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:a4f4115132c39191db1f37b415b8a3eb478fe0645afffa3f43b0b308c8dd27fc
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b5b485f615f36e55c588a3e57c9194b81dea9dc2b93c24bd2523be88e4be6af
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb92e3c9e647b072359e24b45e464e4f651d006318ec9490f6682e87a111106d
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c802735f2e287a83e621605e5369d4ad31b1aa50de94819e45531c0010b860
+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 +1,296 @@
+{"current_steps": 1, "total_steps": 1480, "loss": 0.8392, "lr": 5.405405405405406e-07, "epoch": 0.0033691303432301536, "percentage": 0.07, "elapsed_time": "0:04:31", "remaining_time": "4 days, 15:26:07"}
+{"current_steps": 2, "total_steps": 1480, "loss": 0.8536, "lr": 1.0810810810810812e-06, "epoch": 0.006738260686460307, "percentage": 0.14, "elapsed_time": "0:08:12", "remaining_time": "4 days, 5:10:55"}
+{"current_steps": 3, "total_steps": 1480, "loss": 0.8621, "lr": 1.6216216216216219e-06, "epoch": 0.01010739102969046, "percentage": 0.2, "elapsed_time": "0:11:53", "remaining_time": "4 days, 1:33:53"}
+{"current_steps": 4, "total_steps": 1480, "loss": 0.8421, "lr": 2.1621621621621623e-06, "epoch": 0.013476521372920615, "percentage": 0.27, "elapsed_time": "0:15:34", "remaining_time": "3 days, 23:48:00"}
+{"current_steps": 5, "total_steps": 1480, "loss": 0.8301, "lr": 2.702702702702703e-06, "epoch": 0.01684565171615077, "percentage": 0.34, "elapsed_time": "0:19:15", "remaining_time": "3 days, 22:40:21"}
+{"current_steps": 6, "total_steps": 1480, "loss": 0.7947, "lr": 3.2432432432432437e-06, "epoch": 0.02021478205938092, "percentage": 0.41, "elapsed_time": "0:22:56", "remaining_time": "3 days, 21:54:20"}
+{"current_steps": 7, "total_steps": 1480, "loss": 0.7537, "lr": 3.7837837837837844e-06, "epoch": 0.023583912402611075, "percentage": 0.47, "elapsed_time": "0:26:37", "remaining_time": "3 days, 21:21:10"}
+{"current_steps": 8, "total_steps": 1480, "loss": 0.7536, "lr": 4.324324324324325e-06, "epoch": 0.02695304274584123, "percentage": 0.54, "elapsed_time": "0:30:18", "remaining_time": "3 days, 20:55:34"}
+{"current_steps": 9, "total_steps": 1480, "loss": 0.7464, "lr": 4.864864864864866e-06, "epoch": 0.030322173089071383, "percentage": 0.61, "elapsed_time": "0:33:58", "remaining_time": "3 days, 20:34:15"}
+{"current_steps": 10, "total_steps": 1480, "loss": 0.7471, "lr": 5.405405405405406e-06, "epoch": 0.03369130343230154, "percentage": 0.68, "elapsed_time": "0:37:39", "remaining_time": "3 days, 20:16:24"}
+{"current_steps": 11, "total_steps": 1480, "loss": 0.7372, "lr": 5.945945945945947e-06, "epoch": 0.03706043377553169, "percentage": 0.74, "elapsed_time": "0:41:20", "remaining_time": "3 days, 20:01:48"}
+{"current_steps": 12, "total_steps": 1480, "loss": 0.7303, "lr": 6.486486486486487e-06, "epoch": 0.04042956411876184, "percentage": 0.81, "elapsed_time": "0:45:02", "remaining_time": "3 days, 19:49:32"}
+{"current_steps": 13, "total_steps": 1480, "loss": 0.6951, "lr": 7.027027027027028e-06, "epoch": 0.043798694461992, "percentage": 0.88, "elapsed_time": "0:48:43", "remaining_time": "3 days, 19:37:38"}
+{"current_steps": 14, "total_steps": 1480, "loss": 0.6964, "lr": 7.567567567567569e-06, "epoch": 0.04716782480522215, "percentage": 0.95, "elapsed_time": "0:52:23", "remaining_time": "3 days, 19:26:49"}
+{"current_steps": 15, "total_steps": 1480, "loss": 0.6719, "lr": 8.108108108108109e-06, "epoch": 0.05053695514845231, "percentage": 1.01, "elapsed_time": "0:56:04", "remaining_time": "3 days, 19:17:28"}
+{"current_steps": 16, "total_steps": 1480, "loss": 0.6547, "lr": 8.64864864864865e-06, "epoch": 0.05390608549168246, "percentage": 1.08, "elapsed_time": "0:59:46", "remaining_time": "3 days, 19:08:49"}
+{"current_steps": 17, "total_steps": 1480, "loss": 0.6523, "lr": 9.189189189189191e-06, "epoch": 0.057275215834912616, "percentage": 1.15, "elapsed_time": "1:03:26", "remaining_time": "3 days, 19:00:15"}
+{"current_steps": 18, "total_steps": 1480, "loss": 0.6431, "lr": 9.729729729729732e-06, "epoch": 0.060644346178142766, "percentage": 1.22, "elapsed_time": "1:07:07", "remaining_time": "3 days, 18:52:27"}
+{"current_steps": 19, "total_steps": 1480, "loss": 0.6396, "lr": 1.027027027027027e-05, "epoch": 0.06401347652137292, "percentage": 1.28, "elapsed_time": "1:10:49", "remaining_time": "3 days, 18:45:31"}
+{"current_steps": 20, "total_steps": 1480, "loss": 0.6283, "lr": 1.0810810810810812e-05, "epoch": 0.06738260686460308, "percentage": 1.35, "elapsed_time": "1:14:30", "remaining_time": "3 days, 18:38:59"}
+{"current_steps": 21, "total_steps": 1480, "loss": 0.6154, "lr": 1.1351351351351352e-05, "epoch": 0.07075173720783323, "percentage": 1.42, "elapsed_time": "1:18:11", "remaining_time": "3 days, 18:32:05"}
+{"current_steps": 22, "total_steps": 1480, "loss": 0.6044, "lr": 1.1891891891891894e-05, "epoch": 0.07412086755106338, "percentage": 1.49, "elapsed_time": "1:21:52", "remaining_time": "3 days, 18:25:42"}
+{"current_steps": 23, "total_steps": 1480, "loss": 0.603, "lr": 1.2432432432432433e-05, "epoch": 0.07748999789429353, "percentage": 1.55, "elapsed_time": "1:25:34", "remaining_time": "3 days, 18:20:31"}
+{"current_steps": 24, "total_steps": 1480, "loss": 0.6013, "lr": 1.2972972972972975e-05, "epoch": 0.08085912823752368, "percentage": 1.62, "elapsed_time": "1:29:15", "remaining_time": "3 days, 18:14:43"}
+{"current_steps": 25, "total_steps": 1480, "loss": 0.5786, "lr": 1.3513513513513515e-05, "epoch": 0.08422825858075385, "percentage": 1.69, "elapsed_time": "1:32:56", "remaining_time": "3 days, 18:09:03"}
+{"current_steps": 26, "total_steps": 1480, "loss": 0.5786, "lr": 1.4054054054054055e-05, "epoch": 0.087597388923984, "percentage": 1.76, "elapsed_time": "1:36:36", "remaining_time": "3 days, 18:03:04"}
+{"current_steps": 27, "total_steps": 1480, "loss": 0.5727, "lr": 1.4594594594594596e-05, "epoch": 0.09096651926721415, "percentage": 1.82, "elapsed_time": "1:40:17", "remaining_time": "3 days, 17:57:09"}
+{"current_steps": 28, "total_steps": 1480, "loss": 0.5756, "lr": 1.5135135135135138e-05, "epoch": 0.0943356496104443, "percentage": 1.89, "elapsed_time": "1:43:58", "remaining_time": "3 days, 17:51:47"}
+{"current_steps": 29, "total_steps": 1480, "loss": 0.5635, "lr": 1.5675675675675676e-05, "epoch": 0.09770477995367446, "percentage": 1.96, "elapsed_time": "1:47:39", "remaining_time": "3 days, 17:46:28"}
+{"current_steps": 30, "total_steps": 1480, "loss": 0.5627, "lr": 1.6216216216216218e-05, "epoch": 0.10107391029690461, "percentage": 2.03, "elapsed_time": "1:51:20", "remaining_time": "3 days, 17:41:10"}
+{"current_steps": 31, "total_steps": 1480, "loss": 0.5621, "lr": 1.6756756756756757e-05, "epoch": 0.10444304064013477, "percentage": 2.09, "elapsed_time": "1:55:00", "remaining_time": "3 days, 17:35:49"}
+{"current_steps": 32, "total_steps": 1480, "loss": 0.5572, "lr": 1.72972972972973e-05, "epoch": 0.10781217098336492, "percentage": 2.16, "elapsed_time": "1:58:41", "remaining_time": "3 days, 17:30:29"}
+{"current_steps": 33, "total_steps": 1480, "loss": 0.5475, "lr": 1.783783783783784e-05, "epoch": 0.11118130132659507, "percentage": 2.23, "elapsed_time": "2:02:22", "remaining_time": "3 days, 17:25:38"}
+{"current_steps": 34, "total_steps": 1480, "loss": 0.5487, "lr": 1.8378378378378383e-05, "epoch": 0.11455043166982523, "percentage": 2.3, "elapsed_time": "2:06:02", "remaining_time": "3 days, 17:20:24"}
+{"current_steps": 35, "total_steps": 1480, "loss": 0.5496, "lr": 1.891891891891892e-05, "epoch": 0.11791956201305538, "percentage": 2.36, "elapsed_time": "2:09:43", "remaining_time": "3 days, 17:15:37"}
