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:c75469354b4bbb357c6f4fec88a2971a1817c1df851970ace847328c1fd922df
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3bae3d108c4e13e0027591781c44540e249b25123376f20fbbad586815d9445
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b770be08cc403f8dd36388fcc92cd614861adba355da14e9e0d5390de36481
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf3bf52e34e068bd5998f0b8b21b6288e251b6cc2f924507afd46837f60f70b
+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 +1,168 @@
+{"current_steps": 1, "total_steps": 498, "loss": 1.2696, "lr": 2.0000000000000002e-07, "epoch": 0.006, "percentage": 0.2, "elapsed_time": "0:01:04", "remaining_time": "8:52:53"}
+{"current_steps": 2, "total_steps": 498, "loss": 1.2574, "lr": 4.0000000000000003e-07, "epoch": 0.012, "percentage": 0.4, "elapsed_time": "0:02:02", "remaining_time": "8:25:10"}
+{"current_steps": 3, "total_steps": 498, "loss": 1.2562, "lr": 6.000000000000001e-07, "epoch": 0.018, "percentage": 0.6, "elapsed_time": "0:02:57", "remaining_time": "8:08:09"}
+{"current_steps": 4, "total_steps": 498, "loss": 1.2938, "lr": 8.000000000000001e-07, "epoch": 0.024, "percentage": 0.8, "elapsed_time": "0:03:55", "remaining_time": "8:05:25"}
+{"current_steps": 5, "total_steps": 498, "loss": 1.2508, "lr": 1.0000000000000002e-06, "epoch": 0.03, "percentage": 1.0, "elapsed_time": "0:04:54", "remaining_time": "8:04:32"}
+{"current_steps": 6, "total_steps": 498, "loss": 1.2622, "lr": 1.2000000000000002e-06, "epoch": 0.036, "percentage": 1.2, "elapsed_time": "0:05:50", "remaining_time": "7:58:57"}
+{"current_steps": 7, "total_steps": 498, "loss": 1.2409, "lr": 1.4000000000000001e-06, "epoch": 0.042, "percentage": 1.41, "elapsed_time": "0:06:47", "remaining_time": "7:55:55"}
+{"current_steps": 8, "total_steps": 498, "loss": 1.2019, "lr": 1.6000000000000001e-06, "epoch": 0.048, "percentage": 1.61, "elapsed_time": "0:07:39", "remaining_time": "7:48:54"}
+{"current_steps": 9, "total_steps": 498, "loss": 1.1884, "lr": 1.8000000000000001e-06, "epoch": 0.054, "percentage": 1.81, "elapsed_time": "0:08:42", "remaining_time": "7:52:43"}
+{"current_steps": 10, "total_steps": 498, "loss": 1.2281, "lr": 2.0000000000000003e-06, "epoch": 0.06, "percentage": 2.01, "elapsed_time": "0:09:42", "remaining_time": "7:53:36"}
+{"current_steps": 11, "total_steps": 498, "loss": 1.1239, "lr": 2.2e-06, "epoch": 0.066, "percentage": 2.21, "elapsed_time": "0:10:38", "remaining_time": "7:50:46"}
+{"current_steps": 12, "total_steps": 498, "loss": 1.1911, "lr": 2.4000000000000003e-06, "epoch": 0.072, "percentage": 2.41, "elapsed_time": "0:11:34", "remaining_time": "7:48:51"}
+{"current_steps": 13, "total_steps": 498, "loss": 1.1153, "lr": 2.6e-06, "epoch": 0.078, "percentage": 2.61, "elapsed_time": "0:12:23", "remaining_time": "7:42:19"}
+{"current_steps": 14, "total_steps": 498, "loss": 1.1497, "lr": 2.8000000000000003e-06, "epoch": 0.084, "percentage": 2.81, "elapsed_time": "0:13:14", "remaining_time": "7:37:31"}
+{"current_steps": 15, "total_steps": 498, "loss": 1.1334, "lr": 3e-06, "epoch": 0.09, "percentage": 3.01, "elapsed_time": "0:14:14", "remaining_time": "7:38:28"}
+{"current_steps": 16, "total_steps": 498, "loss": 1.1403, "lr": 3.2000000000000003e-06, "epoch": 0.096, "percentage": 3.21, "elapsed_time": "0:15:00", "remaining_time": "7:32:11"}
+{"current_steps": 17, "total_steps": 498, "loss": 1.1283, "lr": 3.4000000000000005e-06, "epoch": 0.102, "percentage": 3.41, "elapsed_time": "0:15:47", "remaining_time": "7:26:34"}
+{"current_steps": 18, "total_steps": 498, "loss": 1.0746, "lr": 3.6000000000000003e-06, "epoch": 0.108, "percentage": 3.61, "elapsed_time": "0:16:35", "remaining_time": "7:22:29"}
+{"current_steps": 19, "total_steps": 498, "loss": 1.1355, "lr": 3.8000000000000005e-06, "epoch": 0.114, "percentage": 3.82, "elapsed_time": "0:17:28", "remaining_time": "7:20:37"}
