Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543e4ea525f108540f6a481bbbce612b97427c8391f109b35e96edf39093bd07
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8483d9a5565eefd24c1b90f7ce45d6ea08f20f9fd8855a168b156a111b9e27fb
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4c1e7d20ef366badd7d834cb27417b171f0708f49d8eb505d7fbd93a345250
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d21825a78aa9727a6db5cb8f59b89f2ca93d6be9082e4f583cb843877b00313
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,209 @@
+{"current_steps": 1, "total_steps": 621, "loss": 1.2509, "lr": 1.5873015873015874e-07, "epoch": 0.004830917874396135, "percentage": 0.16, "elapsed_time": "0:00:59", "remaining_time": "10:16:12"}
+{"current_steps": 2, "total_steps": 621, "loss": 1.294, "lr": 3.174603174603175e-07, "epoch": 0.00966183574879227, "percentage": 0.32, "elapsed_time": "0:01:54", "remaining_time": "9:51:03"}
+{"current_steps": 3, "total_steps": 621, "loss": 1.2325, "lr": 4.7619047619047623e-07, "epoch": 0.014492753623188406, "percentage": 0.48, "elapsed_time": "0:02:35", "remaining_time": "8:53:44"}
+{"current_steps": 4, "total_steps": 621, "loss": 1.2676, "lr": 6.34920634920635e-07, "epoch": 0.01932367149758454, "percentage": 0.64, "elapsed_time": "0:03:19", "remaining_time": "8:32:42"}
+{"current_steps": 5, "total_steps": 621, "loss": 1.2375, "lr": 7.936507936507937e-07, "epoch": 0.024154589371980676, "percentage": 0.81, "elapsed_time": "0:04:10", "remaining_time": "8:35:11"}
+{"current_steps": 6, "total_steps": 621, "loss": 1.2592, "lr": 9.523809523809525e-07, "epoch": 0.028985507246376812, "percentage": 0.97, "elapsed_time": "0:04:54", "remaining_time": "8:23:38"}
+{"current_steps": 7, "total_steps": 621, "loss": 1.2144, "lr": 1.111111111111111e-06, "epoch": 0.033816425120772944, "percentage": 1.13, "elapsed_time": "0:05:39", "remaining_time": "8:16:32"}
+{"current_steps": 8, "total_steps": 621, "loss": 1.1995, "lr": 1.26984126984127e-06, "epoch": 0.03864734299516908, "percentage": 1.29, "elapsed_time": "0:06:28", "remaining_time": "8:16:12"}
+{"current_steps": 9, "total_steps": 621, "loss": 1.1667, "lr": 1.4285714285714286e-06, "epoch": 0.043478260869565216, "percentage": 1.45, "elapsed_time": "0:07:21", "remaining_time": "8:20:09"}
+{"current_steps": 10, "total_steps": 621, "loss": 1.2129, "lr": 1.5873015873015873e-06, "epoch": 0.04830917874396135, "percentage": 1.61, "elapsed_time": "0:08:03", "remaining_time": "8:12:19"}
+{"current_steps": 11, "total_steps": 621, "loss": 1.2057, "lr": 1.746031746031746e-06, "epoch": 0.05314009661835749, "percentage": 1.77, "elapsed_time": "0:08:44", "remaining_time": "8:05:04"}
+{"current_steps": 12, "total_steps": 621, "loss": 1.1337, "lr": 1.904761904761905e-06, "epoch": 0.057971014492753624, "percentage": 1.93, "elapsed_time": "0:09:37", "remaining_time": "8:08:10"}
+{"current_steps": 13, "total_steps": 621, "loss": 1.1577, "lr": 2.0634920634920634e-06, "epoch": 0.06280193236714976, "percentage": 2.09, "elapsed_time": "0:10:26", "remaining_time": "8:08:06"}
+{"current_steps": 14, "total_steps": 621, "loss": 1.1333, "lr": 2.222222222222222e-06, "epoch": 0.06763285024154589, "percentage": 2.25, "elapsed_time": "0:11:20", "remaining_time": "8:11:30"}
+{"current_steps": 15, "total_steps": 621, "loss": 1.1074, "lr": 2.380952380952381e-06, "epoch": 0.07246376811594203, "percentage": 2.42, "elapsed_time": "0:12:04", "remaining_time": "8:07:39"}
+{"current_steps": 16, "total_steps": 621, "loss": 1.1057, "lr": 2.53968253968254e-06, "epoch": 0.07729468599033816, "percentage": 2.58, "elapsed_time": "0:12:52", "remaining_time": "8:07:02"}
+{"current_steps": 17, "total_steps": 621, "loss": 1.1045, "lr": 2.6984126984126986e-06, "epoch": 0.0821256038647343, "percentage": 2.74, "elapsed_time": "0:13:37", "remaining_time": "8:03:54"}
+{"current_steps": 18, "total_steps": 621, "loss": 1.1112, "lr": 2.8571428571428573e-06, "epoch": 0.08695652173913043, "percentage": 2.9, "elapsed_time": "0:14:28", "remaining_time": "8:04:41"}
+{"current_steps": 19, "total_steps": 621, "loss": 1.0995, "lr": 3.015873015873016e-06, "epoch": 0.09178743961352658, "percentage": 3.06, "elapsed_time": "0:15:12", "remaining_time": "8:02:03"}
+{"current_steps": 20, "total_steps": 621, "loss": 1.0742, "lr": 3.1746031746031746e-06, "epoch": 0.0966183574879227, "percentage": 3.22, "elapsed_time": "0:16:03", "remaining_time": "8:02:28"}
+{"current_steps": 21, "total_steps": 621, "loss": 1.0497, "lr": 3.3333333333333333e-06, "epoch": 0.10144927536231885, "percentage": 3.38, "elapsed_time": "0:16:53", "remaining_time": "8:02:28"}
+{"current_steps": 22, "total_steps": 621, "loss": 1.0556, "lr": 3.492063492063492e-06, "epoch": 0.10628019323671498, "percentage": 3.54, "elapsed_time": "0:17:37", "remaining_time": "7:59:42"}
+{"current_steps": 23, "total_steps": 621, "loss": 1.0459, "lr": 3.6507936507936507e-06, "epoch": 0.1111111111111111, "percentage": 3.7, "elapsed_time": "0:18:24", "remaining_time": "7:58:41"}
+{"current_steps": 24, "total_steps": 621, "loss": 1.0059, "lr": 3.80952380952381e-06, "epoch": 0.11594202898550725, "percentage": 3.86, "elapsed_time": "0:19:08", "remaining_time": "7:56:13"}
