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:cfa56e923b13e9fe82d956e0c791640e673e470bc6730c65ecd16fe284fa0584
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa90ebcab9e06320b2f2d3256356d33367ca2264848a6a7aec8b28f159f8ef21
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29573f88e439a37502752fc094cda57af629fb2facd2c83e56fc678d8ee18222
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c952ff633b3c1558e36f2751e8fe15681ccd4721e9f57125c8980cdd4a89378a
+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 +1,238 @@
+{"current_steps": 1, "total_steps": 1170, "loss": 0.8544, "lr": 3.4188034188034194e-07, "epoch": 0.0042643923240938165, "percentage": 0.09, "elapsed_time": "0:00:47", "remaining_time": "15:28:20"}
+{"current_steps": 2, "total_steps": 1170, "loss": 0.8386, "lr": 6.837606837606839e-07, "epoch": 0.008528784648187633, "percentage": 0.17, "elapsed_time": "0:01:24", "remaining_time": "13:46:20"}
+{"current_steps": 3, "total_steps": 1170, "loss": 0.884, "lr": 1.0256410256410257e-06, "epoch": 0.01279317697228145, "percentage": 0.26, "elapsed_time": "0:02:08", "remaining_time": "13:54:54"}
+{"current_steps": 4, "total_steps": 1170, "loss": 0.8563, "lr": 1.3675213675213678e-06, "epoch": 0.017057569296375266, "percentage": 0.34, "elapsed_time": "0:02:50", "remaining_time": "13:47:49"}
+{"current_steps": 5, "total_steps": 1170, "loss": 0.852, "lr": 1.7094017094017097e-06, "epoch": 0.021321961620469083, "percentage": 0.43, "elapsed_time": "0:03:30", "remaining_time": "13:37:05"}
+{"current_steps": 6, "total_steps": 1170, "loss": 0.8753, "lr": 2.0512820512820513e-06, "epoch": 0.0255863539445629, "percentage": 0.51, "elapsed_time": "0:04:13", "remaining_time": "13:40:23"}
+{"current_steps": 7, "total_steps": 1170, "loss": 0.8191, "lr": 2.3931623931623937e-06, "epoch": 0.029850746268656716, "percentage": 0.6, "elapsed_time": "0:04:56", "remaining_time": "13:40:41"}
+{"current_steps": 8, "total_steps": 1170, "loss": 0.7877, "lr": 2.7350427350427355e-06, "epoch": 0.03411513859275053, "percentage": 0.68, "elapsed_time": "0:05:37", "remaining_time": "13:38:08"}
+{"current_steps": 9, "total_steps": 1170, "loss": 0.8057, "lr": 3.0769230769230774e-06, "epoch": 0.03837953091684435, "percentage": 0.77, "elapsed_time": "0:06:21", "remaining_time": "13:39:38"}
+{"current_steps": 10, "total_steps": 1170, "loss": 0.7537, "lr": 3.4188034188034193e-06, "epoch": 0.042643923240938165, "percentage": 0.85, "elapsed_time": "0:07:04", "remaining_time": "13:41:29"}
+{"current_steps": 11, "total_steps": 1170, "loss": 0.7445, "lr": 3.760683760683761e-06, "epoch": 0.046908315565031986, "percentage": 0.94, "elapsed_time": "0:07:49", "remaining_time": "13:44:28"}
+{"current_steps": 12, "total_steps": 1170, "loss": 0.7596, "lr": 4.102564102564103e-06, "epoch": 0.0511727078891258, "percentage": 1.03, "elapsed_time": "0:08:33", "remaining_time": "13:46:11"}
+{"current_steps": 13, "total_steps": 1170, "loss": 0.7396, "lr": 4.444444444444444e-06, "epoch": 0.05543710021321962, "percentage": 1.11, "elapsed_time": "0:09:13", "remaining_time": "13:40:24"}
+{"current_steps": 14, "total_steps": 1170, "loss": 0.7307, "lr": 4.786324786324787e-06, "epoch": 0.05970149253731343, "percentage": 1.2, "elapsed_time": "0:10:00", "remaining_time": "13:46:27"}
+{"current_steps": 15, "total_steps": 1170, "loss": 0.7104, "lr": 5.128205128205128e-06, "epoch": 0.06396588486140725, "percentage": 1.28, "elapsed_time": "0:10:39", "remaining_time": "13:41:05"}
+{"current_steps": 16, "total_steps": 1170, "loss": 0.6875, "lr": 5.470085470085471e-06, "epoch": 0.06823027718550106, "percentage": 1.37, "elapsed_time": "0:11:27", "remaining_time": "13:46:34"}
+{"current_steps": 17, "total_steps": 1170, "loss": 0.6755, "lr": 5.8119658119658126e-06, "epoch": 0.07249466950959488, "percentage": 1.45, "elapsed_time": "0:12:10", "remaining_time": "13:45:21"}
+{"current_steps": 18, "total_steps": 1170, "loss": 0.6897, "lr": 6.153846153846155e-06, "epoch": 0.0767590618336887, "percentage": 1.54, "elapsed_time": "0:12:51", "remaining_time": "13:42:35"}
+{"current_steps": 19, "total_steps": 1170, "loss": 0.6613, "lr": 6.495726495726496e-06, "epoch": 0.08102345415778252, "percentage": 1.62, "elapsed_time": "0:13:33", "remaining_time": "13:40:55"}
+{"current_steps": 20, "total_steps": 1170, "loss": 0.6393, "lr": 6.837606837606839e-06, "epoch": 0.08528784648187633, "percentage": 1.71, "elapsed_time": "0:14:14", "remaining_time": "13:39:05"}
+{"current_steps": 21, "total_steps": 1170, "loss": 0.6399, "lr": 7.17948717948718e-06, "epoch": 0.08955223880597014, "percentage": 1.79, "elapsed_time": "0:14:57", "remaining_time": "13:38:41"}
+{"current_steps": 22, "total_steps": 1170, "loss": 0.6195, "lr": 7.521367521367522e-06, "epoch": 0.09381663113006397, "percentage": 1.88, "elapsed_time": "0:15:45", "remaining_time": "13:42:23"}
+{"current_steps": 23, "total_steps": 1170, "loss": 0.6235, "lr": 7.863247863247863e-06, "epoch": 0.09808102345415778, "percentage": 1.97, "elapsed_time": "0:16:29", "remaining_time": "13:42:30"}
+{"current_steps": 24, "total_steps": 1170, "loss": 0.6236, "lr": 8.205128205128205e-06, "epoch": 0.1023454157782516, "percentage": 2.05, "elapsed_time": "0:17:11", "remaining_time": "13:40:37"}
+{"current_steps": 25, "total_steps": 1170, "loss": 0.6317, "lr": 8.547008547008548e-06, "epoch": 0.10660980810234541, "percentage": 2.14, "elapsed_time": "0:17:52", "remaining_time": "13:38:33"}
+{"current_steps": 26, "total_steps": 1170, "loss": 0.6061, "lr": 8.888888888888888e-06, "epoch": 0.11087420042643924, "percentage": 2.22, "elapsed_time": "0:18:36", "remaining_time": "13:38:49"}
+{"current_steps": 27, "total_steps": 1170, "loss": 0.6225, "lr": 9.230769230769232e-06, "epoch": 0.11513859275053305, "percentage": 2.31, "elapsed_time": "0:19:20", "remaining_time": "13:38:40"}
