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:b9110dc73ef4180d509694b606ea1e1f790ef28ce4c9290e0c3ae95cbb247c9b
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc82023c2ca188997963138670dad0817cd749bc44d518289905946d30023eb
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ae4ad8216795ab5c67562512ef23b08030bdddb69f7852eb8ea97bf638bef0
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0406d31eaec916ea98d7fe4750b83d07dd10379c43d752f685b0ea4550da648
+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": 7.547169811320755e-07, "epoch": 0.0057361376673040155, "percentage": 0.19, "elapsed_time": "0:00:28", "remaining_time": "4:08:01"}
+{"current_steps": 2, "total_steps": 522, "loss": 0.9165, "lr": 1.509433962264151e-06, "epoch": 0.011472275334608031, "percentage": 0.38, "elapsed_time": "0:00:44", "remaining_time": "3:13:28"}
+{"current_steps": 3, "total_steps": 522, "loss": 0.9408, "lr": 2.2641509433962266e-06, "epoch": 0.017208413001912046, "percentage": 0.57, "elapsed_time": "0:00:58", "remaining_time": "2:48:15"}
+{"current_steps": 4, "total_steps": 522, "loss": 0.8925, "lr": 3.018867924528302e-06, "epoch": 0.022944550669216062, "percentage": 0.77, "elapsed_time": "0:01:12", "remaining_time": "2:35:51"}
+{"current_steps": 5, "total_steps": 522, "loss": 0.8569, "lr": 3.7735849056603777e-06, "epoch": 0.028680688336520075, "percentage": 0.96, "elapsed_time": "0:01:27", "remaining_time": "2:29:57"}
+{"current_steps": 6, "total_steps": 522, "loss": 0.8331, "lr": 4.528301886792453e-06, "epoch": 0.03441682600382409, "percentage": 1.15, "elapsed_time": "0:01:39", "remaining_time": "2:23:17"}
+{"current_steps": 7, "total_steps": 522, "loss": 0.8192, "lr": 5.283018867924529e-06, "epoch": 0.040152963671128104, "percentage": 1.34, "elapsed_time": "0:01:56", "remaining_time": "2:22:23"}
+{"current_steps": 8, "total_steps": 522, "loss": 0.7936, "lr": 6.037735849056604e-06, "epoch": 0.045889101338432124, "percentage": 1.53, "elapsed_time": "0:02:10", "remaining_time": "2:19:33"}
+{"current_steps": 9, "total_steps": 522, "loss": 0.7749, "lr": 6.792452830188679e-06, "epoch": 0.05162523900573614, "percentage": 1.72, "elapsed_time": "0:02:26", "remaining_time": "2:19:19"}
+{"current_steps": 10, "total_steps": 522, "loss": 0.8084, "lr": 7.5471698113207555e-06, "epoch": 0.05736137667304015, "percentage": 1.92, "elapsed_time": "0:02:42", "remaining_time": "2:18:27"}
+{"current_steps": 11, "total_steps": 522, "loss": 0.7579, "lr": 8.301886792452832e-06, "epoch": 0.06309751434034416, "percentage": 2.11, "elapsed_time": "0:02:57", "remaining_time": "2:17:38"}
+{"current_steps": 12, "total_steps": 522, "loss": 0.6838, "lr": 9.056603773584907e-06, "epoch": 0.06883365200764818, "percentage": 2.3, "elapsed_time": "0:03:16", "remaining_time": "2:18:58"}
+{"current_steps": 13, "total_steps": 522, "loss": 0.7421, "lr": 9.811320754716981e-06, "epoch": 0.0745697896749522, "percentage": 2.49, "elapsed_time": "0:03:32", "remaining_time": "2:18:37"}
+{"current_steps": 14, "total_steps": 522, "loss": 0.6922, "lr": 1.0566037735849058e-05, "epoch": 0.08030592734225621, "percentage": 2.68, "elapsed_time": "0:03:46", "remaining_time": "2:16:45"}
+{"current_steps": 15, "total_steps": 522, "loss": 0.695, "lr": 1.1320754716981132e-05, "epoch": 0.08604206500956023, "percentage": 2.87, "elapsed_time": "0:04:01", "remaining_time": "2:16:00"}
+{"current_steps": 16, "total_steps": 522, "loss": 0.6969, "lr": 1.2075471698113209e-05, "epoch": 0.09177820267686425, "percentage": 3.07, "elapsed_time": "0:04:17", "remaining_time": "2:15:42"}
+{"current_steps": 17, "total_steps": 522, "loss": 0.6608, "lr": 1.2830188679245283e-05, "epoch": 0.09751434034416825, "percentage": 3.26, "elapsed_time": "0:04:32", "remaining_time": "2:14:42"}
+{"current_steps": 18, "total_steps": 522, "loss": 0.6611, "lr": 1.3584905660377358e-05, "epoch": 0.10325047801147227, "percentage": 3.45, "elapsed_time": "0:04:48", "remaining_time": "2:14:37"}
+{"current_steps": 19, "total_steps": 522, "loss": 0.5937, "lr": 1.4339622641509435e-05, "epoch": 0.1089866156787763, "percentage": 3.64, "elapsed_time": "0:05:05", "remaining_time": "2:14:37"}
+{"current_steps": 20, "total_steps": 522, "loss": 0.6311, "lr": 1.5094339622641511e-05, "epoch": 0.1147227533460803, "percentage": 3.83, "elapsed_time": "0:05:22", "remaining_time": "2:15:00"}
+{"current_steps": 21, "total_steps": 522, "loss": 0.613, "lr": 1.5849056603773586e-05, "epoch": 0.12045889101338432, "percentage": 4.02, "elapsed_time": "0:05:40", "remaining_time": "2:15:20"}
