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 sha256:5aff6b799f3c9b130c7004bc615e7ea2f288292b5073958b192980a526e9ad35
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6222a6ad3ea31a5006c859207959677bf2c6fb5c02a24ec70b142a7112023d74
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3a87df8295ec557f68f41d02874efb6800c2841afe3e0e1382c5acb5849488
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103947d60c055103af4b495f18a2d91dfd2a2db71e00ab0735fc2ffc0e00cc36
+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 +1,201 @@
+{"current_steps": 1, "total_steps": 546, "loss": 1.8883, "lr": 0.0, "epoch": 0.005471956224350205, "percentage": 0.18, "elapsed_time": "0:02:03", "remaining_time": "18:43:38"}
+{"current_steps": 2, "total_steps": 546, "loss": 1.6762, "lr": 1.8181818181818183e-07, "epoch": 0.01094391244870041, "percentage": 0.37, "elapsed_time": "0:03:26", "remaining_time": "15:34:59"}
+{"current_steps": 3, "total_steps": 546, "loss": 1.7134, "lr": 3.6363636363636366e-07, "epoch": 0.016415868673050615, "percentage": 0.55, "elapsed_time": "0:05:02", "remaining_time": "15:11:43"}
+{"current_steps": 4, "total_steps": 546, "loss": 1.8695, "lr": 5.454545454545455e-07, "epoch": 0.02188782489740082, "percentage": 0.73, "elapsed_time": "0:06:45", "remaining_time": "15:16:08"}
+{"current_steps": 5, "total_steps": 546, "loss": 1.8403, "lr": 7.272727272727273e-07, "epoch": 0.027359781121751026, "percentage": 0.92, "elapsed_time": "0:08:14", "remaining_time": "14:51:35"}
+{"current_steps": 6, "total_steps": 546, "loss": 1.8047, "lr": 9.090909090909091e-07, "epoch": 0.03283173734610123, "percentage": 1.1, "elapsed_time": "0:09:56", "remaining_time": "14:54:01"}
+{"current_steps": 7, "total_steps": 546, "loss": 1.8478, "lr": 1.090909090909091e-06, "epoch": 0.038303693570451436, "percentage": 1.28, "elapsed_time": "0:11:41", "remaining_time": "14:59:40"}
+{"current_steps": 8, "total_steps": 546, "loss": 1.9031, "lr": 1.2727272727272728e-06, "epoch": 0.04377564979480164, "percentage": 1.47, "elapsed_time": "0:13:25", "remaining_time": "15:02:20"}
+{"current_steps": 9, "total_steps": 546, "loss": 1.8532, "lr": 1.4545454545454546e-06, "epoch": 0.049247606019151846, "percentage": 1.65, "elapsed_time": "0:15:17", "remaining_time": "15:12:01"}
+{"current_steps": 10, "total_steps": 546, "loss": 1.7478, "lr": 1.6363636363636365e-06, "epoch": 0.05471956224350205, "percentage": 1.83, "elapsed_time": "0:17:06", "remaining_time": "15:17:06"}
+{"current_steps": 11, "total_steps": 546, "loss": 1.8029, "lr": 1.8181818181818183e-06, "epoch": 0.060191518467852256, "percentage": 2.01, "elapsed_time": "0:19:18", "remaining_time": "15:39:02"}
+{"current_steps": 12, "total_steps": 546, "loss": 1.5675, "lr": 2.0000000000000003e-06, "epoch": 0.06566347469220246, "percentage": 2.2, "elapsed_time": "0:21:17", "remaining_time": "15:47:09"}
+{"current_steps": 13, "total_steps": 546, "loss": 1.5805, "lr": 2.181818181818182e-06, "epoch": 0.07113543091655267, "percentage": 2.38, "elapsed_time": "0:22:59", "remaining_time": "15:42:41"}
+{"current_steps": 14, "total_steps": 546, "loss": 1.4595, "lr": 2.363636363636364e-06, "epoch": 0.07660738714090287, "percentage": 2.56, "elapsed_time": "0:25:07", "remaining_time": "15:55:01"}
+{"current_steps": 15, "total_steps": 546, "loss": 1.5726, "lr": 2.5454545454545456e-06, "epoch": 0.08207934336525308, "percentage": 2.75, "elapsed_time": "0:27:07", "remaining_time": "16:00:12"}
+{"current_steps": 16, "total_steps": 546, "loss": 1.4351, "lr": 2.7272727272727272e-06, "epoch": 0.08755129958960328, "percentage": 2.93, "elapsed_time": "0:28:27", "remaining_time": "15:42:46"}
+{"current_steps": 17, "total_steps": 546, "loss": 1.3786, "lr": 2.9090909090909093e-06, "epoch": 0.09302325581395349, "percentage": 3.11, "elapsed_time": "0:30:07", "remaining_time": "15:37:37"}
+{"current_steps": 18, "total_steps": 546, "loss": 1.4688, "lr": 3.090909090909091e-06, "epoch": 0.09849521203830369, "percentage": 3.3, "elapsed_time": "0:31:47", "remaining_time": "15:32:41"}
+{"current_steps": 19, "total_steps": 546, "loss": 1.3943, "lr": 3.272727272727273e-06, "epoch": 0.1039671682626539, "percentage": 3.48, "elapsed_time": "0:33:53", "remaining_time": "15:39:55"}
+{"current_steps": 20, "total_steps": 546, "loss": 1.3837, "lr": 3.454545454545455e-06, "epoch": 0.1094391244870041, "percentage": 3.66, "elapsed_time": "0:35:46", "remaining_time": "15:40:47"}
+{"current_steps": 21, "total_steps": 546, "loss": 1.2383, "lr": 3.6363636363636366e-06, "epoch": 0.11491108071135431, "percentage": 3.85, "elapsed_time": "0:37:14", "remaining_time": "15:30:53"}
+{"current_steps": 22, "total_steps": 546, "loss": 1.2007, "lr": 3.818181818181819e-06, "epoch": 0.12038303693570451, "percentage": 4.03, "elapsed_time": "0:38:41", "remaining_time": "15:21:36"}
+{"current_steps": 23, "total_steps": 546, "loss": 1.3034, "lr": 4.000000000000001e-06, "epoch": 0.12585499316005472, "percentage": 4.21, "elapsed_time": "0:40:25", "remaining_time": "15:19:17"}