+{"current_steps": 36, "total_steps": 1480, "loss": 0.5394, "lr": 1.9459459459459463e-05, "epoch": 0.12128869235628553, "percentage": 2.43, "elapsed_time": "2:13:24", "remaining_time": "3 days, 17:11:27"}
+{"current_steps": 37, "total_steps": 1480, "loss": 0.5406, "lr": 2e-05, "epoch": 0.12465782269951568, "percentage": 2.5, "elapsed_time": "2:17:05", "remaining_time": "3 days, 17:06:45"}
+{"current_steps": 38, "total_steps": 1480, "loss": 0.5435, "lr": 2.054054054054054e-05, "epoch": 0.12802695304274583, "percentage": 2.57, "elapsed_time": "2:20:46", "remaining_time": "3 days, 17:02:00"}
+{"current_steps": 39, "total_steps": 1480, "loss": 0.5354, "lr": 2.1081081081081082e-05, "epoch": 0.131396083385976, "percentage": 2.64, "elapsed_time": "2:24:27", "remaining_time": "3 days, 16:57:22"}
+{"current_steps": 40, "total_steps": 1480, "loss": 0.5363, "lr": 2.1621621621621624e-05, "epoch": 0.13476521372920616, "percentage": 2.7, "elapsed_time": "2:28:08", "remaining_time": "3 days, 16:53:03"}
+{"current_steps": 41, "total_steps": 1480, "loss": 0.5217, "lr": 2.2162162162162163e-05, "epoch": 0.1381343440724363, "percentage": 2.77, "elapsed_time": "2:31:49", "remaining_time": "3 days, 16:48:32"}
+{"current_steps": 42, "total_steps": 1480, "loss": 0.531, "lr": 2.2702702702702705e-05, "epoch": 0.14150347441566646, "percentage": 2.84, "elapsed_time": "2:35:30", "remaining_time": "3 days, 16:44:09"}
+{"current_steps": 43, "total_steps": 1480, "loss": 0.5257, "lr": 2.3243243243243243e-05, "epoch": 0.1448726047588966, "percentage": 2.91, "elapsed_time": "2:39:11", "remaining_time": "3 days, 16:39:47"}
+{"current_steps": 44, "total_steps": 1480, "loss": 0.5253, "lr": 2.378378378378379e-05, "epoch": 0.14824173510212676, "percentage": 2.97, "elapsed_time": "2:42:51", "remaining_time": "3 days, 16:35:10"}
+{"current_steps": 45, "total_steps": 1480, "loss": 0.5181, "lr": 2.4324324324324327e-05, "epoch": 0.15161086544535693, "percentage": 3.04, "elapsed_time": "2:46:32", "remaining_time": "3 days, 16:30:51"}
+{"current_steps": 46, "total_steps": 1480, "loss": 0.523, "lr": 2.4864864864864866e-05, "epoch": 0.15497999578858707, "percentage": 3.11, "elapsed_time": "2:50:13", "remaining_time": "3 days, 16:26:26"}
+{"current_steps": 47, "total_steps": 1480, "loss": 0.5177, "lr": 2.5405405405405404e-05, "epoch": 0.15834912613181723, "percentage": 3.18, "elapsed_time": "2:53:54", "remaining_time": "3 days, 16:22:13"}
+{"current_steps": 48, "total_steps": 1480, "loss": 0.5155, "lr": 2.594594594594595e-05, "epoch": 0.16171825647504737, "percentage": 3.24, "elapsed_time": "2:57:34", "remaining_time": "3 days, 16:17:35"}
+{"current_steps": 49, "total_steps": 1480, "loss": 0.513, "lr": 2.6486486486486488e-05, "epoch": 0.16508738681827753, "percentage": 3.31, "elapsed_time": "3:01:14", "remaining_time": "3 days, 16:13:00"}
+{"current_steps": 50, "total_steps": 1480, "loss": 0.5098, "lr": 2.702702702702703e-05, "epoch": 0.1684565171615077, "percentage": 3.38, "elapsed_time": "3:04:55", "remaining_time": "3 days, 16:08:45"}
+{"current_steps": 51, "total_steps": 1480, "loss": 0.5164, "lr": 2.756756756756757e-05, "epoch": 0.17182564750473783, "percentage": 3.45, "elapsed_time": "3:08:36", "remaining_time": "3 days, 16:04:33"}
+{"current_steps": 52, "total_steps": 1480, "loss": 0.5137, "lr": 2.810810810810811e-05, "epoch": 0.175194777847968, "percentage": 3.51, "elapsed_time": "3:12:16", "remaining_time": "3 days, 16:00:20"}
+{"current_steps": 53, "total_steps": 1480, "loss": 0.5093, "lr": 2.8648648648648653e-05, "epoch": 0.17856390819119813, "percentage": 3.58, "elapsed_time": "3:15:57", "remaining_time": "3 days, 15:56:18"}
+{"current_steps": 54, "total_steps": 1480, "loss": 0.4999, "lr": 2.918918918918919e-05, "epoch": 0.1819330385344283, "percentage": 3.65, "elapsed_time": "3:19:38", "remaining_time": "3 days, 15:51:58"}
+{"current_steps": 55, "total_steps": 1480, "loss": 0.5036, "lr": 2.972972972972973e-05, "epoch": 0.18530216887765846, "percentage": 3.72, "elapsed_time": "3:23:19", "remaining_time": "3 days, 15:47:52"}
+{"current_steps": 56, "total_steps": 1480, "loss": 0.5084, "lr": 3.0270270270270275e-05, "epoch": 0.1886712992208886, "percentage": 3.78, "elapsed_time": "3:27:00", "remaining_time": "3 days, 15:43:51"}
+{"current_steps": 57, "total_steps": 1480, "loss": 0.5136, "lr": 3.081081081081082e-05, "epoch": 0.19204042956411876, "percentage": 3.85, "elapsed_time": "3:30:40", "remaining_time": "3 days, 15:39:38"}
+{"current_steps": 58, "total_steps": 1480, "loss": 0.5066, "lr": 3.135135135135135e-05, "epoch": 0.19540955990734893, "percentage": 3.92, "elapsed_time": "3:34:21", "remaining_time": "3 days, 15:35:18"}
+{"current_steps": 59, "total_steps": 1480, "loss": 0.5081, "lr": 3.1891891891891894e-05, "epoch": 0.19877869025057907, "percentage": 3.99, "elapsed_time": "3:38:01", "remaining_time": "3 days, 15:31:13"}
+{"current_steps": 60, "total_steps": 1480, "loss": 0.5056, "lr": 3.2432432432432436e-05, "epoch": 0.20214782059380923, "percentage": 4.05, "elapsed_time": "3:41:42", "remaining_time": "3 days, 15:27:07"}
+{"current_steps": 61, "total_steps": 1480, "loss": 0.5037, "lr": 3.297297297297298e-05, "epoch": 0.20551695093703937, "percentage": 4.12, "elapsed_time": "3:45:23", "remaining_time": "3 days, 15:23:12"}
+{"current_steps": 62, "total_steps": 1480, "loss": 0.4956, "lr": 3.351351351351351e-05, "epoch": 0.20888608128026953, "percentage": 4.19, "elapsed_time": "3:49:05", "remaining_time": "3 days, 15:19:24"}
+{"current_steps": 63, "total_steps": 1480, "loss": 0.4943, "lr": 3.4054054054054055e-05, "epoch": 0.2122552116234997, "percentage": 4.26, "elapsed_time": "3:52:46", "remaining_time": "3 days, 15:15:26"}
+{"current_steps": 64, "total_steps": 1480, "loss": 0.5063, "lr": 3.45945945945946e-05, "epoch": 0.21562434196672983, "percentage": 4.32, "elapsed_time": "3:56:26", "remaining_time": "3 days, 15:11:25"}
+{"current_steps": 65, "total_steps": 1480, "loss": 0.4903, "lr": 3.513513513513514e-05, "epoch": 0.21899347230996, "percentage": 4.39, "elapsed_time": "4:00:07", "remaining_time": "3 days, 15:07:28"}
+{"current_steps": 66, "total_steps": 1480, "loss": 0.5051, "lr": 3.567567567567568e-05, "epoch": 0.22236260265319013, "percentage": 4.46, "elapsed_time": "4:03:49", "remaining_time": "3 days, 15:03:37"}
+{"current_steps": 67, "total_steps": 1480, "loss": 0.5014, "lr": 3.6216216216216216e-05, "epoch": 0.2257317329964203, "percentage": 4.53, "elapsed_time": "4:07:30", "remaining_time": "3 days, 14:59:43"}
+{"current_steps": 68, "total_steps": 1480, "loss": 0.4995, "lr": 3.6756756756756765e-05, "epoch": 0.22910086333965046, "percentage": 4.59, "elapsed_time": "4:11:10", "remaining_time": "3 days, 14:55:43"}
+{"current_steps": 69, "total_steps": 1480, "loss": 0.497, "lr": 3.72972972972973e-05, "epoch": 0.2324699936828806, "percentage": 4.66, "elapsed_time": "4:14:52", "remaining_time": "3 days, 14:51:53"}
+{"current_steps": 70, "total_steps": 1480, "loss": 0.4872, "lr": 3.783783783783784e-05, "epoch": 0.23583912402611076, "percentage": 4.73, "elapsed_time": "4:18:33", "remaining_time": "3 days, 14:48:00"}
+{"current_steps": 71, "total_steps": 1480, "loss": 0.4933, "lr": 3.837837837837838e-05, "epoch": 0.2392082543693409, "percentage": 4.8, "elapsed_time": "4:22:13", "remaining_time": "3 days, 14:44:02"}
+{"current_steps": 72, "total_steps": 1480, "loss": 0.4984, "lr": 3.8918918918918926e-05, "epoch": 0.24257738471257106, "percentage": 4.86, "elapsed_time": "4:25:54", "remaining_time": "3 days, 14:40:08"}
