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:cb00d2aea659f36b7ebbe3ca4a17d9377822b288e600661e2f28baef1d4427bc
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd7caae88cb4e140e1756e3a5913ea9197861898adca60b5dd6e298beb72f44c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bd15ab549010fe9e2db6f7d18df39877105cd3fd2ab96ca14294f9e48f8b17
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441c5219e8bc6ae051978552376bd37f8848f1b38bc62e8d59c5d7b69000c1a8
+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 +1,175 @@
+{"current_steps": 1, "total_steps": 519, "loss": 0.8904, "lr": 1.5384615384615387e-06, "epoch": 0.005772005772005772, "percentage": 0.19, "elapsed_time": "0:01:38", "remaining_time": "14:06:55"}
+{"current_steps": 2, "total_steps": 519, "loss": 0.9046, "lr": 3.0769230769230774e-06, "epoch": 0.011544011544011544, "percentage": 0.39, "elapsed_time": "0:02:28", "remaining_time": "10:40:50"}
+{"current_steps": 3, "total_steps": 519, "loss": 0.894, "lr": 4.615384615384616e-06, "epoch": 0.017316017316017316, "percentage": 0.58, "elapsed_time": "0:03:20", "remaining_time": "9:33:30"}
+{"current_steps": 4, "total_steps": 519, "loss": 0.8572, "lr": 6.153846153846155e-06, "epoch": 0.023088023088023088, "percentage": 0.77, "elapsed_time": "0:04:10", "remaining_time": "8:58:34"}
+{"current_steps": 5, "total_steps": 519, "loss": 0.793, "lr": 7.692307692307694e-06, "epoch": 0.02886002886002886, "percentage": 0.96, "elapsed_time": "0:05:01", "remaining_time": "8:36:35"}
+{"current_steps": 6, "total_steps": 519, "loss": 0.7612, "lr": 9.230769230769232e-06, "epoch": 0.03463203463203463, "percentage": 1.16, "elapsed_time": "0:05:51", "remaining_time": "8:21:11"}
+{"current_steps": 7, "total_steps": 519, "loss": 0.7896, "lr": 1.076923076923077e-05, "epoch": 0.04040404040404041, "percentage": 1.35, "elapsed_time": "0:06:42", "remaining_time": "8:10:58"}
+{"current_steps": 8, "total_steps": 519, "loss": 0.7438, "lr": 1.230769230769231e-05, "epoch": 0.046176046176046176, "percentage": 1.54, "elapsed_time": "0:07:32", "remaining_time": "8:02:15"}
+{"current_steps": 9, "total_steps": 519, "loss": 0.7438, "lr": 1.3846153846153847e-05, "epoch": 0.05194805194805195, "percentage": 1.73, "elapsed_time": "0:08:23", "remaining_time": "7:55:43"}
+{"current_steps": 10, "total_steps": 519, "loss": 0.7188, "lr": 1.5384615384615387e-05, "epoch": 0.05772005772005772, "percentage": 1.93, "elapsed_time": "0:09:13", "remaining_time": "7:49:51"}
+{"current_steps": 11, "total_steps": 519, "loss": 0.6873, "lr": 1.6923076923076924e-05, "epoch": 0.06349206349206349, "percentage": 2.12, "elapsed_time": "0:10:04", "remaining_time": "7:44:56"}
+{"current_steps": 12, "total_steps": 519, "loss": 0.6739, "lr": 1.8461538461538465e-05, "epoch": 0.06926406926406926, "percentage": 2.31, "elapsed_time": "0:10:55", "remaining_time": "7:41:51"}
+{"current_steps": 13, "total_steps": 519, "loss": 0.6549, "lr": 2e-05, "epoch": 0.07503607503607504, "percentage": 2.5, "elapsed_time": "0:11:50", "remaining_time": "7:40:57"}
+{"current_steps": 14, "total_steps": 519, "loss": 0.6572, "lr": 2.153846153846154e-05, "epoch": 0.08080808080808081, "percentage": 2.7, "elapsed_time": "0:12:40", "remaining_time": "7:37:19"}
+{"current_steps": 15, "total_steps": 519, "loss": 0.6267, "lr": 2.3076923076923076e-05, "epoch": 0.08658008658008658, "percentage": 2.89, "elapsed_time": "0:13:31", "remaining_time": "7:34:19"}
+{"current_steps": 16, "total_steps": 519, "loss": 0.6148, "lr": 2.461538461538462e-05, "epoch": 0.09235209235209235, "percentage": 3.08, "elapsed_time": "0:14:21", "remaining_time": "7:31:27"}
+{"current_steps": 17, "total_steps": 519, "loss": 0.6063, "lr": 2.6153846153846157e-05, "epoch": 0.09812409812409813, "percentage": 3.28, "elapsed_time": "0:15:11", "remaining_time": "7:28:49"}
+{"current_steps": 18, "total_steps": 519, "loss": 0.6027, "lr": 2.7692307692307694e-05, "epoch": 0.1038961038961039, "percentage": 3.47, "elapsed_time": "0:16:02", "remaining_time": "7:26:18"}
+{"current_steps": 19, "total_steps": 519, "loss": 0.6048, "lr": 2.923076923076923e-05, "epoch": 0.10966810966810966, "percentage": 3.66, "elapsed_time": "0:16:52", "remaining_time": "7:24:00"}
+{"current_steps": 20, "total_steps": 519, "loss": 0.5891, "lr": 3.0769230769230774e-05, "epoch": 0.11544011544011544, "percentage": 3.85, "elapsed_time": "0:17:42", "remaining_time": "7:21:51"}
