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 sha256:69e8407f88eeabdf51292acd68a316b4d2c22750652f7a05fbe4e02c8979df8d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626803f8224e439bf5f3f1b99b7bd7356b0ee10deebe418475de183b8d5d7e74
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41aa7e1a58000b519be75ca4d75d76b09824e7fba9d8848c13e41b7ff7f7d4ac
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba11352b7e68d52bab06b90f0f7f51b7d964ba7d5d79e8f06c0a7f9210e3f92
+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 +1,196 @@
+{"current_steps": 10, "total_steps": 5547, "loss": 0.8785, "lr": 1.801801801801802e-07, "epoch": 0.005406379527842855, "percentage": 0.18, "elapsed_time": "0:02:50", "remaining_time": "1 day, 2:13:54"}
+{"current_steps": 20, "total_steps": 5547, "loss": 0.8654, "lr": 3.603603603603604e-07, "epoch": 0.01081275905568571, "percentage": 0.36, "elapsed_time": "0:05:42", "remaining_time": "1 day, 2:15:37"}
+{"current_steps": 30, "total_steps": 5547, "loss": 0.8205, "lr": 5.405405405405406e-07, "epoch": 0.016219138583528563, "percentage": 0.54, "elapsed_time": "0:08:32", "remaining_time": "1 day, 2:12:01"}
+{"current_steps": 40, "total_steps": 5547, "loss": 0.778, "lr": 7.207207207207208e-07, "epoch": 0.02162551811137142, "percentage": 0.72, "elapsed_time": "0:11:15", "remaining_time": "1 day, 1:49:40"}
+{"current_steps": 50, "total_steps": 5547, "loss": 0.7286, "lr": 9.00900900900901e-07, "epoch": 0.027031897639214274, "percentage": 0.9, "elapsed_time": "0:14:03", "remaining_time": "1 day, 1:45:10"}
+{"current_steps": 60, "total_steps": 5547, "loss": 0.6968, "lr": 1.0810810810810812e-06, "epoch": 0.03243827716705713, "percentage": 1.08, "elapsed_time": "0:16:50", "remaining_time": "1 day, 1:40:20"}
+{"current_steps": 70, "total_steps": 5547, "loss": 0.6689, "lr": 1.2612612612612613e-06, "epoch": 0.03784465669489998, "percentage": 1.26, "elapsed_time": "0:19:38", "remaining_time": "1 day, 1:36:28"}
+{"current_steps": 80, "total_steps": 5547, "loss": 0.6408, "lr": 1.4414414414414416e-06, "epoch": 0.04325103622274284, "percentage": 1.44, "elapsed_time": "0:22:29", "remaining_time": "1 day, 1:36:56"}
+{"current_steps": 90, "total_steps": 5547, "loss": 0.6153, "lr": 1.6216216216216219e-06, "epoch": 0.04865741575058569, "percentage": 1.62, "elapsed_time": "0:25:20", "remaining_time": "1 day, 1:36:57"}
+{"current_steps": 100, "total_steps": 5547, "loss": 0.6082, "lr": 1.801801801801802e-06, "epoch": 0.05406379527842855, "percentage": 1.8, "elapsed_time": "0:28:14", "remaining_time": "1 day, 1:38:36"}
+{"current_steps": 110, "total_steps": 5547, "loss": 0.6049, "lr": 1.9819819819819822e-06, "epoch": 0.0594701748062714, "percentage": 1.98, "elapsed_time": "0:30:58", "remaining_time": "1 day, 1:30:50"}
+{"current_steps": 120, "total_steps": 5547, "loss": 0.5889, "lr": 2.1621621621621623e-06, "epoch": 0.06487655433411425, "percentage": 2.16, "elapsed_time": "0:33:45", "remaining_time": "1 day, 1:26:55"}
+{"current_steps": 130, "total_steps": 5547, "loss": 0.5842, "lr": 2.3423423423423424e-06, "epoch": 0.07028293386195711, "percentage": 2.34, "elapsed_time": "0:36:35", "remaining_time": "1 day, 1:24:50"}
+{"current_steps": 140, "total_steps": 5547, "loss": 0.592, "lr": 2.5225225225225225e-06, "epoch": 0.07568931338979996, "percentage": 2.52, "elapsed_time": "0:39:32", "remaining_time": "1 day, 1:26:51"}
+{"current_steps": 150, "total_steps": 5547, "loss": 0.5732, "lr": 2.702702702702703e-06, "epoch": 0.08109569291764282, "percentage": 2.7, "elapsed_time": "0:42:20", "remaining_time": "1 day, 1:23:28"}
+{"current_steps": 160, "total_steps": 5547, "loss": 0.5679, "lr": 2.882882882882883e-06, "epoch": 0.08650207244548568, "percentage": 2.88, "elapsed_time": "0:45:10", "remaining_time": "1 day, 1:20:57"}
+{"current_steps": 170, "total_steps": 5547, "loss": 0.5583, "lr": 3.063063063063063e-06, "epoch": 0.09190845197332853, "percentage": 3.06, "elapsed_time": "0:47:56", "remaining_time": "1 day, 1:16:08"}
+{"current_steps": 180, "total_steps": 5547, "loss": 0.5658, "lr": 3.2432432432432437e-06, "epoch": 0.09731483150117139, "percentage": 3.24, "elapsed_time": "0:50:39", "remaining_time": "1 day, 1:10:26"}
+{"current_steps": 190, "total_steps": 5547, "loss": 0.5554, "lr": 3.423423423423424e-06, "epoch": 0.10272121102901424, "percentage": 3.43, "elapsed_time": "0:53:23", "remaining_time": "1 day, 1:05:17"}
+{"current_steps": 200, "total_steps": 5547, "loss": 0.5534, "lr": 3.603603603603604e-06, "epoch": 0.1081275905568571, "percentage": 3.61, "elapsed_time": "0:56:12", "remaining_time": "1 day, 1:02:43"}
+{"current_steps": 210, "total_steps": 5547, "loss": 0.5527, "lr": 3.7837837837837844e-06, "epoch": 0.11353397008469994, "percentage": 3.79, "elapsed_time": "0:59:06", "remaining_time": "1 day, 1:02:05"}
+{"current_steps": 220, "total_steps": 5547, "loss": 0.5521, "lr": 3.9639639639639645e-06, "epoch": 0.1189403496125428, "percentage": 3.97, "elapsed_time": "1:01:53", "remaining_time": "1 day, 0:58:28"}
