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 sha256:011bb9123db1618462e7d61f851ad19ef9a6ecd60063e9b9300df6aae144645d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5089f08b574285eb4e4931205a7791b10701cf7ec806fb477aab66a4b619823d
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0143c931d229dccdf5af3b0436697f525c95a74252f8040c6b67e60696b4d838
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a63baea6b049b933ba661fcbf8c569c72eeb549e3342b9ac52dfdbc323699e
+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": 0.8709, "lr": 3.2520325203252037e-07, "epoch": 0.004050632911392405, "percentage": 0.08, "elapsed_time": "0:01:14", "remaining_time": "1 day, 1:32:13"}
+{"current_steps": 2, "total_steps": 1230, "loss": 0.8699, "lr": 6.504065040650407e-07, "epoch": 0.00810126582278481, "percentage": 0.16, "elapsed_time": "0:02:07", "remaining_time": "21:44:40"}
+{"current_steps": 3, "total_steps": 1230, "loss": 0.8666, "lr": 9.75609756097561e-07, "epoch": 0.012151898734177215, "percentage": 0.24, "elapsed_time": "0:03:26", "remaining_time": "23:27:07"}
+{"current_steps": 4, "total_steps": 1230, "loss": 0.8798, "lr": 1.3008130081300815e-06, "epoch": 0.01620253164556962, "percentage": 0.33, "elapsed_time": "0:04:37", "remaining_time": "23:35:28"}
+{"current_steps": 5, "total_steps": 1230, "loss": 0.8387, "lr": 1.6260162601626018e-06, "epoch": 0.020253164556962026, "percentage": 0.41, "elapsed_time": "0:05:58", "remaining_time": "1 day, 0:23:58"}
+{"current_steps": 6, "total_steps": 1230, "loss": 0.8262, "lr": 1.951219512195122e-06, "epoch": 0.02430379746835443, "percentage": 0.49, "elapsed_time": "0:21:51", "remaining_time": "3 days, 2:19:14"}
+{"current_steps": 7, "total_steps": 1230, "loss": 0.8124, "lr": 2.2764227642276426e-06, "epoch": 0.028354430379746835, "percentage": 0.57, "elapsed_time": "0:22:51", "remaining_time": "2 days, 18:32:48"}
+{"current_steps": 8, "total_steps": 1230, "loss": 0.8177, "lr": 2.601626016260163e-06, "epoch": 0.03240506329113924, "percentage": 0.65, "elapsed_time": "0:23:45", "remaining_time": "2 days, 12:28:44"}
+{"current_steps": 9, "total_steps": 1230, "loss": 0.7283, "lr": 2.926829268292683e-06, "epoch": 0.03645569620253165, "percentage": 0.73, "elapsed_time": "0:24:55", "remaining_time": "2 days, 8:22:34"}
+{"current_steps": 10, "total_steps": 1230, "loss": 0.7166, "lr": 3.2520325203252037e-06, "epoch": 0.04050632911392405, "percentage": 0.81, "elapsed_time": "0:26:07", "remaining_time": "2 days, 5:07:51"}
+{"current_steps": 11, "total_steps": 1230, "loss": 0.7297, "lr": 3.577235772357724e-06, "epoch": 0.044556962025316456, "percentage": 0.89, "elapsed_time": "0:27:17", "remaining_time": "2 days, 2:23:42"}
+{"current_steps": 12, "total_steps": 1230, "loss": 0.6967, "lr": 3.902439024390244e-06, "epoch": 0.04860759493670886, "percentage": 0.98, "elapsed_time": "0:28:33", "remaining_time": "2 days, 0:18:11"}
+{"current_steps": 13, "total_steps": 1230, "loss": 0.6986, "lr": 4.227642276422765e-06, "epoch": 0.052658227848101265, "percentage": 1.06, "elapsed_time": "0:29:30", "remaining_time": "1 day, 22:02:54"}
+{"current_steps": 14, "total_steps": 1230, "loss": 0.668, "lr": 4.552845528455285e-06, "epoch": 0.05670886075949367, "percentage": 1.14, "elapsed_time": "0:30:24", "remaining_time": "1 day, 20:01:13"}
+{"current_steps": 15, "total_steps": 1230, "loss": 0.6539, "lr": 4.8780487804878055e-06, "epoch": 0.060759493670886074, "percentage": 1.22, "elapsed_time": "0:31:37", "remaining_time": "1 day, 18:41:34"}
+{"current_steps": 16, "total_steps": 1230, "loss": 0.6151, "lr": 5.203252032520326e-06, "epoch": 0.06481012658227848, "percentage": 1.3, "elapsed_time": "0:32:40", "remaining_time": "1 day, 17:19:25"}
+{"current_steps": 17, "total_steps": 1230, "loss": 0.5994, "lr": 5.528455284552846e-06, "epoch": 0.06886075949367089, "percentage": 1.38, "elapsed_time": "0:33:56", "remaining_time": "1 day, 16:21:27"}
+{"current_steps": 18, "total_steps": 1230, "loss": 0.5908, "lr": 5.853658536585366e-06, "epoch": 0.0729113924050633, "percentage": 1.46, "elapsed_time": "0:35:05", "remaining_time": "1 day, 15:22:24"}
+{"current_steps": 19, "total_steps": 1230, "loss": 0.5876, "lr": 6.178861788617887e-06, "epoch": 0.0769620253164557, "percentage": 1.54, "elapsed_time": "0:36:12", "remaining_time": "1 day, 14:28:09"}
+{"current_steps": 20, "total_steps": 1230, "loss": 0.5867, "lr": 6.504065040650407e-06, "epoch": 0.0810126582278481, "percentage": 1.63, "elapsed_time": "0:37:32", "remaining_time": "1 day, 13:51:17"}
+{"current_steps": 21, "total_steps": 1230, "loss": 0.5403, "lr": 6.829268292682928e-06, "epoch": 0.08506329113924051, "percentage": 1.71, "elapsed_time": "0:38:46", "remaining_time": "1 day, 13:11:59"}
+{"current_steps": 22, "total_steps": 1230, "loss": 0.5459, "lr": 7.154471544715448e-06, "epoch": 0.08911392405063291, "percentage": 1.79, "elapsed_time": "0:39:52", "remaining_time": "1 day, 12:29:16"}
+{"current_steps": 23, "total_steps": 1230, "loss": 0.5285, "lr": 7.4796747967479676e-06, "epoch": 0.09316455696202532, "percentage": 1.87, "elapsed_time": "0:40:58", "remaining_time": "1 day, 11:50:05"}
+{"current_steps": 24, "total_steps": 1230, "loss": 0.5338, "lr": 7.804878048780489e-06, "epoch": 0.09721518987341772, "percentage": 1.95, "elapsed_time": "0:42:04", "remaining_time": "1 day, 11:14:13"}
+{"current_steps": 25, "total_steps": 1230, "loss": 0.5287, "lr": 8.130081300813009e-06, "epoch": 0.10126582278481013, "percentage": 2.03, "elapsed_time": "0:43:17", "remaining_time": "1 day, 10:46:47"}
+{"current_steps": 26, "total_steps": 1230, "loss": 0.5234, "lr": 8.45528455284553e-06, "epoch": 0.10531645569620253, "percentage": 2.11, "elapsed_time": "0:44:25", "remaining_time": "1 day, 10:17:34"}
+{"current_steps": 27, "total_steps": 1230, "loss": 0.5054, "lr": 8.78048780487805e-06, "epoch": 0.10936708860759493, "percentage": 2.2, "elapsed_time": "0:45:26", "remaining_time": "1 day, 9:44:44"}
+{"current_steps": 28, "total_steps": 1230, "loss": 0.5109, "lr": 9.10569105691057e-06, "epoch": 0.11341772151898734, "percentage": 2.28, "elapsed_time": "0:46:38", "remaining_time": "1 day, 9:22:31"}
+{"current_steps": 29, "total_steps": 1230, "loss": 0.5238, "lr": 9.43089430894309e-06, "epoch": 0.11746835443037974, "percentage": 2.36, "elapsed_time": "0:47:59", "remaining_time": "1 day, 9:07:45"}
