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 sha256:4a4c7825ebf7fcd29cbedc6b8e8890e4375b74303047a10fa771a9cb4969db10
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7b8f24339a2cae6a42cc66932f4d2608322eb3f7fe160c88747ad62eff05fa
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a4240241e26712c6be133e78a192c9c230c99a70e4b012ffd6a11a2588d90a
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e45a0bc943f96a23b50862fd5e709aed123080d3ee79ac082a4a510dbb0fb40
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,250 @@
+{"current_steps": 1, "total_steps": 1230, "loss": 0.8354, "lr": 3.2520325203252037e-07, "epoch": 0.0040547389761784085, "percentage": 0.08, "elapsed_time": "0:00:50", "remaining_time": "17:19:58"}
+{"current_steps": 2, "total_steps": 1230, "loss": 0.8068, "lr": 6.504065040650407e-07, "epoch": 0.008109477952356817, "percentage": 0.16, "elapsed_time": "0:01:32", "remaining_time": "15:44:03"}
+{"current_steps": 3, "total_steps": 1230, "loss": 0.8156, "lr": 9.75609756097561e-07, "epoch": 0.012164216928535226, "percentage": 0.24, "elapsed_time": "0:02:17", "remaining_time": "15:34:35"}
+{"current_steps": 4, "total_steps": 1230, "loss": 0.8123, "lr": 1.3008130081300815e-06, "epoch": 0.016218955904713634, "percentage": 0.33, "elapsed_time": "0:03:02", "remaining_time": "15:33:42"}
+{"current_steps": 5, "total_steps": 1230, "loss": 0.8397, "lr": 1.6260162601626018e-06, "epoch": 0.02027369488089204, "percentage": 0.41, "elapsed_time": "0:03:49", "remaining_time": "15:38:10"}
+{"current_steps": 6, "total_steps": 1230, "loss": 0.7889, "lr": 1.951219512195122e-06, "epoch": 0.024328433857070453, "percentage": 0.49, "elapsed_time": "0:04:32", "remaining_time": "15:26:13"}
+{"current_steps": 7, "total_steps": 1230, "loss": 0.7544, "lr": 2.2764227642276426e-06, "epoch": 0.02838317283324886, "percentage": 0.57, "elapsed_time": "0:05:17", "remaining_time": "15:24:00"}
+{"current_steps": 8, "total_steps": 1230, "loss": 0.768, "lr": 2.601626016260163e-06, "epoch": 0.03243791180942727, "percentage": 0.65, "elapsed_time": "0:06:01", "remaining_time": "15:20:52"}
+{"current_steps": 9, "total_steps": 1230, "loss": 0.7156, "lr": 2.926829268292683e-06, "epoch": 0.03649265078560568, "percentage": 0.73, "elapsed_time": "0:06:48", "remaining_time": "15:22:45"}
+{"current_steps": 10, "total_steps": 1230, "loss": 0.7275, "lr": 3.2520325203252037e-06, "epoch": 0.04054738976178408, "percentage": 0.81, "elapsed_time": "0:07:30", "remaining_time": "15:16:02"}
+{"current_steps": 11, "total_steps": 1230, "loss": 0.7081, "lr": 3.577235772357724e-06, "epoch": 0.044602128737962494, "percentage": 0.89, "elapsed_time": "0:08:12", "remaining_time": "15:08:56"}
+{"current_steps": 12, "total_steps": 1230, "loss": 0.7164, "lr": 3.902439024390244e-06, "epoch": 0.048656867714140906, "percentage": 0.98, "elapsed_time": "0:08:55", "remaining_time": "15:05:42"}
+{"current_steps": 13, "total_steps": 1230, "loss": 0.7398, "lr": 4.227642276422765e-06, "epoch": 0.05271160669031931, "percentage": 1.06, "elapsed_time": "0:09:36", "remaining_time": "15:00:11"}
+{"current_steps": 14, "total_steps": 1230, "loss": 0.7034, "lr": 4.552845528455285e-06, "epoch": 0.05676634566649772, "percentage": 1.14, "elapsed_time": "0:10:23", "remaining_time": "15:01:54"}
+{"current_steps": 15, "total_steps": 1230, "loss": 0.6932, "lr": 4.8780487804878055e-06, "epoch": 0.060821084642676125, "percentage": 1.22, "elapsed_time": "0:11:06", "remaining_time": "14:59:31"}
+{"current_steps": 16, "total_steps": 1230, "loss": 0.6894, "lr": 5.203252032520326e-06, "epoch": 0.06487582361885454, "percentage": 1.3, "elapsed_time": "0:11:53", "remaining_time": "15:01:47"}
+{"current_steps": 17, "total_steps": 1230, "loss": 0.6593, "lr": 5.528455284552846e-06, "epoch": 0.06893056259503294, "percentage": 1.38, "elapsed_time": "0:12:34", "remaining_time": "14:57:06"}
+{"current_steps": 18, "total_steps": 1230, "loss": 0.6369, "lr": 5.853658536585366e-06, "epoch": 0.07298530157121136, "percentage": 1.46, "elapsed_time": "0:13:17", "remaining_time": "14:55:18"}
+{"current_steps": 19, "total_steps": 1230, "loss": 0.6506, "lr": 6.178861788617887e-06, "epoch": 0.07704004054738976, "percentage": 1.54, "elapsed_time": "0:14:01", "remaining_time": "14:54:12"}
+{"current_steps": 20, "total_steps": 1230, "loss": 0.6114, "lr": 6.504065040650407e-06, "epoch": 0.08109477952356817, "percentage": 1.63, "elapsed_time": "0:14:43", "remaining_time": "14:51:12"}
+{"current_steps": 21, "total_steps": 1230, "loss": 0.6308, "lr": 6.829268292682928e-06, "epoch": 0.08514951849974658, "percentage": 1.71, "elapsed_time": "0:15:27", "remaining_time": "14:50:23"}
+{"current_steps": 22, "total_steps": 1230, "loss": 0.6209, "lr": 7.154471544715448e-06, "epoch": 0.08920425747592499, "percentage": 1.79, "elapsed_time": "0:16:11", "remaining_time": "14:49:02"}
+{"current_steps": 23, "total_steps": 1230, "loss": 0.5988, "lr": 7.4796747967479676e-06, "epoch": 0.0932589964521034, "percentage": 1.87, "elapsed_time": "0:16:56", "remaining_time": "14:49:10"}
+{"current_steps": 24, "total_steps": 1230, "loss": 0.5892, "lr": 7.804878048780489e-06, "epoch": 0.09731373542828181, "percentage": 1.95, "elapsed_time": "0:17:42", "remaining_time": "14:49:49"}
+{"current_steps": 25, "total_steps": 1230, "loss": 0.5882, "lr": 8.130081300813009e-06, "epoch": 0.10136847440446022, "percentage": 2.03, "elapsed_time": "0:18:27", "remaining_time": "14:49:19"}
+{"current_steps": 26, "total_steps": 1230, "loss": 0.571, "lr": 8.45528455284553e-06, "epoch": 0.10542321338063862, "percentage": 2.11, "elapsed_time": "0:19:13", "remaining_time": "14:49:57"}
+{"current_steps": 27, "total_steps": 1230, "loss": 0.5823, "lr": 8.78048780487805e-06, "epoch": 0.10947795235681702, "percentage": 2.2, "elapsed_time": "0:19:57", "remaining_time": "14:49:04"}
+{"current_steps": 28, "total_steps": 1230, "loss": 0.5703, "lr": 9.10569105691057e-06, "epoch": 0.11353269133299544, "percentage": 2.28, "elapsed_time": "0:20:40", "remaining_time": "14:47:30"}
+{"current_steps": 29, "total_steps": 1230, "loss": 0.5715, "lr": 9.43089430894309e-06, "epoch": 0.11758743030917385, "percentage": 2.36, "elapsed_time": "0:21:25", "remaining_time": "14:47:09"}
