Training in progress, epoch 0

.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 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "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 sha256:102e23b09a4fba88b323da5eff74be9607b73d0114a97034bf2d1f4030b51d3d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21079eac4e48fcfc9ae093080f14e6c9c10ab95579fde7c42d9c39634cd9b7aa
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a48c9d4fc70f92b570d44077942170f37b046b4b3f72b2b18b86c68a8afbc6c
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a7fe44a24ba95139bdf99aa8ff12a86ef573a21998015433659d23d01e6fd9
+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": "<|endoftext|>",
+    "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 +1,208 @@
+{
+  "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": "<|endoftext|>",
+  "errors": "replace",
+  "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 +1,250 @@
+{"current_steps": 1, "total_steps": 1230, "loss": 1.0514, "lr": 3.2520325203252037e-07, "epoch": 0.004052684903748734, "percentage": 0.08, "elapsed_time": "0:00:52", "remaining_time": "17:49:45"}
+{"current_steps": 2, "total_steps": 1230, "loss": 1.0362, "lr": 6.504065040650407e-07, "epoch": 0.008105369807497468, "percentage": 0.16, "elapsed_time": "0:01:37", "remaining_time": "16:39:10"}
+{"current_steps": 3, "total_steps": 1230, "loss": 1.0544, "lr": 9.75609756097561e-07, "epoch": 0.0121580547112462, "percentage": 0.24, "elapsed_time": "0:02:21", "remaining_time": "16:07:39"}
+{"current_steps": 4, "total_steps": 1230, "loss": 1.0401, "lr": 1.3008130081300815e-06, "epoch": 0.016210739614994935, "percentage": 0.33, "elapsed_time": "0:03:05", "remaining_time": "15:46:11"}
+{"current_steps": 5, "total_steps": 1230, "loss": 1.042, "lr": 1.6260162601626018e-06, "epoch": 0.020263424518743668, "percentage": 0.41, "elapsed_time": "0:03:50", "remaining_time": "15:39:15"}
+{"current_steps": 6, "total_steps": 1230, "loss": 1.039, "lr": 1.951219512195122e-06, "epoch": 0.0243161094224924, "percentage": 0.49, "elapsed_time": "0:04:32", "remaining_time": "15:27:17"}
+{"current_steps": 7, "total_steps": 1230, "loss": 0.9873, "lr": 2.2764227642276426e-06, "epoch": 0.028368794326241134, "percentage": 0.57, "elapsed_time": "0:05:13", "remaining_time": "15:12:07"}
+{"current_steps": 8, "total_steps": 1230, "loss": 1.0035, "lr": 2.601626016260163e-06, "epoch": 0.03242147922998987, "percentage": 0.65, "elapsed_time": "0:05:56", "remaining_time": "15:08:45"}
+{"current_steps": 9, "total_steps": 1230, "loss": 0.9471, "lr": 2.926829268292683e-06, "epoch": 0.0364741641337386, "percentage": 0.73, "elapsed_time": "0:06:40", "remaining_time": "15:04:32"}
+{"current_steps": 10, "total_steps": 1230, "loss": 0.9319, "lr": 3.2520325203252037e-06, "epoch": 0.040526849037487336, "percentage": 0.81, "elapsed_time": "0:07:22", "remaining_time": "14:59:27"}
+{"current_steps": 11, "total_steps": 1230, "loss": 0.9467, "lr": 3.577235772357724e-06, "epoch": 0.044579533941236066, "percentage": 0.89, "elapsed_time": "0:08:08", "remaining_time": "15:02:52"}
+{"current_steps": 12, "total_steps": 1230, "loss": 0.9029, "lr": 3.902439024390244e-06, "epoch": 0.0486322188449848, "percentage": 0.98, "elapsed_time": "0:08:48", "remaining_time": "14:53:22"}
+{"current_steps": 13, "total_steps": 1230, "loss": 0.924, "lr": 4.227642276422765e-06, "epoch": 0.05268490374873354, "percentage": 1.06, "elapsed_time": "0:09:29", "remaining_time": "14:49:07"}
+{"current_steps": 14, "total_steps": 1230, "loss": 0.9197, "lr": 4.552845528455285e-06, "epoch": 0.05673758865248227, "percentage": 1.14, "elapsed_time": "0:10:15", "remaining_time": "14:51:13"}
+{"current_steps": 15, "total_steps": 1230, "loss": 0.8887, "lr": 4.8780487804878055e-06, "epoch": 0.060790273556231005, "percentage": 1.22, "elapsed_time": "0:10:57", "remaining_time": "14:48:09"}
+{"current_steps": 16, "total_steps": 1230, "loss": 0.8642, "lr": 5.203252032520326e-06, "epoch": 0.06484295845997974, "percentage": 1.3, "elapsed_time": "0:11:40", "remaining_time": "14:46:18"}
+{"current_steps": 17, "total_steps": 1230, "loss": 0.839, "lr": 5.528455284552846e-06, "epoch": 0.06889564336372847, "percentage": 1.38, "elapsed_time": "0:12:25", "remaining_time": "14:46:24"}
+{"current_steps": 18, "total_steps": 1230, "loss": 0.8238, "lr": 5.853658536585366e-06, "epoch": 0.0729483282674772, "percentage": 1.46, "elapsed_time": "0:13:10", "remaining_time": "14:46:56"}
+{"current_steps": 19, "total_steps": 1230, "loss": 0.8125, "lr": 6.178861788617887e-06, "epoch": 0.07700101317122594, "percentage": 1.54, "elapsed_time": "0:13:53", "remaining_time": "14:45:20"}
+{"current_steps": 20, "total_steps": 1230, "loss": 0.7996, "lr": 6.504065040650407e-06, "epoch": 0.08105369807497467, "percentage": 1.63, "elapsed_time": "0:14:35", "remaining_time": "14:43:12"}
+{"current_steps": 21, "total_steps": 1230, "loss": 0.791, "lr": 6.829268292682928e-06, "epoch": 0.0851063829787234, "percentage": 1.71, "elapsed_time": "0:15:16", "remaining_time": "14:39:49"}
+{"current_steps": 22, "total_steps": 1230, "loss": 0.7845, "lr": 7.154471544715448e-06, "epoch": 0.08915906788247213, "percentage": 1.79, "elapsed_time": "0:15:59", "remaining_time": "14:38:00"}
+{"current_steps": 23, "total_steps": 1230, "loss": 0.7643, "lr": 7.4796747967479676e-06, "epoch": 0.09321175278622088, "percentage": 1.87, "elapsed_time": "0:16:41", "remaining_time": "14:35:47"}
+{"current_steps": 24, "total_steps": 1230, "loss": 0.7651, "lr": 7.804878048780489e-06, "epoch": 0.0972644376899696, "percentage": 1.95, "elapsed_time": "0:17:21", "remaining_time": "14:32:26"}
+{"current_steps": 25, "total_steps": 1230, "loss": 0.7303, "lr": 8.130081300813009e-06, "epoch": 0.10131712259371833, "percentage": 2.03, "elapsed_time": "0:18:06", "remaining_time": "14:32:35"}
+{"current_steps": 26, "total_steps": 1230, "loss": 0.7368, "lr": 8.45528455284553e-06, "epoch": 0.10536980749746708, "percentage": 2.11, "elapsed_time": "0:18:45", "remaining_time": "14:28:22"}
+{"current_steps": 27, "total_steps": 1230, "loss": 0.7253, "lr": 8.78048780487805e-06, "epoch": 0.1094224924012158, "percentage": 2.2, "elapsed_time": "0:19:28", "remaining_time": "14:27:38"}