+{"current_steps": 22, "total_steps": 522, "loss": 0.6066, "lr": 1.6603773584905664e-05, "epoch": 0.12619502868068833, "percentage": 4.21, "elapsed_time": "0:05:50", "remaining_time": "2:12:36"}
+{"current_steps": 23, "total_steps": 522, "loss": 0.5748, "lr": 1.735849056603774e-05, "epoch": 0.13193116634799235, "percentage": 4.41, "elapsed_time": "0:06:06", "remaining_time": "2:12:32"}
+{"current_steps": 24, "total_steps": 522, "loss": 0.6075, "lr": 1.8113207547169813e-05, "epoch": 0.13766730401529637, "percentage": 4.6, "elapsed_time": "0:06:22", "remaining_time": "2:12:26"}
+{"current_steps": 25, "total_steps": 522, "loss": 0.5943, "lr": 1.8867924528301888e-05, "epoch": 0.14340344168260039, "percentage": 4.79, "elapsed_time": "0:06:41", "remaining_time": "2:12:54"}
+{"current_steps": 26, "total_steps": 522, "loss": 0.5737, "lr": 1.9622641509433963e-05, "epoch": 0.1491395793499044, "percentage": 4.98, "elapsed_time": "0:06:57", "remaining_time": "2:12:38"}
+{"current_steps": 27, "total_steps": 522, "loss": 0.6161, "lr": 2.037735849056604e-05, "epoch": 0.15487571701720843, "percentage": 5.17, "elapsed_time": "0:07:16", "remaining_time": "2:13:22"}
+{"current_steps": 28, "total_steps": 522, "loss": 0.594, "lr": 2.1132075471698115e-05, "epoch": 0.16061185468451242, "percentage": 5.36, "elapsed_time": "0:07:32", "remaining_time": "2:13:02"}
+{"current_steps": 29, "total_steps": 522, "loss": 0.5809, "lr": 2.188679245283019e-05, "epoch": 0.16634799235181644, "percentage": 5.56, "elapsed_time": "0:07:46", "remaining_time": "2:12:14"}
+{"current_steps": 30, "total_steps": 522, "loss": 0.5813, "lr": 2.2641509433962265e-05, "epoch": 0.17208413001912046, "percentage": 5.75, "elapsed_time": "0:08:03", "remaining_time": "2:12:11"}
+{"current_steps": 31, "total_steps": 522, "loss": 0.5523, "lr": 2.339622641509434e-05, "epoch": 0.17782026768642448, "percentage": 5.94, "elapsed_time": "0:08:20", "remaining_time": "2:12:12"}
+{"current_steps": 32, "total_steps": 522, "loss": 0.5376, "lr": 2.4150943396226418e-05, "epoch": 0.1835564053537285, "percentage": 6.13, "elapsed_time": "0:08:33", "remaining_time": "2:11:05"}
+{"current_steps": 33, "total_steps": 522, "loss": 0.5652, "lr": 2.4905660377358492e-05, "epoch": 0.18929254302103252, "percentage": 6.32, "elapsed_time": "0:08:50", "remaining_time": "2:11:08"}
+{"current_steps": 34, "total_steps": 522, "loss": 0.5927, "lr": 2.5660377358490567e-05, "epoch": 0.1950286806883365, "percentage": 6.51, "elapsed_time": "0:09:04", "remaining_time": "2:10:11"}
+{"current_steps": 35, "total_steps": 522, "loss": 0.5668, "lr": 2.641509433962264e-05, "epoch": 0.20076481835564053, "percentage": 6.7, "elapsed_time": "0:09:22", "remaining_time": "2:10:20"}
+{"current_steps": 36, "total_steps": 522, "loss": 0.5569, "lr": 2.7169811320754716e-05, "epoch": 0.20650095602294455, "percentage": 6.9, "elapsed_time": "0:09:40", "remaining_time": "2:10:37"}
+{"current_steps": 37, "total_steps": 522, "loss": 0.5566, "lr": 2.7924528301886794e-05, "epoch": 0.21223709369024857, "percentage": 7.09, "elapsed_time": "0:09:59", "remaining_time": "2:10:59"}
+{"current_steps": 38, "total_steps": 522, "loss": 0.5757, "lr": 2.867924528301887e-05, "epoch": 0.2179732313575526, "percentage": 7.28, "elapsed_time": "0:10:18", "remaining_time": "2:11:14"}
+{"current_steps": 39, "total_steps": 522, "loss": 0.5794, "lr": 2.9433962264150944e-05, "epoch": 0.2237093690248566, "percentage": 7.47, "elapsed_time": "0:10:35", "remaining_time": "2:11:05"}
+{"current_steps": 40, "total_steps": 522, "loss": 0.5319, "lr": 3.0188679245283022e-05, "epoch": 0.2294455066921606, "percentage": 7.66, "elapsed_time": "0:10:52", "remaining_time": "2:10:56"}
+{"current_steps": 41, "total_steps": 522, "loss": 0.587, "lr": 3.09433962264151e-05, "epoch": 0.23518164435946462, "percentage": 7.85, "elapsed_time": "0:11:07", "remaining_time": "2:10:30"}
+{"current_steps": 42, "total_steps": 522, "loss": 0.5268, "lr": 3.169811320754717e-05, "epoch": 0.24091778202676864, "percentage": 8.05, "elapsed_time": "0:11:27", "remaining_time": "2:10:52"}
+{"current_steps": 43, "total_steps": 522, "loss": 0.5802, "lr": 3.245283018867925e-05, "epoch": 0.24665391969407266, "percentage": 8.24, "elapsed_time": "0:11:44", "remaining_time": "2:10:53"}
+{"current_steps": 44, "total_steps": 522, "loss": 0.5766, "lr": 3.320754716981133e-05, "epoch": 0.25239005736137665, "percentage": 8.43, "elapsed_time": "0:12:02", "remaining_time": "2:10:43"}
+{"current_steps": 45, "total_steps": 522, "loss": 0.561, "lr": 3.39622641509434e-05, "epoch": 0.25812619502868067, "percentage": 8.62, "elapsed_time": "0:12:16", "remaining_time": "2:10:08"}