+{"current_steps": 30, "total_steps": 1230, "loss": 0.4838, "lr": 9.756097560975611e-06, "epoch": 0.12151898734177215, "percentage": 2.44, "elapsed_time": "0:49:14", "remaining_time": "1 day, 8:49:33"}
+{"current_steps": 31, "total_steps": 1230, "loss": 0.5105, "lr": 1.008130081300813e-05, "epoch": 0.12556962025316457, "percentage": 2.52, "elapsed_time": "0:50:25", "remaining_time": "1 day, 8:30:04"}
+{"current_steps": 32, "total_steps": 1230, "loss": 0.4684, "lr": 1.0406504065040652e-05, "epoch": 0.12962025316455697, "percentage": 2.6, "elapsed_time": "0:51:36", "remaining_time": "1 day, 8:12:01"}
+{"current_steps": 33, "total_steps": 1230, "loss": 0.4917, "lr": 1.0731707317073172e-05, "epoch": 0.13367088607594937, "percentage": 2.68, "elapsed_time": "0:52:51", "remaining_time": "1 day, 7:57:08"}
+{"current_steps": 34, "total_steps": 1230, "loss": 0.4769, "lr": 1.1056910569105692e-05, "epoch": 0.13772151898734178, "percentage": 2.76, "elapsed_time": "0:53:47", "remaining_time": "1 day, 7:32:13"}
+{"current_steps": 35, "total_steps": 1230, "loss": 0.4871, "lr": 1.1382113821138213e-05, "epoch": 0.14177215189873418, "percentage": 2.85, "elapsed_time": "0:54:59", "remaining_time": "1 day, 7:17:40"}
+{"current_steps": 36, "total_steps": 1230, "loss": 0.4662, "lr": 1.1707317073170731e-05, "epoch": 0.1458227848101266, "percentage": 2.93, "elapsed_time": "0:55:51", "remaining_time": "1 day, 6:52:48"}
+{"current_steps": 37, "total_steps": 1230, "loss": 0.4793, "lr": 1.2032520325203254e-05, "epoch": 0.149873417721519, "percentage": 3.01, "elapsed_time": "0:57:03", "remaining_time": "1 day, 6:39:31"}
+{"current_steps": 38, "total_steps": 1230, "loss": 0.4725, "lr": 1.2357723577235774e-05, "epoch": 0.1539240506329114, "percentage": 3.09, "elapsed_time": "0:58:01", "remaining_time": "1 day, 6:20:11"}
+{"current_steps": 39, "total_steps": 1230, "loss": 0.4795, "lr": 1.2682926829268294e-05, "epoch": 0.1579746835443038, "percentage": 3.17, "elapsed_time": "0:59:09", "remaining_time": "1 day, 6:06:41"}
+{"current_steps": 40, "total_steps": 1230, "loss": 0.4848, "lr": 1.3008130081300815e-05, "epoch": 0.1620253164556962, "percentage": 3.25, "elapsed_time": "1:00:19", "remaining_time": "1 day, 5:54:51"}
+{"current_steps": 41, "total_steps": 1230, "loss": 0.4582, "lr": 1.3333333333333333e-05, "epoch": 0.1660759493670886, "percentage": 3.33, "elapsed_time": "1:01:22", "remaining_time": "1 day, 5:39:50"}
+{"current_steps": 42, "total_steps": 1230, "loss": 0.4758, "lr": 1.3658536585365855e-05, "epoch": 0.17012658227848101, "percentage": 3.41, "elapsed_time": "1:02:20", "remaining_time": "1 day, 5:23:26"}
+{"current_steps": 43, "total_steps": 1230, "loss": 0.4623, "lr": 1.3983739837398376e-05, "epoch": 0.17417721518987342, "percentage": 3.5, "elapsed_time": "1:03:27", "remaining_time": "1 day, 5:11:54"}
+{"current_steps": 44, "total_steps": 1230, "loss": 0.4497, "lr": 1.4308943089430896e-05, "epoch": 0.17822784810126582, "percentage": 3.58, "elapsed_time": "1:04:29", "remaining_time": "1 day, 4:58:17"}
+{"current_steps": 45, "total_steps": 1230, "loss": 0.473, "lr": 1.4634146341463415e-05, "epoch": 0.18227848101265823, "percentage": 3.66, "elapsed_time": "1:05:33", "remaining_time": "1 day, 4:46:22"}
+{"current_steps": 46, "total_steps": 1230, "loss": 0.4335, "lr": 1.4959349593495935e-05, "epoch": 0.18632911392405063, "percentage": 3.74, "elapsed_time": "1:06:32", "remaining_time": "1 day, 4:32:53"}
+{"current_steps": 47, "total_steps": 1230, "loss": 0.4301, "lr": 1.528455284552846e-05, "epoch": 0.19037974683544304, "percentage": 3.82, "elapsed_time": "1:07:35", "remaining_time": "1 day, 4:21:06"}
+{"current_steps": 48, "total_steps": 1230, "loss": 0.4535, "lr": 1.5609756097560978e-05, "epoch": 0.19443037974683544, "percentage": 3.9, "elapsed_time": "1:08:37", "remaining_time": "1 day, 4:09:53"}
+{"current_steps": 49, "total_steps": 1230, "loss": 0.4545, "lr": 1.5934959349593496e-05, "epoch": 0.19848101265822785, "percentage": 3.98, "elapsed_time": "1:10:02", "remaining_time": "1 day, 4:08:02"}
+{"current_steps": 50, "total_steps": 1230, "loss": 0.4557, "lr": 1.6260162601626018e-05, "epoch": 0.20253164556962025, "percentage": 4.07, "elapsed_time": "1:11:18", "remaining_time": "1 day, 4:02:41"}
+{"current_steps": 51, "total_steps": 1230, "loss": 0.4542, "lr": 1.6585365853658537e-05, "epoch": 0.20658227848101265, "percentage": 4.15, "elapsed_time": "1:12:36", "remaining_time": "1 day, 3:58:21"}
+{"current_steps": 52, "total_steps": 1230, "loss": 0.4403, "lr": 1.691056910569106e-05, "epoch": 0.21063291139240506, "percentage": 4.23, "elapsed_time": "1:13:57", "remaining_time": "1 day, 3:55:26"}
+{"current_steps": 53, "total_steps": 1230, "loss": 0.4668, "lr": 1.7235772357723578e-05, "epoch": 0.21468354430379746, "percentage": 4.31, "elapsed_time": "1:15:04", "remaining_time": "1 day, 3:47:15"}
+{"current_steps": 54, "total_steps": 1230, "loss": 0.4553, "lr": 1.75609756097561e-05, "epoch": 0.21873417721518987, "percentage": 4.39, "elapsed_time": "1:16:21", "remaining_time": "1 day, 3:43:05"}
+{"current_steps": 55, "total_steps": 1230, "loss": 0.4542, "lr": 1.788617886178862e-05, "epoch": 0.22278481012658227, "percentage": 4.47, "elapsed_time": "1:17:33", "remaining_time": "1 day, 3:37:04"}
+{"current_steps": 56, "total_steps": 1230, "loss": 0.4369, "lr": 1.821138211382114e-05, "epoch": 0.22683544303797468, "percentage": 4.55, "elapsed_time": "1:18:48", "remaining_time": "1 day, 3:32:06"}
+{"current_steps": 57, "total_steps": 1230, "loss": 0.4418, "lr": 1.8536585365853663e-05, "epoch": 0.23088607594936708, "percentage": 4.63, "elapsed_time": "1:19:48", "remaining_time": "1 day, 3:22:29"}
+{"current_steps": 58, "total_steps": 1230, "loss": 0.4497, "lr": 1.886178861788618e-05, "epoch": 0.23493670886075949, "percentage": 4.72, "elapsed_time": "1:21:03", "remaining_time": "1 day, 3:17:50"}
+{"current_steps": 59, "total_steps": 1230, "loss": 0.4415, "lr": 1.91869918699187e-05, "epoch": 0.2389873417721519, "percentage": 4.8, "elapsed_time": "1:22:06", "remaining_time": "1 day, 3:09:35"}
+{"current_steps": 60, "total_steps": 1230, "loss": 0.4316, "lr": 1.9512195121951222e-05, "epoch": 0.2430379746835443, "percentage": 4.88, "elapsed_time": "1:22:58", "remaining_time": "1 day, 2:58:04"}
