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 sha256:225f726a60ff1f5f278c7a5e7f739fe4b02676a6a67a65334fb48316a7c213d7
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2f9c3e1da6bfbad2055bc88255c2f2be4d53ed9bfa1edc06cc9edf061e450a
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0637875e7651feac2e88e10a18ac9f33563e09e4b7677769139575686b0fcaa
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53cf3eea83e71b927fb03eddec7de4da81f00456063cbbc1b7a49e21a17b1f78
+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 +1,204 @@
+{"current_steps": 1, "total_steps": 1005, "loss": 0.8036, "lr": 7.920792079207921e-07, "epoch": 0.004956629491945477, "percentage": 0.1, "elapsed_time": "0:01:36", "remaining_time": "1 day, 2:49:55"}
+{"current_steps": 2, "total_steps": 1005, "loss": 0.7966, "lr": 1.5841584158415842e-06, "epoch": 0.009913258983890954, "percentage": 0.2, "elapsed_time": "0:02:27", "remaining_time": "20:34:23"}
+{"current_steps": 3, "total_steps": 1005, "loss": 0.7948, "lr": 2.3762376237623762e-06, "epoch": 0.01486988847583643, "percentage": 0.3, "elapsed_time": "0:03:19", "remaining_time": "18:29:43"}
+{"current_steps": 4, "total_steps": 1005, "loss": 0.7762, "lr": 3.1683168316831685e-06, "epoch": 0.01982651796778191, "percentage": 0.4, "elapsed_time": "0:04:10", "remaining_time": "17:22:59"}
+{"current_steps": 5, "total_steps": 1005, "loss": 0.7499, "lr": 3.960396039603961e-06, "epoch": 0.024783147459727387, "percentage": 0.5, "elapsed_time": "0:05:01", "remaining_time": "16:43:44"}
+{"current_steps": 6, "total_steps": 1005, "loss": 0.6956, "lr": 4.7524752475247525e-06, "epoch": 0.02973977695167286, "percentage": 0.6, "elapsed_time": "0:05:52", "remaining_time": "16:17:23"}
+{"current_steps": 7, "total_steps": 1005, "loss": 0.6839, "lr": 5.544554455445545e-06, "epoch": 0.03469640644361834, "percentage": 0.7, "elapsed_time": "0:06:43", "remaining_time": "15:58:28"}
+{"current_steps": 8, "total_steps": 1005, "loss": 0.6668, "lr": 6.336633663366337e-06, "epoch": 0.03965303593556382, "percentage": 0.8, "elapsed_time": "0:07:34", "remaining_time": "15:43:13"}
+{"current_steps": 9, "total_steps": 1005, "loss": 0.677, "lr": 7.128712871287129e-06, "epoch": 0.04460966542750929, "percentage": 0.9, "elapsed_time": "0:08:25", "remaining_time": "15:31:34"}
+{"current_steps": 10, "total_steps": 1005, "loss": 0.6624, "lr": 7.920792079207921e-06, "epoch": 0.04956629491945477, "percentage": 1.0, "elapsed_time": "0:09:15", "remaining_time": "15:21:38"}
+{"current_steps": 11, "total_steps": 1005, "loss": 0.6236, "lr": 8.712871287128714e-06, "epoch": 0.05452292441140025, "percentage": 1.09, "elapsed_time": "0:10:06", "remaining_time": "15:13:56"}
+{"current_steps": 12, "total_steps": 1005, "loss": 0.6228, "lr": 9.504950495049505e-06, "epoch": 0.05947955390334572, "percentage": 1.19, "elapsed_time": "0:10:57", "remaining_time": "15:07:11"}
+{"current_steps": 13, "total_steps": 1005, "loss": 0.6038, "lr": 1.0297029702970298e-05, "epoch": 0.0644361833952912, "percentage": 1.29, "elapsed_time": "0:11:57", "remaining_time": "15:12:11"}
+{"current_steps": 14, "total_steps": 1005, "loss": 0.5935, "lr": 1.108910891089109e-05, "epoch": 0.06939281288723669, "percentage": 1.39, "elapsed_time": "0:12:48", "remaining_time": "15:06:15"}
+{"current_steps": 15, "total_steps": 1005, "loss": 0.572, "lr": 1.1881188118811881e-05, "epoch": 0.07434944237918216, "percentage": 1.49, "elapsed_time": "0:13:39", "remaining_time": "15:01:05"}
+{"current_steps": 16, "total_steps": 1005, "loss": 0.5634, "lr": 1.2673267326732674e-05, "epoch": 0.07930607187112763, "percentage": 1.59, "elapsed_time": "0:14:29", "remaining_time": "14:56:13"}
+{"current_steps": 17, "total_steps": 1005, "loss": 0.5572, "lr": 1.3465346534653467e-05, "epoch": 0.08426270136307311, "percentage": 1.69, "elapsed_time": "0:15:20", "remaining_time": "14:51:55"}
+{"current_steps": 18, "total_steps": 1005, "loss": 0.5474, "lr": 1.4257425742574257e-05, "epoch": 0.08921933085501858, "percentage": 1.79, "elapsed_time": "0:16:12", "remaining_time": "14:48:42"}
+{"current_steps": 19, "total_steps": 1005, "loss": 0.5477, "lr": 1.504950495049505e-05, "epoch": 0.09417596034696406, "percentage": 1.89, "elapsed_time": "0:17:03", "remaining_time": "14:45:01"}
+{"current_steps": 20, "total_steps": 1005, "loss": 0.5397, "lr": 1.5841584158415843e-05, "epoch": 0.09913258983890955, "percentage": 1.99, "elapsed_time": "0:17:54", "remaining_time": "14:41:40"}
+{"current_steps": 21, "total_steps": 1005, "loss": 0.5281, "lr": 1.6633663366336635e-05, "epoch": 0.10408921933085502, "percentage": 2.09, "elapsed_time": "0:18:45", "remaining_time": "14:38:40"}
+{"current_steps": 22, "total_steps": 1005, "loss": 0.5199, "lr": 1.7425742574257428e-05, "epoch": 0.1090458488228005, "percentage": 2.19, "elapsed_time": "0:19:35", "remaining_time": "14:35:41"}
+{"current_steps": 23, "total_steps": 1005, "loss": 0.5139, "lr": 1.821782178217822e-05, "epoch": 0.11400247831474597, "percentage": 2.29, "elapsed_time": "0:20:26", "remaining_time": "14:32:59"}
