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:b3325e202d46ce2dc09a3fce904cbf30d71c841a867d1754b0a75cd5d6ea616e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0fb27b38cff846ac913426fe8fe63768c94a8e457f56d2f933165f1923798c5
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4046676ab578dd483ef7c66b60ab3674001120d5cda8a406a3f077e83da9aeda
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d5ca8cf143f5b8866e47489173c0f5d5c95f87cb14ff71e420604eb4635859
+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 +1,180 @@
+{"current_steps": 1, "total_steps": 312, "loss": 0.8336, "lr": 3.125e-07, "epoch": 0.009584664536741214, "percentage": 0.32, "elapsed_time": "0:00:20", "remaining_time": "1:46:26"}
+{"current_steps": 2, "total_steps": 312, "loss": 0.8843, "lr": 6.25e-07, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:00:37", "remaining_time": "1:37:08"}
+{"current_steps": 3, "total_steps": 312, "loss": 0.8479, "lr": 9.375000000000001e-07, "epoch": 0.02875399361022364, "percentage": 0.96, "elapsed_time": "0:00:53", "remaining_time": "1:31:15"}
+{"current_steps": 4, "total_steps": 312, "loss": 0.8791, "lr": 1.25e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:01:08", "remaining_time": "1:27:46"}
+{"current_steps": 5, "total_steps": 312, "loss": 0.9072, "lr": 1.5625e-06, "epoch": 0.04792332268370607, "percentage": 1.6, "elapsed_time": "0:01:25", "remaining_time": "1:27:33"}
+{"current_steps": 6, "total_steps": 312, "loss": 0.8949, "lr": 1.8750000000000003e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:01:41", "remaining_time": "1:26:05"}
+{"current_steps": 7, "total_steps": 312, "loss": 0.8507, "lr": 2.1875000000000002e-06, "epoch": 0.0670926517571885, "percentage": 2.24, "elapsed_time": "0:01:58", "remaining_time": "1:26:14"}
+{"current_steps": 8, "total_steps": 312, "loss": 0.81, "lr": 2.5e-06, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:02:14", "remaining_time": "1:25:16"}
+{"current_steps": 9, "total_steps": 312, "loss": 0.7747, "lr": 2.8125e-06, "epoch": 0.08626198083067092, "percentage": 2.88, "elapsed_time": "0:02:29", "remaining_time": "1:24:07"}
+{"current_steps": 10, "total_steps": 312, "loss": 0.7642, "lr": 3.125e-06, "epoch": 0.09584664536741214, "percentage": 3.21, "elapsed_time": "0:02:46", "remaining_time": "1:23:35"}
+{"current_steps": 11, "total_steps": 312, "loss": 0.7635, "lr": 3.4375e-06, "epoch": 0.10543130990415335, "percentage": 3.53, "elapsed_time": "0:03:01", "remaining_time": "1:22:51"}
+{"current_steps": 12, "total_steps": 312, "loss": 0.7144, "lr": 3.7500000000000005e-06, "epoch": 0.11501597444089456, "percentage": 3.85, "elapsed_time": "0:03:16", "remaining_time": "1:22:03"}
+{"current_steps": 13, "total_steps": 312, "loss": 0.7222, "lr": 4.0625000000000005e-06, "epoch": 0.12460063897763578, "percentage": 4.17, "elapsed_time": "0:03:34", "remaining_time": "1:22:17"}
+{"current_steps": 14, "total_steps": 312, "loss": 0.7088, "lr": 4.3750000000000005e-06, "epoch": 0.134185303514377, "percentage": 4.49, "elapsed_time": "0:03:49", "remaining_time": "1:21:19"}
+{"current_steps": 15, "total_steps": 312, "loss": 0.7256, "lr": 4.6875000000000004e-06, "epoch": 0.14376996805111822, "percentage": 4.81, "elapsed_time": "0:04:04", "remaining_time": "1:20:40"}
+{"current_steps": 16, "total_steps": 312, "loss": 0.6711, "lr": 5e-06, "epoch": 0.15335463258785942, "percentage": 5.13, "elapsed_time": "0:04:17", "remaining_time": "1:19:22"}
+{"current_steps": 17, "total_steps": 312, "loss": 0.6688, "lr": 5.3125e-06, "epoch": 0.16293929712460065, "percentage": 5.45, "elapsed_time": "0:04:30", "remaining_time": "1:18:22"}
+{"current_steps": 18, "total_steps": 312, "loss": 0.6681, "lr": 5.625e-06, "epoch": 0.17252396166134185, "percentage": 5.77, "elapsed_time": "0:04:48", "remaining_time": "1:18:30"}
+{"current_steps": 19, "total_steps": 312, "loss": 0.6903, "lr": 5.9375e-06, "epoch": 0.18210862619808307, "percentage": 6.09, "elapsed_time": "0:05:05", "remaining_time": "1:18:25"}
+{"current_steps": 20, "total_steps": 312, "loss": 0.6458, "lr": 6.25e-06, "epoch": 0.19169329073482427, "percentage": 6.41, "elapsed_time": "0:05:20", "remaining_time": "1:17:55"}
+{"current_steps": 21, "total_steps": 312, "loss": 0.6478, "lr": 6.5625e-06, "epoch": 0.2012779552715655, "percentage": 6.73, "elapsed_time": "0:05:39", "remaining_time": "1:18:17"}
