Training in progress, step 200

.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 +1,28 @@
+{
+  "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": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.2",
+  "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 sha256:7c15c505c3b6de5105ebeb0b331ab52bdffddfb839482e2e82bd938ca6f29578
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d9bb2f70bfc64cc1d46e11ffe5c15a21647591b9a4ebfdf95642a5098d0dfb
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09fb0729e6b233aeb827057c0afe0aa802185fe79366738ca6253960cba7ceb0
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea06a4f5eed26ec00e251e3b269076fbf986590a3a34589e2bc8e911a9f4f66
+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": "<|im_end|>",
+    "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 +1,209 @@
+{
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "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 +1,214 @@
+{"current_steps": 1, "total_steps": 567, "loss": 1.678, "lr": 0.0, "epoch": 0.005279366476022877, "percentage": 0.18, "elapsed_time": "0:02:01", "remaining_time": "19:10:00"}
+{"current_steps": 1, "total_steps": 378, "loss": 1.7456, "lr": 0.0, "epoch": 0.007920792079207921, "percentage": 0.26, "elapsed_time": "0:03:24", "remaining_time": "21:26:26"}
+{"current_steps": 2, "total_steps": 378, "loss": 1.7255, "lr": 2.6315789473684213e-07, "epoch": 0.015841584158415842, "percentage": 0.53, "elapsed_time": "0:07:23", "remaining_time": "23:10:59"}
+{"current_steps": 3, "total_steps": 378, "loss": 1.7724, "lr": 5.263157894736843e-07, "epoch": 0.023762376237623763, "percentage": 0.79, "elapsed_time": "0:11:04", "remaining_time": "23:04:05"}
+{"current_steps": 4, "total_steps": 378, "loss": 1.7355, "lr": 7.894736842105263e-07, "epoch": 0.031683168316831684, "percentage": 1.06, "elapsed_time": "0:14:35", "remaining_time": "22:44:45"}
+{"current_steps": 5, "total_steps": 378, "loss": 1.7437, "lr": 1.0526315789473685e-06, "epoch": 0.039603960396039604, "percentage": 1.32, "elapsed_time": "0:17:36", "remaining_time": "21:53:50"}
+{"current_steps": 6, "total_steps": 378, "loss": 1.7268, "lr": 1.3157894736842106e-06, "epoch": 0.047524752475247525, "percentage": 1.59, "elapsed_time": "0:20:55", "remaining_time": "21:37:26"}
+{"current_steps": 7, "total_steps": 378, "loss": 1.7184, "lr": 1.5789473684210526e-06, "epoch": 0.055445544554455446, "percentage": 1.85, "elapsed_time": "0:24:19", "remaining_time": "21:29:26"}
+{"current_steps": 8, "total_steps": 378, "loss": 1.7595, "lr": 1.8421052631578948e-06, "epoch": 0.06336633663366337, "percentage": 2.12, "elapsed_time": "0:27:00", "remaining_time": "20:49:26"}
+{"current_steps": 9, "total_steps": 378, "loss": 1.6533, "lr": 2.105263157894737e-06, "epoch": 0.07128712871287128, "percentage": 2.38, "elapsed_time": "0:30:19", "remaining_time": "20:43:15"}
+{"current_steps": 10, "total_steps": 378, "loss": 1.5203, "lr": 2.368421052631579e-06, "epoch": 0.07920792079207921, "percentage": 2.65, "elapsed_time": "0:34:20", "remaining_time": "21:03:36"}
+{"current_steps": 11, "total_steps": 378, "loss": 1.5747, "lr": 2.631578947368421e-06, "epoch": 0.08712871287128712, "percentage": 2.91, "elapsed_time": "0:36:52", "remaining_time": "20:30:32"}
+{"current_steps": 12, "total_steps": 378, "loss": 1.6309, "lr": 2.8947368421052634e-06, "epoch": 0.09504950495049505, "percentage": 3.17, "elapsed_time": "0:40:13", "remaining_time": "20:27:02"}
+{"current_steps": 1, "total_steps": 567, "loss": 1.678, "lr": 0.0, "epoch": 0.005279366476022877, "percentage": 0.18, "elapsed_time": "0:01:48", "remaining_time": "17:06:34"}
+{"current_steps": 2, "total_steps": 567, "loss": 1.8487, "lr": 1.7543859649122808e-07, "epoch": 0.010558732952045754, "percentage": 0.35, "elapsed_time": "0:03:51", "remaining_time": "18:09:34"}
+{"current_steps": 3, "total_steps": 567, "loss": 1.6855, "lr": 3.5087719298245616e-07, "epoch": 0.01583809942806863, "percentage": 0.53, "elapsed_time": "0:06:23", "remaining_time": "20:02:35"}
+{"current_steps": 4, "total_steps": 567, "loss": 1.79, "lr": 5.263157894736843e-07, "epoch": 0.02111746590409151, "percentage": 0.71, "elapsed_time": "0:08:14", "remaining_time": "19:20:31"}
+{"current_steps": 5, "total_steps": 567, "loss": 1.6796, "lr": 7.017543859649123e-07, "epoch": 0.026396832380114386, "percentage": 0.88, "elapsed_time": "0:10:24", "remaining_time": "19:29:04"}
+{"current_steps": 6, "total_steps": 567, "loss": 1.8326, "lr": 8.771929824561404e-07, "epoch": 0.03167619885613726, "percentage": 1.06, "elapsed_time": "0:12:36", "remaining_time": "19:39:35"}
+{"current_steps": 7, "total_steps": 567, "loss": 1.7229, "lr": 1.0526315789473685e-06, "epoch": 0.03695556533216014, "percentage": 1.23, "elapsed_time": "0:14:30", "remaining_time": "19:21:06"}
+{"current_steps": 8, "total_steps": 567, "loss": 1.782, "lr": 1.2280701754385965e-06, "epoch": 0.04223493180818302, "percentage": 1.41, "elapsed_time": "0:16:17", "remaining_time": "18:58:04"}
+{"current_steps": 9, "total_steps": 567, "loss": 1.6596, "lr": 1.4035087719298246e-06, "epoch": 0.0475142982842059, "percentage": 1.59, "elapsed_time": "0:18:16", "remaining_time": "18:53:18"}
+{"current_steps": 10, "total_steps": 567, "loss": 1.6707, "lr": 1.5789473684210526e-06, "epoch": 0.05279366476022877, "percentage": 1.76, "elapsed_time": "0:20:20", "remaining_time": "18:53:10"}
