Training in progress, epoch 0

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a8f3663e44b4235897265801544fac50ff60c14aafb702f4e6227ebce39665
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e920cc2a681bb8ae05b8e0dd2cb7337fb4510ae2261b14d5ef7a8f7dfe5761
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d3cb0f22b2bfd2a31a894a5d3e30b2723826d2c4e347ca454fe49ecabdbaaf
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:450c249f9c7baf52e8985f65174e0859b799e39ba74ce4be020f2df4cf13d4b1
+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 +1,185 @@
+{"current_steps": 1, "total_steps": 522, "loss": 0.8872, "lr": 3.773584905660378e-07, "epoch": 0.0057361376673040155, "percentage": 0.19, "elapsed_time": "0:00:28", "remaining_time": "4:11:11"}
+{"current_steps": 2, "total_steps": 522, "loss": 0.9165, "lr": 7.547169811320755e-07, "epoch": 0.011472275334608031, "percentage": 0.38, "elapsed_time": "0:00:44", "remaining_time": "3:14:53"}
+{"current_steps": 3, "total_steps": 522, "loss": 0.9418, "lr": 1.1320754716981133e-06, "epoch": 0.017208413001912046, "percentage": 0.57, "elapsed_time": "0:00:58", "remaining_time": "2:49:15"}
+{"current_steps": 4, "total_steps": 522, "loss": 0.9044, "lr": 1.509433962264151e-06, "epoch": 0.022944550669216062, "percentage": 0.77, "elapsed_time": "0:01:12", "remaining_time": "2:36:38"}
+{"current_steps": 5, "total_steps": 522, "loss": 0.8938, "lr": 1.8867924528301889e-06, "epoch": 0.028680688336520075, "percentage": 0.96, "elapsed_time": "0:01:27", "remaining_time": "2:30:26"}
+{"current_steps": 6, "total_steps": 522, "loss": 0.8815, "lr": 2.2641509433962266e-06, "epoch": 0.03441682600382409, "percentage": 1.15, "elapsed_time": "0:01:40", "remaining_time": "2:23:34"}
+{"current_steps": 7, "total_steps": 522, "loss": 0.8718, "lr": 2.6415094339622644e-06, "epoch": 0.040152963671128104, "percentage": 1.34, "elapsed_time": "0:01:56", "remaining_time": "2:22:27"}
+{"current_steps": 8, "total_steps": 522, "loss": 0.8163, "lr": 3.018867924528302e-06, "epoch": 0.045889101338432124, "percentage": 1.53, "elapsed_time": "0:02:10", "remaining_time": "2:19:33"}
+{"current_steps": 9, "total_steps": 522, "loss": 0.7805, "lr": 3.3962264150943395e-06, "epoch": 0.05162523900573614, "percentage": 1.72, "elapsed_time": "0:02:26", "remaining_time": "2:19:19"}
+{"current_steps": 10, "total_steps": 522, "loss": 0.8185, "lr": 3.7735849056603777e-06, "epoch": 0.05736137667304015, "percentage": 1.92, "elapsed_time": "0:02:42", "remaining_time": "2:18:24"}
+{"current_steps": 11, "total_steps": 522, "loss": 0.7837, "lr": 4.150943396226416e-06, "epoch": 0.06309751434034416, "percentage": 2.11, "elapsed_time": "0:02:57", "remaining_time": "2:17:36"}
+{"current_steps": 12, "total_steps": 522, "loss": 0.733, "lr": 4.528301886792453e-06, "epoch": 0.06883365200764818, "percentage": 2.3, "elapsed_time": "0:03:16", "remaining_time": "2:18:59"}
+{"current_steps": 13, "total_steps": 522, "loss": 0.7995, "lr": 4.905660377358491e-06, "epoch": 0.0745697896749522, "percentage": 2.49, "elapsed_time": "0:03:32", "remaining_time": "2:18:36"}
+{"current_steps": 14, "total_steps": 522, "loss": 0.7584, "lr": 5.283018867924529e-06, "epoch": 0.08030592734225621, "percentage": 2.68, "elapsed_time": "0:03:46", "remaining_time": "2:16:43"}
+{"current_steps": 15, "total_steps": 522, "loss": 0.7447, "lr": 5.660377358490566e-06, "epoch": 0.08604206500956023, "percentage": 2.87, "elapsed_time": "0:04:01", "remaining_time": "2:15:58"}
+{"current_steps": 16, "total_steps": 522, "loss": 0.74, "lr": 6.037735849056604e-06, "epoch": 0.09177820267686425, "percentage": 3.07, "elapsed_time": "0:04:17", "remaining_time": "2:15:41"}
+{"current_steps": 17, "total_steps": 522, "loss": 0.7052, "lr": 6.415094339622642e-06, "epoch": 0.09751434034416825, "percentage": 3.26, "elapsed_time": "0:04:32", "remaining_time": "2:14:41"}
+{"current_steps": 18, "total_steps": 522, "loss": 0.7006, "lr": 6.792452830188679e-06, "epoch": 0.10325047801147227, "percentage": 3.45, "elapsed_time": "0:04:48", "remaining_time": "2:14:37"}
+{"current_steps": 19, "total_steps": 522, "loss": 0.6299, "lr": 7.169811320754717e-06, "epoch": 0.1089866156787763, "percentage": 3.64, "elapsed_time": "0:05:05", "remaining_time": "2:14:36"}
+{"current_steps": 20, "total_steps": 522, "loss": 0.6694, "lr": 7.5471698113207555e-06, "epoch": 0.1147227533460803, "percentage": 3.83, "elapsed_time": "0:05:22", "remaining_time": "2:14:56"}
+{"current_steps": 21, "total_steps": 522, "loss": 0.6481, "lr": 7.924528301886793e-06, "epoch": 0.12045889101338432, "percentage": 4.02, "elapsed_time": "0:05:40", "remaining_time": "2:15:16"}