+{"current_steps": 25, "total_steps": 621, "loss": 0.9934, "lr": 3.968253968253968e-06, "epoch": 0.12077294685990338, "percentage": 4.03, "elapsed_time": "0:19:53", "remaining_time": "7:54:06"}
+{"current_steps": 26, "total_steps": 621, "loss": 1.0023, "lr": 4.126984126984127e-06, "epoch": 0.12560386473429952, "percentage": 4.19, "elapsed_time": "0:20:43", "remaining_time": "7:54:16"}
+{"current_steps": 27, "total_steps": 621, "loss": 1.0085, "lr": 4.2857142857142855e-06, "epoch": 0.13043478260869565, "percentage": 4.35, "elapsed_time": "0:21:43", "remaining_time": "7:57:52"}
+{"current_steps": 28, "total_steps": 621, "loss": 1.0117, "lr": 4.444444444444444e-06, "epoch": 0.13526570048309178, "percentage": 4.51, "elapsed_time": "0:22:29", "remaining_time": "7:56:10"}
+{"current_steps": 29, "total_steps": 621, "loss": 1.022, "lr": 4.603174603174604e-06, "epoch": 0.14009661835748793, "percentage": 4.67, "elapsed_time": "0:23:21", "remaining_time": "7:56:47"}
+{"current_steps": 30, "total_steps": 621, "loss": 0.9697, "lr": 4.761904761904762e-06, "epoch": 0.14492753623188406, "percentage": 4.83, "elapsed_time": "0:24:05", "remaining_time": "7:54:29"}
+{"current_steps": 31, "total_steps": 621, "loss": 0.9374, "lr": 4.920634920634921e-06, "epoch": 0.1497584541062802, "percentage": 4.99, "elapsed_time": "0:24:53", "remaining_time": "7:53:42"}
+{"current_steps": 32, "total_steps": 621, "loss": 0.9662, "lr": 5.07936507936508e-06, "epoch": 0.15458937198067632, "percentage": 5.15, "elapsed_time": "0:25:41", "remaining_time": "7:52:47"}
+{"current_steps": 33, "total_steps": 621, "loss": 0.9419, "lr": 5.2380952380952384e-06, "epoch": 0.15942028985507245, "percentage": 5.31, "elapsed_time": "0:26:25", "remaining_time": "7:50:48"}
+{"current_steps": 34, "total_steps": 621, "loss": 0.9036, "lr": 5.396825396825397e-06, "epoch": 0.1642512077294686, "percentage": 5.48, "elapsed_time": "0:27:04", "remaining_time": "7:47:32"}
+{"current_steps": 35, "total_steps": 621, "loss": 0.9402, "lr": 5.555555555555557e-06, "epoch": 0.16908212560386474, "percentage": 5.64, "elapsed_time": "0:27:50", "remaining_time": "7:46:08"}
+{"current_steps": 36, "total_steps": 621, "loss": 0.9335, "lr": 5.7142857142857145e-06, "epoch": 0.17391304347826086, "percentage": 5.8, "elapsed_time": "0:28:41", "remaining_time": "7:46:20"}
+{"current_steps": 37, "total_steps": 621, "loss": 0.9084, "lr": 5.873015873015874e-06, "epoch": 0.178743961352657, "percentage": 5.96, "elapsed_time": "0:29:24", "remaining_time": "7:44:07"}
+{"current_steps": 38, "total_steps": 621, "loss": 0.9343, "lr": 6.031746031746032e-06, "epoch": 0.18357487922705315, "percentage": 6.12, "elapsed_time": "0:30:15", "remaining_time": "7:44:10"}
+{"current_steps": 39, "total_steps": 621, "loss": 0.9141, "lr": 6.1904761904761914e-06, "epoch": 0.18840579710144928, "percentage": 6.28, "elapsed_time": "0:30:49", "remaining_time": "7:40:06"}
+{"current_steps": 40, "total_steps": 621, "loss": 0.9409, "lr": 6.349206349206349e-06, "epoch": 0.1932367149758454, "percentage": 6.44, "elapsed_time": "0:31:44", "remaining_time": "7:41:03"}
+{"current_steps": 41, "total_steps": 621, "loss": 0.9085, "lr": 6.507936507936509e-06, "epoch": 0.19806763285024154, "percentage": 6.6, "elapsed_time": "0:32:27", "remaining_time": "7:39:11"}
+{"current_steps": 42, "total_steps": 621, "loss": 0.9286, "lr": 6.666666666666667e-06, "epoch": 0.2028985507246377, "percentage": 6.76, "elapsed_time": "0:33:22", "remaining_time": "7:40:09"}
+{"current_steps": 43, "total_steps": 621, "loss": 0.9239, "lr": 6.825396825396826e-06, "epoch": 0.20772946859903382, "percentage": 6.92, "elapsed_time": "0:34:09", "remaining_time": "7:39:09"}
+{"current_steps": 44, "total_steps": 621, "loss": 0.9135, "lr": 6.984126984126984e-06, "epoch": 0.21256038647342995, "percentage": 7.09, "elapsed_time": "0:35:02", "remaining_time": "7:39:34"}
+{"current_steps": 45, "total_steps": 621, "loss": 0.9253, "lr": 7.1428571428571436e-06, "epoch": 0.21739130434782608, "percentage": 7.25, "elapsed_time": "0:35:45", "remaining_time": "7:37:44"}
+{"current_steps": 46, "total_steps": 621, "loss": 0.9366, "lr": 7.301587301587301e-06, "epoch": 0.2222222222222222, "percentage": 7.41, "elapsed_time": "0:36:39", "remaining_time": "7:38:10"}
+{"current_steps": 47, "total_steps": 621, "loss": 0.9105, "lr": 7.460317460317461e-06, "epoch": 0.22705314009661837, "percentage": 7.57, "elapsed_time": "0:37:24", "remaining_time": "7:36:48"}
+{"current_steps": 48, "total_steps": 621, "loss": 0.8868, "lr": 7.61904761904762e-06, "epoch": 0.2318840579710145, "percentage": 7.73, "elapsed_time": "0:38:10", "remaining_time": "7:35:43"}
+{"current_steps": 49, "total_steps": 621, "loss": 0.887, "lr": 7.77777777777778e-06, "epoch": 0.23671497584541062, "percentage": 7.89, "elapsed_time": "0:38:55", "remaining_time": "7:34:23"}
+{"current_steps": 50, "total_steps": 621, "loss": 0.906, "lr": 7.936507936507936e-06, "epoch": 0.24154589371980675, "percentage": 8.05, "elapsed_time": "0:39:45", "remaining_time": "7:34:02"}
