 0.09798748775156403,
+      "grad_norm": 0.14330938458442688,
+      "learning_rate": 9.76495626304427e-05,
+      "loss": 0.4347,
+      "step": 1300
+    },
+    {
+      "epoch": 0.10175623728047034,
+      "grad_norm": 0.14001183211803436,
+      "learning_rate": 9.746685421703961e-05,
+      "loss": 0.4331,
+      "step": 1350
+    },
+    {
+      "epoch": 0.10552498680937665,
+      "grad_norm": 0.16508500277996063,
+      "learning_rate": 9.727749185149388e-05,
+      "loss": 0.4339,
+      "step": 1400
+    },
+    {
+      "epoch": 0.10929373633828296,
+      "grad_norm": 0.14644689857959747,
+      "learning_rate": 9.708150207881543e-05,
+      "loss": 0.4337,
+      "step": 1450
+    },
+    {
+      "epoch": 0.11306248586718927,
+      "grad_norm": 0.14279577136039734,
+      "learning_rate": 9.687891237305096e-05,
+      "loss": 0.4339,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11683123539609558,
+      "grad_norm": 0.14988760650157928,
+      "learning_rate": 9.666975113343246e-05,
+      "loss": 0.4321,
+      "step": 1550
+    },
+    {
+      "epoch": 0.12059998492500189,
+      "grad_norm": 0.1408597081899643,
+      "learning_rate": 9.645404768039633e-05,
+      "loss": 0.4311,
+      "step": 1600
+    },
+    {
+      "epoch": 0.1243687344539082,
+      "grad_norm": 0.1554020494222641,
+      "learning_rate": 9.623183225147308e-05,
+      "loss": 0.4311,
+      "step": 1650
+    },
+    {
+      "epoch": 0.1281374839828145,
+      "grad_norm": 0.14362740516662598,
+      "learning_rate": 9.600313599704869e-05,
+      "loss": 0.429,
+      "step": 1700
+    },
+    {
+      "epoch": 0.13190623351172082,
+      "grad_norm": 0.1427031308412552,
+      "learning_rate": 9.576799097599786e-05,
+      "loss": 0.4298,
+      "step": 1750
+    },
+    {
+      "epoch": 0.1356749830406271,
+      "grad_norm": 0.145565927028656,
+      "learning_rate": 9.552643015118998e-05,
+      "loss": 0.427,
+      "step": 1800
+    },
+    {
+      "epoch": 0.13944373256953344,
+      "grad_norm": 0.14019770920276642,
+      "learning_rate": 9.527848738486842e-05,
+      "loss": 0.4265,
+      "step": 1850
+    },
+    {
+      "epoch": 0.14321248209843973,
+      "grad_norm": 0.14158335328102112,
+      "learning_rate": 9.502419743390357e-05,
+      "loss": 0.4283,
+      "step": 1900
+    },
+    {
+      "epoch": 0.14698123162734605,
+      "grad_norm": 0.14075861871242523,
+      "learning_rate": 9.476359594492068e-05,
+      "loss": 0.4277,
+      "step": 1950
+    },
+    {
+      "epoch": 0.15074998115625235,
+      "grad_norm": 0.1477021872997284,
+      "learning_rate": 9.449671944930288e-05,
+      "loss": 0.4277,
+      "step": 2000
+    },
+    {
+      "epoch": 0.15451873068515867,
+      "grad_norm": 0.13484624028205872,
+      "learning_rate": 9.422360535807009e-05,
+      "loss": 0.4285,
+      "step": 2050
+    },
+    {
+      "epoch": 0.15828748021406497,
+      "grad_norm": 0.13757042586803436,
+      "learning_rate": 9.394429195663478e-05,
+      "loss": 0.4268,
+      "step": 2100
+    },
+    {
+      "epoch": 0.1620562297429713,
+      "grad_norm": 0.1443628966808319,
+      "learning_rate": 9.365881839943508e-05,
+      "loss": 0.4249,
+      "step": 2150
+    },
+    {
+      "epoch": 0.1658249792718776,
+      "grad_norm": 0.138884037733078,
+      "learning_rate": 9.336722470444604e-05,
+      "loss": 0.4265,
+      "step": 2200
+    },
+    {
+      "epoch": 0.1695937288007839,
+      "grad_norm": 0.14065410196781158,
+      "learning_rate": 9.306955174756985e-05,
+      "loss": 0.4258,
+      "step": 2250
+    },
+    {
+      "epoch": 0.1733624783296902,
+      "grad_norm": 0.1357513815164566,
+      "learning_rate": 9.27658412569059e-05,
+      "loss": 0.4246,
+      "step": 2300
+    },
+    {
+      "epoch": 0.17713122785859653,
+      "grad_norm": 0.13815779983997345,
+      "learning_rate": 9.24561358069012e-05,
+      "loss": 0.4239,
+      "step": 2350
+    },
+    {
+      "epoch": 0.18089997738750282,
+      "grad_norm": 0.135328009724617,
+      "learning_rate": 9.214047881238233e-05,
+      "loss": 0.4233,
+      "step": 2400
+    },
+    {
+      "epoch": 0.18466872691640915,
+      "grad_norm": 0.13310644030570984,
+      "learning_rate": 9.181891452246937e-05,
+      "loss": 0.4262,
+      "step": 2450
+    },
+    {
+      "epoch": 0.18843747644531544,
+      "grad_norm": 0.15285935997962952,
+      "learning_rate": 9.149148801437321e-05,
+      "loss": 0.4233,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19220622597422174,
+      "grad_norm": 0.1368732899427414,
+      "learning_rate": 9.115824518707644e-05,
+      "loss": 0.4225,
+      "step": 2550
+    },
+    {
+      "epoch": 0.19597497550312806,
+      "grad_norm": 0.1352555751800537,
+      "learning_rate": 9.08192327548992e-05,
+      "loss": 0.4219,
+      "step": 2600
+    },
+    {
+      "epoch": 0.19974372503203436,
+      "grad_norm": 0.1387627273797989,
+      "learning_rate": 9.047449824095075e-05,
+      "loss": 0.421,
+      "step": 2650
+    },
+    {
+      "epoch": 0.20351247456094068,
+      "grad_norm": 0.13286112248897552,
+      "learning_rate": 9.012408997046766e-05,
+      "loss": 0.4217,
+      "step": 2700
+    },
+    {
+      "epoch": 0.20728122408984698,
+      "grad_norm": 0.1302906721830368,
+      "learning_rate": 8.976805706403942e-05,
+      "loss": 0.4207,
+      "step": 2750
+    },
+    {
+      "epoch": 0.2110499736187533,
+      "grad_norm": 0.13901737332344055,
