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:d1ea63e32ae6445c55e61e0c4ae378bcb514b13e3a5ff767165930d8a0d2cc75
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a396068cc16803a239ac685d482eacf648a00457a30a011ff585d21a5b5e825
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a90690d350130709fb7f21bab1ca42bb0980bee06267e9a9e817ca1a892b337
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89035deaf0a412615a469474ac4409d185018a82caa714c60b57ff1606b191fa
+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 +1,202 @@
+{"current_steps": 1, "total_steps": 201, "loss": 1.1703, "lr": 4.7619047619047623e-07, "epoch": 0.01485148514851485, "percentage": 0.5, "elapsed_time": "0:00:12", "remaining_time": "0:41:55"}
+{"current_steps": 2, "total_steps": 201, "loss": 1.1918, "lr": 9.523809523809525e-07, "epoch": 0.0297029702970297, "percentage": 1.0, "elapsed_time": "0:00:22", "remaining_time": "0:36:30"}
+{"current_steps": 3, "total_steps": 201, "loss": 1.1576, "lr": 1.4285714285714286e-06, "epoch": 0.04455445544554455, "percentage": 1.49, "elapsed_time": "0:00:32", "remaining_time": "0:36:02"}
+{"current_steps": 4, "total_steps": 201, "loss": 1.2099, "lr": 1.904761904761905e-06, "epoch": 0.0594059405940594, "percentage": 1.99, "elapsed_time": "0:00:46", "remaining_time": "0:38:17"}
+{"current_steps": 5, "total_steps": 201, "loss": 1.1447, "lr": 2.380952380952381e-06, "epoch": 0.07425742574257425, "percentage": 2.49, "elapsed_time": "0:00:59", "remaining_time": "0:39:06"}
+{"current_steps": 6, "total_steps": 201, "loss": 1.1128, "lr": 2.8571428571428573e-06, "epoch": 0.0891089108910891, "percentage": 2.99, "elapsed_time": "0:01:15", "remaining_time": "0:41:03"}
+{"current_steps": 7, "total_steps": 201, "loss": 1.1444, "lr": 3.3333333333333333e-06, "epoch": 0.10396039603960396, "percentage": 3.48, "elapsed_time": "0:01:29", "remaining_time": "0:41:30"}
+{"current_steps": 8, "total_steps": 201, "loss": 1.0333, "lr": 3.80952380952381e-06, "epoch": 0.1188118811881188, "percentage": 3.98, "elapsed_time": "0:01:38", "remaining_time": "0:39:42"}
+{"current_steps": 9, "total_steps": 201, "loss": 1.039, "lr": 4.2857142857142855e-06, "epoch": 0.13366336633663367, "percentage": 4.48, "elapsed_time": "0:01:51", "remaining_time": "0:39:37"}
+{"current_steps": 10, "total_steps": 201, "loss": 1.0171, "lr": 4.761904761904762e-06, "epoch": 0.1485148514851485, "percentage": 4.98, "elapsed_time": "0:02:00", "remaining_time": "0:38:24"}
+{"current_steps": 11, "total_steps": 201, "loss": 1.0232, "lr": 5.2380952380952384e-06, "epoch": 0.16336633663366337, "percentage": 5.47, "elapsed_time": "0:02:14", "remaining_time": "0:38:38"}
+{"current_steps": 12, "total_steps": 201, "loss": 1.0875, "lr": 5.7142857142857145e-06, "epoch": 0.1782178217821782, "percentage": 5.97, "elapsed_time": "0:02:27", "remaining_time": "0:38:46"}
+{"current_steps": 13, "total_steps": 201, "loss": 1.0108, "lr": 6.1904761904761914e-06, "epoch": 0.19306930693069307, "percentage": 6.47, "elapsed_time": "0:02:39", "remaining_time": "0:38:25"}
+{"current_steps": 14, "total_steps": 201, "loss": 0.9857, "lr": 6.666666666666667e-06, "epoch": 0.2079207920792079, "percentage": 6.97, "elapsed_time": "0:02:49", "remaining_time": "0:37:48"}
+{"current_steps": 15, "total_steps": 201, "loss": 0.9728, "lr": 7.1428571428571436e-06, "epoch": 0.22277227722772278, "percentage": 7.46, "elapsed_time": "0:03:04", "remaining_time": "0:38:05"}
+{"current_steps": 16, "total_steps": 201, "loss": 0.9694, "lr": 7.61904761904762e-06, "epoch": 0.2376237623762376, "percentage": 7.96, "elapsed_time": "0:03:18", "remaining_time": "0:38:13"}
+{"current_steps": 17, "total_steps": 201, "loss": 0.934, "lr": 8.095238095238097e-06, "epoch": 0.2524752475247525, "percentage": 8.46, "elapsed_time": "0:03:30", "remaining_time": "0:38:01"}
+{"current_steps": 18, "total_steps": 201, "loss": 0.9175, "lr": 8.571428571428571e-06, "epoch": 0.26732673267326734, "percentage": 8.96, "elapsed_time": "0:03:44", "remaining_time": "0:38:03"}
+{"current_steps": 19, "total_steps": 201, "loss": 0.9595, "lr": 9.047619047619049e-06, "epoch": 0.28217821782178215, "percentage": 9.45, "elapsed_time": "0:03:59", "remaining_time": "0:38:12"}
