Training in progress, step 400

.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 +1,33 @@
+{
+  "_name_or_path": "google/gemma-2-2b",
+  "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": 2304,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 256000
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a025cf8e388d5133fd8a48471b771c33e13a5418b14b15409d7136a7d313a65
+size 4988025760

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb68596bff6d898bb4354681a1667915cc3293b7d9156022bff46e181d0d2c2
+size 240691728

model.safetensors.index.json

@@ -0,0 +1,295 @@
+{
+  "metadata": {
+    "total_size": 5228683776
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "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 sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357

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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_log.jsonl

@@ -0,0 +1,412 @@
+{"current_steps": 1, "total_steps": 3906, "loss": 7.1027, "learning_rate": 1.0000000000000002e-06, "epoch": 0.000256, "percentage": 0.03, "elapsed_time": "0:00:21", "remaining_time": "23:22:04"}
+{"current_steps": 2, "total_steps": 3906, "loss": 7.1034, "learning_rate": 2.0000000000000003e-06, "epoch": 0.000512, "percentage": 0.05, "elapsed_time": "0:00:34", "remaining_time": "18:50:02"}
+{"current_steps": 3, "total_steps": 3906, "loss": 6.5723, "learning_rate": 3e-06, "epoch": 0.000768, "percentage": 0.08, "elapsed_time": "0:00:47", "remaining_time": "17:18:37"}
+{"current_steps": 4, "total_steps": 3906, "loss": 5.2188, "learning_rate": 4.000000000000001e-06, "epoch": 0.001024, "percentage": 0.1, "elapsed_time": "0:01:01", "remaining_time": "16:32:40"}
+{"current_steps": 5, "total_steps": 3906, "loss": 4.0969, "learning_rate": 5e-06, "epoch": 0.00128, "percentage": 0.13, "elapsed_time": "0:01:14", "remaining_time": "16:04:54"}
+{"current_steps": 6, "total_steps": 3906, "loss": 3.4141, "learning_rate": 6e-06, "epoch": 0.001536, "percentage": 0.15, "elapsed_time": "0:01:27", "remaining_time": "15:46:27"}
+{"current_steps": 7, "total_steps": 3906, "loss": 3.2294, "learning_rate": 7e-06, "epoch": 0.001792, "percentage": 0.18, "elapsed_time": "0:01:40", "remaining_time": "15:33:30"}
+{"current_steps": 8, "total_steps": 3906, "loss": 2.7187, "learning_rate": 8.000000000000001e-06, "epoch": 0.002048, "percentage": 0.2, "elapsed_time": "0:01:53", "remaining_time": "15:23:36"}
+{"current_steps": 9, "total_steps": 3906, "loss": 2.6165, "learning_rate": 9e-06, "epoch": 0.002304, "percentage": 0.23, "elapsed_time": "0:02:06", "remaining_time": "15:15:54"}
+{"current_steps": 10, "total_steps": 3906, "loss": 2.5339, "learning_rate": 1e-05, "epoch": 0.00256, "percentage": 0.26, "elapsed_time": "0:02:20", "remaining_time": "15:09:52"}
+{"current_steps": 11, "total_steps": 3906, "loss": 2.4265, "learning_rate": 1.1000000000000001e-05, "epoch": 0.002816, "percentage": 0.28, "elapsed_time": "0:02:33", "remaining_time": "15:04:57"}
+{"current_steps": 12, "total_steps": 3906, "loss": 2.3719, "learning_rate": 1.2e-05, "epoch": 0.003072, "percentage": 0.31, "elapsed_time": "0:02:46", "remaining_time": "15:00:39"}
+{"current_steps": 13, "total_steps": 3906, "loss": 2.2678, "learning_rate": 1.3000000000000001e-05, "epoch": 0.003328, "percentage": 0.33, "elapsed_time": "0:02:59", "remaining_time": "14:57:01"}
+{"current_steps": 14, "total_steps": 3906, "loss": 2.4163, "learning_rate": 1.4e-05, "epoch": 0.003584, "percentage": 0.36, "elapsed_time": "0:03:12", "remaining_time": "14:53:48"}
+{"current_steps": 15, "total_steps": 3906, "loss": 2.2873, "learning_rate": 1.5000000000000002e-05, "epoch": 0.00384, "percentage": 0.38, "elapsed_time": "0:03:26", "remaining_time": "14:50:55"}
+{"current_steps": 16, "total_steps": 3906, "loss": 2.3126, "learning_rate": 1.6000000000000003e-05, "epoch": 0.004096, "percentage": 0.41, "elapsed_time": "0:03:39", "remaining_time": "14:48:20"}
+{"current_steps": 17, "total_steps": 3906, "loss": 2.1398, "learning_rate": 1.7e-05, "epoch": 0.004352, "percentage": 0.44, "elapsed_time": "0:03:52", "remaining_time": "14:46:03"}
+{"current_steps": 18, "total_steps": 3906, "loss": 2.1752, "learning_rate": 1.8e-05, "epoch": 0.004608, "percentage": 0.46, "elapsed_time": "0:04:05", "remaining_time": "14:44:05"}
+{"current_steps": 19, "total_steps": 3906, "loss": 2.2289, "learning_rate": 1.9e-05, "epoch": 0.004864, "percentage": 0.49, "elapsed_time": "0:04:18", "remaining_time": "14:42:19"}
+{"current_steps": 20, "total_steps": 3906, "loss": 2.2723, "learning_rate": 2e-05, "epoch": 0.00512, "percentage": 0.51, "elapsed_time": "0:04:31", "remaining_time": "14:40:39"}
+{"current_steps": 21, "total_steps": 3906, "loss": 2.1972, "learning_rate": 2.1000000000000002e-05, "epoch": 0.005376, "percentage": 0.54, "elapsed_time": "0:04:45", "remaining_time": "14:39:08"}
+{"current_steps": 22, "total_steps": 3906, "loss": 2.1221, "learning_rate": 2.2000000000000003e-05, "epoch": 0.005632, "percentage": 0.56, "elapsed_time": "0:04:58", "remaining_time": "14:37:48"}
+{"current_steps": 23, "total_steps": 3906, "loss": 2.144, "learning_rate": 2.3e-05, "epoch": 0.005888, "percentage": 0.59, "elapsed_time": "0:05:11", "remaining_time": "14:36:36"}
+{"current_steps": 24, "total_steps": 3906, "loss": 2.1498, "learning_rate": 2.4e-05, "epoch": 0.006144, "percentage": 0.61, "elapsed_time": "0:05:24", "remaining_time": "14:35:28"}
+{"current_steps": 25, "total_steps": 3906, "loss": 2.2104, "learning_rate": 2.5e-05, "epoch": 0.0064, "percentage": 0.64, "elapsed_time": "0:05:37", "remaining_time": "14:34:23"}
+{"current_steps": 26, "total_steps": 3906, "loss": 2.1118, "learning_rate": 2.6000000000000002e-05, "epoch": 0.006656, "percentage": 0.67, "elapsed_time": "0:05:51", "remaining_time": "14:33:11"}
+{"current_steps": 27, "total_steps": 3906, "loss": 2.0654, "learning_rate": 2.7000000000000002e-05, "epoch": 0.006912, "percentage": 0.69, "elapsed_time": "0:06:04", "remaining_time": "14:32:01"}
+{"current_steps": 28, "total_steps": 3906, "loss": 2.0889, "learning_rate": 2.8e-05, "epoch": 0.007168, "percentage": 0.72, "elapsed_time": "0:06:17", "remaining_time": "14:31:07"}
+{"current_steps": 29, "total_steps": 3906, "loss": 2.0099, "learning_rate": 2.9e-05, "epoch": 0.007424, "percentage": 0.74, "elapsed_time": "0:06:30", "remaining_time": "14:30:08"}
+{"current_steps": 30, "total_steps": 3906, "loss": 2.0453, "learning_rate": 3.0000000000000004e-05, "epoch": 0.00768, "percentage": 0.77, "elapsed_time": "0:06:43", "remaining_time": "14:29:18"}
+{"current_steps": 31, "total_steps": 3906, "loss": 2.0467, "learning_rate": 3.1e-05, "epoch": 0.007936, "percentage": 0.79, "elapsed_time": "0:06:56", "remaining_time": "14:28:33"}
+{"current_steps": 32, "total_steps": 3906, "loss": 2.064, "learning_rate": 3.2000000000000005e-05, "epoch": 0.008192, "percentage": 0.82, "elapsed_time": "0:07:10", "remaining_time": "14:27:51"}
+{"current_steps": 33, "total_steps": 3906, "loss": 2.0269, "learning_rate": 3.3e-05, "epoch": 0.008448, "percentage": 0.84, "elapsed_time": "0:07:23", "remaining_time": "14:27:08"}
+{"current_steps": 34, "total_steps": 3906, "loss": 2.0346, "learning_rate": 3.4e-05, "epoch": 0.008704, "percentage": 0.87, "elapsed_time": "0:07:36", "remaining_time": "14:26:27"}
+{"current_steps": 35, "total_steps": 3906, "loss": 1.9448, "learning_rate": 3.5000000000000004e-05, "epoch": 0.00896, "percentage": 0.9, "elapsed_time": "0:07:49", "remaining_time": "14:25:48"}
+{"current_steps": 36, "total_steps": 3906, "loss": 1.9426, "learning_rate": 3.6e-05, "epoch": 0.009216, "percentage": 0.92, "elapsed_time": "0:08:02", "remaining_time": "14:25:09"}
+{"current_steps": 37, "total_steps": 3906, "loss": 2.0256, "learning_rate": 3.7000000000000005e-05, "epoch": 0.009472, "percentage": 0.95, "elapsed_time": "0:08:16", "remaining_time": "14:24:31"}
+{"current_steps": 38, "total_steps": 3906, "loss": 1.9751, "learning_rate": 3.8e-05, "epoch": 0.009728, "percentage": 0.97, "elapsed_time": "0:08:29", "remaining_time": "14:23:57"}
+{"current_steps": 39, "total_steps": 3906, "loss": 1.9972, "learning_rate": 3.9e-05, "epoch": 0.009984, "percentage": 1.0, "elapsed_time": "0:08:42", "remaining_time": "14:23:22"}
+{"current_steps": 40, "total_steps": 3906, "loss": 1.9717, "learning_rate": 4e-05, "epoch": 0.01024, "percentage": 1.02, "elapsed_time": "0:08:55", "remaining_time": "14:22:49"}
+{"current_steps": 41, "total_steps": 3906, "loss": 2.0233, "learning_rate": 3.999999339647203e-05, "epoch": 0.010496, "percentage": 1.05, "elapsed_time": "0:09:08", "remaining_time": "14:22:14"}
+{"current_steps": 42, "total_steps": 3906, "loss": 2.051, "learning_rate": 3.9999973585892455e-05, "epoch": 0.010752, "percentage": 1.08, "elapsed_time": "0:09:22", "remaining_time": "14:21:44"}
+{"current_steps": 43, "total_steps": 3906, "loss": 1.9142, "learning_rate": 3.999994056827438e-05, "epoch": 0.011008, "percentage": 1.1, "elapsed_time": "0:09:35", "remaining_time": "14:21:13"}
+{"current_steps": 44, "total_steps": 3906, "loss": 2.0122, "learning_rate": 3.999989434363959e-05, "epoch": 0.011264, "percentage": 1.13, "elapsed_time": "0:09:48", "remaining_time": "14:20:44"}
+{"current_steps": 45, "total_steps": 3906, "loss": 1.9614, "learning_rate": 3.999983491201863e-05, "epoch": 0.01152, "percentage": 1.15, "elapsed_time": "0:10:01", "remaining_time": "14:20:16"}
+{"current_steps": 46, "total_steps": 3906, "loss": 1.9205, "learning_rate": 3.999976227345072e-05, "epoch": 0.011776, "percentage": 1.18, "elapsed_time": "0:10:14", "remaining_time": "14:19:50"}
+{"current_steps": 47, "total_steps": 3906, "loss": 1.9214, "learning_rate": 3.999967642798385e-05, "epoch": 0.012032, "percentage": 1.2, "elapsed_time": "0:10:27", "remaining_time": "14:19:22"}
+{"current_steps": 48, "total_steps": 3906, "loss": 1.9153, "learning_rate": 3.99995773756747e-05, "epoch": 0.012288, "percentage": 1.23, "elapsed_time": "0:10:41", "remaining_time": "14:18:56"}
+{"current_steps": 49, "total_steps": 3906, "loss": 1.8511, "learning_rate": 3.9999465116588664e-05, "epoch": 0.012544, "percentage": 1.25, "elapsed_time": "0:10:54", "remaining_time": "14:18:29"}
