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 sha256:3af07f2e6055d4f371c38eb1aa42bdca07d4072b9f2a552863d0c84d98c4b95c
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2517b96a81107a94e3b20d7d3e08ee18671f275ba0f300701ce53899d14089f5
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dae535dc5016731fa113b99c1a39b9e518eba6476ee25e83cb98880923c8dd
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e836bc70b66866f76db95a0e21b17239bf965bd3671e9b21297e8cc3cf9476
+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 +1,150 @@
+{"current_steps": 1, "total_steps": 735, "loss": 1.1988, "lr": 1.0810810810810812e-06, "epoch": 0.006779661016949152, "percentage": 0.14, "elapsed_time": "0:01:34", "remaining_time": "19:13:12"}
+{"current_steps": 2, "total_steps": 735, "loss": 1.1925, "lr": 2.1621621621621623e-06, "epoch": 0.013559322033898305, "percentage": 0.27, "elapsed_time": "0:02:24", "remaining_time": "14:43:12"}
+{"current_steps": 3, "total_steps": 735, "loss": 1.1869, "lr": 3.2432432432432437e-06, "epoch": 0.020338983050847456, "percentage": 0.41, "elapsed_time": "0:03:15", "remaining_time": "13:13:45"}
+{"current_steps": 4, "total_steps": 735, "loss": 1.1664, "lr": 4.324324324324325e-06, "epoch": 0.02711864406779661, "percentage": 0.54, "elapsed_time": "0:04:05", "remaining_time": "12:26:56"}
+{"current_steps": 5, "total_steps": 735, "loss": 1.1314, "lr": 5.405405405405406e-06, "epoch": 0.03389830508474576, "percentage": 0.68, "elapsed_time": "0:04:55", "remaining_time": "11:58:35"}
+{"current_steps": 6, "total_steps": 735, "loss": 1.0895, "lr": 6.486486486486487e-06, "epoch": 0.04067796610169491, "percentage": 0.82, "elapsed_time": "0:05:45", "remaining_time": "11:39:25"}
+{"current_steps": 7, "total_steps": 735, "loss": 1.0536, "lr": 7.567567567567569e-06, "epoch": 0.04745762711864407, "percentage": 0.95, "elapsed_time": "0:06:35", "remaining_time": "11:26:09"}
+{"current_steps": 8, "total_steps": 735, "loss": 1.0809, "lr": 8.64864864864865e-06, "epoch": 0.05423728813559322, "percentage": 1.09, "elapsed_time": "0:07:25", "remaining_time": "11:15:21"}
+{"current_steps": 9, "total_steps": 735, "loss": 1.0613, "lr": 9.729729729729732e-06, "epoch": 0.061016949152542375, "percentage": 1.22, "elapsed_time": "0:08:16", "remaining_time": "11:07:17"}
+{"current_steps": 10, "total_steps": 735, "loss": 1.0031, "lr": 1.0810810810810812e-05, "epoch": 0.06779661016949153, "percentage": 1.36, "elapsed_time": "0:09:06", "remaining_time": "11:00:44"}
+{"current_steps": 11, "total_steps": 735, "loss": 0.9963, "lr": 1.1891891891891894e-05, "epoch": 0.07457627118644068, "percentage": 1.5, "elapsed_time": "0:09:57", "remaining_time": "10:55:11"}
+{"current_steps": 12, "total_steps": 735, "loss": 0.9667, "lr": 1.2972972972972975e-05, "epoch": 0.08135593220338982, "percentage": 1.63, "elapsed_time": "0:10:47", "remaining_time": "10:50:17"}
+{"current_steps": 13, "total_steps": 735, "loss": 0.9244, "lr": 1.4054054054054055e-05, "epoch": 0.08813559322033898, "percentage": 1.77, "elapsed_time": "0:11:43", "remaining_time": "10:51:17"}
+{"current_steps": 14, "total_steps": 735, "loss": 0.917, "lr": 1.5135135135135138e-05, "epoch": 0.09491525423728814, "percentage": 1.9, "elapsed_time": "0:12:33", "remaining_time": "10:47:00"}
+{"current_steps": 15, "total_steps": 735, "loss": 0.9109, "lr": 1.6216216216216218e-05, "epoch": 0.1016949152542373, "percentage": 2.04, "elapsed_time": "0:13:24", "remaining_time": "10:43:21"}
+{"current_steps": 16, "total_steps": 735, "loss": 0.8739, "lr": 1.72972972972973e-05, "epoch": 0.10847457627118644, "percentage": 2.18, "elapsed_time": "0:14:14", "remaining_time": "10:40:04"}