+      "learning_rate": 8.94064494307228e-05,
+      "loss": 0.4193,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2148187231476596,
+      "grad_norm": 0.12851282954216003,
+      "learning_rate": 8.903931776104545e-05,
+      "loss": 0.4182,
+      "step": 2850
+    },
+    {
+      "epoch": 0.21858747267656592,
+      "grad_norm": 0.13808579742908478,
+      "learning_rate": 8.866671351990007e-05,
+      "loss": 0.4181,
+      "step": 2900
+    },
+    {
+      "epoch": 0.22235622220547221,
+      "grad_norm": 0.14110170304775238,
+      "learning_rate": 8.82886889393301e-05,
+      "loss": 0.4193,
+      "step": 2950
+    },
+    {
+      "epoch": 0.22612497173437854,
+      "grad_norm": 0.13282662630081177,
+      "learning_rate": 8.790529701120759e-05,
+      "loss": 0.4166,
+      "step": 3000
+    },
+    {
+      "epoch": 0.22989372126328483,
+      "grad_norm": 0.12828828394412994,
+      "learning_rate": 8.751659147980493e-05,
+      "loss": 0.4185,
+      "step": 3050
+    },
+    {
+      "epoch": 0.23366247079219116,
+      "grad_norm": 0.13336990773677826,
+      "learning_rate": 8.712262683426082e-05,
+      "loss": 0.4149,
+      "step": 3100
+    },
+    {
+      "epoch": 0.23743122032109745,
+      "grad_norm": 0.13983511924743652,
+      "learning_rate": 8.672345830094199e-05,
+      "loss": 0.4174,
+      "step": 3150
+    },
+    {
+      "epoch": 0.24119996985000378,
+      "grad_norm": 0.13716702163219452,
+      "learning_rate": 8.631914183570143e-05,
+      "loss": 0.4167,
+      "step": 3200
+    },
+    {
+      "epoch": 0.24496871937891007,
+      "grad_norm": 0.12907662987709045,
+      "learning_rate": 8.590973411603452e-05,
+      "loss": 0.4159,
+      "step": 3250
+    },
+    {
+      "epoch": 0.2487374689078164,
+      "grad_norm": 0.12837421894073486,
+      "learning_rate": 8.549529253313386e-05,
+      "loss": 0.4165,
+      "step": 3300
+    },
+    {
+      "epoch": 0.2525062184367227,
+      "grad_norm": 0.13946649432182312,
+      "learning_rate": 8.507587518384421e-05,
+      "loss": 0.414,
+      "step": 3350
+    },
+    {
+      "epoch": 0.256274967965629,
+      "grad_norm": 0.128893181681633,
+      "learning_rate": 8.465154086251828e-05,
+      "loss": 0.4133,
+      "step": 3400
+    },
+    {
+      "epoch": 0.2600437174945353,
+      "grad_norm": 0.13107603788375854,
+      "learning_rate": 8.422234905277495e-05,
+      "loss": 0.414,
+      "step": 3450
+    },
+    {
+      "epoch": 0.26381246702344163,
+      "grad_norm": 0.1320282369852066,
+      "learning_rate": 8.378835991916083e-05,
+      "loss": 0.4139,
+      "step": 3500
+    },
+    {
+      "epoch": 0.26758121655234796,
+      "grad_norm": 0.135846346616745,
+      "learning_rate": 8.334963429871627e-05,
+      "loss": 0.4154,
+      "step": 3550
+    },
+    {
+      "epoch": 0.2713499660812542,
+      "grad_norm": 0.1381276398897171,
+      "learning_rate": 8.290623369244721e-05,
+      "loss": 0.413,
+      "step": 3600
+    },
+    {
+      "epoch": 0.27511871561016055,
+      "grad_norm": 0.1333329826593399,
+      "learning_rate": 8.245822025670384e-05,
+      "loss": 0.4146,
+      "step": 3650
+    },
+    {
+      "epoch": 0.27888746513906687,
+      "grad_norm": 0.12488547712564468,
+      "learning_rate": 8.200565679446753e-05,
+      "loss": 0.4102,
+      "step": 3700
+    },
+    {
+      "epoch": 0.2826562146679732,
+      "grad_norm": 0.13603095710277557,
+      "learning_rate": 8.154860674654698e-05,
+      "loss": 0.4114,
+      "step": 3750
+    },
+    {
+      "epoch": 0.28642496419687946,
+      "grad_norm": 0.13111622631549835,
+      "learning_rate": 8.108713418268514e-05,
+      "loss": 0.4112,
+      "step": 3800
+    },
+    {
+      "epoch": 0.2901937137257858,
+      "grad_norm": 0.1286476105451584,
+      "learning_rate": 8.062130379257764e-05,
+      "loss": 0.4112,
+      "step": 3850
+    },
+    {
+      "epoch": 0.2939624632546921,
+      "grad_norm": 0.13606774806976318,
+      "learning_rate": 8.015118087680477e-05,
+      "loss": 0.4117,
+      "step": 3900
+    },
+    {
+      "epoch": 0.2977312127835984,
+      "grad_norm": 0.12688776850700378,
+      "learning_rate": 7.96768313376774e-05,
+      "loss": 0.4077,
+      "step": 3950
+    },
+    {
+      "epoch": 0.3014999623125047,
+      "grad_norm": 0.13127557933330536,
+      "learning_rate": 7.919832166999874e-05,
+      "loss": 0.4091,
+      "step": 4000
+    },
+    {
+      "epoch": 0.305268711841411,
+      "grad_norm": 0.12965704500675201,
+      "learning_rate": 7.871571895174316e-05,
+      "loss": 0.4076,
+      "step": 4050
+    },
+    {
+      "epoch": 0.30903746137031735,
+      "grad_norm": 0.1248898133635521,
+      "learning_rate": 7.822909083465298e-05,
+      "loss": 0.4099,
+      "step": 4100
+    },
+    {
+      "epoch": 0.3128062108992236,
+      "grad_norm": 0.13600467145442963,
+      "learning_rate": 7.773850553475508e-05,
+      "loss": 0.4071,
+      "step": 4150
+    },
+    {
+      "epoch": 0.31657496042812994,
+      "grad_norm": 0.13761986792087555,
+      "learning_rate": 7.724403182279823e-05,
+      "loss": 0.4097,
+      "step": 4200
+    },
+    {
+      "epoch": 0.32034370995703626,
+      "grad_norm": 0.13098478317260742,
+      "learning_rate": 7.674573901461282e-05,
+      "loss": 0.4046,
+      "step": 4250
+    },
+    {
+      "epoch": 0.3241124594859426,
+      "grad_norm": 0.1297547072172165,
+      "learning_rate": 7.624369696139402e-05,