+{"current_steps": 46, "total_steps": 522, "loss": 0.5193, "lr": 3.471698113207548e-05, "epoch": 0.2638623326959847, "percentage": 8.81, "elapsed_time": "0:12:36", "remaining_time": "2:10:26"}
+{"current_steps": 47, "total_steps": 522, "loss": 0.5639, "lr": 3.547169811320755e-05, "epoch": 0.2695984703632887, "percentage": 9.0, "elapsed_time": "0:12:51", "remaining_time": "2:09:57"}
+{"current_steps": 48, "total_steps": 522, "loss": 0.549, "lr": 3.6226415094339626e-05, "epoch": 0.27533460803059273, "percentage": 9.2, "elapsed_time": "0:13:08", "remaining_time": "2:09:45"}
+{"current_steps": 49, "total_steps": 522, "loss": 0.5742, "lr": 3.6981132075471704e-05, "epoch": 0.28107074569789675, "percentage": 9.39, "elapsed_time": "0:13:27", "remaining_time": "2:09:52"}
+{"current_steps": 50, "total_steps": 522, "loss": 0.5326, "lr": 3.7735849056603776e-05, "epoch": 0.28680688336520077, "percentage": 9.58, "elapsed_time": "0:13:44", "remaining_time": "2:09:41"}
+{"current_steps": 51, "total_steps": 522, "loss": 0.5245, "lr": 3.8490566037735854e-05, "epoch": 0.2925430210325048, "percentage": 9.77, "elapsed_time": "0:14:02", "remaining_time": "2:09:44"}
+{"current_steps": 52, "total_steps": 522, "loss": 0.5621, "lr": 3.9245283018867925e-05, "epoch": 0.2982791586998088, "percentage": 9.96, "elapsed_time": "0:14:19", "remaining_time": "2:09:26"}
+{"current_steps": 53, "total_steps": 522, "loss": 0.5527, "lr": 4e-05, "epoch": 0.30401529636711283, "percentage": 10.15, "elapsed_time": "0:14:30", "remaining_time": "2:08:26"}
+{"current_steps": 54, "total_steps": 522, "loss": 0.5207, "lr": 3.999955130375398e-05, "epoch": 0.30975143403441685, "percentage": 10.34, "elapsed_time": "0:14:48", "remaining_time": "2:08:22"}
+{"current_steps": 55, "total_steps": 522, "loss": 0.5388, "lr": 3.999820523514873e-05, "epoch": 0.3154875717017208, "percentage": 10.54, "elapsed_time": "0:15:03", "remaining_time": "2:07:55"}
+{"current_steps": 56, "total_steps": 522, "loss": 0.5443, "lr": 3.9995961854581855e-05, "epoch": 0.32122370936902483, "percentage": 10.73, "elapsed_time": "0:15:19", "remaining_time": "2:07:34"}
+{"current_steps": 57, "total_steps": 522, "loss": 0.5475, "lr": 3.999282126271299e-05, "epoch": 0.32695984703632885, "percentage": 10.92, "elapsed_time": "0:15:37", "remaining_time": "2:07:25"}
+{"current_steps": 58, "total_steps": 522, "loss": 0.5471, "lr": 3.998878360045933e-05, "epoch": 0.3326959847036329, "percentage": 11.11, "elapsed_time": "0:15:54", "remaining_time": "2:07:16"}
+{"current_steps": 59, "total_steps": 522, "loss": 0.532, "lr": 3.998384904898926e-05, "epoch": 0.3384321223709369, "percentage": 11.3, "elapsed_time": "0:16:10", "remaining_time": "2:06:53"}
+{"current_steps": 60, "total_steps": 522, "loss": 0.5196, "lr": 3.997801782971423e-05, "epoch": 0.3441682600382409, "percentage": 11.49, "elapsed_time": "0:16:26", "remaining_time": "2:06:32"}
+{"current_steps": 61, "total_steps": 522, "loss": 0.5485, "lr": 3.997129020427888e-05, "epoch": 0.34990439770554493, "percentage": 11.69, "elapsed_time": "0:16:45", "remaining_time": "2:06:38"}
+{"current_steps": 62, "total_steps": 522, "loss": 0.5466, "lr": 3.996366647454924e-05, "epoch": 0.35564053537284895, "percentage": 11.88, "elapsed_time": "0:17:02", "remaining_time": "2:06:25"}
+{"current_steps": 63, "total_steps": 522, "loss": 0.5468, "lr": 3.9955146982599194e-05, "epoch": 0.361376673040153, "percentage": 12.07, "elapsed_time": "0:17:19", "remaining_time": "2:06:14"}
+{"current_steps": 64, "total_steps": 522, "loss": 0.525, "lr": 3.9945732110695145e-05, "epoch": 0.367112810707457, "percentage": 12.26, "elapsed_time": "0:17:38", "remaining_time": "2:06:12"}
+{"current_steps": 65, "total_steps": 522, "loss": 0.5382, "lr": 3.993542228127886e-05, "epoch": 0.372848948374761, "percentage": 12.45, "elapsed_time": "0:17:51", "remaining_time": "2:05:33"}
+{"current_steps": 66, "total_steps": 522, "loss": 0.5431, "lr": 3.992421795694853e-05, "epoch": 0.37858508604206503, "percentage": 12.64, "elapsed_time": "0:18:06", "remaining_time": "2:05:03"}
+{"current_steps": 67, "total_steps": 522, "loss": 0.5154, "lr": 3.9912119640437965e-05, "epoch": 0.384321223709369, "percentage": 12.84, "elapsed_time": "0:18:18", "remaining_time": "2:04:19"}
+{"current_steps": 68, "total_steps": 522, "loss": 0.527, "lr": 3.989912787459409e-05, "epoch": 0.390057361376673, "percentage": 13.03, "elapsed_time": "0:18:34", "remaining_time": "2:04:02"}
