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:ac362453984fdb2f9332eb36dd41829e72e7c2d552e90dca3dbcf5009a0c3d2e
+size 4988025760

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a9b216050ae33d0be10cd1ec29484d012ad09e5c700cd6f68a9697074d4f3f
+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 +1,411 @@
+{"current_steps": 1, "total_steps": 5627, "loss": 7.1545, "learning_rate": 7.017543859649123e-07, "epoch": 0.00017770669509973788, "percentage": 0.02, "elapsed_time": "0:00:22", "remaining_time": "1 day, 10:45:56"}
+{"current_steps": 2, "total_steps": 5627, "loss": 7.0683, "learning_rate": 1.4035087719298246e-06, "epoch": 0.00035541339019947576, "percentage": 0.04, "elapsed_time": "0:00:35", "remaining_time": "1 day, 3:40:36"}
+{"current_steps": 3, "total_steps": 5627, "loss": 6.9978, "learning_rate": 2.105263157894737e-06, "epoch": 0.0005331200852992136, "percentage": 0.05, "elapsed_time": "0:00:48", "remaining_time": "1 day, 1:18:23"}
+{"current_steps": 4, "total_steps": 5627, "loss": 5.4451, "learning_rate": 2.8070175438596493e-06, "epoch": 0.0007108267803989515, "percentage": 0.07, "elapsed_time": "0:01:01", "remaining_time": "1 day, 0:07:17"}
+{"current_steps": 5, "total_steps": 5627, "loss": 4.2204, "learning_rate": 3.5087719298245615e-06, "epoch": 0.0008885334754986894, "percentage": 0.09, "elapsed_time": "0:01:14", "remaining_time": "23:25:13"}
+{"current_steps": 6, "total_steps": 5627, "loss": 3.8457, "learning_rate": 4.210526315789474e-06, "epoch": 0.0010662401705984273, "percentage": 0.11, "elapsed_time": "0:01:28", "remaining_time": "22:56:55"}
+{"current_steps": 7, "total_steps": 5627, "loss": 3.2549, "learning_rate": 4.912280701754386e-06, "epoch": 0.0012439468656981652, "percentage": 0.12, "elapsed_time": "0:01:41", "remaining_time": "22:36:45"}
+{"current_steps": 8, "total_steps": 5627, "loss": 3.2042, "learning_rate": 5.6140350877192985e-06, "epoch": 0.001421653560797903, "percentage": 0.14, "elapsed_time": "0:01:54", "remaining_time": "22:21:28"}
+{"current_steps": 9, "total_steps": 5627, "loss": 2.6104, "learning_rate": 6.31578947368421e-06, "epoch": 0.001599360255897641, "percentage": 0.16, "elapsed_time": "0:02:07", "remaining_time": "22:09:19"}
+{"current_steps": 10, "total_steps": 5627, "loss": 2.4822, "learning_rate": 7.017543859649123e-06, "epoch": 0.0017770669509973788, "percentage": 0.18, "elapsed_time": "0:02:20", "remaining_time": "21:59:29"}
+{"current_steps": 11, "total_steps": 5627, "loss": 2.6837, "learning_rate": 7.719298245614036e-06, "epoch": 0.0019547736460971167, "percentage": 0.2, "elapsed_time": "0:02:34", "remaining_time": "21:51:06"}
+{"current_steps": 12, "total_steps": 5627, "loss": 2.4258, "learning_rate": 8.421052631578948e-06, "epoch": 0.0021324803411968546, "percentage": 0.21, "elapsed_time": "0:02:47", "remaining_time": "21:43:35"}
+{"current_steps": 13, "total_steps": 5627, "loss": 2.463, "learning_rate": 9.12280701754386e-06, "epoch": 0.0023101870362965925, "percentage": 0.23, "elapsed_time": "0:03:00", "remaining_time": "21:37:55"}
+{"current_steps": 14, "total_steps": 5627, "loss": 2.3072, "learning_rate": 9.824561403508772e-06, "epoch": 0.0024878937313963304, "percentage": 0.25, "elapsed_time": "0:03:13", "remaining_time": "21:33:15"}
+{"current_steps": 15, "total_steps": 5627, "loss": 2.4683, "learning_rate": 1.0526315789473684e-05, "epoch": 0.0026656004264960682, "percentage": 0.27, "elapsed_time": "0:03:26", "remaining_time": "21:29:05"}
+{"current_steps": 16, "total_steps": 5627, "loss": 2.4925, "learning_rate": 1.1228070175438597e-05, "epoch": 0.002843307121595806, "percentage": 0.28, "elapsed_time": "0:03:40", "remaining_time": "21:25:53"}
+{"current_steps": 17, "total_steps": 5627, "loss": 2.2503, "learning_rate": 1.192982456140351e-05, "epoch": 0.003021013816695544, "percentage": 0.3, "elapsed_time": "0:03:53", "remaining_time": "21:22:35"}
+{"current_steps": 18, "total_steps": 5627, "loss": 2.2602, "learning_rate": 1.263157894736842e-05, "epoch": 0.003198720511795282, "percentage": 0.32, "elapsed_time": "0:04:06", "remaining_time": "21:19:39"}
+{"current_steps": 19, "total_steps": 5627, "loss": 2.3477, "learning_rate": 1.3333333333333333e-05, "epoch": 0.0033764272068950198, "percentage": 0.34, "elapsed_time": "0:04:19", "remaining_time": "21:16:47"}
+{"current_steps": 20, "total_steps": 5627, "loss": 2.3348, "learning_rate": 1.4035087719298246e-05, "epoch": 0.0035541339019947576, "percentage": 0.36, "elapsed_time": "0:04:32", "remaining_time": "21:14:04"}
+{"current_steps": 21, "total_steps": 5627, "loss": 2.1845, "learning_rate": 1.4736842105263159e-05, "epoch": 0.0037318405970944955, "percentage": 0.37, "elapsed_time": "0:04:45", "remaining_time": "21:11:51"}
+{"current_steps": 22, "total_steps": 5627, "loss": 2.2383, "learning_rate": 1.543859649122807e-05, "epoch": 0.003909547292194233, "percentage": 0.39, "elapsed_time": "0:04:59", "remaining_time": "21:09:46"}
+{"current_steps": 23, "total_steps": 5627, "loss": 2.2439, "learning_rate": 1.6140350877192984e-05, "epoch": 0.004087253987293971, "percentage": 0.41, "elapsed_time": "0:05:12", "remaining_time": "21:07:48"}
+{"current_steps": 24, "total_steps": 5627, "loss": 2.2131, "learning_rate": 1.6842105263157896e-05, "epoch": 0.004264960682393709, "percentage": 0.43, "elapsed_time": "0:05:25", "remaining_time": "21:05:53"}
+{"current_steps": 25, "total_steps": 5627, "loss": 2.1535, "learning_rate": 1.754385964912281e-05, "epoch": 0.004442667377493447, "percentage": 0.44, "elapsed_time": "0:05:38", "remaining_time": "21:04:10"}
+{"current_steps": 26, "total_steps": 5627, "loss": 2.1073, "learning_rate": 1.824561403508772e-05, "epoch": 0.004620374072593185, "percentage": 0.46, "elapsed_time": "0:05:51", "remaining_time": "21:02:23"}
+{"current_steps": 27, "total_steps": 5627, "loss": 2.0962, "learning_rate": 1.894736842105263e-05, "epoch": 0.004798080767692923, "percentage": 0.48, "elapsed_time": "0:06:04", "remaining_time": "21:01:02"}
+{"current_steps": 28, "total_steps": 5627, "loss": 2.2948, "learning_rate": 1.9649122807017544e-05, "epoch": 0.004975787462792661, "percentage": 0.5, "elapsed_time": "0:06:17", "remaining_time": "20:59:43"}
+{"current_steps": 29, "total_steps": 5627, "loss": 2.1363, "learning_rate": 2.035087719298246e-05, "epoch": 0.005153494157892399, "percentage": 0.52, "elapsed_time": "0:06:31", "remaining_time": "20:58:37"}
+{"current_steps": 30, "total_steps": 5627, "loss": 2.1441, "learning_rate": 2.105263157894737e-05, "epoch": 0.0053312008529921365, "percentage": 0.53, "elapsed_time": "0:06:44", "remaining_time": "20:57:13"}
+{"current_steps": 31, "total_steps": 5627, "loss": 1.9666, "learning_rate": 2.1754385964912285e-05, "epoch": 0.005508907548091874, "percentage": 0.55, "elapsed_time": "0:06:57", "remaining_time": "20:55:58"}
+{"current_steps": 32, "total_steps": 5627, "loss": 2.0112, "learning_rate": 2.2456140350877194e-05, "epoch": 0.005686614243191612, "percentage": 0.57, "elapsed_time": "0:07:10", "remaining_time": "20:54:58"}
+{"current_steps": 33, "total_steps": 5627, "loss": 2.0019, "learning_rate": 2.3157894736842107e-05, "epoch": 0.00586432093829135, "percentage": 0.59, "elapsed_time": "0:07:23", "remaining_time": "20:53:56"}
+{"current_steps": 34, "total_steps": 5627, "loss": 2.007, "learning_rate": 2.385964912280702e-05, "epoch": 0.006042027633391088, "percentage": 0.6, "elapsed_time": "0:07:37", "remaining_time": "20:52:59"}
+{"current_steps": 35, "total_steps": 5627, "loss": 2.0439, "learning_rate": 2.4561403508771932e-05, "epoch": 0.006219734328490826, "percentage": 0.62, "elapsed_time": "0:07:50", "remaining_time": "20:52:04"}
+{"current_steps": 36, "total_steps": 5627, "loss": 2.027, "learning_rate": 2.526315789473684e-05, "epoch": 0.006397441023590564, "percentage": 0.64, "elapsed_time": "0:08:03", "remaining_time": "20:51:17"}
+{"current_steps": 37, "total_steps": 5627, "loss": 2.006, "learning_rate": 2.5964912280701757e-05, "epoch": 0.006575147718690302, "percentage": 0.66, "elapsed_time": "0:08:16", "remaining_time": "20:50:29"}
+{"current_steps": 38, "total_steps": 5627, "loss": 1.9948, "learning_rate": 2.6666666666666667e-05, "epoch": 0.0067528544137900395, "percentage": 0.68, "elapsed_time": "0:08:29", "remaining_time": "20:49:43"}
+{"current_steps": 39, "total_steps": 5627, "loss": 2.0396, "learning_rate": 2.7368421052631583e-05, "epoch": 0.006930561108889777, "percentage": 0.69, "elapsed_time": "0:08:43", "remaining_time": "20:48:58"}
+{"current_steps": 40, "total_steps": 5627, "loss": 1.968, "learning_rate": 2.8070175438596492e-05, "epoch": 0.007108267803989515, "percentage": 0.71, "elapsed_time": "0:08:56", "remaining_time": "20:48:12"}
+{"current_steps": 41, "total_steps": 5627, "loss": 1.9611, "learning_rate": 2.8771929824561408e-05, "epoch": 0.007285974499089253, "percentage": 0.73, "elapsed_time": "0:09:09", "remaining_time": "20:47:16"}
+{"current_steps": 42, "total_steps": 5627, "loss": 2.0122, "learning_rate": 2.9473684210526317e-05, "epoch": 0.007463681194188991, "percentage": 0.75, "elapsed_time": "0:09:22", "remaining_time": "20:46:34"}
+{"current_steps": 43, "total_steps": 5627, "loss": 2.0516, "learning_rate": 3.017543859649123e-05, "epoch": 0.007641387889288729, "percentage": 0.76, "elapsed_time": "0:09:35", "remaining_time": "20:45:53"}
+{"current_steps": 44, "total_steps": 5627, "loss": 1.8842, "learning_rate": 3.087719298245614e-05, "epoch": 0.007819094584388467, "percentage": 0.78, "elapsed_time": "0:09:48", "remaining_time": "20:45:20"}
+{"current_steps": 45, "total_steps": 5627, "loss": 2.0397, "learning_rate": 3.157894736842106e-05, "epoch": 0.007996801279488205, "percentage": 0.8, "elapsed_time": "0:10:02", "remaining_time": "20:44:42"}
+{"current_steps": 46, "total_steps": 5627, "loss": 2.007, "learning_rate": 3.228070175438597e-05, "epoch": 0.008174507974587943, "percentage": 0.82, "elapsed_time": "0:10:15", "remaining_time": "20:44:05"}
+{"current_steps": 47, "total_steps": 5627, "loss": 1.927, "learning_rate": 3.298245614035088e-05, "epoch": 0.00835221466968768, "percentage": 0.84, "elapsed_time": "0:10:28", "remaining_time": "20:43:31"}
+{"current_steps": 48, "total_steps": 5627, "loss": 2.0038, "learning_rate": 3.368421052631579e-05, "epoch": 0.008529921364787418, "percentage": 0.85, "elapsed_time": "0:10:41", "remaining_time": "20:42:56"}
+{"current_steps": 49, "total_steps": 5627, "loss": 1.8921, "learning_rate": 3.43859649122807e-05, "epoch": 0.008707628059887156, "percentage": 0.87, "elapsed_time": "0:10:54", "remaining_time": "20:42:21"}
+{"current_steps": 50, "total_steps": 5627, "loss": 1.9108, "learning_rate": 3.508771929824562e-05, "epoch": 0.008885334754986894, "percentage": 0.89, "elapsed_time": "0:11:07", "remaining_time": "20:41:48"}