+{"current_steps": 230, "total_steps": 5547, "loss": 0.55, "lr": 4.1441441441441446e-06, "epoch": 0.12434672914038565, "percentage": 4.15, "elapsed_time": "1:04:41", "remaining_time": "1 day, 0:55:23"}
+{"current_steps": 240, "total_steps": 5547, "loss": 0.5455, "lr": 4.324324324324325e-06, "epoch": 0.1297531086682285, "percentage": 4.33, "elapsed_time": "1:07:25", "remaining_time": "1 day, 0:51:02"}
+{"current_steps": 250, "total_steps": 5547, "loss": 0.5392, "lr": 4.504504504504505e-06, "epoch": 0.13515948819607138, "percentage": 4.51, "elapsed_time": "1:10:16", "remaining_time": "1 day, 0:48:53"}
+{"current_steps": 260, "total_steps": 5547, "loss": 0.5317, "lr": 4.684684684684685e-06, "epoch": 0.14056586772391422, "percentage": 4.69, "elapsed_time": "1:13:04", "remaining_time": "1 day, 0:45:59"}
+{"current_steps": 270, "total_steps": 5547, "loss": 0.5317, "lr": 4.864864864864866e-06, "epoch": 0.1459722472517571, "percentage": 4.87, "elapsed_time": "1:15:52", "remaining_time": "1 day, 0:42:53"}
+{"current_steps": 280, "total_steps": 5547, "loss": 0.5342, "lr": 5.045045045045045e-06, "epoch": 0.15137862677959993, "percentage": 5.05, "elapsed_time": "1:18:47", "remaining_time": "1 day, 0:42:15"}
+{"current_steps": 290, "total_steps": 5547, "loss": 0.5325, "lr": 5.225225225225226e-06, "epoch": 0.15678500630744277, "percentage": 5.23, "elapsed_time": "1:21:40", "remaining_time": "1 day, 0:40:40"}
+{"current_steps": 300, "total_steps": 5547, "loss": 0.5236, "lr": 5.405405405405406e-06, "epoch": 0.16219138583528564, "percentage": 5.41, "elapsed_time": "1:24:30", "remaining_time": "1 day, 0:37:58"}
+{"current_steps": 310, "total_steps": 5547, "loss": 0.5316, "lr": 5.585585585585585e-06, "epoch": 0.16759776536312848, "percentage": 5.59, "elapsed_time": "1:27:17", "remaining_time": "1 day, 0:34:38"}
+{"current_steps": 320, "total_steps": 5547, "loss": 0.5304, "lr": 5.765765765765766e-06, "epoch": 0.17300414489097135, "percentage": 5.77, "elapsed_time": "1:30:06", "remaining_time": "1 day, 0:31:57"}
+{"current_steps": 330, "total_steps": 5547, "loss": 0.5307, "lr": 5.945945945945947e-06, "epoch": 0.1784105244188142, "percentage": 5.95, "elapsed_time": "1:32:54", "remaining_time": "1 day, 0:28:40"}
+{"current_steps": 340, "total_steps": 5547, "loss": 0.5142, "lr": 6.126126126126126e-06, "epoch": 0.18381690394665706, "percentage": 6.13, "elapsed_time": "1:35:42", "remaining_time": "1 day, 0:25:37"}
+{"current_steps": 350, "total_steps": 5547, "loss": 0.5252, "lr": 6.3063063063063065e-06, "epoch": 0.1892232834744999, "percentage": 6.31, "elapsed_time": "1:38:34", "remaining_time": "1 day, 0:23:35"}
+{"current_steps": 360, "total_steps": 5547, "loss": 0.5203, "lr": 6.486486486486487e-06, "epoch": 0.19462966300234277, "percentage": 6.49, "elapsed_time": "1:41:17", "remaining_time": "1 day, 0:19:19"}
+{"current_steps": 370, "total_steps": 5547, "loss": 0.5198, "lr": 6.666666666666667e-06, "epoch": 0.20003604253018561, "percentage": 6.67, "elapsed_time": "1:44:04", "remaining_time": "1 day, 0:16:10"}
+{"current_steps": 380, "total_steps": 5547, "loss": 0.5164, "lr": 6.846846846846848e-06, "epoch": 0.20544242205802848, "percentage": 6.85, "elapsed_time": "1:46:55", "remaining_time": "1 day, 0:13:55"}
+{"current_steps": 390, "total_steps": 5547, "loss": 0.5201, "lr": 7.027027027027028e-06, "epoch": 0.21084880158587133, "percentage": 7.03, "elapsed_time": "1:49:42", "remaining_time": "1 day, 0:10:43"}
+{"current_steps": 400, "total_steps": 5547, "loss": 0.5241, "lr": 7.207207207207208e-06, "epoch": 0.2162551811137142, "percentage": 7.21, "elapsed_time": "1:52:32", "remaining_time": "1 day, 0:08:01"}
+{"current_steps": 410, "total_steps": 5547, "loss": 0.5141, "lr": 7.387387387387388e-06, "epoch": 0.22166156064155704, "percentage": 7.39, "elapsed_time": "1:55:19", "remaining_time": "1 day, 0:04:52"}
+{"current_steps": 420, "total_steps": 5547, "loss": 0.5058, "lr": 7.567567567567569e-06, "epoch": 0.22706794016939988, "percentage": 7.57, "elapsed_time": "1:58:10", "remaining_time": "1 day, 0:02:37"}
+{"current_steps": 430, "total_steps": 5547, "loss": 0.5132, "lr": 7.747747747747749e-06, "epoch": 0.23247431969724275, "percentage": 7.75, "elapsed_time": "2:00:58", "remaining_time": "23:59:35"}
+{"current_steps": 440, "total_steps": 5547, "loss": 0.5116, "lr": 7.927927927927929e-06, "epoch": 0.2378806992250856, "percentage": 7.93, "elapsed_time": "2:03:47", "remaining_time": "23:56:47"}
+{"current_steps": 450, "total_steps": 5547, "loss": 0.5168, "lr": 8.108108108108109e-06, "epoch": 0.24328707875292846, "percentage": 8.11, "elapsed_time": "2:06:32", "remaining_time": "23:53:19"}
+{"current_steps": 460, "total_steps": 5547, "loss": 0.5078, "lr": 8.288288288288289e-06, "epoch": 0.2486934582807713, "percentage": 8.29, "elapsed_time": "2:09:22", "remaining_time": "23:50:41"}