+{"current_steps": 50, "total_steps": 3906, "loss": 1.8317, "learning_rate": 3.99993396507999e-05, "epoch": 0.0128, "percentage": 1.28, "elapsed_time": "0:11:07", "remaining_time": "14:17:57"}
+{"current_steps": 51, "total_steps": 3906, "loss": 1.8839, "learning_rate": 3.999920097839124e-05, "epoch": 0.013056, "percentage": 1.31, "elapsed_time": "0:11:20", "remaining_time": "14:17:28"}
+{"current_steps": 52, "total_steps": 3906, "loss": 1.8511, "learning_rate": 3.999904909945427e-05, "epoch": 0.013312, "percentage": 1.33, "elapsed_time": "0:11:33", "remaining_time": "14:17:04"}
+{"current_steps": 53, "total_steps": 3906, "loss": 1.8425, "learning_rate": 3.999888401408927e-05, "epoch": 0.013568, "percentage": 1.36, "elapsed_time": "0:11:47", "remaining_time": "14:16:39"}
+{"current_steps": 54, "total_steps": 3906, "loss": 1.841, "learning_rate": 3.999870572240527e-05, "epoch": 0.013824, "percentage": 1.38, "elapsed_time": "0:12:00", "remaining_time": "14:16:16"}
+{"current_steps": 55, "total_steps": 3906, "loss": 1.8339, "learning_rate": 3.999851422451999e-05, "epoch": 0.01408, "percentage": 1.41, "elapsed_time": "0:12:13", "remaining_time": "14:15:54"}
+{"current_steps": 56, "total_steps": 3906, "loss": 1.9235, "learning_rate": 3.9998309520559904e-05, "epoch": 0.014336, "percentage": 1.43, "elapsed_time": "0:12:26", "remaining_time": "14:15:31"}
+{"current_steps": 57, "total_steps": 3906, "loss": 1.9388, "learning_rate": 3.999809161066017e-05, "epoch": 0.014592, "percentage": 1.46, "elapsed_time": "0:12:39", "remaining_time": "14:15:10"}
+{"current_steps": 58, "total_steps": 3906, "loss": 1.815, "learning_rate": 3.999786049496469e-05, "epoch": 0.014848, "percentage": 1.48, "elapsed_time": "0:12:53", "remaining_time": "14:14:48"}
+{"current_steps": 59, "total_steps": 3906, "loss": 1.8619, "learning_rate": 3.999761617362609e-05, "epoch": 0.015104, "percentage": 1.51, "elapsed_time": "0:13:06", "remaining_time": "14:14:27"}
+{"current_steps": 60, "total_steps": 3906, "loss": 1.8577, "learning_rate": 3.99973586468057e-05, "epoch": 0.01536, "percentage": 1.54, "elapsed_time": "0:13:19", "remaining_time": "14:14:07"}
+{"current_steps": 61, "total_steps": 3906, "loss": 1.8654, "learning_rate": 3.9997087914673585e-05, "epoch": 0.015616, "percentage": 1.56, "elapsed_time": "0:13:32", "remaining_time": "14:13:43"}
+{"current_steps": 62, "total_steps": 3906, "loss": 1.8033, "learning_rate": 3.999680397740852e-05, "epoch": 0.015872, "percentage": 1.59, "elapsed_time": "0:13:45", "remaining_time": "14:13:21"}
+{"current_steps": 63, "total_steps": 3906, "loss": 1.7934, "learning_rate": 3.9996506835198005e-05, "epoch": 0.016128, "percentage": 1.61, "elapsed_time": "0:13:59", "remaining_time": "14:13:00"}
+{"current_steps": 64, "total_steps": 3906, "loss": 1.8388, "learning_rate": 3.999619648823826e-05, "epoch": 0.016384, "percentage": 1.64, "elapsed_time": "0:14:12", "remaining_time": "14:12:37"}
+{"current_steps": 65, "total_steps": 3906, "loss": 1.8471, "learning_rate": 3.999587293673422e-05, "epoch": 0.01664, "percentage": 1.66, "elapsed_time": "0:14:25", "remaining_time": "14:12:18"}
+{"current_steps": 66, "total_steps": 3906, "loss": 1.7755, "learning_rate": 3.9995536180899544e-05, "epoch": 0.016896, "percentage": 1.69, "elapsed_time": "0:14:38", "remaining_time": "14:11:59"}
+{"current_steps": 67, "total_steps": 3906, "loss": 1.8353, "learning_rate": 3.9995186220956616e-05, "epoch": 0.017152, "percentage": 1.72, "elapsed_time": "0:14:51", "remaining_time": "14:11:38"}
+{"current_steps": 68, "total_steps": 3906, "loss": 1.8891, "learning_rate": 3.999482305713653e-05, "epoch": 0.017408, "percentage": 1.74, "elapsed_time": "0:15:04", "remaining_time": "14:11:18"}
+{"current_steps": 69, "total_steps": 3906, "loss": 1.8241, "learning_rate": 3.9994446689679085e-05, "epoch": 0.017664, "percentage": 1.77, "elapsed_time": "0:15:18", "remaining_time": "14:10:58"}
+{"current_steps": 70, "total_steps": 3906, "loss": 1.7861, "learning_rate": 3.999405711883285e-05, "epoch": 0.01792, "percentage": 1.79, "elapsed_time": "0:15:31", "remaining_time": "14:10:41"}
+{"current_steps": 71, "total_steps": 3906, "loss": 1.7952, "learning_rate": 3.999365434485504e-05, "epoch": 0.018176, "percentage": 1.82, "elapsed_time": "0:15:44", "remaining_time": "14:10:22"}
+{"current_steps": 72, "total_steps": 3906, "loss": 1.8357, "learning_rate": 3.999323836801166e-05, "epoch": 0.018432, "percentage": 1.84, "elapsed_time": "0:15:57", "remaining_time": "14:10:03"}
+{"current_steps": 73, "total_steps": 3906, "loss": 1.7782, "learning_rate": 3.999280918857739e-05, "epoch": 0.018688, "percentage": 1.87, "elapsed_time": "0:16:10", "remaining_time": "14:09:43"}
+{"current_steps": 74, "total_steps": 3906, "loss": 1.817, "learning_rate": 3.999236680683564e-05, "epoch": 0.018944, "percentage": 1.89, "elapsed_time": "0:16:24", "remaining_time": "14:09:20"}
+{"current_steps": 75, "total_steps": 3906, "loss": 1.7895, "learning_rate": 3.9991911223078537e-05, "epoch": 0.0192, "percentage": 1.92, "elapsed_time": "0:16:37", "remaining_time": "14:09:04"}
+{"current_steps": 76, "total_steps": 3906, "loss": 1.7798, "learning_rate": 3.999144243760693e-05, "epoch": 0.019456, "percentage": 1.95, "elapsed_time": "0:16:50", "remaining_time": "14:08:46"}
+{"current_steps": 77, "total_steps": 3906, "loss": 1.7809, "learning_rate": 3.9990960450730376e-05, "epoch": 0.019712, "percentage": 1.97, "elapsed_time": "0:17:03", "remaining_time": "14:08:27"}
+{"current_steps": 78, "total_steps": 3906, "loss": 1.7588, "learning_rate": 3.999046526276716e-05, "epoch": 0.019968, "percentage": 2.0, "elapsed_time": "0:17:16", "remaining_time": "14:08:09"}
+{"current_steps": 79, "total_steps": 3906, "loss": 1.7642, "learning_rate": 3.998995687404429e-05, "epoch": 0.020224, "percentage": 2.02, "elapsed_time": "0:17:30", "remaining_time": "14:07:52"}
+{"current_steps": 80, "total_steps": 3906, "loss": 1.741, "learning_rate": 3.998943528489746e-05, "epoch": 0.02048, "percentage": 2.05, "elapsed_time": "0:17:43", "remaining_time": "14:07:34"}
+{"current_steps": 81, "total_steps": 3906, "loss": 1.7976, "learning_rate": 3.998890049567113e-05, "epoch": 0.020736, "percentage": 2.07, "elapsed_time": "0:17:56", "remaining_time": "14:07:18"}
+{"current_steps": 82, "total_steps": 3906, "loss": 1.7517, "learning_rate": 3.9988352506718426e-05, "epoch": 0.020992, "percentage": 2.1, "elapsed_time": "0:18:09", "remaining_time": "14:07:01"}
+{"current_steps": 83, "total_steps": 3906, "loss": 1.721, "learning_rate": 3.998779131840123e-05, "epoch": 0.021248, "percentage": 2.12, "elapsed_time": "0:18:22", "remaining_time": "14:06:43"}
+{"current_steps": 84, "total_steps": 3906, "loss": 1.735, "learning_rate": 3.998721693109011e-05, "epoch": 0.021504, "percentage": 2.15, "elapsed_time": "0:18:36", "remaining_time": "14:06:25"}
+{"current_steps": 85, "total_steps": 3906, "loss": 1.7742, "learning_rate": 3.998662934516438e-05, "epoch": 0.02176, "percentage": 2.18, "elapsed_time": "0:18:49", "remaining_time": "14:06:07"}
+{"current_steps": 86, "total_steps": 3906, "loss": 1.7198, "learning_rate": 3.998602856101205e-05, "epoch": 0.022016, "percentage": 2.2, "elapsed_time": "0:19:02", "remaining_time": "14:05:48"}
+{"current_steps": 87, "total_steps": 3906, "loss": 1.7398, "learning_rate": 3.9985414579029836e-05, "epoch": 0.022272, "percentage": 2.23, "elapsed_time": "0:19:15", "remaining_time": "14:05:28"}
+{"current_steps": 88, "total_steps": 3906, "loss": 1.735, "learning_rate": 3.99847873996232e-05, "epoch": 0.022528, "percentage": 2.25, "elapsed_time": "0:19:28", "remaining_time": "14:05:11"}
+{"current_steps": 89, "total_steps": 3906, "loss": 1.7487, "learning_rate": 3.9984147023206295e-05, "epoch": 0.022784, "percentage": 2.28, "elapsed_time": "0:19:42", "remaining_time": "14:04:54"}
+{"current_steps": 90, "total_steps": 3906, "loss": 1.7461, "learning_rate": 3.9983493450202e-05, "epoch": 0.02304, "percentage": 2.3, "elapsed_time": "0:19:55", "remaining_time": "14:04:37"}
+{"current_steps": 91, "total_steps": 3906, "loss": 1.7403, "learning_rate": 3.998282668104188e-05, "epoch": 0.023296, "percentage": 2.33, "elapsed_time": "0:20:08", "remaining_time": "14:04:20"}
+{"current_steps": 92, "total_steps": 3906, "loss": 1.6954, "learning_rate": 3.998214671616627e-05, "epoch": 0.023552, "percentage": 2.36, "elapsed_time": "0:20:21", "remaining_time": "14:04:04"}
+{"current_steps": 93, "total_steps": 3906, "loss": 1.8071, "learning_rate": 3.9981453556024175e-05, "epoch": 0.023808, "percentage": 2.38, "elapsed_time": "0:20:34", "remaining_time": "14:03:48"}
+{"current_steps": 94, "total_steps": 3906, "loss": 1.711, "learning_rate": 3.998074720107332e-05, "epoch": 0.024064, "percentage": 2.41, "elapsed_time": "0:20:48", "remaining_time": "14:03:31"}
+{"current_steps": 95, "total_steps": 3906, "loss": 1.7698, "learning_rate": 3.998002765178015e-05, "epoch": 0.02432, "percentage": 2.43, "elapsed_time": "0:21:01", "remaining_time": "14:03:13"}
+{"current_steps": 96, "total_steps": 3906, "loss": 1.7301, "learning_rate": 3.997929490861983e-05, "epoch": 0.024576, "percentage": 2.46, "elapsed_time": "0:21:14", "remaining_time": "14:02:57"}
+{"current_steps": 97, "total_steps": 3906, "loss": 1.7179, "learning_rate": 3.997854897207621e-05, "epoch": 0.024832, "percentage": 2.48, "elapsed_time": "0:21:27", "remaining_time": "14:02:39"}
+{"current_steps": 98, "total_steps": 3906, "loss": 1.7119, "learning_rate": 3.997778984264189e-05, "epoch": 0.025088, "percentage": 2.51, "elapsed_time": "0:21:40", "remaining_time": "14:02:23"}
+{"current_steps": 99, "total_steps": 3906, "loss": 1.7394, "learning_rate": 3.997701752081816e-05, "epoch": 0.025344, "percentage": 2.53, "elapsed_time": "0:21:53", "remaining_time": "14:02:06"}
+{"current_steps": 100, "total_steps": 3906, "loss": 1.6803, "learning_rate": 3.9976232007115015e-05, "epoch": 0.0256, "percentage": 2.56, "elapsed_time": "0:22:07", "remaining_time": "14:01:51"}
+{"current_steps": 101, "total_steps": 3906, "loss": 1.7406, "learning_rate": 3.9975433302051184e-05, "epoch": 0.025856, "percentage": 2.59, "elapsed_time": "0:22:20", "remaining_time": "14:01:34"}