+{"current_steps": 61, "total_steps": 1230, "loss": 0.4454, "lr": 1.983739837398374e-05, "epoch": 0.2470886075949367, "percentage": 4.96, "elapsed_time": "1:24:25", "remaining_time": "1 day, 2:57:59"}
+{"current_steps": 62, "total_steps": 1230, "loss": 0.431, "lr": 2.016260162601626e-05, "epoch": 0.25113924050632913, "percentage": 5.04, "elapsed_time": "1:25:31", "remaining_time": "1 day, 2:51:11"}
+{"current_steps": 63, "total_steps": 1230, "loss": 0.4388, "lr": 2.048780487804878e-05, "epoch": 0.25518987341772154, "percentage": 5.12, "elapsed_time": "1:26:40", "remaining_time": "1 day, 2:45:36"}
+{"current_steps": 64, "total_steps": 1230, "loss": 0.4333, "lr": 2.0813008130081303e-05, "epoch": 0.25924050632911394, "percentage": 5.2, "elapsed_time": "1:27:40", "remaining_time": "1 day, 2:37:20"}
+{"current_steps": 65, "total_steps": 1230, "loss": 0.4449, "lr": 2.1138211382113822e-05, "epoch": 0.26329113924050634, "percentage": 5.28, "elapsed_time": "1:28:52", "remaining_time": "1 day, 2:33:03"}
+{"current_steps": 66, "total_steps": 1230, "loss": 0.4414, "lr": 2.1463414634146344e-05, "epoch": 0.26734177215189875, "percentage": 5.37, "elapsed_time": "1:30:02", "remaining_time": "1 day, 2:27:52"}
+{"current_steps": 67, "total_steps": 1230, "loss": 0.4301, "lr": 2.1788617886178863e-05, "epoch": 0.27139240506329115, "percentage": 5.45, "elapsed_time": "1:31:11", "remaining_time": "1 day, 2:23:00"}
+{"current_steps": 68, "total_steps": 1230, "loss": 0.4438, "lr": 2.2113821138211385e-05, "epoch": 0.27544303797468356, "percentage": 5.53, "elapsed_time": "1:32:33", "remaining_time": "1 day, 2:21:36"}
+{"current_steps": 69, "total_steps": 1230, "loss": 0.4225, "lr": 2.2439024390243907e-05, "epoch": 0.27949367088607596, "percentage": 5.61, "elapsed_time": "1:33:29", "remaining_time": "1 day, 2:13:01"}
+{"current_steps": 70, "total_steps": 1230, "loss": 0.4267, "lr": 2.2764227642276426e-05, "epoch": 0.28354430379746837, "percentage": 5.69, "elapsed_time": "1:34:36", "remaining_time": "1 day, 2:07:49"}
+{"current_steps": 71, "total_steps": 1230, "loss": 0.428, "lr": 2.3089430894308948e-05, "epoch": 0.28759493670886077, "percentage": 5.77, "elapsed_time": "1:35:27", "remaining_time": "1 day, 1:58:19"}
+{"current_steps": 72, "total_steps": 1230, "loss": 0.4436, "lr": 2.3414634146341463e-05, "epoch": 0.2916455696202532, "percentage": 5.85, "elapsed_time": "1:36:25", "remaining_time": "1 day, 1:50:54"}
+{"current_steps": 73, "total_steps": 1230, "loss": 0.4403, "lr": 2.3739837398373985e-05, "epoch": 0.2956962025316456, "percentage": 5.93, "elapsed_time": "1:37:38", "remaining_time": "1 day, 1:47:30"}
+{"current_steps": 74, "total_steps": 1230, "loss": 0.4394, "lr": 2.4065040650406507e-05, "epoch": 0.299746835443038, "percentage": 6.02, "elapsed_time": "1:38:46", "remaining_time": "1 day, 1:43:05"}
+{"current_steps": 75, "total_steps": 1230, "loss": 0.4354, "lr": 2.4390243902439026e-05, "epoch": 0.3037974683544304, "percentage": 6.1, "elapsed_time": "1:39:51", "remaining_time": "1 day, 1:37:43"}
+{"current_steps": 76, "total_steps": 1230, "loss": 0.4375, "lr": 2.4715447154471548e-05, "epoch": 0.3078481012658228, "percentage": 6.18, "elapsed_time": "1:40:52", "remaining_time": "1 day, 1:31:42"}
+{"current_steps": 77, "total_steps": 1230, "loss": 0.4172, "lr": 2.5040650406504066e-05, "epoch": 0.3118987341772152, "percentage": 6.26, "elapsed_time": "1:42:08", "remaining_time": "1 day, 1:29:33"}
+{"current_steps": 78, "total_steps": 1230, "loss": 0.4384, "lr": 2.536585365853659e-05, "epoch": 0.3159493670886076, "percentage": 6.34, "elapsed_time": "1:43:10", "remaining_time": "1 day, 1:23:49"}
+{"current_steps": 79, "total_steps": 1230, "loss": 0.4173, "lr": 2.569105691056911e-05, "epoch": 0.32, "percentage": 6.42, "elapsed_time": "1:44:21", "remaining_time": "1 day, 1:20:23"}
+{"current_steps": 80, "total_steps": 1230, "loss": 0.447, "lr": 2.601626016260163e-05, "epoch": 0.3240506329113924, "percentage": 6.5, "elapsed_time": "1:45:28", "remaining_time": "1 day, 1:16:06"}
+{"current_steps": 81, "total_steps": 1230, "loss": 0.4174, "lr": 2.634146341463415e-05, "epoch": 0.3281012658227848, "percentage": 6.59, "elapsed_time": "1:46:53", "remaining_time": "1 day, 1:16:15"}
+{"current_steps": 82, "total_steps": 1230, "loss": 0.4385, "lr": 2.6666666666666667e-05, "epoch": 0.3321518987341772, "percentage": 6.67, "elapsed_time": "1:48:10", "remaining_time": "1 day, 1:14:29"}
+{"current_steps": 83, "total_steps": 1230, "loss": 0.4294, "lr": 2.699186991869919e-05, "epoch": 0.3362025316455696, "percentage": 6.75, "elapsed_time": "1:49:25", "remaining_time": "1 day, 1:12:17"}
+{"current_steps": 84, "total_steps": 1230, "loss": 0.4441, "lr": 2.731707317073171e-05, "epoch": 0.34025316455696203, "percentage": 6.83, "elapsed_time": "1:50:35", "remaining_time": "1 day, 1:08:41"}
+{"current_steps": 85, "total_steps": 1230, "loss": 0.4216, "lr": 2.764227642276423e-05, "epoch": 0.34430379746835443, "percentage": 6.91, "elapsed_time": "1:51:41", "remaining_time": "1 day, 1:04:39"}
+{"current_steps": 86, "total_steps": 1230, "loss": 0.4123, "lr": 2.796747967479675e-05, "epoch": 0.34835443037974684, "percentage": 6.99, "elapsed_time": "1:52:57", "remaining_time": "1 day, 1:02:43"}
+{"current_steps": 87, "total_steps": 1230, "loss": 0.4228, "lr": 2.829268292682927e-05, "epoch": 0.35240506329113924, "percentage": 7.07, "elapsed_time": "1:54:12", "remaining_time": "1 day, 1:00:30"}
+{"current_steps": 88, "total_steps": 1230, "loss": 0.4272, "lr": 2.8617886178861792e-05, "epoch": 0.35645569620253165, "percentage": 7.15, "elapsed_time": "1:55:17", "remaining_time": "1 day, 0:56:12"}
+{"current_steps": 89, "total_steps": 1230, "loss": 0.4081, "lr": 2.8943089430894314e-05, "epoch": 0.36050632911392405, "percentage": 7.24, "elapsed_time": "1:56:04", "remaining_time": "1 day, 0:48:09"}
+{"current_steps": 90, "total_steps": 1230, "loss": 0.4174, "lr": 2.926829268292683e-05, "epoch": 0.36455696202531646, "percentage": 7.32, "elapsed_time": "1:57:09", "remaining_time": "1 day, 0:44:01"}
+{"current_steps": 91, "total_steps": 1230, "loss": 0.4291, "lr": 2.959349593495935e-05, "epoch": 0.36860759493670886, "percentage": 7.4, "elapsed_time": "1:58:14", "remaining_time": "1 day, 0:40:01"}