+{"current_steps": 17, "total_steps": 735, "loss": 0.8659, "lr": 1.8378378378378383e-05, "epoch": 0.1152542372881356, "percentage": 2.31, "elapsed_time": "0:15:05", "remaining_time": "10:37:07"}
+{"current_steps": 18, "total_steps": 735, "loss": 0.868, "lr": 1.9459459459459463e-05, "epoch": 0.12203389830508475, "percentage": 2.45, "elapsed_time": "0:15:55", "remaining_time": "10:34:06"}
+{"current_steps": 19, "total_steps": 735, "loss": 0.8638, "lr": 2.054054054054054e-05, "epoch": 0.1288135593220339, "percentage": 2.59, "elapsed_time": "0:16:45", "remaining_time": "10:31:19"}
+{"current_steps": 20, "total_steps": 735, "loss": 0.8585, "lr": 2.1621621621621624e-05, "epoch": 0.13559322033898305, "percentage": 2.72, "elapsed_time": "0:17:35", "remaining_time": "10:28:53"}
+{"current_steps": 21, "total_steps": 735, "loss": 0.8312, "lr": 2.2702702702702705e-05, "epoch": 0.1423728813559322, "percentage": 2.86, "elapsed_time": "0:18:25", "remaining_time": "10:26:27"}
+{"current_steps": 22, "total_steps": 735, "loss": 0.8252, "lr": 2.378378378378379e-05, "epoch": 0.14915254237288136, "percentage": 2.99, "elapsed_time": "0:19:15", "remaining_time": "10:24:11"}
+{"current_steps": 23, "total_steps": 735, "loss": 0.815, "lr": 2.4864864864864866e-05, "epoch": 0.15593220338983052, "percentage": 3.13, "elapsed_time": "0:20:05", "remaining_time": "10:22:04"}
+{"current_steps": 24, "total_steps": 735, "loss": 0.8296, "lr": 2.594594594594595e-05, "epoch": 0.16271186440677965, "percentage": 3.27, "elapsed_time": "0:20:55", "remaining_time": "10:19:57"}
+{"current_steps": 25, "total_steps": 735, "loss": 0.8319, "lr": 2.702702702702703e-05, "epoch": 0.1694915254237288, "percentage": 3.4, "elapsed_time": "0:21:45", "remaining_time": "10:18:02"}
+{"current_steps": 26, "total_steps": 735, "loss": 0.8201, "lr": 2.810810810810811e-05, "epoch": 0.17627118644067796, "percentage": 3.54, "elapsed_time": "0:22:35", "remaining_time": "10:16:07"}
+{"current_steps": 27, "total_steps": 735, "loss": 0.8049, "lr": 2.918918918918919e-05, "epoch": 0.18305084745762712, "percentage": 3.67, "elapsed_time": "0:23:27", "remaining_time": "10:15:08"}
+{"current_steps": 28, "total_steps": 735, "loss": 0.8053, "lr": 3.0270270270270275e-05, "epoch": 0.18983050847457628, "percentage": 3.81, "elapsed_time": "0:24:20", "remaining_time": "10:14:49"}
+{"current_steps": 29, "total_steps": 735, "loss": 0.7936, "lr": 3.135135135135135e-05, "epoch": 0.19661016949152543, "percentage": 3.95, "elapsed_time": "0:25:10", "remaining_time": "10:13:02"}
+{"current_steps": 30, "total_steps": 735, "loss": 0.7996, "lr": 3.2432432432432436e-05, "epoch": 0.2033898305084746, "percentage": 4.08, "elapsed_time": "0:26:00", "remaining_time": "10:11:21"}
+{"current_steps": 31, "total_steps": 735, "loss": 0.7871, "lr": 3.351351351351351e-05, "epoch": 0.21016949152542372, "percentage": 4.22, "elapsed_time": "0:26:50", "remaining_time": "10:09:43"}
+{"current_steps": 32, "total_steps": 735, "loss": 0.7882, "lr": 3.45945945945946e-05, "epoch": 0.21694915254237288, "percentage": 4.35, "elapsed_time": "0:27:40", "remaining_time": "10:08:06"}
+{"current_steps": 33, "total_steps": 735, "loss": 0.7962, "lr": 3.567567567567568e-05, "epoch": 0.22372881355932203, "percentage": 4.49, "elapsed_time": "0:28:30", "remaining_time": "10:06:33"}
+{"current_steps": 34, "total_steps": 735, "loss": 0.7873, "lr": 3.6756756756756765e-05, "epoch": 0.2305084745762712, "percentage": 4.63, "elapsed_time": "0:29:20", "remaining_time": "10:05:04"}
+{"current_steps": 35, "total_steps": 735, "loss": 0.7965, "lr": 3.783783783783784e-05, "epoch": 0.23728813559322035, "percentage": 4.76, "elapsed_time": "0:30:11", "remaining_time": "10:03:46"}
