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:d78bb2a79f9a7ada2cdbdb5783c243b540406e025fdccae8a6ae62fd5ce788d4
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e5eb059322994c989c821f294cecbad00b589b3a70c1feac02ad9ba50dbf01
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f56499826d84fdaa95ba00c3056fab46d17667f120d6e630cef4d86bb9fd55e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:355af90552b58e62841a767d6328ed578b1f87b15d0e0c181de60e1bf9a5d4a7
+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 +1,187 @@
+{"current_steps": 1, "total_steps": 930, "loss": 1.078, "lr": 8.60215053763441e-07, "epoch": 0.0053637277908146165, "percentage": 0.11, "elapsed_time": "0:01:52", "remaining_time": "1 day, 5:06:51"}
+{"current_steps": 2, "total_steps": 930, "loss": 1.0759, "lr": 1.720430107526882e-06, "epoch": 0.010727455581629233, "percentage": 0.22, "elapsed_time": "0:03:32", "remaining_time": "1 day, 3:23:57"}
+{"current_steps": 3, "total_steps": 930, "loss": 1.0708, "lr": 2.580645161290323e-06, "epoch": 0.01609118337244385, "percentage": 0.32, "elapsed_time": "0:05:12", "remaining_time": "1 day, 2:47:53"}
+{"current_steps": 4, "total_steps": 930, "loss": 1.0682, "lr": 3.440860215053764e-06, "epoch": 0.021454911163258466, "percentage": 0.43, "elapsed_time": "0:06:51", "remaining_time": "1 day, 2:29:14"}
+{"current_steps": 5, "total_steps": 930, "loss": 1.0306, "lr": 4.3010752688172045e-06, "epoch": 0.02681863895407308, "percentage": 0.54, "elapsed_time": "0:08:32", "remaining_time": "1 day, 2:20:12"}
+{"current_steps": 6, "total_steps": 930, "loss": 0.9885, "lr": 5.161290322580646e-06, "epoch": 0.0321823667448877, "percentage": 0.65, "elapsed_time": "0:10:12", "remaining_time": "1 day, 2:10:59"}
+{"current_steps": 7, "total_steps": 930, "loss": 0.9701, "lr": 6.021505376344087e-06, "epoch": 0.03754609453570231, "percentage": 0.75, "elapsed_time": "0:11:51", "remaining_time": "1 day, 2:04:31"}
+{"current_steps": 8, "total_steps": 930, "loss": 0.9509, "lr": 6.881720430107528e-06, "epoch": 0.04290982232651693, "percentage": 0.86, "elapsed_time": "0:13:31", "remaining_time": "1 day, 1:58:05"}
+{"current_steps": 9, "total_steps": 930, "loss": 0.9599, "lr": 7.741935483870968e-06, "epoch": 0.048273550117331546, "percentage": 0.97, "elapsed_time": "0:15:10", "remaining_time": "1 day, 1:53:20"}
+{"current_steps": 10, "total_steps": 930, "loss": 0.9366, "lr": 8.602150537634409e-06, "epoch": 0.05363727790814616, "percentage": 1.08, "elapsed_time": "0:16:50", "remaining_time": "1 day, 1:49:47"}
+{"current_steps": 11, "total_steps": 930, "loss": 0.9, "lr": 9.46236559139785e-06, "epoch": 0.05900100569896078, "percentage": 1.18, "elapsed_time": "0:18:29", "remaining_time": "1 day, 1:45:30"}
+{"current_steps": 12, "total_steps": 930, "loss": 0.8784, "lr": 1.0322580645161291e-05, "epoch": 0.0643647334897754, "percentage": 1.29, "elapsed_time": "0:20:10", "remaining_time": "1 day, 1:42:46"}
+{"current_steps": 13, "total_steps": 930, "loss": 0.8577, "lr": 1.118279569892473e-05, "epoch": 0.06972846128059002, "percentage": 1.4, "elapsed_time": "0:21:49", "remaining_time": "1 day, 1:39:56"}
+{"current_steps": 14, "total_steps": 930, "loss": 0.8332, "lr": 1.2043010752688173e-05, "epoch": 0.07509218907140462, "percentage": 1.51, "elapsed_time": "0:23:28", "remaining_time": "1 day, 1:36:26"}
+{"current_steps": 15, "total_steps": 930, "loss": 0.8233, "lr": 1.2903225806451613e-05, "epoch": 0.08045591686221924, "percentage": 1.61, "elapsed_time": "0:25:08", "remaining_time": "1 day, 1:33:47"}
+{"current_steps": 16, "total_steps": 930, "loss": 0.8046, "lr": 1.3763440860215056e-05, "epoch": 0.08581964465303386, "percentage": 1.72, "elapsed_time": "0:26:47", "remaining_time": "1 day, 1:30:50"}
+{"current_steps": 17, "total_steps": 930, "loss": 0.7915, "lr": 1.4623655913978497e-05, "epoch": 0.09118337244384847, "percentage": 1.83, "elapsed_time": "0:28:27", "remaining_time": "1 day, 1:27:57"}
+{"current_steps": 18, "total_steps": 930, "loss": 0.7924, "lr": 1.5483870967741936e-05, "epoch": 0.09654710023466309, "percentage": 1.94, "elapsed_time": "0:30:06", "remaining_time": "1 day, 1:25:17"}
+{"current_steps": 19, "total_steps": 930, "loss": 0.7815, "lr": 1.6344086021505377e-05, "epoch": 0.10191082802547771, "percentage": 2.04, "elapsed_time": "0:31:45", "remaining_time": "1 day, 1:22:42"}
+{"current_steps": 20, "total_steps": 930, "loss": 0.7695, "lr": 1.7204301075268818e-05, "epoch": 0.10727455581629232, "percentage": 2.15, "elapsed_time": "0:33:24", "remaining_time": "1 day, 1:20:17"}
+{"current_steps": 21, "total_steps": 930, "loss": 0.7656, "lr": 1.806451612903226e-05, "epoch": 0.11263828360710694, "percentage": 2.26, "elapsed_time": "0:35:04", "remaining_time": "1 day, 1:17:53"}