+      "loss": 0.406,
+      "step": 4300
+    },
+    {
+      "epoch": 0.32788120901484885,
+      "grad_norm": 0.12281239032745361,
+      "learning_rate": 7.573797603991004e-05,
+      "loss": 0.4072,
+      "step": 4350
+    },
+    {
+      "epoch": 0.3316499585437552,
+      "grad_norm": 0.1250068098306656,
+      "learning_rate": 7.522864714263655e-05,
+      "loss": 0.4068,
+      "step": 4400
+    },
+    {
+      "epoch": 0.3354187080726615,
+      "grad_norm": 0.12702082097530365,
+      "learning_rate": 7.471578166781899e-05,
+      "loss": 0.4069,
+      "step": 4450
+    },
+    {
+      "epoch": 0.3391874576015678,
+      "grad_norm": 0.1302025467157364,
+      "learning_rate": 7.419945150946386e-05,
+      "loss": 0.4045,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3429562071304741,
+      "grad_norm": 0.13086843490600586,
+      "learning_rate": 7.367972904726055e-05,
+      "loss": 0.4065,
+      "step": 4550
+    },
+    {
+      "epoch": 0.3467249566593804,
+      "grad_norm": 0.12231607735157013,
+      "learning_rate": 7.3156687136435e-05,
+      "loss": 0.4041,
+      "step": 4600
+    },
+    {
+      "epoch": 0.35049370618828674,
+      "grad_norm": 0.12740549445152283,
+      "learning_rate": 7.26303990975369e-05,
+      "loss": 0.4045,
+      "step": 4650
+    },
+    {
+      "epoch": 0.35426245571719306,
+      "grad_norm": 0.1309334933757782,
+      "learning_rate": 7.210093870616155e-05,
+      "loss": 0.4043,
+      "step": 4700
+    },
+    {
+      "epoch": 0.3580312052460993,
+      "grad_norm": 0.12529818713665009,
+      "learning_rate": 7.156838018260776e-05,
+      "loss": 0.4034,
+      "step": 4750
+    },
+    {
+      "epoch": 0.36179995477500565,
+      "grad_norm": 0.12599386274814606,
+      "learning_rate": 7.103279818147371e-05,
+      "loss": 0.4014,
+      "step": 4800
+    },
+    {
+      "epoch": 0.365568704303912,
+      "grad_norm": 0.13122481107711792,
+      "learning_rate": 7.049426778119179e-05,
+      "loss": 0.402,
+      "step": 4850
+    },
+    {
+      "epoch": 0.3693374538328183,
+      "grad_norm": 0.1257227212190628,
+      "learning_rate": 6.995286447350397e-05,
+      "loss": 0.402,
+      "step": 4900
+    },
+    {
+      "epoch": 0.37310620336172456,
+      "grad_norm": 0.13369211554527283,
+      "learning_rate": 6.940866415287931e-05,
+      "loss": 0.4021,
+      "step": 4950
+    },
+    {
+      "epoch": 0.3768749528906309,
+      "grad_norm": 0.12336255609989166,
+      "learning_rate": 6.886174310587501e-05,
+      "loss": 0.3999,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3806437024195372,
+      "grad_norm": 0.12576647102832794,
+      "learning_rate": 6.831217800044252e-05,
+      "loss": 0.4027,
+      "step": 5050
+    },
+    {
+      "epoch": 0.3844124519484435,
+      "grad_norm": 0.12260672450065613,
+      "learning_rate": 6.776004587518001e-05,
+      "loss": 0.4018,
+      "step": 5100
+    },
+    {
+      "epoch": 0.3881812014773498,
+      "grad_norm": 0.12775105237960815,
+      "learning_rate": 6.720542412853319e-05,
+      "loss": 0.3993,
+      "step": 5150
+    },
+    {
+      "epoch": 0.3919499510062561,
+      "grad_norm": 0.126275435090065,
+      "learning_rate": 6.66483905079454e-05,
+      "loss": 0.3991,
+      "step": 5200
+    },
+    {
+      "epoch": 0.39571870053516245,
+      "grad_norm": 0.12239239364862442,
+      "learning_rate": 6.608902309895895e-05,
+      "loss": 0.3974,
+      "step": 5250
+    },
+    {
+      "epoch": 0.3994874500640687,
+      "grad_norm": 0.12439530342817307,
+      "learning_rate": 6.552740031426902e-05,
+      "loss": 0.3949,
+      "step": 5300
+    },
+    {
+      "epoch": 0.40325619959297504,
+      "grad_norm": 0.12401723861694336,
+      "learning_rate": 6.496360088273161e-05,
+      "loss": 0.3974,
+      "step": 5350
+    },
+    {
+      "epoch": 0.40702494912188136,
+      "grad_norm": 0.12568959593772888,
+      "learning_rate": 6.439770383832732e-05,
+      "loss": 0.3977,
+      "step": 5400
+    },
+    {
+      "epoch": 0.4107936986507877,
+      "grad_norm": 0.12248090654611588,
+      "learning_rate": 6.382978850908226e-05,
+      "loss": 0.3969,
+      "step": 5450
+    },
+    {
+      "epoch": 0.41456244817969395,
+      "grad_norm": 0.12089215964078903,
+      "learning_rate": 6.325993450594782e-05,
+      "loss": 0.3973,
+      "step": 5500
+    },
+    {
+      "epoch": 0.4183311977086003,
+      "grad_norm": 0.13026227056980133,
+      "learning_rate": 6.26882217116406e-05,
+      "loss": 0.3959,
+      "step": 5550
+    },
+    {
+      "epoch": 0.4220999472375066,
+      "grad_norm": 0.12836764752864838,
+      "learning_rate": 6.211473026944452e-05,
+      "loss": 0.3945,
+      "step": 5600
+    },
+    {
+      "epoch": 0.4258686967664129,
+      "grad_norm": 0.12013324350118637,
+      "learning_rate": 6.153954057197612e-05,
+      "loss": 0.3955,
+      "step": 5650
+    },
+    {
+      "epoch": 0.4296374462953192,
+      "grad_norm": 0.125695139169693,
+      "learning_rate": 6.0962733249915135e-05,
+      "loss": 0.3942,
+      "step": 5700
+    },
+    {
+      "epoch": 0.4334061958242255,
+      "grad_norm": 0.12257810682058334,
+      "learning_rate": 6.038438916070155e-05,
+      "loss": 0.3953,
+      "step": 5750
+    },
+    {
+      "epoch": 0.43717494535313184,
+      "grad_norm": 0.12903869152069092,
+      "learning_rate": 5.9804589377200946e-05,
+      "loss": 0.3946,
+      "step": 5800
