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 +1,35 @@
+{
+  "_name_or_path": "estrogen/gemma-2-9b-it-cursed",
+  "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": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 8192,
+  "sliding_window_size": 8192,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": 1,
+  "max_length": 8192,
+  "pad_token_id": 0,
+  "transformers_version": "4.50.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d349b3f04926ebafe2147e2a60c9475a2741bddbf2ff230d989fbd9b7cf2011a
+size 4903351912

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fedf2e6948d8d4d28d97dd2060dc442edf73382f245f3d1084e7d8ab894f95c5
+size 4947570872

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9fa8656c245aa69f92d9df791c37c82bb8e6cdf3ce9182c1817c17a17d8a0e
+size 4962221464

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686594cb61a3d43e47372222d71b80bdb1319596adb2e4ba19c297e21a427bfe
+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"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7e89b071d9631ff2553b0050e0706ec3ea8e9ed483cb7781395072270d7d80
+size 936

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d6966334ba1ebaeb72dd015982a95b52b2ef38525c7c4e860e91dafbdf8d59
+size 1000

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 sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,2015 @@
+{
+  "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
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "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 }}{% for message in messages %}\n{%- if message['role'] == 'system' %}\n{{- '<start_of_turn>system\n' + message['content'] + '<end_of_turn>\n' }}\n{%- elif message['role'] == 'user' %}\n{{- '<start_of_turn>user\n' + message['content'] + '<end_of_turn>\n' }}\n{%- elif message['role'] == 'assistant' %}\n{{- '<start_of_turn>model\n' + message['content'] + '<end_of_turn>\n' }}\n{%- endif %}\n{%- endfor %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2399 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 338,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029585798816568047,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 2.3867,
+      "step": 1
+    },
+    {
+      "epoch": 0.005917159763313609,
+      "grad_norm": 0.0,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 2.2471,
+      "step": 2
+    },
+    {
+      "epoch": 0.008875739644970414,
+      "grad_norm": 0.0,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.2662,
+      "step": 3
+    },
+    {
+      "epoch": 0.011834319526627219,
+      "grad_norm": 0.0,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 2.3544,
+      "step": 4
+    },
+    {
+      "epoch": 0.014792899408284023,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.2586,
+      "step": 5
+    },
+    {
+      "epoch": 0.01775147928994083,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 2.3907,
+      "step": 6
+    },
+    {
+      "epoch": 0.020710059171597635,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 2.3655,
+      "step": 7
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 2.0928,
+      "step": 8
+    },
+    {
+      "epoch": 0.026627218934911243,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 2.0631,
+      "step": 9
+    },
+    {
+      "epoch": 0.029585798816568046,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.0782,
+      "step": 10
+    },
+    {
+      "epoch": 0.03254437869822485,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2e-06,
+      "loss": 2.1475,
+      "step": 11
+    },
+    {
+      "epoch": 0.03550295857988166,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 2.2993,
+      "step": 12
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6e-06,
+      "loss": 2.2898,
+      "step": 13
+    },
+    {
+      "epoch": 0.04142011834319527,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 2.174,
+      "step": 14
+    },
+    {
+      "epoch": 0.04437869822485207,
+      "grad_norm": 0.0,
+      "learning_rate": 3e-06,
+      "loss": 2.1127,
+      "step": 15
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "grad_norm": 0.0,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 2.175,
+      "step": 16
+    },
+    {
+      "epoch": 0.05029585798816568,
+      "grad_norm": 0.0,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 2.1672,
+      "step": 17
+    },
+    {
+      "epoch": 0.05325443786982249,
+      "grad_norm": 0.0,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.9976,
+      "step": 18
+    },
+    {
+      "epoch": 0.05621301775147929,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 2.0976,
+      "step": 19
+    },
+    {
+      "epoch": 0.05917159763313609,
+      "grad_norm": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.1695,
+      "step": 20
+    },
+    {
+      "epoch": 0.0621301775147929,
+      "grad_norm": 0.0,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 2.1697,
+      "step": 21
+    },
+    {
+      "epoch": 0.0650887573964497,
+      "grad_norm": 0.0,
+      "learning_rate": 4.4e-06,
+      "loss": 1.9651,
+      "step": 22
+    },
+    {
+      "epoch": 0.06804733727810651,
+      "grad_norm": 0.0,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 2.1625,
+      "step": 23
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 0.0,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.8718,
+      "step": 24
+    },
+    {
+      "epoch": 0.07396449704142012,
+      "grad_norm": 0.0,
+      "learning_rate": 5e-06,
+      "loss": 1.9899,
+      "step": 25
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.0,
+      "learning_rate": 5.2e-06,
+      "loss": 2.0724,
+      "step": 26
+    },
+    {
+      "epoch": 0.07988165680473373,
+      "grad_norm": 0.0,
+      "learning_rate": 5.400000000000001e-06,
+      "loss": 2.0547,
+      "step": 27
+    },
+    {
+      "epoch": 0.08284023668639054,
+      "grad_norm": 0.0,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 2.2418,
+      "step": 28
+    },
+    {
+      "epoch": 0.08579881656804733,
+      "grad_norm": 0.0,
+      "learning_rate": 5.8e-06,
+      "loss": 2.0636,
+      "step": 29
+    },
+    {
+      "epoch": 0.08875739644970414,
+      "grad_norm": 0.0,
+      "learning_rate": 6e-06,
+      "loss": 2.0891,
+      "step": 30
+    },
+    {
+      "epoch": 0.09171597633136094,
+      "grad_norm": 0.0,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 2.0278,
+      "step": 31
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "grad_norm": 0.0,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 1.9477,
+      "step": 32
+    },
+    {
+      "epoch": 0.09763313609467456,
+      "grad_norm": 0.0,
+      "learning_rate": 6.600000000000001e-06,
+      "loss": 1.8948,
+      "step": 33
+    },
+    {
+      "epoch": 0.10059171597633136,
+      "grad_norm": 0.0,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 2.2138,
+      "step": 34
+    },
+    {
+      "epoch": 0.10355029585798817,
+      "grad_norm": 0.0,
+      "learning_rate": 7e-06,
+      "loss": 2.145,
+      "step": 35
+    },
+    {