+{"current_steps": 51, "total_steps": 5627, "loss": 1.9533, "learning_rate": 3.578947368421053e-05, "epoch": 0.009063041450086632, "percentage": 0.91, "elapsed_time": "0:11:21", "remaining_time": "20:41:22"}
+{"current_steps": 52, "total_steps": 5627, "loss": 1.9123, "learning_rate": 3.649122807017544e-05, "epoch": 0.00924074814518637, "percentage": 0.92, "elapsed_time": "0:11:34", "remaining_time": "20:40:51"}
+{"current_steps": 53, "total_steps": 5627, "loss": 1.9081, "learning_rate": 3.719298245614035e-05, "epoch": 0.009418454840286108, "percentage": 0.94, "elapsed_time": "0:11:47", "remaining_time": "20:40:14"}
+{"current_steps": 54, "total_steps": 5627, "loss": 1.9663, "learning_rate": 3.789473684210526e-05, "epoch": 0.009596161535385846, "percentage": 0.96, "elapsed_time": "0:12:00", "remaining_time": "20:39:39"}
+{"current_steps": 55, "total_steps": 5627, "loss": 1.8523, "learning_rate": 3.859649122807018e-05, "epoch": 0.009773868230485584, "percentage": 0.98, "elapsed_time": "0:12:13", "remaining_time": "20:39:10"}
+{"current_steps": 56, "total_steps": 5627, "loss": 1.928, "learning_rate": 3.929824561403509e-05, "epoch": 0.009951574925585321, "percentage": 1.0, "elapsed_time": "0:12:27", "remaining_time": "20:38:41"}
+{"current_steps": 57, "total_steps": 5627, "loss": 1.8731, "learning_rate": 4e-05, "epoch": 0.01012928162068506, "percentage": 1.01, "elapsed_time": "0:12:40", "remaining_time": "20:38:12"}
+{"current_steps": 58, "total_steps": 5627, "loss": 1.8971, "learning_rate": 3.999999681881194e-05, "epoch": 0.010306988315784797, "percentage": 1.03, "elapsed_time": "0:12:53", "remaining_time": "20:37:44"}
+{"current_steps": 59, "total_steps": 5627, "loss": 1.9188, "learning_rate": 3.9999987275248785e-05, "epoch": 0.010484695010884535, "percentage": 1.05, "elapsed_time": "0:13:06", "remaining_time": "20:37:18"}
+{"current_steps": 60, "total_steps": 5627, "loss": 1.8498, "learning_rate": 3.999997136931355e-05, "epoch": 0.010662401705984273, "percentage": 1.07, "elapsed_time": "0:13:19", "remaining_time": "20:36:43"}
+{"current_steps": 61, "total_steps": 5627, "loss": 1.8885, "learning_rate": 3.9999949101011305e-05, "epoch": 0.01084010840108401, "percentage": 1.08, "elapsed_time": "0:13:32", "remaining_time": "20:36:17"}
+{"current_steps": 62, "total_steps": 5627, "loss": 1.8108, "learning_rate": 3.999992047034914e-05, "epoch": 0.011017815096183749, "percentage": 1.1, "elapsed_time": "0:13:46", "remaining_time": "20:35:47"}
+{"current_steps": 63, "total_steps": 5627, "loss": 1.882, "learning_rate": 3.9999885477336156e-05, "epoch": 0.011195521791283487, "percentage": 1.12, "elapsed_time": "0:13:59", "remaining_time": "20:35:20"}
+{"current_steps": 64, "total_steps": 5627, "loss": 1.7691, "learning_rate": 3.999984412198349e-05, "epoch": 0.011373228486383224, "percentage": 1.14, "elapsed_time": "0:14:12", "remaining_time": "20:34:54"}
+{"current_steps": 65, "total_steps": 5627, "loss": 1.8332, "learning_rate": 3.9999796404304294e-05, "epoch": 0.011550935181482962, "percentage": 1.16, "elapsed_time": "0:14:25", "remaining_time": "20:34:28"}
+{"current_steps": 66, "total_steps": 5627, "loss": 1.9104, "learning_rate": 3.999974232431375e-05, "epoch": 0.0117286418765827, "percentage": 1.17, "elapsed_time": "0:14:38", "remaining_time": "20:34:03"}
+{"current_steps": 67, "total_steps": 5627, "loss": 1.8237, "learning_rate": 3.999968188202905e-05, "epoch": 0.011906348571682438, "percentage": 1.19, "elapsed_time": "0:14:51", "remaining_time": "20:33:38"}
+{"current_steps": 68, "total_steps": 5627, "loss": 1.812, "learning_rate": 3.999961507746944e-05, "epoch": 0.012084055266782176, "percentage": 1.21, "elapsed_time": "0:15:05", "remaining_time": "20:33:16"}
+{"current_steps": 69, "total_steps": 5627, "loss": 1.8748, "learning_rate": 3.999954191065617e-05, "epoch": 0.012261761961881914, "percentage": 1.23, "elapsed_time": "0:15:18", "remaining_time": "20:32:52"}
+{"current_steps": 70, "total_steps": 5627, "loss": 1.7363, "learning_rate": 3.9999462381612505e-05, "epoch": 0.012439468656981652, "percentage": 1.24, "elapsed_time": "0:15:31", "remaining_time": "20:32:30"}
+{"current_steps": 71, "total_steps": 5627, "loss": 1.7783, "learning_rate": 3.999937649036375e-05, "epoch": 0.01261717535208139, "percentage": 1.26, "elapsed_time": "0:15:44", "remaining_time": "20:32:08"}
+{"current_steps": 72, "total_steps": 5627, "loss": 1.7838, "learning_rate": 3.999928423693723e-05, "epoch": 0.012794882047181128, "percentage": 1.28, "elapsed_time": "0:15:57", "remaining_time": "20:31:48"}
+{"current_steps": 73, "total_steps": 5627, "loss": 1.816, "learning_rate": 3.999918562136229e-05, "epoch": 0.012972588742280865, "percentage": 1.3, "elapsed_time": "0:16:11", "remaining_time": "20:31:32"}
+{"current_steps": 74, "total_steps": 5627, "loss": 1.8286, "learning_rate": 3.999908064367029e-05, "epoch": 0.013150295437380603, "percentage": 1.32, "elapsed_time": "0:16:24", "remaining_time": "20:31:03"}
+{"current_steps": 75, "total_steps": 5627, "loss": 1.8032, "learning_rate": 3.999896930389465e-05, "epoch": 0.013328002132480341, "percentage": 1.33, "elapsed_time": "0:16:37", "remaining_time": "20:30:41"}
+{"current_steps": 76, "total_steps": 5627, "loss": 1.8146, "learning_rate": 3.9998851602070775e-05, "epoch": 0.013505708827580079, "percentage": 1.35, "elapsed_time": "0:16:50", "remaining_time": "20:30:19"}
+{"current_steps": 77, "total_steps": 5627, "loss": 1.825, "learning_rate": 3.999872753823611e-05, "epoch": 0.013683415522679817, "percentage": 1.37, "elapsed_time": "0:17:03", "remaining_time": "20:29:56"}
+{"current_steps": 78, "total_steps": 5627, "loss": 1.8412, "learning_rate": 3.9998597112430124e-05, "epoch": 0.013861122217779555, "percentage": 1.39, "elapsed_time": "0:17:16", "remaining_time": "20:29:31"}
+{"current_steps": 79, "total_steps": 5627, "loss": 1.7968, "learning_rate": 3.99984603246943e-05, "epoch": 0.014038828912879293, "percentage": 1.4, "elapsed_time": "0:17:30", "remaining_time": "20:29:11"}
+{"current_steps": 80, "total_steps": 5627, "loss": 1.7711, "learning_rate": 3.999831717507217e-05, "epoch": 0.01421653560797903, "percentage": 1.42, "elapsed_time": "0:17:43", "remaining_time": "20:28:52"}
+{"current_steps": 81, "total_steps": 5627, "loss": 1.7927, "learning_rate": 3.999816766360925e-05, "epoch": 0.014394242303078768, "percentage": 1.44, "elapsed_time": "0:17:56", "remaining_time": "20:28:34"}
+{"current_steps": 82, "total_steps": 5627, "loss": 1.7488, "learning_rate": 3.9998011790353117e-05, "epoch": 0.014571948998178506, "percentage": 1.46, "elapsed_time": "0:18:09", "remaining_time": "20:28:15"}
+{"current_steps": 83, "total_steps": 5627, "loss": 1.8654, "learning_rate": 3.9997849555353356e-05, "epoch": 0.014749655693278244, "percentage": 1.48, "elapsed_time": "0:18:22", "remaining_time": "20:27:52"}
+{"current_steps": 84, "total_steps": 5627, "loss": 1.7623, "learning_rate": 3.999768095866157e-05, "epoch": 0.014927362388377982, "percentage": 1.49, "elapsed_time": "0:18:36", "remaining_time": "20:27:34"}
+{"current_steps": 85, "total_steps": 5627, "loss": 1.7645, "learning_rate": 3.999750600033141e-05, "epoch": 0.01510506908347772, "percentage": 1.51, "elapsed_time": "0:18:49", "remaining_time": "20:27:13"}
+{"current_steps": 86, "total_steps": 5627, "loss": 1.7335, "learning_rate": 3.9997324680418514e-05, "epoch": 0.015282775778577458, "percentage": 1.53, "elapsed_time": "0:19:02", "remaining_time": "20:26:55"}
+{"current_steps": 87, "total_steps": 5627, "loss": 1.7694, "learning_rate": 3.999713699898057e-05, "epoch": 0.015460482473677196, "percentage": 1.55, "elapsed_time": "0:19:15", "remaining_time": "20:26:35"}
+{"current_steps": 88, "total_steps": 5627, "loss": 1.7343, "learning_rate": 3.999694295607728e-05, "epoch": 0.015638189168776934, "percentage": 1.56, "elapsed_time": "0:19:28", "remaining_time": "20:26:16"}
+{"current_steps": 89, "total_steps": 5627, "loss": 1.8091, "learning_rate": 3.999674255177038e-05, "epoch": 0.01581589586387667, "percentage": 1.58, "elapsed_time": "0:19:42", "remaining_time": "20:25:51"}
+{"current_steps": 90, "total_steps": 5627, "loss": 1.7431, "learning_rate": 3.999653578612362e-05, "epoch": 0.01599360255897641, "percentage": 1.6, "elapsed_time": "0:19:55", "remaining_time": "20:25:33"}
+{"current_steps": 91, "total_steps": 5627, "loss": 1.7802, "learning_rate": 3.999632265920277e-05, "epoch": 0.016171309254076147, "percentage": 1.62, "elapsed_time": "0:20:08", "remaining_time": "20:25:15"}
+{"current_steps": 92, "total_steps": 5627, "loss": 1.7826, "learning_rate": 3.999610317107564e-05, "epoch": 0.016349015949175885, "percentage": 1.63, "elapsed_time": "0:20:21", "remaining_time": "20:25:01"}
+{"current_steps": 93, "total_steps": 5627, "loss": 1.7418, "learning_rate": 3.999587732181205e-05, "epoch": 0.016526722644275623, "percentage": 1.65, "elapsed_time": "0:20:34", "remaining_time": "20:24:43"}
+{"current_steps": 94, "total_steps": 5627, "loss": 1.7564, "learning_rate": 3.999564511148384e-05, "epoch": 0.01670442933937536, "percentage": 1.67, "elapsed_time": "0:20:48", "remaining_time": "20:24:25"}
+{"current_steps": 95, "total_steps": 5627, "loss": 1.7633, "learning_rate": 3.999540654016488e-05, "epoch": 0.0168821360344751, "percentage": 1.69, "elapsed_time": "0:21:01", "remaining_time": "20:24:06"}
+{"current_steps": 96, "total_steps": 5627, "loss": 1.7022, "learning_rate": 3.999516160793107e-05, "epoch": 0.017059842729574837, "percentage": 1.71, "elapsed_time": "0:21:14", "remaining_time": "20:23:48"}
+{"current_steps": 97, "total_steps": 5627, "loss": 1.7699, "learning_rate": 3.9994910314860334e-05, "epoch": 0.017237549424674575, "percentage": 1.72, "elapsed_time": "0:21:27", "remaining_time": "20:23:28"}
+{"current_steps": 98, "total_steps": 5627, "loss": 1.7267, "learning_rate": 3.99946526610326e-05, "epoch": 0.017415256119774312, "percentage": 1.74, "elapsed_time": "0:21:40", "remaining_time": "20:23:07"}
+{"current_steps": 99, "total_steps": 5627, "loss": 1.7269, "learning_rate": 3.999438864652984e-05, "epoch": 0.01759296281487405, "percentage": 1.76, "elapsed_time": "0:21:53", "remaining_time": "20:22:44"}
+{"current_steps": 100, "total_steps": 5627, "loss": 1.7254, "learning_rate": 3.999411827143604e-05, "epoch": 0.017770669509973788, "percentage": 1.78, "elapsed_time": "0:22:07", "remaining_time": "20:22:28"}
+{"current_steps": 101, "total_steps": 5627, "loss": 1.7174, "learning_rate": 3.999384153583721e-05, "epoch": 0.017948376205073526, "percentage": 1.79, "elapsed_time": "0:22:20", "remaining_time": "20:22:11"}
+{"current_steps": 102, "total_steps": 5627, "loss": 1.7588, "learning_rate": 3.999355843982139e-05, "epoch": 0.018126082900173264, "percentage": 1.81, "elapsed_time": "0:22:33", "remaining_time": "20:21:54"}