+{"current_steps": 24, "total_steps": 546, "loss": 1.2581, "lr": 4.181818181818182e-06, "epoch": 0.13132694938440492, "percentage": 4.4, "elapsed_time": "0:42:14", "remaining_time": "15:18:55"}
+{"current_steps": 25, "total_steps": 546, "loss": 1.2718, "lr": 4.363636363636364e-06, "epoch": 0.13679890560875513, "percentage": 4.58, "elapsed_time": "0:44:00", "remaining_time": "15:16:57"}
+{"current_steps": 26, "total_steps": 546, "loss": 1.2783, "lr": 4.5454545454545455e-06, "epoch": 0.14227086183310533, "percentage": 4.76, "elapsed_time": "0:45:32", "remaining_time": "15:10:53"}
+{"current_steps": 27, "total_steps": 546, "loss": 1.2178, "lr": 4.727272727272728e-06, "epoch": 0.14774281805745554, "percentage": 4.95, "elapsed_time": "0:47:33", "remaining_time": "15:14:04"}
+{"current_steps": 28, "total_steps": 546, "loss": 1.2405, "lr": 4.90909090909091e-06, "epoch": 0.15321477428180574, "percentage": 5.13, "elapsed_time": "0:48:45", "remaining_time": "15:02:01"}
+{"current_steps": 29, "total_steps": 546, "loss": 1.1669, "lr": 5.090909090909091e-06, "epoch": 0.15868673050615595, "percentage": 5.31, "elapsed_time": "0:50:34", "remaining_time": "15:01:40"}
+{"current_steps": 30, "total_steps": 546, "loss": 1.1599, "lr": 5.272727272727273e-06, "epoch": 0.16415868673050615, "percentage": 5.49, "elapsed_time": "0:52:48", "remaining_time": "15:08:14"}
+{"current_steps": 31, "total_steps": 546, "loss": 1.2979, "lr": 5.4545454545454545e-06, "epoch": 0.16963064295485636, "percentage": 5.68, "elapsed_time": "0:54:58", "remaining_time": "15:13:20"}
+{"current_steps": 32, "total_steps": 546, "loss": 1.1704, "lr": 5.636363636363636e-06, "epoch": 0.17510259917920656, "percentage": 5.86, "elapsed_time": "0:56:43", "remaining_time": "15:11:15"}
+{"current_steps": 33, "total_steps": 546, "loss": 1.2306, "lr": 5.8181818181818185e-06, "epoch": 0.18057455540355677, "percentage": 6.04, "elapsed_time": "0:58:24", "remaining_time": "15:07:55"}
+{"current_steps": 34, "total_steps": 546, "loss": 1.1128, "lr": 6e-06, "epoch": 0.18604651162790697, "percentage": 6.23, "elapsed_time": "0:59:58", "remaining_time": "15:03:15"}
+{"current_steps": 35, "total_steps": 546, "loss": 1.1292, "lr": 6.181818181818182e-06, "epoch": 0.19151846785225718, "percentage": 6.41, "elapsed_time": "1:01:26", "remaining_time": "14:57:00"}
+{"current_steps": 36, "total_steps": 546, "loss": 1.1514, "lr": 6.363636363636364e-06, "epoch": 0.19699042407660738, "percentage": 6.59, "elapsed_time": "1:02:59", "remaining_time": "14:52:21"}
+{"current_steps": 37, "total_steps": 546, "loss": 1.0348, "lr": 6.545454545454546e-06, "epoch": 0.2024623803009576, "percentage": 6.78, "elapsed_time": "1:04:54", "remaining_time": "14:52:57"}
+{"current_steps": 38, "total_steps": 546, "loss": 1.0895, "lr": 6.7272727272727275e-06, "epoch": 0.2079343365253078, "percentage": 6.96, "elapsed_time": "1:06:41", "remaining_time": "14:51:27"}
+{"current_steps": 39, "total_steps": 546, "loss": 1.0314, "lr": 6.90909090909091e-06, "epoch": 0.213406292749658, "percentage": 7.14, "elapsed_time": "1:07:59", "remaining_time": "14:43:54"}
+{"current_steps": 40, "total_steps": 546, "loss": 1.0393, "lr": 7.0909090909090916e-06, "epoch": 0.2188782489740082, "percentage": 7.33, "elapsed_time": "1:10:14", "remaining_time": "14:48:38"}
+{"current_steps": 41, "total_steps": 546, "loss": 1.0725, "lr": 7.272727272727273e-06, "epoch": 0.2243502051983584, "percentage": 7.51, "elapsed_time": "1:12:46", "remaining_time": "14:56:22"}
+{"current_steps": 42, "total_steps": 546, "loss": 1.1064, "lr": 7.454545454545456e-06, "epoch": 0.22982216142270862, "percentage": 7.69, "elapsed_time": "1:14:05", "remaining_time": "14:49:02"}
+{"current_steps": 43, "total_steps": 546, "loss": 1.1167, "lr": 7.636363636363638e-06, "epoch": 0.23529411764705882, "percentage": 7.88, "elapsed_time": "1:16:04", "remaining_time": "14:49:56"}
+{"current_steps": 44, "total_steps": 546, "loss": 1.0057, "lr": 7.81818181818182e-06, "epoch": 0.24076607387140903, "percentage": 8.06, "elapsed_time": "1:17:57", "remaining_time": "14:49:21"}
+{"current_steps": 45, "total_steps": 546, "loss": 1.0419, "lr": 8.000000000000001e-06, "epoch": 0.24623803009575923, "percentage": 8.24, "elapsed_time": "1:20:00", "remaining_time": "14:50:40"}
+{"current_steps": 46, "total_steps": 546, "loss": 1.0261, "lr": 8.181818181818183e-06, "epoch": 0.25170998632010944, "percentage": 8.42, "elapsed_time": "1:21:55", "remaining_time": "14:50:27"}
+{"current_steps": 47, "total_steps": 546, "loss": 1.0732, "lr": 8.363636363636365e-06, "epoch": 0.25718194254445964, "percentage": 8.61, "elapsed_time": "1:23:47", "remaining_time": "14:49:32"}
+{"current_steps": 48, "total_steps": 546, "loss": 1.0268, "lr": 8.545454545454546e-06, "epoch": 0.26265389876880985, "percentage": 8.79, "elapsed_time": "1:25:46", "remaining_time": "14:49:55"}