+{"current_steps": 92, "total_steps": 1230, "loss": 0.4294, "lr": 2.991869918699187e-05, "epoch": 0.37265822784810126, "percentage": 7.48, "elapsed_time": "1:59:09", "remaining_time": "1 day, 0:33:53"}
+{"current_steps": 93, "total_steps": 1230, "loss": 0.441, "lr": 3.0243902439024392e-05, "epoch": 0.37670886075949367, "percentage": 7.56, "elapsed_time": "2:00:20", "remaining_time": "1 day, 0:31:15"}
+{"current_steps": 94, "total_steps": 1230, "loss": 0.4068, "lr": 3.056910569105692e-05, "epoch": 0.3807594936708861, "percentage": 7.64, "elapsed_time": "2:01:29", "remaining_time": "1 day, 0:28:17"}
+{"current_steps": 95, "total_steps": 1230, "loss": 0.4399, "lr": 3.089430894308943e-05, "epoch": 0.3848101265822785, "percentage": 7.72, "elapsed_time": "2:02:40", "remaining_time": "1 day, 0:25:37"}
+{"current_steps": 96, "total_steps": 1230, "loss": 0.4289, "lr": 3.1219512195121955e-05, "epoch": 0.3888607594936709, "percentage": 7.8, "elapsed_time": "2:03:45", "remaining_time": "1 day, 0:21:53"}
+{"current_steps": 97, "total_steps": 1230, "loss": 0.4397, "lr": 3.154471544715447e-05, "epoch": 0.3929113924050633, "percentage": 7.89, "elapsed_time": "2:05:04", "remaining_time": "1 day, 0:20:56"}
+{"current_steps": 98, "total_steps": 1230, "loss": 0.4388, "lr": 3.186991869918699e-05, "epoch": 0.3969620253164557, "percentage": 7.97, "elapsed_time": "2:06:16", "remaining_time": "1 day, 0:18:41"}
+{"current_steps": 99, "total_steps": 1230, "loss": 0.425, "lr": 3.2195121951219514e-05, "epoch": 0.4010126582278481, "percentage": 8.05, "elapsed_time": "2:09:01", "remaining_time": "1 day, 0:34:05"}
+{"current_steps": 100, "total_steps": 1230, "loss": 0.4317, "lr": 3.2520325203252037e-05, "epoch": 0.4050632911392405, "percentage": 8.13, "elapsed_time": "2:11:00", "remaining_time": "1 day, 0:40:26"}
+{"current_steps": 101, "total_steps": 1230, "loss": 0.4385, "lr": 3.284552845528456e-05, "epoch": 0.4091139240506329, "percentage": 8.21, "elapsed_time": "2:12:37", "remaining_time": "1 day, 0:42:27"}
+{"current_steps": 102, "total_steps": 1230, "loss": 0.4392, "lr": 3.3170731707317074e-05, "epoch": 0.4131645569620253, "percentage": 8.29, "elapsed_time": "2:16:13", "remaining_time": "1 day, 1:06:25"}
+{"current_steps": 103, "total_steps": 1230, "loss": 0.4215, "lr": 3.3495934959349596e-05, "epoch": 0.4172151898734177, "percentage": 8.37, "elapsed_time": "2:18:22", "remaining_time": "1 day, 1:14:07"}
+{"current_steps": 104, "total_steps": 1230, "loss": 0.4295, "lr": 3.382113821138212e-05, "epoch": 0.4212658227848101, "percentage": 8.46, "elapsed_time": "2:19:53", "remaining_time": "1 day, 1:14:35"}
+{"current_steps": 105, "total_steps": 1230, "loss": 0.4235, "lr": 3.414634146341463e-05, "epoch": 0.4253164556962025, "percentage": 8.54, "elapsed_time": "2:21:18", "remaining_time": "1 day, 1:14:01"}
+{"current_steps": 106, "total_steps": 1230, "loss": 0.4208, "lr": 3.4471544715447155e-05, "epoch": 0.4293670886075949, "percentage": 8.62, "elapsed_time": "2:22:22", "remaining_time": "1 day, 1:09:46"}
+{"current_steps": 107, "total_steps": 1230, "loss": 0.4113, "lr": 3.479674796747968e-05, "epoch": 0.43341772151898733, "percentage": 8.7, "elapsed_time": "2:23:19", "remaining_time": "1 day, 1:04:13"}
+{"current_steps": 108, "total_steps": 1230, "loss": 0.4327, "lr": 3.51219512195122e-05, "epoch": 0.43746835443037974, "percentage": 8.78, "elapsed_time": "2:24:32", "remaining_time": "1 day, 1:01:41"}
+{"current_steps": 109, "total_steps": 1230, "loss": 0.4456, "lr": 3.544715447154472e-05, "epoch": 0.44151898734177214, "percentage": 8.86, "elapsed_time": "2:25:38", "remaining_time": "1 day, 0:57:48"}
+{"current_steps": 110, "total_steps": 1230, "loss": 0.4155, "lr": 3.577235772357724e-05, "epoch": 0.44556962025316454, "percentage": 8.94, "elapsed_time": "2:26:32", "remaining_time": "1 day, 0:51:59"}
+{"current_steps": 111, "total_steps": 1230, "loss": 0.441, "lr": 3.609756097560976e-05, "epoch": 0.44962025316455695, "percentage": 9.02, "elapsed_time": "2:27:48", "remaining_time": "1 day, 0:50:07"}
+{"current_steps": 112, "total_steps": 1230, "loss": 0.4228, "lr": 3.642276422764228e-05, "epoch": 0.45367088607594935, "percentage": 9.11, "elapsed_time": "2:28:56", "remaining_time": "1 day, 0:46:46"}
+{"current_steps": 113, "total_steps": 1230, "loss": 0.4285, "lr": 3.67479674796748e-05, "epoch": 0.45772151898734176, "percentage": 9.19, "elapsed_time": "2:30:08", "remaining_time": "1 day, 0:44:13"}
+{"current_steps": 114, "total_steps": 1230, "loss": 0.4422, "lr": 3.7073170731707325e-05, "epoch": 0.46177215189873416, "percentage": 9.27, "elapsed_time": "2:31:26", "remaining_time": "1 day, 0:42:31"}
+{"current_steps": 115, "total_steps": 1230, "loss": 0.4256, "lr": 3.739837398373984e-05, "epoch": 0.46582278481012657, "percentage": 9.35, "elapsed_time": "2:32:34", "remaining_time": "1 day, 0:39:18"}
+{"current_steps": 116, "total_steps": 1230, "loss": 0.4125, "lr": 3.772357723577236e-05, "epoch": 0.46987341772151897, "percentage": 9.43, "elapsed_time": "2:33:43", "remaining_time": "1 day, 0:36:12"}
+{"current_steps": 117, "total_steps": 1230, "loss": 0.4547, "lr": 3.804878048780488e-05, "epoch": 0.4739240506329114, "percentage": 9.51, "elapsed_time": "2:34:53", "remaining_time": "1 day, 0:33:30"}
+{"current_steps": 118, "total_steps": 1230, "loss": 0.4191, "lr": 3.83739837398374e-05, "epoch": 0.4779746835443038, "percentage": 9.59, "elapsed_time": "2:35:53", "remaining_time": "1 day, 0:29:04"}
+{"current_steps": 119, "total_steps": 1230, "loss": 0.4049, "lr": 3.869918699186992e-05, "epoch": 0.4820253164556962, "percentage": 9.67, "elapsed_time": "2:36:53", "remaining_time": "1 day, 0:24:49"}
+{"current_steps": 120, "total_steps": 1230, "loss": 0.426, "lr": 3.9024390243902444e-05, "epoch": 0.4860759493670886, "percentage": 9.76, "elapsed_time": "2:38:06", "remaining_time": "1 day, 0:22:30"}
+{"current_steps": 121, "total_steps": 1230, "loss": 0.4244, "lr": 3.9349593495934966e-05, "epoch": 0.490126582278481, "percentage": 9.84, "elapsed_time": "2:39:25", "remaining_time": "1 day, 0:21:13"}
+{"current_steps": 122, "total_steps": 1230, "loss": 0.4207, "lr": 3.967479674796748e-05, "epoch": 0.4941772151898734, "percentage": 9.92, "elapsed_time": "2:40:34", "remaining_time": "1 day, 0:18:16"}
+{"current_steps": 123, "total_steps": 1230, "loss": 0.4113, "lr": 4e-05, "epoch": 0.4982278481012658, "percentage": 10.0, "elapsed_time": "2:41:33", "remaining_time": "1 day, 0:14:05"}