+{"current_steps": 73, "total_steps": 1480, "loss": 0.4941, "lr": 3.945945945945946e-05, "epoch": 0.24594651505580123, "percentage": 4.93, "elapsed_time": "4:29:35", "remaining_time": "3 days, 14:36:15"}
+{"current_steps": 74, "total_steps": 1480, "loss": 0.4905, "lr": 4e-05, "epoch": 0.24931564539903137, "percentage": 5.0, "elapsed_time": "4:33:16", "remaining_time": "3 days, 14:32:22"}
+{"current_steps": 75, "total_steps": 1480, "loss": 0.4969, "lr": 4.0540540540540545e-05, "epoch": 0.2526847757422615, "percentage": 5.07, "elapsed_time": "4:36:58", "remaining_time": "3 days, 14:28:30"}
+{"current_steps": 76, "total_steps": 1480, "loss": 0.4921, "lr": 4.108108108108108e-05, "epoch": 0.25605390608549167, "percentage": 5.14, "elapsed_time": "4:40:39", "remaining_time": "3 days, 14:24:40"}
+{"current_steps": 77, "total_steps": 1480, "loss": 0.4967, "lr": 4.162162162162163e-05, "epoch": 0.25942303642872183, "percentage": 5.2, "elapsed_time": "4:44:20", "remaining_time": "3 days, 14:20:49"}
+{"current_steps": 78, "total_steps": 1480, "loss": 0.4921, "lr": 4.2162162162162164e-05, "epoch": 0.262792166771952, "percentage": 5.27, "elapsed_time": "4:48:00", "remaining_time": "3 days, 14:16:51"}
+{"current_steps": 79, "total_steps": 1480, "loss": 0.4894, "lr": 4.2702702702702706e-05, "epoch": 0.26616129711518216, "percentage": 5.34, "elapsed_time": "4:51:41", "remaining_time": "3 days, 14:13:01"}
+{"current_steps": 80, "total_steps": 1480, "loss": 0.4953, "lr": 4.324324324324325e-05, "epoch": 0.2695304274584123, "percentage": 5.41, "elapsed_time": "4:55:22", "remaining_time": "3 days, 14:09:09"}
+{"current_steps": 81, "total_steps": 1480, "loss": 0.4943, "lr": 4.3783783783783783e-05, "epoch": 0.27289955780164243, "percentage": 5.47, "elapsed_time": "4:59:03", "remaining_time": "3 days, 14:05:16"}
+{"current_steps": 82, "total_steps": 1480, "loss": 0.4902, "lr": 4.4324324324324325e-05, "epoch": 0.2762686881448726, "percentage": 5.54, "elapsed_time": "5:02:44", "remaining_time": "3 days, 14:01:23"}
+{"current_steps": 83, "total_steps": 1480, "loss": 0.4937, "lr": 4.4864864864864874e-05, "epoch": 0.27963781848810276, "percentage": 5.61, "elapsed_time": "5:06:25", "remaining_time": "3 days, 13:57:32"}
+{"current_steps": 84, "total_steps": 1480, "loss": 0.4918, "lr": 4.540540540540541e-05, "epoch": 0.2830069488313329, "percentage": 5.68, "elapsed_time": "5:10:06", "remaining_time": "3 days, 13:53:45"}
+{"current_steps": 85, "total_steps": 1480, "loss": 0.4886, "lr": 4.594594594594595e-05, "epoch": 0.2863760791745631, "percentage": 5.74, "elapsed_time": "5:13:47", "remaining_time": "3 days, 13:49:55"}
+{"current_steps": 86, "total_steps": 1480, "loss": 0.4833, "lr": 4.6486486486486486e-05, "epoch": 0.2897452095177932, "percentage": 5.81, "elapsed_time": "5:17:28", "remaining_time": "3 days, 13:45:58"}
+{"current_steps": 87, "total_steps": 1480, "loss": 0.4839, "lr": 4.702702702702703e-05, "epoch": 0.29311433986102337, "percentage": 5.88, "elapsed_time": "5:21:09", "remaining_time": "3 days, 13:42:08"}
+{"current_steps": 88, "total_steps": 1480, "loss": 0.491, "lr": 4.756756756756758e-05, "epoch": 0.29648347020425353, "percentage": 5.95, "elapsed_time": "5:24:50", "remaining_time": "3 days, 13:38:17"}
+{"current_steps": 89, "total_steps": 1480, "loss": 0.4887, "lr": 4.810810810810811e-05, "epoch": 0.2998526005474837, "percentage": 6.01, "elapsed_time": "5:28:30", "remaining_time": "3 days, 13:34:25"}
+{"current_steps": 90, "total_steps": 1480, "loss": 0.4934, "lr": 4.8648648648648654e-05, "epoch": 0.30322173089071386, "percentage": 6.08, "elapsed_time": "5:32:11", "remaining_time": "3 days, 13:30:38"}
+{"current_steps": 91, "total_steps": 1480, "loss": 0.4921, "lr": 4.9189189189189196e-05, "epoch": 0.30659086123394397, "percentage": 6.15, "elapsed_time": "5:35:52", "remaining_time": "3 days, 13:26:47"}
+{"current_steps": 92, "total_steps": 1480, "loss": 0.4848, "lr": 4.972972972972973e-05, "epoch": 0.30995999157717413, "percentage": 6.22, "elapsed_time": "5:39:33", "remaining_time": "3 days, 13:22:52"}
+{"current_steps": 93, "total_steps": 1480, "loss": 0.4951, "lr": 5.027027027027027e-05, "epoch": 0.3133291219204043, "percentage": 6.28, "elapsed_time": "5:43:13", "remaining_time": "3 days, 13:18:53"}
+{"current_steps": 94, "total_steps": 1480, "loss": 0.4876, "lr": 5.081081081081081e-05, "epoch": 0.31669825226363446, "percentage": 6.35, "elapsed_time": "5:46:54", "remaining_time": "3 days, 13:15:04"}
+{"current_steps": 95, "total_steps": 1480, "loss": 0.4855, "lr": 5.135135135135136e-05, "epoch": 0.3200673826068646, "percentage": 6.42, "elapsed_time": "5:50:35", "remaining_time": "3 days, 13:11:14"}
+{"current_steps": 96, "total_steps": 1480, "loss": 0.4935, "lr": 5.18918918918919e-05, "epoch": 0.32343651295009473, "percentage": 6.49, "elapsed_time": "5:54:16", "remaining_time": "3 days, 13:07:23"}
+{"current_steps": 97, "total_steps": 1480, "loss": 0.4888, "lr": 5.2432432432432434e-05, "epoch": 0.3268056432933249, "percentage": 6.55, "elapsed_time": "5:57:56", "remaining_time": "3 days, 13:03:32"}
+{"current_steps": 98, "total_steps": 1480, "loss": 0.4899, "lr": 5.2972972972972976e-05, "epoch": 0.33017477363655506, "percentage": 6.62, "elapsed_time": "6:01:37", "remaining_time": "3 days, 12:59:44"}
+{"current_steps": 99, "total_steps": 1480, "loss": 0.4825, "lr": 5.3513513513513525e-05, "epoch": 0.33354390397978523, "percentage": 6.69, "elapsed_time": "6:05:18", "remaining_time": "3 days, 12:55:57"}
+{"current_steps": 100, "total_steps": 1480, "loss": 0.4802, "lr": 5.405405405405406e-05, "epoch": 0.3369130343230154, "percentage": 6.76, "elapsed_time": "6:09:00", "remaining_time": "3 days, 12:52:14"}
+{"current_steps": 101, "total_steps": 1480, "loss": 0.4795, "lr": 5.45945945945946e-05, "epoch": 0.3402821646662455, "percentage": 6.82, "elapsed_time": "6:12:40", "remaining_time": "3 days, 12:48:17"}
+{"current_steps": 102, "total_steps": 1480, "loss": 0.4916, "lr": 5.513513513513514e-05, "epoch": 0.34365129500947567, "percentage": 6.89, "elapsed_time": "6:16:21", "remaining_time": "3 days, 12:44:32"}
+{"current_steps": 103, "total_steps": 1480, "loss": 0.4797, "lr": 5.567567567567568e-05, "epoch": 0.34702042535270583, "percentage": 6.96, "elapsed_time": "6:20:02", "remaining_time": "3 days, 12:40:47"}
+{"current_steps": 104, "total_steps": 1480, "loss": 0.4838, "lr": 5.621621621621622e-05, "epoch": 0.350389555695936, "percentage": 7.03, "elapsed_time": "6:23:43", "remaining_time": "3 days, 12:36:59"}
+{"current_steps": 105, "total_steps": 1480, "loss": 0.4801, "lr": 5.6756756756756757e-05, "epoch": 0.35375868603916616, "percentage": 7.09, "elapsed_time": "6:27:24", "remaining_time": "3 days, 12:33:12"}
+{"current_steps": 106, "total_steps": 1480, "loss": 0.4852, "lr": 5.7297297297297305e-05, "epoch": 0.35712781638239627, "percentage": 7.16, "elapsed_time": "6:31:05", "remaining_time": "3 days, 12:29:23"}
+{"current_steps": 107, "total_steps": 1480, "loss": 0.4834, "lr": 5.783783783783785e-05, "epoch": 0.36049694672562643, "percentage": 7.23, "elapsed_time": "6:34:46", "remaining_time": "3 days, 12:25:36"}
+{"current_steps": 108, "total_steps": 1480, "loss": 0.4845, "lr": 5.837837837837838e-05, "epoch": 0.3638660770688566, "percentage": 7.3, "elapsed_time": "6:38:27", "remaining_time": "3 days, 12:21:53"}
+{"current_steps": 109, "total_steps": 1480, "loss": 0.4784, "lr": 5.8918918918918924e-05, "epoch": 0.36723520741208676, "percentage": 7.36, "elapsed_time": "6:42:08", "remaining_time": "3 days, 12:18:06"}
+{"current_steps": 110, "total_steps": 1480, "loss": 0.4957, "lr": 5.945945945945946e-05, "epoch": 0.3706043377553169, "percentage": 7.43, "elapsed_time": "6:45:49", "remaining_time": "3 days, 12:14:17"}