+{"current_steps": 103, "total_steps": 5627, "loss": 1.7692, "learning_rate": 3.999326898347863e-05, "epoch": 0.018303789595273002, "percentage": 1.83, "elapsed_time": "0:22:46", "remaining_time": "20:21:36"}
+{"current_steps": 104, "total_steps": 5627, "loss": 1.7229, "learning_rate": 3.9992973166901026e-05, "epoch": 0.01848149629037274, "percentage": 1.85, "elapsed_time": "0:22:59", "remaining_time": "20:21:19"}
+{"current_steps": 105, "total_steps": 5627, "loss": 1.716, "learning_rate": 3.9992670990182666e-05, "epoch": 0.018659202985472478, "percentage": 1.87, "elapsed_time": "0:23:13", "remaining_time": "20:21:01"}
+{"current_steps": 106, "total_steps": 5627, "loss": 1.7099, "learning_rate": 3.999236245341968e-05, "epoch": 0.018836909680572216, "percentage": 1.88, "elapsed_time": "0:23:26", "remaining_time": "20:20:44"}
+{"current_steps": 107, "total_steps": 5627, "loss": 1.7334, "learning_rate": 3.999204755671023e-05, "epoch": 0.019014616375671953, "percentage": 1.9, "elapsed_time": "0:23:39", "remaining_time": "20:20:23"}
+{"current_steps": 108, "total_steps": 5627, "loss": 1.6963, "learning_rate": 3.999172630015448e-05, "epoch": 0.01919232307077169, "percentage": 1.92, "elapsed_time": "0:23:52", "remaining_time": "20:20:04"}
+{"current_steps": 109, "total_steps": 5627, "loss": 1.728, "learning_rate": 3.999139868385464e-05, "epoch": 0.01937002976587143, "percentage": 1.94, "elapsed_time": "0:24:05", "remaining_time": "20:19:47"}
+{"current_steps": 110, "total_steps": 5627, "loss": 1.7138, "learning_rate": 3.999106470791492e-05, "epoch": 0.019547736460971167, "percentage": 1.95, "elapsed_time": "0:24:18", "remaining_time": "20:19:29"}
+{"current_steps": 111, "total_steps": 5627, "loss": 1.7108, "learning_rate": 3.999072437244157e-05, "epoch": 0.019725443156070905, "percentage": 1.97, "elapsed_time": "0:24:32", "remaining_time": "20:19:11"}
+{"current_steps": 112, "total_steps": 5627, "loss": 1.6981, "learning_rate": 3.999037767754285e-05, "epoch": 0.019903149851170643, "percentage": 1.99, "elapsed_time": "0:24:45", "remaining_time": "20:18:53"}
+{"current_steps": 113, "total_steps": 5627, "loss": 1.6938, "learning_rate": 3.999002462332905e-05, "epoch": 0.02008085654627038, "percentage": 2.01, "elapsed_time": "0:24:58", "remaining_time": "20:18:36"}
+{"current_steps": 114, "total_steps": 5627, "loss": 1.6945, "learning_rate": 3.99896652099125e-05, "epoch": 0.02025856324137012, "percentage": 2.03, "elapsed_time": "0:25:11", "remaining_time": "20:18:21"}
+{"current_steps": 115, "total_steps": 5627, "loss": 1.7146, "learning_rate": 3.998929943740752e-05, "epoch": 0.020436269936469856, "percentage": 2.04, "elapsed_time": "0:25:24", "remaining_time": "20:18:04"}
+{"current_steps": 116, "total_steps": 5627, "loss": 1.6832, "learning_rate": 3.998892730593047e-05, "epoch": 0.020613976631569594, "percentage": 2.06, "elapsed_time": "0:25:37", "remaining_time": "20:17:47"}
+{"current_steps": 117, "total_steps": 5627, "loss": 1.6759, "learning_rate": 3.998854881559974e-05, "epoch": 0.020791683326669332, "percentage": 2.08, "elapsed_time": "0:25:51", "remaining_time": "20:17:29"}
+{"current_steps": 118, "total_steps": 5627, "loss": 1.7151, "learning_rate": 3.998816396653573e-05, "epoch": 0.02096939002176907, "percentage": 2.1, "elapsed_time": "0:26:04", "remaining_time": "20:17:11"}
+{"current_steps": 119, "total_steps": 5627, "loss": 1.7496, "learning_rate": 3.998777275886086e-05, "epoch": 0.021147096716868808, "percentage": 2.11, "elapsed_time": "0:26:17", "remaining_time": "20:16:56"}
+{"current_steps": 120, "total_steps": 5627, "loss": 1.7266, "learning_rate": 3.9987375192699603e-05, "epoch": 0.021324803411968546, "percentage": 2.13, "elapsed_time": "0:26:30", "remaining_time": "20:16:44"}
+{"current_steps": 121, "total_steps": 5627, "loss": 1.7176, "learning_rate": 3.998697126817841e-05, "epoch": 0.021502510107068284, "percentage": 2.15, "elapsed_time": "0:26:43", "remaining_time": "20:16:23"}
+{"current_steps": 122, "total_steps": 5627, "loss": 1.7587, "learning_rate": 3.998656098542578e-05, "epoch": 0.02168021680216802, "percentage": 2.17, "elapsed_time": "0:26:57", "remaining_time": "20:16:05"}
+{"current_steps": 123, "total_steps": 5627, "loss": 1.6356, "learning_rate": 3.9986144344572244e-05, "epoch": 0.02185792349726776, "percentage": 2.19, "elapsed_time": "0:27:10", "remaining_time": "20:15:48"}
+{"current_steps": 124, "total_steps": 5627, "loss": 1.6403, "learning_rate": 3.998572134575033e-05, "epoch": 0.022035630192367497, "percentage": 2.2, "elapsed_time": "0:27:23", "remaining_time": "20:15:34"}
+{"current_steps": 125, "total_steps": 5627, "loss": 1.6716, "learning_rate": 3.998529198909461e-05, "epoch": 0.022213336887467235, "percentage": 2.22, "elapsed_time": "0:27:36", "remaining_time": "20:15:21"}
+{"current_steps": 126, "total_steps": 5627, "loss": 1.6616, "learning_rate": 3.9984856274741666e-05, "epoch": 0.022391043582566973, "percentage": 2.24, "elapsed_time": "0:27:49", "remaining_time": "20:15:05"}
+{"current_steps": 127, "total_steps": 5627, "loss": 1.6513, "learning_rate": 3.998441420283011e-05, "epoch": 0.02256875027766671, "percentage": 2.26, "elapsed_time": "0:28:03", "remaining_time": "20:14:50"}
+{"current_steps": 128, "total_steps": 5627, "loss": 1.6824, "learning_rate": 3.998396577350057e-05, "epoch": 0.02274645697276645, "percentage": 2.27, "elapsed_time": "0:28:16", "remaining_time": "20:14:34"}
+{"current_steps": 129, "total_steps": 5627, "loss": 1.6936, "learning_rate": 3.9983510986895714e-05, "epoch": 0.022924163667866187, "percentage": 2.29, "elapsed_time": "0:28:29", "remaining_time": "20:14:18"}
+{"current_steps": 130, "total_steps": 5627, "loss": 1.7095, "learning_rate": 3.998304984316019e-05, "epoch": 0.023101870362965925, "percentage": 2.31, "elapsed_time": "0:28:42", "remaining_time": "20:14:00"}
+{"current_steps": 131, "total_steps": 5627, "loss": 1.6822, "learning_rate": 3.9982582342440726e-05, "epoch": 0.023279577058065663, "percentage": 2.33, "elapsed_time": "0:28:55", "remaining_time": "20:13:40"}
+{"current_steps": 132, "total_steps": 5627, "loss": 1.6502, "learning_rate": 3.9982108484886016e-05, "epoch": 0.0234572837531654, "percentage": 2.35, "elapsed_time": "0:29:08", "remaining_time": "20:13:21"}
+{"current_steps": 133, "total_steps": 5627, "loss": 1.6866, "learning_rate": 3.998162827064683e-05, "epoch": 0.02363499044826514, "percentage": 2.36, "elapsed_time": "0:29:21", "remaining_time": "20:13:03"}
+{"current_steps": 134, "total_steps": 5627, "loss": 1.6819, "learning_rate": 3.998114169987591e-05, "epoch": 0.023812697143364876, "percentage": 2.38, "elapsed_time": "0:29:35", "remaining_time": "20:12:48"}
+{"current_steps": 135, "total_steps": 5627, "loss": 1.7422, "learning_rate": 3.998064877272806e-05, "epoch": 0.023990403838464614, "percentage": 2.4, "elapsed_time": "0:29:48", "remaining_time": "20:12:33"}
+{"current_steps": 136, "total_steps": 5627, "loss": 1.6836, "learning_rate": 3.998014948936008e-05, "epoch": 0.024168110533564352, "percentage": 2.42, "elapsed_time": "0:30:01", "remaining_time": "20:12:16"}
+{"current_steps": 137, "total_steps": 5627, "loss": 1.6646, "learning_rate": 3.99796438499308e-05, "epoch": 0.02434581722866409, "percentage": 2.43, "elapsed_time": "0:30:14", "remaining_time": "20:12:01"}
+{"current_steps": 138, "total_steps": 5627, "loss": 1.665, "learning_rate": 3.997913185460108e-05, "epoch": 0.024523523923763828, "percentage": 2.45, "elapsed_time": "0:30:27", "remaining_time": "20:11:47"}
+{"current_steps": 139, "total_steps": 5627, "loss": 1.6624, "learning_rate": 3.997861350353379e-05, "epoch": 0.024701230618863566, "percentage": 2.47, "elapsed_time": "0:30:41", "remaining_time": "20:11:32"}
+{"current_steps": 140, "total_steps": 5627, "loss": 1.7147, "learning_rate": 3.997808879689384e-05, "epoch": 0.024878937313963304, "percentage": 2.49, "elapsed_time": "0:30:54", "remaining_time": "20:11:17"}
+{"current_steps": 141, "total_steps": 5627, "loss": 1.6909, "learning_rate": 3.9977557734848127e-05, "epoch": 0.02505664400906304, "percentage": 2.51, "elapsed_time": "0:31:07", "remaining_time": "20:11:01"}
+{"current_steps": 142, "total_steps": 5627, "loss": 1.6584, "learning_rate": 3.997702031756561e-05, "epoch": 0.02523435070416278, "percentage": 2.52, "elapsed_time": "0:31:20", "remaining_time": "20:10:45"}
+{"current_steps": 143, "total_steps": 5627, "loss": 1.6917, "learning_rate": 3.997647654521724e-05, "epoch": 0.025412057399262517, "percentage": 2.54, "elapsed_time": "0:31:33", "remaining_time": "20:10:29"}
+{"current_steps": 144, "total_steps": 5627, "loss": 1.6634, "learning_rate": 3.997592641797601e-05, "epoch": 0.025589764094362255, "percentage": 2.56, "elapsed_time": "0:31:47", "remaining_time": "20:10:15"}
+{"current_steps": 145, "total_steps": 5627, "loss": 1.6671, "learning_rate": 3.997536993601692e-05, "epoch": 0.025767470789461993, "percentage": 2.58, "elapsed_time": "0:32:00", "remaining_time": "20:10:01"}
+{"current_steps": 146, "total_steps": 5627, "loss": 1.675, "learning_rate": 3.997480709951701e-05, "epoch": 0.02594517748456173, "percentage": 2.59, "elapsed_time": "0:32:13", "remaining_time": "20:09:46"}
+{"current_steps": 147, "total_steps": 5627, "loss": 1.6687, "learning_rate": 3.997423790865531e-05, "epoch": 0.02612288417966147, "percentage": 2.61, "elapsed_time": "0:32:26", "remaining_time": "20:09:31"}
+{"current_steps": 148, "total_steps": 5627, "loss": 1.6241, "learning_rate": 3.99736623636129e-05, "epoch": 0.026300590874761207, "percentage": 2.63, "elapsed_time": "0:32:39", "remaining_time": "20:09:17"}
+{"current_steps": 149, "total_steps": 5627, "loss": 1.6455, "learning_rate": 3.997308046457287e-05, "epoch": 0.026478297569860944, "percentage": 2.65, "elapsed_time": "0:32:53", "remaining_time": "20:09:03"}
+{"current_steps": 150, "total_steps": 5627, "loss": 1.7277, "learning_rate": 3.997249221172033e-05, "epoch": 0.026656004264960682, "percentage": 2.67, "elapsed_time": "0:33:06", "remaining_time": "20:08:48"}
+{"current_steps": 151, "total_steps": 5627, "loss": 1.637, "learning_rate": 3.997189760524242e-05, "epoch": 0.02683371096006042, "percentage": 2.68, "elapsed_time": "0:33:19", "remaining_time": "20:08:32"}
+{"current_steps": 152, "total_steps": 5627, "loss": 1.6634, "learning_rate": 3.997129664532829e-05, "epoch": 0.027011417655160158, "percentage": 2.7, "elapsed_time": "0:33:32", "remaining_time": "20:08:13"}
+{"current_steps": 153, "total_steps": 5627, "loss": 1.6723, "learning_rate": 3.9970689332169124e-05, "epoch": 0.027189124350259896, "percentage": 2.72, "elapsed_time": "0:33:45", "remaining_time": "20:07:55"}