+      "epoch": 0.10650887573964497,
+      "grad_norm": 0.0,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 1.9846,
+      "step": 36
+    },
+    {
+      "epoch": 0.10946745562130178,
+      "grad_norm": 0.0,
+      "learning_rate": 7.4e-06,
+      "loss": 2.0312,
+      "step": 37
+    },
+    {
+      "epoch": 0.11242603550295859,
+      "grad_norm": 0.0,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 1.8683,
+      "step": 38
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 0.0,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 2.1375,
+      "step": 39
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "grad_norm": 0.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.1697,
+      "step": 40
+    },
+    {
+      "epoch": 0.12130177514792899,
+      "grad_norm": 0.0,
+      "learning_rate": 8.2e-06,
+      "loss": 2.1194,
+      "step": 41
+    },
+    {
+      "epoch": 0.1242603550295858,
+      "grad_norm": 0.0,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 2.1117,
+      "step": 42
+    },
+    {
+      "epoch": 0.12721893491124261,
+      "grad_norm": 0.0,
+      "learning_rate": 8.6e-06,
+      "loss": 2.1602,
+      "step": 43
+    },
+    {
+      "epoch": 0.1301775147928994,
+      "grad_norm": 0.0,
+      "learning_rate": 8.8e-06,
+      "loss": 2.1266,
+      "step": 44
+    },
+    {
+      "epoch": 0.13313609467455623,
+      "grad_norm": 0.0,
+      "learning_rate": 9e-06,
+      "loss": 2.0014,
+      "step": 45
+    },
+    {
+      "epoch": 0.13609467455621302,
+      "grad_norm": 0.0,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 2.2091,
+      "step": 46
+    },
+    {
+      "epoch": 0.1390532544378698,
+      "grad_norm": 0.0,
+      "learning_rate": 9.4e-06,
+      "loss": 2.1576,
+      "step": 47
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "grad_norm": 0.0,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.9604,
+      "step": 48
+    },
+    {
+      "epoch": 0.14497041420118342,
+      "grad_norm": 0.0,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.9441,
+      "step": 49
+    },
+    {
+      "epoch": 0.14792899408284024,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-05,
+      "loss": 2.2556,
+      "step": 50
+    },
+    {
+      "epoch": 0.15088757396449703,
+      "grad_norm": 0.0,
+      "learning_rate": 9.999937036309402e-06,
+      "loss": 1.8544,
+      "step": 51
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.0,
+      "learning_rate": 9.999748146823376e-06,
+      "loss": 1.993,
+      "step": 52
+    },
+    {
+      "epoch": 0.15680473372781065,
+      "grad_norm": 0.0,
+      "learning_rate": 9.999433336299195e-06,
+      "loss": 1.9912,
+      "step": 53
+    },
+    {
+      "epoch": 0.15976331360946747,
+      "grad_norm": 0.0,
+      "learning_rate": 9.99899261266551e-06,
+      "loss": 1.9475,
+      "step": 54
+    },
+    {
+      "epoch": 0.16272189349112426,
+      "grad_norm": 0.0,
+      "learning_rate": 9.99842598702216e-06,
+      "loss": 1.8537,
+      "step": 55
+    },
+    {
+      "epoch": 0.16568047337278108,
+      "grad_norm": 0.0,
+      "learning_rate": 9.997733473639876e-06,
+      "loss": 1.9285,
+      "step": 56
+    },
+    {
+      "epoch": 0.16863905325443787,
+      "grad_norm": 0.0,
+      "learning_rate": 9.996915089959942e-06,
+      "loss": 2.1754,
+      "step": 57
+    },
+    {
+      "epoch": 0.17159763313609466,
+      "grad_norm": 0.0,
+      "learning_rate": 9.995970856593739e-06,
+      "loss": 2.0349,
+      "step": 58
+    },
+    {
+      "epoch": 0.17455621301775148,
+      "grad_norm": 0.0,
+      "learning_rate": 9.994900797322233e-06,
+      "loss": 2.0156,
+      "step": 59
+    },
+    {
+      "epoch": 0.17751479289940827,
+      "grad_norm": 0.0,
+      "learning_rate": 9.993704939095376e-06,
+      "loss": 1.9629,
+      "step": 60
+    },
+    {
+      "epoch": 0.1804733727810651,
+      "grad_norm": 0.0,
+      "learning_rate": 9.99238331203143e-06,
+      "loss": 2.0124,
+      "step": 61
+    },
+    {
+      "epoch": 0.1834319526627219,
+      "grad_norm": 0.0,
+      "learning_rate": 9.9909359494162e-06,
+      "loss": 1.9907,
+      "step": 62
+    },
+    {
+      "epoch": 0.1863905325443787,
+      "grad_norm": 0.0,
+      "learning_rate": 9.989362887702203e-06,
+      "loss": 1.9201,
+      "step": 63
+    },
+    {
+      "epoch": 0.1893491124260355,
+      "grad_norm": 0.0,
+      "learning_rate": 9.987664166507749e-06,
+      "loss": 2.0519,
+      "step": 64
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 0.0,
+      "learning_rate": 9.985839828615937e-06,
+      "loss": 1.8084,
+      "step": 65
+    },
+    {
+      "epoch": 0.1952662721893491,
+      "grad_norm": 0.0,
+      "learning_rate": 9.983889919973586e-06,
+      "loss": 1.6792,
+      "step": 66
+    },
+    {
+      "epoch": 0.19822485207100593,
+      "grad_norm": 0.0,
+      "learning_rate": 9.981814489690077e-06,
+      "loss": 2.1584,
+      "step": 67
+    },
+    {
+      "epoch": 0.20118343195266272,
+      "grad_norm": 0.0,
+      "learning_rate": 9.979613590036108e-06,
+      "loss": 2.1141,
+      "step": 68
+    },
+    {
+      "epoch": 0.20414201183431951,
+      "grad_norm": 0.0,
+      "learning_rate": 9.977287276442385e-06,
+      "loss": 2.1541,
+      "step": 69
+    },
+    {
+      "epoch": 0.20710059171597633,
+      "grad_norm": 0.0,
+      "learning_rate": 9.974835607498224e-06,
+      "loss": 2.3373,
+      "step": 70
+    },
+    {
+      "epoch": 0.21005917159763313,
+      "grad_norm": 0.0,
+      "learning_rate": 9.972258644950074e-06,
+      "loss": 2.1491,
+      "step": 71
+    },
+    {
+      "epoch": 0.21301775147928995,
+      "grad_norm": 0.0,
+      "learning_rate": 9.969556453699966e-06,
+      "loss": 2.1541,
+      "step": 72
+    },
+    {
+      "epoch": 0.21597633136094674,
+      "grad_norm": 0.0,
+      "learning_rate": 9.966729101803872e-06,
+      "loss": 2.2422,
+      "step": 73
+    },
+    {
+      "epoch": 0.21893491124260356,
+      "grad_norm": 0.0,
+      "learning_rate": 9.963776660469996e-06,
+      "loss": 2.1639,
+      "step": 74
+    },
+    {
+      "epoch": 0.22189349112426035,
+      "grad_norm": 0.0,
+      "learning_rate": 9.960699204056978e-06,
+      "loss": 1.8449,
+      "step": 75
+    },
+    {
+      "epoch": 0.22485207100591717,
+      "grad_norm": 0.0,
+      "learning_rate": 9.957496810072027e-06,
+      "loss": 2.0897,
+      "step": 76
+    },
+    {
+      "epoch": 0.22781065088757396,
+      "grad_norm": 0.0,
+      "learning_rate": 9.954169559168958e-06,
+      "loss": 1.9484,
+      "step": 77
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.0,
+      "learning_rate": 9.95071753514617e-06,
+      "loss": 2.0419,
+      "step": 78
+    },
+    {
+      "epoch": 0.23372781065088757,
+      "grad_norm": 0.0,
+      "learning_rate": 9.947140824944533e-06,
+      "loss": 1.8759,
+      "step": 79
+    },
+    {
+      "epoch": 0.23668639053254437,
+      "grad_norm": 0.0,
+      "learning_rate": 9.943439518645193e-06,
+      "loss": 2.1681,