+{"current_steps": 20, "total_steps": 201, "loss": 0.9082, "lr": 9.523809523809525e-06, "epoch": 0.297029702970297, "percentage": 9.95, "elapsed_time": "0:04:08", "remaining_time": "0:37:32"}
+{"current_steps": 21, "total_steps": 201, "loss": 0.8293, "lr": 1e-05, "epoch": 0.3118811881188119, "percentage": 10.45, "elapsed_time": "0:04:19", "remaining_time": "0:37:02"}
+{"current_steps": 22, "total_steps": 201, "loss": 0.8615, "lr": 9.999238475781957e-06, "epoch": 0.32673267326732675, "percentage": 10.95, "elapsed_time": "0:04:31", "remaining_time": "0:36:49"}
+{"current_steps": 23, "total_steps": 201, "loss": 0.8963, "lr": 9.99695413509548e-06, "epoch": 0.3415841584158416, "percentage": 11.44, "elapsed_time": "0:04:44", "remaining_time": "0:36:40"}
+{"current_steps": 24, "total_steps": 201, "loss": 0.875, "lr": 9.993147673772869e-06, "epoch": 0.3564356435643564, "percentage": 11.94, "elapsed_time": "0:04:58", "remaining_time": "0:36:40"}
+{"current_steps": 25, "total_steps": 201, "loss": 0.8488, "lr": 9.987820251299121e-06, "epoch": 0.3712871287128713, "percentage": 12.44, "elapsed_time": "0:05:14", "remaining_time": "0:36:53"}
+{"current_steps": 26, "total_steps": 201, "loss": 0.8838, "lr": 9.980973490458728e-06, "epoch": 0.38613861386138615, "percentage": 12.94, "elapsed_time": "0:05:25", "remaining_time": "0:36:30"}
+{"current_steps": 27, "total_steps": 201, "loss": 0.8299, "lr": 9.972609476841368e-06, "epoch": 0.400990099009901, "percentage": 13.43, "elapsed_time": "0:05:40", "remaining_time": "0:36:36"}
+{"current_steps": 28, "total_steps": 201, "loss": 0.866, "lr": 9.962730758206612e-06, "epoch": 0.4158415841584158, "percentage": 13.93, "elapsed_time": "0:05:53", "remaining_time": "0:36:22"}
+{"current_steps": 29, "total_steps": 201, "loss": 0.8509, "lr": 9.951340343707852e-06, "epoch": 0.4306930693069307, "percentage": 14.43, "elapsed_time": "0:06:05", "remaining_time": "0:36:05"}
+{"current_steps": 30, "total_steps": 201, "loss": 0.8288, "lr": 9.938441702975689e-06, "epoch": 0.44554455445544555, "percentage": 14.93, "elapsed_time": "0:06:15", "remaining_time": "0:35:38"}
+{"current_steps": 31, "total_steps": 201, "loss": 0.838, "lr": 9.924038765061042e-06, "epoch": 0.4603960396039604, "percentage": 15.42, "elapsed_time": "0:06:28", "remaining_time": "0:35:32"}
+{"current_steps": 32, "total_steps": 201, "loss": 0.8609, "lr": 9.908135917238321e-06, "epoch": 0.4752475247524752, "percentage": 15.92, "elapsed_time": "0:06:44", "remaining_time": "0:35:36"}
+{"current_steps": 33, "total_steps": 201, "loss": 0.8583, "lr": 9.890738003669029e-06, "epoch": 0.4900990099009901, "percentage": 16.42, "elapsed_time": "0:06:57", "remaining_time": "0:35:27"}
+{"current_steps": 34, "total_steps": 201, "loss": 0.7944, "lr": 9.871850323926178e-06, "epoch": 0.504950495049505, "percentage": 16.92, "elapsed_time": "0:07:03", "remaining_time": "0:34:42"}
+{"current_steps": 35, "total_steps": 201, "loss": 0.8975, "lr": 9.851478631379982e-06, "epoch": 0.5198019801980198, "percentage": 17.41, "elapsed_time": "0:07:19", "remaining_time": "0:34:45"}
+{"current_steps": 36, "total_steps": 201, "loss": 0.8676, "lr": 9.829629131445342e-06, "epoch": 0.5346534653465347, "percentage": 17.91, "elapsed_time": "0:07:35", "remaining_time": "0:34:49"}
+{"current_steps": 37, "total_steps": 201, "loss": 0.8975, "lr": 9.806308479691595e-06, "epoch": 0.5495049504950495, "percentage": 18.41, "elapsed_time": "0:07:48", "remaining_time": "0:34:37"}
+{"current_steps": 38, "total_steps": 201, "loss": 0.8207, "lr": 9.781523779815178e-06, "epoch": 0.5643564356435643, "percentage": 18.91, "elapsed_time": "0:07:59", "remaining_time": "0:34:17"}
+{"current_steps": 39, "total_steps": 201, "loss": 0.8416, "lr": 9.755282581475769e-06, "epoch": 0.5792079207920792, "percentage": 19.4, "elapsed_time": "0:08:14", "remaining_time": "0:34:15"}
+{"current_steps": 40, "total_steps": 201, "loss": 0.9003, "lr": 9.727592877996585e-06, "epoch": 0.594059405940594, "percentage": 19.9, "elapsed_time": "0:08:32", "remaining_time": "0:34:22"}