+{"current_steps": 36, "total_steps": 735, "loss": 0.7667, "lr": 3.8918918918918926e-05, "epoch": 0.2440677966101695, "percentage": 4.9, "elapsed_time": "0:31:01", "remaining_time": "10:02:20"}
+{"current_steps": 37, "total_steps": 735, "loss": 0.787, "lr": 4e-05, "epoch": 0.25084745762711863, "percentage": 5.03, "elapsed_time": "0:31:51", "remaining_time": "10:00:58"}
+{"current_steps": 38, "total_steps": 735, "loss": 0.7908, "lr": 4.108108108108108e-05, "epoch": 0.2576271186440678, "percentage": 5.17, "elapsed_time": "0:32:41", "remaining_time": "9:59:35"}
+{"current_steps": 39, "total_steps": 735, "loss": 0.7803, "lr": 4.2162162162162164e-05, "epoch": 0.26440677966101694, "percentage": 5.31, "elapsed_time": "0:33:31", "remaining_time": "9:58:17"}
+{"current_steps": 40, "total_steps": 735, "loss": 0.7809, "lr": 4.324324324324325e-05, "epoch": 0.2711864406779661, "percentage": 5.44, "elapsed_time": "0:34:21", "remaining_time": "9:56:58"}
+{"current_steps": 41, "total_steps": 735, "loss": 0.7747, "lr": 4.4324324324324325e-05, "epoch": 0.27796610169491526, "percentage": 5.58, "elapsed_time": "0:35:11", "remaining_time": "9:55:42"}
+{"current_steps": 42, "total_steps": 735, "loss": 0.7766, "lr": 4.540540540540541e-05, "epoch": 0.2847457627118644, "percentage": 5.71, "elapsed_time": "0:36:06", "remaining_time": "9:55:42"}
+{"current_steps": 43, "total_steps": 735, "loss": 0.7757, "lr": 4.6486486486486486e-05, "epoch": 0.29152542372881357, "percentage": 5.85, "elapsed_time": "0:36:58", "remaining_time": "9:55:08"}
+{"current_steps": 44, "total_steps": 735, "loss": 0.7567, "lr": 4.756756756756758e-05, "epoch": 0.2983050847457627, "percentage": 5.99, "elapsed_time": "0:37:48", "remaining_time": "9:53:51"}
+{"current_steps": 45, "total_steps": 735, "loss": 0.7717, "lr": 4.8648648648648654e-05, "epoch": 0.3050847457627119, "percentage": 6.12, "elapsed_time": "0:38:38", "remaining_time": "9:52:36"}
+{"current_steps": 46, "total_steps": 735, "loss": 0.7796, "lr": 4.972972972972973e-05, "epoch": 0.31186440677966104, "percentage": 6.26, "elapsed_time": "0:39:29", "remaining_time": "9:51:23"}
+{"current_steps": 47, "total_steps": 735, "loss": 0.7571, "lr": 5.081081081081081e-05, "epoch": 0.31864406779661014, "percentage": 6.39, "elapsed_time": "0:40:19", "remaining_time": "9:50:11"}
+{"current_steps": 48, "total_steps": 735, "loss": 0.7585, "lr": 5.18918918918919e-05, "epoch": 0.3254237288135593, "percentage": 6.53, "elapsed_time": "0:41:09", "remaining_time": "9:49:00"}
+{"current_steps": 49, "total_steps": 735, "loss": 0.7615, "lr": 5.2972972972972976e-05, "epoch": 0.33220338983050846, "percentage": 6.67, "elapsed_time": "0:41:59", "remaining_time": "9:47:51"}
+{"current_steps": 50, "total_steps": 735, "loss": 0.7755, "lr": 5.405405405405406e-05, "epoch": 0.3389830508474576, "percentage": 6.8, "elapsed_time": "0:42:49", "remaining_time": "9:46:39"}
+{"current_steps": 51, "total_steps": 735, "loss": 0.7614, "lr": 5.513513513513514e-05, "epoch": 0.34576271186440677, "percentage": 6.94, "elapsed_time": "0:43:39", "remaining_time": "9:45:32"}
+{"current_steps": 52, "total_steps": 735, "loss": 0.7725, "lr": 5.621621621621622e-05, "epoch": 0.3525423728813559, "percentage": 7.07, "elapsed_time": "0:44:29", "remaining_time": "9:44:23"}
+{"current_steps": 53, "total_steps": 735, "loss": 0.7535, "lr": 5.7297297297297305e-05, "epoch": 0.3593220338983051, "percentage": 7.21, "elapsed_time": "0:45:19", "remaining_time": "9:43:15"}
+{"current_steps": 54, "total_steps": 735, "loss": 0.7579, "lr": 5.837837837837838e-05, "epoch": 0.36610169491525424, "percentage": 7.35, "elapsed_time": "0:46:09", "remaining_time": "9:42:06"}
+{"current_steps": 55, "total_steps": 735, "loss": 0.7499, "lr": 5.945945945945946e-05, "epoch": 0.3728813559322034, "percentage": 7.48, "elapsed_time": "0:46:59", "remaining_time": "9:41:04"}