+{"current_steps": 49, "total_steps": 546, "loss": 0.9602, "lr": 8.727272727272728e-06, "epoch": 0.26812585499316005, "percentage": 8.97, "elapsed_time": "1:27:08", "remaining_time": "14:43:49"}
+{"current_steps": 50, "total_steps": 546, "loss": 1.0214, "lr": 8.90909090909091e-06, "epoch": 0.27359781121751026, "percentage": 9.16, "elapsed_time": "1:29:01", "remaining_time": "14:43:11"}
+{"current_steps": 51, "total_steps": 546, "loss": 0.9672, "lr": 9.090909090909091e-06, "epoch": 0.27906976744186046, "percentage": 9.34, "elapsed_time": "1:30:34", "remaining_time": "14:39:09"}
+{"current_steps": 52, "total_steps": 546, "loss": 1.0336, "lr": 9.272727272727273e-06, "epoch": 0.28454172366621067, "percentage": 9.52, "elapsed_time": "1:32:16", "remaining_time": "14:36:35"}
+{"current_steps": 53, "total_steps": 546, "loss": 0.921, "lr": 9.454545454545456e-06, "epoch": 0.29001367989056087, "percentage": 9.71, "elapsed_time": "1:34:08", "remaining_time": "14:35:43"}
+{"current_steps": 54, "total_steps": 546, "loss": 0.9601, "lr": 9.636363636363638e-06, "epoch": 0.2954856361149111, "percentage": 9.89, "elapsed_time": "1:36:41", "remaining_time": "14:40:55"}
+{"current_steps": 55, "total_steps": 546, "loss": 1.0595, "lr": 9.81818181818182e-06, "epoch": 0.3009575923392613, "percentage": 10.07, "elapsed_time": "1:38:26", "remaining_time": "14:38:45"}
+{"current_steps": 56, "total_steps": 546, "loss": 0.9707, "lr": 1e-05, "epoch": 0.3064295485636115, "percentage": 10.26, "elapsed_time": "1:40:04", "remaining_time": "14:35:43"}
+{"current_steps": 57, "total_steps": 546, "loss": 1.0395, "lr": 9.999897652959688e-06, "epoch": 0.3119015047879617, "percentage": 10.44, "elapsed_time": "1:41:58", "remaining_time": "14:34:52"}
+{"current_steps": 58, "total_steps": 546, "loss": 0.9859, "lr": 9.999590616028718e-06, "epoch": 0.3173734610123119, "percentage": 10.62, "elapsed_time": "1:43:45", "remaining_time": "14:33:00"}
+{"current_steps": 59, "total_steps": 546, "loss": 0.8967, "lr": 9.999078901776819e-06, "epoch": 0.3228454172366621, "percentage": 10.81, "elapsed_time": "1:45:36", "remaining_time": "14:31:44"}
+{"current_steps": 60, "total_steps": 546, "loss": 0.8705, "lr": 9.998362531152967e-06, "epoch": 0.3283173734610123, "percentage": 10.99, "elapsed_time": "1:47:47", "remaining_time": "14:33:06"}
+{"current_steps": 61, "total_steps": 546, "loss": 0.9106, "lr": 9.997441533484527e-06, "epoch": 0.3337893296853625, "percentage": 11.17, "elapsed_time": "1:50:01", "remaining_time": "14:34:48"}
+{"current_steps": 62, "total_steps": 546, "loss": 0.9483, "lr": 9.996315946476054e-06, "epoch": 0.3392612859097127, "percentage": 11.36, "elapsed_time": "1:52:02", "remaining_time": "14:34:36"}
+{"current_steps": 63, "total_steps": 546, "loss": 0.9165, "lr": 9.994985816207745e-06, "epoch": 0.3447332421340629, "percentage": 11.54, "elapsed_time": "1:53:50", "remaining_time": "14:32:48"}
+{"current_steps": 64, "total_steps": 546, "loss": 0.9197, "lr": 9.993451197133558e-06, "epoch": 0.35020519835841313, "percentage": 11.72, "elapsed_time": "1:55:46", "remaining_time": "14:31:56"}
+{"current_steps": 65, "total_steps": 546, "loss": 0.9584, "lr": 9.991712152078988e-06, "epoch": 0.35567715458276333, "percentage": 11.9, "elapsed_time": "1:57:10", "remaining_time": "14:27:02"}
+{"current_steps": 66, "total_steps": 546, "loss": 0.8481, "lr": 9.989768752238473e-06, "epoch": 0.36114911080711354, "percentage": 12.09, "elapsed_time": "1:58:20", "remaining_time": "14:20:40"}
+{"current_steps": 67, "total_steps": 546, "loss": 0.9649, "lr": 9.987621077172504e-06, "epoch": 0.36662106703146374, "percentage": 12.27, "elapsed_time": "1:59:56", "remaining_time": "14:17:31"}
+{"current_steps": 68, "total_steps": 546, "loss": 1.0005, "lr": 9.985269214804358e-06, "epoch": 0.37209302325581395, "percentage": 12.45, "elapsed_time": "2:01:39", "remaining_time": "14:15:08"}
+{"current_steps": 69, "total_steps": 546, "loss": 0.9358, "lr": 9.982713261416493e-06, "epoch": 0.37756497948016415, "percentage": 12.64, "elapsed_time": "2:03:16", "remaining_time": "14:12:11"}
+{"current_steps": 70, "total_steps": 546, "loss": 0.9322, "lr": 9.979953321646615e-06, "epoch": 0.38303693570451436, "percentage": 12.82, "elapsed_time": "2:05:56", "remaining_time": "14:16:24"}
+{"current_steps": 71, "total_steps": 546, "loss": 0.8887, "lr": 9.976989508483395e-06, "epoch": 0.38850889192886456, "percentage": 13.0, "elapsed_time": "2:08:26", "remaining_time": "14:19:16"}
+{"current_steps": 72, "total_steps": 546, "loss": 0.8773, "lr": 9.97382194326183e-06, "epoch": 0.39398084815321477, "percentage": 13.19, "elapsed_time": "2:10:22", "remaining_time": "14:18:17"}
+{"current_steps": 73, "total_steps": 546, "loss": 0.9411, "lr": 9.970450755658293e-06, "epoch": 0.399452804377565, "percentage": 13.37, "elapsed_time": "2:11:49", "remaining_time": "14:14:06"}
+{"current_steps": 74, "total_steps": 546, "loss": 0.9381, "lr": 9.96687608368521e-06, "epoch": 0.4049247606019152, "percentage": 13.55, "elapsed_time": "2:13:33", "remaining_time": "14:11:50"}