+{"current_steps": 41, "total_steps": 201, "loss": 0.8279, "lr": 9.698463103929542e-06, "epoch": 0.6089108910891089, "percentage": 20.4, "elapsed_time": "0:08:46", "remaining_time": "0:34:15"}
+{"current_steps": 42, "total_steps": 201, "loss": 0.8252, "lr": 9.667902132486009e-06, "epoch": 0.6237623762376238, "percentage": 20.9, "elapsed_time": "0:08:58", "remaining_time": "0:33:57"}
+{"current_steps": 43, "total_steps": 201, "loss": 0.8417, "lr": 9.635919272833938e-06, "epoch": 0.6386138613861386, "percentage": 21.39, "elapsed_time": "0:09:10", "remaining_time": "0:33:44"}
+{"current_steps": 44, "total_steps": 201, "loss": 0.8068, "lr": 9.602524267262202e-06, "epoch": 0.6534653465346535, "percentage": 21.89, "elapsed_time": "0:09:22", "remaining_time": "0:33:28"}
+{"current_steps": 45, "total_steps": 201, "loss": 0.8116, "lr": 9.567727288213005e-06, "epoch": 0.6683168316831684, "percentage": 22.39, "elapsed_time": "0:09:34", "remaining_time": "0:33:10"}
+{"current_steps": 46, "total_steps": 201, "loss": 0.8049, "lr": 9.531538935183252e-06, "epoch": 0.6831683168316832, "percentage": 22.89, "elapsed_time": "0:09:46", "remaining_time": "0:32:57"}
+{"current_steps": 47, "total_steps": 201, "loss": 0.8158, "lr": 9.493970231495836e-06, "epoch": 0.698019801980198, "percentage": 23.38, "elapsed_time": "0:10:00", "remaining_time": "0:32:48"}
+{"current_steps": 48, "total_steps": 201, "loss": 0.7963, "lr": 9.45503262094184e-06, "epoch": 0.7128712871287128, "percentage": 23.88, "elapsed_time": "0:10:14", "remaining_time": "0:32:37"}
+{"current_steps": 49, "total_steps": 201, "loss": 0.8372, "lr": 9.414737964294636e-06, "epoch": 0.7277227722772277, "percentage": 24.38, "elapsed_time": "0:10:24", "remaining_time": "0:32:17"}
+{"current_steps": 50, "total_steps": 201, "loss": 0.7974, "lr": 9.37309853569698e-06, "epoch": 0.7425742574257426, "percentage": 24.88, "elapsed_time": "0:10:35", "remaining_time": "0:31:59"}
+{"current_steps": 51, "total_steps": 201, "loss": 0.797, "lr": 9.330127018922195e-06, "epoch": 0.7574257425742574, "percentage": 25.37, "elapsed_time": "0:10:46", "remaining_time": "0:31:40"}
+{"current_steps": 52, "total_steps": 201, "loss": 0.8178, "lr": 9.285836503510562e-06, "epoch": 0.7722772277227723, "percentage": 25.87, "elapsed_time": "0:10:54", "remaining_time": "0:31:16"}
+{"current_steps": 53, "total_steps": 201, "loss": 0.8286, "lr": 9.24024048078213e-06, "epoch": 0.7871287128712872, "percentage": 26.37, "elapsed_time": "0:11:06", "remaining_time": "0:31:01"}
+{"current_steps": 54, "total_steps": 201, "loss": 0.8199, "lr": 9.193352839727122e-06, "epoch": 0.801980198019802, "percentage": 26.87, "elapsed_time": "0:11:18", "remaining_time": "0:30:47"}
+{"current_steps": 55, "total_steps": 201, "loss": 0.8325, "lr": 9.145187862775208e-06, "epoch": 0.8168316831683168, "percentage": 27.36, "elapsed_time": "0:11:31", "remaining_time": "0:30:35"}
+{"current_steps": 56, "total_steps": 201, "loss": 0.7876, "lr": 9.09576022144496e-06, "epoch": 0.8316831683168316, "percentage": 27.86, "elapsed_time": "0:11:44", "remaining_time": "0:30:23"}
+{"current_steps": 57, "total_steps": 201, "loss": 0.7889, "lr": 9.045084971874738e-06, "epoch": 0.8465346534653465, "percentage": 28.36, "elapsed_time": "0:11:53", "remaining_time": "0:30:01"}
+{"current_steps": 58, "total_steps": 201, "loss": 0.819, "lr": 8.993177550236464e-06, "epoch": 0.8613861386138614, "percentage": 28.86, "elapsed_time": "0:12:05", "remaining_time": "0:29:48"}
+{"current_steps": 59, "total_steps": 201, "loss": 0.815, "lr": 8.94005376803361e-06, "epoch": 0.8762376237623762, "percentage": 29.35, "elapsed_time": "0:12:18", "remaining_time": "0:29:36"}
+{"current_steps": 60, "total_steps": 201, "loss": 0.8033, "lr": 8.885729807284855e-06, "epoch": 0.8910891089108911, "percentage": 29.85, "elapsed_time": "0:12:31", "remaining_time": "0:29:25"}
+{"current_steps": 61, "total_steps": 201, "loss": 0.8495, "lr": 8.83022221559489e-06, "epoch": 0.905940594059406, "percentage": 30.35, "elapsed_time": "0:12:43", "remaining_time": "0:29:13"}
+{"current_steps": 62, "total_steps": 201, "loss": 0.7934, "lr": 8.773547901113862e-06, "epoch": 0.9207920792079208, "percentage": 30.85, "elapsed_time": "0:12:56", "remaining_time": "0:29:00"}