+{"current_steps": 28, "total_steps": 1170, "loss": 0.5981, "lr": 9.572649572649575e-06, "epoch": 0.11940298507462686, "percentage": 2.39, "elapsed_time": "0:20:01", "remaining_time": "13:36:34"}
+{"current_steps": 29, "total_steps": 1170, "loss": 0.5908, "lr": 9.914529914529915e-06, "epoch": 0.12366737739872068, "percentage": 2.48, "elapsed_time": "0:20:42", "remaining_time": "13:34:33"}
+{"current_steps": 30, "total_steps": 1170, "loss": 0.5978, "lr": 1.0256410256410256e-05, "epoch": 0.1279317697228145, "percentage": 2.56, "elapsed_time": "0:21:25", "remaining_time": "13:33:54"}
+{"current_steps": 31, "total_steps": 1170, "loss": 0.5638, "lr": 1.05982905982906e-05, "epoch": 0.13219616204690832, "percentage": 2.65, "elapsed_time": "0:22:11", "remaining_time": "13:35:32"}
+{"current_steps": 32, "total_steps": 1170, "loss": 0.5913, "lr": 1.0940170940170942e-05, "epoch": 0.13646055437100213, "percentage": 2.74, "elapsed_time": "0:22:55", "remaining_time": "13:35:21"}
+{"current_steps": 33, "total_steps": 1170, "loss": 0.6077, "lr": 1.1282051282051283e-05, "epoch": 0.14072494669509594, "percentage": 2.82, "elapsed_time": "0:23:38", "remaining_time": "13:34:23"}
+{"current_steps": 34, "total_steps": 1170, "loss": 0.5749, "lr": 1.1623931623931625e-05, "epoch": 0.14498933901918976, "percentage": 2.91, "elapsed_time": "0:24:19", "remaining_time": "13:32:40"}
+{"current_steps": 35, "total_steps": 1170, "loss": 0.5503, "lr": 1.1965811965811966e-05, "epoch": 0.14925373134328357, "percentage": 2.99, "elapsed_time": "0:25:02", "remaining_time": "13:32:18"}
+{"current_steps": 36, "total_steps": 1170, "loss": 0.5765, "lr": 1.230769230769231e-05, "epoch": 0.1535181236673774, "percentage": 3.08, "elapsed_time": "0:25:41", "remaining_time": "13:29:28"}
+{"current_steps": 37, "total_steps": 1170, "loss": 0.5592, "lr": 1.264957264957265e-05, "epoch": 0.15778251599147122, "percentage": 3.16, "elapsed_time": "0:26:26", "remaining_time": "13:29:30"}
+{"current_steps": 38, "total_steps": 1170, "loss": 0.553, "lr": 1.2991452991452993e-05, "epoch": 0.16204690831556504, "percentage": 3.25, "elapsed_time": "0:27:03", "remaining_time": "13:26:17"}
+{"current_steps": 39, "total_steps": 1170, "loss": 0.5866, "lr": 1.3333333333333333e-05, "epoch": 0.16631130063965885, "percentage": 3.33, "elapsed_time": "0:27:46", "remaining_time": "13:25:22"}
+{"current_steps": 40, "total_steps": 1170, "loss": 0.5439, "lr": 1.3675213675213677e-05, "epoch": 0.17057569296375266, "percentage": 3.42, "elapsed_time": "0:28:16", "remaining_time": "13:18:58"}
+{"current_steps": 41, "total_steps": 1170, "loss": 0.5702, "lr": 1.4017094017094018e-05, "epoch": 0.17484008528784648, "percentage": 3.5, "elapsed_time": "0:29:01", "remaining_time": "13:19:15"}
+{"current_steps": 42, "total_steps": 1170, "loss": 0.5709, "lr": 1.435897435897436e-05, "epoch": 0.1791044776119403, "percentage": 3.59, "elapsed_time": "0:29:42", "remaining_time": "13:18:03"}
+{"current_steps": 43, "total_steps": 1170, "loss": 0.5607, "lr": 1.4700854700854703e-05, "epoch": 0.18336886993603413, "percentage": 3.68, "elapsed_time": "0:30:18", "remaining_time": "13:14:30"}
+{"current_steps": 44, "total_steps": 1170, "loss": 0.591, "lr": 1.5042735042735043e-05, "epoch": 0.18763326226012794, "percentage": 3.76, "elapsed_time": "0:31:01", "remaining_time": "13:14:06"}
+{"current_steps": 45, "total_steps": 1170, "loss": 0.557, "lr": 1.5384615384615387e-05, "epoch": 0.19189765458422176, "percentage": 3.85, "elapsed_time": "0:31:44", "remaining_time": "13:13:44"}
+{"current_steps": 46, "total_steps": 1170, "loss": 0.5436, "lr": 1.5726495726495726e-05, "epoch": 0.19616204690831557, "percentage": 3.93, "elapsed_time": "0:32:22", "remaining_time": "13:11:00"}
+{"current_steps": 47, "total_steps": 1170, "loss": 0.5555, "lr": 1.6068376068376072e-05, "epoch": 0.20042643923240938, "percentage": 4.02, "elapsed_time": "0:33:03", "remaining_time": "13:09:42"}
+{"current_steps": 48, "total_steps": 1170, "loss": 0.5219, "lr": 1.641025641025641e-05, "epoch": 0.2046908315565032, "percentage": 4.1, "elapsed_time": "0:33:46", "remaining_time": "13:09:32"}
+{"current_steps": 49, "total_steps": 1170, "loss": 0.5316, "lr": 1.6752136752136753e-05, "epoch": 0.208955223880597, "percentage": 4.19, "elapsed_time": "0:34:27", "remaining_time": "13:08:23"}
+{"current_steps": 50, "total_steps": 1170, "loss": 0.5806, "lr": 1.7094017094017095e-05, "epoch": 0.21321961620469082, "percentage": 4.27, "elapsed_time": "0:35:10", "remaining_time": "13:07:47"}
+{"current_steps": 51, "total_steps": 1170, "loss": 0.5119, "lr": 1.7435897435897438e-05, "epoch": 0.21748400852878466, "percentage": 4.36, "elapsed_time": "0:35:52", "remaining_time": "13:07:09"}
+{"current_steps": 52, "total_steps": 1170, "loss": 0.5427, "lr": 1.7777777777777777e-05, "epoch": 0.22174840085287847, "percentage": 4.44, "elapsed_time": "0:36:30", "remaining_time": "13:05:05"}
+{"current_steps": 53, "total_steps": 1170, "loss": 0.5113, "lr": 1.8119658119658122e-05, "epoch": 0.2260127931769723, "percentage": 4.53, "elapsed_time": "0:37:09", "remaining_time": "13:03:08"}
+{"current_steps": 54, "total_steps": 1170, "loss": 0.5527, "lr": 1.8461538461538465e-05, "epoch": 0.2302771855010661, "percentage": 4.62, "elapsed_time": "0:37:45", "remaining_time": "13:00:28"}
+{"current_steps": 55, "total_steps": 1170, "loss": 0.5293, "lr": 1.8803418803418804e-05, "epoch": 0.2345415778251599, "percentage": 4.7, "elapsed_time": "0:38:31", "remaining_time": "13:00:53"}
+{"current_steps": 56, "total_steps": 1170, "loss": 0.5365, "lr": 1.914529914529915e-05, "epoch": 0.23880597014925373, "percentage": 4.79, "elapsed_time": "0:39:09", "remaining_time": "12:58:48"}
+{"current_steps": 57, "total_steps": 1170, "loss": 0.5159, "lr": 1.9487179487179488e-05, "epoch": 0.24307036247334754, "percentage": 4.87, "elapsed_time": "0:39:47", "remaining_time": "12:56:52"}
+{"current_steps": 58, "total_steps": 1170, "loss": 0.5579, "lr": 1.982905982905983e-05, "epoch": 0.24733475479744135, "percentage": 4.96, "elapsed_time": "0:40:35", "remaining_time": "12:58:07"}