+{"current_steps": 11, "total_steps": 567, "loss": 1.718, "lr": 1.7543859649122807e-06, "epoch": 0.05807303123625165, "percentage": 1.94, "elapsed_time": "0:21:58", "remaining_time": "18:31:05"}
+{"current_steps": 12, "total_steps": 567, "loss": 1.5939, "lr": 1.929824561403509e-06, "epoch": 0.06335239771227452, "percentage": 2.12, "elapsed_time": "0:23:38", "remaining_time": "18:13:29"}
+{"current_steps": 13, "total_steps": 567, "loss": 1.497, "lr": 2.105263157894737e-06, "epoch": 0.0686317641882974, "percentage": 2.29, "elapsed_time": "0:25:38", "remaining_time": "18:12:41"}
+{"current_steps": 14, "total_steps": 567, "loss": 1.4584, "lr": 2.280701754385965e-06, "epoch": 0.07391113066432028, "percentage": 2.47, "elapsed_time": "0:27:22", "remaining_time": "18:01:02"}
+{"current_steps": 15, "total_steps": 567, "loss": 1.4996, "lr": 2.456140350877193e-06, "epoch": 0.07919049714034315, "percentage": 2.65, "elapsed_time": "0:29:53", "remaining_time": "18:19:48"}
+{"current_steps": 16, "total_steps": 567, "loss": 1.4042, "lr": 2.631578947368421e-06, "epoch": 0.08446986361636603, "percentage": 2.82, "elapsed_time": "0:31:11", "remaining_time": "17:54:05"}
+{"current_steps": 17, "total_steps": 567, "loss": 1.4125, "lr": 2.8070175438596493e-06, "epoch": 0.08974923009238892, "percentage": 3.0, "elapsed_time": "0:32:39", "remaining_time": "17:36:21"}
+{"current_steps": 18, "total_steps": 567, "loss": 1.4723, "lr": 2.9824561403508774e-06, "epoch": 0.0950285965684118, "percentage": 3.17, "elapsed_time": "0:34:36", "remaining_time": "17:35:46"}
+{"current_steps": 19, "total_steps": 567, "loss": 1.2987, "lr": 3.157894736842105e-06, "epoch": 0.10030796304443466, "percentage": 3.35, "elapsed_time": "0:36:35", "remaining_time": "17:35:15"}
+{"current_steps": 20, "total_steps": 567, "loss": 1.2651, "lr": 3.3333333333333333e-06, "epoch": 0.10558732952045755, "percentage": 3.53, "elapsed_time": "0:38:21", "remaining_time": "17:28:57"}
+{"current_steps": 21, "total_steps": 567, "loss": 1.2512, "lr": 3.5087719298245615e-06, "epoch": 0.11086669599648043, "percentage": 3.7, "elapsed_time": "0:40:41", "remaining_time": "17:37:53"}
+{"current_steps": 22, "total_steps": 567, "loss": 1.3191, "lr": 3.6842105263157896e-06, "epoch": 0.1161460624725033, "percentage": 3.88, "elapsed_time": "0:42:24", "remaining_time": "17:30:44"}
+{"current_steps": 23, "total_steps": 567, "loss": 1.2354, "lr": 3.859649122807018e-06, "epoch": 0.12142542894852618, "percentage": 4.06, "elapsed_time": "0:44:45", "remaining_time": "17:38:36"}
+{"current_steps": 24, "total_steps": 567, "loss": 1.174, "lr": 4.035087719298246e-06, "epoch": 0.12670479542454904, "percentage": 4.23, "elapsed_time": "0:46:40", "remaining_time": "17:36:05"}
+{"current_steps": 25, "total_steps": 567, "loss": 1.2824, "lr": 4.210526315789474e-06, "epoch": 0.13198416190057194, "percentage": 4.41, "elapsed_time": "0:48:34", "remaining_time": "17:33:03"}
+{"current_steps": 26, "total_steps": 567, "loss": 1.2023, "lr": 4.385964912280702e-06, "epoch": 0.1372635283765948, "percentage": 4.59, "elapsed_time": "0:50:44", "remaining_time": "17:35:39"}
+{"current_steps": 27, "total_steps": 567, "loss": 1.1412, "lr": 4.56140350877193e-06, "epoch": 0.14254289485261767, "percentage": 4.76, "elapsed_time": "0:52:45", "remaining_time": "17:35:18"}
+{"current_steps": 28, "total_steps": 567, "loss": 1.1989, "lr": 4.736842105263158e-06, "epoch": 0.14782226132864057, "percentage": 4.94, "elapsed_time": "0:54:06", "remaining_time": "17:21:27"}
+{"current_steps": 29, "total_steps": 567, "loss": 1.0738, "lr": 4.912280701754386e-06, "epoch": 0.15310162780466344, "percentage": 5.11, "elapsed_time": "0:56:03", "remaining_time": "17:19:49"}
+{"current_steps": 30, "total_steps": 567, "loss": 1.0853, "lr": 5.087719298245615e-06, "epoch": 0.1583809942806863, "percentage": 5.29, "elapsed_time": "0:57:41", "remaining_time": "17:12:34"}
+{"current_steps": 31, "total_steps": 567, "loss": 1.061, "lr": 5.263157894736842e-06, "epoch": 0.1636603607567092, "percentage": 5.47, "elapsed_time": "0:59:40", "remaining_time": "17:11:42"}
+{"current_steps": 32, "total_steps": 567, "loss": 1.1496, "lr": 5.438596491228071e-06, "epoch": 0.16893972723273207, "percentage": 5.64, "elapsed_time": "1:01:25", "remaining_time": "17:07:02"}
+{"current_steps": 33, "total_steps": 567, "loss": 1.1424, "lr": 5.6140350877192985e-06, "epoch": 0.17421909370875496, "percentage": 5.82, "elapsed_time": "1:03:28", "remaining_time": "17:07:08"}
+{"current_steps": 34, "total_steps": 567, "loss": 1.0655, "lr": 5.789473684210527e-06, "epoch": 0.17949846018477783, "percentage": 6.0, "elapsed_time": "1:05:04", "remaining_time": "17:00:04"}
+{"current_steps": 35, "total_steps": 567, "loss": 1.0241, "lr": 5.964912280701755e-06, "epoch": 0.1847778266608007, "percentage": 6.17, "elapsed_time": "1:06:27", "remaining_time": "16:50:07"}
+{"current_steps": 36, "total_steps": 567, "loss": 1.0076, "lr": 6.140350877192983e-06, "epoch": 0.1900571931368236, "percentage": 6.35, "elapsed_time": "1:09:03", "remaining_time": "16:58:40"}
+{"current_steps": 37, "total_steps": 567, "loss": 1.0991, "lr": 6.31578947368421e-06, "epoch": 0.19533655961284646, "percentage": 6.53, "elapsed_time": "1:10:51", "remaining_time": "16:55:03"}