+{"current_steps": 102, "total_steps": 3906, "loss": 1.7512, "learning_rate": 3.997462140615408e-05, "epoch": 0.026112, "percentage": 2.61, "elapsed_time": "0:22:33", "remaining_time": "14:01:19"}
+{"current_steps": 103, "total_steps": 3906, "loss": 1.7349, "learning_rate": 3.9973796319959854e-05, "epoch": 0.026368, "percentage": 2.64, "elapsed_time": "0:22:46", "remaining_time": "14:01:03"}
+{"current_steps": 104, "total_steps": 3906, "loss": 1.8028, "learning_rate": 3.997295804401335e-05, "epoch": 0.026624, "percentage": 2.66, "elapsed_time": "0:22:59", "remaining_time": "14:00:48"}
+{"current_steps": 105, "total_steps": 3906, "loss": 1.6684, "learning_rate": 3.997210657886813e-05, "epoch": 0.02688, "percentage": 2.69, "elapsed_time": "0:23:13", "remaining_time": "14:00:33"}
+{"current_steps": 106, "total_steps": 3906, "loss": 1.6906, "learning_rate": 3.9971241925086444e-05, "epoch": 0.027136, "percentage": 2.71, "elapsed_time": "0:23:26", "remaining_time": "14:00:18"}
+{"current_steps": 107, "total_steps": 3906, "loss": 1.6753, "learning_rate": 3.9970364083239284e-05, "epoch": 0.027392, "percentage": 2.74, "elapsed_time": "0:23:39", "remaining_time": "14:00:07"}
+{"current_steps": 108, "total_steps": 3906, "loss": 1.6673, "learning_rate": 3.996947305390634e-05, "epoch": 0.027648, "percentage": 2.76, "elapsed_time": "0:23:52", "remaining_time": "13:59:52"}
+{"current_steps": 109, "total_steps": 3906, "loss": 1.6906, "learning_rate": 3.9968568837675986e-05, "epoch": 0.027904, "percentage": 2.79, "elapsed_time": "0:24:06", "remaining_time": "13:59:35"}
+{"current_steps": 110, "total_steps": 3906, "loss": 1.7352, "learning_rate": 3.996765143514534e-05, "epoch": 0.02816, "percentage": 2.82, "elapsed_time": "0:24:19", "remaining_time": "13:59:17"}
+{"current_steps": 111, "total_steps": 3906, "loss": 1.6813, "learning_rate": 3.996672084692021e-05, "epoch": 0.028416, "percentage": 2.84, "elapsed_time": "0:24:32", "remaining_time": "13:59:01"}
+{"current_steps": 112, "total_steps": 3906, "loss": 1.6841, "learning_rate": 3.9965777073615105e-05, "epoch": 0.028672, "percentage": 2.87, "elapsed_time": "0:24:45", "remaining_time": "13:58:43"}
+{"current_steps": 113, "total_steps": 3906, "loss": 1.7104, "learning_rate": 3.996482011585325e-05, "epoch": 0.028928, "percentage": 2.89, "elapsed_time": "0:24:58", "remaining_time": "13:58:26"}
+{"current_steps": 114, "total_steps": 3906, "loss": 1.6565, "learning_rate": 3.996384997426658e-05, "epoch": 0.029184, "percentage": 2.92, "elapsed_time": "0:25:11", "remaining_time": "13:58:10"}
+{"current_steps": 115, "total_steps": 3906, "loss": 1.6614, "learning_rate": 3.996286664949573e-05, "epoch": 0.02944, "percentage": 2.94, "elapsed_time": "0:25:25", "remaining_time": "13:57:55"}
+{"current_steps": 116, "total_steps": 3906, "loss": 1.716, "learning_rate": 3.996187014219004e-05, "epoch": 0.029696, "percentage": 2.97, "elapsed_time": "0:25:38", "remaining_time": "13:57:39"}
+{"current_steps": 117, "total_steps": 3906, "loss": 1.6901, "learning_rate": 3.9960860453007555e-05, "epoch": 0.029952, "percentage": 3.0, "elapsed_time": "0:25:51", "remaining_time": "13:57:24"}
+{"current_steps": 118, "total_steps": 3906, "loss": 1.7093, "learning_rate": 3.995983758261502e-05, "epoch": 0.030208, "percentage": 3.02, "elapsed_time": "0:26:04", "remaining_time": "13:57:09"}
+{"current_steps": 119, "total_steps": 3906, "loss": 1.6738, "learning_rate": 3.9958801531687904e-05, "epoch": 0.030464, "percentage": 3.05, "elapsed_time": "0:26:17", "remaining_time": "13:56:54"}
+{"current_steps": 120, "total_steps": 3906, "loss": 1.6735, "learning_rate": 3.995775230091035e-05, "epoch": 0.03072, "percentage": 3.07, "elapsed_time": "0:26:31", "remaining_time": "13:56:39"}
+{"current_steps": 121, "total_steps": 3906, "loss": 1.7062, "learning_rate": 3.995668989097525e-05, "epoch": 0.030976, "percentage": 3.1, "elapsed_time": "0:26:44", "remaining_time": "13:56:23"}
+{"current_steps": 122, "total_steps": 3906, "loss": 1.6642, "learning_rate": 3.995561430258413e-05, "epoch": 0.031232, "percentage": 3.12, "elapsed_time": "0:26:57", "remaining_time": "13:56:07"}
+{"current_steps": 123, "total_steps": 3906, "loss": 1.6459, "learning_rate": 3.995452553644728e-05, "epoch": 0.031488, "percentage": 3.15, "elapsed_time": "0:27:10", "remaining_time": "13:55:51"}
+{"current_steps": 124, "total_steps": 3906, "loss": 1.6897, "learning_rate": 3.995342359328367e-05, "epoch": 0.031744, "percentage": 3.17, "elapsed_time": "0:27:23", "remaining_time": "13:55:36"}
+{"current_steps": 125, "total_steps": 3906, "loss": 1.7132, "learning_rate": 3.995230847382096e-05, "epoch": 0.032, "percentage": 3.2, "elapsed_time": "0:27:37", "remaining_time": "13:55:21"}
+{"current_steps": 126, "total_steps": 3906, "loss": 1.581, "learning_rate": 3.995118017879554e-05, "epoch": 0.032256, "percentage": 3.23, "elapsed_time": "0:27:50", "remaining_time": "13:55:06"}
+{"current_steps": 127, "total_steps": 3906, "loss": 1.6804, "learning_rate": 3.995003870895247e-05, "epoch": 0.032512, "percentage": 3.25, "elapsed_time": "0:28:03", "remaining_time": "13:54:49"}
+{"current_steps": 128, "total_steps": 3906, "loss": 1.7045, "learning_rate": 3.994888406504552e-05, "epoch": 0.032768, "percentage": 3.28, "elapsed_time": "0:28:16", "remaining_time": "13:54:35"}
+{"current_steps": 129, "total_steps": 3906, "loss": 1.6389, "learning_rate": 3.994771624783718e-05, "epoch": 0.033024, "percentage": 3.3, "elapsed_time": "0:28:29", "remaining_time": "13:54:19"}
+{"current_steps": 130, "total_steps": 3906, "loss": 1.7005, "learning_rate": 3.994653525809859e-05, "epoch": 0.03328, "percentage": 3.33, "elapsed_time": "0:28:42", "remaining_time": "13:54:03"}
+{"current_steps": 131, "total_steps": 3906, "loss": 1.6992, "learning_rate": 3.9945341096609655e-05, "epoch": 0.033536, "percentage": 3.35, "elapsed_time": "0:28:56", "remaining_time": "13:53:48"}
+{"current_steps": 132, "total_steps": 3906, "loss": 1.6899, "learning_rate": 3.9944133764158925e-05, "epoch": 0.033792, "percentage": 3.38, "elapsed_time": "0:29:09", "remaining_time": "13:53:33"}
+{"current_steps": 133, "total_steps": 3906, "loss": 1.6429, "learning_rate": 3.9942913261543664e-05, "epoch": 0.034048, "percentage": 3.41, "elapsed_time": "0:29:22", "remaining_time": "13:53:17"}
+{"current_steps": 134, "total_steps": 3906, "loss": 1.6891, "learning_rate": 3.9941679589569836e-05, "epoch": 0.034304, "percentage": 3.43, "elapsed_time": "0:29:35", "remaining_time": "13:53:02"}
+{"current_steps": 135, "total_steps": 3906, "loss": 1.6226, "learning_rate": 3.99404327490521e-05, "epoch": 0.03456, "percentage": 3.46, "elapsed_time": "0:29:48", "remaining_time": "13:52:47"}
+{"current_steps": 136, "total_steps": 3906, "loss": 1.6255, "learning_rate": 3.9939172740813825e-05, "epoch": 0.034816, "percentage": 3.48, "elapsed_time": "0:30:01", "remaining_time": "13:52:32"}
+{"current_steps": 137, "total_steps": 3906, "loss": 1.7171, "learning_rate": 3.993789956568704e-05, "epoch": 0.035072, "percentage": 3.51, "elapsed_time": "0:30:15", "remaining_time": "13:52:17"}
+{"current_steps": 138, "total_steps": 3906, "loss": 1.5579, "learning_rate": 3.9936613224512495e-05, "epoch": 0.035328, "percentage": 3.53, "elapsed_time": "0:30:28", "remaining_time": "13:52:03"}
+{"current_steps": 139, "total_steps": 3906, "loss": 1.6577, "learning_rate": 3.993531371813963e-05, "epoch": 0.035584, "percentage": 3.56, "elapsed_time": "0:30:41", "remaining_time": "13:51:48"}
+{"current_steps": 140, "total_steps": 3906, "loss": 1.6809, "learning_rate": 3.9934001047426585e-05, "epoch": 0.03584, "percentage": 3.58, "elapsed_time": "0:30:54", "remaining_time": "13:51:34"}
+{"current_steps": 141, "total_steps": 3906, "loss": 1.627, "learning_rate": 3.9932675213240175e-05, "epoch": 0.036096, "percentage": 3.61, "elapsed_time": "0:31:08", "remaining_time": "13:51:19"}
+{"current_steps": 142, "total_steps": 3906, "loss": 1.6764, "learning_rate": 3.993133621645593e-05, "epoch": 0.036352, "percentage": 3.64, "elapsed_time": "0:31:21", "remaining_time": "13:51:05"}
+{"current_steps": 143, "total_steps": 3906, "loss": 1.6521, "learning_rate": 3.9929984057958055e-05, "epoch": 0.036608, "percentage": 3.66, "elapsed_time": "0:31:34", "remaining_time": "13:50:50"}
+{"current_steps": 144, "total_steps": 3906, "loss": 1.6497, "learning_rate": 3.992861873863944e-05, "epoch": 0.036864, "percentage": 3.69, "elapsed_time": "0:31:47", "remaining_time": "13:50:35"}
+{"current_steps": 145, "total_steps": 3906, "loss": 1.5884, "learning_rate": 3.9927240259401694e-05, "epoch": 0.03712, "percentage": 3.71, "elapsed_time": "0:32:00", "remaining_time": "13:50:21"}
+{"current_steps": 146, "total_steps": 3906, "loss": 1.5987, "learning_rate": 3.992584862115509e-05, "epoch": 0.037376, "percentage": 3.74, "elapsed_time": "0:32:13", "remaining_time": "13:50:06"}
+{"current_steps": 147, "total_steps": 3906, "loss": 1.5948, "learning_rate": 3.992444382481862e-05, "epoch": 0.037632, "percentage": 3.76, "elapsed_time": "0:32:27", "remaining_time": "13:49:51"}
+{"current_steps": 148, "total_steps": 3906, "loss": 1.6598, "learning_rate": 3.992302587131991e-05, "epoch": 0.037888, "percentage": 3.79, "elapsed_time": "0:32:40", "remaining_time": "13:49:37"}
+{"current_steps": 149, "total_steps": 3906, "loss": 1.5991, "learning_rate": 3.9921594761595334e-05, "epoch": 0.038144, "percentage": 3.81, "elapsed_time": "0:32:53", "remaining_time": "13:49:22"}
+{"current_steps": 150, "total_steps": 3906, "loss": 1.6543, "learning_rate": 3.992015049658992e-05, "epoch": 0.0384, "percentage": 3.84, "elapsed_time": "0:33:06", "remaining_time": "13:49:08"}
+{"current_steps": 151, "total_steps": 3906, "loss": 1.6648, "learning_rate": 3.991869307725741e-05, "epoch": 0.038656, "percentage": 3.87, "elapsed_time": "0:33:19", "remaining_time": "13:48:53"}
+{"current_steps": 152, "total_steps": 3906, "loss": 1.6041, "learning_rate": 3.9917222504560184e-05, "epoch": 0.038912, "percentage": 3.89, "elapsed_time": "0:33:33", "remaining_time": "13:48:39"}
+{"current_steps": 153, "total_steps": 3906, "loss": 1.6443, "learning_rate": 3.991573877946937e-05, "epoch": 0.039168, "percentage": 3.92, "elapsed_time": "0:33:46", "remaining_time": "13:48:23"}