+{"current_steps": 22, "total_steps": 312, "loss": 0.6561, "lr": 6.875e-06, "epoch": 0.2108626198083067, "percentage": 7.05, "elapsed_time": "0:05:55", "remaining_time": "1:18:08"}
+{"current_steps": 23, "total_steps": 312, "loss": 0.6412, "lr": 7.1875e-06, "epoch": 0.22044728434504793, "percentage": 7.37, "elapsed_time": "0:06:13", "remaining_time": "1:18:12"}
+{"current_steps": 24, "total_steps": 312, "loss": 0.5841, "lr": 7.500000000000001e-06, "epoch": 0.23003194888178913, "percentage": 7.69, "elapsed_time": "0:06:29", "remaining_time": "1:17:51"}
+{"current_steps": 25, "total_steps": 312, "loss": 0.6154, "lr": 7.8125e-06, "epoch": 0.23961661341853036, "percentage": 8.01, "elapsed_time": "0:06:47", "remaining_time": "1:17:55"}
+{"current_steps": 26, "total_steps": 312, "loss": 0.612, "lr": 8.125000000000001e-06, "epoch": 0.24920127795527156, "percentage": 8.33, "elapsed_time": "0:07:05", "remaining_time": "1:18:05"}
+{"current_steps": 27, "total_steps": 312, "loss": 0.5846, "lr": 8.4375e-06, "epoch": 0.25878594249201275, "percentage": 8.65, "elapsed_time": "0:07:21", "remaining_time": "1:17:35"}
+{"current_steps": 28, "total_steps": 312, "loss": 0.6023, "lr": 8.750000000000001e-06, "epoch": 0.268370607028754, "percentage": 8.97, "elapsed_time": "0:07:36", "remaining_time": "1:17:09"}
+{"current_steps": 29, "total_steps": 312, "loss": 0.6173, "lr": 9.0625e-06, "epoch": 0.2779552715654952, "percentage": 9.29, "elapsed_time": "0:07:51", "remaining_time": "1:16:40"}
+{"current_steps": 30, "total_steps": 312, "loss": 0.5681, "lr": 9.375000000000001e-06, "epoch": 0.28753993610223644, "percentage": 9.62, "elapsed_time": "0:08:07", "remaining_time": "1:16:25"}
+{"current_steps": 31, "total_steps": 312, "loss": 0.6093, "lr": 9.6875e-06, "epoch": 0.2971246006389776, "percentage": 9.94, "elapsed_time": "0:08:24", "remaining_time": "1:16:15"}
+{"current_steps": 32, "total_steps": 312, "loss": 0.6073, "lr": 1e-05, "epoch": 0.30670926517571884, "percentage": 10.26, "elapsed_time": "0:08:39", "remaining_time": "1:15:49"}
+{"current_steps": 33, "total_steps": 312, "loss": 0.5769, "lr": 9.999685283773504e-06, "epoch": 0.31629392971246006, "percentage": 10.58, "elapsed_time": "0:08:56", "remaining_time": "1:15:38"}
+{"current_steps": 34, "total_steps": 312, "loss": 0.5687, "lr": 9.998741174712534e-06, "epoch": 0.3258785942492013, "percentage": 10.9, "elapsed_time": "0:09:13", "remaining_time": "1:15:21"}
+{"current_steps": 35, "total_steps": 312, "loss": 0.5418, "lr": 9.997167791667668e-06, "epoch": 0.3354632587859425, "percentage": 11.22, "elapsed_time": "0:09:28", "remaining_time": "1:14:59"}
+{"current_steps": 36, "total_steps": 312, "loss": 0.5795, "lr": 9.994965332706574e-06, "epoch": 0.3450479233226837, "percentage": 11.54, "elapsed_time": "0:09:45", "remaining_time": "1:14:49"}
+{"current_steps": 37, "total_steps": 312, "loss": 0.542, "lr": 9.992134075089085e-06, "epoch": 0.3546325878594249, "percentage": 11.86, "elapsed_time": "0:09:58", "remaining_time": "1:14:07"}
+{"current_steps": 38, "total_steps": 312, "loss": 0.5782, "lr": 9.98867437523228e-06, "epoch": 0.36421725239616615, "percentage": 12.18, "elapsed_time": "0:10:13", "remaining_time": "1:13:46"}
+{"current_steps": 39, "total_steps": 312, "loss": 0.5631, "lr": 9.984586668665641e-06, "epoch": 0.3738019169329074, "percentage": 12.5, "elapsed_time": "0:10:27", "remaining_time": "1:13:12"}
+{"current_steps": 40, "total_steps": 312, "loss": 0.5282, "lr": 9.979871469976197e-06, "epoch": 0.38338658146964855, "percentage": 12.82, "elapsed_time": "0:10:44", "remaining_time": "1:13:02"}
+{"current_steps": 41, "total_steps": 312, "loss": 0.529, "lr": 9.974529372743762e-06, "epoch": 0.3929712460063898, "percentage": 13.14, "elapsed_time": "0:11:01", "remaining_time": "1:12:54"}
+{"current_steps": 42, "total_steps": 312, "loss": 0.5579, "lr": 9.968561049466214e-06, "epoch": 0.402555910543131, "percentage": 13.46, "elapsed_time": "0:11:17", "remaining_time": "1:12:34"}
+{"current_steps": 43, "total_steps": 312, "loss": 0.5705, "lr": 9.961967251474823e-06, "epoch": 0.41214057507987223, "percentage": 13.78, "elapsed_time": "0:11:32", "remaining_time": "1:12:13"}
+{"current_steps": 44, "total_steps": 312, "loss": 0.5643, "lr": 9.954748808839675e-06, "epoch": 0.4217252396166134, "percentage": 14.1, "elapsed_time": "0:11:47", "remaining_time": "1:11:50"}