+{"current_steps": 38, "total_steps": 567, "loss": 1.0824, "lr": 6.491228070175439e-06, "epoch": 0.20061592608886933, "percentage": 6.7, "elapsed_time": "1:12:57", "remaining_time": "16:55:45"}
+{"current_steps": 39, "total_steps": 567, "loss": 0.994, "lr": 6.666666666666667e-06, "epoch": 0.20589529256489222, "percentage": 6.88, "elapsed_time": "1:15:05", "remaining_time": "16:56:33"}
+{"current_steps": 40, "total_steps": 567, "loss": 1.0583, "lr": 6.842105263157896e-06, "epoch": 0.2111746590409151, "percentage": 7.05, "elapsed_time": "1:17:14", "remaining_time": "16:57:44"}
+{"current_steps": 41, "total_steps": 567, "loss": 0.9892, "lr": 7.017543859649123e-06, "epoch": 0.21645402551693796, "percentage": 7.23, "elapsed_time": "1:19:19", "remaining_time": "16:57:38"}
+{"current_steps": 42, "total_steps": 567, "loss": 1.0051, "lr": 7.192982456140352e-06, "epoch": 0.22173339199296085, "percentage": 7.41, "elapsed_time": "1:20:47", "remaining_time": "16:49:51"}
+{"current_steps": 43, "total_steps": 567, "loss": 0.9833, "lr": 7.368421052631579e-06, "epoch": 0.22701275846898372, "percentage": 7.58, "elapsed_time": "1:22:36", "remaining_time": "16:46:42"}
+{"current_steps": 44, "total_steps": 567, "loss": 0.9793, "lr": 7.5438596491228074e-06, "epoch": 0.2322921249450066, "percentage": 7.76, "elapsed_time": "1:24:01", "remaining_time": "16:38:43"}
+{"current_steps": 45, "total_steps": 567, "loss": 0.9366, "lr": 7.719298245614036e-06, "epoch": 0.23757149142102948, "percentage": 7.94, "elapsed_time": "1:25:43", "remaining_time": "16:34:29"}
+{"current_steps": 46, "total_steps": 567, "loss": 0.9006, "lr": 7.894736842105265e-06, "epoch": 0.24285085789705235, "percentage": 8.11, "elapsed_time": "1:28:11", "remaining_time": "16:38:51"}
+{"current_steps": 47, "total_steps": 567, "loss": 0.9785, "lr": 8.070175438596492e-06, "epoch": 0.24813022437307522, "percentage": 8.29, "elapsed_time": "1:29:57", "remaining_time": "16:35:18"}
+{"current_steps": 48, "total_steps": 567, "loss": 0.9941, "lr": 8.24561403508772e-06, "epoch": 0.2534095908490981, "percentage": 8.47, "elapsed_time": "1:31:37", "remaining_time": "16:30:41"}
+{"current_steps": 49, "total_steps": 567, "loss": 0.938, "lr": 8.421052631578948e-06, "epoch": 0.258688957325121, "percentage": 8.64, "elapsed_time": "1:33:40", "remaining_time": "16:30:19"}
+{"current_steps": 50, "total_steps": 567, "loss": 1.009, "lr": 8.596491228070176e-06, "epoch": 0.2639683238011439, "percentage": 8.82, "elapsed_time": "1:35:27", "remaining_time": "16:27:03"}
+{"current_steps": 51, "total_steps": 567, "loss": 0.9557, "lr": 8.771929824561405e-06, "epoch": 0.2692476902771667, "percentage": 8.99, "elapsed_time": "1:37:01", "remaining_time": "16:21:41"}
+{"current_steps": 52, "total_steps": 567, "loss": 0.9773, "lr": 8.947368421052632e-06, "epoch": 0.2745270567531896, "percentage": 9.17, "elapsed_time": "1:39:10", "remaining_time": "16:22:17"}
+{"current_steps": 53, "total_steps": 567, "loss": 0.979, "lr": 9.12280701754386e-06, "epoch": 0.2798064232292125, "percentage": 9.35, "elapsed_time": "1:41:11", "remaining_time": "16:21:19"}
+{"current_steps": 54, "total_steps": 567, "loss": 0.9909, "lr": 9.298245614035088e-06, "epoch": 0.28508578970523535, "percentage": 9.52, "elapsed_time": "1:42:52", "remaining_time": "16:17:21"}
+{"current_steps": 55, "total_steps": 567, "loss": 0.9343, "lr": 9.473684210526315e-06, "epoch": 0.29036515618125824, "percentage": 9.7, "elapsed_time": "1:44:26", "remaining_time": "16:12:16"}
+{"current_steps": 56, "total_steps": 567, "loss": 0.9711, "lr": 9.649122807017545e-06, "epoch": 0.29564452265728114, "percentage": 9.88, "elapsed_time": "1:46:14", "remaining_time": "16:09:31"}
+{"current_steps": 57, "total_steps": 567, "loss": 1.0189, "lr": 9.824561403508772e-06, "epoch": 0.300923889133304, "percentage": 10.05, "elapsed_time": "1:48:26", "remaining_time": "16:10:13"}
+{"current_steps": 58, "total_steps": 567, "loss": 0.9581, "lr": 1e-05, "epoch": 0.3062032556093269, "percentage": 10.23, "elapsed_time": "1:49:48", "remaining_time": "16:03:43"}
+{"current_steps": 59, "total_steps": 567, "loss": 1.0108, "lr": 9.999905136743635e-06, "epoch": 0.31148262208534977, "percentage": 10.41, "elapsed_time": "1:51:36", "remaining_time": "16:01:01"}
+{"current_steps": 60, "total_steps": 567, "loss": 0.8755, "lr": 9.999620550574155e-06, "epoch": 0.3167619885613726, "percentage": 10.58, "elapsed_time": "1:53:36", "remaining_time": "16:00:02"}
+{"current_steps": 61, "total_steps": 567, "loss": 0.9038, "lr": 9.999146252290264e-06, "epoch": 0.3220413550373955, "percentage": 10.76, "elapsed_time": "1:55:14", "remaining_time": "15:55:54"}
+{"current_steps": 62, "total_steps": 567, "loss": 0.9326, "lr": 9.99848225988936e-06, "epoch": 0.3273207215134184, "percentage": 10.93, "elapsed_time": "1:57:11", "remaining_time": "15:54:29"}
+{"current_steps": 63, "total_steps": 567, "loss": 0.8677, "lr": 9.99762859856683e-06, "epoch": 0.33260008798944124, "percentage": 11.11, "elapsed_time": "1:58:54", "remaining_time": "15:51:14"}
+{"current_steps": 64, "total_steps": 567, "loss": 0.9299, "lr": 9.996585300715117e-06, "epoch": 0.33787945446546414, "percentage": 11.29, "elapsed_time": "2:00:24", "remaining_time": "15:46:19"}
+{"current_steps": 65, "total_steps": 567, "loss": 0.9017, "lr": 9.995352405922467e-06, "epoch": 0.34315882094148703, "percentage": 11.46, "elapsed_time": "2:02:09", "remaining_time": "15:43:24"}