+{"current_steps": 154, "total_steps": 5627, "loss": 1.6404, "learning_rate": 3.9970075665958124e-05, "epoch": 0.027366831045359634, "percentage": 2.74, "elapsed_time": "0:33:58", "remaining_time": "20:07:37"}
+{"current_steps": 155, "total_steps": 5627, "loss": 1.6465, "learning_rate": 3.996945564689049e-05, "epoch": 0.027544537740459372, "percentage": 2.75, "elapsed_time": "0:34:12", "remaining_time": "20:07:22"}
+{"current_steps": 156, "total_steps": 5627, "loss": 1.6791, "learning_rate": 3.996882927516347e-05, "epoch": 0.02772224443555911, "percentage": 2.77, "elapsed_time": "0:34:25", "remaining_time": "20:07:07"}
+{"current_steps": 157, "total_steps": 5627, "loss": 1.6456, "learning_rate": 3.9968196550976335e-05, "epoch": 0.027899951130658848, "percentage": 2.79, "elapsed_time": "0:34:38", "remaining_time": "20:06:52"}
+{"current_steps": 158, "total_steps": 5627, "loss": 1.6253, "learning_rate": 3.996755747453036e-05, "epoch": 0.028077657825758585, "percentage": 2.81, "elapsed_time": "0:34:51", "remaining_time": "20:06:34"}
+{"current_steps": 159, "total_steps": 5627, "loss": 1.6612, "learning_rate": 3.996691204602884e-05, "epoch": 0.028255364520858323, "percentage": 2.83, "elapsed_time": "0:35:04", "remaining_time": "20:06:16"}
+{"current_steps": 160, "total_steps": 5627, "loss": 1.696, "learning_rate": 3.99662602656771e-05, "epoch": 0.02843307121595806, "percentage": 2.84, "elapsed_time": "0:35:17", "remaining_time": "20:06:03"}
+{"current_steps": 161, "total_steps": 5627, "loss": 1.6818, "learning_rate": 3.9965602133682495e-05, "epoch": 0.0286107779110578, "percentage": 2.86, "elapsed_time": "0:35:31", "remaining_time": "20:05:48"}
+{"current_steps": 162, "total_steps": 5627, "loss": 1.6113, "learning_rate": 3.9964937650254375e-05, "epoch": 0.028788484606157537, "percentage": 2.88, "elapsed_time": "0:35:44", "remaining_time": "20:05:32"}
+{"current_steps": 163, "total_steps": 5627, "loss": 1.634, "learning_rate": 3.9964266815604135e-05, "epoch": 0.028966191301257275, "percentage": 2.9, "elapsed_time": "0:35:57", "remaining_time": "20:05:15"}
+{"current_steps": 164, "total_steps": 5627, "loss": 1.6214, "learning_rate": 3.9963589629945174e-05, "epoch": 0.029143897996357013, "percentage": 2.91, "elapsed_time": "0:36:10", "remaining_time": "20:05:00"}
+{"current_steps": 165, "total_steps": 5627, "loss": 1.6764, "learning_rate": 3.996290609349292e-05, "epoch": 0.02932160469145675, "percentage": 2.93, "elapsed_time": "0:36:23", "remaining_time": "20:04:45"}
+{"current_steps": 166, "total_steps": 5627, "loss": 1.6439, "learning_rate": 3.996221620646482e-05, "epoch": 0.02949931138655649, "percentage": 2.95, "elapsed_time": "0:36:36", "remaining_time": "20:04:30"}
+{"current_steps": 167, "total_steps": 5627, "loss": 1.6424, "learning_rate": 3.996151996908034e-05, "epoch": 0.029677018081656226, "percentage": 2.97, "elapsed_time": "0:36:50", "remaining_time": "20:04:16"}
+{"current_steps": 168, "total_steps": 5627, "loss": 1.6484, "learning_rate": 3.996081738156096e-05, "epoch": 0.029854724776755964, "percentage": 2.99, "elapsed_time": "0:37:03", "remaining_time": "20:04:02"}
+{"current_steps": 169, "total_steps": 5627, "loss": 1.6558, "learning_rate": 3.996010844413019e-05, "epoch": 0.030032431471855702, "percentage": 3.0, "elapsed_time": "0:37:16", "remaining_time": "20:03:47"}
+{"current_steps": 170, "total_steps": 5627, "loss": 1.6892, "learning_rate": 3.995939315701356e-05, "epoch": 0.03021013816695544, "percentage": 3.02, "elapsed_time": "0:37:29", "remaining_time": "20:03:33"}
+{"current_steps": 171, "total_steps": 5627, "loss": 1.6204, "learning_rate": 3.995867152043861e-05, "epoch": 0.030387844862055178, "percentage": 3.04, "elapsed_time": "0:37:42", "remaining_time": "20:03:16"}
+{"current_steps": 172, "total_steps": 5627, "loss": 1.6518, "learning_rate": 3.9957943534634914e-05, "epoch": 0.030565551557154916, "percentage": 3.06, "elapsed_time": "0:37:55", "remaining_time": "20:02:57"}
+{"current_steps": 173, "total_steps": 5627, "loss": 1.6389, "learning_rate": 3.9957209199834055e-05, "epoch": 0.030743258252254654, "percentage": 3.07, "elapsed_time": "0:38:08", "remaining_time": "20:02:41"}
+{"current_steps": 174, "total_steps": 5627, "loss": 1.6426, "learning_rate": 3.995646851626964e-05, "epoch": 0.03092096494735439, "percentage": 3.09, "elapsed_time": "0:38:22", "remaining_time": "20:02:24"}
+{"current_steps": 175, "total_steps": 5627, "loss": 1.6373, "learning_rate": 3.9955721484177285e-05, "epoch": 0.03109867164245413, "percentage": 3.11, "elapsed_time": "0:38:35", "remaining_time": "20:02:09"}
+{"current_steps": 176, "total_steps": 5627, "loss": 1.659, "learning_rate": 3.9954968103794643e-05, "epoch": 0.03127637833755387, "percentage": 3.13, "elapsed_time": "0:38:48", "remaining_time": "20:01:55"}
+{"current_steps": 177, "total_steps": 5627, "loss": 1.6385, "learning_rate": 3.9954208375361376e-05, "epoch": 0.03145408503265361, "percentage": 3.15, "elapsed_time": "0:39:01", "remaining_time": "20:01:41"}
+{"current_steps": 178, "total_steps": 5627, "loss": 1.6435, "learning_rate": 3.9953442299119166e-05, "epoch": 0.03163179172775334, "percentage": 3.16, "elapsed_time": "0:39:14", "remaining_time": "20:01:27"}
+{"current_steps": 179, "total_steps": 5627, "loss": 1.6432, "learning_rate": 3.995266987531173e-05, "epoch": 0.031809498422853084, "percentage": 3.18, "elapsed_time": "0:39:28", "remaining_time": "20:01:13"}
+{"current_steps": 180, "total_steps": 5627, "loss": 1.6434, "learning_rate": 3.995189110418477e-05, "epoch": 0.03198720511795282, "percentage": 3.2, "elapsed_time": "0:39:41", "remaining_time": "20:00:58"}
+{"current_steps": 181, "total_steps": 5627, "loss": 1.603, "learning_rate": 3.9951105985986044e-05, "epoch": 0.03216491181305256, "percentage": 3.22, "elapsed_time": "0:39:54", "remaining_time": "20:00:42"}
+{"current_steps": 182, "total_steps": 5627, "loss": 1.6698, "learning_rate": 3.9950314520965304e-05, "epoch": 0.032342618508152295, "percentage": 3.23, "elapsed_time": "0:40:07", "remaining_time": "20:00:26"}
+{"current_steps": 183, "total_steps": 5627, "loss": 1.6363, "learning_rate": 3.9949516709374337e-05, "epoch": 0.032520325203252036, "percentage": 3.25, "elapsed_time": "0:40:20", "remaining_time": "20:00:12"}
+{"current_steps": 184, "total_steps": 5627, "loss": 1.6761, "learning_rate": 3.9948712551466925e-05, "epoch": 0.03269803189835177, "percentage": 3.27, "elapsed_time": "0:40:33", "remaining_time": "19:59:58"}
+{"current_steps": 185, "total_steps": 5627, "loss": 1.6228, "learning_rate": 3.994790204749891e-05, "epoch": 0.03287573859345151, "percentage": 3.29, "elapsed_time": "0:40:47", "remaining_time": "19:59:44"}
+{"current_steps": 186, "total_steps": 5627, "loss": 1.6578, "learning_rate": 3.994708519772811e-05, "epoch": 0.033053445288551246, "percentage": 3.31, "elapsed_time": "0:41:00", "remaining_time": "19:59:29"}
+{"current_steps": 187, "total_steps": 5627, "loss": 1.6126, "learning_rate": 3.994626200241439e-05, "epoch": 0.03323115198365099, "percentage": 3.32, "elapsed_time": "0:41:13", "remaining_time": "19:59:15"}
+{"current_steps": 188, "total_steps": 5627, "loss": 1.6306, "learning_rate": 3.9945432461819615e-05, "epoch": 0.03340885867875072, "percentage": 3.34, "elapsed_time": "0:41:26", "remaining_time": "19:59:02"}
+{"current_steps": 189, "total_steps": 5627, "loss": 1.6146, "learning_rate": 3.994459657620769e-05, "epoch": 0.03358656537385046, "percentage": 3.36, "elapsed_time": "0:41:39", "remaining_time": "19:58:50"}
+{"current_steps": 190, "total_steps": 5627, "loss": 1.6378, "learning_rate": 3.994375434584452e-05, "epoch": 0.0337642720689502, "percentage": 3.38, "elapsed_time": "0:41:53", "remaining_time": "19:58:36"}
+{"current_steps": 191, "total_steps": 5627, "loss": 1.6357, "learning_rate": 3.9942905770998025e-05, "epoch": 0.03394197876404994, "percentage": 3.39, "elapsed_time": "0:42:06", "remaining_time": "19:58:22"}
+{"current_steps": 192, "total_steps": 5627, "loss": 1.6567, "learning_rate": 3.994205085193817e-05, "epoch": 0.03411968545914967, "percentage": 3.41, "elapsed_time": "0:42:19", "remaining_time": "19:58:08"}
+{"current_steps": 193, "total_steps": 5627, "loss": 1.6044, "learning_rate": 3.9941189588936905e-05, "epoch": 0.034297392154249415, "percentage": 3.43, "elapsed_time": "0:42:32", "remaining_time": "19:57:53"}
+{"current_steps": 194, "total_steps": 5627, "loss": 1.626, "learning_rate": 3.994032198226823e-05, "epoch": 0.03447509884934915, "percentage": 3.45, "elapsed_time": "0:42:45", "remaining_time": "19:57:37"}
+{"current_steps": 195, "total_steps": 5627, "loss": 1.6657, "learning_rate": 3.993944803220813e-05, "epoch": 0.03465280554444889, "percentage": 3.47, "elapsed_time": "0:42:58", "remaining_time": "19:57:19"}
+{"current_steps": 196, "total_steps": 5627, "loss": 1.6047, "learning_rate": 3.9938567739034634e-05, "epoch": 0.034830512239548625, "percentage": 3.48, "elapsed_time": "0:43:12", "remaining_time": "19:57:04"}
+{"current_steps": 197, "total_steps": 5627, "loss": 1.5915, "learning_rate": 3.993768110302778e-05, "epoch": 0.035008218934648366, "percentage": 3.5, "elapsed_time": "0:43:25", "remaining_time": "19:56:50"}
+{"current_steps": 198, "total_steps": 5627, "loss": 1.6338, "learning_rate": 3.9936788124469615e-05, "epoch": 0.0351859256297481, "percentage": 3.52, "elapsed_time": "0:43:38", "remaining_time": "19:56:37"}
+{"current_steps": 199, "total_steps": 5627, "loss": 1.6309, "learning_rate": 3.993588880364423e-05, "epoch": 0.03536363232484784, "percentage": 3.54, "elapsed_time": "0:43:51", "remaining_time": "19:56:23"}
+{"current_steps": 200, "total_steps": 5627, "loss": 1.6072, "learning_rate": 3.99349831408377e-05, "epoch": 0.035541339019947576, "percentage": 3.55, "elapsed_time": "0:44:04", "remaining_time": "19:56:10"}
+{"current_steps": 201, "total_steps": 5627, "loss": 1.5952, "learning_rate": 3.993407113633814e-05, "epoch": 0.03571904571504732, "percentage": 3.57, "elapsed_time": "0:44:18", "remaining_time": "19:55:56"}
+{"current_steps": 202, "total_steps": 5627, "loss": 1.6452, "learning_rate": 3.993315279043568e-05, "epoch": 0.03589675241014705, "percentage": 3.59, "elapsed_time": "0:44:31", "remaining_time": "19:55:39"}
+{"current_steps": 203, "total_steps": 5627, "loss": 1.5831, "learning_rate": 3.9932228103422445e-05, "epoch": 0.036074459105246794, "percentage": 3.61, "elapsed_time": "0:44:44", "remaining_time": "19:55:22"}
+{"current_steps": 204, "total_steps": 5627, "loss": 1.5641, "learning_rate": 3.993129707559262e-05, "epoch": 0.03625216580034653, "percentage": 3.63, "elapsed_time": "0:44:57", "remaining_time": "19:55:07"}
+{"current_steps": 205, "total_steps": 5627, "loss": 1.5688, "learning_rate": 3.9930359707242364e-05, "epoch": 0.03642987249544627, "percentage": 3.64, "elapsed_time": "0:45:10", "remaining_time": "19:54:52"}