+{"current_steps": 59, "total_steps": 1170, "loss": 0.5227, "lr": 2.0170940170940173e-05, "epoch": 0.2515991471215352, "percentage": 5.04, "elapsed_time": "0:41:10", "remaining_time": "12:55:25"}
+{"current_steps": 60, "total_steps": 1170, "loss": 0.5242, "lr": 2.0512820512820512e-05, "epoch": 0.255863539445629, "percentage": 5.13, "elapsed_time": "0:41:55", "remaining_time": "12:55:34"}
+{"current_steps": 61, "total_steps": 1170, "loss": 0.4985, "lr": 2.0854700854700857e-05, "epoch": 0.2601279317697228, "percentage": 5.21, "elapsed_time": "0:42:37", "remaining_time": "12:54:53"}
+{"current_steps": 62, "total_steps": 1170, "loss": 0.5361, "lr": 2.11965811965812e-05, "epoch": 0.26439232409381663, "percentage": 5.3, "elapsed_time": "0:43:22", "remaining_time": "12:55:03"}
+{"current_steps": 63, "total_steps": 1170, "loss": 0.5278, "lr": 2.153846153846154e-05, "epoch": 0.26865671641791045, "percentage": 5.38, "elapsed_time": "0:44:01", "remaining_time": "12:53:38"}
+{"current_steps": 64, "total_steps": 1170, "loss": 0.5544, "lr": 2.1880341880341884e-05, "epoch": 0.27292110874200426, "percentage": 5.47, "elapsed_time": "0:44:39", "remaining_time": "12:51:50"}
+{"current_steps": 65, "total_steps": 1170, "loss": 0.5345, "lr": 2.2222222222222227e-05, "epoch": 0.2771855010660981, "percentage": 5.56, "elapsed_time": "0:45:16", "remaining_time": "12:49:45"}
+{"current_steps": 66, "total_steps": 1170, "loss": 0.494, "lr": 2.2564102564102566e-05, "epoch": 0.2814498933901919, "percentage": 5.64, "elapsed_time": "0:46:00", "remaining_time": "12:49:36"}
+{"current_steps": 67, "total_steps": 1170, "loss": 0.508, "lr": 2.2905982905982908e-05, "epoch": 0.2857142857142857, "percentage": 5.73, "elapsed_time": "0:46:46", "remaining_time": "12:49:55"}
+{"current_steps": 68, "total_steps": 1170, "loss": 0.541, "lr": 2.324786324786325e-05, "epoch": 0.2899786780383795, "percentage": 5.81, "elapsed_time": "0:47:29", "remaining_time": "12:49:35"}
+{"current_steps": 69, "total_steps": 1170, "loss": 0.511, "lr": 2.3589743589743593e-05, "epoch": 0.2942430703624733, "percentage": 5.9, "elapsed_time": "0:48:12", "remaining_time": "12:49:19"}
+{"current_steps": 70, "total_steps": 1170, "loss": 0.5069, "lr": 2.393162393162393e-05, "epoch": 0.29850746268656714, "percentage": 5.98, "elapsed_time": "0:48:51", "remaining_time": "12:47:40"}
+{"current_steps": 71, "total_steps": 1170, "loss": 0.5029, "lr": 2.4273504273504274e-05, "epoch": 0.302771855010661, "percentage": 6.07, "elapsed_time": "0:49:21", "remaining_time": "12:43:56"}
+{"current_steps": 72, "total_steps": 1170, "loss": 0.5145, "lr": 2.461538461538462e-05, "epoch": 0.3070362473347548, "percentage": 6.15, "elapsed_time": "0:50:03", "remaining_time": "12:43:24"}
+{"current_steps": 73, "total_steps": 1170, "loss": 0.5213, "lr": 2.495726495726496e-05, "epoch": 0.31130063965884863, "percentage": 6.24, "elapsed_time": "0:50:45", "remaining_time": "12:42:52"}
+{"current_steps": 74, "total_steps": 1170, "loss": 0.5092, "lr": 2.52991452991453e-05, "epoch": 0.31556503198294245, "percentage": 6.32, "elapsed_time": "0:51:24", "remaining_time": "12:41:25"}
+{"current_steps": 75, "total_steps": 1170, "loss": 0.5408, "lr": 2.5641025641025646e-05, "epoch": 0.31982942430703626, "percentage": 6.41, "elapsed_time": "0:52:09", "remaining_time": "12:41:26"}
+{"current_steps": 76, "total_steps": 1170, "loss": 0.5693, "lr": 2.5982905982905985e-05, "epoch": 0.32409381663113007, "percentage": 6.5, "elapsed_time": "0:52:52", "remaining_time": "12:41:01"}
+{"current_steps": 77, "total_steps": 1170, "loss": 0.5214, "lr": 2.6324786324786328e-05, "epoch": 0.3283582089552239, "percentage": 6.58, "elapsed_time": "0:53:37", "remaining_time": "12:41:13"}
+{"current_steps": 78, "total_steps": 1170, "loss": 0.5414, "lr": 2.6666666666666667e-05, "epoch": 0.3326226012793177, "percentage": 6.67, "elapsed_time": "0:54:22", "remaining_time": "12:41:09"}
+{"current_steps": 79, "total_steps": 1170, "loss": 0.523, "lr": 2.7008547008547012e-05, "epoch": 0.3368869936034115, "percentage": 6.75, "elapsed_time": "0:55:01", "remaining_time": "12:39:50"}
+{"current_steps": 80, "total_steps": 1170, "loss": 0.5305, "lr": 2.7350427350427355e-05, "epoch": 0.3411513859275053, "percentage": 6.84, "elapsed_time": "0:55:44", "remaining_time": "12:39:33"}
+{"current_steps": 81, "total_steps": 1170, "loss": 0.5179, "lr": 2.7692307692307694e-05, "epoch": 0.34541577825159914, "percentage": 6.92, "elapsed_time": "0:56:32", "remaining_time": "12:40:13"}
+{"current_steps": 82, "total_steps": 1170, "loss": 0.533, "lr": 2.8034188034188036e-05, "epoch": 0.34968017057569295, "percentage": 7.01, "elapsed_time": "0:57:13", "remaining_time": "12:39:22"}
+{"current_steps": 83, "total_steps": 1170, "loss": 0.5135, "lr": 2.8376068376068378e-05, "epoch": 0.35394456289978676, "percentage": 7.09, "elapsed_time": "0:57:58", "remaining_time": "12:39:11"}
+{"current_steps": 84, "total_steps": 1170, "loss": 0.518, "lr": 2.871794871794872e-05, "epoch": 0.3582089552238806, "percentage": 7.18, "elapsed_time": "0:58:36", "remaining_time": "12:37:37"}
+{"current_steps": 85, "total_steps": 1170, "loss": 0.5383, "lr": 2.9059829059829063e-05, "epoch": 0.3624733475479744, "percentage": 7.26, "elapsed_time": "0:59:15", "remaining_time": "12:36:25"}
+{"current_steps": 86, "total_steps": 1170, "loss": 0.5177, "lr": 2.9401709401709405e-05, "epoch": 0.36673773987206826, "percentage": 7.35, "elapsed_time": "0:59:56", "remaining_time": "12:35:32"}
+{"current_steps": 87, "total_steps": 1170, "loss": 0.5089, "lr": 2.9743589743589747e-05, "epoch": 0.37100213219616207, "percentage": 7.44, "elapsed_time": "1:00:39", "remaining_time": "12:35:05"}
+{"current_steps": 88, "total_steps": 1170, "loss": 0.4971, "lr": 3.0085470085470086e-05, "epoch": 0.3752665245202559, "percentage": 7.52, "elapsed_time": "1:01:20", "remaining_time": "12:34:12"}