+{"current_steps": 20, "total_steps": 498, "loss": 1.0489, "lr": 4.000000000000001e-06, "epoch": 0.12, "percentage": 4.02, "elapsed_time": "0:18:23", "remaining_time": "7:19:41"}
+{"current_steps": 21, "total_steps": 498, "loss": 1.0639, "lr": 4.2000000000000004e-06, "epoch": 0.126, "percentage": 4.22, "elapsed_time": "0:19:23", "remaining_time": "7:20:26"}
+{"current_steps": 22, "total_steps": 498, "loss": 1.0202, "lr": 4.4e-06, "epoch": 0.132, "percentage": 4.42, "elapsed_time": "0:20:17", "remaining_time": "7:18:56"}
+{"current_steps": 23, "total_steps": 498, "loss": 1.029, "lr": 4.600000000000001e-06, "epoch": 0.138, "percentage": 4.62, "elapsed_time": "0:21:08", "remaining_time": "7:16:35"}
+{"current_steps": 24, "total_steps": 498, "loss": 1.0487, "lr": 4.800000000000001e-06, "epoch": 0.144, "percentage": 4.82, "elapsed_time": "0:22:03", "remaining_time": "7:15:47"}
+{"current_steps": 25, "total_steps": 498, "loss": 0.996, "lr": 5e-06, "epoch": 0.15, "percentage": 5.02, "elapsed_time": "0:22:57", "remaining_time": "7:14:16"}
+{"current_steps": 26, "total_steps": 498, "loss": 0.9986, "lr": 5.2e-06, "epoch": 0.156, "percentage": 5.22, "elapsed_time": "0:23:52", "remaining_time": "7:13:20"}
+{"current_steps": 27, "total_steps": 498, "loss": 1.01, "lr": 5.400000000000001e-06, "epoch": 0.162, "percentage": 5.42, "elapsed_time": "0:24:45", "remaining_time": "7:11:45"}
+{"current_steps": 28, "total_steps": 498, "loss": 1.022, "lr": 5.600000000000001e-06, "epoch": 0.168, "percentage": 5.62, "elapsed_time": "0:25:43", "remaining_time": "7:11:51"}
+{"current_steps": 29, "total_steps": 498, "loss": 0.9666, "lr": 5.8e-06, "epoch": 0.174, "percentage": 5.82, "elapsed_time": "0:26:30", "remaining_time": "7:08:48"}
+{"current_steps": 30, "total_steps": 498, "loss": 1.0246, "lr": 6e-06, "epoch": 0.18, "percentage": 6.02, "elapsed_time": "0:27:29", "remaining_time": "7:08:57"}
+{"current_steps": 31, "total_steps": 498, "loss": 0.9475, "lr": 6.200000000000001e-06, "epoch": 0.186, "percentage": 6.22, "elapsed_time": "0:28:23", "remaining_time": "7:07:37"}
+{"current_steps": 32, "total_steps": 498, "loss": 0.9389, "lr": 6.4000000000000006e-06, "epoch": 0.192, "percentage": 6.43, "elapsed_time": "0:29:12", "remaining_time": "7:05:18"}
+{"current_steps": 33, "total_steps": 498, "loss": 0.9617, "lr": 6.600000000000001e-06, "epoch": 0.198, "percentage": 6.63, "elapsed_time": "0:30:03", "remaining_time": "7:03:31"}
+{"current_steps": 34, "total_steps": 498, "loss": 0.958, "lr": 6.800000000000001e-06, "epoch": 0.204, "percentage": 6.83, "elapsed_time": "0:30:58", "remaining_time": "7:02:47"}
+{"current_steps": 35, "total_steps": 498, "loss": 0.967, "lr": 7e-06, "epoch": 0.21, "percentage": 7.03, "elapsed_time": "0:31:53", "remaining_time": "7:01:48"}
+{"current_steps": 36, "total_steps": 498, "loss": 0.9741, "lr": 7.2000000000000005e-06, "epoch": 0.216, "percentage": 7.23, "elapsed_time": "0:32:45", "remaining_time": "7:00:25"}
+{"current_steps": 37, "total_steps": 498, "loss": 0.9337, "lr": 7.4e-06, "epoch": 0.222, "percentage": 7.43, "elapsed_time": "0:33:39", "remaining_time": "6:59:16"}
+{"current_steps": 38, "total_steps": 498, "loss": 0.9611, "lr": 7.600000000000001e-06, "epoch": 0.228, "percentage": 7.63, "elapsed_time": "0:34:32", "remaining_time": "6:58:07"}
+{"current_steps": 39, "total_steps": 498, "loss": 0.9655, "lr": 7.800000000000002e-06, "epoch": 0.234, "percentage": 7.83, "elapsed_time": "0:35:32", "remaining_time": "6:58:20"}
+{"current_steps": 40, "total_steps": 498, "loss": 0.9412, "lr": 8.000000000000001e-06, "epoch": 0.24, "percentage": 8.03, "elapsed_time": "0:36:22", "remaining_time": "6:56:25"}
+{"current_steps": 41, "total_steps": 498, "loss": 0.9366, "lr": 8.2e-06, "epoch": 0.246, "percentage": 8.23, "elapsed_time": "0:37:11", "remaining_time": "6:54:32"}
