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:fac88ce5215f6ed057e4124ef1eb268b5d14131277c0e7b2ef54c52d9ebdccc6
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699a5e8768798dae7c60f586b11fbe9c03921609c1b6d89b2e2d16f5787ae5b8
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c366ef25483b4d4ec1f1755aeae19ae4852b31e29275adc2e67e18d1b4d2cb41
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e365d210b56c0e0b928b27161a751e909346aeeeb9469aa6433c4e2cf6e2aa
+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 +1,165 @@
+{"current_steps": 1, "total_steps": 468, "loss": 0.8883, "lr": 8.510638297872341e-07, "epoch": 0.006389776357827476, "percentage": 0.21, "elapsed_time": "0:00:29", "remaining_time": "3:47:13"}
+{"current_steps": 2, "total_steps": 468, "loss": 0.8365, "lr": 1.7021276595744682e-06, "epoch": 0.012779552715654952, "percentage": 0.43, "elapsed_time": "0:00:52", "remaining_time": "3:24:21"}
+{"current_steps": 3, "total_steps": 468, "loss": 0.8853, "lr": 2.553191489361702e-06, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:01:14", "remaining_time": "3:13:17"}
+{"current_steps": 4, "total_steps": 468, "loss": 0.8686, "lr": 3.4042553191489363e-06, "epoch": 0.025559105431309903, "percentage": 0.85, "elapsed_time": "0:01:36", "remaining_time": "3:06:35"}
+{"current_steps": 5, "total_steps": 468, "loss": 0.792, "lr": 4.255319148936171e-06, "epoch": 0.03194888178913738, "percentage": 1.07, "elapsed_time": "0:01:59", "remaining_time": "3:04:33"}
+{"current_steps": 6, "total_steps": 468, "loss": 0.7978, "lr": 5.106382978723404e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:02:23", "remaining_time": "3:03:52"}
+{"current_steps": 7, "total_steps": 468, "loss": 0.7656, "lr": 5.957446808510638e-06, "epoch": 0.04472843450479233, "percentage": 1.5, "elapsed_time": "0:02:39", "remaining_time": "2:55:31"}
+{"current_steps": 8, "total_steps": 468, "loss": 0.7476, "lr": 6.808510638297873e-06, "epoch": 0.051118210862619806, "percentage": 1.71, "elapsed_time": "0:03:00", "remaining_time": "2:52:32"}
+{"current_steps": 9, "total_steps": 468, "loss": 0.751, "lr": 7.659574468085107e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:03:23", "remaining_time": "2:53:01"}
+{"current_steps": 10, "total_steps": 468, "loss": 0.7376, "lr": 8.510638297872341e-06, "epoch": 0.06389776357827476, "percentage": 2.14, "elapsed_time": "0:03:45", "remaining_time": "2:51:59"}
+{"current_steps": 11, "total_steps": 468, "loss": 0.6577, "lr": 9.361702127659576e-06, "epoch": 0.07028753993610223, "percentage": 2.35, "elapsed_time": "0:04:05", "remaining_time": "2:50:04"}
+{"current_steps": 12, "total_steps": 468, "loss": 0.7587, "lr": 1.0212765957446808e-05, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:04:25", "remaining_time": "2:48:09"}
+{"current_steps": 13, "total_steps": 468, "loss": 0.7102, "lr": 1.1063829787234044e-05, "epoch": 0.08306709265175719, "percentage": 2.78, "elapsed_time": "0:04:47", "remaining_time": "2:47:50"}
+{"current_steps": 14, "total_steps": 468, "loss": 0.6686, "lr": 1.1914893617021277e-05, "epoch": 0.08945686900958466, "percentage": 2.99, "elapsed_time": "0:05:11", "remaining_time": "2:48:07"}
+{"current_steps": 15, "total_steps": 468, "loss": 0.6976, "lr": 1.2765957446808513e-05, "epoch": 0.09584664536741214, "percentage": 3.21, "elapsed_time": "0:05:29", "remaining_time": "2:45:54"}
+{"current_steps": 16, "total_steps": 468, "loss": 0.66, "lr": 1.3617021276595745e-05, "epoch": 0.10223642172523961, "percentage": 3.42, "elapsed_time": "0:05:52", "remaining_time": "2:45:47"}
+{"current_steps": 17, "total_steps": 468, "loss": 0.6222, "lr": 1.4468085106382981e-05, "epoch": 0.10862619808306709, "percentage": 3.63, "elapsed_time": "0:06:12", "remaining_time": "2:44:47"}
+{"current_steps": 18, "total_steps": 468, "loss": 0.616, "lr": 1.5319148936170214e-05, "epoch": 0.11501597444089456, "percentage": 3.85, "elapsed_time": "0:06:36", "remaining_time": "2:45:05"}
+{"current_steps": 19, "total_steps": 468, "loss": 0.6394, "lr": 1.6170212765957446e-05, "epoch": 0.12140575079872204, "percentage": 4.06, "elapsed_time": "0:06:58", "remaining_time": "2:44:53"}
