Upload folder using huggingface_hub

.gitattributes

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

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "SillyTilly/google-gemma-2-9b",
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 224,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.43.1"
+}

latest

@@ -0,0 +1 @@
+global_step252

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f350fa6b3defcd2f919510f78efe28fda444be31c14edf62e58b2f63bf8f82
+size 4903351912

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eebbd41dbb660a21d8e84e684970a01f7603773437c4037aa6f49689f28cf933
+size 4947570872

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf88768c0885a3743d4f8d0f9ee1610008a8bf61ebaafb06c499eb96501725c
+size 4962221464

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157fa5bf720f890d250ae0283690abe14d478be6fe1151aca5ae91445bc0473b
+size 3670322200

model.safetensors.index.json

@@ -0,0 +1,471 @@
+{
+  "metadata": {
+    "total_size": 18483411968
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4
+size 14512

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6
+size 14512

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ee9dc1b818089105a4bb03c8006f95800169439e149e986e49d215385b1c98
+size 1064

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
+size 17518525

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,1757 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1797 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7558488302339532,
+  "eval_steps": 500,
+  "global_step": 252,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002999400119976005,
+      "grad_norm": 12.213529318427376,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.6991,
+      "step": 1
+    },
+    {
+      "epoch": 0.00599880023995201,
+      "grad_norm": 11.149836011452198,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.5997,
+      "step": 2
+    },
+    {
+      "epoch": 0.008998200359928014,
+      "grad_norm": 5.296165512046405,
+      "learning_rate": 3e-06,
+      "loss": 1.3037,
+      "step": 3
+    },
+    {
+      "epoch": 0.01199760047990402,
+      "grad_norm": 3.7277911972297235,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.3472,
+      "step": 4
+    },
+    {
+      "epoch": 0.014997000599880024,
+      "grad_norm": 6.970291148182751,
+      "learning_rate": 5e-06,
+      "loss": 1.5234,
+      "step": 5
+    },
+    {
+      "epoch": 0.017996400719856028,
+      "grad_norm": 5.825870871741097,
+      "learning_rate": 6e-06,
+      "loss": 1.2331,
+      "step": 6
+    },
+    {
+      "epoch": 0.020995800839832032,
+      "grad_norm": 4.789226733983147,
+      "learning_rate": 7e-06,
+      "loss": 1.2847,
+      "step": 7
+    },
+    {
+      "epoch": 0.02399520095980804,
+      "grad_norm": 5.735809923380043,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3148,
+      "step": 8
+    },
+    {
+      "epoch": 0.026994601079784044,
+      "grad_norm": 4.146594143559111,
+      "learning_rate": 9e-06,
+      "loss": 1.3241,
+      "step": 9
+    },
+    {
+      "epoch": 0.029994001199760048,
+      "grad_norm": 4.3548572301609365,
+      "learning_rate": 1e-05,
+      "loss": 1.2048,
+      "step": 10
+    },
+    {
+      "epoch": 0.032993401319736056,
+      "grad_norm": 3.186860649490824,
+      "learning_rate": 9.999942663491213e-06,
+      "loss": 1.271,
+      "step": 11
+    },
+    {
+      "epoch": 0.035992801439712056,
+      "grad_norm": 5.683449148461711,
+      "learning_rate": 9.999770655279843e-06,
+      "loss": 1.4619,
+      "step": 12
+    },
+    {
+      "epoch": 0.038992201559688064,
+      "grad_norm": 2.918639590322084,
+      "learning_rate": 9.99948397931083e-06,
+      "loss": 1.2698,
+      "step": 13
+    },
+    {
+      "epoch": 0.041991601679664065,
+      "grad_norm": 3.1049642688975228,
+      "learning_rate": 9.999082642158972e-06,
+      "loss": 1.4018,
+      "step": 14
+    },
+    {
+      "epoch": 0.04499100179964007,
+      "grad_norm": 2.396816425806027,
+      "learning_rate": 9.99856665302878e-06,
+      "loss": 1.1897,
+      "step": 15
+    },
+    {
+      "epoch": 0.04799040191961608,
+      "grad_norm": 2.6334601975355283,
+      "learning_rate": 9.997936023754258e-06,
+      "loss": 1.3976,
+      "step": 16
+    },
+    {
+      "epoch": 0.05098980203959208,
+      "grad_norm": 2.619689679258694,
+      "learning_rate": 9.997190768798639e-06,
+      "loss": 1.286,
+      "step": 17
+    },
+    {
+      "epoch": 0.05398920215956809,
+      "grad_norm": 2.7084119507983377,
+      "learning_rate": 9.99633090525405e-06,
+      "loss": 1.3328,
+      "step": 18
+    },
+    {
+      "epoch": 0.05698860227954409,
+      "grad_norm": 2.3481903809919404,
+      "learning_rate": 9.995356452841122e-06,
+      "loss": 1.1662,
+      "step": 19
+    },
+    {
+      "epoch": 0.059988002399520096,
+      "grad_norm": 4.651416427067284,
+      "learning_rate": 9.994267433908533e-06,
+      "loss": 1.5033,
+      "step": 20
+    },
+    {
+      "epoch": 0.0629874025194961,
+      "grad_norm": 2.625598226472764,
+      "learning_rate": 9.9930638734325e-06,
+      "loss": 1.2022,
+      "step": 21
+    },
+    {
+      "epoch": 0.06598680263947211,
+      "grad_norm": 2.4104347021265973,
+      "learning_rate": 9.991745799016206e-06,
+      "loss": 1.1979,
+      "step": 22
+    },
+    {
+      "epoch": 0.06898620275944811,
+      "grad_norm": 3.1305838351835478,
+      "learning_rate": 9.990313240889167e-06,
+      "loss": 1.3105,
+      "step": 23
+    },
+    {
+      "epoch": 0.07198560287942411,
+      "grad_norm": 3.18309366674778,
+      "learning_rate": 9.988766231906532e-06,
+      "loss": 1.3079,
+      "step": 24
+    },
+    {
+      "epoch": 0.07498500299940011,
+      "grad_norm": 3.5781057246328563,
+      "learning_rate": 9.987104807548341e-06,
+      "loss": 1.3255,
+      "step": 25