+{"current_steps": 89, "total_steps": 1170, "loss": 0.5417, "lr": 3.042735042735043e-05, "epoch": 0.3795309168443497, "percentage": 7.61, "elapsed_time": "1:02:00", "remaining_time": "12:33:05"}
+{"current_steps": 90, "total_steps": 1170, "loss": 0.4945, "lr": 3.0769230769230774e-05, "epoch": 0.3837953091684435, "percentage": 7.69, "elapsed_time": "1:02:41", "remaining_time": "12:32:19"}
+{"current_steps": 91, "total_steps": 1170, "loss": 0.5044, "lr": 3.111111111111112e-05, "epoch": 0.3880597014925373, "percentage": 7.78, "elapsed_time": "1:03:18", "remaining_time": "12:30:35"}
+{"current_steps": 92, "total_steps": 1170, "loss": 0.5202, "lr": 3.145299145299145e-05, "epoch": 0.39232409381663114, "percentage": 7.86, "elapsed_time": "1:04:00", "remaining_time": "12:30:02"}
+{"current_steps": 93, "total_steps": 1170, "loss": 0.5295, "lr": 3.1794871794871795e-05, "epoch": 0.39658848614072495, "percentage": 7.95, "elapsed_time": "1:04:34", "remaining_time": "12:27:51"}
+{"current_steps": 94, "total_steps": 1170, "loss": 0.5043, "lr": 3.2136752136752144e-05, "epoch": 0.40085287846481876, "percentage": 8.03, "elapsed_time": "1:05:16", "remaining_time": "12:27:08"}
+{"current_steps": 95, "total_steps": 1170, "loss": 0.5026, "lr": 3.247863247863248e-05, "epoch": 0.4051172707889126, "percentage": 8.12, "elapsed_time": "1:05:57", "remaining_time": "12:26:24"}
+{"current_steps": 96, "total_steps": 1170, "loss": 0.5188, "lr": 3.282051282051282e-05, "epoch": 0.4093816631130064, "percentage": 8.21, "elapsed_time": "1:06:37", "remaining_time": "12:25:22"}
+{"current_steps": 97, "total_steps": 1170, "loss": 0.5144, "lr": 3.316239316239317e-05, "epoch": 0.4136460554371002, "percentage": 8.29, "elapsed_time": "1:07:18", "remaining_time": "12:24:31"}
+{"current_steps": 98, "total_steps": 1170, "loss": 0.507, "lr": 3.3504273504273506e-05, "epoch": 0.417910447761194, "percentage": 8.38, "elapsed_time": "1:08:03", "remaining_time": "12:24:30"}
+{"current_steps": 99, "total_steps": 1170, "loss": 0.5241, "lr": 3.384615384615385e-05, "epoch": 0.42217484008528783, "percentage": 8.46, "elapsed_time": "1:08:46", "remaining_time": "12:23:57"}
+{"current_steps": 100, "total_steps": 1170, "loss": 0.5124, "lr": 3.418803418803419e-05, "epoch": 0.42643923240938164, "percentage": 8.55, "elapsed_time": "1:09:34", "remaining_time": "12:24:29"}
+{"current_steps": 101, "total_steps": 1170, "loss": 0.5106, "lr": 3.452991452991453e-05, "epoch": 0.43070362473347545, "percentage": 8.63, "elapsed_time": "1:10:15", "remaining_time": "12:23:38"}
+{"current_steps": 102, "total_steps": 1170, "loss": 0.4896, "lr": 3.4871794871794875e-05, "epoch": 0.4349680170575693, "percentage": 8.72, "elapsed_time": "1:10:54", "remaining_time": "12:22:31"}
+{"current_steps": 103, "total_steps": 1170, "loss": 0.4981, "lr": 3.521367521367522e-05, "epoch": 0.43923240938166314, "percentage": 8.8, "elapsed_time": "1:11:34", "remaining_time": "12:21:30"}
+{"current_steps": 104, "total_steps": 1170, "loss": 0.5062, "lr": 3.555555555555555e-05, "epoch": 0.44349680170575695, "percentage": 8.89, "elapsed_time": "1:12:19", "remaining_time": "12:21:20"}
+{"current_steps": 105, "total_steps": 1170, "loss": 0.5007, "lr": 3.58974358974359e-05, "epoch": 0.44776119402985076, "percentage": 8.97, "elapsed_time": "1:12:58", "remaining_time": "12:20:14"}
+{"current_steps": 106, "total_steps": 1170, "loss": 0.5025, "lr": 3.6239316239316245e-05, "epoch": 0.4520255863539446, "percentage": 9.06, "elapsed_time": "1:13:42", "remaining_time": "12:19:51"}
+{"current_steps": 107, "total_steps": 1170, "loss": 0.5208, "lr": 3.658119658119658e-05, "epoch": 0.4562899786780384, "percentage": 9.15, "elapsed_time": "1:14:20", "remaining_time": "12:18:32"}
+{"current_steps": 108, "total_steps": 1170, "loss": 0.5276, "lr": 3.692307692307693e-05, "epoch": 0.4605543710021322, "percentage": 9.23, "elapsed_time": "1:15:00", "remaining_time": "12:17:39"}
+{"current_steps": 109, "total_steps": 1170, "loss": 0.5052, "lr": 3.726495726495727e-05, "epoch": 0.464818763326226, "percentage": 9.32, "elapsed_time": "1:15:41", "remaining_time": "12:16:42"}
+{"current_steps": 110, "total_steps": 1170, "loss": 0.5255, "lr": 3.760683760683761e-05, "epoch": 0.4690831556503198, "percentage": 9.4, "elapsed_time": "1:16:23", "remaining_time": "12:16:04"}
+{"current_steps": 111, "total_steps": 1170, "loss": 0.4983, "lr": 3.794871794871795e-05, "epoch": 0.47334754797441364, "percentage": 9.49, "elapsed_time": "1:17:02", "remaining_time": "12:14:57"}
+{"current_steps": 112, "total_steps": 1170, "loss": 0.5124, "lr": 3.82905982905983e-05, "epoch": 0.47761194029850745, "percentage": 9.57, "elapsed_time": "1:17:44", "remaining_time": "12:14:19"}
+{"current_steps": 113, "total_steps": 1170, "loss": 0.4883, "lr": 3.8632478632478634e-05, "epoch": 0.48187633262260127, "percentage": 9.66, "elapsed_time": "1:18:23", "remaining_time": "12:13:19"}
+{"current_steps": 114, "total_steps": 1170, "loss": 0.5292, "lr": 3.8974358974358976e-05, "epoch": 0.4861407249466951, "percentage": 9.74, "elapsed_time": "1:19:05", "remaining_time": "12:12:33"}
+{"current_steps": 115, "total_steps": 1170, "loss": 0.5174, "lr": 3.931623931623932e-05, "epoch": 0.4904051172707889, "percentage": 9.83, "elapsed_time": "1:19:51", "remaining_time": "12:12:37"}
+{"current_steps": 116, "total_steps": 1170, "loss": 0.5147, "lr": 3.965811965811966e-05, "epoch": 0.4946695095948827, "percentage": 9.91, "elapsed_time": "1:20:35", "remaining_time": "12:12:17"}
+{"current_steps": 117, "total_steps": 1170, "loss": 0.5027, "lr": 4e-05, "epoch": 0.4989339019189765, "percentage": 10.0, "elapsed_time": "1:21:13", "remaining_time": "12:11:02"}
+{"current_steps": 118, "total_steps": 1170, "loss": 0.5286, "lr": 3.9999910989204816e-05, "epoch": 0.5031982942430704, "percentage": 10.09, "elapsed_time": "1:21:55", "remaining_time": "12:10:26"}