+{"current_steps": 154, "total_steps": 3906, "loss": 1.7052, "learning_rate": 3.9914241902964725e-05, "epoch": 0.039424, "percentage": 3.94, "elapsed_time": "0:33:59", "remaining_time": "13:48:06"}
+{"current_steps": 155, "total_steps": 3906, "loss": 1.6251, "learning_rate": 3.991273187603473e-05, "epoch": 0.03968, "percentage": 3.97, "elapsed_time": "0:34:12", "remaining_time": "13:47:49"}
+{"current_steps": 156, "total_steps": 3906, "loss": 1.6287, "learning_rate": 3.9911208699676537e-05, "epoch": 0.039936, "percentage": 3.99, "elapsed_time": "0:34:25", "remaining_time": "13:47:34"}
+{"current_steps": 157, "total_steps": 3906, "loss": 1.6348, "learning_rate": 3.990967237489597e-05, "epoch": 0.040192, "percentage": 4.02, "elapsed_time": "0:34:38", "remaining_time": "13:47:19"}
+{"current_steps": 158, "total_steps": 3906, "loss": 1.6133, "learning_rate": 3.990812290270755e-05, "epoch": 0.040448, "percentage": 4.05, "elapsed_time": "0:34:51", "remaining_time": "13:47:05"}
+{"current_steps": 159, "total_steps": 3906, "loss": 1.6297, "learning_rate": 3.990656028413448e-05, "epoch": 0.040704, "percentage": 4.07, "elapsed_time": "0:35:05", "remaining_time": "13:46:51"}
+{"current_steps": 160, "total_steps": 3906, "loss": 1.6098, "learning_rate": 3.9904984520208626e-05, "epoch": 0.04096, "percentage": 4.1, "elapsed_time": "0:35:18", "remaining_time": "13:46:37"}
+{"current_steps": 161, "total_steps": 3906, "loss": 1.6131, "learning_rate": 3.9903395611970565e-05, "epoch": 0.041216, "percentage": 4.12, "elapsed_time": "0:35:31", "remaining_time": "13:46:23"}
+{"current_steps": 162, "total_steps": 3906, "loss": 1.5826, "learning_rate": 3.990179356046952e-05, "epoch": 0.041472, "percentage": 4.15, "elapsed_time": "0:35:44", "remaining_time": "13:46:08"}
+{"current_steps": 163, "total_steps": 3906, "loss": 1.6436, "learning_rate": 3.990017836676344e-05, "epoch": 0.041728, "percentage": 4.17, "elapsed_time": "0:35:58", "remaining_time": "13:45:58"}
+{"current_steps": 164, "total_steps": 3906, "loss": 1.6775, "learning_rate": 3.9898550031918886e-05, "epoch": 0.041984, "percentage": 4.2, "elapsed_time": "0:36:11", "remaining_time": "13:45:44"}
+{"current_steps": 165, "total_steps": 3906, "loss": 1.6481, "learning_rate": 3.9896908557011146e-05, "epoch": 0.04224, "percentage": 4.22, "elapsed_time": "0:36:24", "remaining_time": "13:45:29"}
+{"current_steps": 166, "total_steps": 3906, "loss": 1.6508, "learning_rate": 3.989525394312418e-05, "epoch": 0.042496, "percentage": 4.25, "elapsed_time": "0:36:37", "remaining_time": "13:45:16"}
+{"current_steps": 167, "total_steps": 3906, "loss": 1.6493, "learning_rate": 3.989358619135062e-05, "epoch": 0.042752, "percentage": 4.28, "elapsed_time": "0:36:50", "remaining_time": "13:44:59"}
+{"current_steps": 168, "total_steps": 3906, "loss": 1.6417, "learning_rate": 3.989190530279175e-05, "epoch": 0.043008, "percentage": 4.3, "elapsed_time": "0:37:03", "remaining_time": "13:44:43"}
+{"current_steps": 169, "total_steps": 3906, "loss": 1.5947, "learning_rate": 3.9890211278557576e-05, "epoch": 0.043264, "percentage": 4.33, "elapsed_time": "0:37:17", "remaining_time": "13:44:29"}
+{"current_steps": 170, "total_steps": 3906, "loss": 1.6538, "learning_rate": 3.988850411976674e-05, "epoch": 0.04352, "percentage": 4.35, "elapsed_time": "0:37:30", "remaining_time": "13:44:15"}
+{"current_steps": 171, "total_steps": 3906, "loss": 1.5596, "learning_rate": 3.988678382754656e-05, "epoch": 0.043776, "percentage": 4.38, "elapsed_time": "0:37:43", "remaining_time": "13:44:00"}
+{"current_steps": 172, "total_steps": 3906, "loss": 1.6272, "learning_rate": 3.988505040303304e-05, "epoch": 0.044032, "percentage": 4.4, "elapsed_time": "0:37:56", "remaining_time": "13:43:46"}
+{"current_steps": 173, "total_steps": 3906, "loss": 1.6455, "learning_rate": 3.9883303847370866e-05, "epoch": 0.044288, "percentage": 4.43, "elapsed_time": "0:38:09", "remaining_time": "13:43:32"}
+{"current_steps": 174, "total_steps": 3906, "loss": 1.6205, "learning_rate": 3.988154416171336e-05, "epoch": 0.044544, "percentage": 4.45, "elapsed_time": "0:38:23", "remaining_time": "13:43:18"}
+{"current_steps": 175, "total_steps": 3906, "loss": 1.6421, "learning_rate": 3.987977134722255e-05, "epoch": 0.0448, "percentage": 4.48, "elapsed_time": "0:38:36", "remaining_time": "13:43:04"}
+{"current_steps": 176, "total_steps": 3906, "loss": 1.6395, "learning_rate": 3.987798540506911e-05, "epoch": 0.045056, "percentage": 4.51, "elapsed_time": "0:38:49", "remaining_time": "13:42:49"}
+{"current_steps": 177, "total_steps": 3906, "loss": 1.5974, "learning_rate": 3.9876186336432404e-05, "epoch": 0.045312, "percentage": 4.53, "elapsed_time": "0:39:02", "remaining_time": "13:42:34"}
+{"current_steps": 178, "total_steps": 3906, "loss": 1.6324, "learning_rate": 3.987437414250044e-05, "epoch": 0.045568, "percentage": 4.56, "elapsed_time": "0:39:15", "remaining_time": "13:42:20"}
+{"current_steps": 179, "total_steps": 3906, "loss": 1.6155, "learning_rate": 3.9872548824469913e-05, "epoch": 0.045824, "percentage": 4.58, "elapsed_time": "0:39:28", "remaining_time": "13:42:04"}
+{"current_steps": 180, "total_steps": 3906, "loss": 1.6201, "learning_rate": 3.9870710383546166e-05, "epoch": 0.04608, "percentage": 4.61, "elapsed_time": "0:39:42", "remaining_time": "13:41:50"}
+{"current_steps": 181, "total_steps": 3906, "loss": 1.6282, "learning_rate": 3.986885882094324e-05, "epoch": 0.046336, "percentage": 4.63, "elapsed_time": "0:39:55", "remaining_time": "13:41:35"}
+{"current_steps": 182, "total_steps": 3906, "loss": 1.6151, "learning_rate": 3.98669941378838e-05, "epoch": 0.046592, "percentage": 4.66, "elapsed_time": "0:40:08", "remaining_time": "13:41:21"}
+{"current_steps": 183, "total_steps": 3906, "loss": 1.6322, "learning_rate": 3.986511633559919e-05, "epoch": 0.046848, "percentage": 4.69, "elapsed_time": "0:40:21", "remaining_time": "13:41:07"}
+{"current_steps": 184, "total_steps": 3906, "loss": 1.5858, "learning_rate": 3.986322541532944e-05, "epoch": 0.047104, "percentage": 4.71, "elapsed_time": "0:40:34", "remaining_time": "13:40:54"}
+{"current_steps": 185, "total_steps": 3906, "loss": 1.6501, "learning_rate": 3.986132137832322e-05, "epoch": 0.04736, "percentage": 4.74, "elapsed_time": "0:40:48", "remaining_time": "13:40:40"}
+{"current_steps": 186, "total_steps": 3906, "loss": 1.619, "learning_rate": 3.985940422583786e-05, "epoch": 0.047616, "percentage": 4.76, "elapsed_time": "0:41:01", "remaining_time": "13:40:26"}
+{"current_steps": 187, "total_steps": 3906, "loss": 1.6122, "learning_rate": 3.985747395913936e-05, "epoch": 0.047872, "percentage": 4.79, "elapsed_time": "0:41:14", "remaining_time": "13:40:13"}
+{"current_steps": 188, "total_steps": 3906, "loss": 1.5991, "learning_rate": 3.9855530579502375e-05, "epoch": 0.048128, "percentage": 4.81, "elapsed_time": "0:41:27", "remaining_time": "13:39:58"}
+{"current_steps": 189, "total_steps": 3906, "loss": 1.6093, "learning_rate": 3.9853574088210224e-05, "epoch": 0.048384, "percentage": 4.84, "elapsed_time": "0:41:40", "remaining_time": "13:39:43"}
+{"current_steps": 190, "total_steps": 3906, "loss": 1.644, "learning_rate": 3.985160448655488e-05, "epoch": 0.04864, "percentage": 4.86, "elapsed_time": "0:41:54", "remaining_time": "13:39:28"}
+{"current_steps": 191, "total_steps": 3906, "loss": 1.6516, "learning_rate": 3.984962177583698e-05, "epoch": 0.048896, "percentage": 4.89, "elapsed_time": "0:42:07", "remaining_time": "13:39:15"}
+{"current_steps": 192, "total_steps": 3906, "loss": 1.5579, "learning_rate": 3.984762595736581e-05, "epoch": 0.049152, "percentage": 4.92, "elapsed_time": "0:42:20", "remaining_time": "13:39:01"}
+{"current_steps": 193, "total_steps": 3906, "loss": 1.6606, "learning_rate": 3.98456170324593e-05, "epoch": 0.049408, "percentage": 4.94, "elapsed_time": "0:42:33", "remaining_time": "13:38:46"}
+{"current_steps": 194, "total_steps": 3906, "loss": 1.602, "learning_rate": 3.9843595002444075e-05, "epoch": 0.049664, "percentage": 4.97, "elapsed_time": "0:42:46", "remaining_time": "13:38:32"}
+{"current_steps": 195, "total_steps": 3906, "loss": 1.5955, "learning_rate": 3.984155986865537e-05, "epoch": 0.04992, "percentage": 4.99, "elapsed_time": "0:42:59", "remaining_time": "13:38:16"}
+{"current_steps": 196, "total_steps": 3906, "loss": 1.5357, "learning_rate": 3.9839511632437096e-05, "epoch": 0.050176, "percentage": 5.02, "elapsed_time": "0:43:13", "remaining_time": "13:38:02"}
+{"current_steps": 197, "total_steps": 3906, "loss": 1.5909, "learning_rate": 3.9837450295141816e-05, "epoch": 0.050432, "percentage": 5.04, "elapsed_time": "0:43:26", "remaining_time": "13:37:48"}
+{"current_steps": 198, "total_steps": 3906, "loss": 1.6708, "learning_rate": 3.983537585813073e-05, "epoch": 0.050688, "percentage": 5.07, "elapsed_time": "0:43:39", "remaining_time": "13:37:34"}
+{"current_steps": 199, "total_steps": 3906, "loss": 1.5605, "learning_rate": 3.98332883227737e-05, "epoch": 0.050944, "percentage": 5.09, "elapsed_time": "0:43:52", "remaining_time": "13:37:18"}
+{"current_steps": 200, "total_steps": 3906, "loss": 1.6156, "learning_rate": 3.9831187690449254e-05, "epoch": 0.0512, "percentage": 5.12, "elapsed_time": "0:44:05", "remaining_time": "13:37:04"}
+{"current_steps": 201, "total_steps": 3906, "loss": 1.624, "learning_rate": 3.9829073962544525e-05, "epoch": 0.051456, "percentage": 5.15, "elapsed_time": "0:44:18", "remaining_time": "13:36:50"}
+{"current_steps": 202, "total_steps": 3906, "loss": 1.6255, "learning_rate": 3.9826947140455334e-05, "epoch": 0.051712, "percentage": 5.17, "elapsed_time": "0:44:31", "remaining_time": "13:36:35"}
+{"current_steps": 203, "total_steps": 3906, "loss": 1.5554, "learning_rate": 3.982480722558613e-05, "epoch": 0.051968, "percentage": 5.2, "elapsed_time": "0:44:45", "remaining_time": "13:36:21"}
+{"current_steps": 204, "total_steps": 3906, "loss": 1.6158, "learning_rate": 3.982265421935001e-05, "epoch": 0.052224, "percentage": 5.22, "elapsed_time": "0:44:58", "remaining_time": "13:36:07"}
+{"current_steps": 205, "total_steps": 3906, "loss": 1.6056, "learning_rate": 3.982048812316872e-05, "epoch": 0.05248, "percentage": 5.25, "elapsed_time": "0:45:11", "remaining_time": "13:35:54"}
