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 sha256:63856058fa8651f4545fdd1951eac4e69def138dd3638485b5c6b0fbeadf512f
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37da6ec0243d7506685ec8b73fd28f3997b312ed1ab67fabd66455db7aabd0e
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690d0d9b8338ae94ab8bed163c0fca58bb0eeb04af1f343cbd20e142a84446f6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4dfcae80c9bfbb340f031583ab55db821b71440c91e1a731c997b146cced5a
+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 +1,185 @@
+{"current_steps": 1, "total_steps": 915, "loss": 1.4358, "lr": 8.695652173913044e-07, "epoch": 0.005457025920873124, "percentage": 0.11, "elapsed_time": "0:01:37", "remaining_time": "1 day, 0:51:57"}
+{"current_steps": 2, "total_steps": 915, "loss": 1.4226, "lr": 1.7391304347826088e-06, "epoch": 0.010914051841746248, "percentage": 0.22, "elapsed_time": "0:02:28", "remaining_time": "18:52:24"}
+{"current_steps": 3, "total_steps": 915, "loss": 1.4261, "lr": 2.6086956521739132e-06, "epoch": 0.01637107776261937, "percentage": 0.33, "elapsed_time": "0:03:20", "remaining_time": "16:54:25"}
+{"current_steps": 4, "total_steps": 915, "loss": 1.4289, "lr": 3.4782608695652175e-06, "epoch": 0.021828103683492497, "percentage": 0.44, "elapsed_time": "0:04:12", "remaining_time": "15:57:09"}
+{"current_steps": 5, "total_steps": 915, "loss": 1.3628, "lr": 4.347826086956522e-06, "epoch": 0.027285129604365622, "percentage": 0.55, "elapsed_time": "0:05:03", "remaining_time": "15:19:53"}
+{"current_steps": 6, "total_steps": 915, "loss": 1.3331, "lr": 5.2173913043478265e-06, "epoch": 0.03274215552523874, "percentage": 0.66, "elapsed_time": "0:05:55", "remaining_time": "14:56:22"}
+{"current_steps": 7, "total_steps": 915, "loss": 1.3014, "lr": 6.086956521739132e-06, "epoch": 0.03819918144611187, "percentage": 0.77, "elapsed_time": "0:06:46", "remaining_time": "14:37:45"}
+{"current_steps": 8, "total_steps": 915, "loss": 1.3117, "lr": 6.956521739130435e-06, "epoch": 0.04365620736698499, "percentage": 0.87, "elapsed_time": "0:07:37", "remaining_time": "14:23:55"}
+{"current_steps": 9, "total_steps": 915, "loss": 1.3125, "lr": 7.82608695652174e-06, "epoch": 0.04911323328785812, "percentage": 0.98, "elapsed_time": "0:08:28", "remaining_time": "14:13:05"}
+{"current_steps": 10, "total_steps": 915, "loss": 1.3128, "lr": 8.695652173913044e-06, "epoch": 0.054570259208731244, "percentage": 1.09, "elapsed_time": "0:09:19", "remaining_time": "14:04:10"}
+{"current_steps": 11, "total_steps": 915, "loss": 1.2766, "lr": 9.565217391304349e-06, "epoch": 0.06002728512960437, "percentage": 1.2, "elapsed_time": "0:10:10", "remaining_time": "13:56:37"}
+{"current_steps": 12, "total_steps": 915, "loss": 1.2624, "lr": 1.0434782608695653e-05, "epoch": 0.06548431105047749, "percentage": 1.31, "elapsed_time": "0:11:01", "remaining_time": "13:50:06"}
+{"current_steps": 13, "total_steps": 915, "loss": 1.2325, "lr": 1.1304347826086957e-05, "epoch": 0.07094133697135062, "percentage": 1.42, "elapsed_time": "0:12:00", "remaining_time": "13:52:36"}
+{"current_steps": 14, "total_steps": 915, "loss": 1.2134, "lr": 1.2173913043478263e-05, "epoch": 0.07639836289222374, "percentage": 1.53, "elapsed_time": "0:12:51", "remaining_time": "13:47:28"}
+{"current_steps": 15, "total_steps": 915, "loss": 1.1939, "lr": 1.3043478260869566e-05, "epoch": 0.08185538881309687, "percentage": 1.64, "elapsed_time": "0:13:42", "remaining_time": "13:42:29"}
+{"current_steps": 16, "total_steps": 915, "loss": 1.1798, "lr": 1.391304347826087e-05, "epoch": 0.08731241473396999, "percentage": 1.75, "elapsed_time": "0:14:33", "remaining_time": "13:38:11"}
+{"current_steps": 17, "total_steps": 915, "loss": 1.1507, "lr": 1.4782608695652174e-05, "epoch": 0.0927694406548431, "percentage": 1.86, "elapsed_time": "0:15:24", "remaining_time": "13:34:19"}
+{"current_steps": 18, "total_steps": 915, "loss": 1.1593, "lr": 1.565217391304348e-05, "epoch": 0.09822646657571624, "percentage": 1.97, "elapsed_time": "0:16:16", "remaining_time": "13:30:42"}
+{"current_steps": 19, "total_steps": 915, "loss": 1.1374, "lr": 1.6521739130434785e-05, "epoch": 0.10368349249658936, "percentage": 2.08, "elapsed_time": "0:17:07", "remaining_time": "13:27:31"}
+{"current_steps": 20, "total_steps": 915, "loss": 1.1342, "lr": 1.739130434782609e-05, "epoch": 0.10914051841746249, "percentage": 2.19, "elapsed_time": "0:17:58", "remaining_time": "13:24:25"}
+{"current_steps": 21, "total_steps": 915, "loss": 1.133, "lr": 1.8260869565217393e-05, "epoch": 0.1145975443383356, "percentage": 2.3, "elapsed_time": "0:18:49", "remaining_time": "13:21:17"}