+{"current_steps": 28, "total_steps": 1230, "loss": 0.7189, "lr": 9.10569105691057e-06, "epoch": 0.11347517730496454, "percentage": 2.28, "elapsed_time": "0:20:12", "remaining_time": "14:27:45"}
+{"current_steps": 29, "total_steps": 1230, "loss": 0.7207, "lr": 9.43089430894309e-06, "epoch": 0.11752786220871327, "percentage": 2.36, "elapsed_time": "0:20:56", "remaining_time": "14:27:01"}
+{"current_steps": 30, "total_steps": 1230, "loss": 0.7194, "lr": 9.756097560975611e-06, "epoch": 0.12158054711246201, "percentage": 2.44, "elapsed_time": "0:21:39", "remaining_time": "14:26:19"}
+{"current_steps": 31, "total_steps": 1230, "loss": 0.7013, "lr": 1.008130081300813e-05, "epoch": 0.12563323201621074, "percentage": 2.52, "elapsed_time": "0:22:25", "remaining_time": "14:27:06"}
+{"current_steps": 32, "total_steps": 1230, "loss": 0.7167, "lr": 1.0406504065040652e-05, "epoch": 0.12968591691995948, "percentage": 2.6, "elapsed_time": "0:23:08", "remaining_time": "14:26:34"}
+{"current_steps": 33, "total_steps": 1230, "loss": 0.7171, "lr": 1.0731707317073172e-05, "epoch": 0.1337386018237082, "percentage": 2.68, "elapsed_time": "0:23:50", "remaining_time": "14:24:53"}
+{"current_steps": 34, "total_steps": 1230, "loss": 0.6808, "lr": 1.1056910569105692e-05, "epoch": 0.13779128672745694, "percentage": 2.76, "elapsed_time": "0:24:33", "remaining_time": "14:24:03"}
+{"current_steps": 35, "total_steps": 1230, "loss": 0.6799, "lr": 1.1382113821138213e-05, "epoch": 0.14184397163120568, "percentage": 2.85, "elapsed_time": "0:25:17", "remaining_time": "14:23:48"}
+{"current_steps": 36, "total_steps": 1230, "loss": 0.6916, "lr": 1.1707317073170731e-05, "epoch": 0.1458966565349544, "percentage": 2.93, "elapsed_time": "0:26:02", "remaining_time": "14:23:44"}
+{"current_steps": 37, "total_steps": 1230, "loss": 0.6841, "lr": 1.2032520325203254e-05, "epoch": 0.14994934143870314, "percentage": 3.01, "elapsed_time": "0:26:44", "remaining_time": "14:22:19"}
+{"current_steps": 38, "total_steps": 1230, "loss": 0.678, "lr": 1.2357723577235774e-05, "epoch": 0.1540020263424519, "percentage": 3.09, "elapsed_time": "0:27:23", "remaining_time": "14:19:10"}
+{"current_steps": 39, "total_steps": 1230, "loss": 0.6889, "lr": 1.2682926829268294e-05, "epoch": 0.1580547112462006, "percentage": 3.17, "elapsed_time": "0:28:07", "remaining_time": "14:18:38"}
+{"current_steps": 40, "total_steps": 1230, "loss": 0.6842, "lr": 1.3008130081300815e-05, "epoch": 0.16210739614994935, "percentage": 3.25, "elapsed_time": "0:28:51", "remaining_time": "14:18:26"}
+{"current_steps": 41, "total_steps": 1230, "loss": 0.6668, "lr": 1.3333333333333333e-05, "epoch": 0.1661600810536981, "percentage": 3.33, "elapsed_time": "0:29:32", "remaining_time": "14:16:48"}
+{"current_steps": 42, "total_steps": 1230, "loss": 0.652, "lr": 1.3658536585365855e-05, "epoch": 0.1702127659574468, "percentage": 3.41, "elapsed_time": "0:30:14", "remaining_time": "14:15:36"}
+{"current_steps": 43, "total_steps": 1230, "loss": 0.6664, "lr": 1.3983739837398376e-05, "epoch": 0.17426545086119555, "percentage": 3.5, "elapsed_time": "0:30:57", "remaining_time": "14:14:27"}
+{"current_steps": 44, "total_steps": 1230, "loss": 0.6611, "lr": 1.4308943089430896e-05, "epoch": 0.17831813576494426, "percentage": 3.58, "elapsed_time": "0:31:40", "remaining_time": "14:13:42"}
+{"current_steps": 45, "total_steps": 1230, "loss": 0.6501, "lr": 1.4634146341463415e-05, "epoch": 0.182370820668693, "percentage": 3.66, "elapsed_time": "0:32:22", "remaining_time": "14:12:41"}
+{"current_steps": 46, "total_steps": 1230, "loss": 0.6579, "lr": 1.4959349593495935e-05, "epoch": 0.18642350557244175, "percentage": 3.74, "elapsed_time": "0:33:06", "remaining_time": "14:12:12"}
+{"current_steps": 47, "total_steps": 1230, "loss": 0.6634, "lr": 1.528455284552846e-05, "epoch": 0.19047619047619047, "percentage": 3.82, "elapsed_time": "0:33:49", "remaining_time": "14:11:29"}
+{"current_steps": 48, "total_steps": 1230, "loss": 0.6487, "lr": 1.5609756097560978e-05, "epoch": 0.1945288753799392, "percentage": 3.9, "elapsed_time": "0:34:34", "remaining_time": "14:11:21"}
+{"current_steps": 49, "total_steps": 1230, "loss": 0.6578, "lr": 1.5934959349593496e-05, "epoch": 0.19858156028368795, "percentage": 3.98, "elapsed_time": "0:35:17", "remaining_time": "14:10:39"}
+{"current_steps": 50, "total_steps": 1230, "loss": 0.6503, "lr": 1.6260162601626018e-05, "epoch": 0.20263424518743667, "percentage": 4.07, "elapsed_time": "0:36:01", "remaining_time": "14:10:15"}
+{"current_steps": 51, "total_steps": 1230, "loss": 0.6696, "lr": 1.6585365853658537e-05, "epoch": 0.2066869300911854, "percentage": 4.15, "elapsed_time": "0:36:44", "remaining_time": "14:09:26"}
+{"current_steps": 52, "total_steps": 1230, "loss": 0.6517, "lr": 1.691056910569106e-05, "epoch": 0.21073961499493415, "percentage": 4.23, "elapsed_time": "0:37:27", "remaining_time": "14:08:30"}
+{"current_steps": 53, "total_steps": 1230, "loss": 0.6511, "lr": 1.7235772357723578e-05, "epoch": 0.21479229989868287, "percentage": 4.31, "elapsed_time": "0:38:10", "remaining_time": "14:07:39"}
+{"current_steps": 54, "total_steps": 1230, "loss": 0.6513, "lr": 1.75609756097561e-05, "epoch": 0.2188449848024316, "percentage": 4.39, "elapsed_time": "0:38:55", "remaining_time": "14:07:39"}
+{"current_steps": 55, "total_steps": 1230, "loss": 0.6578, "lr": 1.788617886178862e-05, "epoch": 0.22289766970618036, "percentage": 4.47, "elapsed_time": "0:39:39", "remaining_time": "14:07:22"}
+{"current_steps": 56, "total_steps": 1230, "loss": 0.6411, "lr": 1.821138211382114e-05, "epoch": 0.22695035460992907, "percentage": 4.55, "elapsed_time": "0:40:23", "remaining_time": "14:06:49"}
+{"current_steps": 57, "total_steps": 1230, "loss": 0.6364, "lr": 1.8536585365853663e-05, "epoch": 0.23100303951367782, "percentage": 4.63, "elapsed_time": "0:41:04", "remaining_time": "14:05:11"}
+{"current_steps": 58, "total_steps": 1230, "loss": 0.6445, "lr": 1.886178861788618e-05, "epoch": 0.23505572441742653, "percentage": 4.72, "elapsed_time": "0:41:49", "remaining_time": "14:05:04"}
+{"current_steps": 59, "total_steps": 1230, "loss": 0.6467, "lr": 1.91869918699187e-05, "epoch": 0.23910840932117527, "percentage": 4.8, "elapsed_time": "0:42:32", "remaining_time": "14:04:24"}