+{"current_steps": 69, "total_steps": 522, "loss": 0.5351, "lr": 3.9885243242352565e-05, "epoch": 0.39579349904397704, "percentage": 13.22, "elapsed_time": "0:18:55", "remaining_time": "2:04:12"}
+{"current_steps": 70, "total_steps": 522, "loss": 0.4824, "lr": 3.987046636671162e-05, "epoch": 0.40152963671128106, "percentage": 13.41, "elapsed_time": "0:19:11", "remaining_time": "2:03:54"}
+{"current_steps": 71, "total_steps": 522, "loss": 0.5364, "lr": 3.9854797910704124e-05, "epoch": 0.4072657743785851, "percentage": 13.6, "elapsed_time": "0:19:21", "remaining_time": "2:03:00"}
+{"current_steps": 72, "total_steps": 522, "loss": 0.5014, "lr": 3.9838238577367816e-05, "epoch": 0.4130019120458891, "percentage": 13.79, "elapsed_time": "0:19:37", "remaining_time": "2:02:37"}
+{"current_steps": 73, "total_steps": 522, "loss": 0.5349, "lr": 3.982078910971376e-05, "epoch": 0.4187380497131931, "percentage": 13.98, "elapsed_time": "0:19:55", "remaining_time": "2:02:32"}
+{"current_steps": 74, "total_steps": 522, "loss": 0.5334, "lr": 3.980245029069302e-05, "epoch": 0.42447418738049714, "percentage": 14.18, "elapsed_time": "0:20:10", "remaining_time": "2:02:08"}
+{"current_steps": 75, "total_steps": 522, "loss": 0.5509, "lr": 3.978322294316153e-05, "epoch": 0.43021032504780116, "percentage": 14.37, "elapsed_time": "0:20:28", "remaining_time": "2:02:01"}
+{"current_steps": 76, "total_steps": 522, "loss": 0.5323, "lr": 3.976310792984315e-05, "epoch": 0.4359464627151052, "percentage": 14.56, "elapsed_time": "0:20:47", "remaining_time": "2:02:01"}
+{"current_steps": 77, "total_steps": 522, "loss": 0.5451, "lr": 3.974210615329098e-05, "epoch": 0.4416826003824092, "percentage": 14.75, "elapsed_time": "0:21:06", "remaining_time": "2:02:01"}
+{"current_steps": 78, "total_steps": 522, "loss": 0.5339, "lr": 3.9720218555846834e-05, "epoch": 0.4474187380497132, "percentage": 14.94, "elapsed_time": "0:21:24", "remaining_time": "2:01:53"}
+{"current_steps": 79, "total_steps": 522, "loss": 0.544, "lr": 3.9697446119599015e-05, "epoch": 0.45315487571701724, "percentage": 15.13, "elapsed_time": "0:21:44", "remaining_time": "2:01:56"}
+{"current_steps": 80, "total_steps": 522, "loss": 0.5256, "lr": 3.967378986633818e-05, "epoch": 0.4588910133843212, "percentage": 15.33, "elapsed_time": "0:22:04", "remaining_time": "2:01:56"}
+{"current_steps": 81, "total_steps": 522, "loss": 0.53, "lr": 3.964925085751152e-05, "epoch": 0.4646271510516252, "percentage": 15.52, "elapsed_time": "0:22:19", "remaining_time": "2:01:34"}
+{"current_steps": 82, "total_steps": 522, "loss": 0.552, "lr": 3.9623830194175175e-05, "epoch": 0.47036328871892924, "percentage": 15.71, "elapsed_time": "0:22:37", "remaining_time": "2:01:26"}
+{"current_steps": 83, "total_steps": 522, "loss": 0.5265, "lr": 3.9597529016944746e-05, "epoch": 0.47609942638623326, "percentage": 15.9, "elapsed_time": "0:22:53", "remaining_time": "2:01:03"}
+{"current_steps": 84, "total_steps": 522, "loss": 0.5389, "lr": 3.9570348505944185e-05, "epoch": 0.4818355640535373, "percentage": 16.09, "elapsed_time": "0:23:06", "remaining_time": "2:00:31"}
+{"current_steps": 85, "total_steps": 522, "loss": 0.5258, "lr": 3.9542289880752827e-05, "epoch": 0.4875717017208413, "percentage": 16.28, "elapsed_time": "0:23:23", "remaining_time": "2:00:16"}
+{"current_steps": 86, "total_steps": 522, "loss": 0.5295, "lr": 3.951335440035063e-05, "epoch": 0.4933078393881453, "percentage": 16.48, "elapsed_time": "0:23:40", "remaining_time": "2:00:00"}
+{"current_steps": 87, "total_steps": 522, "loss": 0.5516, "lr": 3.948354336306176e-05, "epoch": 0.49904397705544934, "percentage": 16.67, "elapsed_time": "0:23:56", "remaining_time": "1:59:44"}
+{"current_steps": 88, "total_steps": 522, "loss": 0.5315, "lr": 3.945285810649626e-05, "epoch": 0.5047801147227533, "percentage": 16.86, "elapsed_time": "0:24:16", "remaining_time": "1:59:41"}
+{"current_steps": 89, "total_steps": 522, "loss": 0.5415, "lr": 3.942130000749008e-05, "epoch": 0.5105162523900574, "percentage": 17.05, "elapsed_time": "0:24:32", "remaining_time": "1:59:22"}
+{"current_steps": 90, "total_steps": 522, "loss": 0.5465, "lr": 3.938887048204326e-05, "epoch": 0.5162523900573613, "percentage": 17.24, "elapsed_time": "0:24:48", "remaining_time": "1:59:03"}
+{"current_steps": 91, "total_steps": 522, "loss": 0.5005, "lr": 3.935557098525644e-05, "epoch": 0.5219885277246654, "percentage": 17.43, "elapsed_time": "0:25:04", "remaining_time": "1:58:45"}
+{"current_steps": 92, "total_steps": 522, "loss": 0.5189, "lr": 3.9321403011265546e-05, "epoch": 0.5277246653919694, "percentage": 17.62, "elapsed_time": "0:25:23", "remaining_time": "1:58:39"}