+{"current_steps": 45, "total_steps": 312, "loss": 0.5619, "lr": 9.946906630265184e-06, "epoch": 0.43130990415335463, "percentage": 14.42, "elapsed_time": "0:12:05", "remaining_time": "1:11:45"}
+{"current_steps": 46, "total_steps": 312, "loss": 0.5449, "lr": 9.938441702975689e-06, "epoch": 0.44089456869009586, "percentage": 14.74, "elapsed_time": "0:12:24", "remaining_time": "1:11:42"}
+{"current_steps": 47, "total_steps": 312, "loss": 0.5598, "lr": 9.92935509259118e-06, "epoch": 0.4504792332268371, "percentage": 15.06, "elapsed_time": "0:12:41", "remaining_time": "1:11:35"}
+{"current_steps": 48, "total_steps": 312, "loss": 0.5327, "lr": 9.91964794299315e-06, "epoch": 0.46006389776357826, "percentage": 15.38, "elapsed_time": "0:12:58", "remaining_time": "1:11:20"}
+{"current_steps": 49, "total_steps": 312, "loss": 0.5218, "lr": 9.909321476180594e-06, "epoch": 0.4696485623003195, "percentage": 15.71, "elapsed_time": "0:13:10", "remaining_time": "1:10:43"}
+{"current_steps": 50, "total_steps": 312, "loss": 0.5566, "lr": 9.898376992116179e-06, "epoch": 0.4792332268370607, "percentage": 16.03, "elapsed_time": "0:13:26", "remaining_time": "1:10:24"}
+{"current_steps": 51, "total_steps": 312, "loss": 0.5538, "lr": 9.886815868562596e-06, "epoch": 0.48881789137380194, "percentage": 16.35, "elapsed_time": "0:13:42", "remaining_time": "1:10:09"}
+{"current_steps": 52, "total_steps": 312, "loss": 0.581, "lr": 9.874639560909118e-06, "epoch": 0.4984025559105431, "percentage": 16.67, "elapsed_time": "0:13:58", "remaining_time": "1:09:51"}
+{"current_steps": 53, "total_steps": 312, "loss": 0.5386, "lr": 9.861849601988384e-06, "epoch": 0.5079872204472844, "percentage": 16.99, "elapsed_time": "0:14:14", "remaining_time": "1:09:35"}
+{"current_steps": 54, "total_steps": 312, "loss": 0.5299, "lr": 9.848447601883436e-06, "epoch": 0.5175718849840255, "percentage": 17.31, "elapsed_time": "0:14:28", "remaining_time": "1:09:10"}
+{"current_steps": 55, "total_steps": 312, "loss": 0.5186, "lr": 9.834435247725032e-06, "epoch": 0.5271565495207667, "percentage": 17.63, "elapsed_time": "0:14:45", "remaining_time": "1:08:58"}
+{"current_steps": 56, "total_steps": 312, "loss": 0.5103, "lr": 9.819814303479268e-06, "epoch": 0.536741214057508, "percentage": 17.95, "elapsed_time": "0:15:00", "remaining_time": "1:08:36"}
+{"current_steps": 57, "total_steps": 312, "loss": 0.5412, "lr": 9.804586609725499e-06, "epoch": 0.5463258785942492, "percentage": 18.27, "elapsed_time": "0:15:18", "remaining_time": "1:08:31"}
+{"current_steps": 58, "total_steps": 312, "loss": 0.578, "lr": 9.788754083424654e-06, "epoch": 0.5559105431309904, "percentage": 18.59, "elapsed_time": "0:15:33", "remaining_time": "1:08:06"}
+{"current_steps": 59, "total_steps": 312, "loss": 0.5451, "lr": 9.772318717677905e-06, "epoch": 0.5654952076677316, "percentage": 18.91, "elapsed_time": "0:15:47", "remaining_time": "1:07:42"}
+{"current_steps": 60, "total_steps": 312, "loss": 0.5469, "lr": 9.755282581475769e-06, "epoch": 0.5750798722044729, "percentage": 19.23, "elapsed_time": "0:16:03", "remaining_time": "1:07:28"}
+{"current_steps": 61, "total_steps": 312, "loss": 0.5323, "lr": 9.737647819437645e-06, "epoch": 0.5846645367412141, "percentage": 19.55, "elapsed_time": "0:16:17", "remaining_time": "1:07:03"}
+{"current_steps": 62, "total_steps": 312, "loss": 0.5046, "lr": 9.719416651541839e-06, "epoch": 0.5942492012779552, "percentage": 19.87, "elapsed_time": "0:16:30", "remaining_time": "1:06:32"}
+{"current_steps": 63, "total_steps": 312, "loss": 0.5207, "lr": 9.700591372846096e-06, "epoch": 0.6038338658146964, "percentage": 20.19, "elapsed_time": "0:16:46", "remaining_time": "1:06:16"}
+{"current_steps": 64, "total_steps": 312, "loss": 0.5441, "lr": 9.681174353198687e-06, "epoch": 0.6134185303514377, "percentage": 20.51, "elapsed_time": "0:17:02", "remaining_time": "1:06:03"}
+{"current_steps": 65, "total_steps": 312, "loss": 0.5372, "lr": 9.661168036940071e-06, "epoch": 0.6230031948881789, "percentage": 20.83, "elapsed_time": "0:17:17", "remaining_time": "1:05:42"}
+{"current_steps": 66, "total_steps": 312, "loss": 0.5293, "lr": 9.640574942595195e-06, "epoch": 0.6325878594249201, "percentage": 21.15, "elapsed_time": "0:17:34", "remaining_time": "1:05:29"}
+{"current_steps": 67, "total_steps": 312, "loss": 0.533, "lr": 9.619397662556434e-06, "epoch": 0.6421725239616614, "percentage": 21.47, "elapsed_time": "0:17:49", "remaining_time": "1:05:11"}