+{"current_steps": 66, "total_steps": 567, "loss": 0.9452, "lr": 9.99392996097145e-06, "epoch": 0.3484381874175099, "percentage": 11.64, "elapsed_time": "2:04:00", "remaining_time": "15:41:17"}
+{"current_steps": 67, "total_steps": 567, "loss": 1.0884, "lr": 9.992318019837171e-06, "epoch": 0.35371755389353277, "percentage": 11.82, "elapsed_time": "2:06:01", "remaining_time": "15:40:26"}
+{"current_steps": 68, "total_steps": 567, "loss": 0.9171, "lr": 9.990516643685222e-06, "epoch": 0.35899692036955566, "percentage": 11.99, "elapsed_time": "2:07:54", "remaining_time": "15:38:39"}
+{"current_steps": 69, "total_steps": 567, "loss": 0.9075, "lr": 9.988525900869366e-06, "epoch": 0.36427628684557856, "percentage": 12.17, "elapsed_time": "2:09:32", "remaining_time": "15:34:59"}
+{"current_steps": 70, "total_steps": 567, "loss": 0.885, "lr": 9.98634586692894e-06, "epoch": 0.3695556533216014, "percentage": 12.35, "elapsed_time": "2:11:11", "remaining_time": "15:31:28"}
+{"current_steps": 71, "total_steps": 567, "loss": 0.9215, "lr": 9.983976624585996e-06, "epoch": 0.3748350197976243, "percentage": 12.52, "elapsed_time": "2:13:03", "remaining_time": "15:29:28"}
+{"current_steps": 72, "total_steps": 567, "loss": 0.9121, "lr": 9.981418263742148e-06, "epoch": 0.3801143862736472, "percentage": 12.7, "elapsed_time": "2:15:16", "remaining_time": "15:30:00"}
+{"current_steps": 73, "total_steps": 567, "loss": 0.8719, "lr": 9.978670881475173e-06, "epoch": 0.38539375274967, "percentage": 12.87, "elapsed_time": "2:16:45", "remaining_time": "15:25:24"}
+{"current_steps": 74, "total_steps": 567, "loss": 0.9158, "lr": 9.975734582035323e-06, "epoch": 0.3906731192256929, "percentage": 13.05, "elapsed_time": "2:19:14", "remaining_time": "15:27:37"}
+{"current_steps": 75, "total_steps": 567, "loss": 0.9519, "lr": 9.972609476841368e-06, "epoch": 0.3959524857017158, "percentage": 13.23, "elapsed_time": "2:21:10", "remaining_time": "15:26:04"}
+{"current_steps": 76, "total_steps": 567, "loss": 0.8892, "lr": 9.96929568447637e-06, "epoch": 0.40123185217773866, "percentage": 13.4, "elapsed_time": "2:22:41", "remaining_time": "15:21:54"}
+{"current_steps": 77, "total_steps": 567, "loss": 0.8749, "lr": 9.965793330683182e-06, "epoch": 0.40651121865376155, "percentage": 13.58, "elapsed_time": "2:24:24", "remaining_time": "15:18:59"}
+{"current_steps": 78, "total_steps": 567, "loss": 0.8218, "lr": 9.96210254835968e-06, "epoch": 0.41179058512978445, "percentage": 13.76, "elapsed_time": "2:26:18", "remaining_time": "15:17:13"}
+{"current_steps": 79, "total_steps": 567, "loss": 0.8215, "lr": 9.958223477553715e-06, "epoch": 0.4170699516058073, "percentage": 13.93, "elapsed_time": "2:28:01", "remaining_time": "15:14:25"}
+{"current_steps": 80, "total_steps": 567, "loss": 0.8103, "lr": 9.954156265457801e-06, "epoch": 0.4223493180818302, "percentage": 14.11, "elapsed_time": "2:29:45", "remaining_time": "15:11:36"}
+{"current_steps": 81, "total_steps": 567, "loss": 0.8992, "lr": 9.949901066403536e-06, "epoch": 0.4276286845578531, "percentage": 14.29, "elapsed_time": "2:31:49", "remaining_time": "15:10:55"}
+{"current_steps": 82, "total_steps": 567, "loss": 0.8831, "lr": 9.945458041855732e-06, "epoch": 0.4329080510338759, "percentage": 14.46, "elapsed_time": "2:33:31", "remaining_time": "15:08:03"}
+{"current_steps": 83, "total_steps": 567, "loss": 0.8843, "lr": 9.940827360406297e-06, "epoch": 0.4381874175098988, "percentage": 14.64, "elapsed_time": "2:35:24", "remaining_time": "15:06:15"}
+{"current_steps": 84, "total_steps": 567, "loss": 0.8714, "lr": 9.936009197767847e-06, "epoch": 0.4434667839859217, "percentage": 14.81, "elapsed_time": "2:37:11", "remaining_time": "15:03:51"}
+{"current_steps": 85, "total_steps": 567, "loss": 0.9267, "lr": 9.931003736767013e-06, "epoch": 0.44874615046194455, "percentage": 14.99, "elapsed_time": "2:38:52", "remaining_time": "15:00:55"}
+{"current_steps": 86, "total_steps": 567, "loss": 0.8765, "lr": 9.925811167337533e-06, "epoch": 0.45402551693796744, "percentage": 15.17, "elapsed_time": "2:40:34", "remaining_time": "14:58:07"}
+{"current_steps": 87, "total_steps": 567, "loss": 0.8835, "lr": 9.920431686513023e-06, "epoch": 0.45930488341399034, "percentage": 15.34, "elapsed_time": "2:42:27", "remaining_time": "14:56:21"}
+{"current_steps": 88, "total_steps": 567, "loss": 0.8557, "lr": 9.91486549841951e-06, "epoch": 0.4645842498900132, "percentage": 15.52, "elapsed_time": "2:44:12", "remaining_time": "14:53:48"}
+{"current_steps": 89, "total_steps": 567, "loss": 0.93, "lr": 9.909112814267686e-06, "epoch": 0.4698636163660361, "percentage": 15.7, "elapsed_time": "2:45:57", "remaining_time": "14:51:21"}
+{"current_steps": 90, "total_steps": 567, "loss": 0.8493, "lr": 9.903173852344889e-06, "epoch": 0.47514298284205897, "percentage": 15.87, "elapsed_time": "2:47:52", "remaining_time": "14:49:43"}
+{"current_steps": 91, "total_steps": 567, "loss": 0.9375, "lr": 9.89704883800683e-06, "epoch": 0.4804223493180818, "percentage": 16.05, "elapsed_time": "2:49:28", "remaining_time": "14:46:27"}
+{"current_steps": 92, "total_steps": 567, "loss": 0.8502, "lr": 9.890738003669029e-06, "epoch": 0.4857017157941047, "percentage": 16.23, "elapsed_time": "2:51:44", "remaining_time": "14:46:40"}