+{"current_steps": 60, "total_steps": 1230, "loss": 0.6444, "lr": 1.9512195121951222e-05, "epoch": 0.24316109422492402, "percentage": 4.88, "elapsed_time": "0:43:16", "remaining_time": "14:03:51"}
+{"current_steps": 61, "total_steps": 1230, "loss": 0.6325, "lr": 1.983739837398374e-05, "epoch": 0.24721377912867273, "percentage": 4.96, "elapsed_time": "0:43:57", "remaining_time": "14:02:28"}
+{"current_steps": 62, "total_steps": 1230, "loss": 0.6362, "lr": 2.016260162601626e-05, "epoch": 0.2512664640324215, "percentage": 5.04, "elapsed_time": "0:44:39", "remaining_time": "14:01:26"}
+{"current_steps": 63, "total_steps": 1230, "loss": 0.6275, "lr": 2.048780487804878e-05, "epoch": 0.2553191489361702, "percentage": 5.12, "elapsed_time": "0:45:21", "remaining_time": "14:00:17"}
+{"current_steps": 64, "total_steps": 1230, "loss": 0.6435, "lr": 2.0813008130081303e-05, "epoch": 0.25937183383991896, "percentage": 5.2, "elapsed_time": "0:46:03", "remaining_time": "13:59:01"}
+{"current_steps": 65, "total_steps": 1230, "loss": 0.6449, "lr": 2.1138211382113822e-05, "epoch": 0.2634245187436677, "percentage": 5.28, "elapsed_time": "0:46:46", "remaining_time": "13:58:23"}
+{"current_steps": 66, "total_steps": 1230, "loss": 0.6305, "lr": 2.1463414634146344e-05, "epoch": 0.2674772036474164, "percentage": 5.37, "elapsed_time": "0:47:29", "remaining_time": "13:57:31"}
+{"current_steps": 67, "total_steps": 1230, "loss": 0.6267, "lr": 2.1788617886178863e-05, "epoch": 0.27152988855116517, "percentage": 5.45, "elapsed_time": "0:48:11", "remaining_time": "13:56:37"}
+{"current_steps": 68, "total_steps": 1230, "loss": 0.6296, "lr": 2.2113821138211385e-05, "epoch": 0.2755825734549139, "percentage": 5.53, "elapsed_time": "0:48:57", "remaining_time": "13:56:42"}
+{"current_steps": 69, "total_steps": 1230, "loss": 0.6344, "lr": 2.2439024390243907e-05, "epoch": 0.2796352583586626, "percentage": 5.61, "elapsed_time": "0:49:41", "remaining_time": "13:56:07"}
+{"current_steps": 70, "total_steps": 1230, "loss": 0.6243, "lr": 2.2764227642276426e-05, "epoch": 0.28368794326241137, "percentage": 5.69, "elapsed_time": "0:50:24", "remaining_time": "13:55:23"}
+{"current_steps": 71, "total_steps": 1230, "loss": 0.6159, "lr": 2.3089430894308948e-05, "epoch": 0.2877406281661601, "percentage": 5.77, "elapsed_time": "0:51:03", "remaining_time": "13:53:35"}
+{"current_steps": 72, "total_steps": 1230, "loss": 0.6083, "lr": 2.3414634146341463e-05, "epoch": 0.2917933130699088, "percentage": 5.85, "elapsed_time": "0:51:46", "remaining_time": "13:52:50"}
+{"current_steps": 73, "total_steps": 1230, "loss": 0.6276, "lr": 2.3739837398373985e-05, "epoch": 0.29584599797365757, "percentage": 5.93, "elapsed_time": "0:52:28", "remaining_time": "13:51:45"}
+{"current_steps": 74, "total_steps": 1230, "loss": 0.6129, "lr": 2.4065040650406507e-05, "epoch": 0.2998986828774063, "percentage": 6.02, "elapsed_time": "0:53:12", "remaining_time": "13:51:17"}
+{"current_steps": 75, "total_steps": 1230, "loss": 0.6236, "lr": 2.4390243902439026e-05, "epoch": 0.303951367781155, "percentage": 6.1, "elapsed_time": "0:53:56", "remaining_time": "13:50:43"}
+{"current_steps": 76, "total_steps": 1230, "loss": 0.6263, "lr": 2.4715447154471548e-05, "epoch": 0.3080040526849038, "percentage": 6.18, "elapsed_time": "0:54:40", "remaining_time": "13:50:18"}
+{"current_steps": 77, "total_steps": 1230, "loss": 0.6229, "lr": 2.5040650406504066e-05, "epoch": 0.3120567375886525, "percentage": 6.26, "elapsed_time": "0:55:24", "remaining_time": "13:49:38"}
+{"current_steps": 78, "total_steps": 1230, "loss": 0.6155, "lr": 2.536585365853659e-05, "epoch": 0.3161094224924012, "percentage": 6.34, "elapsed_time": "0:56:08", "remaining_time": "13:49:03"}
+{"current_steps": 79, "total_steps": 1230, "loss": 0.6137, "lr": 2.569105691056911e-05, "epoch": 0.32016210739615, "percentage": 6.42, "elapsed_time": "0:56:49", "remaining_time": "13:47:58"}
+{"current_steps": 80, "total_steps": 1230, "loss": 0.6111, "lr": 2.601626016260163e-05, "epoch": 0.3242147922998987, "percentage": 6.5, "elapsed_time": "0:57:33", "remaining_time": "13:47:30"}
+{"current_steps": 81, "total_steps": 1230, "loss": 0.6187, "lr": 2.634146341463415e-05, "epoch": 0.3282674772036474, "percentage": 6.59, "elapsed_time": "0:58:19", "remaining_time": "13:47:20"}
+{"current_steps": 82, "total_steps": 1230, "loss": 0.6168, "lr": 2.6666666666666667e-05, "epoch": 0.3323201621073962, "percentage": 6.67, "elapsed_time": "0:59:03", "remaining_time": "13:46:55"}
+{"current_steps": 83, "total_steps": 1230, "loss": 0.6119, "lr": 2.699186991869919e-05, "epoch": 0.3363728470111449, "percentage": 6.75, "elapsed_time": "0:59:48", "remaining_time": "13:46:23"}
+{"current_steps": 84, "total_steps": 1230, "loss": 0.6123, "lr": 2.731707317073171e-05, "epoch": 0.3404255319148936, "percentage": 6.83, "elapsed_time": "1:00:29", "remaining_time": "13:45:18"}
+{"current_steps": 85, "total_steps": 1230, "loss": 0.6202, "lr": 2.764227642276423e-05, "epoch": 0.3444782168186423, "percentage": 6.91, "elapsed_time": "1:01:14", "remaining_time": "13:44:57"}
+{"current_steps": 86, "total_steps": 1230, "loss": 0.6287, "lr": 2.796747967479675e-05, "epoch": 0.3485309017223911, "percentage": 6.99, "elapsed_time": "1:01:55", "remaining_time": "13:43:41"}
+{"current_steps": 87, "total_steps": 1230, "loss": 0.604, "lr": 2.829268292682927e-05, "epoch": 0.3525835866261398, "percentage": 7.07, "elapsed_time": "1:02:37", "remaining_time": "13:42:40"}
+{"current_steps": 88, "total_steps": 1230, "loss": 0.609, "lr": 2.8617886178861792e-05, "epoch": 0.3566362715298885, "percentage": 7.15, "elapsed_time": "1:03:24", "remaining_time": "13:42:58"}
+{"current_steps": 89, "total_steps": 1230, "loss": 0.6166, "lr": 2.8943089430894314e-05, "epoch": 0.3606889564336373, "percentage": 7.24, "elapsed_time": "1:04:09", "remaining_time": "13:42:35"}
+{"current_steps": 90, "total_steps": 1230, "loss": 0.6205, "lr": 2.926829268292683e-05, "epoch": 0.364741641337386, "percentage": 7.32, "elapsed_time": "1:04:52", "remaining_time": "13:41:44"}
+{"current_steps": 91, "total_steps": 1230, "loss": 0.6038, "lr": 2.959349593495935e-05, "epoch": 0.36879432624113473, "percentage": 7.4, "elapsed_time": "1:05:37", "remaining_time": "13:41:24"}