+{"current_steps": 119, "total_steps": 1170, "loss": 0.5085, "lr": 3.999964395761154e-05, "epoch": 0.5074626865671642, "percentage": 10.17, "elapsed_time": "1:22:36", "remaining_time": "12:09:37"}
+{"current_steps": 120, "total_steps": 1170, "loss": 0.5293, "lr": 3.9999198907597046e-05, "epoch": 0.511727078891258, "percentage": 10.26, "elapsed_time": "1:23:23", "remaining_time": "12:09:39"}
+{"current_steps": 121, "total_steps": 1170, "loss": 0.5222, "lr": 3.999857584312277e-05, "epoch": 0.5159914712153518, "percentage": 10.34, "elapsed_time": "1:24:05", "remaining_time": "12:08:58"}
+{"current_steps": 122, "total_steps": 1170, "loss": 0.5076, "lr": 3.9997774769734646e-05, "epoch": 0.5202558635394456, "percentage": 10.43, "elapsed_time": "1:24:51", "remaining_time": "12:08:56"}
+{"current_steps": 123, "total_steps": 1170, "loss": 0.5265, "lr": 3.9996795694563096e-05, "epoch": 0.5245202558635395, "percentage": 10.51, "elapsed_time": "1:25:35", "remaining_time": "12:08:30"}
+{"current_steps": 124, "total_steps": 1170, "loss": 0.5052, "lr": 3.999563862632295e-05, "epoch": 0.5287846481876333, "percentage": 10.6, "elapsed_time": "1:26:15", "remaining_time": "12:07:40"}
+{"current_steps": 125, "total_steps": 1170, "loss": 0.4833, "lr": 3.9994303575313356e-05, "epoch": 0.5330490405117271, "percentage": 10.68, "elapsed_time": "1:26:53", "remaining_time": "12:06:27"}
+{"current_steps": 126, "total_steps": 1170, "loss": 0.5088, "lr": 3.999279055341771e-05, "epoch": 0.5373134328358209, "percentage": 10.77, "elapsed_time": "1:27:35", "remaining_time": "12:05:48"}
+{"current_steps": 127, "total_steps": 1170, "loss": 0.4969, "lr": 3.9991099574103544e-05, "epoch": 0.5415778251599147, "percentage": 10.85, "elapsed_time": "1:28:18", "remaining_time": "12:05:11"}
+{"current_steps": 128, "total_steps": 1170, "loss": 0.4858, "lr": 3.9989230652422407e-05, "epoch": 0.5458422174840085, "percentage": 10.94, "elapsed_time": "1:29:00", "remaining_time": "12:04:34"}
+{"current_steps": 129, "total_steps": 1170, "loss": 0.4867, "lr": 3.998718380500971e-05, "epoch": 0.5501066098081023, "percentage": 11.03, "elapsed_time": "1:29:44", "remaining_time": "12:04:15"}
+{"current_steps": 130, "total_steps": 1170, "loss": 0.5108, "lr": 3.998495905008461e-05, "epoch": 0.5543710021321961, "percentage": 11.11, "elapsed_time": "1:30:27", "remaining_time": "12:03:39"}
+{"current_steps": 131, "total_steps": 1170, "loss": 0.4779, "lr": 3.9982556407449816e-05, "epoch": 0.55863539445629, "percentage": 11.2, "elapsed_time": "1:31:08", "remaining_time": "12:02:54"}
+{"current_steps": 132, "total_steps": 1170, "loss": 0.488, "lr": 3.997997589849145e-05, "epoch": 0.5628997867803838, "percentage": 11.28, "elapsed_time": "1:31:51", "remaining_time": "12:02:19"}
+{"current_steps": 133, "total_steps": 1170, "loss": 0.5293, "lr": 3.9977217546178825e-05, "epoch": 0.5671641791044776, "percentage": 11.37, "elapsed_time": "1:32:35", "remaining_time": "12:01:57"}
+{"current_steps": 134, "total_steps": 1170, "loss": 0.4949, "lr": 3.997428137506426e-05, "epoch": 0.5714285714285714, "percentage": 11.45, "elapsed_time": "1:33:18", "remaining_time": "12:01:26"}
+{"current_steps": 135, "total_steps": 1170, "loss": 0.5054, "lr": 3.9971167411282835e-05, "epoch": 0.5756929637526652, "percentage": 11.54, "elapsed_time": "1:34:05", "remaining_time": "12:01:24"}
+{"current_steps": 136, "total_steps": 1170, "loss": 0.5219, "lr": 3.9967875682552206e-05, "epoch": 0.579957356076759, "percentage": 11.62, "elapsed_time": "1:34:53", "remaining_time": "12:01:27"}
+{"current_steps": 137, "total_steps": 1170, "loss": 0.5182, "lr": 3.9964406218172305e-05, "epoch": 0.5842217484008528, "percentage": 11.71, "elapsed_time": "1:35:29", "remaining_time": "12:00:00"}
+{"current_steps": 138, "total_steps": 1170, "loss": 0.5039, "lr": 3.99607590490251e-05, "epoch": 0.5884861407249466, "percentage": 11.79, "elapsed_time": "1:36:13", "remaining_time": "11:59:38"}
+{"current_steps": 139, "total_steps": 1170, "loss": 0.4946, "lr": 3.995693420757435e-05, "epoch": 0.5927505330490405, "percentage": 11.88, "elapsed_time": "1:36:56", "remaining_time": "11:58:59"}
+{"current_steps": 140, "total_steps": 1170, "loss": 0.5128, "lr": 3.9952931727865264e-05, "epoch": 0.5970149253731343, "percentage": 11.97, "elapsed_time": "1:37:35", "remaining_time": "11:58:03"}
+{"current_steps": 141, "total_steps": 1170, "loss": 0.4946, "lr": 3.9948751645524235e-05, "epoch": 0.6012793176972282, "percentage": 12.05, "elapsed_time": "1:38:18", "remaining_time": "11:57:28"}
+{"current_steps": 142, "total_steps": 1170, "loss": 0.522, "lr": 3.994439399775851e-05, "epoch": 0.605543710021322, "percentage": 12.14, "elapsed_time": "1:38:59", "remaining_time": "11:56:39"}
+{"current_steps": 143, "total_steps": 1170, "loss": 0.5226, "lr": 3.993985882335584e-05, "epoch": 0.6098081023454158, "percentage": 12.22, "elapsed_time": "1:39:38", "remaining_time": "11:55:38"}
+{"current_steps": 144, "total_steps": 1170, "loss": 0.493, "lr": 3.9935146162684206e-05, "epoch": 0.6140724946695096, "percentage": 12.31, "elapsed_time": "1:40:20", "remaining_time": "11:54:53"}
+{"current_steps": 145, "total_steps": 1170, "loss": 0.4963, "lr": 3.993025605769135e-05, "epoch": 0.6183368869936035, "percentage": 12.39, "elapsed_time": "1:41:02", "remaining_time": "11:54:13"}
+{"current_steps": 146, "total_steps": 1170, "loss": 0.4952, "lr": 3.992518855190449e-05, "epoch": 0.6226012793176973, "percentage": 12.48, "elapsed_time": "1:41:42", "remaining_time": "11:53:22"}
+{"current_steps": 147, "total_steps": 1170, "loss": 0.5246, "lr": 3.9919943690429906e-05, "epoch": 0.6268656716417911, "percentage": 12.56, "elapsed_time": "1:42:24", "remaining_time": "11:52:39"}
+{"current_steps": 148, "total_steps": 1170, "loss": 0.489, "lr": 3.991452151995252e-05, "epoch": 0.6311300639658849, "percentage": 12.65, "elapsed_time": "1:43:06", "remaining_time": "11:52:02"}