+{"current_steps": 124, "total_steps": 1230, "loss": 0.4372, "lr": 3.999991946137476e-05, "epoch": 0.5022784810126583, "percentage": 10.08, "elapsed_time": "2:42:36", "remaining_time": "1 day, 0:10:25"}
+{"current_steps": 125, "total_steps": 1230, "loss": 0.4347, "lr": 3.999967784614766e-05, "epoch": 0.5063291139240507, "percentage": 10.16, "elapsed_time": "2:43:47", "remaining_time": "1 day, 0:07:57"}
+{"current_steps": 126, "total_steps": 1230, "loss": 0.4365, "lr": 3.9999275156264656e-05, "epoch": 0.5103797468354431, "percentage": 10.24, "elapsed_time": "2:45:01", "remaining_time": "1 day, 0:05:55"}
+{"current_steps": 127, "total_steps": 1230, "loss": 0.4231, "lr": 3.999871139496895e-05, "epoch": 0.5144303797468355, "percentage": 10.33, "elapsed_time": "2:45:53", "remaining_time": "1 day, 0:00:50"}
+{"current_steps": 128, "total_steps": 1230, "loss": 0.3873, "lr": 3.9997986566800995e-05, "epoch": 0.5184810126582279, "percentage": 10.41, "elapsed_time": "2:46:48", "remaining_time": "23:56:02"}
+{"current_steps": 129, "total_steps": 1230, "loss": 0.4243, "lr": 3.999710067759846e-05, "epoch": 0.5225316455696203, "percentage": 10.49, "elapsed_time": "2:48:04", "remaining_time": "23:54:27"}
+{"current_steps": 130, "total_steps": 1230, "loss": 0.4269, "lr": 3.999605373449617e-05, "epoch": 0.5265822784810127, "percentage": 10.57, "elapsed_time": "2:49:12", "remaining_time": "23:51:49"}
+{"current_steps": 131, "total_steps": 1230, "loss": 0.4372, "lr": 3.9994845745926075e-05, "epoch": 0.5306329113924051, "percentage": 10.65, "elapsed_time": "2:50:21", "remaining_time": "23:49:13"}
+{"current_steps": 132, "total_steps": 1230, "loss": 0.4216, "lr": 3.999347672161713e-05, "epoch": 0.5346835443037975, "percentage": 10.73, "elapsed_time": "2:51:18", "remaining_time": "23:44:56"}
+{"current_steps": 133, "total_steps": 1230, "loss": 0.4245, "lr": 3.999194667259528e-05, "epoch": 0.5387341772151899, "percentage": 10.81, "elapsed_time": "2:52:28", "remaining_time": "23:42:38"}
+{"current_steps": 134, "total_steps": 1230, "loss": 0.4366, "lr": 3.999025561118334e-05, "epoch": 0.5427848101265823, "percentage": 10.89, "elapsed_time": "2:53:31", "remaining_time": "23:39:16"}
+{"current_steps": 135, "total_steps": 1230, "loss": 0.4451, "lr": 3.998840355100086e-05, "epoch": 0.5468354430379747, "percentage": 10.98, "elapsed_time": "2:54:49", "remaining_time": "23:38:05"}
+{"current_steps": 136, "total_steps": 1230, "loss": 0.4235, "lr": 3.998639050696409e-05, "epoch": 0.5508860759493671, "percentage": 11.06, "elapsed_time": "2:55:41", "remaining_time": "23:33:20"}
+{"current_steps": 137, "total_steps": 1230, "loss": 0.4154, "lr": 3.998421649528582e-05, "epoch": 0.5549367088607595, "percentage": 11.14, "elapsed_time": "2:56:41", "remaining_time": "23:29:37"}
+{"current_steps": 138, "total_steps": 1230, "loss": 0.4259, "lr": 3.9981881533475234e-05, "epoch": 0.5589873417721519, "percentage": 11.22, "elapsed_time": "2:57:48", "remaining_time": "23:26:59"}
+{"current_steps": 139, "total_steps": 1230, "loss": 0.4166, "lr": 3.997938564033779e-05, "epoch": 0.5630379746835443, "percentage": 11.3, "elapsed_time": "2:58:59", "remaining_time": "23:24:53"}
+{"current_steps": 140, "total_steps": 1230, "loss": 0.4247, "lr": 3.9976728835975064e-05, "epoch": 0.5670886075949367, "percentage": 11.38, "elapsed_time": "2:59:50", "remaining_time": "23:20:12"}
+{"current_steps": 141, "total_steps": 1230, "loss": 0.4065, "lr": 3.9973911141784605e-05, "epoch": 0.5711392405063291, "percentage": 11.46, "elapsed_time": "3:00:56", "remaining_time": "23:17:30"}
+{"current_steps": 142, "total_steps": 1230, "loss": 0.4142, "lr": 3.997093258045973e-05, "epoch": 0.5751898734177215, "percentage": 11.54, "elapsed_time": "3:02:12", "remaining_time": "23:16:02"}
+{"current_steps": 143, "total_steps": 1230, "loss": 0.4296, "lr": 3.996779317598936e-05, "epoch": 0.579240506329114, "percentage": 11.63, "elapsed_time": "3:03:22", "remaining_time": "23:13:52"}
+{"current_steps": 144, "total_steps": 1230, "loss": 0.426, "lr": 3.996449295365782e-05, "epoch": 0.5832911392405064, "percentage": 11.71, "elapsed_time": "3:04:24", "remaining_time": "23:10:46"}
+{"current_steps": 145, "total_steps": 1230, "loss": 0.4079, "lr": 3.996103194004467e-05, "epoch": 0.5873417721518988, "percentage": 11.79, "elapsed_time": "3:05:34", "remaining_time": "23:08:33"}
+{"current_steps": 146, "total_steps": 1230, "loss": 0.4221, "lr": 3.995741016302441e-05, "epoch": 0.5913924050632912, "percentage": 11.87, "elapsed_time": "3:06:55", "remaining_time": "23:07:52"}
+{"current_steps": 147, "total_steps": 1230, "loss": 0.4153, "lr": 3.9953627651766364e-05, "epoch": 0.5954430379746836, "percentage": 11.95, "elapsed_time": "3:08:05", "remaining_time": "23:05:47"}
+{"current_steps": 148, "total_steps": 1230, "loss": 0.4079, "lr": 3.9949684436734325e-05, "epoch": 0.599493670886076, "percentage": 12.03, "elapsed_time": "3:09:05", "remaining_time": "23:02:22"}
+{"current_steps": 149, "total_steps": 1230, "loss": 0.4238, "lr": 3.994558054968643e-05, "epoch": 0.6035443037974684, "percentage": 12.11, "elapsed_time": "3:10:20", "remaining_time": "23:00:56"}
+{"current_steps": 150, "total_steps": 1230, "loss": 0.4259, "lr": 3.994131602367481e-05, "epoch": 0.6075949367088608, "percentage": 12.2, "elapsed_time": "3:11:36", "remaining_time": "22:59:37"}
+{"current_steps": 151, "total_steps": 1230, "loss": 0.4262, "lr": 3.9936890893045376e-05, "epoch": 0.6116455696202532, "percentage": 12.28, "elapsed_time": "3:12:53", "remaining_time": "22:58:21"}
+{"current_steps": 152, "total_steps": 1230, "loss": 0.4335, "lr": 3.993230519343752e-05, "epoch": 0.6156962025316456, "percentage": 12.36, "elapsed_time": "3:14:08", "remaining_time": "22:56:51"}
+{"current_steps": 153, "total_steps": 1230, "loss": 0.4154, "lr": 3.992755896178383e-05, "epoch": 0.619746835443038, "percentage": 12.44, "elapsed_time": "3:15:14", "remaining_time": "22:54:19"}
+{"current_steps": 154, "total_steps": 1230, "loss": 0.412, "lr": 3.992265223630981e-05, "epoch": 0.6237974683544304, "percentage": 12.52, "elapsed_time": "3:16:19", "remaining_time": "22:51:42"}