+    },
+    {
+      "epoch": 0.44094369488203816,
+      "grad_norm": 0.12327694892883301,
+      "learning_rate": 5.922341517633965e-05,
+      "loss": 0.3953,
+      "step": 5850
+    },
+    {
+      "epoch": 0.44471244441094443,
+      "grad_norm": 0.11745862662792206,
+      "learning_rate": 5.864094802771115e-05,
+      "loss": 0.3925,
+      "step": 5900
+    },
+    {
+      "epoch": 0.44848119393985075,
+      "grad_norm": 0.1281508505344391,
+      "learning_rate": 5.8057269582155735e-05,
+      "loss": 0.395,
+      "step": 5950
+    },
+    {
+      "epoch": 0.4522499434687571,
+      "grad_norm": 0.12625160813331604,
+      "learning_rate": 5.7472461660314504e-05,
+      "loss": 0.3928,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4560186929976634,
+      "grad_norm": 0.1253785938024521,
+      "learning_rate": 5.6886606241159714e-05,
+      "loss": 0.3915,
+      "step": 6050
+    },
+    {
+      "epoch": 0.45978744252656967,
+      "grad_norm": 0.1176779568195343,
+      "learning_rate": 5.6299785450502853e-05,
+      "loss": 0.3912,
+      "step": 6100
+    },
+    {
+      "epoch": 0.463556192055476,
+      "grad_norm": 0.1299523264169693,
+      "learning_rate": 5.571208154948218e-05,
+      "loss": 0.3916,
+      "step": 6150
+    },
+    {
+      "epoch": 0.4673249415843823,
+      "grad_norm": 0.12234111875295639,
+      "learning_rate": 5.5123576923031253e-05,
+      "loss": 0.3907,
+      "step": 6200
+    },
+    {
+      "epoch": 0.47109369111328864,
+      "grad_norm": 0.12556277215480804,
+      "learning_rate": 5.453435406833017e-05,
+      "loss": 0.3877,
+      "step": 6250
+    },
+    {
+      "epoch": 0.4748624406421949,
+      "grad_norm": 0.12356381118297577,
+      "learning_rate": 5.3944495583240987e-05,
+      "loss": 0.3922,
+      "step": 6300
+    },
+    {
+      "epoch": 0.47863119017110123,
+      "grad_norm": 0.12636062502861023,
+      "learning_rate": 5.3354084154729034e-05,
+      "loss": 0.3889,
+      "step": 6350
+    },
+    {
+      "epoch": 0.48239993970000755,
+      "grad_norm": 0.12002749741077423,
+      "learning_rate": 5.276320254727187e-05,
+      "loss": 0.3894,
+      "step": 6400
+    },
+    {
+      "epoch": 0.4861686892289138,
+      "grad_norm": 0.11866312474012375,
+      "learning_rate": 5.217193359125724e-05,
+      "loss": 0.3904,
+      "step": 6450
+    },
+    {
+      "epoch": 0.48993743875782014,
+      "grad_norm": 0.12735402584075928,
+      "learning_rate": 5.15803601713717e-05,
+      "loss": 0.3898,
+      "step": 6500
+    },
+    {
+      "epoch": 0.49370618828672647,
+      "grad_norm": 0.12688295543193817,
+      "learning_rate": 5.0988565214981976e-05,
+      "loss": 0.3875,
+      "step": 6550
+    },
+    {
+      "epoch": 0.4974749378156328,
+      "grad_norm": 0.12292376905679703,
+      "learning_rate": 5.0396631680509945e-05,
+      "loss": 0.3878,
+      "step": 6600
+    },
+    {
+      "epoch": 0.5012436873445391,
+      "grad_norm": 0.12782977521419525,
+      "learning_rate": 4.9804642545803524e-05,
+      "loss": 0.3882,
+      "step": 6650
+    },
+    {
+      "epoch": 0.5050124368734454,
+      "grad_norm": 0.12405069172382355,
+      "learning_rate": 4.9212680796504704e-05,
+      "loss": 0.387,
+      "step": 6700
+    },
+    {
+      "epoch": 0.5087811864023517,
+      "grad_norm": 0.12035728245973587,
+      "learning_rate": 4.8620829414416615e-05,
+      "loss": 0.3875,
+      "step": 6750
+    },
+    {
+      "epoch": 0.512549935931258,
+      "grad_norm": 0.12531401216983795,
+      "learning_rate": 4.8029171365870926e-05,
+      "loss": 0.3864,
+      "step": 6800
+    },
+    {
+      "epoch": 0.5163186854601644,
+      "grad_norm": 0.12338712066411972,
+      "learning_rate": 4.743778959009766e-05,
+      "loss": 0.3848,
+      "step": 6850
+    },
+    {
+      "epoch": 0.5200874349890706,
+      "grad_norm": 0.11947856098413467,
+      "learning_rate": 4.684676698759864e-05,
+      "loss": 0.385,
+      "step": 6900
+    },
+    {
+      "epoch": 0.5238561845179769,
+      "grad_norm": 0.12007743120193481,
+      "learning_rate": 4.62561864085264e-05,
+      "loss": 0.3843,
+      "step": 6950
+    },
+    {
+      "epoch": 0.5276249340468833,
+      "grad_norm": 0.1278475821018219,
+      "learning_rate": 4.566613064107015e-05,
+      "loss": 0.3853,
+      "step": 7000
+    },
+    {
+      "epoch": 0.5313936835757895,
+      "grad_norm": 0.1218569353222847,
+      "learning_rate": 4.507668239985055e-05,
+      "loss": 0.3845,
+      "step": 7050
+    },
+    {
+      "epoch": 0.5351624331046959,
+      "grad_norm": 0.11835400015115738,
+      "learning_rate": 4.448792431432451e-05,
+      "loss": 0.3859,
+      "step": 7100
+    },
+    {
+      "epoch": 0.5389311826336022,
+      "grad_norm": 0.12840606272220612,
+      "learning_rate": 4.389993891720232e-05,
+      "loss": 0.3845,
+      "step": 7150
+    },
+    {
+      "epoch": 0.5426999321625084,
+      "grad_norm": 0.13272738456726074,
+      "learning_rate": 4.3312808632877924e-05,
+      "loss": 0.3811,
+      "step": 7200
+    },
+    {
+      "epoch": 0.5464686816914148,
+      "grad_norm": 0.12915217876434326,
+      "learning_rate": 4.27266157658747e-05,
+      "loss": 0.382,
+      "step": 7250
+    },
+    {
+      "epoch": 0.5502374312203211,
+      "grad_norm": 0.12107321619987488,
+      "learning_rate": 4.214144248930797e-05,
+      "loss": 0.3826,
+      "step": 7300
+    },
+    {
+      "epoch": 0.5540061807492274,