+{"current_steps": 22, "total_steps": 930, "loss": 0.7577, "lr": 1.89247311827957e-05, "epoch": 0.11800201139792156, "percentage": 2.37, "elapsed_time": "0:36:43", "remaining_time": "1 day, 1:15:30"}
+{"current_steps": 23, "total_steps": 930, "loss": 0.7494, "lr": 1.978494623655914e-05, "epoch": 0.12336573918873617, "percentage": 2.47, "elapsed_time": "0:38:22", "remaining_time": "1 day, 1:13:12"}
+{"current_steps": 24, "total_steps": 930, "loss": 0.743, "lr": 2.0645161290322582e-05, "epoch": 0.1287294669795508, "percentage": 2.58, "elapsed_time": "0:40:02", "remaining_time": "1 day, 1:11:15"}
+{"current_steps": 25, "total_steps": 930, "loss": 0.7375, "lr": 2.1505376344086024e-05, "epoch": 0.1340931947703654, "percentage": 2.69, "elapsed_time": "0:41:41", "remaining_time": "1 day, 1:09:03"}
+{"current_steps": 26, "total_steps": 930, "loss": 0.7351, "lr": 2.236559139784946e-05, "epoch": 0.13945692256118003, "percentage": 2.8, "elapsed_time": "0:43:20", "remaining_time": "1 day, 1:06:57"}
+{"current_steps": 27, "total_steps": 930, "loss": 0.7271, "lr": 2.3225806451612906e-05, "epoch": 0.14482065035199462, "percentage": 2.9, "elapsed_time": "0:45:00", "remaining_time": "1 day, 1:05:18"}
+{"current_steps": 28, "total_steps": 930, "loss": 0.7199, "lr": 2.4086021505376347e-05, "epoch": 0.15018437814280924, "percentage": 3.01, "elapsed_time": "0:46:40", "remaining_time": "1 day, 1:03:41"}
+{"current_steps": 29, "total_steps": 930, "loss": 0.7234, "lr": 2.4946236559139788e-05, "epoch": 0.15554810593362386, "percentage": 3.12, "elapsed_time": "0:48:19", "remaining_time": "1 day, 1:01:39"}
+{"current_steps": 30, "total_steps": 930, "loss": 0.7178, "lr": 2.5806451612903226e-05, "epoch": 0.16091183372443849, "percentage": 3.23, "elapsed_time": "0:49:59", "remaining_time": "1 day, 0:59:43"}
+{"current_steps": 31, "total_steps": 930, "loss": 0.7136, "lr": 2.6666666666666667e-05, "epoch": 0.1662755615152531, "percentage": 3.33, "elapsed_time": "0:51:39", "remaining_time": "1 day, 0:57:54"}
+{"current_steps": 32, "total_steps": 930, "loss": 0.7099, "lr": 2.752688172043011e-05, "epoch": 0.17163928930606773, "percentage": 3.44, "elapsed_time": "0:53:18", "remaining_time": "1 day, 0:56:02"}
+{"current_steps": 33, "total_steps": 930, "loss": 0.7043, "lr": 2.8387096774193552e-05, "epoch": 0.17700301709688232, "percentage": 3.55, "elapsed_time": "0:54:57", "remaining_time": "1 day, 0:54:00"}
+{"current_steps": 34, "total_steps": 930, "loss": 0.7037, "lr": 2.9247311827956993e-05, "epoch": 0.18236674488769694, "percentage": 3.66, "elapsed_time": "0:56:37", "remaining_time": "1 day, 0:52:01"}
+{"current_steps": 35, "total_steps": 930, "loss": 0.7058, "lr": 3.010752688172043e-05, "epoch": 0.18773047267851156, "percentage": 3.76, "elapsed_time": "0:58:16", "remaining_time": "1 day, 0:50:16"}
+{"current_steps": 36, "total_steps": 930, "loss": 0.6989, "lr": 3.096774193548387e-05, "epoch": 0.19309420046932618, "percentage": 3.87, "elapsed_time": "0:59:57", "remaining_time": "1 day, 0:48:52"}
+{"current_steps": 37, "total_steps": 930, "loss": 0.7036, "lr": 3.182795698924731e-05, "epoch": 0.1984579282601408, "percentage": 3.98, "elapsed_time": "1:01:36", "remaining_time": "1 day, 0:46:56"}
+{"current_steps": 38, "total_steps": 930, "loss": 0.6961, "lr": 3.2688172043010754e-05, "epoch": 0.20382165605095542, "percentage": 4.09, "elapsed_time": "1:03:15", "remaining_time": "1 day, 0:44:58"}
+{"current_steps": 39, "total_steps": 930, "loss": 0.6889, "lr": 3.3548387096774195e-05, "epoch": 0.20918538384177002, "percentage": 4.19, "elapsed_time": "1:04:54", "remaining_time": "1 day, 0:43:03"}
+{"current_steps": 40, "total_steps": 930, "loss": 0.7016, "lr": 3.4408602150537636e-05, "epoch": 0.21454911163258464, "percentage": 4.3, "elapsed_time": "1:06:34", "remaining_time": "1 day, 0:41:19"}
+{"current_steps": 41, "total_steps": 930, "loss": 0.6924, "lr": 3.526881720430108e-05, "epoch": 0.21991283942339926, "percentage": 4.41, "elapsed_time": "1:08:14", "remaining_time": "1 day, 0:39:38"}
+{"current_steps": 42, "total_steps": 930, "loss": 0.6948, "lr": 3.612903225806452e-05, "epoch": 0.22527656721421388, "percentage": 4.52, "elapsed_time": "1:09:54", "remaining_time": "1 day, 0:37:53"}
+{"current_steps": 43, "total_steps": 930, "loss": 0.6843, "lr": 3.698924731182796e-05, "epoch": 0.2306402950050285, "percentage": 4.62, "elapsed_time": "1:11:33", "remaining_time": "1 day, 0:36:01"}
+{"current_steps": 44, "total_steps": 930, "loss": 0.6859, "lr": 3.78494623655914e-05, "epoch": 0.23600402279584312, "percentage": 4.73, "elapsed_time": "1:13:13", "remaining_time": "1 day, 0:34:20"}