+{"current_steps": 30, "total_steps": 1230, "loss": 0.5707, "lr": 9.756097560975611e-06, "epoch": 0.12164216928535225, "percentage": 2.44, "elapsed_time": "0:22:09", "remaining_time": "14:46:15"}
+{"current_steps": 31, "total_steps": 1230, "loss": 0.5488, "lr": 1.008130081300813e-05, "epoch": 0.12569690826153065, "percentage": 2.52, "elapsed_time": "0:22:50", "remaining_time": "14:43:44"}
+{"current_steps": 32, "total_steps": 1230, "loss": 0.5426, "lr": 1.0406504065040652e-05, "epoch": 0.12975164723770907, "percentage": 2.6, "elapsed_time": "0:23:34", "remaining_time": "14:42:17"}
+{"current_steps": 33, "total_steps": 1230, "loss": 0.5429, "lr": 1.0731707317073172e-05, "epoch": 0.1338063862138875, "percentage": 2.68, "elapsed_time": "0:24:17", "remaining_time": "14:40:55"}
+{"current_steps": 34, "total_steps": 1230, "loss": 0.5559, "lr": 1.1056910569105692e-05, "epoch": 0.13786112519006588, "percentage": 2.76, "elapsed_time": "0:25:02", "remaining_time": "14:40:52"}
+{"current_steps": 35, "total_steps": 1230, "loss": 0.5277, "lr": 1.1382113821138213e-05, "epoch": 0.1419158641662443, "percentage": 2.85, "elapsed_time": "0:25:45", "remaining_time": "14:39:37"}
+{"current_steps": 36, "total_steps": 1230, "loss": 0.5343, "lr": 1.1707317073170731e-05, "epoch": 0.14597060314242272, "percentage": 2.93, "elapsed_time": "0:26:26", "remaining_time": "14:37:11"}
+{"current_steps": 37, "total_steps": 1230, "loss": 0.5416, "lr": 1.2032520325203254e-05, "epoch": 0.1500253421186011, "percentage": 3.01, "elapsed_time": "0:27:11", "remaining_time": "14:36:30"}
+{"current_steps": 38, "total_steps": 1230, "loss": 0.5212, "lr": 1.2357723577235774e-05, "epoch": 0.15408008109477953, "percentage": 3.09, "elapsed_time": "0:27:53", "remaining_time": "14:34:56"}
+{"current_steps": 39, "total_steps": 1230, "loss": 0.5295, "lr": 1.2682926829268294e-05, "epoch": 0.15813482007095794, "percentage": 3.17, "elapsed_time": "0:28:39", "remaining_time": "14:34:56"}
+{"current_steps": 40, "total_steps": 1230, "loss": 0.5196, "lr": 1.3008130081300815e-05, "epoch": 0.16218955904713633, "percentage": 3.25, "elapsed_time": "0:29:22", "remaining_time": "14:33:46"}
+{"current_steps": 41, "total_steps": 1230, "loss": 0.5157, "lr": 1.3333333333333333e-05, "epoch": 0.16624429802331475, "percentage": 3.33, "elapsed_time": "0:30:07", "remaining_time": "14:33:28"}
+{"current_steps": 42, "total_steps": 1230, "loss": 0.5284, "lr": 1.3658536585365855e-05, "epoch": 0.17029903699949317, "percentage": 3.41, "elapsed_time": "0:30:49", "remaining_time": "14:31:58"}
+{"current_steps": 43, "total_steps": 1230, "loss": 0.5251, "lr": 1.3983739837398376e-05, "epoch": 0.17435377597567156, "percentage": 3.5, "elapsed_time": "0:31:33", "remaining_time": "14:31:22"}
+{"current_steps": 44, "total_steps": 1230, "loss": 0.5221, "lr": 1.4308943089430896e-05, "epoch": 0.17840851495184998, "percentage": 3.58, "elapsed_time": "0:32:19", "remaining_time": "14:31:05"}
+{"current_steps": 45, "total_steps": 1230, "loss": 0.5104, "lr": 1.4634146341463415e-05, "epoch": 0.1824632539280284, "percentage": 3.66, "elapsed_time": "0:33:01", "remaining_time": "14:29:30"}
+{"current_steps": 46, "total_steps": 1230, "loss": 0.5057, "lr": 1.4959349593495935e-05, "epoch": 0.1865179929042068, "percentage": 3.74, "elapsed_time": "0:33:43", "remaining_time": "14:27:57"}
+{"current_steps": 47, "total_steps": 1230, "loss": 0.5119, "lr": 1.528455284552846e-05, "epoch": 0.1905727318803852, "percentage": 3.82, "elapsed_time": "0:34:23", "remaining_time": "14:25:37"}
+{"current_steps": 48, "total_steps": 1230, "loss": 0.5029, "lr": 1.5609756097560978e-05, "epoch": 0.19462747085656362, "percentage": 3.9, "elapsed_time": "0:35:07", "remaining_time": "14:25:02"}
+{"current_steps": 49, "total_steps": 1230, "loss": 0.5018, "lr": 1.5934959349593496e-05, "epoch": 0.198682209832742, "percentage": 3.98, "elapsed_time": "0:35:53", "remaining_time": "14:25:08"}
+{"current_steps": 50, "total_steps": 1230, "loss": 0.5013, "lr": 1.6260162601626018e-05, "epoch": 0.20273694880892043, "percentage": 4.07, "elapsed_time": "0:36:38", "remaining_time": "14:24:45"}
+{"current_steps": 51, "total_steps": 1230, "loss": 0.5137, "lr": 1.6585365853658537e-05, "epoch": 0.20679168778509882, "percentage": 4.15, "elapsed_time": "0:37:22", "remaining_time": "14:24:02"}
+{"current_steps": 52, "total_steps": 1230, "loss": 0.4997, "lr": 1.691056910569106e-05, "epoch": 0.21084642676127724, "percentage": 4.23, "elapsed_time": "0:38:09", "remaining_time": "14:24:23"}
+{"current_steps": 53, "total_steps": 1230, "loss": 0.4988, "lr": 1.7235772357723578e-05, "epoch": 0.21490116573745566, "percentage": 4.31, "elapsed_time": "0:38:53", "remaining_time": "14:23:46"}
+{"current_steps": 54, "total_steps": 1230, "loss": 0.498, "lr": 1.75609756097561e-05, "epoch": 0.21895590471363405, "percentage": 4.39, "elapsed_time": "0:39:38", "remaining_time": "14:23:15"}
+{"current_steps": 55, "total_steps": 1230, "loss": 0.5001, "lr": 1.788617886178862e-05, "epoch": 0.22301064368981247, "percentage": 4.47, "elapsed_time": "0:40:20", "remaining_time": "14:22:00"}
+{"current_steps": 56, "total_steps": 1230, "loss": 0.4934, "lr": 1.821138211382114e-05, "epoch": 0.22706538266599088, "percentage": 4.55, "elapsed_time": "0:41:02", "remaining_time": "14:20:29"}
+{"current_steps": 57, "total_steps": 1230, "loss": 0.4968, "lr": 1.8536585365853663e-05, "epoch": 0.23112012164216927, "percentage": 4.63, "elapsed_time": "0:41:48", "remaining_time": "14:20:12"}
+{"current_steps": 58, "total_steps": 1230, "loss": 0.4993, "lr": 1.886178861788618e-05, "epoch": 0.2351748606183477, "percentage": 4.72, "elapsed_time": "0:42:30", "remaining_time": "14:19:02"}
+{"current_steps": 59, "total_steps": 1230, "loss": 0.4915, "lr": 1.91869918699187e-05, "epoch": 0.2392295995945261, "percentage": 4.8, "elapsed_time": "0:43:12", "remaining_time": "14:17:34"}
+{"current_steps": 60, "total_steps": 1230, "loss": 0.4911, "lr": 1.9512195121951222e-05, "epoch": 0.2432843385707045, "percentage": 4.88, "elapsed_time": "0:43:55", "remaining_time": "14:16:23"}
+{"current_steps": 61, "total_steps": 1230, "loss": 0.4976, "lr": 1.983739837398374e-05, "epoch": 0.24733907754688292, "percentage": 4.96, "elapsed_time": "0:44:39", "remaining_time": "14:15:46"}
