Training in progress, epoch 1

.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:fc45d572185f1162e45b9f419e852e00a259a65aa74ee9696db1fdc7065e6a15
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda1ffbcfd8027d335a93695f0fc86c85ef14e6917cb7a7be61a72147032a53f
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861b1530d4327d58d2d220b68a03844bd9fe57cb0ddb6073a97a73116c4fc83a
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7450a591d911170ba7f7c37bac458ece7c35018ce0a03ac631cef293da8af94f
+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 +1,252 @@
+{"current_steps": 1, "total_steps": 750, "loss": 1.2845, "lr": 1.3333333333333336e-07, "epoch": 0.004, "percentage": 0.13, "elapsed_time": "0:01:12", "remaining_time": "15:05:44"}
+{"current_steps": 2, "total_steps": 750, "loss": 1.2808, "lr": 2.666666666666667e-07, "epoch": 0.008, "percentage": 0.27, "elapsed_time": "0:02:12", "remaining_time": "13:43:43"}
+{"current_steps": 3, "total_steps": 750, "loss": 1.2611, "lr": 4.0000000000000003e-07, "epoch": 0.012, "percentage": 0.4, "elapsed_time": "0:03:01", "remaining_time": "12:32:21"}
+{"current_steps": 4, "total_steps": 750, "loss": 1.2732, "lr": 5.333333333333335e-07, "epoch": 0.016, "percentage": 0.53, "elapsed_time": "0:03:59", "remaining_time": "12:24:29"}
+{"current_steps": 5, "total_steps": 750, "loss": 1.2664, "lr": 6.666666666666667e-07, "epoch": 0.02, "percentage": 0.67, "elapsed_time": "0:05:02", "remaining_time": "12:31:53"}
+{"current_steps": 6, "total_steps": 750, "loss": 1.268, "lr": 8.000000000000001e-07, "epoch": 0.024, "percentage": 0.8, "elapsed_time": "0:06:01", "remaining_time": "12:26:44"}
+{"current_steps": 7, "total_steps": 750, "loss": 1.2577, "lr": 9.333333333333334e-07, "epoch": 0.028, "percentage": 0.93, "elapsed_time": "0:06:51", "remaining_time": "12:07:27"}
+{"current_steps": 8, "total_steps": 750, "loss": 1.2439, "lr": 1.066666666666667e-06, "epoch": 0.032, "percentage": 1.07, "elapsed_time": "0:07:45", "remaining_time": "11:59:02"}
+{"current_steps": 9, "total_steps": 750, "loss": 1.2432, "lr": 1.2000000000000002e-06, "epoch": 0.036, "percentage": 1.2, "elapsed_time": "0:08:32", "remaining_time": "11:43:37"}
+{"current_steps": 10, "total_steps": 750, "loss": 1.1761, "lr": 1.3333333333333334e-06, "epoch": 0.04, "percentage": 1.33, "elapsed_time": "0:09:36", "remaining_time": "11:50:34"}
+{"current_steps": 11, "total_steps": 750, "loss": 1.1907, "lr": 1.4666666666666669e-06, "epoch": 0.044, "percentage": 1.47, "elapsed_time": "0:10:28", "remaining_time": "11:43:44"}
+{"current_steps": 12, "total_steps": 750, "loss": 1.1929, "lr": 1.6000000000000001e-06, "epoch": 0.048, "percentage": 1.6, "elapsed_time": "0:11:26", "remaining_time": "11:43:12"}
+{"current_steps": 13, "total_steps": 750, "loss": 1.1881, "lr": 1.7333333333333336e-06, "epoch": 0.052, "percentage": 1.73, "elapsed_time": "0:12:28", "remaining_time": "11:47:14"}
+{"current_steps": 14, "total_steps": 750, "loss": 1.1643, "lr": 1.8666666666666669e-06, "epoch": 0.056, "percentage": 1.87, "elapsed_time": "0:13:26", "remaining_time": "11:47:01"}
+{"current_steps": 15, "total_steps": 750, "loss": 1.1545, "lr": 2.0000000000000003e-06, "epoch": 0.06, "percentage": 2.0, "elapsed_time": "0:14:32", "remaining_time": "11:52:17"}
+{"current_steps": 16, "total_steps": 750, "loss": 1.1581, "lr": 2.133333333333334e-06, "epoch": 0.064, "percentage": 2.13, "elapsed_time": "0:15:31", "remaining_time": "11:52:21"}
+{"current_steps": 17, "total_steps": 750, "loss": 1.1464, "lr": 2.266666666666667e-06, "epoch": 0.068, "percentage": 2.27, "elapsed_time": "0:16:35", "remaining_time": "11:55:06"}
+{"current_steps": 18, "total_steps": 750, "loss": 1.1216, "lr": 2.4000000000000003e-06, "epoch": 0.072, "percentage": 2.4, "elapsed_time": "0:17:28", "remaining_time": "11:50:49"}
+{"current_steps": 19, "total_steps": 750, "loss": 1.1291, "lr": 2.5333333333333338e-06, "epoch": 0.076, "percentage": 2.53, "elapsed_time": "0:18:26", "remaining_time": "11:49:38"}
+{"current_steps": 20, "total_steps": 750, "loss": 1.1498, "lr": 2.666666666666667e-06, "epoch": 0.08, "percentage": 2.67, "elapsed_time": "0:19:19", "remaining_time": "11:45:39"}
+{"current_steps": 21, "total_steps": 750, "loss": 1.1392, "lr": 2.8000000000000003e-06, "epoch": 0.084, "percentage": 2.8, "elapsed_time": "0:20:16", "remaining_time": "11:44:03"}
+{"current_steps": 22, "total_steps": 750, "loss": 1.0711, "lr": 2.9333333333333338e-06, "epoch": 0.088, "percentage": 2.93, "elapsed_time": "0:21:19", "remaining_time": "11:45:53"}
+{"current_steps": 23, "total_steps": 750, "loss": 1.0696, "lr": 3.066666666666667e-06, "epoch": 0.092, "percentage": 3.07, "elapsed_time": "0:22:15", "remaining_time": "11:43:30"}
+{"current_steps": 24, "total_steps": 750, "loss": 1.0776, "lr": 3.2000000000000003e-06, "epoch": 0.096, "percentage": 3.2, "elapsed_time": "0:23:13", "remaining_time": "11:42:45"}
+{"current_steps": 25, "total_steps": 750, "loss": 1.0791, "lr": 3.3333333333333333e-06, "epoch": 0.1, "percentage": 3.33, "elapsed_time": "0:24:09", "remaining_time": "11:40:23"}
+{"current_steps": 26, "total_steps": 750, "loss": 1.0203, "lr": 3.4666666666666672e-06, "epoch": 0.104, "percentage": 3.47, "elapsed_time": "0:24:58", "remaining_time": "11:35:24"}
+{"current_steps": 27, "total_steps": 750, "loss": 1.0466, "lr": 3.6000000000000003e-06, "epoch": 0.108, "percentage": 3.6, "elapsed_time": "0:25:57", "remaining_time": "11:35:13"}
+{"current_steps": 28, "total_steps": 750, "loss": 1.075, "lr": 3.7333333333333337e-06, "epoch": 0.112, "percentage": 3.73, "elapsed_time": "0:26:47", "remaining_time": "11:30:57"}
+{"current_steps": 29, "total_steps": 750, "loss": 1.0127, "lr": 3.866666666666667e-06, "epoch": 0.116, "percentage": 3.87, "elapsed_time": "0:27:41", "remaining_time": "11:28:16"}