+{"current_steps": 155, "total_steps": 1230, "loss": 0.4147, "lr": 3.991758505653355e-05, "epoch": 0.6278481012658228, "percentage": 12.6, "elapsed_time": "3:17:23", "remaining_time": "22:48:57"}
+{"current_steps": 156, "total_steps": 1230, "loss": 0.4105, "lr": 3.991235746326543e-05, "epoch": 0.6318987341772152, "percentage": 12.68, "elapsed_time": "3:18:36", "remaining_time": "22:47:20"}
+{"current_steps": 157, "total_steps": 1230, "loss": 0.3887, "lr": 3.9906969498607745e-05, "epoch": 0.6359493670886076, "percentage": 12.76, "elapsed_time": "3:19:47", "remaining_time": "22:45:29"}
+{"current_steps": 158, "total_steps": 1230, "loss": 0.42, "lr": 3.990142120595444e-05, "epoch": 0.64, "percentage": 12.85, "elapsed_time": "3:20:57", "remaining_time": "22:43:26"}
+{"current_steps": 159, "total_steps": 1230, "loss": 0.4278, "lr": 3.98957126299907e-05, "epoch": 0.6440506329113924, "percentage": 12.93, "elapsed_time": "3:22:07", "remaining_time": "22:41:30"}
+{"current_steps": 160, "total_steps": 1230, "loss": 0.4211, "lr": 3.9889843816692596e-05, "epoch": 0.6481012658227848, "percentage": 13.01, "elapsed_time": "3:23:11", "remaining_time": "22:38:50"}
+{"current_steps": 161, "total_steps": 1230, "loss": 0.4131, "lr": 3.9883814813326766e-05, "epoch": 0.6521518987341772, "percentage": 13.09, "elapsed_time": "3:24:10", "remaining_time": "22:35:38"}
+{"current_steps": 162, "total_steps": 1230, "loss": 0.4234, "lr": 3.9877625668449956e-05, "epoch": 0.6562025316455696, "percentage": 13.17, "elapsed_time": "3:25:34", "remaining_time": "22:35:16"}
+{"current_steps": 163, "total_steps": 1230, "loss": 0.404, "lr": 3.98712764319087e-05, "epoch": 0.660253164556962, "percentage": 13.25, "elapsed_time": "3:26:55", "remaining_time": "22:34:33"}
+{"current_steps": 164, "total_steps": 1230, "loss": 0.439, "lr": 3.9864767154838864e-05, "epoch": 0.6643037974683544, "percentage": 13.33, "elapsed_time": "3:28:00", "remaining_time": "22:32:02"}
+{"current_steps": 165, "total_steps": 1230, "loss": 0.4004, "lr": 3.9858097889665277e-05, "epoch": 0.6683544303797468, "percentage": 13.41, "elapsed_time": "3:29:17", "remaining_time": "22:30:50"}
+{"current_steps": 166, "total_steps": 1230, "loss": 0.4207, "lr": 3.985126869010129e-05, "epoch": 0.6724050632911392, "percentage": 13.5, "elapsed_time": "3:30:17", "remaining_time": "22:27:56"}
+{"current_steps": 167, "total_steps": 1230, "loss": 0.4186, "lr": 3.984427961114833e-05, "epoch": 0.6764556962025317, "percentage": 13.58, "elapsed_time": "3:31:31", "remaining_time": "22:26:23"}
+{"current_steps": 168, "total_steps": 1230, "loss": 0.4076, "lr": 3.9837130709095475e-05, "epoch": 0.6805063291139241, "percentage": 13.66, "elapsed_time": "3:32:34", "remaining_time": "22:23:46"}
+{"current_steps": 169, "total_steps": 1230, "loss": 0.4297, "lr": 3.982982204151901e-05, "epoch": 0.6845569620253165, "percentage": 13.74, "elapsed_time": "3:33:28", "remaining_time": "22:20:12"}
+{"current_steps": 170, "total_steps": 1230, "loss": 0.4003, "lr": 3.982235366728193e-05, "epoch": 0.6886075949367089, "percentage": 13.82, "elapsed_time": "3:34:27", "remaining_time": "22:17:11"}
+{"current_steps": 171, "total_steps": 1230, "loss": 0.4163, "lr": 3.9814725646533505e-05, "epoch": 0.6926582278481013, "percentage": 13.9, "elapsed_time": "3:35:47", "remaining_time": "22:16:25"}
+{"current_steps": 172, "total_steps": 1230, "loss": 0.4095, "lr": 3.9806938040708746e-05, "epoch": 0.6967088607594937, "percentage": 13.98, "elapsed_time": "3:36:56", "remaining_time": "22:14:26"}
+{"current_steps": 173, "total_steps": 1230, "loss": 0.4204, "lr": 3.9798990912527976e-05, "epoch": 0.7007594936708861, "percentage": 14.07, "elapsed_time": "3:37:47", "remaining_time": "22:10:38"}
+{"current_steps": 174, "total_steps": 1230, "loss": 0.425, "lr": 3.979088432599627e-05, "epoch": 0.7048101265822785, "percentage": 14.15, "elapsed_time": "3:38:51", "remaining_time": "22:08:13"}
+{"current_steps": 175, "total_steps": 1230, "loss": 0.4038, "lr": 3.9782618346402964e-05, "epoch": 0.7088607594936709, "percentage": 14.23, "elapsed_time": "3:40:02", "remaining_time": "22:06:30"}
+{"current_steps": 176, "total_steps": 1230, "loss": 0.3977, "lr": 3.977419304032111e-05, "epoch": 0.7129113924050633, "percentage": 14.31, "elapsed_time": "3:41:01", "remaining_time": "22:03:35"}
+{"current_steps": 177, "total_steps": 1230, "loss": 0.4266, "lr": 3.976560847560697e-05, "epoch": 0.7169620253164557, "percentage": 14.39, "elapsed_time": "3:42:01", "remaining_time": "22:00:52"}
+{"current_steps": 178, "total_steps": 1230, "loss": 0.4097, "lr": 3.9756864721399456e-05, "epoch": 0.7210126582278481, "percentage": 14.47, "elapsed_time": "3:43:08", "remaining_time": "21:58:47"}
+{"current_steps": 179, "total_steps": 1230, "loss": 0.3967, "lr": 3.974796184811956e-05, "epoch": 0.7250632911392405, "percentage": 14.55, "elapsed_time": "3:44:11", "remaining_time": "21:56:19"}
+{"current_steps": 180, "total_steps": 1230, "loss": 0.424, "lr": 3.973889992746979e-05, "epoch": 0.7291139240506329, "percentage": 14.63, "elapsed_time": "3:45:28", "remaining_time": "21:55:17"}
+{"current_steps": 181, "total_steps": 1230, "loss": 0.4169, "lr": 3.972967903243361e-05, "epoch": 0.7331645569620253, "percentage": 14.72, "elapsed_time": "3:46:47", "remaining_time": "21:54:23"}
+{"current_steps": 182, "total_steps": 1230, "loss": 0.4099, "lr": 3.972029923727486e-05, "epoch": 0.7372151898734177, "percentage": 14.8, "elapsed_time": "3:47:50", "remaining_time": "21:51:55"}
+{"current_steps": 183, "total_steps": 1230, "loss": 0.4033, "lr": 3.971076061753709e-05, "epoch": 0.7412658227848101, "percentage": 14.88, "elapsed_time": "3:48:55", "remaining_time": "21:49:47"}
+{"current_steps": 184, "total_steps": 1230, "loss": 0.4064, "lr": 3.9701063250043066e-05, "epoch": 0.7453164556962025, "percentage": 14.96, "elapsed_time": "3:50:03", "remaining_time": "21:47:50"}
+{"current_steps": 185, "total_steps": 1230, "loss": 0.4054, "lr": 3.969120721289402e-05, "epoch": 0.7493670886075949, "percentage": 15.04, "elapsed_time": "3:51:07", "remaining_time": "21:45:34"}
+{"current_steps": 186, "total_steps": 1230, "loss": 0.4031, "lr": 3.9681192585469146e-05, "epoch": 0.7534177215189873, "percentage": 15.12, "elapsed_time": "3:52:14", "remaining_time": "21:43:31"}
+{"current_steps": 187, "total_steps": 1230, "loss": 0.4213, "lr": 3.9671019448424865e-05, "epoch": 0.7574683544303797, "percentage": 15.2, "elapsed_time": "3:53:15", "remaining_time": "21:40:59"}