+    },
+    {
+      "epoch": 0.07798440311937613,
+      "grad_norm": 2.259604288692876,
+      "learning_rate": 9.985329005918702e-06,
+      "loss": 1.242,
+      "step": 26
+    },
+    {
+      "epoch": 0.08098380323935213,
+      "grad_norm": 5.16511455231151,
+      "learning_rate": 9.983438867744923e-06,
+      "loss": 1.5295,
+      "step": 27
+    },
+    {
+      "epoch": 0.08398320335932813,
+      "grad_norm": 2.5507458276752955,
+      "learning_rate": 9.981434436376572e-06,
+      "loss": 1.1835,
+      "step": 28
+    },
+    {
+      "epoch": 0.08698260347930414,
+      "grad_norm": 2.374301337319529,
+      "learning_rate": 9.97931575778449e-06,
+      "loss": 1.2602,
+      "step": 29
+    },
+    {
+      "epoch": 0.08998200359928014,
+      "grad_norm": 2.869182508074545,
+      "learning_rate": 9.977082880559725e-06,
+      "loss": 1.2714,
+      "step": 30
+    },
+    {
+      "epoch": 0.09298140371925614,
+      "grad_norm": 3.352349678924823,
+      "learning_rate": 9.974735855912436e-06,
+      "loss": 1.2895,
+      "step": 31
+    },
+    {
+      "epoch": 0.09598080383923216,
+      "grad_norm": 2.402498887438619,
+      "learning_rate": 9.972274737670702e-06,
+      "loss": 1.2169,
+      "step": 32
+    },
+    {
+      "epoch": 0.09898020395920816,
+      "grad_norm": 2.3026043458108356,
+      "learning_rate": 9.969699582279294e-06,
+      "loss": 1.2486,
+      "step": 33
+    },
+    {
+      "epoch": 0.10197960407918416,
+      "grad_norm": 2.7234482697971796,
+      "learning_rate": 9.967010448798376e-06,
+      "loss": 1.3611,
+      "step": 34
+    },
+    {
+      "epoch": 0.10497900419916016,
+      "grad_norm": 2.3328312481588096,
+      "learning_rate": 9.964207398902163e-06,
+      "loss": 1.2112,
+      "step": 35
+    },
+    {
+      "epoch": 0.10797840431913618,
+      "grad_norm": 2.3738667556158304,
+      "learning_rate": 9.961290496877492e-06,
+      "loss": 1.1489,
+      "step": 36
+    },
+    {
+      "epoch": 0.11097780443911218,
+      "grad_norm": 2.381064080119671,
+      "learning_rate": 9.958259809622353e-06,
+      "loss": 1.3426,
+      "step": 37
+    },
+    {
+      "epoch": 0.11397720455908818,
+      "grad_norm": 2.789399877084244,
+      "learning_rate": 9.955115406644357e-06,
+      "loss": 1.2355,
+      "step": 38
+    },
+    {
+      "epoch": 0.11697660467906419,
+      "grad_norm": 2.2360091447066885,
+      "learning_rate": 9.951857360059141e-06,
+      "loss": 1.298,
+      "step": 39
+    },
+    {
+      "epoch": 0.11997600479904019,
+      "grad_norm": 2.3420608415672644,
+      "learning_rate": 9.948485744588709e-06,
+      "loss": 1.2597,
+      "step": 40
+    },
+    {
+      "epoch": 0.12297540491901619,
+      "grad_norm": 2.0514216630297786,
+      "learning_rate": 9.945000637559728e-06,
+      "loss": 1.2464,
+      "step": 41
+    },
+    {
+      "epoch": 0.1259748050389922,
+      "grad_norm": 2.1083906964286765,
+      "learning_rate": 9.941402118901743e-06,
+      "loss": 1.2223,
+      "step": 42
+    },
+    {
+      "epoch": 0.1289742051589682,
+      "grad_norm": 2.584585224378793,
+      "learning_rate": 9.937690271145356e-06,
+      "loss": 1.2575,
+      "step": 43
+    },
+    {
+      "epoch": 0.13197360527894422,
+      "grad_norm": 2.3779090684986652,
+      "learning_rate": 9.93386517942032e-06,
+      "loss": 1.1451,
+      "step": 44
+    },
+    {
+      "epoch": 0.1349730053989202,
+      "grad_norm": 2.108339055225494,
+      "learning_rate": 9.9299269314536e-06,
+      "loss": 1.2248,
+      "step": 45
+    },
+    {
+      "epoch": 0.13797240551889622,
+      "grad_norm": 2.121719885374642,
+      "learning_rate": 9.92587561756735e-06,
+      "loss": 1.207,
+      "step": 46
+    },
+    {
+      "epoch": 0.14097180563887224,
+      "grad_norm": 2.205771486341789,
+      "learning_rate": 9.921711330676848e-06,
+      "loss": 1.2321,
+      "step": 47
+    },
+    {
+      "epoch": 0.14397120575884823,
+      "grad_norm": 2.288650968193418,
+      "learning_rate": 9.917434166288364e-06,
+      "loss": 1.244,
+      "step": 48
+    },
+    {
+      "epoch": 0.14697060587882424,
+      "grad_norm": 2.3703349873199917,
+      "learning_rate": 9.913044222496966e-06,
+      "loss": 1.2758,
+      "step": 49
+    },
+    {
+      "epoch": 0.14997000599880023,
+      "grad_norm": 2.342816783402187,
+      "learning_rate": 9.908541599984276e-06,
+      "loss": 1.2799,
+      "step": 50
+    },
+    {
+      "epoch": 0.15296940611877624,
+      "grad_norm": 2.290011867632185,
+      "learning_rate": 9.903926402016153e-06,
+      "loss": 1.137,
+      "step": 51
+    },
+    {
+      "epoch": 0.15596880623875226,
+      "grad_norm": 2.2455094517388825,
+      "learning_rate": 9.899198734440335e-06,
+      "loss": 1.2133,
+      "step": 52
+    },
+    {
+      "epoch": 0.15896820635872824,
+      "grad_norm": 2.263487895355519,
+      "learning_rate": 9.894358705684002e-06,
+      "loss": 1.1898,
+      "step": 53
+    },
+    {
+      "epoch": 0.16196760647870426,
+      "grad_norm": 2.094119128560065,
+      "learning_rate": 9.889406426751296e-06,
+      "loss": 1.1847,
+      "step": 54
+    },
+    {
+      "epoch": 0.16496700659868027,
+      "grad_norm": 2.45640150031141,
+      "learning_rate": 9.88434201122077e-06,
+      "loss": 1.2662,
+      "step": 55
+    },
+    {
+      "epoch": 0.16796640671865626,
+      "grad_norm": 3.7462847341409606,
+      "learning_rate": 9.879165575242788e-06,
+      "loss": 1.1912,
+      "step": 56
+    },
+    {
+      "epoch": 0.17096580683863227,
+      "grad_norm": 2.382097038596032,
+      "learning_rate": 9.873877237536854e-06,
+      "loss": 1.2652,
+      "step": 57
+    },
+    {
+      "epoch": 0.1739652069586083,
+      "grad_norm": 2.320080713494513,
+      "learning_rate": 9.868477119388897e-06,
+      "loss": 1.2682,
+      "step": 58
+    },
+    {