+{"current_steps": 42, "total_steps": 498, "loss": 0.9556, "lr": 8.400000000000001e-06, "epoch": 0.252, "percentage": 8.43, "elapsed_time": "0:38:09", "remaining_time": "6:54:12"}
+{"current_steps": 43, "total_steps": 498, "loss": 0.9534, "lr": 8.6e-06, "epoch": 0.258, "percentage": 8.63, "elapsed_time": "0:39:04", "remaining_time": "6:53:31"}
+{"current_steps": 44, "total_steps": 498, "loss": 0.9778, "lr": 8.8e-06, "epoch": 0.264, "percentage": 8.84, "elapsed_time": "0:39:55", "remaining_time": "6:52:01"}
+{"current_steps": 45, "total_steps": 498, "loss": 0.9147, "lr": 9e-06, "epoch": 0.27, "percentage": 9.04, "elapsed_time": "0:40:55", "remaining_time": "6:52:02"}
+{"current_steps": 46, "total_steps": 498, "loss": 0.9265, "lr": 9.200000000000002e-06, "epoch": 0.276, "percentage": 9.24, "elapsed_time": "0:41:47", "remaining_time": "6:50:34"}
+{"current_steps": 47, "total_steps": 498, "loss": 0.9426, "lr": 9.4e-06, "epoch": 0.282, "percentage": 9.44, "elapsed_time": "0:42:54", "remaining_time": "6:51:41"}
+{"current_steps": 48, "total_steps": 498, "loss": 0.9417, "lr": 9.600000000000001e-06, "epoch": 0.288, "percentage": 9.64, "elapsed_time": "0:43:51", "remaining_time": "6:51:13"}
+{"current_steps": 49, "total_steps": 498, "loss": 0.9448, "lr": 9.800000000000001e-06, "epoch": 0.294, "percentage": 9.84, "elapsed_time": "0:44:50", "remaining_time": "6:50:55"}
+{"current_steps": 50, "total_steps": 498, "loss": 0.9279, "lr": 1e-05, "epoch": 0.3, "percentage": 10.04, "elapsed_time": "0:45:47", "remaining_time": "6:50:16"}
+{"current_steps": 51, "total_steps": 498, "loss": 0.9508, "lr": 9.999877063188124e-06, "epoch": 0.306, "percentage": 10.24, "elapsed_time": "0:46:45", "remaining_time": "6:49:46"}
+{"current_steps": 52, "total_steps": 498, "loss": 0.9041, "lr": 9.999508258797876e-06, "epoch": 0.312, "percentage": 10.44, "elapsed_time": "0:47:29", "remaining_time": "6:47:23"}
+{"current_steps": 53, "total_steps": 498, "loss": 0.9314, "lr": 9.998893604965111e-06, "epoch": 0.318, "percentage": 10.64, "elapsed_time": "0:48:26", "remaining_time": "6:46:42"}
+{"current_steps": 54, "total_steps": 498, "loss": 0.9362, "lr": 9.998033131915266e-06, "epoch": 0.324, "percentage": 10.84, "elapsed_time": "0:49:24", "remaining_time": "6:46:12"}
+{"current_steps": 55, "total_steps": 498, "loss": 0.9242, "lr": 9.996926881961862e-06, "epoch": 0.33, "percentage": 11.04, "elapsed_time": "0:50:17", "remaining_time": "6:45:06"}
+{"current_steps": 56, "total_steps": 498, "loss": 0.9422, "lr": 9.995574909504434e-06, "epoch": 0.336, "percentage": 11.24, "elapsed_time": "0:51:15", "remaining_time": "6:44:37"}
+{"current_steps": 57, "total_steps": 498, "loss": 0.9283, "lr": 9.993977281025862e-06, "epoch": 0.342, "percentage": 11.45, "elapsed_time": "0:52:06", "remaining_time": "6:43:06"}
+{"current_steps": 58, "total_steps": 498, "loss": 0.9116, "lr": 9.992134075089085e-06, "epoch": 0.348, "percentage": 11.65, "elapsed_time": "0:53:01", "remaining_time": "6:42:14"}
+{"current_steps": 59, "total_steps": 498, "loss": 0.8707, "lr": 9.990045382333243e-06, "epoch": 0.354, "percentage": 11.85, "elapsed_time": "0:53:51", "remaining_time": "6:40:47"}
+{"current_steps": 60, "total_steps": 498, "loss": 0.9255, "lr": 9.987711305469232e-06, "epoch": 0.36, "percentage": 12.05, "elapsed_time": "0:54:37", "remaining_time": "6:38:47"}
+{"current_steps": 61, "total_steps": 498, "loss": 0.9027, "lr": 9.985131959274637e-06, "epoch": 0.366, "percentage": 12.25, "elapsed_time": "0:55:32", "remaining_time": "6:37:51"}
+{"current_steps": 62, "total_steps": 498, "loss": 0.9195, "lr": 9.982307470588097e-06, "epoch": 0.372, "percentage": 12.45, "elapsed_time": "0:56:31", "remaining_time": "6:37:29"}