+{"current_steps": 470, "total_steps": 5547, "loss": 0.5033, "lr": 8.46846846846847e-06, "epoch": 0.25409983780861417, "percentage": 8.47, "elapsed_time": "2:12:12", "remaining_time": "23:48:08"}
+{"current_steps": 480, "total_steps": 5547, "loss": 0.5023, "lr": 8.64864864864865e-06, "epoch": 0.259506217336457, "percentage": 8.65, "elapsed_time": "2:15:03", "remaining_time": "23:45:40"}
+{"current_steps": 490, "total_steps": 5547, "loss": 0.5101, "lr": 8.82882882882883e-06, "epoch": 0.26491259686429985, "percentage": 8.83, "elapsed_time": "2:17:50", "remaining_time": "23:42:33"}
+{"current_steps": 500, "total_steps": 5547, "loss": 0.508, "lr": 9.00900900900901e-06, "epoch": 0.27031897639214275, "percentage": 9.01, "elapsed_time": "2:20:40", "remaining_time": "23:39:58"}
+{"current_steps": 510, "total_steps": 5547, "loss": 0.5057, "lr": 9.189189189189191e-06, "epoch": 0.2757253559199856, "percentage": 9.19, "elapsed_time": "2:23:36", "remaining_time": "23:38:18"}
+{"current_steps": 520, "total_steps": 5547, "loss": 0.5026, "lr": 9.36936936936937e-06, "epoch": 0.28113173544782843, "percentage": 9.37, "elapsed_time": "2:26:22", "remaining_time": "23:34:58"}
+{"current_steps": 530, "total_steps": 5547, "loss": 0.5106, "lr": 9.54954954954955e-06, "epoch": 0.2865381149756713, "percentage": 9.55, "elapsed_time": "2:29:08", "remaining_time": "23:31:47"}
+{"current_steps": 540, "total_steps": 5547, "loss": 0.4974, "lr": 9.729729729729732e-06, "epoch": 0.2919444945035142, "percentage": 9.73, "elapsed_time": "2:31:57", "remaining_time": "23:28:58"}
+{"current_steps": 550, "total_steps": 5547, "loss": 0.4999, "lr": 9.90990990990991e-06, "epoch": 0.297350874031357, "percentage": 9.92, "elapsed_time": "2:34:45", "remaining_time": "23:26:00"}
+{"current_steps": 560, "total_steps": 5547, "loss": 0.5103, "lr": 9.999975246862685e-06, "epoch": 0.30275725355919986, "percentage": 10.1, "elapsed_time": "2:37:33", "remaining_time": "23:23:05"}
+{"current_steps": 570, "total_steps": 5547, "loss": 0.5015, "lr": 9.999777223234682e-06, "epoch": 0.3081636330870427, "percentage": 10.28, "elapsed_time": "2:40:21", "remaining_time": "23:20:08"}
+{"current_steps": 580, "total_steps": 5547, "loss": 0.5079, "lr": 9.999381183821387e-06, "epoch": 0.31357001261488554, "percentage": 10.46, "elapsed_time": "2:43:09", "remaining_time": "23:17:18"}
+{"current_steps": 590, "total_steps": 5547, "loss": 0.4946, "lr": 9.998787144307906e-06, "epoch": 0.31897639214272844, "percentage": 10.64, "elapsed_time": "2:45:55", "remaining_time": "23:14:00"}
+{"current_steps": 600, "total_steps": 5547, "loss": 0.4963, "lr": 9.997995128221131e-06, "epoch": 0.3243827716705713, "percentage": 10.82, "elapsed_time": "2:48:42", "remaining_time": "23:10:59"}
+{"current_steps": 610, "total_steps": 5547, "loss": 0.4937, "lr": 9.9970051669288e-06, "epoch": 0.3297891511984141, "percentage": 11.0, "elapsed_time": "2:51:29", "remaining_time": "23:07:54"}
+{"current_steps": 620, "total_steps": 5547, "loss": 0.5002, "lr": 9.995817299638244e-06, "epoch": 0.33519553072625696, "percentage": 11.18, "elapsed_time": "2:54:15", "remaining_time": "23:04:49"}
+{"current_steps": 630, "total_steps": 5547, "loss": 0.5029, "lr": 9.994431573394861e-06, "epoch": 0.34060191025409986, "percentage": 11.36, "elapsed_time": "2:57:07", "remaining_time": "23:02:22"}
+{"current_steps": 640, "total_steps": 5547, "loss": 0.4952, "lr": 9.99284804308023e-06, "epoch": 0.3460082897819427, "percentage": 11.54, "elapsed_time": "2:59:58", "remaining_time": "22:59:51"}
+{"current_steps": 650, "total_steps": 5547, "loss": 0.4915, "lr": 9.991066771409941e-06, "epoch": 0.35141466930978554, "percentage": 11.72, "elapsed_time": "3:02:49", "remaining_time": "22:57:18"}
+{"current_steps": 660, "total_steps": 5547, "loss": 0.4981, "lr": 9.989087828931121e-06, "epoch": 0.3568210488376284, "percentage": 11.9, "elapsed_time": "3:05:35", "remaining_time": "22:54:10"}
+{"current_steps": 670, "total_steps": 5547, "loss": 0.4975, "lr": 9.986911294019631e-06, "epoch": 0.3622274283654713, "percentage": 12.08, "elapsed_time": "3:08:23", "remaining_time": "22:51:22"}
+{"current_steps": 680, "total_steps": 5547, "loss": 0.4908, "lr": 9.984537252876969e-06, "epoch": 0.3676338078933141, "percentage": 12.26, "elapsed_time": "3:11:17", "remaining_time": "22:49:10"}
+{"current_steps": 690, "total_steps": 5547, "loss": 0.5016, "lr": 9.981965799526846e-06, "epoch": 0.37304018742115697, "percentage": 12.44, "elapsed_time": "3:14:04", "remaining_time": "22:46:05"}
+{"current_steps": 700, "total_steps": 5547, "loss": 0.4876, "lr": 9.97919703581147e-06, "epoch": 0.3784465669489998, "percentage": 12.62, "elapsed_time": "3:16:52", "remaining_time": "22:43:15"}
+{"current_steps": 710, "total_steps": 5547, "loss": 0.4903, "lr": 9.976231071387513e-06, "epoch": 0.38385294647684265, "percentage": 12.8, "elapsed_time": "3:19:38", "remaining_time": "22:40:04"}