+{"current_steps": 20, "total_steps": 468, "loss": 0.5704, "lr": 1.7021276595744682e-05, "epoch": 0.12779552715654952, "percentage": 4.27, "elapsed_time": "0:07:21", "remaining_time": "2:44:56"}
+{"current_steps": 21, "total_steps": 468, "loss": 0.592, "lr": 1.7872340425531915e-05, "epoch": 0.134185303514377, "percentage": 4.49, "elapsed_time": "0:07:43", "remaining_time": "2:44:18"}
+{"current_steps": 22, "total_steps": 468, "loss": 0.6111, "lr": 1.872340425531915e-05, "epoch": 0.14057507987220447, "percentage": 4.7, "elapsed_time": "0:08:03", "remaining_time": "2:43:25"}
+{"current_steps": 23, "total_steps": 468, "loss": 0.6105, "lr": 1.9574468085106384e-05, "epoch": 0.14696485623003194, "percentage": 4.91, "elapsed_time": "0:08:24", "remaining_time": "2:42:32"}
+{"current_steps": 24, "total_steps": 468, "loss": 0.6196, "lr": 2.0425531914893616e-05, "epoch": 0.15335463258785942, "percentage": 5.13, "elapsed_time": "0:08:43", "remaining_time": "2:41:17"}
+{"current_steps": 25, "total_steps": 468, "loss": 0.6022, "lr": 2.1276595744680852e-05, "epoch": 0.1597444089456869, "percentage": 5.34, "elapsed_time": "0:09:04", "remaining_time": "2:40:48"}
+{"current_steps": 26, "total_steps": 468, "loss": 0.6149, "lr": 2.2127659574468088e-05, "epoch": 0.16613418530351437, "percentage": 5.56, "elapsed_time": "0:09:25", "remaining_time": "2:40:21"}
+{"current_steps": 27, "total_steps": 468, "loss": 0.57, "lr": 2.2978723404255324e-05, "epoch": 0.17252396166134185, "percentage": 5.77, "elapsed_time": "0:09:44", "remaining_time": "2:39:13"}
+{"current_steps": 28, "total_steps": 468, "loss": 0.5663, "lr": 2.3829787234042553e-05, "epoch": 0.17891373801916932, "percentage": 5.98, "elapsed_time": "0:10:02", "remaining_time": "2:37:52"}
+{"current_steps": 29, "total_steps": 468, "loss": 0.5675, "lr": 2.468085106382979e-05, "epoch": 0.1853035143769968, "percentage": 6.2, "elapsed_time": "0:10:23", "remaining_time": "2:37:17"}
+{"current_steps": 30, "total_steps": 468, "loss": 0.5647, "lr": 2.5531914893617025e-05, "epoch": 0.19169329073482427, "percentage": 6.41, "elapsed_time": "0:10:42", "remaining_time": "2:36:21"}
+{"current_steps": 31, "total_steps": 468, "loss": 0.5571, "lr": 2.6382978723404255e-05, "epoch": 0.19808306709265175, "percentage": 6.62, "elapsed_time": "0:11:01", "remaining_time": "2:35:29"}
+{"current_steps": 32, "total_steps": 468, "loss": 0.5675, "lr": 2.723404255319149e-05, "epoch": 0.20447284345047922, "percentage": 6.84, "elapsed_time": "0:11:19", "remaining_time": "2:34:22"}
+{"current_steps": 33, "total_steps": 468, "loss": 0.5684, "lr": 2.8085106382978727e-05, "epoch": 0.2108626198083067, "percentage": 7.05, "elapsed_time": "0:11:39", "remaining_time": "2:33:34"}
+{"current_steps": 34, "total_steps": 468, "loss": 0.5394, "lr": 2.8936170212765963e-05, "epoch": 0.21725239616613418, "percentage": 7.26, "elapsed_time": "0:11:57", "remaining_time": "2:32:32"}
+{"current_steps": 35, "total_steps": 468, "loss": 0.5912, "lr": 2.9787234042553192e-05, "epoch": 0.22364217252396165, "percentage": 7.48, "elapsed_time": "0:12:20", "remaining_time": "2:32:46"}
+{"current_steps": 36, "total_steps": 468, "loss": 0.5284, "lr": 3.063829787234043e-05, "epoch": 0.23003194888178913, "percentage": 7.69, "elapsed_time": "0:12:41", "remaining_time": "2:32:12"}
+{"current_steps": 37, "total_steps": 468, "loss": 0.5448, "lr": 3.1489361702127664e-05, "epoch": 0.2364217252396166, "percentage": 7.91, "elapsed_time": "0:13:03", "remaining_time": "2:32:01"}
+{"current_steps": 38, "total_steps": 468, "loss": 0.5427, "lr": 3.234042553191489e-05, "epoch": 0.24281150159744408, "percentage": 8.12, "elapsed_time": "0:13:24", "remaining_time": "2:31:47"}
+{"current_steps": 39, "total_steps": 468, "loss": 0.5242, "lr": 3.319148936170213e-05, "epoch": 0.24920127795527156, "percentage": 8.33, "elapsed_time": "0:13:45", "remaining_time": "2:31:15"}
+{"current_steps": 40, "total_steps": 468, "loss": 0.5327, "lr": 3.4042553191489365e-05, "epoch": 0.25559105431309903, "percentage": 8.55, "elapsed_time": "0:14:05", "remaining_time": "2:30:41"}