+{"current_steps": 22, "total_steps": 522, "loss": 0.643, "lr": 8.301886792452832e-06, "epoch": 0.12619502868068833, "percentage": 4.21, "elapsed_time": "0:05:49", "remaining_time": "2:12:31"}
+{"current_steps": 23, "total_steps": 522, "loss": 0.6076, "lr": 8.67924528301887e-06, "epoch": 0.13193116634799235, "percentage": 4.41, "elapsed_time": "0:06:06", "remaining_time": "2:12:27"}
+{"current_steps": 24, "total_steps": 522, "loss": 0.6383, "lr": 9.056603773584907e-06, "epoch": 0.13766730401529637, "percentage": 4.6, "elapsed_time": "0:06:22", "remaining_time": "2:12:20"}
+{"current_steps": 25, "total_steps": 522, "loss": 0.6244, "lr": 9.433962264150944e-06, "epoch": 0.14340344168260039, "percentage": 4.79, "elapsed_time": "0:06:40", "remaining_time": "2:12:47"}
+{"current_steps": 26, "total_steps": 522, "loss": 0.6012, "lr": 9.811320754716981e-06, "epoch": 0.1491395793499044, "percentage": 4.98, "elapsed_time": "0:06:56", "remaining_time": "2:12:32"}
+{"current_steps": 27, "total_steps": 522, "loss": 0.6421, "lr": 1.018867924528302e-05, "epoch": 0.15487571701720843, "percentage": 5.17, "elapsed_time": "0:07:16", "remaining_time": "2:13:15"}
+{"current_steps": 28, "total_steps": 522, "loss": 0.6205, "lr": 1.0566037735849058e-05, "epoch": 0.16061185468451242, "percentage": 5.36, "elapsed_time": "0:07:31", "remaining_time": "2:12:54"}
+{"current_steps": 29, "total_steps": 522, "loss": 0.6032, "lr": 1.0943396226415095e-05, "epoch": 0.16634799235181644, "percentage": 5.56, "elapsed_time": "0:07:46", "remaining_time": "2:12:05"}
+{"current_steps": 30, "total_steps": 522, "loss": 0.6013, "lr": 1.1320754716981132e-05, "epoch": 0.17208413001912046, "percentage": 5.75, "elapsed_time": "0:08:03", "remaining_time": "2:12:01"}
+{"current_steps": 31, "total_steps": 522, "loss": 0.5721, "lr": 1.169811320754717e-05, "epoch": 0.17782026768642448, "percentage": 5.94, "elapsed_time": "0:08:20", "remaining_time": "2:12:02"}
+{"current_steps": 32, "total_steps": 522, "loss": 0.5571, "lr": 1.2075471698113209e-05, "epoch": 0.1835564053537285, "percentage": 6.13, "elapsed_time": "0:08:33", "remaining_time": "2:11:02"}
+{"current_steps": 33, "total_steps": 522, "loss": 0.5833, "lr": 1.2452830188679246e-05, "epoch": 0.18929254302103252, "percentage": 6.32, "elapsed_time": "0:08:50", "remaining_time": "2:10:59"}
+{"current_steps": 34, "total_steps": 522, "loss": 0.6104, "lr": 1.2830188679245283e-05, "epoch": 0.1950286806883365, "percentage": 6.51, "elapsed_time": "0:09:03", "remaining_time": "2:10:02"}
+{"current_steps": 35, "total_steps": 522, "loss": 0.5837, "lr": 1.320754716981132e-05, "epoch": 0.20076481835564053, "percentage": 6.7, "elapsed_time": "0:09:21", "remaining_time": "2:10:12"}
+{"current_steps": 36, "total_steps": 522, "loss": 0.5722, "lr": 1.3584905660377358e-05, "epoch": 0.20650095602294455, "percentage": 6.9, "elapsed_time": "0:09:40", "remaining_time": "2:10:30"}
+{"current_steps": 37, "total_steps": 522, "loss": 0.5711, "lr": 1.3962264150943397e-05, "epoch": 0.21223709369024857, "percentage": 7.09, "elapsed_time": "0:09:59", "remaining_time": "2:10:53"}
+{"current_steps": 38, "total_steps": 522, "loss": 0.5892, "lr": 1.4339622641509435e-05, "epoch": 0.2179732313575526, "percentage": 7.28, "elapsed_time": "0:10:17", "remaining_time": "2:11:08"}
+{"current_steps": 39, "total_steps": 522, "loss": 0.5924, "lr": 1.4716981132075472e-05, "epoch": 0.2237093690248566, "percentage": 7.47, "elapsed_time": "0:10:34", "remaining_time": "2:10:58"}
+{"current_steps": 40, "total_steps": 522, "loss": 0.5446, "lr": 1.5094339622641511e-05, "epoch": 0.2294455066921606, "percentage": 7.66, "elapsed_time": "0:10:51", "remaining_time": "2:10:49"}
+{"current_steps": 41, "total_steps": 522, "loss": 0.5982, "lr": 1.547169811320755e-05, "epoch": 0.23518164435946462, "percentage": 7.85, "elapsed_time": "0:11:06", "remaining_time": "2:10:22"}
+{"current_steps": 42, "total_steps": 522, "loss": 0.5336, "lr": 1.5849056603773586e-05, "epoch": 0.24091778202676864, "percentage": 8.05, "elapsed_time": "0:11:26", "remaining_time": "2:10:43"}
+{"current_steps": 43, "total_steps": 522, "loss": 0.5879, "lr": 1.6226415094339625e-05, "epoch": 0.24665391969407266, "percentage": 8.24, "elapsed_time": "0:11:44", "remaining_time": "2:10:44"}
+{"current_steps": 44, "total_steps": 522, "loss": 0.5854, "lr": 1.6603773584905664e-05, "epoch": 0.25239005736137665, "percentage": 8.43, "elapsed_time": "0:12:01", "remaining_time": "2:10:34"}