+      "grad_norm": 0.11897026747465134,
+      "learning_rate": 4.155737083336575e-05,
+      "loss": 0.3823,
+      "step": 7350
+    },
+    {
+      "epoch": 0.5577749302781337,
+      "grad_norm": 0.12942850589752197,
+      "learning_rate": 4.097448267380979e-05,
+      "loss": 0.3832,
+      "step": 7400
+    },
+    {
+      "epoch": 0.56154367980704,
+      "grad_norm": 0.12150803208351135,
+      "learning_rate": 4.03928597204981e-05,
+      "loss": 0.3794,
+      "step": 7450
+    },
+    {
+      "epoch": 0.5653124293359464,
+      "grad_norm": 0.12691834568977356,
+      "learning_rate": 3.9812583505930786e-05,
+      "loss": 0.3823,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5690811788648527,
+      "grad_norm": 0.12072654068470001,
+      "learning_rate": 3.923373537382074e-05,
+      "loss": 0.3805,
+      "step": 7550
+    },
+    {
+      "epoch": 0.5728499283937589,
+      "grad_norm": 0.1254051923751831,
+      "learning_rate": 3.86563964676908e-05,
+      "loss": 0.3801,
+      "step": 7600
+    },
+    {
+      "epoch": 0.5766186779226653,
+      "grad_norm": 0.12295497953891754,
+      "learning_rate": 3.808064771949893e-05,
+      "loss": 0.3798,
+      "step": 7650
+    },
+    {
+      "epoch": 0.5803874274515716,
+      "grad_norm": 0.1204095408320427,
+      "learning_rate": 3.75065698382932e-05,
+      "loss": 0.3804,
+      "step": 7700
+    },
+    {
+      "epoch": 0.5841561769804778,
+      "grad_norm": 0.1274949461221695,
+      "learning_rate": 3.693424329889776e-05,
+      "loss": 0.3797,
+      "step": 7750
+    },
+    {
+      "epoch": 0.5879249265093842,
+      "grad_norm": 0.12017184495925903,
+      "learning_rate": 3.636374833063191e-05,
+      "loss": 0.3793,
+      "step": 7800
+    },
+    {
+      "epoch": 0.5916936760382905,
+      "grad_norm": 0.11911458522081375,
+      "learning_rate": 3.579516490606346e-05,
+      "loss": 0.378,
+      "step": 7850
+    },
+    {
+      "epoch": 0.5954624255671968,
+      "grad_norm": 0.12406555563211441,
+      "learning_rate": 3.522857272979804e-05,
+      "loss": 0.3772,
+      "step": 7900
+    },
+    {
+      "epoch": 0.5992311750961031,
+      "grad_norm": 0.1240847259759903,
+      "learning_rate": 3.4664051227306026e-05,
+      "loss": 0.3767,
+      "step": 7950
+    },
+    {
+      "epoch": 0.6029999246250094,
+      "grad_norm": 0.12354228645563126,
+      "learning_rate": 3.4101679533788734e-05,
+      "loss": 0.3756,
+      "step": 8000
+    },
+    {
+      "epoch": 0.6067686741539158,
+      "grad_norm": 0.12415247410535812,
+      "learning_rate": 3.354153648308492e-05,
+      "loss": 0.3758,
+      "step": 8050
+    },
+    {
+      "epoch": 0.610537423682822,
+      "grad_norm": 0.12234577536582947,
+      "learning_rate": 3.298370059662004e-05,
+      "loss": 0.376,
+      "step": 8100
+    },
+    {
+      "epoch": 0.6143061732117283,
+      "grad_norm": 0.1265120804309845,
+      "learning_rate": 3.2428250072398846e-05,
+      "loss": 0.3753,
+      "step": 8150
+    },
+    {
+      "epoch": 0.6180749227406347,
+      "grad_norm": 0.12359097599983215,
+      "learning_rate": 3.187526277404355e-05,
+      "loss": 0.3766,
+      "step": 8200
+    },
+    {
+      "epoch": 0.621843672269541,
+      "grad_norm": 0.12145058065652847,
+      "learning_rate": 3.1324816219878903e-05,
+      "loss": 0.3752,
+      "step": 8250
+    },
+    {
+      "epoch": 0.6256124217984472,
+      "grad_norm": 0.12867897748947144,
+      "learning_rate": 3.077698757206552e-05,
+      "loss": 0.3759,
+      "step": 8300
+    },
+    {
+      "epoch": 0.6293811713273536,
+      "grad_norm": 0.11933314055204391,
+      "learning_rate": 3.0231853625783163e-05,
+      "loss": 0.3737,
+      "step": 8350
+    },
+    {
+      "epoch": 0.6331499208562599,
+      "grad_norm": 0.12191013246774673,
+      "learning_rate": 2.9689490798465698e-05,
+      "loss": 0.3739,
+      "step": 8400
+    },
+    {
+      "epoch": 0.6369186703851663,
+      "grad_norm": 0.12023235857486725,
+      "learning_rate": 2.9149975119088596e-05,
+      "loss": 0.3739,
+      "step": 8450
+    },
+    {
+      "epoch": 0.6406874199140725,
+      "grad_norm": 0.1173822283744812,
+      "learning_rate": 2.8613382217511265e-05,
+      "loss": 0.3721,
+      "step": 8500
+    },
+    {
+      "epoch": 0.6444561694429788,
+      "grad_norm": 0.11978928744792938,
+      "learning_rate": 2.807978731387516e-05,
+      "loss": 0.3744,
+      "step": 8550
+    },
+    {
+      "epoch": 0.6482249189718852,
+      "grad_norm": 0.12471877038478851,
+      "learning_rate": 2.754926520805925e-05,
+      "loss": 0.3734,
+      "step": 8600
+    },
+    {
+      "epoch": 0.6519936685007914,
+      "grad_norm": 0.12483327090740204,
+      "learning_rate": 2.702189026919465e-05,
+      "loss": 0.3739,
+      "step": 8650
+    },
+    {
+      "epoch": 0.6557624180296977,
+      "grad_norm": 0.12658704817295074,
+      "learning_rate": 2.6497736425239315e-05,
+      "loss": 0.3721,
+      "step": 8700
+    },
+    {
+      "epoch": 0.6595311675586041,
+      "grad_norm": 0.12170502543449402,
+      "learning_rate": 2.597687715261484e-05,
+      "loss": 0.3725,
+      "step": 8750
+    },
+    {
+      "epoch": 0.6632999170875103,
+      "grad_norm": 0.12154766917228699,
+      "learning_rate": 2.5459385465906517e-05,
+      "loss": 0.3727,
+      "step": 8800
+    },
+    {
+      "epoch": 0.6670686666164167,
+      "grad_norm": 0.12545736134052277,