+{"current_steps": 56, "total_steps": 735, "loss": 0.7504, "lr": 6.054054054054055e-05, "epoch": 0.37966101694915255, "percentage": 7.62, "elapsed_time": "0:47:49", "remaining_time": "9:39:58"}
+{"current_steps": 57, "total_steps": 735, "loss": 0.7527, "lr": 6.162162162162163e-05, "epoch": 0.3864406779661017, "percentage": 7.76, "elapsed_time": "0:48:46", "remaining_time": "9:40:10"}
+{"current_steps": 58, "total_steps": 735, "loss": 0.7483, "lr": 6.27027027027027e-05, "epoch": 0.39322033898305087, "percentage": 7.89, "elapsed_time": "0:49:38", "remaining_time": "9:39:21"}
+{"current_steps": 59, "total_steps": 735, "loss": 0.7581, "lr": 6.378378378378379e-05, "epoch": 0.4, "percentage": 8.03, "elapsed_time": "0:50:28", "remaining_time": "9:38:15"}
+{"current_steps": 60, "total_steps": 735, "loss": 0.7658, "lr": 6.486486486486487e-05, "epoch": 0.4067796610169492, "percentage": 8.16, "elapsed_time": "0:51:18", "remaining_time": "9:37:10"}
+{"current_steps": 61, "total_steps": 735, "loss": 0.7397, "lr": 6.594594594594596e-05, "epoch": 0.4135593220338983, "percentage": 8.3, "elapsed_time": "0:52:08", "remaining_time": "9:36:04"}
+{"current_steps": 62, "total_steps": 735, "loss": 0.7491, "lr": 6.702702702702703e-05, "epoch": 0.42033898305084744, "percentage": 8.44, "elapsed_time": "0:52:58", "remaining_time": "9:35:00"}
+{"current_steps": 63, "total_steps": 735, "loss": 0.7573, "lr": 6.810810810810811e-05, "epoch": 0.4271186440677966, "percentage": 8.57, "elapsed_time": "0:53:48", "remaining_time": "9:33:56"}
+{"current_steps": 64, "total_steps": 735, "loss": 0.7482, "lr": 6.91891891891892e-05, "epoch": 0.43389830508474575, "percentage": 8.71, "elapsed_time": "0:54:38", "remaining_time": "9:32:53"}
+{"current_steps": 65, "total_steps": 735, "loss": 0.7548, "lr": 7.027027027027028e-05, "epoch": 0.4406779661016949, "percentage": 8.84, "elapsed_time": "0:55:28", "remaining_time": "9:31:51"}
+{"current_steps": 66, "total_steps": 735, "loss": 0.767, "lr": 7.135135135135136e-05, "epoch": 0.44745762711864406, "percentage": 8.98, "elapsed_time": "0:56:18", "remaining_time": "9:30:48"}
+{"current_steps": 67, "total_steps": 735, "loss": 0.7379, "lr": 7.243243243243243e-05, "epoch": 0.4542372881355932, "percentage": 9.12, "elapsed_time": "0:57:08", "remaining_time": "9:29:46"}
+{"current_steps": 68, "total_steps": 735, "loss": 0.7703, "lr": 7.351351351351353e-05, "epoch": 0.4610169491525424, "percentage": 9.25, "elapsed_time": "0:57:58", "remaining_time": "9:28:43"}
+{"current_steps": 69, "total_steps": 735, "loss": 0.7487, "lr": 7.45945945945946e-05, "epoch": 0.46779661016949153, "percentage": 9.39, "elapsed_time": "0:58:49", "remaining_time": "9:27:42"}
+{"current_steps": 70, "total_steps": 735, "loss": 0.7579, "lr": 7.567567567567568e-05, "epoch": 0.4745762711864407, "percentage": 9.52, "elapsed_time": "0:59:39", "remaining_time": "9:26:40"}
+{"current_steps": 71, "total_steps": 735, "loss": 0.7488, "lr": 7.675675675675675e-05, "epoch": 0.48135593220338985, "percentage": 9.66, "elapsed_time": "1:00:29", "remaining_time": "9:25:39"}
+{"current_steps": 72, "total_steps": 735, "loss": 0.7715, "lr": 7.783783783783785e-05, "epoch": 0.488135593220339, "percentage": 9.8, "elapsed_time": "1:01:26", "remaining_time": "9:25:50"}
+{"current_steps": 73, "total_steps": 735, "loss": 0.7551, "lr": 7.891891891891892e-05, "epoch": 0.49491525423728816, "percentage": 9.93, "elapsed_time": "1:02:17", "remaining_time": "9:24:57"}
+{"current_steps": 74, "total_steps": 735, "loss": 0.7505, "lr": 8e-05, "epoch": 0.5016949152542373, "percentage": 10.07, "elapsed_time": "1:03:07", "remaining_time": "9:23:55"}