+{"current_steps": 62, "total_steps": 1230, "loss": 0.5175, "lr": 2.016260162601626e-05, "epoch": 0.2513938165230613, "percentage": 5.04, "elapsed_time": "0:45:22", "remaining_time": "14:14:51"}
+{"current_steps": 63, "total_steps": 1230, "loss": 0.5037, "lr": 2.048780487804878e-05, "epoch": 0.2554485554992397, "percentage": 5.12, "elapsed_time": "0:46:06", "remaining_time": "14:14:10"}
+{"current_steps": 64, "total_steps": 1230, "loss": 0.4766, "lr": 2.0813008130081303e-05, "epoch": 0.25950329447541814, "percentage": 5.2, "elapsed_time": "0:46:50", "remaining_time": "14:13:30"}
+{"current_steps": 65, "total_steps": 1230, "loss": 0.4843, "lr": 2.1138211382113822e-05, "epoch": 0.26355803345159656, "percentage": 5.28, "elapsed_time": "0:47:36", "remaining_time": "14:13:10"}
+{"current_steps": 66, "total_steps": 1230, "loss": 0.4788, "lr": 2.1463414634146344e-05, "epoch": 0.267612772427775, "percentage": 5.37, "elapsed_time": "0:48:23", "remaining_time": "14:13:24"}
+{"current_steps": 67, "total_steps": 1230, "loss": 0.5097, "lr": 2.1788617886178863e-05, "epoch": 0.27166751140395334, "percentage": 5.45, "elapsed_time": "0:49:08", "remaining_time": "14:12:52"}
+{"current_steps": 68, "total_steps": 1230, "loss": 0.4981, "lr": 2.2113821138211385e-05, "epoch": 0.27572225038013176, "percentage": 5.53, "elapsed_time": "0:49:54", "remaining_time": "14:12:43"}
+{"current_steps": 69, "total_steps": 1230, "loss": 0.4995, "lr": 2.2439024390243907e-05, "epoch": 0.2797769893563102, "percentage": 5.61, "elapsed_time": "0:50:37", "remaining_time": "14:11:41"}
+{"current_steps": 70, "total_steps": 1230, "loss": 0.4929, "lr": 2.2764227642276426e-05, "epoch": 0.2838317283324886, "percentage": 5.69, "elapsed_time": "0:51:18", "remaining_time": "14:10:09"}
+{"current_steps": 71, "total_steps": 1230, "loss": 0.4925, "lr": 2.3089430894308948e-05, "epoch": 0.287886467308667, "percentage": 5.77, "elapsed_time": "0:52:02", "remaining_time": "14:09:24"}
+{"current_steps": 72, "total_steps": 1230, "loss": 0.4754, "lr": 2.3414634146341463e-05, "epoch": 0.29194120628484543, "percentage": 5.85, "elapsed_time": "0:52:46", "remaining_time": "14:08:42"}
+{"current_steps": 73, "total_steps": 1230, "loss": 0.4977, "lr": 2.3739837398373985e-05, "epoch": 0.2959959452610238, "percentage": 5.93, "elapsed_time": "0:53:30", "remaining_time": "14:08:02"}
+{"current_steps": 74, "total_steps": 1230, "loss": 0.4928, "lr": 2.4065040650406507e-05, "epoch": 0.3000506842372022, "percentage": 6.02, "elapsed_time": "0:54:14", "remaining_time": "14:07:23"}
+{"current_steps": 75, "total_steps": 1230, "loss": 0.4852, "lr": 2.4390243902439026e-05, "epoch": 0.30410542321338063, "percentage": 6.1, "elapsed_time": "0:54:58", "remaining_time": "14:06:41"}
+{"current_steps": 76, "total_steps": 1230, "loss": 0.4614, "lr": 2.4715447154471548e-05, "epoch": 0.30816016218955905, "percentage": 6.18, "elapsed_time": "0:55:44", "remaining_time": "14:06:19"}
+{"current_steps": 77, "total_steps": 1230, "loss": 0.4644, "lr": 2.5040650406504066e-05, "epoch": 0.31221490116573747, "percentage": 6.26, "elapsed_time": "0:56:27", "remaining_time": "14:05:31"}
+{"current_steps": 78, "total_steps": 1230, "loss": 0.4872, "lr": 2.536585365853659e-05, "epoch": 0.3162696401419159, "percentage": 6.34, "elapsed_time": "0:57:13", "remaining_time": "14:05:04"}
+{"current_steps": 79, "total_steps": 1230, "loss": 0.4738, "lr": 2.569105691056911e-05, "epoch": 0.32032437911809425, "percentage": 6.42, "elapsed_time": "0:57:57", "remaining_time": "14:04:20"}
+{"current_steps": 80, "total_steps": 1230, "loss": 0.4962, "lr": 2.601626016260163e-05, "epoch": 0.32437911809427267, "percentage": 6.5, "elapsed_time": "0:58:39", "remaining_time": "14:03:15"}
+{"current_steps": 81, "total_steps": 1230, "loss": 0.4769, "lr": 2.634146341463415e-05, "epoch": 0.3284338570704511, "percentage": 6.59, "elapsed_time": "0:59:23", "remaining_time": "14:02:26"}
+{"current_steps": 82, "total_steps": 1230, "loss": 0.4925, "lr": 2.6666666666666667e-05, "epoch": 0.3324885960466295, "percentage": 6.67, "elapsed_time": "1:00:05", "remaining_time": "14:01:19"}
+{"current_steps": 83, "total_steps": 1230, "loss": 0.4885, "lr": 2.699186991869919e-05, "epoch": 0.3365433350228079, "percentage": 6.75, "elapsed_time": "1:00:49", "remaining_time": "14:00:36"}
+{"current_steps": 84, "total_steps": 1230, "loss": 0.4821, "lr": 2.731707317073171e-05, "epoch": 0.34059807399898634, "percentage": 6.83, "elapsed_time": "1:01:32", "remaining_time": "13:59:43"}
+{"current_steps": 85, "total_steps": 1230, "loss": 0.4821, "lr": 2.764227642276423e-05, "epoch": 0.3446528129751647, "percentage": 6.91, "elapsed_time": "1:02:16", "remaining_time": "13:58:53"}
+{"current_steps": 86, "total_steps": 1230, "loss": 0.4821, "lr": 2.796747967479675e-05, "epoch": 0.3487075519513431, "percentage": 6.99, "elapsed_time": "1:03:02", "remaining_time": "13:58:39"}
+{"current_steps": 87, "total_steps": 1230, "loss": 0.4708, "lr": 2.829268292682927e-05, "epoch": 0.35276229092752154, "percentage": 7.07, "elapsed_time": "1:03:47", "remaining_time": "13:58:02"}
+{"current_steps": 88, "total_steps": 1230, "loss": 0.4711, "lr": 2.8617886178861792e-05, "epoch": 0.35681702990369996, "percentage": 7.15, "elapsed_time": "1:04:27", "remaining_time": "13:56:32"}
+{"current_steps": 89, "total_steps": 1230, "loss": 0.4715, "lr": 2.8943089430894314e-05, "epoch": 0.3608717688798784, "percentage": 7.24, "elapsed_time": "1:05:14", "remaining_time": "13:56:22"}
+{"current_steps": 90, "total_steps": 1230, "loss": 0.4678, "lr": 2.926829268292683e-05, "epoch": 0.3649265078560568, "percentage": 7.32, "elapsed_time": "1:05:57", "remaining_time": "13:55:31"}
+{"current_steps": 91, "total_steps": 1230, "loss": 0.4781, "lr": 2.959349593495935e-05, "epoch": 0.36898124683223515, "percentage": 7.4, "elapsed_time": "1:06:41", "remaining_time": "13:54:48"}
+{"current_steps": 92, "total_steps": 1230, "loss": 0.4766, "lr": 2.991869918699187e-05, "epoch": 0.3730359858084136, "percentage": 7.48, "elapsed_time": "1:07:22", "remaining_time": "13:53:28"}
+{"current_steps": 93, "total_steps": 1230, "loss": 0.4777, "lr": 3.0243902439024392e-05, "epoch": 0.377090724784592, "percentage": 7.56, "elapsed_time": "1:08:04", "remaining_time": "13:52:18"}