+{"current_steps": 720, "total_steps": 5547, "loss": 0.4898, "lr": 9.973068023721761e-06, "epoch": 0.38925932600468555, "percentage": 12.98, "elapsed_time": "3:22:30", "remaining_time": "22:37:36"}
+{"current_steps": 730, "total_steps": 5547, "loss": 0.4881, "lr": 9.969708018086472e-06, "epoch": 0.3946657055325284, "percentage": 13.16, "elapsed_time": "3:25:17", "remaining_time": "22:34:38"}
+{"current_steps": 740, "total_steps": 5547, "loss": 0.4895, "lr": 9.966151187554403e-06, "epoch": 0.40007208506037123, "percentage": 13.34, "elapsed_time": "3:28:04", "remaining_time": "22:31:40"}
+{"current_steps": 750, "total_steps": 5547, "loss": 0.487, "lr": 9.962397672993552e-06, "epoch": 0.40547846458821407, "percentage": 13.52, "elapsed_time": "3:30:54", "remaining_time": "22:28:56"}
+{"current_steps": 760, "total_steps": 5547, "loss": 0.4872, "lr": 9.958447623061564e-06, "epoch": 0.41088484411605697, "percentage": 13.7, "elapsed_time": "3:33:42", "remaining_time": "22:26:05"}
+{"current_steps": 770, "total_steps": 5547, "loss": 0.4903, "lr": 9.954301194199864e-06, "epoch": 0.4162912236438998, "percentage": 13.88, "elapsed_time": "3:36:31", "remaining_time": "22:23:15"}
+{"current_steps": 780, "total_steps": 5547, "loss": 0.4885, "lr": 9.949958550627436e-06, "epoch": 0.42169760317174265, "percentage": 14.06, "elapsed_time": "3:39:22", "remaining_time": "22:20:43"}
+{"current_steps": 790, "total_steps": 5547, "loss": 0.4774, "lr": 9.945419864334344e-06, "epoch": 0.4271039826995855, "percentage": 14.24, "elapsed_time": "3:42:08", "remaining_time": "22:17:40"}
+{"current_steps": 800, "total_steps": 5547, "loss": 0.4754, "lr": 9.940685315074898e-06, "epoch": 0.4325103622274284, "percentage": 14.42, "elapsed_time": "3:44:56", "remaining_time": "22:14:45"}
+{"current_steps": 810, "total_steps": 5547, "loss": 0.4765, "lr": 9.935755090360554e-06, "epoch": 0.43791674175527123, "percentage": 14.6, "elapsed_time": "3:47:47", "remaining_time": "22:12:07"}
+{"current_steps": 820, "total_steps": 5547, "loss": 0.4757, "lr": 9.930629385452475e-06, "epoch": 0.4433231212831141, "percentage": 14.78, "elapsed_time": "3:50:38", "remaining_time": "22:09:31"}
+{"current_steps": 830, "total_steps": 5547, "loss": 0.4871, "lr": 9.925308403353801e-06, "epoch": 0.4487295008109569, "percentage": 14.96, "elapsed_time": "3:53:26", "remaining_time": "22:06:42"}
+{"current_steps": 840, "total_steps": 5547, "loss": 0.4792, "lr": 9.919792354801614e-06, "epoch": 0.45413588033879976, "percentage": 15.14, "elapsed_time": "3:56:08", "remaining_time": "22:03:16"}
+{"current_steps": 850, "total_steps": 5547, "loss": 0.4896, "lr": 9.914081458258582e-06, "epoch": 0.45954225986664266, "percentage": 15.32, "elapsed_time": "3:59:00", "remaining_time": "22:00:45"}
+{"current_steps": 860, "total_steps": 5547, "loss": 0.492, "lr": 9.908175939904317e-06, "epoch": 0.4649486393944855, "percentage": 15.5, "elapsed_time": "4:01:49", "remaining_time": "21:57:56"}
+{"current_steps": 870, "total_steps": 5547, "loss": 0.4863, "lr": 9.902076033626409e-06, "epoch": 0.47035501892232834, "percentage": 15.68, "elapsed_time": "4:04:43", "remaining_time": "21:55:34"}
+{"current_steps": 880, "total_steps": 5547, "loss": 0.48, "lr": 9.89578198101117e-06, "epoch": 0.4757613984501712, "percentage": 15.86, "elapsed_time": "4:07:34", "remaining_time": "21:52:58"}
+{"current_steps": 890, "total_steps": 5547, "loss": 0.4875, "lr": 9.88929403133406e-06, "epoch": 0.4811677779780141, "percentage": 16.04, "elapsed_time": "4:10:20", "remaining_time": "21:49:56"}
+{"current_steps": 900, "total_steps": 5547, "loss": 0.4886, "lr": 9.882612441549817e-06, "epoch": 0.4865741575058569, "percentage": 16.22, "elapsed_time": "4:13:14", "remaining_time": "21:47:33"}
+{"current_steps": 910, "total_steps": 5547, "loss": 0.4837, "lr": 9.875737476282283e-06, "epoch": 0.49198053703369976, "percentage": 16.41, "elapsed_time": "4:16:02", "remaining_time": "21:44:43"}
+{"current_steps": 920, "total_steps": 5547, "loss": 0.4877, "lr": 9.868669407813919e-06, "epoch": 0.4973869165615426, "percentage": 16.59, "elapsed_time": "4:18:54", "remaining_time": "21:42:06"}
+{"current_steps": 930, "total_steps": 5547, "loss": 0.4826, "lr": 9.86140851607502e-06, "epoch": 0.5027932960893855, "percentage": 16.77, "elapsed_time": "4:21:36", "remaining_time": "21:38:45"}
+{"current_steps": 940, "total_steps": 5547, "loss": 0.4827, "lr": 9.85395508863264e-06, "epoch": 0.5081996756172283, "percentage": 16.95, "elapsed_time": "4:24:26", "remaining_time": "21:36:00"}
+{"current_steps": 950, "total_steps": 5547, "loss": 0.4807, "lr": 9.846309420679181e-06, "epoch": 0.5136060551450712, "percentage": 17.13, "elapsed_time": "4:27:18", "remaining_time": "21:33:30"}
+{"current_steps": 960, "total_steps": 5547, "loss": 0.483, "lr": 9.838471815020731e-06, "epoch": 0.519012434672914, "percentage": 17.31, "elapsed_time": "4:30:07", "remaining_time": "21:30:41"}
+{"current_steps": 970, "total_steps": 5547, "loss": 0.4847, "lr": 9.830442582065046e-06, "epoch": 0.5244188142007569, "percentage": 17.49, "elapsed_time": "4:32:55", "remaining_time": "21:27:47"}