+{"current_steps": 63, "total_steps": 498, "loss": 0.9432, "lr": 9.979237978303066e-06, "epoch": 0.378, "percentage": 12.65, "elapsed_time": "0:57:25", "remaining_time": "6:36:33"}
+{"current_steps": 64, "total_steps": 498, "loss": 0.9259, "lr": 9.975923633360985e-06, "epoch": 0.384, "percentage": 12.85, "elapsed_time": "0:58:16", "remaining_time": "6:35:08"}
+{"current_steps": 65, "total_steps": 498, "loss": 0.8883, "lr": 9.972364598743851e-06, "epoch": 0.39, "percentage": 13.05, "elapsed_time": "0:59:17", "remaining_time": "6:34:56"}
+{"current_steps": 66, "total_steps": 498, "loss": 0.8914, "lr": 9.968561049466214e-06, "epoch": 0.396, "percentage": 13.25, "elapsed_time": "1:00:12", "remaining_time": "6:34:06"}
+{"current_steps": 67, "total_steps": 498, "loss": 0.8648, "lr": 9.96451317256656e-06, "epoch": 0.402, "percentage": 13.45, "elapsed_time": "1:00:59", "remaining_time": "6:32:24"}
+{"current_steps": 68, "total_steps": 498, "loss": 0.9126, "lr": 9.960221167098124e-06, "epoch": 0.408, "percentage": 13.65, "elapsed_time": "1:01:53", "remaining_time": "6:31:20"}
+{"current_steps": 69, "total_steps": 498, "loss": 0.8957, "lr": 9.955685244119092e-06, "epoch": 0.414, "percentage": 13.86, "elapsed_time": "1:02:47", "remaining_time": "6:30:22"}
+{"current_steps": 70, "total_steps": 498, "loss": 0.8948, "lr": 9.950905626682229e-06, "epoch": 0.42, "percentage": 14.06, "elapsed_time": "1:03:33", "remaining_time": "6:28:39"}
+{"current_steps": 71, "total_steps": 498, "loss": 0.911, "lr": 9.945882549823906e-06, "epoch": 0.426, "percentage": 14.26, "elapsed_time": "1:04:19", "remaining_time": "6:26:53"}
+{"current_steps": 72, "total_steps": 498, "loss": 0.8891, "lr": 9.940616260552545e-06, "epoch": 0.432, "percentage": 14.46, "elapsed_time": "1:05:11", "remaining_time": "6:25:40"}
+{"current_steps": 73, "total_steps": 498, "loss": 0.9046, "lr": 9.935107017836472e-06, "epoch": 0.438, "percentage": 14.66, "elapsed_time": "1:06:05", "remaining_time": "6:24:44"}
+{"current_steps": 74, "total_steps": 498, "loss": 0.8906, "lr": 9.92935509259118e-06, "epoch": 0.444, "percentage": 14.86, "elapsed_time": "1:06:59", "remaining_time": "6:23:49"}
+{"current_steps": 75, "total_steps": 498, "loss": 0.9212, "lr": 9.92336076766601e-06, "epoch": 0.45, "percentage": 15.06, "elapsed_time": "1:07:56", "remaining_time": "6:23:13"}
+{"current_steps": 76, "total_steps": 498, "loss": 0.9124, "lr": 9.917124337830242e-06, "epoch": 0.456, "percentage": 15.26, "elapsed_time": "1:08:53", "remaining_time": "6:22:32"}
+{"current_steps": 77, "total_steps": 498, "loss": 0.9014, "lr": 9.910646109758596e-06, "epoch": 0.462, "percentage": 15.46, "elapsed_time": "1:09:48", "remaining_time": "6:21:38"}
+{"current_steps": 78, "total_steps": 498, "loss": 0.8854, "lr": 9.903926402016153e-06, "epoch": 0.468, "percentage": 15.66, "elapsed_time": "1:10:38", "remaining_time": "6:20:25"}
+{"current_steps": 79, "total_steps": 498, "loss": 0.9108, "lr": 9.896965545042692e-06, "epoch": 0.474, "percentage": 15.86, "elapsed_time": "1:11:31", "remaining_time": "6:19:21"}
+{"current_steps": 80, "total_steps": 498, "loss": 0.904, "lr": 9.889763881136439e-06, "epoch": 0.48, "percentage": 16.06, "elapsed_time": "1:12:20", "remaining_time": "6:17:58"}
+{"current_steps": 81, "total_steps": 498, "loss": 0.8938, "lr": 9.882321764437234e-06, "epoch": 0.486, "percentage": 16.27, "elapsed_time": "1:13:06", "remaining_time": "6:16:24"}
+{"current_steps": 82, "total_steps": 498, "loss": 0.8863, "lr": 9.874639560909118e-06, "epoch": 0.492, "percentage": 16.47, "elapsed_time": "1:14:02", "remaining_time": "6:15:38"}
+{"current_steps": 83, "total_steps": 498, "loss": 0.9067, "lr": 9.866717648322335e-06, "epoch": 0.498, "percentage": 16.67, "elapsed_time": "1:14:59", "remaining_time": "6:14:55"}
+{"current_steps": 84, "total_steps": 498, "loss": 0.8882, "lr": 9.858556416234755e-06, "epoch": 0.504, "percentage": 16.87, "elapsed_time": "1:15:57", "remaining_time": "6:14:21"}