+{"current_steps": 94, "total_steps": 1230, "loss": 0.492, "lr": 3.056910569105692e-05, "epoch": 0.3811454637607704, "percentage": 7.64, "elapsed_time": "1:08:48", "remaining_time": "13:51:39"}
+{"current_steps": 95, "total_steps": 1230, "loss": 0.4744, "lr": 3.089430894308943e-05, "epoch": 0.3852002027369488, "percentage": 7.72, "elapsed_time": "1:09:32", "remaining_time": "13:50:48"}
+{"current_steps": 96, "total_steps": 1230, "loss": 0.4621, "lr": 3.1219512195121955e-05, "epoch": 0.38925494171312724, "percentage": 7.8, "elapsed_time": "1:10:17", "remaining_time": "13:50:15"}
+{"current_steps": 97, "total_steps": 1230, "loss": 0.4786, "lr": 3.154471544715447e-05, "epoch": 0.3933096806893056, "percentage": 7.89, "elapsed_time": "1:11:01", "remaining_time": "13:49:34"}
+{"current_steps": 98, "total_steps": 1230, "loss": 0.474, "lr": 3.186991869918699e-05, "epoch": 0.397364419665484, "percentage": 7.97, "elapsed_time": "1:11:43", "remaining_time": "13:48:29"}
+{"current_steps": 99, "total_steps": 1230, "loss": 0.4709, "lr": 3.2195121951219514e-05, "epoch": 0.40141915864166244, "percentage": 8.05, "elapsed_time": "1:12:29", "remaining_time": "13:48:05"}
+{"current_steps": 100, "total_steps": 1230, "loss": 0.4605, "lr": 3.2520325203252037e-05, "epoch": 0.40547389761784086, "percentage": 8.13, "elapsed_time": "1:13:11", "remaining_time": "13:47:04"}
+{"current_steps": 101, "total_steps": 1230, "loss": 0.4687, "lr": 3.284552845528456e-05, "epoch": 0.4095286365940193, "percentage": 8.21, "elapsed_time": "1:13:57", "remaining_time": "13:46:48"}
+{"current_steps": 102, "total_steps": 1230, "loss": 0.4676, "lr": 3.3170731707317074e-05, "epoch": 0.41358337557019764, "percentage": 8.29, "elapsed_time": "1:14:41", "remaining_time": "13:45:56"}
+{"current_steps": 103, "total_steps": 1230, "loss": 0.4764, "lr": 3.3495934959349596e-05, "epoch": 0.41763811454637606, "percentage": 8.37, "elapsed_time": "1:15:23", "remaining_time": "13:44:54"}
+{"current_steps": 104, "total_steps": 1230, "loss": 0.466, "lr": 3.382113821138212e-05, "epoch": 0.4216928535225545, "percentage": 8.46, "elapsed_time": "1:16:06", "remaining_time": "13:43:59"}
+{"current_steps": 105, "total_steps": 1230, "loss": 0.4563, "lr": 3.414634146341463e-05, "epoch": 0.4257475924987329, "percentage": 8.54, "elapsed_time": "1:16:48", "remaining_time": "13:43:00"}
+{"current_steps": 106, "total_steps": 1230, "loss": 0.4625, "lr": 3.4471544715447155e-05, "epoch": 0.4298023314749113, "percentage": 8.62, "elapsed_time": "1:17:34", "remaining_time": "13:42:30"}
+{"current_steps": 107, "total_steps": 1230, "loss": 0.48, "lr": 3.479674796747968e-05, "epoch": 0.43385707045108973, "percentage": 8.7, "elapsed_time": "1:18:19", "remaining_time": "13:42:04"}
+{"current_steps": 108, "total_steps": 1230, "loss": 0.4754, "lr": 3.51219512195122e-05, "epoch": 0.4379118094272681, "percentage": 8.78, "elapsed_time": "1:19:02", "remaining_time": "13:41:11"}
+{"current_steps": 109, "total_steps": 1230, "loss": 0.4601, "lr": 3.544715447154472e-05, "epoch": 0.4419665484034465, "percentage": 8.86, "elapsed_time": "1:19:48", "remaining_time": "13:40:43"}
+{"current_steps": 110, "total_steps": 1230, "loss": 0.465, "lr": 3.577235772357724e-05, "epoch": 0.44602128737962493, "percentage": 8.94, "elapsed_time": "1:20:30", "remaining_time": "13:39:46"}
+{"current_steps": 111, "total_steps": 1230, "loss": 0.4529, "lr": 3.609756097560976e-05, "epoch": 0.45007602635580335, "percentage": 9.02, "elapsed_time": "1:21:19", "remaining_time": "13:39:47"}
+{"current_steps": 112, "total_steps": 1230, "loss": 0.4673, "lr": 3.642276422764228e-05, "epoch": 0.45413076533198177, "percentage": 9.11, "elapsed_time": "1:22:03", "remaining_time": "13:39:02"}
+{"current_steps": 113, "total_steps": 1230, "loss": 0.4526, "lr": 3.67479674796748e-05, "epoch": 0.4581855043081602, "percentage": 9.19, "elapsed_time": "1:22:48", "remaining_time": "13:38:28"}
+{"current_steps": 114, "total_steps": 1230, "loss": 0.4663, "lr": 3.7073170731707325e-05, "epoch": 0.46224024328433855, "percentage": 9.27, "elapsed_time": "1:23:30", "remaining_time": "13:37:34"}
+{"current_steps": 115, "total_steps": 1230, "loss": 0.4544, "lr": 3.739837398373984e-05, "epoch": 0.46629498226051697, "percentage": 9.35, "elapsed_time": "1:24:14", "remaining_time": "13:36:43"}
+{"current_steps": 116, "total_steps": 1230, "loss": 0.4541, "lr": 3.772357723577236e-05, "epoch": 0.4703497212366954, "percentage": 9.43, "elapsed_time": "1:24:57", "remaining_time": "13:35:49"}
+{"current_steps": 117, "total_steps": 1230, "loss": 0.4563, "lr": 3.804878048780488e-05, "epoch": 0.4744044602128738, "percentage": 9.51, "elapsed_time": "1:25:35", "remaining_time": "13:34:17"}
+{"current_steps": 118, "total_steps": 1230, "loss": 0.4681, "lr": 3.83739837398374e-05, "epoch": 0.4784591991890522, "percentage": 9.59, "elapsed_time": "1:26:19", "remaining_time": "13:33:26"}
+{"current_steps": 119, "total_steps": 1230, "loss": 0.4696, "lr": 3.869918699186992e-05, "epoch": 0.48251393816523064, "percentage": 9.67, "elapsed_time": "1:27:01", "remaining_time": "13:32:25"}
+{"current_steps": 120, "total_steps": 1230, "loss": 0.4736, "lr": 3.9024390243902444e-05, "epoch": 0.486568677141409, "percentage": 9.76, "elapsed_time": "1:27:47", "remaining_time": "13:32:02"}
+{"current_steps": 121, "total_steps": 1230, "loss": 0.4679, "lr": 3.9349593495934966e-05, "epoch": 0.4906234161175874, "percentage": 9.84, "elapsed_time": "1:28:29", "remaining_time": "13:31:07"}
+{"current_steps": 122, "total_steps": 1230, "loss": 0.4499, "lr": 3.967479674796748e-05, "epoch": 0.49467815509376584, "percentage": 9.92, "elapsed_time": "1:29:15", "remaining_time": "13:30:35"}
+{"current_steps": 123, "total_steps": 1230, "loss": 0.4585, "lr": 4e-05, "epoch": 0.49873289406994425, "percentage": 10.0, "elapsed_time": "1:29:59", "remaining_time": "13:29:59"}
+{"current_steps": 124, "total_steps": 1230, "loss": 0.4588, "lr": 3.999991946137476e-05, "epoch": 0.5027876330461226, "percentage": 10.08, "elapsed_time": "1:30:43", "remaining_time": "13:29:08"}