+{"current_steps": 45, "total_steps": 522, "loss": 0.5684, "lr": 1.69811320754717e-05, "epoch": 0.25812619502868067, "percentage": 8.62, "elapsed_time": "0:12:15", "remaining_time": "2:09:58"}
+{"current_steps": 46, "total_steps": 522, "loss": 0.5275, "lr": 1.735849056603774e-05, "epoch": 0.2638623326959847, "percentage": 8.81, "elapsed_time": "0:12:35", "remaining_time": "2:10:16"}
+{"current_steps": 47, "total_steps": 522, "loss": 0.5689, "lr": 1.7735849056603774e-05, "epoch": 0.2695984703632887, "percentage": 9.0, "elapsed_time": "0:12:50", "remaining_time": "2:09:47"}
+{"current_steps": 48, "total_steps": 522, "loss": 0.5544, "lr": 1.8113207547169813e-05, "epoch": 0.27533460803059273, "percentage": 9.2, "elapsed_time": "0:13:07", "remaining_time": "2:09:35"}
+{"current_steps": 49, "total_steps": 522, "loss": 0.5788, "lr": 1.8490566037735852e-05, "epoch": 0.28107074569789675, "percentage": 9.39, "elapsed_time": "0:13:26", "remaining_time": "2:09:42"}
+{"current_steps": 50, "total_steps": 522, "loss": 0.5352, "lr": 1.8867924528301888e-05, "epoch": 0.28680688336520077, "percentage": 9.58, "elapsed_time": "0:13:43", "remaining_time": "2:09:30"}
+{"current_steps": 51, "total_steps": 522, "loss": 0.5248, "lr": 1.9245283018867927e-05, "epoch": 0.2925430210325048, "percentage": 9.77, "elapsed_time": "0:14:01", "remaining_time": "2:09:32"}
+{"current_steps": 52, "total_steps": 522, "loss": 0.5665, "lr": 1.9622641509433963e-05, "epoch": 0.2982791586998088, "percentage": 9.96, "elapsed_time": "0:14:17", "remaining_time": "2:09:14"}
+{"current_steps": 53, "total_steps": 522, "loss": 0.5539, "lr": 2e-05, "epoch": 0.30401529636711283, "percentage": 10.15, "elapsed_time": "0:14:29", "remaining_time": "2:08:14"}
+{"current_steps": 54, "total_steps": 522, "loss": 0.5232, "lr": 1.999977565187699e-05, "epoch": 0.30975143403441685, "percentage": 10.34, "elapsed_time": "0:14:47", "remaining_time": "2:08:10"}
+{"current_steps": 55, "total_steps": 522, "loss": 0.5387, "lr": 1.9999102617574366e-05, "epoch": 0.3154875717017208, "percentage": 10.54, "elapsed_time": "0:15:02", "remaining_time": "2:07:43"}
+{"current_steps": 56, "total_steps": 522, "loss": 0.5461, "lr": 1.9997980927290928e-05, "epoch": 0.32122370936902483, "percentage": 10.73, "elapsed_time": "0:15:18", "remaining_time": "2:07:22"}
+{"current_steps": 57, "total_steps": 522, "loss": 0.5501, "lr": 1.9996410631356496e-05, "epoch": 0.32695984703632885, "percentage": 10.92, "elapsed_time": "0:15:35", "remaining_time": "2:07:14"}
+{"current_steps": 58, "total_steps": 522, "loss": 0.5475, "lr": 1.9994391800229666e-05, "epoch": 0.3326959847036329, "percentage": 11.11, "elapsed_time": "0:15:53", "remaining_time": "2:07:06"}
+{"current_steps": 59, "total_steps": 522, "loss": 0.5341, "lr": 1.999192452449463e-05, "epoch": 0.3384321223709369, "percentage": 11.3, "elapsed_time": "0:16:08", "remaining_time": "2:06:42"}
+{"current_steps": 60, "total_steps": 522, "loss": 0.5215, "lr": 1.9989008914857115e-05, "epoch": 0.3441682600382409, "percentage": 11.49, "elapsed_time": "0:16:24", "remaining_time": "2:06:21"}
+{"current_steps": 61, "total_steps": 522, "loss": 0.5485, "lr": 1.998564510213944e-05, "epoch": 0.34990439770554493, "percentage": 11.69, "elapsed_time": "0:16:44", "remaining_time": "2:06:28"}
+{"current_steps": 62, "total_steps": 522, "loss": 0.5472, "lr": 1.998183323727462e-05, "epoch": 0.35564053537284895, "percentage": 11.88, "elapsed_time": "0:17:01", "remaining_time": "2:06:16"}
+{"current_steps": 63, "total_steps": 522, "loss": 0.5458, "lr": 1.9977573491299597e-05, "epoch": 0.361376673040153, "percentage": 12.07, "elapsed_time": "0:17:18", "remaining_time": "2:06:05"}
+{"current_steps": 64, "total_steps": 522, "loss": 0.5268, "lr": 1.9972866055347572e-05, "epoch": 0.367112810707457, "percentage": 12.26, "elapsed_time": "0:17:36", "remaining_time": "2:06:02"}
+{"current_steps": 65, "total_steps": 522, "loss": 0.5388, "lr": 1.996771114063943e-05, "epoch": 0.372848948374761, "percentage": 12.45, "elapsed_time": "0:17:50", "remaining_time": "2:05:23"}
+{"current_steps": 66, "total_steps": 522, "loss": 0.5431, "lr": 1.9962108978474265e-05, "epoch": 0.37858508604206503, "percentage": 12.64, "elapsed_time": "0:18:04", "remaining_time": "2:04:54"}
+{"current_steps": 67, "total_steps": 522, "loss": 0.5151, "lr": 1.9956059820218982e-05, "epoch": 0.384321223709369, "percentage": 12.84, "elapsed_time": "0:18:17", "remaining_time": "2:04:10"}
+{"current_steps": 68, "total_steps": 522, "loss": 0.5268, "lr": 1.9949563937297045e-05, "epoch": 0.390057361376673, "percentage": 13.03, "elapsed_time": "0:18:33", "remaining_time": "2:03:53"}