+{"current_steps": 85, "total_steps": 498, "loss": 0.913, "lr": 9.850156265972722e-06, "epoch": 0.51, "percentage": 17.07, "elapsed_time": "1:16:53", "remaining_time": "6:13:38"}
+{"current_steps": 86, "total_steps": 498, "loss": 0.9085, "lr": 9.841517610611309e-06, "epoch": 0.516, "percentage": 17.27, "elapsed_time": "1:17:52", "remaining_time": "6:13:03"}
+{"current_steps": 87, "total_steps": 498, "loss": 0.9203, "lr": 9.832640874954017e-06, "epoch": 0.522, "percentage": 17.47, "elapsed_time": "1:18:50", "remaining_time": "6:12:28"}
+{"current_steps": 88, "total_steps": 498, "loss": 0.8833, "lr": 9.82352649551188e-06, "epoch": 0.528, "percentage": 17.67, "elapsed_time": "1:19:49", "remaining_time": "6:11:56"}
+{"current_steps": 89, "total_steps": 498, "loss": 0.8802, "lr": 9.814174920481999e-06, "epoch": 0.534, "percentage": 17.87, "elapsed_time": "1:20:47", "remaining_time": "6:11:15"}
+{"current_steps": 90, "total_steps": 498, "loss": 0.8726, "lr": 9.804586609725499e-06, "epoch": 0.54, "percentage": 18.07, "elapsed_time": "1:21:45", "remaining_time": "6:10:36"}
+{"current_steps": 91, "total_steps": 498, "loss": 0.9173, "lr": 9.794762034744925e-06, "epoch": 0.546, "percentage": 18.27, "elapsed_time": "1:22:39", "remaining_time": "6:09:40"}
+{"current_steps": 92, "total_steps": 498, "loss": 0.9242, "lr": 9.784701678661045e-06, "epoch": 0.552, "percentage": 18.47, "elapsed_time": "1:23:46", "remaining_time": "6:09:41"}
+{"current_steps": 93, "total_steps": 498, "loss": 0.9162, "lr": 9.774406036189104e-06, "epoch": 0.558, "percentage": 18.67, "elapsed_time": "1:24:44", "remaining_time": "6:09:03"}
+{"current_steps": 94, "total_steps": 498, "loss": 0.8712, "lr": 9.763875613614482e-06, "epoch": 0.564, "percentage": 18.88, "elapsed_time": "1:25:41", "remaining_time": "6:08:15"}
+{"current_steps": 95, "total_steps": 498, "loss": 0.91, "lr": 9.753110928767816e-06, "epoch": 0.57, "percentage": 19.08, "elapsed_time": "1:26:37", "remaining_time": "6:07:29"}
+{"current_steps": 96, "total_steps": 498, "loss": 0.9004, "lr": 9.742112510999516e-06, "epoch": 0.576, "percentage": 19.28, "elapsed_time": "1:27:26", "remaining_time": "6:06:10"}
+{"current_steps": 97, "total_steps": 498, "loss": 0.9157, "lr": 9.730880901153747e-06, "epoch": 0.582, "percentage": 19.48, "elapsed_time": "1:28:37", "remaining_time": "6:06:21"}
+{"current_steps": 98, "total_steps": 498, "loss": 0.9058, "lr": 9.719416651541839e-06, "epoch": 0.588, "percentage": 19.68, "elapsed_time": "1:29:35", "remaining_time": "6:05:39"}
+{"current_steps": 99, "total_steps": 498, "loss": 0.9156, "lr": 9.707720325915105e-06, "epoch": 0.594, "percentage": 19.88, "elapsed_time": "1:30:34", "remaining_time": "6:05:01"}
+{"current_steps": 100, "total_steps": 498, "loss": 0.9283, "lr": 9.69579249943714e-06, "epoch": 0.6, "percentage": 20.08, "elapsed_time": "1:31:30", "remaining_time": "6:04:11"}
+{"current_steps": 101, "total_steps": 498, "loss": 0.9148, "lr": 9.683633758655529e-06, "epoch": 0.606, "percentage": 20.28, "elapsed_time": "1:32:28", "remaining_time": "6:03:30"}
+{"current_steps": 102, "total_steps": 498, "loss": 0.8542, "lr": 9.671244701472999e-06, "epoch": 0.612, "percentage": 20.48, "elapsed_time": "1:33:22", "remaining_time": "6:02:29"}
+{"current_steps": 103, "total_steps": 498, "loss": 0.9185, "lr": 9.658625937118033e-06, "epoch": 0.618, "percentage": 20.68, "elapsed_time": "1:34:19", "remaining_time": "6:01:42"}
+{"current_steps": 104, "total_steps": 498, "loss": 0.9427, "lr": 9.645778086114892e-06, "epoch": 0.624, "percentage": 20.88, "elapsed_time": "1:35:17", "remaining_time": "6:01:00"}
+{"current_steps": 105, "total_steps": 498, "loss": 0.9034, "lr": 9.632701780253111e-06, "epoch": 0.63, "percentage": 21.08, "elapsed_time": "1:36:13", "remaining_time": "6:00:09"}