+{"current_steps": 21, "total_steps": 519, "loss": 0.5787, "lr": 3.230769230769231e-05, "epoch": 0.12121212121212122, "percentage": 4.05, "elapsed_time": "0:18:32", "remaining_time": "7:19:48"}
+{"current_steps": 22, "total_steps": 519, "loss": 0.5651, "lr": 3.384615384615385e-05, "epoch": 0.12698412698412698, "percentage": 4.24, "elapsed_time": "0:19:22", "remaining_time": "7:17:51"}
+{"current_steps": 23, "total_steps": 519, "loss": 0.5778, "lr": 3.538461538461539e-05, "epoch": 0.13275613275613277, "percentage": 4.43, "elapsed_time": "0:20:13", "remaining_time": "7:16:03"}
+{"current_steps": 24, "total_steps": 519, "loss": 0.566, "lr": 3.692307692307693e-05, "epoch": 0.13852813852813853, "percentage": 4.62, "elapsed_time": "0:21:03", "remaining_time": "7:14:20"}
+{"current_steps": 25, "total_steps": 519, "loss": 0.5629, "lr": 3.846153846153846e-05, "epoch": 0.1443001443001443, "percentage": 4.82, "elapsed_time": "0:21:53", "remaining_time": "7:12:40"}
+{"current_steps": 26, "total_steps": 519, "loss": 0.5576, "lr": 4e-05, "epoch": 0.15007215007215008, "percentage": 5.01, "elapsed_time": "0:22:43", "remaining_time": "7:11:02"}
+{"current_steps": 27, "total_steps": 519, "loss": 0.5588, "lr": 4.1538461538461544e-05, "epoch": 0.15584415584415584, "percentage": 5.2, "elapsed_time": "0:23:36", "remaining_time": "7:10:18"}
+{"current_steps": 28, "total_steps": 519, "loss": 0.5538, "lr": 4.307692307692308e-05, "epoch": 0.16161616161616163, "percentage": 5.39, "elapsed_time": "0:24:29", "remaining_time": "7:09:29"}
+{"current_steps": 29, "total_steps": 519, "loss": 0.5527, "lr": 4.461538461538462e-05, "epoch": 0.1673881673881674, "percentage": 5.59, "elapsed_time": "0:25:19", "remaining_time": "7:08:00"}
+{"current_steps": 30, "total_steps": 519, "loss": 0.5483, "lr": 4.615384615384615e-05, "epoch": 0.17316017316017315, "percentage": 5.78, "elapsed_time": "0:26:09", "remaining_time": "7:06:29"}
+{"current_steps": 31, "total_steps": 519, "loss": 0.542, "lr": 4.76923076923077e-05, "epoch": 0.17893217893217894, "percentage": 5.97, "elapsed_time": "0:27:00", "remaining_time": "7:05:06"}
+{"current_steps": 32, "total_steps": 519, "loss": 0.5438, "lr": 4.923076923076924e-05, "epoch": 0.1847041847041847, "percentage": 6.17, "elapsed_time": "0:27:50", "remaining_time": "7:03:45"}
+{"current_steps": 33, "total_steps": 519, "loss": 0.5435, "lr": 5.076923076923077e-05, "epoch": 0.19047619047619047, "percentage": 6.36, "elapsed_time": "0:28:41", "remaining_time": "7:02:26"}
+{"current_steps": 34, "total_steps": 519, "loss": 0.5362, "lr": 5.230769230769231e-05, "epoch": 0.19624819624819625, "percentage": 6.55, "elapsed_time": "0:29:31", "remaining_time": "7:01:07"}
+{"current_steps": 35, "total_steps": 519, "loss": 0.5368, "lr": 5.3846153846153853e-05, "epoch": 0.20202020202020202, "percentage": 6.74, "elapsed_time": "0:30:21", "remaining_time": "6:59:51"}
+{"current_steps": 36, "total_steps": 519, "loss": 0.5436, "lr": 5.538461538461539e-05, "epoch": 0.2077922077922078, "percentage": 6.94, "elapsed_time": "0:31:11", "remaining_time": "6:58:33"}
+{"current_steps": 37, "total_steps": 519, "loss": 0.5425, "lr": 5.692307692307693e-05, "epoch": 0.21356421356421357, "percentage": 7.13, "elapsed_time": "0:32:01", "remaining_time": "6:57:17"}
+{"current_steps": 38, "total_steps": 519, "loss": 0.53, "lr": 5.846153846153846e-05, "epoch": 0.21933621933621933, "percentage": 7.32, "elapsed_time": "0:32:52", "remaining_time": "6:56:03"}
+{"current_steps": 39, "total_steps": 519, "loss": 0.5211, "lr": 6.000000000000001e-05, "epoch": 0.22510822510822512, "percentage": 7.51, "elapsed_time": "0:33:42", "remaining_time": "6:54:51"}
+{"current_steps": 40, "total_steps": 519, "loss": 0.5263, "lr": 6.153846153846155e-05, "epoch": 0.23088023088023088, "percentage": 7.71, "elapsed_time": "0:34:32", "remaining_time": "6:53:39"}
+{"current_steps": 41, "total_steps": 519, "loss": 0.5327, "lr": 6.307692307692308e-05, "epoch": 0.23665223665223664, "percentage": 7.9, "elapsed_time": "0:35:22", "remaining_time": "6:52:30"}
+{"current_steps": 42, "total_steps": 519, "loss": 0.5319, "lr": 6.461538461538462e-05, "epoch": 0.24242424242424243, "percentage": 8.09, "elapsed_time": "0:36:19", "remaining_time": "6:52:28"}