+{"current_steps": 149, "total_steps": 1170, "loss": 0.5258, "lr": 3.9908922088735504e-05, "epoch": 0.6353944562899787, "percentage": 12.74, "elapsed_time": "1:43:44", "remaining_time": "11:50:49"}
+{"current_steps": 150, "total_steps": 1170, "loss": 0.4901, "lr": 3.9903145446619837e-05, "epoch": 0.6396588486140725, "percentage": 12.82, "elapsed_time": "1:44:21", "remaining_time": "11:49:37"}
+{"current_steps": 151, "total_steps": 1170, "loss": 0.4998, "lr": 3.989719164502388e-05, "epoch": 0.6439232409381663, "percentage": 12.91, "elapsed_time": "1:45:04", "remaining_time": "11:49:01"}
+{"current_steps": 152, "total_steps": 1170, "loss": 0.5103, "lr": 3.989106073694289e-05, "epoch": 0.6481876332622601, "percentage": 12.99, "elapsed_time": "1:45:48", "remaining_time": "11:48:35"}
+{"current_steps": 153, "total_steps": 1170, "loss": 0.5296, "lr": 3.9884752776948564e-05, "epoch": 0.652452025586354, "percentage": 13.08, "elapsed_time": "1:46:31", "remaining_time": "11:48:02"}
+{"current_steps": 154, "total_steps": 1170, "loss": 0.497, "lr": 3.987826782118855e-05, "epoch": 0.6567164179104478, "percentage": 13.16, "elapsed_time": "1:47:09", "remaining_time": "11:46:56"}
+{"current_steps": 155, "total_steps": 1170, "loss": 0.5089, "lr": 3.9871605927385976e-05, "epoch": 0.6609808102345416, "percentage": 13.25, "elapsed_time": "1:47:53", "remaining_time": "11:46:30"}
+{"current_steps": 156, "total_steps": 1170, "loss": 0.4952, "lr": 3.9864767154838864e-05, "epoch": 0.6652452025586354, "percentage": 13.33, "elapsed_time": "1:48:36", "remaining_time": "11:45:58"}
+{"current_steps": 157, "total_steps": 1170, "loss": 0.4991, "lr": 3.985775156441968e-05, "epoch": 0.6695095948827292, "percentage": 13.42, "elapsed_time": "1:49:18", "remaining_time": "11:45:13"}
+{"current_steps": 158, "total_steps": 1170, "loss": 0.4973, "lr": 3.985055921857477e-05, "epoch": 0.673773987206823, "percentage": 13.5, "elapsed_time": "1:49:58", "remaining_time": "11:44:23"}
+{"current_steps": 159, "total_steps": 1170, "loss": 0.5416, "lr": 3.9843190181323744e-05, "epoch": 0.6780383795309168, "percentage": 13.59, "elapsed_time": "1:50:41", "remaining_time": "11:43:52"}
+{"current_steps": 160, "total_steps": 1170, "loss": 0.5052, "lr": 3.9835644518259015e-05, "epoch": 0.6823027718550106, "percentage": 13.68, "elapsed_time": "1:51:23", "remaining_time": "11:43:08"}
+{"current_steps": 161, "total_steps": 1170, "loss": 0.4863, "lr": 3.982792229654512e-05, "epoch": 0.6865671641791045, "percentage": 13.76, "elapsed_time": "1:52:03", "remaining_time": "11:42:17"}
+{"current_steps": 162, "total_steps": 1170, "loss": 0.4896, "lr": 3.982002358491817e-05, "epoch": 0.6908315565031983, "percentage": 13.85, "elapsed_time": "1:52:48", "remaining_time": "11:41:57"}
+{"current_steps": 163, "total_steps": 1170, "loss": 0.5059, "lr": 3.981194845368523e-05, "epoch": 0.6950959488272921, "percentage": 13.93, "elapsed_time": "1:53:26", "remaining_time": "11:40:52"}
+{"current_steps": 164, "total_steps": 1170, "loss": 0.5099, "lr": 3.980369697472367e-05, "epoch": 0.6993603411513859, "percentage": 14.02, "elapsed_time": "1:54:07", "remaining_time": "11:40:03"}
+{"current_steps": 165, "total_steps": 1170, "loss": 0.518, "lr": 3.979526922148058e-05, "epoch": 0.7036247334754797, "percentage": 14.1, "elapsed_time": "1:54:47", "remaining_time": "11:39:11"}
+{"current_steps": 166, "total_steps": 1170, "loss": 0.49, "lr": 3.978666526897204e-05, "epoch": 0.7078891257995735, "percentage": 14.19, "elapsed_time": "1:55:29", "remaining_time": "11:38:32"}
+{"current_steps": 167, "total_steps": 1170, "loss": 0.5197, "lr": 3.9777885193782534e-05, "epoch": 0.7121535181236673, "percentage": 14.27, "elapsed_time": "1:56:10", "remaining_time": "11:37:42"}
+{"current_steps": 168, "total_steps": 1170, "loss": 0.5035, "lr": 3.9768929074064206e-05, "epoch": 0.7164179104477612, "percentage": 14.36, "elapsed_time": "1:56:47", "remaining_time": "11:36:34"}
+{"current_steps": 169, "total_steps": 1170, "loss": 0.504, "lr": 3.9759796989536185e-05, "epoch": 0.720682302771855, "percentage": 14.44, "elapsed_time": "1:57:29", "remaining_time": "11:35:54"}
+{"current_steps": 170, "total_steps": 1170, "loss": 0.4878, "lr": 3.975048902148388e-05, "epoch": 0.7249466950959488, "percentage": 14.53, "elapsed_time": "1:58:11", "remaining_time": "11:35:17"}
+{"current_steps": 171, "total_steps": 1170, "loss": 0.4701, "lr": 3.9741005252758255e-05, "epoch": 0.7292110874200426, "percentage": 14.62, "elapsed_time": "1:58:57", "remaining_time": "11:34:56"}
+{"current_steps": 172, "total_steps": 1170, "loss": 0.5018, "lr": 3.9731345767775105e-05, "epoch": 0.7334754797441365, "percentage": 14.7, "elapsed_time": "1:59:39", "remaining_time": "11:34:19"}
+{"current_steps": 173, "total_steps": 1170, "loss": 0.4853, "lr": 3.972151065251425e-05, "epoch": 0.7377398720682303, "percentage": 14.79, "elapsed_time": "2:00:20", "remaining_time": "11:33:33"}
+{"current_steps": 174, "total_steps": 1170, "loss": 0.4736, "lr": 3.971149999451886e-05, "epoch": 0.7420042643923241, "percentage": 14.87, "elapsed_time": "2:01:02", "remaining_time": "11:32:49"}
+{"current_steps": 175, "total_steps": 1170, "loss": 0.4931, "lr": 3.970131388289456e-05, "epoch": 0.746268656716418, "percentage": 14.96, "elapsed_time": "2:01:42", "remaining_time": "11:31:58"}
+{"current_steps": 176, "total_steps": 1170, "loss": 0.4908, "lr": 3.9690952408308775e-05, "epoch": 0.7505330490405118, "percentage": 15.04, "elapsed_time": "2:02:24", "remaining_time": "11:31:18"}
+{"current_steps": 177, "total_steps": 1170, "loss": 0.4866, "lr": 3.9680415662989806e-05, "epoch": 0.7547974413646056, "percentage": 15.13, "elapsed_time": "2:03:07", "remaining_time": "11:30:47"}
+{"current_steps": 178, "total_steps": 1170, "loss": 0.5181, "lr": 3.966970374072605e-05, "epoch": 0.7590618336886994, "percentage": 15.21, "elapsed_time": "2:03:47", "remaining_time": "11:29:52"}