+{"current_steps": 30, "total_steps": 750, "loss": 1.0196, "lr": 4.000000000000001e-06, "epoch": 0.12, "percentage": 4.0, "elapsed_time": "0:28:35", "remaining_time": "11:26:16"}
+{"current_steps": 31, "total_steps": 750, "loss": 1.0085, "lr": 4.133333333333333e-06, "epoch": 0.124, "percentage": 4.13, "elapsed_time": "0:29:35", "remaining_time": "11:26:27"}
+{"current_steps": 32, "total_steps": 750, "loss": 0.974, "lr": 4.266666666666668e-06, "epoch": 0.128, "percentage": 4.27, "elapsed_time": "0:30:28", "remaining_time": "11:23:47"}
+{"current_steps": 33, "total_steps": 750, "loss": 1.0066, "lr": 4.4e-06, "epoch": 0.132, "percentage": 4.4, "elapsed_time": "0:31:23", "remaining_time": "11:22:10"}
+{"current_steps": 34, "total_steps": 750, "loss": 1.007, "lr": 4.533333333333334e-06, "epoch": 0.136, "percentage": 4.53, "elapsed_time": "0:32:12", "remaining_time": "11:18:23"}
+{"current_steps": 35, "total_steps": 750, "loss": 0.9797, "lr": 4.666666666666667e-06, "epoch": 0.14, "percentage": 4.67, "elapsed_time": "0:33:04", "remaining_time": "11:15:45"}
+{"current_steps": 36, "total_steps": 750, "loss": 0.944, "lr": 4.800000000000001e-06, "epoch": 0.144, "percentage": 4.8, "elapsed_time": "0:34:00", "remaining_time": "11:14:36"}
+{"current_steps": 37, "total_steps": 750, "loss": 0.9859, "lr": 4.933333333333334e-06, "epoch": 0.148, "percentage": 4.93, "elapsed_time": "0:34:53", "remaining_time": "11:12:25"}
+{"current_steps": 38, "total_steps": 750, "loss": 0.9217, "lr": 5.0666666666666676e-06, "epoch": 0.152, "percentage": 5.07, "elapsed_time": "0:35:44", "remaining_time": "11:09:43"}
+{"current_steps": 39, "total_steps": 750, "loss": 1.0214, "lr": 5.2e-06, "epoch": 0.156, "percentage": 5.2, "elapsed_time": "0:36:38", "remaining_time": "11:08:06"}
+{"current_steps": 40, "total_steps": 750, "loss": 0.9908, "lr": 5.333333333333334e-06, "epoch": 0.16, "percentage": 5.33, "elapsed_time": "0:37:34", "remaining_time": "11:06:54"}
+{"current_steps": 41, "total_steps": 750, "loss": 0.9556, "lr": 5.466666666666667e-06, "epoch": 0.164, "percentage": 5.47, "elapsed_time": "0:38:29", "remaining_time": "11:05:40"}
+{"current_steps": 42, "total_steps": 750, "loss": 0.9895, "lr": 5.600000000000001e-06, "epoch": 0.168, "percentage": 5.6, "elapsed_time": "0:39:31", "remaining_time": "11:06:11"}
+{"current_steps": 43, "total_steps": 750, "loss": 0.9436, "lr": 5.733333333333334e-06, "epoch": 0.172, "percentage": 5.73, "elapsed_time": "0:40:20", "remaining_time": "11:03:22"}
+{"current_steps": 44, "total_steps": 750, "loss": 0.9396, "lr": 5.8666666666666675e-06, "epoch": 0.176, "percentage": 5.87, "elapsed_time": "0:41:20", "remaining_time": "11:03:19"}
+{"current_steps": 45, "total_steps": 750, "loss": 0.9163, "lr": 6e-06, "epoch": 0.18, "percentage": 6.0, "elapsed_time": "0:42:12", "remaining_time": "11:01:13"}
+{"current_steps": 46, "total_steps": 750, "loss": 0.9423, "lr": 6.133333333333334e-06, "epoch": 0.184, "percentage": 6.13, "elapsed_time": "0:43:06", "remaining_time": "10:59:39"}
+{"current_steps": 47, "total_steps": 750, "loss": 0.9291, "lr": 6.266666666666668e-06, "epoch": 0.188, "percentage": 6.27, "elapsed_time": "0:43:56", "remaining_time": "10:57:17"}
+{"current_steps": 48, "total_steps": 750, "loss": 0.9342, "lr": 6.4000000000000006e-06, "epoch": 0.192, "percentage": 6.4, "elapsed_time": "0:44:50", "remaining_time": "10:55:41"}
+{"current_steps": 49, "total_steps": 750, "loss": 0.9692, "lr": 6.533333333333334e-06, "epoch": 0.196, "percentage": 6.53, "elapsed_time": "0:45:45", "remaining_time": "10:54:38"}
+{"current_steps": 50, "total_steps": 750, "loss": 0.9217, "lr": 6.666666666666667e-06, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "0:46:40", "remaining_time": "10:53:28"}
+{"current_steps": 51, "total_steps": 750, "loss": 0.9415, "lr": 6.800000000000001e-06, "epoch": 0.204, "percentage": 6.8, "elapsed_time": "0:47:39", "remaining_time": "10:53:17"}
+{"current_steps": 52, "total_steps": 750, "loss": 0.9221, "lr": 6.9333333333333344e-06, "epoch": 0.208, "percentage": 6.93, "elapsed_time": "0:48:40", "remaining_time": "10:53:28"}
+{"current_steps": 53, "total_steps": 750, "loss": 0.9241, "lr": 7.066666666666667e-06, "epoch": 0.212, "percentage": 7.07, "elapsed_time": "0:49:32", "remaining_time": "10:51:26"}
+{"current_steps": 54, "total_steps": 750, "loss": 0.938, "lr": 7.2000000000000005e-06, "epoch": 0.216, "percentage": 7.2, "elapsed_time": "0:50:27", "remaining_time": "10:50:21"}
+{"current_steps": 55, "total_steps": 750, "loss": 0.9446, "lr": 7.333333333333333e-06, "epoch": 0.22, "percentage": 7.33, "elapsed_time": "0:51:20", "remaining_time": "10:48:51"}
+{"current_steps": 56, "total_steps": 750, "loss": 0.9678, "lr": 7.4666666666666675e-06, "epoch": 0.224, "percentage": 7.47, "elapsed_time": "0:52:10", "remaining_time": "10:46:38"}
+{"current_steps": 57, "total_steps": 750, "loss": 0.9881, "lr": 7.600000000000001e-06, "epoch": 0.228, "percentage": 7.6, "elapsed_time": "0:53:02", "remaining_time": "10:44:49"}
+{"current_steps": 58, "total_steps": 750, "loss": 0.8889, "lr": 7.733333333333334e-06, "epoch": 0.232, "percentage": 7.73, "elapsed_time": "0:53:41", "remaining_time": "10:40:39"}
+{"current_steps": 59, "total_steps": 750, "loss": 0.9487, "lr": 7.866666666666667e-06, "epoch": 0.236, "percentage": 7.87, "elapsed_time": "0:54:29", "remaining_time": "10:38:13"}
+{"current_steps": 60, "total_steps": 750, "loss": 0.9578, "lr": 8.000000000000001e-06, "epoch": 0.24, "percentage": 8.0, "elapsed_time": "0:55:23", "remaining_time": "10:37:04"}
+{"current_steps": 61, "total_steps": 750, "loss": 0.8946, "lr": 8.133333333333334e-06, "epoch": 0.244, "percentage": 8.13, "elapsed_time": "0:56:15", "remaining_time": "10:35:27"}