+{"current_steps": 43, "total_steps": 519, "loss": 0.5288, "lr": 6.615384615384616e-05, "epoch": 0.2481962481962482, "percentage": 8.29, "elapsed_time": "0:37:11", "remaining_time": "6:51:44"}
+{"current_steps": 44, "total_steps": 519, "loss": 0.5203, "lr": 6.76923076923077e-05, "epoch": 0.25396825396825395, "percentage": 8.48, "elapsed_time": "0:38:01", "remaining_time": "6:50:33"}
+{"current_steps": 45, "total_steps": 519, "loss": 0.5261, "lr": 6.923076923076924e-05, "epoch": 0.2597402597402597, "percentage": 8.67, "elapsed_time": "0:38:51", "remaining_time": "6:49:23"}
+{"current_steps": 46, "total_steps": 519, "loss": 0.5243, "lr": 7.076923076923078e-05, "epoch": 0.26551226551226553, "percentage": 8.86, "elapsed_time": "0:39:42", "remaining_time": "6:48:13"}
+{"current_steps": 47, "total_steps": 519, "loss": 0.5161, "lr": 7.230769230769232e-05, "epoch": 0.2712842712842713, "percentage": 9.06, "elapsed_time": "0:40:32", "remaining_time": "6:47:05"}
+{"current_steps": 48, "total_steps": 519, "loss": 0.5159, "lr": 7.384615384615386e-05, "epoch": 0.27705627705627706, "percentage": 9.25, "elapsed_time": "0:41:22", "remaining_time": "6:45:57"}
+{"current_steps": 49, "total_steps": 519, "loss": 0.516, "lr": 7.538461538461539e-05, "epoch": 0.2828282828282828, "percentage": 9.44, "elapsed_time": "0:42:12", "remaining_time": "6:44:51"}
+{"current_steps": 50, "total_steps": 519, "loss": 0.5302, "lr": 7.692307692307693e-05, "epoch": 0.2886002886002886, "percentage": 9.63, "elapsed_time": "0:43:02", "remaining_time": "6:43:45"}
+{"current_steps": 51, "total_steps": 519, "loss": 0.5172, "lr": 7.846153846153847e-05, "epoch": 0.2943722943722944, "percentage": 9.83, "elapsed_time": "0:43:52", "remaining_time": "6:42:41"}
+{"current_steps": 52, "total_steps": 519, "loss": 0.5184, "lr": 8e-05, "epoch": 0.30014430014430016, "percentage": 10.02, "elapsed_time": "0:44:43", "remaining_time": "6:41:36"}
+{"current_steps": 53, "total_steps": 519, "loss": 0.5163, "lr": 7.999909490463248e-05, "epoch": 0.3059163059163059, "percentage": 10.21, "elapsed_time": "0:45:33", "remaining_time": "6:40:32"}
+{"current_steps": 54, "total_steps": 519, "loss": 0.5156, "lr": 7.999637965948977e-05, "epoch": 0.3116883116883117, "percentage": 10.4, "elapsed_time": "0:46:23", "remaining_time": "6:39:29"}
+{"current_steps": 55, "total_steps": 519, "loss": 0.5054, "lr": 7.999185438744968e-05, "epoch": 0.31746031746031744, "percentage": 10.6, "elapsed_time": "0:47:13", "remaining_time": "6:38:27"}
+{"current_steps": 56, "total_steps": 519, "loss": 0.5151, "lr": 7.998551929330234e-05, "epoch": 0.32323232323232326, "percentage": 10.79, "elapsed_time": "0:48:04", "remaining_time": "6:37:27"}
+{"current_steps": 57, "total_steps": 519, "loss": 0.5237, "lr": 7.997737466374096e-05, "epoch": 0.329004329004329, "percentage": 10.98, "elapsed_time": "0:49:01", "remaining_time": "6:37:25"}
+{"current_steps": 58, "total_steps": 519, "loss": 0.5029, "lr": 7.99674208673489e-05, "epoch": 0.3347763347763348, "percentage": 11.18, "elapsed_time": "0:49:52", "remaining_time": "6:36:23"}
+{"current_steps": 59, "total_steps": 519, "loss": 0.4971, "lr": 7.995565835458286e-05, "epoch": 0.34054834054834054, "percentage": 11.37, "elapsed_time": "0:50:42", "remaining_time": "6:35:21"}
+{"current_steps": 60, "total_steps": 519, "loss": 0.5174, "lr": 7.994208765775267e-05, "epoch": 0.3463203463203463, "percentage": 11.56, "elapsed_time": "0:51:32", "remaining_time": "6:34:18"}
+{"current_steps": 61, "total_steps": 519, "loss": 0.5055, "lr": 7.992670939099704e-05, "epoch": 0.35209235209235207, "percentage": 11.75, "elapsed_time": "0:52:22", "remaining_time": "6:33:16"}
+{"current_steps": 62, "total_steps": 519, "loss": 0.5098, "lr": 7.99095242502559e-05, "epoch": 0.3578643578643579, "percentage": 11.95, "elapsed_time": "0:53:12", "remaining_time": "6:32:15"}
+{"current_steps": 63, "total_steps": 519, "loss": 0.5054, "lr": 7.989053301323881e-05, "epoch": 0.36363636363636365, "percentage": 12.14, "elapsed_time": "0:54:03", "remaining_time": "6:31:15"}
+{"current_steps": 64, "total_steps": 519, "loss": 0.5034, "lr": 7.986973653938977e-05, "epoch": 0.3694083694083694, "percentage": 12.33, "elapsed_time": "0:54:53", "remaining_time": "6:30:13"}