+      "epoch": 0.17696460707858427,
+      "grad_norm": 2.1974546622057938,
+      "learning_rate": 9.862965344648485e-06,
+      "loss": 1.1956,
+      "step": 59
+    },
+    {
+      "epoch": 0.1799640071985603,
+      "grad_norm": 2.40241845961337,
+      "learning_rate": 9.85734203972599e-06,
+      "loss": 1.2948,
+      "step": 60
+    },
+    {
+      "epoch": 0.1829634073185363,
+      "grad_norm": 2.1855343450625053,
+      "learning_rate": 9.851607333589677e-06,
+      "loss": 1.1967,
+      "step": 61
+    },
+    {
+      "epoch": 0.1859628074385123,
+      "grad_norm": 2.772912562685191,
+      "learning_rate": 9.84576135776276e-06,
+      "loss": 1.1864,
+      "step": 62
+    },
+    {
+      "epoch": 0.1889622075584883,
+      "grad_norm": 2.420057020746961,
+      "learning_rate": 9.839804246320374e-06,
+      "loss": 1.2534,
+      "step": 63
+    },
+    {
+      "epoch": 0.19196160767846432,
+      "grad_norm": 2.265555099135192,
+      "learning_rate": 9.833736135886513e-06,
+      "loss": 1.2563,
+      "step": 64
+    },
+    {
+      "epoch": 0.1949610077984403,
+      "grad_norm": 2.292076182842636,
+      "learning_rate": 9.827557165630879e-06,
+      "loss": 1.193,
+      "step": 65
+    },
+    {
+      "epoch": 0.19796040791841632,
+      "grad_norm": 2.032874490713336,
+      "learning_rate": 9.821267477265705e-06,
+      "loss": 1.231,
+      "step": 66
+    },
+    {
+      "epoch": 0.20095980803839233,
+      "grad_norm": 2.1341683347971543,
+      "learning_rate": 9.814867215042503e-06,
+      "loss": 1.2317,
+      "step": 67
+    },
+    {
+      "epoch": 0.20395920815836832,
+      "grad_norm": 2.2463443930345077,
+      "learning_rate": 9.808356525748748e-06,
+      "loss": 1.2911,
+      "step": 68
+    },
+    {
+      "epoch": 0.20695860827834434,
+      "grad_norm": 2.0325804061530848,
+      "learning_rate": 9.801735558704516e-06,
+      "loss": 1.254,
+      "step": 69
+    },
+    {
+      "epoch": 0.20995800839832032,
+      "grad_norm": 2.0568500164008086,
+      "learning_rate": 9.795004465759067e-06,
+      "loss": 1.206,
+      "step": 70
+    },
+    {
+      "epoch": 0.21295740851829634,
+      "grad_norm": 2.082577302356669,
+      "learning_rate": 9.78816340128734e-06,
+      "loss": 1.2027,
+      "step": 71
+    },
+    {
+      "epoch": 0.21595680863827235,
+      "grad_norm": 2.048998263808703,
+      "learning_rate": 9.781212522186442e-06,
+      "loss": 1.2288,
+      "step": 72
+    },
+    {
+      "epoch": 0.21895620875824834,
+      "grad_norm": 2.49581568276726,
+      "learning_rate": 9.774151987872029e-06,
+      "loss": 1.2493,
+      "step": 73
+    },
+    {
+      "epoch": 0.22195560887822435,
+      "grad_norm": 1.8323511888260988,
+      "learning_rate": 9.766981960274653e-06,
+      "loss": 1.2133,
+      "step": 74
+    },
+    {
+      "epoch": 0.22495500899820037,
+      "grad_norm": 1.9244897973012691,
+      "learning_rate": 9.759702603836059e-06,
+      "loss": 1.1556,
+      "step": 75
+    },
+    {
+      "epoch": 0.22795440911817635,
+      "grad_norm": 2.2391757657702476,
+      "learning_rate": 9.752314085505396e-06,
+      "loss": 1.139,
+      "step": 76
+    },
+    {
+      "epoch": 0.23095380923815237,
+      "grad_norm": 2.1062513435343955,
+      "learning_rate": 9.744816574735405e-06,
+      "loss": 1.1568,
+      "step": 77
+    },
+    {
+      "epoch": 0.23395320935812838,
+      "grad_norm": 2.244216493001031,
+      "learning_rate": 9.737210243478522e-06,
+      "loss": 1.1672,
+      "step": 78
+    },
+    {
+      "epoch": 0.23695260947810437,
+      "grad_norm": 2.2301876958310585,
+      "learning_rate": 9.72949526618294e-06,
+      "loss": 1.1805,
+      "step": 79
+    },
+    {
+      "epoch": 0.23995200959808038,
+      "grad_norm": 2.087760281351449,
+      "learning_rate": 9.721671819788603e-06,
+      "loss": 1.2595,
+      "step": 80
+    },
+    {
+      "epoch": 0.2429514097180564,
+      "grad_norm": 2.040923837775886,
+      "learning_rate": 9.713740083723152e-06,
+      "loss": 1.1853,
+      "step": 81
+    },
+    {
+      "epoch": 0.24595080983803239,
+      "grad_norm": 1.9835044903865013,
+      "learning_rate": 9.705700239897809e-06,
+      "loss": 1.1165,
+      "step": 82
+    },
+    {
+      "epoch": 0.2489502099580084,
+      "grad_norm": 2.4048211037733433,
+      "learning_rate": 9.697552472703205e-06,
+      "loss": 1.2442,
+      "step": 83
+    },
+    {
+      "epoch": 0.2519496100779844,
+      "grad_norm": 1.9274434259225983,
+      "learning_rate": 9.689296969005151e-06,
+      "loss": 1.2233,
+      "step": 84
+    },
+    {
+      "epoch": 0.2549490101979604,
+      "grad_norm": 2.0930221605237813,
+      "learning_rate": 9.680933918140348e-06,
+      "loss": 1.2042,
+      "step": 85
+    },
+    {
+      "epoch": 0.2579484103179364,
+      "grad_norm": 2.050947291358715,
+      "learning_rate": 9.672463511912056e-06,
+      "loss": 1.1526,
+      "step": 86
+    },
+    {
+      "epoch": 0.26094781043791243,
+      "grad_norm": 2.1905662044973218,
+      "learning_rate": 9.66388594458568e-06,
+      "loss": 1.2428,
+      "step": 87
+    },
+    {
+      "epoch": 0.26394721055788845,
+      "grad_norm": 2.194939852549527,
+      "learning_rate": 9.655201412884328e-06,
+      "loss": 1.1842,
+      "step": 88
+    },
+    {
+      "epoch": 0.2669466106778644,
+      "grad_norm": 1.9191574847419615,
+      "learning_rate": 9.64641011598429e-06,
+      "loss": 1.2005,
+      "step": 89
+    },
+    {
+      "epoch": 0.2699460107978404,
+      "grad_norm": 2.0406272846772597,
+      "learning_rate": 9.637512255510475e-06,
+      "loss": 1.1275,
+      "step": 90
+    },
+    {
+      "epoch": 0.27294541091781643,
+      "grad_norm": 1.9546291627174466,
+      "learning_rate": 9.628508035531785e-06,
+      "loss": 1.2274,
+      "step": 91
+    },
+    {
+      "epoch": 0.27594481103779245,
