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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829561e835609d8be8cc428e09d4b6a700acb81e3d184e42cc4713b4b859992a
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad47f5da5f6e6e655c3deb7d1ca7a27c69ef655bdc5b6d5d17504a7ad681712
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d6a78d38bb3df584d75c4f7041cfdd180ac9d4438a2abb74757f0eb7e5ea2e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b5fdf06f6d34d45c46c02707e4d3636b361e65b70665ebfd7e5f418c8d372a
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,409 @@
+{"current_steps": 1, "total_steps": 1095, "loss": 1.3675, "lr": 0.0, "epoch": 0.0027347310847766638, "percentage": 0.09, "elapsed_time": "0:00:17", "remaining_time": "5:21:15"}
+{"current_steps": 2, "total_steps": 1095, "loss": 1.4718, "lr": 9.090909090909091e-08, "epoch": 0.0054694621695533276, "percentage": 0.18, "elapsed_time": "0:00:25", "remaining_time": "3:51:43"}
+{"current_steps": 3, "total_steps": 1095, "loss": 1.3661, "lr": 1.8181818181818183e-07, "epoch": 0.008204193254329991, "percentage": 0.27, "elapsed_time": "0:00:34", "remaining_time": "3:29:29"}
+{"current_steps": 4, "total_steps": 1095, "loss": 1.3345, "lr": 2.7272727272727274e-07, "epoch": 0.010938924339106655, "percentage": 0.37, "elapsed_time": "0:00:49", "remaining_time": "3:45:58"}
+{"current_steps": 5, "total_steps": 1095, "loss": 1.4462, "lr": 3.6363636363636366e-07, "epoch": 0.013673655423883319, "percentage": 0.46, "elapsed_time": "0:01:02", "remaining_time": "3:45:54"}
+{"current_steps": 6, "total_steps": 1095, "loss": 1.3867, "lr": 4.5454545454545457e-07, "epoch": 0.016408386508659983, "percentage": 0.55, "elapsed_time": "0:01:12", "remaining_time": "3:39:07"}
+{"current_steps": 7, "total_steps": 1095, "loss": 1.3108, "lr": 5.454545454545455e-07, "epoch": 0.019143117593436645, "percentage": 0.64, "elapsed_time": "0:01:25", "remaining_time": "3:40:18"}
+{"current_steps": 8, "total_steps": 1095, "loss": 1.3623, "lr": 6.363636363636364e-07, "epoch": 0.02187784867821331, "percentage": 0.73, "elapsed_time": "0:01:35", "remaining_time": "3:36:16"}
+{"current_steps": 9, "total_steps": 1095, "loss": 1.3801, "lr": 7.272727272727273e-07, "epoch": 0.024612579762989972, "percentage": 0.82, "elapsed_time": "0:01:46", "remaining_time": "3:34:01"}
+{"current_steps": 10, "total_steps": 1095, "loss": 1.2531, "lr": 8.181818181818182e-07, "epoch": 0.027347310847766638, "percentage": 0.91, "elapsed_time": "0:02:00", "remaining_time": "3:38:37"}
+{"current_steps": 11, "total_steps": 1095, "loss": 1.3977, "lr": 9.090909090909091e-07, "epoch": 0.0300820419325433, "percentage": 1.0, "elapsed_time": "0:02:21", "remaining_time": "3:51:50"}
+{"current_steps": 12, "total_steps": 1095, "loss": 1.2259, "lr": 1.0000000000000002e-06, "epoch": 0.032816773017319965, "percentage": 1.1, "elapsed_time": "0:02:32", "remaining_time": "3:49:57"}
+{"current_steps": 13, "total_steps": 1095, "loss": 1.3087, "lr": 1.090909090909091e-06, "epoch": 0.03555150410209663, "percentage": 1.19, "elapsed_time": "0:02:42", "remaining_time": "3:46:05"}
+{"current_steps": 14, "total_steps": 1095, "loss": 1.2497, "lr": 1.181818181818182e-06, "epoch": 0.03828623518687329, "percentage": 1.28, "elapsed_time": "0:02:54", "remaining_time": "3:44:34"}
+{"current_steps": 15, "total_steps": 1095, "loss": 1.2414, "lr": 1.2727272727272728e-06, "epoch": 0.04102096627164995, "percentage": 1.37, "elapsed_time": "0:03:03", "remaining_time": "3:40:26"}
+{"current_steps": 16, "total_steps": 1095, "loss": 1.3036, "lr": 1.3636363636363636e-06, "epoch": 0.04375569735642662, "percentage": 1.46, "elapsed_time": "0:03:15", "remaining_time": "3:39:41"}
+{"current_steps": 17, "total_steps": 1095, "loss": 1.185, "lr": 1.4545454545454546e-06, "epoch": 0.04649042844120328, "percentage": 1.55, "elapsed_time": "0:03:26", "remaining_time": "3:38:12"}
+{"current_steps": 18, "total_steps": 1095, "loss": 1.2571, "lr": 1.5454545454545454e-06, "epoch": 0.049225159525979945, "percentage": 1.64, "elapsed_time": "0:03:37", "remaining_time": "3:37:01"}
+{"current_steps": 19, "total_steps": 1095, "loss": 1.1922, "lr": 1.6363636363636365e-06, "epoch": 0.05195989061075661, "percentage": 1.74, "elapsed_time": "0:03:47", "remaining_time": "3:34:50"}
+{"current_steps": 20, "total_steps": 1095, "loss": 1.1992, "lr": 1.7272727272727275e-06, "epoch": 0.054694621695533276, "percentage": 1.83, "elapsed_time": "0:04:04", "remaining_time": "3:39:15"}
+{"current_steps": 21, "total_steps": 1095, "loss": 1.1687, "lr": 1.8181818181818183e-06, "epoch": 0.05742935278030994, "percentage": 1.92, "elapsed_time": "0:04:18", "remaining_time": "3:40:20"}
+{"current_steps": 22, "total_steps": 1095, "loss": 1.0779, "lr": 1.9090909090909095e-06, "epoch": 0.0601640838650866, "percentage": 2.01, "elapsed_time": "0:04:28", "remaining_time": "3:38:19"}
+{"current_steps": 23, "total_steps": 1095, "loss": 1.1448, "lr": 2.0000000000000003e-06, "epoch": 0.06289881494986327, "percentage": 2.1, "elapsed_time": "0:04:38", "remaining_time": "3:36:19"}
+{"current_steps": 24, "total_steps": 1095, "loss": 1.0443, "lr": 2.090909090909091e-06, "epoch": 0.06563354603463993, "percentage": 2.19, "elapsed_time": "0:04:47", "remaining_time": "3:33:30"}
+{"current_steps": 25, "total_steps": 1095, "loss": 1.0431, "lr": 2.181818181818182e-06, "epoch": 0.06836827711941659, "percentage": 2.28, "elapsed_time": "0:05:02", "remaining_time": "3:36:04"}
+{"current_steps": 26, "total_steps": 1095, "loss": 1.1011, "lr": 2.2727272727272728e-06, "epoch": 0.07110300820419325, "percentage": 2.37, "elapsed_time": "0:05:16", "remaining_time": "3:36:41"}
+{"current_steps": 27, "total_steps": 1095, "loss": 1.1368, "lr": 2.363636363636364e-06, "epoch": 0.07383773928896992, "percentage": 2.47, "elapsed_time": "0:05:25", "remaining_time": "3:34:44"}
+{"current_steps": 28, "total_steps": 1095, "loss": 1.0321, "lr": 2.454545454545455e-06, "epoch": 0.07657247037374658, "percentage": 2.56, "elapsed_time": "0:05:35", "remaining_time": "3:32:59"}
+{"current_steps": 29, "total_steps": 1095, "loss": 1.0381, "lr": 2.5454545454545456e-06, "epoch": 0.07930720145852324, "percentage": 2.65, "elapsed_time": "0:05:51", "remaining_time": "3:35:26"}
+{"current_steps": 30, "total_steps": 1095, "loss": 0.9819, "lr": 2.6363636363636364e-06, "epoch": 0.0820419325432999, "percentage": 2.74, "elapsed_time": "0:06:08", "remaining_time": "3:37:45"}
+{"current_steps": 31, "total_steps": 1095, "loss": 0.98, "lr": 2.7272727272727272e-06, "epoch": 0.08477666362807658, "percentage": 2.83, "elapsed_time": "0:06:18", "remaining_time": "3:36:43"}
+{"current_steps": 32, "total_steps": 1095, "loss": 0.9626, "lr": 2.818181818181818e-06, "epoch": 0.08751139471285324, "percentage": 2.92, "elapsed_time": "0:06:28", "remaining_time": "3:34:57"}
+{"current_steps": 33, "total_steps": 1095, "loss": 0.9602, "lr": 2.9090909090909093e-06, "epoch": 0.0902461257976299, "percentage": 3.01, "elapsed_time": "0:06:42", "remaining_time": "3:35:55"}
+{"current_steps": 34, "total_steps": 1095, "loss": 1.0666, "lr": 3e-06, "epoch": 0.09298085688240657, "percentage": 3.11, "elapsed_time": "0:06:54", "remaining_time": "3:35:35"}
+{"current_steps": 35, "total_steps": 1095, "loss": 0.9724, "lr": 3.090909090909091e-06, "epoch": 0.09571558796718323, "percentage": 3.2, "elapsed_time": "0:07:10", "remaining_time": "3:37:28"}
+{"current_steps": 36, "total_steps": 1095, "loss": 0.9949, "lr": 3.181818181818182e-06, "epoch": 0.09845031905195989, "percentage": 3.29, "elapsed_time": "0:07:28", "remaining_time": "3:40:03"}
+{"current_steps": 37, "total_steps": 1095, "loss": 1.1051, "lr": 3.272727272727273e-06, "epoch": 0.10118505013673655, "percentage": 3.38, "elapsed_time": "0:07:40", "remaining_time": "3:39:13"}
+{"current_steps": 38, "total_steps": 1095, "loss": 0.9979, "lr": 3.3636363636363637e-06, "epoch": 0.10391978122151321, "percentage": 3.47, "elapsed_time": "0:07:51", "remaining_time": "3:38:37"}
+{"current_steps": 39, "total_steps": 1095, "loss": 0.9482, "lr": 3.454545454545455e-06, "epoch": 0.10665451230628988, "percentage": 3.56, "elapsed_time": "0:08:01", "remaining_time": "3:37:07"}
+{"current_steps": 40, "total_steps": 1095, "loss": 0.9657, "lr": 3.5454545454545458e-06, "epoch": 0.10938924339106655, "percentage": 3.65, "elapsed_time": "0:08:13", "remaining_time": "3:36:46"}
+{"current_steps": 41, "total_steps": 1095, "loss": 0.8906, "lr": 3.6363636363636366e-06, "epoch": 0.11212397447584321, "percentage": 3.74, "elapsed_time": "0:08:22", "remaining_time": "3:35:16"}
+{"current_steps": 42, "total_steps": 1095, "loss": 0.9947, "lr": 3.727272727272728e-06, "epoch": 0.11485870556061988, "percentage": 3.84, "elapsed_time": "0:08:36", "remaining_time": "3:35:57"}
+{"current_steps": 43, "total_steps": 1095, "loss": 0.9854, "lr": 3.818181818181819e-06, "epoch": 0.11759343664539654, "percentage": 3.93, "elapsed_time": "0:08:50", "remaining_time": "3:36:10"}
+{"current_steps": 44, "total_steps": 1095, "loss": 0.934, "lr": 3.90909090909091e-06, "epoch": 0.1203281677301732, "percentage": 4.02, "elapsed_time": "0:09:04", "remaining_time": "3:36:44"}
+{"current_steps": 45, "total_steps": 1095, "loss": 0.9748, "lr": 4.000000000000001e-06, "epoch": 0.12306289881494986, "percentage": 4.11, "elapsed_time": "0:09:20", "remaining_time": "3:38:06"}
+{"current_steps": 46, "total_steps": 1095, "loss": 0.9704, "lr": 4.0909090909090915e-06, "epoch": 0.12579762989972654, "percentage": 4.2, "elapsed_time": "0:09:39", "remaining_time": "3:40:19"}
+{"current_steps": 47, "total_steps": 1095, "loss": 0.9109, "lr": 4.181818181818182e-06, "epoch": 0.12853236098450319, "percentage": 4.29, "elapsed_time": "0:09:56", "remaining_time": "3:41:40"}
+{"current_steps": 48, "total_steps": 1095, "loss": 0.9387, "lr": 4.272727272727273e-06, "epoch": 0.13126709206927986, "percentage": 4.38, "elapsed_time": "0:10:09", "remaining_time": "3:41:43"}
+{"current_steps": 49, "total_steps": 1095, "loss": 0.8944, "lr": 4.363636363636364e-06, "epoch": 0.1340018231540565, "percentage": 4.47, "elapsed_time": "0:10:21", "remaining_time": "3:41:05"}