+{"current_steps": 68, "total_steps": 312, "loss": 0.525, "lr": 9.597638862757255e-06, "epoch": 0.6517571884984026, "percentage": 21.79, "elapsed_time": "0:18:05", "remaining_time": "1:04:55"}
+{"current_steps": 69, "total_steps": 312, "loss": 0.5145, "lr": 9.5753012823366e-06, "epoch": 0.6613418530351438, "percentage": 22.12, "elapsed_time": "0:18:21", "remaining_time": "1:04:39"}
+{"current_steps": 70, "total_steps": 312, "loss": 0.514, "lr": 9.552387733294081e-06, "epoch": 0.670926517571885, "percentage": 22.44, "elapsed_time": "0:18:34", "remaining_time": "1:04:13"}
+{"current_steps": 71, "total_steps": 312, "loss": 0.5372, "lr": 9.528901100135971e-06, "epoch": 0.6805111821086262, "percentage": 22.76, "elapsed_time": "0:18:51", "remaining_time": "1:03:59"}
+{"current_steps": 72, "total_steps": 312, "loss": 0.5373, "lr": 9.504844339512096e-06, "epoch": 0.6900958466453674, "percentage": 23.08, "elapsed_time": "0:19:07", "remaining_time": "1:03:44"}
+{"current_steps": 73, "total_steps": 312, "loss": 0.5042, "lr": 9.480220479843627e-06, "epoch": 0.6996805111821086, "percentage": 23.4, "elapsed_time": "0:19:23", "remaining_time": "1:03:30"}
+{"current_steps": 74, "total_steps": 312, "loss": 0.5333, "lr": 9.45503262094184e-06, "epoch": 0.7092651757188498, "percentage": 23.72, "elapsed_time": "0:19:40", "remaining_time": "1:03:18"}
+{"current_steps": 75, "total_steps": 312, "loss": 0.5325, "lr": 9.4292839336179e-06, "epoch": 0.7188498402555911, "percentage": 24.04, "elapsed_time": "0:19:55", "remaining_time": "1:02:56"}
+{"current_steps": 76, "total_steps": 312, "loss": 0.51, "lr": 9.40297765928369e-06, "epoch": 0.7284345047923323, "percentage": 24.36, "elapsed_time": "0:20:12", "remaining_time": "1:02:45"}
+{"current_steps": 77, "total_steps": 312, "loss": 0.5051, "lr": 9.376117109543769e-06, "epoch": 0.7380191693290735, "percentage": 24.68, "elapsed_time": "0:20:29", "remaining_time": "1:02:33"}
+{"current_steps": 78, "total_steps": 312, "loss": 0.5336, "lr": 9.348705665778479e-06, "epoch": 0.7476038338658147, "percentage": 25.0, "elapsed_time": "0:20:45", "remaining_time": "1:02:15"}
+{"current_steps": 79, "total_steps": 312, "loss": 0.5639, "lr": 9.320746778718274e-06, "epoch": 0.7571884984025559, "percentage": 25.32, "elapsed_time": "0:21:03", "remaining_time": "1:02:05"}
+{"current_steps": 80, "total_steps": 312, "loss": 0.5023, "lr": 9.292243968009332e-06, "epoch": 0.7667731629392971, "percentage": 25.64, "elapsed_time": "0:21:20", "remaining_time": "1:01:54"}
+{"current_steps": 81, "total_steps": 312, "loss": 0.5141, "lr": 9.263200821770462e-06, "epoch": 0.7763578274760383, "percentage": 25.96, "elapsed_time": "0:21:35", "remaining_time": "1:01:35"}
+{"current_steps": 82, "total_steps": 312, "loss": 0.5275, "lr": 9.233620996141421e-06, "epoch": 0.7859424920127795, "percentage": 26.28, "elapsed_time": "0:21:51", "remaining_time": "1:01:18"}
+{"current_steps": 83, "total_steps": 312, "loss": 0.5452, "lr": 9.203508214822652e-06, "epoch": 0.7955271565495208, "percentage": 26.6, "elapsed_time": "0:22:08", "remaining_time": "1:01:05"}
+{"current_steps": 84, "total_steps": 312, "loss": 0.5231, "lr": 9.172866268606514e-06, "epoch": 0.805111821086262, "percentage": 26.92, "elapsed_time": "0:22:24", "remaining_time": "1:00:48"}
+{"current_steps": 85, "total_steps": 312, "loss": 0.5276, "lr": 9.141699014900084e-06, "epoch": 0.8146964856230032, "percentage": 27.24, "elapsed_time": "0:22:40", "remaining_time": "1:00:34"}
+{"current_steps": 86, "total_steps": 312, "loss": 0.4883, "lr": 9.110010377239552e-06, "epoch": 0.8242811501597445, "percentage": 27.56, "elapsed_time": "0:22:57", "remaining_time": "1:00:20"}
+{"current_steps": 87, "total_steps": 312, "loss": 0.5079, "lr": 9.077804344796302e-06, "epoch": 0.8338658146964856, "percentage": 27.88, "elapsed_time": "0:23:15", "remaining_time": "1:00:09"}
+{"current_steps": 88, "total_steps": 312, "loss": 0.5191, "lr": 9.045084971874738e-06, "epoch": 0.8434504792332268, "percentage": 28.21, "elapsed_time": "0:23:32", "remaining_time": "0:59:54"}
+{"current_steps": 89, "total_steps": 312, "loss": 0.5219, "lr": 9.011856377401891e-06, "epoch": 0.853035143769968, "percentage": 28.53, "elapsed_time": "0:23:45", "remaining_time": "0:59:32"}
+{"current_steps": 90, "total_steps": 312, "loss": 0.5026, "lr": 8.978122744408905e-06, "epoch": 0.8626198083067093, "percentage": 28.85, "elapsed_time": "0:24:03", "remaining_time": "0:59:20"}