+{"current_steps": 69, "total_steps": 522, "loss": 0.5349, "lr": 1.9942621621176283e-05, "epoch": 0.39579349904397704, "percentage": 13.22, "elapsed_time": "0:18:53", "remaining_time": "2:04:01"}
+{"current_steps": 70, "total_steps": 522, "loss": 0.4825, "lr": 1.993523318335581e-05, "epoch": 0.40152963671128106, "percentage": 13.41, "elapsed_time": "0:19:09", "remaining_time": "2:03:43"}
+{"current_steps": 71, "total_steps": 522, "loss": 0.5363, "lr": 1.9927398955352062e-05, "epoch": 0.4072657743785851, "percentage": 13.6, "elapsed_time": "0:19:20", "remaining_time": "2:02:49"}
+{"current_steps": 72, "total_steps": 522, "loss": 0.504, "lr": 1.9919119288683908e-05, "epoch": 0.4130019120458891, "percentage": 13.79, "elapsed_time": "0:19:35", "remaining_time": "2:02:26"}
+{"current_steps": 73, "total_steps": 522, "loss": 0.5364, "lr": 1.991039455485688e-05, "epoch": 0.4187380497131931, "percentage": 13.98, "elapsed_time": "0:19:53", "remaining_time": "2:02:22"}
+{"current_steps": 74, "total_steps": 522, "loss": 0.5331, "lr": 1.990122514534651e-05, "epoch": 0.42447418738049714, "percentage": 14.18, "elapsed_time": "0:20:08", "remaining_time": "2:01:58"}
+{"current_steps": 75, "total_steps": 522, "loss": 0.5496, "lr": 1.9891611471580767e-05, "epoch": 0.43021032504780116, "percentage": 14.37, "elapsed_time": "0:20:26", "remaining_time": "2:01:51"}
+{"current_steps": 76, "total_steps": 522, "loss": 0.5313, "lr": 1.9881553964921574e-05, "epoch": 0.4359464627151052, "percentage": 14.56, "elapsed_time": "0:20:45", "remaining_time": "2:01:51"}
+{"current_steps": 77, "total_steps": 522, "loss": 0.544, "lr": 1.987105307664549e-05, "epoch": 0.4416826003824092, "percentage": 14.75, "elapsed_time": "0:21:05", "remaining_time": "2:01:51"}
+{"current_steps": 78, "total_steps": 522, "loss": 0.5314, "lr": 1.9860109277923417e-05, "epoch": 0.4474187380497132, "percentage": 14.94, "elapsed_time": "0:21:22", "remaining_time": "2:01:42"}
+{"current_steps": 79, "total_steps": 522, "loss": 0.5429, "lr": 1.9848723059799508e-05, "epoch": 0.45315487571701724, "percentage": 15.13, "elapsed_time": "0:21:42", "remaining_time": "2:01:45"}
+{"current_steps": 80, "total_steps": 522, "loss": 0.5223, "lr": 1.983689493316909e-05, "epoch": 0.4588910133843212, "percentage": 15.33, "elapsed_time": "0:22:02", "remaining_time": "2:01:45"}
+{"current_steps": 81, "total_steps": 522, "loss": 0.5277, "lr": 1.982462542875576e-05, "epoch": 0.4646271510516252, "percentage": 15.52, "elapsed_time": "0:22:17", "remaining_time": "2:01:23"}
+{"current_steps": 82, "total_steps": 522, "loss": 0.5496, "lr": 1.9811915097087587e-05, "epoch": 0.47036328871892924, "percentage": 15.71, "elapsed_time": "0:22:35", "remaining_time": "2:01:15"}
+{"current_steps": 83, "total_steps": 522, "loss": 0.5234, "lr": 1.9798764508472373e-05, "epoch": 0.47609942638623326, "percentage": 15.9, "elapsed_time": "0:22:51", "remaining_time": "2:00:52"}
+{"current_steps": 84, "total_steps": 522, "loss": 0.5361, "lr": 1.9785174252972092e-05, "epoch": 0.4818355640535373, "percentage": 16.09, "elapsed_time": "0:23:04", "remaining_time": "2:00:20"}
+{"current_steps": 85, "total_steps": 522, "loss": 0.5214, "lr": 1.9771144940376413e-05, "epoch": 0.4875717017208413, "percentage": 16.28, "elapsed_time": "0:23:21", "remaining_time": "2:00:05"}
+{"current_steps": 86, "total_steps": 522, "loss": 0.5261, "lr": 1.9756677200175316e-05, "epoch": 0.4933078393881453, "percentage": 16.48, "elapsed_time": "0:23:38", "remaining_time": "1:59:50"}
+{"current_steps": 87, "total_steps": 522, "loss": 0.5485, "lr": 1.974177168153088e-05, "epoch": 0.49904397705544934, "percentage": 16.67, "elapsed_time": "0:23:54", "remaining_time": "1:59:34"}
+{"current_steps": 88, "total_steps": 522, "loss": 0.5281, "lr": 1.972642905324813e-05, "epoch": 0.5047801147227533, "percentage": 16.86, "elapsed_time": "0:24:13", "remaining_time": "1:59:30"}
+{"current_steps": 89, "total_steps": 522, "loss": 0.5372, "lr": 1.971065000374504e-05, "epoch": 0.5105162523900574, "percentage": 17.05, "elapsed_time": "0:24:30", "remaining_time": "1:59:12"}
+{"current_steps": 90, "total_steps": 522, "loss": 0.5429, "lr": 1.969443524102163e-05, "epoch": 0.5162523900573613, "percentage": 17.24, "elapsed_time": "0:24:45", "remaining_time": "1:58:52"}
+{"current_steps": 91, "total_steps": 522, "loss": 0.497, "lr": 1.967778549262822e-05, "epoch": 0.5219885277246654, "percentage": 17.43, "elapsed_time": "0:25:02", "remaining_time": "1:58:35"}
+{"current_steps": 92, "total_steps": 522, "loss": 0.514, "lr": 1.9660701505632773e-05, "epoch": 0.5277246653919694, "percentage": 17.62, "elapsed_time": "0:25:20", "remaining_time": "1:58:28"}