+{"current_steps": 93, "total_steps": 567, "loss": 0.8722, "lr": 9.884241588798004e-06, "epoch": 0.4909810822701276, "percentage": 16.4, "elapsed_time": "2:54:02", "remaining_time": "14:47:04"}
+{"current_steps": 94, "total_steps": 567, "loss": 0.9781, "lr": 9.877559839902185e-06, "epoch": 0.49626044874615044, "percentage": 16.58, "elapsed_time": "2:55:53", "remaining_time": "14:45:02"}
+{"current_steps": 95, "total_steps": 567, "loss": 0.9494, "lr": 9.870693010522552e-06, "epoch": 0.5015398152221734, "percentage": 16.75, "elapsed_time": "2:57:44", "remaining_time": "14:43:07"}
+{"current_steps": 96, "total_steps": 567, "loss": 0.8948, "lr": 9.863641361223025e-06, "epoch": 0.5068191816981962, "percentage": 16.93, "elapsed_time": "2:59:18", "remaining_time": "14:39:45"}
+{"current_steps": 97, "total_steps": 567, "loss": 0.9305, "lr": 9.85640515958057e-06, "epoch": 0.5120985481742191, "percentage": 17.11, "elapsed_time": "3:01:22", "remaining_time": "14:38:48"}
+{"current_steps": 98, "total_steps": 567, "loss": 1.0241, "lr": 9.848984680175049e-06, "epoch": 0.517377914650242, "percentage": 17.28, "elapsed_time": "3:03:25", "remaining_time": "14:37:50"}
+{"current_steps": 99, "total_steps": 567, "loss": 0.8869, "lr": 9.841380204578795e-06, "epoch": 0.5226572811262649, "percentage": 17.46, "elapsed_time": "3:05:10", "remaining_time": "14:35:23"}
+{"current_steps": 100, "total_steps": 567, "loss": 0.8854, "lr": 9.833592021345938e-06, "epoch": 0.5279366476022878, "percentage": 17.64, "elapsed_time": "3:07:07", "remaining_time": "14:33:53"}
+{"current_steps": 101, "total_steps": 567, "loss": 0.9243, "lr": 9.825620426001446e-06, "epoch": 0.5332160140783107, "percentage": 17.81, "elapsed_time": "3:08:58", "remaining_time": "14:31:54"}
+{"current_steps": 102, "total_steps": 567, "loss": 0.8645, "lr": 9.817465721029916e-06, "epoch": 0.5384953805543334, "percentage": 17.99, "elapsed_time": "3:11:08", "remaining_time": "14:31:22"}
+{"current_steps": 103, "total_steps": 567, "loss": 0.9064, "lr": 9.809128215864096e-06, "epoch": 0.5437747470303563, "percentage": 18.17, "elapsed_time": "3:13:02", "remaining_time": "14:29:37"}
+{"current_steps": 104, "total_steps": 567, "loss": 0.8828, "lr": 9.800608226873143e-06, "epoch": 0.5490541135063792, "percentage": 18.34, "elapsed_time": "3:15:16", "remaining_time": "14:29:22"}
+{"current_steps": 105, "total_steps": 567, "loss": 0.8687, "lr": 9.791906077350613e-06, "epoch": 0.5543334799824021, "percentage": 18.52, "elapsed_time": "3:17:06", "remaining_time": "14:27:15"}
+{"current_steps": 106, "total_steps": 567, "loss": 1.0081, "lr": 9.783022097502204e-06, "epoch": 0.559612846458425, "percentage": 18.69, "elapsed_time": "3:18:51", "remaining_time": "14:24:50"}
+{"current_steps": 107, "total_steps": 567, "loss": 0.8988, "lr": 9.773956624433224e-06, "epoch": 0.5648922129344479, "percentage": 18.87, "elapsed_time": "3:20:53", "remaining_time": "14:23:40"}
+{"current_steps": 108, "total_steps": 567, "loss": 0.8097, "lr": 9.764710002135784e-06, "epoch": 0.5701715794104707, "percentage": 19.05, "elapsed_time": "3:22:46", "remaining_time": "14:21:46"}
+{"current_steps": 109, "total_steps": 567, "loss": 0.8707, "lr": 9.755282581475769e-06, "epoch": 0.5754509458864936, "percentage": 19.22, "elapsed_time": "3:24:28", "remaining_time": "14:19:10"}
+{"current_steps": 110, "total_steps": 567, "loss": 0.913, "lr": 9.745674720179507e-06, "epoch": 0.5807303123625165, "percentage": 19.4, "elapsed_time": "3:26:00", "remaining_time": "14:15:50"}
+{"current_steps": 111, "total_steps": 567, "loss": 0.8495, "lr": 9.735886782820202e-06, "epoch": 0.5860096788385394, "percentage": 19.58, "elapsed_time": "3:28:06", "remaining_time": "14:14:56"}
+{"current_steps": 112, "total_steps": 567, "loss": 0.7694, "lr": 9.7259191408041e-06, "epoch": 0.5912890453145623, "percentage": 19.75, "elapsed_time": "3:29:37", "remaining_time": "14:11:36"}
+{"current_steps": 113, "total_steps": 567, "loss": 0.8874, "lr": 9.715772172356388e-06, "epoch": 0.5965684117905852, "percentage": 19.93, "elapsed_time": "3:31:18", "remaining_time": "14:08:56"}
+{"current_steps": 114, "total_steps": 567, "loss": 0.9887, "lr": 9.705446262506858e-06, "epoch": 0.601847778266608, "percentage": 20.11, "elapsed_time": "3:32:49", "remaining_time": "14:05:43"}
+{"current_steps": 115, "total_steps": 567, "loss": 0.8731, "lr": 9.694941803075285e-06, "epoch": 0.6071271447426309, "percentage": 20.28, "elapsed_time": "3:34:45", "remaining_time": "14:04:07"}
+{"current_steps": 116, "total_steps": 567, "loss": 0.8773, "lr": 9.684259192656554e-06, "epoch": 0.6124065112186537, "percentage": 20.46, "elapsed_time": "3:36:31", "remaining_time": "14:01:51"}
+{"current_steps": 117, "total_steps": 567, "loss": 0.9415, "lr": 9.673398836605554e-06, "epoch": 0.6176858776946766, "percentage": 20.63, "elapsed_time": "3:37:59", "remaining_time": "13:58:26"}
+{"current_steps": 118, "total_steps": 567, "loss": 0.8214, "lr": 9.66236114702178e-06, "epoch": 0.6229652441706995, "percentage": 20.81, "elapsed_time": "3:39:35", "remaining_time": "13:55:33"}
+{"current_steps": 119, "total_steps": 567, "loss": 0.9561, "lr": 9.651146542733702e-06, "epoch": 0.6282446106467224, "percentage": 20.99, "elapsed_time": "3:40:57", "remaining_time": "13:51:48"}
+{"current_steps": 120, "total_steps": 567, "loss": 0.8812, "lr": 9.639755449282874e-06, "epoch": 0.6335239771227452, "percentage": 21.16, "elapsed_time": "3:42:38", "remaining_time": "13:49:22"}