+{"current_steps": 91, "total_steps": 312, "loss": 0.5203, "lr": 8.943888319504456e-06, "epoch": 0.8722044728434505, "percentage": 29.17, "elapsed_time": "0:24:17", "remaining_time": "0:59:00"}
+{"current_steps": 92, "total_steps": 312, "loss": 0.5554, "lr": 8.90915741234015e-06, "epoch": 0.8817891373801917, "percentage": 29.49, "elapsed_time": "0:24:33", "remaining_time": "0:58:44"}
+{"current_steps": 93, "total_steps": 312, "loss": 0.5196, "lr": 8.873934395068006e-06, "epoch": 0.8913738019169329, "percentage": 29.81, "elapsed_time": "0:24:50", "remaining_time": "0:58:29"}
+{"current_steps": 94, "total_steps": 312, "loss": 0.5121, "lr": 8.838223701790057e-06, "epoch": 0.9009584664536742, "percentage": 30.13, "elapsed_time": "0:25:06", "remaining_time": "0:58:14"}
+{"current_steps": 95, "total_steps": 312, "loss": 0.5153, "lr": 8.802029828000157e-06, "epoch": 0.9105431309904153, "percentage": 30.45, "elapsed_time": "0:25:24", "remaining_time": "0:58:02"}
+{"current_steps": 96, "total_steps": 312, "loss": 0.5301, "lr": 8.765357330018056e-06, "epoch": 0.9201277955271565, "percentage": 30.77, "elapsed_time": "0:25:38", "remaining_time": "0:57:42"}
+{"current_steps": 97, "total_steps": 312, "loss": 0.5391, "lr": 8.728210824415829e-06, "epoch": 0.9297124600638977, "percentage": 31.09, "elapsed_time": "0:25:56", "remaining_time": "0:57:30"}
+{"current_steps": 98, "total_steps": 312, "loss": 0.4876, "lr": 8.690594987436705e-06, "epoch": 0.939297124600639, "percentage": 31.41, "elapsed_time": "0:26:11", "remaining_time": "0:57:11"}
+{"current_steps": 99, "total_steps": 312, "loss": 0.4977, "lr": 8.652514554406388e-06, "epoch": 0.9488817891373802, "percentage": 31.73, "elapsed_time": "0:26:27", "remaining_time": "0:56:56"}
+{"current_steps": 100, "total_steps": 312, "loss": 0.5305, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:26:44", "remaining_time": "0:56:41"}
+{"current_steps": 101, "total_steps": 312, "loss": 0.5434, "lr": 8.574979133323378e-06, "epoch": 0.9680511182108626, "percentage": 32.37, "elapsed_time": "0:27:01", "remaining_time": "0:56:26"}
+{"current_steps": 102, "total_steps": 312, "loss": 0.545, "lr": 8.535533905932739e-06, "epoch": 0.9776357827476039, "percentage": 32.69, "elapsed_time": "0:27:16", "remaining_time": "0:56:08"}
+{"current_steps": 103, "total_steps": 312, "loss": 0.4969, "lr": 8.495643602586287e-06, "epoch": 0.987220447284345, "percentage": 33.01, "elapsed_time": "0:27:33", "remaining_time": "0:55:54"}
+{"current_steps": 104, "total_steps": 312, "loss": 0.5166, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:27:50", "remaining_time": "0:55:40"}
+{"current_steps": 105, "total_steps": 312, "loss": 0.8209, "lr": 8.414547910024035e-06, "epoch": 1.0063897763578276, "percentage": 33.65, "elapsed_time": "0:29:07", "remaining_time": "0:57:24"}
+{"current_steps": 106, "total_steps": 312, "loss": 0.5144, "lr": 8.373352729660373e-06, "epoch": 1.0159744408945688, "percentage": 33.97, "elapsed_time": "0:29:23", "remaining_time": "0:57:06"}
+{"current_steps": 107, "total_steps": 312, "loss": 0.4628, "lr": 8.331732889760021e-06, "epoch": 1.0255591054313098, "percentage": 34.29, "elapsed_time": "0:29:39", "remaining_time": "0:56:49"}
+{"current_steps": 108, "total_steps": 312, "loss": 0.5073, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:29:56", "remaining_time": "0:56:32"}
+{"current_steps": 109, "total_steps": 312, "loss": 0.4536, "lr": 8.247240241650918e-06, "epoch": 1.0447284345047922, "percentage": 34.94, "elapsed_time": "0:30:12", "remaining_time": "0:56:15"}
+{"current_steps": 110, "total_steps": 312, "loss": 0.4868, "lr": 8.204378069925121e-06, "epoch": 1.0543130990415335, "percentage": 35.26, "elapsed_time": "0:30:28", "remaining_time": "0:55:57"}
+{"current_steps": 111, "total_steps": 312, "loss": 0.4985, "lr": 8.16111251028955e-06, "epoch": 1.0638977635782747, "percentage": 35.58, "elapsed_time": "0:30:43", "remaining_time": "0:55:38"}
+{"current_steps": 112, "total_steps": 312, "loss": 0.4672, "lr": 8.117449009293668e-06, "epoch": 1.073482428115016, "percentage": 35.9, "elapsed_time": "0:31:01", "remaining_time": "0:55:24"}
+{"current_steps": 113, "total_steps": 312, "loss": 0.4868, "lr": 8.073393063582386e-06, "epoch": 1.0830670926517572, "percentage": 36.22, "elapsed_time": "0:31:17", "remaining_time": "0:55:06"}