+      "step": 80
+    },
+    {
+      "epoch": 0.23964497041420119,
+      "grad_norm": 0.0,
+      "learning_rate": 9.939613709467317e-06,
+      "loss": 1.8824,
+      "step": 81
+    },
+    {
+      "epoch": 0.24260355029585798,
+      "grad_norm": 0.0,
+      "learning_rate": 9.935663493765726e-06,
+      "loss": 1.971,
+      "step": 82
+    },
+    {
+      "epoch": 0.2455621301775148,
+      "grad_norm": 0.0,
+      "learning_rate": 9.93158897102849e-06,
+      "loss": 2.076,
+      "step": 83
+    },
+    {
+      "epoch": 0.2485207100591716,
+      "grad_norm": 0.0,
+      "learning_rate": 9.9273902438744e-06,
+      "loss": 2.1269,
+      "step": 84
+    },
+    {
+      "epoch": 0.2514792899408284,
+      "grad_norm": 0.0,
+      "learning_rate": 9.923067418050399e-06,
+      "loss": 1.8968,
+      "step": 85
+    },
+    {
+      "epoch": 0.25443786982248523,
+      "grad_norm": 0.0,
+      "learning_rate": 9.918620602428916e-06,
+      "loss": 2.0881,
+      "step": 86
+    },
+    {
+      "epoch": 0.257396449704142,
+      "grad_norm": 0.0,
+      "learning_rate": 9.91404990900512e-06,
+      "loss": 2.0064,
+      "step": 87
+    },
+    {
+      "epoch": 0.2603550295857988,
+      "grad_norm": 0.0,
+      "learning_rate": 9.909355452894098e-06,
+      "loss": 1.7917,
+      "step": 88
+    },
+    {
+      "epoch": 0.26331360946745563,
+      "grad_norm": 0.0,
+      "learning_rate": 9.904537352327968e-06,
+      "loss": 2.1953,
+      "step": 89
+    },
+    {
+      "epoch": 0.26627218934911245,
+      "grad_norm": 0.0,
+      "learning_rate": 9.899595728652883e-06,
+      "loss": 2.2008,
+      "step": 90
+    },
+    {
+      "epoch": 0.2692307692307692,
+      "grad_norm": 0.0,
+      "learning_rate": 9.894530706325994e-06,
+      "loss": 2.1582,
+      "step": 91
+    },
+    {
+      "epoch": 0.27218934911242604,
+      "grad_norm": 0.0,
+      "learning_rate": 9.889342412912296e-06,
+      "loss": 1.9303,
+      "step": 92
+    },
+    {
+      "epoch": 0.27514792899408286,
+      "grad_norm": 0.0,
+      "learning_rate": 9.88403097908143e-06,
+      "loss": 1.8805,
+      "step": 93
+    },
+    {
+      "epoch": 0.2781065088757396,
+      "grad_norm": 0.0,
+      "learning_rate": 9.878596538604388e-06,
+      "loss": 2.0595,
+      "step": 94
+    },
+    {
+      "epoch": 0.28106508875739644,
+      "grad_norm": 0.0,
+      "learning_rate": 9.87303922835014e-06,
+      "loss": 2.0986,
+      "step": 95
+    },
+    {
+      "epoch": 0.28402366863905326,
+      "grad_norm": 0.0,
+      "learning_rate": 9.867359188282193e-06,
+      "loss": 2.0202,
+      "step": 96
+    },
+    {
+      "epoch": 0.2869822485207101,
+      "grad_norm": 0.0,
+      "learning_rate": 9.861556561455061e-06,
+      "loss": 2.1159,
+      "step": 97
+    },
+    {
+      "epoch": 0.28994082840236685,
+      "grad_norm": 0.0,
+      "learning_rate": 9.855631494010661e-06,
+      "loss": 2.163,
+      "step": 98
+    },
+    {
+      "epoch": 0.29289940828402367,
+      "grad_norm": 0.0,
+      "learning_rate": 9.849584135174642e-06,
+      "loss": 1.992,
+      "step": 99
+    },
+    {
+      "epoch": 0.2958579881656805,
+      "grad_norm": 0.0,
+      "learning_rate": 9.843414637252615e-06,
+      "loss": 2.1032,
+      "step": 100
+    },
+    {
+      "epoch": 0.2988165680473373,
+      "grad_norm": 0.0,
+      "learning_rate": 9.837123155626323e-06,
+      "loss": 1.9705,
+      "step": 101
+    },
+    {
+      "epoch": 0.30177514792899407,
+      "grad_norm": 0.0,
+      "learning_rate": 9.830709848749727e-06,
+      "loss": 1.9496,
+      "step": 102
+    },
+    {
+      "epoch": 0.3047337278106509,
+      "grad_norm": 0.0,
+      "learning_rate": 9.824174878145017e-06,
+      "loss": 1.9727,
+      "step": 103
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 9.817518408398536e-06,
+      "loss": 2.0889,
+      "step": 104
+    },
+    {
+      "epoch": 0.3106508875739645,
+      "grad_norm": 0.0,
+      "learning_rate": 9.810740607156647e-06,
+      "loss": 1.9065,
+      "step": 105
+    },
+    {
+      "epoch": 0.3136094674556213,
+      "grad_norm": 0.0,
+      "learning_rate": 9.803841645121505e-06,
+      "loss": 1.8313,
+      "step": 106
+    },
+    {
+      "epoch": 0.3165680473372781,
+      "grad_norm": 0.0,
+      "learning_rate": 9.796821696046748e-06,
+      "loss": 1.8081,
+      "step": 107
+    },
+    {
+      "epoch": 0.31952662721893493,
+      "grad_norm": 0.0,
+      "learning_rate": 9.78968093673314e-06,
+      "loss": 1.8999,
+      "step": 108
+    },
+    {
+      "epoch": 0.3224852071005917,
+      "grad_norm": 0.0,
+      "learning_rate": 9.782419547024108e-06,
+      "loss": 1.932,
+      "step": 109
+    },
+    {
+      "epoch": 0.3254437869822485,
+      "grad_norm": 0.0,
+      "learning_rate": 9.775037709801206e-06,
+      "loss": 2.0389,
+      "step": 110
+    },
+    {
+      "epoch": 0.32840236686390534,
+      "grad_norm": 0.0,
+      "learning_rate": 9.76753561097952e-06,
+      "loss": 2.1882,
+      "step": 111
+    },
+    {
+      "epoch": 0.33136094674556216,
+      "grad_norm": 0.0,
+      "learning_rate": 9.759913439502982e-06,
+      "loss": 2.1666,
+      "step": 112
+    },
+    {
+      "epoch": 0.3343195266272189,
+      "grad_norm": 0.0,
+      "learning_rate": 9.752171387339612e-06,
+      "loss": 2.0586,
+      "step": 113
+    },
+    {
+      "epoch": 0.33727810650887574,
+      "grad_norm": 0.0,
+      "learning_rate": 9.74430964947668e-06,
+      "loss": 2.2467,
+      "step": 114
+    },
+    {
+      "epoch": 0.34023668639053256,
+      "grad_norm": 0.0,
+      "learning_rate": 9.736328423915797e-06,
+      "loss": 1.9752,
+      "step": 115
+    },
+    {
+      "epoch": 0.3431952662721893,
+      "grad_norm": 0.0,
+      "learning_rate": 9.728227911667934e-06,
+      "loss": 2.0287,
+      "step": 116
+    },
+    {
+      "epoch": 0.34615384615384615,
+      "grad_norm": 0.0,
+      "learning_rate": 9.720008316748344e-06,
+      "loss": 1.9418,
+      "step": 117
+    },
+    {
+      "epoch": 0.34911242603550297,
+      "grad_norm": 0.0,
+      "learning_rate": 9.711669846171443e-06,
+      "loss": 1.8564,
+      "step": 118
+    },
+    {
+      "epoch": 0.3520710059171598,
+      "grad_norm": 0.0,
+      "learning_rate": 9.703212709945583e-06,
+      "loss": 2.1265,
+      "step": 119
+    },
+    {
+      "epoch": 0.35502958579881655,
+      "grad_norm": 0.0,
+      "learning_rate": 9.694637121067764e-06,
+      "loss": 2.1465,
+      "step": 120
+    },
+    {
+      "epoch": 0.35798816568047337,
+      "grad_norm": 0.0,
+      "learning_rate": 9.685943295518283e-06,
+      "loss": 2.0634,
+      "step": 121
+    },
+    {
+      "epoch": 0.3609467455621302,
+      "grad_norm": 0.0,
+      "learning_rate": 9.677131452255272e-06,
+      "loss": 1.8979,
+      "step": 122
+    },
+    {
+      "epoch": 0.363905325443787,
+      "grad_norm": 0.0,
+      "learning_rate": 9.668201813209202e-06,
+      "loss": 2.1077,
+      "step": 123
+    },
+    {
