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 sha256:65e52041bd73f87ccd2279ceb343fa1178be07265fc0f9c155849efc50a35f74
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953f71529ef4d489035b0616426038e83b67f30490c9ed2a944e374d181cf8bc
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ae8d7fd39273049ed6ddde3a437687351ad1814947b6f041b875dbd89aa0ae
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0581dc9af5f2690c1d95c3393481797eba7bf0bbcd7258ba14b81bae30935d20
+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 +1,201 @@
+{"current_steps": 1, "total_steps": 573, "loss": 1.0919, "lr": 1.7241379310344828e-07, "epoch": 0.005226480836236934, "percentage": 0.17, "elapsed_time": "0:00:17", "remaining_time": "2:48:06"}
+{"current_steps": 2, "total_steps": 573, "loss": 1.1216, "lr": 3.4482758620689656e-07, "epoch": 0.010452961672473868, "percentage": 0.35, "elapsed_time": "0:00:34", "remaining_time": "2:46:27"}
+{"current_steps": 3, "total_steps": 573, "loss": 1.0823, "lr": 5.172413793103449e-07, "epoch": 0.0156794425087108, "percentage": 0.52, "elapsed_time": "0:00:49", "remaining_time": "2:37:04"}
+{"current_steps": 4, "total_steps": 573, "loss": 1.1163, "lr": 6.896551724137931e-07, "epoch": 0.020905923344947737, "percentage": 0.7, "elapsed_time": "0:01:04", "remaining_time": "2:33:03"}
+{"current_steps": 5, "total_steps": 573, "loss": 1.0475, "lr": 8.620689655172415e-07, "epoch": 0.02613240418118467, "percentage": 0.87, "elapsed_time": "0:01:21", "remaining_time": "2:33:37"}
+{"current_steps": 6, "total_steps": 573, "loss": 1.0632, "lr": 1.0344827586206898e-06, "epoch": 0.0313588850174216, "percentage": 1.05, "elapsed_time": "0:01:35", "remaining_time": "2:30:48"}
+{"current_steps": 7, "total_steps": 573, "loss": 1.0867, "lr": 1.2068965517241381e-06, "epoch": 0.036585365853658534, "percentage": 1.22, "elapsed_time": "0:01:50", "remaining_time": "2:29:14"}
+{"current_steps": 8, "total_steps": 573, "loss": 1.0679, "lr": 1.3793103448275862e-06, "epoch": 0.041811846689895474, "percentage": 1.4, "elapsed_time": "0:02:03", "remaining_time": "2:25:13"}
+{"current_steps": 9, "total_steps": 573, "loss": 1.0599, "lr": 1.5517241379310346e-06, "epoch": 0.047038327526132406, "percentage": 1.57, "elapsed_time": "0:02:20", "remaining_time": "2:26:57"}
+{"current_steps": 10, "total_steps": 573, "loss": 1.0377, "lr": 1.724137931034483e-06, "epoch": 0.05226480836236934, "percentage": 1.75, "elapsed_time": "0:02:36", "remaining_time": "2:27:12"}
+{"current_steps": 11, "total_steps": 573, "loss": 0.9836, "lr": 1.896551724137931e-06, "epoch": 0.05749128919860627, "percentage": 1.92, "elapsed_time": "0:02:52", "remaining_time": "2:27:09"}
+{"current_steps": 12, "total_steps": 573, "loss": 1.0003, "lr": 2.0689655172413796e-06, "epoch": 0.0627177700348432, "percentage": 2.09, "elapsed_time": "0:03:09", "remaining_time": "2:27:57"}
+{"current_steps": 13, "total_steps": 573, "loss": 0.9805, "lr": 2.241379310344828e-06, "epoch": 0.06794425087108014, "percentage": 2.27, "elapsed_time": "0:03:24", "remaining_time": "2:27:07"}
+{"current_steps": 14, "total_steps": 573, "loss": 0.9785, "lr": 2.4137931034482762e-06, "epoch": 0.07317073170731707, "percentage": 2.44, "elapsed_time": "0:03:39", "remaining_time": "2:25:46"}
+{"current_steps": 15, "total_steps": 573, "loss": 0.9579, "lr": 2.5862068965517246e-06, "epoch": 0.078397212543554, "percentage": 2.62, "elapsed_time": "0:03:52", "remaining_time": "2:23:51"}
+{"current_steps": 16, "total_steps": 573, "loss": 0.9266, "lr": 2.7586206896551725e-06, "epoch": 0.08362369337979095, "percentage": 2.79, "elapsed_time": "0:04:08", "remaining_time": "2:24:27"}
+{"current_steps": 17, "total_steps": 573, "loss": 0.9496, "lr": 2.931034482758621e-06, "epoch": 0.08885017421602788, "percentage": 2.97, "elapsed_time": "0:04:25", "remaining_time": "2:24:43"}
+{"current_steps": 18, "total_steps": 573, "loss": 0.9417, "lr": 3.103448275862069e-06, "epoch": 0.09407665505226481, "percentage": 3.14, "elapsed_time": "0:04:39", "remaining_time": "2:23:32"}
+{"current_steps": 19, "total_steps": 573, "loss": 0.9133, "lr": 3.2758620689655175e-06, "epoch": 0.09930313588850175, "percentage": 3.32, "elapsed_time": "0:04:55", "remaining_time": "2:23:50"}
+{"current_steps": 20, "total_steps": 573, "loss": 0.9181, "lr": 3.448275862068966e-06, "epoch": 0.10452961672473868, "percentage": 3.49, "elapsed_time": "0:05:08", "remaining_time": "2:22:06"}
+{"current_steps": 21, "total_steps": 573, "loss": 0.8708, "lr": 3.620689655172414e-06, "epoch": 0.10975609756097561, "percentage": 3.66, "elapsed_time": "0:05:20", "remaining_time": "2:20:29"}
+{"current_steps": 22, "total_steps": 573, "loss": 0.8532, "lr": 3.793103448275862e-06, "epoch": 0.11498257839721254, "percentage": 3.84, "elapsed_time": "0:05:38", "remaining_time": "2:21:06"}
+{"current_steps": 23, "total_steps": 573, "loss": 0.867, "lr": 3.96551724137931e-06, "epoch": 0.12020905923344948, "percentage": 4.01, "elapsed_time": "0:05:51", "remaining_time": "2:19:56"}