+{"current_steps": 75, "total_steps": 735, "loss": 0.7498, "lr": 7.999954822103665e-05, "epoch": 0.5084745762711864, "percentage": 10.2, "elapsed_time": "1:03:57", "remaining_time": "9:22:53"}
+{"current_steps": 76, "total_steps": 735, "loss": 0.7477, "lr": 7.999819289435179e-05, "epoch": 0.5152542372881356, "percentage": 10.34, "elapsed_time": "1:04:47", "remaining_time": "9:21:52"}
+{"current_steps": 77, "total_steps": 735, "loss": 0.7456, "lr": 7.999593405056084e-05, "epoch": 0.5220338983050847, "percentage": 10.48, "elapsed_time": "1:05:38", "remaining_time": "9:20:52"}
+{"current_steps": 78, "total_steps": 735, "loss": 0.7342, "lr": 7.999277174068872e-05, "epoch": 0.5288135593220339, "percentage": 10.61, "elapsed_time": "1:06:28", "remaining_time": "9:19:52"}
+{"current_steps": 79, "total_steps": 735, "loss": 0.7407, "lr": 7.998870603616864e-05, "epoch": 0.535593220338983, "percentage": 10.75, "elapsed_time": "1:07:18", "remaining_time": "9:18:53"}
+{"current_steps": 80, "total_steps": 735, "loss": 0.7466, "lr": 7.998373702884062e-05, "epoch": 0.5423728813559322, "percentage": 10.88, "elapsed_time": "1:08:08", "remaining_time": "9:17:53"}
+{"current_steps": 81, "total_steps": 735, "loss": 0.7642, "lr": 7.997786483094931e-05, "epoch": 0.5491525423728814, "percentage": 11.02, "elapsed_time": "1:08:58", "remaining_time": "9:16:53"}
+{"current_steps": 82, "total_steps": 735, "loss": 0.7273, "lr": 7.997108957514146e-05, "epoch": 0.5559322033898305, "percentage": 11.16, "elapsed_time": "1:09:48", "remaining_time": "9:15:52"}
+{"current_steps": 83, "total_steps": 735, "loss": 0.746, "lr": 7.9963411414463e-05, "epoch": 0.5627118644067797, "percentage": 11.29, "elapsed_time": "1:10:38", "remaining_time": "9:14:53"}
+{"current_steps": 84, "total_steps": 735, "loss": 0.7299, "lr": 7.99548305223555e-05, "epoch": 0.5694915254237288, "percentage": 11.43, "elapsed_time": "1:11:28", "remaining_time": "9:13:53"}
+{"current_steps": 85, "total_steps": 735, "loss": 0.7356, "lr": 7.994534709265226e-05, "epoch": 0.576271186440678, "percentage": 11.56, "elapsed_time": "1:12:18", "remaining_time": "9:12:55"}
+{"current_steps": 86, "total_steps": 735, "loss": 0.744, "lr": 7.993496133957401e-05, "epoch": 0.5830508474576271, "percentage": 11.7, "elapsed_time": "1:13:08", "remaining_time": "9:11:59"}
+{"current_steps": 87, "total_steps": 735, "loss": 0.7438, "lr": 7.992367349772398e-05, "epoch": 0.5898305084745763, "percentage": 11.84, "elapsed_time": "1:14:07", "remaining_time": "9:12:02"}
+{"current_steps": 88, "total_steps": 735, "loss": 0.7504, "lr": 7.991148382208265e-05, "epoch": 0.5966101694915255, "percentage": 11.97, "elapsed_time": "1:14:58", "remaining_time": "9:11:13"}
+{"current_steps": 89, "total_steps": 735, "loss": 0.7425, "lr": 7.989839258800196e-05, "epoch": 0.6033898305084746, "percentage": 12.11, "elapsed_time": "1:15:48", "remaining_time": "9:10:15"}
+{"current_steps": 90, "total_steps": 735, "loss": 0.7525, "lr": 7.988440009119911e-05, "epoch": 0.6101694915254238, "percentage": 12.24, "elapsed_time": "1:16:38", "remaining_time": "9:09:16"}
+{"current_steps": 91, "total_steps": 735, "loss": 0.7454, "lr": 7.986950664774992e-05, "epoch": 0.6169491525423729, "percentage": 12.38, "elapsed_time": "1:17:28", "remaining_time": "9:08:18"}
+{"current_steps": 92, "total_steps": 735, "loss": 0.7331, "lr": 7.985371259408157e-05, "epoch": 0.6237288135593221, "percentage": 12.52, "elapsed_time": "1:18:18", "remaining_time": "9:07:20"}
+{"current_steps": 93, "total_steps": 735, "loss": 0.7385, "lr": 7.983701828696515e-05, "epoch": 0.6305084745762712, "percentage": 12.65, "elapsed_time": "1:19:08", "remaining_time": "9:06:22"}