+      "epoch": 0.3668639053254438,
+      "grad_norm": 0.0,
+      "learning_rate": 9.659154603277283e-06,
+      "loss": 1.9526,
+      "step": 124
+    },
+    {
+      "epoch": 0.3698224852071006,
+      "grad_norm": 0.0,
+      "learning_rate": 9.649990050317806e-06,
+      "loss": 2.0087,
+      "step": 125
+    },
+    {
+      "epoch": 0.3727810650887574,
+      "grad_norm": 0.0,
+      "learning_rate": 9.640708385144403e-06,
+      "loss": 2.2126,
+      "step": 126
+    },
+    {
+      "epoch": 0.3757396449704142,
+      "grad_norm": 0.0,
+      "learning_rate": 9.631309841520233e-06,
+      "loss": 1.9505,
+      "step": 127
+    },
+    {
+      "epoch": 0.378698224852071,
+      "grad_norm": 0.0,
+      "learning_rate": 9.62179465615209e-06,
+      "loss": 2.0827,
+      "step": 128
+    },
+    {
+      "epoch": 0.3816568047337278,
+      "grad_norm": 0.0,
+      "learning_rate": 9.612163068684453e-06,
+      "loss": 1.9128,
+      "step": 129
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.0,
+      "learning_rate": 9.602415321693434e-06,
+      "loss": 2.0497,
+      "step": 130
+    },
+    {
+      "epoch": 0.3875739644970414,
+      "grad_norm": 0.0,
+      "learning_rate": 9.592551660680687e-06,
+      "loss": 2.0195,
+      "step": 131
+    },
+    {
+      "epoch": 0.3905325443786982,
+      "grad_norm": 0.0,
+      "learning_rate": 9.582572334067213e-06,
+      "loss": 1.98,
+      "step": 132
+    },
+    {
+      "epoch": 0.39349112426035504,
+      "grad_norm": 0.0,
+      "learning_rate": 9.572477593187101e-06,
+      "loss": 2.1905,
+      "step": 133
+    },
+    {
+      "epoch": 0.39644970414201186,
+      "grad_norm": 0.0,
+      "learning_rate": 9.562267692281212e-06,
+      "loss": 1.9325,
+      "step": 134
+    },
+    {
+      "epoch": 0.3994082840236686,
+      "grad_norm": 0.0,
+      "learning_rate": 9.551942888490759e-06,
+      "loss": 1.8932,
+      "step": 135
+    },
+    {
+      "epoch": 0.40236686390532544,
+      "grad_norm": 0.0,
+      "learning_rate": 9.541503441850844e-06,
+      "loss": 2.1088,
+      "step": 136
+    },
+    {
+      "epoch": 0.40532544378698226,
+      "grad_norm": 0.0,
+      "learning_rate": 9.530949615283902e-06,
+      "loss": 2.0482,
+      "step": 137
+    },
+    {
+      "epoch": 0.40828402366863903,
+      "grad_norm": 0.0,
+      "learning_rate": 9.520281674593084e-06,
+      "loss": 1.9527,
+      "step": 138
+    },
+    {
+      "epoch": 0.41124260355029585,
+      "grad_norm": 0.0,
+      "learning_rate": 9.509499888455554e-06,
+      "loss": 2.2079,
+      "step": 139
+    },
+    {
+      "epoch": 0.41420118343195267,
+      "grad_norm": 0.0,
+      "learning_rate": 9.498604528415731e-06,
+      "loss": 2.078,
+      "step": 140
+    },
+    {
+      "epoch": 0.4171597633136095,
+      "grad_norm": 0.0,
+      "learning_rate": 9.487595868878447e-06,
+      "loss": 1.8665,
+      "step": 141
+    },
+    {
+      "epoch": 0.42011834319526625,
+      "grad_norm": 0.0,
+      "learning_rate": 9.476474187102033e-06,
+      "loss": 2.1273,
+      "step": 142
+    },
+    {
+      "epoch": 0.4230769230769231,
+      "grad_norm": 0.0,
+      "learning_rate": 9.465239763191345e-06,
+      "loss": 2.149,
+      "step": 143
+    },
+    {
+      "epoch": 0.4260355029585799,
+      "grad_norm": 0.0,
+      "learning_rate": 9.453892880090696e-06,
+      "loss": 2.2777,
+      "step": 144
+    },
+    {
+      "epoch": 0.4289940828402367,
+      "grad_norm": 0.0,
+      "learning_rate": 9.442433823576741e-06,
+      "loss": 1.909,
+      "step": 145
+    },
+    {
+      "epoch": 0.4319526627218935,
+      "grad_norm": 0.0,
+      "learning_rate": 9.430862882251279e-06,
+      "loss": 2.0979,
+      "step": 146
+    },
+    {
+      "epoch": 0.4349112426035503,
+      "grad_norm": 0.0,
+      "learning_rate": 9.419180347533976e-06,
+      "loss": 2.0014,
+      "step": 147
+    },
+    {
+      "epoch": 0.4378698224852071,
+      "grad_norm": 0.0,
+      "learning_rate": 9.40738651365503e-06,
+      "loss": 1.9684,
+      "step": 148
+    },
+    {
+      "epoch": 0.4408284023668639,
+      "grad_norm": 0.0,
+      "learning_rate": 9.395481677647767e-06,
+      "loss": 1.9934,
+      "step": 149
+    },
+    {
+      "epoch": 0.4437869822485207,
+      "grad_norm": 0.0,
+      "learning_rate": 9.38346613934115e-06,
+      "loss": 2.0623,
+      "step": 150
+    },
+    {
+      "epoch": 0.4467455621301775,
+      "grad_norm": 0.0,
+      "learning_rate": 9.371340201352234e-06,
+      "loss": 1.9309,
+      "step": 151
+    },
+    {
+      "epoch": 0.44970414201183434,
+      "grad_norm": 0.0,
+      "learning_rate": 9.359104169078541e-06,
+      "loss": 2.051,
+      "step": 152
+    },
+    {
+      "epoch": 0.4526627218934911,
+      "grad_norm": 0.0,
+      "learning_rate": 9.346758350690373e-06,
+      "loss": 1.8275,
+      "step": 153
+    },
+    {
+      "epoch": 0.4556213017751479,
+      "grad_norm": 0.0,
+      "learning_rate": 9.334303057123044e-06,
+      "loss": 2.1241,
+      "step": 154
+    },
+    {
+      "epoch": 0.45857988165680474,
+      "grad_norm": 0.0,
+      "learning_rate": 9.321738602069057e-06,
+      "loss": 1.744,
+      "step": 155
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.0,
+      "learning_rate": 9.309065301970193e-06,
+      "loss": 1.9512,
+      "step": 156
+    },
+    {
+      "epoch": 0.46449704142011833,
+      "grad_norm": 0.0,
+      "learning_rate": 9.296283476009551e-06,
+      "loss": 1.7762,
+      "step": 157
+    },
+    {
+      "epoch": 0.46745562130177515,
+      "grad_norm": 0.0,
+      "learning_rate": 9.283393446103506e-06,
+      "loss": 2.0851,
+      "step": 158
+    },
+    {
+      "epoch": 0.47041420118343197,
+      "grad_norm": 0.0,
+      "learning_rate": 9.270395536893599e-06,
+      "loss": 1.9134,
+      "step": 159
+    },
+    {
+      "epoch": 0.47337278106508873,
+      "grad_norm": 0.0,
+      "learning_rate": 9.257290075738365e-06,
+      "loss": 1.9303,
+      "step": 160
+    },
+    {
+      "epoch": 0.47633136094674555,
+      "grad_norm": 0.0,
+      "learning_rate": 9.244077392705085e-06,
+      "loss": 2.0788,
+      "step": 161
+    },
+    {
+      "epoch": 0.47928994082840237,
+      "grad_norm": 0.0,
+      "learning_rate": 9.23075782056147e-06,
+      "loss": 2.0059,
+      "step": 162
+    },
+    {
+      "epoch": 0.4822485207100592,
+      "grad_norm": 0.0,
+      "learning_rate": 9.217331694767291e-06,
+      "loss": 1.9133,
+      "step": 163
+    },
+    {
+      "epoch": 0.48520710059171596,
+      "grad_norm": 0.0,
+      "learning_rate": 9.20379935346592e-06,
+      "loss": 1.8088,
+      "step": 164
+    },
+    {
+      "epoch": 0.4881656804733728,
+      "grad_norm": 0.0,
+      "learning_rate": 9.190161137475814e-06,
+      "loss": 2.1096,
+      "step": 165
+    },
+    {
+      "epoch": 0.4911242603550296,
+      "grad_norm": 0.0,
+      "learning_rate": 9.176417390281944e-06,
+      "loss": 2.0724,
+      "step": 166
+    },
+    {
+      "epoch": 0.4940828402366864,