+{"current_steps": 125, "total_steps": 1230, "loss": 0.461, "lr": 3.999967784614766e-05, "epoch": 0.5068423720223011, "percentage": 10.16, "elapsed_time": "1:31:28", "remaining_time": "13:28:36"}
+{"current_steps": 126, "total_steps": 1230, "loss": 0.4652, "lr": 3.9999275156264656e-05, "epoch": 0.5108971109984795, "percentage": 10.24, "elapsed_time": "1:32:12", "remaining_time": "13:27:56"}
+{"current_steps": 127, "total_steps": 1230, "loss": 0.4637, "lr": 3.999871139496895e-05, "epoch": 0.5149518499746579, "percentage": 10.33, "elapsed_time": "1:32:57", "remaining_time": "13:27:20"}
+{"current_steps": 128, "total_steps": 1230, "loss": 0.4753, "lr": 3.9997986566800995e-05, "epoch": 0.5190065889508363, "percentage": 10.41, "elapsed_time": "1:33:41", "remaining_time": "13:26:34"}
+{"current_steps": 129, "total_steps": 1230, "loss": 0.4638, "lr": 3.999710067759846e-05, "epoch": 0.5230613279270147, "percentage": 10.49, "elapsed_time": "1:34:25", "remaining_time": "13:25:50"}
+{"current_steps": 130, "total_steps": 1230, "loss": 0.463, "lr": 3.999605373449617e-05, "epoch": 0.5271160669031931, "percentage": 10.57, "elapsed_time": "1:35:07", "remaining_time": "13:24:51"}
+{"current_steps": 131, "total_steps": 1230, "loss": 0.4814, "lr": 3.9994845745926075e-05, "epoch": 0.5311708058793715, "percentage": 10.65, "elapsed_time": "1:35:51", "remaining_time": "13:24:12"}
+{"current_steps": 132, "total_steps": 1230, "loss": 0.4464, "lr": 3.999347672161713e-05, "epoch": 0.53522554485555, "percentage": 10.73, "elapsed_time": "1:36:35", "remaining_time": "13:23:29"}
+{"current_steps": 133, "total_steps": 1230, "loss": 0.452, "lr": 3.999194667259528e-05, "epoch": 0.5392802838317283, "percentage": 10.81, "elapsed_time": "1:37:19", "remaining_time": "13:22:46"}
+{"current_steps": 134, "total_steps": 1230, "loss": 0.4632, "lr": 3.999025561118334e-05, "epoch": 0.5433350228079067, "percentage": 10.89, "elapsed_time": "1:38:03", "remaining_time": "13:22:01"}
+{"current_steps": 135, "total_steps": 1230, "loss": 0.4508, "lr": 3.998840355100086e-05, "epoch": 0.5473897617840852, "percentage": 10.98, "elapsed_time": "1:38:47", "remaining_time": "13:21:21"}
+{"current_steps": 136, "total_steps": 1230, "loss": 0.4575, "lr": 3.998639050696409e-05, "epoch": 0.5514445007602635, "percentage": 11.06, "elapsed_time": "1:39:33", "remaining_time": "13:20:52"}
+{"current_steps": 137, "total_steps": 1230, "loss": 0.4709, "lr": 3.998421649528582e-05, "epoch": 0.555499239736442, "percentage": 11.14, "elapsed_time": "1:40:16", "remaining_time": "13:20:01"}
+{"current_steps": 138, "total_steps": 1230, "loss": 0.4552, "lr": 3.9981881533475234e-05, "epoch": 0.5595539787126204, "percentage": 11.22, "elapsed_time": "1:40:59", "remaining_time": "13:19:09"}
+{"current_steps": 139, "total_steps": 1230, "loss": 0.4527, "lr": 3.997938564033779e-05, "epoch": 0.5636087176887988, "percentage": 11.3, "elapsed_time": "1:41:44", "remaining_time": "13:18:35"}
+{"current_steps": 140, "total_steps": 1230, "loss": 0.4563, "lr": 3.9976728835975064e-05, "epoch": 0.5676634566649772, "percentage": 11.38, "elapsed_time": "1:42:28", "remaining_time": "13:17:47"}
+{"current_steps": 141, "total_steps": 1230, "loss": 0.4601, "lr": 3.9973911141784605e-05, "epoch": 0.5717181956411556, "percentage": 11.46, "elapsed_time": "1:43:12", "remaining_time": "13:17:06"}
+{"current_steps": 142, "total_steps": 1230, "loss": 0.4594, "lr": 3.997093258045973e-05, "epoch": 0.575772934617334, "percentage": 11.54, "elapsed_time": "1:43:57", "remaining_time": "13:16:32"}
+{"current_steps": 143, "total_steps": 1230, "loss": 0.4611, "lr": 3.996779317598936e-05, "epoch": 0.5798276735935124, "percentage": 11.63, "elapsed_time": "1:44:40", "remaining_time": "13:15:40"}
+{"current_steps": 144, "total_steps": 1230, "loss": 0.4607, "lr": 3.996449295365782e-05, "epoch": 0.5838824125696909, "percentage": 11.71, "elapsed_time": "1:45:25", "remaining_time": "13:15:02"}
+{"current_steps": 145, "total_steps": 1230, "loss": 0.4424, "lr": 3.996103194004467e-05, "epoch": 0.5879371515458692, "percentage": 11.79, "elapsed_time": "1:46:08", "remaining_time": "13:14:11"}
+{"current_steps": 146, "total_steps": 1230, "loss": 0.4563, "lr": 3.995741016302441e-05, "epoch": 0.5919918905220476, "percentage": 11.87, "elapsed_time": "1:46:51", "remaining_time": "13:13:24"}
+{"current_steps": 147, "total_steps": 1230, "loss": 0.4578, "lr": 3.9953627651766364e-05, "epoch": 0.5960466294982261, "percentage": 11.95, "elapsed_time": "1:47:34", "remaining_time": "13:12:35"}
+{"current_steps": 148, "total_steps": 1230, "loss": 0.4454, "lr": 3.9949684436734325e-05, "epoch": 0.6001013684744044, "percentage": 12.03, "elapsed_time": "1:48:17", "remaining_time": "13:11:38"}
+{"current_steps": 149, "total_steps": 1230, "loss": 0.4634, "lr": 3.994558054968643e-05, "epoch": 0.6041561074505829, "percentage": 12.11, "elapsed_time": "1:48:57", "remaining_time": "13:10:32"}
+{"current_steps": 150, "total_steps": 1230, "loss": 0.4559, "lr": 3.994131602367481e-05, "epoch": 0.6082108464267613, "percentage": 12.2, "elapsed_time": "1:49:42", "remaining_time": "13:09:57"}
+{"current_steps": 151, "total_steps": 1230, "loss": 0.4496, "lr": 3.9936890893045376e-05, "epoch": 0.6122655854029397, "percentage": 12.28, "elapsed_time": "1:50:25", "remaining_time": "13:09:01"}
+{"current_steps": 152, "total_steps": 1230, "loss": 0.4481, "lr": 3.993230519343752e-05, "epoch": 0.6163203243791181, "percentage": 12.36, "elapsed_time": "1:51:08", "remaining_time": "13:08:10"}
+{"current_steps": 153, "total_steps": 1230, "loss": 0.4557, "lr": 3.992755896178383e-05, "epoch": 0.6203750633552965, "percentage": 12.44, "elapsed_time": "1:51:51", "remaining_time": "13:07:23"}
+{"current_steps": 154, "total_steps": 1230, "loss": 0.4476, "lr": 3.992265223630981e-05, "epoch": 0.6244298023314749, "percentage": 12.52, "elapsed_time": "1:52:35", "remaining_time": "13:06:43"}
+{"current_steps": 155, "total_steps": 1230, "loss": 0.4496, "lr": 3.991758505653355e-05, "epoch": 0.6284845413076533, "percentage": 12.6, "elapsed_time": "1:53:19", "remaining_time": "13:05:56"}
+{"current_steps": 156, "total_steps": 1230, "loss": 0.4526, "lr": 3.991235746326543e-05, "epoch": 0.6325392802838318, "percentage": 12.68, "elapsed_time": "1:54:03", "remaining_time": "13:05:16"}