+{"current_steps": 75, "total_steps": 546, "loss": 0.9509, "lr": 9.963098073685425e-06, "epoch": 0.4103967168262654, "percentage": 13.74, "elapsed_time": "2:15:35", "remaining_time": "14:11:32"}
+{"current_steps": 76, "total_steps": 546, "loss": 0.9841, "lr": 9.95911688032619e-06, "epoch": 0.4158686730506156, "percentage": 13.92, "elapsed_time": "2:17:03", "remaining_time": "14:07:33"}
+{"current_steps": 77, "total_steps": 546, "loss": 0.9244, "lr": 9.954932666592852e-06, "epoch": 0.4213406292749658, "percentage": 14.1, "elapsed_time": "2:18:30", "remaining_time": "14:03:37"}
+{"current_steps": 78, "total_steps": 546, "loss": 0.8224, "lr": 9.950545603782163e-06, "epoch": 0.426812585499316, "percentage": 14.29, "elapsed_time": "2:20:43", "remaining_time": "14:04:22"}
+{"current_steps": 79, "total_steps": 546, "loss": 0.9675, "lr": 9.945955871495284e-06, "epoch": 0.4322845417236662, "percentage": 14.47, "elapsed_time": "2:22:28", "remaining_time": "14:02:14"}
+{"current_steps": 80, "total_steps": 546, "loss": 0.931, "lr": 9.94116365763042e-06, "epoch": 0.4377564979480164, "percentage": 14.65, "elapsed_time": "2:23:56", "remaining_time": "13:58:29"}
+{"current_steps": 81, "total_steps": 546, "loss": 0.9014, "lr": 9.936169158375132e-06, "epoch": 0.4432284541723666, "percentage": 14.84, "elapsed_time": "2:25:30", "remaining_time": "13:55:19"}
+{"current_steps": 82, "total_steps": 546, "loss": 1.0038, "lr": 9.93097257819831e-06, "epoch": 0.4487004103967168, "percentage": 15.02, "elapsed_time": "2:27:13", "remaining_time": "13:53:04"}
+{"current_steps": 83, "total_steps": 546, "loss": 0.9125, "lr": 9.925574129841793e-06, "epoch": 0.454172366621067, "percentage": 15.2, "elapsed_time": "2:29:00", "remaining_time": "13:51:14"}
+{"current_steps": 84, "total_steps": 546, "loss": 1.1419, "lr": 9.919974034311665e-06, "epoch": 0.45964432284541723, "percentage": 15.38, "elapsed_time": "2:31:12", "remaining_time": "13:51:41"}
+{"current_steps": 85, "total_steps": 546, "loss": 0.9291, "lr": 9.914172520869207e-06, "epoch": 0.46511627906976744, "percentage": 15.57, "elapsed_time": "2:33:07", "remaining_time": "13:50:27"}
+{"current_steps": 86, "total_steps": 546, "loss": 1.0433, "lr": 9.90816982702151e-06, "epoch": 0.47058823529411764, "percentage": 15.75, "elapsed_time": "2:34:38", "remaining_time": "13:47:10"}
+{"current_steps": 87, "total_steps": 546, "loss": 0.8418, "lr": 9.901966198511756e-06, "epoch": 0.47606019151846785, "percentage": 15.93, "elapsed_time": "2:36:18", "remaining_time": "13:44:41"}
+{"current_steps": 88, "total_steps": 546, "loss": 0.8594, "lr": 9.895561889309152e-06, "epoch": 0.48153214774281805, "percentage": 16.12, "elapsed_time": "2:37:49", "remaining_time": "13:41:24"}
+{"current_steps": 89, "total_steps": 546, "loss": 0.8793, "lr": 9.888957161598532e-06, "epoch": 0.48700410396716826, "percentage": 16.3, "elapsed_time": "2:39:56", "remaining_time": "13:41:16"}
+{"current_steps": 90, "total_steps": 546, "loss": 0.8542, "lr": 9.882152285769633e-06, "epoch": 0.49247606019151846, "percentage": 16.48, "elapsed_time": "2:41:22", "remaining_time": "13:37:38"}
+{"current_steps": 91, "total_steps": 546, "loss": 0.877, "lr": 9.875147540406012e-06, "epoch": 0.49794801641586867, "percentage": 16.67, "elapsed_time": "2:43:16", "remaining_time": "13:36:24"}
+{"current_steps": 92, "total_steps": 546, "loss": 0.9977, "lr": 9.867943212273653e-06, "epoch": 0.5034199726402189, "percentage": 16.85, "elapsed_time": "2:45:21", "remaining_time": "13:35:58"}
+{"current_steps": 93, "total_steps": 546, "loss": 0.9423, "lr": 9.86053959630922e-06, "epoch": 0.5088919288645691, "percentage": 17.03, "elapsed_time": "2:46:34", "remaining_time": "13:31:23"}
+{"current_steps": 94, "total_steps": 546, "loss": 0.8744, "lr": 9.852936995607986e-06, "epoch": 0.5143638850889193, "percentage": 17.22, "elapsed_time": "2:48:48", "remaining_time": "13:31:44"}
+{"current_steps": 95, "total_steps": 546, "loss": 1.0106, "lr": 9.845135721411425e-06, "epoch": 0.5198358413132695, "percentage": 17.4, "elapsed_time": "2:50:41", "remaining_time": "13:30:19"}
+{"current_steps": 96, "total_steps": 546, "loss": 0.9134, "lr": 9.837136093094465e-06, "epoch": 0.5253077975376197, "percentage": 17.58, "elapsed_time": "2:53:00", "remaining_time": "13:30:57"}
+{"current_steps": 97, "total_steps": 546, "loss": 0.9009, "lr": 9.828938438152418e-06, "epoch": 0.53077975376197, "percentage": 17.77, "elapsed_time": "2:54:23", "remaining_time": "13:27:14"}
+{"current_steps": 98, "total_steps": 546, "loss": 0.9185, "lr": 9.820543092187574e-06, "epoch": 0.5362517099863201, "percentage": 17.95, "elapsed_time": "2:55:42", "remaining_time": "13:23:16"}
+{"current_steps": 99, "total_steps": 546, "loss": 0.8773, "lr": 9.811950398895457e-06, "epoch": 0.5417236662106704, "percentage": 18.13, "elapsed_time": "2:57:42", "remaining_time": "13:22:23"}
+{"current_steps": 100, "total_steps": 546, "loss": 0.9434, "lr": 9.803160710050757e-06, "epoch": 0.5471956224350205, "percentage": 18.32, "elapsed_time": "2:59:48", "remaining_time": "13:21:56"}