+{"current_steps": 41, "total_steps": 468, "loss": 0.55, "lr": 3.48936170212766e-05, "epoch": 0.26198083067092653, "percentage": 8.76, "elapsed_time": "0:14:22", "remaining_time": "2:29:47"}
+{"current_steps": 42, "total_steps": 468, "loss": 0.5057, "lr": 3.574468085106383e-05, "epoch": 0.268370607028754, "percentage": 8.97, "elapsed_time": "0:14:40", "remaining_time": "2:28:53"}
+{"current_steps": 43, "total_steps": 468, "loss": 0.563, "lr": 3.6595744680851066e-05, "epoch": 0.2747603833865815, "percentage": 9.19, "elapsed_time": "0:15:00", "remaining_time": "2:28:23"}
+{"current_steps": 44, "total_steps": 468, "loss": 0.5716, "lr": 3.74468085106383e-05, "epoch": 0.28115015974440893, "percentage": 9.4, "elapsed_time": "0:15:24", "remaining_time": "2:28:30"}
+{"current_steps": 45, "total_steps": 468, "loss": 0.5202, "lr": 3.829787234042554e-05, "epoch": 0.28753993610223644, "percentage": 9.62, "elapsed_time": "0:15:48", "remaining_time": "2:28:32"}
+{"current_steps": 46, "total_steps": 468, "loss": 0.5333, "lr": 3.914893617021277e-05, "epoch": 0.2939297124600639, "percentage": 9.83, "elapsed_time": "0:16:09", "remaining_time": "2:28:17"}
+{"current_steps": 47, "total_steps": 468, "loss": 0.5569, "lr": 4e-05, "epoch": 0.3003194888178914, "percentage": 10.04, "elapsed_time": "0:16:33", "remaining_time": "2:28:21"}
+{"current_steps": 48, "total_steps": 468, "loss": 0.5412, "lr": 3.999944315600779e-05, "epoch": 0.30670926517571884, "percentage": 10.26, "elapsed_time": "0:16:56", "remaining_time": "2:28:17"}
+{"current_steps": 49, "total_steps": 468, "loss": 0.5493, "lr": 3.9997772655038674e-05, "epoch": 0.31309904153354634, "percentage": 10.47, "elapsed_time": "0:17:12", "remaining_time": "2:27:12"}
+{"current_steps": 50, "total_steps": 468, "loss": 0.5464, "lr": 3.99949885901135e-05, "epoch": 0.3194888178913738, "percentage": 10.68, "elapsed_time": "0:17:33", "remaining_time": "2:26:46"}
+{"current_steps": 51, "total_steps": 468, "loss": 0.5488, "lr": 3.999109111626125e-05, "epoch": 0.3258785942492013, "percentage": 10.9, "elapsed_time": "0:17:53", "remaining_time": "2:26:18"}
+{"current_steps": 52, "total_steps": 468, "loss": 0.5406, "lr": 3.998608045051041e-05, "epoch": 0.33226837060702874, "percentage": 11.11, "elapsed_time": "0:18:18", "remaining_time": "2:26:31"}
+{"current_steps": 53, "total_steps": 468, "loss": 0.5057, "lr": 3.99799568718769e-05, "epoch": 0.33865814696485624, "percentage": 11.32, "elapsed_time": "0:18:38", "remaining_time": "2:25:58"}
+{"current_steps": 54, "total_steps": 468, "loss": 0.5568, "lr": 3.9972720721348503e-05, "epoch": 0.3450479233226837, "percentage": 11.54, "elapsed_time": "0:18:58", "remaining_time": "2:25:25"}
+{"current_steps": 55, "total_steps": 468, "loss": 0.5376, "lr": 3.996437240186593e-05, "epoch": 0.3514376996805112, "percentage": 11.75, "elapsed_time": "0:19:19", "remaining_time": "2:25:08"}
+{"current_steps": 56, "total_steps": 468, "loss": 0.5845, "lr": 3.995491237830033e-05, "epoch": 0.35782747603833864, "percentage": 11.97, "elapsed_time": "0:19:38", "remaining_time": "2:24:27"}
+{"current_steps": 57, "total_steps": 468, "loss": 0.5861, "lr": 3.994434117742743e-05, "epoch": 0.36421725239616615, "percentage": 12.18, "elapsed_time": "0:20:01", "remaining_time": "2:24:24"}
+{"current_steps": 58, "total_steps": 468, "loss": 0.4967, "lr": 3.9932659387898195e-05, "epoch": 0.3706070287539936, "percentage": 12.39, "elapsed_time": "0:20:24", "remaining_time": "2:24:18"}
+{"current_steps": 59, "total_steps": 468, "loss": 0.5163, "lr": 3.991986766020607e-05, "epoch": 0.3769968051118211, "percentage": 12.61, "elapsed_time": "0:20:44", "remaining_time": "2:23:49"}
+{"current_steps": 60, "total_steps": 468, "loss": 0.5236, "lr": 3.9905966706650715e-05, "epoch": 0.38338658146964855, "percentage": 12.82, "elapsed_time": "0:21:06", "remaining_time": "2:23:34"}
+{"current_steps": 61, "total_steps": 468, "loss": 0.5442, "lr": 3.9890957301298385e-05, "epoch": 0.38977635782747605, "percentage": 13.03, "elapsed_time": "0:21:29", "remaining_time": "2:23:26"}