+{"current_steps": 65, "total_steps": 519, "loss": 0.5079, "lr": 7.984713576984842e-05, "epoch": 0.37518037518037517, "percentage": 12.52, "elapsed_time": "0:55:43", "remaining_time": "6:29:13"}
+{"current_steps": 66, "total_steps": 519, "loss": 0.4968, "lr": 7.982273172740734e-05, "epoch": 0.38095238095238093, "percentage": 12.72, "elapsed_time": "0:56:33", "remaining_time": "6:28:13"}
+{"current_steps": 67, "total_steps": 519, "loss": 0.5016, "lr": 7.979652551646583e-05, "epoch": 0.38672438672438675, "percentage": 12.91, "elapsed_time": "0:57:24", "remaining_time": "6:27:15"}
+{"current_steps": 68, "total_steps": 519, "loss": 0.5044, "lr": 7.976851832297987e-05, "epoch": 0.3924963924963925, "percentage": 13.1, "elapsed_time": "0:58:14", "remaining_time": "6:26:16"}
+{"current_steps": 69, "total_steps": 519, "loss": 0.503, "lr": 7.973871141440853e-05, "epoch": 0.39826839826839827, "percentage": 13.29, "elapsed_time": "0:59:04", "remaining_time": "6:25:17"}
+{"current_steps": 70, "total_steps": 519, "loss": 0.501, "lr": 7.970710613965657e-05, "epoch": 0.40404040404040403, "percentage": 13.49, "elapsed_time": "0:59:54", "remaining_time": "6:24:18"}
+{"current_steps": 71, "total_steps": 519, "loss": 0.4964, "lr": 7.967370392901334e-05, "epoch": 0.4098124098124098, "percentage": 13.68, "elapsed_time": "1:00:45", "remaining_time": "6:23:23"}
+{"current_steps": 72, "total_steps": 519, "loss": 0.5005, "lr": 7.963850629408817e-05, "epoch": 0.4155844155844156, "percentage": 13.87, "elapsed_time": "1:01:45", "remaining_time": "6:23:27"}
+{"current_steps": 73, "total_steps": 519, "loss": 0.4989, "lr": 7.960151482774188e-05, "epoch": 0.4213564213564214, "percentage": 14.07, "elapsed_time": "1:02:35", "remaining_time": "6:22:27"}
+{"current_steps": 74, "total_steps": 519, "loss": 0.4901, "lr": 7.95627312040147e-05, "epoch": 0.42712842712842713, "percentage": 14.26, "elapsed_time": "1:03:26", "remaining_time": "6:21:28"}
+{"current_steps": 75, "total_steps": 519, "loss": 0.4895, "lr": 7.952215717805055e-05, "epoch": 0.4329004329004329, "percentage": 14.45, "elapsed_time": "1:04:16", "remaining_time": "6:20:30"}
+{"current_steps": 76, "total_steps": 519, "loss": 0.4939, "lr": 7.947979458601756e-05, "epoch": 0.43867243867243866, "percentage": 14.64, "elapsed_time": "1:05:06", "remaining_time": "6:19:31"}
+{"current_steps": 77, "total_steps": 519, "loss": 0.4909, "lr": 7.943564534502503e-05, "epoch": 0.4444444444444444, "percentage": 14.84, "elapsed_time": "1:05:56", "remaining_time": "6:18:33"}
+{"current_steps": 78, "total_steps": 519, "loss": 0.4962, "lr": 7.938971145303666e-05, "epoch": 0.45021645021645024, "percentage": 15.03, "elapsed_time": "1:06:46", "remaining_time": "6:17:34"}
+{"current_steps": 79, "total_steps": 519, "loss": 0.4918, "lr": 7.934199498878005e-05, "epoch": 0.455988455988456, "percentage": 15.22, "elapsed_time": "1:07:37", "remaining_time": "6:16:37"}
+{"current_steps": 80, "total_steps": 519, "loss": 0.4826, "lr": 7.929249811165274e-05, "epoch": 0.46176046176046176, "percentage": 15.41, "elapsed_time": "1:08:27", "remaining_time": "6:15:40"}
+{"current_steps": 81, "total_steps": 519, "loss": 0.4828, "lr": 7.924122306162448e-05, "epoch": 0.4675324675324675, "percentage": 15.61, "elapsed_time": "1:09:17", "remaining_time": "6:14:43"}
+{"current_steps": 82, "total_steps": 519, "loss": 0.4802, "lr": 7.918817215913574e-05, "epoch": 0.4733044733044733, "percentage": 15.8, "elapsed_time": "1:10:08", "remaining_time": "6:13:46"}
+{"current_steps": 83, "total_steps": 519, "loss": 0.4844, "lr": 7.913334780499284e-05, "epoch": 0.4790764790764791, "percentage": 15.99, "elapsed_time": "1:10:58", "remaining_time": "6:12:49"}
+{"current_steps": 84, "total_steps": 519, "loss": 0.4787, "lr": 7.907675248025926e-05, "epoch": 0.48484848484848486, "percentage": 16.18, "elapsed_time": "1:11:48", "remaining_time": "6:11:52"}
+{"current_steps": 85, "total_steps": 519, "loss": 0.4851, "lr": 7.901838874614325e-05, "epoch": 0.4906204906204906, "percentage": 16.38, "elapsed_time": "1:12:38", "remaining_time": "6:10:56"}
+{"current_steps": 86, "total_steps": 519, "loss": 0.4936, "lr": 7.895825924388214e-05, "epoch": 0.4963924963924964, "percentage": 16.57, "elapsed_time": "1:13:30", "remaining_time": "6:10:07"}
+{"current_steps": 87, "total_steps": 519, "loss": 0.4827, "lr": 7.889636669462257e-05, "epoch": 0.5021645021645021, "percentage": 16.76, "elapsed_time": "1:14:31", "remaining_time": "6:10:04"}