+{"current_steps": 92, "total_steps": 1230, "loss": 0.5924, "lr": 2.991869918699187e-05, "epoch": 0.3728470111448835, "percentage": 7.48, "elapsed_time": "1:06:21", "remaining_time": "13:40:55"}
+{"current_steps": 93, "total_steps": 1230, "loss": 0.5966, "lr": 3.0243902439024392e-05, "epoch": 0.3768996960486322, "percentage": 7.56, "elapsed_time": "1:07:06", "remaining_time": "13:40:24"}
+{"current_steps": 94, "total_steps": 1230, "loss": 0.6025, "lr": 3.056910569105692e-05, "epoch": 0.38095238095238093, "percentage": 7.64, "elapsed_time": "1:07:50", "remaining_time": "13:39:54"}
+{"current_steps": 95, "total_steps": 1230, "loss": 0.6155, "lr": 3.089430894308943e-05, "epoch": 0.3850050658561297, "percentage": 7.72, "elapsed_time": "1:08:34", "remaining_time": "13:39:18"}
+{"current_steps": 96, "total_steps": 1230, "loss": 0.6034, "lr": 3.1219512195121955e-05, "epoch": 0.3890577507598784, "percentage": 7.8, "elapsed_time": "1:09:13", "remaining_time": "13:37:37"}
+{"current_steps": 97, "total_steps": 1230, "loss": 0.608, "lr": 3.154471544715447e-05, "epoch": 0.39311043566362713, "percentage": 7.89, "elapsed_time": "1:09:58", "remaining_time": "13:37:17"}
+{"current_steps": 98, "total_steps": 1230, "loss": 0.6009, "lr": 3.186991869918699e-05, "epoch": 0.3971631205673759, "percentage": 7.97, "elapsed_time": "1:10:39", "remaining_time": "13:36:13"}
+{"current_steps": 99, "total_steps": 1230, "loss": 0.6145, "lr": 3.2195121951219514e-05, "epoch": 0.4012158054711246, "percentage": 8.05, "elapsed_time": "1:11:25", "remaining_time": "13:35:56"}
+{"current_steps": 100, "total_steps": 1230, "loss": 0.6165, "lr": 3.2520325203252037e-05, "epoch": 0.40526849037487334, "percentage": 8.13, "elapsed_time": "1:12:12", "remaining_time": "13:35:57"}
+{"current_steps": 101, "total_steps": 1230, "loss": 0.6121, "lr": 3.284552845528456e-05, "epoch": 0.4093211752786221, "percentage": 8.21, "elapsed_time": "1:12:54", "remaining_time": "13:34:55"}
+{"current_steps": 102, "total_steps": 1230, "loss": 0.608, "lr": 3.3170731707317074e-05, "epoch": 0.4133738601823708, "percentage": 8.29, "elapsed_time": "1:13:38", "remaining_time": "13:34:22"}
+{"current_steps": 103, "total_steps": 1230, "loss": 0.607, "lr": 3.3495934959349596e-05, "epoch": 0.41742654508611954, "percentage": 8.37, "elapsed_time": "1:14:22", "remaining_time": "13:33:50"}
+{"current_steps": 104, "total_steps": 1230, "loss": 0.611, "lr": 3.382113821138212e-05, "epoch": 0.4214792299898683, "percentage": 8.46, "elapsed_time": "1:15:05", "remaining_time": "13:33:01"}
+{"current_steps": 105, "total_steps": 1230, "loss": 0.6119, "lr": 3.414634146341463e-05, "epoch": 0.425531914893617, "percentage": 8.54, "elapsed_time": "1:15:50", "remaining_time": "13:32:30"}
+{"current_steps": 106, "total_steps": 1230, "loss": 0.5882, "lr": 3.4471544715447155e-05, "epoch": 0.42958459979736574, "percentage": 8.62, "elapsed_time": "1:16:29", "remaining_time": "13:31:10"}
+{"current_steps": 107, "total_steps": 1230, "loss": 0.6032, "lr": 3.479674796747968e-05, "epoch": 0.4336372847011145, "percentage": 8.7, "elapsed_time": "1:17:11", "remaining_time": "13:30:04"}
+{"current_steps": 108, "total_steps": 1230, "loss": 0.5977, "lr": 3.51219512195122e-05, "epoch": 0.4376899696048632, "percentage": 8.78, "elapsed_time": "1:17:53", "remaining_time": "13:29:10"}
+{"current_steps": 109, "total_steps": 1230, "loss": 0.6193, "lr": 3.544715447154472e-05, "epoch": 0.44174265450861194, "percentage": 8.86, "elapsed_time": "1:18:36", "remaining_time": "13:28:29"}
+{"current_steps": 110, "total_steps": 1230, "loss": 0.6133, "lr": 3.577235772357724e-05, "epoch": 0.4457953394123607, "percentage": 8.94, "elapsed_time": "1:19:18", "remaining_time": "13:27:30"}
+{"current_steps": 111, "total_steps": 1230, "loss": 0.6137, "lr": 3.609756097560976e-05, "epoch": 0.44984802431610943, "percentage": 9.02, "elapsed_time": "1:20:01", "remaining_time": "13:26:44"}
+{"current_steps": 112, "total_steps": 1230, "loss": 0.6036, "lr": 3.642276422764228e-05, "epoch": 0.45390070921985815, "percentage": 9.11, "elapsed_time": "1:20:47", "remaining_time": "13:26:27"}
+{"current_steps": 113, "total_steps": 1230, "loss": 0.6024, "lr": 3.67479674796748e-05, "epoch": 0.4579533941236069, "percentage": 9.19, "elapsed_time": "1:21:30", "remaining_time": "13:25:46"}
+{"current_steps": 114, "total_steps": 1230, "loss": 0.6028, "lr": 3.7073170731707325e-05, "epoch": 0.46200607902735563, "percentage": 9.27, "elapsed_time": "1:22:10", "remaining_time": "13:24:30"}
+{"current_steps": 115, "total_steps": 1230, "loss": 0.5965, "lr": 3.739837398373984e-05, "epoch": 0.46605876393110435, "percentage": 9.35, "elapsed_time": "1:22:54", "remaining_time": "13:23:52"}
+{"current_steps": 116, "total_steps": 1230, "loss": 0.6009, "lr": 3.772357723577236e-05, "epoch": 0.47011144883485306, "percentage": 9.43, "elapsed_time": "1:23:38", "remaining_time": "13:23:14"}
+{"current_steps": 117, "total_steps": 1230, "loss": 0.6078, "lr": 3.804878048780488e-05, "epoch": 0.47416413373860183, "percentage": 9.51, "elapsed_time": "1:24:25", "remaining_time": "13:23:08"}
+{"current_steps": 118, "total_steps": 1230, "loss": 0.5862, "lr": 3.83739837398374e-05, "epoch": 0.47821681864235055, "percentage": 9.59, "elapsed_time": "1:25:09", "remaining_time": "13:22:29"}
+{"current_steps": 119, "total_steps": 1230, "loss": 0.5932, "lr": 3.869918699186992e-05, "epoch": 0.48226950354609927, "percentage": 9.67, "elapsed_time": "1:25:51", "remaining_time": "13:21:36"}
+{"current_steps": 120, "total_steps": 1230, "loss": 0.6064, "lr": 3.9024390243902444e-05, "epoch": 0.48632218844984804, "percentage": 9.76, "elapsed_time": "1:26:37", "remaining_time": "13:21:15"}
+{"current_steps": 121, "total_steps": 1230, "loss": 0.614, "lr": 3.9349593495934966e-05, "epoch": 0.49037487335359675, "percentage": 9.84, "elapsed_time": "1:27:21", "remaining_time": "13:20:36"}
+{"current_steps": 122, "total_steps": 1230, "loss": 0.5964, "lr": 3.967479674796748e-05, "epoch": 0.49442755825734547, "percentage": 9.92, "elapsed_time": "1:28:03", "remaining_time": "13:19:48"}
+{"current_steps": 123, "total_steps": 1230, "loss": 0.5996, "lr": 4e-05, "epoch": 0.49848024316109424, "percentage": 10.0, "elapsed_time": "1:28:49", "remaining_time": "13:19:24"}