+{"current_steps": 62, "total_steps": 468, "loss": 0.5481, "lr": 3.9874840279938794e-05, "epoch": 0.3961661341853035, "percentage": 13.25, "elapsed_time": "0:21:51", "remaining_time": "2:23:10"}
+{"current_steps": 63, "total_steps": 468, "loss": 0.587, "lr": 3.9857616540038595e-05, "epoch": 0.402555910543131, "percentage": 13.46, "elapsed_time": "0:22:16", "remaining_time": "2:23:11"}
+{"current_steps": 64, "total_steps": 468, "loss": 0.5405, "lr": 3.9839287040691396e-05, "epoch": 0.40894568690095845, "percentage": 13.68, "elapsed_time": "0:22:38", "remaining_time": "2:22:54"}
+{"current_steps": 65, "total_steps": 468, "loss": 0.5661, "lr": 3.981985280256436e-05, "epoch": 0.41533546325878595, "percentage": 13.89, "elapsed_time": "0:23:00", "remaining_time": "2:22:36"}
+{"current_steps": 66, "total_steps": 468, "loss": 0.5376, "lr": 3.979931490784136e-05, "epoch": 0.4217252396166134, "percentage": 14.1, "elapsed_time": "0:23:19", "remaining_time": "2:22:06"}
+{"current_steps": 67, "total_steps": 468, "loss": 0.5501, "lr": 3.977767450016272e-05, "epoch": 0.4281150159744409, "percentage": 14.32, "elapsed_time": "0:23:40", "remaining_time": "2:21:42"}
+{"current_steps": 68, "total_steps": 468, "loss": 0.5495, "lr": 3.9754932784561545e-05, "epoch": 0.43450479233226835, "percentage": 14.53, "elapsed_time": "0:24:02", "remaining_time": "2:21:26"}
+{"current_steps": 69, "total_steps": 468, "loss": 0.5468, "lr": 3.973109102739661e-05, "epoch": 0.44089456869009586, "percentage": 14.74, "elapsed_time": "0:24:21", "remaining_time": "2:20:52"}
+{"current_steps": 70, "total_steps": 468, "loss": 0.5578, "lr": 3.9706150556281827e-05, "epoch": 0.4472843450479233, "percentage": 14.96, "elapsed_time": "0:24:42", "remaining_time": "2:20:30"}
+{"current_steps": 71, "total_steps": 468, "loss": 0.5769, "lr": 3.968011276001236e-05, "epoch": 0.4536741214057508, "percentage": 15.17, "elapsed_time": "0:25:05", "remaining_time": "2:20:20"}
+{"current_steps": 72, "total_steps": 468, "loss": 0.5545, "lr": 3.9652979088487246e-05, "epoch": 0.46006389776357826, "percentage": 15.38, "elapsed_time": "0:25:26", "remaining_time": "2:19:54"}
+{"current_steps": 73, "total_steps": 468, "loss": 0.5443, "lr": 3.962475105262868e-05, "epoch": 0.46645367412140576, "percentage": 15.6, "elapsed_time": "0:25:49", "remaining_time": "2:19:45"}
+{"current_steps": 74, "total_steps": 468, "loss": 0.5597, "lr": 3.9595430224297874e-05, "epoch": 0.4728434504792332, "percentage": 15.81, "elapsed_time": "0:26:10", "remaining_time": "2:19:22"}
+{"current_steps": 75, "total_steps": 468, "loss": 0.5364, "lr": 3.9565018236207545e-05, "epoch": 0.4792332268370607, "percentage": 16.03, "elapsed_time": "0:26:32", "remaining_time": "2:19:02"}
+{"current_steps": 76, "total_steps": 468, "loss": 0.5507, "lr": 3.953351678183099e-05, "epoch": 0.48562300319488816, "percentage": 16.24, "elapsed_time": "0:26:51", "remaining_time": "2:18:33"}
+{"current_steps": 77, "total_steps": 468, "loss": 0.5244, "lr": 3.9500927615307745e-05, "epoch": 0.49201277955271566, "percentage": 16.45, "elapsed_time": "0:27:16", "remaining_time": "2:18:29"}
+{"current_steps": 78, "total_steps": 468, "loss": 0.5594, "lr": 3.9467252551346e-05, "epoch": 0.4984025559105431, "percentage": 16.67, "elapsed_time": "0:27:36", "remaining_time": "2:18:04"}
+{"current_steps": 79, "total_steps": 468, "loss": 0.4883, "lr": 3.943249346512143e-05, "epoch": 0.5047923322683706, "percentage": 16.88, "elapsed_time": "0:28:00", "remaining_time": "2:17:56"}
+{"current_steps": 80, "total_steps": 468, "loss": 0.5144, "lr": 3.939665229217289e-05, "epoch": 0.5111821086261981, "percentage": 17.09, "elapsed_time": "0:28:20", "remaining_time": "2:17:28"}
+{"current_steps": 81, "total_steps": 468, "loss": 0.5527, "lr": 3.935973102829456e-05, "epoch": 0.5175718849840255, "percentage": 17.31, "elapsed_time": "0:28:41", "remaining_time": "2:17:03"}
+{"current_steps": 82, "total_steps": 468, "loss": 0.5672, "lr": 3.9321731729424826e-05, "epoch": 0.5239616613418531, "percentage": 17.52, "elapsed_time": "0:28:59", "remaining_time": "2:16:29"}