+{"current_steps": 62, "total_steps": 750, "loss": 0.9212, "lr": 8.266666666666667e-06, "epoch": 0.248, "percentage": 8.27, "elapsed_time": "0:57:11", "remaining_time": "10:34:36"}
+{"current_steps": 63, "total_steps": 750, "loss": 0.9059, "lr": 8.400000000000001e-06, "epoch": 0.252, "percentage": 8.4, "elapsed_time": "0:58:00", "remaining_time": "10:32:36"}
+{"current_steps": 64, "total_steps": 750, "loss": 0.9252, "lr": 8.533333333333335e-06, "epoch": 0.256, "percentage": 8.53, "elapsed_time": "0:58:56", "remaining_time": "10:31:43"}
+{"current_steps": 65, "total_steps": 750, "loss": 0.9111, "lr": 8.666666666666668e-06, "epoch": 0.26, "percentage": 8.67, "elapsed_time": "0:59:45", "remaining_time": "10:29:47"}
+{"current_steps": 66, "total_steps": 750, "loss": 0.9215, "lr": 8.8e-06, "epoch": 0.264, "percentage": 8.8, "elapsed_time": "1:00:41", "remaining_time": "10:29:04"}
+{"current_steps": 67, "total_steps": 750, "loss": 0.9181, "lr": 8.933333333333333e-06, "epoch": 0.268, "percentage": 8.93, "elapsed_time": "1:01:30", "remaining_time": "10:27:02"}
+{"current_steps": 68, "total_steps": 750, "loss": 0.9102, "lr": 9.066666666666667e-06, "epoch": 0.272, "percentage": 9.07, "elapsed_time": "1:02:21", "remaining_time": "10:25:24"}
+{"current_steps": 69, "total_steps": 750, "loss": 0.9628, "lr": 9.200000000000002e-06, "epoch": 0.276, "percentage": 9.2, "elapsed_time": "1:03:21", "remaining_time": "10:25:15"}
+{"current_steps": 70, "total_steps": 750, "loss": 0.9093, "lr": 9.333333333333334e-06, "epoch": 0.28, "percentage": 9.33, "elapsed_time": "1:04:10", "remaining_time": "10:23:23"}
+{"current_steps": 71, "total_steps": 750, "loss": 0.9196, "lr": 9.466666666666667e-06, "epoch": 0.284, "percentage": 9.47, "elapsed_time": "1:05:11", "remaining_time": "10:23:26"}
+{"current_steps": 72, "total_steps": 750, "loss": 0.9103, "lr": 9.600000000000001e-06, "epoch": 0.288, "percentage": 9.6, "elapsed_time": "1:06:11", "remaining_time": "10:23:15"}
+{"current_steps": 73, "total_steps": 750, "loss": 0.912, "lr": 9.733333333333334e-06, "epoch": 0.292, "percentage": 9.73, "elapsed_time": "1:06:59", "remaining_time": "10:21:19"}
+{"current_steps": 74, "total_steps": 750, "loss": 0.9267, "lr": 9.866666666666668e-06, "epoch": 0.296, "percentage": 9.87, "elapsed_time": "1:07:53", "remaining_time": "10:20:12"}
+{"current_steps": 75, "total_steps": 750, "loss": 0.9362, "lr": 1e-05, "epoch": 0.3, "percentage": 10.0, "elapsed_time": "1:08:52", "remaining_time": "10:19:48"}
+{"current_steps": 76, "total_steps": 750, "loss": 0.9044, "lr": 9.999945845889795e-06, "epoch": 0.304, "percentage": 10.13, "elapsed_time": "1:09:47", "remaining_time": "10:18:57"}
+{"current_steps": 77, "total_steps": 750, "loss": 0.9154, "lr": 9.999783384732242e-06, "epoch": 0.308, "percentage": 10.27, "elapsed_time": "1:10:42", "remaining_time": "10:18:04"}
+{"current_steps": 78, "total_steps": 750, "loss": 0.9165, "lr": 9.999512620046523e-06, "epoch": 0.312, "percentage": 10.4, "elapsed_time": "1:11:36", "remaining_time": "10:16:59"}
+{"current_steps": 79, "total_steps": 750, "loss": 0.888, "lr": 9.99913355769784e-06, "epoch": 0.316, "percentage": 10.53, "elapsed_time": "1:12:29", "remaining_time": "10:15:43"}
+{"current_steps": 80, "total_steps": 750, "loss": 0.893, "lr": 9.99864620589731e-06, "epoch": 0.32, "percentage": 10.67, "elapsed_time": "1:13:24", "remaining_time": "10:14:49"}
+{"current_steps": 81, "total_steps": 750, "loss": 0.9172, "lr": 9.998050575201772e-06, "epoch": 0.324, "percentage": 10.8, "elapsed_time": "1:14:23", "remaining_time": "10:14:28"}
+{"current_steps": 82, "total_steps": 750, "loss": 0.92, "lr": 9.99734667851357e-06, "epoch": 0.328, "percentage": 10.93, "elapsed_time": "1:15:16", "remaining_time": "10:13:16"}
+{"current_steps": 83, "total_steps": 750, "loss": 0.9024, "lr": 9.99653453108026e-06, "epoch": 0.332, "percentage": 11.07, "elapsed_time": "1:16:08", "remaining_time": "10:11:49"}
+{"current_steps": 84, "total_steps": 750, "loss": 0.8922, "lr": 9.995614150494293e-06, "epoch": 0.336, "percentage": 11.2, "elapsed_time": "1:17:03", "remaining_time": "10:10:57"}
+{"current_steps": 85, "total_steps": 750, "loss": 0.8498, "lr": 9.994585556692624e-06, "epoch": 0.34, "percentage": 11.33, "elapsed_time": "1:17:58", "remaining_time": "10:10:04"}
+{"current_steps": 86, "total_steps": 750, "loss": 0.8773, "lr": 9.993448771956285e-06, "epoch": 0.344, "percentage": 11.47, "elapsed_time": "1:18:44", "remaining_time": "10:07:56"}
+{"current_steps": 87, "total_steps": 750, "loss": 0.8891, "lr": 9.992203820909906e-06, "epoch": 0.348, "percentage": 11.6, "elapsed_time": "1:19:34", "remaining_time": "10:06:21"}
+{"current_steps": 88, "total_steps": 750, "loss": 0.8881, "lr": 9.99085073052117e-06, "epoch": 0.352, "percentage": 11.73, "elapsed_time": "1:20:20", "remaining_time": "10:04:25"}
+{"current_steps": 89, "total_steps": 750, "loss": 0.8782, "lr": 9.989389530100242e-06, "epoch": 0.356, "percentage": 11.87, "elapsed_time": "1:21:21", "remaining_time": "10:04:12"}
+{"current_steps": 90, "total_steps": 750, "loss": 0.8983, "lr": 9.987820251299121e-06, "epoch": 0.36, "percentage": 12.0, "elapsed_time": "1:22:20", "remaining_time": "10:03:48"}
+{"current_steps": 91, "total_steps": 750, "loss": 0.9172, "lr": 9.986142928110972e-06, "epoch": 0.364, "percentage": 12.13, "elapsed_time": "1:23:19", "remaining_time": "10:03:27"}
+{"current_steps": 92, "total_steps": 750, "loss": 0.9262, "lr": 9.984357596869369e-06, "epoch": 0.368, "percentage": 12.27, "elapsed_time": "1:24:12", "remaining_time": "10:02:19"}
+{"current_steps": 93, "total_steps": 750, "loss": 0.8963, "lr": 9.982464296247523e-06, "epoch": 0.372, "percentage": 12.4, "elapsed_time": "1:25:01", "remaining_time": "10:00:39"}