+{"current_steps": 88, "total_steps": 519, "loss": 0.492, "lr": 7.883271389929755e-05, "epoch": 0.5079365079365079, "percentage": 16.96, "elapsed_time": "1:15:21", "remaining_time": "6:09:07"}
+{"current_steps": 89, "total_steps": 519, "loss": 0.4878, "lr": 7.87673037384996e-05, "epoch": 0.5137085137085137, "percentage": 17.15, "elapsed_time": "1:16:12", "remaining_time": "6:08:10"}
+{"current_steps": 90, "total_steps": 519, "loss": 0.4869, "lr": 7.870013917235039e-05, "epoch": 0.5194805194805194, "percentage": 17.34, "elapsed_time": "1:17:02", "remaining_time": "6:07:13"}
+{"current_steps": 91, "total_steps": 519, "loss": 0.4856, "lr": 7.86312232403668e-05, "epoch": 0.5252525252525253, "percentage": 17.53, "elapsed_time": "1:17:52", "remaining_time": "6:06:16"}
+{"current_steps": 92, "total_steps": 519, "loss": 0.4836, "lr": 7.856055906132337e-05, "epoch": 0.5310245310245311, "percentage": 17.73, "elapsed_time": "1:18:42", "remaining_time": "6:05:20"}
+{"current_steps": 93, "total_steps": 519, "loss": 0.4681, "lr": 7.848814983311114e-05, "epoch": 0.5367965367965368, "percentage": 17.92, "elapsed_time": "1:19:33", "remaining_time": "6:04:23"}
+{"current_steps": 94, "total_steps": 519, "loss": 0.4857, "lr": 7.841399883259298e-05, "epoch": 0.5425685425685426, "percentage": 18.11, "elapsed_time": "1:20:23", "remaining_time": "6:03:26"}
+{"current_steps": 95, "total_steps": 519, "loss": 0.4781, "lr": 7.833810941545525e-05, "epoch": 0.5483405483405484, "percentage": 18.3, "elapsed_time": "1:21:13", "remaining_time": "6:02:30"}
+{"current_steps": 96, "total_steps": 519, "loss": 0.4843, "lr": 7.826048501605592e-05, "epoch": 0.5541125541125541, "percentage": 18.5, "elapsed_time": "1:22:03", "remaining_time": "6:01:34"}
+{"current_steps": 97, "total_steps": 519, "loss": 0.4876, "lr": 7.818112914726922e-05, "epoch": 0.5598845598845599, "percentage": 18.69, "elapsed_time": "1:22:53", "remaining_time": "6:00:39"}
+{"current_steps": 98, "total_steps": 519, "loss": 0.4847, "lr": 7.81000454003266e-05, "epoch": 0.5656565656565656, "percentage": 18.88, "elapsed_time": "1:23:44", "remaining_time": "5:59:43"}
+{"current_steps": 99, "total_steps": 519, "loss": 0.4759, "lr": 7.801723744465427e-05, "epoch": 0.5714285714285714, "percentage": 19.08, "elapsed_time": "1:24:34", "remaining_time": "5:58:48"}
+{"current_steps": 100, "total_steps": 519, "loss": 0.4751, "lr": 7.793270902770707e-05, "epoch": 0.5772005772005772, "percentage": 19.27, "elapsed_time": "1:25:24", "remaining_time": "5:57:53"}
+{"current_steps": 101, "total_steps": 519, "loss": 0.481, "lr": 7.784646397479892e-05, "epoch": 0.5829725829725829, "percentage": 19.46, "elapsed_time": "1:26:18", "remaining_time": "5:57:12"}
+{"current_steps": 102, "total_steps": 519, "loss": 0.4785, "lr": 7.775850618892973e-05, "epoch": 0.5887445887445888, "percentage": 19.65, "elapsed_time": "1:27:17", "remaining_time": "5:56:53"}
+{"current_steps": 103, "total_steps": 519, "loss": 0.4775, "lr": 7.766883965060871e-05, "epoch": 0.5945165945165946, "percentage": 19.85, "elapsed_time": "1:28:08", "remaining_time": "5:55:57"}
+{"current_steps": 104, "total_steps": 519, "loss": 0.4881, "lr": 7.757746841767431e-05, "epoch": 0.6002886002886003, "percentage": 20.04, "elapsed_time": "1:28:58", "remaining_time": "5:55:01"}
+{"current_steps": 105, "total_steps": 519, "loss": 0.4751, "lr": 7.748439662511049e-05, "epoch": 0.6060606060606061, "percentage": 20.23, "elapsed_time": "1:29:48", "remaining_time": "5:54:06"}
+{"current_steps": 106, "total_steps": 519, "loss": 0.4739, "lr": 7.738962848485967e-05, "epoch": 0.6118326118326118, "percentage": 20.42, "elapsed_time": "1:30:38", "remaining_time": "5:53:10"}
+{"current_steps": 107, "total_steps": 519, "loss": 0.476, "lr": 7.729316828563207e-05, "epoch": 0.6176046176046176, "percentage": 20.62, "elapsed_time": "1:31:29", "remaining_time": "5:52:15"}
+{"current_steps": 108, "total_steps": 519, "loss": 0.4737, "lr": 7.71950203927117e-05, "epoch": 0.6233766233766234, "percentage": 20.81, "elapsed_time": "1:32:19", "remaining_time": "5:51:20"}
+{"current_steps": 109, "total_steps": 519, "loss": 0.4815, "lr": 7.709518924775869e-05, "epoch": 0.6291486291486291, "percentage": 21.0, "elapsed_time": "1:33:09", "remaining_time": "5:50:25"}