+{"current_steps": 206, "total_steps": 5627, "loss": 1.5621, "learning_rate": 3.9929415998669875e-05, "epoch": 0.036607579190546004, "percentage": 3.66, "elapsed_time": "0:45:23", "remaining_time": "19:54:38"}
+{"current_steps": 207, "total_steps": 5627, "loss": 1.6295, "learning_rate": 3.992846595017538e-05, "epoch": 0.036785285885645745, "percentage": 3.68, "elapsed_time": "0:45:37", "remaining_time": "19:54:24"}
+{"current_steps": 208, "total_steps": 5627, "loss": 1.5886, "learning_rate": 3.9927509562061084e-05, "epoch": 0.03696299258074548, "percentage": 3.7, "elapsed_time": "0:45:50", "remaining_time": "19:54:10"}
+{"current_steps": 209, "total_steps": 5627, "loss": 1.598, "learning_rate": 3.9926546834631244e-05, "epoch": 0.03714069927584522, "percentage": 3.71, "elapsed_time": "0:46:03", "remaining_time": "19:53:56"}
+{"current_steps": 210, "total_steps": 5627, "loss": 1.5967, "learning_rate": 3.9925577768192116e-05, "epoch": 0.037318405970944955, "percentage": 3.73, "elapsed_time": "0:46:16", "remaining_time": "19:53:43"}
+{"current_steps": 211, "total_steps": 5627, "loss": 1.6137, "learning_rate": 3.9924602363051995e-05, "epoch": 0.0374961126660447, "percentage": 3.75, "elapsed_time": "0:46:29", "remaining_time": "19:53:28"}
+{"current_steps": 212, "total_steps": 5627, "loss": 1.6328, "learning_rate": 3.992362061952115e-05, "epoch": 0.03767381936114443, "percentage": 3.77, "elapsed_time": "0:46:42", "remaining_time": "19:53:15"}
+{"current_steps": 213, "total_steps": 5627, "loss": 1.5706, "learning_rate": 3.9922632537911916e-05, "epoch": 0.03785152605624417, "percentage": 3.79, "elapsed_time": "0:46:56", "remaining_time": "19:52:58"}
+{"current_steps": 214, "total_steps": 5627, "loss": 1.5984, "learning_rate": 3.9921638118538607e-05, "epoch": 0.03802923275134391, "percentage": 3.8, "elapsed_time": "0:47:09", "remaining_time": "19:52:41"}
+{"current_steps": 215, "total_steps": 5627, "loss": 1.629, "learning_rate": 3.9920637361717566e-05, "epoch": 0.03820693944644365, "percentage": 3.82, "elapsed_time": "0:47:22", "remaining_time": "19:52:25"}
+{"current_steps": 216, "total_steps": 5627, "loss": 1.5745, "learning_rate": 3.991963026776716e-05, "epoch": 0.03838464614154338, "percentage": 3.84, "elapsed_time": "0:47:35", "remaining_time": "19:52:11"}
+{"current_steps": 217, "total_steps": 5627, "loss": 1.5943, "learning_rate": 3.9918616837007755e-05, "epoch": 0.038562352836643124, "percentage": 3.86, "elapsed_time": "0:47:48", "remaining_time": "19:51:57"}
+{"current_steps": 218, "total_steps": 5627, "loss": 1.5936, "learning_rate": 3.9917597069761746e-05, "epoch": 0.03874005953174286, "percentage": 3.87, "elapsed_time": "0:48:01", "remaining_time": "19:51:43"}
+{"current_steps": 219, "total_steps": 5627, "loss": 1.5849, "learning_rate": 3.991657096635355e-05, "epoch": 0.0389177662268426, "percentage": 3.89, "elapsed_time": "0:48:15", "remaining_time": "19:51:30"}
+{"current_steps": 220, "total_steps": 5627, "loss": 1.6322, "learning_rate": 3.991553852710958e-05, "epoch": 0.039095472921942334, "percentage": 3.91, "elapsed_time": "0:48:28", "remaining_time": "19:51:16"}
+{"current_steps": 221, "total_steps": 5627, "loss": 1.6001, "learning_rate": 3.991449975235827e-05, "epoch": 0.039273179617042075, "percentage": 3.93, "elapsed_time": "0:48:41", "remaining_time": "19:51:03"}
+{"current_steps": 222, "total_steps": 5627, "loss": 1.5732, "learning_rate": 3.991345464243009e-05, "epoch": 0.03945088631214181, "percentage": 3.95, "elapsed_time": "0:48:54", "remaining_time": "19:50:49"}
+{"current_steps": 223, "total_steps": 5627, "loss": 1.5818, "learning_rate": 3.9912403197657485e-05, "epoch": 0.03962859300724155, "percentage": 3.96, "elapsed_time": "0:49:07", "remaining_time": "19:50:36"}
+{"current_steps": 224, "total_steps": 5627, "loss": 1.5495, "learning_rate": 3.9911345418374965e-05, "epoch": 0.039806299702341286, "percentage": 3.98, "elapsed_time": "0:49:21", "remaining_time": "19:50:21"}
+{"current_steps": 225, "total_steps": 5627, "loss": 1.5785, "learning_rate": 3.991028130491901e-05, "epoch": 0.03998400639744103, "percentage": 4.0, "elapsed_time": "0:49:34", "remaining_time": "19:50:06"}
+{"current_steps": 226, "total_steps": 5627, "loss": 1.5928, "learning_rate": 3.990921085762815e-05, "epoch": 0.04016171309254076, "percentage": 4.02, "elapsed_time": "0:49:47", "remaining_time": "19:49:51"}
+{"current_steps": 227, "total_steps": 5627, "loss": 1.5949, "learning_rate": 3.99081340768429e-05, "epoch": 0.0403394197876405, "percentage": 4.03, "elapsed_time": "0:50:00", "remaining_time": "19:49:38"}
+{"current_steps": 228, "total_steps": 5627, "loss": 1.599, "learning_rate": 3.9907050962905814e-05, "epoch": 0.04051712648274024, "percentage": 4.05, "elapsed_time": "0:50:13", "remaining_time": "19:49:24"}
+{"current_steps": 229, "total_steps": 5627, "loss": 1.5809, "learning_rate": 3.990596151616145e-05, "epoch": 0.04069483317783998, "percentage": 4.07, "elapsed_time": "0:50:26", "remaining_time": "19:49:11"}
+{"current_steps": 230, "total_steps": 5627, "loss": 1.6317, "learning_rate": 3.9904865736956376e-05, "epoch": 0.04087253987293971, "percentage": 4.09, "elapsed_time": "0:50:40", "remaining_time": "19:48:57"}
+{"current_steps": 231, "total_steps": 5627, "loss": 1.6248, "learning_rate": 3.990376362563918e-05, "epoch": 0.041050246568039454, "percentage": 4.11, "elapsed_time": "0:50:53", "remaining_time": "19:48:43"}
+{"current_steps": 232, "total_steps": 5627, "loss": 1.628, "learning_rate": 3.990265518256047e-05, "epoch": 0.04122795326313919, "percentage": 4.12, "elapsed_time": "0:51:06", "remaining_time": "19:48:29"}
+{"current_steps": 233, "total_steps": 5627, "loss": 1.5614, "learning_rate": 3.990154040807287e-05, "epoch": 0.04140565995823893, "percentage": 4.14, "elapsed_time": "0:51:19", "remaining_time": "19:48:14"}
+{"current_steps": 234, "total_steps": 5627, "loss": 1.5737, "learning_rate": 3.9900419302530984e-05, "epoch": 0.041583366653338664, "percentage": 4.16, "elapsed_time": "0:51:32", "remaining_time": "19:47:58"}
+{"current_steps": 235, "total_steps": 5627, "loss": 1.59, "learning_rate": 3.989929186629149e-05, "epoch": 0.041761073348438406, "percentage": 4.18, "elapsed_time": "0:51:45", "remaining_time": "19:47:42"}
+{"current_steps": 236, "total_steps": 5627, "loss": 1.6081, "learning_rate": 3.989815809971302e-05, "epoch": 0.04193878004353814, "percentage": 4.19, "elapsed_time": "0:51:59", "remaining_time": "19:47:28"}
+{"current_steps": 237, "total_steps": 5627, "loss": 1.6122, "learning_rate": 3.989701800315626e-05, "epoch": 0.04211648673863788, "percentage": 4.21, "elapsed_time": "0:52:12", "remaining_time": "19:47:12"}
+{"current_steps": 238, "total_steps": 5627, "loss": 1.5899, "learning_rate": 3.989587157698389e-05, "epoch": 0.042294193433737616, "percentage": 4.23, "elapsed_time": "0:52:25", "remaining_time": "19:46:58"}
+{"current_steps": 239, "total_steps": 5627, "loss": 1.5385, "learning_rate": 3.989471882156061e-05, "epoch": 0.04247190012883736, "percentage": 4.25, "elapsed_time": "0:52:38", "remaining_time": "19:46:44"}
+{"current_steps": 240, "total_steps": 5627, "loss": 1.589, "learning_rate": 3.989355973725315e-05, "epoch": 0.04264960682393709, "percentage": 4.27, "elapsed_time": "0:52:51", "remaining_time": "19:46:31"}
+{"current_steps": 241, "total_steps": 5627, "loss": 1.6116, "learning_rate": 3.9892394324430215e-05, "epoch": 0.04282731351903683, "percentage": 4.28, "elapsed_time": "0:53:04", "remaining_time": "19:46:17"}
+{"current_steps": 242, "total_steps": 5627, "loss": 1.561, "learning_rate": 3.989122258346255e-05, "epoch": 0.04300502021413657, "percentage": 4.3, "elapsed_time": "0:53:18", "remaining_time": "19:46:04"}
+{"current_steps": 243, "total_steps": 5627, "loss": 1.6205, "learning_rate": 3.989004451472291e-05, "epoch": 0.04318272690923631, "percentage": 4.32, "elapsed_time": "0:53:31", "remaining_time": "19:45:50"}
+{"current_steps": 244, "total_steps": 5627, "loss": 1.6104, "learning_rate": 3.988886011858606e-05, "epoch": 0.04336043360433604, "percentage": 4.34, "elapsed_time": "0:53:44", "remaining_time": "19:45:36"}
+{"current_steps": 245, "total_steps": 5627, "loss": 1.5922, "learning_rate": 3.9887669395428776e-05, "epoch": 0.043538140299435785, "percentage": 4.35, "elapsed_time": "0:53:57", "remaining_time": "19:45:23"}
+{"current_steps": 246, "total_steps": 5627, "loss": 1.5628, "learning_rate": 3.988647234562986e-05, "epoch": 0.04371584699453552, "percentage": 4.37, "elapsed_time": "0:54:10", "remaining_time": "19:45:09"}
+{"current_steps": 247, "total_steps": 5627, "loss": 1.609, "learning_rate": 3.988526896957011e-05, "epoch": 0.04389355368963526, "percentage": 4.39, "elapsed_time": "0:54:24", "remaining_time": "19:44:55"}
+{"current_steps": 248, "total_steps": 5627, "loss": 1.5913, "learning_rate": 3.988405926763234e-05, "epoch": 0.044071260384734995, "percentage": 4.41, "elapsed_time": "0:54:37", "remaining_time": "19:44:41"}
+{"current_steps": 249, "total_steps": 5627, "loss": 1.5972, "learning_rate": 3.9882843240201374e-05, "epoch": 0.044248967079834736, "percentage": 4.43, "elapsed_time": "0:54:50", "remaining_time": "19:44:28"}
+{"current_steps": 250, "total_steps": 5627, "loss": 1.5783, "learning_rate": 3.988162088766406e-05, "epoch": 0.04442667377493447, "percentage": 4.44, "elapsed_time": "0:55:03", "remaining_time": "19:44:14"}
+{"current_steps": 251, "total_steps": 5627, "loss": 1.587, "learning_rate": 3.988039221040926e-05, "epoch": 0.04460438047003421, "percentage": 4.46, "elapsed_time": "0:55:16", "remaining_time": "19:44:01"}
+{"current_steps": 252, "total_steps": 5627, "loss": 1.5918, "learning_rate": 3.9879157208827826e-05, "epoch": 0.044782087165133946, "percentage": 4.48, "elapsed_time": "0:55:30", "remaining_time": "19:43:49"}
+{"current_steps": 253, "total_steps": 5627, "loss": 1.5574, "learning_rate": 3.9877915883312636e-05, "epoch": 0.04495979386023369, "percentage": 4.5, "elapsed_time": "0:55:43", "remaining_time": "19:43:35"}
+{"current_steps": 254, "total_steps": 5627, "loss": 1.5939, "learning_rate": 3.9876668234258586e-05, "epoch": 0.04513750055533342, "percentage": 4.51, "elapsed_time": "0:55:56", "remaining_time": "19:43:22"}
+{"current_steps": 255, "total_steps": 5627, "loss": 1.61, "learning_rate": 3.9875414262062574e-05, "epoch": 0.045315207250433163, "percentage": 4.53, "elapsed_time": "0:56:09", "remaining_time": "19:43:07"}
+{"current_steps": 256, "total_steps": 5627, "loss": 1.5715, "learning_rate": 3.9874153967123506e-05, "epoch": 0.0454929139455329, "percentage": 4.55, "elapsed_time": "0:56:22", "remaining_time": "19:42:53"}