+      "grad_norm": 0.0,
+      "learning_rate": 9.162568458027122e-06,
+      "loss": 2.0448,
+      "step": 167
+    },
+    {
+      "epoch": 0.4970414201183432,
+      "grad_norm": 0.0,
+      "learning_rate": 9.148614689503307e-06,
+      "loss": 1.9694,
+      "step": 168
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.0,
+      "learning_rate": 9.134556436142801e-06,
+      "loss": 2.3346,
+      "step": 169
+    },
+    {
+      "epoch": 0.5029585798816568,
+      "grad_norm": 0.0,
+      "learning_rate": 9.120394052009412e-06,
+      "loss": 2.1182,
+      "step": 170
+    },
+    {
+      "epoch": 0.5059171597633136,
+      "grad_norm": 0.0,
+      "learning_rate": 9.10612789378953e-06,
+      "loss": 1.9823,
+      "step": 171
+    },
+    {
+      "epoch": 0.5088757396449705,
+      "grad_norm": 0.0,
+      "learning_rate": 9.091758320783139e-06,
+      "loss": 2.0,
+      "step": 172
+    },
+    {
+      "epoch": 0.5118343195266272,
+      "grad_norm": 0.0,
+      "learning_rate": 9.077285694894786e-06,
+      "loss": 2.0533,
+      "step": 173
+    },
+    {
+      "epoch": 0.514792899408284,
+      "grad_norm": 0.0,
+      "learning_rate": 9.062710380624439e-06,
+      "loss": 2.1201,
+      "step": 174
+    },
+    {
+      "epoch": 0.5177514792899408,
+      "grad_norm": 0.0,
+      "learning_rate": 9.048032745058335e-06,
+      "loss": 1.903,
+      "step": 175
+    },
+    {
+      "epoch": 0.5207100591715976,
+      "grad_norm": 0.0,
+      "learning_rate": 9.033253157859715e-06,
+      "loss": 1.9702,
+      "step": 176
+    },
+    {
+      "epoch": 0.5236686390532544,
+      "grad_norm": 0.0,
+      "learning_rate": 9.018371991259516e-06,
+      "loss": 2.006,
+      "step": 177
+    },
+    {
+      "epoch": 0.5266272189349113,
+      "grad_norm": 0.0,
+      "learning_rate": 9.003389620047012e-06,
+      "loss": 1.9672,
+      "step": 178
+    },
+    {
+      "epoch": 0.5295857988165681,
+      "grad_norm": 0.0,
+      "learning_rate": 8.988306421560354e-06,
+      "loss": 2.113,
+      "step": 179
+    },
+    {
+      "epoch": 0.5325443786982249,
+      "grad_norm": 0.0,
+      "learning_rate": 8.973122775677078e-06,
+      "loss": 2.2697,
+      "step": 180
+    },
+    {
+      "epoch": 0.5355029585798816,
+      "grad_norm": 0.0,
+      "learning_rate": 8.957839064804542e-06,
+      "loss": 2.0045,
+      "step": 181
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.0,
+      "learning_rate": 8.942455673870278e-06,
+      "loss": 2.2159,
+      "step": 182
+    },
+    {
+      "epoch": 0.5414201183431953,
+      "grad_norm": 0.0,
+      "learning_rate": 8.926972990312314e-06,
+      "loss": 1.9208,
+      "step": 183
+    },
+    {
+      "epoch": 0.5443786982248521,
+      "grad_norm": 0.0,
+      "learning_rate": 8.91139140406941e-06,
+      "loss": 2.0515,
+      "step": 184
+    },
+    {
+      "epoch": 0.5473372781065089,
+      "grad_norm": 0.0,
+      "learning_rate": 8.895711307571235e-06,
+      "loss": 2.0261,
+      "step": 185
+    },
+    {
+      "epoch": 0.5502958579881657,
+      "grad_norm": 0.0,
+      "learning_rate": 8.879933095728485e-06,
+      "loss": 2.0507,
+      "step": 186
+    },
+    {
+      "epoch": 0.5532544378698225,
+      "grad_norm": 0.0,
+      "learning_rate": 8.864057165922944e-06,
+      "loss": 2.1653,
+      "step": 187
+    },
+    {
+      "epoch": 0.5562130177514792,
+      "grad_norm": 0.0,
+      "learning_rate": 8.848083917997463e-06,
+      "loss": 1.9596,
+      "step": 188
+    },
+    {
+      "epoch": 0.5591715976331361,
+      "grad_norm": 0.0,
+      "learning_rate": 8.832013754245895e-06,
+      "loss": 2.2562,
+      "step": 189
+    },
+    {
+      "epoch": 0.5621301775147929,
+      "grad_norm": 0.0,
+      "learning_rate": 8.815847079402972e-06,
+      "loss": 1.8959,
+      "step": 190
+    },
+    {
+      "epoch": 0.5650887573964497,
+      "grad_norm": 0.0,
+      "learning_rate": 8.799584300634096e-06,
+      "loss": 2.0021,
+      "step": 191
+    },
+    {
+      "epoch": 0.5680473372781065,
+      "grad_norm": 0.0,
+      "learning_rate": 8.783225827525098e-06,
+      "loss": 2.0566,
+      "step": 192
+    },
+    {
+      "epoch": 0.5710059171597633,
+      "grad_norm": 0.0,
+      "learning_rate": 8.766772072071911e-06,
+      "loss": 1.8494,
+      "step": 193
+    },
+    {
+      "epoch": 0.5739644970414202,
+      "grad_norm": 0.0,
+      "learning_rate": 8.750223448670204e-06,
+      "loss": 1.9246,
+      "step": 194
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 0.0,
+      "learning_rate": 8.733580374104936e-06,
+      "loss": 2.0023,
+      "step": 195
+    },
+    {
+      "epoch": 0.5798816568047337,
+      "grad_norm": 0.0,
+      "learning_rate": 8.716843267539868e-06,
+      "loss": 2.0397,
+      "step": 196
+    },
+    {
+      "epoch": 0.5828402366863905,
+      "grad_norm": 0.0,
+      "learning_rate": 8.700012550507e-06,
+      "loss": 1.9078,
+      "step": 197
+    },
+    {
+      "epoch": 0.5857988165680473,
+      "grad_norm": 0.0,
+      "learning_rate": 8.683088646895955e-06,
+      "loss": 1.8544,
+      "step": 198
+    },
+    {
+      "epoch": 0.5887573964497042,
+      "grad_norm": 0.0,
+      "learning_rate": 8.666071982943306e-06,
+      "loss": 2.1141,
+      "step": 199
+    },
+    {
+      "epoch": 0.591715976331361,
+      "grad_norm": 0.0,
+      "learning_rate": 8.648962987221837e-06,
+      "loss": 2.0185,
+      "step": 200
+    },
+    {
+      "epoch": 0.5946745562130178,
+      "grad_norm": 0.0,
+      "learning_rate": 8.631762090629756e-06,
+      "loss": 2.0377,
+      "step": 201
+    },
+    {
+      "epoch": 0.5976331360946746,
+      "grad_norm": 0.0,
+      "learning_rate": 8.614469726379833e-06,
+      "loss": 2.1137,
+      "step": 202
+    },
+    {
+      "epoch": 0.6005917159763313,
+      "grad_norm": 0.0,
+      "learning_rate": 8.597086329988498e-06,
+      "loss": 1.9581,
+      "step": 203
+    },
+    {
+      "epoch": 0.6035502958579881,
+      "grad_norm": 0.0,
+      "learning_rate": 8.579612339264867e-06,
+      "loss": 2.0826,
+      "step": 204
+    },
+    {
+      "epoch": 0.606508875739645,
+      "grad_norm": 0.0,
+      "learning_rate": 8.562048194299719e-06,
+      "loss": 1.9337,
+      "step": 205
+    },
+    {
+      "epoch": 0.6094674556213018,
+      "grad_norm": 0.0,
+      "learning_rate": 8.544394337454409e-06,
+      "loss": 1.7187,
+      "step": 206
+    },
+    {
+      "epoch": 0.6124260355029586,
+      "grad_norm": 0.0,
+      "learning_rate": 8.52665121334973e-06,
+      "loss": 2.0672,
+      "step": 207
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.0,
+      "learning_rate": 8.508819268854713e-06,
+      "loss": 1.9108,
+      "step": 208
+    },
+    {
+      "epoch": 0.6183431952662722,
+      "grad_norm": 0.0,
+      "learning_rate": 8.49089895307537e-06,
+      "loss": 2.0656,
+      "step": 209
+    },
+    {
+      "epoch": 0.621301775147929,
+      "grad_norm": 0.0,
+      "learning_rate": 8.472890717343391e-06,
+      "loss": 1.7451,