+{"current_steps": 124, "total_steps": 1230, "loss": 0.591, "lr": 3.999991946137476e-05, "epoch": 0.502532928064843, "percentage": 10.08, "elapsed_time": "1:29:34", "remaining_time": "13:18:56"}
+{"current_steps": 125, "total_steps": 1230, "loss": 0.5927, "lr": 3.999967784614766e-05, "epoch": 0.5065856129685917, "percentage": 10.16, "elapsed_time": "1:30:17", "remaining_time": "13:18:14"}
+{"current_steps": 126, "total_steps": 1230, "loss": 0.5841, "lr": 3.9999275156264656e-05, "epoch": 0.5106382978723404, "percentage": 10.24, "elapsed_time": "1:30:59", "remaining_time": "13:17:12"}
+{"current_steps": 127, "total_steps": 1230, "loss": 0.5865, "lr": 3.999871139496895e-05, "epoch": 0.5146909827760892, "percentage": 10.33, "elapsed_time": "1:31:42", "remaining_time": "13:16:26"}
+{"current_steps": 128, "total_steps": 1230, "loss": 0.5965, "lr": 3.9997986566800995e-05, "epoch": 0.5187436676798379, "percentage": 10.41, "elapsed_time": "1:32:27", "remaining_time": "13:15:59"}
+{"current_steps": 129, "total_steps": 1230, "loss": 0.6002, "lr": 3.999710067759846e-05, "epoch": 0.5227963525835866, "percentage": 10.49, "elapsed_time": "1:33:11", "remaining_time": "13:15:20"}
+{"current_steps": 130, "total_steps": 1230, "loss": 0.5954, "lr": 3.999605373449617e-05, "epoch": 0.5268490374873354, "percentage": 10.57, "elapsed_time": "1:33:55", "remaining_time": "13:14:41"}
+{"current_steps": 131, "total_steps": 1230, "loss": 0.5927, "lr": 3.9994845745926075e-05, "epoch": 0.5309017223910841, "percentage": 10.65, "elapsed_time": "1:34:38", "remaining_time": "13:14:00"}
+{"current_steps": 132, "total_steps": 1230, "loss": 0.5905, "lr": 3.999347672161713e-05, "epoch": 0.5349544072948328, "percentage": 10.73, "elapsed_time": "1:35:19", "remaining_time": "13:12:55"}
+{"current_steps": 133, "total_steps": 1230, "loss": 0.6016, "lr": 3.999194667259528e-05, "epoch": 0.5390070921985816, "percentage": 10.81, "elapsed_time": "1:36:01", "remaining_time": "13:12:05"}
+{"current_steps": 134, "total_steps": 1230, "loss": 0.5908, "lr": 3.999025561118334e-05, "epoch": 0.5430597771023303, "percentage": 10.89, "elapsed_time": "1:36:43", "remaining_time": "13:11:06"}
+{"current_steps": 135, "total_steps": 1230, "loss": 0.5944, "lr": 3.998840355100086e-05, "epoch": 0.547112462006079, "percentage": 10.98, "elapsed_time": "1:37:24", "remaining_time": "13:10:02"}
+{"current_steps": 136, "total_steps": 1230, "loss": 0.6005, "lr": 3.998639050696409e-05, "epoch": 0.5511651469098278, "percentage": 11.06, "elapsed_time": "1:38:08", "remaining_time": "13:09:28"}
+{"current_steps": 137, "total_steps": 1230, "loss": 0.5913, "lr": 3.998421649528582e-05, "epoch": 0.5552178318135765, "percentage": 11.14, "elapsed_time": "1:38:50", "remaining_time": "13:08:36"}
+{"current_steps": 138, "total_steps": 1230, "loss": 0.5843, "lr": 3.9981881533475234e-05, "epoch": 0.5592705167173252, "percentage": 11.22, "elapsed_time": "1:39:34", "remaining_time": "13:07:59"}
+{"current_steps": 139, "total_steps": 1230, "loss": 0.5927, "lr": 3.997938564033779e-05, "epoch": 0.563323201621074, "percentage": 11.3, "elapsed_time": "1:40:17", "remaining_time": "13:07:11"}
+{"current_steps": 140, "total_steps": 1230, "loss": 0.5961, "lr": 3.9976728835975064e-05, "epoch": 0.5673758865248227, "percentage": 11.38, "elapsed_time": "1:41:02", "remaining_time": "13:06:38"}
+{"current_steps": 141, "total_steps": 1230, "loss": 0.5854, "lr": 3.9973911141784605e-05, "epoch": 0.5714285714285714, "percentage": 11.46, "elapsed_time": "1:41:43", "remaining_time": "13:05:43"}
+{"current_steps": 142, "total_steps": 1230, "loss": 0.6044, "lr": 3.997093258045973e-05, "epoch": 0.5754812563323202, "percentage": 11.54, "elapsed_time": "1:42:29", "remaining_time": "13:05:15"}
+{"current_steps": 143, "total_steps": 1230, "loss": 0.578, "lr": 3.996779317598936e-05, "epoch": 0.5795339412360689, "percentage": 11.63, "elapsed_time": "1:43:10", "remaining_time": "13:04:13"}
+{"current_steps": 144, "total_steps": 1230, "loss": 0.6639, "lr": 3.996449295365782e-05, "epoch": 0.5835866261398176, "percentage": 11.71, "elapsed_time": "1:43:55", "remaining_time": "13:03:44"}
+{"current_steps": 145, "total_steps": 1230, "loss": 0.5946, "lr": 3.996103194004467e-05, "epoch": 0.5876393110435664, "percentage": 11.79, "elapsed_time": "1:44:39", "remaining_time": "13:03:07"}
+{"current_steps": 146, "total_steps": 1230, "loss": 0.5927, "lr": 3.995741016302441e-05, "epoch": 0.5916919959473151, "percentage": 11.87, "elapsed_time": "1:45:18", "remaining_time": "13:01:56"}
+{"current_steps": 147, "total_steps": 1230, "loss": 0.6019, "lr": 3.9953627651766364e-05, "epoch": 0.5957446808510638, "percentage": 11.95, "elapsed_time": "1:46:01", "remaining_time": "13:01:05"}
+{"current_steps": 148, "total_steps": 1230, "loss": 0.5832, "lr": 3.9949684436734325e-05, "epoch": 0.5997973657548126, "percentage": 12.03, "elapsed_time": "1:46:46", "remaining_time": "13:00:34"}
+{"current_steps": 149, "total_steps": 1230, "loss": 0.5923, "lr": 3.994558054968643e-05, "epoch": 0.6038500506585613, "percentage": 12.11, "elapsed_time": "1:47:26", "remaining_time": "12:59:31"}
+{"current_steps": 150, "total_steps": 1230, "loss": 0.6008, "lr": 3.994131602367481e-05, "epoch": 0.60790273556231, "percentage": 12.2, "elapsed_time": "1:48:11", "remaining_time": "12:58:57"}
+{"current_steps": 151, "total_steps": 1230, "loss": 0.5769, "lr": 3.9936890893045376e-05, "epoch": 0.6119554204660588, "percentage": 12.28, "elapsed_time": "1:48:56", "remaining_time": "12:58:25"}
+{"current_steps": 152, "total_steps": 1230, "loss": 0.5864, "lr": 3.993230519343752e-05, "epoch": 0.6160081053698075, "percentage": 12.36, "elapsed_time": "1:49:38", "remaining_time": "12:57:37"}
+{"current_steps": 153, "total_steps": 1230, "loss": 0.5976, "lr": 3.992755896178383e-05, "epoch": 0.6200607902735562, "percentage": 12.44, "elapsed_time": "1:50:22", "remaining_time": "12:56:55"}
+{"current_steps": 154, "total_steps": 1230, "loss": 0.5981, "lr": 3.992265223630981e-05, "epoch": 0.624113475177305, "percentage": 12.52, "elapsed_time": "1:51:06", "remaining_time": "12:56:17"}
+{"current_steps": 155, "total_steps": 1230, "loss": 0.5989, "lr": 3.991758505653355e-05, "epoch": 0.6281661600810537, "percentage": 12.6, "elapsed_time": "1:51:49", "remaining_time": "12:55:34"}