+{"current_steps": 257, "total_steps": 5627, "loss": 1.5788, "learning_rate": 3.9872887349842314e-05, "epoch": 0.04567062064063264, "percentage": 4.57, "elapsed_time": "0:56:36", "remaining_time": "19:42:39"}
+{"current_steps": 258, "total_steps": 5627, "loss": 1.6321, "learning_rate": 3.987161441062194e-05, "epoch": 0.045848327335732374, "percentage": 4.59, "elapsed_time": "0:56:49", "remaining_time": "19:42:23"}
+{"current_steps": 259, "total_steps": 5627, "loss": 1.5522, "learning_rate": 3.98703351498673e-05, "epoch": 0.046026034030832115, "percentage": 4.6, "elapsed_time": "0:57:02", "remaining_time": "19:42:09"}
+{"current_steps": 260, "total_steps": 5627, "loss": 1.5573, "learning_rate": 3.9869049567985384e-05, "epoch": 0.04620374072593185, "percentage": 4.62, "elapsed_time": "0:57:15", "remaining_time": "19:41:56"}
+{"current_steps": 261, "total_steps": 5627, "loss": 1.625, "learning_rate": 3.9867757665385146e-05, "epoch": 0.04638144742103159, "percentage": 4.64, "elapsed_time": "0:57:28", "remaining_time": "19:41:42"}
+{"current_steps": 262, "total_steps": 5627, "loss": 1.5578, "learning_rate": 3.986645944247756e-05, "epoch": 0.046559154116131325, "percentage": 4.66, "elapsed_time": "0:57:41", "remaining_time": "19:41:29"}
+{"current_steps": 263, "total_steps": 5627, "loss": 1.5679, "learning_rate": 3.986515489967562e-05, "epoch": 0.04673686081123107, "percentage": 4.67, "elapsed_time": "0:57:55", "remaining_time": "19:41:15"}
+{"current_steps": 264, "total_steps": 5627, "loss": 1.5496, "learning_rate": 3.9863844037394326e-05, "epoch": 0.0469145675063308, "percentage": 4.69, "elapsed_time": "0:58:08", "remaining_time": "19:41:02"}
+{"current_steps": 265, "total_steps": 5627, "loss": 1.5568, "learning_rate": 3.986252685605069e-05, "epoch": 0.04709227420143054, "percentage": 4.71, "elapsed_time": "0:58:21", "remaining_time": "19:40:47"}
+{"current_steps": 266, "total_steps": 5627, "loss": 1.5567, "learning_rate": 3.986120335606372e-05, "epoch": 0.04726998089653028, "percentage": 4.73, "elapsed_time": "0:58:34", "remaining_time": "19:40:33"}
+{"current_steps": 267, "total_steps": 5627, "loss": 1.5729, "learning_rate": 3.985987353785446e-05, "epoch": 0.04744768759163002, "percentage": 4.74, "elapsed_time": "0:58:47", "remaining_time": "19:40:19"}
+{"current_steps": 268, "total_steps": 5627, "loss": 1.5716, "learning_rate": 3.9858537401845955e-05, "epoch": 0.04762539428672975, "percentage": 4.76, "elapsed_time": "0:59:00", "remaining_time": "19:40:05"}
+{"current_steps": 269, "total_steps": 5627, "loss": 1.5793, "learning_rate": 3.985719494846324e-05, "epoch": 0.047803100981829494, "percentage": 4.78, "elapsed_time": "0:59:14", "remaining_time": "19:39:50"}
+{"current_steps": 270, "total_steps": 5627, "loss": 1.5812, "learning_rate": 3.985584617813338e-05, "epoch": 0.04798080767692923, "percentage": 4.8, "elapsed_time": "0:59:27", "remaining_time": "19:39:36"}
+{"current_steps": 271, "total_steps": 5627, "loss": 1.5836, "learning_rate": 3.985449109128545e-05, "epoch": 0.04815851437202897, "percentage": 4.82, "elapsed_time": "0:59:40", "remaining_time": "19:39:21"}
+{"current_steps": 272, "total_steps": 5627, "loss": 1.5948, "learning_rate": 3.985312968835051e-05, "epoch": 0.048336221067128704, "percentage": 4.83, "elapsed_time": "0:59:53", "remaining_time": "19:39:09"}
+{"current_steps": 273, "total_steps": 5627, "loss": 1.5933, "learning_rate": 3.9851761969761676e-05, "epoch": 0.048513927762228445, "percentage": 4.85, "elapsed_time": "1:00:06", "remaining_time": "19:38:54"}
+{"current_steps": 274, "total_steps": 5627, "loss": 1.5873, "learning_rate": 3.985038793595402e-05, "epoch": 0.04869163445732818, "percentage": 4.87, "elapsed_time": "1:00:19", "remaining_time": "19:38:41"}
+{"current_steps": 275, "total_steps": 5627, "loss": 1.5742, "learning_rate": 3.984900758736467e-05, "epoch": 0.04886934115242792, "percentage": 4.89, "elapsed_time": "1:00:33", "remaining_time": "19:38:28"}
+{"current_steps": 276, "total_steps": 5627, "loss": 1.5751, "learning_rate": 3.984762092443271e-05, "epoch": 0.049047047847527656, "percentage": 4.9, "elapsed_time": "1:00:46", "remaining_time": "19:38:15"}
+{"current_steps": 277, "total_steps": 5627, "loss": 1.5223, "learning_rate": 3.98462279475993e-05, "epoch": 0.0492247545426274, "percentage": 4.92, "elapsed_time": "1:00:59", "remaining_time": "19:38:01"}
+{"current_steps": 278, "total_steps": 5627, "loss": 1.5701, "learning_rate": 3.984482865730755e-05, "epoch": 0.04940246123772713, "percentage": 4.94, "elapsed_time": "1:01:12", "remaining_time": "19:37:46"}
+{"current_steps": 279, "total_steps": 5627, "loss": 1.5868, "learning_rate": 3.98434230540026e-05, "epoch": 0.04958016793282687, "percentage": 4.96, "elapsed_time": "1:01:25", "remaining_time": "19:37:32"}
+{"current_steps": 280, "total_steps": 5627, "loss": 1.5451, "learning_rate": 3.9842011138131605e-05, "epoch": 0.04975787462792661, "percentage": 4.98, "elapsed_time": "1:01:39", "remaining_time": "19:37:18"}
+{"current_steps": 281, "total_steps": 5627, "loss": 1.5473, "learning_rate": 3.984059291014373e-05, "epoch": 0.04993558132302635, "percentage": 4.99, "elapsed_time": "1:01:52", "remaining_time": "19:37:03"}
+{"current_steps": 282, "total_steps": 5627, "loss": 1.5398, "learning_rate": 3.9839168370490126e-05, "epoch": 0.05011328801812608, "percentage": 5.01, "elapsed_time": "1:02:05", "remaining_time": "19:36:50"}
+{"current_steps": 283, "total_steps": 5627, "loss": 1.6196, "learning_rate": 3.983773751962397e-05, "epoch": 0.050290994713225824, "percentage": 5.03, "elapsed_time": "1:02:18", "remaining_time": "19:36:37"}
+{"current_steps": 284, "total_steps": 5627, "loss": 1.5496, "learning_rate": 3.983630035800044e-05, "epoch": 0.05046870140832556, "percentage": 5.05, "elapsed_time": "1:02:31", "remaining_time": "19:36:23"}
+{"current_steps": 285, "total_steps": 5627, "loss": 1.5621, "learning_rate": 3.9834856886076734e-05, "epoch": 0.0506464081034253, "percentage": 5.06, "elapsed_time": "1:02:44", "remaining_time": "19:36:10"}
+{"current_steps": 286, "total_steps": 5627, "loss": 1.6027, "learning_rate": 3.983340710431204e-05, "epoch": 0.050824114798525034, "percentage": 5.08, "elapsed_time": "1:02:58", "remaining_time": "19:35:56"}
+{"current_steps": 287, "total_steps": 5627, "loss": 1.5942, "learning_rate": 3.983195101316756e-05, "epoch": 0.051001821493624776, "percentage": 5.1, "elapsed_time": "1:03:11", "remaining_time": "19:35:43"}
+{"current_steps": 288, "total_steps": 5627, "loss": 1.594, "learning_rate": 3.983048861310651e-05, "epoch": 0.05117952818872451, "percentage": 5.12, "elapsed_time": "1:03:24", "remaining_time": "19:35:28"}
+{"current_steps": 289, "total_steps": 5627, "loss": 1.5616, "learning_rate": 3.98290199045941e-05, "epoch": 0.05135723488382425, "percentage": 5.14, "elapsed_time": "1:03:37", "remaining_time": "19:35:13"}
+{"current_steps": 290, "total_steps": 5627, "loss": 1.5636, "learning_rate": 3.982754488809756e-05, "epoch": 0.051534941578923986, "percentage": 5.15, "elapsed_time": "1:03:50", "remaining_time": "19:35:00"}
+{"current_steps": 291, "total_steps": 5627, "loss": 1.5487, "learning_rate": 3.982606356408611e-05, "epoch": 0.05171264827402373, "percentage": 5.17, "elapsed_time": "1:04:04", "remaining_time": "19:34:46"}
+{"current_steps": 292, "total_steps": 5627, "loss": 1.5767, "learning_rate": 3.9824575933031e-05, "epoch": 0.05189035496912346, "percentage": 5.19, "elapsed_time": "1:04:17", "remaining_time": "19:34:33"}
+{"current_steps": 293, "total_steps": 5627, "loss": 1.586, "learning_rate": 3.982308199540547e-05, "epoch": 0.0520680616642232, "percentage": 5.21, "elapsed_time": "1:04:30", "remaining_time": "19:34:20"}
+{"current_steps": 294, "total_steps": 5627, "loss": 1.5928, "learning_rate": 3.982158175168476e-05, "epoch": 0.05224576835932294, "percentage": 5.22, "elapsed_time": "1:04:43", "remaining_time": "19:34:07"}
+{"current_steps": 295, "total_steps": 5627, "loss": 1.5465, "learning_rate": 3.982007520234614e-05, "epoch": 0.05242347505442268, "percentage": 5.24, "elapsed_time": "1:04:56", "remaining_time": "19:33:53"}
+{"current_steps": 296, "total_steps": 5627, "loss": 1.5574, "learning_rate": 3.9818562347868864e-05, "epoch": 0.05260118174952241, "percentage": 5.26, "elapsed_time": "1:05:10", "remaining_time": "19:33:40"}
+{"current_steps": 297, "total_steps": 5627, "loss": 1.5309, "learning_rate": 3.98170431887342e-05, "epoch": 0.052778888444622155, "percentage": 5.28, "elapsed_time": "1:05:23", "remaining_time": "19:33:27"}
+{"current_steps": 298, "total_steps": 5627, "loss": 1.5313, "learning_rate": 3.981551772542542e-05, "epoch": 0.05295659513972189, "percentage": 5.3, "elapsed_time": "1:05:36", "remaining_time": "19:33:12"}
+{"current_steps": 299, "total_steps": 5627, "loss": 1.5646, "learning_rate": 3.98139859584278e-05, "epoch": 0.05313430183482163, "percentage": 5.31, "elapsed_time": "1:05:49", "remaining_time": "19:32:57"}
+{"current_steps": 300, "total_steps": 5627, "loss": 1.6002, "learning_rate": 3.981244788822864e-05, "epoch": 0.053312008529921365, "percentage": 5.33, "elapsed_time": "1:06:02", "remaining_time": "19:32:41"}
+{"current_steps": 301, "total_steps": 5627, "loss": 1.5156, "learning_rate": 3.98109035153172e-05, "epoch": 0.053489715225021106, "percentage": 5.35, "elapsed_time": "1:06:15", "remaining_time": "19:32:28"}
+{"current_steps": 302, "total_steps": 5627, "loss": 1.608, "learning_rate": 3.980935284018481e-05, "epoch": 0.05366742192012084, "percentage": 5.37, "elapsed_time": "1:06:28", "remaining_time": "19:32:14"}
+{"current_steps": 303, "total_steps": 5627, "loss": 1.5257, "learning_rate": 3.980779586332473e-05, "epoch": 0.05384512861522058, "percentage": 5.38, "elapsed_time": "1:06:42", "remaining_time": "19:32:01"}
+{"current_steps": 304, "total_steps": 5627, "loss": 1.5491, "learning_rate": 3.98062325852323e-05, "epoch": 0.054022835310320316, "percentage": 5.4, "elapsed_time": "1:06:55", "remaining_time": "19:31:46"}
+{"current_steps": 305, "total_steps": 5627, "loss": 1.5504, "learning_rate": 3.98046630064048e-05, "epoch": 0.05420054200542006, "percentage": 5.42, "elapsed_time": "1:07:08", "remaining_time": "19:31:32"}
+{"current_steps": 306, "total_steps": 5627, "loss": 1.557, "learning_rate": 3.980308712734157e-05, "epoch": 0.05437824870051979, "percentage": 5.44, "elapsed_time": "1:07:21", "remaining_time": "19:31:19"}
+{"current_steps": 307, "total_steps": 5627, "loss": 1.5484, "learning_rate": 3.9801504948543896e-05, "epoch": 0.05455595539561953, "percentage": 5.46, "elapsed_time": "1:07:34", "remaining_time": "19:31:06"}
+{"current_steps": 308, "total_steps": 5627, "loss": 1.5941, "learning_rate": 3.9799916470515115e-05, "epoch": 0.05473366209071927, "percentage": 5.47, "elapsed_time": "1:07:48", "remaining_time": "19:30:52"}