+      "step": 210
+    },
+    {
+      "epoch": 0.6242603550295858,
+      "grad_norm": 0.0,
+      "learning_rate": 8.454795015204767e-06,
+      "loss": 1.7999,
+      "step": 211
+    },
+    {
+      "epoch": 0.6272189349112426,
+      "grad_norm": 0.0,
+      "learning_rate": 8.436612302408376e-06,
+      "loss": 2.0113,
+      "step": 212
+    },
+    {
+      "epoch": 0.6301775147928994,
+      "grad_norm": 0.0,
+      "learning_rate": 8.418343036894497e-06,
+      "loss": 1.9203,
+      "step": 213
+    },
+    {
+      "epoch": 0.6331360946745562,
+      "grad_norm": 0.0,
+      "learning_rate": 8.399987678783285e-06,
+      "loss": 2.0855,
+      "step": 214
+    },
+    {
+      "epoch": 0.636094674556213,
+      "grad_norm": 0.0,
+      "learning_rate": 8.381546690363174e-06,
+      "loss": 2.2595,
+      "step": 215
+    },
+    {
+      "epoch": 0.6390532544378699,
+      "grad_norm": 0.0,
+      "learning_rate": 8.36302053607924e-06,
+      "loss": 1.9627,
+      "step": 216
+    },
+    {
+      "epoch": 0.6420118343195266,
+      "grad_norm": 0.0,
+      "learning_rate": 8.344409682521499e-06,
+      "loss": 2.0542,
+      "step": 217
+    },
+    {
+      "epoch": 0.6449704142011834,
+      "grad_norm": 0.0,
+      "learning_rate": 8.325714598413169e-06,
+      "loss": 2.0843,
+      "step": 218
+    },
+    {
+      "epoch": 0.6479289940828402,
+      "grad_norm": 0.0,
+      "learning_rate": 8.306935754598838e-06,
+      "loss": 2.036,
+      "step": 219
+    },
+    {
+      "epoch": 0.650887573964497,
+      "grad_norm": 0.0,
+      "learning_rate": 8.288073624032634e-06,
+      "loss": 1.9346,
+      "step": 220
+    },
+    {
+      "epoch": 0.6538461538461539,
+      "grad_norm": 0.0,
+      "learning_rate": 8.269128681766296e-06,
+      "loss": 2.0075,
+      "step": 221
+    },
+    {
+      "epoch": 0.6568047337278107,
+      "grad_norm": 0.0,
+      "learning_rate": 8.250101404937223e-06,
+      "loss": 1.9172,
+      "step": 222
+    },
+    {
+      "epoch": 0.6597633136094675,
+      "grad_norm": 0.0,
+      "learning_rate": 8.230992272756438e-06,
+      "loss": 1.8597,
+      "step": 223
+    },
+    {
+      "epoch": 0.6627218934911243,
+      "grad_norm": 0.0,
+      "learning_rate": 8.211801766496537e-06,
+      "loss": 2.177,
+      "step": 224
+    },
+    {
+      "epoch": 0.665680473372781,
+      "grad_norm": 0.0,
+      "learning_rate": 8.192530369479562e-06,
+      "loss": 2.061,
+      "step": 225
+    },
+    {
+      "epoch": 0.6686390532544378,
+      "grad_norm": 0.0,
+      "learning_rate": 8.17317856706482e-06,
+      "loss": 1.945,
+      "step": 226
+    },
+    {
+      "epoch": 0.6715976331360947,
+      "grad_norm": 0.0,
+      "learning_rate": 8.153746846636675e-06,
+      "loss": 2.141,
+      "step": 227
+    },
+    {
+      "epoch": 0.6745562130177515,
+      "grad_norm": 0.0,
+      "learning_rate": 8.13423569759226e-06,
+      "loss": 2.0195,
+      "step": 228
+    },
+    {
+      "epoch": 0.6775147928994083,
+      "grad_norm": 0.0,
+      "learning_rate": 8.114645611329152e-06,
+      "loss": 2.0626,
+      "step": 229
+    },
+    {
+      "epoch": 0.6804733727810651,
+      "grad_norm": 0.0,
+      "learning_rate": 8.094977081233006e-06,
+      "loss": 2.0777,
+      "step": 230
+    },
+    {
+      "epoch": 0.6834319526627219,
+      "grad_norm": 0.0,
+      "learning_rate": 8.075230602665118e-06,
+      "loss": 1.9597,
+      "step": 231
+    },
+    {
+      "epoch": 0.6863905325443787,
+      "grad_norm": 0.0,
+      "learning_rate": 8.055406672949957e-06,
+      "loss": 2.1998,
+      "step": 232
+    },
+    {
+      "epoch": 0.6893491124260355,
+      "grad_norm": 0.0,
+      "learning_rate": 8.03550579136263e-06,
+      "loss": 1.9468,
+      "step": 233
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.0,
+      "learning_rate": 8.015528459116321e-06,
+      "loss": 2.1747,
+      "step": 234
+    },
+    {
+      "epoch": 0.6952662721893491,
+      "grad_norm": 0.0,
+      "learning_rate": 7.995475179349657e-06,
+      "loss": 2.0795,
+      "step": 235
+    },
+    {
+      "epoch": 0.6982248520710059,
+      "grad_norm": 0.0,
+      "learning_rate": 7.975346457114034e-06,
+      "loss": 2.0805,
+      "step": 236
+    },
+    {
+      "epoch": 0.7011834319526628,
+      "grad_norm": 0.0,
+      "learning_rate": 7.955142799360914e-06,
+      "loss": 2.0028,
+      "step": 237
+    },
+    {
+      "epoch": 0.7041420118343196,
+      "grad_norm": 0.0,
+      "learning_rate": 7.934864714929036e-06,
+      "loss": 2.1354,
+      "step": 238
+    },
+    {
+      "epoch": 0.7071005917159763,
+      "grad_norm": 0.0,
+      "learning_rate": 7.914512714531612e-06,
+      "loss": 1.9742,
+      "step": 239
+    },
+    {
+      "epoch": 0.7100591715976331,
+      "grad_norm": 0.0,
+      "learning_rate": 7.894087310743468e-06,
+      "loss": 2.0024,
+      "step": 240
+    },
+    {
+      "epoch": 0.7130177514792899,
+      "grad_norm": 0.0,
+      "learning_rate": 7.873589017988124e-06,
+      "loss": 1.9832,
+      "step": 241
+    },
+    {
+      "epoch": 0.7159763313609467,
+      "grad_norm": 0.0,
+      "learning_rate": 7.853018352524845e-06,
+      "loss": 2.021,
+      "step": 242
+    },
+    {
+      "epoch": 0.7189349112426036,
+      "grad_norm": 0.0,
+      "learning_rate": 7.832375832435637e-06,
+      "loss": 2.0464,
+      "step": 243
+    },
+    {
+      "epoch": 0.7218934911242604,
+      "grad_norm": 0.0,
+      "learning_rate": 7.811661977612202e-06,
+      "loss": 2.1695,
+      "step": 244
+    },
+    {
+      "epoch": 0.7248520710059172,
+      "grad_norm": 0.0,
+      "learning_rate": 7.790877309742833e-06,
+      "loss": 2.1147,
+      "step": 245
+    },
+    {
+      "epoch": 0.727810650887574,
+      "grad_norm": 0.0,
+      "learning_rate": 7.770022352299294e-06,
+      "loss": 2.0942,
+      "step": 246
+    },
+    {
+      "epoch": 0.7307692307692307,
+      "grad_norm": 0.0,
+      "learning_rate": 7.749097630523618e-06,
+      "loss": 1.9666,
+      "step": 247
+    },
+    {
+      "epoch": 0.7337278106508875,
+      "grad_norm": 0.0,
+      "learning_rate": 7.728103671414889e-06,
+      "loss": 2.1546,
+      "step": 248
+    },
+    {
+      "epoch": 0.7366863905325444,
+      "grad_norm": 0.0,
+      "learning_rate": 7.707041003715962e-06,
+      "loss": 2.0068,
+      "step": 249
+    },
+    {
+      "epoch": 0.7396449704142012,
+      "grad_norm": 0.0,
+      "learning_rate": 7.685910157900158e-06,
+      "loss": 1.9578,
+      "step": 250
+    },
+    {
+      "epoch": 0.742603550295858,
+      "grad_norm": 0.0,
+      "learning_rate": 7.66471166615789e-06,
+      "loss": 2.0239,
+      "step": 251
+    },
+    {
+      "epoch": 0.7455621301775148,
+      "grad_norm": 0.0,
+      "learning_rate": 7.643446062383273e-06,
+      "loss": 1.9391,
+      "step": 252
+    },
+    {
+      "epoch": 0.7485207100591716,
+      "grad_norm": 0.0,
+      "learning_rate": 7.622113882160658e-06,
+      "loss": 2.0905,
+      "step": 253
+    },
+    {