+{"current_steps": 106, "total_steps": 498, "loss": 0.8935, "lr": 9.619397662556434e-06, "epoch": 0.636, "percentage": 21.29, "elapsed_time": "1:37:04", "remaining_time": "5:59:00"}
+{"current_steps": 107, "total_steps": 498, "loss": 0.8894, "lr": 9.605866387251186e-06, "epoch": 0.642, "percentage": 21.49, "elapsed_time": "1:38:11", "remaining_time": "5:58:47"}
+{"current_steps": 108, "total_steps": 498, "loss": 0.8794, "lr": 9.592108619734107e-06, "epoch": 0.648, "percentage": 21.69, "elapsed_time": "1:39:07", "remaining_time": "5:57:55"}
+{"current_steps": 109, "total_steps": 498, "loss": 0.8985, "lr": 9.578125036539625e-06, "epoch": 0.654, "percentage": 21.89, "elapsed_time": "1:39:57", "remaining_time": "5:56:44"}
+{"current_steps": 110, "total_steps": 498, "loss": 0.9301, "lr": 9.563916325306595e-06, "epoch": 0.66, "percentage": 22.09, "elapsed_time": "1:41:02", "remaining_time": "5:56:25"}
+{"current_steps": 111, "total_steps": 498, "loss": 0.9235, "lr": 9.549483184744483e-06, "epoch": 0.666, "percentage": 22.29, "elapsed_time": "1:42:06", "remaining_time": "5:56:01"}
+{"current_steps": 112, "total_steps": 498, "loss": 0.8869, "lr": 9.534826324599002e-06, "epoch": 0.672, "percentage": 22.49, "elapsed_time": "1:43:02", "remaining_time": "5:55:07"}
+{"current_steps": 113, "total_steps": 498, "loss": 0.891, "lr": 9.519946465617217e-06, "epoch": 0.678, "percentage": 22.69, "elapsed_time": "1:43:58", "remaining_time": "5:54:16"}
+{"current_steps": 114, "total_steps": 498, "loss": 0.9527, "lr": 9.504844339512096e-06, "epoch": 0.684, "percentage": 22.89, "elapsed_time": "1:44:55", "remaining_time": "5:53:25"}
+{"current_steps": 115, "total_steps": 498, "loss": 0.9027, "lr": 9.489520688926534e-06, "epoch": 0.69, "percentage": 23.09, "elapsed_time": "1:45:40", "remaining_time": "5:51:56"}
+{"current_steps": 116, "total_steps": 498, "loss": 0.8903, "lr": 9.473976267396831e-06, "epoch": 0.696, "percentage": 23.29, "elapsed_time": "1:46:37", "remaining_time": "5:51:07"}
+{"current_steps": 117, "total_steps": 498, "loss": 0.8749, "lr": 9.458211839315636e-06, "epoch": 0.702, "percentage": 23.49, "elapsed_time": "1:47:34", "remaining_time": "5:50:17"}
+{"current_steps": 118, "total_steps": 498, "loss": 0.8689, "lr": 9.442228179894362e-06, "epoch": 0.708, "percentage": 23.69, "elapsed_time": "1:48:30", "remaining_time": "5:49:24"}
+{"current_steps": 119, "total_steps": 498, "loss": 0.864, "lr": 9.426026075125062e-06, "epoch": 0.714, "percentage": 23.9, "elapsed_time": "1:49:24", "remaining_time": "5:48:25"}
+{"current_steps": 120, "total_steps": 498, "loss": 0.8627, "lr": 9.409606321741776e-06, "epoch": 0.72, "percentage": 24.1, "elapsed_time": "1:50:23", "remaining_time": "5:47:43"}
+{"current_steps": 121, "total_steps": 498, "loss": 0.902, "lr": 9.39296972718136e-06, "epoch": 0.726, "percentage": 24.3, "elapsed_time": "1:51:13", "remaining_time": "5:46:32"}
+{"current_steps": 122, "total_steps": 498, "loss": 0.8713, "lr": 9.376117109543769e-06, "epoch": 0.732, "percentage": 24.5, "elapsed_time": "1:52:12", "remaining_time": "5:45:49"}
+{"current_steps": 123, "total_steps": 498, "loss": 0.9075, "lr": 9.35904929755184e-06, "epoch": 0.738, "percentage": 24.7, "elapsed_time": "1:53:05", "remaining_time": "5:44:47"}
+{"current_steps": 124, "total_steps": 498, "loss": 0.9153, "lr": 9.341767130510529e-06, "epoch": 0.744, "percentage": 24.9, "elapsed_time": "1:54:06", "remaining_time": "5:44:10"}
+{"current_steps": 125, "total_steps": 498, "loss": 0.9107, "lr": 9.324271458265642e-06, "epoch": 0.75, "percentage": 25.1, "elapsed_time": "1:55:09", "remaining_time": "5:43:37"}
+{"current_steps": 126, "total_steps": 498, "loss": 0.9211, "lr": 9.306563141162046e-06, "epoch": 0.756, "percentage": 25.3, "elapsed_time": "1:56:02", "remaining_time": "5:42:34"}