+{"current_steps": 156, "total_steps": 1230, "loss": 0.5866, "lr": 3.991235746326543e-05, "epoch": 0.6322188449848024, "percentage": 12.68, "elapsed_time": "1:52:32", "remaining_time": "12:54:46"}
+{"current_steps": 157, "total_steps": 1230, "loss": 0.5918, "lr": 3.9906969498607745e-05, "epoch": 0.6362715298885512, "percentage": 12.76, "elapsed_time": "1:53:16", "remaining_time": "12:54:06"}
+{"current_steps": 158, "total_steps": 1230, "loss": 0.5884, "lr": 3.990142120595444e-05, "epoch": 0.6403242147923, "percentage": 12.85, "elapsed_time": "1:53:56", "remaining_time": "12:53:02"}
+{"current_steps": 159, "total_steps": 1230, "loss": 0.5869, "lr": 3.98957126299907e-05, "epoch": 0.6443768996960486, "percentage": 12.93, "elapsed_time": "1:54:38", "remaining_time": "12:52:15"}
+{"current_steps": 160, "total_steps": 1230, "loss": 0.5933, "lr": 3.9889843816692596e-05, "epoch": 0.6484295845997974, "percentage": 13.01, "elapsed_time": "1:55:24", "remaining_time": "12:51:48"}
+{"current_steps": 161, "total_steps": 1230, "loss": 0.5819, "lr": 3.9883814813326766e-05, "epoch": 0.6524822695035462, "percentage": 13.09, "elapsed_time": "1:56:06", "remaining_time": "12:50:52"}
+{"current_steps": 162, "total_steps": 1230, "loss": 0.5956, "lr": 3.9877625668449956e-05, "epoch": 0.6565349544072948, "percentage": 13.17, "elapsed_time": "1:56:49", "remaining_time": "12:50:12"}
+{"current_steps": 163, "total_steps": 1230, "loss": 0.5794, "lr": 3.98712764319087e-05, "epoch": 0.6605876393110436, "percentage": 13.25, "elapsed_time": "1:57:33", "remaining_time": "12:49:34"}
+{"current_steps": 164, "total_steps": 1230, "loss": 0.5855, "lr": 3.9864767154838864e-05, "epoch": 0.6646403242147924, "percentage": 13.33, "elapsed_time": "1:58:17", "remaining_time": "12:48:53"}
+{"current_steps": 165, "total_steps": 1230, "loss": 0.593, "lr": 3.9858097889665277e-05, "epoch": 0.668693009118541, "percentage": 13.41, "elapsed_time": "1:59:02", "remaining_time": "12:48:21"}
+{"current_steps": 166, "total_steps": 1230, "loss": 0.5861, "lr": 3.985126869010129e-05, "epoch": 0.6727456940222898, "percentage": 13.5, "elapsed_time": "1:59:45", "remaining_time": "12:47:36"}
+{"current_steps": 167, "total_steps": 1230, "loss": 0.5746, "lr": 3.984427961114833e-05, "epoch": 0.6767983789260384, "percentage": 13.58, "elapsed_time": "2:00:32", "remaining_time": "12:47:14"}
+{"current_steps": 168, "total_steps": 1230, "loss": 0.6105, "lr": 3.9837130709095475e-05, "epoch": 0.6808510638297872, "percentage": 13.66, "elapsed_time": "2:01:17", "remaining_time": "12:46:47"}
+{"current_steps": 169, "total_steps": 1230, "loss": 0.5921, "lr": 3.982982204151901e-05, "epoch": 0.684903748733536, "percentage": 13.74, "elapsed_time": "2:02:01", "remaining_time": "12:46:03"}
+{"current_steps": 170, "total_steps": 1230, "loss": 0.5903, "lr": 3.982235366728193e-05, "epoch": 0.6889564336372846, "percentage": 13.82, "elapsed_time": "2:02:45", "remaining_time": "12:45:28"}
+{"current_steps": 171, "total_steps": 1230, "loss": 0.5723, "lr": 3.9814725646533505e-05, "epoch": 0.6930091185410334, "percentage": 13.9, "elapsed_time": "2:03:25", "remaining_time": "12:44:21"}
+{"current_steps": 172, "total_steps": 1230, "loss": 0.5759, "lr": 3.9806938040708746e-05, "epoch": 0.6970618034447822, "percentage": 13.98, "elapsed_time": "2:04:09", "remaining_time": "12:43:40"}
+{"current_steps": 173, "total_steps": 1230, "loss": 0.575, "lr": 3.9798990912527976e-05, "epoch": 0.7011144883485309, "percentage": 14.07, "elapsed_time": "2:04:51", "remaining_time": "12:42:53"}
+{"current_steps": 174, "total_steps": 1230, "loss": 0.5775, "lr": 3.979088432599627e-05, "epoch": 0.7051671732522796, "percentage": 14.15, "elapsed_time": "2:05:34", "remaining_time": "12:42:08"}
+{"current_steps": 175, "total_steps": 1230, "loss": 0.5583, "lr": 3.9782618346402964e-05, "epoch": 0.7092198581560284, "percentage": 14.23, "elapsed_time": "2:06:17", "remaining_time": "12:41:23"}
+{"current_steps": 176, "total_steps": 1230, "loss": 0.5829, "lr": 3.977419304032111e-05, "epoch": 0.713272543059777, "percentage": 14.31, "elapsed_time": "2:07:02", "remaining_time": "12:40:50"}
+{"current_steps": 177, "total_steps": 1230, "loss": 0.588, "lr": 3.976560847560697e-05, "epoch": 0.7173252279635258, "percentage": 14.39, "elapsed_time": "2:07:46", "remaining_time": "12:40:09"}
+{"current_steps": 178, "total_steps": 1230, "loss": 0.5762, "lr": 3.9756864721399456e-05, "epoch": 0.7213779128672746, "percentage": 14.47, "elapsed_time": "2:08:30", "remaining_time": "12:39:29"}
+{"current_steps": 179, "total_steps": 1230, "loss": 0.578, "lr": 3.974796184811956e-05, "epoch": 0.7254305977710233, "percentage": 14.55, "elapsed_time": "2:09:17", "remaining_time": "12:39:08"}
+{"current_steps": 180, "total_steps": 1230, "loss": 0.576, "lr": 3.973889992746979e-05, "epoch": 0.729483282674772, "percentage": 14.63, "elapsed_time": "2:10:04", "remaining_time": "12:38:44"}
+{"current_steps": 181, "total_steps": 1230, "loss": 0.574, "lr": 3.972967903243361e-05, "epoch": 0.7335359675785208, "percentage": 14.72, "elapsed_time": "2:10:50", "remaining_time": "12:38:15"}
+{"current_steps": 182, "total_steps": 1230, "loss": 0.5781, "lr": 3.972029923727486e-05, "epoch": 0.7375886524822695, "percentage": 14.8, "elapsed_time": "2:11:31", "remaining_time": "12:37:21"}
+{"current_steps": 183, "total_steps": 1230, "loss": 0.6272, "lr": 3.971076061753709e-05, "epoch": 0.7416413373860182, "percentage": 14.88, "elapsed_time": "2:12:17", "remaining_time": "12:36:53"}
+{"current_steps": 184, "total_steps": 1230, "loss": 0.5804, "lr": 3.9701063250043066e-05, "epoch": 0.745694022289767, "percentage": 14.96, "elapsed_time": "2:13:02", "remaining_time": "12:36:18"}
+{"current_steps": 185, "total_steps": 1230, "loss": 0.5734, "lr": 3.969120721289402e-05, "epoch": 0.7497467071935157, "percentage": 15.04, "elapsed_time": "2:13:47", "remaining_time": "12:35:45"}
+{"current_steps": 186, "total_steps": 1230, "loss": 0.5759, "lr": 3.9681192585469146e-05, "epoch": 0.7537993920972644, "percentage": 15.12, "elapsed_time": "2:14:33", "remaining_time": "12:35:13"}
+{"current_steps": 187, "total_steps": 1230, "loss": 0.5772, "lr": 3.9671019448424865e-05, "epoch": 0.7578520770010132, "percentage": 15.2, "elapsed_time": "2:15:14", "remaining_time": "12:34:16"}