+{"current_steps": 94, "total_steps": 750, "loss": 0.8983, "lr": 9.980463067257437e-06, "epoch": 0.376, "percentage": 12.53, "elapsed_time": "1:25:57", "remaining_time": "9:59:52"}
+{"current_steps": 95, "total_steps": 750, "loss": 0.9304, "lr": 9.978353953249023e-06, "epoch": 0.38, "percentage": 12.67, "elapsed_time": "1:26:58", "remaining_time": "9:59:39"}
+{"current_steps": 96, "total_steps": 750, "loss": 0.8958, "lr": 9.976136999909156e-06, "epoch": 0.384, "percentage": 12.8, "elapsed_time": "1:27:47", "remaining_time": "9:58:04"}
+{"current_steps": 97, "total_steps": 750, "loss": 0.8795, "lr": 9.973812255260692e-06, "epoch": 0.388, "percentage": 12.93, "elapsed_time": "1:28:50", "remaining_time": "9:58:06"}
+{"current_steps": 98, "total_steps": 750, "loss": 0.9067, "lr": 9.971379769661422e-06, "epoch": 0.392, "percentage": 13.07, "elapsed_time": "1:29:54", "remaining_time": "9:58:08"}
+{"current_steps": 99, "total_steps": 750, "loss": 0.9028, "lr": 9.968839595802982e-06, "epoch": 0.396, "percentage": 13.2, "elapsed_time": "1:30:48", "remaining_time": "9:57:06"}
+{"current_steps": 100, "total_steps": 750, "loss": 0.8738, "lr": 9.966191788709716e-06, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "1:31:38", "remaining_time": "9:55:42"}
+{"current_steps": 101, "total_steps": 750, "loss": 0.9183, "lr": 9.963436405737476e-06, "epoch": 0.404, "percentage": 13.47, "elapsed_time": "1:32:43", "remaining_time": "9:55:51"}
+{"current_steps": 102, "total_steps": 750, "loss": 0.8845, "lr": 9.960573506572391e-06, "epoch": 0.408, "percentage": 13.6, "elapsed_time": "1:33:46", "remaining_time": "9:55:46"}
+{"current_steps": 103, "total_steps": 750, "loss": 0.8923, "lr": 9.957603153229559e-06, "epoch": 0.412, "percentage": 13.73, "elapsed_time": "1:34:45", "remaining_time": "9:55:16"}
+{"current_steps": 104, "total_steps": 750, "loss": 0.9223, "lr": 9.95452541005172e-06, "epoch": 0.416, "percentage": 13.87, "elapsed_time": "1:35:49", "remaining_time": "9:55:12"}
+{"current_steps": 105, "total_steps": 750, "loss": 0.9089, "lr": 9.951340343707852e-06, "epoch": 0.42, "percentage": 14.0, "elapsed_time": "1:36:44", "remaining_time": "9:54:15"}
+{"current_steps": 106, "total_steps": 750, "loss": 0.9297, "lr": 9.948048023191728e-06, "epoch": 0.424, "percentage": 14.13, "elapsed_time": "1:37:46", "remaining_time": "9:54:03"}
+{"current_steps": 107, "total_steps": 750, "loss": 0.8841, "lr": 9.94464851982042e-06, "epoch": 0.428, "percentage": 14.27, "elapsed_time": "1:38:48", "remaining_time": "9:53:44"}
+{"current_steps": 108, "total_steps": 750, "loss": 0.8413, "lr": 9.941141907232766e-06, "epoch": 0.432, "percentage": 14.4, "elapsed_time": "1:39:39", "remaining_time": "9:52:25"}
+{"current_steps": 109, "total_steps": 750, "loss": 0.8973, "lr": 9.937528261387753e-06, "epoch": 0.436, "percentage": 14.53, "elapsed_time": "1:40:41", "remaining_time": "9:52:06"}
+{"current_steps": 110, "total_steps": 750, "loss": 0.9139, "lr": 9.933807660562898e-06, "epoch": 0.44, "percentage": 14.67, "elapsed_time": "1:41:39", "remaining_time": "9:51:29"}
+{"current_steps": 111, "total_steps": 750, "loss": 0.8575, "lr": 9.929980185352525e-06, "epoch": 0.444, "percentage": 14.8, "elapsed_time": "1:42:39", "remaining_time": "9:50:56"}
+{"current_steps": 112, "total_steps": 750, "loss": 0.8975, "lr": 9.926045918666045e-06, "epoch": 0.448, "percentage": 14.93, "elapsed_time": "1:43:41", "remaining_time": "9:50:39"}
+{"current_steps": 113, "total_steps": 750, "loss": 0.8744, "lr": 9.92200494572614e-06, "epoch": 0.452, "percentage": 15.07, "elapsed_time": "1:44:28", "remaining_time": "9:48:56"}
+{"current_steps": 114, "total_steps": 750, "loss": 0.9071, "lr": 9.91785735406693e-06, "epoch": 0.456, "percentage": 15.2, "elapsed_time": "1:45:27", "remaining_time": "9:48:21"}
+{"current_steps": 115, "total_steps": 750, "loss": 0.8851, "lr": 9.913603233532067e-06, "epoch": 0.46, "percentage": 15.33, "elapsed_time": "1:46:19", "remaining_time": "9:47:05"}
+{"current_steps": 116, "total_steps": 750, "loss": 0.8859, "lr": 9.909242676272797e-06, "epoch": 0.464, "percentage": 15.47, "elapsed_time": "1:47:21", "remaining_time": "9:46:47"}
+{"current_steps": 117, "total_steps": 750, "loss": 0.9192, "lr": 9.904775776745959e-06, "epoch": 0.468, "percentage": 15.6, "elapsed_time": "1:48:13", "remaining_time": "9:45:32"}
+{"current_steps": 118, "total_steps": 750, "loss": 0.924, "lr": 9.90020263171194e-06, "epoch": 0.472, "percentage": 15.73, "elapsed_time": "1:49:00", "remaining_time": "9:43:49"}
+{"current_steps": 119, "total_steps": 750, "loss": 0.9017, "lr": 9.89552334023258e-06, "epoch": 0.476, "percentage": 15.87, "elapsed_time": "1:50:01", "remaining_time": "9:43:26"}
+{"current_steps": 120, "total_steps": 750, "loss": 0.885, "lr": 9.890738003669029e-06, "epoch": 0.48, "percentage": 16.0, "elapsed_time": "1:50:58", "remaining_time": "9:42:38"}
+{"current_steps": 121, "total_steps": 750, "loss": 0.8535, "lr": 9.88584672567954e-06, "epoch": 0.484, "percentage": 16.13, "elapsed_time": "1:51:54", "remaining_time": "9:41:46"}
+{"current_steps": 122, "total_steps": 750, "loss": 0.9136, "lr": 9.880849612217238e-06, "epoch": 0.488, "percentage": 16.27, "elapsed_time": "1:52:50", "remaining_time": "9:40:52"}
+{"current_steps": 123, "total_steps": 750, "loss": 0.891, "lr": 9.875746771527817e-06, "epoch": 0.492, "percentage": 16.4, "elapsed_time": "1:53:45", "remaining_time": "9:39:55"}
+{"current_steps": 124, "total_steps": 750, "loss": 0.8793, "lr": 9.870538314147194e-06, "epoch": 0.496, "percentage": 16.53, "elapsed_time": "1:54:40", "remaining_time": "9:38:54"}
+{"current_steps": 125, "total_steps": 750, "loss": 0.9114, "lr": 9.86522435289912e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "1:55:32", "remaining_time": "9:37:41"}