+{"current_steps": 45, "total_steps": 930, "loss": 0.6852, "lr": 3.870967741935484e-05, "epoch": 0.24136775058665771, "percentage": 4.84, "elapsed_time": "1:14:52", "remaining_time": "1 day, 0:32:27"}
+{"current_steps": 46, "total_steps": 930, "loss": 0.6911, "lr": 3.956989247311828e-05, "epoch": 0.24673147837747234, "percentage": 4.95, "elapsed_time": "1:16:31", "remaining_time": "1 day, 0:30:37"}
+{"current_steps": 47, "total_steps": 930, "loss": 0.6879, "lr": 4.0430107526881724e-05, "epoch": 0.25209520616828696, "percentage": 5.05, "elapsed_time": "1:18:10", "remaining_time": "1 day, 0:28:45"}
+{"current_steps": 48, "total_steps": 930, "loss": 0.6842, "lr": 4.1290322580645165e-05, "epoch": 0.2574589339591016, "percentage": 5.16, "elapsed_time": "1:19:49", "remaining_time": "1 day, 0:26:55"}
+{"current_steps": 49, "total_steps": 930, "loss": 0.6794, "lr": 4.2150537634408606e-05, "epoch": 0.2628226617499162, "percentage": 5.27, "elapsed_time": "1:21:29", "remaining_time": "1 day, 0:25:05"}
+{"current_steps": 50, "total_steps": 930, "loss": 0.6766, "lr": 4.301075268817205e-05, "epoch": 0.2681863895407308, "percentage": 5.38, "elapsed_time": "1:23:08", "remaining_time": "1 day, 0:23:17"}
+{"current_steps": 51, "total_steps": 930, "loss": 0.6817, "lr": 4.387096774193548e-05, "epoch": 0.27355011733154544, "percentage": 5.48, "elapsed_time": "1:24:47", "remaining_time": "1 day, 0:21:29"}
+{"current_steps": 52, "total_steps": 930, "loss": 0.6831, "lr": 4.473118279569892e-05, "epoch": 0.27891384512236006, "percentage": 5.59, "elapsed_time": "1:26:26", "remaining_time": "1 day, 0:19:40"}
+{"current_steps": 53, "total_steps": 930, "loss": 0.6785, "lr": 4.559139784946237e-05, "epoch": 0.2842775729131747, "percentage": 5.7, "elapsed_time": "1:28:06", "remaining_time": "1 day, 0:17:51"}
+{"current_steps": 54, "total_steps": 930, "loss": 0.6824, "lr": 4.645161290322581e-05, "epoch": 0.28964130070398925, "percentage": 5.81, "elapsed_time": "1:29:45", "remaining_time": "1 day, 0:16:03"}
+{"current_steps": 55, "total_steps": 930, "loss": 0.6796, "lr": 4.731182795698925e-05, "epoch": 0.29500502849480387, "percentage": 5.91, "elapsed_time": "1:31:24", "remaining_time": "1 day, 0:14:15"}
+{"current_steps": 56, "total_steps": 930, "loss": 0.6682, "lr": 4.8172043010752693e-05, "epoch": 0.3003687562856185, "percentage": 6.02, "elapsed_time": "1:33:03", "remaining_time": "1 day, 0:12:28"}
+{"current_steps": 57, "total_steps": 930, "loss": 0.6789, "lr": 4.9032258064516135e-05, "epoch": 0.3057324840764331, "percentage": 6.13, "elapsed_time": "1:34:43", "remaining_time": "1 day, 0:10:39"}
+{"current_steps": 58, "total_steps": 930, "loss": 0.6687, "lr": 4.9892473118279576e-05, "epoch": 0.31109621186724773, "percentage": 6.24, "elapsed_time": "1:36:22", "remaining_time": "1 day, 0:08:53"}
+{"current_steps": 59, "total_steps": 930, "loss": 0.6684, "lr": 5.075268817204302e-05, "epoch": 0.31645993965806235, "percentage": 6.34, "elapsed_time": "1:38:01", "remaining_time": "1 day, 0:07:08"}
+{"current_steps": 60, "total_steps": 930, "loss": 0.6777, "lr": 5.161290322580645e-05, "epoch": 0.32182366744887697, "percentage": 6.45, "elapsed_time": "1:39:40", "remaining_time": "1 day, 0:05:21"}
+{"current_steps": 61, "total_steps": 930, "loss": 0.6662, "lr": 5.247311827956989e-05, "epoch": 0.3271873952396916, "percentage": 6.56, "elapsed_time": "1:41:20", "remaining_time": "1 day, 0:03:44"}
+{"current_steps": 62, "total_steps": 930, "loss": 0.6654, "lr": 5.333333333333333e-05, "epoch": 0.3325511230305062, "percentage": 6.67, "elapsed_time": "1:42:59", "remaining_time": "1 day, 0:01:57"}
+{"current_steps": 63, "total_steps": 930, "loss": 0.6724, "lr": 5.4193548387096774e-05, "epoch": 0.33791485082132083, "percentage": 6.77, "elapsed_time": "1:44:39", "remaining_time": "1 day, 0:00:11"}
+{"current_steps": 64, "total_steps": 930, "loss": 0.6717, "lr": 5.505376344086022e-05, "epoch": 0.34327857861213545, "percentage": 6.88, "elapsed_time": "1:46:18", "remaining_time": "23:58:31"}
+{"current_steps": 65, "total_steps": 930, "loss": 0.6804, "lr": 5.591397849462366e-05, "epoch": 0.3486423064029501, "percentage": 6.99, "elapsed_time": "1:47:57", "remaining_time": "23:56:45"}
+{"current_steps": 66, "total_steps": 930, "loss": 0.6718, "lr": 5.6774193548387104e-05, "epoch": 0.35400603419376464, "percentage": 7.1, "elapsed_time": "1:49:37", "remaining_time": "23:55:00"}
+{"current_steps": 67, "total_steps": 930, "loss": 0.6668, "lr": 5.7634408602150545e-05, "epoch": 0.35936976198457926, "percentage": 7.2, "elapsed_time": "1:51:16", "remaining_time": "23:53:16"}