+      "learning_rate": 2.4945333907627892e-05,
+      "loss": 0.3733,
+      "step": 8850
+    },
+    {
+      "epoch": 0.670837416145323,
+      "grad_norm": 0.12335515767335892,
+      "learning_rate": 2.443479453805189e-05,
+      "loss": 0.3694,
+      "step": 8900
+    },
+    {
+      "epoch": 0.6746061656742293,
+      "grad_norm": 0.12594442069530487,
+      "learning_rate": 2.392783892510917e-05,
+      "loss": 0.3707,
+      "step": 8950
+    },
+    {
+      "epoch": 0.6783749152031356,
+      "grad_norm": 0.12440726161003113,
+      "learning_rate": 2.3424538134355715e-05,
+      "loss": 0.3718,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6821436647320419,
+      "grad_norm": 0.1183919832110405,
+      "learning_rate": 2.2924962719010874e-05,
+      "loss": 0.371,
+      "step": 9050
+    },
+    {
+      "epoch": 0.6859124142609482,
+      "grad_norm": 0.12334096431732178,
+      "learning_rate": 2.242918271006698e-05,
+      "loss": 0.371,
+      "step": 9100
+    },
+    {
+      "epoch": 0.6896811637898546,
+      "grad_norm": 0.12674276530742645,
+      "learning_rate": 2.193726760647245e-05,
+      "loss": 0.3688,
+      "step": 9150
+    },
+    {
+      "epoch": 0.6934499133187608,
+      "grad_norm": 0.1269780695438385,
+      "learning_rate": 2.1449286365389342e-05,
+      "loss": 0.3696,
+      "step": 9200
+    },
+    {
+      "epoch": 0.6972186628476671,
+      "grad_norm": 0.1259194165468216,
+      "learning_rate": 2.0965307392526818e-05,
+      "loss": 0.369,
+      "step": 9250
+    },
+    {
+      "epoch": 0.7009874123765735,
+      "grad_norm": 0.12153580784797668,
+      "learning_rate": 2.048539853255197e-05,
+      "loss": 0.3703,
+      "step": 9300
+    },
+    {
+      "epoch": 0.7047561619054797,
+      "grad_norm": 0.12010648101568222,
+      "learning_rate": 2.0009627059579372e-05,
+      "loss": 0.3705,
+      "step": 9350
+    },
+    {
+      "epoch": 0.7085249114343861,
+      "grad_norm": 0.1195657029747963,
+      "learning_rate": 1.953805966774037e-05,
+      "loss": 0.3709,
+      "step": 9400
+    },
+    {
+      "epoch": 0.7122936609632924,
+      "grad_norm": 0.1207772046327591,
+      "learning_rate": 1.9070762461834018e-05,
+      "loss": 0.3685,
+      "step": 9450
+    },
+    {
+      "epoch": 0.7160624104921987,
+      "grad_norm": 0.1287909597158432,
+      "learning_rate": 1.8607800948060266e-05,
+      "loss": 0.3677,
+      "step": 9500
+    },
+    {
+      "epoch": 0.719831160021105,
+      "grad_norm": 0.12034378945827484,
+      "learning_rate": 1.8149240024837315e-05,
+      "loss": 0.3672,
+      "step": 9550
+    },
+    {
+      "epoch": 0.7235999095500113,
+      "grad_norm": 0.12253709137439728,
+      "learning_rate": 1.7695143973704143e-05,
+      "loss": 0.3667,
+      "step": 9600
+    },
+    {
+      "epoch": 0.7273686590789176,
+      "grad_norm": 0.12438009679317474,
+      "learning_rate": 1.7245576450309316e-05,
+      "loss": 0.368,
+      "step": 9650
+    },
+    {
+      "epoch": 0.731137408607824,
+      "grad_norm": 0.12267523258924484,
+      "learning_rate": 1.6800600475487826e-05,
+      "loss": 0.3686,
+      "step": 9700
+    },
+    {
+      "epoch": 0.7349061581367302,
+      "grad_norm": 0.12052857130765915,
+      "learning_rate": 1.6360278426426624e-05,
+      "loss": 0.3671,
+      "step": 9750
+    },
+    {
+      "epoch": 0.7386749076656366,
+      "grad_norm": 0.12073458731174469,
+      "learning_rate": 1.5924672027920663e-05,
+      "loss": 0.3659,
+      "step": 9800
+    },
+    {
+      "epoch": 0.7424436571945429,
+      "grad_norm": 0.12209140509366989,
+      "learning_rate": 1.5493842343720104e-05,
+      "loss": 0.3651,
+      "step": 9850
+    },
+    {
+      "epoch": 0.7462124067234491,
+      "grad_norm": 0.12427693605422974,
+      "learning_rate": 1.5067849767970488e-05,
+      "loss": 0.365,
+      "step": 9900
+    },
+    {
+      "epoch": 0.7499811562523555,
+      "grad_norm": 0.1223672404885292,
+      "learning_rate": 1.4646754016746483e-05,
+      "loss": 0.3672,
+      "step": 9950
+    },
+    {
+      "epoch": 0.7537499057812618,
+      "grad_norm": 0.11954417079687119,
+      "learning_rate": 1.4230614119680957e-05,
+      "loss": 0.3673,
+      "step": 10000
+    },
+    {
+      "epoch": 0.757518655310168,
+      "grad_norm": 0.12223341315984726,
+      "learning_rate": 1.3819488411690018e-05,
+      "loss": 0.366,
+      "step": 10050
+    },
+    {
+      "epoch": 0.7612874048390744,
+      "grad_norm": 0.12244118750095367,
+      "learning_rate": 1.3413434524795631e-05,
+      "loss": 0.3655,
+      "step": 10100
+    },
+    {
+      "epoch": 0.7650561543679807,
+      "grad_norm": 0.1303243190050125,
+      "learning_rate": 1.3012509380046745e-05,
+      "loss": 0.3635,
+      "step": 10150
+    },
+    {
+      "epoch": 0.768824903896887,
+      "grad_norm": 0.12242712080478668,
+      "learning_rate": 1.2616769179539944e-05,
+      "loss": 0.3653,
+      "step": 10200
+    },
+    {
+      "epoch": 0.7725936534257933,
+      "grad_norm": 0.12988024950027466,
+      "learning_rate": 1.222626939854103e-05,
+      "loss": 0.3634,
+      "step": 10250
+    },
+    {
+      "epoch": 0.7763624029546996,
+      "grad_norm": 0.12370813637971878,
+      "learning_rate": 1.1841064777708483e-05,
+      "loss": 0.3648,
+      "step": 10300
+    },
+    {
+      "epoch": 0.780131152483606,
+      "grad_norm": 0.12255989760160446,
+      "learning_rate": 1.1461209315419758e-05,