+      "grad_norm": 1.9691367121837948,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 1.207,
+      "step": 92
+    },
+    {
+      "epoch": 0.27894421115776846,
+      "grad_norm": 2.3613406410056323,
+      "learning_rate": 9.610181345527217e-06,
+      "loss": 1.2273,
+      "step": 93
+    },
+    {
+      "epoch": 0.2819436112777445,
+      "grad_norm": 1.869890124546451,
+      "learning_rate": 9.600859295816708e-06,
+      "loss": 1.2272,
+      "step": 94
+    },
+    {
+      "epoch": 0.28494301139772044,
+      "grad_norm": 2.1493924596390834,
+      "learning_rate": 9.591431727222425e-06,
+      "loss": 1.1787,
+      "step": 95
+    },
+    {
+      "epoch": 0.28794241151769645,
+      "grad_norm": 2.055643425325773,
+      "learning_rate": 9.581898855961911e-06,
+      "loss": 1.1993,
+      "step": 96
+    },
+    {
+      "epoch": 0.29094181163767247,
+      "grad_norm": 1.84642386683885,
+      "learning_rate": 9.572260900667794e-06,
+      "loss": 1.1839,
+      "step": 97
+    },
+    {
+      "epoch": 0.2939412117576485,
+      "grad_norm": 1.890951805519698,
+      "learning_rate": 9.562518082382751e-06,
+      "loss": 1.207,
+      "step": 98
+    },
+    {
+      "epoch": 0.2969406118776245,
+      "grad_norm": 2.37835708136971,
+      "learning_rate": 9.55267062455446e-06,
+      "loss": 1.1894,
+      "step": 99
+    },
+    {
+      "epoch": 0.29994001199760045,
+      "grad_norm": 1.9298763701114428,
+      "learning_rate": 9.542718753030463e-06,
+      "loss": 1.17,
+      "step": 100
+    },
+    {
+      "epoch": 0.30293941211757647,
+      "grad_norm": 1.9738559838328023,
+      "learning_rate": 9.532662696052986e-06,
+      "loss": 1.1911,
+      "step": 101
+    },
+    {
+      "epoch": 0.3059388122375525,
+      "grad_norm": 2.097481526316711,
+      "learning_rate": 9.522502684253709e-06,
+      "loss": 1.2047,
+      "step": 102
+    },
+    {
+      "epoch": 0.3089382123575285,
+      "grad_norm": 2.2773066391553405,
+      "learning_rate": 9.512238950648474e-06,
+      "loss": 1.1683,
+      "step": 103
+    },
+    {
+      "epoch": 0.3119376124775045,
+      "grad_norm": 2.0545409984803435,
+      "learning_rate": 9.501871730631944e-06,
+      "loss": 1.1777,
+      "step": 104
+    },
+    {
+      "epoch": 0.3149370125974805,
+      "grad_norm": 2.0765643204952435,
+      "learning_rate": 9.491401261972194e-06,
+      "loss": 1.2306,
+      "step": 105
+    },
+    {
+      "epoch": 0.3179364127174565,
+      "grad_norm": 1.9891174989072355,
+      "learning_rate": 9.480827784805278e-06,
+      "loss": 1.2351,
+      "step": 106
+    },
+    {
+      "epoch": 0.3209358128374325,
+      "grad_norm": 1.889574475483626,
+      "learning_rate": 9.4701515416297e-06,
+      "loss": 1.1742,
+      "step": 107
+    },
+    {
+      "epoch": 0.3239352129574085,
+      "grad_norm": 2.0131114525216955,
+      "learning_rate": 9.459372777300863e-06,
+      "loss": 1.127,
+      "step": 108
+    },
+    {
+      "epoch": 0.32693461307738453,
+      "grad_norm": 2.0094971545889506,
+      "learning_rate": 9.448491739025455e-06,
+      "loss": 1.1203,
+      "step": 109
+    },
+    {
+      "epoch": 0.32993401319736054,
+      "grad_norm": 2.007024349964355,
+      "learning_rate": 9.437508676355774e-06,
+      "loss": 1.2005,
+      "step": 110
+    },
+    {
+      "epoch": 0.33293341331733656,
+      "grad_norm": 1.834949376512209,
+      "learning_rate": 9.426423841184007e-06,
+      "loss": 1.1451,
+      "step": 111
+    },
+    {
+      "epoch": 0.3359328134373125,
+      "grad_norm": 2.0659739662077863,
+      "learning_rate": 9.415237487736452e-06,
+      "loss": 1.1978,
+      "step": 112
+    },
+    {
+      "epoch": 0.33893221355728853,
+      "grad_norm": 2.0021385422334714,
+      "learning_rate": 9.403949872567696e-06,
+      "loss": 1.1969,
+      "step": 113
+    },
+    {
+      "epoch": 0.34193161367726455,
+      "grad_norm": 2.131713368907865,
+      "learning_rate": 9.392561254554712e-06,
+      "loss": 1.0958,
+      "step": 114
+    },
+    {
+      "epoch": 0.34493101379724056,
+      "grad_norm": 2.009265355301516,
+      "learning_rate": 9.381071894890942e-06,
+      "loss": 1.2154,
+      "step": 115
+    },
+    {
+      "epoch": 0.3479304139172166,
+      "grad_norm": 1.9134985847126271,
+      "learning_rate": 9.369482057080293e-06,
+      "loss": 1.2242,
+      "step": 116
+    },
+    {
+      "epoch": 0.3509298140371926,
+      "grad_norm": 1.9567206999616176,
+      "learning_rate": 9.3577920069311e-06,
+      "loss": 1.172,
+      "step": 117
+    },
+    {
+      "epoch": 0.35392921415716855,
+      "grad_norm": 1.9433526958741427,
+      "learning_rate": 9.346002012550027e-06,
+      "loss": 1.1785,
+      "step": 118
+    },
+    {
+      "epoch": 0.35692861427714456,
+      "grad_norm": 3.7758127026886776,
+      "learning_rate": 9.334112344335924e-06,
+      "loss": 1.2509,
+      "step": 119
+    },
+    {
+      "epoch": 0.3599280143971206,
+      "grad_norm": 2.2288097190307754,
+      "learning_rate": 9.322123274973613e-06,
+      "loss": 1.2034,
+      "step": 120
+    },
+    {
+      "epoch": 0.3629274145170966,
+      "grad_norm": 2.210018938006893,
+      "learning_rate": 9.310035079427651e-06,
+      "loss": 1.2089,
+      "step": 121
+    },
+    {
+      "epoch": 0.3659268146370726,
+      "grad_norm": 1.8381206653711355,
+      "learning_rate": 9.297848034936007e-06,
+      "loss": 1.186,
+      "step": 122
+    },
+    {
+      "epoch": 0.36892621475704857,
+      "grad_norm": 2.1078020542808913,
+      "learning_rate": 9.285562421003716e-06,
+      "loss": 1.2042,
+      "step": 123
+    },
+    {
+      "epoch": 0.3719256148770246,
+      "grad_norm": 2.2181514311801496,
+      "learning_rate": 9.273178519396459e-06,
+      "loss": 1.1561,
+      "step": 124
+    },
+    {
+      "epoch": 0.3749250149970006,