+{"current_steps": 93, "total_steps": 522, "loss": 0.5277, "lr": 3.9286368093174745e-05, "epoch": 0.5334608030592735, "percentage": 17.82, "elapsed_time": "0:25:39", "remaining_time": "1:58:21"}
+{"current_steps": 94, "total_steps": 522, "loss": 0.5237, "lr": 3.925046780298764e-05, "epoch": 0.5391969407265774, "percentage": 18.01, "elapsed_time": "0:25:53", "remaining_time": "1:57:53"}
+{"current_steps": 95, "total_steps": 522, "loss": 0.5348, "lr": 3.921370375153681e-05, "epoch": 0.5449330783938815, "percentage": 18.2, "elapsed_time": "0:26:11", "remaining_time": "1:57:42"}
+{"current_steps": 96, "total_steps": 522, "loss": 0.5349, "lr": 3.917607758841141e-05, "epoch": 0.5506692160611855, "percentage": 18.39, "elapsed_time": "0:26:26", "remaining_time": "1:57:18"}
+{"current_steps": 97, "total_steps": 522, "loss": 0.5061, "lr": 3.913759100188327e-05, "epoch": 0.5564053537284895, "percentage": 18.58, "elapsed_time": "0:26:41", "remaining_time": "1:56:56"}
+{"current_steps": 98, "total_steps": 522, "loss": 0.5615, "lr": 3.9098245718831076e-05, "epoch": 0.5621414913957935, "percentage": 18.77, "elapsed_time": "0:26:58", "remaining_time": "1:56:40"}
+{"current_steps": 99, "total_steps": 522, "loss": 0.5243, "lr": 3.905804350466291e-05, "epoch": 0.5678776290630975, "percentage": 18.97, "elapsed_time": "0:27:10", "remaining_time": "1:56:07"}
+{"current_steps": 100, "total_steps": 522, "loss": 0.5155, "lr": 3.901698616323703e-05, "epoch": 0.5736137667304015, "percentage": 19.16, "elapsed_time": "0:27:23", "remaining_time": "1:55:34"}
+{"current_steps": 101, "total_steps": 522, "loss": 0.5451, "lr": 3.897507553678093e-05, "epoch": 0.5793499043977055, "percentage": 19.35, "elapsed_time": "0:27:40", "remaining_time": "1:55:23"}
+{"current_steps": 102, "total_steps": 522, "loss": 0.5383, "lr": 3.893231350580869e-05, "epoch": 0.5850860420650096, "percentage": 19.54, "elapsed_time": "0:27:58", "remaining_time": "1:55:11"}
+{"current_steps": 103, "total_steps": 522, "loss": 0.5316, "lr": 3.888870198903658e-05, "epoch": 0.5908221797323135, "percentage": 19.73, "elapsed_time": "0:28:12", "remaining_time": "1:54:43"}
+{"current_steps": 104, "total_steps": 522, "loss": 0.523, "lr": 3.8844242943297e-05, "epoch": 0.5965583173996176, "percentage": 19.92, "elapsed_time": "0:28:30", "remaining_time": "1:54:36"}
+{"current_steps": 105, "total_steps": 522, "loss": 0.5153, "lr": 3.879893836345062e-05, "epoch": 0.6022944550669216, "percentage": 20.11, "elapsed_time": "0:28:42", "remaining_time": "1:54:02"}
+{"current_steps": 106, "total_steps": 522, "loss": 0.5432, "lr": 3.875279028229695e-05, "epoch": 0.6080305927342257, "percentage": 20.31, "elapsed_time": "0:28:57", "remaining_time": "1:53:38"}
+{"current_steps": 107, "total_steps": 522, "loss": 0.5296, "lr": 3.870580077048307e-05, "epoch": 0.6137667304015296, "percentage": 20.5, "elapsed_time": "0:29:13", "remaining_time": "1:53:20"}
+{"current_steps": 108, "total_steps": 522, "loss": 0.5355, "lr": 3.865797193641072e-05, "epoch": 0.6195028680688337, "percentage": 20.69, "elapsed_time": "0:29:29", "remaining_time": "1:53:04"}
+{"current_steps": 109, "total_steps": 522, "loss": 0.4964, "lr": 3.8609305926141735e-05, "epoch": 0.6252390057361377, "percentage": 20.88, "elapsed_time": "0:29:45", "remaining_time": "1:52:43"}
+{"current_steps": 110, "total_steps": 522, "loss": 0.5399, "lr": 3.855980492330173e-05, "epoch": 0.6309751434034416, "percentage": 21.07, "elapsed_time": "0:30:01", "remaining_time": "1:52:27"}
+{"current_steps": 111, "total_steps": 522, "loss": 0.54, "lr": 3.850947114898212e-05, "epoch": 0.6367112810707457, "percentage": 21.26, "elapsed_time": "0:30:15", "remaining_time": "1:52:02"}
+{"current_steps": 112, "total_steps": 522, "loss": 0.5478, "lr": 3.8458306861640465e-05, "epoch": 0.6424474187380497, "percentage": 21.46, "elapsed_time": "0:30:29", "remaining_time": "1:51:37"}
+{"current_steps": 113, "total_steps": 522, "loss": 0.5089, "lr": 3.840631435699912e-05, "epoch": 0.6481835564053537, "percentage": 21.65, "elapsed_time": "0:30:41", "remaining_time": "1:51:06"}
+{"current_steps": 114, "total_steps": 522, "loss": 0.524, "lr": 3.835349596794226e-05, "epoch": 0.6539196940726577, "percentage": 21.84, "elapsed_time": "0:30:57", "remaining_time": "1:50:47"}
+{"current_steps": 115, "total_steps": 522, "loss": 0.5371, "lr": 3.829985406441118e-05, "epoch": 0.6596558317399618, "percentage": 22.03, "elapsed_time": "0:31:12", "remaining_time": "1:50:26"}