+{"current_steps": 51, "total_steps": 621, "loss": 0.9321, "lr": 8.095238095238097e-06, "epoch": 0.2463768115942029, "percentage": 8.21, "elapsed_time": "0:40:30", "remaining_time": "7:32:39"}
+{"current_steps": 52, "total_steps": 621, "loss": 0.9195, "lr": 8.253968253968254e-06, "epoch": 0.25120772946859904, "percentage": 8.37, "elapsed_time": "0:41:11", "remaining_time": "7:30:44"}
+{"current_steps": 53, "total_steps": 621, "loss": 0.932, "lr": 8.412698412698414e-06, "epoch": 0.2560386473429952, "percentage": 8.53, "elapsed_time": "0:42:00", "remaining_time": "7:30:12"}
+{"current_steps": 54, "total_steps": 621, "loss": 0.9115, "lr": 8.571428571428571e-06, "epoch": 0.2608695652173913, "percentage": 8.7, "elapsed_time": "0:42:44", "remaining_time": "7:28:52"}
+{"current_steps": 55, "total_steps": 621, "loss": 0.917, "lr": 8.730158730158731e-06, "epoch": 0.26570048309178745, "percentage": 8.86, "elapsed_time": "0:43:36", "remaining_time": "7:28:47"}
+{"current_steps": 56, "total_steps": 621, "loss": 0.8916, "lr": 8.888888888888888e-06, "epoch": 0.27053140096618356, "percentage": 9.02, "elapsed_time": "0:44:19", "remaining_time": "7:27:07"}
+{"current_steps": 57, "total_steps": 621, "loss": 0.8831, "lr": 9.047619047619049e-06, "epoch": 0.2753623188405797, "percentage": 9.18, "elapsed_time": "0:45:08", "remaining_time": "7:26:43"}
+{"current_steps": 58, "total_steps": 621, "loss": 0.901, "lr": 9.206349206349207e-06, "epoch": 0.28019323671497587, "percentage": 9.34, "elapsed_time": "0:45:54", "remaining_time": "7:25:38"}
+{"current_steps": 59, "total_steps": 621, "loss": 0.9124, "lr": 9.365079365079366e-06, "epoch": 0.28502415458937197, "percentage": 9.5, "elapsed_time": "0:46:43", "remaining_time": "7:25:03"}
+{"current_steps": 60, "total_steps": 621, "loss": 0.8774, "lr": 9.523809523809525e-06, "epoch": 0.2898550724637681, "percentage": 9.66, "elapsed_time": "0:47:36", "remaining_time": "7:25:07"}
+{"current_steps": 61, "total_steps": 621, "loss": 0.9277, "lr": 9.682539682539683e-06, "epoch": 0.2946859903381642, "percentage": 9.82, "elapsed_time": "0:48:21", "remaining_time": "7:23:56"}
+{"current_steps": 62, "total_steps": 621, "loss": 0.8504, "lr": 9.841269841269842e-06, "epoch": 0.2995169082125604, "percentage": 9.98, "elapsed_time": "0:49:08", "remaining_time": "7:23:01"}
+{"current_steps": 63, "total_steps": 621, "loss": 0.9119, "lr": 1e-05, "epoch": 0.30434782608695654, "percentage": 10.14, "elapsed_time": "0:49:59", "remaining_time": "7:22:45"}
+{"current_steps": 64, "total_steps": 621, "loss": 0.8696, "lr": 9.999920755303033e-06, "epoch": 0.30917874396135264, "percentage": 10.31, "elapsed_time": "0:50:40", "remaining_time": "7:20:59"}
+{"current_steps": 65, "total_steps": 621, "loss": 0.8948, "lr": 9.999683023724021e-06, "epoch": 0.3140096618357488, "percentage": 10.47, "elapsed_time": "0:51:27", "remaining_time": "7:20:08"}
+{"current_steps": 66, "total_steps": 621, "loss": 0.9085, "lr": 9.99928681279855e-06, "epoch": 0.3188405797101449, "percentage": 10.63, "elapsed_time": "0:52:16", "remaining_time": "7:19:35"}
+{"current_steps": 67, "total_steps": 621, "loss": 0.9368, "lr": 9.998732135085665e-06, "epoch": 0.32367149758454106, "percentage": 10.79, "elapsed_time": "0:53:04", "remaining_time": "7:18:50"}
+{"current_steps": 68, "total_steps": 621, "loss": 0.8966, "lr": 9.998019008167476e-06, "epoch": 0.3285024154589372, "percentage": 10.95, "elapsed_time": "0:53:53", "remaining_time": "7:18:17"}
+{"current_steps": 69, "total_steps": 621, "loss": 0.8806, "lr": 9.99714745464859e-06, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:54:41", "remaining_time": "7:17:31"}
+{"current_steps": 70, "total_steps": 621, "loss": 0.9018, "lr": 9.99611750215541e-06, "epoch": 0.33816425120772947, "percentage": 11.27, "elapsed_time": "0:55:16", "remaining_time": "7:15:08"}
+{"current_steps": 71, "total_steps": 621, "loss": 0.8668, "lr": 9.994929183335237e-06, "epoch": 0.34299516908212563, "percentage": 11.43, "elapsed_time": "0:56:04", "remaining_time": "7:14:20"}
+{"current_steps": 72, "total_steps": 621, "loss": 0.8809, "lr": 9.993582535855265e-06, "epoch": 0.34782608695652173, "percentage": 11.59, "elapsed_time": "0:56:54", "remaining_time": "7:13:55"}
+{"current_steps": 73, "total_steps": 621, "loss": 0.8878, "lr": 9.992077602401358e-06, "epoch": 0.3526570048309179, "percentage": 11.76, "elapsed_time": "0:57:36", "remaining_time": "7:12:27"}
+{"current_steps": 74, "total_steps": 621, "loss": 0.8555, "lr": 9.990414430676716e-06, "epoch": 0.357487922705314, "percentage": 11.92, "elapsed_time": "0:58:15", "remaining_time": "7:10:34"}
+{"current_steps": 75, "total_steps": 621, "loss": 0.8852, "lr": 9.988593073400354e-06, "epoch": 0.36231884057971014, "percentage": 12.08, "elapsed_time": "0:58:54", "remaining_time": "7:08:51"}
+{"current_steps": 76, "total_steps": 621, "loss": 0.8572, "lr": 9.986613588305435e-06, "epoch": 0.3671497584541063, "percentage": 12.24, "elapsed_time": "0:59:48", "remaining_time": "7:08:52"}
+{"current_steps": 77, "total_steps": 621, "loss": 0.9015, "lr": 9.984476038137437e-06, "epoch": 0.3719806763285024, "percentage": 12.4, "elapsed_time": "1:00:36", "remaining_time": "7:08:08"}