+{"current_steps": 127, "total_steps": 498, "loss": 0.8603, "lr": 9.288643050001362e-06, "epoch": 0.762, "percentage": 25.5, "elapsed_time": "1:56:53", "remaining_time": "5:41:29"}
+{"current_steps": 128, "total_steps": 498, "loss": 0.8865, "lr": 9.270512065999139e-06, "epoch": 0.768, "percentage": 25.7, "elapsed_time": "1:57:51", "remaining_time": "5:40:41"}
+{"current_steps": 129, "total_steps": 498, "loss": 0.8983, "lr": 9.252171080741525e-06, "epoch": 0.774, "percentage": 25.9, "elapsed_time": "1:58:53", "remaining_time": "5:40:05"}
+{"current_steps": 130, "total_steps": 498, "loss": 0.8849, "lr": 9.233620996141421e-06, "epoch": 0.78, "percentage": 26.1, "elapsed_time": "1:59:56", "remaining_time": "5:39:31"}
+{"current_steps": 131, "total_steps": 498, "loss": 0.885, "lr": 9.214862724394133e-06, "epoch": 0.786, "percentage": 26.31, "elapsed_time": "2:00:48", "remaining_time": "5:38:27"}
+{"current_steps": 132, "total_steps": 498, "loss": 0.8919, "lr": 9.195897187932513e-06, "epoch": 0.792, "percentage": 26.51, "elapsed_time": "2:01:37", "remaining_time": "5:37:13"}
+{"current_steps": 133, "total_steps": 498, "loss": 0.8673, "lr": 9.176725319381589e-06, "epoch": 0.798, "percentage": 26.71, "elapsed_time": "2:02:31", "remaining_time": "5:36:16"}
+{"current_steps": 134, "total_steps": 498, "loss": 0.8724, "lr": 9.157348061512728e-06, "epoch": 0.804, "percentage": 26.91, "elapsed_time": "2:03:25", "remaining_time": "5:35:16"}
+{"current_steps": 135, "total_steps": 498, "loss": 0.8901, "lr": 9.137766367197246e-06, "epoch": 0.81, "percentage": 27.11, "elapsed_time": "2:04:35", "remaining_time": "5:34:59"}
+{"current_steps": 136, "total_steps": 498, "loss": 0.881, "lr": 9.117981199359575e-06, "epoch": 0.816, "percentage": 27.31, "elapsed_time": "2:05:27", "remaining_time": "5:33:56"}
+{"current_steps": 137, "total_steps": 498, "loss": 0.8504, "lr": 9.097993530929895e-06, "epoch": 0.822, "percentage": 27.51, "elapsed_time": "2:06:23", "remaining_time": "5:33:02"}
+{"current_steps": 138, "total_steps": 498, "loss": 0.8811, "lr": 9.077804344796302e-06, "epoch": 0.828, "percentage": 27.71, "elapsed_time": "2:07:17", "remaining_time": "5:32:04"}
+{"current_steps": 139, "total_steps": 498, "loss": 0.8868, "lr": 9.057414633756466e-06, "epoch": 0.834, "percentage": 27.91, "elapsed_time": "2:08:05", "remaining_time": "5:30:48"}
+{"current_steps": 140, "total_steps": 498, "loss": 0.8844, "lr": 9.036825400468814e-06, "epoch": 0.84, "percentage": 28.11, "elapsed_time": "2:08:52", "remaining_time": "5:29:34"}
+{"current_steps": 141, "total_steps": 498, "loss": 0.8805, "lr": 9.016037657403225e-06, "epoch": 0.846, "percentage": 28.31, "elapsed_time": "2:09:46", "remaining_time": "5:28:34"}
+{"current_steps": 142, "total_steps": 498, "loss": 0.8913, "lr": 8.995052426791247e-06, "epoch": 0.852, "percentage": 28.51, "elapsed_time": "2:10:38", "remaining_time": "5:27:31"}
+{"current_steps": 143, "total_steps": 498, "loss": 0.8479, "lr": 8.973870740575814e-06, "epoch": 0.858, "percentage": 28.71, "elapsed_time": "2:11:38", "remaining_time": "5:26:46"}
+{"current_steps": 144, "total_steps": 498, "loss": 0.9066, "lr": 8.952493640360518e-06, "epoch": 0.864, "percentage": 28.92, "elapsed_time": "2:12:37", "remaining_time": "5:26:01"}
+{"current_steps": 145, "total_steps": 498, "loss": 0.8713, "lr": 8.930922177358379e-06, "epoch": 0.87, "percentage": 29.12, "elapsed_time": "2:13:22", "remaining_time": "5:24:42"}
+{"current_steps": 146, "total_steps": 498, "loss": 0.8871, "lr": 8.90915741234015e-06, "epoch": 0.876, "percentage": 29.32, "elapsed_time": "2:14:24", "remaining_time": "5:24:03"}
+{"current_steps": 147, "total_steps": 498, "loss": 0.8972, "lr": 8.88720041558216e-06, "epoch": 0.882, "percentage": 29.52, "elapsed_time": "2:15:21", "remaining_time": "5:23:11"}