+{"current_steps": 188, "total_steps": 1230, "loss": 0.5696, "lr": 3.966068788369422e-05, "epoch": 0.7619047619047619, "percentage": 15.28, "elapsed_time": "2:15:58", "remaining_time": "12:33:38"}
+{"current_steps": 189, "total_steps": 1230, "loss": 0.5804, "lr": 3.965019797448622e-05, "epoch": 0.7659574468085106, "percentage": 15.37, "elapsed_time": "2:16:38", "remaining_time": "12:32:37"}
+{"current_steps": 190, "total_steps": 1230, "loss": 0.5816, "lr": 3.963954980528515e-05, "epoch": 0.7700101317122594, "percentage": 15.45, "elapsed_time": "2:17:23", "remaining_time": "12:31:59"}
+{"current_steps": 191, "total_steps": 1230, "loss": 0.5725, "lr": 3.9628743461849905e-05, "epoch": 0.7740628166160081, "percentage": 15.53, "elapsed_time": "2:18:06", "remaining_time": "12:31:16"}
+{"current_steps": 192, "total_steps": 1230, "loss": 0.5799, "lr": 3.961777903121329e-05, "epoch": 0.7781155015197568, "percentage": 15.61, "elapsed_time": "2:18:47", "remaining_time": "12:30:20"}
+{"current_steps": 193, "total_steps": 1230, "loss": 0.5825, "lr": 3.960665660168131e-05, "epoch": 0.7821681864235056, "percentage": 15.69, "elapsed_time": "2:19:31", "remaining_time": "12:29:39"}
+{"current_steps": 194, "total_steps": 1230, "loss": 0.5902, "lr": 3.9595376262832485e-05, "epoch": 0.7862208713272543, "percentage": 15.77, "elapsed_time": "2:20:15", "remaining_time": "12:29:00"}
+{"current_steps": 195, "total_steps": 1230, "loss": 0.5873, "lr": 3.9583938105517127e-05, "epoch": 0.790273556231003, "percentage": 15.85, "elapsed_time": "2:20:58", "remaining_time": "12:28:13"}
+{"current_steps": 196, "total_steps": 1230, "loss": 0.5687, "lr": 3.957234222185657e-05, "epoch": 0.7943262411347518, "percentage": 15.93, "elapsed_time": "2:21:40", "remaining_time": "12:27:23"}
+{"current_steps": 197, "total_steps": 1230, "loss": 0.5751, "lr": 3.9560588705242474e-05, "epoch": 0.7983789260385005, "percentage": 16.02, "elapsed_time": "2:22:21", "remaining_time": "12:26:29"}
+{"current_steps": 198, "total_steps": 1230, "loss": 0.5628, "lr": 3.954867765033605e-05, "epoch": 0.8024316109422492, "percentage": 16.1, "elapsed_time": "2:23:05", "remaining_time": "12:25:50"}
+{"current_steps": 199, "total_steps": 1230, "loss": 0.5618, "lr": 3.953660915306728e-05, "epoch": 0.806484295845998, "percentage": 16.18, "elapsed_time": "2:23:51", "remaining_time": "12:25:20"}
+{"current_steps": 200, "total_steps": 1230, "loss": 0.5672, "lr": 3.952438331063419e-05, "epoch": 0.8105369807497467, "percentage": 16.26, "elapsed_time": "2:24:36", "remaining_time": "12:24:43"}
+{"current_steps": 201, "total_steps": 1230, "loss": 0.5526, "lr": 3.951200022150205e-05, "epoch": 0.8145896656534954, "percentage": 16.34, "elapsed_time": "2:25:21", "remaining_time": "12:24:09"}
+{"current_steps": 202, "total_steps": 1230, "loss": 0.5738, "lr": 3.949945998540253e-05, "epoch": 0.8186423505572442, "percentage": 16.42, "elapsed_time": "2:26:06", "remaining_time": "12:23:31"}
+{"current_steps": 203, "total_steps": 1230, "loss": 0.5768, "lr": 3.9486762703332993e-05, "epoch": 0.8226950354609929, "percentage": 16.5, "elapsed_time": "2:26:50", "remaining_time": "12:22:55"}
+{"current_steps": 204, "total_steps": 1230, "loss": 0.57, "lr": 3.947390847755559e-05, "epoch": 0.8267477203647416, "percentage": 16.59, "elapsed_time": "2:27:34", "remaining_time": "12:22:10"}
+{"current_steps": 205, "total_steps": 1230, "loss": 0.5533, "lr": 3.946089741159648e-05, "epoch": 0.8308004052684904, "percentage": 16.67, "elapsed_time": "2:28:17", "remaining_time": "12:21:26"}
+{"current_steps": 206, "total_steps": 1230, "loss": 0.5625, "lr": 3.944772961024501e-05, "epoch": 0.8348530901722391, "percentage": 16.75, "elapsed_time": "2:29:01", "remaining_time": "12:20:46"}
+{"current_steps": 207, "total_steps": 1230, "loss": 0.5822, "lr": 3.943440517955285e-05, "epoch": 0.8389057750759878, "percentage": 16.83, "elapsed_time": "2:29:44", "remaining_time": "12:20:02"}
+{"current_steps": 208, "total_steps": 1230, "loss": 0.5888, "lr": 3.9420924226833126e-05, "epoch": 0.8429584599797366, "percentage": 16.91, "elapsed_time": "2:30:28", "remaining_time": "12:19:20"}
+{"current_steps": 209, "total_steps": 1230, "loss": 0.5753, "lr": 3.9407286860659566e-05, "epoch": 0.8470111448834853, "percentage": 16.99, "elapsed_time": "2:31:10", "remaining_time": "12:18:32"}
+{"current_steps": 210, "total_steps": 1230, "loss": 0.5563, "lr": 3.9393493190865657e-05, "epoch": 0.851063829787234, "percentage": 17.07, "elapsed_time": "2:31:54", "remaining_time": "12:17:49"}
+{"current_steps": 211, "total_steps": 1230, "loss": 0.5547, "lr": 3.937954332854371e-05, "epoch": 0.8551165146909828, "percentage": 17.15, "elapsed_time": "2:32:39", "remaining_time": "12:17:16"}
+{"current_steps": 212, "total_steps": 1230, "loss": 0.5739, "lr": 3.9365437386044016e-05, "epoch": 0.8591691995947315, "percentage": 17.24, "elapsed_time": "2:33:24", "remaining_time": "12:16:40"}
+{"current_steps": 213, "total_steps": 1230, "loss": 0.5817, "lr": 3.935117547697387e-05, "epoch": 0.8632218844984803, "percentage": 17.32, "elapsed_time": "2:34:07", "remaining_time": "12:15:53"}
+{"current_steps": 214, "total_steps": 1230, "loss": 0.569, "lr": 3.933675771619675e-05, "epoch": 0.867274569402229, "percentage": 17.4, "elapsed_time": "2:34:47", "remaining_time": "12:14:54"}
+{"current_steps": 215, "total_steps": 1230, "loss": 0.5746, "lr": 3.932218421983131e-05, "epoch": 0.8713272543059777, "percentage": 17.48, "elapsed_time": "2:35:31", "remaining_time": "12:14:12"}
+{"current_steps": 216, "total_steps": 1230, "loss": 0.5436, "lr": 3.9307455105250484e-05, "epoch": 0.8753799392097265, "percentage": 17.56, "elapsed_time": "2:36:15", "remaining_time": "12:13:35"}
+{"current_steps": 217, "total_steps": 1230, "loss": 0.581, "lr": 3.929257049108054e-05, "epoch": 0.8794326241134752, "percentage": 17.64, "elapsed_time": "2:36:59", "remaining_time": "12:12:54"}
+{"current_steps": 218, "total_steps": 1230, "loss": 0.5687, "lr": 3.927753049720011e-05, "epoch": 0.8834853090172239, "percentage": 17.72, "elapsed_time": "2:37:41", "remaining_time": "12:12:00"}
+{"current_steps": 219, "total_steps": 1230, "loss": 0.573, "lr": 3.9262335244739234e-05, "epoch": 0.8875379939209727, "percentage": 17.8, "elapsed_time": "2:38:24", "remaining_time": "12:11:15"}