+{"current_steps": 83, "total_steps": 468, "loss": 0.529, "lr": 3.928265651153183e-05, "epoch": 0.5303514376996805, "percentage": 17.74, "elapsed_time": "0:29:24", "remaining_time": "2:16:24"}
+{"current_steps": 84, "total_steps": 468, "loss": 0.5037, "lr": 3.92425075504956e-05, "epoch": 0.536741214057508, "percentage": 17.95, "elapsed_time": "0:29:43", "remaining_time": "2:15:54"}
+{"current_steps": 85, "total_steps": 468, "loss": 0.5561, "lr": 3.9201287081986905e-05, "epoch": 0.5431309904153354, "percentage": 18.16, "elapsed_time": "0:30:07", "remaining_time": "2:15:44"}
+{"current_steps": 86, "total_steps": 468, "loss": 0.533, "lr": 3.915899740134277e-05, "epoch": 0.549520766773163, "percentage": 18.38, "elapsed_time": "0:30:29", "remaining_time": "2:15:26"}
+{"current_steps": 87, "total_steps": 468, "loss": 0.5493, "lr": 3.9115640863438666e-05, "epoch": 0.5559105431309904, "percentage": 18.59, "elapsed_time": "0:30:48", "remaining_time": "2:14:53"}
+{"current_steps": 88, "total_steps": 468, "loss": 0.5196, "lr": 3.907121988255735e-05, "epoch": 0.5623003194888179, "percentage": 18.8, "elapsed_time": "0:31:10", "remaining_time": "2:14:39"}
+{"current_steps": 89, "total_steps": 468, "loss": 0.527, "lr": 3.9025736932254463e-05, "epoch": 0.5686900958466453, "percentage": 19.02, "elapsed_time": "0:31:30", "remaining_time": "2:14:10"}
+{"current_steps": 90, "total_steps": 468, "loss": 0.5295, "lr": 3.8979194545220754e-05, "epoch": 0.5750798722044729, "percentage": 19.23, "elapsed_time": "0:31:48", "remaining_time": "2:13:37"}
+{"current_steps": 91, "total_steps": 468, "loss": 0.5306, "lr": 3.893159531314109e-05, "epoch": 0.5814696485623003, "percentage": 19.44, "elapsed_time": "0:32:11", "remaining_time": "2:13:21"}
+{"current_steps": 92, "total_steps": 468, "loss": 0.5093, "lr": 3.888294188655012e-05, "epoch": 0.5878594249201278, "percentage": 19.66, "elapsed_time": "0:32:29", "remaining_time": "2:12:49"}
+{"current_steps": 93, "total_steps": 468, "loss": 0.4991, "lr": 3.8833236974684666e-05, "epoch": 0.5942492012779552, "percentage": 19.87, "elapsed_time": "0:32:54", "remaining_time": "2:12:41"}
+{"current_steps": 94, "total_steps": 468, "loss": 0.5068, "lr": 3.8782483345332876e-05, "epoch": 0.6006389776357828, "percentage": 20.09, "elapsed_time": "0:33:17", "remaining_time": "2:12:27"}
+{"current_steps": 95, "total_steps": 468, "loss": 0.4921, "lr": 3.873068382468012e-05, "epoch": 0.6070287539936102, "percentage": 20.3, "elapsed_time": "0:33:37", "remaining_time": "2:12:01"}
+{"current_steps": 96, "total_steps": 468, "loss": 0.5062, "lr": 3.8677841297151595e-05, "epoch": 0.6134185303514377, "percentage": 20.51, "elapsed_time": "0:34:00", "remaining_time": "2:11:47"}
+{"current_steps": 97, "total_steps": 468, "loss": 0.5563, "lr": 3.862395870525167e-05, "epoch": 0.6198083067092651, "percentage": 20.73, "elapsed_time": "0:34:20", "remaining_time": "2:11:22"}
+{"current_steps": 98, "total_steps": 468, "loss": 0.5336, "lr": 3.856903904940014e-05, "epoch": 0.6261980830670927, "percentage": 20.94, "elapsed_time": "0:34:45", "remaining_time": "2:11:14"}
+{"current_steps": 99, "total_steps": 468, "loss": 0.5042, "lr": 3.851308538776501e-05, "epoch": 0.6325878594249201, "percentage": 21.15, "elapsed_time": "0:35:04", "remaining_time": "2:10:44"}
+{"current_steps": 100, "total_steps": 468, "loss": 0.5125, "lr": 3.845610083609234e-05, "epoch": 0.6389776357827476, "percentage": 21.37, "elapsed_time": "0:35:27", "remaining_time": "2:10:30"}
+{"current_steps": 101, "total_steps": 468, "loss": 0.5378, "lr": 3.839808856753264e-05, "epoch": 0.645367412140575, "percentage": 21.58, "elapsed_time": "0:35:51", "remaining_time": "2:10:16"}
+{"current_steps": 102, "total_steps": 468, "loss": 0.5201, "lr": 3.833905181246424e-05, "epoch": 0.6517571884984026, "percentage": 21.79, "elapsed_time": "0:36:13", "remaining_time": "2:10:00"}
+{"current_steps": 103, "total_steps": 468, "loss": 0.5219, "lr": 3.827899385831337e-05, "epoch": 0.65814696485623, "percentage": 22.01, "elapsed_time": "0:36:35", "remaining_time": "2:09:41"}