+{"current_steps": 68, "total_steps": 930, "loss": 0.6748, "lr": 5.8494623655913986e-05, "epoch": 0.3647334897753939, "percentage": 7.31, "elapsed_time": "1:52:55", "remaining_time": "23:51:31"}
+{"current_steps": 69, "total_steps": 930, "loss": 0.6743, "lr": 5.935483870967743e-05, "epoch": 0.3700972175662085, "percentage": 7.42, "elapsed_time": "1:54:35", "remaining_time": "23:49:53"}
+{"current_steps": 70, "total_steps": 930, "loss": 0.6678, "lr": 6.021505376344086e-05, "epoch": 0.3754609453570231, "percentage": 7.53, "elapsed_time": "1:56:15", "remaining_time": "23:48:19"}
+{"current_steps": 71, "total_steps": 930, "loss": 0.6522, "lr": 6.10752688172043e-05, "epoch": 0.38082467314783774, "percentage": 7.63, "elapsed_time": "1:57:54", "remaining_time": "23:46:35"}
+{"current_steps": 72, "total_steps": 930, "loss": 0.6676, "lr": 6.193548387096774e-05, "epoch": 0.38618840093865237, "percentage": 7.74, "elapsed_time": "1:59:34", "remaining_time": "23:44:50"}
+{"current_steps": 73, "total_steps": 930, "loss": 0.6661, "lr": 6.279569892473119e-05, "epoch": 0.391552128729467, "percentage": 7.85, "elapsed_time": "2:01:13", "remaining_time": "23:43:11"}
+{"current_steps": 74, "total_steps": 930, "loss": 0.6649, "lr": 6.365591397849463e-05, "epoch": 0.3969158565202816, "percentage": 7.96, "elapsed_time": "2:02:52", "remaining_time": "23:41:26"}
+{"current_steps": 75, "total_steps": 930, "loss": 0.6679, "lr": 6.451612903225807e-05, "epoch": 0.4022795843110962, "percentage": 8.06, "elapsed_time": "2:04:32", "remaining_time": "23:39:44"}
+{"current_steps": 76, "total_steps": 930, "loss": 0.6585, "lr": 6.537634408602151e-05, "epoch": 0.40764331210191085, "percentage": 8.17, "elapsed_time": "2:06:11", "remaining_time": "23:38:00"}
+{"current_steps": 77, "total_steps": 930, "loss": 0.6582, "lr": 6.623655913978495e-05, "epoch": 0.41300703989272547, "percentage": 8.28, "elapsed_time": "2:07:50", "remaining_time": "23:36:16"}
+{"current_steps": 78, "total_steps": 930, "loss": 0.6577, "lr": 6.709677419354839e-05, "epoch": 0.41837076768354003, "percentage": 8.39, "elapsed_time": "2:09:30", "remaining_time": "23:34:33"}
+{"current_steps": 79, "total_steps": 930, "loss": 0.6575, "lr": 6.795698924731183e-05, "epoch": 0.42373449547435466, "percentage": 8.49, "elapsed_time": "2:11:09", "remaining_time": "23:32:49"}
+{"current_steps": 80, "total_steps": 930, "loss": 0.6726, "lr": 6.881720430107527e-05, "epoch": 0.4290982232651693, "percentage": 8.6, "elapsed_time": "2:12:48", "remaining_time": "23:31:05"}
+{"current_steps": 81, "total_steps": 930, "loss": 0.663, "lr": 6.967741935483871e-05, "epoch": 0.4344619510559839, "percentage": 8.71, "elapsed_time": "2:14:28", "remaining_time": "23:29:27"}
+{"current_steps": 82, "total_steps": 930, "loss": 0.6588, "lr": 7.053763440860215e-05, "epoch": 0.4398256788467985, "percentage": 8.82, "elapsed_time": "2:16:07", "remaining_time": "23:27:43"}
+{"current_steps": 83, "total_steps": 930, "loss": 0.6597, "lr": 7.13978494623656e-05, "epoch": 0.44518940663761314, "percentage": 8.92, "elapsed_time": "2:17:46", "remaining_time": "23:25:59"}
+{"current_steps": 84, "total_steps": 930, "loss": 0.6598, "lr": 7.225806451612904e-05, "epoch": 0.45055313442842776, "percentage": 9.03, "elapsed_time": "2:19:25", "remaining_time": "23:24:17"}
+{"current_steps": 85, "total_steps": 930, "loss": 0.6553, "lr": 7.311827956989248e-05, "epoch": 0.4559168622192424, "percentage": 9.14, "elapsed_time": "2:21:05", "remaining_time": "23:22:34"}
+{"current_steps": 86, "total_steps": 930, "loss": 0.6597, "lr": 7.397849462365592e-05, "epoch": 0.461280590010057, "percentage": 9.25, "elapsed_time": "2:22:44", "remaining_time": "23:20:50"}
+{"current_steps": 87, "total_steps": 930, "loss": 0.6563, "lr": 7.483870967741936e-05, "epoch": 0.4666443178008716, "percentage": 9.35, "elapsed_time": "2:24:23", "remaining_time": "23:19:10"}
+{"current_steps": 88, "total_steps": 930, "loss": 0.6501, "lr": 7.56989247311828e-05, "epoch": 0.47200804559168624, "percentage": 9.46, "elapsed_time": "2:26:03", "remaining_time": "23:17:27"}
+{"current_steps": 89, "total_steps": 930, "loss": 0.651, "lr": 7.655913978494624e-05, "epoch": 0.47737177338250086, "percentage": 9.57, "elapsed_time": "2:27:42", "remaining_time": "23:15:44"}
+{"current_steps": 90, "total_steps": 930, "loss": 0.6542, "lr": 7.741935483870968e-05, "epoch": 0.48273550117331543, "percentage": 9.68, "elapsed_time": "2:29:21", "remaining_time": "23:14:02"}
+{"current_steps": 91, "total_steps": 930, "loss": 0.6497, "lr": 7.827956989247312e-05, "epoch": 0.48809922896413005, "percentage": 9.78, "elapsed_time": "2:31:00", "remaining_time": "23:12:19"}
+{"current_steps": 92, "total_steps": 930, "loss": 0.6597, "lr": 7.913978494623657e-05, "epoch": 0.49346295675494467, "percentage": 9.89, "elapsed_time": "2:32:40", "remaining_time": "23:10:37"}