+{"current_steps": 206, "total_steps": 3906, "loss": 1.6017, "learning_rate": 3.981830893847265e-05, "epoch": 0.052736, "percentage": 5.27, "elapsed_time": "0:45:24", "remaining_time": "13:35:40"}
+{"current_steps": 207, "total_steps": 3906, "loss": 1.6227, "learning_rate": 3.981611666670082e-05, "epoch": 0.052992, "percentage": 5.3, "elapsed_time": "0:45:38", "remaining_time": "13:35:27"}
+{"current_steps": 208, "total_steps": 3906, "loss": 1.6319, "learning_rate": 3.9813911309300916e-05, "epoch": 0.053248, "percentage": 5.33, "elapsed_time": "0:45:51", "remaining_time": "13:35:13"}
+{"current_steps": 209, "total_steps": 3906, "loss": 1.627, "learning_rate": 3.981169286772925e-05, "epoch": 0.053504, "percentage": 5.35, "elapsed_time": "0:46:04", "remaining_time": "13:34:58"}
+{"current_steps": 210, "total_steps": 3906, "loss": 1.5803, "learning_rate": 3.980946134345077e-05, "epoch": 0.05376, "percentage": 5.38, "elapsed_time": "0:46:17", "remaining_time": "13:34:44"}
+{"current_steps": 211, "total_steps": 3906, "loss": 1.5945, "learning_rate": 3.980721673793907e-05, "epoch": 0.054016, "percentage": 5.4, "elapsed_time": "0:46:30", "remaining_time": "13:34:30"}
+{"current_steps": 212, "total_steps": 3906, "loss": 1.6166, "learning_rate": 3.9804959052676386e-05, "epoch": 0.054272, "percentage": 5.43, "elapsed_time": "0:46:43", "remaining_time": "13:34:16"}
+{"current_steps": 213, "total_steps": 3906, "loss": 1.6014, "learning_rate": 3.980268828915359e-05, "epoch": 0.054528, "percentage": 5.45, "elapsed_time": "0:46:57", "remaining_time": "13:34:02"}
+{"current_steps": 214, "total_steps": 3906, "loss": 1.6061, "learning_rate": 3.980040444887017e-05, "epoch": 0.054784, "percentage": 5.48, "elapsed_time": "0:47:10", "remaining_time": "13:33:48"}
+{"current_steps": 215, "total_steps": 3906, "loss": 1.5752, "learning_rate": 3.979810753333428e-05, "epoch": 0.05504, "percentage": 5.5, "elapsed_time": "0:47:23", "remaining_time": "13:33:35"}
+{"current_steps": 216, "total_steps": 3906, "loss": 1.5667, "learning_rate": 3.979579754406271e-05, "epoch": 0.055296, "percentage": 5.53, "elapsed_time": "0:47:36", "remaining_time": "13:33:22"}
+{"current_steps": 217, "total_steps": 3906, "loss": 1.577, "learning_rate": 3.979347448258083e-05, "epoch": 0.055552, "percentage": 5.56, "elapsed_time": "0:47:49", "remaining_time": "13:33:09"}
+{"current_steps": 218, "total_steps": 3906, "loss": 1.6513, "learning_rate": 3.979113835042271e-05, "epoch": 0.055808, "percentage": 5.58, "elapsed_time": "0:48:03", "remaining_time": "13:32:55"}
+{"current_steps": 219, "total_steps": 3906, "loss": 1.5861, "learning_rate": 3.9788789149131003e-05, "epoch": 0.056064, "percentage": 5.61, "elapsed_time": "0:48:16", "remaining_time": "13:32:39"}
+{"current_steps": 220, "total_steps": 3906, "loss": 1.6002, "learning_rate": 3.978642688025703e-05, "epoch": 0.05632, "percentage": 5.63, "elapsed_time": "0:48:29", "remaining_time": "13:32:25"}
+{"current_steps": 221, "total_steps": 3906, "loss": 1.5682, "learning_rate": 3.978405154536071e-05, "epoch": 0.056576, "percentage": 5.66, "elapsed_time": "0:48:42", "remaining_time": "13:32:11"}
+{"current_steps": 222, "total_steps": 3906, "loss": 1.5688, "learning_rate": 3.9781663146010595e-05, "epoch": 0.056832, "percentage": 5.68, "elapsed_time": "0:48:55", "remaining_time": "13:31:56"}
+{"current_steps": 223, "total_steps": 3906, "loss": 1.5846, "learning_rate": 3.977926168378389e-05, "epoch": 0.057088, "percentage": 5.71, "elapsed_time": "0:49:08", "remaining_time": "13:31:43"}
+{"current_steps": 224, "total_steps": 3906, "loss": 1.6461, "learning_rate": 3.977684716026639e-05, "epoch": 0.057344, "percentage": 5.73, "elapsed_time": "0:49:22", "remaining_time": "13:31:29"}
+{"current_steps": 225, "total_steps": 3906, "loss": 1.5788, "learning_rate": 3.977441957705254e-05, "epoch": 0.0576, "percentage": 5.76, "elapsed_time": "0:49:35", "remaining_time": "13:31:15"}
+{"current_steps": 226, "total_steps": 3906, "loss": 1.6239, "learning_rate": 3.97719789357454e-05, "epoch": 0.057856, "percentage": 5.79, "elapsed_time": "0:49:48", "remaining_time": "13:31:02"}
+{"current_steps": 227, "total_steps": 3906, "loss": 1.5473, "learning_rate": 3.9769525237956655e-05, "epoch": 0.058112, "percentage": 5.81, "elapsed_time": "0:50:01", "remaining_time": "13:30:48"}
+{"current_steps": 228, "total_steps": 3906, "loss": 1.5923, "learning_rate": 3.976705848530662e-05, "epoch": 0.058368, "percentage": 5.84, "elapsed_time": "0:50:14", "remaining_time": "13:30:34"}
+{"current_steps": 229, "total_steps": 3906, "loss": 1.603, "learning_rate": 3.9764578679424204e-05, "epoch": 0.058624, "percentage": 5.86, "elapsed_time": "0:50:28", "remaining_time": "13:30:21"}
+{"current_steps": 230, "total_steps": 3906, "loss": 1.5565, "learning_rate": 3.976208582194696e-05, "epoch": 0.05888, "percentage": 5.89, "elapsed_time": "0:50:41", "remaining_time": "13:30:08"}
+{"current_steps": 231, "total_steps": 3906, "loss": 1.5812, "learning_rate": 3.975957991452107e-05, "epoch": 0.059136, "percentage": 5.91, "elapsed_time": "0:50:54", "remaining_time": "13:29:54"}
+{"current_steps": 232, "total_steps": 3906, "loss": 1.581, "learning_rate": 3.9757060958801286e-05, "epoch": 0.059392, "percentage": 5.94, "elapsed_time": "0:51:07", "remaining_time": "13:29:40"}
+{"current_steps": 233, "total_steps": 3906, "loss": 1.5698, "learning_rate": 3.9754528956451034e-05, "epoch": 0.059648, "percentage": 5.97, "elapsed_time": "0:51:20", "remaining_time": "13:29:25"}
+{"current_steps": 234, "total_steps": 3906, "loss": 1.6069, "learning_rate": 3.975198390914232e-05, "epoch": 0.059904, "percentage": 5.99, "elapsed_time": "0:51:33", "remaining_time": "13:29:10"}
+{"current_steps": 235, "total_steps": 3906, "loss": 1.586, "learning_rate": 3.974942581855577e-05, "epoch": 0.06016, "percentage": 6.02, "elapsed_time": "0:51:47", "remaining_time": "13:28:56"}
+{"current_steps": 236, "total_steps": 3906, "loss": 1.5755, "learning_rate": 3.974685468638063e-05, "epoch": 0.060416, "percentage": 6.04, "elapsed_time": "0:52:00", "remaining_time": "13:28:43"}
+{"current_steps": 237, "total_steps": 3906, "loss": 1.5765, "learning_rate": 3.9744270514314756e-05, "epoch": 0.060672, "percentage": 6.07, "elapsed_time": "0:52:13", "remaining_time": "13:28:29"}
+{"current_steps": 238, "total_steps": 3906, "loss": 1.5478, "learning_rate": 3.974167330406461e-05, "epoch": 0.060928, "percentage": 6.09, "elapsed_time": "0:52:26", "remaining_time": "13:28:16"}
+{"current_steps": 239, "total_steps": 3906, "loss": 1.575, "learning_rate": 3.973906305734526e-05, "epoch": 0.061184, "percentage": 6.12, "elapsed_time": "0:52:39", "remaining_time": "13:28:03"}
+{"current_steps": 240, "total_steps": 3906, "loss": 1.5564, "learning_rate": 3.973643977588041e-05, "epoch": 0.06144, "percentage": 6.14, "elapsed_time": "0:52:53", "remaining_time": "13:27:50"}
+{"current_steps": 241, "total_steps": 3906, "loss": 1.5936, "learning_rate": 3.973380346140233e-05, "epoch": 0.061696, "percentage": 6.17, "elapsed_time": "0:53:06", "remaining_time": "13:27:36"}
+{"current_steps": 242, "total_steps": 3906, "loss": 1.5702, "learning_rate": 3.973115411565193e-05, "epoch": 0.061952, "percentage": 6.2, "elapsed_time": "0:53:19", "remaining_time": "13:27:22"}
+{"current_steps": 243, "total_steps": 3906, "loss": 1.5163, "learning_rate": 3.9728491740378705e-05, "epoch": 0.062208, "percentage": 6.22, "elapsed_time": "0:53:32", "remaining_time": "13:27:09"}
+{"current_steps": 244, "total_steps": 3906, "loss": 1.5727, "learning_rate": 3.972581633734077e-05, "epoch": 0.062464, "percentage": 6.25, "elapsed_time": "0:53:45", "remaining_time": "13:26:53"}
+{"current_steps": 245, "total_steps": 3906, "loss": 1.5451, "learning_rate": 3.972312790830483e-05, "epoch": 0.06272, "percentage": 6.27, "elapsed_time": "0:53:59", "remaining_time": "13:26:40"}
+{"current_steps": 246, "total_steps": 3906, "loss": 1.5725, "learning_rate": 3.9720426455046195e-05, "epoch": 0.062976, "percentage": 6.3, "elapsed_time": "0:54:12", "remaining_time": "13:26:26"}
+{"current_steps": 247, "total_steps": 3906, "loss": 1.5935, "learning_rate": 3.971771197934878e-05, "epoch": 0.063232, "percentage": 6.32, "elapsed_time": "0:54:25", "remaining_time": "13:26:13"}
+{"current_steps": 248, "total_steps": 3906, "loss": 1.5908, "learning_rate": 3.97149844830051e-05, "epoch": 0.063488, "percentage": 6.35, "elapsed_time": "0:54:38", "remaining_time": "13:26:00"}
+{"current_steps": 249, "total_steps": 3906, "loss": 1.5662, "learning_rate": 3.971224396781626e-05, "epoch": 0.063744, "percentage": 6.37, "elapsed_time": "0:54:51", "remaining_time": "13:25:46"}
+{"current_steps": 250, "total_steps": 3906, "loss": 1.5763, "learning_rate": 3.970949043559197e-05, "epoch": 0.064, "percentage": 6.4, "elapsed_time": "0:55:05", "remaining_time": "13:25:33"}
+{"current_steps": 251, "total_steps": 3906, "loss": 1.5633, "learning_rate": 3.970672388815052e-05, "epoch": 0.064256, "percentage": 6.43, "elapsed_time": "0:55:18", "remaining_time": "13:25:19"}
+{"current_steps": 252, "total_steps": 3906, "loss": 1.5489, "learning_rate": 3.970394432731883e-05, "epoch": 0.064512, "percentage": 6.45, "elapsed_time": "0:55:31", "remaining_time": "13:25:05"}
+{"current_steps": 253, "total_steps": 3906, "loss": 1.5615, "learning_rate": 3.9701151754932376e-05, "epoch": 0.064768, "percentage": 6.48, "elapsed_time": "0:55:44", "remaining_time": "13:24:50"}
+{"current_steps": 254, "total_steps": 3906, "loss": 1.5535, "learning_rate": 3.969834617283525e-05, "epoch": 0.065024, "percentage": 6.5, "elapsed_time": "0:55:57", "remaining_time": "13:24:35"}
+{"current_steps": 255, "total_steps": 3906, "loss": 1.6105, "learning_rate": 3.9695527582880105e-05, "epoch": 0.06528, "percentage": 6.53, "elapsed_time": "0:56:10", "remaining_time": "13:24:20"}
+{"current_steps": 256, "total_steps": 3906, "loss": 1.6258, "learning_rate": 3.969269598692823e-05, "epoch": 0.065536, "percentage": 6.55, "elapsed_time": "0:56:23", "remaining_time": "13:24:05"}
+{"current_steps": 257, "total_steps": 3906, "loss": 1.595, "learning_rate": 3.968985138684947e-05, "epoch": 0.065792, "percentage": 6.58, "elapsed_time": "0:56:36", "remaining_time": "13:23:51"}