+{"current_steps": 110, "total_steps": 519, "loss": 0.467, "lr": 7.69936793686084e-05, "epoch": 0.6349206349206349, "percentage": 21.19, "elapsed_time": "1:33:59", "remaining_time": "5:49:29"}
+{"current_steps": 111, "total_steps": 519, "loss": 0.4681, "lr": 7.689049534906688e-05, "epoch": 0.6406926406926406, "percentage": 21.39, "elapsed_time": "1:34:50", "remaining_time": "5:48:34"}
+{"current_steps": 112, "total_steps": 519, "loss": 0.4765, "lr": 7.678564185870306e-05, "epoch": 0.6464646464646465, "percentage": 21.58, "elapsed_time": "1:35:40", "remaining_time": "5:47:39"}
+{"current_steps": 113, "total_steps": 519, "loss": 0.4786, "lr": 7.667912364263734e-05, "epoch": 0.6522366522366523, "percentage": 21.77, "elapsed_time": "1:36:30", "remaining_time": "5:46:45"}
+{"current_steps": 114, "total_steps": 519, "loss": 0.4662, "lr": 7.657094552132692e-05, "epoch": 0.658008658008658, "percentage": 21.97, "elapsed_time": "1:37:20", "remaining_time": "5:45:49"}
+{"current_steps": 115, "total_steps": 519, "loss": 0.476, "lr": 7.646111239034762e-05, "epoch": 0.6637806637806638, "percentage": 22.16, "elapsed_time": "1:38:11", "remaining_time": "5:44:55"}
+{"current_steps": 116, "total_steps": 519, "loss": 0.4783, "lr": 7.634962922017234e-05, "epoch": 0.6695526695526696, "percentage": 22.35, "elapsed_time": "1:39:05", "remaining_time": "5:44:17"}
+{"current_steps": 117, "total_steps": 519, "loss": 0.4676, "lr": 7.623650105594616e-05, "epoch": 0.6753246753246753, "percentage": 22.54, "elapsed_time": "1:40:05", "remaining_time": "5:43:54"}
+{"current_steps": 118, "total_steps": 519, "loss": 0.4722, "lr": 7.612173301725791e-05, "epoch": 0.6810966810966811, "percentage": 22.74, "elapsed_time": "1:40:55", "remaining_time": "5:42:58"}
+{"current_steps": 119, "total_steps": 519, "loss": 0.4707, "lr": 7.600533029790859e-05, "epoch": 0.6868686868686869, "percentage": 22.93, "elapsed_time": "1:41:45", "remaining_time": "5:42:04"}
+{"current_steps": 120, "total_steps": 519, "loss": 0.4729, "lr": 7.588729816567634e-05, "epoch": 0.6926406926406926, "percentage": 23.12, "elapsed_time": "1:42:36", "remaining_time": "5:41:09"}
+{"current_steps": 121, "total_steps": 519, "loss": 0.4722, "lr": 7.576764196207793e-05, "epoch": 0.6984126984126984, "percentage": 23.31, "elapsed_time": "1:43:26", "remaining_time": "5:40:14"}
+{"current_steps": 122, "total_steps": 519, "loss": 0.4703, "lr": 7.564636710212717e-05, "epoch": 0.7041847041847041, "percentage": 23.51, "elapsed_time": "1:44:16", "remaining_time": "5:39:19"}
+{"current_steps": 123, "total_steps": 519, "loss": 0.4617, "lr": 7.552347907408973e-05, "epoch": 0.70995670995671, "percentage": 23.7, "elapsed_time": "1:45:06", "remaining_time": "5:38:25"}
+{"current_steps": 124, "total_steps": 519, "loss": 0.4644, "lr": 7.539898343923487e-05, "epoch": 0.7157287157287158, "percentage": 23.89, "elapsed_time": "1:45:57", "remaining_time": "5:37:30"}
+{"current_steps": 125, "total_steps": 519, "loss": 0.466, "lr": 7.527288583158371e-05, "epoch": 0.7215007215007215, "percentage": 24.08, "elapsed_time": "1:46:47", "remaining_time": "5:36:35"}
+{"current_steps": 126, "total_steps": 519, "loss": 0.4691, "lr": 7.514519195765428e-05, "epoch": 0.7272727272727273, "percentage": 24.28, "elapsed_time": "1:47:37", "remaining_time": "5:35:41"}
+{"current_steps": 127, "total_steps": 519, "loss": 0.4698, "lr": 7.501590759620324e-05, "epoch": 0.733044733044733, "percentage": 24.47, "elapsed_time": "1:48:27", "remaining_time": "5:34:47"}
+{"current_steps": 128, "total_steps": 519, "loss": 0.4595, "lr": 7.488503859796446e-05, "epoch": 0.7388167388167388, "percentage": 24.66, "elapsed_time": "1:49:18", "remaining_time": "5:33:52"}
+{"current_steps": 129, "total_steps": 519, "loss": 0.4574, "lr": 7.475259088538412e-05, "epoch": 0.7445887445887446, "percentage": 24.86, "elapsed_time": "1:50:08", "remaining_time": "5:32:58"}
+{"current_steps": 130, "total_steps": 519, "loss": 0.4608, "lr": 7.461857045235278e-05, "epoch": 0.7503607503607503, "percentage": 25.05, "elapsed_time": "1:50:58", "remaining_time": "5:32:04"}
+{"current_steps": 131, "total_steps": 519, "loss": 0.466, "lr": 7.448298336393409e-05, "epoch": 0.7561327561327561, "percentage": 25.24, "elapsed_time": "1:51:55", "remaining_time": "5:31:29"}