+{"current_steps": 24, "total_steps": 573, "loss": 0.8596, "lr": 4.137931034482759e-06, "epoch": 0.1254355400696864, "percentage": 4.19, "elapsed_time": "0:06:06", "remaining_time": "2:19:45"}
+{"current_steps": 25, "total_steps": 573, "loss": 0.8119, "lr": 4.310344827586207e-06, "epoch": 0.13066202090592335, "percentage": 4.36, "elapsed_time": "0:06:21", "remaining_time": "2:19:15"}
+{"current_steps": 26, "total_steps": 573, "loss": 0.8374, "lr": 4.482758620689656e-06, "epoch": 0.13588850174216027, "percentage": 4.54, "elapsed_time": "0:06:36", "remaining_time": "2:19:03"}
+{"current_steps": 27, "total_steps": 573, "loss": 0.7917, "lr": 4.655172413793104e-06, "epoch": 0.14111498257839722, "percentage": 4.71, "elapsed_time": "0:06:53", "remaining_time": "2:19:28"}
+{"current_steps": 28, "total_steps": 573, "loss": 0.8187, "lr": 4.8275862068965525e-06, "epoch": 0.14634146341463414, "percentage": 4.89, "elapsed_time": "0:07:08", "remaining_time": "2:19:05"}
+{"current_steps": 29, "total_steps": 573, "loss": 0.8106, "lr": 5e-06, "epoch": 0.15156794425087108, "percentage": 5.06, "elapsed_time": "0:07:25", "remaining_time": "2:19:08"}
+{"current_steps": 30, "total_steps": 573, "loss": 0.7807, "lr": 5.172413793103449e-06, "epoch": 0.156794425087108, "percentage": 5.24, "elapsed_time": "0:07:42", "remaining_time": "2:19:27"}
+{"current_steps": 31, "total_steps": 573, "loss": 0.7987, "lr": 5.344827586206896e-06, "epoch": 0.16202090592334495, "percentage": 5.41, "elapsed_time": "0:07:57", "remaining_time": "2:19:13"}
+{"current_steps": 32, "total_steps": 573, "loss": 0.7978, "lr": 5.517241379310345e-06, "epoch": 0.1672473867595819, "percentage": 5.58, "elapsed_time": "0:08:08", "remaining_time": "2:17:43"}
+{"current_steps": 33, "total_steps": 573, "loss": 0.7872, "lr": 5.689655172413794e-06, "epoch": 0.17247386759581881, "percentage": 5.76, "elapsed_time": "0:08:23", "remaining_time": "2:17:16"}
+{"current_steps": 34, "total_steps": 573, "loss": 0.7704, "lr": 5.862068965517242e-06, "epoch": 0.17770034843205576, "percentage": 5.93, "elapsed_time": "0:08:38", "remaining_time": "2:16:59"}
+{"current_steps": 35, "total_steps": 573, "loss": 0.7581, "lr": 6.03448275862069e-06, "epoch": 0.18292682926829268, "percentage": 6.11, "elapsed_time": "0:08:51", "remaining_time": "2:16:05"}
+{"current_steps": 36, "total_steps": 573, "loss": 0.7787, "lr": 6.206896551724138e-06, "epoch": 0.18815331010452963, "percentage": 6.28, "elapsed_time": "0:09:06", "remaining_time": "2:15:46"}
+{"current_steps": 37, "total_steps": 573, "loss": 0.745, "lr": 6.379310344827587e-06, "epoch": 0.19337979094076654, "percentage": 6.46, "elapsed_time": "0:09:21", "remaining_time": "2:15:29"}
+{"current_steps": 38, "total_steps": 573, "loss": 0.7604, "lr": 6.551724137931035e-06, "epoch": 0.1986062717770035, "percentage": 6.63, "elapsed_time": "0:09:36", "remaining_time": "2:15:11"}
+{"current_steps": 39, "total_steps": 573, "loss": 0.7544, "lr": 6.724137931034484e-06, "epoch": 0.2038327526132404, "percentage": 6.81, "elapsed_time": "0:09:49", "remaining_time": "2:14:25"}
+{"current_steps": 40, "total_steps": 573, "loss": 0.732, "lr": 6.896551724137932e-06, "epoch": 0.20905923344947736, "percentage": 6.98, "elapsed_time": "0:10:05", "remaining_time": "2:14:23"}
+{"current_steps": 41, "total_steps": 573, "loss": 0.7297, "lr": 7.0689655172413796e-06, "epoch": 0.21428571428571427, "percentage": 7.16, "elapsed_time": "0:10:17", "remaining_time": "2:13:36"}
+{"current_steps": 42, "total_steps": 573, "loss": 0.7383, "lr": 7.241379310344828e-06, "epoch": 0.21951219512195122, "percentage": 7.33, "elapsed_time": "0:10:31", "remaining_time": "2:12:59"}
+{"current_steps": 43, "total_steps": 573, "loss": 0.7461, "lr": 7.413793103448277e-06, "epoch": 0.22473867595818817, "percentage": 7.5, "elapsed_time": "0:10:48", "remaining_time": "2:13:18"}
+{"current_steps": 44, "total_steps": 573, "loss": 0.7343, "lr": 7.586206896551724e-06, "epoch": 0.22996515679442509, "percentage": 7.68, "elapsed_time": "0:11:04", "remaining_time": "2:13:06"}
+{"current_steps": 45, "total_steps": 573, "loss": 0.7211, "lr": 7.758620689655173e-06, "epoch": 0.23519163763066203, "percentage": 7.85, "elapsed_time": "0:11:19", "remaining_time": "2:12:56"}
+{"current_steps": 46, "total_steps": 573, "loss": 0.7307, "lr": 7.93103448275862e-06, "epoch": 0.24041811846689895, "percentage": 8.03, "elapsed_time": "0:11:36", "remaining_time": "2:12:54"}
+{"current_steps": 47, "total_steps": 573, "loss": 0.7244, "lr": 8.103448275862069e-06, "epoch": 0.2456445993031359, "percentage": 8.2, "elapsed_time": "0:11:50", "remaining_time": "2:12:29"}
+{"current_steps": 48, "total_steps": 573, "loss": 0.7222, "lr": 8.275862068965518e-06, "epoch": 0.2508710801393728, "percentage": 8.38, "elapsed_time": "0:12:04", "remaining_time": "2:12:07"}