+{"current_steps": 104, "total_steps": 468, "loss": 0.5298, "lr": 3.821791804937114e-05, "epoch": 0.6645367412140575, "percentage": 22.22, "elapsed_time": "0:36:54", "remaining_time": "2:09:10"}
+{"current_steps": 105, "total_steps": 468, "loss": 0.5192, "lr": 3.815582778660726e-05, "epoch": 0.670926517571885, "percentage": 22.44, "elapsed_time": "0:37:10", "remaining_time": "2:08:30"}
+{"current_steps": 106, "total_steps": 468, "loss": 0.5276, "lr": 3.809272652748072e-05, "epoch": 0.6773162939297125, "percentage": 22.65, "elapsed_time": "0:37:29", "remaining_time": "2:08:01"}
+{"current_steps": 107, "total_steps": 468, "loss": 0.5608, "lr": 3.8028617785747224e-05, "epoch": 0.6837060702875399, "percentage": 22.86, "elapsed_time": "0:37:51", "remaining_time": "2:07:42"}
+{"current_steps": 108, "total_steps": 468, "loss": 0.4968, "lr": 3.7963505131263534e-05, "epoch": 0.6900958466453674, "percentage": 23.08, "elapsed_time": "0:38:10", "remaining_time": "2:07:15"}
+{"current_steps": 109, "total_steps": 468, "loss": 0.5693, "lr": 3.789739218978871e-05, "epoch": 0.6964856230031949, "percentage": 23.29, "elapsed_time": "0:38:30", "remaining_time": "2:06:49"}
+{"current_steps": 110, "total_steps": 468, "loss": 0.5372, "lr": 3.783028264278217e-05, "epoch": 0.7028753993610224, "percentage": 23.5, "elapsed_time": "0:38:49", "remaining_time": "2:06:22"}
+{"current_steps": 111, "total_steps": 468, "loss": 0.5277, "lr": 3.7762180227198707e-05, "epoch": 0.7092651757188498, "percentage": 23.72, "elapsed_time": "0:39:12", "remaining_time": "2:06:04"}
+{"current_steps": 112, "total_steps": 468, "loss": 0.4962, "lr": 3.7693088735280435e-05, "epoch": 0.7156549520766773, "percentage": 23.93, "elapsed_time": "0:39:28", "remaining_time": "2:05:27"}
+{"current_steps": 113, "total_steps": 468, "loss": 0.5407, "lr": 3.762301201434558e-05, "epoch": 0.7220447284345048, "percentage": 24.15, "elapsed_time": "0:39:46", "remaining_time": "2:04:58"}
+{"current_steps": 114, "total_steps": 468, "loss": 0.5282, "lr": 3.755195396657423e-05, "epoch": 0.7284345047923323, "percentage": 24.36, "elapsed_time": "0:40:09", "remaining_time": "2:04:41"}
+{"current_steps": 115, "total_steps": 468, "loss": 0.5331, "lr": 3.74799185487911e-05, "epoch": 0.7348242811501597, "percentage": 24.57, "elapsed_time": "0:40:30", "remaining_time": "2:04:19"}
+{"current_steps": 116, "total_steps": 468, "loss": 0.5433, "lr": 3.7406909772245136e-05, "epoch": 0.7412140575079872, "percentage": 24.79, "elapsed_time": "0:40:54", "remaining_time": "2:04:08"}
+{"current_steps": 117, "total_steps": 468, "loss": 0.5128, "lr": 3.73329317023862e-05, "epoch": 0.7476038338658147, "percentage": 25.0, "elapsed_time": "0:41:10", "remaining_time": "2:03:30"}
+{"current_steps": 118, "total_steps": 468, "loss": 0.5067, "lr": 3.725798845863868e-05, "epoch": 0.7539936102236422, "percentage": 25.21, "elapsed_time": "0:41:32", "remaining_time": "2:03:12"}
+{"current_steps": 119, "total_steps": 468, "loss": 0.518, "lr": 3.718208421417208e-05, "epoch": 0.7603833865814696, "percentage": 25.43, "elapsed_time": "0:41:53", "remaining_time": "2:02:52"}
+{"current_steps": 120, "total_steps": 468, "loss": 0.5025, "lr": 3.710522319566864e-05, "epoch": 0.7667731629392971, "percentage": 25.64, "elapsed_time": "0:42:16", "remaining_time": "2:02:36"}
+{"current_steps": 121, "total_steps": 468, "loss": 0.509, "lr": 3.7027409683087994e-05, "epoch": 0.7731629392971247, "percentage": 25.85, "elapsed_time": "0:42:39", "remaining_time": "2:02:21"}
+{"current_steps": 122, "total_steps": 468, "loss": 0.5577, "lr": 3.694864800942886e-05, "epoch": 0.7795527156549521, "percentage": 26.07, "elapsed_time": "0:43:03", "remaining_time": "2:02:06"}
+{"current_steps": 123, "total_steps": 468, "loss": 0.5132, "lr": 3.686894256048771e-05, "epoch": 0.7859424920127795, "percentage": 26.28, "elapsed_time": "0:43:23", "remaining_time": "2:01:41"}
+{"current_steps": 124, "total_steps": 468, "loss": 0.5456, "lr": 3.678829777461457e-05, "epoch": 0.792332268370607, "percentage": 26.5, "elapsed_time": "0:43:44", "remaining_time": "2:01:19"}