+{"current_steps": 50, "total_steps": 1095, "loss": 0.8653, "lr": 4.454545454545455e-06, "epoch": 0.13673655423883319, "percentage": 4.57, "elapsed_time": "0:10:28", "remaining_time": "3:39:03"}
+{"current_steps": 51, "total_steps": 1095, "loss": 1.0568, "lr": 4.5454545454545455e-06, "epoch": 0.13947128532360983, "percentage": 4.66, "elapsed_time": "0:10:41", "remaining_time": "3:38:51"}
+{"current_steps": 52, "total_steps": 1095, "loss": 1.0059, "lr": 4.636363636363636e-06, "epoch": 0.1422060164083865, "percentage": 4.75, "elapsed_time": "0:10:57", "remaining_time": "3:39:46"}
+{"current_steps": 53, "total_steps": 1095, "loss": 0.8361, "lr": 4.727272727272728e-06, "epoch": 0.14494074749316319, "percentage": 4.84, "elapsed_time": "0:11:12", "remaining_time": "3:40:27"}
+{"current_steps": 54, "total_steps": 1095, "loss": 0.8738, "lr": 4.818181818181819e-06, "epoch": 0.14767547857793983, "percentage": 4.93, "elapsed_time": "0:11:23", "remaining_time": "3:39:31"}
+{"current_steps": 55, "total_steps": 1095, "loss": 0.8752, "lr": 4.90909090909091e-06, "epoch": 0.1504102096627165, "percentage": 5.02, "elapsed_time": "0:11:35", "remaining_time": "3:39:08"}
+{"current_steps": 56, "total_steps": 1095, "loss": 0.8648, "lr": 5e-06, "epoch": 0.15314494074749316, "percentage": 5.11, "elapsed_time": "0:11:46", "remaining_time": "3:38:22"}
+{"current_steps": 57, "total_steps": 1095, "loss": 0.9783, "lr": 5.090909090909091e-06, "epoch": 0.15587967183226983, "percentage": 5.21, "elapsed_time": "0:11:59", "remaining_time": "3:38:27"}
+{"current_steps": 58, "total_steps": 1095, "loss": 0.8675, "lr": 5.181818181818182e-06, "epoch": 0.15861440291704648, "percentage": 5.3, "elapsed_time": "0:12:10", "remaining_time": "3:37:46"}
+{"current_steps": 59, "total_steps": 1095, "loss": 0.8897, "lr": 5.272727272727273e-06, "epoch": 0.16134913400182316, "percentage": 5.39, "elapsed_time": "0:12:21", "remaining_time": "3:37:01"}
+{"current_steps": 60, "total_steps": 1095, "loss": 0.8405, "lr": 5.3636363636363645e-06, "epoch": 0.1640838650865998, "percentage": 5.48, "elapsed_time": "0:12:42", "remaining_time": "3:39:08"}
+{"current_steps": 61, "total_steps": 1095, "loss": 1.0835, "lr": 5.4545454545454545e-06, "epoch": 0.16681859617137648, "percentage": 5.57, "elapsed_time": "0:12:52", "remaining_time": "3:38:16"}
+{"current_steps": 62, "total_steps": 1095, "loss": 0.8071, "lr": 5.545454545454546e-06, "epoch": 0.16955332725615316, "percentage": 5.66, "elapsed_time": "0:13:07", "remaining_time": "3:38:35"}
+{"current_steps": 63, "total_steps": 1095, "loss": 0.8558, "lr": 5.636363636363636e-06, "epoch": 0.1722880583409298, "percentage": 5.75, "elapsed_time": "0:13:15", "remaining_time": "3:37:08"}
+{"current_steps": 64, "total_steps": 1095, "loss": 0.9757, "lr": 5.727272727272728e-06, "epoch": 0.17502278942570648, "percentage": 5.84, "elapsed_time": "0:13:25", "remaining_time": "3:36:13"}
+{"current_steps": 65, "total_steps": 1095, "loss": 0.9237, "lr": 5.8181818181818185e-06, "epoch": 0.17775752051048313, "percentage": 5.94, "elapsed_time": "0:13:41", "remaining_time": "3:36:55"}
+{"current_steps": 66, "total_steps": 1095, "loss": 0.8845, "lr": 5.90909090909091e-06, "epoch": 0.1804922515952598, "percentage": 6.03, "elapsed_time": "0:13:53", "remaining_time": "3:36:30"}
+{"current_steps": 67, "total_steps": 1095, "loss": 0.9454, "lr": 6e-06, "epoch": 0.18322698268003645, "percentage": 6.12, "elapsed_time": "0:14:09", "remaining_time": "3:37:10"}
+{"current_steps": 68, "total_steps": 1095, "loss": 0.7864, "lr": 6.090909090909092e-06, "epoch": 0.18596171376481313, "percentage": 6.21, "elapsed_time": "0:14:20", "remaining_time": "3:36:29"}
+{"current_steps": 69, "total_steps": 1095, "loss": 0.9588, "lr": 6.181818181818182e-06, "epoch": 0.18869644484958978, "percentage": 6.3, "elapsed_time": "0:14:34", "remaining_time": "3:36:47"}
+{"current_steps": 70, "total_steps": 1095, "loss": 0.7636, "lr": 6.2727272727272734e-06, "epoch": 0.19143117593436645, "percentage": 6.39, "elapsed_time": "0:14:45", "remaining_time": "3:36:07"}
+{"current_steps": 71, "total_steps": 1095, "loss": 0.9053, "lr": 6.363636363636364e-06, "epoch": 0.19416590701914313, "percentage": 6.48, "elapsed_time": "0:14:57", "remaining_time": "3:35:48"}
+{"current_steps": 72, "total_steps": 1095, "loss": 0.9264, "lr": 6.454545454545456e-06, "epoch": 0.19690063810391978, "percentage": 6.58, "elapsed_time": "0:15:10", "remaining_time": "3:35:39"}
+{"current_steps": 73, "total_steps": 1095, "loss": 0.8527, "lr": 6.545454545454546e-06, "epoch": 0.19963536918869645, "percentage": 6.67, "elapsed_time": "0:15:24", "remaining_time": "3:35:43"}
+{"current_steps": 74, "total_steps": 1095, "loss": 0.8775, "lr": 6.6363636363636375e-06, "epoch": 0.2023701002734731, "percentage": 6.76, "elapsed_time": "0:15:36", "remaining_time": "3:35:23"}
+{"current_steps": 75, "total_steps": 1095, "loss": 0.8185, "lr": 6.7272727272727275e-06, "epoch": 0.20510483135824978, "percentage": 6.85, "elapsed_time": "0:15:52", "remaining_time": "3:35:51"}
+{"current_steps": 76, "total_steps": 1095, "loss": 0.8478, "lr": 6.818181818181818e-06, "epoch": 0.20783956244302643, "percentage": 6.94, "elapsed_time": "0:16:05", "remaining_time": "3:35:48"}
+{"current_steps": 77, "total_steps": 1095, "loss": 0.9981, "lr": 6.90909090909091e-06, "epoch": 0.2105742935278031, "percentage": 7.03, "elapsed_time": "0:16:20", "remaining_time": "3:35:59"}
+{"current_steps": 78, "total_steps": 1095, "loss": 0.9448, "lr": 7e-06, "epoch": 0.21330902461257975, "percentage": 7.12, "elapsed_time": "0:16:34", "remaining_time": "3:36:05"}
+{"current_steps": 79, "total_steps": 1095, "loss": 0.832, "lr": 7.0909090909090916e-06, "epoch": 0.21604375569735643, "percentage": 7.21, "elapsed_time": "0:16:45", "remaining_time": "3:35:30"}
+{"current_steps": 80, "total_steps": 1095, "loss": 0.8056, "lr": 7.181818181818182e-06, "epoch": 0.2187784867821331, "percentage": 7.31, "elapsed_time": "0:16:55", "remaining_time": "3:34:38"}
+{"current_steps": 81, "total_steps": 1095, "loss": 0.8763, "lr": 7.272727272727273e-06, "epoch": 0.22151321786690975, "percentage": 7.4, "elapsed_time": "0:17:08", "remaining_time": "3:34:30"}
+{"current_steps": 82, "total_steps": 1095, "loss": 0.9644, "lr": 7.363636363636364e-06, "epoch": 0.22424794895168643, "percentage": 7.49, "elapsed_time": "0:17:19", "remaining_time": "3:33:55"}
+{"current_steps": 83, "total_steps": 1095, "loss": 0.7797, "lr": 7.454545454545456e-06, "epoch": 0.22698268003646307, "percentage": 7.58, "elapsed_time": "0:17:28", "remaining_time": "3:32:58"}
+{"current_steps": 84, "total_steps": 1095, "loss": 0.8574, "lr": 7.545454545454546e-06, "epoch": 0.22971741112123975, "percentage": 7.67, "elapsed_time": "0:17:41", "remaining_time": "3:32:57"}
+{"current_steps": 85, "total_steps": 1095, "loss": 0.8595, "lr": 7.636363636363638e-06, "epoch": 0.2324521422060164, "percentage": 7.76, "elapsed_time": "0:17:51", "remaining_time": "3:32:08"}
+{"current_steps": 86, "total_steps": 1095, "loss": 0.82, "lr": 7.727272727272727e-06, "epoch": 0.23518687329079307, "percentage": 7.85, "elapsed_time": "0:18:00", "remaining_time": "3:31:18"}
+{"current_steps": 87, "total_steps": 1095, "loss": 0.7881, "lr": 7.81818181818182e-06, "epoch": 0.23792160437556972, "percentage": 7.95, "elapsed_time": "0:18:13", "remaining_time": "3:31:04"}
+{"current_steps": 88, "total_steps": 1095, "loss": 0.7848, "lr": 7.909090909090909e-06, "epoch": 0.2406563354603464, "percentage": 8.04, "elapsed_time": "0:18:21", "remaining_time": "3:30:07"}
+{"current_steps": 89, "total_steps": 1095, "loss": 0.8513, "lr": 8.000000000000001e-06, "epoch": 0.24339106654512307, "percentage": 8.13, "elapsed_time": "0:18:32", "remaining_time": "3:29:36"}
+{"current_steps": 90, "total_steps": 1095, "loss": 0.7856, "lr": 8.090909090909092e-06, "epoch": 0.24612579762989972, "percentage": 8.22, "elapsed_time": "0:18:41", "remaining_time": "3:28:45"}
+{"current_steps": 91, "total_steps": 1095, "loss": 0.8021, "lr": 8.181818181818183e-06, "epoch": 0.2488605287146764, "percentage": 8.31, "elapsed_time": "0:18:54", "remaining_time": "3:28:35"}
+{"current_steps": 92, "total_steps": 1095, "loss": 0.7866, "lr": 8.272727272727274e-06, "epoch": 0.2515952597994531, "percentage": 8.4, "elapsed_time": "0:19:05", "remaining_time": "3:28:09"}
+{"current_steps": 93, "total_steps": 1095, "loss": 0.8169, "lr": 8.363636363636365e-06, "epoch": 0.2543299908842297, "percentage": 8.49, "elapsed_time": "0:19:18", "remaining_time": "3:27:57"}
+{"current_steps": 94, "total_steps": 1095, "loss": 0.7722, "lr": 8.454545454545455e-06, "epoch": 0.25706472196900637, "percentage": 8.58, "elapsed_time": "0:19:27", "remaining_time": "3:27:07"}
+{"current_steps": 95, "total_steps": 1095, "loss": 0.8004, "lr": 8.545454545454546e-06, "epoch": 0.25979945305378305, "percentage": 8.68, "elapsed_time": "0:19:40", "remaining_time": "3:27:02"}
+{"current_steps": 96, "total_steps": 1095, "loss": 0.7916, "lr": 8.636363636363637e-06, "epoch": 0.2625341841385597, "percentage": 8.77, "elapsed_time": "0:19:52", "remaining_time": "3:26:54"}
+{"current_steps": 97, "total_steps": 1095, "loss": 0.7736, "lr": 8.727272727272728e-06, "epoch": 0.2652689152233364, "percentage": 8.86, "elapsed_time": "0:20:03", "remaining_time": "3:26:19"}
+{"current_steps": 98, "total_steps": 1095, "loss": 0.8026, "lr": 8.818181818181819e-06, "epoch": 0.268003646308113, "percentage": 8.95, "elapsed_time": "0:20:11", "remaining_time": "3:25:26"}
+{"current_steps": 99, "total_steps": 1095, "loss": 0.8597, "lr": 8.90909090909091e-06, "epoch": 0.2707383773928897, "percentage": 9.04, "elapsed_time": "0:20:22", "remaining_time": "3:24:58"}
+{"current_steps": 100, "total_steps": 1095, "loss": 0.8072, "lr": 9e-06, "epoch": 0.27347310847766637, "percentage": 9.13, "elapsed_time": "0:20:32", "remaining_time": "3:24:21"}
+{"current_steps": 101, "total_steps": 1095, "loss": 0.824, "lr": 9.090909090909091e-06, "epoch": 0.27620783956244305, "percentage": 9.22, "elapsed_time": "0:20:49", "remaining_time": "3:24:59"}