+{"current_steps": 49, "total_steps": 573, "loss": 0.7325, "lr": 8.448275862068966e-06, "epoch": 0.25609756097560976, "percentage": 8.55, "elapsed_time": "0:12:20", "remaining_time": "2:11:54"}
+{"current_steps": 50, "total_steps": 573, "loss": 0.7166, "lr": 8.620689655172414e-06, "epoch": 0.2613240418118467, "percentage": 8.73, "elapsed_time": "0:12:35", "remaining_time": "2:11:43"}
+{"current_steps": 51, "total_steps": 573, "loss": 0.7367, "lr": 8.793103448275862e-06, "epoch": 0.2665505226480836, "percentage": 8.9, "elapsed_time": "0:12:49", "remaining_time": "2:11:20"}
+{"current_steps": 52, "total_steps": 573, "loss": 0.7104, "lr": 8.965517241379312e-06, "epoch": 0.27177700348432055, "percentage": 9.08, "elapsed_time": "0:13:02", "remaining_time": "2:10:44"}
+{"current_steps": 53, "total_steps": 573, "loss": 0.7183, "lr": 9.13793103448276e-06, "epoch": 0.2770034843205575, "percentage": 9.25, "elapsed_time": "0:13:17", "remaining_time": "2:10:20"}
+{"current_steps": 54, "total_steps": 573, "loss": 0.7153, "lr": 9.310344827586207e-06, "epoch": 0.28222996515679444, "percentage": 9.42, "elapsed_time": "0:13:31", "remaining_time": "2:10:02"}
+{"current_steps": 55, "total_steps": 573, "loss": 0.7093, "lr": 9.482758620689655e-06, "epoch": 0.2874564459930314, "percentage": 9.6, "elapsed_time": "0:13:49", "remaining_time": "2:10:08"}
+{"current_steps": 56, "total_steps": 573, "loss": 0.7176, "lr": 9.655172413793105e-06, "epoch": 0.2926829268292683, "percentage": 9.77, "elapsed_time": "0:14:03", "remaining_time": "2:09:50"}
+{"current_steps": 57, "total_steps": 573, "loss": 0.7211, "lr": 9.827586206896553e-06, "epoch": 0.2979094076655052, "percentage": 9.95, "elapsed_time": "0:14:17", "remaining_time": "2:09:26"}
+{"current_steps": 58, "total_steps": 573, "loss": 0.6993, "lr": 1e-05, "epoch": 0.30313588850174217, "percentage": 10.12, "elapsed_time": "0:14:30", "remaining_time": "2:08:46"}
+{"current_steps": 59, "total_steps": 573, "loss": 0.6963, "lr": 9.999906969801156e-06, "epoch": 0.3083623693379791, "percentage": 10.3, "elapsed_time": "0:14:48", "remaining_time": "2:09:02"}
+{"current_steps": 60, "total_steps": 573, "loss": 0.7151, "lr": 9.999627882666474e-06, "epoch": 0.313588850174216, "percentage": 10.47, "elapsed_time": "0:15:03", "remaining_time": "2:08:45"}
+{"current_steps": 61, "total_steps": 573, "loss": 0.7049, "lr": 9.999162748981362e-06, "epoch": 0.31881533101045295, "percentage": 10.65, "elapsed_time": "0:15:19", "remaining_time": "2:08:39"}
+{"current_steps": 62, "total_steps": 573, "loss": 0.7013, "lr": 9.998511586054415e-06, "epoch": 0.3240418118466899, "percentage": 10.82, "elapsed_time": "0:15:34", "remaining_time": "2:08:18"}
+{"current_steps": 63, "total_steps": 573, "loss": 0.717, "lr": 9.997674418116759e-06, "epoch": 0.32926829268292684, "percentage": 10.99, "elapsed_time": "0:15:44", "remaining_time": "2:07:22"}
+{"current_steps": 64, "total_steps": 573, "loss": 0.6952, "lr": 9.996651276321153e-06, "epoch": 0.3344947735191638, "percentage": 11.17, "elapsed_time": "0:16:02", "remaining_time": "2:07:32"}
+{"current_steps": 65, "total_steps": 573, "loss": 0.701, "lr": 9.995442198740832e-06, "epoch": 0.3397212543554007, "percentage": 11.34, "elapsed_time": "0:16:16", "remaining_time": "2:07:11"}
+{"current_steps": 66, "total_steps": 573, "loss": 0.7124, "lr": 9.994047230368087e-06, "epoch": 0.34494773519163763, "percentage": 11.52, "elapsed_time": "0:16:31", "remaining_time": "2:06:57"}
+{"current_steps": 67, "total_steps": 573, "loss": 0.7041, "lr": 9.99246642311259e-06, "epoch": 0.3501742160278746, "percentage": 11.69, "elapsed_time": "0:16:46", "remaining_time": "2:06:43"}
+{"current_steps": 68, "total_steps": 573, "loss": 0.6885, "lr": 9.99069983579947e-06, "epoch": 0.3554006968641115, "percentage": 11.87, "elapsed_time": "0:17:00", "remaining_time": "2:06:18"}
+{"current_steps": 69, "total_steps": 573, "loss": 0.7179, "lr": 9.988747534167112e-06, "epoch": 0.3606271777003484, "percentage": 12.04, "elapsed_time": "0:17:16", "remaining_time": "2:06:09"}
+{"current_steps": 70, "total_steps": 573, "loss": 0.6955, "lr": 9.98660959086472e-06, "epoch": 0.36585365853658536, "percentage": 12.22, "elapsed_time": "0:17:30", "remaining_time": "2:05:49"}
+{"current_steps": 71, "total_steps": 573, "loss": 0.6903, "lr": 9.98428608544961e-06, "epoch": 0.3710801393728223, "percentage": 12.39, "elapsed_time": "0:17:44", "remaining_time": "2:05:28"}
+{"current_steps": 72, "total_steps": 573, "loss": 0.7082, "lr": 9.981777104384251e-06, "epoch": 0.37630662020905925, "percentage": 12.57, "elapsed_time": "0:18:01", "remaining_time": "2:05:26"}
+{"current_steps": 73, "total_steps": 573, "loss": 0.6768, "lr": 9.979082741033047e-06, "epoch": 0.38153310104529614, "percentage": 12.74, "elapsed_time": "0:18:18", "remaining_time": "2:05:25"}
+{"current_steps": 74, "total_steps": 573, "loss": 0.6761, "lr": 9.976203095658859e-06, "epoch": 0.3867595818815331, "percentage": 12.91, "elapsed_time": "0:18:32", "remaining_time": "2:05:03"}