+      "grad_norm": 2.127427295141141,
+      "learning_rate": 9.260696614134115e-06,
+      "loss": 1.1935,
+      "step": 125
+    },
+    {
+      "epoch": 0.3779244151169766,
+      "grad_norm": 2.179542019285163,
+      "learning_rate": 9.24811699148423e-06,
+      "loss": 1.2001,
+      "step": 126
+    },
+    {
+      "epoch": 0.3809238152369526,
+      "grad_norm": 2.95737675688332,
+      "learning_rate": 9.235439939955458e-06,
+      "loss": 1.1333,
+      "step": 127
+    },
+    {
+      "epoch": 0.38392321535692864,
+      "grad_norm": 2.408346714267433,
+      "learning_rate": 9.222665750290953e-06,
+      "loss": 1.2035,
+      "step": 128
+    },
+    {
+      "epoch": 0.3869226154769046,
+      "grad_norm": 1.9803537052769442,
+      "learning_rate": 9.209794715461691e-06,
+      "loss": 1.2133,
+      "step": 129
+    },
+    {
+      "epoch": 0.3899220155968806,
+      "grad_norm": 2.0753391828539844,
+      "learning_rate": 9.196827130659752e-06,
+      "loss": 1.2389,
+      "step": 130
+    },
+    {
+      "epoch": 0.3929214157168566,
+      "grad_norm": 2.057624573882372,
+      "learning_rate": 9.18376329329155e-06,
+      "loss": 1.1612,
+      "step": 131
+    },
+    {
+      "epoch": 0.39592081583683264,
+      "grad_norm": 2.095421490379302,
+      "learning_rate": 9.170603502971017e-06,
+      "loss": 1.2319,
+      "step": 132
+    },
+    {
+      "epoch": 0.39892021595680865,
+      "grad_norm": 1.9629007266889844,
+      "learning_rate": 9.157348061512728e-06,
+      "loss": 1.2061,
+      "step": 133
+    },
+    {
+      "epoch": 0.40191961607678467,
+      "grad_norm": 1.9702164374790287,
+      "learning_rate": 9.143997272924974e-06,
+      "loss": 1.197,
+      "step": 134
+    },
+    {
+      "epoch": 0.40491901619676063,
+      "grad_norm": 2.094524351597277,
+      "learning_rate": 9.1305514434028e-06,
+      "loss": 1.1508,
+      "step": 135
+    },
+    {
+      "epoch": 0.40791841631673664,
+      "grad_norm": 2.078336809149187,
+      "learning_rate": 9.117010881320973e-06,
+      "loss": 1.2006,
+      "step": 136
+    },
+    {
+      "epoch": 0.41091781643671266,
+      "grad_norm": 2.1047922013296385,
+      "learning_rate": 9.103375897226919e-06,
+      "loss": 1.2225,
+      "step": 137
+    },
+    {
+      "epoch": 0.41391721655668867,
+      "grad_norm": 1.9800892010976672,
+      "learning_rate": 9.089646803833589e-06,
+      "loss": 1.2117,
+      "step": 138
+    },
+    {
+      "epoch": 0.4169166166766647,
+      "grad_norm": 1.948925596250933,
+      "learning_rate": 9.075823916012298e-06,
+      "loss": 1.1917,
+      "step": 139
+    },
+    {
+      "epoch": 0.41991601679664065,
+      "grad_norm": 1.8720535653109143,
+      "learning_rate": 9.061907550785498e-06,
+      "loss": 1.2048,
+      "step": 140
+    },
+    {
+      "epoch": 0.42291541691661666,
+      "grad_norm": 2.1914812005829316,
+      "learning_rate": 9.047898027319508e-06,
+      "loss": 1.2393,
+      "step": 141
+    },
+    {
+      "epoch": 0.4259148170365927,
+      "grad_norm": 3.541065061637063,
+      "learning_rate": 9.033795666917191e-06,
+      "loss": 1.1728,
+      "step": 142
+    },
+    {
+      "epoch": 0.4289142171565687,
+      "grad_norm": 1.958943800312053,
+      "learning_rate": 9.019600793010596e-06,
+      "loss": 1.1204,
+      "step": 143
+    },
+    {
+      "epoch": 0.4319136172765447,
+      "grad_norm": 1.8982949525316917,
+      "learning_rate": 9.005313731153525e-06,
+      "loss": 1.136,
+      "step": 144
+    },
+    {
+      "epoch": 0.4349130173965207,
+      "grad_norm": 2.1962092793560775,
+      "learning_rate": 8.990934809014079e-06,
+      "loss": 1.2025,
+      "step": 145
+    },
+    {
+      "epoch": 0.4379124175164967,
+      "grad_norm": 2.148888648427292,
+      "learning_rate": 8.976464356367133e-06,
+      "loss": 1.1971,
+      "step": 146
+    },
+    {
+      "epoch": 0.4409118176364727,
+      "grad_norm": 2.1656007482087243,
+      "learning_rate": 8.961902705086785e-06,
+      "loss": 1.1531,
+      "step": 147
+    },
+    {
+      "epoch": 0.4439112177564487,
+      "grad_norm": 2.245423572348511,
+      "learning_rate": 8.947250189138732e-06,
+      "loss": 1.205,
+      "step": 148
+    },
+    {
+      "epoch": 0.4469106178764247,
+      "grad_norm": 2.2015971794373037,
+      "learning_rate": 8.932507144572616e-06,
+      "loss": 1.1663,
+      "step": 149
+    },
+    {
+      "epoch": 0.44991001799640074,
+      "grad_norm": 2.040881991969036,
+      "learning_rate": 8.917673909514321e-06,
+      "loss": 1.2318,
+      "step": 150
+    },
+    {
+      "epoch": 0.45290941811637675,
+      "grad_norm": 2.0365534777961884,
+      "learning_rate": 8.902750824158213e-06,
+      "loss": 1.1634,
+      "step": 151
+    },
+    {
+      "epoch": 0.4559088182363527,
+      "grad_norm": 2.0931596144968903,
+      "learning_rate": 8.887738230759334e-06,
+      "loss": 1.1547,
+      "step": 152
+    },
+    {
+      "epoch": 0.4589082183563287,
+      "grad_norm": 2.040316251155918,
+      "learning_rate": 8.872636473625564e-06,
+      "loss": 1.1948,
+      "step": 153
+    },
+    {
+      "epoch": 0.46190761847630474,
+      "grad_norm": 2.0411032824079514,
+      "learning_rate": 8.857445899109716e-06,
+      "loss": 1.1292,
+      "step": 154
+    },
+    {
+      "epoch": 0.46490701859628075,
+      "grad_norm": 2.9762584994335923,
+      "learning_rate": 8.84216685560159e-06,
+      "loss": 1.1308,
+      "step": 155
+    },
+    {
+      "epoch": 0.46790641871625677,
+      "grad_norm": 2.097668580242586,
+      "learning_rate": 8.826799693519996e-06,
+      "loss": 1.1631,
+      "step": 156
+    },
+    {
+      "epoch": 0.4709058188362327,
+      "grad_norm": 2.0737253370280384,
+      "learning_rate": 8.811344765304698e-06,
+      "loss": 1.1484,
+      "step": 157
+    },
+    {