+{"current_steps": 102, "total_steps": 1095, "loss": 0.7196, "lr": 9.181818181818184e-06, "epoch": 0.27894257064721967, "percentage": 9.32, "elapsed_time": "0:20:58", "remaining_time": "3:24:08"}
+{"current_steps": 103, "total_steps": 1095, "loss": 0.8077, "lr": 9.272727272727273e-06, "epoch": 0.28167730173199634, "percentage": 9.41, "elapsed_time": "0:21:10", "remaining_time": "3:23:56"}
+{"current_steps": 104, "total_steps": 1095, "loss": 0.8299, "lr": 9.363636363636365e-06, "epoch": 0.284412032816773, "percentage": 9.5, "elapsed_time": "0:21:20", "remaining_time": "3:23:26"}
+{"current_steps": 105, "total_steps": 1095, "loss": 0.8428, "lr": 9.454545454545456e-06, "epoch": 0.2871467639015497, "percentage": 9.59, "elapsed_time": "0:21:38", "remaining_time": "3:24:03"}
+{"current_steps": 106, "total_steps": 1095, "loss": 0.8952, "lr": 9.545454545454547e-06, "epoch": 0.28988149498632637, "percentage": 9.68, "elapsed_time": "0:21:47", "remaining_time": "3:23:20"}
+{"current_steps": 107, "total_steps": 1095, "loss": 0.8081, "lr": 9.636363636363638e-06, "epoch": 0.292616226071103, "percentage": 9.77, "elapsed_time": "0:21:57", "remaining_time": "3:22:43"}
+{"current_steps": 108, "total_steps": 1095, "loss": 0.9327, "lr": 9.727272727272728e-06, "epoch": 0.29535095715587967, "percentage": 9.86, "elapsed_time": "0:22:14", "remaining_time": "3:23:17"}
+{"current_steps": 109, "total_steps": 1095, "loss": 0.8932, "lr": 9.81818181818182e-06, "epoch": 0.29808568824065634, "percentage": 9.95, "elapsed_time": "0:22:29", "remaining_time": "3:23:29"}
+{"current_steps": 110, "total_steps": 1095, "loss": 0.8032, "lr": 9.90909090909091e-06, "epoch": 0.300820419325433, "percentage": 10.05, "elapsed_time": "0:22:43", "remaining_time": "3:23:26"}
+{"current_steps": 111, "total_steps": 1095, "loss": 0.8794, "lr": 1e-05, "epoch": 0.30355515041020964, "percentage": 10.14, "elapsed_time": "0:22:54", "remaining_time": "3:23:03"}
+{"current_steps": 112, "total_steps": 1095, "loss": 0.7809, "lr": 9.999974568795809e-06, "epoch": 0.3062898814949863, "percentage": 10.23, "elapsed_time": "0:23:04", "remaining_time": "3:22:28"}
+{"current_steps": 113, "total_steps": 1095, "loss": 0.7801, "lr": 9.999898275441935e-06, "epoch": 0.309024612579763, "percentage": 10.32, "elapsed_time": "0:23:12", "remaining_time": "3:21:38"}
+{"current_steps": 114, "total_steps": 1095, "loss": 0.7586, "lr": 9.999771120714468e-06, "epoch": 0.31175934366453967, "percentage": 10.41, "elapsed_time": "0:23:23", "remaining_time": "3:21:19"}
+{"current_steps": 115, "total_steps": 1095, "loss": 0.9294, "lr": 9.99959310590689e-06, "epoch": 0.31449407474931634, "percentage": 10.5, "elapsed_time": "0:23:38", "remaining_time": "3:21:26"}
+{"current_steps": 116, "total_steps": 1095, "loss": 0.7733, "lr": 9.999364232830053e-06, "epoch": 0.31722880583409296, "percentage": 10.59, "elapsed_time": "0:23:51", "remaining_time": "3:21:25"}
+{"current_steps": 117, "total_steps": 1095, "loss": 0.9315, "lr": 9.999084503812161e-06, "epoch": 0.31996353691886964, "percentage": 10.68, "elapsed_time": "0:24:02", "remaining_time": "3:20:55"}
+{"current_steps": 118, "total_steps": 1095, "loss": 0.9093, "lr": 9.998753921698757e-06, "epoch": 0.3226982680036463, "percentage": 10.78, "elapsed_time": "0:24:13", "remaining_time": "3:20:31"}
+{"current_steps": 119, "total_steps": 1095, "loss": 0.9572, "lr": 9.99837248985268e-06, "epoch": 0.325432999088423, "percentage": 10.87, "elapsed_time": "0:24:22", "remaining_time": "3:19:53"}
+{"current_steps": 120, "total_steps": 1095, "loss": 0.7797, "lr": 9.997940212154036e-06, "epoch": 0.3281677301731996, "percentage": 10.96, "elapsed_time": "0:24:32", "remaining_time": "3:19:22"}
+{"current_steps": 121, "total_steps": 1095, "loss": 0.7867, "lr": 9.997457093000165e-06, "epoch": 0.3309024612579763, "percentage": 11.05, "elapsed_time": "0:24:41", "remaining_time": "3:18:48"}
+{"current_steps": 122, "total_steps": 1095, "loss": 0.8397, "lr": 9.996923137305586e-06, "epoch": 0.33363719234275296, "percentage": 11.14, "elapsed_time": "0:24:49", "remaining_time": "3:18:01"}
+{"current_steps": 123, "total_steps": 1095, "loss": 0.8228, "lr": 9.996338350501952e-06, "epoch": 0.33637192342752964, "percentage": 11.23, "elapsed_time": "0:24:59", "remaining_time": "3:17:25"}
+{"current_steps": 124, "total_steps": 1095, "loss": 0.7444, "lr": 9.995702738538e-06, "epoch": 0.3391066545123063, "percentage": 11.32, "elapsed_time": "0:25:07", "remaining_time": "3:16:40"}
+{"current_steps": 125, "total_steps": 1095, "loss": 0.8457, "lr": 9.995016307879479e-06, "epoch": 0.34184138559708294, "percentage": 11.42, "elapsed_time": "0:25:16", "remaining_time": "3:16:07"}
+{"current_steps": 126, "total_steps": 1095, "loss": 0.8602, "lr": 9.994279065509094e-06, "epoch": 0.3445761166818596, "percentage": 11.51, "elapsed_time": "0:25:27", "remaining_time": "3:15:47"}
+{"current_steps": 127, "total_steps": 1095, "loss": 0.8284, "lr": 9.993491018926425e-06, "epoch": 0.3473108477666363, "percentage": 11.6, "elapsed_time": "0:25:43", "remaining_time": "3:16:07"}
+{"current_steps": 128, "total_steps": 1095, "loss": 0.8982, "lr": 9.992652176147866e-06, "epoch": 0.35004557885141296, "percentage": 11.69, "elapsed_time": "0:25:57", "remaining_time": "3:16:10"}
+{"current_steps": 129, "total_steps": 1095, "loss": 0.7564, "lr": 9.991762545706529e-06, "epoch": 0.3527803099361896, "percentage": 11.78, "elapsed_time": "0:26:06", "remaining_time": "3:15:32"}
+{"current_steps": 130, "total_steps": 1095, "loss": 0.9286, "lr": 9.99082213665216e-06, "epoch": 0.35551504102096626, "percentage": 11.87, "elapsed_time": "0:26:21", "remaining_time": "3:15:41"}
+{"current_steps": 131, "total_steps": 1095, "loss": 0.9915, "lr": 9.989830958551058e-06, "epoch": 0.35824977210574294, "percentage": 11.96, "elapsed_time": "0:26:34", "remaining_time": "3:15:34"}
+{"current_steps": 132, "total_steps": 1095, "loss": 0.9057, "lr": 9.988789021485961e-06, "epoch": 0.3609845031905196, "percentage": 12.05, "elapsed_time": "0:26:47", "remaining_time": "3:15:28"}
+{"current_steps": 133, "total_steps": 1095, "loss": 0.814, "lr": 9.987696336055955e-06, "epoch": 0.3637192342752963, "percentage": 12.15, "elapsed_time": "0:27:02", "remaining_time": "3:15:38"}
+{"current_steps": 134, "total_steps": 1095, "loss": 0.778, "lr": 9.986552913376361e-06, "epoch": 0.3664539653600729, "percentage": 12.24, "elapsed_time": "0:27:14", "remaining_time": "3:15:22"}
+{"current_steps": 135, "total_steps": 1095, "loss": 0.8962, "lr": 9.985358765078628e-06, "epoch": 0.3691886964448496, "percentage": 12.33, "elapsed_time": "0:27:29", "remaining_time": "3:15:32"}
+{"current_steps": 136, "total_steps": 1095, "loss": 0.7864, "lr": 9.984113903310206e-06, "epoch": 0.37192342752962626, "percentage": 12.42, "elapsed_time": "0:27:41", "remaining_time": "3:15:17"}
+{"current_steps": 137, "total_steps": 1095, "loss": 0.8568, "lr": 9.98281834073443e-06, "epoch": 0.37465815861440294, "percentage": 12.51, "elapsed_time": "0:27:54", "remaining_time": "3:15:06"}
+{"current_steps": 138, "total_steps": 1095, "loss": 0.7681, "lr": 9.981472090530386e-06, "epoch": 0.37739288969917956, "percentage": 12.6, "elapsed_time": "0:28:07", "remaining_time": "3:15:05"}
+{"current_steps": 139, "total_steps": 1095, "loss": 0.8964, "lr": 9.980075166392778e-06, "epoch": 0.38012762078395623, "percentage": 12.69, "elapsed_time": "0:28:24", "remaining_time": "3:15:20"}
+{"current_steps": 140, "total_steps": 1095, "loss": 0.7862, "lr": 9.978627582531792e-06, "epoch": 0.3828623518687329, "percentage": 12.79, "elapsed_time": "0:28:36", "remaining_time": "3:15:06"}
+{"current_steps": 141, "total_steps": 1095, "loss": 0.9953, "lr": 9.977129353672951e-06, "epoch": 0.3855970829535096, "percentage": 12.88, "elapsed_time": "0:28:50", "remaining_time": "3:15:09"}
+{"current_steps": 142, "total_steps": 1095, "loss": 0.9254, "lr": 9.975580495056956e-06, "epoch": 0.38833181403828626, "percentage": 12.97, "elapsed_time": "0:29:03", "remaining_time": "3:14:59"}
+{"current_steps": 143, "total_steps": 1095, "loss": 0.7954, "lr": 9.973981022439547e-06, "epoch": 0.3910665451230629, "percentage": 13.06, "elapsed_time": "0:29:13", "remaining_time": "3:14:31"}
+{"current_steps": 144, "total_steps": 1095, "loss": 0.7698, "lr": 9.972330952091328e-06, "epoch": 0.39380127620783956, "percentage": 13.15, "elapsed_time": "0:29:22", "remaining_time": "3:13:58"}
+{"current_steps": 145, "total_steps": 1095, "loss": 0.8312, "lr": 9.97063030079761e-06, "epoch": 0.39653600729261623, "percentage": 13.24, "elapsed_time": "0:29:35", "remaining_time": "3:13:50"}
+{"current_steps": 146, "total_steps": 1095, "loss": 0.7833, "lr": 9.968879085858234e-06, "epoch": 0.3992707383773929, "percentage": 13.33, "elapsed_time": "0:29:50", "remaining_time": "3:13:59"}
+{"current_steps": 147, "total_steps": 1095, "loss": 0.7731, "lr": 9.967077325087407e-06, "epoch": 0.40200546946216953, "percentage": 13.42, "elapsed_time": "0:30:04", "remaining_time": "3:13:59"}
+{"current_steps": 148, "total_steps": 1095, "loss": 0.889, "lr": 9.965225036813505e-06, "epoch": 0.4047402005469462, "percentage": 13.52, "elapsed_time": "0:30:14", "remaining_time": "3:13:33"}
+{"current_steps": 149, "total_steps": 1095, "loss": 0.7766, "lr": 9.963322239878894e-06, "epoch": 0.4074749316317229, "percentage": 13.61, "elapsed_time": "0:30:27", "remaining_time": "3:13:22"}
+{"current_steps": 150, "total_steps": 1095, "loss": 1.1178, "lr": 9.961368953639745e-06, "epoch": 0.41020966271649956, "percentage": 13.7, "elapsed_time": "0:30:48", "remaining_time": "3:14:04"}
+{"current_steps": 151, "total_steps": 1095, "loss": 0.8435, "lr": 9.959365197965824e-06, "epoch": 0.41294439380127623, "percentage": 13.79, "elapsed_time": "0:30:59", "remaining_time": "3:13:47"}
+{"current_steps": 152, "total_steps": 1095, "loss": 0.9305, "lr": 9.957310993240301e-06, "epoch": 0.41567912488605285, "percentage": 13.88, "elapsed_time": "0:31:12", "remaining_time": "3:13:36"}