+{"current_steps": 93, "total_steps": 522, "loss": 0.5239, "lr": 1.9643184046587373e-05, "epoch": 0.5334608030592735, "percentage": 17.82, "elapsed_time": "0:25:37", "remaining_time": "1:58:10"}
+{"current_steps": 94, "total_steps": 522, "loss": 0.5207, "lr": 1.962523390149382e-05, "epoch": 0.5391969407265774, "percentage": 18.01, "elapsed_time": "0:25:51", "remaining_time": "1:57:42"}
+{"current_steps": 95, "total_steps": 522, "loss": 0.5331, "lr": 1.9606851875768404e-05, "epoch": 0.5449330783938815, "percentage": 18.2, "elapsed_time": "0:26:08", "remaining_time": "1:57:30"}
+{"current_steps": 96, "total_steps": 522, "loss": 0.5323, "lr": 1.9588038794205705e-05, "epoch": 0.5506692160611855, "percentage": 18.39, "elapsed_time": "0:26:23", "remaining_time": "1:57:06"}
+{"current_steps": 97, "total_steps": 522, "loss": 0.5023, "lr": 1.9568795500941635e-05, "epoch": 0.5564053537284895, "percentage": 18.58, "elapsed_time": "0:26:38", "remaining_time": "1:56:44"}
+{"current_steps": 98, "total_steps": 522, "loss": 0.5576, "lr": 1.9549122859415538e-05, "epoch": 0.5621414913957935, "percentage": 18.77, "elapsed_time": "0:26:55", "remaining_time": "1:56:29"}
+{"current_steps": 99, "total_steps": 522, "loss": 0.5186, "lr": 1.9529021752331455e-05, "epoch": 0.5678776290630975, "percentage": 18.97, "elapsed_time": "0:27:07", "remaining_time": "1:55:55"}
+{"current_steps": 100, "total_steps": 522, "loss": 0.5105, "lr": 1.9508493081618515e-05, "epoch": 0.5736137667304015, "percentage": 19.16, "elapsed_time": "0:27:20", "remaining_time": "1:55:23"}
+{"current_steps": 101, "total_steps": 522, "loss": 0.5406, "lr": 1.9487537768390465e-05, "epoch": 0.5793499043977055, "percentage": 19.35, "elapsed_time": "0:27:38", "remaining_time": "1:55:11"}
+{"current_steps": 102, "total_steps": 522, "loss": 0.5351, "lr": 1.9466156752904344e-05, "epoch": 0.5850860420650096, "percentage": 19.54, "elapsed_time": "0:27:55", "remaining_time": "1:55:00"}
+{"current_steps": 103, "total_steps": 522, "loss": 0.5266, "lr": 1.944435099451829e-05, "epoch": 0.5908221797323135, "percentage": 19.73, "elapsed_time": "0:28:09", "remaining_time": "1:54:32"}
+{"current_steps": 104, "total_steps": 522, "loss": 0.5181, "lr": 1.94221214716485e-05, "epoch": 0.5965583173996176, "percentage": 19.92, "elapsed_time": "0:28:27", "remaining_time": "1:54:24"}
+{"current_steps": 105, "total_steps": 522, "loss": 0.5114, "lr": 1.939946918172531e-05, "epoch": 0.6022944550669216, "percentage": 20.11, "elapsed_time": "0:28:39", "remaining_time": "1:53:50"}
+{"current_steps": 106, "total_steps": 522, "loss": 0.538, "lr": 1.9376395141148475e-05, "epoch": 0.6080305927342257, "percentage": 20.31, "elapsed_time": "0:28:54", "remaining_time": "1:53:26"}
+{"current_steps": 107, "total_steps": 522, "loss": 0.5237, "lr": 1.9352900385241534e-05, "epoch": 0.6137667304015296, "percentage": 20.5, "elapsed_time": "0:29:10", "remaining_time": "1:53:08"}
+{"current_steps": 108, "total_steps": 522, "loss": 0.5315, "lr": 1.932898596820536e-05, "epoch": 0.6195028680688337, "percentage": 20.69, "elapsed_time": "0:29:26", "remaining_time": "1:52:53"}
+{"current_steps": 109, "total_steps": 522, "loss": 0.4925, "lr": 1.9304652963070868e-05, "epoch": 0.6252390057361377, "percentage": 20.88, "elapsed_time": "0:29:42", "remaining_time": "1:52:32"}
+{"current_steps": 110, "total_steps": 522, "loss": 0.5355, "lr": 1.9279902461650866e-05, "epoch": 0.6309751434034416, "percentage": 21.07, "elapsed_time": "0:29:58", "remaining_time": "1:52:15"}
+{"current_steps": 111, "total_steps": 522, "loss": 0.5368, "lr": 1.925473557449106e-05, "epoch": 0.6367112810707457, "percentage": 21.26, "elapsed_time": "0:30:12", "remaining_time": "1:51:50"}
+{"current_steps": 112, "total_steps": 522, "loss": 0.5431, "lr": 1.9229153430820232e-05, "epoch": 0.6424474187380497, "percentage": 21.46, "elapsed_time": "0:30:26", "remaining_time": "1:51:26"}
+{"current_steps": 113, "total_steps": 522, "loss": 0.5043, "lr": 1.920315717849956e-05, "epoch": 0.6481835564053537, "percentage": 21.65, "elapsed_time": "0:30:38", "remaining_time": "1:50:54"}
+{"current_steps": 114, "total_steps": 522, "loss": 0.5187, "lr": 1.917674798397113e-05, "epoch": 0.6539196940726577, "percentage": 21.84, "elapsed_time": "0:30:54", "remaining_time": "1:50:35"}
+{"current_steps": 115, "total_steps": 522, "loss": 0.5333, "lr": 1.914992703220559e-05, "epoch": 0.6596558317399618, "percentage": 22.03, "elapsed_time": "0:31:08", "remaining_time": "1:50:14"}