+{"current_steps": 121, "total_steps": 567, "loss": 0.803, "lr": 9.628188298907782e-06, "epoch": 0.6388033435987681, "percentage": 21.34, "elapsed_time": "3:44:41", "remaining_time": "13:48:11"}
+{"current_steps": 122, "total_steps": 567, "loss": 0.8159, "lr": 9.616445530527448e-06, "epoch": 0.644082710074791, "percentage": 21.52, "elapsed_time": "3:46:36", "remaining_time": "13:46:34"}
+{"current_steps": 123, "total_steps": 567, "loss": 0.8846, "lr": 9.60452758972477e-06, "epoch": 0.6493620765508139, "percentage": 21.69, "elapsed_time": "3:48:26", "remaining_time": "13:44:36"}
+{"current_steps": 124, "total_steps": 567, "loss": 0.7621, "lr": 9.592434928729617e-06, "epoch": 0.6546414430268368, "percentage": 21.87, "elapsed_time": "3:50:10", "remaining_time": "13:42:19"}
+{"current_steps": 125, "total_steps": 567, "loss": 0.9327, "lr": 9.58016800640167e-06, "epoch": 0.6599208095028597, "percentage": 22.05, "elapsed_time": "3:51:55", "remaining_time": "13:40:05"}
+{"current_steps": 126, "total_steps": 567, "loss": 0.8629, "lr": 9.567727288213005e-06, "epoch": 0.6652001759788825, "percentage": 22.22, "elapsed_time": "3:53:52", "remaining_time": "13:38:34"}
+{"current_steps": 127, "total_steps": 567, "loss": 0.943, "lr": 9.555113246230443e-06, "epoch": 0.6704795424549054, "percentage": 22.4, "elapsed_time": "3:55:56", "remaining_time": "13:37:24"}
+{"current_steps": 128, "total_steps": 567, "loss": 0.8841, "lr": 9.542326359097619e-06, "epoch": 0.6757589089309283, "percentage": 22.57, "elapsed_time": "3:57:38", "remaining_time": "13:35:01"}
+{"current_steps": 129, "total_steps": 567, "loss": 0.8039, "lr": 9.529367112016836e-06, "epoch": 0.6810382754069512, "percentage": 22.75, "elapsed_time": "3:59:26", "remaining_time": "13:32:59"}
+{"current_steps": 130, "total_steps": 567, "loss": 0.8409, "lr": 9.516235996730645e-06, "epoch": 0.6863176418829741, "percentage": 22.93, "elapsed_time": "4:01:15", "remaining_time": "13:31:00"}
+{"current_steps": 131, "total_steps": 567, "loss": 0.8499, "lr": 9.502933511503187e-06, "epoch": 0.691597008358997, "percentage": 23.1, "elapsed_time": "4:02:50", "remaining_time": "13:28:15"}
+{"current_steps": 132, "total_steps": 567, "loss": 0.8549, "lr": 9.489460161101291e-06, "epoch": 0.6968763748350199, "percentage": 23.28, "elapsed_time": "4:04:18", "remaining_time": "13:25:07"}
+{"current_steps": 133, "total_steps": 567, "loss": 0.8436, "lr": 9.475816456775313e-06, "epoch": 0.7021557413110426, "percentage": 23.46, "elapsed_time": "4:05:57", "remaining_time": "13:22:37"}
+{"current_steps": 134, "total_steps": 567, "loss": 0.853, "lr": 9.46200291623974e-06, "epoch": 0.7074351077870655, "percentage": 23.63, "elapsed_time": "4:08:00", "remaining_time": "13:21:22"}
+{"current_steps": 135, "total_steps": 567, "loss": 0.8283, "lr": 9.44802006365355e-06, "epoch": 0.7127144742630884, "percentage": 23.81, "elapsed_time": "4:09:42", "remaining_time": "13:19:02"}
+{"current_steps": 136, "total_steps": 567, "loss": 0.8474, "lr": 9.43386842960031e-06, "epoch": 0.7179938407391113, "percentage": 23.99, "elapsed_time": "4:11:07", "remaining_time": "13:15:50"}
+{"current_steps": 137, "total_steps": 567, "loss": 0.8657, "lr": 9.419548551068061e-06, "epoch": 0.7232732072151342, "percentage": 24.16, "elapsed_time": "4:12:38", "remaining_time": "13:12:57"}
+{"current_steps": 138, "total_steps": 567, "loss": 0.8915, "lr": 9.405060971428924e-06, "epoch": 0.7285525736911571, "percentage": 24.34, "elapsed_time": "4:14:06", "remaining_time": "13:09:56"}
+{"current_steps": 139, "total_steps": 567, "loss": 1.024, "lr": 9.39040624041849e-06, "epoch": 0.7338319401671799, "percentage": 24.51, "elapsed_time": "4:15:47", "remaining_time": "13:07:35"}
+{"current_steps": 140, "total_steps": 567, "loss": 0.7808, "lr": 9.375584914114963e-06, "epoch": 0.7391113066432028, "percentage": 24.69, "elapsed_time": "4:17:30", "remaining_time": "13:05:25"}
+{"current_steps": 141, "total_steps": 567, "loss": 0.9497, "lr": 9.360597554918055e-06, "epoch": 0.7443906731192257, "percentage": 24.87, "elapsed_time": "4:19:18", "remaining_time": "13:03:25"}
+{"current_steps": 142, "total_steps": 567, "loss": 0.927, "lr": 9.345444731527642e-06, "epoch": 0.7496700395952486, "percentage": 25.04, "elapsed_time": "4:20:41", "remaining_time": "13:00:13"}
+{"current_steps": 143, "total_steps": 567, "loss": 0.9708, "lr": 9.330127018922195e-06, "epoch": 0.7549494060712715, "percentage": 25.22, "elapsed_time": "4:22:29", "remaining_time": "12:58:17"}
+{"current_steps": 144, "total_steps": 567, "loss": 0.8359, "lr": 9.31464499833695e-06, "epoch": 0.7602287725472944, "percentage": 25.4, "elapsed_time": "4:24:32", "remaining_time": "12:57:06"}
+{"current_steps": 145, "total_steps": 567, "loss": 0.8085, "lr": 9.298999257241862e-06, "epoch": 0.7655081390233172, "percentage": 25.57, "elapsed_time": "4:26:08", "remaining_time": "12:54:32"}
+{"current_steps": 146, "total_steps": 567, "loss": 0.8619, "lr": 9.283190389319315e-06, "epoch": 0.77078750549934, "percentage": 25.75, "elapsed_time": "4:27:53", "remaining_time": "12:52:30"}
+{"current_steps": 147, "total_steps": 567, "loss": 0.8757, "lr": 9.26721899444158e-06, "epoch": 0.776066871975363, "percentage": 25.93, "elapsed_time": "4:29:40", "remaining_time": "12:50:29"}