+{"current_steps": 22, "total_steps": 915, "loss": 1.1181, "lr": 1.9130434782608697e-05, "epoch": 0.12005457025920874, "percentage": 2.4, "elapsed_time": "0:19:40", "remaining_time": "13:18:26"}
+{"current_steps": 23, "total_steps": 915, "loss": 1.1277, "lr": 2e-05, "epoch": 0.12551159618008187, "percentage": 2.51, "elapsed_time": "0:20:31", "remaining_time": "13:15:58"}
+{"current_steps": 24, "total_steps": 915, "loss": 1.0883, "lr": 2.0869565217391306e-05, "epoch": 0.13096862210095497, "percentage": 2.62, "elapsed_time": "0:21:22", "remaining_time": "13:13:38"}
+{"current_steps": 25, "total_steps": 915, "loss": 1.0753, "lr": 2.173913043478261e-05, "epoch": 0.1364256480218281, "percentage": 2.73, "elapsed_time": "0:22:13", "remaining_time": "13:11:15"}
+{"current_steps": 26, "total_steps": 915, "loss": 1.0882, "lr": 2.2608695652173914e-05, "epoch": 0.14188267394270124, "percentage": 2.84, "elapsed_time": "0:23:04", "remaining_time": "13:09:03"}
+{"current_steps": 27, "total_steps": 915, "loss": 1.0601, "lr": 2.3478260869565222e-05, "epoch": 0.14733969986357434, "percentage": 2.95, "elapsed_time": "0:23:57", "remaining_time": "13:08:07"}
+{"current_steps": 28, "total_steps": 915, "loss": 1.06, "lr": 2.4347826086956526e-05, "epoch": 0.15279672578444747, "percentage": 3.06, "elapsed_time": "0:24:55", "remaining_time": "13:09:29"}
+{"current_steps": 29, "total_steps": 915, "loss": 1.0628, "lr": 2.521739130434783e-05, "epoch": 0.1582537517053206, "percentage": 3.17, "elapsed_time": "0:25:46", "remaining_time": "13:07:24"}
+{"current_steps": 30, "total_steps": 915, "loss": 1.0841, "lr": 2.608695652173913e-05, "epoch": 0.16371077762619374, "percentage": 3.28, "elapsed_time": "0:26:38", "remaining_time": "13:05:42"}
+{"current_steps": 31, "total_steps": 915, "loss": 1.0499, "lr": 2.6956521739130436e-05, "epoch": 0.16916780354706684, "percentage": 3.39, "elapsed_time": "0:27:29", "remaining_time": "13:03:49"}
+{"current_steps": 32, "total_steps": 915, "loss": 1.0595, "lr": 2.782608695652174e-05, "epoch": 0.17462482946793997, "percentage": 3.5, "elapsed_time": "0:28:20", "remaining_time": "13:02:03"}
+{"current_steps": 33, "total_steps": 915, "loss": 1.0605, "lr": 2.8695652173913044e-05, "epoch": 0.1800818553888131, "percentage": 3.61, "elapsed_time": "0:29:11", "remaining_time": "13:00:24"}
+{"current_steps": 34, "total_steps": 915, "loss": 1.0592, "lr": 2.956521739130435e-05, "epoch": 0.1855388813096862, "percentage": 3.72, "elapsed_time": "0:30:03", "remaining_time": "12:58:39"}
+{"current_steps": 35, "total_steps": 915, "loss": 1.0672, "lr": 3.0434782608695656e-05, "epoch": 0.19099590723055934, "percentage": 3.83, "elapsed_time": "0:30:54", "remaining_time": "12:57:00"}
+{"current_steps": 36, "total_steps": 915, "loss": 1.0557, "lr": 3.130434782608696e-05, "epoch": 0.19645293315143247, "percentage": 3.93, "elapsed_time": "0:31:45", "remaining_time": "12:55:21"}
+{"current_steps": 37, "total_steps": 915, "loss": 1.0793, "lr": 3.2173913043478265e-05, "epoch": 0.2019099590723056, "percentage": 4.04, "elapsed_time": "0:32:36", "remaining_time": "12:53:48"}
+{"current_steps": 38, "total_steps": 915, "loss": 1.059, "lr": 3.304347826086957e-05, "epoch": 0.2073669849931787, "percentage": 4.15, "elapsed_time": "0:33:27", "remaining_time": "12:52:16"}
+{"current_steps": 39, "total_steps": 915, "loss": 1.027, "lr": 3.391304347826087e-05, "epoch": 0.21282401091405184, "percentage": 4.26, "elapsed_time": "0:34:18", "remaining_time": "12:50:45"}
+{"current_steps": 40, "total_steps": 915, "loss": 1.0311, "lr": 3.478260869565218e-05, "epoch": 0.21828103683492497, "percentage": 4.37, "elapsed_time": "0:35:10", "remaining_time": "12:49:17"}
+{"current_steps": 41, "total_steps": 915, "loss": 1.0546, "lr": 3.565217391304348e-05, "epoch": 0.22373806275579808, "percentage": 4.48, "elapsed_time": "0:36:01", "remaining_time": "12:47:55"}
+{"current_steps": 42, "total_steps": 915, "loss": 1.0414, "lr": 3.6521739130434786e-05, "epoch": 0.2291950886766712, "percentage": 4.59, "elapsed_time": "0:36:56", "remaining_time": "12:47:50"}
+{"current_steps": 43, "total_steps": 915, "loss": 1.0573, "lr": 3.739130434782609e-05, "epoch": 0.23465211459754434, "percentage": 4.7, "elapsed_time": "0:37:53", "remaining_time": "12:48:29"}
+{"current_steps": 44, "total_steps": 915, "loss": 1.039, "lr": 3.8260869565217395e-05, "epoch": 0.24010914051841747, "percentage": 4.81, "elapsed_time": "0:38:44", "remaining_time": "12:47:02"}