+{"current_steps": 309, "total_steps": 5627, "loss": 1.5573, "learning_rate": 3.979832169376056e-05, "epoch": 0.05491136878581901, "percentage": 5.49, "elapsed_time": "1:08:01", "remaining_time": "19:30:38"}
+{"current_steps": 310, "total_steps": 5627, "loss": 1.5945, "learning_rate": 3.979672061878754e-05, "epoch": 0.055089075480918744, "percentage": 5.51, "elapsed_time": "1:08:14", "remaining_time": "19:30:27"}
+{"current_steps": 311, "total_steps": 5627, "loss": 1.5804, "learning_rate": 3.97951132461054e-05, "epoch": 0.055266782176018485, "percentage": 5.53, "elapsed_time": "1:08:27", "remaining_time": "19:30:12"}
+{"current_steps": 312, "total_steps": 5627, "loss": 1.5959, "learning_rate": 3.979349957622548e-05, "epoch": 0.05544448887111822, "percentage": 5.54, "elapsed_time": "1:08:40", "remaining_time": "19:29:58"}
+{"current_steps": 313, "total_steps": 5627, "loss": 1.5378, "learning_rate": 3.97918796096611e-05, "epoch": 0.05562219556621796, "percentage": 5.56, "elapsed_time": "1:08:53", "remaining_time": "19:29:44"}
+{"current_steps": 314, "total_steps": 5627, "loss": 1.5597, "learning_rate": 3.979025334692762e-05, "epoch": 0.055799902261317695, "percentage": 5.58, "elapsed_time": "1:09:07", "remaining_time": "19:29:31"}
+{"current_steps": 315, "total_steps": 5627, "loss": 1.5489, "learning_rate": 3.9788620788542376e-05, "epoch": 0.055977608956417436, "percentage": 5.6, "elapsed_time": "1:09:20", "remaining_time": "19:29:16"}
+{"current_steps": 316, "total_steps": 5627, "loss": 1.5704, "learning_rate": 3.978698193502472e-05, "epoch": 0.05615531565151717, "percentage": 5.62, "elapsed_time": "1:09:33", "remaining_time": "19:29:02"}
+{"current_steps": 317, "total_steps": 5627, "loss": 1.5349, "learning_rate": 3.9785336786896e-05, "epoch": 0.05633302234661691, "percentage": 5.63, "elapsed_time": "1:09:46", "remaining_time": "19:28:49"}
+{"current_steps": 318, "total_steps": 5627, "loss": 1.591, "learning_rate": 3.978368534467956e-05, "epoch": 0.05651072904171665, "percentage": 5.65, "elapsed_time": "1:09:59", "remaining_time": "19:28:36"}
+{"current_steps": 319, "total_steps": 5627, "loss": 1.5256, "learning_rate": 3.978202760890077e-05, "epoch": 0.05668843573681639, "percentage": 5.67, "elapsed_time": "1:10:13", "remaining_time": "19:28:22"}
+{"current_steps": 320, "total_steps": 5627, "loss": 1.5387, "learning_rate": 3.978036358008697e-05, "epoch": 0.05686614243191612, "percentage": 5.69, "elapsed_time": "1:10:26", "remaining_time": "19:28:08"}
+{"current_steps": 321, "total_steps": 5627, "loss": 1.5183, "learning_rate": 3.977869325876754e-05, "epoch": 0.057043849127015864, "percentage": 5.7, "elapsed_time": "1:10:39", "remaining_time": "19:27:54"}
+{"current_steps": 322, "total_steps": 5627, "loss": 1.5027, "learning_rate": 3.977701664547383e-05, "epoch": 0.0572215558221156, "percentage": 5.72, "elapsed_time": "1:10:52", "remaining_time": "19:27:39"}
+{"current_steps": 323, "total_steps": 5627, "loss": 1.5771, "learning_rate": 3.97753337407392e-05, "epoch": 0.05739926251721534, "percentage": 5.74, "elapsed_time": "1:11:05", "remaining_time": "19:27:26"}
+{"current_steps": 324, "total_steps": 5627, "loss": 1.5468, "learning_rate": 3.977364454509901e-05, "epoch": 0.057576969212315074, "percentage": 5.76, "elapsed_time": "1:11:18", "remaining_time": "19:27:12"}
+{"current_steps": 325, "total_steps": 5627, "loss": 1.5383, "learning_rate": 3.977194905909063e-05, "epoch": 0.057754675907414815, "percentage": 5.78, "elapsed_time": "1:11:32", "remaining_time": "19:26:59"}
+{"current_steps": 326, "total_steps": 5627, "loss": 1.57, "learning_rate": 3.977024728325343e-05, "epoch": 0.05793238260251455, "percentage": 5.79, "elapsed_time": "1:11:45", "remaining_time": "19:26:45"}
+{"current_steps": 327, "total_steps": 5627, "loss": 1.5211, "learning_rate": 3.9768539218128776e-05, "epoch": 0.05811008929761429, "percentage": 5.81, "elapsed_time": "1:11:58", "remaining_time": "19:26:32"}
+{"current_steps": 328, "total_steps": 5627, "loss": 1.558, "learning_rate": 3.9766824864260024e-05, "epoch": 0.058287795992714025, "percentage": 5.83, "elapsed_time": "1:12:11", "remaining_time": "19:26:18"}
+{"current_steps": 329, "total_steps": 5627, "loss": 1.5931, "learning_rate": 3.976510422219256e-05, "epoch": 0.05846550268781377, "percentage": 5.85, "elapsed_time": "1:12:24", "remaining_time": "19:26:04"}
+{"current_steps": 330, "total_steps": 5627, "loss": 1.5101, "learning_rate": 3.976337729247374e-05, "epoch": 0.0586432093829135, "percentage": 5.86, "elapsed_time": "1:12:37", "remaining_time": "19:25:50"}
+{"current_steps": 331, "total_steps": 5627, "loss": 1.5339, "learning_rate": 3.976164407565293e-05, "epoch": 0.05882091607801324, "percentage": 5.88, "elapsed_time": "1:12:51", "remaining_time": "19:25:36"}
+{"current_steps": 332, "total_steps": 5627, "loss": 1.5818, "learning_rate": 3.975990457228151e-05, "epoch": 0.05899862277311298, "percentage": 5.9, "elapsed_time": "1:13:04", "remaining_time": "19:25:21"}
+{"current_steps": 333, "total_steps": 5627, "loss": 1.5353, "learning_rate": 3.9758158782912845e-05, "epoch": 0.05917632946821272, "percentage": 5.92, "elapsed_time": "1:13:17", "remaining_time": "19:25:08"}
+{"current_steps": 334, "total_steps": 5627, "loss": 1.5514, "learning_rate": 3.97564067081023e-05, "epoch": 0.05935403616331245, "percentage": 5.94, "elapsed_time": "1:13:30", "remaining_time": "19:24:54"}
+{"current_steps": 335, "total_steps": 5627, "loss": 1.5587, "learning_rate": 3.9754648348407255e-05, "epoch": 0.059531742858412194, "percentage": 5.95, "elapsed_time": "1:13:43", "remaining_time": "19:24:41"}
+{"current_steps": 336, "total_steps": 5627, "loss": 1.528, "learning_rate": 3.975288370438706e-05, "epoch": 0.05970944955351193, "percentage": 5.97, "elapsed_time": "1:13:56", "remaining_time": "19:24:28"}
+{"current_steps": 337, "total_steps": 5627, "loss": 1.5572, "learning_rate": 3.9751112776603085e-05, "epoch": 0.05988715624861167, "percentage": 5.99, "elapsed_time": "1:14:10", "remaining_time": "19:24:14"}
+{"current_steps": 338, "total_steps": 5627, "loss": 1.5531, "learning_rate": 3.9749335565618703e-05, "epoch": 0.060064862943711404, "percentage": 6.01, "elapsed_time": "1:14:23", "remaining_time": "19:24:01"}
+{"current_steps": 339, "total_steps": 5627, "loss": 1.5036, "learning_rate": 3.974755207199927e-05, "epoch": 0.060242569638811146, "percentage": 6.02, "elapsed_time": "1:14:36", "remaining_time": "19:23:48"}
+{"current_steps": 340, "total_steps": 5627, "loss": 1.5212, "learning_rate": 3.974576229631217e-05, "epoch": 0.06042027633391088, "percentage": 6.04, "elapsed_time": "1:14:49", "remaining_time": "19:23:33"}
+{"current_steps": 341, "total_steps": 5627, "loss": 1.5936, "learning_rate": 3.974396623912672e-05, "epoch": 0.06059798302901062, "percentage": 6.06, "elapsed_time": "1:15:02", "remaining_time": "19:23:19"}
+{"current_steps": 342, "total_steps": 5627, "loss": 1.5383, "learning_rate": 3.974216390101433e-05, "epoch": 0.060775689724110356, "percentage": 6.08, "elapsed_time": "1:15:15", "remaining_time": "19:23:04"}
+{"current_steps": 343, "total_steps": 5627, "loss": 1.5525, "learning_rate": 3.974035528254833e-05, "epoch": 0.0609533964192101, "percentage": 6.1, "elapsed_time": "1:15:29", "remaining_time": "19:22:51"}
+{"current_steps": 344, "total_steps": 5627, "loss": 1.5615, "learning_rate": 3.973854038430408e-05, "epoch": 0.06113110311430983, "percentage": 6.11, "elapsed_time": "1:15:42", "remaining_time": "19:22:37"}
+{"current_steps": 345, "total_steps": 5627, "loss": 1.5911, "learning_rate": 3.973671920685893e-05, "epoch": 0.06130880980940957, "percentage": 6.13, "elapsed_time": "1:15:55", "remaining_time": "19:22:23"}
+{"current_steps": 346, "total_steps": 5627, "loss": 1.5219, "learning_rate": 3.973489175079224e-05, "epoch": 0.06148651650450931, "percentage": 6.15, "elapsed_time": "1:16:08", "remaining_time": "19:22:12"}
+{"current_steps": 347, "total_steps": 5627, "loss": 1.5655, "learning_rate": 3.973305801668535e-05, "epoch": 0.06166422319960905, "percentage": 6.17, "elapsed_time": "1:16:21", "remaining_time": "19:21:59"}
+{"current_steps": 348, "total_steps": 5627, "loss": 1.4782, "learning_rate": 3.973121800512161e-05, "epoch": 0.06184192989470878, "percentage": 6.18, "elapsed_time": "1:16:35", "remaining_time": "19:21:45"}
+{"current_steps": 349, "total_steps": 5627, "loss": 1.5489, "learning_rate": 3.9729371716686354e-05, "epoch": 0.062019636589808524, "percentage": 6.2, "elapsed_time": "1:16:48", "remaining_time": "19:21:32"}
+{"current_steps": 350, "total_steps": 5627, "loss": 1.4991, "learning_rate": 3.9727519151966934e-05, "epoch": 0.06219734328490826, "percentage": 6.22, "elapsed_time": "1:17:01", "remaining_time": "19:21:18"}
+{"current_steps": 351, "total_steps": 5627, "loss": 1.5286, "learning_rate": 3.972566031155268e-05, "epoch": 0.062375049980008, "percentage": 6.24, "elapsed_time": "1:17:14", "remaining_time": "19:21:05"}
+{"current_steps": 352, "total_steps": 5627, "loss": 1.5223, "learning_rate": 3.9723795196034914e-05, "epoch": 0.06255275667510773, "percentage": 6.26, "elapsed_time": "1:17:27", "remaining_time": "19:20:51"}
+{"current_steps": 353, "total_steps": 5627, "loss": 1.5403, "learning_rate": 3.972192380600698e-05, "epoch": 0.06273046337020748, "percentage": 6.27, "elapsed_time": "1:17:40", "remaining_time": "19:20:37"}
+{"current_steps": 354, "total_steps": 5627, "loss": 1.541, "learning_rate": 3.9720046142064195e-05, "epoch": 0.06290817006530722, "percentage": 6.29, "elapsed_time": "1:17:54", "remaining_time": "19:20:24"}
+{"current_steps": 355, "total_steps": 5627, "loss": 1.5687, "learning_rate": 3.9718162204803884e-05, "epoch": 0.06308587676040694, "percentage": 6.31, "elapsed_time": "1:18:07", "remaining_time": "19:20:10"}
+{"current_steps": 356, "total_steps": 5627, "loss": 1.526, "learning_rate": 3.9716271994825355e-05, "epoch": 0.06326358345550669, "percentage": 6.33, "elapsed_time": "1:18:20", "remaining_time": "19:19:57"}
+{"current_steps": 357, "total_steps": 5627, "loss": 1.536, "learning_rate": 3.971437551272992e-05, "epoch": 0.06344129015060643, "percentage": 6.34, "elapsed_time": "1:18:33", "remaining_time": "19:19:43"}
+{"current_steps": 358, "total_steps": 5627, "loss": 1.533, "learning_rate": 3.9712472759120895e-05, "epoch": 0.06361899684570617, "percentage": 6.36, "elapsed_time": "1:18:46", "remaining_time": "19:19:30"}
+{"current_steps": 359, "total_steps": 5627, "loss": 1.526, "learning_rate": 3.971056373460357e-05, "epoch": 0.0637967035408059, "percentage": 6.38, "elapsed_time": "1:19:00", "remaining_time": "19:19:17"}
+{"current_steps": 360, "total_steps": 5627, "loss": 1.4867, "learning_rate": 3.970864843978525e-05, "epoch": 0.06397441023590564, "percentage": 6.4, "elapsed_time": "1:19:13", "remaining_time": "19:19:04"}