+{"current_steps": 111, "total_steps": 1480, "loss": 0.4834, "lr": 6.000000000000001e-05, "epoch": 0.37397346809854703, "percentage": 7.5, "elapsed_time": "6:49:29", "remaining_time": "3 days, 12:10:29"}
+{"current_steps": 112, "total_steps": 1480, "loss": 0.4837, "lr": 6.054054054054055e-05, "epoch": 0.3773425984417772, "percentage": 7.57, "elapsed_time": "6:53:11", "remaining_time": "3 days, 12:06:44"}
+{"current_steps": 113, "total_steps": 1480, "loss": 0.4845, "lr": 6.108108108108108e-05, "epoch": 0.38071172878500736, "percentage": 7.64, "elapsed_time": "6:56:51", "remaining_time": "3 days, 12:02:56"}
+{"current_steps": 114, "total_steps": 1480, "loss": 0.4786, "lr": 6.162162162162163e-05, "epoch": 0.38408085912823753, "percentage": 7.7, "elapsed_time": "7:00:32", "remaining_time": "3 days, 11:59:09"}
+{"current_steps": 115, "total_steps": 1480, "loss": 0.4831, "lr": 6.216216216216216e-05, "epoch": 0.3874499894714677, "percentage": 7.77, "elapsed_time": "7:04:13", "remaining_time": "3 days, 11:55:25"}
+{"current_steps": 116, "total_steps": 1480, "loss": 0.4894, "lr": 6.27027027027027e-05, "epoch": 0.39081911981469786, "percentage": 7.84, "elapsed_time": "7:07:54", "remaining_time": "3 days, 11:51:38"}
+{"current_steps": 117, "total_steps": 1480, "loss": 0.4811, "lr": 6.324324324324325e-05, "epoch": 0.39418825015792797, "percentage": 7.91, "elapsed_time": "7:11:35", "remaining_time": "3 days, 11:47:49"}
+{"current_steps": 118, "total_steps": 1480, "loss": 0.4924, "lr": 6.378378378378379e-05, "epoch": 0.39755738050115813, "percentage": 7.97, "elapsed_time": "7:15:16", "remaining_time": "3 days, 11:44:05"}
+{"current_steps": 119, "total_steps": 1480, "loss": 0.481, "lr": 6.432432432432433e-05, "epoch": 0.4009265108443883, "percentage": 8.04, "elapsed_time": "7:18:57", "remaining_time": "3 days, 11:40:25"}
+{"current_steps": 120, "total_steps": 1480, "loss": 0.4888, "lr": 6.486486486486487e-05, "epoch": 0.40429564118761846, "percentage": 8.11, "elapsed_time": "7:22:38", "remaining_time": "3 days, 11:36:35"}
+{"current_steps": 121, "total_steps": 1480, "loss": 0.4798, "lr": 6.540540540540541e-05, "epoch": 0.4076647715308486, "percentage": 8.18, "elapsed_time": "7:26:19", "remaining_time": "3 days, 11:32:48"}
+{"current_steps": 122, "total_steps": 1480, "loss": 0.4768, "lr": 6.594594594594596e-05, "epoch": 0.41103390187407873, "percentage": 8.24, "elapsed_time": "7:30:00", "remaining_time": "3 days, 11:29:08"}
+{"current_steps": 123, "total_steps": 1480, "loss": 0.4926, "lr": 6.648648648648648e-05, "epoch": 0.4144030322173089, "percentage": 8.31, "elapsed_time": "7:33:46", "remaining_time": "3 days, 11:26:13"}
+{"current_steps": 124, "total_steps": 1480, "loss": 0.4856, "lr": 6.702702702702703e-05, "epoch": 0.41777216256053906, "percentage": 8.38, "elapsed_time": "7:37:29", "remaining_time": "3 days, 11:22:53"}
+{"current_steps": 125, "total_steps": 1480, "loss": 0.4896, "lr": 6.756756756756758e-05, "epoch": 0.4211412929037692, "percentage": 8.45, "elapsed_time": "7:41:10", "remaining_time": "3 days, 11:19:04"}
+{"current_steps": 126, "total_steps": 1480, "loss": 0.4885, "lr": 6.810810810810811e-05, "epoch": 0.4245104232469994, "percentage": 8.51, "elapsed_time": "7:44:50", "remaining_time": "3 days, 11:15:12"}
+{"current_steps": 127, "total_steps": 1480, "loss": 0.4821, "lr": 6.864864864864865e-05, "epoch": 0.4278795535902295, "percentage": 8.58, "elapsed_time": "7:48:31", "remaining_time": "3 days, 11:11:25"}
+{"current_steps": 128, "total_steps": 1480, "loss": 0.4823, "lr": 6.91891891891892e-05, "epoch": 0.43124868393345966, "percentage": 8.65, "elapsed_time": "7:52:12", "remaining_time": "3 days, 11:07:37"}
+{"current_steps": 129, "total_steps": 1480, "loss": 0.4938, "lr": 6.972972972972974e-05, "epoch": 0.43461781427668983, "percentage": 8.72, "elapsed_time": "7:55:53", "remaining_time": "3 days, 11:03:52"}
+{"current_steps": 130, "total_steps": 1480, "loss": 0.4909, "lr": 7.027027027027028e-05, "epoch": 0.43798694461992, "percentage": 8.78, "elapsed_time": "7:59:34", "remaining_time": "3 days, 11:00:08"}
+{"current_steps": 131, "total_steps": 1480, "loss": 0.487, "lr": 7.081081081081081e-05, "epoch": 0.44135607496315016, "percentage": 8.85, "elapsed_time": "8:03:15", "remaining_time": "3 days, 10:56:25"}
+{"current_steps": 132, "total_steps": 1480, "loss": 0.488, "lr": 7.135135135135136e-05, "epoch": 0.44472520530638027, "percentage": 8.92, "elapsed_time": "8:06:56", "remaining_time": "3 days, 10:52:39"}
+{"current_steps": 133, "total_steps": 1480, "loss": 0.4815, "lr": 7.18918918918919e-05, "epoch": 0.44809433564961043, "percentage": 8.99, "elapsed_time": "8:10:37", "remaining_time": "3 days, 10:48:56"}
+{"current_steps": 134, "total_steps": 1480, "loss": 0.4757, "lr": 7.243243243243243e-05, "epoch": 0.4514634659928406, "percentage": 9.05, "elapsed_time": "8:14:18", "remaining_time": "3 days, 10:45:09"}
+{"current_steps": 135, "total_steps": 1480, "loss": 0.479, "lr": 7.297297297297297e-05, "epoch": 0.45483259633607076, "percentage": 9.12, "elapsed_time": "8:17:58", "remaining_time": "3 days, 10:41:23"}
+{"current_steps": 136, "total_steps": 1480, "loss": 0.484, "lr": 7.351351351351353e-05, "epoch": 0.4582017266793009, "percentage": 9.19, "elapsed_time": "8:21:39", "remaining_time": "3 days, 10:37:36"}
+{"current_steps": 137, "total_steps": 1480, "loss": 0.4796, "lr": 7.405405405405406e-05, "epoch": 0.46157085702253103, "percentage": 9.26, "elapsed_time": "8:25:20", "remaining_time": "3 days, 10:33:53"}
+{"current_steps": 138, "total_steps": 1480, "loss": 0.4814, "lr": 7.45945945945946e-05, "epoch": 0.4649399873657612, "percentage": 9.32, "elapsed_time": "8:29:01", "remaining_time": "3 days, 10:30:08"}
+{"current_steps": 139, "total_steps": 1480, "loss": 0.4828, "lr": 7.513513513513514e-05, "epoch": 0.46830911770899136, "percentage": 9.39, "elapsed_time": "8:32:42", "remaining_time": "3 days, 10:26:15"}
+{"current_steps": 140, "total_steps": 1480, "loss": 0.4761, "lr": 7.567567567567568e-05, "epoch": 0.4716782480522215, "percentage": 9.46, "elapsed_time": "8:36:22", "remaining_time": "3 days, 10:22:27"}
+{"current_steps": 141, "total_steps": 1480, "loss": 0.4844, "lr": 7.621621621621623e-05, "epoch": 0.4750473783954517, "percentage": 9.53, "elapsed_time": "8:40:03", "remaining_time": "3 days, 10:18:41"}
+{"current_steps": 142, "total_steps": 1480, "loss": 0.4758, "lr": 7.675675675675675e-05, "epoch": 0.4784165087386818, "percentage": 9.59, "elapsed_time": "8:43:44", "remaining_time": "3 days, 10:14:54"}
+{"current_steps": 143, "total_steps": 1480, "loss": 0.472, "lr": 7.729729729729731e-05, "epoch": 0.48178563908191196, "percentage": 9.66, "elapsed_time": "8:47:24", "remaining_time": "3 days, 10:11:08"}
+{"current_steps": 144, "total_steps": 1480, "loss": 0.4848, "lr": 7.783783783783785e-05, "epoch": 0.48515476942514213, "percentage": 9.73, "elapsed_time": "8:51:05", "remaining_time": "3 days, 10:07:16"}
+{"current_steps": 145, "total_steps": 1480, "loss": 0.4784, "lr": 7.837837837837838e-05, "epoch": 0.4885238997683723, "percentage": 9.8, "elapsed_time": "8:54:46", "remaining_time": "3 days, 10:03:32"}
+{"current_steps": 146, "total_steps": 1480, "loss": 0.4771, "lr": 7.891891891891892e-05, "epoch": 0.49189303011160246, "percentage": 9.86, "elapsed_time": "8:58:27", "remaining_time": "3 days, 9:59:50"}
+{"current_steps": 147, "total_steps": 1480, "loss": 0.4764, "lr": 7.945945945945946e-05, "epoch": 0.4952621604548326, "percentage": 9.93, "elapsed_time": "9:02:08", "remaining_time": "3 days, 9:56:08"}