+{"current_steps": 126, "total_steps": 750, "loss": 0.925, "lr": 9.859805002892733e-06, "epoch": 0.504, "percentage": 16.8, "elapsed_time": "1:56:33", "remaining_time": "9:37:13"}
+{"current_steps": 127, "total_steps": 750, "loss": 0.9076, "lr": 9.85428038152006e-06, "epoch": 0.508, "percentage": 16.93, "elapsed_time": "1:57:31", "remaining_time": "9:36:30"}
+{"current_steps": 128, "total_steps": 750, "loss": 0.8609, "lr": 9.84865060845349e-06, "epoch": 0.512, "percentage": 17.07, "elapsed_time": "1:58:32", "remaining_time": "9:36:01"}
+{"current_steps": 129, "total_steps": 750, "loss": 0.8873, "lr": 9.842915805643156e-06, "epoch": 0.516, "percentage": 17.2, "elapsed_time": "1:59:27", "remaining_time": "9:35:05"}
+{"current_steps": 130, "total_steps": 750, "loss": 0.8593, "lr": 9.83707609731432e-06, "epoch": 0.52, "percentage": 17.33, "elapsed_time": "2:00:32", "remaining_time": "9:34:51"}
+{"current_steps": 131, "total_steps": 750, "loss": 0.8927, "lr": 9.831131609964664e-06, "epoch": 0.524, "percentage": 17.47, "elapsed_time": "2:01:22", "remaining_time": "9:33:29"}
+{"current_steps": 132, "total_steps": 750, "loss": 0.8913, "lr": 9.825082472361558e-06, "epoch": 0.528, "percentage": 17.6, "elapsed_time": "2:02:25", "remaining_time": "9:33:11"}
+{"current_steps": 133, "total_steps": 750, "loss": 0.8991, "lr": 9.818928815539266e-06, "epoch": 0.532, "percentage": 17.73, "elapsed_time": "2:03:21", "remaining_time": "9:32:16"}
+{"current_steps": 134, "total_steps": 750, "loss": 0.8736, "lr": 9.812670772796113e-06, "epoch": 0.536, "percentage": 17.87, "elapsed_time": "2:04:15", "remaining_time": "9:31:10"}
+{"current_steps": 135, "total_steps": 750, "loss": 0.9092, "lr": 9.806308479691595e-06, "epoch": 0.54, "percentage": 18.0, "elapsed_time": "2:05:18", "remaining_time": "9:30:49"}
+{"current_steps": 136, "total_steps": 750, "loss": 0.8942, "lr": 9.799842074043438e-06, "epoch": 0.544, "percentage": 18.13, "elapsed_time": "2:06:16", "remaining_time": "9:30:04"}
+{"current_steps": 137, "total_steps": 750, "loss": 0.9019, "lr": 9.793271695924621e-06, "epoch": 0.548, "percentage": 18.27, "elapsed_time": "2:07:19", "remaining_time": "9:29:40"}
+{"current_steps": 138, "total_steps": 750, "loss": 0.8997, "lr": 9.786597487660336e-06, "epoch": 0.552, "percentage": 18.4, "elapsed_time": "2:08:12", "remaining_time": "9:28:34"}
+{"current_steps": 139, "total_steps": 750, "loss": 0.902, "lr": 9.779819593824909e-06, "epoch": 0.556, "percentage": 18.53, "elapsed_time": "2:09:11", "remaining_time": "9:27:51"}
+{"current_steps": 140, "total_steps": 750, "loss": 0.9324, "lr": 9.77293816123866e-06, "epoch": 0.56, "percentage": 18.67, "elapsed_time": "2:10:11", "remaining_time": "9:27:15"}
+{"current_steps": 141, "total_steps": 750, "loss": 0.9258, "lr": 9.765953338964736e-06, "epoch": 0.564, "percentage": 18.8, "elapsed_time": "2:11:12", "remaining_time": "9:26:44"}
+{"current_steps": 142, "total_steps": 750, "loss": 0.9035, "lr": 9.75886527830587e-06, "epoch": 0.568, "percentage": 18.93, "elapsed_time": "2:12:20", "remaining_time": "9:26:40"}
+{"current_steps": 143, "total_steps": 750, "loss": 0.8789, "lr": 9.751674132801106e-06, "epoch": 0.572, "percentage": 19.07, "elapsed_time": "2:13:16", "remaining_time": "9:25:41"}
+{"current_steps": 144, "total_steps": 750, "loss": 0.848, "lr": 9.744380058222483e-06, "epoch": 0.576, "percentage": 19.2, "elapsed_time": "2:14:07", "remaining_time": "9:24:24"}
+{"current_steps": 145, "total_steps": 750, "loss": 0.9007, "lr": 9.736983212571646e-06, "epoch": 0.58, "percentage": 19.33, "elapsed_time": "2:15:07", "remaining_time": "9:23:49"}
+{"current_steps": 146, "total_steps": 750, "loss": 0.8592, "lr": 9.729483756076436e-06, "epoch": 0.584, "percentage": 19.47, "elapsed_time": "2:16:06", "remaining_time": "9:23:03"}
+{"current_steps": 147, "total_steps": 750, "loss": 0.8595, "lr": 9.721881851187406e-06, "epoch": 0.588, "percentage": 19.6, "elapsed_time": "2:17:00", "remaining_time": "9:22:01"}
+{"current_steps": 148, "total_steps": 750, "loss": 0.8635, "lr": 9.714177662574316e-06, "epoch": 0.592, "percentage": 19.73, "elapsed_time": "2:17:51", "remaining_time": "9:20:45"}
+{"current_steps": 149, "total_steps": 750, "loss": 0.9157, "lr": 9.70637135712256e-06, "epoch": 0.596, "percentage": 19.87, "elapsed_time": "2:18:51", "remaining_time": "9:20:07"}
+{"current_steps": 150, "total_steps": 750, "loss": 0.8875, "lr": 9.698463103929542e-06, "epoch": 0.6, "percentage": 20.0, "elapsed_time": "2:19:44", "remaining_time": "9:18:57"}
+{"current_steps": 151, "total_steps": 750, "loss": 0.8598, "lr": 9.690453074301035e-06, "epoch": 0.604, "percentage": 20.13, "elapsed_time": "2:20:41", "remaining_time": "9:18:07"}
+{"current_steps": 152, "total_steps": 750, "loss": 0.8933, "lr": 9.682341441747446e-06, "epoch": 0.608, "percentage": 20.27, "elapsed_time": "2:21:31", "remaining_time": "9:16:46"}
+{"current_steps": 153, "total_steps": 750, "loss": 0.8675, "lr": 9.674128381980073e-06, "epoch": 0.612, "percentage": 20.4, "elapsed_time": "2:22:31", "remaining_time": "9:16:08"}
+{"current_steps": 154, "total_steps": 750, "loss": 0.8784, "lr": 9.665814072907293e-06, "epoch": 0.616, "percentage": 20.53, "elapsed_time": "2:23:27", "remaining_time": "9:15:11"}
+{"current_steps": 155, "total_steps": 750, "loss": 0.8861, "lr": 9.657398694630713e-06, "epoch": 0.62, "percentage": 20.67, "elapsed_time": "2:24:20", "remaining_time": "9:14:06"}
+{"current_steps": 156, "total_steps": 750, "loss": 0.8722, "lr": 9.648882429441258e-06, "epoch": 0.624, "percentage": 20.8, "elapsed_time": "2:25:15", "remaining_time": "9:13:06"}
+{"current_steps": 157, "total_steps": 750, "loss": 0.9008, "lr": 9.640265461815235e-06, "epoch": 0.628, "percentage": 20.93, "elapsed_time": "2:26:07", "remaining_time": "9:11:55"}