+{"current_steps": 63, "total_steps": 201, "loss": 0.8037, "lr": 8.715724127386971e-06, "epoch": 0.9356435643564357, "percentage": 31.34, "elapsed_time": "0:13:09", "remaining_time": "0:28:48"}
+{"current_steps": 64, "total_steps": 201, "loss": 0.8148, "lr": 8.656768508095853e-06, "epoch": 0.9504950495049505, "percentage": 31.84, "elapsed_time": "0:13:22", "remaining_time": "0:28:36"}
+{"current_steps": 65, "total_steps": 201, "loss": 0.8634, "lr": 8.596699001693257e-06, "epoch": 0.9653465346534653, "percentage": 32.34, "elapsed_time": "0:13:33", "remaining_time": "0:28:22"}
+{"current_steps": 66, "total_steps": 201, "loss": 0.8066, "lr": 8.535533905932739e-06, "epoch": 0.9801980198019802, "percentage": 32.84, "elapsed_time": "0:13:48", "remaining_time": "0:28:13"}
+{"current_steps": 67, "total_steps": 201, "loss": 0.7911, "lr": 8.473291852294986e-06, "epoch": 0.995049504950495, "percentage": 33.33, "elapsed_time": "0:14:00", "remaining_time": "0:28:00"}
+{"current_steps": 68, "total_steps": 201, "loss": 1.252, "lr": 8.409991800312493e-06, "epoch": 1.00990099009901, "percentage": 33.83, "elapsed_time": "0:15:17", "remaining_time": "0:29:53"}
+{"current_steps": 69, "total_steps": 201, "loss": 0.8425, "lr": 8.345653031794292e-06, "epoch": 1.0247524752475248, "percentage": 34.33, "elapsed_time": "0:15:30", "remaining_time": "0:29:39"}
+{"current_steps": 70, "total_steps": 201, "loss": 0.6491, "lr": 8.280295144952537e-06, "epoch": 1.0396039603960396, "percentage": 34.83, "elapsed_time": "0:15:38", "remaining_time": "0:29:17"}
+{"current_steps": 71, "total_steps": 201, "loss": 0.7202, "lr": 8.213938048432697e-06, "epoch": 1.0544554455445545, "percentage": 35.32, "elapsed_time": "0:15:51", "remaining_time": "0:29:01"}
+{"current_steps": 72, "total_steps": 201, "loss": 0.741, "lr": 8.146601955249187e-06, "epoch": 1.0693069306930694, "percentage": 35.82, "elapsed_time": "0:16:06", "remaining_time": "0:28:51"}
+{"current_steps": 73, "total_steps": 201, "loss": 0.8075, "lr": 8.078307376628292e-06, "epoch": 1.0841584158415842, "percentage": 36.32, "elapsed_time": "0:16:18", "remaining_time": "0:28:35"}
+{"current_steps": 74, "total_steps": 201, "loss": 0.6919, "lr": 8.009075115760243e-06, "epoch": 1.099009900990099, "percentage": 36.82, "elapsed_time": "0:16:28", "remaining_time": "0:28:16"}
+{"current_steps": 75, "total_steps": 201, "loss": 0.6921, "lr": 7.938926261462366e-06, "epoch": 1.113861386138614, "percentage": 37.31, "elapsed_time": "0:16:41", "remaining_time": "0:28:02"}
+{"current_steps": 76, "total_steps": 201, "loss": 0.7287, "lr": 7.86788218175523e-06, "epoch": 1.1287128712871288, "percentage": 37.81, "elapsed_time": "0:16:52", "remaining_time": "0:27:45"}
+{"current_steps": 77, "total_steps": 201, "loss": 0.8264, "lr": 7.795964517353734e-06, "epoch": 1.1435643564356435, "percentage": 38.31, "elapsed_time": "0:17:06", "remaining_time": "0:27:33"}
+{"current_steps": 78, "total_steps": 201, "loss": 0.6763, "lr": 7.723195175075136e-06, "epoch": 1.1584158415841583, "percentage": 38.81, "elapsed_time": "0:17:17", "remaining_time": "0:27:16"}
+{"current_steps": 79, "total_steps": 201, "loss": 0.7588, "lr": 7.649596321166024e-06, "epoch": 1.1732673267326732, "percentage": 39.3, "elapsed_time": "0:17:33", "remaining_time": "0:27:06"}
+{"current_steps": 80, "total_steps": 201, "loss": 0.7277, "lr": 7.575190374550272e-06, "epoch": 1.188118811881188, "percentage": 39.8, "elapsed_time": "0:17:46", "remaining_time": "0:26:53"}
+{"current_steps": 81, "total_steps": 201, "loss": 0.7174, "lr": 7.500000000000001e-06, "epoch": 1.202970297029703, "percentage": 40.3, "elapsed_time": "0:17:59", "remaining_time": "0:26:39"}
+{"current_steps": 82, "total_steps": 201, "loss": 0.7548, "lr": 7.424048101231687e-06, "epoch": 1.2178217821782178, "percentage": 40.8, "elapsed_time": "0:18:12", "remaining_time": "0:26:25"}
+{"current_steps": 83, "total_steps": 201, "loss": 0.7933, "lr": 7.347357813929455e-06, "epoch": 1.2326732673267327, "percentage": 41.29, "elapsed_time": "0:18:26", "remaining_time": "0:26:12"}
+{"current_steps": 84, "total_steps": 201, "loss": 0.6931, "lr": 7.269952498697734e-06, "epoch": 1.2475247524752475, "percentage": 41.79, "elapsed_time": "0:18:36", "remaining_time": "0:25:55"}