+      "epoch": 0.7514792899408284,
+      "grad_norm": 0.0,
+      "learning_rate": 7.600715662751166e-06,
+      "loss": 2.0219,
+      "step": 254
+    },
+    {
+      "epoch": 0.7544378698224852,
+      "grad_norm": 0.0,
+      "learning_rate": 7.579251943079145e-06,
+      "loss": 1.7913,
+      "step": 255
+    },
+    {
+      "epoch": 0.757396449704142,
+      "grad_norm": 0.0,
+      "learning_rate": 7.557723263718596e-06,
+      "loss": 1.959,
+      "step": 256
+    },
+    {
+      "epoch": 0.7603550295857988,
+      "grad_norm": 0.0,
+      "learning_rate": 7.536130166879561e-06,
+      "loss": 1.6362,
+      "step": 257
+    },
+    {
+      "epoch": 0.7633136094674556,
+      "grad_norm": 0.0,
+      "learning_rate": 7.514473196394467e-06,
+      "loss": 2.0445,
+      "step": 258
+    },
+    {
+      "epoch": 0.7662721893491125,
+      "grad_norm": 0.0,
+      "learning_rate": 7.492752897704432e-06,
+      "loss": 1.7799,
+      "step": 259
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.0,
+      "learning_rate": 7.470969817845518e-06,
+      "loss": 2.2377,
+      "step": 260
+    },
+    {
+      "epoch": 0.772189349112426,
+      "grad_norm": 0.0,
+      "learning_rate": 7.4491245054349716e-06,
+      "loss": 1.9337,
+      "step": 261
+    },
+    {
+      "epoch": 0.7751479289940828,
+      "grad_norm": 0.0,
+      "learning_rate": 7.427217510657383e-06,
+      "loss": 2.0414,
+      "step": 262
+    },
+    {
+      "epoch": 0.7781065088757396,
+      "grad_norm": 0.0,
+      "learning_rate": 7.405249385250854e-06,
+      "loss": 1.9806,
+      "step": 263
+    },
+    {
+      "epoch": 0.7810650887573964,
+      "grad_norm": 0.0,
+      "learning_rate": 7.383220682493081e-06,
+      "loss": 1.9006,
+      "step": 264
+    },
+    {
+      "epoch": 0.7840236686390533,
+      "grad_norm": 0.0,
+      "learning_rate": 7.361131957187435e-06,
+      "loss": 2.012,
+      "step": 265
+    },
+    {
+      "epoch": 0.7869822485207101,
+      "grad_norm": 0.0,
+      "learning_rate": 7.338983765648985e-06,
+      "loss": 1.928,
+      "step": 266
+    },
+    {
+      "epoch": 0.7899408284023669,
+      "grad_norm": 0.0,
+      "learning_rate": 7.31677666569048e-06,
+      "loss": 1.9348,
+      "step": 267
+    },
+    {
+      "epoch": 0.7928994082840237,
+      "grad_norm": 0.0,
+      "learning_rate": 7.294511216608308e-06,
+      "loss": 1.9509,
+      "step": 268
+    },
+    {
+      "epoch": 0.7958579881656804,
+      "grad_norm": 0.0,
+      "learning_rate": 7.272187979168408e-06,
+      "loss": 2.0597,
+      "step": 269
+    },
+    {
+      "epoch": 0.7988165680473372,
+      "grad_norm": 0.0,
+      "learning_rate": 7.249807515592149e-06,
+      "loss": 1.9152,
+      "step": 270
+    },
+    {
+      "epoch": 0.8017751479289941,
+      "grad_norm": 0.0,
+      "learning_rate": 7.227370389542161e-06,
+      "loss": 2.0258,
+      "step": 271
+    },
+    {
+      "epoch": 0.8047337278106509,
+      "grad_norm": 0.0,
+      "learning_rate": 7.2048771661081515e-06,
+      "loss": 2.1344,
+      "step": 272
+    },
+    {
+      "epoch": 0.8076923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 7.182328411792664e-06,
+      "loss": 2.1404,
+      "step": 273
+    },
+    {
+      "epoch": 0.8106508875739645,
+      "grad_norm": 0.0,
+      "learning_rate": 7.159724694496815e-06,
+      "loss": 1.8895,
+      "step": 274
+    },
+    {
+      "epoch": 0.8136094674556213,
+      "grad_norm": 0.0,
+      "learning_rate": 7.137066583505987e-06,
+      "loss": 1.9304,
+      "step": 275
+    },
+    {
+      "epoch": 0.8165680473372781,
+      "grad_norm": 0.0,
+      "learning_rate": 7.114354649475499e-06,
+      "loss": 2.1801,
+      "step": 276
+    },
+    {
+      "epoch": 0.8195266272189349,
+      "grad_norm": 0.0,
+      "learning_rate": 7.091589464416225e-06,
+      "loss": 2.0499,
+      "step": 277
+    },
+    {
+      "epoch": 0.8224852071005917,
+      "grad_norm": 0.0,
+      "learning_rate": 7.068771601680191e-06,
+      "loss": 2.0632,
+      "step": 278
+    },
+    {
+      "epoch": 0.8254437869822485,
+      "grad_norm": 0.0,
+      "learning_rate": 7.04590163594614e-06,
+      "loss": 2.0578,
+      "step": 279
+    },
+    {
+      "epoch": 0.8284023668639053,
+      "grad_norm": 0.0,
+      "learning_rate": 7.022980143205046e-06,
+      "loss": 1.9076,
+      "step": 280
+    },
+    {
+      "epoch": 0.8313609467455622,
+      "grad_norm": 0.0,
+      "learning_rate": 7.000007700745622e-06,
+      "loss": 2.0393,
+      "step": 281
+    },
+    {
+      "epoch": 0.834319526627219,
+      "grad_norm": 0.0,
+      "learning_rate": 6.976984887139775e-06,
+      "loss": 1.8379,
+      "step": 282
+    },
+    {
+      "epoch": 0.8372781065088757,
+      "grad_norm": 0.0,
+      "learning_rate": 6.9539122822280246e-06,
+      "loss": 1.9502,
+      "step": 283
+    },
+    {
+      "epoch": 0.8402366863905325,
+      "grad_norm": 0.0,
+      "learning_rate": 6.930790467104916e-06,
+      "loss": 2.2533,
+      "step": 284
+    },
+    {
+      "epoch": 0.8431952662721893,
+      "grad_norm": 0.0,
+      "learning_rate": 6.907620024104377e-06,
+      "loss": 1.9595,
+      "step": 285
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 0.0,
+      "learning_rate": 6.884401536785045e-06,
+      "loss": 1.8162,
+      "step": 286
+    },
+    {
+      "epoch": 0.849112426035503,
+      "grad_norm": 0.0,
+      "learning_rate": 6.861135589915583e-06,
+      "loss": 1.8172,
+      "step": 287
+    },
+    {
+      "epoch": 0.8520710059171598,
+      "grad_norm": 0.0,
+      "learning_rate": 6.837822769459942e-06,
+      "loss": 1.9625,
+      "step": 288
+    },
+    {
+      "epoch": 0.8550295857988166,
+      "grad_norm": 0.0,
+      "learning_rate": 6.814463662562609e-06,
+      "loss": 1.8102,
+      "step": 289
+    },
+    {
+      "epoch": 0.8579881656804734,
+      "grad_norm": 0.0,
+      "learning_rate": 6.791058857533814e-06,
+      "loss": 2.0348,
+      "step": 290
+    },
+    {
+      "epoch": 0.8609467455621301,
+      "grad_norm": 0.0,
+      "learning_rate": 6.767608943834721e-06,
+      "loss": 2.0201,
+      "step": 291
+    },
+    {
+      "epoch": 0.863905325443787,
+      "grad_norm": 0.0,
+      "learning_rate": 6.744114512062571e-06,
+      "loss": 2.0384,
+      "step": 292
+    },
+    {
+      "epoch": 0.8668639053254438,
+      "grad_norm": 0.0,
+      "learning_rate": 6.720576153935818e-06,
+      "loss": 2.0114,
+      "step": 293
+    },
+    {
+      "epoch": 0.8698224852071006,
+      "grad_norm": 0.0,
+      "learning_rate": 6.696994462279223e-06,
+      "loss": 1.9009,
+      "step": 294
+    },
+    {
+      "epoch": 0.8727810650887574,
+      "grad_norm": 0.0,
+      "learning_rate": 6.673370031008919e-06,
+      "loss": 1.8881,
+      "step": 295
+    },
+    {
+      "epoch": 0.8757396449704142,
+      "grad_norm": 0.0,
+      "learning_rate": 6.6497034551174585e-06,
+      "loss": 2.0063,
+      "step": 296
+    },
+    {
+      "epoch": 0.878698224852071,