+{"current_steps": 148, "total_steps": 567, "loss": 0.8586, "lr": 9.251085678648072e-06, "epoch": 0.7813462384513858, "percentage": 26.1, "elapsed_time": "4:31:21", "remaining_time": "12:48:15"}
+{"current_steps": 149, "total_steps": 567, "loss": 0.8315, "lr": 9.234791054122336e-06, "epoch": 0.7866256049274087, "percentage": 26.28, "elapsed_time": "4:33:00", "remaining_time": "12:45:54"}
+{"current_steps": 150, "total_steps": 567, "loss": 0.8138, "lr": 9.218335739168833e-06, "epoch": 0.7919049714034316, "percentage": 26.46, "elapsed_time": "4:34:42", "remaining_time": "12:43:40"}
+{"current_steps": 151, "total_steps": 567, "loss": 0.8953, "lr": 9.201720358189464e-06, "epoch": 0.7971843378794544, "percentage": 26.63, "elapsed_time": "4:36:21", "remaining_time": "12:41:20"}
+{"current_steps": 152, "total_steps": 567, "loss": 0.8527, "lr": 9.18494554165989e-06, "epoch": 0.8024637043554773, "percentage": 26.81, "elapsed_time": "4:37:57", "remaining_time": "12:38:53"}
+{"current_steps": 153, "total_steps": 567, "loss": 0.7873, "lr": 9.168011926105598e-06, "epoch": 0.8077430708315002, "percentage": 26.98, "elapsed_time": "4:39:58", "remaining_time": "12:37:34"}
+{"current_steps": 154, "total_steps": 567, "loss": 0.9273, "lr": 9.150920154077753e-06, "epoch": 0.8130224373075231, "percentage": 27.16, "elapsed_time": "4:42:12", "remaining_time": "12:36:50"}
+{"current_steps": 155, "total_steps": 567, "loss": 0.8165, "lr": 9.133670874128818e-06, "epoch": 0.818301803783546, "percentage": 27.34, "elapsed_time": "4:44:12", "remaining_time": "12:35:27"}
+{"current_steps": 156, "total_steps": 567, "loss": 0.903, "lr": 9.116264740787937e-06, "epoch": 0.8235811702595689, "percentage": 27.51, "elapsed_time": "4:46:08", "remaining_time": "12:33:53"}
+{"current_steps": 157, "total_steps": 567, "loss": 0.8654, "lr": 9.098702414536107e-06, "epoch": 0.8288605367355917, "percentage": 27.69, "elapsed_time": "4:47:47", "remaining_time": "12:31:32"}
+{"current_steps": 158, "total_steps": 567, "loss": 0.8821, "lr": 9.08098456178111e-06, "epoch": 0.8341399032116146, "percentage": 27.87, "elapsed_time": "4:49:32", "remaining_time": "12:29:31"}
+{"current_steps": 159, "total_steps": 567, "loss": 0.8585, "lr": 9.06311185483223e-06, "epoch": 0.8394192696876375, "percentage": 28.04, "elapsed_time": "4:50:55", "remaining_time": "12:26:32"}
+{"current_steps": 160, "total_steps": 567, "loss": 0.8409, "lr": 9.045084971874738e-06, "epoch": 0.8446986361636604, "percentage": 28.22, "elapsed_time": "4:52:09", "remaining_time": "12:23:10"}
+{"current_steps": 161, "total_steps": 567, "loss": 0.8423, "lr": 9.026904596944163e-06, "epoch": 0.8499780026396833, "percentage": 28.4, "elapsed_time": "4:54:10", "remaining_time": "12:21:50"}
+{"current_steps": 162, "total_steps": 567, "loss": 0.8123, "lr": 9.008571419900334e-06, "epoch": 0.8552573691157062, "percentage": 28.57, "elapsed_time": "4:56:10", "remaining_time": "12:20:27"}
+{"current_steps": 163, "total_steps": 567, "loss": 0.8171, "lr": 8.990086136401199e-06, "epoch": 0.8605367355917289, "percentage": 28.75, "elapsed_time": "4:57:35", "remaining_time": "12:17:34"}
+{"current_steps": 164, "total_steps": 567, "loss": 0.7351, "lr": 8.97144944787643e-06, "epoch": 0.8658161020677518, "percentage": 28.92, "elapsed_time": "4:59:06", "remaining_time": "12:14:59"}
+{"current_steps": 165, "total_steps": 567, "loss": 0.9156, "lr": 8.952662061500817e-06, "epoch": 0.8710954685437747, "percentage": 29.1, "elapsed_time": "5:00:43", "remaining_time": "12:12:40"}
+{"current_steps": 166, "total_steps": 567, "loss": 0.9278, "lr": 8.933724690167417e-06, "epoch": 0.8763748350197976, "percentage": 29.28, "elapsed_time": "5:03:07", "remaining_time": "12:12:15"}
+{"current_steps": 167, "total_steps": 567, "loss": 0.796, "lr": 8.914638052460515e-06, "epoch": 0.8816542014958205, "percentage": 29.45, "elapsed_time": "5:04:44", "remaining_time": "12:09:55"}
+{"current_steps": 168, "total_steps": 567, "loss": 0.8289, "lr": 8.895402872628352e-06, "epoch": 0.8869335679718434, "percentage": 29.63, "elapsed_time": "5:06:21", "remaining_time": "12:07:36"}
+{"current_steps": 169, "total_steps": 567, "loss": 0.9055, "lr": 8.87601988055565e-06, "epoch": 0.8922129344478662, "percentage": 29.81, "elapsed_time": "5:08:06", "remaining_time": "12:05:37"}
+{"current_steps": 170, "total_steps": 567, "loss": 0.8221, "lr": 8.856489811735904e-06, "epoch": 0.8974923009238891, "percentage": 29.98, "elapsed_time": "5:09:58", "remaining_time": "12:03:53"}
+{"current_steps": 171, "total_steps": 567, "loss": 0.8052, "lr": 8.836813407243485e-06, "epoch": 0.902771667399912, "percentage": 30.16, "elapsed_time": "5:11:55", "remaining_time": "12:02:21"}
+{"current_steps": 172, "total_steps": 567, "loss": 0.8048, "lr": 8.816991413705515e-06, "epoch": 0.9080510338759349, "percentage": 30.34, "elapsed_time": "5:13:52", "remaining_time": "12:00:48"}
+{"current_steps": 173, "total_steps": 567, "loss": 0.8403, "lr": 8.797024583273536e-06, "epoch": 0.9133304003519578, "percentage": 30.51, "elapsed_time": "5:16:02", "remaining_time": "11:59:46"}
+{"current_steps": 174, "total_steps": 567, "loss": 0.8558, "lr": 8.776913673594968e-06, "epoch": 0.9186097668279807, "percentage": 30.69, "elapsed_time": "5:17:49", "remaining_time": "11:57:50"}