+{"current_steps": 93, "total_steps": 930, "loss": 0.6577, "lr": 8e-05, "epoch": 0.4988266845457593, "percentage": 10.0, "elapsed_time": "2:34:19", "remaining_time": "23:08:56"}
+{"current_steps": 94, "total_steps": 930, "loss": 0.6532, "lr": 7.999971824066397e-05, "epoch": 0.5041904123365739, "percentage": 10.11, "elapsed_time": "2:35:58", "remaining_time": "23:07:12"}
+{"current_steps": 95, "total_steps": 930, "loss": 0.7033, "lr": 7.99988729666253e-05, "epoch": 0.5095541401273885, "percentage": 10.22, "elapsed_time": "2:37:38", "remaining_time": "23:05:31"}
+{"current_steps": 96, "total_steps": 930, "loss": 0.693, "lr": 7.999746418979217e-05, "epoch": 0.5149178679182032, "percentage": 10.32, "elapsed_time": "2:39:17", "remaining_time": "23:03:48"}
+{"current_steps": 97, "total_steps": 930, "loss": 0.6772, "lr": 7.99954919300114e-05, "epoch": 0.5202815957090178, "percentage": 10.43, "elapsed_time": "2:40:56", "remaining_time": "23:02:05"}
+{"current_steps": 98, "total_steps": 930, "loss": 0.6808, "lr": 7.999295621506808e-05, "epoch": 0.5256453234998324, "percentage": 10.54, "elapsed_time": "2:42:35", "remaining_time": "23:00:24"}
+{"current_steps": 99, "total_steps": 930, "loss": 0.6681, "lr": 7.998985708068532e-05, "epoch": 0.531009051290647, "percentage": 10.65, "elapsed_time": "2:44:15", "remaining_time": "22:58:42"}
+{"current_steps": 100, "total_steps": 930, "loss": 0.6718, "lr": 7.998619457052362e-05, "epoch": 0.5363727790814616, "percentage": 10.75, "elapsed_time": "2:45:54", "remaining_time": "22:57:00"}
+{"current_steps": 101, "total_steps": 930, "loss": 0.6647, "lr": 7.998196873618028e-05, "epoch": 0.5417365068722763, "percentage": 10.86, "elapsed_time": "2:47:33", "remaining_time": "22:55:18"}
+{"current_steps": 102, "total_steps": 930, "loss": 0.6671, "lr": 7.997717963718872e-05, "epoch": 0.5471002346630909, "percentage": 10.97, "elapsed_time": "2:49:12", "remaining_time": "22:53:35"}
+{"current_steps": 103, "total_steps": 930, "loss": 0.6589, "lr": 7.997182734101763e-05, "epoch": 0.5524639624539055, "percentage": 11.08, "elapsed_time": "2:50:51", "remaining_time": "22:51:53"}
+{"current_steps": 104, "total_steps": 930, "loss": 0.656, "lr": 7.996591192306995e-05, "epoch": 0.5578276902447201, "percentage": 11.18, "elapsed_time": "2:52:31", "remaining_time": "22:50:16"}
+{"current_steps": 105, "total_steps": 930, "loss": 0.6564, "lr": 7.99594334666819e-05, "epoch": 0.5631914180355347, "percentage": 11.29, "elapsed_time": "2:54:11", "remaining_time": "22:48:35"}
+{"current_steps": 106, "total_steps": 930, "loss": 0.6452, "lr": 7.995239206312176e-05, "epoch": 0.5685551458263494, "percentage": 11.4, "elapsed_time": "2:55:50", "remaining_time": "22:46:53"}
+{"current_steps": 107, "total_steps": 930, "loss": 0.6484, "lr": 7.994478781158861e-05, "epoch": 0.573918873617164, "percentage": 11.51, "elapsed_time": "2:57:29", "remaining_time": "22:45:14"}
+{"current_steps": 108, "total_steps": 930, "loss": 0.6513, "lr": 7.993662081921086e-05, "epoch": 0.5792826014079785, "percentage": 11.61, "elapsed_time": "2:59:09", "remaining_time": "22:43:31"}
+{"current_steps": 109, "total_steps": 930, "loss": 0.6476, "lr": 7.992789120104486e-05, "epoch": 0.5846463291987931, "percentage": 11.72, "elapsed_time": "3:00:48", "remaining_time": "22:41:50"}
+{"current_steps": 110, "total_steps": 930, "loss": 0.6484, "lr": 7.991859908007314e-05, "epoch": 0.5900100569896077, "percentage": 11.83, "elapsed_time": "3:02:27", "remaining_time": "22:40:09"}
+{"current_steps": 111, "total_steps": 930, "loss": 0.6423, "lr": 7.990874458720283e-05, "epoch": 0.5953737847804224, "percentage": 11.94, "elapsed_time": "3:04:06", "remaining_time": "22:38:28"}
+{"current_steps": 112, "total_steps": 930, "loss": 0.6458, "lr": 7.989832786126369e-05, "epoch": 0.600737512571237, "percentage": 12.04, "elapsed_time": "3:05:46", "remaining_time": "22:36:50"}
+{"current_steps": 113, "total_steps": 930, "loss": 0.663, "lr": 7.98873490490062e-05, "epoch": 0.6061012403620516, "percentage": 12.15, "elapsed_time": "3:07:25", "remaining_time": "22:35:08"}
+{"current_steps": 114, "total_steps": 930, "loss": 0.6475, "lr": 7.987580830509949e-05, "epoch": 0.6114649681528662, "percentage": 12.26, "elapsed_time": "3:09:05", "remaining_time": "22:33:26"}
+{"current_steps": 115, "total_steps": 930, "loss": 0.6477, "lr": 7.986370579212921e-05, "epoch": 0.6168286959436808, "percentage": 12.37, "elapsed_time": "3:10:44", "remaining_time": "22:31:45"}
+{"current_steps": 116, "total_steps": 930, "loss": 0.6452, "lr": 7.985104168059514e-05, "epoch": 0.6221924237344955, "percentage": 12.47, "elapsed_time": "3:12:23", "remaining_time": "22:30:03"}