+{"current_steps": 45, "total_steps": 915, "loss": 1.001, "lr": 3.91304347826087e-05, "epoch": 0.24556616643929058, "percentage": 4.92, "elapsed_time": "0:39:36", "remaining_time": "12:45:36"}
+{"current_steps": 46, "total_steps": 915, "loss": 1.0281, "lr": 4e-05, "epoch": 0.25102319236016374, "percentage": 5.03, "elapsed_time": "0:40:27", "remaining_time": "12:44:16"}
+{"current_steps": 47, "total_steps": 915, "loss": 1.0291, "lr": 4.0869565217391314e-05, "epoch": 0.25648021828103684, "percentage": 5.14, "elapsed_time": "0:41:18", "remaining_time": "12:42:57"}
+{"current_steps": 48, "total_steps": 915, "loss": 1.0332, "lr": 4.173913043478261e-05, "epoch": 0.26193724420190995, "percentage": 5.25, "elapsed_time": "0:42:10", "remaining_time": "12:41:38"}
+{"current_steps": 49, "total_steps": 915, "loss": 1.0266, "lr": 4.2608695652173916e-05, "epoch": 0.2673942701227831, "percentage": 5.36, "elapsed_time": "0:43:01", "remaining_time": "12:40:22"}
+{"current_steps": 50, "total_steps": 915, "loss": 1.033, "lr": 4.347826086956522e-05, "epoch": 0.2728512960436562, "percentage": 5.46, "elapsed_time": "0:43:52", "remaining_time": "12:38:59"}
+{"current_steps": 51, "total_steps": 915, "loss": 1.0217, "lr": 4.4347826086956525e-05, "epoch": 0.2783083219645293, "percentage": 5.57, "elapsed_time": "0:44:43", "remaining_time": "12:37:43"}
+{"current_steps": 52, "total_steps": 915, "loss": 1.0191, "lr": 4.521739130434783e-05, "epoch": 0.2837653478854025, "percentage": 5.68, "elapsed_time": "0:45:35", "remaining_time": "12:36:34"}
+{"current_steps": 53, "total_steps": 915, "loss": 1.0206, "lr": 4.608695652173913e-05, "epoch": 0.2892223738062756, "percentage": 5.79, "elapsed_time": "0:46:26", "remaining_time": "12:35:18"}
+{"current_steps": 54, "total_steps": 915, "loss": 1.0284, "lr": 4.6956521739130444e-05, "epoch": 0.2946793997271487, "percentage": 5.9, "elapsed_time": "0:47:17", "remaining_time": "12:34:02"}
+{"current_steps": 55, "total_steps": 915, "loss": 0.9991, "lr": 4.782608695652174e-05, "epoch": 0.30013642564802184, "percentage": 6.01, "elapsed_time": "0:48:08", "remaining_time": "12:32:50"}
+{"current_steps": 56, "total_steps": 915, "loss": 1.0414, "lr": 4.869565217391305e-05, "epoch": 0.30559345156889495, "percentage": 6.12, "elapsed_time": "0:48:59", "remaining_time": "12:31:36"}
+{"current_steps": 57, "total_steps": 915, "loss": 1.0182, "lr": 4.956521739130435e-05, "epoch": 0.31105047748976805, "percentage": 6.23, "elapsed_time": "0:49:57", "remaining_time": "12:31:53"}
+{"current_steps": 58, "total_steps": 915, "loss": 1.0076, "lr": 5.043478260869566e-05, "epoch": 0.3165075034106412, "percentage": 6.34, "elapsed_time": "0:50:53", "remaining_time": "12:31:52"}
+{"current_steps": 59, "total_steps": 915, "loss": 1.0132, "lr": 5.130434782608696e-05, "epoch": 0.3219645293315143, "percentage": 6.45, "elapsed_time": "0:51:44", "remaining_time": "12:30:36"}
+{"current_steps": 60, "total_steps": 915, "loss": 1.002, "lr": 5.217391304347826e-05, "epoch": 0.3274215552523875, "percentage": 6.56, "elapsed_time": "0:52:35", "remaining_time": "12:29:22"}
+{"current_steps": 61, "total_steps": 915, "loss": 1.0287, "lr": 5.304347826086957e-05, "epoch": 0.3328785811732606, "percentage": 6.67, "elapsed_time": "0:53:26", "remaining_time": "12:28:10"}
+{"current_steps": 62, "total_steps": 915, "loss": 1.0372, "lr": 5.391304347826087e-05, "epoch": 0.3383356070941337, "percentage": 6.78, "elapsed_time": "0:54:17", "remaining_time": "12:27:03"}
+{"current_steps": 63, "total_steps": 915, "loss": 1.0594, "lr": 5.478260869565218e-05, "epoch": 0.34379263301500684, "percentage": 6.89, "elapsed_time": "0:55:08", "remaining_time": "12:25:50"}
+{"current_steps": 64, "total_steps": 915, "loss": 1.0858, "lr": 5.565217391304348e-05, "epoch": 0.34924965893587995, "percentage": 6.99, "elapsed_time": "0:56:00", "remaining_time": "12:24:41"}
+{"current_steps": 65, "total_steps": 915, "loss": 1.0458, "lr": 5.652173913043479e-05, "epoch": 0.35470668485675305, "percentage": 7.1, "elapsed_time": "0:56:51", "remaining_time": "12:23:33"}
+{"current_steps": 66, "total_steps": 915, "loss": 1.0478, "lr": 5.739130434782609e-05, "epoch": 0.3601637107776262, "percentage": 7.21, "elapsed_time": "0:57:42", "remaining_time": "12:22:22"}
+{"current_steps": 67, "total_steps": 915, "loss": 1.0468, "lr": 5.82608695652174e-05, "epoch": 0.3656207366984993, "percentage": 7.32, "elapsed_time": "0:58:34", "remaining_time": "12:21:17"}
+{"current_steps": 68, "total_steps": 915, "loss": 1.0099, "lr": 5.91304347826087e-05, "epoch": 0.3710777626193724, "percentage": 7.43, "elapsed_time": "0:59:25", "remaining_time": "12:20:09"}