+{"current_steps": 158, "total_steps": 750, "loss": 0.8751, "lr": 9.63154797841033e-06, "epoch": 0.632, "percentage": 21.07, "elapsed_time": "2:27:02", "remaining_time": "9:10:56"}
+{"current_steps": 159, "total_steps": 750, "loss": 0.8597, "lr": 9.622730168061568e-06, "epoch": 0.636, "percentage": 21.2, "elapsed_time": "2:27:53", "remaining_time": "9:09:43"}
+{"current_steps": 160, "total_steps": 750, "loss": 0.872, "lr": 9.613812221777212e-06, "epoch": 0.64, "percentage": 21.33, "elapsed_time": "2:28:48", "remaining_time": "9:08:45"}
+{"current_steps": 161, "total_steps": 750, "loss": 0.8832, "lr": 9.604794332734647e-06, "epoch": 0.644, "percentage": 21.47, "elapsed_time": "2:29:52", "remaining_time": "9:08:18"}
+{"current_steps": 162, "total_steps": 750, "loss": 0.8768, "lr": 9.595676696276173e-06, "epoch": 0.648, "percentage": 21.6, "elapsed_time": "2:30:53", "remaining_time": "9:07:42"}
+{"current_steps": 163, "total_steps": 750, "loss": 0.8677, "lr": 9.586459509904786e-06, "epoch": 0.652, "percentage": 21.73, "elapsed_time": "2:31:51", "remaining_time": "9:06:54"}
+{"current_steps": 164, "total_steps": 750, "loss": 0.8617, "lr": 9.577142973279896e-06, "epoch": 0.656, "percentage": 21.87, "elapsed_time": "2:32:49", "remaining_time": "9:06:03"}
+{"current_steps": 165, "total_steps": 750, "loss": 0.8855, "lr": 9.567727288213005e-06, "epoch": 0.66, "percentage": 22.0, "elapsed_time": "2:33:44", "remaining_time": "9:05:05"}
+{"current_steps": 166, "total_steps": 750, "loss": 0.8652, "lr": 9.55821265866333e-06, "epoch": 0.664, "percentage": 22.13, "elapsed_time": "2:34:44", "remaining_time": "9:04:23"}
+{"current_steps": 167, "total_steps": 750, "loss": 0.923, "lr": 9.548599290733393e-06, "epoch": 0.668, "percentage": 22.27, "elapsed_time": "2:35:41", "remaining_time": "9:03:30"}
+{"current_steps": 168, "total_steps": 750, "loss": 0.9191, "lr": 9.538887392664544e-06, "epoch": 0.672, "percentage": 22.4, "elapsed_time": "2:36:40", "remaining_time": "9:02:47"}
+{"current_steps": 169, "total_steps": 750, "loss": 0.8987, "lr": 9.529077174832466e-06, "epoch": 0.676, "percentage": 22.53, "elapsed_time": "2:37:40", "remaining_time": "9:02:03"}
+{"current_steps": 170, "total_steps": 750, "loss": 0.8746, "lr": 9.519168849742603e-06, "epoch": 0.68, "percentage": 22.67, "elapsed_time": "2:38:42", "remaining_time": "9:01:28"}
+{"current_steps": 171, "total_steps": 750, "loss": 0.8844, "lr": 9.50916263202557e-06, "epoch": 0.684, "percentage": 22.8, "elapsed_time": "2:39:39", "remaining_time": "9:00:34"}
+{"current_steps": 172, "total_steps": 750, "loss": 0.8763, "lr": 9.499058738432492e-06, "epoch": 0.688, "percentage": 22.93, "elapsed_time": "2:40:31", "remaining_time": "8:59:24"}
+{"current_steps": 173, "total_steps": 750, "loss": 0.8783, "lr": 9.488857387830315e-06, "epoch": 0.692, "percentage": 23.07, "elapsed_time": "2:41:26", "remaining_time": "8:58:28"}
+{"current_steps": 174, "total_steps": 750, "loss": 0.8808, "lr": 9.478558801197065e-06, "epoch": 0.696, "percentage": 23.2, "elapsed_time": "2:42:24", "remaining_time": "8:57:38"}
+{"current_steps": 175, "total_steps": 750, "loss": 0.8312, "lr": 9.468163201617063e-06, "epoch": 0.7, "percentage": 23.33, "elapsed_time": "2:43:12", "remaining_time": "8:56:15"}
+{"current_steps": 176, "total_steps": 750, "loss": 0.8979, "lr": 9.457670814276083e-06, "epoch": 0.704, "percentage": 23.47, "elapsed_time": "2:44:17", "remaining_time": "8:55:48"}
+{"current_steps": 177, "total_steps": 750, "loss": 0.8708, "lr": 9.44708186645649e-06, "epoch": 0.708, "percentage": 23.6, "elapsed_time": "2:45:14", "remaining_time": "8:54:55"}
+{"current_steps": 178, "total_steps": 750, "loss": 0.9053, "lr": 9.436396587532297e-06, "epoch": 0.712, "percentage": 23.73, "elapsed_time": "2:46:14", "remaining_time": "8:54:13"}
+{"current_steps": 179, "total_steps": 750, "loss": 0.8701, "lr": 9.425615208964217e-06, "epoch": 0.716, "percentage": 23.87, "elapsed_time": "2:47:13", "remaining_time": "8:53:25"}
+{"current_steps": 180, "total_steps": 750, "loss": 0.9063, "lr": 9.414737964294636e-06, "epoch": 0.72, "percentage": 24.0, "elapsed_time": "2:48:09", "remaining_time": "8:52:30"}
+{"current_steps": 181, "total_steps": 750, "loss": 0.8534, "lr": 9.403765089142554e-06, "epoch": 0.724, "percentage": 24.13, "elapsed_time": "2:49:09", "remaining_time": "8:51:44"}
+{"current_steps": 182, "total_steps": 750, "loss": 0.868, "lr": 9.392696821198488e-06, "epoch": 0.728, "percentage": 24.27, "elapsed_time": "2:49:59", "remaining_time": "8:50:32"}
+{"current_steps": 183, "total_steps": 750, "loss": 0.8942, "lr": 9.381533400219319e-06, "epoch": 0.732, "percentage": 24.4, "elapsed_time": "2:50:50", "remaining_time": "8:49:18"}
+{"current_steps": 184, "total_steps": 750, "loss": 0.9089, "lr": 9.370275068023097e-06, "epoch": 0.736, "percentage": 24.53, "elapsed_time": "2:51:51", "remaining_time": "8:48:38"}
+{"current_steps": 185, "total_steps": 750, "loss": 0.8677, "lr": 9.358922068483813e-06, "epoch": 0.74, "percentage": 24.67, "elapsed_time": "2:52:44", "remaining_time": "8:47:35"}
+{"current_steps": 186, "total_steps": 750, "loss": 0.8855, "lr": 9.347474647526095e-06, "epoch": 0.744, "percentage": 24.8, "elapsed_time": "2:53:30", "remaining_time": "8:46:06"}
+{"current_steps": 187, "total_steps": 750, "loss": 0.8683, "lr": 9.335933053119906e-06, "epoch": 0.748, "percentage": 24.93, "elapsed_time": "2:54:16", "remaining_time": "8:44:42"}
+{"current_steps": 188, "total_steps": 750, "loss": 0.8607, "lr": 9.324297535275156e-06, "epoch": 0.752, "percentage": 25.07, "elapsed_time": "2:55:03", "remaining_time": "8:43:19"}
+{"current_steps": 189, "total_steps": 750, "loss": 0.8911, "lr": 9.312568346036288e-06, "epoch": 0.756, "percentage": 25.2, "elapsed_time": "2:56:03", "remaining_time": "8:42:35"}