+{"current_steps": 157, "total_steps": 1230, "loss": 0.4395, "lr": 3.9906969498607745e-05, "epoch": 0.6365940192600101, "percentage": 12.76, "elapsed_time": "1:54:47", "remaining_time": "13:04:33"}
+{"current_steps": 158, "total_steps": 1230, "loss": 0.4464, "lr": 3.990142120595444e-05, "epoch": 0.6406487582361885, "percentage": 12.85, "elapsed_time": "1:55:30", "remaining_time": "13:03:41"}
+{"current_steps": 159, "total_steps": 1230, "loss": 0.4487, "lr": 3.98957126299907e-05, "epoch": 0.644703497212367, "percentage": 12.93, "elapsed_time": "1:56:14", "remaining_time": "13:03:01"}
+{"current_steps": 160, "total_steps": 1230, "loss": 0.4603, "lr": 3.9889843816692596e-05, "epoch": 0.6487582361885453, "percentage": 13.01, "elapsed_time": "1:57:01", "remaining_time": "13:02:33"}
+{"current_steps": 161, "total_steps": 1230, "loss": 0.446, "lr": 3.9883814813326766e-05, "epoch": 0.6528129751647238, "percentage": 13.09, "elapsed_time": "1:57:42", "remaining_time": "13:01:35"}
+{"current_steps": 162, "total_steps": 1230, "loss": 0.4471, "lr": 3.9877625668449956e-05, "epoch": 0.6568677141409022, "percentage": 13.17, "elapsed_time": "1:58:28", "remaining_time": "13:01:03"}
+{"current_steps": 163, "total_steps": 1230, "loss": 0.4542, "lr": 3.98712764319087e-05, "epoch": 0.6609224531170805, "percentage": 13.25, "elapsed_time": "1:59:11", "remaining_time": "13:00:16"}
+{"current_steps": 164, "total_steps": 1230, "loss": 0.4585, "lr": 3.9864767154838864e-05, "epoch": 0.664977192093259, "percentage": 13.33, "elapsed_time": "1:59:56", "remaining_time": "12:59:36"}
+{"current_steps": 165, "total_steps": 1230, "loss": 0.4363, "lr": 3.9858097889665277e-05, "epoch": 0.6690319310694374, "percentage": 13.41, "elapsed_time": "2:00:42", "remaining_time": "12:59:06"}
+{"current_steps": 166, "total_steps": 1230, "loss": 0.4455, "lr": 3.985126869010129e-05, "epoch": 0.6730866700456158, "percentage": 13.5, "elapsed_time": "2:01:26", "remaining_time": "12:58:23"}
+{"current_steps": 167, "total_steps": 1230, "loss": 0.44, "lr": 3.984427961114833e-05, "epoch": 0.6771414090217942, "percentage": 13.58, "elapsed_time": "2:02:09", "remaining_time": "12:57:35"}
+{"current_steps": 168, "total_steps": 1230, "loss": 0.4466, "lr": 3.9837130709095475e-05, "epoch": 0.6811961479979727, "percentage": 13.66, "elapsed_time": "2:02:54", "remaining_time": "12:56:59"}
+{"current_steps": 169, "total_steps": 1230, "loss": 0.4391, "lr": 3.982982204151901e-05, "epoch": 0.685250886974151, "percentage": 13.74, "elapsed_time": "2:03:38", "remaining_time": "12:56:15"}
+{"current_steps": 170, "total_steps": 1230, "loss": 0.4454, "lr": 3.982235366728193e-05, "epoch": 0.6893056259503294, "percentage": 13.82, "elapsed_time": "2:04:22", "remaining_time": "12:55:33"}
+{"current_steps": 171, "total_steps": 1230, "loss": 0.4505, "lr": 3.9814725646533505e-05, "epoch": 0.6933603649265079, "percentage": 13.9, "elapsed_time": "2:05:06", "remaining_time": "12:54:48"}
+{"current_steps": 172, "total_steps": 1230, "loss": 0.4537, "lr": 3.9806938040708746e-05, "epoch": 0.6974151039026862, "percentage": 13.98, "elapsed_time": "2:05:51", "remaining_time": "12:54:10"}
+{"current_steps": 173, "total_steps": 1230, "loss": 0.4575, "lr": 3.9798990912527976e-05, "epoch": 0.7014698428788647, "percentage": 14.07, "elapsed_time": "2:06:36", "remaining_time": "12:53:33"}
+{"current_steps": 174, "total_steps": 1230, "loss": 0.4439, "lr": 3.979088432599627e-05, "epoch": 0.7055245818550431, "percentage": 14.15, "elapsed_time": "2:07:20", "remaining_time": "12:52:49"}
+{"current_steps": 175, "total_steps": 1230, "loss": 0.4482, "lr": 3.9782618346402964e-05, "epoch": 0.7095793208312214, "percentage": 14.23, "elapsed_time": "2:08:06", "remaining_time": "12:52:18"}
+{"current_steps": 176, "total_steps": 1230, "loss": 0.4527, "lr": 3.977419304032111e-05, "epoch": 0.7136340598073999, "percentage": 14.31, "elapsed_time": "2:08:49", "remaining_time": "12:51:31"}
+{"current_steps": 177, "total_steps": 1230, "loss": 0.4444, "lr": 3.976560847560697e-05, "epoch": 0.7176887987835783, "percentage": 14.39, "elapsed_time": "2:09:33", "remaining_time": "12:50:47"}
+{"current_steps": 178, "total_steps": 1230, "loss": 0.4594, "lr": 3.9756864721399456e-05, "epoch": 0.7217435377597567, "percentage": 14.47, "elapsed_time": "2:10:17", "remaining_time": "12:50:04"}
+{"current_steps": 179, "total_steps": 1230, "loss": 0.451, "lr": 3.974796184811956e-05, "epoch": 0.7257982767359351, "percentage": 14.55, "elapsed_time": "2:11:02", "remaining_time": "12:49:22"}
+{"current_steps": 180, "total_steps": 1230, "loss": 0.4339, "lr": 3.973889992746979e-05, "epoch": 0.7298530157121136, "percentage": 14.63, "elapsed_time": "2:11:46", "remaining_time": "12:48:43"}
+{"current_steps": 181, "total_steps": 1230, "loss": 0.4599, "lr": 3.972967903243361e-05, "epoch": 0.733907754688292, "percentage": 14.72, "elapsed_time": "2:12:29", "remaining_time": "12:47:50"}
+{"current_steps": 182, "total_steps": 1230, "loss": 0.4435, "lr": 3.972029923727486e-05, "epoch": 0.7379624936644703, "percentage": 14.8, "elapsed_time": "2:13:11", "remaining_time": "12:46:56"}
+{"current_steps": 183, "total_steps": 1230, "loss": 0.4496, "lr": 3.971076061753709e-05, "epoch": 0.7420172326406488, "percentage": 14.88, "elapsed_time": "2:13:54", "remaining_time": "12:46:06"}
+{"current_steps": 184, "total_steps": 1230, "loss": 0.4474, "lr": 3.9701063250043066e-05, "epoch": 0.7460719716168271, "percentage": 14.96, "elapsed_time": "2:14:39", "remaining_time": "12:45:28"}
+{"current_steps": 185, "total_steps": 1230, "loss": 0.4489, "lr": 3.969120721289402e-05, "epoch": 0.7501267105930056, "percentage": 15.04, "elapsed_time": "2:15:24", "remaining_time": "12:44:53"}
+{"current_steps": 186, "total_steps": 1230, "loss": 0.4383, "lr": 3.9681192585469146e-05, "epoch": 0.754181449569184, "percentage": 15.12, "elapsed_time": "2:16:08", "remaining_time": "12:44:09"}
+{"current_steps": 187, "total_steps": 1230, "loss": 0.4394, "lr": 3.9671019448424865e-05, "epoch": 0.7582361885453623, "percentage": 15.2, "elapsed_time": "2:16:54", "remaining_time": "12:43:36"}