+{"current_steps": 258, "total_steps": 3906, "loss": 1.5708, "learning_rate": 3.968699378452226e-05, "epoch": 0.066048, "percentage": 6.61, "elapsed_time": "0:56:50", "remaining_time": "13:23:38"}
+{"current_steps": 259, "total_steps": 3906, "loss": 1.524, "learning_rate": 3.968412318183362e-05, "epoch": 0.066304, "percentage": 6.63, "elapsed_time": "0:57:03", "remaining_time": "13:23:25"}
+{"current_steps": 260, "total_steps": 3906, "loss": 1.5344, "learning_rate": 3.968123958067917e-05, "epoch": 0.06656, "percentage": 6.66, "elapsed_time": "0:57:16", "remaining_time": "13:23:12"}
+{"current_steps": 261, "total_steps": 3906, "loss": 1.557, "learning_rate": 3.9678342982963105e-05, "epoch": 0.066816, "percentage": 6.68, "elapsed_time": "0:57:29", "remaining_time": "13:22:58"}
+{"current_steps": 262, "total_steps": 3906, "loss": 1.5299, "learning_rate": 3.96754333905982e-05, "epoch": 0.067072, "percentage": 6.71, "elapsed_time": "0:57:43", "remaining_time": "13:22:45"}
+{"current_steps": 263, "total_steps": 3906, "loss": 1.5723, "learning_rate": 3.96725108055058e-05, "epoch": 0.067328, "percentage": 6.73, "elapsed_time": "0:57:56", "remaining_time": "13:22:32"}
+{"current_steps": 264, "total_steps": 3906, "loss": 1.5963, "learning_rate": 3.966957522961586e-05, "epoch": 0.067584, "percentage": 6.76, "elapsed_time": "0:58:09", "remaining_time": "13:22:18"}
+{"current_steps": 265, "total_steps": 3906, "loss": 1.5364, "learning_rate": 3.966662666486689e-05, "epoch": 0.06784, "percentage": 6.78, "elapsed_time": "0:58:22", "remaining_time": "13:22:04"}
+{"current_steps": 266, "total_steps": 3906, "loss": 1.5923, "learning_rate": 3.966366511320598e-05, "epoch": 0.068096, "percentage": 6.81, "elapsed_time": "0:58:35", "remaining_time": "13:21:50"}
+{"current_steps": 267, "total_steps": 3906, "loss": 1.5576, "learning_rate": 3.966069057658881e-05, "epoch": 0.068352, "percentage": 6.84, "elapsed_time": "0:58:48", "remaining_time": "13:21:36"}
+{"current_steps": 268, "total_steps": 3906, "loss": 1.6256, "learning_rate": 3.96577030569796e-05, "epoch": 0.068608, "percentage": 6.86, "elapsed_time": "0:59:02", "remaining_time": "13:21:23"}
+{"current_steps": 269, "total_steps": 3906, "loss": 1.5431, "learning_rate": 3.965470255635119e-05, "epoch": 0.068864, "percentage": 6.89, "elapsed_time": "0:59:15", "remaining_time": "13:21:12"}
+{"current_steps": 270, "total_steps": 3906, "loss": 1.5816, "learning_rate": 3.965168907668496e-05, "epoch": 0.06912, "percentage": 6.91, "elapsed_time": "0:59:28", "remaining_time": "13:20:59"}
+{"current_steps": 271, "total_steps": 3906, "loss": 1.59, "learning_rate": 3.9648662619970866e-05, "epoch": 0.069376, "percentage": 6.94, "elapsed_time": "0:59:41", "remaining_time": "13:20:46"}
+{"current_steps": 272, "total_steps": 3906, "loss": 1.5574, "learning_rate": 3.964562318820744e-05, "epoch": 0.069632, "percentage": 6.96, "elapsed_time": "0:59:55", "remaining_time": "13:20:32"}
+{"current_steps": 273, "total_steps": 3906, "loss": 1.5142, "learning_rate": 3.964257078340178e-05, "epoch": 0.069888, "percentage": 6.99, "elapsed_time": "1:00:08", "remaining_time": "13:20:19"}
+{"current_steps": 274, "total_steps": 3906, "loss": 1.5168, "learning_rate": 3.963950540756955e-05, "epoch": 0.070144, "percentage": 7.01, "elapsed_time": "1:00:21", "remaining_time": "13:20:04"}
+{"current_steps": 275, "total_steps": 3906, "loss": 1.581, "learning_rate": 3.963642706273499e-05, "epoch": 0.0704, "percentage": 7.04, "elapsed_time": "1:00:34", "remaining_time": "13:19:50"}
+{"current_steps": 276, "total_steps": 3906, "loss": 1.5589, "learning_rate": 3.9633335750930874e-05, "epoch": 0.070656, "percentage": 7.07, "elapsed_time": "1:00:47", "remaining_time": "13:19:36"}
+{"current_steps": 277, "total_steps": 3906, "loss": 1.5933, "learning_rate": 3.963023147419858e-05, "epoch": 0.070912, "percentage": 7.09, "elapsed_time": "1:01:00", "remaining_time": "13:19:21"}
+{"current_steps": 278, "total_steps": 3906, "loss": 1.5605, "learning_rate": 3.9627114234588e-05, "epoch": 0.071168, "percentage": 7.12, "elapsed_time": "1:01:14", "remaining_time": "13:19:07"}
+{"current_steps": 279, "total_steps": 3906, "loss": 1.6025, "learning_rate": 3.962398403415763e-05, "epoch": 0.071424, "percentage": 7.14, "elapsed_time": "1:01:27", "remaining_time": "13:18:53"}
+{"current_steps": 280, "total_steps": 3906, "loss": 1.5318, "learning_rate": 3.9620840874974505e-05, "epoch": 0.07168, "percentage": 7.17, "elapsed_time": "1:01:40", "remaining_time": "13:18:40"}
+{"current_steps": 281, "total_steps": 3906, "loss": 1.5637, "learning_rate": 3.961768475911421e-05, "epoch": 0.071936, "percentage": 7.19, "elapsed_time": "1:01:53", "remaining_time": "13:18:26"}
+{"current_steps": 282, "total_steps": 3906, "loss": 1.574, "learning_rate": 3.9614515688660906e-05, "epoch": 0.072192, "percentage": 7.22, "elapsed_time": "1:02:06", "remaining_time": "13:18:13"}
+{"current_steps": 283, "total_steps": 3906, "loss": 1.5605, "learning_rate": 3.961133366570729e-05, "epoch": 0.072448, "percentage": 7.25, "elapsed_time": "1:02:20", "remaining_time": "13:18:00"}
+{"current_steps": 284, "total_steps": 3906, "loss": 1.5433, "learning_rate": 3.960813869235462e-05, "epoch": 0.072704, "percentage": 7.27, "elapsed_time": "1:02:33", "remaining_time": "13:17:46"}
+{"current_steps": 285, "total_steps": 3906, "loss": 1.5768, "learning_rate": 3.960493077071272e-05, "epoch": 0.07296, "percentage": 7.3, "elapsed_time": "1:02:46", "remaining_time": "13:17:33"}
+{"current_steps": 286, "total_steps": 3906, "loss": 1.5973, "learning_rate": 3.960170990289992e-05, "epoch": 0.073216, "percentage": 7.32, "elapsed_time": "1:02:59", "remaining_time": "13:17:19"}
+{"current_steps": 287, "total_steps": 3906, "loss": 1.5591, "learning_rate": 3.9598476091043165e-05, "epoch": 0.073472, "percentage": 7.35, "elapsed_time": "1:03:12", "remaining_time": "13:17:06"}
+{"current_steps": 288, "total_steps": 3906, "loss": 1.5594, "learning_rate": 3.9595229337277884e-05, "epoch": 0.073728, "percentage": 7.37, "elapsed_time": "1:03:25", "remaining_time": "13:16:52"}
+{"current_steps": 289, "total_steps": 3906, "loss": 1.6103, "learning_rate": 3.9591969643748094e-05, "epoch": 0.073984, "percentage": 7.4, "elapsed_time": "1:03:39", "remaining_time": "13:16:39"}
+{"current_steps": 290, "total_steps": 3906, "loss": 1.5677, "learning_rate": 3.958869701260633e-05, "epoch": 0.07424, "percentage": 7.42, "elapsed_time": "1:03:52", "remaining_time": "13:16:25"}
+{"current_steps": 291, "total_steps": 3906, "loss": 1.5817, "learning_rate": 3.95854114460137e-05, "epoch": 0.074496, "percentage": 7.45, "elapsed_time": "1:04:05", "remaining_time": "13:16:12"}
+{"current_steps": 292, "total_steps": 3906, "loss": 1.6012, "learning_rate": 3.958211294613983e-05, "epoch": 0.074752, "percentage": 7.48, "elapsed_time": "1:04:18", "remaining_time": "13:15:58"}
+{"current_steps": 293, "total_steps": 3906, "loss": 1.5017, "learning_rate": 3.957880151516289e-05, "epoch": 0.075008, "percentage": 7.5, "elapsed_time": "1:04:31", "remaining_time": "13:15:45"}
+{"current_steps": 294, "total_steps": 3906, "loss": 1.5916, "learning_rate": 3.957547715526959e-05, "epoch": 0.075264, "percentage": 7.53, "elapsed_time": "1:04:45", "remaining_time": "13:15:31"}
+{"current_steps": 295, "total_steps": 3906, "loss": 1.6245, "learning_rate": 3.957213986865519e-05, "epoch": 0.07552, "percentage": 7.55, "elapsed_time": "1:04:58", "remaining_time": "13:15:18"}
+{"current_steps": 296, "total_steps": 3906, "loss": 1.569, "learning_rate": 3.956878965752348e-05, "epoch": 0.075776, "percentage": 7.58, "elapsed_time": "1:05:11", "remaining_time": "13:15:05"}
+{"current_steps": 297, "total_steps": 3906, "loss": 1.5321, "learning_rate": 3.956542652408676e-05, "epoch": 0.076032, "percentage": 7.6, "elapsed_time": "1:05:24", "remaining_time": "13:14:52"}
+{"current_steps": 298, "total_steps": 3906, "loss": 1.5182, "learning_rate": 3.9562050470565896e-05, "epoch": 0.076288, "percentage": 7.63, "elapsed_time": "1:05:37", "remaining_time": "13:14:38"}
+{"current_steps": 299, "total_steps": 3906, "loss": 1.5448, "learning_rate": 3.9558661499190287e-05, "epoch": 0.076544, "percentage": 7.65, "elapsed_time": "1:05:51", "remaining_time": "13:14:24"}
+{"current_steps": 300, "total_steps": 3906, "loss": 1.5386, "learning_rate": 3.955525961219783e-05, "epoch": 0.0768, "percentage": 7.68, "elapsed_time": "1:06:04", "remaining_time": "13:14:09"}
+{"current_steps": 301, "total_steps": 3906, "loss": 1.521, "learning_rate": 3.9551844811834984e-05, "epoch": 0.077056, "percentage": 7.71, "elapsed_time": "1:06:17", "remaining_time": "13:13:54"}
+{"current_steps": 302, "total_steps": 3906, "loss": 1.5479, "learning_rate": 3.954841710035672e-05, "epoch": 0.077312, "percentage": 7.73, "elapsed_time": "1:06:30", "remaining_time": "13:13:40"}
+{"current_steps": 303, "total_steps": 3906, "loss": 1.5287, "learning_rate": 3.954497648002654e-05, "epoch": 0.077568, "percentage": 7.76, "elapsed_time": "1:06:43", "remaining_time": "13:13:27"}
+{"current_steps": 304, "total_steps": 3906, "loss": 1.5556, "learning_rate": 3.9541522953116446e-05, "epoch": 0.077824, "percentage": 7.78, "elapsed_time": "1:06:56", "remaining_time": "13:13:13"}
+{"current_steps": 305, "total_steps": 3906, "loss": 1.539, "learning_rate": 3.953805652190701e-05, "epoch": 0.07808, "percentage": 7.81, "elapsed_time": "1:07:10", "remaining_time": "13:13:00"}
+{"current_steps": 306, "total_steps": 3906, "loss": 1.5823, "learning_rate": 3.9534577188687285e-05, "epoch": 0.078336, "percentage": 7.83, "elapsed_time": "1:07:23", "remaining_time": "13:12:47"}
+{"current_steps": 307, "total_steps": 3906, "loss": 1.5869, "learning_rate": 3.9531084955754865e-05, "epoch": 0.078592, "percentage": 7.86, "elapsed_time": "1:07:36", "remaining_time": "13:12:36"}
+{"current_steps": 308, "total_steps": 3906, "loss": 1.5601, "learning_rate": 3.952757982541585e-05, "epoch": 0.078848, "percentage": 7.89, "elapsed_time": "1:07:49", "remaining_time": "13:12:21"}
+{"current_steps": 309, "total_steps": 3906, "loss": 1.5167, "learning_rate": 3.952406179998487e-05, "epoch": 0.079104, "percentage": 7.91, "elapsed_time": "1:08:02", "remaining_time": "13:12:08"}