+{"current_steps": 148, "total_steps": 1480, "loss": 0.4762, "lr": 8e-05, "epoch": 0.49863129079806273, "percentage": 10.0, "elapsed_time": "9:05:48", "remaining_time": "3 days, 9:52:18"}
+{"current_steps": 149, "total_steps": 1480, "loss": 0.4798, "lr": 7.999988874460243e-05, "epoch": 0.502000421141293, "percentage": 10.07, "elapsed_time": "9:09:29", "remaining_time": "3 days, 9:48:33"}
+{"current_steps": 150, "total_steps": 1480, "loss": 0.4732, "lr": 7.999955497902857e-05, "epoch": 0.505369551484523, "percentage": 10.14, "elapsed_time": "9:13:10", "remaining_time": "3 days, 9:44:52"}
+{"current_steps": 151, "total_steps": 1480, "loss": 0.4831, "lr": 7.99989987051351e-05, "epoch": 0.5087386818277532, "percentage": 10.2, "elapsed_time": "9:16:51", "remaining_time": "3 days, 9:41:07"}
+{"current_steps": 152, "total_steps": 1480, "loss": 0.4797, "lr": 7.999821992601645e-05, "epoch": 0.5121078121709833, "percentage": 10.27, "elapsed_time": "9:20:32", "remaining_time": "3 days, 9:37:24"}
+{"current_steps": 153, "total_steps": 1480, "loss": 0.4758, "lr": 7.999721864600476e-05, "epoch": 0.5154769425142135, "percentage": 10.34, "elapsed_time": "9:24:13", "remaining_time": "3 days, 9:33:39"}
+{"current_steps": 154, "total_steps": 1480, "loss": 0.4811, "lr": 7.999599487066996e-05, "epoch": 0.5188460728574437, "percentage": 10.41, "elapsed_time": "9:27:54", "remaining_time": "3 days, 9:29:57"}
+{"current_steps": 155, "total_steps": 1480, "loss": 0.4737, "lr": 7.999454860681961e-05, "epoch": 0.5222152032006738, "percentage": 10.47, "elapsed_time": "9:31:35", "remaining_time": "3 days, 9:26:13"}
+{"current_steps": 156, "total_steps": 1480, "loss": 0.4704, "lr": 7.999287986249894e-05, "epoch": 0.525584333543904, "percentage": 10.54, "elapsed_time": "9:35:16", "remaining_time": "3 days, 9:22:27"}
+{"current_steps": 157, "total_steps": 1480, "loss": 0.472, "lr": 7.999098864699078e-05, "epoch": 0.5289534638871342, "percentage": 10.61, "elapsed_time": "9:38:57", "remaining_time": "3 days, 9:18:41"}
+{"current_steps": 158, "total_steps": 1480, "loss": 0.4656, "lr": 7.998887497081555e-05, "epoch": 0.5323225942303643, "percentage": 10.68, "elapsed_time": "9:42:38", "remaining_time": "3 days, 9:14:58"}
+{"current_steps": 159, "total_steps": 1480, "loss": 0.4707, "lr": 7.998653884573114e-05, "epoch": 0.5356917245735945, "percentage": 10.74, "elapsed_time": "9:46:20", "remaining_time": "3 days, 9:11:21"}
+{"current_steps": 160, "total_steps": 1480, "loss": 0.4797, "lr": 7.998398028473287e-05, "epoch": 0.5390608549168246, "percentage": 10.81, "elapsed_time": "9:50:01", "remaining_time": "3 days, 9:07:39"}
+{"current_steps": 161, "total_steps": 1480, "loss": 0.4719, "lr": 7.998119930205342e-05, "epoch": 0.5424299852600547, "percentage": 10.88, "elapsed_time": "9:53:42", "remaining_time": "3 days, 9:03:55"}
+{"current_steps": 162, "total_steps": 1480, "loss": 0.4715, "lr": 7.997819591316278e-05, "epoch": 0.5457991156032849, "percentage": 10.95, "elapsed_time": "9:57:23", "remaining_time": "3 days, 9:00:13"}
+{"current_steps": 163, "total_steps": 1480, "loss": 0.4733, "lr": 7.997497013476808e-05, "epoch": 0.549168245946515, "percentage": 11.01, "elapsed_time": "10:01:03", "remaining_time": "3 days, 8:56:25"}
+{"current_steps": 164, "total_steps": 1480, "loss": 0.4712, "lr": 7.99715219848136e-05, "epoch": 0.5525373762897452, "percentage": 11.08, "elapsed_time": "10:04:44", "remaining_time": "3 days, 8:52:39"}
+{"current_steps": 165, "total_steps": 1480, "loss": 0.4747, "lr": 7.996785148248062e-05, "epoch": 0.5559065066329754, "percentage": 11.15, "elapsed_time": "10:08:24", "remaining_time": "3 days, 8:48:53"}
+{"current_steps": 166, "total_steps": 1480, "loss": 0.4696, "lr": 7.996395864818727e-05, "epoch": 0.5592756369762055, "percentage": 11.22, "elapsed_time": "10:12:05", "remaining_time": "3 days, 8:45:09"}
+{"current_steps": 167, "total_steps": 1480, "loss": 0.4663, "lr": 7.995984350358851e-05, "epoch": 0.5626447673194357, "percentage": 11.28, "elapsed_time": "10:15:46", "remaining_time": "3 days, 8:41:22"}
+{"current_steps": 168, "total_steps": 1480, "loss": 0.4629, "lr": 7.995550607157592e-05, "epoch": 0.5660138976626659, "percentage": 11.35, "elapsed_time": "10:19:26", "remaining_time": "3 days, 8:37:35"}
+{"current_steps": 169, "total_steps": 1480, "loss": 0.4569, "lr": 7.995094637627767e-05, "epoch": 0.569383028005896, "percentage": 11.42, "elapsed_time": "10:23:07", "remaining_time": "3 days, 8:33:50"}
+{"current_steps": 170, "total_steps": 1480, "loss": 0.4694, "lr": 7.994616444305826e-05, "epoch": 0.5727521583491262, "percentage": 11.49, "elapsed_time": "10:26:48", "remaining_time": "3 days, 8:30:04"}
+{"current_steps": 171, "total_steps": 1480, "loss": 0.4709, "lr": 7.994116029851852e-05, "epoch": 0.5761212886923562, "percentage": 11.55, "elapsed_time": "10:30:28", "remaining_time": "3 days, 8:26:18"}
+{"current_steps": 172, "total_steps": 1480, "loss": 0.4657, "lr": 7.993593397049533e-05, "epoch": 0.5794904190355864, "percentage": 11.62, "elapsed_time": "10:34:09", "remaining_time": "3 days, 8:22:30"}
+{"current_steps": 173, "total_steps": 1480, "loss": 0.4667, "lr": 7.993048548806155e-05, "epoch": 0.5828595493788166, "percentage": 11.69, "elapsed_time": "10:37:50", "remaining_time": "3 days, 8:18:47"}
+{"current_steps": 174, "total_steps": 1480, "loss": 0.4719, "lr": 7.992481488152585e-05, "epoch": 0.5862286797220467, "percentage": 11.76, "elapsed_time": "10:41:30", "remaining_time": "3 days, 8:14:59"}
+{"current_steps": 175, "total_steps": 1480, "loss": 0.4722, "lr": 7.991892218243251e-05, "epoch": 0.5895978100652769, "percentage": 11.82, "elapsed_time": "10:45:11", "remaining_time": "3 days, 8:11:14"}
+{"current_steps": 176, "total_steps": 1480, "loss": 0.4664, "lr": 7.991280742356124e-05, "epoch": 0.5929669404085071, "percentage": 11.89, "elapsed_time": "10:48:51", "remaining_time": "3 days, 8:07:29"}
+{"current_steps": 177, "total_steps": 1480, "loss": 0.4602, "lr": 7.990647063892704e-05, "epoch": 0.5963360707517372, "percentage": 11.96, "elapsed_time": "10:52:32", "remaining_time": "3 days, 8:03:45"}
+{"current_steps": 178, "total_steps": 1480, "loss": 0.4716, "lr": 7.989991186378e-05, "epoch": 0.5997052010949674, "percentage": 12.03, "elapsed_time": "10:56:13", "remaining_time": "3 days, 8:00:02"}
+{"current_steps": 179, "total_steps": 1480, "loss": 0.4755, "lr": 7.989313113460506e-05, "epoch": 0.6030743314381976, "percentage": 12.09, "elapsed_time": "10:59:54", "remaining_time": "3 days, 7:56:19"}
+{"current_steps": 180, "total_steps": 1480, "loss": 0.4695, "lr": 7.988612848912186e-05, "epoch": 0.6064434617814277, "percentage": 12.16, "elapsed_time": "11:03:35", "remaining_time": "3 days, 7:52:38"}
+{"current_steps": 181, "total_steps": 1480, "loss": 0.4717, "lr": 7.987890396628451e-05, "epoch": 0.6098125921246578, "percentage": 12.23, "elapsed_time": "11:07:16", "remaining_time": "3 days, 7:48:52"}
+{"current_steps": 182, "total_steps": 1480, "loss": 0.4812, "lr": 7.987145760628138e-05, "epoch": 0.6131817224678879, "percentage": 12.3, "elapsed_time": "11:10:57", "remaining_time": "3 days, 7:45:08"}
+{"current_steps": 183, "total_steps": 1480, "loss": 0.4652, "lr": 7.986378945053483e-05, "epoch": 0.6165508528111181, "percentage": 12.36, "elapsed_time": "11:14:38", "remaining_time": "3 days, 7:41:26"}
+{"current_steps": 184, "total_steps": 1480, "loss": 0.4672, "lr": 7.985589954170107e-05, "epoch": 0.6199199831543483, "percentage": 12.43, "elapsed_time": "11:18:19", "remaining_time": "3 days, 7:37:45"}
+{"current_steps": 185, "total_steps": 1480, "loss": 0.4692, "lr": 7.984778792366983e-05, "epoch": 0.6232891134975784, "percentage": 12.5, "elapsed_time": "11:22:00", "remaining_time": "3 days, 7:34:04"}