+{"current_steps": 116, "total_steps": 522, "loss": 0.4942, "lr": 1.9122695526648968e-05, "epoch": 0.6653919694072657, "percentage": 22.22, "elapsed_time": "0:31:24", "remaining_time": "1:49:55"}
+{"current_steps": 117, "total_steps": 522, "loss": 0.5195, "lr": 1.9095054689168707e-05, "epoch": 0.6711281070745698, "percentage": 22.41, "elapsed_time": "0:31:39", "remaining_time": "1:49:35"}
+{"current_steps": 118, "total_steps": 522, "loss": 0.5423, "lr": 1.9067005759998797e-05, "epoch": 0.6768642447418738, "percentage": 22.61, "elapsed_time": "0:31:59", "remaining_time": "1:49:33"}
+{"current_steps": 119, "total_steps": 522, "loss": 0.5347, "lr": 1.903854999768417e-05, "epoch": 0.6826003824091779, "percentage": 22.8, "elapsed_time": "0:32:17", "remaining_time": "1:49:22"}
+{"current_steps": 120, "total_steps": 522, "loss": 0.5044, "lr": 1.900968867902419e-05, "epoch": 0.6883365200764818, "percentage": 22.99, "elapsed_time": "0:32:33", "remaining_time": "1:49:05"}
+{"current_steps": 121, "total_steps": 522, "loss": 0.5411, "lr": 1.8980423099015402e-05, "epoch": 0.6940726577437859, "percentage": 23.18, "elapsed_time": "0:32:52", "remaining_time": "1:48:57"}
+{"current_steps": 122, "total_steps": 522, "loss": 0.4981, "lr": 1.8950754570793384e-05, "epoch": 0.6998087954110899, "percentage": 23.37, "elapsed_time": "0:33:05", "remaining_time": "1:48:30"}
+{"current_steps": 123, "total_steps": 522, "loss": 0.5067, "lr": 1.8920684425573865e-05, "epoch": 0.7055449330783938, "percentage": 23.56, "elapsed_time": "0:33:21", "remaining_time": "1:48:12"}
+{"current_steps": 124, "total_steps": 522, "loss": 0.5475, "lr": 1.8890214012592977e-05, "epoch": 0.7112810707456979, "percentage": 23.75, "elapsed_time": "0:33:37", "remaining_time": "1:47:55"}
+{"current_steps": 125, "total_steps": 522, "loss": 0.5377, "lr": 1.88593446990467e-05, "epoch": 0.7170172084130019, "percentage": 23.95, "elapsed_time": "0:33:54", "remaining_time": "1:47:41"}
+{"current_steps": 126, "total_steps": 522, "loss": 0.5067, "lr": 1.8828077870029554e-05, "epoch": 0.722753346080306, "percentage": 24.14, "elapsed_time": "0:34:12", "remaining_time": "1:47:31"}
+{"current_steps": 127, "total_steps": 522, "loss": 0.5061, "lr": 1.8796414928472417e-05, "epoch": 0.7284894837476099, "percentage": 24.33, "elapsed_time": "0:34:31", "remaining_time": "1:47:22"}
+{"current_steps": 128, "total_steps": 522, "loss": 0.5222, "lr": 1.876435729507959e-05, "epoch": 0.734225621414914, "percentage": 24.52, "elapsed_time": "0:34:48", "remaining_time": "1:47:08"}
+{"current_steps": 129, "total_steps": 522, "loss": 0.5283, "lr": 1.873190640826505e-05, "epoch": 0.739961759082218, "percentage": 24.71, "elapsed_time": "0:35:03", "remaining_time": "1:46:46"}
+{"current_steps": 130, "total_steps": 522, "loss": 0.533, "lr": 1.8699063724087905e-05, "epoch": 0.745697896749522, "percentage": 24.9, "elapsed_time": "0:35:16", "remaining_time": "1:46:23"}
+{"current_steps": 131, "total_steps": 522, "loss": 0.4986, "lr": 1.8665830716187064e-05, "epoch": 0.751434034416826, "percentage": 25.1, "elapsed_time": "0:35:31", "remaining_time": "1:46:02"}
+{"current_steps": 132, "total_steps": 522, "loss": 0.5052, "lr": 1.8632208875715122e-05, "epoch": 0.7571701720841301, "percentage": 25.29, "elapsed_time": "0:35:48", "remaining_time": "1:45:47"}
+{"current_steps": 133, "total_steps": 522, "loss": 0.4989, "lr": 1.8598199711271433e-05, "epoch": 0.762906309751434, "percentage": 25.48, "elapsed_time": "0:36:00", "remaining_time": "1:45:19"}
+{"current_steps": 134, "total_steps": 522, "loss": 0.4998, "lr": 1.856380474883444e-05, "epoch": 0.768642447418738, "percentage": 25.67, "elapsed_time": "0:36:15", "remaining_time": "1:44:58"}
+{"current_steps": 135, "total_steps": 522, "loss": 0.496, "lr": 1.85290255316932e-05, "epoch": 0.7743785850860421, "percentage": 25.86, "elapsed_time": "0:36:31", "remaining_time": "1:44:42"}
+{"current_steps": 136, "total_steps": 522, "loss": 0.5092, "lr": 1.8493863620378123e-05, "epoch": 0.780114722753346, "percentage": 26.05, "elapsed_time": "0:36:50", "remaining_time": "1:44:35"}
+{"current_steps": 137, "total_steps": 522, "loss": 0.4953, "lr": 1.8458320592590976e-05, "epoch": 0.7858508604206501, "percentage": 26.25, "elapsed_time": "0:37:07", "remaining_time": "1:44:19"}
+{"current_steps": 138, "total_steps": 522, "loss": 0.5071, "lr": 1.8422398043134068e-05, "epoch": 0.7915869980879541, "percentage": 26.44, "elapsed_time": "0:37:24", "remaining_time": "1:44:06"}
+{"current_steps": 139, "total_steps": 522, "loss": 0.5308, "lr": 1.8386097583838714e-05, "epoch": 0.7973231357552581, "percentage": 26.63, "elapsed_time": "0:37:39", "remaining_time": "1:43:44"}