+{"current_steps": 188, "total_steps": 1230, "loss": 0.4342, "lr": 3.966068788369422e-05, "epoch": 0.7622909275215408, "percentage": 15.28, "elapsed_time": "2:17:37", "remaining_time": "12:42:49"}
+{"current_steps": 189, "total_steps": 1230, "loss": 0.4441, "lr": 3.965019797448622e-05, "epoch": 0.7663456664977192, "percentage": 15.37, "elapsed_time": "2:18:22", "remaining_time": "12:42:10"}
+{"current_steps": 190, "total_steps": 1230, "loss": 0.4509, "lr": 3.963954980528515e-05, "epoch": 0.7704004054738977, "percentage": 15.45, "elapsed_time": "2:19:05", "remaining_time": "12:41:21"}
+{"current_steps": 191, "total_steps": 1230, "loss": 0.4408, "lr": 3.9628743461849905e-05, "epoch": 0.774455144450076, "percentage": 15.53, "elapsed_time": "2:19:47", "remaining_time": "12:40:26"}
+{"current_steps": 192, "total_steps": 1230, "loss": 0.4394, "lr": 3.961777903121329e-05, "epoch": 0.7785098834262545, "percentage": 15.61, "elapsed_time": "2:20:30", "remaining_time": "12:39:38"}
+{"current_steps": 193, "total_steps": 1230, "loss": 0.4573, "lr": 3.960665660168131e-05, "epoch": 0.7825646224024329, "percentage": 15.69, "elapsed_time": "2:21:15", "remaining_time": "12:38:58"}
+{"current_steps": 194, "total_steps": 1230, "loss": 0.4398, "lr": 3.9595376262832485e-05, "epoch": 0.7866193613786112, "percentage": 15.77, "elapsed_time": "2:21:59", "remaining_time": "12:38:16"}
+{"current_steps": 195, "total_steps": 1230, "loss": 0.4398, "lr": 3.9583938105517127e-05, "epoch": 0.7906741003547897, "percentage": 15.85, "elapsed_time": "2:22:44", "remaining_time": "12:37:38"}
+{"current_steps": 196, "total_steps": 1230, "loss": 0.4337, "lr": 3.957234222185657e-05, "epoch": 0.794728839330968, "percentage": 15.93, "elapsed_time": "2:23:27", "remaining_time": "12:36:51"}
+{"current_steps": 197, "total_steps": 1230, "loss": 0.452, "lr": 3.9560588705242474e-05, "epoch": 0.7987835783071465, "percentage": 16.02, "elapsed_time": "2:24:11", "remaining_time": "12:36:03"}
+{"current_steps": 198, "total_steps": 1230, "loss": 0.4417, "lr": 3.954867765033605e-05, "epoch": 0.8028383172833249, "percentage": 16.1, "elapsed_time": "2:24:56", "remaining_time": "12:35:28"}
+{"current_steps": 199, "total_steps": 1230, "loss": 0.4353, "lr": 3.953660915306728e-05, "epoch": 0.8068930562595032, "percentage": 16.18, "elapsed_time": "2:25:39", "remaining_time": "12:34:40"}
+{"current_steps": 200, "total_steps": 1230, "loss": 0.4442, "lr": 3.952438331063419e-05, "epoch": 0.8109477952356817, "percentage": 16.26, "elapsed_time": "2:26:22", "remaining_time": "12:33:47"}
+{"current_steps": 201, "total_steps": 1230, "loss": 0.4309, "lr": 3.951200022150205e-05, "epoch": 0.8150025342118601, "percentage": 16.34, "elapsed_time": "2:27:07", "remaining_time": "12:33:13"}
+{"current_steps": 202, "total_steps": 1230, "loss": 0.4302, "lr": 3.949945998540253e-05, "epoch": 0.8190572731880386, "percentage": 16.42, "elapsed_time": "2:27:51", "remaining_time": "12:32:29"}
+{"current_steps": 203, "total_steps": 1230, "loss": 0.4358, "lr": 3.9486762703332993e-05, "epoch": 0.8231120121642169, "percentage": 16.5, "elapsed_time": "2:28:35", "remaining_time": "12:31:42"}
+{"current_steps": 204, "total_steps": 1230, "loss": 0.4594, "lr": 3.947390847755559e-05, "epoch": 0.8271667511403953, "percentage": 16.59, "elapsed_time": "2:29:19", "remaining_time": "12:31:01"}
+{"current_steps": 205, "total_steps": 1230, "loss": 0.4344, "lr": 3.946089741159648e-05, "epoch": 0.8312214901165738, "percentage": 16.67, "elapsed_time": "2:30:04", "remaining_time": "12:30:20"}
+{"current_steps": 206, "total_steps": 1230, "loss": 0.4464, "lr": 3.944772961024501e-05, "epoch": 0.8352762290927521, "percentage": 16.75, "elapsed_time": "2:30:47", "remaining_time": "12:29:34"}
+{"current_steps": 207, "total_steps": 1230, "loss": 0.4374, "lr": 3.943440517955285e-05, "epoch": 0.8393309680689306, "percentage": 16.83, "elapsed_time": "2:31:32", "remaining_time": "12:28:55"}
+{"current_steps": 208, "total_steps": 1230, "loss": 0.4324, "lr": 3.9420924226833126e-05, "epoch": 0.843385707045109, "percentage": 16.91, "elapsed_time": "2:32:15", "remaining_time": "12:28:07"}
+{"current_steps": 209, "total_steps": 1230, "loss": 0.4377, "lr": 3.9407286860659566e-05, "epoch": 0.8474404460212874, "percentage": 16.99, "elapsed_time": "2:32:58", "remaining_time": "12:27:19"}
+{"current_steps": 210, "total_steps": 1230, "loss": 0.4454, "lr": 3.9393493190865657e-05, "epoch": 0.8514951849974658, "percentage": 17.07, "elapsed_time": "2:33:42", "remaining_time": "12:26:36"}
+{"current_steps": 211, "total_steps": 1230, "loss": 0.4469, "lr": 3.937954332854371e-05, "epoch": 0.8555499239736442, "percentage": 17.15, "elapsed_time": "2:34:26", "remaining_time": "12:25:53"}
+{"current_steps": 212, "total_steps": 1230, "loss": 0.4481, "lr": 3.9365437386044016e-05, "epoch": 0.8596046629498226, "percentage": 17.24, "elapsed_time": "2:35:08", "remaining_time": "12:24:57"}
+{"current_steps": 213, "total_steps": 1230, "loss": 0.4462, "lr": 3.935117547697387e-05, "epoch": 0.863659401926001, "percentage": 17.32, "elapsed_time": "2:35:53", "remaining_time": "12:24:21"}
+{"current_steps": 214, "total_steps": 1230, "loss": 0.4488, "lr": 3.933675771619675e-05, "epoch": 0.8677141409021795, "percentage": 17.4, "elapsed_time": "2:36:39", "remaining_time": "12:23:45"}
+{"current_steps": 215, "total_steps": 1230, "loss": 0.4443, "lr": 3.932218421983131e-05, "epoch": 0.8717688798783578, "percentage": 17.48, "elapsed_time": "2:37:22", "remaining_time": "12:22:57"}
+{"current_steps": 216, "total_steps": 1230, "loss": 0.4359, "lr": 3.9307455105250484e-05, "epoch": 0.8758236188545362, "percentage": 17.56, "elapsed_time": "2:38:04", "remaining_time": "12:22:05"}
+{"current_steps": 217, "total_steps": 1230, "loss": 0.4426, "lr": 3.929257049108054e-05, "epoch": 0.8798783578307147, "percentage": 17.64, "elapsed_time": "2:38:47", "remaining_time": "12:21:16"}
+{"current_steps": 218, "total_steps": 1230, "loss": 0.4393, "lr": 3.927753049720011e-05, "epoch": 0.883933096806893, "percentage": 17.72, "elapsed_time": "2:39:28", "remaining_time": "12:20:19"}
+{"current_steps": 219, "total_steps": 1230, "loss": 0.4155, "lr": 3.9262335244739234e-05, "epoch": 0.8879878357830715, "percentage": 17.8, "elapsed_time": "2:40:13", "remaining_time": "12:19:42"}