+{"current_steps": 101, "total_steps": 546, "loss": 0.9904, "lr": 9.79417438549293e-06, "epoch": 0.5526675786593708, "percentage": 18.5, "elapsed_time": "3:01:08", "remaining_time": "13:18:06"}
+{"current_steps": 102, "total_steps": 546, "loss": 0.9558, "lr": 9.784991793111466e-06, "epoch": 0.5581395348837209, "percentage": 18.68, "elapsed_time": "3:02:47", "remaining_time": "13:15:40"}
+{"current_steps": 103, "total_steps": 546, "loss": 0.8844, "lr": 9.775613308830825e-06, "epoch": 0.5636114911080712, "percentage": 18.86, "elapsed_time": "3:04:27", "remaining_time": "13:13:22"}
+{"current_steps": 104, "total_steps": 546, "loss": 0.8812, "lr": 9.766039316595048e-06, "epoch": 0.5690834473324213, "percentage": 19.05, "elapsed_time": "3:06:06", "remaining_time": "13:10:57"}
+{"current_steps": 105, "total_steps": 546, "loss": 0.8349, "lr": 9.756270208352048e-06, "epoch": 0.5745554035567716, "percentage": 19.23, "elapsed_time": "3:08:12", "remaining_time": "13:10:30"}
+{"current_steps": 106, "total_steps": 546, "loss": 0.9154, "lr": 9.746306384037547e-06, "epoch": 0.5800273597811217, "percentage": 19.41, "elapsed_time": "3:09:51", "remaining_time": "13:08:05"}
+{"current_steps": 107, "total_steps": 546, "loss": 0.8915, "lr": 9.736148251558719e-06, "epoch": 0.585499316005472, "percentage": 19.6, "elapsed_time": "3:11:52", "remaining_time": "13:07:13"}
+{"current_steps": 108, "total_steps": 546, "loss": 0.889, "lr": 9.725796226777478e-06, "epoch": 0.5909712722298222, "percentage": 19.78, "elapsed_time": "3:13:17", "remaining_time": "13:03:53"}
+{"current_steps": 109, "total_steps": 546, "loss": 0.8909, "lr": 9.715250733493466e-06, "epoch": 0.5964432284541724, "percentage": 19.96, "elapsed_time": "3:14:56", "remaining_time": "13:01:34"}
+{"current_steps": 110, "total_steps": 546, "loss": 0.8007, "lr": 9.704512203426695e-06, "epoch": 0.6019151846785226, "percentage": 20.15, "elapsed_time": "3:16:55", "remaining_time": "13:00:34"}
+{"current_steps": 111, "total_steps": 546, "loss": 0.8406, "lr": 9.69358107619987e-06, "epoch": 0.6073871409028728, "percentage": 20.33, "elapsed_time": "3:18:20", "remaining_time": "12:57:17"}
+{"current_steps": 112, "total_steps": 546, "loss": 0.9031, "lr": 9.682457799320398e-06, "epoch": 0.612859097127223, "percentage": 20.51, "elapsed_time": "3:20:11", "remaining_time": "12:55:43"}
+{"current_steps": 113, "total_steps": 546, "loss": 0.8727, "lr": 9.671142828162067e-06, "epoch": 0.6183310533515732, "percentage": 20.7, "elapsed_time": "3:22:25", "remaining_time": "12:55:40"}
+{"current_steps": 114, "total_steps": 546, "loss": 0.9793, "lr": 9.659636625946403e-06, "epoch": 0.6238030095759234, "percentage": 20.88, "elapsed_time": "3:23:54", "remaining_time": "12:52:42"}
+{"current_steps": 115, "total_steps": 546, "loss": 0.8545, "lr": 9.6479396637237e-06, "epoch": 0.6292749658002736, "percentage": 21.06, "elapsed_time": "3:25:51", "remaining_time": "12:51:32"}
+{"current_steps": 116, "total_steps": 546, "loss": 0.9157, "lr": 9.636052420353744e-06, "epoch": 0.6347469220246238, "percentage": 21.25, "elapsed_time": "3:27:50", "remaining_time": "12:50:26"}
+{"current_steps": 117, "total_steps": 546, "loss": 1.085, "lr": 9.623975382486206e-06, "epoch": 0.640218878248974, "percentage": 21.43, "elapsed_time": "3:29:36", "remaining_time": "12:48:34"}
+{"current_steps": 118, "total_steps": 546, "loss": 0.9142, "lr": 9.61170904454072e-06, "epoch": 0.6456908344733242, "percentage": 21.61, "elapsed_time": "3:31:27", "remaining_time": "12:46:58"}
+{"current_steps": 119, "total_steps": 546, "loss": 0.8722, "lr": 9.599253908686637e-06, "epoch": 0.6511627906976745, "percentage": 21.79, "elapsed_time": "3:33:10", "remaining_time": "12:44:53"}
+{"current_steps": 120, "total_steps": 546, "loss": 0.9536, "lr": 9.586610484822473e-06, "epoch": 0.6566347469220246, "percentage": 21.98, "elapsed_time": "3:34:48", "remaining_time": "12:42:33"}
+{"current_steps": 121, "total_steps": 546, "loss": 0.9002, "lr": 9.57377929055504e-06, "epoch": 0.6621067031463749, "percentage": 22.16, "elapsed_time": "3:36:34", "remaining_time": "12:40:41"}
+{"current_steps": 122, "total_steps": 546, "loss": 0.8881, "lr": 9.56076085117823e-06, "epoch": 0.667578659370725, "percentage": 22.34, "elapsed_time": "3:38:37", "remaining_time": "12:39:50"}
+{"current_steps": 123, "total_steps": 546, "loss": 0.8939, "lr": 9.547555699651546e-06, "epoch": 0.6730506155950753, "percentage": 22.53, "elapsed_time": "3:40:13", "remaining_time": "12:37:21"}
+{"current_steps": 124, "total_steps": 546, "loss": 0.8814, "lr": 9.534164376578257e-06, "epoch": 0.6785225718194254, "percentage": 22.71, "elapsed_time": "3:41:55", "remaining_time": "12:35:15"}
+{"current_steps": 125, "total_steps": 546, "loss": 0.8962, "lr": 9.520587430183275e-06, "epoch": 0.6839945280437757, "percentage": 22.89, "elapsed_time": "3:43:16", "remaining_time": "12:31:57"}