+{"current_steps": 153, "total_steps": 1095, "loss": 0.96, "lr": 9.955206360359534e-06, "epoch": 0.41841385597082953, "percentage": 13.97, "elapsed_time": "0:31:28", "remaining_time": "3:13:47"}
+{"current_steps": 154, "total_steps": 1095, "loss": 0.7597, "lr": 9.953051320732863e-06, "epoch": 0.4211485870556062, "percentage": 14.06, "elapsed_time": "0:31:38", "remaining_time": "3:13:22"}
+{"current_steps": 155, "total_steps": 1095, "loss": 0.7511, "lr": 9.95084589628239e-06, "epoch": 0.4238833181403829, "percentage": 14.16, "elapsed_time": "0:31:50", "remaining_time": "3:13:08"}
+{"current_steps": 156, "total_steps": 1095, "loss": 0.7429, "lr": 9.948590109442755e-06, "epoch": 0.4266180492251595, "percentage": 14.25, "elapsed_time": "0:32:01", "remaining_time": "3:12:45"}
+{"current_steps": 157, "total_steps": 1095, "loss": 0.7218, "lr": 9.946283983160905e-06, "epoch": 0.4293527803099362, "percentage": 14.34, "elapsed_time": "0:32:11", "remaining_time": "3:12:21"}
+{"current_steps": 158, "total_steps": 1095, "loss": 0.8119, "lr": 9.94392754089587e-06, "epoch": 0.43208751139471285, "percentage": 14.43, "elapsed_time": "0:32:26", "remaining_time": "3:12:24"}
+{"current_steps": 159, "total_steps": 1095, "loss": 1.0725, "lr": 9.941520806618516e-06, "epoch": 0.43482224247948953, "percentage": 14.52, "elapsed_time": "0:32:38", "remaining_time": "3:12:08"}
+{"current_steps": 160, "total_steps": 1095, "loss": 0.7915, "lr": 9.939063804811304e-06, "epoch": 0.4375569735642662, "percentage": 14.61, "elapsed_time": "0:32:49", "remaining_time": "3:11:47"}
+{"current_steps": 161, "total_steps": 1095, "loss": 0.7429, "lr": 9.936556560468037e-06, "epoch": 0.4402917046490428, "percentage": 14.7, "elapsed_time": "0:33:01", "remaining_time": "3:11:35"}
+{"current_steps": 162, "total_steps": 1095, "loss": 0.8506, "lr": 9.933999099093614e-06, "epoch": 0.4430264357338195, "percentage": 14.79, "elapsed_time": "0:33:16", "remaining_time": "3:11:38"}
+{"current_steps": 163, "total_steps": 1095, "loss": 0.7686, "lr": 9.931391446703765e-06, "epoch": 0.4457611668185962, "percentage": 14.89, "elapsed_time": "0:33:29", "remaining_time": "3:11:27"}
+{"current_steps": 164, "total_steps": 1095, "loss": 1.0485, "lr": 9.928733629824782e-06, "epoch": 0.44849589790337285, "percentage": 14.98, "elapsed_time": "0:33:53", "remaining_time": "3:12:22"}
+{"current_steps": 165, "total_steps": 1095, "loss": 0.8622, "lr": 9.926025675493264e-06, "epoch": 0.4512306289881495, "percentage": 15.07, "elapsed_time": "0:34:01", "remaining_time": "3:11:47"}
+{"current_steps": 166, "total_steps": 1095, "loss": 0.8469, "lr": 9.923267611255824e-06, "epoch": 0.45396536007292615, "percentage": 15.16, "elapsed_time": "0:34:11", "remaining_time": "3:11:19"}
+{"current_steps": 167, "total_steps": 1095, "loss": 0.8356, "lr": 9.92045946516882e-06, "epoch": 0.4567000911577028, "percentage": 15.25, "elapsed_time": "0:34:28", "remaining_time": "3:11:31"}
+{"current_steps": 168, "total_steps": 1095, "loss": 0.8438, "lr": 9.917601265798066e-06, "epoch": 0.4594348222424795, "percentage": 15.34, "elapsed_time": "0:34:38", "remaining_time": "3:11:10"}
+{"current_steps": 169, "total_steps": 1095, "loss": 0.7692, "lr": 9.914693042218544e-06, "epoch": 0.4621695533272562, "percentage": 15.43, "elapsed_time": "0:34:49", "remaining_time": "3:10:46"}
+{"current_steps": 170, "total_steps": 1095, "loss": 0.7635, "lr": 9.911734824014104e-06, "epoch": 0.4649042844120328, "percentage": 15.53, "elapsed_time": "0:34:57", "remaining_time": "3:10:14"}
+{"current_steps": 171, "total_steps": 1095, "loss": 0.7645, "lr": 9.908726641277167e-06, "epoch": 0.4676390154968095, "percentage": 15.62, "elapsed_time": "0:35:13", "remaining_time": "3:10:18"}
+{"current_steps": 172, "total_steps": 1095, "loss": 0.7557, "lr": 9.905668524608419e-06, "epoch": 0.47037374658158615, "percentage": 15.71, "elapsed_time": "0:35:23", "remaining_time": "3:09:53"}
+{"current_steps": 173, "total_steps": 1095, "loss": 0.739, "lr": 9.902560505116492e-06, "epoch": 0.4731084776663628, "percentage": 15.8, "elapsed_time": "0:35:31", "remaining_time": "3:09:17"}
+{"current_steps": 174, "total_steps": 1095, "loss": 0.7377, "lr": 9.899402614417657e-06, "epoch": 0.47584320875113945, "percentage": 15.89, "elapsed_time": "0:35:43", "remaining_time": "3:09:06"}
+{"current_steps": 175, "total_steps": 1095, "loss": 0.7628, "lr": 9.896194884635503e-06, "epoch": 0.4785779398359161, "percentage": 15.98, "elapsed_time": "0:35:56", "remaining_time": "3:08:56"}
+{"current_steps": 176, "total_steps": 1095, "loss": 0.8748, "lr": 9.8929373484006e-06, "epoch": 0.4813126709206928, "percentage": 16.07, "elapsed_time": "0:36:11", "remaining_time": "3:08:57"}
+{"current_steps": 177, "total_steps": 1095, "loss": 0.7874, "lr": 9.889630038850177e-06, "epoch": 0.4840474020054695, "percentage": 16.16, "elapsed_time": "0:36:21", "remaining_time": "3:08:34"}
+{"current_steps": 178, "total_steps": 1095, "loss": 0.8041, "lr": 9.88627298962778e-06, "epoch": 0.48678213309024615, "percentage": 16.26, "elapsed_time": "0:36:32", "remaining_time": "3:08:15"}
+{"current_steps": 179, "total_steps": 1095, "loss": 0.8326, "lr": 9.88286623488293e-06, "epoch": 0.48951686417502277, "percentage": 16.35, "elapsed_time": "0:36:44", "remaining_time": "3:08:03"}
+{"current_steps": 180, "total_steps": 1095, "loss": 0.8294, "lr": 9.879409809270775e-06, "epoch": 0.49225159525979945, "percentage": 16.44, "elapsed_time": "0:36:54", "remaining_time": "3:07:39"}
+{"current_steps": 181, "total_steps": 1095, "loss": 0.8154, "lr": 9.875903747951742e-06, "epoch": 0.4949863263445761, "percentage": 16.53, "elapsed_time": "0:37:03", "remaining_time": "3:07:09"}
+{"current_steps": 182, "total_steps": 1095, "loss": 0.7759, "lr": 9.872348086591179e-06, "epoch": 0.4977210574293528, "percentage": 16.62, "elapsed_time": "0:37:16", "remaining_time": "3:07:01"}
+{"current_steps": 183, "total_steps": 1095, "loss": 0.8194, "lr": 9.868742861358984e-06, "epoch": 0.5004557885141294, "percentage": 16.71, "elapsed_time": "0:37:33", "remaining_time": "3:07:12"}
+{"current_steps": 184, "total_steps": 1095, "loss": 0.8055, "lr": 9.865088108929244e-06, "epoch": 0.5031905195989061, "percentage": 16.8, "elapsed_time": "0:37:46", "remaining_time": "3:07:00"}
+{"current_steps": 185, "total_steps": 1095, "loss": 0.8622, "lr": 9.861383866479862e-06, "epoch": 0.5059252506836828, "percentage": 16.89, "elapsed_time": "0:38:00", "remaining_time": "3:06:58"}
+{"current_steps": 186, "total_steps": 1095, "loss": 0.7608, "lr": 9.857630171692175e-06, "epoch": 0.5086599817684594, "percentage": 16.99, "elapsed_time": "0:38:11", "remaining_time": "3:06:39"}
+{"current_steps": 187, "total_steps": 1095, "loss": 0.8379, "lr": 9.853827062750573e-06, "epoch": 0.5113947128532361, "percentage": 17.08, "elapsed_time": "0:38:24", "remaining_time": "3:06:28"}
+{"current_steps": 188, "total_steps": 1095, "loss": 0.8241, "lr": 9.849974578342119e-06, "epoch": 0.5141294439380127, "percentage": 17.17, "elapsed_time": "0:38:36", "remaining_time": "3:06:17"}
+{"current_steps": 189, "total_steps": 1095, "loss": 0.8559, "lr": 9.846072757656134e-06, "epoch": 0.5168641750227895, "percentage": 17.26, "elapsed_time": "0:38:54", "remaining_time": "3:06:30"}
+{"current_steps": 190, "total_steps": 1095, "loss": 0.7727, "lr": 9.842121640383818e-06, "epoch": 0.5195989061075661, "percentage": 17.35, "elapsed_time": "0:39:04", "remaining_time": "3:06:08"}
+{"current_steps": 191, "total_steps": 1095, "loss": 0.7588, "lr": 9.83812126671784e-06, "epoch": 0.5223336371923427, "percentage": 17.44, "elapsed_time": "0:39:15", "remaining_time": "3:05:47"}
+{"current_steps": 192, "total_steps": 1095, "loss": 0.7732, "lr": 9.834071677351928e-06, "epoch": 0.5250683682771194, "percentage": 17.53, "elapsed_time": "0:39:25", "remaining_time": "3:05:27"}
+{"current_steps": 193, "total_steps": 1095, "loss": 0.8511, "lr": 9.829972913480455e-06, "epoch": 0.5278030993618961, "percentage": 17.63, "elapsed_time": "0:39:36", "remaining_time": "3:05:07"}
+{"current_steps": 194, "total_steps": 1095, "loss": 0.801, "lr": 9.825825016798022e-06, "epoch": 0.5305378304466728, "percentage": 17.72, "elapsed_time": "0:39:53", "remaining_time": "3:05:14"}
+{"current_steps": 195, "total_steps": 1095, "loss": 0.8004, "lr": 9.821628029499031e-06, "epoch": 0.5332725615314494, "percentage": 17.81, "elapsed_time": "0:40:01", "remaining_time": "3:04:44"}
+{"current_steps": 196, "total_steps": 1095, "loss": 0.7271, "lr": 9.81738199427726e-06, "epoch": 0.536007292616226, "percentage": 17.9, "elapsed_time": "0:40:16", "remaining_time": "3:04:41"}
+{"current_steps": 197, "total_steps": 1095, "loss": 0.7247, "lr": 9.813086954325424e-06, "epoch": 0.5387420237010028, "percentage": 17.99, "elapsed_time": "0:40:26", "remaining_time": "3:04:21"}
+{"current_steps": 198, "total_steps": 1095, "loss": 0.7561, "lr": 9.808742953334738e-06, "epoch": 0.5414767547857794, "percentage": 18.08, "elapsed_time": "0:40:41", "remaining_time": "3:04:20"}
+{"current_steps": 199, "total_steps": 1095, "loss": 0.8412, "lr": 9.804350035494472e-06, "epoch": 0.544211485870556, "percentage": 18.17, "elapsed_time": "0:40:54", "remaining_time": "3:04:11"}
+{"current_steps": 200, "total_steps": 1095, "loss": 0.788, "lr": 9.799908245491503e-06, "epoch": 0.5469462169553327, "percentage": 18.26, "elapsed_time": "0:41:13", "remaining_time": "3:04:27"}
+{"current_steps": 201, "total_steps": 1095, "loss": 0.8202, "lr": 9.795417628509857e-06, "epoch": 0.5496809480401094, "percentage": 18.36, "elapsed_time": "0:41:27", "remaining_time": "3:04:24"}
+{"current_steps": 202, "total_steps": 1095, "loss": 0.8092, "lr": 9.790878230230255e-06, "epoch": 0.5524156791248861, "percentage": 18.45, "elapsed_time": "0:41:36", "remaining_time": "3:03:56"}
+{"current_steps": 203, "total_steps": 1095, "loss": 0.8732, "lr": 9.786290096829641e-06, "epoch": 0.5551504102096627, "percentage": 18.54, "elapsed_time": "0:41:48", "remaining_time": "3:03:42"}
+{"current_steps": 204, "total_steps": 1095, "loss": 0.7801, "lr": 9.78165327498072e-06, "epoch": 0.5578851412944393, "percentage": 18.63, "elapsed_time": "0:41:58", "remaining_time": "3:03:19"}