+{"current_steps": 24, "total_steps": 1005, "loss": 0.5193, "lr": 1.900990099009901e-05, "epoch": 0.11895910780669144, "percentage": 2.39, "elapsed_time": "0:21:17", "remaining_time": "14:30:22"}
+{"current_steps": 25, "total_steps": 1005, "loss": 0.5147, "lr": 1.9801980198019803e-05, "epoch": 0.12391573729863693, "percentage": 2.49, "elapsed_time": "0:22:08", "remaining_time": "14:27:58"}
+{"current_steps": 26, "total_steps": 1005, "loss": 0.5062, "lr": 2.0594059405940595e-05, "epoch": 0.1288723667905824, "percentage": 2.59, "elapsed_time": "0:22:59", "remaining_time": "14:25:57"}
+{"current_steps": 27, "total_steps": 1005, "loss": 0.4938, "lr": 2.1386138613861388e-05, "epoch": 0.13382899628252787, "percentage": 2.69, "elapsed_time": "0:23:52", "remaining_time": "14:24:47"}
+{"current_steps": 28, "total_steps": 1005, "loss": 0.4978, "lr": 2.217821782178218e-05, "epoch": 0.13878562577447337, "percentage": 2.79, "elapsed_time": "0:24:50", "remaining_time": "14:26:50"}
+{"current_steps": 29, "total_steps": 1005, "loss": 0.4961, "lr": 2.297029702970297e-05, "epoch": 0.14374225526641884, "percentage": 2.89, "elapsed_time": "0:25:41", "remaining_time": "14:24:43"}
+{"current_steps": 30, "total_steps": 1005, "loss": 0.4928, "lr": 2.3762376237623762e-05, "epoch": 0.14869888475836432, "percentage": 2.99, "elapsed_time": "0:26:32", "remaining_time": "14:22:30"}
+{"current_steps": 31, "total_steps": 1005, "loss": 0.4962, "lr": 2.4554455445544555e-05, "epoch": 0.1536555142503098, "percentage": 3.08, "elapsed_time": "0:27:23", "remaining_time": "14:20:24"}
+{"current_steps": 32, "total_steps": 1005, "loss": 0.4841, "lr": 2.5346534653465348e-05, "epoch": 0.15861214374225527, "percentage": 3.18, "elapsed_time": "0:28:13", "remaining_time": "14:18:22"}
+{"current_steps": 33, "total_steps": 1005, "loss": 0.486, "lr": 2.613861386138614e-05, "epoch": 0.16356877323420074, "percentage": 3.28, "elapsed_time": "0:29:04", "remaining_time": "14:16:29"}
+{"current_steps": 34, "total_steps": 1005, "loss": 0.4742, "lr": 2.6930693069306933e-05, "epoch": 0.16852540272614622, "percentage": 3.38, "elapsed_time": "0:29:56", "remaining_time": "14:14:55"}
+{"current_steps": 35, "total_steps": 1005, "loss": 0.4825, "lr": 2.7722772277227722e-05, "epoch": 0.1734820322180917, "percentage": 3.48, "elapsed_time": "0:30:47", "remaining_time": "14:13:10"}
+{"current_steps": 36, "total_steps": 1005, "loss": 0.4824, "lr": 2.8514851485148515e-05, "epoch": 0.17843866171003717, "percentage": 3.58, "elapsed_time": "0:31:37", "remaining_time": "14:11:27"}
+{"current_steps": 37, "total_steps": 1005, "loss": 0.4816, "lr": 2.9306930693069308e-05, "epoch": 0.18339529120198264, "percentage": 3.68, "elapsed_time": "0:32:28", "remaining_time": "14:09:47"}
+{"current_steps": 38, "total_steps": 1005, "loss": 0.4775, "lr": 3.00990099009901e-05, "epoch": 0.18835192069392812, "percentage": 3.78, "elapsed_time": "0:33:19", "remaining_time": "14:08:08"}
+{"current_steps": 39, "total_steps": 1005, "loss": 0.4804, "lr": 3.0891089108910896e-05, "epoch": 0.19330855018587362, "percentage": 3.88, "elapsed_time": "0:34:10", "remaining_time": "14:06:35"}
+{"current_steps": 40, "total_steps": 1005, "loss": 0.4754, "lr": 3.1683168316831686e-05, "epoch": 0.1982651796778191, "percentage": 3.98, "elapsed_time": "0:35:01", "remaining_time": "14:04:59"}
+{"current_steps": 41, "total_steps": 1005, "loss": 0.4694, "lr": 3.247524752475248e-05, "epoch": 0.20322180916976457, "percentage": 4.08, "elapsed_time": "0:35:53", "remaining_time": "14:03:42"}
+{"current_steps": 42, "total_steps": 1005, "loss": 0.4584, "lr": 3.326732673267327e-05, "epoch": 0.20817843866171004, "percentage": 4.18, "elapsed_time": "0:36:46", "remaining_time": "14:03:18"}
+{"current_steps": 43, "total_steps": 1005, "loss": 0.4645, "lr": 3.405940594059406e-05, "epoch": 0.21313506815365552, "percentage": 4.28, "elapsed_time": "0:37:44", "remaining_time": "14:04:28"}
+{"current_steps": 44, "total_steps": 1005, "loss": 0.4708, "lr": 3.4851485148514856e-05, "epoch": 0.218091697645601, "percentage": 4.38, "elapsed_time": "0:38:35", "remaining_time": "14:02:50"}
+{"current_steps": 45, "total_steps": 1005, "loss": 0.4703, "lr": 3.5643564356435645e-05, "epoch": 0.22304832713754646, "percentage": 4.48, "elapsed_time": "0:39:26", "remaining_time": "14:01:20"}
+{"current_steps": 46, "total_steps": 1005, "loss": 0.4661, "lr": 3.643564356435644e-05, "epoch": 0.22800495662949194, "percentage": 4.58, "elapsed_time": "0:40:17", "remaining_time": "13:59:53"}
+{"current_steps": 47, "total_steps": 1005, "loss": 0.4527, "lr": 3.722772277227723e-05, "epoch": 0.23296158612143741, "percentage": 4.68, "elapsed_time": "0:41:08", "remaining_time": "13:58:28"}
+{"current_steps": 48, "total_steps": 1005, "loss": 0.4541, "lr": 3.801980198019802e-05, "epoch": 0.2379182156133829, "percentage": 4.78, "elapsed_time": "0:41:59", "remaining_time": "13:57:05"}
+{"current_steps": 49, "total_steps": 1005, "loss": 0.451, "lr": 3.8811881188118816e-05, "epoch": 0.24287484510532836, "percentage": 4.88, "elapsed_time": "0:42:50", "remaining_time": "13:55:44"}