+{"current_steps": 980, "total_steps": 5547, "loss": 0.4894, "lr": 9.822222039809265e-06, "epoch": 0.5298251937285997, "percentage": 17.67, "elapsed_time": "4:35:44", "remaining_time": "21:24:58"}
+{"current_steps": 990, "total_steps": 5547, "loss": 0.4757, "lr": 9.813810513827324e-06, "epoch": 0.5352315732564425, "percentage": 17.85, "elapsed_time": "4:38:28", "remaining_time": "21:21:52"}
+{"current_steps": 1000, "total_steps": 5547, "loss": 0.4844, "lr": 9.805208337257048e-06, "epoch": 0.5406379527842855, "percentage": 18.03, "elapsed_time": "4:41:18", "remaining_time": "21:19:04"}
+{"current_steps": 1010, "total_steps": 5547, "loss": 0.4712, "lr": 9.79641585078697e-06, "epoch": 0.5460443323121283, "percentage": 18.21, "elapsed_time": "4:44:07", "remaining_time": "21:16:18"}
+{"current_steps": 1020, "total_steps": 5547, "loss": 0.4793, "lr": 9.787433402642823e-06, "epoch": 0.5514507118399712, "percentage": 18.39, "elapsed_time": "4:47:01", "remaining_time": "21:13:52"}
+{"current_steps": 1030, "total_steps": 5547, "loss": 0.4838, "lr": 9.778261348573766e-06, "epoch": 0.556857091367814, "percentage": 18.57, "elapsed_time": "4:49:51", "remaining_time": "21:11:09"}
+{"current_steps": 1040, "total_steps": 5547, "loss": 0.4808, "lr": 9.76890005183828e-06, "epoch": 0.5622634708956569, "percentage": 18.75, "elapsed_time": "4:52:42", "remaining_time": "21:08:29"}
+{"current_steps": 1050, "total_steps": 5547, "loss": 0.4855, "lr": 9.759349883189788e-06, "epoch": 0.5676698504234997, "percentage": 18.93, "elapsed_time": "4:55:30", "remaining_time": "21:05:36"}
+{"current_steps": 1060, "total_steps": 5547, "loss": 0.4825, "lr": 9.749611220861975e-06, "epoch": 0.5730762299513426, "percentage": 19.11, "elapsed_time": "4:58:18", "remaining_time": "21:02:45"}
+{"current_steps": 1070, "total_steps": 5547, "loss": 0.4672, "lr": 9.739684450553796e-06, "epoch": 0.5784826094791854, "percentage": 19.29, "elapsed_time": "5:01:07", "remaining_time": "20:59:58"}
+{"current_steps": 1080, "total_steps": 5547, "loss": 0.4749, "lr": 9.729569965414214e-06, "epoch": 0.5838889890070283, "percentage": 19.47, "elapsed_time": "5:03:52", "remaining_time": "20:56:50"}
+{"current_steps": 1090, "total_steps": 5547, "loss": 0.4714, "lr": 9.719268166026619e-06, "epoch": 0.5892953685348712, "percentage": 19.65, "elapsed_time": "5:06:33", "remaining_time": "20:53:31"}
+{"current_steps": 1100, "total_steps": 5547, "loss": 0.4762, "lr": 9.70877946039297e-06, "epoch": 0.594701748062714, "percentage": 19.83, "elapsed_time": "5:09:24", "remaining_time": "20:50:49"}
+{"current_steps": 1110, "total_steps": 5547, "loss": 0.479, "lr": 9.698104263917632e-06, "epoch": 0.6001081275905569, "percentage": 20.01, "elapsed_time": "5:12:14", "remaining_time": "20:48:06"}
+{"current_steps": 1120, "total_steps": 5547, "loss": 0.4743, "lr": 9.687242999390923e-06, "epoch": 0.6055145071183997, "percentage": 20.19, "elapsed_time": "5:15:05", "remaining_time": "20:45:28"}
+{"current_steps": 1130, "total_steps": 5547, "loss": 0.4831, "lr": 9.676196096972375e-06, "epoch": 0.6109208866462426, "percentage": 20.37, "elapsed_time": "5:17:56", "remaining_time": "20:42:48"}
+{"current_steps": 1140, "total_steps": 5547, "loss": 0.4811, "lr": 9.664963994173695e-06, "epoch": 0.6163272661740854, "percentage": 20.55, "elapsed_time": "5:20:47", "remaining_time": "20:40:05"}
+{"current_steps": 1150, "total_steps": 5547, "loss": 0.482, "lr": 9.653547135841432e-06, "epoch": 0.6217336457019282, "percentage": 20.73, "elapsed_time": "5:23:29", "remaining_time": "20:36:51"}
+{"current_steps": 1160, "total_steps": 5547, "loss": 0.4808, "lr": 9.641945974139368e-06, "epoch": 0.6271400252297711, "percentage": 20.91, "elapsed_time": "5:26:15", "remaining_time": "20:33:51"}
+{"current_steps": 1170, "total_steps": 5547, "loss": 0.4742, "lr": 9.630160968530601e-06, "epoch": 0.632546404757614, "percentage": 21.09, "elapsed_time": "5:29:05", "remaining_time": "20:31:08"}
+{"current_steps": 1180, "total_steps": 5547, "loss": 0.4793, "lr": 9.618192585759358e-06, "epoch": 0.6379527842854569, "percentage": 21.27, "elapsed_time": "5:31:51", "remaining_time": "20:28:09"}
+{"current_steps": 1190, "total_steps": 5547, "loss": 0.476, "lr": 9.606041299832499e-06, "epoch": 0.6433591638132997, "percentage": 21.45, "elapsed_time": "5:34:41", "remaining_time": "20:25:23"}
+{"current_steps": 1200, "total_steps": 5547, "loss": 0.4719, "lr": 9.593707592000751e-06, "epoch": 0.6487655433411426, "percentage": 21.63, "elapsed_time": "5:37:23", "remaining_time": "20:22:12"}
+{"current_steps": 1210, "total_steps": 5547, "loss": 0.4802, "lr": 9.581191950739651e-06, "epoch": 0.6541719228689854, "percentage": 21.81, "elapsed_time": "5:40:10", "remaining_time": "20:19:18"}
+{"current_steps": 1220, "total_steps": 5547, "loss": 0.4751, "lr": 9.568494871730184e-06, "epoch": 0.6595783023968282, "percentage": 21.99, "elapsed_time": "5:42:57", "remaining_time": "20:16:22"}