+{"current_steps": 69, "total_steps": 915, "loss": 1.0185, "lr": 6.000000000000001e-05, "epoch": 0.3765347885402456, "percentage": 7.54, "elapsed_time": "1:00:16", "remaining_time": "12:19:05"}
+{"current_steps": 70, "total_steps": 915, "loss": 1.0291, "lr": 6.086956521739131e-05, "epoch": 0.3819918144611187, "percentage": 7.65, "elapsed_time": "1:01:08", "remaining_time": "12:17:58"}
+{"current_steps": 71, "total_steps": 915, "loss": 1.0281, "lr": 6.173913043478262e-05, "epoch": 0.3874488403819918, "percentage": 7.76, "elapsed_time": "1:01:59", "remaining_time": "12:17:00"}
+{"current_steps": 72, "total_steps": 915, "loss": 1.0242, "lr": 6.260869565217392e-05, "epoch": 0.39290586630286495, "percentage": 7.87, "elapsed_time": "1:02:58", "remaining_time": "12:17:22"}
+{"current_steps": 73, "total_steps": 915, "loss": 1.0296, "lr": 6.347826086956523e-05, "epoch": 0.39836289222373805, "percentage": 7.98, "elapsed_time": "1:03:55", "remaining_time": "12:17:22"}
+{"current_steps": 74, "total_steps": 915, "loss": 1.033, "lr": 6.434782608695653e-05, "epoch": 0.4038199181446112, "percentage": 8.09, "elapsed_time": "1:04:46", "remaining_time": "12:16:12"}
+{"current_steps": 75, "total_steps": 915, "loss": 1.0235, "lr": 6.521739130434783e-05, "epoch": 0.4092769440654843, "percentage": 8.2, "elapsed_time": "1:05:37", "remaining_time": "12:15:02"}
+{"current_steps": 76, "total_steps": 915, "loss": 1.0152, "lr": 6.608695652173914e-05, "epoch": 0.4147339699863574, "percentage": 8.31, "elapsed_time": "1:06:28", "remaining_time": "12:13:52"}
+{"current_steps": 77, "total_steps": 915, "loss": 1.0041, "lr": 6.695652173913044e-05, "epoch": 0.4201909959072306, "percentage": 8.42, "elapsed_time": "1:07:19", "remaining_time": "12:12:44"}
+{"current_steps": 78, "total_steps": 915, "loss": 1.004, "lr": 6.782608695652175e-05, "epoch": 0.4256480218281037, "percentage": 8.52, "elapsed_time": "1:08:10", "remaining_time": "12:11:36"}
+{"current_steps": 79, "total_steps": 915, "loss": 1.0354, "lr": 6.869565217391305e-05, "epoch": 0.4311050477489768, "percentage": 8.63, "elapsed_time": "1:09:01", "remaining_time": "12:10:30"}
+{"current_steps": 80, "total_steps": 915, "loss": 1.0152, "lr": 6.956521739130436e-05, "epoch": 0.43656207366984995, "percentage": 8.74, "elapsed_time": "1:09:52", "remaining_time": "12:09:24"}
+{"current_steps": 81, "total_steps": 915, "loss": 1.008, "lr": 7.043478260869566e-05, "epoch": 0.44201909959072305, "percentage": 8.85, "elapsed_time": "1:10:44", "remaining_time": "12:08:19"}
+{"current_steps": 82, "total_steps": 915, "loss": 1.0246, "lr": 7.130434782608696e-05, "epoch": 0.44747612551159616, "percentage": 8.96, "elapsed_time": "1:11:35", "remaining_time": "12:07:16"}
+{"current_steps": 83, "total_steps": 915, "loss": 1.0105, "lr": 7.217391304347827e-05, "epoch": 0.4529331514324693, "percentage": 9.07, "elapsed_time": "1:12:27", "remaining_time": "12:06:16"}
+{"current_steps": 84, "total_steps": 915, "loss": 0.9939, "lr": 7.304347826086957e-05, "epoch": 0.4583901773533424, "percentage": 9.18, "elapsed_time": "1:13:18", "remaining_time": "12:05:13"}
+{"current_steps": 85, "total_steps": 915, "loss": 1.0123, "lr": 7.391304347826088e-05, "epoch": 0.4638472032742155, "percentage": 9.29, "elapsed_time": "1:14:09", "remaining_time": "12:04:10"}
+{"current_steps": 86, "total_steps": 915, "loss": 1.0051, "lr": 7.478260869565218e-05, "epoch": 0.4693042291950887, "percentage": 9.4, "elapsed_time": "1:15:01", "remaining_time": "12:03:09"}
+{"current_steps": 87, "total_steps": 915, "loss": 1.0177, "lr": 7.565217391304349e-05, "epoch": 0.4747612551159618, "percentage": 9.51, "elapsed_time": "1:16:02", "remaining_time": "12:03:38"}
+{"current_steps": 88, "total_steps": 915, "loss": 1.0193, "lr": 7.652173913043479e-05, "epoch": 0.48021828103683495, "percentage": 9.62, "elapsed_time": "1:16:57", "remaining_time": "12:03:11"}
+{"current_steps": 89, "total_steps": 915, "loss": 0.9986, "lr": 7.73913043478261e-05, "epoch": 0.48567530695770805, "percentage": 9.73, "elapsed_time": "1:17:48", "remaining_time": "12:02:08"}
+{"current_steps": 90, "total_steps": 915, "loss": 1.0165, "lr": 7.82608695652174e-05, "epoch": 0.49113233287858116, "percentage": 9.84, "elapsed_time": "1:18:39", "remaining_time": "12:01:04"}
+{"current_steps": 91, "total_steps": 915, "loss": 0.9995, "lr": 7.91304347826087e-05, "epoch": 0.4965893587994543, "percentage": 9.95, "elapsed_time": "1:19:31", "remaining_time": "12:00:01"}
+{"current_steps": 92, "total_steps": 915, "loss": 1.0226, "lr": 8e-05, "epoch": 0.5020463847203275, "percentage": 10.05, "elapsed_time": "1:20:22", "remaining_time": "11:58:58"}