+{"current_steps": 50, "total_steps": 1005, "loss": 0.4628, "lr": 3.9603960396039605e-05, "epoch": 0.24783147459727387, "percentage": 4.98, "elapsed_time": "0:43:41", "remaining_time": "13:54:23"}
+{"current_steps": 51, "total_steps": 1005, "loss": 0.4572, "lr": 4.03960396039604e-05, "epoch": 0.2527881040892193, "percentage": 5.07, "elapsed_time": "0:44:32", "remaining_time": "13:53:02"}
+{"current_steps": 52, "total_steps": 1005, "loss": 0.4561, "lr": 4.118811881188119e-05, "epoch": 0.2577447335811648, "percentage": 5.17, "elapsed_time": "0:45:22", "remaining_time": "13:51:41"}
+{"current_steps": 53, "total_steps": 1005, "loss": 0.4577, "lr": 4.1980198019801987e-05, "epoch": 0.26270136307311026, "percentage": 5.27, "elapsed_time": "0:46:14", "remaining_time": "13:50:28"}
+{"current_steps": 54, "total_steps": 1005, "loss": 0.4518, "lr": 4.2772277227722776e-05, "epoch": 0.26765799256505574, "percentage": 5.37, "elapsed_time": "0:47:04", "remaining_time": "13:49:09"}
+{"current_steps": 55, "total_steps": 1005, "loss": 0.4592, "lr": 4.356435643564357e-05, "epoch": 0.27261462205700127, "percentage": 5.47, "elapsed_time": "0:47:56", "remaining_time": "13:48:07"}
+{"current_steps": 56, "total_steps": 1005, "loss": 0.4526, "lr": 4.435643564356436e-05, "epoch": 0.27757125154894674, "percentage": 5.57, "elapsed_time": "0:48:47", "remaining_time": "13:46:56"}
+{"current_steps": 57, "total_steps": 1005, "loss": 0.4543, "lr": 4.514851485148515e-05, "epoch": 0.2825278810408922, "percentage": 5.67, "elapsed_time": "0:49:42", "remaining_time": "13:46:44"}
+{"current_steps": 58, "total_steps": 1005, "loss": 0.4562, "lr": 4.594059405940594e-05, "epoch": 0.2874845105328377, "percentage": 5.77, "elapsed_time": "0:50:40", "remaining_time": "13:47:17"}
+{"current_steps": 59, "total_steps": 1005, "loss": 0.4572, "lr": 4.6732673267326736e-05, "epoch": 0.29244114002478316, "percentage": 5.87, "elapsed_time": "0:51:31", "remaining_time": "13:46:02"}
+{"current_steps": 60, "total_steps": 1005, "loss": 0.4563, "lr": 4.7524752475247525e-05, "epoch": 0.29739776951672864, "percentage": 5.97, "elapsed_time": "0:52:22", "remaining_time": "13:44:50"}
+{"current_steps": 61, "total_steps": 1005, "loss": 0.4535, "lr": 4.831683168316832e-05, "epoch": 0.3023543990086741, "percentage": 6.07, "elapsed_time": "0:53:13", "remaining_time": "13:43:36"}
+{"current_steps": 62, "total_steps": 1005, "loss": 0.4536, "lr": 4.910891089108911e-05, "epoch": 0.3073110285006196, "percentage": 6.17, "elapsed_time": "0:54:04", "remaining_time": "13:42:20"}
+{"current_steps": 63, "total_steps": 1005, "loss": 0.4421, "lr": 4.9900990099009906e-05, "epoch": 0.31226765799256506, "percentage": 6.27, "elapsed_time": "0:54:54", "remaining_time": "13:41:06"}
+{"current_steps": 64, "total_steps": 1005, "loss": 0.45, "lr": 5.0693069306930696e-05, "epoch": 0.31722428748451054, "percentage": 6.37, "elapsed_time": "0:55:45", "remaining_time": "13:39:54"}
+{"current_steps": 65, "total_steps": 1005, "loss": 0.4474, "lr": 5.148514851485149e-05, "epoch": 0.322180916976456, "percentage": 6.47, "elapsed_time": "0:56:36", "remaining_time": "13:38:44"}
+{"current_steps": 66, "total_steps": 1005, "loss": 0.445, "lr": 5.227722772277228e-05, "epoch": 0.3271375464684015, "percentage": 6.57, "elapsed_time": "0:57:27", "remaining_time": "13:37:31"}
+{"current_steps": 67, "total_steps": 1005, "loss": 0.4485, "lr": 5.306930693069308e-05, "epoch": 0.33209417596034696, "percentage": 6.67, "elapsed_time": "0:58:18", "remaining_time": "13:36:23"}
+{"current_steps": 68, "total_steps": 1005, "loss": 0.4441, "lr": 5.3861386138613866e-05, "epoch": 0.33705080545229243, "percentage": 6.77, "elapsed_time": "0:59:09", "remaining_time": "13:35:11"}
+{"current_steps": 69, "total_steps": 1005, "loss": 0.4352, "lr": 5.465346534653466e-05, "epoch": 0.3420074349442379, "percentage": 6.87, "elapsed_time": "1:00:00", "remaining_time": "13:34:03"}
+{"current_steps": 70, "total_steps": 1005, "loss": 0.4422, "lr": 5.5445544554455445e-05, "epoch": 0.3469640644361834, "percentage": 6.97, "elapsed_time": "1:00:51", "remaining_time": "13:32:54"}
+{"current_steps": 71, "total_steps": 1005, "loss": 0.4387, "lr": 5.623762376237624e-05, "epoch": 0.35192069392812886, "percentage": 7.06, "elapsed_time": "1:01:42", "remaining_time": "13:31:51"}
+{"current_steps": 72, "total_steps": 1005, "loss": 0.4395, "lr": 5.702970297029703e-05, "epoch": 0.35687732342007433, "percentage": 7.16, "elapsed_time": "1:02:38", "remaining_time": "13:31:37"}
+{"current_steps": 73, "total_steps": 1005, "loss": 0.4412, "lr": 5.7821782178217826e-05, "epoch": 0.3618339529120198, "percentage": 7.26, "elapsed_time": "1:03:35", "remaining_time": "13:31:58"}
+{"current_steps": 74, "total_steps": 1005, "loss": 0.4471, "lr": 5.8613861386138615e-05, "epoch": 0.3667905824039653, "percentage": 7.36, "elapsed_time": "1:04:26", "remaining_time": "13:30:48"}
+{"current_steps": 75, "total_steps": 1005, "loss": 0.4462, "lr": 5.940594059405941e-05, "epoch": 0.37174721189591076, "percentage": 7.46, "elapsed_time": "1:05:17", "remaining_time": "13:29:40"}