+{"current_steps": 78, "total_steps": 621, "loss": 0.8912, "lr": 9.982180490652165e-06, "epoch": 0.37681159420289856, "percentage": 12.56, "elapsed_time": "1:01:25", "remaining_time": "7:07:35"}
+{"current_steps": 79, "total_steps": 621, "loss": 0.9033, "lr": 9.979727018613607e-06, "epoch": 0.38164251207729466, "percentage": 12.72, "elapsed_time": "1:02:01", "remaining_time": "7:05:30"}
+{"current_steps": 80, "total_steps": 621, "loss": 0.8583, "lr": 9.977115699791622e-06, "epoch": 0.3864734299516908, "percentage": 12.88, "elapsed_time": "1:02:49", "remaining_time": "7:04:49"}
+{"current_steps": 81, "total_steps": 621, "loss": 0.8625, "lr": 9.974346616959476e-06, "epoch": 0.391304347826087, "percentage": 13.04, "elapsed_time": "1:03:33", "remaining_time": "7:03:40"}
+{"current_steps": 82, "total_steps": 621, "loss": 0.8967, "lr": 9.971419857891223e-06, "epoch": 0.3961352657004831, "percentage": 13.2, "elapsed_time": "1:04:17", "remaining_time": "7:02:38"}
+{"current_steps": 83, "total_steps": 621, "loss": 0.8727, "lr": 9.968335515358916e-06, "epoch": 0.40096618357487923, "percentage": 13.37, "elapsed_time": "1:05:10", "remaining_time": "7:02:24"}
+{"current_steps": 84, "total_steps": 621, "loss": 0.8489, "lr": 9.965093687129669e-06, "epoch": 0.4057971014492754, "percentage": 13.53, "elapsed_time": "1:05:56", "remaining_time": "7:01:30"}
+{"current_steps": 85, "total_steps": 621, "loss": 0.8862, "lr": 9.961694475962562e-06, "epoch": 0.4106280193236715, "percentage": 13.69, "elapsed_time": "1:06:36", "remaining_time": "6:59:59"}
+{"current_steps": 86, "total_steps": 621, "loss": 0.8481, "lr": 9.95813798960538e-06, "epoch": 0.41545893719806765, "percentage": 13.85, "elapsed_time": "1:07:21", "remaining_time": "6:58:59"}
+{"current_steps": 87, "total_steps": 621, "loss": 0.8574, "lr": 9.954424340791195e-06, "epoch": 0.42028985507246375, "percentage": 14.01, "elapsed_time": "1:08:01", "remaining_time": "6:57:29"}
+{"current_steps": 88, "total_steps": 621, "loss": 0.8876, "lr": 9.950553647234798e-06, "epoch": 0.4251207729468599, "percentage": 14.17, "elapsed_time": "1:08:49", "remaining_time": "6:56:51"}
+{"current_steps": 89, "total_steps": 621, "loss": 0.8833, "lr": 9.94652603162896e-06, "epoch": 0.42995169082125606, "percentage": 14.33, "elapsed_time": "1:09:31", "remaining_time": "6:55:35"}
+{"current_steps": 90, "total_steps": 621, "loss": 0.842, "lr": 9.942341621640558e-06, "epoch": 0.43478260869565216, "percentage": 14.49, "elapsed_time": "1:10:19", "remaining_time": "6:54:54"}
+{"current_steps": 91, "total_steps": 621, "loss": 0.8724, "lr": 9.938000549906509e-06, "epoch": 0.4396135265700483, "percentage": 14.65, "elapsed_time": "1:11:12", "remaining_time": "6:54:43"}
+{"current_steps": 92, "total_steps": 621, "loss": 0.8459, "lr": 9.93350295402958e-06, "epoch": 0.4444444444444444, "percentage": 14.81, "elapsed_time": "1:12:00", "remaining_time": "6:54:05"}
+{"current_steps": 93, "total_steps": 621, "loss": 0.8793, "lr": 9.92884897657402e-06, "epoch": 0.4492753623188406, "percentage": 14.98, "elapsed_time": "1:12:37", "remaining_time": "6:52:16"}
+{"current_steps": 94, "total_steps": 621, "loss": 0.8618, "lr": 9.924038765061042e-06, "epoch": 0.45410628019323673, "percentage": 15.14, "elapsed_time": "1:13:23", "remaining_time": "6:51:27"}
+{"current_steps": 95, "total_steps": 621, "loss": 0.8547, "lr": 9.919072471964146e-06, "epoch": 0.45893719806763283, "percentage": 15.3, "elapsed_time": "1:14:12", "remaining_time": "6:50:54"}
+{"current_steps": 96, "total_steps": 621, "loss": 0.8545, "lr": 9.913950254704291e-06, "epoch": 0.463768115942029, "percentage": 15.46, "elapsed_time": "1:14:50", "remaining_time": "6:49:17"}
+{"current_steps": 97, "total_steps": 621, "loss": 0.8642, "lr": 9.908672275644898e-06, "epoch": 0.46859903381642515, "percentage": 15.62, "elapsed_time": "1:15:42", "remaining_time": "6:49:00"}
+{"current_steps": 98, "total_steps": 621, "loss": 0.8677, "lr": 9.903238702086707e-06, "epoch": 0.47342995169082125, "percentage": 15.78, "elapsed_time": "1:16:33", "remaining_time": "6:48:31"}
+{"current_steps": 99, "total_steps": 621, "loss": 0.8784, "lr": 9.897649706262474e-06, "epoch": 0.4782608695652174, "percentage": 15.94, "elapsed_time": "1:17:19", "remaining_time": "6:47:44"}
+{"current_steps": 100, "total_steps": 621, "loss": 0.8929, "lr": 9.89190546533151e-06, "epoch": 0.4830917874396135, "percentage": 16.1, "elapsed_time": "1:18:03", "remaining_time": "6:46:40"}
+{"current_steps": 101, "total_steps": 621, "loss": 0.8687, "lr": 9.88600616137407e-06, "epoch": 0.48792270531400966, "percentage": 16.26, "elapsed_time": "1:18:48", "remaining_time": "6:45:44"}
+{"current_steps": 102, "total_steps": 621, "loss": 0.8278, "lr": 9.879951981385577e-06, "epoch": 0.4927536231884058, "percentage": 16.43, "elapsed_time": "1:19:38", "remaining_time": "6:45:13"}
+{"current_steps": 103, "total_steps": 621, "loss": 0.8751, "lr": 9.873743117270691e-06, "epoch": 0.4975845410628019, "percentage": 16.59, "elapsed_time": "1:20:31", "remaining_time": "6:44:57"}
+{"current_steps": 104, "total_steps": 621, "loss": 0.8885, "lr": 9.867379765837237e-06, "epoch": 0.5024154589371981, "percentage": 16.75, "elapsed_time": "1:21:25", "remaining_time": "6:44:44"}