+      "epoch": 0.47390521895620874,
+      "grad_norm": 2.1733316818144033,
+      "learning_rate": 8.795802425408352e-06,
+      "loss": 1.1992,
+      "step": 158
+    },
+    {
+      "epoch": 0.47690461907618475,
+      "grad_norm": 3.0100700234706927,
+      "learning_rate": 8.780173030288359e-06,
+      "loss": 1.2115,
+      "step": 159
+    },
+    {
+      "epoch": 0.47990401919616077,
+      "grad_norm": 2.0471682767814374,
+      "learning_rate": 8.7644569383987e-06,
+      "loss": 1.2007,
+      "step": 160
+    },
+    {
+      "epoch": 0.4829034193161368,
+      "grad_norm": 2.069677080263759,
+      "learning_rate": 8.748654510181709e-06,
+      "loss": 1.1719,
+      "step": 161
+    },
+    {
+      "epoch": 0.4859028194361128,
+      "grad_norm": 2.136133148960194,
+      "learning_rate": 8.732766108059814e-06,
+      "loss": 1.1097,
+      "step": 162
+    },
+    {
+      "epoch": 0.48890221955608876,
+      "grad_norm": 2.2078781415683704,
+      "learning_rate": 8.716792096427217e-06,
+      "loss": 1.2822,
+      "step": 163
+    },
+    {
+      "epoch": 0.49190161967606477,
+      "grad_norm": 1.8108893344256605,
+      "learning_rate": 8.700732841641542e-06,
+      "loss": 1.1984,
+      "step": 164
+    },
+    {
+      "epoch": 0.4949010197960408,
+      "grad_norm": 1.9202600268802827,
+      "learning_rate": 8.68458871201543e-06,
+      "loss": 1.1822,
+      "step": 165
+    },
+    {
+      "epoch": 0.4979004199160168,
+      "grad_norm": 2.043987291062948,
+      "learning_rate": 8.668360077808093e-06,
+      "loss": 1.1588,
+      "step": 166
+    },
+    {
+      "epoch": 0.5008998200359928,
+      "grad_norm": 1.8608294617929213,
+      "learning_rate": 8.652047311216823e-06,
+      "loss": 1.1739,
+      "step": 167
+    },
+    {
+      "epoch": 0.5038992201559688,
+      "grad_norm": 2.0614264560161812,
+      "learning_rate": 8.635650786368452e-06,
+      "loss": 1.2053,
+      "step": 168
+    },
+    {
+      "epoch": 0.5068986202759448,
+      "grad_norm": 1.8415134777925706,
+      "learning_rate": 8.61917087931078e-06,
+      "loss": 1.1629,
+      "step": 169
+    },
+    {
+      "epoch": 0.5098980203959208,
+      "grad_norm": 2.067056790142203,
+      "learning_rate": 8.602607968003935e-06,
+      "loss": 1.1656,
+      "step": 170
+    },
+    {
+      "epoch": 0.5128974205158968,
+      "grad_norm": 1.9885496712381465,
+      "learning_rate": 8.585962432311728e-06,
+      "loss": 1.1061,
+      "step": 171
+    },
+    {
+      "epoch": 0.5158968206358728,
+      "grad_norm": 1.8542146492076237,
+      "learning_rate": 8.569234653992916e-06,
+      "loss": 1.2416,
+      "step": 172
+    },
+    {
+      "epoch": 0.5188962207558488,
+      "grad_norm": 2.2130247278463453,
+      "learning_rate": 8.552425016692464e-06,
+      "loss": 1.2651,
+      "step": 173
+    },
+    {
+      "epoch": 0.5218956208758249,
+      "grad_norm": 1.9214372548459986,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 1.2038,
+      "step": 174
+    },
+    {
+      "epoch": 0.5248950209958009,
+      "grad_norm": 1.8202998106553783,
+      "learning_rate": 8.518561709104667e-06,
+      "loss": 1.1806,
+      "step": 175
+    },
+    {
+      "epoch": 0.5278944211157769,
+      "grad_norm": 2.033480383542316,
+      "learning_rate": 8.501508815458856e-06,
+      "loss": 1.1138,
+      "step": 176
+    },
+    {
+      "epoch": 0.5308938212357528,
+      "grad_norm": 1.8173739641856819,
+      "learning_rate": 8.484375616096658e-06,
+      "loss": 1.0463,
+      "step": 177
+    },
+    {
+      "epoch": 0.5338932213557288,
+      "grad_norm": 1.9159018093250713,
+      "learning_rate": 8.467162503961209e-06,
+      "loss": 1.1438,
+      "step": 178
+    },
+    {
+      "epoch": 0.5368926214757048,
+      "grad_norm": 2.0146669190076416,
+      "learning_rate": 8.449869873828411e-06,
+      "loss": 1.2241,
+      "step": 179
+    },
+    {
+      "epoch": 0.5398920215956808,
+      "grad_norm": 2.07880204207024,
+      "learning_rate": 8.432498122297879e-06,
+      "loss": 1.2059,
+      "step": 180
+    },
+    {
+      "epoch": 0.5428914217156569,
+      "grad_norm": 2.1530579237214593,
+      "learning_rate": 8.415047647783847e-06,
+      "loss": 1.1945,
+      "step": 181
+    },
+    {
+      "epoch": 0.5458908218356329,
+      "grad_norm": 1.9176382821131852,
+      "learning_rate": 8.39751885050603e-06,
+      "loss": 1.2025,
+      "step": 182
+    },
+    {
+      "epoch": 0.5488902219556089,
+      "grad_norm": 2.032474526366641,
+      "learning_rate": 8.379912132480441e-06,
+      "loss": 1.1962,
+      "step": 183
+    },
+    {
+      "epoch": 0.5518896220755849,
+      "grad_norm": 2.454514968342902,
+      "learning_rate": 8.36222789751018e-06,
+      "loss": 1.2075,
+      "step": 184
+    },
+    {
+      "epoch": 0.5548890221955609,
+      "grad_norm": 2.033627242661126,
+      "learning_rate": 8.344466551176163e-06,
+      "loss": 1.2134,
+      "step": 185
+    },
+    {
+      "epoch": 0.5578884223155369,
+      "grad_norm": 2.0441091460883585,
+      "learning_rate": 8.326628500827826e-06,
+      "loss": 1.2038,
+      "step": 186
+    },
+    {
+      "epoch": 0.5608878224355129,
+      "grad_norm": 1.9807070431779146,
+      "learning_rate": 8.308714155573785e-06,
+      "loss": 1.12,
+      "step": 187
+    },
+    {
+      "epoch": 0.563887222555489,
+      "grad_norm": 1.9349184602121337,
+      "learning_rate": 8.290723926272439e-06,
+      "loss": 1.1802,
+      "step": 188
+    },
+    {
+      "epoch": 0.5668866226754649,
+      "grad_norm": 1.8384106015909107,
+      "learning_rate": 8.27265822552257e-06,
+      "loss": 1.1826,
+      "step": 189
+    },
+    {
+      "epoch": 0.5698860227954409,
+      "grad_norm": 1.9156655051619718,
+      "learning_rate": 8.254517467653858e-06,
+      "loss": 1.1257,
+      "step": 190
+    },
+    {