+{"current_steps": 1230, "total_steps": 5547, "loss": 0.476, "lr": 9.555616857839171e-06, "epoch": 0.6649846819246711, "percentage": 22.17, "elapsed_time": "5:45:51", "remaining_time": "20:13:51"}
+{"current_steps": 1240, "total_steps": 5547, "loss": 0.4671, "lr": 9.542558419099348e-06, "epoch": 0.6703910614525139, "percentage": 22.35, "elapsed_time": "5:48:34", "remaining_time": "20:10:44"}
+{"current_steps": 1250, "total_steps": 5547, "loss": 0.4663, "lr": 9.529320072689157e-06, "epoch": 0.6757974409803568, "percentage": 22.53, "elapsed_time": "5:51:23", "remaining_time": "20:07:57"}
+{"current_steps": 1260, "total_steps": 5547, "loss": 0.4696, "lr": 9.515902342912268e-06, "epoch": 0.6812038205081997, "percentage": 22.71, "elapsed_time": "5:54:15", "remaining_time": "20:05:17"}
+{"current_steps": 1270, "total_steps": 5547, "loss": 0.4742, "lr": 9.50230576117682e-06, "epoch": 0.6866102000360426, "percentage": 22.9, "elapsed_time": "5:56:59", "remaining_time": "20:02:14"}
+{"current_steps": 1280, "total_steps": 5547, "loss": 0.4701, "lr": 9.488530865974365e-06, "epoch": 0.6920165795638854, "percentage": 23.08, "elapsed_time": "5:59:49", "remaining_time": "19:59:30"}
+{"current_steps": 1290, "total_steps": 5547, "loss": 0.4701, "lr": 9.47457820285855e-06, "epoch": 0.6974229590917282, "percentage": 23.26, "elapsed_time": "6:02:37", "remaining_time": "19:56:40"}
+{"current_steps": 1300, "total_steps": 5547, "loss": 0.4767, "lr": 9.460448324423508e-06, "epoch": 0.7028293386195711, "percentage": 23.44, "elapsed_time": "6:05:28", "remaining_time": "19:53:58"}
+{"current_steps": 1310, "total_steps": 5547, "loss": 0.4757, "lr": 9.446141790281961e-06, "epoch": 0.7082357181474139, "percentage": 23.62, "elapsed_time": "6:08:20", "remaining_time": "19:51:19"}
+{"current_steps": 1320, "total_steps": 5547, "loss": 0.4657, "lr": 9.431659167043079e-06, "epoch": 0.7136420976752568, "percentage": 23.8, "elapsed_time": "6:11:03", "remaining_time": "19:48:14"}
+{"current_steps": 1330, "total_steps": 5547, "loss": 0.47, "lr": 9.417001028290019e-06, "epoch": 0.7190484772030996, "percentage": 23.98, "elapsed_time": "6:13:55", "remaining_time": "19:45:36"}
+{"current_steps": 1340, "total_steps": 5547, "loss": 0.4622, "lr": 9.402167954557218e-06, "epoch": 0.7244548567309426, "percentage": 24.16, "elapsed_time": "6:16:35", "remaining_time": "19:42:20"}
+{"current_steps": 1350, "total_steps": 5547, "loss": 0.4735, "lr": 9.387160533307398e-06, "epoch": 0.7298612362587854, "percentage": 24.34, "elapsed_time": "6:19:24", "remaining_time": "19:39:31"}
+{"current_steps": 1360, "total_steps": 5547, "loss": 0.4647, "lr": 9.371979358908302e-06, "epoch": 0.7352676157866282, "percentage": 24.52, "elapsed_time": "6:22:10", "remaining_time": "19:36:36"}
+{"current_steps": 1370, "total_steps": 5547, "loss": 0.4716, "lr": 9.356625032609157e-06, "epoch": 0.7406739953144711, "percentage": 24.7, "elapsed_time": "6:24:56", "remaining_time": "19:33:39"}
+{"current_steps": 1380, "total_steps": 5547, "loss": 0.4753, "lr": 9.341098162516848e-06, "epoch": 0.7460803748423139, "percentage": 24.88, "elapsed_time": "6:27:40", "remaining_time": "19:30:36"}
+{"current_steps": 1390, "total_steps": 5547, "loss": 0.4637, "lr": 9.325399363571853e-06, "epoch": 0.7514867543701568, "percentage": 25.06, "elapsed_time": "6:30:24", "remaining_time": "19:27:34"}
+{"current_steps": 1400, "total_steps": 5547, "loss": 0.4833, "lr": 9.309529257523873e-06, "epoch": 0.7568931338979996, "percentage": 25.24, "elapsed_time": "6:33:06", "remaining_time": "19:24:25"}
+{"current_steps": 1410, "total_steps": 5547, "loss": 0.4741, "lr": 9.293488472907213e-06, "epoch": 0.7622995134258425, "percentage": 25.42, "elapsed_time": "6:35:48", "remaining_time": "19:21:17"}
+{"current_steps": 1420, "total_steps": 5547, "loss": 0.4645, "lr": 9.277277645015895e-06, "epoch": 0.7677058929536853, "percentage": 25.6, "elapsed_time": "6:38:36", "remaining_time": "19:18:30"}
+{"current_steps": 1430, "total_steps": 5547, "loss": 0.4737, "lr": 9.260897415878484e-06, "epoch": 0.7731122724815283, "percentage": 25.78, "elapsed_time": "6:41:28", "remaining_time": "19:15:52"}
+{"current_steps": 1440, "total_steps": 5547, "loss": 0.4807, "lr": 9.244348434232676e-06, "epoch": 0.7785186520093711, "percentage": 25.96, "elapsed_time": "6:44:18", "remaining_time": "19:13:06"}
+{"current_steps": 1450, "total_steps": 5547, "loss": 0.4711, "lr": 9.227631355499588e-06, "epoch": 0.7839250315372139, "percentage": 26.14, "elapsed_time": "6:47:11", "remaining_time": "19:10:31"}
+{"current_steps": 1460, "total_steps": 5547, "loss": 0.4606, "lr": 9.210746841757816e-06, "epoch": 0.7893314110650568, "percentage": 26.32, "elapsed_time": "6:49:57", "remaining_time": "19:07:35"}
+{"current_steps": 1470, "total_steps": 5547, "loss": 0.4789, "lr": 9.193695561717207e-06, "epoch": 0.7947377905928996, "percentage": 26.5, "elapsed_time": "6:52:46", "remaining_time": "19:04:48"}