+{"current_steps": 105, "total_steps": 621, "loss": 0.8686, "lr": 9.860862128789954e-06, "epoch": 0.5072463768115942, "percentage": 16.91, "elapsed_time": "1:22:24", "remaining_time": "6:45:00"}
+{"current_steps": 106, "total_steps": 621, "loss": 0.8665, "lr": 9.854190412724114e-06, "epoch": 0.5120772946859904, "percentage": 17.07, "elapsed_time": "1:23:12", "remaining_time": "6:44:15"}
+{"current_steps": 107, "total_steps": 621, "loss": 0.86, "lr": 9.847364829118963e-06, "epoch": 0.5169082125603864, "percentage": 17.23, "elapsed_time": "1:24:01", "remaining_time": "6:43:38"}
+{"current_steps": 108, "total_steps": 621, "loss": 0.8251, "lr": 9.840385594331022e-06, "epoch": 0.5217391304347826, "percentage": 17.39, "elapsed_time": "1:24:48", "remaining_time": "6:42:51"}
+{"current_steps": 109, "total_steps": 621, "loss": 0.8688, "lr": 9.833252929587231e-06, "epoch": 0.5265700483091788, "percentage": 17.55, "elapsed_time": "1:25:49", "remaining_time": "6:43:06"}
+{"current_steps": 110, "total_steps": 621, "loss": 0.8599, "lr": 9.825967060977933e-06, "epoch": 0.5314009661835749, "percentage": 17.71, "elapsed_time": "1:26:38", "remaining_time": "6:42:30"}
+{"current_steps": 111, "total_steps": 621, "loss": 0.8659, "lr": 9.818528219449705e-06, "epoch": 0.5362318840579711, "percentage": 17.87, "elapsed_time": "1:27:27", "remaining_time": "6:41:51"}
+{"current_steps": 112, "total_steps": 621, "loss": 0.853, "lr": 9.810936640798046e-06, "epoch": 0.5410628019323671, "percentage": 18.04, "elapsed_time": "1:28:12", "remaining_time": "6:40:50"}
+{"current_steps": 113, "total_steps": 621, "loss": 0.8404, "lr": 9.803192565659898e-06, "epoch": 0.5458937198067633, "percentage": 18.2, "elapsed_time": "1:28:56", "remaining_time": "6:39:48"}
+{"current_steps": 114, "total_steps": 621, "loss": 0.8722, "lr": 9.795296239506011e-06, "epoch": 0.5507246376811594, "percentage": 18.36, "elapsed_time": "1:29:46", "remaining_time": "6:39:15"}
+{"current_steps": 115, "total_steps": 621, "loss": 0.8656, "lr": 9.78724791263318e-06, "epoch": 0.5555555555555556, "percentage": 18.52, "elapsed_time": "1:30:30", "remaining_time": "6:38:14"}
+{"current_steps": 116, "total_steps": 621, "loss": 0.8821, "lr": 9.779047840156288e-06, "epoch": 0.5603864734299517, "percentage": 18.68, "elapsed_time": "1:31:29", "remaining_time": "6:38:20"}
+{"current_steps": 117, "total_steps": 621, "loss": 0.8461, "lr": 9.770696282000245e-06, "epoch": 0.5652173913043478, "percentage": 18.84, "elapsed_time": "1:32:19", "remaining_time": "6:37:42"}
+{"current_steps": 118, "total_steps": 621, "loss": 0.8723, "lr": 9.762193502891726e-06, "epoch": 0.5700483091787439, "percentage": 19.0, "elapsed_time": "1:32:57", "remaining_time": "6:36:13"}
+{"current_steps": 119, "total_steps": 621, "loss": 0.8751, "lr": 9.753539772350792e-06, "epoch": 0.5748792270531401, "percentage": 19.16, "elapsed_time": "1:33:43", "remaining_time": "6:35:21"}
+{"current_steps": 120, "total_steps": 621, "loss": 0.8829, "lr": 9.744735364682347e-06, "epoch": 0.5797101449275363, "percentage": 19.32, "elapsed_time": "1:34:35", "remaining_time": "6:34:54"}
+{"current_steps": 121, "total_steps": 621, "loss": 0.8725, "lr": 9.735780558967434e-06, "epoch": 0.5845410628019324, "percentage": 19.48, "elapsed_time": "1:35:23", "remaining_time": "6:34:09"}
+{"current_steps": 122, "total_steps": 621, "loss": 0.8398, "lr": 9.726675639054403e-06, "epoch": 0.5893719806763285, "percentage": 19.65, "elapsed_time": "1:36:14", "remaining_time": "6:33:39"}
+{"current_steps": 123, "total_steps": 621, "loss": 0.8523, "lr": 9.717420893549902e-06, "epoch": 0.5942028985507246, "percentage": 19.81, "elapsed_time": "1:37:11", "remaining_time": "6:33:28"}
+{"current_steps": 124, "total_steps": 621, "loss": 0.8584, "lr": 9.70801661580973e-06, "epoch": 0.5990338164251208, "percentage": 19.97, "elapsed_time": "1:38:00", "remaining_time": "6:32:47"}
+{"current_steps": 125, "total_steps": 621, "loss": 0.8821, "lr": 9.698463103929542e-06, "epoch": 0.6038647342995169, "percentage": 20.13, "elapsed_time": "1:38:36", "remaining_time": "6:31:17"}
+{"current_steps": 126, "total_steps": 621, "loss": 0.8791, "lr": 9.688760660735403e-06, "epoch": 0.6086956521739131, "percentage": 20.29, "elapsed_time": "1:39:25", "remaining_time": "6:30:36"}
+{"current_steps": 127, "total_steps": 621, "loss": 0.8738, "lr": 9.67890959377418e-06, "epoch": 0.6135265700483091, "percentage": 20.45, "elapsed_time": "1:40:16", "remaining_time": "6:30:04"}
+{"current_steps": 128, "total_steps": 621, "loss": 0.8889, "lr": 9.668910215303797e-06, "epoch": 0.6183574879227053, "percentage": 20.61, "elapsed_time": "1:41:00", "remaining_time": "6:29:02"}
+{"current_steps": 129, "total_steps": 621, "loss": 0.8625, "lr": 9.658762842283343e-06, "epoch": 0.6231884057971014, "percentage": 20.77, "elapsed_time": "1:41:48", "remaining_time": "6:28:18"}
+{"current_steps": 130, "total_steps": 621, "loss": 0.8458, "lr": 9.648467796363019e-06, "epoch": 0.6280193236714976, "percentage": 20.93, "elapsed_time": "1:42:42", "remaining_time": "6:27:54"}