+{"current_steps": 205, "total_steps": 1095, "loss": 0.8229, "lr": 9.776967811851474e-06, "epoch": 0.5606198723792161, "percentage": 18.72, "elapsed_time": "0:42:17", "remaining_time": "3:03:36"}
+{"current_steps": 206, "total_steps": 1095, "loss": 0.8926, "lr": 9.772233755104695e-06, "epoch": 0.5633546034639927, "percentage": 18.81, "elapsed_time": "0:42:31", "remaining_time": "3:03:31"}
+{"current_steps": 207, "total_steps": 1095, "loss": 0.864, "lr": 9.767451152897486e-06, "epoch": 0.5660893345487694, "percentage": 18.9, "elapsed_time": "0:42:44", "remaining_time": "3:03:21"}
+{"current_steps": 208, "total_steps": 1095, "loss": 0.8294, "lr": 9.762620053880779e-06, "epoch": 0.568824065633546, "percentage": 19.0, "elapsed_time": "0:42:57", "remaining_time": "3:03:11"}
+{"current_steps": 209, "total_steps": 1095, "loss": 0.7713, "lr": 9.757740507198842e-06, "epoch": 0.5715587967183227, "percentage": 19.09, "elapsed_time": "0:43:09", "remaining_time": "3:02:55"}
+{"current_steps": 210, "total_steps": 1095, "loss": 0.8753, "lr": 9.752812562488775e-06, "epoch": 0.5742935278030994, "percentage": 19.18, "elapsed_time": "0:43:19", "remaining_time": "3:02:35"}
+{"current_steps": 211, "total_steps": 1095, "loss": 0.9019, "lr": 9.747836269880005e-06, "epoch": 0.577028258887876, "percentage": 19.27, "elapsed_time": "0:43:37", "remaining_time": "3:02:46"}
+{"current_steps": 212, "total_steps": 1095, "loss": 0.6997, "lr": 9.742811679993775e-06, "epoch": 0.5797629899726527, "percentage": 19.36, "elapsed_time": "0:43:51", "remaining_time": "3:02:41"}
+{"current_steps": 213, "total_steps": 1095, "loss": 0.7689, "lr": 9.737738843942636e-06, "epoch": 0.5824977210574294, "percentage": 19.45, "elapsed_time": "0:44:00", "remaining_time": "3:02:13"}
+{"current_steps": 214, "total_steps": 1095, "loss": 0.7255, "lr": 9.73261781332992e-06, "epoch": 0.585232452142206, "percentage": 19.54, "elapsed_time": "0:44:17", "remaining_time": "3:02:18"}
+{"current_steps": 215, "total_steps": 1095, "loss": 0.8137, "lr": 9.727448640249215e-06, "epoch": 0.5879671832269827, "percentage": 19.63, "elapsed_time": "0:44:29", "remaining_time": "3:02:06"}
+{"current_steps": 216, "total_steps": 1095, "loss": 0.7789, "lr": 9.722231377283841e-06, "epoch": 0.5907019143117593, "percentage": 19.73, "elapsed_time": "0:44:42", "remaining_time": "3:01:57"}
+{"current_steps": 217, "total_steps": 1095, "loss": 0.9312, "lr": 9.71696607750631e-06, "epoch": 0.593436645396536, "percentage": 19.82, "elapsed_time": "0:44:59", "remaining_time": "3:02:02"}
+{"current_steps": 218, "total_steps": 1095, "loss": 0.7714, "lr": 9.711652794477788e-06, "epoch": 0.5961713764813127, "percentage": 19.91, "elapsed_time": "0:45:11", "remaining_time": "3:01:48"}
+{"current_steps": 219, "total_steps": 1095, "loss": 0.9452, "lr": 9.706291582247547e-06, "epoch": 0.5989061075660893, "percentage": 20.0, "elapsed_time": "0:45:30", "remaining_time": "3:02:01"}
+{"current_steps": 220, "total_steps": 1095, "loss": 0.7559, "lr": 9.700882495352421e-06, "epoch": 0.601640838650866, "percentage": 20.09, "elapsed_time": "0:45:44", "remaining_time": "3:01:54"}
+{"current_steps": 221, "total_steps": 1095, "loss": 0.7598, "lr": 9.695425588816248e-06, "epoch": 0.6043755697356427, "percentage": 20.18, "elapsed_time": "0:45:54", "remaining_time": "3:01:32"}
+{"current_steps": 222, "total_steps": 1095, "loss": 0.7573, "lr": 9.68992091814931e-06, "epoch": 0.6071103008204193, "percentage": 20.27, "elapsed_time": "0:46:11", "remaining_time": "3:01:36"}
+{"current_steps": 223, "total_steps": 1095, "loss": 0.7483, "lr": 9.684368539347767e-06, "epoch": 0.609845031905196, "percentage": 20.37, "elapsed_time": "0:46:22", "remaining_time": "3:01:19"}
+{"current_steps": 224, "total_steps": 1095, "loss": 0.7466, "lr": 9.678768508893094e-06, "epoch": 0.6125797629899726, "percentage": 20.46, "elapsed_time": "0:46:43", "remaining_time": "3:01:39"}
+{"current_steps": 225, "total_steps": 1095, "loss": 0.913, "lr": 9.673120883751494e-06, "epoch": 0.6153144940747494, "percentage": 20.55, "elapsed_time": "0:46:57", "remaining_time": "3:01:34"}
+{"current_steps": 226, "total_steps": 1095, "loss": 0.7562, "lr": 9.667425721373333e-06, "epoch": 0.618049225159526, "percentage": 20.64, "elapsed_time": "0:47:08", "remaining_time": "3:01:16"}
+{"current_steps": 227, "total_steps": 1095, "loss": 0.6351, "lr": 9.661683079692544e-06, "epoch": 0.6207839562443026, "percentage": 20.73, "elapsed_time": "0:47:19", "remaining_time": "3:00:56"}
+{"current_steps": 228, "total_steps": 1095, "loss": 0.8274, "lr": 9.655893017126045e-06, "epoch": 0.6235186873290793, "percentage": 20.82, "elapsed_time": "0:47:29", "remaining_time": "3:00:36"}
+{"current_steps": 229, "total_steps": 1095, "loss": 0.8524, "lr": 9.650055592573143e-06, "epoch": 0.626253418413856, "percentage": 20.91, "elapsed_time": "0:47:42", "remaining_time": "3:00:26"}
+{"current_steps": 230, "total_steps": 1095, "loss": 0.6763, "lr": 9.64417086541493e-06, "epoch": 0.6289881494986327, "percentage": 21.0, "elapsed_time": "0:47:52", "remaining_time": "3:00:02"}
+{"current_steps": 231, "total_steps": 1095, "loss": 0.8565, "lr": 9.638238895513687e-06, "epoch": 0.6317228805834093, "percentage": 21.1, "elapsed_time": "0:48:07", "remaining_time": "2:59:58"}
+{"current_steps": 232, "total_steps": 1095, "loss": 0.8128, "lr": 9.632259743212268e-06, "epoch": 0.6344576116681859, "percentage": 21.19, "elapsed_time": "0:48:20", "remaining_time": "2:59:48"}
+{"current_steps": 233, "total_steps": 1095, "loss": 0.7684, "lr": 9.62623346933349e-06, "epoch": 0.6371923427529627, "percentage": 21.28, "elapsed_time": "0:48:28", "remaining_time": "2:59:21"}
+{"current_steps": 234, "total_steps": 1095, "loss": 0.6786, "lr": 9.620160135179515e-06, "epoch": 0.6399270738377393, "percentage": 21.37, "elapsed_time": "0:48:39", "remaining_time": "2:59:00"}
+{"current_steps": 235, "total_steps": 1095, "loss": 0.7108, "lr": 9.614039802531222e-06, "epoch": 0.6426618049225159, "percentage": 21.46, "elapsed_time": "0:48:53", "remaining_time": "2:58:54"}
+{"current_steps": 236, "total_steps": 1095, "loss": 0.8787, "lr": 9.607872533647584e-06, "epoch": 0.6453965360072926, "percentage": 21.55, "elapsed_time": "0:49:09", "remaining_time": "2:58:56"}
+{"current_steps": 237, "total_steps": 1095, "loss": 0.8311, "lr": 9.60165839126503e-06, "epoch": 0.6481312670920693, "percentage": 21.64, "elapsed_time": "0:49:19", "remaining_time": "2:58:35"}
+{"current_steps": 238, "total_steps": 1095, "loss": 0.7217, "lr": 9.595397438596807e-06, "epoch": 0.650865998176846, "percentage": 21.74, "elapsed_time": "0:49:31", "remaining_time": "2:58:18"}
+{"current_steps": 239, "total_steps": 1095, "loss": 0.7584, "lr": 9.589089739332346e-06, "epoch": 0.6536007292616226, "percentage": 21.83, "elapsed_time": "0:49:44", "remaining_time": "2:58:09"}
+{"current_steps": 240, "total_steps": 1095, "loss": 0.741, "lr": 9.582735357636599e-06, "epoch": 0.6563354603463992, "percentage": 21.92, "elapsed_time": "0:49:55", "remaining_time": "2:57:51"}
+{"current_steps": 241, "total_steps": 1095, "loss": 0.9249, "lr": 9.5763343581494e-06, "epoch": 0.659070191431176, "percentage": 22.01, "elapsed_time": "0:50:11", "remaining_time": "2:57:51"}
+{"current_steps": 242, "total_steps": 1095, "loss": 0.8766, "lr": 9.569886805984797e-06, "epoch": 0.6618049225159526, "percentage": 22.1, "elapsed_time": "0:50:23", "remaining_time": "2:57:37"}
+{"current_steps": 243, "total_steps": 1095, "loss": 0.8473, "lr": 9.563392766730396e-06, "epoch": 0.6645396536007293, "percentage": 22.19, "elapsed_time": "0:50:38", "remaining_time": "2:57:32"}
+{"current_steps": 244, "total_steps": 1095, "loss": 0.7833, "lr": 9.556852306446692e-06, "epoch": 0.6672743846855059, "percentage": 22.28, "elapsed_time": "0:50:56", "remaining_time": "2:57:40"}
+{"current_steps": 245, "total_steps": 1095, "loss": 0.7371, "lr": 9.550265491666397e-06, "epoch": 0.6700091157702825, "percentage": 22.37, "elapsed_time": "0:51:08", "remaining_time": "2:57:27"}
+{"current_steps": 246, "total_steps": 1095, "loss": 0.8339, "lr": 9.543632389393767e-06, "epoch": 0.6727438468550593, "percentage": 22.47, "elapsed_time": "0:51:22", "remaining_time": "2:57:16"}
+{"current_steps": 247, "total_steps": 1095, "loss": 0.6881, "lr": 9.536953067103912e-06, "epoch": 0.6754785779398359, "percentage": 22.56, "elapsed_time": "0:51:39", "remaining_time": "2:57:21"}
+{"current_steps": 248, "total_steps": 1095, "loss": 0.7834, "lr": 9.530227592742114e-06, "epoch": 0.6782133090246126, "percentage": 22.65, "elapsed_time": "0:51:49", "remaining_time": "2:56:59"}
+{"current_steps": 249, "total_steps": 1095, "loss": 0.9233, "lr": 9.523456034723137e-06, "epoch": 0.6809480401093893, "percentage": 22.74, "elapsed_time": "0:52:01", "remaining_time": "2:56:45"}
+{"current_steps": 250, "total_steps": 1095, "loss": 0.712, "lr": 9.516638461930534e-06, "epoch": 0.6836827711941659, "percentage": 22.83, "elapsed_time": "0:52:11", "remaining_time": "2:56:22"}
+{"current_steps": 251, "total_steps": 1095, "loss": 0.7791, "lr": 9.50977494371594e-06, "epoch": 0.6864175022789426, "percentage": 22.92, "elapsed_time": "0:52:23", "remaining_time": "2:56:09"}
+{"current_steps": 252, "total_steps": 1095, "loss": 0.7791, "lr": 9.502865549898363e-06, "epoch": 0.6891522333637192, "percentage": 23.01, "elapsed_time": "0:52:31", "remaining_time": "2:55:41"}
+{"current_steps": 253, "total_steps": 1095, "loss": 0.6921, "lr": 9.495910350763488e-06, "epoch": 0.6918869644484958, "percentage": 23.11, "elapsed_time": "0:52:41", "remaining_time": "2:55:21"}
+{"current_steps": 254, "total_steps": 1095, "loss": 0.7082, "lr": 9.488909417062953e-06, "epoch": 0.6946216955332726, "percentage": 23.2, "elapsed_time": "0:52:54", "remaining_time": "2:55:09"}
+{"current_steps": 255, "total_steps": 1095, "loss": 0.7131, "lr": 9.481862820013624e-06, "epoch": 0.6973564266180492, "percentage": 23.29, "elapsed_time": "0:53:06", "remaining_time": "2:54:56"}