+{"current_steps": 126, "total_steps": 546, "loss": 0.8379, "lr": 9.506825416290712e-06, "epoch": 0.6894664842681258, "percentage": 23.08, "elapsed_time": "3:45:04", "remaining_time": "12:30:14"}
+{"current_steps": 127, "total_steps": 546, "loss": 0.825, "lr": 9.492878898301126e-06, "epoch": 0.6949384404924761, "percentage": 23.26, "elapsed_time": "3:47:33", "remaining_time": "12:30:44"}
+{"current_steps": 128, "total_steps": 546, "loss": 0.8565, "lr": 9.47874844716845e-06, "epoch": 0.7004103967168263, "percentage": 23.44, "elapsed_time": "3:49:45", "remaining_time": "12:30:19"}
+{"current_steps": 129, "total_steps": 546, "loss": 0.9507, "lr": 9.464434641376626e-06, "epoch": 0.7058823529411765, "percentage": 23.63, "elapsed_time": "3:51:39", "remaining_time": "12:28:51"}
+{"current_steps": 130, "total_steps": 546, "loss": 0.8671, "lr": 9.449938066915918e-06, "epoch": 0.7113543091655267, "percentage": 23.81, "elapsed_time": "3:53:29", "remaining_time": "12:27:09"}
+{"current_steps": 131, "total_steps": 546, "loss": 0.8903, "lr": 9.435259317258922e-06, "epoch": 0.7168262653898769, "percentage": 23.99, "elapsed_time": "3:55:54", "remaining_time": "12:27:21"}
+{"current_steps": 132, "total_steps": 546, "loss": 0.9351, "lr": 9.42039899333627e-06, "epoch": 0.7222982216142271, "percentage": 24.18, "elapsed_time": "3:57:37", "remaining_time": "12:25:17"}
+{"current_steps": 133, "total_steps": 546, "loss": 0.9344, "lr": 9.40535770351203e-06, "epoch": 0.7277701778385773, "percentage": 24.36, "elapsed_time": "3:59:54", "remaining_time": "12:24:58"}
+{"current_steps": 134, "total_steps": 546, "loss": 0.8538, "lr": 9.390136063558803e-06, "epoch": 0.7332421340629275, "percentage": 24.54, "elapsed_time": "4:02:11", "remaining_time": "12:24:38"}
+{"current_steps": 135, "total_steps": 546, "loss": 0.851, "lr": 9.374734696632508e-06, "epoch": 0.7387140902872777, "percentage": 24.73, "elapsed_time": "4:04:00", "remaining_time": "12:22:53"}
+{"current_steps": 136, "total_steps": 546, "loss": 0.9007, "lr": 9.359154233246872e-06, "epoch": 0.7441860465116279, "percentage": 24.91, "elapsed_time": "4:05:53", "remaining_time": "12:21:16"}
+{"current_steps": 137, "total_steps": 546, "loss": 0.8761, "lr": 9.34339531124762e-06, "epoch": 0.7496580027359782, "percentage": 25.09, "elapsed_time": "4:07:47", "remaining_time": "12:19:46"}
+{"current_steps": 138, "total_steps": 546, "loss": 0.9599, "lr": 9.327458575786365e-06, "epoch": 0.7551299589603283, "percentage": 25.27, "elapsed_time": "4:09:52", "remaining_time": "12:18:44"}
+{"current_steps": 139, "total_steps": 546, "loss": 0.9159, "lr": 9.311344679294186e-06, "epoch": 0.7606019151846786, "percentage": 25.46, "elapsed_time": "4:11:49", "remaining_time": "12:17:21"}
+{"current_steps": 140, "total_steps": 546, "loss": 0.8942, "lr": 9.295054281454931e-06, "epoch": 0.7660738714090287, "percentage": 25.64, "elapsed_time": "4:13:35", "remaining_time": "12:15:26"}
+{"current_steps": 141, "total_steps": 546, "loss": 0.9061, "lr": 9.278588049178203e-06, "epoch": 0.771545827633379, "percentage": 25.82, "elapsed_time": "4:15:15", "remaining_time": "12:13:11"}
+{"current_steps": 142, "total_steps": 546, "loss": 0.8498, "lr": 9.261946656572056e-06, "epoch": 0.7770177838577291, "percentage": 26.01, "elapsed_time": "4:16:37", "remaining_time": "12:10:06"}
+{"current_steps": 143, "total_steps": 546, "loss": 0.9037, "lr": 9.2451307849154e-06, "epoch": 0.7824897400820794, "percentage": 26.19, "elapsed_time": "4:18:53", "remaining_time": "12:09:36"}
+{"current_steps": 144, "total_steps": 546, "loss": 0.8793, "lr": 9.228141122630114e-06, "epoch": 0.7879616963064295, "percentage": 26.37, "elapsed_time": "4:20:47", "remaining_time": "12:08:01"}
+{"current_steps": 145, "total_steps": 546, "loss": 0.9432, "lr": 9.21097836525286e-06, "epoch": 0.7934336525307798, "percentage": 26.56, "elapsed_time": "4:22:28", "remaining_time": "12:05:53"}
+{"current_steps": 146, "total_steps": 546, "loss": 0.862, "lr": 9.193643215406605e-06, "epoch": 0.79890560875513, "percentage": 26.74, "elapsed_time": "4:24:52", "remaining_time": "12:05:40"}
+{"current_steps": 147, "total_steps": 546, "loss": 0.8631, "lr": 9.176136382771861e-06, "epoch": 0.8043775649794802, "percentage": 26.92, "elapsed_time": "4:26:54", "remaining_time": "12:04:29"}
+{"current_steps": 148, "total_steps": 546, "loss": 1.0209, "lr": 9.15845858405763e-06, "epoch": 0.8098495212038304, "percentage": 27.11, "elapsed_time": "4:28:32", "remaining_time": "12:02:10"}
+{"current_steps": 149, "total_steps": 546, "loss": 0.9388, "lr": 9.140610542972064e-06, "epoch": 0.8153214774281806, "percentage": 27.29, "elapsed_time": "4:30:05", "remaining_time": "11:59:38"}
+{"current_steps": 150, "total_steps": 546, "loss": 0.8924, "lr": 9.122592990192836e-06, "epoch": 0.8207934336525308, "percentage": 27.47, "elapsed_time": "4:32:11", "remaining_time": "11:58:35"}
+{"current_steps": 151, "total_steps": 546, "loss": 0.8725, "lr": 9.104406663337222e-06, "epoch": 0.826265389876881, "percentage": 27.66, "elapsed_time": "4:33:40", "remaining_time": "11:55:54"}