+{"current_steps": 131, "total_steps": 621, "loss": 0.8241, "lr": 9.638025403873939e-06, "epoch": 0.6328502415458938, "percentage": 21.1, "elapsed_time": "1:43:26", "remaining_time": "6:26:53"}
+{"current_steps": 132, "total_steps": 621, "loss": 0.8459, "lr": 9.627435995817799e-06, "epoch": 0.6376811594202898, "percentage": 21.26, "elapsed_time": "1:44:10", "remaining_time": "6:25:54"}
+{"current_steps": 133, "total_steps": 621, "loss": 0.881, "lr": 9.616699907856368e-06, "epoch": 0.642512077294686, "percentage": 21.42, "elapsed_time": "1:45:11", "remaining_time": "6:25:57"}
+{"current_steps": 134, "total_steps": 621, "loss": 0.822, "lr": 9.605817480300863e-06, "epoch": 0.6473429951690821, "percentage": 21.58, "elapsed_time": "1:45:54", "remaining_time": "6:24:53"}
+{"current_steps": 135, "total_steps": 621, "loss": 0.8841, "lr": 9.594789058101154e-06, "epoch": 0.6521739130434783, "percentage": 21.74, "elapsed_time": "1:46:53", "remaining_time": "6:24:47"}
+{"current_steps": 136, "total_steps": 621, "loss": 0.8266, "lr": 9.58361499083483e-06, "epoch": 0.6570048309178744, "percentage": 21.9, "elapsed_time": "1:47:37", "remaining_time": "6:23:49"}
+{"current_steps": 137, "total_steps": 621, "loss": 0.8691, "lr": 9.57229563269612e-06, "epoch": 0.6618357487922706, "percentage": 22.06, "elapsed_time": "1:48:33", "remaining_time": "6:23:32"}
+{"current_steps": 138, "total_steps": 621, "loss": 0.8842, "lr": 9.560831342484668e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "1:49:38", "remaining_time": "6:23:44"}
+{"current_steps": 139, "total_steps": 621, "loss": 0.82, "lr": 9.549222483594154e-06, "epoch": 0.6714975845410628, "percentage": 22.38, "elapsed_time": "1:50:17", "remaining_time": "6:22:25"}
+{"current_steps": 140, "total_steps": 621, "loss": 0.8919, "lr": 9.53746942400078e-06, "epoch": 0.6763285024154589, "percentage": 22.54, "elapsed_time": "1:51:17", "remaining_time": "6:22:21"}
+{"current_steps": 141, "total_steps": 621, "loss": 0.8453, "lr": 9.525572536251608e-06, "epoch": 0.6811594202898551, "percentage": 22.71, "elapsed_time": "1:52:06", "remaining_time": "6:21:38"}
+{"current_steps": 142, "total_steps": 621, "loss": 0.833, "lr": 9.513532197452737e-06, "epoch": 0.6859903381642513, "percentage": 22.87, "elapsed_time": "1:52:50", "remaining_time": "6:20:37"}
+{"current_steps": 143, "total_steps": 621, "loss": 0.8634, "lr": 9.501348789257373e-06, "epoch": 0.6908212560386473, "percentage": 23.03, "elapsed_time": "1:53:38", "remaining_time": "6:19:50"}
+{"current_steps": 144, "total_steps": 621, "loss": 0.8844, "lr": 9.48902269785371e-06, "epoch": 0.6956521739130435, "percentage": 23.19, "elapsed_time": "1:54:22", "remaining_time": "6:18:52"}
+{"current_steps": 145, "total_steps": 621, "loss": 0.8543, "lr": 9.476554313952697e-06, "epoch": 0.7004830917874396, "percentage": 23.35, "elapsed_time": "1:55:09", "remaining_time": "6:18:03"}
+{"current_steps": 146, "total_steps": 621, "loss": 0.8325, "lr": 9.46394403277566e-06, "epoch": 0.7053140096618358, "percentage": 23.51, "elapsed_time": "1:55:48", "remaining_time": "6:16:47"}
+{"current_steps": 147, "total_steps": 621, "loss": 0.8591, "lr": 9.451192254041759e-06, "epoch": 0.7101449275362319, "percentage": 23.67, "elapsed_time": "1:56:36", "remaining_time": "6:16:00"}
+{"current_steps": 148, "total_steps": 621, "loss": 0.8646, "lr": 9.438299381955333e-06, "epoch": 0.714975845410628, "percentage": 23.83, "elapsed_time": "1:57:19", "remaining_time": "6:14:56"}
+{"current_steps": 149, "total_steps": 621, "loss": 0.8394, "lr": 9.425265825193077e-06, "epoch": 0.7198067632850241, "percentage": 23.99, "elapsed_time": "1:58:00", "remaining_time": "6:13:50"}
+{"current_steps": 150, "total_steps": 621, "loss": 0.8865, "lr": 9.412091996891097e-06, "epoch": 0.7246376811594203, "percentage": 24.15, "elapsed_time": "1:58:45", "remaining_time": "6:12:54"}
+{"current_steps": 151, "total_steps": 621, "loss": 0.8644, "lr": 9.398778314631801e-06, "epoch": 0.7294685990338164, "percentage": 24.32, "elapsed_time": "1:59:39", "remaining_time": "6:12:27"}
+{"current_steps": 152, "total_steps": 621, "loss": 0.8421, "lr": 9.385325200430679e-06, "epoch": 0.7342995169082126, "percentage": 24.48, "elapsed_time": "2:00:25", "remaining_time": "6:11:33"}
+{"current_steps": 153, "total_steps": 621, "loss": 0.8562, "lr": 9.371733080722911e-06, "epoch": 0.7391304347826086, "percentage": 24.64, "elapsed_time": "2:01:17", "remaining_time": "6:11:02"}
+{"current_steps": 154, "total_steps": 621, "loss": 0.8867, "lr": 9.358002386349862e-06, "epoch": 0.7439613526570048, "percentage": 24.8, "elapsed_time": "2:02:06", "remaining_time": "6:10:16"}
+{"current_steps": 155, "total_steps": 621, "loss": 0.8403, "lr": 9.34413355254542e-06, "epoch": 0.748792270531401, "percentage": 24.96, "elapsed_time": "2:03:05", "remaining_time": "6:10:04"}
+{"current_steps": 156, "total_steps": 621, "loss": 0.8489, "lr": 9.330127018922195e-06, "epoch": 0.7536231884057971, "percentage": 25.12, "elapsed_time": "2:03:53", "remaining_time": "6:09:18"}
+{"current_steps": 157, "total_steps": 621, "loss": 0.8623, "lr": 9.31598322945759e-06, "epoch": 0.7584541062801933, "percentage": 25.28, "elapsed_time": "2:04:44", "remaining_time": "6:08:38"}