+{"current_steps": 190, "total_steps": 750, "loss": 0.8981, "lr": 9.30074573947683e-06, "epoch": 0.76, "percentage": 25.33, "elapsed_time": "2:57:07", "remaining_time": "8:42:03"}
+{"current_steps": 191, "total_steps": 750, "loss": 0.8827, "lr": 9.288829971693869e-06, "epoch": 0.764, "percentage": 25.47, "elapsed_time": "2:58:02", "remaining_time": "8:41:04"}
+{"current_steps": 192, "total_steps": 750, "loss": 0.8589, "lr": 9.276821300802535e-06, "epoch": 0.768, "percentage": 25.6, "elapsed_time": "2:59:03", "remaining_time": "8:40:21"}
+{"current_steps": 193, "total_steps": 750, "loss": 0.8921, "lr": 9.264719986930376e-06, "epoch": 0.772, "percentage": 25.73, "elapsed_time": "2:59:58", "remaining_time": "8:39:23"}
+{"current_steps": 194, "total_steps": 750, "loss": 0.8886, "lr": 9.25252629221175e-06, "epoch": 0.776, "percentage": 25.87, "elapsed_time": "3:00:54", "remaining_time": "8:38:29"}
+{"current_steps": 195, "total_steps": 750, "loss": 0.891, "lr": 9.24024048078213e-06, "epoch": 0.78, "percentage": 26.0, "elapsed_time": "3:02:06", "remaining_time": "8:38:19"}
+{"current_steps": 196, "total_steps": 750, "loss": 0.8743, "lr": 9.227862818772392e-06, "epoch": 0.784, "percentage": 26.13, "elapsed_time": "3:02:59", "remaining_time": "8:37:13"}
+{"current_steps": 197, "total_steps": 750, "loss": 0.8985, "lr": 9.215393574303043e-06, "epoch": 0.788, "percentage": 26.27, "elapsed_time": "3:03:57", "remaining_time": "8:36:23"}
+{"current_steps": 198, "total_steps": 750, "loss": 0.8848, "lr": 9.202833017478421e-06, "epoch": 0.792, "percentage": 26.4, "elapsed_time": "3:04:44", "remaining_time": "8:35:01"}
+{"current_steps": 199, "total_steps": 750, "loss": 0.8926, "lr": 9.190181420380838e-06, "epoch": 0.796, "percentage": 26.53, "elapsed_time": "3:05:50", "remaining_time": "8:34:33"}
+{"current_steps": 200, "total_steps": 750, "loss": 0.8825, "lr": 9.177439057064684e-06, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "3:06:43", "remaining_time": "8:33:29"}
+{"current_steps": 201, "total_steps": 750, "loss": 0.8927, "lr": 9.164606203550498e-06, "epoch": 0.804, "percentage": 26.8, "elapsed_time": "3:07:45", "remaining_time": "8:32:49"}
+{"current_steps": 202, "total_steps": 750, "loss": 0.8901, "lr": 9.151683137818989e-06, "epoch": 0.808, "percentage": 26.93, "elapsed_time": "3:08:47", "remaining_time": "8:32:10"}
+{"current_steps": 203, "total_steps": 750, "loss": 0.8637, "lr": 9.138670139805004e-06, "epoch": 0.812, "percentage": 27.07, "elapsed_time": "3:09:38", "remaining_time": "8:31:00"}
+{"current_steps": 204, "total_steps": 750, "loss": 0.8796, "lr": 9.125567491391476e-06, "epoch": 0.816, "percentage": 27.2, "elapsed_time": "3:10:27", "remaining_time": "8:29:45"}
+{"current_steps": 205, "total_steps": 750, "loss": 0.8838, "lr": 9.112375476403313e-06, "epoch": 0.82, "percentage": 27.33, "elapsed_time": "3:11:29", "remaining_time": "8:29:06"}
+{"current_steps": 206, "total_steps": 750, "loss": 0.8806, "lr": 9.099094380601244e-06, "epoch": 0.824, "percentage": 27.47, "elapsed_time": "3:12:25", "remaining_time": "8:28:10"}
+{"current_steps": 207, "total_steps": 750, "loss": 0.8677, "lr": 9.085724491675642e-06, "epoch": 0.828, "percentage": 27.6, "elapsed_time": "3:13:26", "remaining_time": "8:27:25"}
+{"current_steps": 208, "total_steps": 750, "loss": 0.8656, "lr": 9.072266099240286e-06, "epoch": 0.832, "percentage": 27.73, "elapsed_time": "3:14:18", "remaining_time": "8:26:20"}
+{"current_steps": 209, "total_steps": 750, "loss": 0.9051, "lr": 9.058719494826076e-06, "epoch": 0.836, "percentage": 27.87, "elapsed_time": "3:15:20", "remaining_time": "8:25:38"}
+{"current_steps": 210, "total_steps": 750, "loss": 0.8553, "lr": 9.045084971874738e-06, "epoch": 0.84, "percentage": 28.0, "elapsed_time": "3:16:16", "remaining_time": "8:24:41"}
+{"current_steps": 211, "total_steps": 750, "loss": 0.838, "lr": 9.031362825732456e-06, "epoch": 0.844, "percentage": 28.13, "elapsed_time": "3:17:07", "remaining_time": "8:23:32"}
+{"current_steps": 212, "total_steps": 750, "loss": 0.8485, "lr": 9.017553353643479e-06, "epoch": 0.848, "percentage": 28.27, "elapsed_time": "3:17:58", "remaining_time": "8:22:24"}
+{"current_steps": 213, "total_steps": 750, "loss": 0.8685, "lr": 9.003656854743667e-06, "epoch": 0.852, "percentage": 28.4, "elapsed_time": "3:18:54", "remaining_time": "8:21:28"}
+{"current_steps": 214, "total_steps": 750, "loss": 0.8838, "lr": 8.989673630054044e-06, "epoch": 0.856, "percentage": 28.53, "elapsed_time": "3:19:50", "remaining_time": "8:20:32"}
+{"current_steps": 215, "total_steps": 750, "loss": 0.8941, "lr": 8.97560398247424e-06, "epoch": 0.86, "percentage": 28.67, "elapsed_time": "3:20:48", "remaining_time": "8:19:42"}
+{"current_steps": 216, "total_steps": 750, "loss": 0.8749, "lr": 8.961448216775955e-06, "epoch": 0.864, "percentage": 28.8, "elapsed_time": "3:21:43", "remaining_time": "8:18:43"}
+{"current_steps": 217, "total_steps": 750, "loss": 0.8698, "lr": 8.947206639596346e-06, "epoch": 0.868, "percentage": 28.93, "elapsed_time": "3:22:32", "remaining_time": "8:17:29"}
+{"current_steps": 218, "total_steps": 750, "loss": 0.8785, "lr": 8.932879559431392e-06, "epoch": 0.872, "percentage": 29.07, "elapsed_time": "3:23:27", "remaining_time": "8:16:31"}
+{"current_steps": 219, "total_steps": 750, "loss": 0.8544, "lr": 8.9184672866292e-06, "epoch": 0.876, "percentage": 29.2, "elapsed_time": "3:24:18", "remaining_time": "8:15:22"}
+{"current_steps": 220, "total_steps": 750, "loss": 0.8718, "lr": 8.903970133383297e-06, "epoch": 0.88, "percentage": 29.33, "elapsed_time": "3:25:15", "remaining_time": "8:14:28"}
+{"current_steps": 221, "total_steps": 750, "loss": 0.8845, "lr": 8.889388413725857e-06, "epoch": 0.884, "percentage": 29.47, "elapsed_time": "3:26:13", "remaining_time": "8:13:37"}