+{"current_steps": 152, "total_steps": 546, "loss": 0.8792, "lr": 9.086052306931919e-06, "epoch": 0.8317373461012312, "percentage": 27.84, "elapsed_time": "4:35:34", "remaining_time": "11:54:19"}
+{"current_steps": 153, "total_steps": 546, "loss": 0.8701, "lr": 9.067530672382544e-06, "epoch": 0.8372093023255814, "percentage": 28.02, "elapsed_time": "4:37:56", "remaining_time": "11:53:55"}
+{"current_steps": 154, "total_steps": 546, "loss": 0.8282, "lr": 9.04884251794289e-06, "epoch": 0.8426812585499316, "percentage": 28.21, "elapsed_time": "4:39:22", "remaining_time": "11:51:07"}
+{"current_steps": 155, "total_steps": 546, "loss": 0.8931, "lr": 9.029988608683877e-06, "epoch": 0.8481532147742818, "percentage": 28.39, "elapsed_time": "4:41:23", "remaining_time": "11:49:49"}
+{"current_steps": 156, "total_steps": 546, "loss": 0.8944, "lr": 9.010969716462228e-06, "epoch": 0.853625170998632, "percentage": 28.57, "elapsed_time": "4:42:48", "remaining_time": "11:47:00"}
+{"current_steps": 157, "total_steps": 546, "loss": 0.8643, "lr": 8.991786619888873e-06, "epoch": 0.8590971272229823, "percentage": 28.75, "elapsed_time": "4:44:53", "remaining_time": "11:45:53"}
+{"current_steps": 158, "total_steps": 546, "loss": 0.9268, "lr": 8.972440104297078e-06, "epoch": 0.8645690834473324, "percentage": 28.94, "elapsed_time": "4:46:46", "remaining_time": "11:44:13"}
+{"current_steps": 159, "total_steps": 546, "loss": 0.8852, "lr": 8.952930961710284e-06, "epoch": 0.8700410396716827, "percentage": 29.12, "elapsed_time": "4:48:31", "remaining_time": "11:42:16"}
+{"current_steps": 160, "total_steps": 546, "loss": 0.9337, "lr": 8.933259990809698e-06, "epoch": 0.8755129958960328, "percentage": 29.3, "elapsed_time": "4:50:11", "remaining_time": "11:40:04"}
+{"current_steps": 161, "total_steps": 546, "loss": 0.9081, "lr": 8.913427996901574e-06, "epoch": 0.8809849521203831, "percentage": 29.49, "elapsed_time": "4:52:00", "remaining_time": "11:38:17"}
+{"current_steps": 162, "total_steps": 546, "loss": 0.7921, "lr": 8.893435791884268e-06, "epoch": 0.8864569083447332, "percentage": 29.67, "elapsed_time": "4:53:16", "remaining_time": "11:35:09"}
+{"current_steps": 163, "total_steps": 546, "loss": 0.8238, "lr": 8.873284194214983e-06, "epoch": 0.8919288645690835, "percentage": 29.85, "elapsed_time": "4:55:23", "remaining_time": "11:34:04"}
+{"current_steps": 164, "total_steps": 546, "loss": 0.8774, "lr": 8.852974028876273e-06, "epoch": 0.8974008207934336, "percentage": 30.04, "elapsed_time": "4:57:14", "remaining_time": "11:32:20"}
+{"current_steps": 165, "total_steps": 546, "loss": 0.8396, "lr": 8.832506127342261e-06, "epoch": 0.9028727770177839, "percentage": 30.22, "elapsed_time": "4:58:34", "remaining_time": "11:29:27"}
+{"current_steps": 166, "total_steps": 546, "loss": 0.829, "lr": 8.811881327544604e-06, "epoch": 0.908344733242134, "percentage": 30.4, "elapsed_time": "5:00:44", "remaining_time": "11:28:26"}
+{"current_steps": 167, "total_steps": 546, "loss": 0.8345, "lr": 8.79110047383819e-06, "epoch": 0.9138166894664843, "percentage": 30.59, "elapsed_time": "5:02:13", "remaining_time": "11:25:54"}
+{"current_steps": 168, "total_steps": 546, "loss": 0.9128, "lr": 8.770164416966565e-06, "epoch": 0.9192886456908345, "percentage": 30.77, "elapsed_time": "5:03:36", "remaining_time": "11:23:07"}
+{"current_steps": 169, "total_steps": 546, "loss": 0.8803, "lr": 8.749074014027116e-06, "epoch": 0.9247606019151847, "percentage": 30.95, "elapsed_time": "5:05:43", "remaining_time": "11:21:59"}
+{"current_steps": 170, "total_steps": 546, "loss": 0.8813, "lr": 8.727830128435965e-06, "epoch": 0.9302325581395349, "percentage": 31.14, "elapsed_time": "5:07:24", "remaining_time": "11:19:55"}
+{"current_steps": 171, "total_steps": 546, "loss": 0.8473, "lr": 8.706433629892643e-06, "epoch": 0.9357045143638851, "percentage": 31.32, "elapsed_time": "5:08:49", "remaining_time": "11:17:15"}
+{"current_steps": 172, "total_steps": 546, "loss": 0.8233, "lr": 8.684885394344469e-06, "epoch": 0.9411764705882353, "percentage": 31.5, "elapsed_time": "5:11:06", "remaining_time": "11:16:29"}
+{"current_steps": 173, "total_steps": 546, "loss": 0.8639, "lr": 8.663186303950694e-06, "epoch": 0.9466484268125855, "percentage": 31.68, "elapsed_time": "5:12:29", "remaining_time": "11:13:44"}
+{"current_steps": 174, "total_steps": 546, "loss": 0.8479, "lr": 8.64133724704639e-06, "epoch": 0.9521203830369357, "percentage": 31.87, "elapsed_time": "5:14:31", "remaining_time": "11:12:26"}
+{"current_steps": 175, "total_steps": 546, "loss": 0.772, "lr": 8.61933911810608e-06, "epoch": 0.957592339261286, "percentage": 32.05, "elapsed_time": "5:16:17", "remaining_time": "11:10:31"}
+{"current_steps": 176, "total_steps": 546, "loss": 0.8885, "lr": 8.597192817707121e-06, "epoch": 0.9630642954856361, "percentage": 32.23, "elapsed_time": "5:18:20", "remaining_time": "11:09:15"}