+{"current_steps": 75, "total_steps": 573, "loss": 0.6934, "lr": 9.97313827541928e-06, "epoch": 0.39198606271777003, "percentage": 13.09, "elapsed_time": "0:18:48", "remaining_time": "2:04:55"}
+{"current_steps": 76, "total_steps": 573, "loss": 0.7041, "lr": 9.969888394362648e-06, "epoch": 0.397212543554007, "percentage": 13.26, "elapsed_time": "0:19:02", "remaining_time": "2:04:33"}
+{"current_steps": 77, "total_steps": 573, "loss": 0.6945, "lr": 9.96645357342379e-06, "epoch": 0.4024390243902439, "percentage": 13.44, "elapsed_time": "0:19:19", "remaining_time": "2:04:27"}
+{"current_steps": 78, "total_steps": 573, "loss": 0.696, "lr": 9.96283394041954e-06, "epoch": 0.4076655052264808, "percentage": 13.61, "elapsed_time": "0:19:37", "remaining_time": "2:04:30"}
+{"current_steps": 79, "total_steps": 573, "loss": 0.691, "lr": 9.959029630043969e-06, "epoch": 0.41289198606271776, "percentage": 13.79, "elapsed_time": "0:19:51", "remaining_time": "2:04:08"}
+{"current_steps": 80, "total_steps": 573, "loss": 0.692, "lr": 9.955040783863373e-06, "epoch": 0.4181184668989547, "percentage": 13.96, "elapsed_time": "0:20:04", "remaining_time": "2:03:44"}
+{"current_steps": 81, "total_steps": 573, "loss": 0.7196, "lr": 9.950867550311019e-06, "epoch": 0.42334494773519166, "percentage": 14.14, "elapsed_time": "0:20:19", "remaining_time": "2:03:25"}
+{"current_steps": 82, "total_steps": 573, "loss": 0.6726, "lr": 9.946510084681602e-06, "epoch": 0.42857142857142855, "percentage": 14.31, "elapsed_time": "0:20:36", "remaining_time": "2:03:24"}
+{"current_steps": 83, "total_steps": 573, "loss": 0.6897, "lr": 9.941968549125481e-06, "epoch": 0.4337979094076655, "percentage": 14.49, "elapsed_time": "0:20:52", "remaining_time": "2:03:12"}
+{"current_steps": 84, "total_steps": 573, "loss": 0.6918, "lr": 9.937243112642639e-06, "epoch": 0.43902439024390244, "percentage": 14.66, "elapsed_time": "0:21:08", "remaining_time": "2:03:07"}
+{"current_steps": 85, "total_steps": 573, "loss": 0.6766, "lr": 9.932333951076395e-06, "epoch": 0.4442508710801394, "percentage": 14.83, "elapsed_time": "0:21:24", "remaining_time": "2:02:56"}
+{"current_steps": 86, "total_steps": 573, "loss": 0.695, "lr": 9.927241247106856e-06, "epoch": 0.44947735191637633, "percentage": 15.01, "elapsed_time": "0:21:37", "remaining_time": "2:02:26"}
+{"current_steps": 87, "total_steps": 573, "loss": 0.6534, "lr": 9.921965190244129e-06, "epoch": 0.4547038327526132, "percentage": 15.18, "elapsed_time": "0:21:52", "remaining_time": "2:02:10"}
+{"current_steps": 88, "total_steps": 573, "loss": 0.6964, "lr": 9.916505976821262e-06, "epoch": 0.45993031358885017, "percentage": 15.36, "elapsed_time": "0:22:07", "remaining_time": "2:01:54"}
+{"current_steps": 89, "total_steps": 573, "loss": 0.6948, "lr": 9.910863809986942e-06, "epoch": 0.4651567944250871, "percentage": 15.53, "elapsed_time": "0:22:23", "remaining_time": "2:01:45"}
+{"current_steps": 90, "total_steps": 573, "loss": 0.6748, "lr": 9.905038899697924e-06, "epoch": 0.47038327526132406, "percentage": 15.71, "elapsed_time": "0:22:37", "remaining_time": "2:01:27"}
+{"current_steps": 91, "total_steps": 573, "loss": 0.698, "lr": 9.899031462711237e-06, "epoch": 0.47560975609756095, "percentage": 15.88, "elapsed_time": "0:22:51", "remaining_time": "2:01:05"}
+{"current_steps": 92, "total_steps": 573, "loss": 0.6839, "lr": 9.892841722576103e-06, "epoch": 0.4808362369337979, "percentage": 16.06, "elapsed_time": "0:23:06", "remaining_time": "2:00:50"}
+{"current_steps": 93, "total_steps": 573, "loss": 0.6865, "lr": 9.886469909625624e-06, "epoch": 0.48606271777003485, "percentage": 16.23, "elapsed_time": "0:23:22", "remaining_time": "2:00:39"}
+{"current_steps": 94, "total_steps": 573, "loss": 0.6693, "lr": 9.879916260968212e-06, "epoch": 0.4912891986062718, "percentage": 16.4, "elapsed_time": "0:23:35", "remaining_time": "2:00:10"}
+{"current_steps": 95, "total_steps": 573, "loss": 0.6812, "lr": 9.87318102047876e-06, "epoch": 0.4965156794425087, "percentage": 16.58, "elapsed_time": "0:23:49", "remaining_time": "1:59:51"}
+{"current_steps": 96, "total_steps": 573, "loss": 0.686, "lr": 9.866264438789573e-06, "epoch": 0.5017421602787456, "percentage": 16.75, "elapsed_time": "0:24:01", "remaining_time": "1:59:20"}
+{"current_steps": 97, "total_steps": 573, "loss": 0.7037, "lr": 9.85916677328104e-06, "epoch": 0.5069686411149826, "percentage": 16.93, "elapsed_time": "0:24:16", "remaining_time": "1:59:07"}
+{"current_steps": 98, "total_steps": 573, "loss": 0.7037, "lr": 9.851888288072053e-06, "epoch": 0.5121951219512195, "percentage": 17.1, "elapsed_time": "0:24:31", "remaining_time": "1:58:52"}
+{"current_steps": 99, "total_steps": 573, "loss": 0.6969, "lr": 9.844429254010184e-06, "epoch": 0.5174216027874564, "percentage": 17.28, "elapsed_time": "0:24:47", "remaining_time": "1:58:42"}
+{"current_steps": 100, "total_steps": 573, "loss": 0.6879, "lr": 9.836789948661602e-06, "epoch": 0.5226480836236934, "percentage": 17.45, "elapsed_time": "0:25:02", "remaining_time": "1:58:27"}