+{"current_steps": 116, "total_steps": 522, "loss": 0.4979, "lr": 3.8245391053297936e-05, "epoch": 0.6653919694072657, "percentage": 22.22, "elapsed_time": "0:31:27", "remaining_time": "1:50:07"}
+{"current_steps": 117, "total_steps": 522, "loss": 0.5239, "lr": 3.8190109378337413e-05, "epoch": 0.6711281070745698, "percentage": 22.41, "elapsed_time": "0:31:43", "remaining_time": "1:49:47"}
+{"current_steps": 118, "total_steps": 522, "loss": 0.5475, "lr": 3.813401151999759e-05, "epoch": 0.6768642447418738, "percentage": 22.61, "elapsed_time": "0:32:03", "remaining_time": "1:49:45"}
+{"current_steps": 119, "total_steps": 522, "loss": 0.5395, "lr": 3.807709999536834e-05, "epoch": 0.6826003824091779, "percentage": 22.8, "elapsed_time": "0:32:21", "remaining_time": "1:49:34"}
+{"current_steps": 120, "total_steps": 522, "loss": 0.5087, "lr": 3.801937735804838e-05, "epoch": 0.6883365200764818, "percentage": 22.99, "elapsed_time": "0:32:37", "remaining_time": "1:49:17"}
+{"current_steps": 121, "total_steps": 522, "loss": 0.5453, "lr": 3.7960846198030804e-05, "epoch": 0.6940726577437859, "percentage": 23.18, "elapsed_time": "0:32:56", "remaining_time": "1:49:09"}
+{"current_steps": 122, "total_steps": 522, "loss": 0.5043, "lr": 3.790150914158677e-05, "epoch": 0.6998087954110899, "percentage": 23.37, "elapsed_time": "0:33:09", "remaining_time": "1:48:41"}
+{"current_steps": 123, "total_steps": 522, "loss": 0.5129, "lr": 3.784136885114773e-05, "epoch": 0.7055449330783938, "percentage": 23.56, "elapsed_time": "0:33:24", "remaining_time": "1:48:23"}
+{"current_steps": 124, "total_steps": 522, "loss": 0.5533, "lr": 3.7780428025185954e-05, "epoch": 0.7112810707456979, "percentage": 23.75, "elapsed_time": "0:33:40", "remaining_time": "1:48:06"}
+{"current_steps": 125, "total_steps": 522, "loss": 0.5421, "lr": 3.77186893980934e-05, "epoch": 0.7170172084130019, "percentage": 23.95, "elapsed_time": "0:33:58", "remaining_time": "1:47:53"}
+{"current_steps": 126, "total_steps": 522, "loss": 0.5139, "lr": 3.765615574005911e-05, "epoch": 0.722753346080306, "percentage": 24.14, "elapsed_time": "0:34:16", "remaining_time": "1:47:41"}
+{"current_steps": 127, "total_steps": 522, "loss": 0.511, "lr": 3.7592829856944835e-05, "epoch": 0.7284894837476099, "percentage": 24.33, "elapsed_time": "0:34:35", "remaining_time": "1:47:33"}
+{"current_steps": 128, "total_steps": 522, "loss": 0.5286, "lr": 3.752871459015918e-05, "epoch": 0.734225621414914, "percentage": 24.52, "elapsed_time": "0:34:51", "remaining_time": "1:47:19"}
+{"current_steps": 129, "total_steps": 522, "loss": 0.5329, "lr": 3.74638128165301e-05, "epoch": 0.739961759082218, "percentage": 24.71, "elapsed_time": "0:35:06", "remaining_time": "1:46:57"}
+{"current_steps": 130, "total_steps": 522, "loss": 0.5362, "lr": 3.739812744817581e-05, "epoch": 0.745697896749522, "percentage": 24.9, "elapsed_time": "0:35:20", "remaining_time": "1:46:34"}
+{"current_steps": 131, "total_steps": 522, "loss": 0.5035, "lr": 3.733166143237413e-05, "epoch": 0.751434034416826, "percentage": 25.1, "elapsed_time": "0:35:35", "remaining_time": "1:46:13"}
+{"current_steps": 132, "total_steps": 522, "loss": 0.5085, "lr": 3.7264417751430244e-05, "epoch": 0.7571701720841301, "percentage": 25.29, "elapsed_time": "0:35:52", "remaining_time": "1:45:58"}
+{"current_steps": 133, "total_steps": 522, "loss": 0.5065, "lr": 3.7196399422542866e-05, "epoch": 0.762906309751434, "percentage": 25.48, "elapsed_time": "0:36:04", "remaining_time": "1:45:30"}
+{"current_steps": 134, "total_steps": 522, "loss": 0.5038, "lr": 3.712760949766888e-05, "epoch": 0.768642447418738, "percentage": 25.67, "elapsed_time": "0:36:19", "remaining_time": "1:45:09"}
+{"current_steps": 135, "total_steps": 522, "loss": 0.5008, "lr": 3.70580510633864e-05, "epoch": 0.7743785850860421, "percentage": 25.86, "elapsed_time": "0:36:35", "remaining_time": "1:44:53"}
+{"current_steps": 136, "total_steps": 522, "loss": 0.5142, "lr": 3.6987727240756246e-05, "epoch": 0.780114722753346, "percentage": 26.05, "elapsed_time": "0:36:55", "remaining_time": "1:44:46"}
+{"current_steps": 137, "total_steps": 522, "loss": 0.4994, "lr": 3.691664118518195e-05, "epoch": 0.7858508604206501, "percentage": 26.25, "elapsed_time": "0:37:11", "remaining_time": "1:44:31"}
+{"current_steps": 138, "total_steps": 522, "loss": 0.5164, "lr": 3.6844796086268136e-05, "epoch": 0.7915869980879541, "percentage": 26.44, "elapsed_time": "0:37:28", "remaining_time": "1:44:17"}
+{"current_steps": 139, "total_steps": 522, "loss": 0.5349, "lr": 3.677219516767743e-05, "epoch": 0.7973231357552581, "percentage": 26.63, "elapsed_time": "0:37:43", "remaining_time": "1:43:56"}