+{"current_steps": 186, "total_steps": 1480, "loss": 0.4637, "lr": 7.983945464156419e-05, "epoch": 0.6266582438408086, "percentage": 12.57, "elapsed_time": "11:25:41", "remaining_time": "3 days, 7:30:20"}
+{"current_steps": 187, "total_steps": 1480, "loss": 0.4735, "lr": 7.983089974174026e-05, "epoch": 0.6300273741840388, "percentage": 12.64, "elapsed_time": "11:29:22", "remaining_time": "3 days, 7:26:40"}
+{"current_steps": 188, "total_steps": 1480, "loss": 0.4685, "lr": 7.982212327178699e-05, "epoch": 0.6333965045272689, "percentage": 12.7, "elapsed_time": "11:33:03", "remaining_time": "3 days, 7:22:57"}
+{"current_steps": 189, "total_steps": 1480, "loss": 0.466, "lr": 7.981312528052587e-05, "epoch": 0.6367656348704991, "percentage": 12.77, "elapsed_time": "11:36:44", "remaining_time": "3 days, 7:19:14"}
+{"current_steps": 190, "total_steps": 1480, "loss": 0.4661, "lr": 7.980390581801064e-05, "epoch": 0.6401347652137293, "percentage": 12.84, "elapsed_time": "11:40:25", "remaining_time": "3 days, 7:15:30"}
+{"current_steps": 191, "total_steps": 1480, "loss": 0.4622, "lr": 7.979446493552708e-05, "epoch": 0.6435038955569593, "percentage": 12.91, "elapsed_time": "11:44:05", "remaining_time": "3 days, 7:11:45"}
+{"current_steps": 192, "total_steps": 1480, "loss": 0.4522, "lr": 7.97848026855926e-05, "epoch": 0.6468730259001895, "percentage": 12.97, "elapsed_time": "11:47:46", "remaining_time": "3 days, 7:08:00"}
+{"current_steps": 193, "total_steps": 1480, "loss": 0.4674, "lr": 7.977491912195611e-05, "epoch": 0.6502421562434196, "percentage": 13.04, "elapsed_time": "11:51:27", "remaining_time": "3 days, 7:04:20"}
+{"current_steps": 194, "total_steps": 1480, "loss": 0.4656, "lr": 7.976481429959758e-05, "epoch": 0.6536112865866498, "percentage": 13.11, "elapsed_time": "11:55:09", "remaining_time": "3 days, 7:00:39"}
+{"current_steps": 195, "total_steps": 1480, "loss": 0.4569, "lr": 7.975448827472782e-05, "epoch": 0.65698041692988, "percentage": 13.18, "elapsed_time": "11:58:49", "remaining_time": "3 days, 6:56:55"}
+{"current_steps": 196, "total_steps": 1480, "loss": 0.4644, "lr": 7.974394110478813e-05, "epoch": 0.6603495472731101, "percentage": 13.24, "elapsed_time": "12:02:30", "remaining_time": "3 days, 6:53:12"}
+{"current_steps": 197, "total_steps": 1480, "loss": 0.4672, "lr": 7.973317284844998e-05, "epoch": 0.6637186776163403, "percentage": 13.31, "elapsed_time": "12:06:11", "remaining_time": "3 days, 6:49:30"}
+{"current_steps": 198, "total_steps": 1480, "loss": 0.4561, "lr": 7.972218356561471e-05, "epoch": 0.6670878079595705, "percentage": 13.38, "elapsed_time": "12:09:52", "remaining_time": "3 days, 6:45:46"}
+{"current_steps": 199, "total_steps": 1480, "loss": 0.4581, "lr": 7.971097331741318e-05, "epoch": 0.6704569383028006, "percentage": 13.45, "elapsed_time": "12:13:33", "remaining_time": "3 days, 6:42:03"}
+{"current_steps": 200, "total_steps": 1480, "loss": 0.4572, "lr": 7.96995421662054e-05, "epoch": 0.6738260686460308, "percentage": 13.51, "elapsed_time": "12:17:14", "remaining_time": "3 days, 6:38:19"}
+{"current_steps": 201, "total_steps": 1480, "loss": 0.4438, "lr": 7.968789017558026e-05, "epoch": 0.677195198989261, "percentage": 13.58, "elapsed_time": "12:20:54", "remaining_time": "3 days, 6:34:34"}
+{"current_steps": 202, "total_steps": 1480, "loss": 0.4538, "lr": 7.967601741035507e-05, "epoch": 0.680564329332491, "percentage": 13.65, "elapsed_time": "12:24:36", "remaining_time": "3 days, 6:30:54"}
+{"current_steps": 203, "total_steps": 1480, "loss": 0.4567, "lr": 7.966392393657533e-05, "epoch": 0.6839334596757212, "percentage": 13.72, "elapsed_time": "12:28:17", "remaining_time": "3 days, 6:27:12"}
+{"current_steps": 204, "total_steps": 1480, "loss": 0.4636, "lr": 7.965160982151422e-05, "epoch": 0.6873025900189513, "percentage": 13.78, "elapsed_time": "12:31:58", "remaining_time": "3 days, 6:23:32"}
+{"current_steps": 205, "total_steps": 1480, "loss": 0.4674, "lr": 7.963907513367234e-05, "epoch": 0.6906717203621815, "percentage": 13.85, "elapsed_time": "12:35:39", "remaining_time": "3 days, 6:19:50"}
+{"current_steps": 206, "total_steps": 1480, "loss": 0.4481, "lr": 7.962631994277728e-05, "epoch": 0.6940408507054117, "percentage": 13.92, "elapsed_time": "12:39:21", "remaining_time": "3 days, 6:16:10"}
+{"current_steps": 207, "total_steps": 1480, "loss": 0.4557, "lr": 7.961334431978321e-05, "epoch": 0.6974099810486418, "percentage": 13.99, "elapsed_time": "12:43:02", "remaining_time": "3 days, 6:12:29"}
+{"current_steps": 208, "total_steps": 1480, "loss": 0.4584, "lr": 7.960014833687055e-05, "epoch": 0.700779111391872, "percentage": 14.05, "elapsed_time": "12:46:43", "remaining_time": "3 days, 6:08:49"}
+{"current_steps": 209, "total_steps": 1480, "loss": 0.463, "lr": 7.958673206744553e-05, "epoch": 0.7041482417351022, "percentage": 14.12, "elapsed_time": "12:50:24", "remaining_time": "3 days, 6:05:07"}
+{"current_steps": 210, "total_steps": 1480, "loss": 0.4533, "lr": 7.957309558613974e-05, "epoch": 0.7075173720783323, "percentage": 14.19, "elapsed_time": "12:54:05", "remaining_time": "3 days, 6:01:21"}
+{"current_steps": 211, "total_steps": 1480, "loss": 0.4616, "lr": 7.955923896880982e-05, "epoch": 0.7108865024215625, "percentage": 14.26, "elapsed_time": "12:57:46", "remaining_time": "3 days, 5:57:39"}
+{"current_steps": 212, "total_steps": 1480, "loss": 0.4592, "lr": 7.954516229253691e-05, "epoch": 0.7142556327647925, "percentage": 14.32, "elapsed_time": "13:01:27", "remaining_time": "3 days, 5:53:57"}
+{"current_steps": 213, "total_steps": 1480, "loss": 0.4535, "lr": 7.953086563562635e-05, "epoch": 0.7176247631080227, "percentage": 14.39, "elapsed_time": "13:05:07", "remaining_time": "3 days, 5:50:14"}
+{"current_steps": 214, "total_steps": 1480, "loss": 0.453, "lr": 7.951634907760713e-05, "epoch": 0.7209938934512529, "percentage": 14.46, "elapsed_time": "13:08:48", "remaining_time": "3 days, 5:46:32"}
+{"current_steps": 215, "total_steps": 1480, "loss": 0.4621, "lr": 7.950161269923153e-05, "epoch": 0.724363023794483, "percentage": 14.53, "elapsed_time": "13:12:29", "remaining_time": "3 days, 5:42:49"}
+{"current_steps": 216, "total_steps": 1480, "loss": 0.4623, "lr": 7.948665658247463e-05, "epoch": 0.7277321541377132, "percentage": 14.59, "elapsed_time": "13:16:10", "remaining_time": "3 days, 5:39:07"}
+{"current_steps": 217, "total_steps": 1480, "loss": 0.4538, "lr": 7.947148081053388e-05, "epoch": 0.7311012844809434, "percentage": 14.66, "elapsed_time": "13:19:51", "remaining_time": "3 days, 5:35:25"}
+{"current_steps": 218, "total_steps": 1480, "loss": 0.4674, "lr": 7.945608546782858e-05, "epoch": 0.7344704148241735, "percentage": 14.73, "elapsed_time": "13:23:33", "remaining_time": "3 days, 5:31:47"}
+{"current_steps": 219, "total_steps": 1480, "loss": 0.4577, "lr": 7.944047063999952e-05, "epoch": 0.7378395451674037, "percentage": 14.8, "elapsed_time": "13:27:14", "remaining_time": "3 days, 5:28:06"}
+{"current_steps": 220, "total_steps": 1480, "loss": 0.4488, "lr": 7.942463641390834e-05, "epoch": 0.7412086755106339, "percentage": 14.86, "elapsed_time": "13:30:55", "remaining_time": "3 days, 5:24:25"}
+{"current_steps": 221, "total_steps": 1480, "loss": 0.4579, "lr": 7.940858287763724e-05, "epoch": 0.744577805853864, "percentage": 14.93, "elapsed_time": "13:34:36", "remaining_time": "3 days, 5:20:41"}
+{"current_steps": 222, "total_steps": 1480, "loss": 0.4642, "lr": 7.939231012048833e-05, "epoch": 0.7479469361970941, "percentage": 15.0, "elapsed_time": "13:38:17", "remaining_time": "3 days, 5:16:56"}