+{"current_steps": 101, "total_steps": 573, "loss": 0.6898, "lr": 9.828970656300743e-06, "epoch": 0.5278745644599303, "percentage": 17.63, "elapsed_time": "0:25:17", "remaining_time": "1:58:13"}
+{"current_steps": 102, "total_steps": 573, "loss": 0.6778, "lr": 9.82097166789974e-06, "epoch": 0.5331010452961672, "percentage": 17.8, "elapsed_time": "0:25:34", "remaining_time": "1:58:04"}
+{"current_steps": 103, "total_steps": 573, "loss": 0.6882, "lr": 9.81279328111758e-06, "epoch": 0.5383275261324042, "percentage": 17.98, "elapsed_time": "0:25:47", "remaining_time": "1:57:39"}
+{"current_steps": 104, "total_steps": 573, "loss": 0.6893, "lr": 9.804435800289047e-06, "epoch": 0.5435540069686411, "percentage": 18.15, "elapsed_time": "0:26:02", "remaining_time": "1:57:27"}
+{"current_steps": 105, "total_steps": 573, "loss": 0.663, "lr": 9.795899536413383e-06, "epoch": 0.5487804878048781, "percentage": 18.32, "elapsed_time": "0:26:18", "remaining_time": "1:57:13"}
+{"current_steps": 106, "total_steps": 573, "loss": 0.6782, "lr": 9.787184807142713e-06, "epoch": 0.554006968641115, "percentage": 18.5, "elapsed_time": "0:26:35", "remaining_time": "1:57:08"}
+{"current_steps": 107, "total_steps": 573, "loss": 0.6948, "lr": 9.778291936770241e-06, "epoch": 0.5592334494773519, "percentage": 18.67, "elapsed_time": "0:26:48", "remaining_time": "1:56:44"}
+{"current_steps": 108, "total_steps": 573, "loss": 0.6855, "lr": 9.769221256218165e-06, "epoch": 0.5644599303135889, "percentage": 18.85, "elapsed_time": "0:27:04", "remaining_time": "1:56:33"}
+{"current_steps": 109, "total_steps": 573, "loss": 0.6692, "lr": 9.759973103025369e-06, "epoch": 0.5696864111498258, "percentage": 19.02, "elapsed_time": "0:27:20", "remaining_time": "1:56:22"}
+{"current_steps": 110, "total_steps": 573, "loss": 0.6881, "lr": 9.750547821334868e-06, "epoch": 0.5749128919860628, "percentage": 19.2, "elapsed_time": "0:27:36", "remaining_time": "1:56:11"}
+{"current_steps": 111, "total_steps": 573, "loss": 0.6483, "lr": 9.740945761880993e-06, "epoch": 0.5801393728222997, "percentage": 19.37, "elapsed_time": "0:27:52", "remaining_time": "1:56:01"}
+{"current_steps": 112, "total_steps": 573, "loss": 0.6573, "lr": 9.731167281976346e-06, "epoch": 0.5853658536585366, "percentage": 19.55, "elapsed_time": "0:28:10", "remaining_time": "1:55:59"}
+{"current_steps": 113, "total_steps": 573, "loss": 0.6831, "lr": 9.721212745498493e-06, "epoch": 0.5905923344947736, "percentage": 19.72, "elapsed_time": "0:28:27", "remaining_time": "1:55:49"}
+{"current_steps": 114, "total_steps": 573, "loss": 0.6883, "lr": 9.711082522876445e-06, "epoch": 0.5958188153310104, "percentage": 19.9, "elapsed_time": "0:28:42", "remaining_time": "1:55:36"}
+{"current_steps": 115, "total_steps": 573, "loss": 0.6826, "lr": 9.700776991076846e-06, "epoch": 0.6010452961672473, "percentage": 20.07, "elapsed_time": "0:28:55", "remaining_time": "1:55:11"}
+{"current_steps": 116, "total_steps": 573, "loss": 0.6669, "lr": 9.690296533589967e-06, "epoch": 0.6062717770034843, "percentage": 20.24, "elapsed_time": "0:29:07", "remaining_time": "1:54:45"}
+{"current_steps": 117, "total_steps": 573, "loss": 0.6659, "lr": 9.679641540415428e-06, "epoch": 0.6114982578397212, "percentage": 20.42, "elapsed_time": "0:29:24", "remaining_time": "1:54:36"}
+{"current_steps": 118, "total_steps": 573, "loss": 0.6597, "lr": 9.66881240804768e-06, "epoch": 0.6167247386759582, "percentage": 20.59, "elapsed_time": "0:29:39", "remaining_time": "1:54:20"}
+{"current_steps": 119, "total_steps": 573, "loss": 0.6831, "lr": 9.657809539461256e-06, "epoch": 0.6219512195121951, "percentage": 20.77, "elapsed_time": "0:29:55", "remaining_time": "1:54:09"}
+{"current_steps": 120, "total_steps": 573, "loss": 0.666, "lr": 9.64663334409578e-06, "epoch": 0.627177700348432, "percentage": 20.94, "elapsed_time": "0:30:05", "remaining_time": "1:53:36"}
+{"current_steps": 121, "total_steps": 573, "loss": 0.6553, "lr": 9.635284237840721e-06, "epoch": 0.632404181184669, "percentage": 21.12, "elapsed_time": "0:30:18", "remaining_time": "1:53:14"}
+{"current_steps": 122, "total_steps": 573, "loss": 0.6771, "lr": 9.623762643019927e-06, "epoch": 0.6376306620209059, "percentage": 21.29, "elapsed_time": "0:30:34", "remaining_time": "1:53:00"}
+{"current_steps": 123, "total_steps": 573, "loss": 0.6715, "lr": 9.612068988375898e-06, "epoch": 0.6428571428571429, "percentage": 21.47, "elapsed_time": "0:30:47", "remaining_time": "1:52:40"}
+{"current_steps": 124, "total_steps": 573, "loss": 0.6514, "lr": 9.60020370905384e-06, "epoch": 0.6480836236933798, "percentage": 21.64, "elapsed_time": "0:31:03", "remaining_time": "1:52:28"}
+{"current_steps": 125, "total_steps": 573, "loss": 0.6459, "lr": 9.588167246585474e-06, "epoch": 0.6533101045296167, "percentage": 21.82, "elapsed_time": "0:31:19", "remaining_time": "1:52:14"}