+{"current_steps": 85, "total_steps": 201, "loss": 0.7785, "lr": 7.191855733945388e-06, "epoch": 1.2623762376237624, "percentage": 42.29, "elapsed_time": "0:18:48", "remaining_time": "0:25:39"}
+{"current_steps": 86, "total_steps": 201, "loss": 0.709, "lr": 7.113091308703498e-06, "epoch": 1.2772277227722773, "percentage": 42.79, "elapsed_time": "0:18:59", "remaining_time": "0:25:24"}
+{"current_steps": 87, "total_steps": 201, "loss": 0.6866, "lr": 7.033683215379002e-06, "epoch": 1.2920792079207921, "percentage": 43.28, "elapsed_time": "0:19:12", "remaining_time": "0:25:10"}
+{"current_steps": 88, "total_steps": 201, "loss": 0.7576, "lr": 6.953655642446368e-06, "epoch": 1.306930693069307, "percentage": 43.78, "elapsed_time": "0:19:24", "remaining_time": "0:24:55"}
+{"current_steps": 89, "total_steps": 201, "loss": 0.7615, "lr": 6.873032967079562e-06, "epoch": 1.3217821782178218, "percentage": 44.28, "elapsed_time": "0:19:40", "remaining_time": "0:24:44"}
+{"current_steps": 90, "total_steps": 201, "loss": 0.7158, "lr": 6.7918397477265e-06, "epoch": 1.3366336633663367, "percentage": 44.78, "elapsed_time": "0:19:52", "remaining_time": "0:24:30"}
+{"current_steps": 91, "total_steps": 201, "loss": 0.8109, "lr": 6.710100716628345e-06, "epoch": 1.3514851485148514, "percentage": 45.27, "elapsed_time": "0:20:07", "remaining_time": "0:24:19"}
+{"current_steps": 92, "total_steps": 201, "loss": 0.6553, "lr": 6.627840772285784e-06, "epoch": 1.3663366336633662, "percentage": 45.77, "elapsed_time": "0:20:20", "remaining_time": "0:24:05"}
+{"current_steps": 93, "total_steps": 201, "loss": 0.7604, "lr": 6.545084971874738e-06, "epoch": 1.381188118811881, "percentage": 46.27, "elapsed_time": "0:20:33", "remaining_time": "0:23:52"}
+{"current_steps": 94, "total_steps": 201, "loss": 0.7548, "lr": 6.461858523613684e-06, "epoch": 1.396039603960396, "percentage": 46.77, "elapsed_time": "0:20:45", "remaining_time": "0:23:38"}
+{"current_steps": 95, "total_steps": 201, "loss": 0.7484, "lr": 6.378186779084996e-06, "epoch": 1.4108910891089108, "percentage": 47.26, "elapsed_time": "0:20:56", "remaining_time": "0:23:22"}
+{"current_steps": 96, "total_steps": 201, "loss": 0.7523, "lr": 6.294095225512604e-06, "epoch": 1.4257425742574257, "percentage": 47.76, "elapsed_time": "0:21:11", "remaining_time": "0:23:10"}
+{"current_steps": 97, "total_steps": 201, "loss": 0.7334, "lr": 6.209609477998339e-06, "epoch": 1.4405940594059405, "percentage": 48.26, "elapsed_time": "0:21:24", "remaining_time": "0:22:56"}
+{"current_steps": 98, "total_steps": 201, "loss": 0.6584, "lr": 6.124755271719326e-06, "epoch": 1.4554455445544554, "percentage": 48.76, "elapsed_time": "0:21:36", "remaining_time": "0:22:42"}
+{"current_steps": 99, "total_steps": 201, "loss": 0.8677, "lr": 6.039558454088796e-06, "epoch": 1.4702970297029703, "percentage": 49.25, "elapsed_time": "0:21:51", "remaining_time": "0:22:31"}
+{"current_steps": 100, "total_steps": 201, "loss": 0.7591, "lr": 5.954044976882725e-06, "epoch": 1.4851485148514851, "percentage": 49.75, "elapsed_time": "0:22:03", "remaining_time": "0:22:16"}
+{"current_steps": 101, "total_steps": 201, "loss": 0.7024, "lr": 5.8682408883346535e-06, "epoch": 1.5, "percentage": 50.25, "elapsed_time": "0:22:14", "remaining_time": "0:22:01"}
+{"current_steps": 102, "total_steps": 201, "loss": 0.7647, "lr": 5.782172325201155e-06, "epoch": 1.5148514851485149, "percentage": 50.75, "elapsed_time": "0:22:28", "remaining_time": "0:21:48"}
+{"current_steps": 103, "total_steps": 201, "loss": 0.746, "lr": 5.695865504800328e-06, "epoch": 1.5297029702970297, "percentage": 51.24, "elapsed_time": "0:22:44", "remaining_time": "0:21:37"}
+{"current_steps": 104, "total_steps": 201, "loss": 0.7653, "lr": 5.609346717025738e-06, "epoch": 1.5445544554455446, "percentage": 51.74, "elapsed_time": "0:22:55", "remaining_time": "0:21:22"}
+{"current_steps": 105, "total_steps": 201, "loss": 0.7284, "lr": 5.522642316338268e-06, "epoch": 1.5594059405940595, "percentage": 52.24, "elapsed_time": "0:23:10", "remaining_time": "0:21:11"}