+      "epoch": 0.5728854229154169,
+      "grad_norm": 2.1724786856863973,
+      "learning_rate": 8.236302068717393e-06,
+      "loss": 1.1839,
+      "step": 191
+    },
+    {
+      "epoch": 0.5758848230353929,
+      "grad_norm": 1.8396024645135292,
+      "learning_rate": 8.218012446476128e-06,
+      "loss": 1.16,
+      "step": 192
+    },
+    {
+      "epoch": 0.5788842231553689,
+      "grad_norm": 1.9408487099445306,
+      "learning_rate": 8.199649020395299e-06,
+      "loss": 1.2241,
+      "step": 193
+    },
+    {
+      "epoch": 0.5818836232753449,
+      "grad_norm": 1.9108055995475,
+      "learning_rate": 8.1812122116328e-06,
+      "loss": 1.164,
+      "step": 194
+    },
+    {
+      "epoch": 0.584883023395321,
+      "grad_norm": 2.098400399811293,
+      "learning_rate": 8.16270244302953e-06,
+      "loss": 1.1549,
+      "step": 195
+    },
+    {
+      "epoch": 0.587882423515297,
+      "grad_norm": 2.1600698972560015,
+      "learning_rate": 8.144120139099697e-06,
+      "loss": 1.2257,
+      "step": 196
+    },
+    {
+      "epoch": 0.590881823635273,
+      "grad_norm": 2.4157151117755826,
+      "learning_rate": 8.125465726021068e-06,
+      "loss": 1.2377,
+      "step": 197
+    },
+    {
+      "epoch": 0.593881223755249,
+      "grad_norm": 2.0852805021246246,
+      "learning_rate": 8.106739631625216e-06,
+      "loss": 1.2469,
+      "step": 198
+    },
+    {
+      "epoch": 0.596880623875225,
+      "grad_norm": 1.9748280355919685,
+      "learning_rate": 8.08794228538769e-06,
+      "loss": 1.1286,
+      "step": 199
+    },
+    {
+      "epoch": 0.5998800239952009,
+      "grad_norm": 1.9281839006734618,
+      "learning_rate": 8.06907411841817e-06,
+      "loss": 1.1319,
+      "step": 200
+    },
+    {
+      "epoch": 0.6028794241151769,
+      "grad_norm": 1.8690571721258256,
+      "learning_rate": 8.050135563450587e-06,
+      "loss": 1.1856,
+      "step": 201
+    },
+    {
+      "epoch": 0.6058788242351529,
+      "grad_norm": 1.9748712035222622,
+      "learning_rate": 8.031127054833192e-06,
+      "loss": 1.1948,
+      "step": 202
+    },
+    {
+      "epoch": 0.608878224355129,
+      "grad_norm": 1.991151818988732,
+      "learning_rate": 8.01204902851859e-06,
+      "loss": 1.1659,
+      "step": 203
+    },
+    {
+      "epoch": 0.611877624475105,
+      "grad_norm": 2.958946009978542,
+      "learning_rate": 7.992901922053751e-06,
+      "loss": 1.1856,
+      "step": 204
+    },
+    {
+      "epoch": 0.614877024595081,
+      "grad_norm": 2.065918241043226,
+      "learning_rate": 7.973686174569971e-06,
+      "loss": 1.0692,
+      "step": 205
+    },
+    {
+      "epoch": 0.617876424715057,
+      "grad_norm": 2.123952469982477,
+      "learning_rate": 7.954402226772804e-06,
+      "loss": 1.1462,
+      "step": 206
+    },
+    {
+      "epoch": 0.620875824835033,
+      "grad_norm": 2.384554268129999,
+      "learning_rate": 7.93505052093194e-06,
+      "loss": 1.2331,
+      "step": 207
+    },
+    {
+      "epoch": 0.623875224955009,
+      "grad_norm": 2.213816272262928,
+      "learning_rate": 7.915631500871084e-06,
+      "loss": 1.2179,
+      "step": 208
+    },
+    {
+      "epoch": 0.626874625074985,
+      "grad_norm": 2.041537464539173,
+      "learning_rate": 7.896145611957759e-06,
+      "loss": 1.1869,
+      "step": 209
+    },
+    {
+      "epoch": 0.629874025194961,
+      "grad_norm": 1.9032099687526678,
+      "learning_rate": 7.876593301093104e-06,
+      "loss": 1.1041,
+      "step": 210
+    },
+    {
+      "epoch": 0.6328734253149371,
+      "grad_norm": 2.0485786710751452,
+      "learning_rate": 7.856975016701616e-06,
+      "loss": 1.2018,
+      "step": 211
+    },
+    {
+      "epoch": 0.635872825434913,
+      "grad_norm": 1.985579363766555,
+      "learning_rate": 7.837291208720867e-06,
+      "loss": 1.2284,
+      "step": 212
+    },
+    {
+      "epoch": 0.638872225554889,
+      "grad_norm": 1.8372693078207498,
+      "learning_rate": 7.81754232859119e-06,
+      "loss": 1.2194,
+      "step": 213
+    },
+    {
+      "epoch": 0.641871625674865,
+      "grad_norm": 2.034191799766837,
+      "learning_rate": 7.797728829245321e-06,
+      "loss": 1.2119,
+      "step": 214
+    },
+    {
+      "epoch": 0.644871025794841,
+      "grad_norm": 2.172768388345461,
+      "learning_rate": 7.777851165098012e-06,
+      "loss": 1.2264,
+      "step": 215
+    },
+    {
+      "epoch": 0.647870425914817,
+      "grad_norm": 2.036813209788241,
+      "learning_rate": 7.757909792035608e-06,
+      "loss": 1.2233,
+      "step": 216
+    },
+    {
+      "epoch": 0.650869826034793,
+      "grad_norm": 1.7687192297667345,
+      "learning_rate": 7.737905167405596e-06,
+      "loss": 1.2008,
+      "step": 217
+    },
+    {
+      "epoch": 0.6538692261547691,
+      "grad_norm": 1.9034513819160714,
+      "learning_rate": 7.717837750006106e-06,
+      "loss": 1.2116,
+      "step": 218
+    },
+    {
+      "epoch": 0.6568686262747451,
+      "grad_norm": 1.896055349909721,
+      "learning_rate": 7.697708000075404e-06,
+      "loss": 1.0943,
+      "step": 219
+    },
+    {
+      "epoch": 0.6598680263947211,
+      "grad_norm": 2.01228606334524,
+      "learning_rate": 7.67751637928132e-06,
+      "loss": 1.1236,
+      "step": 220
+    },
+    {
+      "epoch": 0.6628674265146971,
+      "grad_norm": 2.156992216970816,
+      "learning_rate": 7.657263350710676e-06,
+      "loss": 1.1291,
+      "step": 221
+    },
+    {
+      "epoch": 0.6658668266346731,
+      "grad_norm": 1.9699773673672667,
+      "learning_rate": 7.636949378858647e-06,
+      "loss": 1.1458,
+      "step": 222
+    },
+    {
+      "epoch": 0.668866226754649,
+      "grad_norm": 2.1989186993052754,
+      "learning_rate": 7.616574929618126e-06,
+      "loss": 1.1121,
+      "step": 223
+    },
+    {
+      "epoch": 0.671865626874625,