+{"current_steps": 94, "total_steps": 735, "loss": 0.7503, "lr": 7.98194241035075e-05, "epoch": 0.6372881355932203, "percentage": 12.79, "elapsed_time": "1:19:58", "remaining_time": "9:05:24"}
+{"current_steps": 95, "total_steps": 735, "loss": 0.7389, "lr": 7.980093044114269e-05, "epoch": 0.6440677966101694, "percentage": 12.93, "elapsed_time": "1:20:48", "remaining_time": "9:04:26"}
+{"current_steps": 96, "total_steps": 735, "loss": 0.7578, "lr": 7.978153771762311e-05, "epoch": 0.6508474576271186, "percentage": 13.06, "elapsed_time": "1:21:38", "remaining_time": "9:03:28"}
+{"current_steps": 97, "total_steps": 735, "loss": 0.7339, "lr": 7.976124637101e-05, "epoch": 0.6576271186440678, "percentage": 13.2, "elapsed_time": "1:22:29", "remaining_time": "9:02:31"}
+{"current_steps": 98, "total_steps": 735, "loss": 0.7268, "lr": 7.974005685966354e-05, "epoch": 0.6644067796610169, "percentage": 13.33, "elapsed_time": "1:23:19", "remaining_time": "9:01:33"}
+{"current_steps": 99, "total_steps": 735, "loss": 0.7472, "lr": 7.971796966223248e-05, "epoch": 0.6711864406779661, "percentage": 13.47, "elapsed_time": "1:24:08", "remaining_time": "9:00:35"}
+{"current_steps": 100, "total_steps": 735, "loss": 0.7295, "lr": 7.969498527764341e-05, "epoch": 0.6779661016949152, "percentage": 13.61, "elapsed_time": "1:24:58", "remaining_time": "8:59:38"}
+{"current_steps": 101, "total_steps": 735, "loss": 0.7232, "lr": 7.967110422508936e-05, "epoch": 0.6847457627118644, "percentage": 13.74, "elapsed_time": "1:25:49", "remaining_time": "8:58:42"}
+{"current_steps": 102, "total_steps": 735, "loss": 0.7471, "lr": 7.964632704401823e-05, "epoch": 0.6915254237288135, "percentage": 13.88, "elapsed_time": "1:26:49", "remaining_time": "8:58:50"}
+{"current_steps": 103, "total_steps": 735, "loss": 0.7301, "lr": 7.962065429412046e-05, "epoch": 0.6983050847457627, "percentage": 14.01, "elapsed_time": "1:27:40", "remaining_time": "8:57:59"}
+{"current_steps": 104, "total_steps": 735, "loss": 0.7366, "lr": 7.959408655531646e-05, "epoch": 0.7050847457627119, "percentage": 14.15, "elapsed_time": "1:28:30", "remaining_time": "8:57:02"}
+{"current_steps": 105, "total_steps": 735, "loss": 0.7207, "lr": 7.956662442774351e-05, "epoch": 0.711864406779661, "percentage": 14.29, "elapsed_time": "1:29:20", "remaining_time": "8:56:05"}
+{"current_steps": 106, "total_steps": 735, "loss": 0.721, "lr": 7.953826853174218e-05, "epoch": 0.7186440677966102, "percentage": 14.42, "elapsed_time": "1:30:11", "remaining_time": "8:55:08"}
+{"current_steps": 107, "total_steps": 735, "loss": 0.7206, "lr": 7.950901950784236e-05, "epoch": 0.7254237288135593, "percentage": 14.56, "elapsed_time": "1:31:01", "remaining_time": "8:54:12"}
+{"current_steps": 108, "total_steps": 735, "loss": 0.7203, "lr": 7.947887801674872e-05, "epoch": 0.7322033898305085, "percentage": 14.69, "elapsed_time": "1:31:51", "remaining_time": "8:53:15"}
+{"current_steps": 109, "total_steps": 735, "loss": 0.7236, "lr": 7.944784473932583e-05, "epoch": 0.7389830508474576, "percentage": 14.83, "elapsed_time": "1:32:41", "remaining_time": "8:52:19"}
+{"current_steps": 110, "total_steps": 735, "loss": 0.7149, "lr": 7.941592037658279e-05, "epoch": 0.7457627118644068, "percentage": 14.97, "elapsed_time": "1:33:31", "remaining_time": "8:51:22"}
+{"current_steps": 111, "total_steps": 735, "loss": 0.7193, "lr": 7.93831056496574e-05, "epoch": 0.752542372881356, "percentage": 15.1, "elapsed_time": "1:34:21", "remaining_time": "8:50:26"}
+{"current_steps": 112, "total_steps": 735, "loss": 0.7335, "lr": 7.934940129979979e-05, "epoch": 0.7593220338983051, "percentage": 15.24, "elapsed_time": "1:35:11", "remaining_time": "8:49:30"}