+{"current_steps": 106, "total_steps": 201, "loss": 0.7081, "lr": 5.435778713738292e-06, "epoch": 1.5742574257425743, "percentage": 52.74, "elapsed_time": "0:23:19", "remaining_time": "0:20:54"}
+{"current_steps": 107, "total_steps": 201, "loss": 0.7653, "lr": 5.348782368720627e-06, "epoch": 1.5891089108910892, "percentage": 53.23, "elapsed_time": "0:23:29", "remaining_time": "0:20:38"}
+{"current_steps": 108, "total_steps": 201, "loss": 0.6936, "lr": 5.2616797812147205e-06, "epoch": 1.603960396039604, "percentage": 53.73, "elapsed_time": "0:23:42", "remaining_time": "0:20:24"}
+{"current_steps": 109, "total_steps": 201, "loss": 0.6781, "lr": 5.174497483512506e-06, "epoch": 1.618811881188119, "percentage": 54.23, "elapsed_time": "0:23:55", "remaining_time": "0:20:11"}
+{"current_steps": 110, "total_steps": 201, "loss": 0.7442, "lr": 5.087262032186418e-06, "epoch": 1.6336633663366338, "percentage": 54.73, "elapsed_time": "0:24:08", "remaining_time": "0:19:58"}
+{"current_steps": 111, "total_steps": 201, "loss": 0.781, "lr": 5e-06, "epoch": 1.6485148514851486, "percentage": 55.22, "elapsed_time": "0:24:20", "remaining_time": "0:19:44"}
+{"current_steps": 112, "total_steps": 201, "loss": 0.6567, "lr": 4.9127379678135825e-06, "epoch": 1.6633663366336635, "percentage": 55.72, "elapsed_time": "0:24:31", "remaining_time": "0:19:29"}
+{"current_steps": 113, "total_steps": 201, "loss": 0.8752, "lr": 4.825502516487497e-06, "epoch": 1.6782178217821784, "percentage": 56.22, "elapsed_time": "0:24:43", "remaining_time": "0:19:15"}
+{"current_steps": 114, "total_steps": 201, "loss": 0.6735, "lr": 4.738320218785281e-06, "epoch": 1.693069306930693, "percentage": 56.72, "elapsed_time": "0:24:58", "remaining_time": "0:19:03"}
+{"current_steps": 115, "total_steps": 201, "loss": 0.6056, "lr": 4.651217631279374e-06, "epoch": 1.7079207920792079, "percentage": 57.21, "elapsed_time": "0:25:06", "remaining_time": "0:18:46"}
+{"current_steps": 116, "total_steps": 201, "loss": 0.7485, "lr": 4.564221286261709e-06, "epoch": 1.7227722772277227, "percentage": 57.71, "elapsed_time": "0:25:17", "remaining_time": "0:18:31"}
+{"current_steps": 117, "total_steps": 201, "loss": 0.7505, "lr": 4.477357683661734e-06, "epoch": 1.7376237623762376, "percentage": 58.21, "elapsed_time": "0:25:28", "remaining_time": "0:18:17"}
+{"current_steps": 118, "total_steps": 201, "loss": 0.7236, "lr": 4.390653282974264e-06, "epoch": 1.7524752475247525, "percentage": 58.71, "elapsed_time": "0:25:40", "remaining_time": "0:18:03"}
+{"current_steps": 119, "total_steps": 201, "loss": 0.7576, "lr": 4.304134495199675e-06, "epoch": 1.7673267326732673, "percentage": 59.2, "elapsed_time": "0:25:56", "remaining_time": "0:17:52"}
+{"current_steps": 120, "total_steps": 201, "loss": 0.6612, "lr": 4.217827674798845e-06, "epoch": 1.7821782178217822, "percentage": 59.7, "elapsed_time": "0:26:10", "remaining_time": "0:17:39"}
+{"current_steps": 121, "total_steps": 201, "loss": 0.8031, "lr": 4.131759111665349e-06, "epoch": 1.797029702970297, "percentage": 60.2, "elapsed_time": "0:26:23", "remaining_time": "0:17:26"}
+{"current_steps": 122, "total_steps": 201, "loss": 0.7083, "lr": 4.045955023117276e-06, "epoch": 1.811881188118812, "percentage": 60.7, "elapsed_time": "0:26:37", "remaining_time": "0:17:14"}
+{"current_steps": 123, "total_steps": 201, "loss": 0.6603, "lr": 3.960441545911205e-06, "epoch": 1.8267326732673266, "percentage": 61.19, "elapsed_time": "0:26:47", "remaining_time": "0:16:59"}
+{"current_steps": 124, "total_steps": 201, "loss": 0.7428, "lr": 3.875244728280676e-06, "epoch": 1.8415841584158414, "percentage": 61.69, "elapsed_time": "0:26:57", "remaining_time": "0:16:44"}
+{"current_steps": 125, "total_steps": 201, "loss": 0.7071, "lr": 3.790390522001662e-06, "epoch": 1.8564356435643563, "percentage": 62.19, "elapsed_time": "0:27:09", "remaining_time": "0:16:30"}
+{"current_steps": 126, "total_steps": 201, "loss": 0.7738, "lr": 3.705904774487396e-06, "epoch": 1.8712871287128712, "percentage": 62.69, "elapsed_time": "0:27:22", "remaining_time": "0:16:17"}
+{"current_steps": 127, "total_steps": 201, "loss": 0.7353, "lr": 3.6218132209150047e-06, "epoch": 1.886138613861386, "percentage": 63.18, "elapsed_time": "0:27:35", "remaining_time": "0:16:04"}