+{"current_steps": 93, "total_steps": 915, "loss": 0.9975, "lr": 7.999970857316263e-05, "epoch": 0.5075034106412005, "percentage": 10.16, "elapsed_time": "1:21:13", "remaining_time": "11:57:56"}
+{"current_steps": 94, "total_steps": 915, "loss": 1.0067, "lr": 7.999883429689698e-05, "epoch": 0.5129604365620737, "percentage": 10.27, "elapsed_time": "1:22:04", "remaining_time": "11:56:53"}
+{"current_steps": 95, "total_steps": 915, "loss": 1.0242, "lr": 7.999737718394245e-05, "epoch": 0.5184174624829468, "percentage": 10.38, "elapsed_time": "1:22:56", "remaining_time": "11:55:52"}
+{"current_steps": 96, "total_steps": 915, "loss": 0.9984, "lr": 7.999533725553111e-05, "epoch": 0.5238744884038199, "percentage": 10.49, "elapsed_time": "1:23:47", "remaining_time": "11:54:48"}
+{"current_steps": 97, "total_steps": 915, "loss": 0.9959, "lr": 7.999271454138746e-05, "epoch": 0.529331514324693, "percentage": 10.6, "elapsed_time": "1:24:38", "remaining_time": "11:53:47"}
+{"current_steps": 98, "total_steps": 915, "loss": 0.9979, "lr": 7.998950907972797e-05, "epoch": 0.5347885402455662, "percentage": 10.71, "elapsed_time": "1:25:29", "remaining_time": "11:52:44"}
+{"current_steps": 99, "total_steps": 915, "loss": 0.9941, "lr": 7.998572091726051e-05, "epoch": 0.5402455661664393, "percentage": 10.82, "elapsed_time": "1:26:20", "remaining_time": "11:51:43"}
+{"current_steps": 100, "total_steps": 915, "loss": 1.0043, "lr": 7.99813501091837e-05, "epoch": 0.5457025920873124, "percentage": 10.93, "elapsed_time": "1:27:12", "remaining_time": "11:50:41"}
+{"current_steps": 101, "total_steps": 915, "loss": 0.9744, "lr": 7.997639671918607e-05, "epoch": 0.5511596180081856, "percentage": 11.04, "elapsed_time": "1:28:03", "remaining_time": "11:49:41"}
+{"current_steps": 102, "total_steps": 915, "loss": 0.9853, "lr": 7.997086081944518e-05, "epoch": 0.5566166439290586, "percentage": 11.15, "elapsed_time": "1:29:04", "remaining_time": "11:49:57"}
+{"current_steps": 103, "total_steps": 915, "loss": 0.9889, "lr": 7.996474249062649e-05, "epoch": 0.5620736698499318, "percentage": 11.26, "elapsed_time": "1:30:00", "remaining_time": "11:49:35"}
+{"current_steps": 104, "total_steps": 915, "loss": 0.9871, "lr": 7.995804182188227e-05, "epoch": 0.567530695770805, "percentage": 11.37, "elapsed_time": "1:30:51", "remaining_time": "11:48:32"}
+{"current_steps": 105, "total_steps": 915, "loss": 0.9715, "lr": 7.995075891085025e-05, "epoch": 0.572987721691678, "percentage": 11.48, "elapsed_time": "1:31:42", "remaining_time": "11:47:30"}
+{"current_steps": 106, "total_steps": 915, "loss": 0.9946, "lr": 7.994289386365223e-05, "epoch": 0.5784447476125512, "percentage": 11.58, "elapsed_time": "1:32:33", "remaining_time": "11:46:27"}
+{"current_steps": 107, "total_steps": 915, "loss": 0.9963, "lr": 7.99344467948925e-05, "epoch": 0.5839017735334243, "percentage": 11.69, "elapsed_time": "1:33:25", "remaining_time": "11:45:27"}
+{"current_steps": 108, "total_steps": 915, "loss": 0.9943, "lr": 7.992541782765617e-05, "epoch": 0.5893587994542974, "percentage": 11.8, "elapsed_time": "1:34:16", "remaining_time": "11:44:26"}
+{"current_steps": 109, "total_steps": 915, "loss": 1.0062, "lr": 7.991580709350743e-05, "epoch": 0.5948158253751705, "percentage": 11.91, "elapsed_time": "1:35:07", "remaining_time": "11:43:24"}
+{"current_steps": 110, "total_steps": 915, "loss": 0.9949, "lr": 7.990561473248756e-05, "epoch": 0.6002728512960437, "percentage": 12.02, "elapsed_time": "1:35:58", "remaining_time": "11:42:24"}
+{"current_steps": 111, "total_steps": 915, "loss": 0.9918, "lr": 7.989484089311294e-05, "epoch": 0.6057298772169167, "percentage": 12.13, "elapsed_time": "1:36:50", "remaining_time": "11:41:24"}
+{"current_steps": 112, "total_steps": 915, "loss": 1.0199, "lr": 7.988348573237286e-05, "epoch": 0.6111869031377899, "percentage": 12.24, "elapsed_time": "1:37:41", "remaining_time": "11:40:25"}
+{"current_steps": 113, "total_steps": 915, "loss": 0.9874, "lr": 7.987154941572726e-05, "epoch": 0.616643929058663, "percentage": 12.35, "elapsed_time": "1:38:32", "remaining_time": "11:39:24"}
+{"current_steps": 114, "total_steps": 915, "loss": 0.9808, "lr": 7.985903211710429e-05, "epoch": 0.6221009549795361, "percentage": 12.46, "elapsed_time": "1:39:23", "remaining_time": "11:38:23"}
+{"current_steps": 115, "total_steps": 915, "loss": 0.9782, "lr": 7.984593401889778e-05, "epoch": 0.6275579809004093, "percentage": 12.57, "elapsed_time": "1:40:15", "remaining_time": "11:37:24"}