+{"current_steps": 177, "total_steps": 546, "loss": 0.8218, "lr": 8.574899252492833e-06, "epoch": 0.9685362517099864, "percentage": 32.42, "elapsed_time": "5:19:59", "remaining_time": "11:07:05"}
+{"current_steps": 178, "total_steps": 546, "loss": 0.8549, "lr": 8.552459335135382e-06, "epoch": 0.9740082079343365, "percentage": 32.6, "elapsed_time": "5:21:59", "remaining_time": "11:05:41"}
+{"current_steps": 179, "total_steps": 546, "loss": 0.893, "lr": 8.529873984298418e-06, "epoch": 0.9794801641586868, "percentage": 32.78, "elapsed_time": "5:23:35", "remaining_time": "11:03:27"}
+{"current_steps": 180, "total_steps": 546, "loss": 0.7664, "lr": 8.507144124599469e-06, "epoch": 0.9849521203830369, "percentage": 32.97, "elapsed_time": "5:25:01", "remaining_time": "11:00:53"}
+{"current_steps": 181, "total_steps": 546, "loss": 0.8556, "lr": 8.484270686572078e-06, "epoch": 0.9904240766073872, "percentage": 33.15, "elapsed_time": "5:26:36", "remaining_time": "10:58:37"}
+{"current_steps": 182, "total_steps": 546, "loss": 0.8664, "lr": 8.46125460662772e-06, "epoch": 0.9958960328317373, "percentage": 33.33, "elapsed_time": "5:28:37", "remaining_time": "10:57:15"}
+{"current_steps": 183, "total_steps": 546, "loss": 0.8435, "lr": 8.438096827017461e-06, "epoch": 1.0, "percentage": 33.52, "elapsed_time": "5:29:58", "remaining_time": "10:54:32"}
+{"current_steps": 184, "total_steps": 546, "loss": 0.6684, "lr": 8.41479829579338e-06, "epoch": 1.0054719562243501, "percentage": 33.7, "elapsed_time": "5:31:18", "remaining_time": "10:51:48"}
+{"current_steps": 185, "total_steps": 546, "loss": 0.6753, "lr": 8.391359966769765e-06, "epoch": 1.0109439124487003, "percentage": 33.88, "elapsed_time": "5:33:07", "remaining_time": "10:50:02"}
+{"current_steps": 186, "total_steps": 546, "loss": 0.724, "lr": 8.367782799484057e-06, "epoch": 1.0164158686730507, "percentage": 34.07, "elapsed_time": "5:35:31", "remaining_time": "10:49:24"}
+{"current_steps": 187, "total_steps": 546, "loss": 0.6771, "lr": 8.344067759157572e-06, "epoch": 1.0218878248974008, "percentage": 34.25, "elapsed_time": "5:37:43", "remaining_time": "10:48:22"}
+{"current_steps": 188, "total_steps": 546, "loss": 0.7047, "lr": 8.320215816655987e-06, "epoch": 1.027359781121751, "percentage": 34.43, "elapsed_time": "5:39:25", "remaining_time": "10:46:21"}
+{"current_steps": 189, "total_steps": 546, "loss": 0.7324, "lr": 8.296227948449589e-06, "epoch": 1.0328317373461013, "percentage": 34.62, "elapsed_time": "5:41:43", "remaining_time": "10:45:28"}
+{"current_steps": 190, "total_steps": 546, "loss": 0.6813, "lr": 8.272105136573304e-06, "epoch": 1.0383036935704515, "percentage": 34.8, "elapsed_time": "5:44:03", "remaining_time": "10:44:40"}
+{"current_steps": 191, "total_steps": 546, "loss": 0.7278, "lr": 8.247848368586491e-06, "epoch": 1.0437756497948016, "percentage": 34.98, "elapsed_time": "5:46:11", "remaining_time": "10:43:27"}
+{"current_steps": 192, "total_steps": 546, "loss": 0.6951, "lr": 8.223458637532516e-06, "epoch": 1.0492476060191518, "percentage": 35.16, "elapsed_time": "5:47:39", "remaining_time": "10:40:59"}
+{"current_steps": 193, "total_steps": 546, "loss": 0.634, "lr": 8.198936941898092e-06, "epoch": 1.054719562243502, "percentage": 35.35, "elapsed_time": "5:49:17", "remaining_time": "10:38:52"}
+{"current_steps": 194, "total_steps": 546, "loss": 0.6791, "lr": 8.174284285572408e-06, "epoch": 1.0601915184678523, "percentage": 35.53, "elapsed_time": "5:51:36", "remaining_time": "10:37:59"}
+{"current_steps": 195, "total_steps": 546, "loss": 0.6872, "lr": 8.14950167780603e-06, "epoch": 1.0656634746922025, "percentage": 35.71, "elapsed_time": "5:53:52", "remaining_time": "10:36:58"}
+{"current_steps": 196, "total_steps": 546, "loss": 0.6869, "lr": 8.12459013316958e-06, "epoch": 1.0711354309165526, "percentage": 35.9, "elapsed_time": "5:56:07", "remaining_time": "10:35:56"}
+{"current_steps": 197, "total_steps": 546, "loss": 0.7162, "lr": 8.099550671512202e-06, "epoch": 1.076607387140903, "percentage": 36.08, "elapsed_time": "5:57:52", "remaining_time": "10:33:59"}
+{"current_steps": 198, "total_steps": 546, "loss": 0.6265, "lr": 8.074384317919812e-06, "epoch": 1.0820793433652531, "percentage": 36.26, "elapsed_time": "5:59:26", "remaining_time": "10:31:44"}
+{"current_steps": 199, "total_steps": 546, "loss": 0.6755, "lr": 8.049092102673135e-06, "epoch": 1.0875512995896033, "percentage": 36.45, "elapsed_time": "6:01:18", "remaining_time": "10:30:01"}
+{"current_steps": 200, "total_steps": 546, "loss": 0.7468, "lr": 8.023675061205519e-06, "epoch": 1.0930232558139534, "percentage": 36.63, "elapsed_time": "6:03:20", "remaining_time": "10:28:34"}
+{"current_steps": 201, "total_steps": 546, "loss": 0.6451, "lr": 7.99813423406055e-06, "epoch": 1.0984952120383036, "percentage": 36.81, "elapsed_time": "6:06:32", "remaining_time": "10:29:08"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf94a39ef4a68de1cf8c9549e01851bb7e5bca28b49f0e652e53230b32b1aaf0
+size 8273