+{"current_steps": 256, "total_steps": 1095, "loss": 0.7781, "lr": 9.474770631296882e-06, "epoch": 0.7000911577028259, "percentage": 23.38, "elapsed_time": "0:53:19", "remaining_time": "2:54:47"}
+{"current_steps": 257, "total_steps": 1095, "loss": 0.8288, "lr": 9.467632923057886e-06, "epoch": 0.7028258887876025, "percentage": 23.47, "elapsed_time": "0:53:30", "remaining_time": "2:54:29"}
+{"current_steps": 258, "total_steps": 1095, "loss": 0.7481, "lr": 9.460449767904845e-06, "epoch": 0.7055606198723792, "percentage": 23.56, "elapsed_time": "0:53:53", "remaining_time": "2:54:49"}
+{"current_steps": 259, "total_steps": 1095, "loss": 0.7537, "lr": 9.45322123890827e-06, "epoch": 0.7082953509571559, "percentage": 23.65, "elapsed_time": "0:54:05", "remaining_time": "2:54:37"}
+{"current_steps": 260, "total_steps": 1095, "loss": 0.8812, "lr": 9.44594740960024e-06, "epoch": 0.7110300820419325, "percentage": 23.74, "elapsed_time": "0:54:15", "remaining_time": "2:54:16"}
+{"current_steps": 261, "total_steps": 1095, "loss": 0.896, "lr": 9.438628353973654e-06, "epoch": 0.7137648131267093, "percentage": 23.84, "elapsed_time": "0:54:30", "remaining_time": "2:54:09"}
+{"current_steps": 262, "total_steps": 1095, "loss": 0.6757, "lr": 9.431264146481465e-06, "epoch": 0.7164995442114859, "percentage": 23.93, "elapsed_time": "0:54:42", "remaining_time": "2:53:57"}
+{"current_steps": 263, "total_steps": 1095, "loss": 0.8411, "lr": 9.423854862035944e-06, "epoch": 0.7192342752962625, "percentage": 24.02, "elapsed_time": "0:54:55", "remaining_time": "2:53:45"}
+{"current_steps": 264, "total_steps": 1095, "loss": 0.7609, "lr": 9.4164005760079e-06, "epoch": 0.7219690063810392, "percentage": 24.11, "elapsed_time": "0:55:05", "remaining_time": "2:53:23"}
+{"current_steps": 265, "total_steps": 1095, "loss": 0.8869, "lr": 9.40890136422592e-06, "epoch": 0.7247037374658158, "percentage": 24.2, "elapsed_time": "0:55:18", "remaining_time": "2:53:13"}
+{"current_steps": 266, "total_steps": 1095, "loss": 0.8188, "lr": 9.4013573029756e-06, "epoch": 0.7274384685505926, "percentage": 24.29, "elapsed_time": "0:55:29", "remaining_time": "2:52:55"}
+{"current_steps": 267, "total_steps": 1095, "loss": 0.7225, "lr": 9.393768468998764e-06, "epoch": 0.7301731996353692, "percentage": 24.38, "elapsed_time": "0:55:42", "remaining_time": "2:52:45"}
+{"current_steps": 268, "total_steps": 1095, "loss": 0.7914, "lr": 9.386134939492686e-06, "epoch": 0.7329079307201458, "percentage": 24.47, "elapsed_time": "0:55:51", "remaining_time": "2:52:22"}
+{"current_steps": 269, "total_steps": 1095, "loss": 0.6821, "lr": 9.378456792109305e-06, "epoch": 0.7356426618049225, "percentage": 24.57, "elapsed_time": "0:56:00", "remaining_time": "2:51:59"}
+{"current_steps": 270, "total_steps": 1095, "loss": 0.8998, "lr": 9.370734104954436e-06, "epoch": 0.7383773928896992, "percentage": 24.66, "elapsed_time": "0:56:12", "remaining_time": "2:51:45"}
+{"current_steps": 271, "total_steps": 1095, "loss": 0.7837, "lr": 9.36296695658697e-06, "epoch": 0.7411121239744758, "percentage": 24.75, "elapsed_time": "0:56:31", "remaining_time": "2:51:51"}
+{"current_steps": 272, "total_steps": 1095, "loss": 0.7473, "lr": 9.355155426018084e-06, "epoch": 0.7438468550592525, "percentage": 24.84, "elapsed_time": "0:56:48", "remaining_time": "2:51:52"}
+{"current_steps": 273, "total_steps": 1095, "loss": 0.7322, "lr": 9.347299592710427e-06, "epoch": 0.7465815861440291, "percentage": 24.93, "elapsed_time": "0:56:57", "remaining_time": "2:51:28"}
+{"current_steps": 274, "total_steps": 1095, "loss": 0.7526, "lr": 9.339399536577323e-06, "epoch": 0.7493163172288059, "percentage": 25.02, "elapsed_time": "0:57:09", "remaining_time": "2:51:15"}
+{"current_steps": 275, "total_steps": 1095, "loss": 0.7143, "lr": 9.331455337981947e-06, "epoch": 0.7520510483135825, "percentage": 25.11, "elapsed_time": "0:57:19", "remaining_time": "2:50:56"}
+{"current_steps": 276, "total_steps": 1095, "loss": 0.735, "lr": 9.323467077736513e-06, "epoch": 0.7547857793983591, "percentage": 25.21, "elapsed_time": "0:57:30", "remaining_time": "2:50:39"}
+{"current_steps": 277, "total_steps": 1095, "loss": 0.7286, "lr": 9.315434837101449e-06, "epoch": 0.7575205104831358, "percentage": 25.3, "elapsed_time": "0:57:40", "remaining_time": "2:50:18"}
+{"current_steps": 278, "total_steps": 1095, "loss": 0.8657, "lr": 9.307358697784582e-06, "epoch": 0.7602552415679125, "percentage": 25.39, "elapsed_time": "0:57:55", "remaining_time": "2:50:12"}
+{"current_steps": 279, "total_steps": 1095, "loss": 0.793, "lr": 9.299238741940283e-06, "epoch": 0.7629899726526892, "percentage": 25.48, "elapsed_time": "0:58:06", "remaining_time": "2:49:58"}
+{"current_steps": 280, "total_steps": 1095, "loss": 0.7839, "lr": 9.291075052168662e-06, "epoch": 0.7657247037374658, "percentage": 25.57, "elapsed_time": "0:58:21", "remaining_time": "2:49:52"}
+{"current_steps": 281, "total_steps": 1095, "loss": 0.8196, "lr": 9.282867711514703e-06, "epoch": 0.7684594348222424, "percentage": 25.66, "elapsed_time": "0:58:39", "remaining_time": "2:49:55"}
+{"current_steps": 282, "total_steps": 1095, "loss": 0.7334, "lr": 9.274616803467422e-06, "epoch": 0.7711941659070192, "percentage": 25.75, "elapsed_time": "0:58:52", "remaining_time": "2:49:45"}
+{"current_steps": 283, "total_steps": 1095, "loss": 0.7793, "lr": 9.266322411959034e-06, "epoch": 0.7739288969917958, "percentage": 25.84, "elapsed_time": "0:59:07", "remaining_time": "2:49:37"}
+{"current_steps": 284, "total_steps": 1095, "loss": 0.7539, "lr": 9.257984621364086e-06, "epoch": 0.7766636280765725, "percentage": 25.94, "elapsed_time": "0:59:17", "remaining_time": "2:49:18"}
+{"current_steps": 285, "total_steps": 1095, "loss": 0.8354, "lr": 9.249603516498599e-06, "epoch": 0.7793983591613491, "percentage": 26.03, "elapsed_time": "0:59:28", "remaining_time": "2:49:01"}
+{"current_steps": 286, "total_steps": 1095, "loss": 0.7556, "lr": 9.241179182619207e-06, "epoch": 0.7821330902461258, "percentage": 26.12, "elapsed_time": "0:59:43", "remaining_time": "2:48:57"}
+{"current_steps": 287, "total_steps": 1095, "loss": 0.8393, "lr": 9.232711705422292e-06, "epoch": 0.7848678213309025, "percentage": 26.21, "elapsed_time": "0:59:54", "remaining_time": "2:48:40"}
+{"current_steps": 288, "total_steps": 1095, "loss": 0.7389, "lr": 9.224201171043115e-06, "epoch": 0.7876025524156791, "percentage": 26.3, "elapsed_time": "1:00:06", "remaining_time": "2:48:25"}
+{"current_steps": 289, "total_steps": 1095, "loss": 0.8341, "lr": 9.215647666054926e-06, "epoch": 0.7903372835004557, "percentage": 26.39, "elapsed_time": "1:00:18", "remaining_time": "2:48:11"}
+{"current_steps": 290, "total_steps": 1095, "loss": 0.7842, "lr": 9.207051277468098e-06, "epoch": 0.7930720145852325, "percentage": 26.48, "elapsed_time": "1:00:36", "remaining_time": "2:48:14"}
+{"current_steps": 291, "total_steps": 1095, "loss": 0.6949, "lr": 9.19841209272924e-06, "epoch": 0.7958067456700091, "percentage": 26.58, "elapsed_time": "1:00:49", "remaining_time": "2:48:02"}
+{"current_steps": 292, "total_steps": 1095, "loss": 0.7651, "lr": 9.189730199720298e-06, "epoch": 0.7985414767547858, "percentage": 26.67, "elapsed_time": "1:01:01", "remaining_time": "2:47:48"}
+{"current_steps": 293, "total_steps": 1095, "loss": 0.7461, "lr": 9.181005686757669e-06, "epoch": 0.8012762078395624, "percentage": 26.76, "elapsed_time": "1:01:18", "remaining_time": "2:47:49"}
+{"current_steps": 294, "total_steps": 1095, "loss": 0.7516, "lr": 9.172238642591304e-06, "epoch": 0.8040109389243391, "percentage": 26.85, "elapsed_time": "1:01:32", "remaining_time": "2:47:39"}
+{"current_steps": 295, "total_steps": 1095, "loss": 0.7852, "lr": 9.163429156403796e-06, "epoch": 0.8067456700091158, "percentage": 26.94, "elapsed_time": "1:01:45", "remaining_time": "2:47:28"}
+{"current_steps": 296, "total_steps": 1095, "loss": 0.7687, "lr": 9.154577317809483e-06, "epoch": 0.8094804010938924, "percentage": 27.03, "elapsed_time": "1:01:57", "remaining_time": "2:47:14"}
+{"current_steps": 297, "total_steps": 1095, "loss": 0.8241, "lr": 9.145683216853534e-06, "epoch": 0.8122151321786691, "percentage": 27.12, "elapsed_time": "1:02:08", "remaining_time": "2:46:57"}
+{"current_steps": 298, "total_steps": 1095, "loss": 0.7333, "lr": 9.136746944011021e-06, "epoch": 0.8149498632634458, "percentage": 27.21, "elapsed_time": "1:02:16", "remaining_time": "2:46:33"}
+{"current_steps": 299, "total_steps": 1095, "loss": 0.8012, "lr": 9.127768590186022e-06, "epoch": 0.8176845943482224, "percentage": 27.31, "elapsed_time": "1:02:29", "remaining_time": "2:46:22"}
+{"current_steps": 300, "total_steps": 1095, "loss": 0.8279, "lr": 9.118748246710675e-06, "epoch": 0.8204193254329991, "percentage": 27.4, "elapsed_time": "1:02:38", "remaining_time": "2:46:00"}
+{"current_steps": 301, "total_steps": 1095, "loss": 0.8353, "lr": 9.109686005344258e-06, "epoch": 0.8231540565177757, "percentage": 27.49, "elapsed_time": "1:02:49", "remaining_time": "2:45:43"}
+{"current_steps": 302, "total_steps": 1095, "loss": 0.6926, "lr": 9.100581958272255e-06, "epoch": 0.8258887876025525, "percentage": 27.58, "elapsed_time": "1:03:01", "remaining_time": "2:45:28"}
+{"current_steps": 303, "total_steps": 1095, "loss": 0.9119, "lr": 9.091436198105418e-06, "epoch": 0.8286235186873291, "percentage": 27.67, "elapsed_time": "1:03:23", "remaining_time": "2:45:42"}
+{"current_steps": 304, "total_steps": 1095, "loss": 0.7234, "lr": 9.082248817878828e-06, "epoch": 0.8313582497721057, "percentage": 27.76, "elapsed_time": "1:03:36", "remaining_time": "2:45:30"}
+{"current_steps": 305, "total_steps": 1095, "loss": 0.6756, "lr": 9.073019911050936e-06, "epoch": 0.8340929808568824, "percentage": 27.85, "elapsed_time": "1:03:48", "remaining_time": "2:45:15"}
+{"current_steps": 306, "total_steps": 1095, "loss": 0.8578, "lr": 9.063749571502633e-06, "epoch": 0.8368277119416591, "percentage": 27.95, "elapsed_time": "1:04:03", "remaining_time": "2:45:09"}
+{"current_steps": 307, "total_steps": 1095, "loss": 0.8125, "lr": 9.054437893536275e-06, "epoch": 0.8395624430264357, "percentage": 28.04, "elapsed_time": "1:04:18", "remaining_time": "2:45:04"}