+{"current_steps": 310, "total_steps": 3906, "loss": 1.5454, "learning_rate": 3.952053088178506e-05, "epoch": 0.07936, "percentage": 7.94, "elapsed_time": "1:08:16", "remaining_time": "13:11:54"}
+{"current_steps": 311, "total_steps": 3906, "loss": 1.5442, "learning_rate": 3.951698707314808e-05, "epoch": 0.079616, "percentage": 7.96, "elapsed_time": "1:08:29", "remaining_time": "13:11:40"}
+{"current_steps": 312, "total_steps": 3906, "loss": 1.5223, "learning_rate": 3.9513430376414065e-05, "epoch": 0.079872, "percentage": 7.99, "elapsed_time": "1:08:42", "remaining_time": "13:11:26"}
+{"current_steps": 313, "total_steps": 3906, "loss": 1.5353, "learning_rate": 3.9509860793931716e-05, "epoch": 0.080128, "percentage": 8.01, "elapsed_time": "1:08:55", "remaining_time": "13:11:13"}
+{"current_steps": 314, "total_steps": 3906, "loss": 1.5443, "learning_rate": 3.9506278328058217e-05, "epoch": 0.080384, "percentage": 8.04, "elapsed_time": "1:09:08", "remaining_time": "13:11:00"}
+{"current_steps": 315, "total_steps": 3906, "loss": 1.548, "learning_rate": 3.950268298115925e-05, "epoch": 0.08064, "percentage": 8.06, "elapsed_time": "1:09:21", "remaining_time": "13:10:46"}
+{"current_steps": 316, "total_steps": 3906, "loss": 1.6164, "learning_rate": 3.949907475560901e-05, "epoch": 0.080896, "percentage": 8.09, "elapsed_time": "1:09:35", "remaining_time": "13:10:33"}
+{"current_steps": 317, "total_steps": 3906, "loss": 1.5858, "learning_rate": 3.9495453653790207e-05, "epoch": 0.081152, "percentage": 8.12, "elapsed_time": "1:09:48", "remaining_time": "13:10:20"}
+{"current_steps": 318, "total_steps": 3906, "loss": 1.5514, "learning_rate": 3.949181967809404e-05, "epoch": 0.081408, "percentage": 8.14, "elapsed_time": "1:10:01", "remaining_time": "13:10:06"}
+{"current_steps": 319, "total_steps": 3906, "loss": 1.5811, "learning_rate": 3.948817283092022e-05, "epoch": 0.081664, "percentage": 8.17, "elapsed_time": "1:10:14", "remaining_time": "13:09:53"}
+{"current_steps": 320, "total_steps": 3906, "loss": 1.5182, "learning_rate": 3.948451311467695e-05, "epoch": 0.08192, "percentage": 8.19, "elapsed_time": "1:10:28", "remaining_time": "13:09:40"}
+{"current_steps": 321, "total_steps": 3906, "loss": 1.5497, "learning_rate": 3.948084053178094e-05, "epoch": 0.082176, "percentage": 8.22, "elapsed_time": "1:10:41", "remaining_time": "13:09:27"}
+{"current_steps": 322, "total_steps": 3906, "loss": 1.5614, "learning_rate": 3.947715508465738e-05, "epoch": 0.082432, "percentage": 8.24, "elapsed_time": "1:10:54", "remaining_time": "13:09:14"}
+{"current_steps": 323, "total_steps": 3906, "loss": 1.5218, "learning_rate": 3.947345677573997e-05, "epoch": 0.082688, "percentage": 8.27, "elapsed_time": "1:11:07", "remaining_time": "13:09:00"}
+{"current_steps": 324, "total_steps": 3906, "loss": 1.5016, "learning_rate": 3.946974560747089e-05, "epoch": 0.082944, "percentage": 8.29, "elapsed_time": "1:11:20", "remaining_time": "13:08:45"}
+{"current_steps": 325, "total_steps": 3906, "loss": 1.5219, "learning_rate": 3.946602158230084e-05, "epoch": 0.0832, "percentage": 8.32, "elapsed_time": "1:11:33", "remaining_time": "13:08:32"}
+{"current_steps": 326, "total_steps": 3906, "loss": 1.5709, "learning_rate": 3.946228470268898e-05, "epoch": 0.083456, "percentage": 8.35, "elapsed_time": "1:11:47", "remaining_time": "13:08:18"}
+{"current_steps": 327, "total_steps": 3906, "loss": 1.5026, "learning_rate": 3.945853497110296e-05, "epoch": 0.083712, "percentage": 8.37, "elapsed_time": "1:12:00", "remaining_time": "13:08:05"}
+{"current_steps": 328, "total_steps": 3906, "loss": 1.5638, "learning_rate": 3.945477239001893e-05, "epoch": 0.083968, "percentage": 8.4, "elapsed_time": "1:12:13", "remaining_time": "13:07:52"}
+{"current_steps": 329, "total_steps": 3906, "loss": 1.5849, "learning_rate": 3.9450996961921536e-05, "epoch": 0.084224, "percentage": 8.42, "elapsed_time": "1:12:26", "remaining_time": "13:07:39"}
+{"current_steps": 330, "total_steps": 3906, "loss": 1.5437, "learning_rate": 3.944720868930388e-05, "epoch": 0.08448, "percentage": 8.45, "elapsed_time": "1:12:39", "remaining_time": "13:07:25"}
+{"current_steps": 331, "total_steps": 3906, "loss": 1.5299, "learning_rate": 3.944340757466756e-05, "epoch": 0.084736, "percentage": 8.47, "elapsed_time": "1:12:53", "remaining_time": "13:07:12"}
+{"current_steps": 332, "total_steps": 3906, "loss": 1.5006, "learning_rate": 3.9439593620522644e-05, "epoch": 0.084992, "percentage": 8.5, "elapsed_time": "1:13:06", "remaining_time": "13:06:59"}
+{"current_steps": 333, "total_steps": 3906, "loss": 1.5268, "learning_rate": 3.9435766829387706e-05, "epoch": 0.085248, "percentage": 8.53, "elapsed_time": "1:13:19", "remaining_time": "13:06:44"}
+{"current_steps": 334, "total_steps": 3906, "loss": 1.5115, "learning_rate": 3.943192720378976e-05, "epoch": 0.085504, "percentage": 8.55, "elapsed_time": "1:13:32", "remaining_time": "13:06:30"}
+{"current_steps": 335, "total_steps": 3906, "loss": 1.556, "learning_rate": 3.942807474626433e-05, "epoch": 0.08576, "percentage": 8.58, "elapsed_time": "1:13:45", "remaining_time": "13:06:16"}
+{"current_steps": 336, "total_steps": 3906, "loss": 1.5597, "learning_rate": 3.9424209459355385e-05, "epoch": 0.086016, "percentage": 8.6, "elapsed_time": "1:13:58", "remaining_time": "13:06:02"}
+{"current_steps": 337, "total_steps": 3906, "loss": 1.4676, "learning_rate": 3.942033134561538e-05, "epoch": 0.086272, "percentage": 8.63, "elapsed_time": "1:14:12", "remaining_time": "13:05:49"}
+{"current_steps": 338, "total_steps": 3906, "loss": 1.5329, "learning_rate": 3.941644040760523e-05, "epoch": 0.086528, "percentage": 8.65, "elapsed_time": "1:14:25", "remaining_time": "13:05:36"}
+{"current_steps": 339, "total_steps": 3906, "loss": 1.5304, "learning_rate": 3.941253664789435e-05, "epoch": 0.086784, "percentage": 8.68, "elapsed_time": "1:14:38", "remaining_time": "13:05:23"}
+{"current_steps": 340, "total_steps": 3906, "loss": 1.5164, "learning_rate": 3.9408620069060584e-05, "epoch": 0.08704, "percentage": 8.7, "elapsed_time": "1:14:51", "remaining_time": "13:05:09"}
+{"current_steps": 341, "total_steps": 3906, "loss": 1.5121, "learning_rate": 3.9404690673690255e-05, "epoch": 0.087296, "percentage": 8.73, "elapsed_time": "1:15:04", "remaining_time": "13:04:56"}
+{"current_steps": 342, "total_steps": 3906, "loss": 1.525, "learning_rate": 3.940074846437815e-05, "epoch": 0.087552, "percentage": 8.76, "elapsed_time": "1:15:18", "remaining_time": "13:04:43"}
+{"current_steps": 343, "total_steps": 3906, "loss": 1.4974, "learning_rate": 3.939679344372753e-05, "epoch": 0.087808, "percentage": 8.78, "elapsed_time": "1:15:31", "remaining_time": "13:04:29"}
+{"current_steps": 344, "total_steps": 3906, "loss": 1.5145, "learning_rate": 3.9392825614350085e-05, "epoch": 0.088064, "percentage": 8.81, "elapsed_time": "1:15:44", "remaining_time": "13:04:15"}
+{"current_steps": 345, "total_steps": 3906, "loss": 1.5629, "learning_rate": 3.9388844978865994e-05, "epoch": 0.08832, "percentage": 8.83, "elapsed_time": "1:15:57", "remaining_time": "13:04:01"}
+{"current_steps": 346, "total_steps": 3906, "loss": 1.4852, "learning_rate": 3.938485153990388e-05, "epoch": 0.088576, "percentage": 8.86, "elapsed_time": "1:16:10", "remaining_time": "13:03:47"}
+{"current_steps": 347, "total_steps": 3906, "loss": 1.5562, "learning_rate": 3.9380845300100816e-05, "epoch": 0.088832, "percentage": 8.88, "elapsed_time": "1:16:23", "remaining_time": "13:03:34"}
+{"current_steps": 348, "total_steps": 3906, "loss": 1.533, "learning_rate": 3.937682626210234e-05, "epoch": 0.089088, "percentage": 8.91, "elapsed_time": "1:16:37", "remaining_time": "13:03:21"}
+{"current_steps": 349, "total_steps": 3906, "loss": 1.5696, "learning_rate": 3.9372794428562426e-05, "epoch": 0.089344, "percentage": 8.93, "elapsed_time": "1:16:50", "remaining_time": "13:03:07"}
+{"current_steps": 350, "total_steps": 3906, "loss": 1.5335, "learning_rate": 3.9368749802143524e-05, "epoch": 0.0896, "percentage": 8.96, "elapsed_time": "1:17:03", "remaining_time": "13:02:54"}
+{"current_steps": 351, "total_steps": 3906, "loss": 1.5339, "learning_rate": 3.93646923855165e-05, "epoch": 0.089856, "percentage": 8.99, "elapsed_time": "1:17:16", "remaining_time": "13:02:41"}
+{"current_steps": 352, "total_steps": 3906, "loss": 1.5391, "learning_rate": 3.9360622181360675e-05, "epoch": 0.090112, "percentage": 9.01, "elapsed_time": "1:17:29", "remaining_time": "13:02:28"}
+{"current_steps": 353, "total_steps": 3906, "loss": 1.5424, "learning_rate": 3.9356539192363834e-05, "epoch": 0.090368, "percentage": 9.04, "elapsed_time": "1:17:43", "remaining_time": "13:02:14"}
+{"current_steps": 354, "total_steps": 3906, "loss": 1.5176, "learning_rate": 3.935244342122219e-05, "epoch": 0.090624, "percentage": 9.06, "elapsed_time": "1:17:56", "remaining_time": "13:02:01"}
+{"current_steps": 355, "total_steps": 3906, "loss": 1.5632, "learning_rate": 3.934833487064038e-05, "epoch": 0.09088, "percentage": 9.09, "elapsed_time": "1:18:09", "remaining_time": "13:01:47"}
+{"current_steps": 356, "total_steps": 3906, "loss": 1.5766, "learning_rate": 3.9344213543331524e-05, "epoch": 0.091136, "percentage": 9.11, "elapsed_time": "1:18:22", "remaining_time": "13:01:33"}
+{"current_steps": 357, "total_steps": 3906, "loss": 1.5205, "learning_rate": 3.934007944201713e-05, "epoch": 0.091392, "percentage": 9.14, "elapsed_time": "1:18:35", "remaining_time": "13:01:20"}
+{"current_steps": 358, "total_steps": 3906, "loss": 1.5189, "learning_rate": 3.933593256942717e-05, "epoch": 0.091648, "percentage": 9.17, "elapsed_time": "1:18:48", "remaining_time": "13:01:06"}
+{"current_steps": 359, "total_steps": 3906, "loss": 1.498, "learning_rate": 3.933177292830004e-05, "epoch": 0.091904, "percentage": 9.19, "elapsed_time": "1:19:02", "remaining_time": "13:00:53"}
+{"current_steps": 360, "total_steps": 3906, "loss": 1.5586, "learning_rate": 3.932760052138258e-05, "epoch": 0.09216, "percentage": 9.22, "elapsed_time": "1:19:15", "remaining_time": "13:00:40"}
+{"current_steps": 361, "total_steps": 3906, "loss": 1.4637, "learning_rate": 3.932341535143003e-05, "epoch": 0.092416, "percentage": 9.24, "elapsed_time": "1:19:28", "remaining_time": "13:00:26"}