+{"current_steps": 126, "total_steps": 573, "loss": 0.6896, "lr": 9.575960048872595e-06, "epoch": 0.6585365853658537, "percentage": 21.99, "elapsed_time": "0:31:32", "remaining_time": "1:51:55"}
+{"current_steps": 127, "total_steps": 573, "loss": 0.6613, "lr": 9.563582570170418e-06, "epoch": 0.6637630662020906, "percentage": 22.16, "elapsed_time": "0:31:48", "remaining_time": "1:51:41"}
+{"current_steps": 128, "total_steps": 573, "loss": 0.6516, "lr": 9.551035271070665e-06, "epoch": 0.6689895470383276, "percentage": 22.34, "elapsed_time": "0:32:03", "remaining_time": "1:51:27"}
+{"current_steps": 129, "total_steps": 573, "loss": 0.6618, "lr": 9.538318618484426e-06, "epoch": 0.6742160278745645, "percentage": 22.51, "elapsed_time": "0:32:17", "remaining_time": "1:51:09"}
+{"current_steps": 130, "total_steps": 573, "loss": 0.6864, "lr": 9.52543308562479e-06, "epoch": 0.6794425087108014, "percentage": 22.69, "elapsed_time": "0:32:34", "remaining_time": "1:50:59"}
+{"current_steps": 131, "total_steps": 573, "loss": 0.6784, "lr": 9.512379151989229e-06, "epoch": 0.6846689895470384, "percentage": 22.86, "elapsed_time": "0:32:51", "remaining_time": "1:50:50"}
+{"current_steps": 132, "total_steps": 573, "loss": 0.6653, "lr": 9.499157303341761e-06, "epoch": 0.6898954703832753, "percentage": 23.04, "elapsed_time": "0:33:07", "remaining_time": "1:50:39"}
+{"current_steps": 133, "total_steps": 573, "loss": 0.6731, "lr": 9.485768031694872e-06, "epoch": 0.6951219512195121, "percentage": 23.21, "elapsed_time": "0:33:21", "remaining_time": "1:50:23"}
+{"current_steps": 134, "total_steps": 573, "loss": 0.6663, "lr": 9.4722118352912e-06, "epoch": 0.7003484320557491, "percentage": 23.39, "elapsed_time": "0:33:38", "remaining_time": "1:50:11"}
+{"current_steps": 135, "total_steps": 573, "loss": 0.655, "lr": 9.458489218585003e-06, "epoch": 0.705574912891986, "percentage": 23.56, "elapsed_time": "0:33:54", "remaining_time": "1:50:00"}
+{"current_steps": 136, "total_steps": 573, "loss": 0.6749, "lr": 9.44460069222339e-06, "epoch": 0.710801393728223, "percentage": 23.73, "elapsed_time": "0:34:08", "remaining_time": "1:49:42"}
+{"current_steps": 137, "total_steps": 573, "loss": 0.6686, "lr": 9.430546773027302e-06, "epoch": 0.7160278745644599, "percentage": 23.91, "elapsed_time": "0:34:24", "remaining_time": "1:49:28"}
+{"current_steps": 138, "total_steps": 573, "loss": 0.6594, "lr": 9.416327983972304e-06, "epoch": 0.7212543554006968, "percentage": 24.08, "elapsed_time": "0:34:37", "remaining_time": "1:49:08"}
+{"current_steps": 139, "total_steps": 573, "loss": 0.6749, "lr": 9.401944854169103e-06, "epoch": 0.7264808362369338, "percentage": 24.26, "elapsed_time": "0:34:50", "remaining_time": "1:48:47"}
+{"current_steps": 140, "total_steps": 573, "loss": 0.6579, "lr": 9.38739791884387e-06, "epoch": 0.7317073170731707, "percentage": 24.43, "elapsed_time": "0:35:01", "remaining_time": "1:48:20"}
+{"current_steps": 141, "total_steps": 573, "loss": 0.681, "lr": 9.372687719318316e-06, "epoch": 0.7369337979094077, "percentage": 24.61, "elapsed_time": "0:35:13", "remaining_time": "1:47:55"}
+{"current_steps": 142, "total_steps": 573, "loss": 0.6666, "lr": 9.35781480298956e-06, "epoch": 0.7421602787456446, "percentage": 24.78, "elapsed_time": "0:35:25", "remaining_time": "1:47:32"}
+{"current_steps": 143, "total_steps": 573, "loss": 0.6238, "lr": 9.342779723309746e-06, "epoch": 0.7473867595818815, "percentage": 24.96, "elapsed_time": "0:35:42", "remaining_time": "1:47:22"}
+{"current_steps": 144, "total_steps": 573, "loss": 0.6637, "lr": 9.327583039765453e-06, "epoch": 0.7526132404181185, "percentage": 25.13, "elapsed_time": "0:35:57", "remaining_time": "1:47:06"}
+{"current_steps": 145, "total_steps": 573, "loss": 0.6523, "lr": 9.31222531785688e-06, "epoch": 0.7578397212543554, "percentage": 25.31, "elapsed_time": "0:36:12", "remaining_time": "1:46:52"}
+{"current_steps": 146, "total_steps": 573, "loss": 0.6626, "lr": 9.296707129076794e-06, "epoch": 0.7630662020905923, "percentage": 25.48, "elapsed_time": "0:36:25", "remaining_time": "1:46:33"}
+{"current_steps": 147, "total_steps": 573, "loss": 0.6786, "lr": 9.281029050889274e-06, "epoch": 0.7682926829268293, "percentage": 25.65, "elapsed_time": "0:36:40", "remaining_time": "1:46:17"}
+{"current_steps": 148, "total_steps": 573, "loss": 0.6861, "lr": 9.26519166670821e-06, "epoch": 0.7735191637630662, "percentage": 25.83, "elapsed_time": "0:36:58", "remaining_time": "1:46:10"}
+{"current_steps": 149, "total_steps": 573, "loss": 0.6591, "lr": 9.2491955658756e-06, "epoch": 0.7787456445993032, "percentage": 26.0, "elapsed_time": "0:37:13", "remaining_time": "1:45:55"}
+{"current_steps": 150, "total_steps": 573, "loss": 0.6881, "lr": 9.233041343639623e-06, "epoch": 0.7839721254355401, "percentage": 26.18, "elapsed_time": "0:37:26", "remaining_time": "1:45:35"}
+{"current_steps": 151, "total_steps": 573, "loss": 0.6702, "lr": 9.216729601132481e-06, "epoch": 0.789198606271777, "percentage": 26.35, "elapsed_time": "0:37:43", "remaining_time": "1:45:24"}