+{"current_steps": 308, "total_steps": 1095, "loss": 0.8667, "lr": 9.045084971874738e-06, "epoch": 0.8422971741112124, "percentage": 28.13, "elapsed_time": "1:04:30", "remaining_time": "2:44:49"}
+{"current_steps": 309, "total_steps": 1095, "loss": 0.781, "lr": 9.035690901660443e-06, "epoch": 0.845031905195989, "percentage": 28.22, "elapsed_time": "1:04:49", "remaining_time": "2:44:53"}
+{"current_steps": 310, "total_steps": 1095, "loss": 0.6776, "lr": 9.0262557784544e-06, "epoch": 0.8477666362807658, "percentage": 28.31, "elapsed_time": "1:05:01", "remaining_time": "2:44:40"}
+{"current_steps": 311, "total_steps": 1095, "loss": 0.6692, "lr": 9.016779698235227e-06, "epoch": 0.8505013673655424, "percentage": 28.4, "elapsed_time": "1:05:14", "remaining_time": "2:44:28"}
+{"current_steps": 312, "total_steps": 1095, "loss": 0.7815, "lr": 9.007262757398175e-06, "epoch": 0.853236098450319, "percentage": 28.49, "elapsed_time": "1:05:29", "remaining_time": "2:44:21"}
+{"current_steps": 313, "total_steps": 1095, "loss": 0.6663, "lr": 8.99770505275415e-06, "epoch": 0.8559708295350957, "percentage": 28.58, "elapsed_time": "1:05:39", "remaining_time": "2:44:02"}
+{"current_steps": 314, "total_steps": 1095, "loss": 0.6871, "lr": 8.988106681528726e-06, "epoch": 0.8587055606198724, "percentage": 28.68, "elapsed_time": "1:05:48", "remaining_time": "2:43:41"}
+{"current_steps": 315, "total_steps": 1095, "loss": 0.7793, "lr": 8.978467741361162e-06, "epoch": 0.8614402917046491, "percentage": 28.77, "elapsed_time": "1:06:01", "remaining_time": "2:43:28"}
+{"current_steps": 316, "total_steps": 1095, "loss": 0.7419, "lr": 8.9687883303034e-06, "epoch": 0.8641750227894257, "percentage": 28.86, "elapsed_time": "1:06:09", "remaining_time": "2:43:06"}
+{"current_steps": 317, "total_steps": 1095, "loss": 0.812, "lr": 8.959068546819068e-06, "epoch": 0.8669097538742023, "percentage": 28.95, "elapsed_time": "1:06:21", "remaining_time": "2:42:50"}
+{"current_steps": 318, "total_steps": 1095, "loss": 0.7035, "lr": 8.949308489782488e-06, "epoch": 0.8696444849589791, "percentage": 29.04, "elapsed_time": "1:06:31", "remaining_time": "2:42:32"}
+{"current_steps": 319, "total_steps": 1095, "loss": 0.6826, "lr": 8.939508258477662e-06, "epoch": 0.8723792160437557, "percentage": 29.13, "elapsed_time": "1:06:42", "remaining_time": "2:42:16"}
+{"current_steps": 320, "total_steps": 1095, "loss": 0.7991, "lr": 8.92966795259726e-06, "epoch": 0.8751139471285324, "percentage": 29.22, "elapsed_time": "1:06:52", "remaining_time": "2:41:58"}
+{"current_steps": 321, "total_steps": 1095, "loss": 0.7267, "lr": 8.919787672241619e-06, "epoch": 0.877848678213309, "percentage": 29.32, "elapsed_time": "1:07:06", "remaining_time": "2:41:48"}
+{"current_steps": 322, "total_steps": 1095, "loss": 0.7754, "lr": 8.909867517917703e-06, "epoch": 0.8805834092980857, "percentage": 29.41, "elapsed_time": "1:07:17", "remaining_time": "2:41:33"}
+{"current_steps": 323, "total_steps": 1095, "loss": 0.7453, "lr": 8.899907590538106e-06, "epoch": 0.8833181403828624, "percentage": 29.5, "elapsed_time": "1:07:31", "remaining_time": "2:41:24"}
+{"current_steps": 324, "total_steps": 1095, "loss": 0.8389, "lr": 8.889907991420003e-06, "epoch": 0.886052871467639, "percentage": 29.59, "elapsed_time": "1:07:47", "remaining_time": "2:41:19"}
+{"current_steps": 325, "total_steps": 1095, "loss": 0.8601, "lr": 8.879868822284136e-06, "epoch": 0.8887876025524157, "percentage": 29.68, "elapsed_time": "1:08:02", "remaining_time": "2:41:11"}
+{"current_steps": 326, "total_steps": 1095, "loss": 0.7388, "lr": 8.869790185253766e-06, "epoch": 0.8915223336371924, "percentage": 29.77, "elapsed_time": "1:08:10", "remaining_time": "2:40:48"}
+{"current_steps": 327, "total_steps": 1095, "loss": 0.6596, "lr": 8.859672182853645e-06, "epoch": 0.894257064721969, "percentage": 29.86, "elapsed_time": "1:08:22", "remaining_time": "2:40:35"}
+{"current_steps": 328, "total_steps": 1095, "loss": 0.7041, "lr": 8.849514918008966e-06, "epoch": 0.8969917958067457, "percentage": 29.95, "elapsed_time": "1:08:31", "remaining_time": "2:40:14"}
+{"current_steps": 329, "total_steps": 1095, "loss": 0.718, "lr": 8.83931849404432e-06, "epoch": 0.8997265268915223, "percentage": 30.05, "elapsed_time": "1:08:43", "remaining_time": "2:40:01"}
+{"current_steps": 330, "total_steps": 1095, "loss": 0.7163, "lr": 8.829083014682645e-06, "epoch": 0.902461257976299, "percentage": 30.14, "elapsed_time": "1:08:51", "remaining_time": "2:39:37"}
+{"current_steps": 331, "total_steps": 1095, "loss": 0.6936, "lr": 8.818808584044163e-06, "epoch": 0.9051959890610757, "percentage": 30.23, "elapsed_time": "1:09:01", "remaining_time": "2:39:18"}
+{"current_steps": 332, "total_steps": 1095, "loss": 0.9616, "lr": 8.808495306645334e-06, "epoch": 0.9079307201458523, "percentage": 30.32, "elapsed_time": "1:09:22", "remaining_time": "2:39:26"}
+{"current_steps": 333, "total_steps": 1095, "loss": 0.7569, "lr": 8.798143287397785e-06, "epoch": 0.910665451230629, "percentage": 30.41, "elapsed_time": "1:09:38", "remaining_time": "2:39:22"}
+{"current_steps": 334, "total_steps": 1095, "loss": 0.697, "lr": 8.78775263160724e-06, "epoch": 0.9134001823154057, "percentage": 30.5, "elapsed_time": "1:09:48", "remaining_time": "2:39:04"}
+{"current_steps": 335, "total_steps": 1095, "loss": 0.776, "lr": 8.777323444972455e-06, "epoch": 0.9161349134001823, "percentage": 30.59, "elapsed_time": "1:10:06", "remaining_time": "2:39:01"}
+{"current_steps": 336, "total_steps": 1095, "loss": 0.7149, "lr": 8.76685583358414e-06, "epoch": 0.918869644484959, "percentage": 30.68, "elapsed_time": "1:10:20", "remaining_time": "2:38:53"}
+{"current_steps": 337, "total_steps": 1095, "loss": 0.8179, "lr": 8.75634990392388e-06, "epoch": 0.9216043755697356, "percentage": 30.78, "elapsed_time": "1:10:37", "remaining_time": "2:38:50"}
+{"current_steps": 338, "total_steps": 1095, "loss": 0.8005, "lr": 8.745805762863052e-06, "epoch": 0.9243391066545124, "percentage": 30.87, "elapsed_time": "1:10:52", "remaining_time": "2:38:43"}
+{"current_steps": 339, "total_steps": 1095, "loss": 0.8201, "lr": 8.735223517661735e-06, "epoch": 0.927073837739289, "percentage": 30.96, "elapsed_time": "1:10:59", "remaining_time": "2:38:19"}
+{"current_steps": 340, "total_steps": 1095, "loss": 0.7693, "lr": 8.72460327596763e-06, "epoch": 0.9298085688240656, "percentage": 31.05, "elapsed_time": "1:11:12", "remaining_time": "2:38:06"}
+{"current_steps": 341, "total_steps": 1095, "loss": 0.7168, "lr": 8.713945145814948e-06, "epoch": 0.9325432999088423, "percentage": 31.14, "elapsed_time": "1:11:23", "remaining_time": "2:37:50"}
+{"current_steps": 342, "total_steps": 1095, "loss": 0.8334, "lr": 8.703249235623321e-06, "epoch": 0.935278030993619, "percentage": 31.23, "elapsed_time": "1:11:39", "remaining_time": "2:37:46"}
+{"current_steps": 343, "total_steps": 1095, "loss": 1.1559, "lr": 8.692515654196703e-06, "epoch": 0.9380127620783957, "percentage": 31.32, "elapsed_time": "1:11:56", "remaining_time": "2:37:43"}
+{"current_steps": 344, "total_steps": 1095, "loss": 0.8115, "lr": 8.681744510722252e-06, "epoch": 0.9407474931631723, "percentage": 31.42, "elapsed_time": "1:12:07", "remaining_time": "2:37:27"}
+{"current_steps": 345, "total_steps": 1095, "loss": 0.6115, "lr": 8.670935914769228e-06, "epoch": 0.9434822242479489, "percentage": 31.51, "elapsed_time": "1:12:15", "remaining_time": "2:37:05"}
+{"current_steps": 346, "total_steps": 1095, "loss": 0.874, "lr": 8.660089976287875e-06, "epoch": 0.9462169553327257, "percentage": 31.6, "elapsed_time": "1:12:24", "remaining_time": "2:36:45"}
+{"current_steps": 347, "total_steps": 1095, "loss": 0.7171, "lr": 8.649206805608304e-06, "epoch": 0.9489516864175023, "percentage": 31.69, "elapsed_time": "1:12:35", "remaining_time": "2:36:29"}
+{"current_steps": 348, "total_steps": 1095, "loss": 0.9273, "lr": 8.638286513439372e-06, "epoch": 0.9516864175022789, "percentage": 31.78, "elapsed_time": "1:12:52", "remaining_time": "2:36:26"}
+{"current_steps": 349, "total_steps": 1095, "loss": 0.788, "lr": 8.627329210867545e-06, "epoch": 0.9544211485870556, "percentage": 31.87, "elapsed_time": "1:13:05", "remaining_time": "2:36:14"}
+{"current_steps": 350, "total_steps": 1095, "loss": 0.7793, "lr": 8.616335009355785e-06, "epoch": 0.9571558796718322, "percentage": 31.96, "elapsed_time": "1:13:17", "remaining_time": "2:35:59"}
+{"current_steps": 351, "total_steps": 1095, "loss": 0.8051, "lr": 8.60530402074241e-06, "epoch": 0.959890610756609, "percentage": 32.05, "elapsed_time": "1:13:32", "remaining_time": "2:35:53"}
+{"current_steps": 352, "total_steps": 1095, "loss": 0.8739, "lr": 8.594236357239945e-06, "epoch": 0.9626253418413856, "percentage": 32.15, "elapsed_time": "1:13:45", "remaining_time": "2:35:41"}
+{"current_steps": 353, "total_steps": 1095, "loss": 0.7062, "lr": 8.583132131433994e-06, "epoch": 0.9653600729261622, "percentage": 32.24, "elapsed_time": "1:14:00", "remaining_time": "2:35:34"}
+{"current_steps": 354, "total_steps": 1095, "loss": 0.7156, "lr": 8.571991456282092e-06, "epoch": 0.968094804010939, "percentage": 32.33, "elapsed_time": "1:14:17", "remaining_time": "2:35:30"}
+{"current_steps": 355, "total_steps": 1095, "loss": 0.6847, "lr": 8.560814445112552e-06, "epoch": 0.9708295350957156, "percentage": 32.42, "elapsed_time": "1:14:24", "remaining_time": "2:35:06"}
+{"current_steps": 356, "total_steps": 1095, "loss": 0.8822, "lr": 8.549601211623316e-06, "epoch": 0.9735642661804923, "percentage": 32.51, "elapsed_time": "1:14:39", "remaining_time": "2:34:59"}
+{"current_steps": 357, "total_steps": 1095, "loss": 0.8401, "lr": 8.538351869880796e-06, "epoch": 0.9762989972652689, "percentage": 32.6, "elapsed_time": "1:14:54", "remaining_time": "2:34:50"}
+{"current_steps": 358, "total_steps": 1095, "loss": 0.669, "lr": 8.527066534318716e-06, "epoch": 0.9790337283500455, "percentage": 32.69, "elapsed_time": "1:15:07", "remaining_time": "2:34:39"}