+{"current_steps": 114, "total_steps": 312, "loss": 0.4806, "lr": 8.0289502192041e-06, "epoch": 1.0926517571884984, "percentage": 36.54, "elapsed_time": "0:31:34", "remaining_time": "0:54:49"}
+{"current_steps": 115, "total_steps": 312, "loss": 0.4795, "lr": 7.984126070912519e-06, "epoch": 1.1022364217252396, "percentage": 36.86, "elapsed_time": "0:31:52", "remaining_time": "0:54:37"}
+{"current_steps": 116, "total_steps": 312, "loss": 0.4551, "lr": 7.938926261462366e-06, "epoch": 1.1118210862619808, "percentage": 37.18, "elapsed_time": "0:32:07", "remaining_time": "0:54:16"}
+{"current_steps": 117, "total_steps": 312, "loss": 0.5244, "lr": 7.89335648089903e-06, "epoch": 1.121405750798722, "percentage": 37.5, "elapsed_time": "0:32:23", "remaining_time": "0:53:58"}
+{"current_steps": 118, "total_steps": 312, "loss": 0.5057, "lr": 7.84742246584226e-06, "epoch": 1.1309904153354633, "percentage": 37.82, "elapsed_time": "0:32:38", "remaining_time": "0:53:40"}
+{"current_steps": 119, "total_steps": 312, "loss": 0.4386, "lr": 7.801129998764014e-06, "epoch": 1.1405750798722045, "percentage": 38.14, "elapsed_time": "0:32:53", "remaining_time": "0:53:20"}
+{"current_steps": 120, "total_steps": 312, "loss": 0.5037, "lr": 7.754484907260513e-06, "epoch": 1.1501597444089458, "percentage": 38.46, "elapsed_time": "0:33:10", "remaining_time": "0:53:04"}
+{"current_steps": 121, "total_steps": 312, "loss": 0.4854, "lr": 7.70749306331863e-06, "epoch": 1.159744408945687, "percentage": 38.78, "elapsed_time": "0:33:26", "remaining_time": "0:52:47"}
+{"current_steps": 122, "total_steps": 312, "loss": 0.4561, "lr": 7.660160382576683e-06, "epoch": 1.1693290734824282, "percentage": 39.1, "elapsed_time": "0:33:39", "remaining_time": "0:52:25"}
+{"current_steps": 123, "total_steps": 312, "loss": 0.4612, "lr": 7.612492823579744e-06, "epoch": 1.1789137380191694, "percentage": 39.42, "elapsed_time": "0:33:55", "remaining_time": "0:52:07"}
+{"current_steps": 124, "total_steps": 312, "loss": 0.4712, "lr": 7.564496387029532e-06, "epoch": 1.1884984025559104, "percentage": 39.74, "elapsed_time": "0:34:11", "remaining_time": "0:51:50"}
+{"current_steps": 125, "total_steps": 312, "loss": 0.5056, "lr": 7.516177115029002e-06, "epoch": 1.1980830670926517, "percentage": 40.06, "elapsed_time": "0:34:29", "remaining_time": "0:51:35"}
+{"current_steps": 126, "total_steps": 312, "loss": 0.4621, "lr": 7.467541090321735e-06, "epoch": 1.207667731629393, "percentage": 40.38, "elapsed_time": "0:34:46", "remaining_time": "0:51:20"}
+{"current_steps": 127, "total_steps": 312, "loss": 0.4798, "lr": 7.4185944355261996e-06, "epoch": 1.2172523961661341, "percentage": 40.71, "elapsed_time": "0:35:04", "remaining_time": "0:51:05"}
+{"current_steps": 128, "total_steps": 312, "loss": 0.4532, "lr": 7.369343312364994e-06, "epoch": 1.2268370607028753, "percentage": 41.03, "elapsed_time": "0:35:20", "remaining_time": "0:50:48"}
+{"current_steps": 129, "total_steps": 312, "loss": 0.4666, "lr": 7.319793920889171e-06, "epoch": 1.2364217252396166, "percentage": 41.35, "elapsed_time": "0:35:36", "remaining_time": "0:50:31"}
+{"current_steps": 130, "total_steps": 312, "loss": 0.4718, "lr": 7.269952498697734e-06, "epoch": 1.2460063897763578, "percentage": 41.67, "elapsed_time": "0:35:53", "remaining_time": "0:50:14"}
+{"current_steps": 131, "total_steps": 312, "loss": 0.4614, "lr": 7.219825320152411e-06, "epoch": 1.255591054313099, "percentage": 41.99, "elapsed_time": "0:36:09", "remaining_time": "0:49:58"}
+{"current_steps": 132, "total_steps": 312, "loss": 0.4763, "lr": 7.169418695587791e-06, "epoch": 1.2651757188498403, "percentage": 42.31, "elapsed_time": "0:36:25", "remaining_time": "0:49:40"}
+{"current_steps": 133, "total_steps": 312, "loss": 0.4538, "lr": 7.118738970516944e-06, "epoch": 1.2747603833865815, "percentage": 42.63, "elapsed_time": "0:36:42", "remaining_time": "0:49:24"}
+{"current_steps": 134, "total_steps": 312, "loss": 0.4902, "lr": 7.067792524832604e-06, "epoch": 1.2843450479233227, "percentage": 42.95, "elapsed_time": "0:36:59", "remaining_time": "0:49:08"}
+{"current_steps": 135, "total_steps": 312, "loss": 0.4953, "lr": 7.016585772004026e-06, "epoch": 1.293929712460064, "percentage": 43.27, "elapsed_time": "0:37:17", "remaining_time": "0:48:53"}