+{"current_steps": 152, "total_steps": 573, "loss": 0.6652, "lr": 9.200260945348034e-06, "epoch": 0.794425087108014, "percentage": 26.53, "elapsed_time": "0:37:56", "remaining_time": "1:45:04"}
+{"current_steps": 153, "total_steps": 573, "loss": 0.6569, "lr": 9.183635989119211e-06, "epoch": 0.7996515679442509, "percentage": 26.7, "elapsed_time": "0:38:13", "remaining_time": "1:44:54"}
+{"current_steps": 154, "total_steps": 573, "loss": 0.6629, "lr": 9.166855351095205e-06, "epoch": 0.8048780487804879, "percentage": 26.88, "elapsed_time": "0:38:25", "remaining_time": "1:44:32"}
+{"current_steps": 155, "total_steps": 573, "loss": 0.6615, "lr": 9.149919655718453e-06, "epoch": 0.8101045296167247, "percentage": 27.05, "elapsed_time": "0:38:37", "remaining_time": "1:44:10"}
+{"current_steps": 156, "total_steps": 573, "loss": 0.6321, "lr": 9.132829533201397e-06, "epoch": 0.8153310104529616, "percentage": 27.23, "elapsed_time": "0:38:50", "remaining_time": "1:43:50"}
+{"current_steps": 157, "total_steps": 573, "loss": 0.6471, "lr": 9.115585619503039e-06, "epoch": 0.8205574912891986, "percentage": 27.4, "elapsed_time": "0:39:02", "remaining_time": "1:43:27"}
+{"current_steps": 158, "total_steps": 573, "loss": 0.6748, "lr": 9.098188556305262e-06, "epoch": 0.8257839721254355, "percentage": 27.57, "elapsed_time": "0:39:16", "remaining_time": "1:43:09"}
+{"current_steps": 159, "total_steps": 573, "loss": 0.6564, "lr": 9.080638990988971e-06, "epoch": 0.8310104529616724, "percentage": 27.75, "elapsed_time": "0:39:26", "remaining_time": "1:42:43"}
+{"current_steps": 160, "total_steps": 573, "loss": 0.654, "lr": 9.062937576609983e-06, "epoch": 0.8362369337979094, "percentage": 27.92, "elapsed_time": "0:39:38", "remaining_time": "1:42:20"}
+{"current_steps": 161, "total_steps": 573, "loss": 0.6558, "lr": 9.045084971874738e-06, "epoch": 0.8414634146341463, "percentage": 28.1, "elapsed_time": "0:39:54", "remaining_time": "1:42:08"}
+{"current_steps": 162, "total_steps": 573, "loss": 0.6663, "lr": 9.027081841115784e-06, "epoch": 0.8466898954703833, "percentage": 28.27, "elapsed_time": "0:40:12", "remaining_time": "1:41:59"}
+{"current_steps": 163, "total_steps": 573, "loss": 0.6443, "lr": 9.008928854267054e-06, "epoch": 0.8519163763066202, "percentage": 28.45, "elapsed_time": "0:40:26", "remaining_time": "1:41:43"}
+{"current_steps": 164, "total_steps": 573, "loss": 0.6536, "lr": 8.99062668683894e-06, "epoch": 0.8571428571428571, "percentage": 28.62, "elapsed_time": "0:40:40", "remaining_time": "1:41:27"}
+{"current_steps": 165, "total_steps": 573, "loss": 0.6579, "lr": 8.97217601989315e-06, "epoch": 0.8623693379790941, "percentage": 28.8, "elapsed_time": "0:40:57", "remaining_time": "1:41:17"}
+{"current_steps": 166, "total_steps": 573, "loss": 0.6713, "lr": 8.95357754001737e-06, "epoch": 0.867595818815331, "percentage": 28.97, "elapsed_time": "0:41:13", "remaining_time": "1:41:04"}
+{"current_steps": 167, "total_steps": 573, "loss": 0.6696, "lr": 8.934831939299715e-06, "epoch": 0.872822299651568, "percentage": 29.14, "elapsed_time": "0:41:28", "remaining_time": "1:40:50"}
+{"current_steps": 168, "total_steps": 573, "loss": 0.6584, "lr": 8.91593991530297e-06, "epoch": 0.8780487804878049, "percentage": 29.32, "elapsed_time": "0:41:47", "remaining_time": "1:40:44"}
+{"current_steps": 169, "total_steps": 573, "loss": 0.6529, "lr": 8.896902171038629e-06, "epoch": 0.8832752613240418, "percentage": 29.49, "elapsed_time": "0:42:03", "remaining_time": "1:40:32"}
+{"current_steps": 170, "total_steps": 573, "loss": 0.6816, "lr": 8.877719414940751e-06, "epoch": 0.8885017421602788, "percentage": 29.67, "elapsed_time": "0:42:13", "remaining_time": "1:40:06"}
+{"current_steps": 171, "total_steps": 573, "loss": 0.6591, "lr": 8.85839236083958e-06, "epoch": 0.8937282229965157, "percentage": 29.84, "elapsed_time": "0:42:28", "remaining_time": "1:39:50"}
+{"current_steps": 172, "total_steps": 573, "loss": 0.6725, "lr": 8.838921727934992e-06, "epoch": 0.8989547038327527, "percentage": 30.02, "elapsed_time": "0:42:39", "remaining_time": "1:39:26"}
+{"current_steps": 173, "total_steps": 573, "loss": 0.663, "lr": 8.819308240769726e-06, "epoch": 0.9041811846689896, "percentage": 30.19, "elapsed_time": "0:42:56", "remaining_time": "1:39:16"}
+{"current_steps": 174, "total_steps": 573, "loss": 0.6593, "lr": 8.799552629202424e-06, "epoch": 0.9094076655052264, "percentage": 30.37, "elapsed_time": "0:43:11", "remaining_time": "1:39:02"}
+{"current_steps": 175, "total_steps": 573, "loss": 0.6366, "lr": 8.779655628380479e-06, "epoch": 0.9146341463414634, "percentage": 30.54, "elapsed_time": "0:43:27", "remaining_time": "1:38:49"}
+{"current_steps": 176, "total_steps": 573, "loss": 0.6588, "lr": 8.759617978712667e-06, "epoch": 0.9198606271777003, "percentage": 30.72, "elapsed_time": "0:43:43", "remaining_time": "1:38:37"}