+{"current_steps": 76, "total_steps": 1005, "loss": 0.437, "lr": 6.01980198019802e-05, "epoch": 0.37670384138785623, "percentage": 7.56, "elapsed_time": "1:06:08", "remaining_time": "13:28:33"}
+{"current_steps": 77, "total_steps": 1005, "loss": 0.4393, "lr": 6.0990099009900997e-05, "epoch": 0.38166047087980176, "percentage": 7.66, "elapsed_time": "1:06:59", "remaining_time": "13:27:28"}
+{"current_steps": 78, "total_steps": 1005, "loss": 0.4443, "lr": 6.178217821782179e-05, "epoch": 0.38661710037174724, "percentage": 7.76, "elapsed_time": "1:07:50", "remaining_time": "13:26:19"}
+{"current_steps": 79, "total_steps": 1005, "loss": 0.4362, "lr": 6.257425742574258e-05, "epoch": 0.3915737298636927, "percentage": 7.86, "elapsed_time": "1:08:41", "remaining_time": "13:25:15"}
+{"current_steps": 80, "total_steps": 1005, "loss": 0.4418, "lr": 6.336633663366337e-05, "epoch": 0.3965303593556382, "percentage": 7.96, "elapsed_time": "1:09:33", "remaining_time": "13:24:13"}
+{"current_steps": 81, "total_steps": 1005, "loss": 0.4432, "lr": 6.415841584158417e-05, "epoch": 0.40148698884758366, "percentage": 8.06, "elapsed_time": "1:10:24", "remaining_time": "13:23:08"}
+{"current_steps": 82, "total_steps": 1005, "loss": 0.435, "lr": 6.495049504950496e-05, "epoch": 0.40644361833952913, "percentage": 8.16, "elapsed_time": "1:11:15", "remaining_time": "13:22:01"}
+{"current_steps": 83, "total_steps": 1005, "loss": 0.4391, "lr": 6.574257425742575e-05, "epoch": 0.4114002478314746, "percentage": 8.26, "elapsed_time": "1:12:06", "remaining_time": "13:20:57"}
+{"current_steps": 84, "total_steps": 1005, "loss": 0.4348, "lr": 6.653465346534654e-05, "epoch": 0.4163568773234201, "percentage": 8.36, "elapsed_time": "1:12:57", "remaining_time": "13:19:52"}
+{"current_steps": 85, "total_steps": 1005, "loss": 0.44, "lr": 6.732673267326732e-05, "epoch": 0.42131350681536556, "percentage": 8.46, "elapsed_time": "1:13:48", "remaining_time": "13:18:48"}
+{"current_steps": 86, "total_steps": 1005, "loss": 0.4412, "lr": 6.811881188118812e-05, "epoch": 0.42627013630731103, "percentage": 8.56, "elapsed_time": "1:14:39", "remaining_time": "13:17:48"}
+{"current_steps": 87, "total_steps": 1005, "loss": 0.4402, "lr": 6.891089108910892e-05, "epoch": 0.4312267657992565, "percentage": 8.66, "elapsed_time": "1:15:35", "remaining_time": "13:17:36"}
+{"current_steps": 88, "total_steps": 1005, "loss": 0.4413, "lr": 6.970297029702971e-05, "epoch": 0.436183395291202, "percentage": 8.76, "elapsed_time": "1:16:33", "remaining_time": "13:17:46"}
+{"current_steps": 89, "total_steps": 1005, "loss": 0.4387, "lr": 7.04950495049505e-05, "epoch": 0.44114002478314746, "percentage": 8.86, "elapsed_time": "1:17:24", "remaining_time": "13:16:38"}
+{"current_steps": 90, "total_steps": 1005, "loss": 0.4459, "lr": 7.128712871287129e-05, "epoch": 0.44609665427509293, "percentage": 8.96, "elapsed_time": "1:18:14", "remaining_time": "13:15:32"}
+{"current_steps": 91, "total_steps": 1005, "loss": 0.4386, "lr": 7.207920792079209e-05, "epoch": 0.4510532837670384, "percentage": 9.05, "elapsed_time": "1:19:06", "remaining_time": "13:14:29"}
+{"current_steps": 92, "total_steps": 1005, "loss": 0.446, "lr": 7.287128712871288e-05, "epoch": 0.4560099132589839, "percentage": 9.15, "elapsed_time": "1:19:56", "remaining_time": "13:13:22"}
+{"current_steps": 93, "total_steps": 1005, "loss": 0.437, "lr": 7.366336633663368e-05, "epoch": 0.46096654275092935, "percentage": 9.25, "elapsed_time": "1:20:47", "remaining_time": "13:12:15"}
+{"current_steps": 94, "total_steps": 1005, "loss": 0.4484, "lr": 7.445544554455446e-05, "epoch": 0.46592317224287483, "percentage": 9.35, "elapsed_time": "1:21:38", "remaining_time": "13:11:09"}
+{"current_steps": 95, "total_steps": 1005, "loss": 0.4413, "lr": 7.524752475247524e-05, "epoch": 0.4708798017348203, "percentage": 9.45, "elapsed_time": "1:22:28", "remaining_time": "13:10:06"}
+{"current_steps": 96, "total_steps": 1005, "loss": 0.4506, "lr": 7.603960396039604e-05, "epoch": 0.4758364312267658, "percentage": 9.55, "elapsed_time": "1:23:19", "remaining_time": "13:09:02"}
+{"current_steps": 97, "total_steps": 1005, "loss": 0.4395, "lr": 7.683168316831684e-05, "epoch": 0.48079306071871125, "percentage": 9.65, "elapsed_time": "1:24:11", "remaining_time": "13:08:04"}
+{"current_steps": 98, "total_steps": 1005, "loss": 0.4314, "lr": 7.762376237623763e-05, "epoch": 0.4857496902106567, "percentage": 9.75, "elapsed_time": "1:25:02", "remaining_time": "13:07:02"}
+{"current_steps": 99, "total_steps": 1005, "loss": 0.4445, "lr": 7.841584158415841e-05, "epoch": 0.49070631970260226, "percentage": 9.85, "elapsed_time": "1:25:53", "remaining_time": "13:06:00"}
+{"current_steps": 100, "total_steps": 1005, "loss": 0.4347, "lr": 7.920792079207921e-05, "epoch": 0.49566294919454773, "percentage": 9.95, "elapsed_time": "1:26:44", "remaining_time": "13:04:56"}
+{"current_steps": 101, "total_steps": 1005, "loss": 0.4342, "lr": 8e-05, "epoch": 0.5006195786864932, "percentage": 10.05, "elapsed_time": "1:27:35", "remaining_time": "13:03:57"}