+{"current_steps": 220, "total_steps": 1230, "loss": 0.5804, "lr": 3.92469848560784e-05, "epoch": 0.8915906788247214, "percentage": 17.89, "elapsed_time": "2:39:07", "remaining_time": "12:10:32"}
+{"current_steps": 221, "total_steps": 1230, "loss": 0.5648, "lr": 3.923147945484751e-05, "epoch": 0.8956433637284701, "percentage": 17.97, "elapsed_time": "2:39:51", "remaining_time": "12:09:52"}
+{"current_steps": 222, "total_steps": 1230, "loss": 0.5603, "lr": 3.9215819165924956e-05, "epoch": 0.8996960486322189, "percentage": 18.05, "elapsed_time": "2:40:36", "remaining_time": "12:09:14"}
+{"current_steps": 223, "total_steps": 1230, "loss": 0.5651, "lr": 3.920000411543654e-05, "epoch": 0.9037487335359676, "percentage": 18.13, "elapsed_time": "2:41:22", "remaining_time": "12:08:44"}
+{"current_steps": 224, "total_steps": 1230, "loss": 0.565, "lr": 3.9184034430754495e-05, "epoch": 0.9078014184397163, "percentage": 18.21, "elapsed_time": "2:42:03", "remaining_time": "12:07:50"}
+{"current_steps": 225, "total_steps": 1230, "loss": 0.5632, "lr": 3.916791024049648e-05, "epoch": 0.9118541033434651, "percentage": 18.29, "elapsed_time": "2:42:46", "remaining_time": "12:07:01"}
+{"current_steps": 226, "total_steps": 1230, "loss": 0.5613, "lr": 3.91516316745245e-05, "epoch": 0.9159067882472138, "percentage": 18.37, "elapsed_time": "2:43:32", "remaining_time": "12:06:30"}
+{"current_steps": 227, "total_steps": 1230, "loss": 0.5753, "lr": 3.913519886394389e-05, "epoch": 0.9199594731509625, "percentage": 18.46, "elapsed_time": "2:44:16", "remaining_time": "12:05:50"}
+{"current_steps": 228, "total_steps": 1230, "loss": 0.5742, "lr": 3.911861194110225e-05, "epoch": 0.9240121580547113, "percentage": 18.54, "elapsed_time": "2:44:58", "remaining_time": "12:05:01"}
+{"current_steps": 229, "total_steps": 1230, "loss": 0.5665, "lr": 3.910187103958837e-05, "epoch": 0.92806484295846, "percentage": 18.62, "elapsed_time": "2:45:41", "remaining_time": "12:04:17"}
+{"current_steps": 230, "total_steps": 1230, "loss": 0.5757, "lr": 3.908497629423117e-05, "epoch": 0.9321175278622087, "percentage": 18.7, "elapsed_time": "2:46:28", "remaining_time": "12:03:47"}
+{"current_steps": 231, "total_steps": 1230, "loss": 0.5649, "lr": 3.9067927841098614e-05, "epoch": 0.9361702127659575, "percentage": 18.78, "elapsed_time": "2:47:13", "remaining_time": "12:03:12"}
+{"current_steps": 232, "total_steps": 1230, "loss": 0.5697, "lr": 3.9050725817496594e-05, "epoch": 0.9402228976697061, "percentage": 18.86, "elapsed_time": "2:48:00", "remaining_time": "12:02:45"}
+{"current_steps": 233, "total_steps": 1230, "loss": 0.5702, "lr": 3.9033370361967844e-05, "epoch": 0.9442755825734549, "percentage": 18.94, "elapsed_time": "2:48:46", "remaining_time": "12:02:10"}
+{"current_steps": 234, "total_steps": 1230, "loss": 0.5696, "lr": 3.901586161429081e-05, "epoch": 0.9483282674772037, "percentage": 19.02, "elapsed_time": "2:49:28", "remaining_time": "12:01:23"}
+{"current_steps": 235, "total_steps": 1230, "loss": 0.5663, "lr": 3.8998199715478545e-05, "epoch": 0.9523809523809523, "percentage": 19.11, "elapsed_time": "2:50:11", "remaining_time": "12:00:37"}
+{"current_steps": 236, "total_steps": 1230, "loss": 0.5736, "lr": 3.8980384807777564e-05, "epoch": 0.9564336372847011, "percentage": 19.19, "elapsed_time": "2:50:56", "remaining_time": "11:59:58"}
+{"current_steps": 237, "total_steps": 1230, "loss": 0.5723, "lr": 3.896241703466667e-05, "epoch": 0.9604863221884499, "percentage": 19.27, "elapsed_time": "2:51:39", "remaining_time": "11:59:11"}
+{"current_steps": 238, "total_steps": 1230, "loss": 0.567, "lr": 3.894429654085585e-05, "epoch": 0.9645390070921985, "percentage": 19.35, "elapsed_time": "2:52:23", "remaining_time": "11:58:31"}
+{"current_steps": 239, "total_steps": 1230, "loss": 0.555, "lr": 3.892602347228505e-05, "epoch": 0.9685916919959473, "percentage": 19.43, "elapsed_time": "2:53:01", "remaining_time": "11:57:28"}
+{"current_steps": 240, "total_steps": 1230, "loss": 0.556, "lr": 3.890759797612307e-05, "epoch": 0.9726443768996961, "percentage": 19.51, "elapsed_time": "2:53:45", "remaining_time": "11:56:46"}
+{"current_steps": 241, "total_steps": 1230, "loss": 0.5656, "lr": 3.888902020076632e-05, "epoch": 0.9766970618034447, "percentage": 19.59, "elapsed_time": "2:54:31", "remaining_time": "11:56:12"}
+{"current_steps": 242, "total_steps": 1230, "loss": 0.5753, "lr": 3.887029029583764e-05, "epoch": 0.9807497467071935, "percentage": 19.67, "elapsed_time": "2:55:15", "remaining_time": "11:55:29"}
+{"current_steps": 243, "total_steps": 1230, "loss": 0.5644, "lr": 3.8851408412185125e-05, "epoch": 0.9848024316109423, "percentage": 19.76, "elapsed_time": "2:55:57", "remaining_time": "11:54:41"}
+{"current_steps": 244, "total_steps": 1230, "loss": 0.5503, "lr": 3.8832374701880855e-05, "epoch": 0.9888551165146909, "percentage": 19.84, "elapsed_time": "2:56:39", "remaining_time": "11:53:52"}
+{"current_steps": 245, "total_steps": 1230, "loss": 0.5727, "lr": 3.881318931821972e-05, "epoch": 0.9929078014184397, "percentage": 19.92, "elapsed_time": "2:57:20", "remaining_time": "11:53:00"}
+{"current_steps": 246, "total_steps": 1230, "loss": 0.5711, "lr": 3.879385241571817e-05, "epoch": 0.9969604863221885, "percentage": 20.0, "elapsed_time": "2:58:04", "remaining_time": "11:52:16"}
+{"current_steps": 247, "total_steps": 1230, "loss": 0.5424, "lr": 3.8774364150112955e-05, "epoch": 1.0030395136778116, "percentage": 20.08, "elapsed_time": "3:00:38", "remaining_time": "11:58:54"}
+{"current_steps": 248, "total_steps": 1230, "loss": 0.5231, "lr": 3.8754724678359884e-05, "epoch": 1.0070921985815602, "percentage": 20.16, "elapsed_time": "3:01:22", "remaining_time": "11:58:10"}
+{"current_steps": 249, "total_steps": 1230, "loss": 0.5134, "lr": 3.873493415863256e-05, "epoch": 1.011144883485309, "percentage": 20.24, "elapsed_time": "3:02:02", "remaining_time": "11:57:11"}
+{"current_steps": 250, "total_steps": 1230, "loss": 0.5215, "lr": 3.871499275032111e-05, "epoch": 1.0151975683890577, "percentage": 20.33, "elapsed_time": "3:02:45", "remaining_time": "11:56:24"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733bfb4341d53615c69b46066a967f0f09add9c2044628b16a44d85408878204
+size 7288