+{"current_steps": 220, "total_steps": 1230, "loss": 0.4332, "lr": 3.92469848560784e-05, "epoch": 0.8920425747592499, "percentage": 17.89, "elapsed_time": "2:40:55", "remaining_time": "12:18:49"}
+{"current_steps": 221, "total_steps": 1230, "loss": 0.4345, "lr": 3.923147945484751e-05, "epoch": 0.8960973137354283, "percentage": 17.97, "elapsed_time": "2:41:39", "remaining_time": "12:18:02"}
+{"current_steps": 222, "total_steps": 1230, "loss": 0.4364, "lr": 3.9215819165924956e-05, "epoch": 0.9001520527116067, "percentage": 18.05, "elapsed_time": "2:42:23", "remaining_time": "12:17:21"}
+{"current_steps": 223, "total_steps": 1230, "loss": 0.4379, "lr": 3.920000411543654e-05, "epoch": 0.9042067916877851, "percentage": 18.13, "elapsed_time": "2:43:09", "remaining_time": "12:16:45"}
+{"current_steps": 224, "total_steps": 1230, "loss": 0.4458, "lr": 3.9184034430754495e-05, "epoch": 0.9082615306639635, "percentage": 18.21, "elapsed_time": "2:43:53", "remaining_time": "12:16:03"}
+{"current_steps": 225, "total_steps": 1230, "loss": 0.4358, "lr": 3.916791024049648e-05, "epoch": 0.9123162696401419, "percentage": 18.29, "elapsed_time": "2:44:38", "remaining_time": "12:15:22"}
+{"current_steps": 226, "total_steps": 1230, "loss": 0.453, "lr": 3.91516316745245e-05, "epoch": 0.9163710086163204, "percentage": 18.37, "elapsed_time": "2:45:22", "remaining_time": "12:14:40"}
+{"current_steps": 227, "total_steps": 1230, "loss": 0.4405, "lr": 3.913519886394389e-05, "epoch": 0.9204257475924987, "percentage": 18.46, "elapsed_time": "2:46:08", "remaining_time": "12:14:04"}
+{"current_steps": 228, "total_steps": 1230, "loss": 0.4369, "lr": 3.911861194110225e-05, "epoch": 0.9244804865686771, "percentage": 18.54, "elapsed_time": "2:46:50", "remaining_time": "12:13:11"}
+{"current_steps": 229, "total_steps": 1230, "loss": 0.4433, "lr": 3.910187103958837e-05, "epoch": 0.9285352255448556, "percentage": 18.62, "elapsed_time": "2:47:33", "remaining_time": "12:12:25"}
+{"current_steps": 230, "total_steps": 1230, "loss": 0.437, "lr": 3.908497629423117e-05, "epoch": 0.9325899645210339, "percentage": 18.7, "elapsed_time": "2:48:18", "remaining_time": "12:11:46"}
+{"current_steps": 231, "total_steps": 1230, "loss": 0.4411, "lr": 3.9067927841098614e-05, "epoch": 0.9366447034972124, "percentage": 18.78, "elapsed_time": "2:49:02", "remaining_time": "12:11:03"}
+{"current_steps": 232, "total_steps": 1230, "loss": 0.4346, "lr": 3.9050725817496594e-05, "epoch": 0.9406994424733908, "percentage": 18.86, "elapsed_time": "2:49:45", "remaining_time": "12:10:13"}
+{"current_steps": 233, "total_steps": 1230, "loss": 0.4241, "lr": 3.9033370361967844e-05, "epoch": 0.9447541814495691, "percentage": 18.94, "elapsed_time": "2:50:27", "remaining_time": "12:09:21"}
+{"current_steps": 234, "total_steps": 1230, "loss": 0.4236, "lr": 3.901586161429081e-05, "epoch": 0.9488089204257476, "percentage": 19.02, "elapsed_time": "2:51:08", "remaining_time": "12:08:27"}
+{"current_steps": 235, "total_steps": 1230, "loss": 0.4442, "lr": 3.8998199715478545e-05, "epoch": 0.952863659401926, "percentage": 19.11, "elapsed_time": "2:51:53", "remaining_time": "12:07:47"}
+{"current_steps": 236, "total_steps": 1230, "loss": 0.4381, "lr": 3.8980384807777564e-05, "epoch": 0.9569183983781044, "percentage": 19.19, "elapsed_time": "2:52:38", "remaining_time": "12:07:07"}
+{"current_steps": 237, "total_steps": 1230, "loss": 0.4432, "lr": 3.896241703466667e-05, "epoch": 0.9609731373542828, "percentage": 19.27, "elapsed_time": "2:53:23", "remaining_time": "12:06:27"}
+{"current_steps": 238, "total_steps": 1230, "loss": 0.4281, "lr": 3.894429654085585e-05, "epoch": 0.9650278763304613, "percentage": 19.35, "elapsed_time": "2:54:06", "remaining_time": "12:05:43"}
+{"current_steps": 239, "total_steps": 1230, "loss": 0.439, "lr": 3.892602347228505e-05, "epoch": 0.9690826153066396, "percentage": 19.43, "elapsed_time": "2:54:50", "remaining_time": "12:04:59"}
+{"current_steps": 240, "total_steps": 1230, "loss": 0.418, "lr": 3.890759797612307e-05, "epoch": 0.973137354282818, "percentage": 19.51, "elapsed_time": "2:55:35", "remaining_time": "12:04:19"}
+{"current_steps": 241, "total_steps": 1230, "loss": 0.4298, "lr": 3.888902020076632e-05, "epoch": 0.9771920932589965, "percentage": 19.59, "elapsed_time": "2:56:17", "remaining_time": "12:03:27"}
+{"current_steps": 242, "total_steps": 1230, "loss": 0.4397, "lr": 3.887029029583764e-05, "epoch": 0.9812468322351748, "percentage": 19.67, "elapsed_time": "2:57:04", "remaining_time": "12:02:55"}
+{"current_steps": 243, "total_steps": 1230, "loss": 0.4315, "lr": 3.8851408412185125e-05, "epoch": 0.9853015712113533, "percentage": 19.76, "elapsed_time": "2:57:48", "remaining_time": "12:02:13"}
+{"current_steps": 244, "total_steps": 1230, "loss": 0.4291, "lr": 3.8832374701880855e-05, "epoch": 0.9893563101875317, "percentage": 19.84, "elapsed_time": "2:58:31", "remaining_time": "12:01:24"}
+{"current_steps": 245, "total_steps": 1230, "loss": 0.4537, "lr": 3.881318931821972e-05, "epoch": 0.99341104916371, "percentage": 19.92, "elapsed_time": "2:59:16", "remaining_time": "12:00:45"}
+{"current_steps": 246, "total_steps": 1230, "loss": 0.4405, "lr": 3.879385241571817e-05, "epoch": 0.9974657881398885, "percentage": 20.0, "elapsed_time": "3:00:01", "remaining_time": "12:00:05"}
+{"current_steps": 247, "total_steps": 1230, "loss": 0.4257, "lr": 3.8774364150112955e-05, "epoch": 1.0025342118601115, "percentage": 20.08, "elapsed_time": "3:03:01", "remaining_time": "12:08:25"}
+{"current_steps": 248, "total_steps": 1230, "loss": 0.3953, "lr": 3.8754724678359884e-05, "epoch": 1.00658895083629, "percentage": 20.16, "elapsed_time": "3:03:44", "remaining_time": "12:07:33"}
+{"current_steps": 249, "total_steps": 1230, "loss": 0.4084, "lr": 3.873493415863256e-05, "epoch": 1.0106436898124682, "percentage": 20.24, "elapsed_time": "3:04:25", "remaining_time": "12:06:36"}
+{"current_steps": 250, "total_steps": 1230, "loss": 0.3946, "lr": 3.871499275032111e-05, "epoch": 1.0146984287886467, "percentage": 20.33, "elapsed_time": "3:05:12", "remaining_time": "12:06:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e609120132402b0f5624b0e3adf0897837677edb749ae02480d918807536e9
+size 7224