+      "loss": 0.3619,
+      "step": 10350
+    },
+    {
+      "epoch": 0.7838999020125123,
+      "grad_norm": 0.1202356219291687,
+      "learning_rate": 1.1086756260201859e-05,
+      "loss": 0.3635,
+      "step": 10400
+    },
+    {
+      "epoch": 0.7876686515414185,
+      "grad_norm": 0.12302669882774353,
+      "learning_rate": 1.0717758103266805e-05,
+      "loss": 0.3637,
+      "step": 10450
+    },
+    {
+      "epoch": 0.7914374010703249,
+      "grad_norm": 0.12413894385099411,
+      "learning_rate": 1.0354266571153399e-05,
+      "loss": 0.3628,
+      "step": 10500
+    },
+    {
+      "epoch": 0.7952061505992312,
+      "grad_norm": 0.13576340675354004,
+      "learning_rate": 9.996332618476172e-06,
+      "loss": 0.3642,
+      "step": 10550
+    },
+    {
+      "epoch": 0.7989749001281374,
+      "grad_norm": 0.11875317990779877,
+      "learning_rate": 9.644006420782476e-06,
+      "loss": 0.3616,
+      "step": 10600
+    },
+    {
+      "epoch": 0.8027436496570438,
+      "grad_norm": 0.11939128488302231,
+      "learning_rate": 9.29733736751881e-06,
+      "loss": 0.3645,
+      "step": 10650
+    },
+    {
+      "epoch": 0.8065123991859501,
+      "grad_norm": 0.12436193227767944,
+      "learning_rate": 8.956374055107442e-06,
+      "loss": 0.3628,
+      "step": 10700
+    },
+    {
+      "epoch": 0.8102811487148565,
+      "grad_norm": 0.1196485161781311,
+      "learning_rate": 8.621164280134004e-06,
+      "loss": 0.3627,
+      "step": 10750
+    },
+    {
+      "epoch": 0.8140498982437627,
+      "grad_norm": 0.12489930540323257,
+      "learning_rate": 8.291755032647402e-06,
+      "loss": 0.3623,
+      "step": 10800
+    },
+    {
+      "epoch": 0.817818647772669,
+      "grad_norm": 0.123841792345047,
+      "learning_rate": 7.96819248957265e-06,
+      "loss": 0.3625,
+      "step": 10850
+    },
+    {
+      "epoch": 0.8215873973015754,
+      "grad_norm": 0.11904341727495193,
+      "learning_rate": 7.650522008237754e-06,
+      "loss": 0.3621,
+      "step": 10900
+    },
+    {
+      "epoch": 0.8253561468304816,
+      "grad_norm": 0.12214882671833038,
+      "learning_rate": 7.338788120015522e-06,
+      "loss": 0.3615,
+      "step": 10950
+    },
+    {
+      "epoch": 0.8291248963593879,
+      "grad_norm": 0.11963903903961182,
+      "learning_rate": 7.033034524081023e-06,
+      "loss": 0.3616,
+      "step": 11000
+    },
+    {
+      "epoch": 0.8328936458882943,
+      "grad_norm": 0.1206718236207962,
+      "learning_rate": 6.733304081285874e-06,
+      "loss": 0.3615,
+      "step": 11050
+    },
+    {
+      "epoch": 0.8366623954172006,
+      "grad_norm": 0.12292595952749252,
+      "learning_rate": 6.439638808149923e-06,
+      "loss": 0.3626,
+      "step": 11100
+    },
+    {
+      "epoch": 0.8404311449461069,
+      "grad_norm": 0.11864078789949417,
+      "learning_rate": 6.152079870971311e-06,
+      "loss": 0.3604,
+      "step": 11150
+    },
+    {
+      "epoch": 0.8441998944750132,
+      "grad_norm": 0.11779944598674774,
+      "learning_rate": 5.870667580055805e-06,
+      "loss": 0.362,
+      "step": 11200
+    },
+    {
+      "epoch": 0.8479686440039195,
+      "grad_norm": 0.1210256963968277,
+      "learning_rate": 5.595441384065986e-06,
+      "loss": 0.3625,
+      "step": 11250
+    },
+    {
+      "epoch": 0.8517373935328258,
+      "grad_norm": 0.11869262158870697,
+      "learning_rate": 5.3264398644913114e-06,
+      "loss": 0.3606,
+      "step": 11300
+    },
+    {
+      "epoch": 0.8555061430617321,
+      "grad_norm": 0.11657856404781342,
+      "learning_rate": 5.063700730239784e-06,
+      "loss": 0.3603,
+      "step": 11350
+    },
+    {
+      "epoch": 0.8592748925906384,
+      "grad_norm": 0.12736374139785767,
+      "learning_rate": 4.807260812351793e-06,
+      "loss": 0.3597,
+      "step": 11400
+    },
+    {
+      "epoch": 0.8630436421195448,
+      "grad_norm": 0.12483314424753189,
+      "learning_rate": 4.557156058837137e-06,
+      "loss": 0.3595,
+      "step": 11450
+    },
+    {
+      "epoch": 0.866812391648451,
+      "grad_norm": 0.12260041385889053,
+      "learning_rate": 4.31342152963583e-06,
+      "loss": 0.3605,
+      "step": 11500
+    },
+    {
+      "epoch": 0.8705811411773573,
+      "grad_norm": 0.12077975273132324,
+      "learning_rate": 4.076091391703302e-06,
+      "loss": 0.361,
+      "step": 11550
+    },
+    {
+      "epoch": 0.8743498907062637,
+      "grad_norm": 0.12066470086574554,
+      "learning_rate": 3.845198914220871e-06,
+      "loss": 0.3595,
+      "step": 11600
+    },
+    {
+      "epoch": 0.87811864023517,
+      "grad_norm": 0.11941241472959518,
+      "learning_rate": 3.6207764639320462e-06,
+      "loss": 0.3598,
+      "step": 11650
+    },
+    {
+      "epoch": 0.8818873897640763,
+      "grad_norm": 0.11988034099340439,
+      "learning_rate": 3.4028555006052953e-06,
+      "loss": 0.3623,
+      "step": 11700
+    },
+    {
+      "epoch": 0.8856561392929826,
+      "grad_norm": 0.11922150105237961,
+      "learning_rate": 3.191466572624019e-06,
+      "loss": 0.359,
+      "step": 11750
+    },
+    {
+      "epoch": 0.8894248888218889,
+      "grad_norm": 0.12553803622722626,
+      "learning_rate": 2.986639312704209e-06,
+      "loss": 0.3591,
+      "step": 11800
+    },
+    {
+      "epoch": 0.8931936383507952,
+      "grad_norm": 0.12020330131053925,
+      "learning_rate": 2.788402433740517e-06,