+{"current_steps": 148, "total_steps": 498, "loss": 0.9008, "lr": 8.865052266813686e-06, "epoch": 0.888, "percentage": 29.72, "elapsed_time": "2:16:19", "remaining_time": "5:22:23"}
+{"current_steps": 149, "total_steps": 498, "loss": 0.866, "lr": 8.842714055163841e-06, "epoch": 0.894, "percentage": 29.92, "elapsed_time": "2:17:04", "remaining_time": "5:21:04"}
+{"current_steps": 150, "total_steps": 498, "loss": 0.8995, "lr": 8.820186879108038e-06, "epoch": 0.9, "percentage": 30.12, "elapsed_time": "2:18:05", "remaining_time": "5:20:22"}
+{"current_steps": 151, "total_steps": 498, "loss": 0.881, "lr": 8.797471846413957e-06, "epoch": 0.906, "percentage": 30.32, "elapsed_time": "2:18:52", "remaining_time": "5:19:07"}
+{"current_steps": 152, "total_steps": 498, "loss": 0.8812, "lr": 8.77457007408708e-06, "epoch": 0.912, "percentage": 30.52, "elapsed_time": "2:19:44", "remaining_time": "5:18:05"}
+{"current_steps": 153, "total_steps": 498, "loss": 0.8645, "lr": 8.751482688315758e-06, "epoch": 0.918, "percentage": 30.72, "elapsed_time": "2:20:33", "remaining_time": "5:16:56"}
+{"current_steps": 154, "total_steps": 498, "loss": 0.9134, "lr": 8.728210824415829e-06, "epoch": 0.924, "percentage": 30.92, "elapsed_time": "2:21:33", "remaining_time": "5:16:12"}
+{"current_steps": 155, "total_steps": 498, "loss": 0.9009, "lr": 8.704755626774796e-06, "epoch": 0.93, "percentage": 31.12, "elapsed_time": "2:22:24", "remaining_time": "5:15:08"}
+{"current_steps": 156, "total_steps": 498, "loss": 0.8654, "lr": 8.681118248795548e-06, "epoch": 0.936, "percentage": 31.33, "elapsed_time": "2:23:20", "remaining_time": "5:14:13"}
+{"current_steps": 157, "total_steps": 498, "loss": 0.917, "lr": 8.65729985283964e-06, "epoch": 0.942, "percentage": 31.53, "elapsed_time": "2:24:16", "remaining_time": "5:13:22"}
+{"current_steps": 158, "total_steps": 498, "loss": 0.899, "lr": 8.633301610170136e-06, "epoch": 0.948, "percentage": 31.73, "elapsed_time": "2:25:12", "remaining_time": "5:12:27"}
+{"current_steps": 159, "total_steps": 498, "loss": 0.8325, "lr": 8.609124700894017e-06, "epoch": 0.954, "percentage": 31.93, "elapsed_time": "2:25:59", "remaining_time": "5:11:15"}
+{"current_steps": 160, "total_steps": 498, "loss": 0.8266, "lr": 8.584770313904138e-06, "epoch": 0.96, "percentage": 32.13, "elapsed_time": "2:26:58", "remaining_time": "5:10:29"}
+{"current_steps": 161, "total_steps": 498, "loss": 0.895, "lr": 8.560239646820779e-06, "epoch": 0.966, "percentage": 32.33, "elapsed_time": "2:27:52", "remaining_time": "5:09:31"}
+{"current_steps": 162, "total_steps": 498, "loss": 0.9012, "lr": 8.535533905932739e-06, "epoch": 0.972, "percentage": 32.53, "elapsed_time": "2:28:52", "remaining_time": "5:08:47"}
+{"current_steps": 163, "total_steps": 498, "loss": 0.8691, "lr": 8.510654306138028e-06, "epoch": 0.978, "percentage": 32.73, "elapsed_time": "2:29:52", "remaining_time": "5:08:01"}
+{"current_steps": 164, "total_steps": 498, "loss": 0.8629, "lr": 8.485602070884118e-06, "epoch": 0.984, "percentage": 32.93, "elapsed_time": "2:30:51", "remaining_time": "5:07:13"}
+{"current_steps": 165, "total_steps": 498, "loss": 0.8684, "lr": 8.460378432107779e-06, "epoch": 0.99, "percentage": 33.13, "elapsed_time": "2:31:53", "remaining_time": "5:06:33"}
+{"current_steps": 166, "total_steps": 498, "loss": 0.9096, "lr": 8.43498463017451e-06, "epoch": 0.996, "percentage": 33.33, "elapsed_time": "2:32:57", "remaining_time": "5:05:54"}
+{"current_steps": 167, "total_steps": 498, "loss": 1.4196, "lr": 8.409421913817526e-06, "epoch": 1.004, "percentage": 33.53, "elapsed_time": "2:35:03", "remaining_time": "5:07:19"}
+{"current_steps": 168, "total_steps": 498, "loss": 0.7903, "lr": 8.383691540076372e-06, "epoch": 1.01, "percentage": 33.73, "elapsed_time": "2:36:01", "remaining_time": "5:06:29"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81db1f4fe4d35b988eace1f9d51e66e6d4a266fdcdc2fd39f161dda2a90c13a
+size 7416