+      "grad_norm": 1.993731506914194,
+      "learning_rate": 7.596140470269029e-06,
+      "loss": 1.0735,
+      "step": 224
+    },
+    {
+      "epoch": 0.674865026994601,
+      "grad_norm": 1.8252968956264437,
+      "learning_rate": 7.575646469467576e-06,
+      "loss": 1.149,
+      "step": 225
+    },
+    {
+      "epoch": 0.6778644271145771,
+      "grad_norm": 2.055158428727496,
+      "learning_rate": 7.555093397235553e-06,
+      "loss": 1.154,
+      "step": 226
+    },
+    {
+      "epoch": 0.6808638272345531,
+      "grad_norm": 1.9915560854905294,
+      "learning_rate": 7.5344817249495195e-06,
+      "loss": 1.0942,
+      "step": 227
+    },
+    {
+      "epoch": 0.6838632273545291,
+      "grad_norm": 2.06764585971135,
+      "learning_rate": 7.51381192533001e-06,
+      "loss": 1.1884,
+      "step": 228
+    },
+    {
+      "epoch": 0.6868626274745051,
+      "grad_norm": 1.9341247237628625,
+      "learning_rate": 7.493084472430683e-06,
+      "loss": 1.1791,
+      "step": 229
+    },
+    {
+      "epoch": 0.6898620275944811,
+      "grad_norm": 1.9931838011874805,
+      "learning_rate": 7.472299841627452e-06,
+      "loss": 1.1299,
+      "step": 230
+    },
+    {
+      "epoch": 0.6928614277144571,
+      "grad_norm": 1.9296797551564173,
+      "learning_rate": 7.451458509607583e-06,
+      "loss": 1.1513,
+      "step": 231
+    },
+    {
+      "epoch": 0.6958608278344331,
+      "grad_norm": 2.0306426071035544,
+      "learning_rate": 7.430560954358764e-06,
+      "loss": 1.1837,
+      "step": 232
+    },
+    {
+      "epoch": 0.6988602279544092,
+      "grad_norm": 1.8564265209276956,
+      "learning_rate": 7.409607655158139e-06,
+      "loss": 1.2164,
+      "step": 233
+    },
+    {
+      "epoch": 0.7018596280743852,
+      "grad_norm": 2.2341388452646727,
+      "learning_rate": 7.388599092561315e-06,
+      "loss": 1.1252,
+      "step": 234
+    },
+    {
+      "epoch": 0.7048590281943611,
+      "grad_norm": 2.1161776966895496,
+      "learning_rate": 7.367535748391349e-06,
+      "loss": 1.213,
+      "step": 235
+    },
+    {
+      "epoch": 0.7078584283143371,
+      "grad_norm": 1.9243533852197758,
+      "learning_rate": 7.3464181057276864e-06,
+      "loss": 1.1046,
+      "step": 236
+    },
+    {
+      "epoch": 0.7108578284343131,
+      "grad_norm": 1.9237683937108236,
+      "learning_rate": 7.325246648895089e-06,
+      "loss": 1.1577,
+      "step": 237
+    },
+    {
+      "epoch": 0.7138572285542891,
+      "grad_norm": 1.7984916602185241,
+      "learning_rate": 7.304021863452525e-06,
+      "loss": 1.2052,
+      "step": 238
+    },
+    {
+      "epoch": 0.7168566286742651,
+      "grad_norm": 1.8721994512639362,
+      "learning_rate": 7.282744236182033e-06,
+      "loss": 1.1676,
+      "step": 239
+    },
+    {
+      "epoch": 0.7198560287942412,
+      "grad_norm": 1.8334072031704922,
+      "learning_rate": 7.261414255077561e-06,
+      "loss": 1.1118,
+      "step": 240
+    },
+    {
+      "epoch": 0.7228554289142172,
+      "grad_norm": 2.2489377670615474,
+      "learning_rate": 7.240032409333765e-06,
+      "loss": 1.1682,
+      "step": 241
+    },
+    {
+      "epoch": 0.7258548290341932,
+      "grad_norm": 1.8400363638367707,
+      "learning_rate": 7.218599189334799e-06,
+      "loss": 1.1638,
+      "step": 242
+    },
+    {
+      "epoch": 0.7288542291541692,
+      "grad_norm": 1.8851878635905157,
+      "learning_rate": 7.197115086643069e-06,
+      "loss": 1.1176,
+      "step": 243
+    },
+    {
+      "epoch": 0.7318536292741452,
+      "grad_norm": 1.8023550249649072,
+      "learning_rate": 7.175580593987952e-06,
+      "loss": 1.1164,
+      "step": 244
+    },
+    {
+      "epoch": 0.7348530293941212,
+      "grad_norm": 2.694191659057711,
+      "learning_rate": 7.153996205254495e-06,
+      "loss": 1.1573,
+      "step": 245
+    },
+    {
+      "epoch": 0.7378524295140971,
+      "grad_norm": 1.964255695607597,
+      "learning_rate": 7.132362415472099e-06,
+      "loss": 1.0549,
+      "step": 246
+    },
+    {
+      "epoch": 0.7408518296340731,
+      "grad_norm": 1.8017763616156734,
+      "learning_rate": 7.1106797208031554e-06,
+      "loss": 1.1446,
+      "step": 247
+    },
+    {
+      "epoch": 0.7438512297540492,
+      "grad_norm": 1.9428097126313124,
+      "learning_rate": 7.088948618531668e-06,
+      "loss": 1.1081,
+      "step": 248
+    },
+    {
+      "epoch": 0.7468506298740252,
+      "grad_norm": 2.002394147288212,
+      "learning_rate": 7.067169607051851e-06,
+      "loss": 1.1359,
+      "step": 249
+    },
+    {
+      "epoch": 0.7498500299940012,
+      "grad_norm": 1.8198961995762413,
+      "learning_rate": 7.045343185856701e-06,
+      "loss": 1.1201,
+      "step": 250
+    },
+    {
+      "epoch": 0.7528494301139772,
+      "grad_norm": 1.9151331196894974,
+      "learning_rate": 7.02346985552653e-06,
+      "loss": 1.0402,
+      "step": 251
+    },
+    {
+      "epoch": 0.7558488302339532,
+      "grad_norm": 1.9384378002461773,
+      "learning_rate": 7.001550117717499e-06,
+      "loss": 1.175,
+      "step": 252
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 666,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 84,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 139507934232576.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494d572b90754ea162ceb159834dd59cfa64e2eb57bebdab5361db5946a343ef
+size 7992

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, 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 param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               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_file, 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_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--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_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)