+{"current_steps": 116, "total_steps": 915, "loss": 0.9962, "lr": 7.98322553119646e-05, "epoch": 0.6330150068212824, "percentage": 12.68, "elapsed_time": "1:41:06", "remaining_time": "11:36:26"}
+{"current_steps": 117, "total_steps": 915, "loss": 0.9805, "lr": 7.981799619562186e-05, "epoch": 0.6384720327421555, "percentage": 12.79, "elapsed_time": "1:42:10", "remaining_time": "11:36:50"}
+{"current_steps": 118, "total_steps": 915, "loss": 0.9874, "lr": 7.980315687764404e-05, "epoch": 0.6439290586630286, "percentage": 12.9, "elapsed_time": "1:43:04", "remaining_time": "11:36:13"}
+{"current_steps": 119, "total_steps": 915, "loss": 0.99, "lr": 7.978773757425987e-05, "epoch": 0.6493860845839018, "percentage": 13.01, "elapsed_time": "1:43:55", "remaining_time": "11:35:12"}
+{"current_steps": 120, "total_steps": 915, "loss": 1.0013, "lr": 7.977173851014935e-05, "epoch": 0.654843110504775, "percentage": 13.11, "elapsed_time": "1:44:47", "remaining_time": "11:34:11"}
+{"current_steps": 121, "total_steps": 915, "loss": 1.0019, "lr": 7.975515991844028e-05, "epoch": 0.660300136425648, "percentage": 13.22, "elapsed_time": "1:45:38", "remaining_time": "11:33:12"}
+{"current_steps": 122, "total_steps": 915, "loss": 1.0144, "lr": 7.973800204070497e-05, "epoch": 0.6657571623465212, "percentage": 13.33, "elapsed_time": "1:46:30", "remaining_time": "11:32:15"}
+{"current_steps": 123, "total_steps": 915, "loss": 0.9946, "lr": 7.972026512695677e-05, "epoch": 0.6712141882673943, "percentage": 13.44, "elapsed_time": "1:47:21", "remaining_time": "11:31:16"}
+{"current_steps": 124, "total_steps": 915, "loss": 0.9965, "lr": 7.970194943564626e-05, "epoch": 0.6766712141882674, "percentage": 13.55, "elapsed_time": "1:48:12", "remaining_time": "11:30:17"}
+{"current_steps": 125, "total_steps": 915, "loss": 0.9884, "lr": 7.968305523365768e-05, "epoch": 0.6821282401091405, "percentage": 13.66, "elapsed_time": "1:49:04", "remaining_time": "11:29:18"}
+{"current_steps": 126, "total_steps": 915, "loss": 1.008, "lr": 7.96635827963049e-05, "epoch": 0.6875852660300137, "percentage": 13.77, "elapsed_time": "1:49:55", "remaining_time": "11:28:19"}
+{"current_steps": 127, "total_steps": 915, "loss": 0.9685, "lr": 7.964353240732744e-05, "epoch": 0.6930422919508867, "percentage": 13.88, "elapsed_time": "1:50:46", "remaining_time": "11:27:19"}
+{"current_steps": 128, "total_steps": 915, "loss": 0.9996, "lr": 7.96229043588864e-05, "epoch": 0.6984993178717599, "percentage": 13.99, "elapsed_time": "1:51:37", "remaining_time": "11:26:21"}
+{"current_steps": 129, "total_steps": 915, "loss": 1.008, "lr": 7.960169895156011e-05, "epoch": 0.703956343792633, "percentage": 14.1, "elapsed_time": "1:52:29", "remaining_time": "11:25:22"}
+{"current_steps": 130, "total_steps": 915, "loss": 0.9718, "lr": 7.95799164943398e-05, "epoch": 0.7094133697135061, "percentage": 14.21, "elapsed_time": "1:53:20", "remaining_time": "11:24:24"}
+{"current_steps": 131, "total_steps": 915, "loss": 0.9924, "lr": 7.955755730462512e-05, "epoch": 0.7148703956343793, "percentage": 14.32, "elapsed_time": "1:54:11", "remaining_time": "11:23:25"}
+{"current_steps": 132, "total_steps": 915, "loss": 0.9855, "lr": 7.953462170821948e-05, "epoch": 0.7203274215552524, "percentage": 14.43, "elapsed_time": "1:55:14", "remaining_time": "11:23:36"}
+{"current_steps": 133, "total_steps": 915, "loss": 0.9893, "lr": 7.951111003932526e-05, "epoch": 0.7257844474761255, "percentage": 14.54, "elapsed_time": "1:56:09", "remaining_time": "11:22:56"}
+{"current_steps": 134, "total_steps": 915, "loss": 0.9758, "lr": 7.948702264053904e-05, "epoch": 0.7312414733969986, "percentage": 14.64, "elapsed_time": "1:57:00", "remaining_time": "11:21:57"}
+{"current_steps": 135, "total_steps": 915, "loss": 0.985, "lr": 7.946235986284655e-05, "epoch": 0.7366984993178718, "percentage": 14.75, "elapsed_time": "1:57:51", "remaining_time": "11:20:57"}
+{"current_steps": 136, "total_steps": 915, "loss": 0.9912, "lr": 7.943712206561755e-05, "epoch": 0.7421555252387448, "percentage": 14.86, "elapsed_time": "1:58:42", "remaining_time": "11:19:58"}
+{"current_steps": 137, "total_steps": 915, "loss": 0.9658, "lr": 7.94113096166006e-05, "epoch": 0.747612551159618, "percentage": 14.97, "elapsed_time": "1:59:34", "remaining_time": "11:19:00"}
+{"current_steps": 138, "total_steps": 915, "loss": 0.9926, "lr": 7.938492289191775e-05, "epoch": 0.7530695770804912, "percentage": 15.08, "elapsed_time": "2:00:25", "remaining_time": "11:18:00"}
+{"current_steps": 139, "total_steps": 915, "loss": 0.9767, "lr": 7.935796227605896e-05, "epoch": 0.7585266030013642, "percentage": 15.19, "elapsed_time": "2:01:16", "remaining_time": "11:17:00"}