+      "grad_norm": 0.0,
+      "learning_rate": 6.625995330658828e-06,
+      "loss": 1.9046,
+      "step": 297
+    },
+    {
+      "epoch": 0.8816568047337278,
+      "grad_norm": 0.0,
+      "learning_rate": 6.602246254733431e-06,
+      "loss": 2.1515,
+      "step": 298
+    },
+    {
+      "epoch": 0.8846153846153846,
+      "grad_norm": 0.0,
+      "learning_rate": 6.578456825473055e-06,
+      "loss": 2.0301,
+      "step": 299
+    },
+    {
+      "epoch": 0.8875739644970414,
+      "grad_norm": 0.0,
+      "learning_rate": 6.554627642025807e-06,
+      "loss": 1.8527,
+      "step": 300
+    },
+    {
+      "epoch": 0.8905325443786982,
+      "grad_norm": 0.0,
+      "learning_rate": 6.53075930454102e-06,
+      "loss": 1.956,
+      "step": 301
+    },
+    {
+      "epoch": 0.893491124260355,
+      "grad_norm": 0.0,
+      "learning_rate": 6.506852414154138e-06,
+      "loss": 2.0515,
+      "step": 302
+    },
+    {
+      "epoch": 0.8964497041420119,
+      "grad_norm": 0.0,
+      "learning_rate": 6.482907572971584e-06,
+      "loss": 1.9696,
+      "step": 303
+    },
+    {
+      "epoch": 0.8994082840236687,
+      "grad_norm": 0.0,
+      "learning_rate": 6.4589253840555856e-06,
+      "loss": 2.0332,
+      "step": 304
+    },
+    {
+      "epoch": 0.9023668639053254,
+      "grad_norm": 0.0,
+      "learning_rate": 6.434906451408991e-06,
+      "loss": 1.984,
+      "step": 305
+    },
+    {
+      "epoch": 0.9053254437869822,
+      "grad_norm": 0.0,
+      "learning_rate": 6.41085137996006e-06,
+      "loss": 2.1404,
+      "step": 306
+    },
+    {
+      "epoch": 0.908284023668639,
+      "grad_norm": 0.0,
+      "learning_rate": 6.386760775547221e-06,
+      "loss": 1.861,
+      "step": 307
+    },
+    {
+      "epoch": 0.9112426035502958,
+      "grad_norm": 0.0,
+      "learning_rate": 6.362635244903818e-06,
+      "loss": 1.9027,
+      "step": 308
+    },
+    {
+      "epoch": 0.9142011834319527,
+      "grad_norm": 0.0,
+      "learning_rate": 6.338475395642834e-06,
+      "loss": 2.037,
+      "step": 309
+    },
+    {
+      "epoch": 0.9171597633136095,
+      "grad_norm": 0.0,
+      "learning_rate": 6.314281836241573e-06,
+      "loss": 1.8811,
+      "step": 310
+    },
+    {
+      "epoch": 0.9201183431952663,
+      "grad_norm": 0.0,
+      "learning_rate": 6.2900551760263564e-06,
+      "loss": 2.0109,
+      "step": 311
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.0,
+      "learning_rate": 6.265796025157154e-06,
+      "loss": 1.9025,
+      "step": 312
+    },
+    {
+      "epoch": 0.9260355029585798,
+      "grad_norm": 0.0,
+      "learning_rate": 6.241504994612237e-06,
+      "loss": 2.0042,
+      "step": 313
+    },
+    {
+      "epoch": 0.9289940828402367,
+      "grad_norm": 0.0,
+      "learning_rate": 6.217182696172776e-06,
+      "loss": 1.8823,
+      "step": 314
+    },
+    {
+      "epoch": 0.9319526627218935,
+      "grad_norm": 0.0,
+      "learning_rate": 6.192829742407442e-06,
+      "loss": 1.9187,
+      "step": 315
+    },
+    {
+      "epoch": 0.9349112426035503,
+      "grad_norm": 0.0,
+      "learning_rate": 6.168446746656973e-06,
+      "loss": 2.0873,
+      "step": 316
+    },
+    {
+      "epoch": 0.9378698224852071,
+      "grad_norm": 0.0,
+      "learning_rate": 6.144034323018728e-06,
+      "loss": 1.9483,
+      "step": 317
+    },
+    {
+      "epoch": 0.9408284023668639,
+      "grad_norm": 0.0,
+      "learning_rate": 6.119593086331225e-06,
+      "loss": 1.9173,
+      "step": 318
+    },
+    {
+      "epoch": 0.9437869822485208,
+      "grad_norm": 0.0,
+      "learning_rate": 6.095123652158648e-06,
+      "loss": 2.1901,
+      "step": 319
+    },
+    {
+      "epoch": 0.9467455621301775,
+      "grad_norm": 0.0,
+      "learning_rate": 6.070626636775349e-06,
+      "loss": 1.9096,
+      "step": 320
+    },
+    {
+      "epoch": 0.9497041420118343,
+      "grad_norm": 0.0,
+      "learning_rate": 6.046102657150328e-06,
+      "loss": 1.7635,
+      "step": 321
+    },
+    {
+      "epoch": 0.9526627218934911,
+      "grad_norm": 0.0,
+      "learning_rate": 6.021552330931693e-06,
+      "loss": 1.791,
+      "step": 322
+    },
+    {
+      "epoch": 0.9556213017751479,
+      "grad_norm": 0.0,
+      "learning_rate": 5.996976276431097e-06,
+      "loss": 1.8559,
+      "step": 323
+    },
+    {
+      "epoch": 0.9585798816568047,
+      "grad_norm": 0.0,
+      "learning_rate": 5.972375112608182e-06,
+      "loss": 1.7571,
+      "step": 324
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 0.0,
+      "learning_rate": 5.947749459054972e-06,
+      "loss": 2.1249,
+      "step": 325
+    },
+    {
+      "epoch": 0.9644970414201184,
+      "grad_norm": 0.0,
+      "learning_rate": 5.923099935980278e-06,
+      "loss": 1.8671,
+      "step": 326
+    },
+    {
+      "epoch": 0.9674556213017751,
+      "grad_norm": 0.0,
+      "learning_rate": 5.898427164194084e-06,
+      "loss": 2.0426,
+      "step": 327
+    },
+    {
+      "epoch": 0.9704142011834319,
+      "grad_norm": 0.0,
+      "learning_rate": 5.8737317650918905e-06,
+      "loss": 2.1029,
+      "step": 328
+    },
+    {
+      "epoch": 0.9733727810650887,
+      "grad_norm": 0.0,
+      "learning_rate": 5.849014360639087e-06,
+      "loss": 2.1421,
+      "step": 329
+    },
+    {
+      "epoch": 0.9763313609467456,
+      "grad_norm": 0.0,
+      "learning_rate": 5.824275573355278e-06,
+      "loss": 1.9183,
+      "step": 330
+    },
+    {
+      "epoch": 0.9792899408284024,
+      "grad_norm": 0.0,
+      "learning_rate": 5.799516026298601e-06,
+      "loss": 1.9911,
+      "step": 331
+    },
+    {
+      "epoch": 0.9822485207100592,
+      "grad_norm": 0.0,
+      "learning_rate": 5.7747363430500395e-06,
+      "loss": 1.9728,
+      "step": 332
+    },
+    {
+      "epoch": 0.985207100591716,
+      "grad_norm": 0.0,
+      "learning_rate": 5.74993714769772e-06,
+      "loss": 2.0264,
+      "step": 333
+    },
+    {
+      "epoch": 0.9881656804733728,
+      "grad_norm": 0.0,
+      "learning_rate": 5.725119064821185e-06,
+      "loss": 1.8333,
+      "step": 334
+    },
+    {
+      "epoch": 0.9911242603550295,
+      "grad_norm": 0.0,
+      "learning_rate": 5.700282719475672e-06,
+      "loss": 2.0225,
+      "step": 335
+    },
+    {
+      "epoch": 0.9940828402366864,
+      "grad_norm": 0.0,
+      "learning_rate": 5.675428737176367e-06,
+      "loss": 1.8918,
+      "step": 336
+    },
+    {
+      "epoch": 0.9970414201183432,
+      "grad_norm": 0.0,
+      "learning_rate": 5.65055774388265e-06,
+      "loss": 2.0365,
+      "step": 337
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 5.625670365982332e-06,
+      "loss": 1.9262,
+      "step": 338
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 676,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 169,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2094163499548672e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e01d58647da904db0b7444e4d0ccbcca4f52556c0b1f468eb26728cedc3947f1
+size 7096