+{"current_steps": 188, "total_steps": 1230, "loss": 0.4355, "lr": 3.966068788369422e-05, "epoch": 0.7615189873417721, "percentage": 15.28, "elapsed_time": "3:54:41", "remaining_time": "21:40:47"}
+{"current_steps": 189, "total_steps": 1230, "loss": 0.4105, "lr": 3.965019797448622e-05, "epoch": 0.7655696202531646, "percentage": 15.37, "elapsed_time": "3:55:54", "remaining_time": "21:39:20"}
+{"current_steps": 190, "total_steps": 1230, "loss": 0.3944, "lr": 3.963954980528515e-05, "epoch": 0.769620253164557, "percentage": 15.45, "elapsed_time": "3:56:47", "remaining_time": "21:36:05"}
+{"current_steps": 191, "total_steps": 1230, "loss": 0.4137, "lr": 3.9628743461849905e-05, "epoch": 0.7736708860759494, "percentage": 15.53, "elapsed_time": "3:58:03", "remaining_time": "21:34:59"}
+{"current_steps": 192, "total_steps": 1230, "loss": 0.3873, "lr": 3.961777903121329e-05, "epoch": 0.7777215189873418, "percentage": 15.61, "elapsed_time": "3:59:06", "remaining_time": "21:32:39"}
+{"current_steps": 193, "total_steps": 1230, "loss": 0.4109, "lr": 3.960665660168131e-05, "epoch": 0.7817721518987342, "percentage": 15.69, "elapsed_time": "4:00:14", "remaining_time": "21:30:48"}
+{"current_steps": 194, "total_steps": 1230, "loss": 0.4078, "lr": 3.9595376262832485e-05, "epoch": 0.7858227848101266, "percentage": 15.77, "elapsed_time": "4:01:28", "remaining_time": "21:29:31"}
+{"current_steps": 195, "total_steps": 1230, "loss": 0.4101, "lr": 3.9583938105517127e-05, "epoch": 0.789873417721519, "percentage": 15.85, "elapsed_time": "4:02:42", "remaining_time": "21:28:13"}
+{"current_steps": 196, "total_steps": 1230, "loss": 0.4112, "lr": 3.957234222185657e-05, "epoch": 0.7939240506329114, "percentage": 15.93, "elapsed_time": "4:03:52", "remaining_time": "21:26:34"}
+{"current_steps": 197, "total_steps": 1230, "loss": 0.4036, "lr": 3.9560588705242474e-05, "epoch": 0.7979746835443038, "percentage": 16.02, "elapsed_time": "4:04:54", "remaining_time": "21:24:13"}
+{"current_steps": 198, "total_steps": 1230, "loss": 0.4002, "lr": 3.954867765033605e-05, "epoch": 0.8020253164556962, "percentage": 16.1, "elapsed_time": "4:05:39", "remaining_time": "21:20:24"}
+{"current_steps": 199, "total_steps": 1230, "loss": 0.4151, "lr": 3.953660915306728e-05, "epoch": 0.8060759493670886, "percentage": 16.18, "elapsed_time": "4:06:47", "remaining_time": "21:18:34"}
+{"current_steps": 200, "total_steps": 1230, "loss": 0.3975, "lr": 3.952438331063419e-05, "epoch": 0.810126582278481, "percentage": 16.26, "elapsed_time": "4:07:43", "remaining_time": "21:15:48"}
+{"current_steps": 201, "total_steps": 1230, "loss": 0.4223, "lr": 3.951200022150205e-05, "epoch": 0.8141772151898734, "percentage": 16.34, "elapsed_time": "4:08:35", "remaining_time": "21:12:40"}
+{"current_steps": 202, "total_steps": 1230, "loss": 0.3972, "lr": 3.949945998540253e-05, "epoch": 0.8182278481012658, "percentage": 16.42, "elapsed_time": "4:09:43", "remaining_time": "21:10:50"}
+{"current_steps": 203, "total_steps": 1230, "loss": 0.4171, "lr": 3.9486762703332993e-05, "epoch": 0.8222784810126582, "percentage": 16.5, "elapsed_time": "4:10:49", "remaining_time": "21:08:54"}
+{"current_steps": 204, "total_steps": 1230, "loss": 0.3978, "lr": 3.947390847755559e-05, "epoch": 0.8263291139240506, "percentage": 16.59, "elapsed_time": "4:11:49", "remaining_time": "21:06:31"}
+{"current_steps": 205, "total_steps": 1230, "loss": 0.4009, "lr": 3.946089741159648e-05, "epoch": 0.830379746835443, "percentage": 16.67, "elapsed_time": "4:12:59", "remaining_time": "21:04:57"}
+{"current_steps": 206, "total_steps": 1230, "loss": 0.4242, "lr": 3.944772961024501e-05, "epoch": 0.8344303797468354, "percentage": 16.75, "elapsed_time": "4:14:02", "remaining_time": "21:02:47"}
+{"current_steps": 207, "total_steps": 1230, "loss": 0.4051, "lr": 3.943440517955285e-05, "epoch": 0.8384810126582278, "percentage": 16.83, "elapsed_time": "4:15:35", "remaining_time": "21:03:08"}
+{"current_steps": 208, "total_steps": 1230, "loss": 0.3983, "lr": 3.9420924226833126e-05, "epoch": 0.8425316455696202, "percentage": 16.91, "elapsed_time": "4:16:49", "remaining_time": "21:01:54"}
+{"current_steps": 209, "total_steps": 1230, "loss": 0.4078, "lr": 3.9407286860659566e-05, "epoch": 0.8465822784810126, "percentage": 16.99, "elapsed_time": "4:18:03", "remaining_time": "21:00:41"}
+{"current_steps": 210, "total_steps": 1230, "loss": 0.4181, "lr": 3.9393493190865657e-05, "epoch": 0.850632911392405, "percentage": 17.07, "elapsed_time": "4:19:16", "remaining_time": "20:59:22"}
+{"current_steps": 211, "total_steps": 1230, "loss": 0.4031, "lr": 3.937954332854371e-05, "epoch": 0.8546835443037974, "percentage": 17.15, "elapsed_time": "4:20:15", "remaining_time": "20:56:54"}
+{"current_steps": 212, "total_steps": 1230, "loss": 0.403, "lr": 3.9365437386044016e-05, "epoch": 0.8587341772151899, "percentage": 17.24, "elapsed_time": "4:21:05", "remaining_time": "20:53:42"}
+{"current_steps": 213, "total_steps": 1230, "loss": 0.3903, "lr": 3.935117547697387e-05, "epoch": 0.8627848101265823, "percentage": 17.32, "elapsed_time": "4:22:10", "remaining_time": "20:51:45"}
+{"current_steps": 214, "total_steps": 1230, "loss": 0.4069, "lr": 3.933675771619675e-05, "epoch": 0.8668354430379747, "percentage": 17.4, "elapsed_time": "4:23:26", "remaining_time": "20:50:46"}
+{"current_steps": 215, "total_steps": 1230, "loss": 0.4186, "lr": 3.932218421983131e-05, "epoch": 0.8708860759493671, "percentage": 17.48, "elapsed_time": "4:24:26", "remaining_time": "20:48:25"}
+{"current_steps": 216, "total_steps": 1230, "loss": 0.4203, "lr": 3.9307455105250484e-05, "epoch": 0.8749367088607595, "percentage": 17.56, "elapsed_time": "4:25:42", "remaining_time": "20:47:23"}
+{"current_steps": 217, "total_steps": 1230, "loss": 0.415, "lr": 3.929257049108054e-05, "epoch": 0.8789873417721519, "percentage": 17.64, "elapsed_time": "4:26:50", "remaining_time": "20:45:39"}
+{"current_steps": 218, "total_steps": 1230, "loss": 0.4049, "lr": 3.927753049720011e-05, "epoch": 0.8830379746835443, "percentage": 17.72, "elapsed_time": "4:28:01", "remaining_time": "20:44:13"}
+{"current_steps": 219, "total_steps": 1230, "loss": 0.4093, "lr": 3.9262335244739234e-05, "epoch": 0.8870886075949367, "percentage": 17.8, "elapsed_time": "4:29:15", "remaining_time": "20:43:02"}