+{"current_steps": 158, "total_steps": 621, "loss": 0.8434, "lr": 9.301702632479734e-06, "epoch": 0.7632850241545893, "percentage": 25.44, "elapsed_time": "2:05:37", "remaining_time": "6:08:06"}
+{"current_steps": 159, "total_steps": 621, "loss": 0.8924, "lr": 9.287285680653254e-06, "epoch": 0.7681159420289855, "percentage": 25.6, "elapsed_time": "2:06:21", "remaining_time": "6:07:08"}
+{"current_steps": 160, "total_steps": 621, "loss": 0.8694, "lr": 9.272732830964948e-06, "epoch": 0.7729468599033816, "percentage": 25.76, "elapsed_time": "2:07:20", "remaining_time": "6:06:52"}
+{"current_steps": 161, "total_steps": 621, "loss": 0.8541, "lr": 9.258044544709276e-06, "epoch": 0.7777777777777778, "percentage": 25.93, "elapsed_time": "2:08:07", "remaining_time": "6:06:04"}
+{"current_steps": 162, "total_steps": 621, "loss": 0.8679, "lr": 9.243221287473755e-06, "epoch": 0.782608695652174, "percentage": 26.09, "elapsed_time": "2:08:57", "remaining_time": "6:05:23"}
+{"current_steps": 163, "total_steps": 621, "loss": 0.8318, "lr": 9.228263529124199e-06, "epoch": 0.7874396135265701, "percentage": 26.25, "elapsed_time": "2:09:45", "remaining_time": "6:04:35"}
+{"current_steps": 164, "total_steps": 621, "loss": 0.8526, "lr": 9.21317174378982e-06, "epoch": 0.7922705314009661, "percentage": 26.41, "elapsed_time": "2:10:31", "remaining_time": "6:03:44"}
+{"current_steps": 165, "total_steps": 621, "loss": 0.8707, "lr": 9.197946409848196e-06, "epoch": 0.7971014492753623, "percentage": 26.57, "elapsed_time": "2:11:24", "remaining_time": "6:03:08"}
+{"current_steps": 166, "total_steps": 621, "loss": 0.8601, "lr": 9.182588009910119e-06, "epoch": 0.8019323671497585, "percentage": 26.73, "elapsed_time": "2:12:08", "remaining_time": "6:02:11"}
+{"current_steps": 167, "total_steps": 621, "loss": 0.8398, "lr": 9.167097030804289e-06, "epoch": 0.8067632850241546, "percentage": 26.89, "elapsed_time": "2:12:55", "remaining_time": "6:01:21"}
+{"current_steps": 168, "total_steps": 621, "loss": 0.7931, "lr": 9.151473963561884e-06, "epoch": 0.8115942028985508, "percentage": 27.05, "elapsed_time": "2:13:38", "remaining_time": "6:00:21"}
+{"current_steps": 169, "total_steps": 621, "loss": 0.8542, "lr": 9.135719303400995e-06, "epoch": 0.8164251207729468, "percentage": 27.21, "elapsed_time": "2:14:19", "remaining_time": "5:59:16"}
+{"current_steps": 170, "total_steps": 621, "loss": 0.8251, "lr": 9.119833549710927e-06, "epoch": 0.821256038647343, "percentage": 27.38, "elapsed_time": "2:15:11", "remaining_time": "5:58:39"}
+{"current_steps": 171, "total_steps": 621, "loss": 0.8496, "lr": 9.103817206036383e-06, "epoch": 0.8260869565217391, "percentage": 27.54, "elapsed_time": "2:16:00", "remaining_time": "5:57:53"}
+{"current_steps": 172, "total_steps": 621, "loss": 0.8558, "lr": 9.087670780061477e-06, "epoch": 0.8309178743961353, "percentage": 27.7, "elapsed_time": "2:16:49", "remaining_time": "5:57:10"}
+{"current_steps": 173, "total_steps": 621, "loss": 0.8295, "lr": 9.071394783593664e-06, "epoch": 0.8357487922705314, "percentage": 27.86, "elapsed_time": "2:17:32", "remaining_time": "5:56:11"}
+{"current_steps": 174, "total_steps": 621, "loss": 0.859, "lr": 9.054989732547507e-06, "epoch": 0.8405797101449275, "percentage": 28.02, "elapsed_time": "2:18:21", "remaining_time": "5:55:26"}
+{"current_steps": 175, "total_steps": 621, "loss": 0.8654, "lr": 9.038456146928325e-06, "epoch": 0.8454106280193237, "percentage": 28.18, "elapsed_time": "2:19:10", "remaining_time": "5:54:41"}
+{"current_steps": 176, "total_steps": 621, "loss": 0.8752, "lr": 9.021794550815713e-06, "epoch": 0.8502415458937198, "percentage": 28.34, "elapsed_time": "2:20:07", "remaining_time": "5:54:18"}
+{"current_steps": 177, "total_steps": 621, "loss": 0.8326, "lr": 9.005005472346923e-06, "epoch": 0.855072463768116, "percentage": 28.5, "elapsed_time": "2:20:48", "remaining_time": "5:53:12"}
+{"current_steps": 178, "total_steps": 621, "loss": 0.8185, "lr": 8.988089443700131e-06, "epoch": 0.8599033816425121, "percentage": 28.66, "elapsed_time": "2:21:29", "remaining_time": "5:52:09"}
+{"current_steps": 179, "total_steps": 621, "loss": 0.8957, "lr": 8.971047001077561e-06, "epoch": 0.8647342995169082, "percentage": 28.82, "elapsed_time": "2:22:19", "remaining_time": "5:51:25"}
+{"current_steps": 180, "total_steps": 621, "loss": 0.8769, "lr": 8.953878684688492e-06, "epoch": 0.8695652173913043, "percentage": 28.99, "elapsed_time": "2:23:06", "remaining_time": "5:50:37"}
+{"current_steps": 181, "total_steps": 621, "loss": 0.863, "lr": 8.936585038732143e-06, "epoch": 0.8743961352657005, "percentage": 29.15, "elapsed_time": "2:23:58", "remaining_time": "5:50:00"}
+{"current_steps": 182, "total_steps": 621, "loss": 0.8449, "lr": 8.919166611380397e-06, "epoch": 0.8792270531400966, "percentage": 29.31, "elapsed_time": "2:24:51", "remaining_time": "5:49:24"}
+{"current_steps": 183, "total_steps": 621, "loss": 0.8473, "lr": 8.90162395476046e-06, "epoch": 0.8840579710144928, "percentage": 29.47, "elapsed_time": "2:25:35", "remaining_time": "5:48:28"}