+{"current_steps": 128, "total_steps": 201, "loss": 0.7185, "lr": 3.538141476386317e-06, "epoch": 1.900990099009901, "percentage": 63.68, "elapsed_time": "0:27:47", "remaining_time": "0:15:50"}
+{"current_steps": 129, "total_steps": 201, "loss": 0.696, "lr": 3.4549150281252635e-06, "epoch": 1.9158415841584158, "percentage": 64.18, "elapsed_time": "0:27:56", "remaining_time": "0:15:35"}
+{"current_steps": 130, "total_steps": 201, "loss": 0.7649, "lr": 3.372159227714218e-06, "epoch": 1.9306930693069306, "percentage": 64.68, "elapsed_time": "0:28:09", "remaining_time": "0:15:22"}
+{"current_steps": 131, "total_steps": 201, "loss": 0.7024, "lr": 3.289899283371657e-06, "epoch": 1.9455445544554455, "percentage": 65.17, "elapsed_time": "0:28:20", "remaining_time": "0:15:08"}
+{"current_steps": 132, "total_steps": 201, "loss": 0.823, "lr": 3.2081602522734987e-06, "epoch": 1.9603960396039604, "percentage": 65.67, "elapsed_time": "0:28:33", "remaining_time": "0:14:55"}
+{"current_steps": 133, "total_steps": 201, "loss": 0.7705, "lr": 3.12696703292044e-06, "epoch": 1.9752475247524752, "percentage": 66.17, "elapsed_time": "0:28:49", "remaining_time": "0:14:44"}
+{"current_steps": 134, "total_steps": 201, "loss": 0.7319, "lr": 3.0463443575536324e-06, "epoch": 1.99009900990099, "percentage": 66.67, "elapsed_time": "0:28:59", "remaining_time": "0:14:29"}
+{"current_steps": 135, "total_steps": 201, "loss": 0.9991, "lr": 2.966316784621e-06, "epoch": 2.004950495049505, "percentage": 67.16, "elapsed_time": "0:30:16", "remaining_time": "0:14:47"}
+{"current_steps": 136, "total_steps": 201, "loss": 0.7344, "lr": 2.886908691296504e-06, "epoch": 2.01980198019802, "percentage": 67.66, "elapsed_time": "0:30:25", "remaining_time": "0:14:32"}
+{"current_steps": 137, "total_steps": 201, "loss": 0.6747, "lr": 2.8081442660546126e-06, "epoch": 2.0346534653465347, "percentage": 68.16, "elapsed_time": "0:30:36", "remaining_time": "0:14:17"}
+{"current_steps": 138, "total_steps": 201, "loss": 0.603, "lr": 2.7300475013022666e-06, "epoch": 2.0495049504950495, "percentage": 68.66, "elapsed_time": "0:30:49", "remaining_time": "0:14:04"}
+{"current_steps": 139, "total_steps": 201, "loss": 0.7451, "lr": 2.6526421860705474e-06, "epoch": 2.0643564356435644, "percentage": 69.15, "elapsed_time": "0:31:01", "remaining_time": "0:13:50"}
+{"current_steps": 140, "total_steps": 201, "loss": 0.7037, "lr": 2.5759518987683154e-06, "epoch": 2.0792079207920793, "percentage": 69.65, "elapsed_time": "0:31:14", "remaining_time": "0:13:36"}
+{"current_steps": 141, "total_steps": 201, "loss": 0.6763, "lr": 2.5000000000000015e-06, "epoch": 2.094059405940594, "percentage": 70.15, "elapsed_time": "0:31:28", "remaining_time": "0:13:23"}
+{"current_steps": 142, "total_steps": 201, "loss": 0.6384, "lr": 2.424809625449729e-06, "epoch": 2.108910891089109, "percentage": 70.65, "elapsed_time": "0:31:40", "remaining_time": "0:13:09"}
+{"current_steps": 143, "total_steps": 201, "loss": 0.7545, "lr": 2.3504036788339763e-06, "epoch": 2.123762376237624, "percentage": 71.14, "elapsed_time": "0:31:53", "remaining_time": "0:12:56"}
+{"current_steps": 144, "total_steps": 201, "loss": 0.5474, "lr": 2.2768048249248648e-06, "epoch": 2.1386138613861387, "percentage": 71.64, "elapsed_time": "0:32:01", "remaining_time": "0:12:40"}
+{"current_steps": 145, "total_steps": 201, "loss": 0.6522, "lr": 2.204035482646267e-06, "epoch": 2.1534653465346536, "percentage": 72.14, "elapsed_time": "0:32:13", "remaining_time": "0:12:26"}
+{"current_steps": 146, "total_steps": 201, "loss": 0.6746, "lr": 2.132117818244771e-06, "epoch": 2.1683168316831685, "percentage": 72.64, "elapsed_time": "0:32:26", "remaining_time": "0:12:13"}
+{"current_steps": 147, "total_steps": 201, "loss": 0.6705, "lr": 2.061073738537635e-06, "epoch": 2.1831683168316833, "percentage": 73.13, "elapsed_time": "0:32:39", "remaining_time": "0:11:59"}
+{"current_steps": 148, "total_steps": 201, "loss": 0.7101, "lr": 1.990924884239758e-06, "epoch": 2.198019801980198, "percentage": 73.63, "elapsed_time": "0:32:51", "remaining_time": "0:11:45"}