+{"current_steps": 136, "total_steps": 312, "loss": 0.4589, "lr": 6.965125158269619e-06, "epoch": 1.3035143769968052, "percentage": 43.59, "elapsed_time": "0:37:33", "remaining_time": "0:48:36"}
+{"current_steps": 137, "total_steps": 312, "loss": 0.4767, "lr": 6.913417161825449e-06, "epoch": 1.3130990415335464, "percentage": 43.91, "elapsed_time": "0:37:50", "remaining_time": "0:48:20"}
+{"current_steps": 138, "total_steps": 312, "loss": 0.4823, "lr": 6.8614682920097265e-06, "epoch": 1.3226837060702876, "percentage": 44.23, "elapsed_time": "0:38:03", "remaining_time": "0:47:59"}
+{"current_steps": 139, "total_steps": 312, "loss": 0.4146, "lr": 6.809285088483361e-06, "epoch": 1.3322683706070286, "percentage": 44.55, "elapsed_time": "0:38:17", "remaining_time": "0:47:39"}
+{"current_steps": 140, "total_steps": 312, "loss": 0.5314, "lr": 6.7568741204067145e-06, "epoch": 1.34185303514377, "percentage": 44.87, "elapsed_time": "0:38:35", "remaining_time": "0:47:24"}
+{"current_steps": 141, "total_steps": 312, "loss": 0.4044, "lr": 6.704241985612625e-06, "epoch": 1.351437699680511, "percentage": 45.19, "elapsed_time": "0:38:50", "remaining_time": "0:47:06"}
+{"current_steps": 142, "total_steps": 312, "loss": 0.5233, "lr": 6.651395309775837e-06, "epoch": 1.3610223642172525, "percentage": 45.51, "elapsed_time": "0:39:03", "remaining_time": "0:46:45"}
+{"current_steps": 143, "total_steps": 312, "loss": 0.4586, "lr": 6.598340745578908e-06, "epoch": 1.3706070287539935, "percentage": 45.83, "elapsed_time": "0:39:18", "remaining_time": "0:46:27"}
+{"current_steps": 144, "total_steps": 312, "loss": 0.4664, "lr": 6.545084971874738e-06, "epoch": 1.3801916932907348, "percentage": 46.15, "elapsed_time": "0:39:32", "remaining_time": "0:46:08"}
+{"current_steps": 145, "total_steps": 312, "loss": 0.4963, "lr": 6.491634692845781e-06, "epoch": 1.389776357827476, "percentage": 46.47, "elapsed_time": "0:39:48", "remaining_time": "0:45:51"}
+{"current_steps": 146, "total_steps": 312, "loss": 0.4546, "lr": 6.437996637160086e-06, "epoch": 1.3993610223642172, "percentage": 46.79, "elapsed_time": "0:40:04", "remaining_time": "0:45:33"}
+{"current_steps": 147, "total_steps": 312, "loss": 0.4916, "lr": 6.384177557124247e-06, "epoch": 1.4089456869009584, "percentage": 47.12, "elapsed_time": "0:40:21", "remaining_time": "0:45:18"}
+{"current_steps": 148, "total_steps": 312, "loss": 0.4555, "lr": 6.330184227833376e-06, "epoch": 1.4185303514376997, "percentage": 47.44, "elapsed_time": "0:40:38", "remaining_time": "0:45:01"}
+{"current_steps": 149, "total_steps": 312, "loss": 0.4712, "lr": 6.276023446318214e-06, "epoch": 1.428115015974441, "percentage": 47.76, "elapsed_time": "0:40:54", "remaining_time": "0:44:45"}
+{"current_steps": 150, "total_steps": 312, "loss": 0.4373, "lr": 6.2217020306894705e-06, "epoch": 1.4376996805111821, "percentage": 48.08, "elapsed_time": "0:41:12", "remaining_time": "0:44:29"}
+{"current_steps": 151, "total_steps": 312, "loss": 0.4535, "lr": 6.1672268192795285e-06, "epoch": 1.4472843450479234, "percentage": 48.4, "elapsed_time": "0:41:28", "remaining_time": "0:44:13"}
+{"current_steps": 152, "total_steps": 312, "loss": 0.4811, "lr": 6.112604669781572e-06, "epoch": 1.4568690095846646, "percentage": 48.72, "elapsed_time": "0:41:42", "remaining_time": "0:43:53"}
+{"current_steps": 153, "total_steps": 312, "loss": 0.4644, "lr": 6.057842458386315e-06, "epoch": 1.4664536741214058, "percentage": 49.04, "elapsed_time": "0:41:58", "remaining_time": "0:43:37"}
+{"current_steps": 154, "total_steps": 312, "loss": 0.4603, "lr": 6.002947078916365e-06, "epoch": 1.476038338658147, "percentage": 49.36, "elapsed_time": "0:42:13", "remaining_time": "0:43:19"}
+{"current_steps": 155, "total_steps": 312, "loss": 0.4655, "lr": 5.947925441958393e-06, "epoch": 1.4856230031948883, "percentage": 49.68, "elapsed_time": "0:42:29", "remaining_time": "0:43:02"}
+{"current_steps": 156, "total_steps": 312, "loss": 0.4542, "lr": 5.892784473993184e-06, "epoch": 1.4952076677316293, "percentage": 50.0, "elapsed_time": "0:42:47", "remaining_time": "0:42:47"}
+{"current_steps": 157, "total_steps": 312, "loss": 0.5096, "lr": 5.837531116523683e-06, "epoch": 1.5047923322683707, "percentage": 50.32, "elapsed_time": "0:43:02", "remaining_time": "0:42:29"}
+{"current_steps": 158, "total_steps": 312, "loss": 0.4623, "lr": 5.782172325201155e-06, "epoch": 1.5143769968051117, "percentage": 50.64, "elapsed_time": "0:43:19", "remaining_time": "0:42:13"}