+{"current_steps": 140, "total_steps": 522, "loss": 0.559, "lr": 3.669884168698578e-05, "epoch": 0.8030592734225621, "percentage": 26.82, "elapsed_time": "0:38:00", "remaining_time": "1:43:43"}
+{"current_steps": 141, "total_steps": 522, "loss": 0.5082, "lr": 3.6624738935536336e-05, "epoch": 0.8087954110898662, "percentage": 27.01, "elapsed_time": "0:38:15", "remaining_time": "1:43:23"}
+{"current_steps": 142, "total_steps": 522, "loss": 0.5401, "lr": 3.654989023829174e-05, "epoch": 0.8145315487571702, "percentage": 27.2, "elapsed_time": "0:38:35", "remaining_time": "1:43:15"}
+{"current_steps": 143, "total_steps": 522, "loss": 0.5071, "lr": 3.6474298953684945e-05, "epoch": 0.8202676864244742, "percentage": 27.39, "elapsed_time": "0:38:52", "remaining_time": "1:43:02"}
+{"current_steps": 144, "total_steps": 522, "loss": 0.5343, "lr": 3.639796847346849e-05, "epoch": 0.8260038240917782, "percentage": 27.59, "elapsed_time": "0:39:06", "remaining_time": "1:42:40"}
+{"current_steps": 145, "total_steps": 522, "loss": 0.515, "lr": 3.6320902222562405e-05, "epoch": 0.8317399617590823, "percentage": 27.78, "elapsed_time": "0:39:24", "remaining_time": "1:42:27"}
+{"current_steps": 146, "total_steps": 522, "loss": 0.5235, "lr": 3.62431036589004e-05, "epoch": 0.8374760994263862, "percentage": 27.97, "elapsed_time": "0:39:43", "remaining_time": "1:42:17"}
+{"current_steps": 147, "total_steps": 522, "loss": 0.5075, "lr": 3.616457627327484e-05, "epoch": 0.8432122370936902, "percentage": 28.16, "elapsed_time": "0:39:59", "remaining_time": "1:42:00"}
+{"current_steps": 148, "total_steps": 522, "loss": 0.5092, "lr": 3.6085323589180046e-05, "epoch": 0.8489483747609943, "percentage": 28.35, "elapsed_time": "0:40:15", "remaining_time": "1:41:45"}
+{"current_steps": 149, "total_steps": 522, "loss": 0.4943, "lr": 3.600534916265419e-05, "epoch": 0.8546845124282982, "percentage": 28.54, "elapsed_time": "0:40:33", "remaining_time": "1:41:31"}
+{"current_steps": 150, "total_steps": 522, "loss": 0.5133, "lr": 3.592465658211977e-05, "epoch": 0.8604206500956023, "percentage": 28.74, "elapsed_time": "0:40:46", "remaining_time": "1:41:07"}
+{"current_steps": 151, "total_steps": 522, "loss": 0.5264, "lr": 3.5843249468222585e-05, "epoch": 0.8661567877629063, "percentage": 28.93, "elapsed_time": "0:41:03", "remaining_time": "1:40:53"}
+{"current_steps": 152, "total_steps": 522, "loss": 0.4759, "lr": 3.5761131473669285e-05, "epoch": 0.8718929254302104, "percentage": 29.12, "elapsed_time": "0:41:19", "remaining_time": "1:40:35"}
+{"current_steps": 153, "total_steps": 522, "loss": 0.5335, "lr": 3.567830628306344e-05, "epoch": 0.8776290630975143, "percentage": 29.31, "elapsed_time": "0:41:34", "remaining_time": "1:40:16"}
+{"current_steps": 154, "total_steps": 522, "loss": 0.4993, "lr": 3.5594777612740263e-05, "epoch": 0.8833652007648184, "percentage": 29.5, "elapsed_time": "0:41:50", "remaining_time": "1:39:59"}
+{"current_steps": 155, "total_steps": 522, "loss": 0.5176, "lr": 3.551054921059985e-05, "epoch": 0.8891013384321224, "percentage": 29.69, "elapsed_time": "0:42:07", "remaining_time": "1:39:44"}
+{"current_steps": 156, "total_steps": 522, "loss": 0.5238, "lr": 3.542562485593897e-05, "epoch": 0.8948374760994264, "percentage": 29.89, "elapsed_time": "0:42:22", "remaining_time": "1:39:25"}
+{"current_steps": 157, "total_steps": 522, "loss": 0.501, "lr": 3.5340008359281546e-05, "epoch": 0.9005736137667304, "percentage": 30.08, "elapsed_time": "0:42:37", "remaining_time": "1:39:05"}
+{"current_steps": 158, "total_steps": 522, "loss": 0.5345, "lr": 3.525370356220764e-05, "epoch": 0.9063097514340345, "percentage": 30.27, "elapsed_time": "0:42:55", "remaining_time": "1:38:53"}
+{"current_steps": 159, "total_steps": 522, "loss": 0.5018, "lr": 3.5166714337181104e-05, "epoch": 0.9120458891013384, "percentage": 30.46, "elapsed_time": "0:43:10", "remaining_time": "1:38:34"}
+{"current_steps": 160, "total_steps": 522, "loss": 0.5078, "lr": 3.50790445873758e-05, "epoch": 0.9177820267686424, "percentage": 30.65, "elapsed_time": "0:43:24", "remaining_time": "1:38:11"}
+{"current_steps": 161, "total_steps": 522, "loss": 0.5256, "lr": 3.4990698246500484e-05, "epoch": 0.9235181644359465, "percentage": 30.84, "elapsed_time": "0:43:39", "remaining_time": "1:37:52"}
+{"current_steps": 162, "total_steps": 522, "loss": 0.4722, "lr": 3.490167927862233e-05, "epoch": 0.9292543021032504, "percentage": 31.03, "elapsed_time": "0:43:51", "remaining_time": "1:37:28"}