+{"current_steps": 125, "total_steps": 468, "loss": 0.51, "lr": 3.670671814246591e-05, "epoch": 0.7987220447284346, "percentage": 26.71, "elapsed_time": "0:44:07", "remaining_time": "2:01:04"}
+{"current_steps": 126, "total_steps": 468, "loss": 0.4998, "lr": 3.662420820675453e-05, "epoch": 0.805111821086262, "percentage": 26.92, "elapsed_time": "0:44:26", "remaining_time": "2:00:37"}
+{"current_steps": 127, "total_steps": 468, "loss": 0.4945, "lr": 3.654077256199662e-05, "epoch": 0.8115015974440895, "percentage": 27.14, "elapsed_time": "0:44:46", "remaining_time": "2:00:13"}
+{"current_steps": 128, "total_steps": 468, "loss": 0.5031, "lr": 3.645641585425594e-05, "epoch": 0.8178913738019169, "percentage": 27.35, "elapsed_time": "0:45:08", "remaining_time": "1:59:53"}
+{"current_steps": 129, "total_steps": 468, "loss": 0.4892, "lr": 3.6371142780885085e-05, "epoch": 0.8242811501597445, "percentage": 27.56, "elapsed_time": "0:45:31", "remaining_time": "1:59:37"}
+{"current_steps": 130, "total_steps": 468, "loss": 0.526, "lr": 3.628495809026391e-05, "epoch": 0.8306709265175719, "percentage": 27.78, "elapsed_time": "0:45:51", "remaining_time": "1:59:14"}
+{"current_steps": 131, "total_steps": 468, "loss": 0.5289, "lr": 3.619786658153514e-05, "epoch": 0.8370607028753994, "percentage": 27.99, "elapsed_time": "0:46:12", "remaining_time": "1:58:51"}
+{"current_steps": 132, "total_steps": 468, "loss": 0.5394, "lr": 3.6109873104337096e-05, "epoch": 0.8434504792332268, "percentage": 28.21, "elapsed_time": "0:46:27", "remaining_time": "1:58:15"}
+{"current_steps": 133, "total_steps": 468, "loss": 0.4852, "lr": 3.602098255853372e-05, "epoch": 0.8498402555910544, "percentage": 28.42, "elapsed_time": "0:46:45", "remaining_time": "1:57:45"}
+{"current_steps": 134, "total_steps": 468, "loss": 0.4989, "lr": 3.593119989394163e-05, "epoch": 0.8562300319488818, "percentage": 28.63, "elapsed_time": "0:47:04", "remaining_time": "1:57:20"}
+{"current_steps": 135, "total_steps": 468, "loss": 0.5261, "lr": 3.584053011005457e-05, "epoch": 0.8626198083067093, "percentage": 28.85, "elapsed_time": "0:47:28", "remaining_time": "1:57:05"}
+{"current_steps": 136, "total_steps": 468, "loss": 0.5336, "lr": 3.574897825576499e-05, "epoch": 0.8690095846645367, "percentage": 29.06, "elapsed_time": "0:47:50", "remaining_time": "1:56:48"}
+{"current_steps": 137, "total_steps": 468, "loss": 0.5291, "lr": 3.565654942908289e-05, "epoch": 0.8753993610223643, "percentage": 29.27, "elapsed_time": "0:48:13", "remaining_time": "1:56:30"}
+{"current_steps": 138, "total_steps": 468, "loss": 0.5135, "lr": 3.556324877685195e-05, "epoch": 0.8817891373801917, "percentage": 29.49, "elapsed_time": "0:48:34", "remaining_time": "1:56:08"}
+{"current_steps": 139, "total_steps": 468, "loss": 0.4844, "lr": 3.546908149446294e-05, "epoch": 0.8881789137380192, "percentage": 29.7, "elapsed_time": "0:48:56", "remaining_time": "1:55:50"}
+{"current_steps": 140, "total_steps": 468, "loss": 0.5467, "lr": 3.53740528255644e-05, "epoch": 0.8945686900958466, "percentage": 29.91, "elapsed_time": "0:49:20", "remaining_time": "1:55:35"}
+{"current_steps": 141, "total_steps": 468, "loss": 0.5182, "lr": 3.527816806177068e-05, "epoch": 0.9009584664536742, "percentage": 30.13, "elapsed_time": "0:49:42", "remaining_time": "1:55:17"}
+{"current_steps": 142, "total_steps": 468, "loss": 0.5033, "lr": 3.518143254236724e-05, "epoch": 0.9073482428115016, "percentage": 30.34, "elapsed_time": "0:49:59", "remaining_time": "1:54:46"}
+{"current_steps": 143, "total_steps": 468, "loss": 0.5127, "lr": 3.508385165401336e-05, "epoch": 0.9137380191693291, "percentage": 30.56, "elapsed_time": "0:50:21", "remaining_time": "1:54:26"}
+{"current_steps": 144, "total_steps": 468, "loss": 0.516, "lr": 3.4985430830442175e-05, "epoch": 0.9201277955271565, "percentage": 30.77, "elapsed_time": "0:50:40", "remaining_time": "1:54:00"}
+{"current_steps": 145, "total_steps": 468, "loss": 0.4947, "lr": 3.4886175552158135e-05, "epoch": 0.9265175718849841, "percentage": 30.98, "elapsed_time": "0:51:02", "remaining_time": "1:53:42"}