+{"current_steps": 117, "total_steps": 930, "loss": 0.6399, "lr": 7.983781614890886e-05, "epoch": 0.6275561515253101, "percentage": 12.58, "elapsed_time": "3:14:02", "remaining_time": "22:28:22"}
+{"current_steps": 118, "total_steps": 930, "loss": 0.643, "lr": 7.982402938339123e-05, "epoch": 0.6329198793161247, "percentage": 12.69, "elapsed_time": "3:15:41", "remaining_time": "22:26:40"}
+{"current_steps": 119, "total_steps": 930, "loss": 0.6373, "lr": 7.980968157826976e-05, "epoch": 0.6382836071069393, "percentage": 12.8, "elapsed_time": "3:17:21", "remaining_time": "22:24:58"}
+{"current_steps": 120, "total_steps": 930, "loss": 0.6371, "lr": 7.97947729356758e-05, "epoch": 0.6436473348977539, "percentage": 12.9, "elapsed_time": "3:19:00", "remaining_time": "22:23:19"}
+{"current_steps": 121, "total_steps": 930, "loss": 0.6372, "lr": 7.977930366564188e-05, "epoch": 0.6490110626885686, "percentage": 13.01, "elapsed_time": "3:20:40", "remaining_time": "22:21:42"}
+{"current_steps": 122, "total_steps": 930, "loss": 0.6354, "lr": 7.976327398609851e-05, "epoch": 0.6543747904793832, "percentage": 13.12, "elapsed_time": "3:22:21", "remaining_time": "22:20:10"}
+{"current_steps": 123, "total_steps": 930, "loss": 0.6344, "lr": 7.974668412287133e-05, "epoch": 0.6597385182701978, "percentage": 13.23, "elapsed_time": "3:24:01", "remaining_time": "22:18:33"}
+{"current_steps": 124, "total_steps": 930, "loss": 0.6363, "lr": 7.972953430967773e-05, "epoch": 0.6651022460610124, "percentage": 13.33, "elapsed_time": "3:25:40", "remaining_time": "22:16:55"}
+{"current_steps": 125, "total_steps": 930, "loss": 0.6349, "lr": 7.971182478812374e-05, "epoch": 0.670465973851827, "percentage": 13.44, "elapsed_time": "3:27:20", "remaining_time": "22:15:15"}
+{"current_steps": 126, "total_steps": 930, "loss": 0.6326, "lr": 7.96935558077005e-05, "epoch": 0.6758297016426417, "percentage": 13.55, "elapsed_time": "3:28:59", "remaining_time": "22:13:34"}
+{"current_steps": 127, "total_steps": 930, "loss": 0.6335, "lr": 7.967472762578082e-05, "epoch": 0.6811934294334563, "percentage": 13.66, "elapsed_time": "3:30:38", "remaining_time": "22:11:53"}
+{"current_steps": 128, "total_steps": 930, "loss": 0.6287, "lr": 7.965534050761548e-05, "epoch": 0.6865571572242709, "percentage": 13.76, "elapsed_time": "3:32:18", "remaining_time": "22:10:12"}
+{"current_steps": 129, "total_steps": 930, "loss": 0.6423, "lr": 7.963539472632956e-05, "epoch": 0.6919208850150855, "percentage": 13.87, "elapsed_time": "3:33:57", "remaining_time": "22:08:31"}
+{"current_steps": 130, "total_steps": 930, "loss": 0.6392, "lr": 7.961489056291858e-05, "epoch": 0.6972846128059002, "percentage": 13.98, "elapsed_time": "3:35:36", "remaining_time": "22:06:49"}
+{"current_steps": 131, "total_steps": 930, "loss": 0.6292, "lr": 7.95938283062445e-05, "epoch": 0.7026483405967148, "percentage": 14.09, "elapsed_time": "3:37:15", "remaining_time": "22:05:08"}
+{"current_steps": 132, "total_steps": 930, "loss": 0.6317, "lr": 7.957220825303168e-05, "epoch": 0.7080120683875293, "percentage": 14.19, "elapsed_time": "3:38:55", "remaining_time": "22:03:27"}
+{"current_steps": 133, "total_steps": 930, "loss": 0.631, "lr": 7.955003070786275e-05, "epoch": 0.7133757961783439, "percentage": 14.3, "elapsed_time": "3:40:34", "remaining_time": "22:01:47"}
+{"current_steps": 134, "total_steps": 930, "loss": 0.6332, "lr": 7.95272959831742e-05, "epoch": 0.7187395239691585, "percentage": 14.41, "elapsed_time": "3:42:13", "remaining_time": "22:00:06"}
+{"current_steps": 135, "total_steps": 930, "loss": 0.6353, "lr": 7.950400439925207e-05, "epoch": 0.7241032517599731, "percentage": 14.52, "elapsed_time": "3:43:52", "remaining_time": "21:58:25"}
+{"current_steps": 136, "total_steps": 930, "loss": 0.6287, "lr": 7.948015628422745e-05, "epoch": 0.7294669795507878, "percentage": 14.62, "elapsed_time": "3:45:32", "remaining_time": "21:56:43"}
+{"current_steps": 137, "total_steps": 930, "loss": 0.6348, "lr": 7.945575197407177e-05, "epoch": 0.7348307073416024, "percentage": 14.73, "elapsed_time": "3:47:11", "remaining_time": "21:55:03"}
+{"current_steps": 138, "total_steps": 930, "loss": 0.6251, "lr": 7.943079181259215e-05, "epoch": 0.740194435132417, "percentage": 14.84, "elapsed_time": "3:48:50", "remaining_time": "21:53:21"}
+{"current_steps": 139, "total_steps": 930, "loss": 0.6268, "lr": 7.940527615142653e-05, "epoch": 0.7455581629232316, "percentage": 14.95, "elapsed_time": "3:50:29", "remaining_time": "21:51:40"}
+{"current_steps": 140, "total_steps": 930, "loss": 0.6318, "lr": 7.937920535003866e-05, "epoch": 0.7509218907140462, "percentage": 15.05, "elapsed_time": "3:52:08", "remaining_time": "21:49:59"}