+{"current_steps": 223, "total_steps": 1480, "loss": 0.448, "lr": 7.93758182329832e-05, "epoch": 0.7513160665403242, "percentage": 15.07, "elapsed_time": "13:41:57", "remaining_time": "3 days, 5:13:13"}
+{"current_steps": 224, "total_steps": 1480, "loss": 0.4545, "lr": 7.935910730686246e-05, "epoch": 0.7546851968835544, "percentage": 15.14, "elapsed_time": "13:45:38", "remaining_time": "3 days, 5:09:29"}
+{"current_steps": 225, "total_steps": 1480, "loss": 0.4549, "lr": 7.934217743508513e-05, "epoch": 0.7580543272267846, "percentage": 15.2, "elapsed_time": "13:49:19", "remaining_time": "3 days, 5:05:45"}
+{"current_steps": 226, "total_steps": 1480, "loss": 0.4587, "lr": 7.932502871182818e-05, "epoch": 0.7614234575700147, "percentage": 15.27, "elapsed_time": "13:52:59", "remaining_time": "3 days, 5:02:02"}
+{"current_steps": 227, "total_steps": 1480, "loss": 0.4523, "lr": 7.930766123248602e-05, "epoch": 0.7647925879132449, "percentage": 15.34, "elapsed_time": "13:56:40", "remaining_time": "3 days, 4:58:18"}
+{"current_steps": 228, "total_steps": 1480, "loss": 0.4562, "lr": 7.929007509366994e-05, "epoch": 0.7681617182564751, "percentage": 15.41, "elapsed_time": "14:00:21", "remaining_time": "3 days, 4:54:37"}
+{"current_steps": 229, "total_steps": 1480, "loss": 0.4472, "lr": 7.927227039320758e-05, "epoch": 0.7715308485997052, "percentage": 15.47, "elapsed_time": "14:04:02", "remaining_time": "3 days, 4:50:53"}
+{"current_steps": 230, "total_steps": 1480, "loss": 0.4573, "lr": 7.925424723014239e-05, "epoch": 0.7748999789429354, "percentage": 15.54, "elapsed_time": "14:07:43", "remaining_time": "3 days, 4:47:11"}
+{"current_steps": 231, "total_steps": 1480, "loss": 0.4541, "lr": 7.923600570473308e-05, "epoch": 0.7782691092861656, "percentage": 15.61, "elapsed_time": "14:11:24", "remaining_time": "3 days, 4:43:28"}
+{"current_steps": 232, "total_steps": 1480, "loss": 0.4481, "lr": 7.921754591845307e-05, "epoch": 0.7816382396293957, "percentage": 15.68, "elapsed_time": "14:15:05", "remaining_time": "3 days, 4:39:47"}
+{"current_steps": 233, "total_steps": 1480, "loss": 0.4521, "lr": 7.91988679739899e-05, "epoch": 0.7850073699726258, "percentage": 15.74, "elapsed_time": "14:18:46", "remaining_time": "3 days, 4:36:04"}
+{"current_steps": 234, "total_steps": 1480, "loss": 0.4449, "lr": 7.917997197524467e-05, "epoch": 0.7883765003158559, "percentage": 15.81, "elapsed_time": "14:22:27", "remaining_time": "3 days, 4:32:22"}
+{"current_steps": 235, "total_steps": 1480, "loss": 0.4496, "lr": 7.916085802733147e-05, "epoch": 0.7917456306590861, "percentage": 15.88, "elapsed_time": "14:26:08", "remaining_time": "3 days, 4:28:40"}
+{"current_steps": 236, "total_steps": 1480, "loss": 0.4506, "lr": 7.914152623657678e-05, "epoch": 0.7951147610023163, "percentage": 15.95, "elapsed_time": "14:29:49", "remaining_time": "3 days, 4:24:59"}
+{"current_steps": 237, "total_steps": 1480, "loss": 0.4496, "lr": 7.912197671051894e-05, "epoch": 0.7984838913455464, "percentage": 16.01, "elapsed_time": "14:33:30", "remaining_time": "3 days, 4:21:16"}
+{"current_steps": 238, "total_steps": 1480, "loss": 0.4494, "lr": 7.910220955790746e-05, "epoch": 0.8018530216887766, "percentage": 16.08, "elapsed_time": "14:37:10", "remaining_time": "3 days, 4:17:32"}
+{"current_steps": 239, "total_steps": 1480, "loss": 0.4505, "lr": 7.908222488870243e-05, "epoch": 0.8052221520320068, "percentage": 16.15, "elapsed_time": "14:40:51", "remaining_time": "3 days, 4:13:51"}
+{"current_steps": 240, "total_steps": 1480, "loss": 0.452, "lr": 7.906202281407398e-05, "epoch": 0.8085912823752369, "percentage": 16.22, "elapsed_time": "14:44:32", "remaining_time": "3 days, 4:10:10"}
+{"current_steps": 241, "total_steps": 1480, "loss": 0.4505, "lr": 7.90416034464016e-05, "epoch": 0.8119604127184671, "percentage": 16.28, "elapsed_time": "14:48:13", "remaining_time": "3 days, 4:06:28"}
+{"current_steps": 242, "total_steps": 1480, "loss": 0.4448, "lr": 7.902096689927355e-05, "epoch": 0.8153295430616972, "percentage": 16.35, "elapsed_time": "14:51:54", "remaining_time": "3 days, 4:02:46"}
+{"current_steps": 243, "total_steps": 1480, "loss": 0.4459, "lr": 7.900011328748619e-05, "epoch": 0.8186986734049273, "percentage": 16.42, "elapsed_time": "14:55:35", "remaining_time": "3 days, 3:59:04"}
+{"current_steps": 244, "total_steps": 1480, "loss": 0.4446, "lr": 7.897904272704333e-05, "epoch": 0.8220678037481575, "percentage": 16.49, "elapsed_time": "14:59:17", "remaining_time": "3 days, 3:55:24"}
+{"current_steps": 245, "total_steps": 1480, "loss": 0.4508, "lr": 7.895775533515569e-05, "epoch": 0.8254369340913876, "percentage": 16.55, "elapsed_time": "15:02:57", "remaining_time": "3 days, 3:51:40"}
+{"current_steps": 246, "total_steps": 1480, "loss": 0.4415, "lr": 7.893625123024011e-05, "epoch": 0.8288060644346178, "percentage": 16.62, "elapsed_time": "15:06:38", "remaining_time": "3 days, 3:47:59"}
+{"current_steps": 247, "total_steps": 1480, "loss": 0.4495, "lr": 7.891453053191898e-05, "epoch": 0.832175194777848, "percentage": 16.69, "elapsed_time": "15:10:20", "remaining_time": "3 days, 3:44:18"}
+{"current_steps": 248, "total_steps": 1480, "loss": 0.4519, "lr": 7.889259336101957e-05, "epoch": 0.8355443251210781, "percentage": 16.76, "elapsed_time": "15:14:01", "remaining_time": "3 days, 3:40:36"}
+{"current_steps": 249, "total_steps": 1480, "loss": 0.4437, "lr": 7.887043983957327e-05, "epoch": 0.8389134554643083, "percentage": 16.82, "elapsed_time": "15:17:42", "remaining_time": "3 days, 3:36:54"}
+{"current_steps": 250, "total_steps": 1480, "loss": 0.4446, "lr": 7.884807009081506e-05, "epoch": 0.8422825858075385, "percentage": 16.89, "elapsed_time": "15:21:23", "remaining_time": "3 days, 3:33:14"}
+{"current_steps": 251, "total_steps": 1480, "loss": 0.4487, "lr": 7.882548423918268e-05, "epoch": 0.8456517161507686, "percentage": 16.96, "elapsed_time": "15:25:04", "remaining_time": "3 days, 3:29:33"}
+{"current_steps": 252, "total_steps": 1480, "loss": 0.4386, "lr": 7.880268241031604e-05, "epoch": 0.8490208464939988, "percentage": 17.03, "elapsed_time": "15:28:45", "remaining_time": "3 days, 3:25:51"}
+{"current_steps": 253, "total_steps": 1480, "loss": 0.4517, "lr": 7.877966473105645e-05, "epoch": 0.8523899768372288, "percentage": 17.09, "elapsed_time": "15:32:26", "remaining_time": "3 days, 3:22:11"}
+{"current_steps": 254, "total_steps": 1480, "loss": 0.4482, "lr": 7.875643132944599e-05, "epoch": 0.855759107180459, "percentage": 17.16, "elapsed_time": "15:36:07", "remaining_time": "3 days, 3:18:28"}
+{"current_steps": 255, "total_steps": 1480, "loss": 0.4441, "lr": 7.873298233472671e-05, "epoch": 0.8591282375236892, "percentage": 17.23, "elapsed_time": "15:39:48", "remaining_time": "3 days, 3:14:45"}
+{"current_steps": 256, "total_steps": 1480, "loss": 0.4443, "lr": 7.870931787733996e-05, "epoch": 0.8624973678669193, "percentage": 17.3, "elapsed_time": "15:43:30", "remaining_time": "3 days, 3:11:07"}
+{"current_steps": 257, "total_steps": 1480, "loss": 0.4447, "lr": 7.868543808892569e-05, "epoch": 0.8658664982101495, "percentage": 17.36, "elapsed_time": "15:47:11", "remaining_time": "3 days, 3:07:26"}
+{"current_steps": 258, "total_steps": 1480, "loss": 0.4424, "lr": 7.866134310232167e-05, "epoch": 0.8692356285533797, "percentage": 17.43, "elapsed_time": "15:50:52", "remaining_time": "3 days, 3:03:45"}
+{"current_steps": 259, "total_steps": 1480, "loss": 0.4488, "lr": 7.863703305156273e-05, "epoch": 0.8726047588966098, "percentage": 17.5, "elapsed_time": "15:54:33", "remaining_time": "3 days, 3:00:03"}