+{"current_steps": 175, "total_steps": 567, "loss": 0.8265, "lr": 8.756659447784367e-06, "epoch": 0.9238891333040036, "percentage": 30.86, "elapsed_time": "5:19:51", "remaining_time": "11:56:29"}
+{"current_steps": 176, "total_steps": 567, "loss": 0.8558, "lr": 8.736262674394455e-06, "epoch": 0.9291684997800264, "percentage": 31.04, "elapsed_time": "5:21:56", "remaining_time": "11:55:13"}
+{"current_steps": 177, "total_steps": 567, "loss": 0.7684, "lr": 8.715724127386971e-06, "epoch": 0.9344478662560493, "percentage": 31.22, "elapsed_time": "5:23:56", "remaining_time": "11:53:46"}
+{"current_steps": 178, "total_steps": 567, "loss": 0.8404, "lr": 8.695044586103297e-06, "epoch": 0.9397272327320721, "percentage": 31.39, "elapsed_time": "5:25:09", "remaining_time": "11:50:37"}
+{"current_steps": 179, "total_steps": 567, "loss": 0.855, "lr": 8.674224835234879e-06, "epoch": 0.945006599208095, "percentage": 31.57, "elapsed_time": "5:27:00", "remaining_time": "11:48:48"}
+{"current_steps": 180, "total_steps": 567, "loss": 0.8966, "lr": 8.653265664793466e-06, "epoch": 0.9502859656841179, "percentage": 31.75, "elapsed_time": "5:28:48", "remaining_time": "11:46:55"}
+{"current_steps": 181, "total_steps": 567, "loss": 0.8983, "lr": 8.632167870081122e-06, "epoch": 0.9555653321601408, "percentage": 31.92, "elapsed_time": "5:30:28", "remaining_time": "11:44:47"}
+{"current_steps": 182, "total_steps": 567, "loss": 0.7676, "lr": 8.610932251660046e-06, "epoch": 0.9608446986361636, "percentage": 32.1, "elapsed_time": "5:32:05", "remaining_time": "11:42:30"}
+{"current_steps": 183, "total_steps": 567, "loss": 0.8486, "lr": 8.58955961532221e-06, "epoch": 0.9661240651121865, "percentage": 32.28, "elapsed_time": "5:34:01", "remaining_time": "11:40:54"}
+{"current_steps": 184, "total_steps": 567, "loss": 1.0695, "lr": 8.568050772058763e-06, "epoch": 0.9714034315882094, "percentage": 32.45, "elapsed_time": "5:36:24", "remaining_time": "11:40:14"}
+{"current_steps": 185, "total_steps": 567, "loss": 0.8744, "lr": 8.546406538029268e-06, "epoch": 0.9766827980642323, "percentage": 32.63, "elapsed_time": "5:37:51", "remaining_time": "11:37:37"}
+{"current_steps": 186, "total_steps": 567, "loss": 0.8009, "lr": 8.524627734530738e-06, "epoch": 0.9819621645402552, "percentage": 32.8, "elapsed_time": "5:39:54", "remaining_time": "11:36:15"}
+{"current_steps": 187, "total_steps": 567, "loss": 0.8211, "lr": 8.502715187966455e-06, "epoch": 0.9872415310162781, "percentage": 32.98, "elapsed_time": "5:41:47", "remaining_time": "11:34:33"}
+{"current_steps": 188, "total_steps": 567, "loss": 0.8909, "lr": 8.480669729814635e-06, "epoch": 0.9925208974923009, "percentage": 33.16, "elapsed_time": "5:43:26", "remaining_time": "11:32:22"}
+{"current_steps": 189, "total_steps": 567, "loss": 0.7842, "lr": 8.458492196596852e-06, "epoch": 0.9978002639683238, "percentage": 33.33, "elapsed_time": "5:45:21", "remaining_time": "11:30:42"}
+{"current_steps": 190, "total_steps": 567, "loss": 0.8917, "lr": 8.436183429846314e-06, "epoch": 1.0, "percentage": 33.51, "elapsed_time": "5:46:38", "remaining_time": "11:27:49"}
+{"current_steps": 191, "total_steps": 567, "loss": 0.7453, "lr": 8.413744276075928e-06, "epoch": 1.005279366476023, "percentage": 33.69, "elapsed_time": "5:48:33", "remaining_time": "11:26:10"}
+{"current_steps": 192, "total_steps": 567, "loss": 0.6252, "lr": 8.39117558674617e-06, "epoch": 1.0105587329520458, "percentage": 33.86, "elapsed_time": "5:51:03", "remaining_time": "11:25:39"}
+{"current_steps": 193, "total_steps": 567, "loss": 0.6357, "lr": 8.368478218232787e-06, "epoch": 1.0158380994280687, "percentage": 34.04, "elapsed_time": "5:52:52", "remaining_time": "11:23:48"}
+{"current_steps": 194, "total_steps": 567, "loss": 0.6568, "lr": 8.345653031794292e-06, "epoch": 1.0211174659040916, "percentage": 34.22, "elapsed_time": "5:54:23", "remaining_time": "11:21:23"}
+{"current_steps": 195, "total_steps": 567, "loss": 0.6674, "lr": 8.32270089353929e-06, "epoch": 1.0263968323801145, "percentage": 34.39, "elapsed_time": "5:55:52", "remaining_time": "11:18:54"}
+{"current_steps": 196, "total_steps": 567, "loss": 0.7704, "lr": 8.299622674393615e-06, "epoch": 1.0316761988561374, "percentage": 34.57, "elapsed_time": "5:57:17", "remaining_time": "11:16:17"}
+{"current_steps": 197, "total_steps": 567, "loss": 0.6893, "lr": 8.27641925006727e-06, "epoch": 1.03695556533216, "percentage": 34.74, "elapsed_time": "5:59:20", "remaining_time": "11:14:54"}
+{"current_steps": 198, "total_steps": 567, "loss": 0.6783, "lr": 8.25309150102121e-06, "epoch": 1.042234931808183, "percentage": 34.92, "elapsed_time": "6:01:12", "remaining_time": "11:13:09"}
+{"current_steps": 199, "total_steps": 567, "loss": 0.6328, "lr": 8.229640312433938e-06, "epoch": 1.0475142982842058, "percentage": 35.1, "elapsed_time": "6:02:49", "remaining_time": "11:10:56"}
+{"current_steps": 200, "total_steps": 567, "loss": 0.7054, "lr": 8.206066574167893e-06, "epoch": 1.0527936647602287, "percentage": 35.27, "elapsed_time": "6:04:23", "remaining_time": "11:08:40"}
+{"current_steps": 201, "total_steps": 567, "loss": 0.6596, "lr": 8.182371180735708e-06, "epoch": 1.0580730312362516, "percentage": 35.45, "elapsed_time": "6:06:57", "remaining_time": "11:08:11"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5112128fa95110033f44c32cb886824f96ee1883e8fe650fd40e4aa5449f1a
+size 7864