+{"current_steps": 222, "total_steps": 750, "loss": 0.8734, "lr": 8.874722443520898e-06, "epoch": 0.888, "percentage": 29.6, "elapsed_time": "3:27:23", "remaining_time": "8:13:14"}
+{"current_steps": 223, "total_steps": 750, "loss": 0.8626, "lr": 8.859972540457451e-06, "epoch": 0.892, "percentage": 29.73, "elapsed_time": "3:28:28", "remaining_time": "8:12:40"}
+{"current_steps": 224, "total_steps": 750, "loss": 0.8909, "lr": 8.845139024042664e-06, "epoch": 0.896, "percentage": 29.87, "elapsed_time": "3:29:19", "remaining_time": "8:11:32"}
+{"current_steps": 225, "total_steps": 750, "loss": 0.8861, "lr": 8.83022221559489e-06, "epoch": 0.9, "percentage": 30.0, "elapsed_time": "3:30:22", "remaining_time": "8:10:52"}
+{"current_steps": 226, "total_steps": 750, "loss": 0.8782, "lr": 8.815222438236726e-06, "epoch": 0.904, "percentage": 30.13, "elapsed_time": "3:31:20", "remaining_time": "8:10:00"}
+{"current_steps": 227, "total_steps": 750, "loss": 0.9471, "lr": 8.800140016888009e-06, "epoch": 0.908, "percentage": 30.27, "elapsed_time": "3:32:22", "remaining_time": "8:09:17"}
+{"current_steps": 228, "total_steps": 750, "loss": 0.8722, "lr": 8.784975278258783e-06, "epoch": 0.912, "percentage": 30.4, "elapsed_time": "3:33:15", "remaining_time": "8:08:14"}
+{"current_steps": 229, "total_steps": 750, "loss": 0.8919, "lr": 8.769728550842217e-06, "epoch": 0.916, "percentage": 30.53, "elapsed_time": "3:34:08", "remaining_time": "8:07:11"}
+{"current_steps": 230, "total_steps": 750, "loss": 0.8262, "lr": 8.754400164907496e-06, "epoch": 0.92, "percentage": 30.67, "elapsed_time": "3:35:05", "remaining_time": "8:06:17"}
+{"current_steps": 231, "total_steps": 750, "loss": 0.8602, "lr": 8.73899045249266e-06, "epoch": 0.924, "percentage": 30.8, "elapsed_time": "3:35:55", "remaining_time": "8:05:08"}
+{"current_steps": 232, "total_steps": 750, "loss": 0.8629, "lr": 8.723499747397415e-06, "epoch": 0.928, "percentage": 30.93, "elapsed_time": "3:36:50", "remaining_time": "8:04:10"}
+{"current_steps": 233, "total_steps": 750, "loss": 0.8843, "lr": 8.707928385175898e-06, "epoch": 0.932, "percentage": 31.07, "elapsed_time": "3:37:45", "remaining_time": "8:03:11"}
+{"current_steps": 234, "total_steps": 750, "loss": 0.8469, "lr": 8.692276703129421e-06, "epoch": 0.936, "percentage": 31.2, "elapsed_time": "3:38:41", "remaining_time": "8:02:13"}
+{"current_steps": 235, "total_steps": 750, "loss": 0.8523, "lr": 8.676545040299145e-06, "epoch": 0.94, "percentage": 31.33, "elapsed_time": "3:39:50", "remaining_time": "8:01:47"}
+{"current_steps": 236, "total_steps": 750, "loss": 0.8734, "lr": 8.660733737458751e-06, "epoch": 0.944, "percentage": 31.47, "elapsed_time": "3:40:35", "remaining_time": "8:00:26"}
+{"current_steps": 237, "total_steps": 750, "loss": 0.872, "lr": 8.644843137107058e-06, "epoch": 0.948, "percentage": 31.6, "elapsed_time": "3:41:27", "remaining_time": "7:59:20"}
+{"current_steps": 238, "total_steps": 750, "loss": 0.8441, "lr": 8.628873583460593e-06, "epoch": 0.952, "percentage": 31.73, "elapsed_time": "3:42:25", "remaining_time": "7:58:28"}
+{"current_steps": 239, "total_steps": 750, "loss": 0.8928, "lr": 8.61282542244614e-06, "epoch": 0.956, "percentage": 31.87, "elapsed_time": "3:43:24", "remaining_time": "7:57:39"}
+{"current_steps": 240, "total_steps": 750, "loss": 0.8329, "lr": 8.596699001693257e-06, "epoch": 0.96, "percentage": 32.0, "elapsed_time": "3:44:18", "remaining_time": "7:56:38"}
+{"current_steps": 241, "total_steps": 750, "loss": 0.892, "lr": 8.580494670526725e-06, "epoch": 0.964, "percentage": 32.13, "elapsed_time": "3:45:18", "remaining_time": "7:55:52"}
+{"current_steps": 242, "total_steps": 750, "loss": 0.9021, "lr": 8.564212779959003e-06, "epoch": 0.968, "percentage": 32.27, "elapsed_time": "3:46:19", "remaining_time": "7:55:06"}
+{"current_steps": 243, "total_steps": 750, "loss": 0.8855, "lr": 8.547853682682605e-06, "epoch": 0.972, "percentage": 32.4, "elapsed_time": "3:47:09", "remaining_time": "7:53:57"}
+{"current_steps": 244, "total_steps": 750, "loss": 0.8609, "lr": 8.531417733062476e-06, "epoch": 0.976, "percentage": 32.53, "elapsed_time": "3:47:59", "remaining_time": "7:52:48"}
+{"current_steps": 245, "total_steps": 750, "loss": 0.8396, "lr": 8.51490528712831e-06, "epoch": 0.98, "percentage": 32.67, "elapsed_time": "3:48:41", "remaining_time": "7:51:22"}
+{"current_steps": 246, "total_steps": 750, "loss": 0.8544, "lr": 8.498316702566828e-06, "epoch": 0.984, "percentage": 32.8, "elapsed_time": "3:49:36", "remaining_time": "7:50:24"}
+{"current_steps": 247, "total_steps": 750, "loss": 0.8283, "lr": 8.481652338714048e-06, "epoch": 0.988, "percentage": 32.93, "elapsed_time": "3:50:25", "remaining_time": "7:49:14"}
+{"current_steps": 248, "total_steps": 750, "loss": 0.8407, "lr": 8.464912556547486e-06, "epoch": 0.992, "percentage": 33.07, "elapsed_time": "3:51:15", "remaining_time": "7:48:05"}
+{"current_steps": 249, "total_steps": 750, "loss": 0.8549, "lr": 8.44809771867835e-06, "epoch": 0.996, "percentage": 33.2, "elapsed_time": "3:52:10", "remaining_time": "7:47:08"}
+{"current_steps": 250, "total_steps": 750, "loss": 0.87, "lr": 8.43120818934367e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "3:53:09", "remaining_time": "7:46:19"}
+{"current_steps": 251, "total_steps": 750, "loss": 0.7984, "lr": 8.414244334398418e-06, "epoch": 1.004, "percentage": 33.47, "elapsed_time": "3:55:01", "remaining_time": "7:47:15"}
+{"current_steps": 252, "total_steps": 750, "loss": 0.8299, "lr": 8.397206521307584e-06, "epoch": 1.008, "percentage": 33.6, "elapsed_time": "3:55:59", "remaining_time": "7:46:21"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6dde0bf551dceceb18476c6302cbe38752cdc90f9bf09df287325021cd7b184
+size 7416