+{"current_steps": 184, "total_steps": 621, "loss": 0.839, "lr": 8.883957624937333e-06, "epoch": 0.8888888888888888, "percentage": 29.63, "elapsed_time": "2:26:28", "remaining_time": "5:47:52"}
+{"current_steps": 185, "total_steps": 621, "loss": 0.876, "lr": 8.866168181896198e-06, "epoch": 0.893719806763285, "percentage": 29.79, "elapsed_time": "2:27:25", "remaining_time": "5:47:27"}
+{"current_steps": 186, "total_steps": 621, "loss": 0.8496, "lr": 8.848256189524661e-06, "epoch": 0.8985507246376812, "percentage": 29.95, "elapsed_time": "2:28:19", "remaining_time": "5:46:54"}
+{"current_steps": 187, "total_steps": 621, "loss": 0.8522, "lr": 8.83022221559489e-06, "epoch": 0.9033816425120773, "percentage": 30.11, "elapsed_time": "2:28:58", "remaining_time": "5:45:45"}
+{"current_steps": 188, "total_steps": 621, "loss": 0.8649, "lr": 8.812066831745602e-06, "epoch": 0.9082125603864735, "percentage": 30.27, "elapsed_time": "2:29:50", "remaining_time": "5:45:06"}
+{"current_steps": 189, "total_steps": 621, "loss": 0.8464, "lr": 8.793790613463956e-06, "epoch": 0.9130434782608695, "percentage": 30.43, "elapsed_time": "2:30:39", "remaining_time": "5:44:21"}
+{"current_steps": 190, "total_steps": 621, "loss": 0.8051, "lr": 8.775394140067299e-06, "epoch": 0.9178743961352657, "percentage": 30.6, "elapsed_time": "2:31:19", "remaining_time": "5:43:17"}
+{"current_steps": 191, "total_steps": 621, "loss": 0.8543, "lr": 8.756877994684818e-06, "epoch": 0.9227053140096618, "percentage": 30.76, "elapsed_time": "2:32:04", "remaining_time": "5:42:22"}
+{"current_steps": 192, "total_steps": 621, "loss": 0.8202, "lr": 8.738242764239046e-06, "epoch": 0.927536231884058, "percentage": 30.92, "elapsed_time": "2:32:48", "remaining_time": "5:41:26"}
+{"current_steps": 193, "total_steps": 621, "loss": 0.8058, "lr": 8.719489039427256e-06, "epoch": 0.9323671497584541, "percentage": 31.08, "elapsed_time": "2:33:36", "remaining_time": "5:40:39"}
+{"current_steps": 194, "total_steps": 621, "loss": 0.8518, "lr": 8.700617414702746e-06, "epoch": 0.9371980676328503, "percentage": 31.24, "elapsed_time": "2:34:27", "remaining_time": "5:39:58"}
+{"current_steps": 195, "total_steps": 621, "loss": 0.8444, "lr": 8.681628488255986e-06, "epoch": 0.9420289855072463, "percentage": 31.4, "elapsed_time": "2:35:08", "remaining_time": "5:38:56"}
+{"current_steps": 196, "total_steps": 621, "loss": 0.8505, "lr": 8.66252286199567e-06, "epoch": 0.9468599033816425, "percentage": 31.56, "elapsed_time": "2:35:59", "remaining_time": "5:38:14"}
+{"current_steps": 197, "total_steps": 621, "loss": 0.8238, "lr": 8.643301141529619e-06, "epoch": 0.9516908212560387, "percentage": 31.72, "elapsed_time": "2:36:41", "remaining_time": "5:37:13"}
+{"current_steps": 198, "total_steps": 621, "loss": 0.8455, "lr": 8.6239639361456e-06, "epoch": 0.9565217391304348, "percentage": 31.88, "elapsed_time": "2:37:26", "remaining_time": "5:36:21"}
+{"current_steps": 199, "total_steps": 621, "loss": 0.8275, "lr": 8.604511858792006e-06, "epoch": 0.961352657004831, "percentage": 32.05, "elapsed_time": "2:38:08", "remaining_time": "5:35:20"}
+{"current_steps": 200, "total_steps": 621, "loss": 0.8218, "lr": 8.584945526058426e-06, "epoch": 0.966183574879227, "percentage": 32.21, "elapsed_time": "2:38:42", "remaining_time": "5:34:04"}
+{"current_steps": 201, "total_steps": 621, "loss": 0.8291, "lr": 8.565265558156101e-06, "epoch": 0.9710144927536232, "percentage": 32.37, "elapsed_time": "2:39:26", "remaining_time": "5:33:09"}
+{"current_steps": 202, "total_steps": 621, "loss": 0.87, "lr": 8.545472578898276e-06, "epoch": 0.9758454106280193, "percentage": 32.53, "elapsed_time": "2:40:14", "remaining_time": "5:32:23"}
+{"current_steps": 203, "total_steps": 621, "loss": 0.8411, "lr": 8.525567215680397e-06, "epoch": 0.9806763285024155, "percentage": 32.69, "elapsed_time": "2:41:04", "remaining_time": "5:31:40"}
+{"current_steps": 204, "total_steps": 621, "loss": 0.806, "lr": 8.505550099460264e-06, "epoch": 0.9855072463768116, "percentage": 32.85, "elapsed_time": "2:41:45", "remaining_time": "5:30:39"}
+{"current_steps": 205, "total_steps": 621, "loss": 0.8181, "lr": 8.485421864737997e-06, "epoch": 0.9903381642512077, "percentage": 33.01, "elapsed_time": "2:42:36", "remaining_time": "5:29:58"}
+{"current_steps": 206, "total_steps": 621, "loss": 0.8617, "lr": 8.465183149535939e-06, "epoch": 0.9951690821256038, "percentage": 33.17, "elapsed_time": "2:43:22", "remaining_time": "5:29:08"}
+{"current_steps": 207, "total_steps": 621, "loss": 0.8778, "lr": 8.444834595378434e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "2:44:15", "remaining_time": "5:28:31"}
+{"current_steps": 208, "total_steps": 621, "loss": 0.7686, "lr": 8.424376847271483e-06, "epoch": 1.0048309178743962, "percentage": 33.49, "elapsed_time": "2:45:59", "remaining_time": "5:29:35"}
+{"current_steps": 209, "total_steps": 621, "loss": 0.7638, "lr": 8.403810553682307e-06, "epoch": 1.0096618357487923, "percentage": 33.66, "elapsed_time": "2:46:46", "remaining_time": "5:28:46"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e27599ef31559ed210adb4cb7ec010aa1e6606526b7db559d1428665ee6e59
+size 7416