+{"current_steps": 260, "total_steps": 1480, "loss": 0.451, "lr": 7.861250807188014e-05, "epoch": 0.87597388923984, "percentage": 17.57, "elapsed_time": "15:58:14", "remaining_time": "3 days, 2:56:22"}
+{"current_steps": 261, "total_steps": 1480, "loss": 0.4415, "lr": 7.858776829970069e-05, "epoch": 0.8793430195830702, "percentage": 17.64, "elapsed_time": "16:01:56", "remaining_time": "3 days, 2:52:43"}
+{"current_steps": 262, "total_steps": 1480, "loss": 0.4412, "lr": 7.856281387264603e-05, "epoch": 0.8827121499263003, "percentage": 17.7, "elapsed_time": "16:05:37", "remaining_time": "3 days, 2:49:02"}
+{"current_steps": 263, "total_steps": 1480, "loss": 0.447, "lr": 7.853764492953192e-05, "epoch": 0.8860812802695305, "percentage": 17.77, "elapsed_time": "16:09:18", "remaining_time": "3 days, 2:45:21"}
+{"current_steps": 264, "total_steps": 1480, "loss": 0.4442, "lr": 7.851226161036739e-05, "epoch": 0.8894504106127605, "percentage": 17.84, "elapsed_time": "16:12:59", "remaining_time": "3 days, 2:41:39"}
+{"current_steps": 265, "total_steps": 1480, "loss": 0.4451, "lr": 7.848666405635398e-05, "epoch": 0.8928195409559907, "percentage": 17.91, "elapsed_time": "16:16:40", "remaining_time": "3 days, 2:37:57"}
+{"current_steps": 266, "total_steps": 1480, "loss": 0.4529, "lr": 7.846085240988503e-05, "epoch": 0.8961886712992209, "percentage": 17.97, "elapsed_time": "16:20:21", "remaining_time": "3 days, 2:34:16"}
+{"current_steps": 267, "total_steps": 1480, "loss": 0.445, "lr": 7.843482681454476e-05, "epoch": 0.899557801642451, "percentage": 18.04, "elapsed_time": "16:24:03", "remaining_time": "3 days, 2:30:36"}
+{"current_steps": 268, "total_steps": 1480, "loss": 0.446, "lr": 7.840858741510758e-05, "epoch": 0.9029269319856812, "percentage": 18.11, "elapsed_time": "16:27:43", "remaining_time": "3 days, 2:26:54"}
+{"current_steps": 269, "total_steps": 1480, "loss": 0.4451, "lr": 7.838213435753724e-05, "epoch": 0.9062960623289114, "percentage": 18.18, "elapsed_time": "16:31:24", "remaining_time": "3 days, 2:23:12"}
+{"current_steps": 270, "total_steps": 1480, "loss": 0.4483, "lr": 7.835546778898599e-05, "epoch": 0.9096651926721415, "percentage": 18.24, "elapsed_time": "16:35:06", "remaining_time": "3 days, 2:19:31"}
+{"current_steps": 271, "total_steps": 1480, "loss": 0.4356, "lr": 7.832858785779383e-05, "epoch": 0.9130343230153717, "percentage": 18.31, "elapsed_time": "16:38:47", "remaining_time": "3 days, 2:15:50"}
+{"current_steps": 272, "total_steps": 1480, "loss": 0.435, "lr": 7.830149471348763e-05, "epoch": 0.9164034533586018, "percentage": 18.38, "elapsed_time": "16:42:28", "remaining_time": "3 days, 2:12:10"}
+{"current_steps": 273, "total_steps": 1480, "loss": 0.4443, "lr": 7.827418850678034e-05, "epoch": 0.919772583701832, "percentage": 18.45, "elapsed_time": "16:46:09", "remaining_time": "3 days, 2:08:28"}
+{"current_steps": 274, "total_steps": 1480, "loss": 0.4408, "lr": 7.824666938957004e-05, "epoch": 0.9231417140450621, "percentage": 18.51, "elapsed_time": "16:49:52", "remaining_time": "3 days, 2:04:54"}
+{"current_steps": 275, "total_steps": 1480, "loss": 0.4471, "lr": 7.82189375149393e-05, "epoch": 0.9265108443882922, "percentage": 18.58, "elapsed_time": "16:53:35", "remaining_time": "3 days, 2:01:24"}
+{"current_steps": 276, "total_steps": 1480, "loss": 0.4417, "lr": 7.819099303715414e-05, "epoch": 0.9298799747315224, "percentage": 18.65, "elapsed_time": "16:57:17", "remaining_time": "3 days, 1:57:44"}
+{"current_steps": 277, "total_steps": 1480, "loss": 0.4376, "lr": 7.816283611166328e-05, "epoch": 0.9332491050747526, "percentage": 18.72, "elapsed_time": "17:00:58", "remaining_time": "3 days, 1:54:03"}
+{"current_steps": 278, "total_steps": 1480, "loss": 0.4468, "lr": 7.813446689509718e-05, "epoch": 0.9366182354179827, "percentage": 18.78, "elapsed_time": "17:04:39", "remaining_time": "3 days, 1:50:22"}
+{"current_steps": 279, "total_steps": 1480, "loss": 0.4492, "lr": 7.810588554526728e-05, "epoch": 0.9399873657612129, "percentage": 18.85, "elapsed_time": "17:08:21", "remaining_time": "3 days, 1:46:42"}
+{"current_steps": 280, "total_steps": 1480, "loss": 0.4423, "lr": 7.807709222116506e-05, "epoch": 0.943356496104443, "percentage": 18.92, "elapsed_time": "17:12:02", "remaining_time": "3 days, 1:43:01"}
+{"current_steps": 281, "total_steps": 1480, "loss": 0.4507, "lr": 7.804808708296116e-05, "epoch": 0.9467256264476732, "percentage": 18.99, "elapsed_time": "17:15:43", "remaining_time": "3 days, 1:39:21"}
+{"current_steps": 282, "total_steps": 1480, "loss": 0.4434, "lr": 7.801887029200448e-05, "epoch": 0.9500947567909034, "percentage": 19.05, "elapsed_time": "17:19:25", "remaining_time": "3 days, 1:35:42"}
+{"current_steps": 283, "total_steps": 1480, "loss": 0.4359, "lr": 7.798944201082128e-05, "epoch": 0.9534638871341335, "percentage": 19.12, "elapsed_time": "17:23:06", "remaining_time": "3 days, 1:32:00"}
+{"current_steps": 284, "total_steps": 1480, "loss": 0.446, "lr": 7.795980240311436e-05, "epoch": 0.9568330174773636, "percentage": 19.19, "elapsed_time": "17:26:47", "remaining_time": "3 days, 1:28:19"}
+{"current_steps": 285, "total_steps": 1480, "loss": 0.4429, "lr": 7.7929951633762e-05, "epoch": 0.9602021478205938, "percentage": 19.26, "elapsed_time": "17:30:28", "remaining_time": "3 days, 1:24:38"}
+{"current_steps": 286, "total_steps": 1480, "loss": 0.4371, "lr": 7.789988986881719e-05, "epoch": 0.9635712781638239, "percentage": 19.32, "elapsed_time": "17:34:09", "remaining_time": "3 days, 1:20:56"}
+{"current_steps": 287, "total_steps": 1480, "loss": 0.441, "lr": 7.78696172755066e-05, "epoch": 0.9669404085070541, "percentage": 19.39, "elapsed_time": "17:37:50", "remaining_time": "3 days, 1:17:15"}
+{"current_steps": 288, "total_steps": 1480, "loss": 0.4397, "lr": 7.78391340222297e-05, "epoch": 0.9703095388502843, "percentage": 19.46, "elapsed_time": "17:41:31", "remaining_time": "3 days, 1:13:33"}
+{"current_steps": 289, "total_steps": 1480, "loss": 0.441, "lr": 7.78084402785578e-05, "epoch": 0.9736786691935144, "percentage": 19.53, "elapsed_time": "17:45:13", "remaining_time": "3 days, 1:09:52"}
+{"current_steps": 290, "total_steps": 1480, "loss": 0.4436, "lr": 7.777753621523316e-05, "epoch": 0.9770477995367446, "percentage": 19.59, "elapsed_time": "17:48:53", "remaining_time": "3 days, 1:06:10"}
+{"current_steps": 291, "total_steps": 1480, "loss": 0.44, "lr": 7.774642200416795e-05, "epoch": 0.9804169298799748, "percentage": 19.66, "elapsed_time": "17:52:34", "remaining_time": "3 days, 1:02:28"}
+{"current_steps": 292, "total_steps": 1480, "loss": 0.4431, "lr": 7.771509781844338e-05, "epoch": 0.9837860602232049, "percentage": 19.73, "elapsed_time": "17:56:15", "remaining_time": "3 days, 0:58:46"}
+{"current_steps": 293, "total_steps": 1480, "loss": 0.4423, "lr": 7.768356383230868e-05, "epoch": 0.9871551905664351, "percentage": 19.8, "elapsed_time": "17:59:56", "remaining_time": "3 days, 0:55:03"}
+{"current_steps": 294, "total_steps": 1480, "loss": 0.4386, "lr": 7.765182022118014e-05, "epoch": 0.9905243209096652, "percentage": 19.86, "elapsed_time": "18:03:37", "remaining_time": "3 days, 0:51:22"}
+{"current_steps": 295, "total_steps": 1480, "loss": 0.4403, "lr": 7.761986716164019e-05, "epoch": 0.9938934512528953, "percentage": 19.93, "elapsed_time": "18:07:18", "remaining_time": "3 days, 0:47:39"}
+{"current_steps": 296, "total_steps": 1480, "loss": 0.4428, "lr": 7.758770483143634e-05, "epoch": 0.9972625815961255, "percentage": 20.0, "elapsed_time": "18:10:59", "remaining_time": "3 days, 0:43:57"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af75f5d80d8bdadd56ce7171ee5ae3a928dced0fbe2601c188cf10b0c3eaf5a
+size 7160