+{"current_steps": 1480, "total_steps": 5547, "loss": 0.4713, "lr": 9.176478190692369e-06, "epoch": 0.8001441701207425, "percentage": 26.68, "elapsed_time": "6:55:33", "remaining_time": "19:01:55"}
+{"current_steps": 1490, "total_steps": 5547, "loss": 0.4725, "lr": 9.159095410575931e-06, "epoch": 0.8055505496485853, "percentage": 26.86, "elapsed_time": "6:58:24", "remaining_time": "18:59:14"}
+{"current_steps": 1500, "total_steps": 5547, "loss": 0.4594, "lr": 9.14154790981154e-06, "epoch": 0.8109569291764281, "percentage": 27.04, "elapsed_time": "7:01:16", "remaining_time": "18:56:34"}
+{"current_steps": 1510, "total_steps": 5547, "loss": 0.4731, "lr": 9.12383638336659e-06, "epoch": 0.816363308704271, "percentage": 27.22, "elapsed_time": "7:04:02", "remaining_time": "18:53:41"}
+{"current_steps": 1520, "total_steps": 5547, "loss": 0.4744, "lr": 9.105961532704695e-06, "epoch": 0.8217696882321139, "percentage": 27.4, "elapsed_time": "7:06:56", "remaining_time": "18:51:06"}
+{"current_steps": 1530, "total_steps": 5547, "loss": 0.4596, "lr": 9.08792406575792e-06, "epoch": 0.8271760677599568, "percentage": 27.58, "elapsed_time": "7:09:46", "remaining_time": "18:48:23"}
+{"current_steps": 1540, "total_steps": 5547, "loss": 0.4644, "lr": 9.069724696898727e-06, "epoch": 0.8325824472877996, "percentage": 27.76, "elapsed_time": "7:12:39", "remaining_time": "18:45:44"}
+{"current_steps": 1550, "total_steps": 5547, "loss": 0.4695, "lr": 9.051364146911696e-06, "epoch": 0.8379888268156425, "percentage": 27.94, "elapsed_time": "7:15:30", "remaining_time": "18:43:02"}
+{"current_steps": 1560, "total_steps": 5547, "loss": 0.4699, "lr": 9.03284314296497e-06, "epoch": 0.8433952063434853, "percentage": 28.12, "elapsed_time": "7:18:21", "remaining_time": "18:40:19"}
+{"current_steps": 1570, "total_steps": 5547, "loss": 0.4669, "lr": 9.01416241858146e-06, "epoch": 0.8488015858713281, "percentage": 28.3, "elapsed_time": "7:21:10", "remaining_time": "18:37:33"}
+{"current_steps": 1580, "total_steps": 5547, "loss": 0.4672, "lr": 8.995322713609792e-06, "epoch": 0.854207965399171, "percentage": 28.48, "elapsed_time": "7:24:02", "remaining_time": "18:34:52"}
+{"current_steps": 1590, "total_steps": 5547, "loss": 0.4683, "lr": 8.976324774195005e-06, "epoch": 0.8596143449270138, "percentage": 28.66, "elapsed_time": "7:26:54", "remaining_time": "18:32:12"}
+{"current_steps": 1600, "total_steps": 5547, "loss": 0.4652, "lr": 8.957169352749005e-06, "epoch": 0.8650207244548568, "percentage": 28.84, "elapsed_time": "7:29:45", "remaining_time": "18:29:30"}
+{"current_steps": 1610, "total_steps": 5547, "loss": 0.4693, "lr": 8.937857207920751e-06, "epoch": 0.8704271039826996, "percentage": 29.02, "elapsed_time": "7:32:33", "remaining_time": "18:26:39"}
+{"current_steps": 1620, "total_steps": 5547, "loss": 0.4653, "lr": 8.918389104566232e-06, "epoch": 0.8758334835105425, "percentage": 29.2, "elapsed_time": "7:35:18", "remaining_time": "18:23:43"}
+{"current_steps": 1630, "total_steps": 5547, "loss": 0.4575, "lr": 8.898765813718155e-06, "epoch": 0.8812398630383853, "percentage": 29.39, "elapsed_time": "7:38:11", "remaining_time": "18:21:04"}
+{"current_steps": 1640, "total_steps": 5547, "loss": 0.4635, "lr": 8.878988112555415e-06, "epoch": 0.8866462425662281, "percentage": 29.57, "elapsed_time": "7:41:00", "remaining_time": "18:18:15"}
+{"current_steps": 1650, "total_steps": 5547, "loss": 0.4637, "lr": 8.85905678437232e-06, "epoch": 0.892052622094071, "percentage": 29.75, "elapsed_time": "7:43:47", "remaining_time": "18:15:22"}
+{"current_steps": 1660, "total_steps": 5547, "loss": 0.4668, "lr": 8.838972618547561e-06, "epoch": 0.8974590016219138, "percentage": 29.93, "elapsed_time": "7:46:40", "remaining_time": "18:12:44"}
+{"current_steps": 1670, "total_steps": 5547, "loss": 0.4626, "lr": 8.81873641051295e-06, "epoch": 0.9028653811497567, "percentage": 30.11, "elapsed_time": "7:49:25", "remaining_time": "18:09:47"}
+{"current_steps": 1680, "total_steps": 5547, "loss": 0.4618, "lr": 8.798348961721925e-06, "epoch": 0.9082717606775995, "percentage": 30.29, "elapsed_time": "7:52:17", "remaining_time": "18:07:07"}
+{"current_steps": 1690, "total_steps": 5547, "loss": 0.4735, "lr": 8.777811079617793e-06, "epoch": 0.9136781402054425, "percentage": 30.47, "elapsed_time": "7:55:04", "remaining_time": "18:04:15"}
+{"current_steps": 1700, "total_steps": 5547, "loss": 0.4642, "lr": 8.757123577601771e-06, "epoch": 0.9190845197332853, "percentage": 30.65, "elapsed_time": "7:57:53", "remaining_time": "18:01:27"}
+{"current_steps": 1710, "total_steps": 5547, "loss": 0.465, "lr": 8.736287275000755e-06, "epoch": 0.9244908992611282, "percentage": 30.83, "elapsed_time": "8:00:41", "remaining_time": "17:58:36"}
+{"current_steps": 1720, "total_steps": 5547, "loss": 0.4702, "lr": 8.715302997034876e-06, "epoch": 0.929897278788971, "percentage": 31.01, "elapsed_time": "8:03:38", "remaining_time": "17:56:05"}