+{"current_steps": 102, "total_steps": 1005, "loss": 0.4357, "lr": 7.999975845811957e-05, "epoch": 0.5055762081784386, "percentage": 10.15, "elapsed_time": "1:28:32", "remaining_time": "13:03:52"}
+{"current_steps": 103, "total_steps": 1005, "loss": 0.4338, "lr": 7.999903383539539e-05, "epoch": 0.5105328376703842, "percentage": 10.25, "elapsed_time": "1:29:31", "remaining_time": "13:04:00"}
+{"current_steps": 104, "total_steps": 1005, "loss": 0.444, "lr": 7.99978261405788e-05, "epoch": 0.5154894671623296, "percentage": 10.35, "elapsed_time": "1:30:22", "remaining_time": "13:02:58"}
+{"current_steps": 105, "total_steps": 1005, "loss": 0.4349, "lr": 7.999613538825525e-05, "epoch": 0.5204460966542751, "percentage": 10.45, "elapsed_time": "1:31:13", "remaining_time": "13:01:53"}
+{"current_steps": 106, "total_steps": 1005, "loss": 0.443, "lr": 7.999396159884411e-05, "epoch": 0.5254027261462205, "percentage": 10.55, "elapsed_time": "1:32:04", "remaining_time": "13:00:51"}
+{"current_steps": 107, "total_steps": 1005, "loss": 0.4391, "lr": 7.999130479859843e-05, "epoch": 0.530359355638166, "percentage": 10.65, "elapsed_time": "1:32:55", "remaining_time": "12:59:49"}
+{"current_steps": 108, "total_steps": 1005, "loss": 0.4336, "lr": 7.998816501960465e-05, "epoch": 0.5353159851301115, "percentage": 10.75, "elapsed_time": "1:33:46", "remaining_time": "12:58:48"}
+{"current_steps": 109, "total_steps": 1005, "loss": 0.4391, "lr": 7.998454229978217e-05, "epoch": 0.540272614622057, "percentage": 10.85, "elapsed_time": "1:34:37", "remaining_time": "12:57:48"}
+{"current_steps": 110, "total_steps": 1005, "loss": 0.4455, "lr": 7.998043668288292e-05, "epoch": 0.5452292441140025, "percentage": 10.95, "elapsed_time": "1:35:28", "remaining_time": "12:56:46"}
+{"current_steps": 111, "total_steps": 1005, "loss": 0.4323, "lr": 7.997584821849081e-05, "epoch": 0.550185873605948, "percentage": 11.04, "elapsed_time": "1:36:19", "remaining_time": "12:55:44"}
+{"current_steps": 112, "total_steps": 1005, "loss": 0.4345, "lr": 7.997077696202118e-05, "epoch": 0.5551425030978935, "percentage": 11.14, "elapsed_time": "1:37:10", "remaining_time": "12:54:44"}
+{"current_steps": 113, "total_steps": 1005, "loss": 0.4357, "lr": 7.996522297472005e-05, "epoch": 0.5600991325898389, "percentage": 11.24, "elapsed_time": "1:38:01", "remaining_time": "12:53:45"}
+{"current_steps": 114, "total_steps": 1005, "loss": 0.4244, "lr": 7.995918632366346e-05, "epoch": 0.5650557620817844, "percentage": 11.34, "elapsed_time": "1:38:52", "remaining_time": "12:52:45"}
+{"current_steps": 115, "total_steps": 1005, "loss": 0.4344, "lr": 7.995266708175662e-05, "epoch": 0.5700123915737298, "percentage": 11.44, "elapsed_time": "1:39:43", "remaining_time": "12:51:47"}
+{"current_steps": 116, "total_steps": 1005, "loss": 0.4254, "lr": 7.994566532773299e-05, "epoch": 0.5749690210656754, "percentage": 11.54, "elapsed_time": "1:40:34", "remaining_time": "12:50:45"}
+{"current_steps": 117, "total_steps": 1005, "loss": 0.4207, "lr": 7.993818114615345e-05, "epoch": 0.5799256505576208, "percentage": 11.64, "elapsed_time": "1:41:33", "remaining_time": "12:50:50"}
+{"current_steps": 118, "total_steps": 1005, "loss": 0.4283, "lr": 7.993021462740514e-05, "epoch": 0.5848822800495663, "percentage": 11.74, "elapsed_time": "1:42:32", "remaining_time": "12:50:48"}
+{"current_steps": 119, "total_steps": 1005, "loss": 0.4239, "lr": 7.992176586770047e-05, "epoch": 0.5898389095415117, "percentage": 11.84, "elapsed_time": "1:43:23", "remaining_time": "12:49:47"}
+{"current_steps": 120, "total_steps": 1005, "loss": 0.4247, "lr": 7.991283496907591e-05, "epoch": 0.5947955390334573, "percentage": 11.94, "elapsed_time": "1:44:14", "remaining_time": "12:48:49"}
+{"current_steps": 121, "total_steps": 1005, "loss": 0.4272, "lr": 7.990342203939075e-05, "epoch": 0.5997521685254027, "percentage": 12.04, "elapsed_time": "1:45:05", "remaining_time": "12:47:49"}
+{"current_steps": 122, "total_steps": 1005, "loss": 0.419, "lr": 7.989352719232583e-05, "epoch": 0.6047087980173482, "percentage": 12.14, "elapsed_time": "1:45:56", "remaining_time": "12:46:48"}
+{"current_steps": 123, "total_steps": 1005, "loss": 0.4245, "lr": 7.988315054738214e-05, "epoch": 0.6096654275092936, "percentage": 12.24, "elapsed_time": "1:46:47", "remaining_time": "12:45:47"}
+{"current_steps": 124, "total_steps": 1005, "loss": 0.419, "lr": 7.987229222987942e-05, "epoch": 0.6146220570012392, "percentage": 12.34, "elapsed_time": "1:47:38", "remaining_time": "12:44:47"}
+{"current_steps": 125, "total_steps": 1005, "loss": 0.4241, "lr": 7.986095237095457e-05, "epoch": 0.6195786864931846, "percentage": 12.44, "elapsed_time": "1:48:29", "remaining_time": "12:43:46"}
+{"current_steps": 126, "total_steps": 1005, "loss": 0.4141, "lr": 7.984913110756015e-05, "epoch": 0.6245353159851301, "percentage": 12.54, "elapsed_time": "1:49:20", "remaining_time": "12:42:45"}
+{"current_steps": 127, "total_steps": 1005, "loss": 0.4221, "lr": 7.983682858246265e-05, "epoch": 0.6294919454770755, "percentage": 12.64, "elapsed_time": "1:50:11", "remaining_time": "12:41:44"}