+{"current_steps": 179, "total_steps": 1170, "loss": 0.502, "lr": 3.9658816736865183e-05, "epoch": 0.7633262260127932, "percentage": 15.3, "elapsed_time": "2:04:27", "remaining_time": "11:29:01"}
+{"current_steps": 180, "total_steps": 1170, "loss": 0.4942, "lr": 3.9647754748313294e-05, "epoch": 0.767590618336887, "percentage": 15.38, "elapsed_time": "2:05:09", "remaining_time": "11:28:22"}
+{"current_steps": 181, "total_steps": 1170, "loss": 0.5079, "lr": 3.9636517873534025e-05, "epoch": 0.7718550106609808, "percentage": 15.47, "elapsed_time": "2:05:49", "remaining_time": "11:27:29"}
+{"current_steps": 182, "total_steps": 1170, "loss": 0.5039, "lr": 3.9625106212547696e-05, "epoch": 0.7761194029850746, "percentage": 15.56, "elapsed_time": "2:06:26", "remaining_time": "11:26:23"}
+{"current_steps": 183, "total_steps": 1170, "loss": 0.4899, "lr": 3.96135198669304e-05, "epoch": 0.7803837953091685, "percentage": 15.64, "elapsed_time": "2:07:09", "remaining_time": "11:25:50"}
+{"current_steps": 184, "total_steps": 1170, "loss": 0.4909, "lr": 3.960175893981312e-05, "epoch": 0.7846481876332623, "percentage": 15.73, "elapsed_time": "2:07:53", "remaining_time": "11:25:18"}
+{"current_steps": 185, "total_steps": 1170, "loss": 0.4992, "lr": 3.958982353588081e-05, "epoch": 0.7889125799573561, "percentage": 15.81, "elapsed_time": "2:08:37", "remaining_time": "11:24:50"}
+{"current_steps": 186, "total_steps": 1170, "loss": 0.5103, "lr": 3.957771376137144e-05, "epoch": 0.7931769722814499, "percentage": 15.9, "elapsed_time": "2:09:18", "remaining_time": "11:24:02"}
+{"current_steps": 187, "total_steps": 1170, "loss": 0.4951, "lr": 3.956542972407509e-05, "epoch": 0.7974413646055437, "percentage": 15.98, "elapsed_time": "2:10:00", "remaining_time": "11:23:27"}
+{"current_steps": 188, "total_steps": 1170, "loss": 0.4786, "lr": 3.955297153333294e-05, "epoch": 0.8017057569296375, "percentage": 16.07, "elapsed_time": "2:10:36", "remaining_time": "11:22:11"}
+{"current_steps": 189, "total_steps": 1170, "loss": 0.4862, "lr": 3.954033930003634e-05, "epoch": 0.8059701492537313, "percentage": 16.15, "elapsed_time": "2:11:18", "remaining_time": "11:21:32"}
+{"current_steps": 190, "total_steps": 1170, "loss": 0.4995, "lr": 3.952753313662581e-05, "epoch": 0.8102345415778252, "percentage": 16.24, "elapsed_time": "2:12:03", "remaining_time": "11:21:11"}
+{"current_steps": 191, "total_steps": 1170, "loss": 0.4989, "lr": 3.9514553157090027e-05, "epoch": 0.814498933901919, "percentage": 16.32, "elapsed_time": "2:12:42", "remaining_time": "11:20:11"}
+{"current_steps": 192, "total_steps": 1170, "loss": 0.4638, "lr": 3.9501399476964806e-05, "epoch": 0.8187633262260128, "percentage": 16.41, "elapsed_time": "2:13:25", "remaining_time": "11:19:39"}
+{"current_steps": 193, "total_steps": 1170, "loss": 0.4872, "lr": 3.948807221333212e-05, "epoch": 0.8230277185501066, "percentage": 16.5, "elapsed_time": "2:14:08", "remaining_time": "11:19:05"}
+{"current_steps": 194, "total_steps": 1170, "loss": 0.4934, "lr": 3.947457148481899e-05, "epoch": 0.8272921108742004, "percentage": 16.58, "elapsed_time": "2:14:51", "remaining_time": "11:18:25"}
+{"current_steps": 195, "total_steps": 1170, "loss": 0.5032, "lr": 3.946089741159648e-05, "epoch": 0.8315565031982942, "percentage": 16.67, "elapsed_time": "2:15:32", "remaining_time": "11:17:43"}
+{"current_steps": 196, "total_steps": 1170, "loss": 0.4925, "lr": 3.94470501153786e-05, "epoch": 0.835820895522388, "percentage": 16.75, "elapsed_time": "2:16:11", "remaining_time": "11:16:49"}
+{"current_steps": 197, "total_steps": 1170, "loss": 0.4764, "lr": 3.943302971942124e-05, "epoch": 0.8400852878464818, "percentage": 16.84, "elapsed_time": "2:16:44", "remaining_time": "11:15:22"}
+{"current_steps": 198, "total_steps": 1170, "loss": 0.5101, "lr": 3.9418836348521045e-05, "epoch": 0.8443496801705757, "percentage": 16.92, "elapsed_time": "2:17:23", "remaining_time": "11:14:29"}
+{"current_steps": 199, "total_steps": 1170, "loss": 0.4777, "lr": 3.940447012901435e-05, "epoch": 0.8486140724946695, "percentage": 17.01, "elapsed_time": "2:18:05", "remaining_time": "11:13:47"}
+{"current_steps": 200, "total_steps": 1170, "loss": 0.5, "lr": 3.9389931188776016e-05, "epoch": 0.8528784648187633, "percentage": 17.09, "elapsed_time": "2:18:43", "remaining_time": "11:12:51"}
+{"current_steps": 201, "total_steps": 1170, "loss": 0.4791, "lr": 3.937521965721831e-05, "epoch": 0.8571428571428571, "percentage": 17.18, "elapsed_time": "2:19:19", "remaining_time": "11:11:41"}
+{"current_steps": 202, "total_steps": 1170, "loss": 0.4904, "lr": 3.9360335665289735e-05, "epoch": 0.8614072494669509, "percentage": 17.26, "elapsed_time": "2:19:59", "remaining_time": "11:10:52"}
+{"current_steps": 203, "total_steps": 1170, "loss": 0.497, "lr": 3.9345279345473894e-05, "epoch": 0.8656716417910447, "percentage": 17.35, "elapsed_time": "2:20:41", "remaining_time": "11:10:12"}
+{"current_steps": 204, "total_steps": 1170, "loss": 0.4892, "lr": 3.933005083178828e-05, "epoch": 0.8699360341151386, "percentage": 17.44, "elapsed_time": "2:21:20", "remaining_time": "11:09:19"}
+{"current_steps": 205, "total_steps": 1170, "loss": 0.5076, "lr": 3.9314650259783116e-05, "epoch": 0.8742004264392325, "percentage": 17.52, "elapsed_time": "2:22:04", "remaining_time": "11:08:45"}
+{"current_steps": 206, "total_steps": 1170, "loss": 0.4999, "lr": 3.9299077766540106e-05, "epoch": 0.8784648187633263, "percentage": 17.61, "elapsed_time": "2:22:42", "remaining_time": "11:07:50"}
+{"current_steps": 207, "total_steps": 1170, "loss": 0.5174, "lr": 3.928333349067125e-05, "epoch": 0.8827292110874201, "percentage": 17.69, "elapsed_time": "2:23:21", "remaining_time": "11:06:57"}
+{"current_steps": 208, "total_steps": 1170, "loss": 0.5088, "lr": 3.926741757231761e-05, "epoch": 0.8869936034115139, "percentage": 17.78, "elapsed_time": "2:23:57", "remaining_time": "11:05:50"}