+{"current_steps": 140, "total_steps": 915, "loss": 0.9847, "lr": 7.933042816187659e-05, "epoch": 0.7639836289222374, "percentage": 15.3, "elapsed_time": "2:02:07", "remaining_time": "11:16:02"}
+{"current_steps": 141, "total_steps": 915, "loss": 1.0202, "lr": 7.930232095057961e-05, "epoch": 0.7694406548431105, "percentage": 15.41, "elapsed_time": "2:02:58", "remaining_time": "11:15:03"}
+{"current_steps": 142, "total_steps": 915, "loss": 0.987, "lr": 7.927364105172784e-05, "epoch": 0.7748976807639836, "percentage": 15.52, "elapsed_time": "2:03:49", "remaining_time": "11:14:05"}
+{"current_steps": 143, "total_steps": 915, "loss": 0.9949, "lr": 7.924438888322588e-05, "epoch": 0.7803547066848567, "percentage": 15.63, "elapsed_time": "2:04:40", "remaining_time": "11:13:05"}
+{"current_steps": 144, "total_steps": 915, "loss": 0.9947, "lr": 7.921456487131706e-05, "epoch": 0.7858117326057299, "percentage": 15.74, "elapsed_time": "2:05:31", "remaining_time": "11:12:07"}
+{"current_steps": 145, "total_steps": 915, "loss": 0.9704, "lr": 7.918416945057726e-05, "epoch": 0.791268758526603, "percentage": 15.85, "elapsed_time": "2:06:23", "remaining_time": "11:11:10"}
+{"current_steps": 146, "total_steps": 915, "loss": 1.0124, "lr": 7.915320306390856e-05, "epoch": 0.7967257844474761, "percentage": 15.96, "elapsed_time": "2:07:14", "remaining_time": "11:10:12"}
+{"current_steps": 147, "total_steps": 915, "loss": 0.9622, "lr": 7.912166616253276e-05, "epoch": 0.8021828103683493, "percentage": 16.07, "elapsed_time": "2:08:17", "remaining_time": "11:10:15"}
+{"current_steps": 148, "total_steps": 915, "loss": 0.9645, "lr": 7.908955920598482e-05, "epoch": 0.8076398362892224, "percentage": 16.17, "elapsed_time": "2:09:10", "remaining_time": "11:09:26"}
+{"current_steps": 149, "total_steps": 915, "loss": 0.9997, "lr": 7.90568826621062e-05, "epoch": 0.8130968622100955, "percentage": 16.28, "elapsed_time": "2:10:01", "remaining_time": "11:08:27"}
+{"current_steps": 150, "total_steps": 915, "loss": 0.9816, "lr": 7.902363700703797e-05, "epoch": 0.8185538881309686, "percentage": 16.39, "elapsed_time": "2:10:52", "remaining_time": "11:07:29"}
+{"current_steps": 151, "total_steps": 915, "loss": 0.978, "lr": 7.898982272521396e-05, "epoch": 0.8240109140518418, "percentage": 16.5, "elapsed_time": "2:11:43", "remaining_time": "11:06:30"}
+{"current_steps": 152, "total_steps": 915, "loss": 0.9733, "lr": 7.895544030935361e-05, "epoch": 0.8294679399727148, "percentage": 16.61, "elapsed_time": "2:12:34", "remaining_time": "11:05:31"}
+{"current_steps": 153, "total_steps": 915, "loss": 0.9612, "lr": 7.892049026045487e-05, "epoch": 0.834924965893588, "percentage": 16.72, "elapsed_time": "2:13:26", "remaining_time": "11:04:34"}
+{"current_steps": 154, "total_steps": 915, "loss": 0.9628, "lr": 7.888497308778685e-05, "epoch": 0.8403819918144612, "percentage": 16.83, "elapsed_time": "2:14:17", "remaining_time": "11:03:38"}
+{"current_steps": 155, "total_steps": 915, "loss": 0.9731, "lr": 7.88488893088824e-05, "epoch": 0.8458390177353342, "percentage": 16.94, "elapsed_time": "2:15:09", "remaining_time": "11:02:40"}
+{"current_steps": 156, "total_steps": 915, "loss": 0.9695, "lr": 7.88122394495306e-05, "epoch": 0.8512960436562074, "percentage": 17.05, "elapsed_time": "2:16:00", "remaining_time": "11:01:43"}
+{"current_steps": 157, "total_steps": 915, "loss": 0.9789, "lr": 7.877502404376911e-05, "epoch": 0.8567530695770805, "percentage": 17.16, "elapsed_time": "2:16:51", "remaining_time": "11:00:46"}
+{"current_steps": 158, "total_steps": 915, "loss": 0.9699, "lr": 7.87372436338763e-05, "epoch": 0.8622100954979536, "percentage": 17.27, "elapsed_time": "2:17:42", "remaining_time": "10:59:48"}
+{"current_steps": 159, "total_steps": 915, "loss": 0.9902, "lr": 7.869889877036344e-05, "epoch": 0.8676671214188267, "percentage": 17.38, "elapsed_time": "2:18:34", "remaining_time": "10:58:50"}
+{"current_steps": 160, "total_steps": 915, "loss": 1.0069, "lr": 7.865999001196666e-05, "epoch": 0.8731241473396999, "percentage": 17.49, "elapsed_time": "2:19:25", "remaining_time": "10:57:54"}
+{"current_steps": 161, "total_steps": 915, "loss": 1.0643, "lr": 7.862051792563878e-05, "epoch": 0.878581173260573, "percentage": 17.6, "elapsed_time": "2:20:16", "remaining_time": "10:56:57"}
+{"current_steps": 162, "total_steps": 915, "loss": 1.0055, "lr": 7.858048308654104e-05, "epoch": 0.8840381991814461, "percentage": 17.7, "elapsed_time": "2:21:21", "remaining_time": "10:57:04"}