+{"current_steps": 132, "total_steps": 519, "loss": 0.4642, "lr": 7.434583575609034e-05, "epoch": 0.7619047619047619, "percentage": 25.43, "elapsed_time": "1:52:53", "remaining_time": "5:30:57"}
+{"current_steps": 133, "total_steps": 519, "loss": 0.4653, "lr": 7.420713383540476e-05, "epoch": 0.7676767676767676, "percentage": 25.63, "elapsed_time": "1:53:43", "remaining_time": "5:30:03"}
+{"current_steps": 134, "total_steps": 519, "loss": 0.4527, "lr": 7.406688387880064e-05, "epoch": 0.7734487734487735, "percentage": 25.82, "elapsed_time": "1:54:33", "remaining_time": "5:29:08"}
+{"current_steps": 135, "total_steps": 519, "loss": 0.4579, "lr": 7.392509223325727e-05, "epoch": 0.7792207792207793, "percentage": 26.01, "elapsed_time": "1:55:23", "remaining_time": "5:28:14"}
+{"current_steps": 136, "total_steps": 519, "loss": 0.4591, "lr": 7.378176531552272e-05, "epoch": 0.784992784992785, "percentage": 26.2, "elapsed_time": "1:56:14", "remaining_time": "5:27:20"}
+{"current_steps": 137, "total_steps": 519, "loss": 0.4554, "lr": 7.363690961182348e-05, "epoch": 0.7907647907647908, "percentage": 26.4, "elapsed_time": "1:57:04", "remaining_time": "5:26:26"}
+{"current_steps": 138, "total_steps": 519, "loss": 0.4505, "lr": 7.349053167757087e-05, "epoch": 0.7965367965367965, "percentage": 26.59, "elapsed_time": "1:57:54", "remaining_time": "5:25:32"}
+{"current_steps": 139, "total_steps": 519, "loss": 0.457, "lr": 7.334263813706438e-05, "epoch": 0.8023088023088023, "percentage": 26.78, "elapsed_time": "1:58:44", "remaining_time": "5:24:38"}
+{"current_steps": 140, "total_steps": 519, "loss": 0.4536, "lr": 7.319323568319195e-05, "epoch": 0.8080808080808081, "percentage": 26.97, "elapsed_time": "1:59:35", "remaining_time": "5:23:44"}
+{"current_steps": 141, "total_steps": 519, "loss": 0.4582, "lr": 7.304233107712699e-05, "epoch": 0.8138528138528138, "percentage": 27.17, "elapsed_time": "2:00:25", "remaining_time": "5:22:50"}
+{"current_steps": 142, "total_steps": 519, "loss": 0.4636, "lr": 7.288993114802251e-05, "epoch": 0.8196248196248196, "percentage": 27.36, "elapsed_time": "2:01:15", "remaining_time": "5:21:56"}
+{"current_steps": 143, "total_steps": 519, "loss": 0.4491, "lr": 7.273604279270203e-05, "epoch": 0.8253968253968254, "percentage": 27.55, "elapsed_time": "2:02:05", "remaining_time": "5:21:02"}
+{"current_steps": 144, "total_steps": 519, "loss": 0.4509, "lr": 7.25806729753474e-05, "epoch": 0.8311688311688312, "percentage": 27.75, "elapsed_time": "2:02:56", "remaining_time": "5:20:09"}
+{"current_steps": 145, "total_steps": 519, "loss": 0.4474, "lr": 7.242382872718371e-05, "epoch": 0.836940836940837, "percentage": 27.94, "elapsed_time": "2:03:46", "remaining_time": "5:19:16"}
+{"current_steps": 146, "total_steps": 519, "loss": 0.4562, "lr": 7.226551714616111e-05, "epoch": 0.8427128427128427, "percentage": 28.13, "elapsed_time": "2:04:47", "remaining_time": "5:18:48"}
+{"current_steps": 147, "total_steps": 519, "loss": 0.4482, "lr": 7.210574539663351e-05, "epoch": 0.8484848484848485, "percentage": 28.32, "elapsed_time": "2:05:41", "remaining_time": "5:18:05"}
+{"current_steps": 148, "total_steps": 519, "loss": 0.4488, "lr": 7.194452070903443e-05, "epoch": 0.8542568542568543, "percentage": 28.52, "elapsed_time": "2:06:32", "remaining_time": "5:17:11"}
+{"current_steps": 149, "total_steps": 519, "loss": 0.4441, "lr": 7.178185037954977e-05, "epoch": 0.86002886002886, "percentage": 28.71, "elapsed_time": "2:07:22", "remaining_time": "5:16:17"}
+{"current_steps": 150, "total_steps": 519, "loss": 0.4487, "lr": 7.16177417697876e-05, "epoch": 0.8658008658008658, "percentage": 28.9, "elapsed_time": "2:08:12", "remaining_time": "5:15:23"}
+{"current_steps": 151, "total_steps": 519, "loss": 0.4464, "lr": 7.145220230644507e-05, "epoch": 0.8715728715728716, "percentage": 29.09, "elapsed_time": "2:09:02", "remaining_time": "5:14:29"}
+{"current_steps": 152, "total_steps": 519, "loss": 0.4505, "lr": 7.128523948097222e-05, "epoch": 0.8773448773448773, "percentage": 29.29, "elapsed_time": "2:09:53", "remaining_time": "5:13:36"}
+{"current_steps": 153, "total_steps": 519, "loss": 0.4499, "lr": 7.111686084923306e-05, "epoch": 0.8831168831168831, "percentage": 29.48, "elapsed_time": "2:10:43", "remaining_time": "5:12:42"}