+{"current_steps": 220, "total_steps": 1230, "loss": 0.4096, "lr": 3.92469848560784e-05, "epoch": 0.8911392405063291, "percentage": 17.89, "elapsed_time": "4:30:12", "remaining_time": "20:40:29"}
+{"current_steps": 221, "total_steps": 1230, "loss": 0.4225, "lr": 3.923147945484751e-05, "epoch": 0.8951898734177215, "percentage": 17.97, "elapsed_time": "4:31:27", "remaining_time": "20:39:23"}
+{"current_steps": 222, "total_steps": 1230, "loss": 0.4, "lr": 3.9215819165924956e-05, "epoch": 0.8992405063291139, "percentage": 18.05, "elapsed_time": "4:32:42", "remaining_time": "20:38:13"}
+{"current_steps": 223, "total_steps": 1230, "loss": 0.4507, "lr": 3.920000411543654e-05, "epoch": 0.9032911392405063, "percentage": 18.13, "elapsed_time": "4:33:33", "remaining_time": "20:35:19"}
+{"current_steps": 224, "total_steps": 1230, "loss": 0.4149, "lr": 3.9184034430754495e-05, "epoch": 0.9073417721518987, "percentage": 18.21, "elapsed_time": "4:34:57", "remaining_time": "20:34:51"}
+{"current_steps": 225, "total_steps": 1230, "loss": 0.4001, "lr": 3.916791024049648e-05, "epoch": 0.9113924050632911, "percentage": 18.29, "elapsed_time": "4:36:08", "remaining_time": "20:33:27"}
+{"current_steps": 226, "total_steps": 1230, "loss": 0.4135, "lr": 3.91516316745245e-05, "epoch": 0.9154430379746835, "percentage": 18.37, "elapsed_time": "4:37:18", "remaining_time": "20:31:55"}
+{"current_steps": 227, "total_steps": 1230, "loss": 0.4095, "lr": 3.913519886394389e-05, "epoch": 0.9194936708860759, "percentage": 18.46, "elapsed_time": "4:38:20", "remaining_time": "20:29:51"}
+{"current_steps": 228, "total_steps": 1230, "loss": 0.3941, "lr": 3.911861194110225e-05, "epoch": 0.9235443037974683, "percentage": 18.54, "elapsed_time": "4:39:22", "remaining_time": "20:27:48"}
+{"current_steps": 229, "total_steps": 1230, "loss": 0.4111, "lr": 3.910187103958837e-05, "epoch": 0.9275949367088607, "percentage": 18.62, "elapsed_time": "4:40:46", "remaining_time": "20:27:21"}
+{"current_steps": 230, "total_steps": 1230, "loss": 0.3991, "lr": 3.908497629423117e-05, "epoch": 0.9316455696202531, "percentage": 18.7, "elapsed_time": "4:41:43", "remaining_time": "20:24:51"}
+{"current_steps": 231, "total_steps": 1230, "loss": 0.3852, "lr": 3.9067927841098614e-05, "epoch": 0.9356962025316455, "percentage": 18.78, "elapsed_time": "4:42:40", "remaining_time": "20:22:29"}
+{"current_steps": 232, "total_steps": 1230, "loss": 0.4085, "lr": 3.9050725817496594e-05, "epoch": 0.9397468354430379, "percentage": 18.86, "elapsed_time": "4:43:57", "remaining_time": "20:21:29"}
+{"current_steps": 233, "total_steps": 1230, "loss": 0.392, "lr": 3.9033370361967844e-05, "epoch": 0.9437974683544303, "percentage": 18.94, "elapsed_time": "4:45:10", "remaining_time": "20:20:14"}
+{"current_steps": 234, "total_steps": 1230, "loss": 0.4197, "lr": 3.901586161429081e-05, "epoch": 0.9478481012658228, "percentage": 19.02, "elapsed_time": "4:46:43", "remaining_time": "20:20:26"}
+{"current_steps": 235, "total_steps": 1230, "loss": 0.4179, "lr": 3.8998199715478545e-05, "epoch": 0.9518987341772152, "percentage": 19.11, "elapsed_time": "4:47:59", "remaining_time": "20:19:24"}
+{"current_steps": 236, "total_steps": 1230, "loss": 0.3934, "lr": 3.8980384807777564e-05, "epoch": 0.9559493670886076, "percentage": 19.19, "elapsed_time": "4:48:56", "remaining_time": "20:16:59"}
+{"current_steps": 237, "total_steps": 1230, "loss": 0.4041, "lr": 3.896241703466667e-05, "epoch": 0.96, "percentage": 19.27, "elapsed_time": "4:50:06", "remaining_time": "20:15:29"}
+{"current_steps": 238, "total_steps": 1230, "loss": 0.4143, "lr": 3.894429654085585e-05, "epoch": 0.9640506329113924, "percentage": 19.35, "elapsed_time": "4:51:14", "remaining_time": "20:13:55"}
+{"current_steps": 239, "total_steps": 1230, "loss": 0.3912, "lr": 3.892602347228505e-05, "epoch": 0.9681012658227848, "percentage": 19.43, "elapsed_time": "4:52:09", "remaining_time": "20:11:24"}
+{"current_steps": 240, "total_steps": 1230, "loss": 0.4109, "lr": 3.890759797612307e-05, "epoch": 0.9721518987341772, "percentage": 19.51, "elapsed_time": "4:53:19", "remaining_time": "20:09:59"}
+{"current_steps": 241, "total_steps": 1230, "loss": 0.3888, "lr": 3.888902020076632e-05, "epoch": 0.9762025316455696, "percentage": 19.59, "elapsed_time": "4:54:27", "remaining_time": "20:08:22"}
+{"current_steps": 242, "total_steps": 1230, "loss": 0.3995, "lr": 3.887029029583764e-05, "epoch": 0.980253164556962, "percentage": 19.67, "elapsed_time": "4:55:33", "remaining_time": "20:06:39"}
+{"current_steps": 243, "total_steps": 1230, "loss": 0.3839, "lr": 3.8851408412185125e-05, "epoch": 0.9843037974683544, "percentage": 19.76, "elapsed_time": "4:56:45", "remaining_time": "20:05:19"}
+{"current_steps": 244, "total_steps": 1230, "loss": 0.3979, "lr": 3.8832374701880855e-05, "epoch": 0.9883544303797468, "percentage": 19.84, "elapsed_time": "4:57:42", "remaining_time": "20:03:03"}
+{"current_steps": 245, "total_steps": 1230, "loss": 0.4094, "lr": 3.881318931821972e-05, "epoch": 0.9924050632911392, "percentage": 19.92, "elapsed_time": "4:58:52", "remaining_time": "20:01:36"}
+{"current_steps": 246, "total_steps": 1230, "loss": 0.4024, "lr": 3.879385241571817e-05, "epoch": 0.9964556962025316, "percentage": 20.0, "elapsed_time": "5:00:06", "remaining_time": "20:00:26"}
+{"current_steps": 247, "total_steps": 1230, "loss": 0.3885, "lr": 3.8774364150112955e-05, "epoch": 1.0020253164556963, "percentage": 20.08, "elapsed_time": "5:03:03", "remaining_time": "20:06:04"}
+{"current_steps": 248, "total_steps": 1230, "loss": 0.325, "lr": 3.8754724678359884e-05, "epoch": 1.0060759493670886, "percentage": 20.16, "elapsed_time": "5:04:01", "remaining_time": "20:03:51"}
+{"current_steps": 249, "total_steps": 1230, "loss": 0.3405, "lr": 3.873493415863256e-05, "epoch": 1.010126582278481, "percentage": 20.24, "elapsed_time": "5:05:03", "remaining_time": "20:01:49"}
+{"current_steps": 250, "total_steps": 1230, "loss": 0.3313, "lr": 3.871499275032111e-05, "epoch": 1.0141772151898734, "percentage": 20.33, "elapsed_time": "5:06:17", "remaining_time": "20:00:38"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f562b61c8e416b108fa44160f4a4096a978399bec81938dbfc18c563ced1c60
+size 7352