+{"current_steps": 113, "total_steps": 735, "loss": 0.7266, "lr": 7.931480808835577e-05, "epoch": 0.7661016949152543, "percentage": 15.37, "elapsed_time": "1:36:01", "remaining_time": "8:48:35"}
+{"current_steps": 114, "total_steps": 735, "loss": 0.7195, "lr": 7.927932679674964e-05, "epoch": 0.7728813559322034, "percentage": 15.51, "elapsed_time": "1:36:51", "remaining_time": "8:47:39"}
+{"current_steps": 115, "total_steps": 735, "loss": 0.726, "lr": 7.924295822646643e-05, "epoch": 0.7796610169491526, "percentage": 15.65, "elapsed_time": "1:37:41", "remaining_time": "8:46:43"}
+{"current_steps": 116, "total_steps": 735, "loss": 0.7215, "lr": 7.92057031990339e-05, "epoch": 0.7864406779661017, "percentage": 15.78, "elapsed_time": "1:38:32", "remaining_time": "8:45:50"}
+{"current_steps": 117, "total_steps": 735, "loss": 0.7205, "lr": 7.91675625560039e-05, "epoch": 0.7932203389830509, "percentage": 15.92, "elapsed_time": "1:39:32", "remaining_time": "8:45:46"}
+{"current_steps": 118, "total_steps": 735, "loss": 0.7069, "lr": 7.91285371589335e-05, "epoch": 0.8, "percentage": 16.05, "elapsed_time": "1:40:23", "remaining_time": "8:44:55"}
+{"current_steps": 119, "total_steps": 735, "loss": 0.718, "lr": 7.908862788936532e-05, "epoch": 0.8067796610169492, "percentage": 16.19, "elapsed_time": "1:41:13", "remaining_time": "8:43:58"}
+{"current_steps": 120, "total_steps": 735, "loss": 0.7151, "lr": 7.904783564880779e-05, "epoch": 0.8135593220338984, "percentage": 16.33, "elapsed_time": "1:42:03", "remaining_time": "8:43:02"}
+{"current_steps": 121, "total_steps": 735, "loss": 0.7392, "lr": 7.900616135871474e-05, "epoch": 0.8203389830508474, "percentage": 16.46, "elapsed_time": "1:42:53", "remaining_time": "8:42:06"}
+{"current_steps": 122, "total_steps": 735, "loss": 0.727, "lr": 7.896360596046453e-05, "epoch": 0.8271186440677966, "percentage": 16.6, "elapsed_time": "1:43:43", "remaining_time": "8:41:11"}
+{"current_steps": 123, "total_steps": 735, "loss": 0.7158, "lr": 7.892017041533886e-05, "epoch": 0.8338983050847457, "percentage": 16.73, "elapsed_time": "1:44:33", "remaining_time": "8:40:15"}
+{"current_steps": 124, "total_steps": 735, "loss": 0.7106, "lr": 7.887585570450098e-05, "epoch": 0.8406779661016949, "percentage": 16.87, "elapsed_time": "1:45:23", "remaining_time": "8:39:19"}
+{"current_steps": 125, "total_steps": 735, "loss": 0.7174, "lr": 7.883066282897362e-05, "epoch": 0.847457627118644, "percentage": 17.01, "elapsed_time": "1:46:14", "remaining_time": "8:38:25"}
+{"current_steps": 126, "total_steps": 735, "loss": 0.7141, "lr": 7.878459280961629e-05, "epoch": 0.8542372881355932, "percentage": 17.14, "elapsed_time": "1:47:04", "remaining_time": "8:37:30"}
+{"current_steps": 127, "total_steps": 735, "loss": 0.7163, "lr": 7.873764668710228e-05, "epoch": 0.8610169491525423, "percentage": 17.28, "elapsed_time": "1:47:54", "remaining_time": "8:36:34"}
+{"current_steps": 128, "total_steps": 735, "loss": 0.7121, "lr": 7.868982552189514e-05, "epoch": 0.8677966101694915, "percentage": 17.41, "elapsed_time": "1:48:44", "remaining_time": "8:35:39"}
+{"current_steps": 129, "total_steps": 735, "loss": 0.724, "lr": 7.864113039422464e-05, "epoch": 0.8745762711864407, "percentage": 17.55, "elapsed_time": "1:49:34", "remaining_time": "8:34:44"}
+{"current_steps": 130, "total_steps": 735, "loss": 0.7173, "lr": 7.859156240406252e-05, "epoch": 0.8813559322033898, "percentage": 17.69, "elapsed_time": "1:50:24", "remaining_time": "8:33:49"}
+{"current_steps": 131, "total_steps": 735, "loss": 0.7222, "lr": 7.854112267109756e-05, "epoch": 0.888135593220339, "percentage": 17.82, "elapsed_time": "1:51:14", "remaining_time": "8:32:55"}
+{"current_steps": 132, "total_steps": 735, "loss": 0.7114, "lr": 7.848981233471024e-05, "epoch": 0.8949152542372881, "percentage": 17.96, "elapsed_time": "1:52:16", "remaining_time": "8:32:53"}