+{"current_steps": 154, "total_steps": 519, "loss": 0.449, "lr": 7.094707403116356e-05, "epoch": 0.8888888888888888, "percentage": 29.67, "elapsed_time": "2:11:33", "remaining_time": "5:11:48"}
+{"current_steps": 155, "total_steps": 519, "loss": 0.4462, "lr": 7.077588671042686e-05, "epoch": 0.8946608946608947, "percentage": 29.87, "elapsed_time": "2:12:23", "remaining_time": "5:10:55"}
+{"current_steps": 156, "total_steps": 519, "loss": 0.4359, "lr": 7.06033066340655e-05, "epoch": 0.9004329004329005, "percentage": 30.06, "elapsed_time": "2:13:14", "remaining_time": "5:10:01"}
+{"current_steps": 157, "total_steps": 519, "loss": 0.4556, "lr": 7.042934161215085e-05, "epoch": 0.9062049062049062, "percentage": 30.25, "elapsed_time": "2:14:04", "remaining_time": "5:09:08"}
+{"current_steps": 158, "total_steps": 519, "loss": 0.4509, "lr": 7.02539995174297e-05, "epoch": 0.911976911976912, "percentage": 30.44, "elapsed_time": "2:14:54", "remaining_time": "5:08:14"}
+{"current_steps": 159, "total_steps": 519, "loss": 0.4512, "lr": 7.007728828496793e-05, "epoch": 0.9177489177489178, "percentage": 30.64, "elapsed_time": "2:15:45", "remaining_time": "5:07:22"}
+{"current_steps": 160, "total_steps": 519, "loss": 0.4462, "lr": 6.989921591179145e-05, "epoch": 0.9235209235209235, "percentage": 30.83, "elapsed_time": "2:16:36", "remaining_time": "5:06:29"}
+{"current_steps": 161, "total_steps": 519, "loss": 0.4512, "lr": 6.97197904565242e-05, "epoch": 0.9292929292929293, "percentage": 31.02, "elapsed_time": "2:17:38", "remaining_time": "5:06:04"}
+{"current_steps": 162, "total_steps": 519, "loss": 0.4491, "lr": 6.953902003902368e-05, "epoch": 0.935064935064935, "percentage": 31.21, "elapsed_time": "2:18:31", "remaining_time": "5:05:16"}
+{"current_steps": 163, "total_steps": 519, "loss": 0.4489, "lr": 6.935691284001322e-05, "epoch": 0.9408369408369408, "percentage": 31.41, "elapsed_time": "2:19:21", "remaining_time": "5:04:22"}
+{"current_steps": 164, "total_steps": 519, "loss": 0.4421, "lr": 6.917347710071193e-05, "epoch": 0.9466089466089466, "percentage": 31.6, "elapsed_time": "2:20:11", "remaining_time": "5:03:28"}
+{"current_steps": 165, "total_steps": 519, "loss": 0.4407, "lr": 6.898872112246172e-05, "epoch": 0.9523809523809523, "percentage": 31.79, "elapsed_time": "2:21:02", "remaining_time": "5:02:35"}
+{"current_steps": 166, "total_steps": 519, "loss": 0.447, "lr": 6.880265326635159e-05, "epoch": 0.9581529581529582, "percentage": 31.98, "elapsed_time": "2:21:52", "remaining_time": "5:01:41"}
+{"current_steps": 167, "total_steps": 519, "loss": 0.4364, "lr": 6.861528195283924e-05, "epoch": 0.963924963924964, "percentage": 32.18, "elapsed_time": "2:22:42", "remaining_time": "5:00:48"}
+{"current_steps": 168, "total_steps": 519, "loss": 0.4383, "lr": 6.842661566137011e-05, "epoch": 0.9696969696969697, "percentage": 32.37, "elapsed_time": "2:23:33", "remaining_time": "4:59:55"}
+{"current_steps": 169, "total_steps": 519, "loss": 0.4469, "lr": 6.82366629299935e-05, "epoch": 0.9754689754689755, "percentage": 32.56, "elapsed_time": "2:24:23", "remaining_time": "4:59:01"}
+{"current_steps": 170, "total_steps": 519, "loss": 0.4383, "lr": 6.804543235497625e-05, "epoch": 0.9812409812409812, "percentage": 32.76, "elapsed_time": "2:25:13", "remaining_time": "4:58:08"}
+{"current_steps": 171, "total_steps": 519, "loss": 0.4349, "lr": 6.785293259041376e-05, "epoch": 0.987012987012987, "percentage": 32.95, "elapsed_time": "2:26:03", "remaining_time": "4:57:15"}
+{"current_steps": 172, "total_steps": 519, "loss": 0.4428, "lr": 6.76591723478383e-05, "epoch": 0.9927849927849928, "percentage": 33.14, "elapsed_time": "2:26:53", "remaining_time": "4:56:21"}
+{"current_steps": 173, "total_steps": 519, "loss": 0.4398, "lr": 6.746416039582474e-05, "epoch": 0.9985569985569985, "percentage": 33.33, "elapsed_time": "2:27:44", "remaining_time": "4:55:28"}
+{"current_steps": 174, "total_steps": 519, "loss": 0.7514, "lr": 6.726790555959383e-05, "epoch": 1.0043290043290043, "percentage": 33.53, "elapsed_time": "2:29:50", "remaining_time": "4:57:06"}
+{"current_steps": 175, "total_steps": 519, "loss": 0.4277, "lr": 6.707041672061271e-05, "epoch": 1.0101010101010102, "percentage": 33.72, "elapsed_time": "2:30:41", "remaining_time": "4:56:13"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07783bd767da1c872e2aacd190059d595cd743746ed74e2f6c8a627c1fbe0bf0
+size 7160