+{"current_steps": 141, "total_steps": 930, "loss": 0.6277, "lr": 7.935257977571317e-05, "epoch": 0.7562856185048609, "percentage": 15.16, "elapsed_time": "3:53:48", "remaining_time": "21:48:18"}
+{"current_steps": 142, "total_steps": 930, "loss": 0.6279, "lr": 7.932539980355023e-05, "epoch": 0.7616493462956755, "percentage": 15.27, "elapsed_time": "3:55:27", "remaining_time": "21:46:36"}
+{"current_steps": 143, "total_steps": 930, "loss": 0.6221, "lr": 7.92976658164604e-05, "epoch": 0.7670130740864901, "percentage": 15.38, "elapsed_time": "3:57:06", "remaining_time": "21:44:55"}
+{"current_steps": 144, "total_steps": 930, "loss": 0.6205, "lr": 7.926937820515918e-05, "epoch": 0.7723768018773047, "percentage": 15.48, "elapsed_time": "3:58:47", "remaining_time": "21:43:22"}
+{"current_steps": 145, "total_steps": 930, "loss": 0.6166, "lr": 7.924053736816148e-05, "epoch": 0.7777405296681194, "percentage": 15.59, "elapsed_time": "4:00:26", "remaining_time": "21:41:41"}
+{"current_steps": 146, "total_steps": 930, "loss": 0.6238, "lr": 7.921114371177607e-05, "epoch": 0.783104257458934, "percentage": 15.7, "elapsed_time": "4:02:05", "remaining_time": "21:40:01"}
+{"current_steps": 147, "total_steps": 930, "loss": 0.624, "lr": 7.918119765009979e-05, "epoch": 0.7884679852497486, "percentage": 15.81, "elapsed_time": "4:03:45", "remaining_time": "21:38:20"}
+{"current_steps": 148, "total_steps": 930, "loss": 0.6241, "lr": 7.915069960501177e-05, "epoch": 0.7938317130405632, "percentage": 15.91, "elapsed_time": "4:05:24", "remaining_time": "21:36:40"}
+{"current_steps": 149, "total_steps": 930, "loss": 0.6169, "lr": 7.911965000616746e-05, "epoch": 0.7991954408313778, "percentage": 16.02, "elapsed_time": "4:07:03", "remaining_time": "21:35:00"}
+{"current_steps": 150, "total_steps": 930, "loss": 0.6155, "lr": 7.908804929099256e-05, "epoch": 0.8045591686221925, "percentage": 16.13, "elapsed_time": "4:08:42", "remaining_time": "21:33:19"}
+{"current_steps": 151, "total_steps": 930, "loss": 0.614, "lr": 7.905589790467694e-05, "epoch": 0.8099228964130071, "percentage": 16.24, "elapsed_time": "4:10:22", "remaining_time": "21:31:38"}
+{"current_steps": 152, "total_steps": 930, "loss": 0.6163, "lr": 7.902319630016822e-05, "epoch": 0.8152866242038217, "percentage": 16.34, "elapsed_time": "4:12:01", "remaining_time": "21:29:57"}
+{"current_steps": 153, "total_steps": 930, "loss": 0.622, "lr": 7.898994493816553e-05, "epoch": 0.8206503519946363, "percentage": 16.45, "elapsed_time": "4:13:40", "remaining_time": "21:28:16"}
+{"current_steps": 154, "total_steps": 930, "loss": 0.6132, "lr": 7.895614428711296e-05, "epoch": 0.8260140797854509, "percentage": 16.56, "elapsed_time": "4:15:19", "remaining_time": "21:26:35"}
+{"current_steps": 155, "total_steps": 930, "loss": 0.619, "lr": 7.892179482319297e-05, "epoch": 0.8313778075762656, "percentage": 16.67, "elapsed_time": "4:16:58", "remaining_time": "21:24:54"}
+{"current_steps": 156, "total_steps": 930, "loss": 0.6232, "lr": 7.888689703031963e-05, "epoch": 0.8367415353670801, "percentage": 16.77, "elapsed_time": "4:18:38", "remaining_time": "21:23:14"}
+{"current_steps": 157, "total_steps": 930, "loss": 0.6175, "lr": 7.885145140013192e-05, "epoch": 0.8421052631578947, "percentage": 16.88, "elapsed_time": "4:20:17", "remaining_time": "21:21:33"}
+{"current_steps": 158, "total_steps": 930, "loss": 0.6105, "lr": 7.88154584319867e-05, "epoch": 0.8474689909487093, "percentage": 16.99, "elapsed_time": "4:21:56", "remaining_time": "21:19:52"}
+{"current_steps": 159, "total_steps": 930, "loss": 0.6149, "lr": 7.87789186329517e-05, "epoch": 0.8528327187395239, "percentage": 17.1, "elapsed_time": "4:23:35", "remaining_time": "21:18:12"}
+{"current_steps": 160, "total_steps": 930, "loss": 0.608, "lr": 7.87418325177984e-05, "epoch": 0.8581964465303386, "percentage": 17.2, "elapsed_time": "4:25:15", "remaining_time": "21:16:31"}
+{"current_steps": 161, "total_steps": 930, "loss": 0.6184, "lr": 7.870420060899476e-05, "epoch": 0.8635601743211532, "percentage": 17.31, "elapsed_time": "4:26:54", "remaining_time": "21:14:50"}
+{"current_steps": 162, "total_steps": 930, "loss": 0.6177, "lr": 7.866602343669785e-05, "epoch": 0.8689239021119678, "percentage": 17.42, "elapsed_time": "4:28:33", "remaining_time": "21:13:09"}
+{"current_steps": 163, "total_steps": 930, "loss": 0.613, "lr": 7.862730153874642e-05, "epoch": 0.8742876299027824, "percentage": 17.53, "elapsed_time": "4:30:12", "remaining_time": "21:11:29"}
+{"current_steps": 164, "total_steps": 930, "loss": 0.6171, "lr": 7.858803546065328e-05, "epoch": 0.879651357693597, "percentage": 17.63, "elapsed_time": "4:31:52", "remaining_time": "21:09:52"}