+{"current_steps": 163, "total_steps": 915, "loss": 1.0145, "lr": 7.853988607803479e-05, "epoch": 0.8894952251023193, "percentage": 17.81, "elapsed_time": "2:22:13", "remaining_time": "10:56:10"}
+{"current_steps": 164, "total_steps": 915, "loss": 1.0109, "lr": 7.849872749167291e-05, "epoch": 0.8949522510231923, "percentage": 17.92, "elapsed_time": "2:23:04", "remaining_time": "10:55:11"}
+{"current_steps": 165, "total_steps": 915, "loss": 0.9914, "lr": 7.845700792719124e-05, "epoch": 0.9004092769440655, "percentage": 18.03, "elapsed_time": "2:23:56", "remaining_time": "10:54:14"}
+{"current_steps": 166, "total_steps": 915, "loss": 1.0061, "lr": 7.84147279924998e-05, "epoch": 0.9058663028649386, "percentage": 18.14, "elapsed_time": "2:24:47", "remaining_time": "10:53:16"}
+{"current_steps": 167, "total_steps": 915, "loss": 1.0183, "lr": 7.837188830367401e-05, "epoch": 0.9113233287858117, "percentage": 18.25, "elapsed_time": "2:25:38", "remaining_time": "10:52:19"}
+{"current_steps": 168, "total_steps": 915, "loss": 1.0037, "lr": 7.832848948494559e-05, "epoch": 0.9167803547066848, "percentage": 18.36, "elapsed_time": "2:26:29", "remaining_time": "10:51:22"}
+{"current_steps": 169, "total_steps": 915, "loss": 0.9911, "lr": 7.828453216869356e-05, "epoch": 0.922237380627558, "percentage": 18.47, "elapsed_time": "2:27:20", "remaining_time": "10:50:25"}
+{"current_steps": 170, "total_steps": 915, "loss": 1.0012, "lr": 7.824001699543502e-05, "epoch": 0.927694406548431, "percentage": 18.58, "elapsed_time": "2:28:11", "remaining_time": "10:49:27"}
+{"current_steps": 171, "total_steps": 915, "loss": 1.0003, "lr": 7.819494461381577e-05, "epoch": 0.9331514324693042, "percentage": 18.69, "elapsed_time": "2:29:03", "remaining_time": "10:48:30"}
+{"current_steps": 172, "total_steps": 915, "loss": 0.9924, "lr": 7.81493156806009e-05, "epoch": 0.9386084583901774, "percentage": 18.8, "elapsed_time": "2:29:53", "remaining_time": "10:47:31"}
+{"current_steps": 173, "total_steps": 915, "loss": 0.9756, "lr": 7.81031308606652e-05, "epoch": 0.9440654843110505, "percentage": 18.91, "elapsed_time": "2:30:45", "remaining_time": "10:46:34"}
+{"current_steps": 174, "total_steps": 915, "loss": 0.9678, "lr": 7.805639082698342e-05, "epoch": 0.9495225102319236, "percentage": 19.02, "elapsed_time": "2:31:36", "remaining_time": "10:45:38"}
+{"current_steps": 175, "total_steps": 915, "loss": 0.9782, "lr": 7.800909626062064e-05, "epoch": 0.9549795361527967, "percentage": 19.13, "elapsed_time": "2:32:27", "remaining_time": "10:44:42"}
+{"current_steps": 176, "total_steps": 915, "loss": 0.9921, "lr": 7.796124785072212e-05, "epoch": 0.9604365620736699, "percentage": 19.23, "elapsed_time": "2:33:19", "remaining_time": "10:43:45"}
+{"current_steps": 177, "total_steps": 915, "loss": 0.977, "lr": 7.791284629450338e-05, "epoch": 0.965893587994543, "percentage": 19.34, "elapsed_time": "2:34:25", "remaining_time": "10:43:50"}
+{"current_steps": 178, "total_steps": 915, "loss": 0.9733, "lr": 7.78638922972401e-05, "epoch": 0.9713506139154161, "percentage": 19.45, "elapsed_time": "2:35:16", "remaining_time": "10:42:55"}
+{"current_steps": 179, "total_steps": 915, "loss": 0.9817, "lr": 7.781438657225764e-05, "epoch": 0.9768076398362893, "percentage": 19.56, "elapsed_time": "2:36:07", "remaining_time": "10:41:58"}
+{"current_steps": 180, "total_steps": 915, "loss": 0.9586, "lr": 7.77643298409209e-05, "epoch": 0.9822646657571623, "percentage": 19.67, "elapsed_time": "2:36:58", "remaining_time": "10:41:00"}
+{"current_steps": 181, "total_steps": 915, "loss": 0.9903, "lr": 7.77137228326236e-05, "epoch": 0.9877216916780355, "percentage": 19.78, "elapsed_time": "2:37:50", "remaining_time": "10:40:03"}
+{"current_steps": 182, "total_steps": 915, "loss": 0.9696, "lr": 7.766256628477775e-05, "epoch": 0.9931787175989086, "percentage": 19.89, "elapsed_time": "2:38:41", "remaining_time": "10:39:05"}
+{"current_steps": 183, "total_steps": 915, "loss": 0.9922, "lr": 7.761086094280291e-05, "epoch": 0.9986357435197817, "percentage": 20.0, "elapsed_time": "2:39:32", "remaining_time": "10:38:08"}
+{"current_steps": 184, "total_steps": 915, "loss": 1.6748, "lr": 7.755860756011531e-05, "epoch": 1.004092769440655, "percentage": 20.11, "elapsed_time": "2:41:39", "remaining_time": "10:42:14"}
+{"current_steps": 185, "total_steps": 915, "loss": 0.9345, "lr": 7.750580689811683e-05, "epoch": 1.009549795361528, "percentage": 20.22, "elapsed_time": "2:42:30", "remaining_time": "10:41:15"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718c144ad2ab084cdc333589780bdddeedb79c04808bbd13d9c04cb59946b81f
+size 7160