+{"current_steps": 361, "total_steps": 5627, "loss": 1.5622, "learning_rate": 3.970672687527523e-05, "epoch": 0.06415211693100538, "percentage": 6.42, "elapsed_time": "1:19:26", "remaining_time": "19:18:51"}
+{"current_steps": 362, "total_steps": 5627, "loss": 1.522, "learning_rate": 3.9704799041684785e-05, "epoch": 0.06432982362610512, "percentage": 6.43, "elapsed_time": "1:19:39", "remaining_time": "19:18:37"}
+{"current_steps": 363, "total_steps": 5627, "loss": 1.4895, "learning_rate": 3.97028649396272e-05, "epoch": 0.06450753032120485, "percentage": 6.45, "elapsed_time": "1:19:52", "remaining_time": "19:18:22"}
+{"current_steps": 364, "total_steps": 5627, "loss": 1.5579, "learning_rate": 3.9700924569717745e-05, "epoch": 0.06468523701630459, "percentage": 6.47, "elapsed_time": "1:20:05", "remaining_time": "19:18:07"}
+{"current_steps": 365, "total_steps": 5627, "loss": 1.5034, "learning_rate": 3.969897793257369e-05, "epoch": 0.06486294371140433, "percentage": 6.49, "elapsed_time": "1:20:19", "remaining_time": "19:17:52"}
+{"current_steps": 366, "total_steps": 5627, "loss": 1.5278, "learning_rate": 3.96970250288143e-05, "epoch": 0.06504065040650407, "percentage": 6.5, "elapsed_time": "1:20:32", "remaining_time": "19:17:39"}
+{"current_steps": 367, "total_steps": 5627, "loss": 1.4571, "learning_rate": 3.969506585906083e-05, "epoch": 0.0652183571016038, "percentage": 6.52, "elapsed_time": "1:20:45", "remaining_time": "19:17:26"}
+{"current_steps": 368, "total_steps": 5627, "loss": 1.5244, "learning_rate": 3.9693100423936535e-05, "epoch": 0.06539606379670354, "percentage": 6.54, "elapsed_time": "1:20:58", "remaining_time": "19:17:13"}
+{"current_steps": 369, "total_steps": 5627, "loss": 1.5019, "learning_rate": 3.969112872406664e-05, "epoch": 0.06557377049180328, "percentage": 6.56, "elapsed_time": "1:21:11", "remaining_time": "19:17:00"}
+{"current_steps": 370, "total_steps": 5627, "loss": 1.4871, "learning_rate": 3.96891507600784e-05, "epoch": 0.06575147718690302, "percentage": 6.58, "elapsed_time": "1:21:25", "remaining_time": "19:16:47"}
+{"current_steps": 371, "total_steps": 5627, "loss": 1.4944, "learning_rate": 3.968716653260102e-05, "epoch": 0.06592918388200275, "percentage": 6.59, "elapsed_time": "1:21:38", "remaining_time": "19:16:34"}
+{"current_steps": 372, "total_steps": 5627, "loss": 1.5258, "learning_rate": 3.9685176042265736e-05, "epoch": 0.06610689057710249, "percentage": 6.61, "elapsed_time": "1:21:51", "remaining_time": "19:16:21"}
+{"current_steps": 373, "total_steps": 5627, "loss": 1.5625, "learning_rate": 3.968317928970576e-05, "epoch": 0.06628459727220223, "percentage": 6.63, "elapsed_time": "1:22:04", "remaining_time": "19:16:07"}
+{"current_steps": 374, "total_steps": 5627, "loss": 1.5442, "learning_rate": 3.9681176275556294e-05, "epoch": 0.06646230396730197, "percentage": 6.65, "elapsed_time": "1:22:17", "remaining_time": "19:15:54"}
+{"current_steps": 375, "total_steps": 5627, "loss": 1.5668, "learning_rate": 3.9679167000454526e-05, "epoch": 0.0666400106624017, "percentage": 6.66, "elapsed_time": "1:22:30", "remaining_time": "19:15:38"}
+{"current_steps": 376, "total_steps": 5627, "loss": 1.4702, "learning_rate": 3.967715146503966e-05, "epoch": 0.06681771735750144, "percentage": 6.68, "elapsed_time": "1:22:44", "remaining_time": "19:15:25"}
+{"current_steps": 377, "total_steps": 5627, "loss": 1.5214, "learning_rate": 3.9675129669952864e-05, "epoch": 0.06699542405260119, "percentage": 6.7, "elapsed_time": "1:22:57", "remaining_time": "19:15:11"}
+{"current_steps": 378, "total_steps": 5627, "loss": 1.4872, "learning_rate": 3.967310161583732e-05, "epoch": 0.06717313074770093, "percentage": 6.72, "elapsed_time": "1:23:10", "remaining_time": "19:14:58"}
+{"current_steps": 379, "total_steps": 5627, "loss": 1.596, "learning_rate": 3.967106730333817e-05, "epoch": 0.06735083744280065, "percentage": 6.74, "elapsed_time": "1:23:23", "remaining_time": "19:14:44"}
+{"current_steps": 380, "total_steps": 5627, "loss": 1.5466, "learning_rate": 3.9669026733102584e-05, "epoch": 0.0675285441379004, "percentage": 6.75, "elapsed_time": "1:23:36", "remaining_time": "19:14:31"}
+{"current_steps": 381, "total_steps": 5627, "loss": 1.5579, "learning_rate": 3.9666979905779704e-05, "epoch": 0.06770625083300014, "percentage": 6.77, "elapsed_time": "1:23:50", "remaining_time": "19:14:18"}
+{"current_steps": 382, "total_steps": 5627, "loss": 1.5622, "learning_rate": 3.9664926822020665e-05, "epoch": 0.06788395752809988, "percentage": 6.79, "elapsed_time": "1:24:03", "remaining_time": "19:14:04"}
+{"current_steps": 383, "total_steps": 5627, "loss": 1.5221, "learning_rate": 3.966286748247858e-05, "epoch": 0.0680616642231996, "percentage": 6.81, "elapsed_time": "1:24:16", "remaining_time": "19:13:51"}
+{"current_steps": 384, "total_steps": 5627, "loss": 1.5329, "learning_rate": 3.966080188780858e-05, "epoch": 0.06823937091829935, "percentage": 6.82, "elapsed_time": "1:24:29", "remaining_time": "19:13:37"}
+{"current_steps": 385, "total_steps": 5627, "loss": 1.5542, "learning_rate": 3.965873003866776e-05, "epoch": 0.06841707761339909, "percentage": 6.84, "elapsed_time": "1:24:42", "remaining_time": "19:13:22"}
+{"current_steps": 386, "total_steps": 5627, "loss": 1.5076, "learning_rate": 3.965665193571521e-05, "epoch": 0.06859478430849883, "percentage": 6.86, "elapsed_time": "1:24:55", "remaining_time": "19:13:07"}
+{"current_steps": 387, "total_steps": 5627, "loss": 1.5126, "learning_rate": 3.965456757961202e-05, "epoch": 0.06877249100359856, "percentage": 6.88, "elapsed_time": "1:25:08", "remaining_time": "19:12:52"}
+{"current_steps": 388, "total_steps": 5627, "loss": 1.5552, "learning_rate": 3.9652476971021265e-05, "epoch": 0.0689501976986983, "percentage": 6.9, "elapsed_time": "1:25:21", "remaining_time": "19:12:40"}
+{"current_steps": 389, "total_steps": 5627, "loss": 1.5294, "learning_rate": 3.9650380110608e-05, "epoch": 0.06912790439379804, "percentage": 6.91, "elapsed_time": "1:25:35", "remaining_time": "19:12:26"}
+{"current_steps": 390, "total_steps": 5627, "loss": 1.5204, "learning_rate": 3.964827699903929e-05, "epoch": 0.06930561108889778, "percentage": 6.93, "elapsed_time": "1:25:48", "remaining_time": "19:12:13"}
+{"current_steps": 391, "total_steps": 5627, "loss": 1.4811, "learning_rate": 3.964616763698416e-05, "epoch": 0.06948331778399751, "percentage": 6.95, "elapsed_time": "1:26:01", "remaining_time": "19:12:00"}
+{"current_steps": 392, "total_steps": 5627, "loss": 1.5076, "learning_rate": 3.964405202511364e-05, "epoch": 0.06966102447909725, "percentage": 6.97, "elapsed_time": "1:26:14", "remaining_time": "19:11:47"}
+{"current_steps": 393, "total_steps": 5627, "loss": 1.5143, "learning_rate": 3.964193016410074e-05, "epoch": 0.06983873117419699, "percentage": 6.98, "elapsed_time": "1:26:28", "remaining_time": "19:11:34"}
+{"current_steps": 394, "total_steps": 5627, "loss": 1.5531, "learning_rate": 3.9639802054620484e-05, "epoch": 0.07001643786929673, "percentage": 7.0, "elapsed_time": "1:26:41", "remaining_time": "19:11:21"}
+{"current_steps": 395, "total_steps": 5627, "loss": 1.5204, "learning_rate": 3.963766769734985e-05, "epoch": 0.07019414456439646, "percentage": 7.02, "elapsed_time": "1:26:54", "remaining_time": "19:11:08"}
+{"current_steps": 396, "total_steps": 5627, "loss": 1.4993, "learning_rate": 3.963552709296781e-05, "epoch": 0.0703718512594962, "percentage": 7.04, "elapsed_time": "1:27:07", "remaining_time": "19:10:54"}
+{"current_steps": 397, "total_steps": 5627, "loss": 1.569, "learning_rate": 3.9633380242155353e-05, "epoch": 0.07054955795459594, "percentage": 7.06, "elapsed_time": "1:27:20", "remaining_time": "19:10:41"}
+{"current_steps": 398, "total_steps": 5627, "loss": 1.537, "learning_rate": 3.9631227145595404e-05, "epoch": 0.07072726464969568, "percentage": 7.07, "elapsed_time": "1:27:34", "remaining_time": "19:10:28"}
+{"current_steps": 399, "total_steps": 5627, "loss": 1.5402, "learning_rate": 3.962906780397292e-05, "epoch": 0.07090497134479541, "percentage": 7.09, "elapsed_time": "1:27:47", "remaining_time": "19:10:14"}
+{"current_steps": 400, "total_steps": 5627, "loss": 1.5655, "learning_rate": 3.962690221797484e-05, "epoch": 0.07108267803989515, "percentage": 7.11, "elapsed_time": "1:28:00", "remaining_time": "19:10:01"}
+{"current_steps": 401, "total_steps": 5627, "loss": 1.4918, "learning_rate": 3.962473038829005e-05, "epoch": 0.0712603847349949, "percentage": 7.13, "elapsed_time": "1:28:30", "remaining_time": "19:13:33"}
+{"current_steps": 402, "total_steps": 5627, "loss": 1.5348, "learning_rate": 3.962255231560947e-05, "epoch": 0.07143809143009464, "percentage": 7.14, "elapsed_time": "1:28:44", "remaining_time": "19:13:20"}
+{"current_steps": 403, "total_steps": 5627, "loss": 1.5993, "learning_rate": 3.9620368000625974e-05, "epoch": 0.07161579812519436, "percentage": 7.16, "elapsed_time": "1:28:57", "remaining_time": "19:13:06"}
+{"current_steps": 404, "total_steps": 5627, "loss": 1.5322, "learning_rate": 3.961817744403445e-05, "epoch": 0.0717935048202941, "percentage": 7.18, "elapsed_time": "1:29:10", "remaining_time": "19:12:53"}
+{"current_steps": 405, "total_steps": 5627, "loss": 1.5153, "learning_rate": 3.961598064653173e-05, "epoch": 0.07197121151539385, "percentage": 7.2, "elapsed_time": "1:29:23", "remaining_time": "19:12:40"}
+{"current_steps": 406, "total_steps": 5627, "loss": 1.5721, "learning_rate": 3.961377760881668e-05, "epoch": 0.07214891821049359, "percentage": 7.22, "elapsed_time": "1:29:37", "remaining_time": "19:12:26"}
+{"current_steps": 407, "total_steps": 5627, "loss": 1.5679, "learning_rate": 3.961156833159012e-05, "epoch": 0.07232662490559331, "percentage": 7.23, "elapsed_time": "1:29:50", "remaining_time": "19:12:13"}
+{"current_steps": 408, "total_steps": 5627, "loss": 1.5461, "learning_rate": 3.960935281555486e-05, "epoch": 0.07250433160069306, "percentage": 7.25, "elapsed_time": "1:30:03", "remaining_time": "19:12:00"}
+{"current_steps": 409, "total_steps": 5627, "loss": 1.5101, "learning_rate": 3.96071310614157e-05, "epoch": 0.0726820382957928, "percentage": 7.27, "elapsed_time": "1:30:16", "remaining_time": "19:11:46"}
+{"current_steps": 410, "total_steps": 5627, "loss": 1.5331, "learning_rate": 3.9604903069879424e-05, "epoch": 0.07285974499089254, "percentage": 7.29, "elapsed_time": "1:30:29", "remaining_time": "19:11:33"}
+{"current_steps": 411, "total_steps": 5627, "loss": 1.5576, "learning_rate": 3.960266884165479e-05, "epoch": 0.07303745168599227, "percentage": 7.3, "elapsed_time": "1:30:43", "remaining_time": "19:11:19"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca02f65f590ff50dda2722c414fa61fd63c47fdd56ae19ad8d1de742544ee3a1
+size 7096