+{"current_steps": 1730, "total_steps": 5547, "loss": 0.4674, "lr": 8.694171574784818e-06, "epoch": 0.9353036583168138, "percentage": 31.19, "elapsed_time": "8:06:25", "remaining_time": "17:53:14"}
+{"current_steps": 1740, "total_steps": 5547, "loss": 0.4701, "lr": 8.672893845158908e-06, "epoch": 0.9407100378446567, "percentage": 31.37, "elapsed_time": "8:09:09", "remaining_time": "17:50:15"}
+{"current_steps": 1750, "total_steps": 5547, "loss": 0.4599, "lr": 8.651470650859955e-06, "epoch": 0.9461164173724995, "percentage": 31.55, "elapsed_time": "8:11:58", "remaining_time": "17:47:27"}
+{"current_steps": 1760, "total_steps": 5547, "loss": 0.4637, "lr": 8.629902840351898e-06, "epoch": 0.9515227969003424, "percentage": 31.73, "elapsed_time": "8:14:50", "remaining_time": "17:44:45"}
+{"current_steps": 1770, "total_steps": 5547, "loss": 0.4694, "lr": 8.608191267826179e-06, "epoch": 0.9569291764281853, "percentage": 31.91, "elapsed_time": "8:17:39", "remaining_time": "17:41:56"}
+{"current_steps": 1780, "total_steps": 5547, "loss": 0.4641, "lr": 8.586336793167926e-06, "epoch": 0.9623355559560282, "percentage": 32.09, "elapsed_time": "8:20:31", "remaining_time": "17:39:15"}
+{"current_steps": 1790, "total_steps": 5547, "loss": 0.4566, "lr": 8.5643402819219e-06, "epoch": 0.967741935483871, "percentage": 32.27, "elapsed_time": "8:23:19", "remaining_time": "17:36:24"}
+{"current_steps": 1800, "total_steps": 5547, "loss": 0.463, "lr": 8.542202605258204e-06, "epoch": 0.9731483150117138, "percentage": 32.45, "elapsed_time": "8:26:04", "remaining_time": "17:33:28"}
+{"current_steps": 1810, "total_steps": 5547, "loss": 0.4617, "lr": 8.519924639937786e-06, "epoch": 0.9785546945395567, "percentage": 32.63, "elapsed_time": "8:28:47", "remaining_time": "17:30:29"}
+{"current_steps": 1820, "total_steps": 5547, "loss": 0.4565, "lr": 8.49750726827772e-06, "epoch": 0.9839610740673995, "percentage": 32.81, "elapsed_time": "8:31:40", "remaining_time": "17:27:48"}
+{"current_steps": 1830, "total_steps": 5547, "loss": 0.4639, "lr": 8.474951378116253e-06, "epoch": 0.9893674535952424, "percentage": 32.99, "elapsed_time": "8:34:27", "remaining_time": "17:24:57"}
+{"current_steps": 1840, "total_steps": 5547, "loss": 0.4546, "lr": 8.452257862777653e-06, "epoch": 0.9947738331230852, "percentage": 33.17, "elapsed_time": "8:37:13", "remaining_time": "17:22:02"}
+{"current_steps": 1850, "total_steps": 5547, "loss": 0.4837, "lr": 8.42942762103681e-06, "epoch": 1.000180212650928, "percentage": 33.35, "elapsed_time": "8:41:07", "remaining_time": "17:21:23"}
+{"current_steps": 1860, "total_steps": 5547, "loss": 0.4404, "lr": 8.406461557083666e-06, "epoch": 1.005586592178771, "percentage": 33.53, "elapsed_time": "8:44:01", "remaining_time": "17:18:44"}
+{"current_steps": 1870, "total_steps": 5547, "loss": 0.4393, "lr": 8.383360580487378e-06, "epoch": 1.0109929717066137, "percentage": 33.71, "elapsed_time": "8:46:43", "remaining_time": "17:15:42"}
+{"current_steps": 1880, "total_steps": 5547, "loss": 0.4422, "lr": 8.360125606160323e-06, "epoch": 1.0163993512344567, "percentage": 33.89, "elapsed_time": "8:49:34", "remaining_time": "17:12:57"}
+{"current_steps": 1890, "total_steps": 5547, "loss": 0.4424, "lr": 8.336757554321832e-06, "epoch": 1.0218057307622994, "percentage": 34.07, "elapsed_time": "8:52:25", "remaining_time": "17:10:11"}
+{"current_steps": 1900, "total_steps": 5547, "loss": 0.4376, "lr": 8.313257350461774e-06, "epoch": 1.0272121102901424, "percentage": 34.25, "elapsed_time": "8:55:14", "remaining_time": "17:07:22"}
+{"current_steps": 1910, "total_steps": 5547, "loss": 0.4425, "lr": 8.289625925303877e-06, "epoch": 1.0326184898179853, "percentage": 34.43, "elapsed_time": "8:58:02", "remaining_time": "17:04:31"}
+{"current_steps": 1920, "total_steps": 5547, "loss": 0.4503, "lr": 8.265864214768883e-06, "epoch": 1.038024869345828, "percentage": 34.61, "elapsed_time": "9:00:53", "remaining_time": "17:01:45"}
+{"current_steps": 1930, "total_steps": 5547, "loss": 0.4406, "lr": 8.241973159937482e-06, "epoch": 1.043431248873671, "percentage": 34.79, "elapsed_time": "9:03:46", "remaining_time": "16:59:04"}
+{"current_steps": 1940, "total_steps": 5547, "loss": 0.4393, "lr": 8.217953707013025e-06, "epoch": 1.0488376284015137, "percentage": 34.97, "elapsed_time": "9:06:31", "remaining_time": "16:56:08"}
+{"current_steps": 1950, "total_steps": 5547, "loss": 0.4383, "lr": 8.193806807284064e-06, "epoch": 1.0542440079293567, "percentage": 35.15, "elapsed_time": "9:09:15", "remaining_time": "16:53:10"}
+{"current_steps": 1960, "total_steps": 5547, "loss": 0.4286, "lr": 8.169533417086673e-06, "epoch": 1.0596503874571994, "percentage": 35.33, "elapsed_time": "9:12:04", "remaining_time": "16:50:21"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9810eaf130ad3c5c10a9cb49fa537a728ebfa5af403a2725de0337a8d60aea42
+size 7288