+{"current_steps": 163, "total_steps": 522, "loss": 0.5223, "lr": 3.481199167798899e-05, "epoch": 0.9349904397705545, "percentage": 31.23, "elapsed_time": "0:44:07", "remaining_time": "1:37:11"}
+{"current_steps": 164, "total_steps": 522, "loss": 0.5213, "lr": 3.4721639468849436e-05, "epoch": 0.9407265774378585, "percentage": 31.42, "elapsed_time": "0:44:24", "remaining_time": "1:36:55"}
+{"current_steps": 165, "total_steps": 522, "loss": 0.5273, "lr": 3.463062670527338e-05, "epoch": 0.9464627151051626, "percentage": 31.61, "elapsed_time": "0:44:39", "remaining_time": "1:36:37"}
+{"current_steps": 166, "total_steps": 522, "loss": 0.4904, "lr": 3.4538957470969365e-05, "epoch": 0.9521988527724665, "percentage": 31.8, "elapsed_time": "0:44:55", "remaining_time": "1:36:20"}
+{"current_steps": 167, "total_steps": 522, "loss": 0.4922, "lr": 3.444663587910151e-05, "epoch": 0.9579349904397706, "percentage": 31.99, "elapsed_time": "0:45:09", "remaining_time": "1:36:00"}
+{"current_steps": 168, "total_steps": 522, "loss": 0.4877, "lr": 3.435366607210499e-05, "epoch": 0.9636711281070746, "percentage": 32.18, "elapsed_time": "0:45:27", "remaining_time": "1:35:46"}
+{"current_steps": 169, "total_steps": 522, "loss": 0.5106, "lr": 3.426005222150014e-05, "epoch": 0.9694072657743786, "percentage": 32.38, "elapsed_time": "0:45:40", "remaining_time": "1:35:24"}
+{"current_steps": 170, "total_steps": 522, "loss": 0.5008, "lr": 3.41657985277053e-05, "epoch": 0.9751434034416826, "percentage": 32.57, "elapsed_time": "0:45:58", "remaining_time": "1:35:12"}
+{"current_steps": 171, "total_steps": 522, "loss": 0.5477, "lr": 3.407090921984832e-05, "epoch": 0.9808795411089866, "percentage": 32.76, "elapsed_time": "0:46:16", "remaining_time": "1:34:59"}
+{"current_steps": 172, "total_steps": 522, "loss": 0.5009, "lr": 3.397538855557684e-05, "epoch": 0.9866156787762906, "percentage": 32.95, "elapsed_time": "0:46:30", "remaining_time": "1:34:37"}
+{"current_steps": 173, "total_steps": 522, "loss": 0.5332, "lr": 3.387924082086718e-05, "epoch": 0.9923518164435946, "percentage": 33.14, "elapsed_time": "0:46:46", "remaining_time": "1:34:21"}
+{"current_steps": 174, "total_steps": 522, "loss": 0.522, "lr": 3.378247032983213e-05, "epoch": 0.9980879541108987, "percentage": 33.33, "elapsed_time": "0:47:04", "remaining_time": "1:34:08"}
+{"current_steps": 175, "total_steps": 522, "loss": 0.7212, "lr": 3.368508142452728e-05, "epoch": 1.0038240917782026, "percentage": 33.52, "elapsed_time": "0:48:04", "remaining_time": "1:35:18"}
+{"current_steps": 176, "total_steps": 522, "loss": 0.4198, "lr": 3.358707847475626e-05, "epoch": 1.0095602294455066, "percentage": 33.72, "elapsed_time": "0:48:21", "remaining_time": "1:35:03"}
+{"current_steps": 177, "total_steps": 522, "loss": 0.461, "lr": 3.348846587787462e-05, "epoch": 1.0152963671128108, "percentage": 33.91, "elapsed_time": "0:48:40", "remaining_time": "1:34:52"}
+{"current_steps": 178, "total_steps": 522, "loss": 0.4066, "lr": 3.3389248058592576e-05, "epoch": 1.0210325047801148, "percentage": 34.1, "elapsed_time": "0:48:54", "remaining_time": "1:34:30"}
+{"current_steps": 179, "total_steps": 522, "loss": 0.3977, "lr": 3.328942946877644e-05, "epoch": 1.0267686424474187, "percentage": 34.29, "elapsed_time": "0:49:09", "remaining_time": "1:34:12"}
+{"current_steps": 180, "total_steps": 522, "loss": 0.4345, "lr": 3.318901458724885e-05, "epoch": 1.0325047801147227, "percentage": 34.48, "elapsed_time": "0:49:25", "remaining_time": "1:33:53"}
+{"current_steps": 181, "total_steps": 522, "loss": 0.3577, "lr": 3.308800791958785e-05, "epoch": 1.0382409177820269, "percentage": 34.67, "elapsed_time": "0:49:42", "remaining_time": "1:33:38"}
+{"current_steps": 182, "total_steps": 522, "loss": 0.4369, "lr": 3.2986413997924706e-05, "epoch": 1.0439770554493308, "percentage": 34.87, "elapsed_time": "0:49:57", "remaining_time": "1:33:19"}
+{"current_steps": 183, "total_steps": 522, "loss": 0.4328, "lr": 3.2884237380740545e-05, "epoch": 1.0497131931166348, "percentage": 35.06, "elapsed_time": "0:50:12", "remaining_time": "1:33:00"}
+{"current_steps": 184, "total_steps": 522, "loss": 0.4174, "lr": 3.278148265266182e-05, "epoch": 1.0554493307839388, "percentage": 35.25, "elapsed_time": "0:50:29", "remaining_time": "1:32:45"}
+{"current_steps": 185, "total_steps": 522, "loss": 0.3828, "lr": 3.267815442425459e-05, "epoch": 1.0611854684512427, "percentage": 35.44, "elapsed_time": "0:50:44", "remaining_time": "1:32:25"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025ade32f1d76ca5dc9b4f9e4ac4dc65fb59dfce082375524ee184f090faffdb
+size 7160