+{"current_steps": 359, "total_steps": 1095, "loss": 0.7982, "lr": 8.515745319736942e-06, "epoch": 0.9817684594348223, "percentage": 32.79, "elapsed_time": "1:15:24", "remaining_time": "2:34:36"}
+{"current_steps": 360, "total_steps": 1095, "loss": 0.7605, "lr": 8.504388341300325e-06, "epoch": 0.9845031905195989, "percentage": 32.88, "elapsed_time": "1:15:42", "remaining_time": "2:34:33"}
+{"current_steps": 361, "total_steps": 1095, "loss": 0.7417, "lr": 8.492995714537519e-06, "epoch": 0.9872379216043756, "percentage": 32.97, "elapsed_time": "1:15:53", "remaining_time": "2:34:18"}
+{"current_steps": 362, "total_steps": 1095, "loss": 0.8014, "lr": 8.48156755533981e-06, "epoch": 0.9899726526891522, "percentage": 33.06, "elapsed_time": "1:16:02", "remaining_time": "2:33:58"}
+{"current_steps": 363, "total_steps": 1095, "loss": 0.8308, "lr": 8.470103979959939e-06, "epoch": 0.9927073837739289, "percentage": 33.15, "elapsed_time": "1:16:17", "remaining_time": "2:33:49"}
+{"current_steps": 364, "total_steps": 1095, "loss": 0.842, "lr": 8.458605105010917e-06, "epoch": 0.9954421148587056, "percentage": 33.24, "elapsed_time": "1:16:28", "remaining_time": "2:33:34"}
+{"current_steps": 365, "total_steps": 1095, "loss": 0.8054, "lr": 8.44707104746484e-06, "epoch": 0.9981768459434822, "percentage": 33.33, "elapsed_time": "1:16:47", "remaining_time": "2:33:35"}
+{"current_steps": 366, "total_steps": 1095, "loss": 1.4458, "lr": 8.43550192465169e-06, "epoch": 1.0027347310847767, "percentage": 33.42, "elapsed_time": "1:17:03", "remaining_time": "2:33:28"}
+{"current_steps": 367, "total_steps": 1095, "loss": 0.6817, "lr": 8.423897854258166e-06, "epoch": 1.0054694621695532, "percentage": 33.52, "elapsed_time": "1:17:20", "remaining_time": "2:33:24"}
+{"current_steps": 368, "total_steps": 1095, "loss": 0.6156, "lr": 8.412258954326456e-06, "epoch": 1.00820419325433, "percentage": 33.61, "elapsed_time": "1:17:33", "remaining_time": "2:33:14"}
+{"current_steps": 369, "total_steps": 1095, "loss": 0.5555, "lr": 8.400585343253057e-06, "epoch": 1.0109389243391067, "percentage": 33.7, "elapsed_time": "1:17:45", "remaining_time": "2:32:58"}
+{"current_steps": 370, "total_steps": 1095, "loss": 0.7762, "lr": 8.388877139787567e-06, "epoch": 1.0136736554238832, "percentage": 33.79, "elapsed_time": "1:18:00", "remaining_time": "2:32:50"}
+{"current_steps": 371, "total_steps": 1095, "loss": 0.6686, "lr": 8.377134463031468e-06, "epoch": 1.01640838650866, "percentage": 33.88, "elapsed_time": "1:18:10", "remaining_time": "2:32:34"}
+{"current_steps": 372, "total_steps": 1095, "loss": 0.6178, "lr": 8.365357432436925e-06, "epoch": 1.0191431175934367, "percentage": 33.97, "elapsed_time": "1:18:22", "remaining_time": "2:32:19"}
+{"current_steps": 373, "total_steps": 1095, "loss": 0.6615, "lr": 8.353546167805565e-06, "epoch": 1.0218778486782134, "percentage": 34.06, "elapsed_time": "1:18:38", "remaining_time": "2:32:12"}
+{"current_steps": 374, "total_steps": 1095, "loss": 0.6748, "lr": 8.341700789287262e-06, "epoch": 1.02461257976299, "percentage": 34.16, "elapsed_time": "1:18:49", "remaining_time": "2:31:57"}
+{"current_steps": 375, "total_steps": 1095, "loss": 0.5632, "lr": 8.32982141737891e-06, "epoch": 1.0273473108477666, "percentage": 34.25, "elapsed_time": "1:19:01", "remaining_time": "2:31:42"}
+{"current_steps": 376, "total_steps": 1095, "loss": 0.6324, "lr": 8.317908172923207e-06, "epoch": 1.0300820419325434, "percentage": 34.34, "elapsed_time": "1:19:15", "remaining_time": "2:31:33"}
+{"current_steps": 377, "total_steps": 1095, "loss": 0.5983, "lr": 8.30596117710741e-06, "epoch": 1.03281677301732, "percentage": 34.43, "elapsed_time": "1:19:25", "remaining_time": "2:31:16"}
+{"current_steps": 378, "total_steps": 1095, "loss": 0.8019, "lr": 8.293980551462112e-06, "epoch": 1.0355515041020966, "percentage": 34.52, "elapsed_time": "1:19:36", "remaining_time": "2:31:00"}
+{"current_steps": 379, "total_steps": 1095, "loss": 0.6387, "lr": 8.281966417860015e-06, "epoch": 1.0382862351868734, "percentage": 34.61, "elapsed_time": "1:19:47", "remaining_time": "2:30:44"}
+{"current_steps": 380, "total_steps": 1095, "loss": 0.6094, "lr": 8.26991889851467e-06, "epoch": 1.0410209662716499, "percentage": 34.7, "elapsed_time": "1:19:56", "remaining_time": "2:30:25"}
+{"current_steps": 381, "total_steps": 1095, "loss": 0.6344, "lr": 8.257838115979244e-06, "epoch": 1.0437556973564266, "percentage": 34.79, "elapsed_time": "1:20:07", "remaining_time": "2:30:08"}
+{"current_steps": 382, "total_steps": 1095, "loss": 0.5657, "lr": 8.245724193145281e-06, "epoch": 1.0464904284412033, "percentage": 34.89, "elapsed_time": "1:20:17", "remaining_time": "2:29:52"}
+{"current_steps": 383, "total_steps": 1095, "loss": 0.575, "lr": 8.233577253241434e-06, "epoch": 1.0492251595259798, "percentage": 34.98, "elapsed_time": "1:20:28", "remaining_time": "2:29:35"}
+{"current_steps": 384, "total_steps": 1095, "loss": 0.7274, "lr": 8.221397419832232e-06, "epoch": 1.0519598906107566, "percentage": 35.07, "elapsed_time": "1:20:43", "remaining_time": "2:29:27"}
+{"current_steps": 385, "total_steps": 1095, "loss": 0.5482, "lr": 8.209184816816799e-06, "epoch": 1.0546946216955333, "percentage": 35.16, "elapsed_time": "1:20:53", "remaining_time": "2:29:09"}
+{"current_steps": 386, "total_steps": 1095, "loss": 0.6191, "lr": 8.196939568427624e-06, "epoch": 1.05742935278031, "percentage": 35.25, "elapsed_time": "1:21:01", "remaining_time": "2:28:48"}
+{"current_steps": 387, "total_steps": 1095, "loss": 0.5733, "lr": 8.184661799229267e-06, "epoch": 1.0601640838650865, "percentage": 35.34, "elapsed_time": "1:21:13", "remaining_time": "2:28:35"}
+{"current_steps": 388, "total_steps": 1095, "loss": 0.6275, "lr": 8.172351634117114e-06, "epoch": 1.0628988149498633, "percentage": 35.43, "elapsed_time": "1:21:27", "remaining_time": "2:28:25"}
+{"current_steps": 389, "total_steps": 1095, "loss": 0.5984, "lr": 8.16000919831609e-06, "epoch": 1.06563354603464, "percentage": 35.53, "elapsed_time": "1:21:38", "remaining_time": "2:28:10"}
+{"current_steps": 390, "total_steps": 1095, "loss": 0.7034, "lr": 8.147634617379399e-06, "epoch": 1.0683682771194165, "percentage": 35.62, "elapsed_time": "1:21:48", "remaining_time": "2:27:53"}
+{"current_steps": 391, "total_steps": 1095, "loss": 0.5941, "lr": 8.135228017187238e-06, "epoch": 1.0711030082041932, "percentage": 35.71, "elapsed_time": "1:22:06", "remaining_time": "2:27:50"}
+{"current_steps": 392, "total_steps": 1095, "loss": 0.5898, "lr": 8.12278952394552e-06, "epoch": 1.07383773928897, "percentage": 35.8, "elapsed_time": "1:22:16", "remaining_time": "2:27:32"}
+{"current_steps": 393, "total_steps": 1095, "loss": 0.6688, "lr": 8.110319264184592e-06, "epoch": 1.0765724703737465, "percentage": 35.89, "elapsed_time": "1:22:27", "remaining_time": "2:27:17"}
+{"current_steps": 394, "total_steps": 1095, "loss": 0.6092, "lr": 8.09781736475794e-06, "epoch": 1.0793072014585232, "percentage": 35.98, "elapsed_time": "1:22:41", "remaining_time": "2:27:07"}
+{"current_steps": 395, "total_steps": 1095, "loss": 0.7174, "lr": 8.085283952840907e-06, "epoch": 1.0820419325433, "percentage": 36.07, "elapsed_time": "1:23:00", "remaining_time": "2:27:05"}
+{"current_steps": 396, "total_steps": 1095, "loss": 0.5854, "lr": 8.0727191559294e-06, "epoch": 1.0847766636280767, "percentage": 36.16, "elapsed_time": "1:23:13", "remaining_time": "2:26:54"}
+{"current_steps": 397, "total_steps": 1095, "loss": 0.7157, "lr": 8.060123101838579e-06, "epoch": 1.0875113947128532, "percentage": 36.26, "elapsed_time": "1:23:27", "remaining_time": "2:26:44"}
+{"current_steps": 398, "total_steps": 1095, "loss": 0.6762, "lr": 8.047495918701577e-06, "epoch": 1.09024612579763, "percentage": 36.35, "elapsed_time": "1:23:38", "remaining_time": "2:26:28"}
+{"current_steps": 399, "total_steps": 1095, "loss": 0.5785, "lr": 8.034837734968185e-06, "epoch": 1.0929808568824066, "percentage": 36.44, "elapsed_time": "1:23:52", "remaining_time": "2:26:17"}
+{"current_steps": 400, "total_steps": 1095, "loss": 0.664, "lr": 8.022148679403543e-06, "epoch": 1.0957155879671832, "percentage": 36.53, "elapsed_time": "1:24:17", "remaining_time": "2:26:27"}
+{"current_steps": 401, "total_steps": 1095, "loss": 0.6431, "lr": 8.009428881086836e-06, "epoch": 1.09845031905196, "percentage": 36.62, "elapsed_time": "1:26:08", "remaining_time": "2:29:04"}
+{"current_steps": 402, "total_steps": 1095, "loss": 0.6909, "lr": 7.996678469409978e-06, "epoch": 1.1011850501367366, "percentage": 36.71, "elapsed_time": "1:26:22", "remaining_time": "2:28:53"}
+{"current_steps": 403, "total_steps": 1095, "loss": 0.6168, "lr": 7.9838975740763e-06, "epoch": 1.1039197812215131, "percentage": 36.8, "elapsed_time": "1:26:38", "remaining_time": "2:28:45"}
+{"current_steps": 404, "total_steps": 1095, "loss": 0.749, "lr": 7.971086325099227e-06, "epoch": 1.1066545123062899, "percentage": 36.89, "elapsed_time": "1:26:48", "remaining_time": "2:28:29"}
+{"current_steps": 405, "total_steps": 1095, "loss": 0.679, "lr": 7.958244852800952e-06, "epoch": 1.1093892433910666, "percentage": 36.99, "elapsed_time": "1:26:59", "remaining_time": "2:28:13"}
+{"current_steps": 406, "total_steps": 1095, "loss": 0.8351, "lr": 7.945373287811116e-06, "epoch": 1.112123974475843, "percentage": 37.08, "elapsed_time": "1:27:16", "remaining_time": "2:28:06"}
+{"current_steps": 407, "total_steps": 1095, "loss": 0.6137, "lr": 7.93247176106548e-06, "epoch": 1.1148587055606198, "percentage": 37.17, "elapsed_time": "1:27:28", "remaining_time": "2:27:52"}
+{"current_steps": 408, "total_steps": 1095, "loss": 0.7159, "lr": 7.91954040380459e-06, "epoch": 1.1175934366453966, "percentage": 37.26, "elapsed_time": "1:27:38", "remaining_time": "2:27:35"}
+{"current_steps": 409, "total_steps": 1095, "loss": 0.589, "lr": 7.906579347572434e-06, "epoch": 1.1203281677301733, "percentage": 37.35, "elapsed_time": "1:27:50", "remaining_time": "2:27:20"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b51073cd9b22f0b2090401cb8f14133b0ef3a95e4fb068def97ba13b5f0e2408
+size 7864