+{"current_steps": 159, "total_steps": 312, "loss": 0.4551, "lr": 5.726715068949564e-06, "epoch": 1.5239616613418532, "percentage": 50.96, "elapsed_time": "0:43:34", "remaining_time": "0:41:55"}
+{"current_steps": 160, "total_steps": 312, "loss": 0.4562, "lr": 5.671166329088278e-06, "epoch": 1.5335463258785942, "percentage": 51.28, "elapsed_time": "0:43:51", "remaining_time": "0:41:39"}
+{"current_steps": 161, "total_steps": 312, "loss": 0.4738, "lr": 5.615533098453215e-06, "epoch": 1.5431309904153354, "percentage": 51.6, "elapsed_time": "0:44:08", "remaining_time": "0:41:24"}
+{"current_steps": 162, "total_steps": 312, "loss": 0.4533, "lr": 5.559822380516539e-06, "epoch": 1.5527156549520766, "percentage": 51.92, "elapsed_time": "0:44:26", "remaining_time": "0:41:08"}
+{"current_steps": 163, "total_steps": 312, "loss": 0.4458, "lr": 5.504041188505022e-06, "epoch": 1.5623003194888179, "percentage": 52.24, "elapsed_time": "0:44:40", "remaining_time": "0:40:50"}
+{"current_steps": 164, "total_steps": 312, "loss": 0.4793, "lr": 5.448196544517168e-06, "epoch": 1.571884984025559, "percentage": 52.56, "elapsed_time": "0:44:54", "remaining_time": "0:40:31"}
+{"current_steps": 165, "total_steps": 312, "loss": 0.4886, "lr": 5.392295478639226e-06, "epoch": 1.5814696485623003, "percentage": 52.88, "elapsed_time": "0:45:12", "remaining_time": "0:40:17"}
+{"current_steps": 166, "total_steps": 312, "loss": 0.4569, "lr": 5.336345028060199e-06, "epoch": 1.5910543130990416, "percentage": 53.21, "elapsed_time": "0:45:27", "remaining_time": "0:39:59"}
+{"current_steps": 167, "total_steps": 312, "loss": 0.4906, "lr": 5.2803522361859596e-06, "epoch": 1.6006389776357828, "percentage": 53.53, "elapsed_time": "0:45:43", "remaining_time": "0:39:42"}
+{"current_steps": 168, "total_steps": 312, "loss": 0.487, "lr": 5.224324151752575e-06, "epoch": 1.610223642172524, "percentage": 53.85, "elapsed_time": "0:45:59", "remaining_time": "0:39:24"}
+{"current_steps": 169, "total_steps": 312, "loss": 0.4719, "lr": 5.168267827938971e-06, "epoch": 1.619808306709265, "percentage": 54.17, "elapsed_time": "0:46:15", "remaining_time": "0:39:08"}
+{"current_steps": 170, "total_steps": 312, "loss": 0.4731, "lr": 5.112190321479026e-06, "epoch": 1.6293929712460065, "percentage": 54.49, "elapsed_time": "0:46:32", "remaining_time": "0:38:52"}
+{"current_steps": 171, "total_steps": 312, "loss": 0.4784, "lr": 5.05609869177323e-06, "epoch": 1.6389776357827475, "percentage": 54.81, "elapsed_time": "0:46:48", "remaining_time": "0:38:35"}
+{"current_steps": 172, "total_steps": 312, "loss": 0.4368, "lr": 5e-06, "epoch": 1.648562300319489, "percentage": 55.13, "elapsed_time": "0:47:05", "remaining_time": "0:38:20"}
+{"current_steps": 173, "total_steps": 312, "loss": 0.4993, "lr": 4.943901308226771e-06, "epoch": 1.65814696485623, "percentage": 55.45, "elapsed_time": "0:47:23", "remaining_time": "0:38:04"}
+{"current_steps": 174, "total_steps": 312, "loss": 0.4652, "lr": 4.887809678520976e-06, "epoch": 1.6677316293929714, "percentage": 55.77, "elapsed_time": "0:47:40", "remaining_time": "0:37:48"}
+{"current_steps": 175, "total_steps": 312, "loss": 0.4412, "lr": 4.831732172061032e-06, "epoch": 1.6773162939297124, "percentage": 56.09, "elapsed_time": "0:47:57", "remaining_time": "0:37:32"}
+{"current_steps": 176, "total_steps": 312, "loss": 0.5082, "lr": 4.775675848247427e-06, "epoch": 1.6869009584664538, "percentage": 56.41, "elapsed_time": "0:48:12", "remaining_time": "0:37:15"}
+{"current_steps": 177, "total_steps": 312, "loss": 0.4772, "lr": 4.719647763814041e-06, "epoch": 1.6964856230031948, "percentage": 56.73, "elapsed_time": "0:48:26", "remaining_time": "0:36:56"}
+{"current_steps": 178, "total_steps": 312, "loss": 0.4989, "lr": 4.663654971939802e-06, "epoch": 1.706070287539936, "percentage": 57.05, "elapsed_time": "0:48:43", "remaining_time": "0:36:41"}
+{"current_steps": 179, "total_steps": 312, "loss": 0.4302, "lr": 4.6077045213607765e-06, "epoch": 1.7156549520766773, "percentage": 57.37, "elapsed_time": "0:48:57", "remaining_time": "0:36:22"}
+{"current_steps": 180, "total_steps": 312, "loss": 0.4478, "lr": 4.551803455482833e-06, "epoch": 1.7252396166134185, "percentage": 57.69, "elapsed_time": "0:49:12", "remaining_time": "0:36:05"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a9a41df4ac12a2f39f435bc22f03e83c5222a2d13b4b54c9f4e3f6f090e80ff
+size 7288