+{"current_steps": 362, "total_steps": 3906, "loss": 1.5315, "learning_rate": 3.931921742120611e-05, "epoch": 0.092672, "percentage": 9.27, "elapsed_time": "1:19:41", "remaining_time": "13:00:13"}
+{"current_steps": 363, "total_steps": 3906, "loss": 1.4683, "learning_rate": 3.931500673348291e-05, "epoch": 0.092928, "percentage": 9.29, "elapsed_time": "1:19:54", "remaining_time": "13:00:00"}
+{"current_steps": 364, "total_steps": 3906, "loss": 1.5282, "learning_rate": 3.931078329104098e-05, "epoch": 0.093184, "percentage": 9.32, "elapsed_time": "1:20:08", "remaining_time": "12:59:47"}
+{"current_steps": 365, "total_steps": 3906, "loss": 1.4843, "learning_rate": 3.930654709666927e-05, "epoch": 0.09344, "percentage": 9.34, "elapsed_time": "1:20:21", "remaining_time": "12:59:33"}
+{"current_steps": 366, "total_steps": 3906, "loss": 1.507, "learning_rate": 3.930229815316517e-05, "epoch": 0.093696, "percentage": 9.37, "elapsed_time": "1:20:34", "remaining_time": "12:59:20"}
+{"current_steps": 367, "total_steps": 3906, "loss": 1.5102, "learning_rate": 3.92980364633345e-05, "epoch": 0.093952, "percentage": 9.4, "elapsed_time": "1:20:47", "remaining_time": "12:59:07"}
+{"current_steps": 368, "total_steps": 3906, "loss": 1.4859, "learning_rate": 3.9293762029991454e-05, "epoch": 0.094208, "percentage": 9.42, "elapsed_time": "1:21:00", "remaining_time": "12:58:53"}
+{"current_steps": 369, "total_steps": 3906, "loss": 1.5334, "learning_rate": 3.9289474855958675e-05, "epoch": 0.094464, "percentage": 9.45, "elapsed_time": "1:21:14", "remaining_time": "12:58:40"}
+{"current_steps": 370, "total_steps": 3906, "loss": 1.5007, "learning_rate": 3.928517494406721e-05, "epoch": 0.09472, "percentage": 9.47, "elapsed_time": "1:21:27", "remaining_time": "12:58:27"}
+{"current_steps": 371, "total_steps": 3906, "loss": 1.5516, "learning_rate": 3.928086229715652e-05, "epoch": 0.094976, "percentage": 9.5, "elapsed_time": "1:21:40", "remaining_time": "12:58:13"}
+{"current_steps": 372, "total_steps": 3906, "loss": 1.5632, "learning_rate": 3.927653691807447e-05, "epoch": 0.095232, "percentage": 9.52, "elapsed_time": "1:21:53", "remaining_time": "12:58:00"}
+{"current_steps": 373, "total_steps": 3906, "loss": 1.5356, "learning_rate": 3.927219880967733e-05, "epoch": 0.095488, "percentage": 9.55, "elapsed_time": "1:22:06", "remaining_time": "12:57:47"}
+{"current_steps": 374, "total_steps": 3906, "loss": 1.495, "learning_rate": 3.92678479748298e-05, "epoch": 0.095744, "percentage": 9.58, "elapsed_time": "1:22:20", "remaining_time": "12:57:33"}
+{"current_steps": 375, "total_steps": 3906, "loss": 1.5237, "learning_rate": 3.926348441640495e-05, "epoch": 0.096, "percentage": 9.6, "elapsed_time": "1:22:33", "remaining_time": "12:57:21"}
+{"current_steps": 376, "total_steps": 3906, "loss": 1.5611, "learning_rate": 3.9259108137284275e-05, "epoch": 0.096256, "percentage": 9.63, "elapsed_time": "1:22:46", "remaining_time": "12:57:08"}
+{"current_steps": 377, "total_steps": 3906, "loss": 1.5373, "learning_rate": 3.9254719140357656e-05, "epoch": 0.096512, "percentage": 9.65, "elapsed_time": "1:22:59", "remaining_time": "12:56:54"}
+{"current_steps": 378, "total_steps": 3906, "loss": 1.5063, "learning_rate": 3.925031742852339e-05, "epoch": 0.096768, "percentage": 9.68, "elapsed_time": "1:23:13", "remaining_time": "12:56:41"}
+{"current_steps": 379, "total_steps": 3906, "loss": 1.5304, "learning_rate": 3.9245903004688156e-05, "epoch": 0.097024, "percentage": 9.7, "elapsed_time": "1:23:26", "remaining_time": "12:56:28"}
+{"current_steps": 380, "total_steps": 3906, "loss": 1.5237, "learning_rate": 3.9241475871767026e-05, "epoch": 0.09728, "percentage": 9.73, "elapsed_time": "1:23:39", "remaining_time": "12:56:14"}
+{"current_steps": 381, "total_steps": 3906, "loss": 1.5362, "learning_rate": 3.923703603268348e-05, "epoch": 0.097536, "percentage": 9.75, "elapsed_time": "1:23:52", "remaining_time": "12:56:00"}
+{"current_steps": 382, "total_steps": 3906, "loss": 1.4965, "learning_rate": 3.9232583490369363e-05, "epoch": 0.097792, "percentage": 9.78, "elapsed_time": "1:24:05", "remaining_time": "12:55:47"}
+{"current_steps": 383, "total_steps": 3906, "loss": 1.5107, "learning_rate": 3.922811824776494e-05, "epoch": 0.098048, "percentage": 9.81, "elapsed_time": "1:24:18", "remaining_time": "12:55:33"}
+{"current_steps": 384, "total_steps": 3906, "loss": 1.4619, "learning_rate": 3.922364030781884e-05, "epoch": 0.098304, "percentage": 9.83, "elapsed_time": "1:24:32", "remaining_time": "12:55:20"}
+{"current_steps": 385, "total_steps": 3906, "loss": 1.5492, "learning_rate": 3.921914967348807e-05, "epoch": 0.09856, "percentage": 9.86, "elapsed_time": "1:24:45", "remaining_time": "12:55:07"}
+{"current_steps": 386, "total_steps": 3906, "loss": 1.5979, "learning_rate": 3.9214646347738055e-05, "epoch": 0.098816, "percentage": 9.88, "elapsed_time": "1:24:58", "remaining_time": "12:54:54"}
+{"current_steps": 387, "total_steps": 3906, "loss": 1.4744, "learning_rate": 3.921013033354256e-05, "epoch": 0.099072, "percentage": 9.91, "elapsed_time": "1:25:11", "remaining_time": "12:54:40"}
+{"current_steps": 388, "total_steps": 3906, "loss": 1.4878, "learning_rate": 3.920560163388377e-05, "epoch": 0.099328, "percentage": 9.93, "elapsed_time": "1:25:24", "remaining_time": "12:54:26"}
+{"current_steps": 389, "total_steps": 3906, "loss": 1.4809, "learning_rate": 3.92010602517522e-05, "epoch": 0.099584, "percentage": 9.96, "elapsed_time": "1:25:38", "remaining_time": "12:54:13"}
+{"current_steps": 390, "total_steps": 3906, "loss": 1.5365, "learning_rate": 3.919650619014678e-05, "epoch": 0.09984, "percentage": 9.98, "elapsed_time": "1:25:51", "remaining_time": "12:53:59"}
+{"current_steps": 391, "total_steps": 3906, "loss": 1.5147, "learning_rate": 3.9191939452074786e-05, "epoch": 0.100096, "percentage": 10.01, "elapsed_time": "1:26:04", "remaining_time": "12:53:46"}
+{"current_steps": 392, "total_steps": 3906, "loss": 1.5106, "learning_rate": 3.9187360040551886e-05, "epoch": 0.100352, "percentage": 10.04, "elapsed_time": "1:26:17", "remaining_time": "12:53:33"}
+{"current_steps": 393, "total_steps": 3906, "loss": 1.4999, "learning_rate": 3.9182767958602104e-05, "epoch": 0.100608, "percentage": 10.06, "elapsed_time": "1:26:30", "remaining_time": "12:53:20"}
+{"current_steps": 394, "total_steps": 3906, "loss": 1.5021, "learning_rate": 3.917816320925784e-05, "epoch": 0.100864, "percentage": 10.09, "elapsed_time": "1:26:43", "remaining_time": "12:53:06"}
+{"current_steps": 395, "total_steps": 3906, "loss": 1.4991, "learning_rate": 3.917354579555984e-05, "epoch": 0.10112, "percentage": 10.11, "elapsed_time": "1:26:57", "remaining_time": "12:52:53"}
+{"current_steps": 396, "total_steps": 3906, "loss": 1.5445, "learning_rate": 3.916891572055724e-05, "epoch": 0.101376, "percentage": 10.14, "elapsed_time": "1:27:10", "remaining_time": "12:52:40"}
+{"current_steps": 397, "total_steps": 3906, "loss": 1.5418, "learning_rate": 3.916427298730751e-05, "epoch": 0.101632, "percentage": 10.16, "elapsed_time": "1:27:23", "remaining_time": "12:52:26"}
+{"current_steps": 398, "total_steps": 3906, "loss": 1.4997, "learning_rate": 3.9159617598876495e-05, "epoch": 0.101888, "percentage": 10.19, "elapsed_time": "1:27:36", "remaining_time": "12:52:13"}
+{"current_steps": 399, "total_steps": 3906, "loss": 1.4576, "learning_rate": 3.9154949558338404e-05, "epoch": 0.102144, "percentage": 10.22, "elapsed_time": "1:27:50", "remaining_time": "12:52:00"}
+{"current_steps": 400, "total_steps": 3906, "loss": 1.4819, "learning_rate": 3.915026886877578e-05, "epoch": 0.1024, "percentage": 10.24, "elapsed_time": "1:28:03", "remaining_time": "12:51:48"}
+{"current_steps": 401, "total_steps": 3906, "loss": 1.4622, "learning_rate": 3.914557553327954e-05, "epoch": 0.102656, "percentage": 10.27, "elapsed_time": "1:28:33", "remaining_time": "12:53:59"}
+{"current_steps": 402, "total_steps": 3906, "loss": 1.5045, "learning_rate": 3.914086955494893e-05, "epoch": 0.102912, "percentage": 10.29, "elapsed_time": "1:28:46", "remaining_time": "12:53:45"}
+{"current_steps": 403, "total_steps": 3906, "loss": 1.5452, "learning_rate": 3.913615093689155e-05, "epoch": 0.103168, "percentage": 10.32, "elapsed_time": "1:28:59", "remaining_time": "12:53:32"}
+{"current_steps": 404, "total_steps": 3906, "loss": 1.5164, "learning_rate": 3.9131419682223376e-05, "epoch": 0.103424, "percentage": 10.34, "elapsed_time": "1:29:12", "remaining_time": "12:53:18"}
+{"current_steps": 405, "total_steps": 3906, "loss": 1.5413, "learning_rate": 3.9126675794068686e-05, "epoch": 0.10368, "percentage": 10.37, "elapsed_time": "1:29:25", "remaining_time": "12:53:05"}
+{"current_steps": 406, "total_steps": 3906, "loss": 1.5168, "learning_rate": 3.912191927556013e-05, "epoch": 0.103936, "percentage": 10.39, "elapsed_time": "1:29:39", "remaining_time": "12:52:52"}
+{"current_steps": 407, "total_steps": 3906, "loss": 1.5974, "learning_rate": 3.911715012983868e-05, "epoch": 0.104192, "percentage": 10.42, "elapsed_time": "1:29:52", "remaining_time": "12:52:38"}
+{"current_steps": 408, "total_steps": 3906, "loss": 1.506, "learning_rate": 3.911236836005366e-05, "epoch": 0.104448, "percentage": 10.45, "elapsed_time": "1:30:05", "remaining_time": "12:52:25"}
+{"current_steps": 409, "total_steps": 3906, "loss": 1.5209, "learning_rate": 3.910757396936273e-05, "epoch": 0.104704, "percentage": 10.47, "elapsed_time": "1:30:18", "remaining_time": "12:52:11"}
+{"current_steps": 410, "total_steps": 3906, "loss": 1.4858, "learning_rate": 3.910276696093186e-05, "epoch": 0.10496, "percentage": 10.5, "elapsed_time": "1:30:32", "remaining_time": "12:51:57"}
+{"current_steps": 411, "total_steps": 3906, "loss": 1.54, "learning_rate": 3.90979473379354e-05, "epoch": 0.105216, "percentage": 10.52, "elapsed_time": "1:30:45", "remaining_time": "12:51:43"}
+{"current_steps": 412, "total_steps": 3906, "loss": 1.4793, "learning_rate": 3.909311510355598e-05, "epoch": 0.105472, "percentage": 10.55, "elapsed_time": "1:30:58", "remaining_time": "12:51:30"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de81595e6f9c087c2ca2826609efaeae7a253ad6ec6f25717829ad9cd4d78995
+size 7096