+{"current_steps": 128, "total_steps": 1005, "loss": 0.4252, "lr": 7.982404494424083e-05, "epoch": 0.6344485749690211, "percentage": 12.74, "elapsed_time": "1:51:01", "remaining_time": "12:40:44"}
+{"current_steps": 129, "total_steps": 1005, "loss": 0.4192, "lr": 7.98107803472839e-05, "epoch": 0.6394052044609665, "percentage": 12.84, "elapsed_time": "1:51:53", "remaining_time": "12:39:46"}
+{"current_steps": 130, "total_steps": 1005, "loss": 0.4325, "lr": 7.979703495178964e-05, "epoch": 0.644361833952912, "percentage": 12.94, "elapsed_time": "1:52:44", "remaining_time": "12:38:48"}
+{"current_steps": 131, "total_steps": 1005, "loss": 0.43, "lr": 7.978280892376246e-05, "epoch": 0.6493184634448576, "percentage": 13.03, "elapsed_time": "1:53:35", "remaining_time": "12:37:49"}
+{"current_steps": 132, "total_steps": 1005, "loss": 0.4156, "lr": 7.976810243501147e-05, "epoch": 0.654275092936803, "percentage": 13.13, "elapsed_time": "1:54:34", "remaining_time": "12:37:43"}
+{"current_steps": 133, "total_steps": 1005, "loss": 0.4204, "lr": 7.975291566314832e-05, "epoch": 0.6592317224287485, "percentage": 13.23, "elapsed_time": "1:55:32", "remaining_time": "12:37:33"}
+{"current_steps": 134, "total_steps": 1005, "loss": 0.4282, "lr": 7.973724879158506e-05, "epoch": 0.6641883519206939, "percentage": 13.33, "elapsed_time": "1:56:23", "remaining_time": "12:36:34"}
+{"current_steps": 135, "total_steps": 1005, "loss": 0.419, "lr": 7.972110200953197e-05, "epoch": 0.6691449814126395, "percentage": 13.43, "elapsed_time": "1:57:14", "remaining_time": "12:35:35"}
+{"current_steps": 136, "total_steps": 1005, "loss": 0.4262, "lr": 7.970447551199527e-05, "epoch": 0.6741016109045849, "percentage": 13.53, "elapsed_time": "1:58:05", "remaining_time": "12:34:34"}
+{"current_steps": 137, "total_steps": 1005, "loss": 0.4183, "lr": 7.968736949977473e-05, "epoch": 0.6790582403965304, "percentage": 13.63, "elapsed_time": "1:58:56", "remaining_time": "12:33:34"}
+{"current_steps": 138, "total_steps": 1005, "loss": 0.4254, "lr": 7.966978417946126e-05, "epoch": 0.6840148698884758, "percentage": 13.73, "elapsed_time": "1:59:47", "remaining_time": "12:32:34"}
+{"current_steps": 139, "total_steps": 1005, "loss": 0.4234, "lr": 7.965171976343443e-05, "epoch": 0.6889714993804213, "percentage": 13.83, "elapsed_time": "2:00:38", "remaining_time": "12:31:37"}
+{"current_steps": 140, "total_steps": 1005, "loss": 0.4254, "lr": 7.96331764698599e-05, "epoch": 0.6939281288723668, "percentage": 13.93, "elapsed_time": "2:01:29", "remaining_time": "12:30:38"}
+{"current_steps": 141, "total_steps": 1005, "loss": 0.4348, "lr": 7.961415452268675e-05, "epoch": 0.6988847583643123, "percentage": 14.03, "elapsed_time": "2:02:20", "remaining_time": "12:29:39"}
+{"current_steps": 142, "total_steps": 1005, "loss": 0.4156, "lr": 7.959465415164485e-05, "epoch": 0.7038413878562577, "percentage": 14.13, "elapsed_time": "2:03:11", "remaining_time": "12:28:41"}
+{"current_steps": 143, "total_steps": 1005, "loss": 0.4208, "lr": 7.957467559224202e-05, "epoch": 0.7087980173482032, "percentage": 14.23, "elapsed_time": "2:04:02", "remaining_time": "12:27:40"}
+{"current_steps": 144, "total_steps": 1005, "loss": 0.4176, "lr": 7.955421908576115e-05, "epoch": 0.7137546468401487, "percentage": 14.33, "elapsed_time": "2:04:52", "remaining_time": "12:26:41"}
+{"current_steps": 145, "total_steps": 1005, "loss": 0.4201, "lr": 7.953328487925744e-05, "epoch": 0.7187112763320942, "percentage": 14.43, "elapsed_time": "2:05:44", "remaining_time": "12:25:44"}
+{"current_steps": 146, "total_steps": 1005, "loss": 0.4197, "lr": 7.951187322555525e-05, "epoch": 0.7236679058240396, "percentage": 14.53, "elapsed_time": "2:06:35", "remaining_time": "12:24:47"}
+{"current_steps": 147, "total_steps": 1005, "loss": 0.4164, "lr": 7.948998438324515e-05, "epoch": 0.7286245353159851, "percentage": 14.63, "elapsed_time": "2:07:36", "remaining_time": "12:24:47"}
+{"current_steps": 148, "total_steps": 1005, "loss": 0.4186, "lr": 7.946761861668072e-05, "epoch": 0.7335811648079306, "percentage": 14.73, "elapsed_time": "2:08:33", "remaining_time": "12:24:25"}
+{"current_steps": 149, "total_steps": 1005, "loss": 0.4168, "lr": 7.944477619597546e-05, "epoch": 0.7385377942998761, "percentage": 14.83, "elapsed_time": "2:09:24", "remaining_time": "12:23:25"}
+{"current_steps": 150, "total_steps": 1005, "loss": 0.4191, "lr": 7.94214573969994e-05, "epoch": 0.7434944237918215, "percentage": 14.93, "elapsed_time": "2:10:15", "remaining_time": "12:22:26"}
+{"current_steps": 151, "total_steps": 1005, "loss": 0.421, "lr": 7.939766250137589e-05, "epoch": 0.748451053283767, "percentage": 15.02, "elapsed_time": "2:11:06", "remaining_time": "12:21:28"}
+{"current_steps": 152, "total_steps": 1005, "loss": 0.4172, "lr": 7.93733917964781e-05, "epoch": 0.7534076827757125, "percentage": 15.12, "elapsed_time": "2:11:57", "remaining_time": "12:20:29"}
+{"current_steps": 153, "total_steps": 1005, "loss": 0.4158, "lr": 7.934864557542565e-05, "epoch": 0.758364312267658, "percentage": 15.22, "elapsed_time": "2:12:47", "remaining_time": "12:19:30"}