+      "loss": 0.3594,
+      "step": 11850
+    },
+    {
+      "epoch": 0.8969623878797015,
+      "grad_norm": 0.12430017441511154,
+      "learning_rate": 2.596783724781282e-06,
+      "loss": 0.3611,
+      "step": 11900
+    },
+    {
+      "epoch": 0.9007311374086078,
+      "grad_norm": 0.11724447458982468,
+      "learning_rate": 2.4118100471329787e-06,
+      "loss": 0.3586,
+      "step": 11950
+    },
+    {
+      "epoch": 0.9044998869375142,
+      "grad_norm": 0.12089824676513672,
+      "learning_rate": 2.2335073305948086e-06,
+      "loss": 0.3599,
+      "step": 12000
+    },
+    {
+      "epoch": 0.9082686364664204,
+      "grad_norm": 0.12007749080657959,
+      "learning_rate": 2.0619005698238437e-06,
+      "loss": 0.3596,
+      "step": 12050
+    },
+    {
+      "epoch": 0.9120373859953268,
+      "grad_norm": 0.12171461433172226,
+      "learning_rate": 1.8970138208311949e-06,
+      "loss": 0.3583,
+      "step": 12100
+    },
+    {
+      "epoch": 0.9158061355242331,
+      "grad_norm": 0.12043970823287964,
+      "learning_rate": 1.7388701976099041e-06,
+      "loss": 0.3602,
+      "step": 12150
+    },
+    {
+      "epoch": 0.9195748850531393,
+      "grad_norm": 0.11760008335113525,
+      "learning_rate": 1.5874918688946972e-06,
+      "loss": 0.3595,
+      "step": 12200
+    },
+    {
+      "epoch": 0.9233436345820457,
+      "grad_norm": 0.1200682744383812,
+      "learning_rate": 1.4429000550544414e-06,
+      "loss": 0.36,
+      "step": 12250
+    },
+    {
+      "epoch": 0.927112384110952,
+      "grad_norm": 0.11784795671701431,
+      "learning_rate": 1.305115025117387e-06,
+      "loss": 0.361,
+      "step": 12300
+    },
+    {
+      "epoch": 0.9308811336398582,
+      "grad_norm": 0.12539437413215637,
+      "learning_rate": 1.1741560939298791e-06,
+      "loss": 0.3604,
+      "step": 12350
+    },
+    {
+      "epoch": 0.9346498831687646,
+      "grad_norm": 0.11890075355768204,
+      "learning_rate": 1.0500416194487384e-06,
+      "loss": 0.3603,
+      "step": 12400
+    },
+    {
+      "epoch": 0.9384186326976709,
+      "grad_norm": 0.11838522553443909,
+      "learning_rate": 9.327890001678719e-07,
+      "loss": 0.3583,
+      "step": 12450
+    },
+    {
+      "epoch": 0.9421873822265773,
+      "grad_norm": 0.11805940419435501,
+      "learning_rate": 8.224146726792947e-07,
+      "loss": 0.3584,
+      "step": 12500
+    },
+    {
+      "epoch": 0.9459561317554835,
+      "grad_norm": 0.12155980616807938,
+      "learning_rate": 7.189341093690627e-07,
+      "loss": 0.3573,
+      "step": 12550
+    },
+    {
+      "epoch": 0.9497248812843898,
+      "grad_norm": 0.12234574556350708,
+      "learning_rate": 6.223618162483014e-07,
+      "loss": 0.3602,
+      "step": 12600
+    },
+    {
+      "epoch": 0.9534936308132962,
+      "grad_norm": 0.12211139500141144,
+      "learning_rate": 5.327113309197828e-07,
+      "loss": 0.3607,
+      "step": 12650
+    },
+    {
+      "epoch": 0.9572623803422025,
+      "grad_norm": 0.12177923321723938,
+      "learning_rate": 4.4999522068017164e-07,
+      "loss": 0.3593,
+      "step": 12700
+    },
+    {
+      "epoch": 0.9610311298711087,
+      "grad_norm": 0.12205006927251816,
+      "learning_rate": 3.7422508075835583e-07,
+      "loss": 0.3581,
+      "step": 12750
+    },
+    {
+      "epoch": 0.9647998794000151,
+      "grad_norm": 0.12369778752326965,
+      "learning_rate": 3.05411532689992e-07,
+      "loss": 0.3574,
+      "step": 12800
+    },
+    {
+      "epoch": 0.9685686289289214,
+      "grad_norm": 0.11952103674411774,
+      "learning_rate": 2.435642228285906e-07,
+      "loss": 0.3591,
+      "step": 12850
+    },
+    {
+      "epoch": 0.9723373784578276,
+      "grad_norm": 0.12717215716838837,
+      "learning_rate": 1.886918209932642e-07,
+      "loss": 0.3591,
+      "step": 12900
+    },
+    {
+      "epoch": 0.976106127986734,
+      "grad_norm": 0.11970841139554977,
+      "learning_rate": 1.4080201925338322e-07,
+      "loss": 0.359,
+      "step": 12950
+    },
+    {
+      "epoch": 0.9798748775156403,
+      "grad_norm": 0.11662206053733826,
+      "learning_rate": 9.99015308503215e-08,
+      "loss": 0.361,
+      "step": 13000
+    },
+    {
+      "epoch": 0.9836436270445467,
+      "grad_norm": 0.11980729550123215,
+      "learning_rate": 6.599608925633715e-08,
+      "loss": 0.359,
+      "step": 13050
+    },
+    {
+      "epoch": 0.9874123765734529,
+      "grad_norm": 0.11847749352455139,
+      "learning_rate": 3.909044737089307e-08,
+      "loss": 0.3599,
+      "step": 13100
+    },
+    {
+      "epoch": 0.9911811261023592,
+      "grad_norm": 0.11814071238040924,
+      "learning_rate": 1.9188376854373246e-08,
+      "loss": 0.3593,
+      "step": 13150
+    },
+    {
+      "epoch": 0.9949498756312656,
+      "grad_norm": 0.12487523257732391,
+      "learning_rate": 6.292667599366864e-09,
+      "loss": 0.3591,
+      "step": 13200
+    },
+    {
+      "epoch": 0.9987186251601718,
+      "grad_norm": 0.1255567967891693,
+      "learning_rate": 4.0512733956998837e-10,
+      "loss": 0.3566,
+      "step": 13250
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 13267,
+  "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": 1.473625900334952e+20,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4fd095d9e3347f694748ed61508e022a3136ee420ad0ba22249a8f0b30c2d2
+size 6968

zero_to_fp32.py

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