+{"current_steps": 140, "total_steps": 522, "loss": 0.5547, "lr": 1.834942084349289e-05, "epoch": 0.8030592734225621, "percentage": 26.82, "elapsed_time": "0:37:56", "remaining_time": "1:43:31"}
+{"current_steps": 141, "total_steps": 522, "loss": 0.5046, "lr": 1.8312369467768168e-05, "epoch": 0.8087954110898662, "percentage": 27.01, "elapsed_time": "0:38:11", "remaining_time": "1:43:11"}
+{"current_steps": 142, "total_steps": 522, "loss": 0.5352, "lr": 1.827494511914587e-05, "epoch": 0.8145315487571702, "percentage": 27.2, "elapsed_time": "0:38:30", "remaining_time": "1:43:04"}
+{"current_steps": 143, "total_steps": 522, "loss": 0.5029, "lr": 1.8237149476842472e-05, "epoch": 0.8202676864244742, "percentage": 27.39, "elapsed_time": "0:38:48", "remaining_time": "1:42:50"}
+{"current_steps": 144, "total_steps": 522, "loss": 0.5287, "lr": 1.8198984236734246e-05, "epoch": 0.8260038240917782, "percentage": 27.59, "elapsed_time": "0:39:02", "remaining_time": "1:42:28"}
+{"current_steps": 145, "total_steps": 522, "loss": 0.5114, "lr": 1.8160451111281202e-05, "epoch": 0.8317399617590823, "percentage": 27.78, "elapsed_time": "0:39:19", "remaining_time": "1:42:15"}
+{"current_steps": 146, "total_steps": 522, "loss": 0.5188, "lr": 1.81215518294502e-05, "epoch": 0.8374760994263862, "percentage": 27.97, "elapsed_time": "0:39:38", "remaining_time": "1:42:05"}
+{"current_steps": 147, "total_steps": 522, "loss": 0.5028, "lr": 1.808228813663742e-05, "epoch": 0.8432122370936902, "percentage": 28.16, "elapsed_time": "0:39:54", "remaining_time": "1:41:48"}
+{"current_steps": 148, "total_steps": 522, "loss": 0.5054, "lr": 1.8042661794590023e-05, "epoch": 0.8489483747609943, "percentage": 28.35, "elapsed_time": "0:40:11", "remaining_time": "1:41:33"}
+{"current_steps": 149, "total_steps": 522, "loss": 0.49, "lr": 1.8002674581327096e-05, "epoch": 0.8546845124282982, "percentage": 28.54, "elapsed_time": "0:40:28", "remaining_time": "1:41:19"}
+{"current_steps": 150, "total_steps": 522, "loss": 0.5096, "lr": 1.7962328291059886e-05, "epoch": 0.8604206500956023, "percentage": 28.74, "elapsed_time": "0:40:41", "remaining_time": "1:40:55"}
+{"current_steps": 151, "total_steps": 522, "loss": 0.5218, "lr": 1.7921624734111292e-05, "epoch": 0.8661567877629063, "percentage": 28.93, "elapsed_time": "0:40:59", "remaining_time": "1:40:41"}
+{"current_steps": 152, "total_steps": 522, "loss": 0.4693, "lr": 1.7880565736834642e-05, "epoch": 0.8718929254302104, "percentage": 29.12, "elapsed_time": "0:41:14", "remaining_time": "1:40:23"}
+{"current_steps": 153, "total_steps": 522, "loss": 0.5269, "lr": 1.783915314153172e-05, "epoch": 0.8776290630975143, "percentage": 29.31, "elapsed_time": "0:41:29", "remaining_time": "1:40:04"}
+{"current_steps": 154, "total_steps": 522, "loss": 0.4939, "lr": 1.7797388806370132e-05, "epoch": 0.8833652007648184, "percentage": 29.5, "elapsed_time": "0:41:45", "remaining_time": "1:39:47"}
+{"current_steps": 155, "total_steps": 522, "loss": 0.512, "lr": 1.7755274605299924e-05, "epoch": 0.8891013384321224, "percentage": 29.69, "elapsed_time": "0:42:02", "remaining_time": "1:39:33"}
+{"current_steps": 156, "total_steps": 522, "loss": 0.5177, "lr": 1.7712812427969485e-05, "epoch": 0.8948374760994264, "percentage": 29.89, "elapsed_time": "0:42:17", "remaining_time": "1:39:14"}
+{"current_steps": 157, "total_steps": 522, "loss": 0.4961, "lr": 1.7670004179640773e-05, "epoch": 0.9005736137667304, "percentage": 30.08, "elapsed_time": "0:42:32", "remaining_time": "1:38:54"}
+{"current_steps": 158, "total_steps": 522, "loss": 0.5299, "lr": 1.762685178110382e-05, "epoch": 0.9063097514340345, "percentage": 30.27, "elapsed_time": "0:42:50", "remaining_time": "1:38:42"}
+{"current_steps": 159, "total_steps": 522, "loss": 0.496, "lr": 1.7583357168590552e-05, "epoch": 0.9120458891013384, "percentage": 30.46, "elapsed_time": "0:43:06", "remaining_time": "1:38:24"}
+{"current_steps": 160, "total_steps": 522, "loss": 0.5033, "lr": 1.75395222936879e-05, "epoch": 0.9177820267686424, "percentage": 30.65, "elapsed_time": "0:43:19", "remaining_time": "1:38:00"}
+{"current_steps": 161, "total_steps": 522, "loss": 0.5201, "lr": 1.7495349123250242e-05, "epoch": 0.9235181644359465, "percentage": 30.84, "elapsed_time": "0:43:34", "remaining_time": "1:37:41"}
+{"current_steps": 162, "total_steps": 522, "loss": 0.4674, "lr": 1.7450839639311164e-05, "epoch": 0.9292543021032504, "percentage": 31.03, "elapsed_time": "0:43:46", "remaining_time": "1:37:17"}