+{"current_steps": 133, "total_steps": 735, "loss": 0.711, "lr": 7.843763255394711e-05, "epoch": 0.9016949152542373, "percentage": 18.1, "elapsed_time": "1:53:07", "remaining_time": "8:32:01"}
+{"current_steps": 134, "total_steps": 735, "loss": 0.7097, "lr": 7.838458450749452e-05, "epoch": 0.9084745762711864, "percentage": 18.23, "elapsed_time": "1:53:57", "remaining_time": "8:31:05"}
+{"current_steps": 135, "total_steps": 735, "loss": 0.7021, "lr": 7.833066939365206e-05, "epoch": 0.9152542372881356, "percentage": 18.37, "elapsed_time": "1:54:47", "remaining_time": "8:30:09"}
+{"current_steps": 136, "total_steps": 735, "loss": 0.721, "lr": 7.827588843030543e-05, "epoch": 0.9220338983050848, "percentage": 18.5, "elapsed_time": "1:55:37", "remaining_time": "8:29:13"}
+{"current_steps": 137, "total_steps": 735, "loss": 0.7287, "lr": 7.822024285489896e-05, "epoch": 0.9288135593220339, "percentage": 18.64, "elapsed_time": "1:56:26", "remaining_time": "8:28:17"}
+{"current_steps": 138, "total_steps": 735, "loss": 0.7221, "lr": 7.81637339244077e-05, "epoch": 0.9355932203389831, "percentage": 18.78, "elapsed_time": "1:57:16", "remaining_time": "8:27:22"}
+{"current_steps": 139, "total_steps": 735, "loss": 0.7095, "lr": 7.810636291530893e-05, "epoch": 0.9423728813559322, "percentage": 18.91, "elapsed_time": "1:58:06", "remaining_time": "8:26:27"}
+{"current_steps": 140, "total_steps": 735, "loss": 0.7221, "lr": 7.804813112355339e-05, "epoch": 0.9491525423728814, "percentage": 19.05, "elapsed_time": "1:58:57", "remaining_time": "8:25:32"}
+{"current_steps": 141, "total_steps": 735, "loss": 0.7193, "lr": 7.798903986453603e-05, "epoch": 0.9559322033898305, "percentage": 19.18, "elapsed_time": "1:59:46", "remaining_time": "8:24:37"}
+{"current_steps": 142, "total_steps": 735, "loss": 0.7272, "lr": 7.792909047306623e-05, "epoch": 0.9627118644067797, "percentage": 19.32, "elapsed_time": "2:00:37", "remaining_time": "8:23:42"}
+{"current_steps": 143, "total_steps": 735, "loss": 0.7147, "lr": 7.786828430333769e-05, "epoch": 0.9694915254237289, "percentage": 19.46, "elapsed_time": "2:01:27", "remaining_time": "8:22:47"}
+{"current_steps": 144, "total_steps": 735, "loss": 0.7214, "lr": 7.78066227288978e-05, "epoch": 0.976271186440678, "percentage": 19.59, "elapsed_time": "2:02:17", "remaining_time": "8:21:53"}
+{"current_steps": 145, "total_steps": 735, "loss": 0.7213, "lr": 7.77441071426167e-05, "epoch": 0.9830508474576272, "percentage": 19.73, "elapsed_time": "2:03:07", "remaining_time": "8:20:59"}
+{"current_steps": 146, "total_steps": 735, "loss": 0.7073, "lr": 7.768073895665573e-05, "epoch": 0.9898305084745763, "percentage": 19.86, "elapsed_time": "2:03:57", "remaining_time": "8:20:04"}
+{"current_steps": 147, "total_steps": 735, "loss": 0.7143, "lr": 7.761651960243554e-05, "epoch": 0.9966101694915255, "percentage": 20.0, "elapsed_time": "2:04:59", "remaining_time": "8:19:57"}
+{"current_steps": 148, "total_steps": 735, "loss": 1.1031, "lr": 7.755145053060378e-05, "epoch": 1.0033898305084745, "percentage": 20.14, "elapsed_time": "2:07:05", "remaining_time": "8:24:05"}
+{"current_steps": 149, "total_steps": 735, "loss": 0.6988, "lr": 7.748553321100238e-05, "epoch": 1.0101694915254238, "percentage": 20.27, "elapsed_time": "2:07:55", "remaining_time": "8:23:08"}
+{"current_steps": 150, "total_steps": 735, "loss": 0.7142, "lr": 7.741876913263422e-05, "epoch": 1.0169491525423728, "percentage": 20.41, "elapsed_time": "2:08:46", "remaining_time": "8:22:12"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2f66bdaa04c927a7e1651c888f3b02aff8a7730aa7e75de9099842cabe7dd3
+size 7160