+{"current_steps": 209, "total_steps": 1170, "loss": 0.5001, "lr": 3.925133015314804e-05, "epoch": 0.8912579957356077, "percentage": 17.86, "elapsed_time": "2:24:39", "remaining_time": "11:05:11"}
+{"current_steps": 210, "total_steps": 1170, "loss": 0.4615, "lr": 3.923507137635792e-05, "epoch": 0.8955223880597015, "percentage": 17.95, "elapsed_time": "2:25:26", "remaining_time": "11:04:51"}
+{"current_steps": 211, "total_steps": 1170, "loss": 0.4833, "lr": 3.9218641386667935e-05, "epoch": 0.8997867803837953, "percentage": 18.03, "elapsed_time": "2:26:05", "remaining_time": "11:03:57"}
+{"current_steps": 212, "total_steps": 1170, "loss": 0.5172, "lr": 3.920204033032272e-05, "epoch": 0.9040511727078892, "percentage": 18.12, "elapsed_time": "2:26:48", "remaining_time": "11:03:23"}
+{"current_steps": 213, "total_steps": 1170, "loss": 0.503, "lr": 3.9185268355089606e-05, "epoch": 0.908315565031983, "percentage": 18.21, "elapsed_time": "2:27:29", "remaining_time": "11:02:42"}
+{"current_steps": 214, "total_steps": 1170, "loss": 0.5039, "lr": 3.916832561025727e-05, "epoch": 0.9125799573560768, "percentage": 18.29, "elapsed_time": "2:28:12", "remaining_time": "11:02:03"}
+{"current_steps": 215, "total_steps": 1170, "loss": 0.4769, "lr": 3.915121224663443e-05, "epoch": 0.9168443496801706, "percentage": 18.38, "elapsed_time": "2:28:55", "remaining_time": "11:01:31"}
+{"current_steps": 216, "total_steps": 1170, "loss": 0.4798, "lr": 3.913392841654851e-05, "epoch": 0.9211087420042644, "percentage": 18.46, "elapsed_time": "2:29:39", "remaining_time": "11:00:58"}
+{"current_steps": 217, "total_steps": 1170, "loss": 0.4801, "lr": 3.9116474273844233e-05, "epoch": 0.9253731343283582, "percentage": 18.55, "elapsed_time": "2:30:19", "remaining_time": "11:00:09"}
+{"current_steps": 218, "total_steps": 1170, "loss": 0.5066, "lr": 3.909884997388234e-05, "epoch": 0.929637526652452, "percentage": 18.63, "elapsed_time": "2:30:59", "remaining_time": "10:59:23"}
+{"current_steps": 219, "total_steps": 1170, "loss": 0.4869, "lr": 3.9081055673538093e-05, "epoch": 0.9339019189765458, "percentage": 18.72, "elapsed_time": "2:31:33", "remaining_time": "10:58:10"}
+{"current_steps": 220, "total_steps": 1170, "loss": 0.4847, "lr": 3.90630915312e-05, "epoch": 0.9381663113006397, "percentage": 18.8, "elapsed_time": "2:32:15", "remaining_time": "10:57:30"}
+{"current_steps": 221, "total_steps": 1170, "loss": 0.4779, "lr": 3.904495770676831e-05, "epoch": 0.9424307036247335, "percentage": 18.89, "elapsed_time": "2:32:59", "remaining_time": "10:56:58"}
+{"current_steps": 222, "total_steps": 1170, "loss": 0.4863, "lr": 3.902665436165364e-05, "epoch": 0.9466950959488273, "percentage": 18.97, "elapsed_time": "2:33:41", "remaining_time": "10:56:20"}
+{"current_steps": 223, "total_steps": 1170, "loss": 0.4784, "lr": 3.900818165877552e-05, "epoch": 0.9509594882729211, "percentage": 19.06, "elapsed_time": "2:34:22", "remaining_time": "10:55:32"}
+{"current_steps": 224, "total_steps": 1170, "loss": 0.472, "lr": 3.898953976256094e-05, "epoch": 0.9552238805970149, "percentage": 19.15, "elapsed_time": "2:35:04", "remaining_time": "10:54:55"}
+{"current_steps": 225, "total_steps": 1170, "loss": 0.5014, "lr": 3.897072883894291e-05, "epoch": 0.9594882729211087, "percentage": 19.23, "elapsed_time": "2:35:45", "remaining_time": "10:54:11"}
+{"current_steps": 226, "total_steps": 1170, "loss": 0.4874, "lr": 3.895174905535896e-05, "epoch": 0.9637526652452025, "percentage": 19.32, "elapsed_time": "2:36:20", "remaining_time": "10:53:03"}
+{"current_steps": 227, "total_steps": 1170, "loss": 0.475, "lr": 3.893260058074964e-05, "epoch": 0.9680170575692963, "percentage": 19.4, "elapsed_time": "2:37:00", "remaining_time": "10:52:13"}
+{"current_steps": 228, "total_steps": 1170, "loss": 0.4826, "lr": 3.8913283585557054e-05, "epoch": 0.9722814498933902, "percentage": 19.49, "elapsed_time": "2:37:37", "remaining_time": "10:51:15"}
+{"current_steps": 229, "total_steps": 1170, "loss": 0.4756, "lr": 3.8893798241723306e-05, "epoch": 0.976545842217484, "percentage": 19.57, "elapsed_time": "2:38:13", "remaining_time": "10:50:11"}
+{"current_steps": 230, "total_steps": 1170, "loss": 0.4854, "lr": 3.8874144722689e-05, "epoch": 0.9808102345415778, "percentage": 19.66, "elapsed_time": "2:38:54", "remaining_time": "10:49:25"}
+{"current_steps": 231, "total_steps": 1170, "loss": 0.495, "lr": 3.885432320339167e-05, "epoch": 0.9850746268656716, "percentage": 19.74, "elapsed_time": "2:39:36", "remaining_time": "10:48:48"}
+{"current_steps": 232, "total_steps": 1170, "loss": 0.4868, "lr": 3.883433386026422e-05, "epoch": 0.9893390191897654, "percentage": 19.83, "elapsed_time": "2:40:24", "remaining_time": "10:48:31"}
+{"current_steps": 233, "total_steps": 1170, "loss": 0.4972, "lr": 3.88141768712334e-05, "epoch": 0.9936034115138592, "percentage": 19.91, "elapsed_time": "2:41:04", "remaining_time": "10:47:47"}
+{"current_steps": 234, "total_steps": 1170, "loss": 0.4927, "lr": 3.879385241571817e-05, "epoch": 0.997867803837953, "percentage": 20.0, "elapsed_time": "2:41:47", "remaining_time": "10:47:09"}
+{"current_steps": 235, "total_steps": 1170, "loss": 0.7904, "lr": 3.877336067462812e-05, "epoch": 1.0031982942430704, "percentage": 20.09, "elapsed_time": "2:43:08", "remaining_time": "10:49:07"}
+{"current_steps": 236, "total_steps": 1170, "loss": 0.4162, "lr": 3.875270183036187e-05, "epoch": 1.007462686567164, "percentage": 20.17, "elapsed_time": "2:43:46", "remaining_time": "10:48:08"}
+{"current_steps": 237, "total_steps": 1170, "loss": 0.4699, "lr": 3.873187606680543e-05, "epoch": 1.011727078891258, "percentage": 20.26, "elapsed_time": "2:44:28", "remaining_time": "10:47:31"}
+{"current_steps": 238, "total_steps": 1170, "loss": 0.418, "lr": 3.871088356933059e-05, "epoch": 1.0159914712153517, "percentage": 20.34, "elapsed_time": "2:45:06", "remaining_time": "10:46:32"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45c691f38bad4a2e0c87fedd2e29c94cce783e985a574b711e324907140e21c
+size 7224