+{"current_steps": 163, "total_steps": 522, "loss": 0.5182, "lr": 1.7405995838994495e-05, "epoch": 0.9349904397705545, "percentage": 31.23, "elapsed_time": "0:44:03", "remaining_time": "1:37:01"}
+{"current_steps": 164, "total_steps": 522, "loss": 0.518, "lr": 1.7360819734424718e-05, "epoch": 0.9407265774378585, "percentage": 31.42, "elapsed_time": "0:44:19", "remaining_time": "1:36:44"}
+{"current_steps": 165, "total_steps": 522, "loss": 0.5223, "lr": 1.731531335263669e-05, "epoch": 0.9464627151051626, "percentage": 31.61, "elapsed_time": "0:44:34", "remaining_time": "1:36:26"}
+{"current_steps": 166, "total_steps": 522, "loss": 0.4855, "lr": 1.7269478735484682e-05, "epoch": 0.9521988527724665, "percentage": 31.8, "elapsed_time": "0:44:50", "remaining_time": "1:36:10"}
+{"current_steps": 167, "total_steps": 522, "loss": 0.4881, "lr": 1.7223317939550756e-05, "epoch": 0.9579349904397706, "percentage": 31.99, "elapsed_time": "0:45:04", "remaining_time": "1:35:49"}
+{"current_steps": 168, "total_steps": 522, "loss": 0.4835, "lr": 1.7176833036052495e-05, "epoch": 0.9636711281070746, "percentage": 32.18, "elapsed_time": "0:45:22", "remaining_time": "1:35:35"}
+{"current_steps": 169, "total_steps": 522, "loss": 0.507, "lr": 1.713002611075007e-05, "epoch": 0.9694072657743786, "percentage": 32.38, "elapsed_time": "0:45:35", "remaining_time": "1:35:14"}
+{"current_steps": 170, "total_steps": 522, "loss": 0.4979, "lr": 1.708289926385265e-05, "epoch": 0.9751434034416826, "percentage": 32.57, "elapsed_time": "0:45:53", "remaining_time": "1:35:02"}
+{"current_steps": 171, "total_steps": 522, "loss": 0.5437, "lr": 1.703545460992416e-05, "epoch": 0.9808795411089866, "percentage": 32.76, "elapsed_time": "0:46:11", "remaining_time": "1:34:49"}
+{"current_steps": 172, "total_steps": 522, "loss": 0.497, "lr": 1.698769427778842e-05, "epoch": 0.9866156787762906, "percentage": 32.95, "elapsed_time": "0:46:25", "remaining_time": "1:34:27"}
+{"current_steps": 173, "total_steps": 522, "loss": 0.5283, "lr": 1.693962041043359e-05, "epoch": 0.9923518164435946, "percentage": 33.14, "elapsed_time": "0:46:41", "remaining_time": "1:34:11"}
+{"current_steps": 174, "total_steps": 522, "loss": 0.5188, "lr": 1.6891235164916066e-05, "epoch": 0.9980879541108987, "percentage": 33.33, "elapsed_time": "0:46:59", "remaining_time": "1:33:58"}
+{"current_steps": 175, "total_steps": 522, "loss": 0.726, "lr": 1.684254071226364e-05, "epoch": 1.0038240917782026, "percentage": 33.52, "elapsed_time": "0:48:00", "remaining_time": "1:35:11"}
+{"current_steps": 176, "total_steps": 522, "loss": 0.4404, "lr": 1.679353923737813e-05, "epoch": 1.0095602294455066, "percentage": 33.72, "elapsed_time": "0:48:17", "remaining_time": "1:34:55"}
+{"current_steps": 177, "total_steps": 522, "loss": 0.4864, "lr": 1.674423293893731e-05, "epoch": 1.0152963671128108, "percentage": 33.91, "elapsed_time": "0:48:36", "remaining_time": "1:34:44"}
+{"current_steps": 178, "total_steps": 522, "loss": 0.4239, "lr": 1.6694624029296288e-05, "epoch": 1.0210325047801148, "percentage": 34.1, "elapsed_time": "0:48:50", "remaining_time": "1:34:22"}
+{"current_steps": 179, "total_steps": 522, "loss": 0.419, "lr": 1.664471473438822e-05, "epoch": 1.0267686424474187, "percentage": 34.29, "elapsed_time": "0:49:05", "remaining_time": "1:34:04"}
+{"current_steps": 180, "total_steps": 522, "loss": 0.4517, "lr": 1.6594507293624426e-05, "epoch": 1.0325047801147227, "percentage": 34.48, "elapsed_time": "0:49:21", "remaining_time": "1:33:46"}
+{"current_steps": 181, "total_steps": 522, "loss": 0.3741, "lr": 1.6544003959793925e-05, "epoch": 1.0382409177820269, "percentage": 34.67, "elapsed_time": "0:49:38", "remaining_time": "1:33:30"}
+{"current_steps": 182, "total_steps": 522, "loss": 0.4579, "lr": 1.6493206998962353e-05, "epoch": 1.0439770554493308, "percentage": 34.87, "elapsed_time": "0:49:53", "remaining_time": "1:33:11"}
+{"current_steps": 183, "total_steps": 522, "loss": 0.4572, "lr": 1.6442118690370272e-05, "epoch": 1.0497131931166348, "percentage": 35.06, "elapsed_time": "0:50:08", "remaining_time": "1:32:52"}
+{"current_steps": 184, "total_steps": 522, "loss": 0.4421, "lr": 1.639074132633091e-05, "epoch": 1.0554493307839388, "percentage": 35.25, "elapsed_time": "0:50:25", "remaining_time": "1:32:37"}
+{"current_steps": 185, "total_steps": 522, "loss": 0.4006, "lr": 1.6339077212127294e-05, "epoch": 1.0611854684512427, "percentage": 35.44, "elapsed_time": "0:50:39", "remaining_time": "1:32:17"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b39c88f2c7c9707fa8939a34e1bd3d3ce3b051a553b7a6e273805226cef039a
+size 7160