+{"current_steps": 154, "total_steps": 1005, "loss": 0.4096, "lr": 7.932342413708094e-05, "epoch": 0.7633209417596035, "percentage": 15.32, "elapsed_time": "2:13:38", "remaining_time": "12:18:31"}
+{"current_steps": 155, "total_steps": 1005, "loss": 0.4175, "lr": 7.929772778604569e-05, "epoch": 0.7682775712515489, "percentage": 15.42, "elapsed_time": "2:14:29", "remaining_time": "12:17:32"}
+{"current_steps": 156, "total_steps": 1005, "loss": 0.4075, "lr": 7.927155683265711e-05, "epoch": 0.7732342007434945, "percentage": 15.52, "elapsed_time": "2:15:20", "remaining_time": "12:16:34"}
+{"current_steps": 157, "total_steps": 1005, "loss": 0.4162, "lr": 7.924491159298429e-05, "epoch": 0.7781908302354399, "percentage": 15.62, "elapsed_time": "2:16:11", "remaining_time": "12:15:36"}
+{"current_steps": 158, "total_steps": 1005, "loss": 0.4178, "lr": 7.921779238882428e-05, "epoch": 0.7831474597273854, "percentage": 15.72, "elapsed_time": "2:17:02", "remaining_time": "12:14:38"}
+{"current_steps": 159, "total_steps": 1005, "loss": 0.4087, "lr": 7.919019954769828e-05, "epoch": 0.7881040892193308, "percentage": 15.82, "elapsed_time": "2:17:53", "remaining_time": "12:13:40"}
+{"current_steps": 160, "total_steps": 1005, "loss": 0.4162, "lr": 7.916213340284759e-05, "epoch": 0.7930607187112764, "percentage": 15.92, "elapsed_time": "2:18:44", "remaining_time": "12:12:45"}
+{"current_steps": 161, "total_steps": 1005, "loss": 0.4122, "lr": 7.913359429322972e-05, "epoch": 0.7980173482032218, "percentage": 16.02, "elapsed_time": "2:19:35", "remaining_time": "12:11:47"}
+{"current_steps": 162, "total_steps": 1005, "loss": 0.4053, "lr": 7.910458256351416e-05, "epoch": 0.8029739776951673, "percentage": 16.12, "elapsed_time": "2:20:38", "remaining_time": "12:11:50"}
+{"current_steps": 163, "total_steps": 1005, "loss": 0.4066, "lr": 7.907509856407828e-05, "epoch": 0.8079306071871127, "percentage": 16.22, "elapsed_time": "2:21:35", "remaining_time": "12:11:25"}
+{"current_steps": 164, "total_steps": 1005, "loss": 0.4131, "lr": 7.904514265100315e-05, "epoch": 0.8128872366790583, "percentage": 16.32, "elapsed_time": "2:22:26", "remaining_time": "12:10:27"}
+{"current_steps": 165, "total_steps": 1005, "loss": 0.4125, "lr": 7.901471518606913e-05, "epoch": 0.8178438661710037, "percentage": 16.42, "elapsed_time": "2:23:17", "remaining_time": "12:09:30"}
+{"current_steps": 166, "total_steps": 1005, "loss": 0.4078, "lr": 7.898381653675158e-05, "epoch": 0.8228004956629492, "percentage": 16.52, "elapsed_time": "2:24:08", "remaining_time": "12:08:32"}
+{"current_steps": 167, "total_steps": 1005, "loss": 0.4096, "lr": 7.895244707621638e-05, "epoch": 0.8277571251548946, "percentage": 16.62, "elapsed_time": "2:24:59", "remaining_time": "12:07:34"}
+{"current_steps": 168, "total_steps": 1005, "loss": 0.4123, "lr": 7.892060718331546e-05, "epoch": 0.8327137546468402, "percentage": 16.72, "elapsed_time": "2:25:50", "remaining_time": "12:06:36"}
+{"current_steps": 169, "total_steps": 1005, "loss": 0.4103, "lr": 7.888829724258221e-05, "epoch": 0.8376703841387856, "percentage": 16.82, "elapsed_time": "2:26:41", "remaining_time": "12:05:38"}
+{"current_steps": 170, "total_steps": 1005, "loss": 0.4133, "lr": 7.885551764422682e-05, "epoch": 0.8426270136307311, "percentage": 16.92, "elapsed_time": "2:27:32", "remaining_time": "12:04:39"}
+{"current_steps": 171, "total_steps": 1005, "loss": 0.4124, "lr": 7.882226878413157e-05, "epoch": 0.8475836431226765, "percentage": 17.01, "elapsed_time": "2:28:23", "remaining_time": "12:03:41"}
+{"current_steps": 172, "total_steps": 1005, "loss": 0.4091, "lr": 7.878855106384608e-05, "epoch": 0.8525402726146221, "percentage": 17.11, "elapsed_time": "2:29:13", "remaining_time": "12:02:44"}
+{"current_steps": 173, "total_steps": 1005, "loss": 0.4069, "lr": 7.875436489058243e-05, "epoch": 0.8574969021065675, "percentage": 17.21, "elapsed_time": "2:30:04", "remaining_time": "12:01:46"}
+{"current_steps": 174, "total_steps": 1005, "loss": 0.4079, "lr": 7.871971067721024e-05, "epoch": 0.862453531598513, "percentage": 17.31, "elapsed_time": "2:30:56", "remaining_time": "12:00:51"}
+{"current_steps": 175, "total_steps": 1005, "loss": 0.4122, "lr": 7.86845888422517e-05, "epoch": 0.8674101610904585, "percentage": 17.41, "elapsed_time": "2:31:47", "remaining_time": "11:59:55"}
+{"current_steps": 176, "total_steps": 1005, "loss": 0.4027, "lr": 7.864899980987654e-05, "epoch": 0.872366790582404, "percentage": 17.51, "elapsed_time": "2:32:38", "remaining_time": "11:58:58"}
+{"current_steps": 177, "total_steps": 1005, "loss": 0.4012, "lr": 7.861294400989681e-05, "epoch": 0.8773234200743495, "percentage": 17.61, "elapsed_time": "2:33:41", "remaining_time": "11:58:56"}
+{"current_steps": 178, "total_steps": 1005, "loss": 0.4042, "lr": 7.857642187776182e-05, "epoch": 0.8822800495662949, "percentage": 17.71, "elapsed_time": "2:34:37", "remaining_time": "11:58:22"}
+{"current_steps": 179, "total_steps": 1005, "loss": 0.4036, "lr": 7.85394338545528e-05, "epoch": 0.8872366790582404, "percentage": 17.81, "elapsed_time": "2:35:28", "remaining_time": "11:57:24"}