+{"current_steps": 146, "total_steps": 468, "loss": 0.5022, "lr": 3.478609134613176e-05, "epoch": 0.9329073482428115, "percentage": 31.2, "elapsed_time": "0:51:23", "remaining_time": "1:53:20"}
+{"current_steps": 147, "total_steps": 468, "loss": 0.5149, "lr": 3.4685183785491956e-05, "epoch": 0.939297124600639, "percentage": 31.41, "elapsed_time": "0:51:43", "remaining_time": "1:52:56"}
+{"current_steps": 148, "total_steps": 468, "loss": 0.5484, "lr": 3.45834584892156e-05, "epoch": 0.9456869009584664, "percentage": 31.62, "elapsed_time": "0:52:04", "remaining_time": "1:52:35"}
+{"current_steps": 149, "total_steps": 468, "loss": 0.5113, "lr": 3.448092112181469e-05, "epoch": 0.952076677316294, "percentage": 31.84, "elapsed_time": "0:52:21", "remaining_time": "1:52:06"}
+{"current_steps": 150, "total_steps": 468, "loss": 0.5057, "lr": 3.4377577393020955e-05, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:52:46", "remaining_time": "1:51:52"}
+{"current_steps": 151, "total_steps": 468, "loss": 0.4993, "lr": 3.427343305746783e-05, "epoch": 0.9648562300319489, "percentage": 32.26, "elapsed_time": "0:53:02", "remaining_time": "1:51:21"}
+{"current_steps": 152, "total_steps": 468, "loss": 0.4784, "lr": 3.416849391437007e-05, "epoch": 0.9712460063897763, "percentage": 32.48, "elapsed_time": "0:53:27", "remaining_time": "1:51:07"}
+{"current_steps": 153, "total_steps": 468, "loss": 0.4958, "lr": 3.406276580720082e-05, "epoch": 0.9776357827476039, "percentage": 32.69, "elapsed_time": "0:53:46", "remaining_time": "1:50:42"}
+{"current_steps": 154, "total_steps": 468, "loss": 0.5126, "lr": 3.3956254623366206e-05, "epoch": 0.9840255591054313, "percentage": 32.91, "elapsed_time": "0:54:02", "remaining_time": "1:50:12"}
+{"current_steps": 155, "total_steps": 468, "loss": 0.4954, "lr": 3.384896629387751e-05, "epoch": 0.9904153354632588, "percentage": 33.12, "elapsed_time": "0:54:22", "remaining_time": "1:49:48"}
+{"current_steps": 156, "total_steps": 468, "loss": 0.5326, "lr": 3.374090679302091e-05, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:54:42", "remaining_time": "1:49:24"}
+{"current_steps": 157, "total_steps": 468, "loss": 0.7746, "lr": 3.363208213802478e-05, "epoch": 1.0031948881789137, "percentage": 33.55, "elapsed_time": "0:55:48", "remaining_time": "1:50:32"}
+{"current_steps": 158, "total_steps": 468, "loss": 0.4163, "lr": 3.352249838872466e-05, "epoch": 1.0095846645367412, "percentage": 33.76, "elapsed_time": "0:56:07", "remaining_time": "1:50:06"}
+{"current_steps": 159, "total_steps": 468, "loss": 0.3854, "lr": 3.3412161647225795e-05, "epoch": 1.0159744408945688, "percentage": 33.97, "elapsed_time": "0:56:29", "remaining_time": "1:49:46"}
+{"current_steps": 160, "total_steps": 468, "loss": 0.3674, "lr": 3.330107805756334e-05, "epoch": 1.0223642172523961, "percentage": 34.19, "elapsed_time": "0:56:50", "remaining_time": "1:49:24"}
+{"current_steps": 161, "total_steps": 468, "loss": 0.4473, "lr": 3.318925380536026e-05, "epoch": 1.0287539936102237, "percentage": 34.4, "elapsed_time": "0:57:10", "remaining_time": "1:49:01"}
+{"current_steps": 162, "total_steps": 468, "loss": 0.3834, "lr": 3.307669511748285e-05, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:57:30", "remaining_time": "1:48:37"}
+{"current_steps": 163, "total_steps": 468, "loss": 0.4215, "lr": 3.2963408261694026e-05, "epoch": 1.0415335463258786, "percentage": 34.83, "elapsed_time": "0:57:49", "remaining_time": "1:48:12"}
+{"current_steps": 164, "total_steps": 468, "loss": 0.4247, "lr": 3.284939954630428e-05, "epoch": 1.0479233226837061, "percentage": 35.04, "elapsed_time": "0:58:12", "remaining_time": "1:47:53"}
+{"current_steps": 165, "total_steps": 468, "loss": 0.4013, "lr": 3.2734675319820446e-05, "epoch": 1.0543130990415335, "percentage": 35.26, "elapsed_time": "0:58:35", "remaining_time": "1:47:35"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174a9d9065bbc8d8298b2ca041db24bb3f975dd798917b024c89579f4c8d1556
+size 7224