+{"current_steps": 165, "total_steps": 930, "loss": 0.6164, "lr": 7.854822575559764e-05, "epoch": 0.8850150854844117, "percentage": 17.74, "elapsed_time": "4:33:31", "remaining_time": "21:08:11"}
+{"current_steps": 166, "total_steps": 930, "loss": 0.616, "lr": 7.85078729844173e-05, "epoch": 0.8903788132752263, "percentage": 17.85, "elapsed_time": "4:35:11", "remaining_time": "21:06:31"}
+{"current_steps": 167, "total_steps": 930, "loss": 0.6145, "lr": 7.846697771560075e-05, "epoch": 0.8957425410660409, "percentage": 17.96, "elapsed_time": "4:36:51", "remaining_time": "21:04:54"}
+{"current_steps": 168, "total_steps": 930, "loss": 0.6136, "lr": 7.842554052527918e-05, "epoch": 0.9011062688568555, "percentage": 18.06, "elapsed_time": "4:38:30", "remaining_time": "21:03:14"}
+{"current_steps": 169, "total_steps": 930, "loss": 0.6096, "lr": 7.838356199721836e-05, "epoch": 0.9064699966476701, "percentage": 18.17, "elapsed_time": "4:40:09", "remaining_time": "21:01:33"}
+{"current_steps": 170, "total_steps": 930, "loss": 0.6143, "lr": 7.834104272281041e-05, "epoch": 0.9118337244384848, "percentage": 18.28, "elapsed_time": "4:41:49", "remaining_time": "20:59:53"}
+{"current_steps": 171, "total_steps": 930, "loss": 0.6124, "lr": 7.829798330106544e-05, "epoch": 0.9171974522292994, "percentage": 18.39, "elapsed_time": "4:43:28", "remaining_time": "20:58:13"}
+{"current_steps": 172, "total_steps": 930, "loss": 0.6208, "lr": 7.825438433860314e-05, "epoch": 0.922561180020114, "percentage": 18.49, "elapsed_time": "4:45:07", "remaining_time": "20:56:32"}
+{"current_steps": 173, "total_steps": 930, "loss": 0.6112, "lr": 7.821024644964429e-05, "epoch": 0.9279249078109286, "percentage": 18.6, "elapsed_time": "4:46:46", "remaining_time": "20:54:51"}
+{"current_steps": 174, "total_steps": 930, "loss": 0.6041, "lr": 7.816557025600196e-05, "epoch": 0.9332886356017432, "percentage": 18.71, "elapsed_time": "4:48:25", "remaining_time": "20:53:11"}
+{"current_steps": 175, "total_steps": 930, "loss": 0.6117, "lr": 7.81203563870729e-05, "epoch": 0.9386523633925579, "percentage": 18.82, "elapsed_time": "4:50:05", "remaining_time": "20:51:31"}
+{"current_steps": 176, "total_steps": 930, "loss": 0.617, "lr": 7.807460547982861e-05, "epoch": 0.9440160911833725, "percentage": 18.92, "elapsed_time": "4:51:44", "remaining_time": "20:49:50"}
+{"current_steps": 177, "total_steps": 930, "loss": 0.6136, "lr": 7.802831817880633e-05, "epoch": 0.9493798189741871, "percentage": 19.03, "elapsed_time": "4:53:23", "remaining_time": "20:48:10"}
+{"current_steps": 178, "total_steps": 930, "loss": 0.6063, "lr": 7.798149513610003e-05, "epoch": 0.9547435467650017, "percentage": 19.14, "elapsed_time": "4:55:02", "remaining_time": "20:46:29"}
+{"current_steps": 179, "total_steps": 930, "loss": 0.6094, "lr": 7.793413701135119e-05, "epoch": 0.9601072745558162, "percentage": 19.25, "elapsed_time": "4:56:42", "remaining_time": "20:44:48"}
+{"current_steps": 180, "total_steps": 930, "loss": 0.6091, "lr": 7.788624447173948e-05, "epoch": 0.9654710023466309, "percentage": 19.35, "elapsed_time": "4:58:21", "remaining_time": "20:43:08"}
+{"current_steps": 181, "total_steps": 930, "loss": 0.6102, "lr": 7.783781819197341e-05, "epoch": 0.9708347301374455, "percentage": 19.46, "elapsed_time": "5:00:00", "remaining_time": "20:41:27"}
+{"current_steps": 182, "total_steps": 930, "loss": 0.6177, "lr": 7.778885885428082e-05, "epoch": 0.9761984579282601, "percentage": 19.57, "elapsed_time": "5:01:39", "remaining_time": "20:39:47"}
+{"current_steps": 183, "total_steps": 930, "loss": 0.607, "lr": 7.773936714839922e-05, "epoch": 0.9815621857190747, "percentage": 19.68, "elapsed_time": "5:03:18", "remaining_time": "20:38:07"}
+{"current_steps": 184, "total_steps": 930, "loss": 0.6063, "lr": 7.768934377156613e-05, "epoch": 0.9869259135098893, "percentage": 19.78, "elapsed_time": "5:04:58", "remaining_time": "20:36:27"}
+{"current_steps": 185, "total_steps": 930, "loss": 0.6079, "lr": 7.76387894285092e-05, "epoch": 0.992289641300704, "percentage": 19.89, "elapsed_time": "5:06:37", "remaining_time": "20:34:46"}
+{"current_steps": 186, "total_steps": 930, "loss": 0.6066, "lr": 7.758770483143634e-05, "epoch": 0.9976533690915186, "percentage": 20.0, "elapsed_time": "5:08:16", "remaining_time": "20:33:06"}
+{"current_steps": 187, "total_steps": 930, "loss": 0.5859, "lr": 7.75360907000257e-05, "epoch": 1.003687562856185, "percentage": 20.11, "elapsed_time": "5:11:41", "remaining_time": "20:38:25"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4cb5a8f71548c3073c09074f4d1897f0e34f9b4f0f4a2c92ce09bbc91668ab
+size 7352