+{"current_steps": 180, "total_steps": 1005, "loss": 0.405, "lr": 7.850198038697756e-05, "epoch": 0.8921933085501859, "percentage": 17.91, "elapsed_time": "2:36:18", "remaining_time": "11:56:26"}
+{"current_steps": 181, "total_steps": 1005, "loss": 0.4022, "lr": 7.846406192736517e-05, "epoch": 0.8971499380421314, "percentage": 18.01, "elapsed_time": "2:37:09", "remaining_time": "11:55:29"}
+{"current_steps": 182, "total_steps": 1005, "loss": 0.3952, "lr": 7.842567893366043e-05, "epoch": 0.9021065675340768, "percentage": 18.11, "elapsed_time": "2:38:00", "remaining_time": "11:54:32"}
+{"current_steps": 183, "total_steps": 1005, "loss": 0.4087, "lr": 7.838683186941835e-05, "epoch": 0.9070631970260223, "percentage": 18.21, "elapsed_time": "2:38:51", "remaining_time": "11:53:34"}
+{"current_steps": 184, "total_steps": 1005, "loss": 0.4035, "lr": 7.834752120379857e-05, "epoch": 0.9120198265179678, "percentage": 18.31, "elapsed_time": "2:39:42", "remaining_time": "11:52:36"}
+{"current_steps": 185, "total_steps": 1005, "loss": 0.4125, "lr": 7.830774741155975e-05, "epoch": 0.9169764560099133, "percentage": 18.41, "elapsed_time": "2:40:33", "remaining_time": "11:51:40"}
+{"current_steps": 186, "total_steps": 1005, "loss": 0.4006, "lr": 7.826751097305367e-05, "epoch": 0.9219330855018587, "percentage": 18.51, "elapsed_time": "2:41:24", "remaining_time": "11:50:43"}
+{"current_steps": 187, "total_steps": 1005, "loss": 0.399, "lr": 7.822681237421956e-05, "epoch": 0.9268897149938042, "percentage": 18.61, "elapsed_time": "2:42:15", "remaining_time": "11:49:45"}
+{"current_steps": 188, "total_steps": 1005, "loss": 0.3977, "lr": 7.818565210657827e-05, "epoch": 0.9318463444857497, "percentage": 18.71, "elapsed_time": "2:43:06", "remaining_time": "11:48:48"}
+{"current_steps": 189, "total_steps": 1005, "loss": 0.4067, "lr": 7.814403066722622e-05, "epoch": 0.9368029739776952, "percentage": 18.81, "elapsed_time": "2:43:57", "remaining_time": "11:47:52"}
+{"current_steps": 190, "total_steps": 1005, "loss": 0.4086, "lr": 7.810194855882943e-05, "epoch": 0.9417596034696406, "percentage": 18.91, "elapsed_time": "2:44:48", "remaining_time": "11:46:56"}
+{"current_steps": 191, "total_steps": 1005, "loss": 0.4073, "lr": 7.805940628961747e-05, "epoch": 0.9467162329615861, "percentage": 19.0, "elapsed_time": "2:45:39", "remaining_time": "11:45:59"}
+{"current_steps": 192, "total_steps": 1005, "loss": 0.4019, "lr": 7.801640437337736e-05, "epoch": 0.9516728624535316, "percentage": 19.1, "elapsed_time": "2:46:43", "remaining_time": "11:45:58"}
+{"current_steps": 193, "total_steps": 1005, "loss": 0.4045, "lr": 7.797294332944725e-05, "epoch": 0.9566294919454771, "percentage": 19.2, "elapsed_time": "2:47:40", "remaining_time": "11:45:26"}
+{"current_steps": 194, "total_steps": 1005, "loss": 0.3992, "lr": 7.792902368271027e-05, "epoch": 0.9615861214374225, "percentage": 19.3, "elapsed_time": "2:48:31", "remaining_time": "11:44:28"}
+{"current_steps": 195, "total_steps": 1005, "loss": 0.4028, "lr": 7.788464596358811e-05, "epoch": 0.966542750929368, "percentage": 19.4, "elapsed_time": "2:49:21", "remaining_time": "11:43:31"}
+{"current_steps": 196, "total_steps": 1005, "loss": 0.4088, "lr": 7.783981070803469e-05, "epoch": 0.9714993804213135, "percentage": 19.5, "elapsed_time": "2:50:12", "remaining_time": "11:42:34"}
+{"current_steps": 197, "total_steps": 1005, "loss": 0.4121, "lr": 7.779451845752957e-05, "epoch": 0.976456009913259, "percentage": 19.6, "elapsed_time": "2:51:04", "remaining_time": "11:41:39"}
+{"current_steps": 198, "total_steps": 1005, "loss": 0.3978, "lr": 7.774876975907154e-05, "epoch": 0.9814126394052045, "percentage": 19.7, "elapsed_time": "2:51:55", "remaining_time": "11:40:42"}
+{"current_steps": 199, "total_steps": 1005, "loss": 0.4006, "lr": 7.770256516517191e-05, "epoch": 0.9863692688971499, "percentage": 19.8, "elapsed_time": "2:52:46", "remaining_time": "11:39:45"}
+{"current_steps": 200, "total_steps": 1005, "loss": 0.406, "lr": 7.765590523384794e-05, "epoch": 0.9913258983890955, "percentage": 19.9, "elapsed_time": "2:53:37", "remaining_time": "11:38:48"}
+{"current_steps": 201, "total_steps": 1005, "loss": 0.3971, "lr": 7.760879052861596e-05, "epoch": 0.9962825278810409, "percentage": 20.0, "elapsed_time": "2:54:27", "remaining_time": "11:37:50"}
+{"current_steps": 202, "total_steps": 1005, "loss": 0.4958, "lr": 7.756122161848474e-05, "epoch": 1.0012391573729864, "percentage": 20.1, "elapsed_time": "2:56:36", "remaining_time": "11:42:02"}
+{"current_steps": 203, "total_steps": 1005, "loss": 0.3909, "lr": 7.751319907794846e-05, "epoch": 1.0061957868649318, "percentage": 20.2, "elapsed_time": "2:57:27", "remaining_time": "11:41:05"}
+{"current_steps": 204, "total_steps": 1005, "loss": 0.3833, "lr": 7.746472348697987e-05, "epoch": 1.0111524163568772, "percentage": 20.3, "elapsed_time": "2:58:18", "remaining_time": "11:40:07"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db78c898af058a4a3b01ccff66d572709714e2bc010e28acb808be5e6e56cf6
+size 7160