+{"current_steps": 177, "total_steps": 573, "loss": 0.6708, "lr": 8.7394404258416e-06, "epoch": 0.9250871080139372, "percentage": 30.89, "elapsed_time": "0:43:56", "remaining_time": "1:38:19"}
+{"current_steps": 178, "total_steps": 573, "loss": 0.6581, "lr": 8.71912372061598e-06, "epoch": 0.9303135888501742, "percentage": 31.06, "elapsed_time": "0:44:12", "remaining_time": "1:38:05"}
+{"current_steps": 179, "total_steps": 573, "loss": 0.675, "lr": 8.69866861906266e-06, "epoch": 0.9355400696864111, "percentage": 31.24, "elapsed_time": "0:44:29", "remaining_time": "1:37:55"}
+{"current_steps": 180, "total_steps": 573, "loss": 0.6315, "lr": 8.678075882358506e-06, "epoch": 0.9407665505226481, "percentage": 31.41, "elapsed_time": "0:44:44", "remaining_time": "1:37:40"}
+{"current_steps": 181, "total_steps": 573, "loss": 0.6407, "lr": 8.657346276802071e-06, "epoch": 0.945993031358885, "percentage": 31.59, "elapsed_time": "0:44:58", "remaining_time": "1:37:23"}
+{"current_steps": 182, "total_steps": 573, "loss": 0.6665, "lr": 8.636480573785089e-06, "epoch": 0.9512195121951219, "percentage": 31.76, "elapsed_time": "0:45:08", "remaining_time": "1:36:59"}
+{"current_steps": 183, "total_steps": 573, "loss": 0.6618, "lr": 8.615479549763756e-06, "epoch": 0.9564459930313589, "percentage": 31.94, "elapsed_time": "0:45:22", "remaining_time": "1:36:42"}
+{"current_steps": 184, "total_steps": 573, "loss": 0.6773, "lr": 8.594343986229854e-06, "epoch": 0.9616724738675958, "percentage": 32.11, "elapsed_time": "0:45:37", "remaining_time": "1:36:28"}
+{"current_steps": 185, "total_steps": 573, "loss": 0.6429, "lr": 8.57307466968165e-06, "epoch": 0.9668989547038328, "percentage": 32.29, "elapsed_time": "0:45:52", "remaining_time": "1:36:13"}
+{"current_steps": 186, "total_steps": 573, "loss": 0.6735, "lr": 8.551672391594646e-06, "epoch": 0.9721254355400697, "percentage": 32.46, "elapsed_time": "0:46:09", "remaining_time": "1:36:01"}
+{"current_steps": 187, "total_steps": 573, "loss": 0.6614, "lr": 8.530137948392113e-06, "epoch": 0.9773519163763066, "percentage": 32.64, "elapsed_time": "0:46:27", "remaining_time": "1:35:53"}
+{"current_steps": 188, "total_steps": 573, "loss": 0.6539, "lr": 8.508472141415468e-06, "epoch": 0.9825783972125436, "percentage": 32.81, "elapsed_time": "0:46:43", "remaining_time": "1:35:40"}
+{"current_steps": 189, "total_steps": 573, "loss": 0.6346, "lr": 8.48667577689444e-06, "epoch": 0.9878048780487805, "percentage": 32.98, "elapsed_time": "0:46:57", "remaining_time": "1:35:25"}
+{"current_steps": 190, "total_steps": 573, "loss": 0.6626, "lr": 8.46474966591708e-06, "epoch": 0.9930313588850174, "percentage": 33.16, "elapsed_time": "0:47:12", "remaining_time": "1:35:09"}
+{"current_steps": 191, "total_steps": 573, "loss": 0.6604, "lr": 8.442694624399576e-06, "epoch": 0.9982578397212544, "percentage": 33.33, "elapsed_time": "0:47:27", "remaining_time": "1:34:54"}
+{"current_steps": 192, "total_steps": 573, "loss": 1.0489, "lr": 8.420511473055887e-06, "epoch": 1.0034843205574913, "percentage": 33.51, "elapsed_time": "0:49:31", "remaining_time": "1:38:16"}
+{"current_steps": 193, "total_steps": 573, "loss": 0.6419, "lr": 8.398201037367202e-06, "epoch": 1.0087108013937283, "percentage": 33.68, "elapsed_time": "0:49:46", "remaining_time": "1:38:00"}
+{"current_steps": 194, "total_steps": 573, "loss": 0.6137, "lr": 8.37576414755123e-06, "epoch": 1.0139372822299653, "percentage": 33.86, "elapsed_time": "0:50:02", "remaining_time": "1:37:45"}
+{"current_steps": 195, "total_steps": 573, "loss": 0.6243, "lr": 8.3532016385313e-06, "epoch": 1.019163763066202, "percentage": 34.03, "elapsed_time": "0:50:19", "remaining_time": "1:37:34"}
+{"current_steps": 196, "total_steps": 573, "loss": 0.6368, "lr": 8.330514349905295e-06, "epoch": 1.024390243902439, "percentage": 34.21, "elapsed_time": "0:50:35", "remaining_time": "1:37:18"}
+{"current_steps": 197, "total_steps": 573, "loss": 0.5435, "lr": 8.307703125914397e-06, "epoch": 1.029616724738676, "percentage": 34.38, "elapsed_time": "0:50:49", "remaining_time": "1:37:00"}
+{"current_steps": 198, "total_steps": 573, "loss": 0.6031, "lr": 8.284768815411693e-06, "epoch": 1.0348432055749128, "percentage": 34.55, "elapsed_time": "0:51:06", "remaining_time": "1:36:47"}
+{"current_steps": 199, "total_steps": 573, "loss": 0.5943, "lr": 8.261712271830564e-06, "epoch": 1.0400696864111498, "percentage": 34.73, "elapsed_time": "0:51:19", "remaining_time": "1:36:27"}
+{"current_steps": 200, "total_steps": 573, "loss": 0.5491, "lr": 8.23853435315295e-06, "epoch": 1.0452961672473868, "percentage": 34.9, "elapsed_time": "0:51:32", "remaining_time": "1:36:07"}
+{"current_steps": 201, "total_steps": 573, "loss": 0.5604, "lr": 8.215235921877403e-06, "epoch": 1.0505226480836236, "percentage": 35.08, "elapsed_time": "0:51:49", "remaining_time": "1:35:54"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d0c0c83c1ae29f3d9779f18c0d8aeb84fa40342b927b3137f8d15a6ef3390d
+size 7352