+{"current_steps": 149, "total_steps": 201, "loss": 0.6503, "lr": 1.9216926233717087e-06, "epoch": 2.212871287128713, "percentage": 74.13, "elapsed_time": "0:33:03", "remaining_time": "0:11:32"}
+{"current_steps": 150, "total_steps": 201, "loss": 0.6597, "lr": 1.8533980447508138e-06, "epoch": 2.227722772277228, "percentage": 74.63, "elapsed_time": "0:33:13", "remaining_time": "0:11:17"}
+{"current_steps": 151, "total_steps": 201, "loss": 0.7937, "lr": 1.7860619515673034e-06, "epoch": 2.2425742574257423, "percentage": 75.12, "elapsed_time": "0:33:27", "remaining_time": "0:11:04"}
+{"current_steps": 152, "total_steps": 201, "loss": 0.574, "lr": 1.7197048550474643e-06, "epoch": 2.2574257425742577, "percentage": 75.62, "elapsed_time": "0:33:37", "remaining_time": "0:10:50"}
+{"current_steps": 153, "total_steps": 201, "loss": 0.6766, "lr": 1.6543469682057105e-06, "epoch": 2.272277227722772, "percentage": 76.12, "elapsed_time": "0:33:49", "remaining_time": "0:10:36"}
+{"current_steps": 154, "total_steps": 201, "loss": 0.7836, "lr": 1.5900081996875083e-06, "epoch": 2.287128712871287, "percentage": 76.62, "elapsed_time": "0:34:04", "remaining_time": "0:10:23"}
+{"current_steps": 155, "total_steps": 201, "loss": 0.5805, "lr": 1.5267081477050132e-06, "epoch": 2.301980198019802, "percentage": 77.11, "elapsed_time": "0:34:14", "remaining_time": "0:10:09"}
+{"current_steps": 156, "total_steps": 201, "loss": 0.6805, "lr": 1.4644660940672628e-06, "epoch": 2.3168316831683167, "percentage": 77.61, "elapsed_time": "0:34:29", "remaining_time": "0:09:57"}
+{"current_steps": 157, "total_steps": 201, "loss": 0.6958, "lr": 1.4033009983067454e-06, "epoch": 2.3316831683168315, "percentage": 78.11, "elapsed_time": "0:34:43", "remaining_time": "0:09:43"}
+{"current_steps": 158, "total_steps": 201, "loss": 0.7157, "lr": 1.3432314919041478e-06, "epoch": 2.3465346534653464, "percentage": 78.61, "elapsed_time": "0:34:56", "remaining_time": "0:09:30"}
+{"current_steps": 159, "total_steps": 201, "loss": 0.6421, "lr": 1.2842758726130283e-06, "epoch": 2.3613861386138613, "percentage": 79.1, "elapsed_time": "0:35:10", "remaining_time": "0:09:17"}
+{"current_steps": 160, "total_steps": 201, "loss": 0.7546, "lr": 1.22645209888614e-06, "epoch": 2.376237623762376, "percentage": 79.6, "elapsed_time": "0:35:21", "remaining_time": "0:09:03"}
+{"current_steps": 161, "total_steps": 201, "loss": 0.7018, "lr": 1.1697777844051105e-06, "epoch": 2.391089108910891, "percentage": 80.1, "elapsed_time": "0:35:34", "remaining_time": "0:08:50"}
+{"current_steps": 162, "total_steps": 201, "loss": 0.639, "lr": 1.1142701927151456e-06, "epoch": 2.405940594059406, "percentage": 80.6, "elapsed_time": "0:35:45", "remaining_time": "0:08:36"}
+{"current_steps": 163, "total_steps": 201, "loss": 0.7345, "lr": 1.0599462319663906e-06, "epoch": 2.4207920792079207, "percentage": 81.09, "elapsed_time": "0:35:57", "remaining_time": "0:08:23"}
+{"current_steps": 164, "total_steps": 201, "loss": 0.6413, "lr": 1.006822449763537e-06, "epoch": 2.4356435643564356, "percentage": 81.59, "elapsed_time": "0:36:07", "remaining_time": "0:08:09"}
+{"current_steps": 165, "total_steps": 201, "loss": 0.6647, "lr": 9.549150281252633e-07, "epoch": 2.4504950495049505, "percentage": 82.09, "elapsed_time": "0:36:22", "remaining_time": "0:07:56"}
+{"current_steps": 166, "total_steps": 201, "loss": 0.7179, "lr": 9.042397785550405e-07, "epoch": 2.4653465346534653, "percentage": 82.59, "elapsed_time": "0:36:35", "remaining_time": "0:07:42"}
+{"current_steps": 167, "total_steps": 201, "loss": 0.6727, "lr": 8.54812137224792e-07, "epoch": 2.48019801980198, "percentage": 83.08, "elapsed_time": "0:36:47", "remaining_time": "0:07:29"}
+{"current_steps": 168, "total_steps": 201, "loss": 0.7016, "lr": 8.066471602728804e-07, "epoch": 2.495049504950495, "percentage": 83.58, "elapsed_time": "0:37:02", "remaining_time": "0:07:16"}
+{"current_steps": 169, "total_steps": 201, "loss": 0.7249, "lr": 7.597595192178702e-07, "epoch": 2.50990099009901, "percentage": 84.08, "elapsed_time": "0:37:14", "remaining_time": "0:07:03"}
+{"current_steps": 170, "total_steps": 201, "loss": 0.6672, "lr": 7.141634964894389e-07, "epoch": 2.5247524752475248, "percentage": 84.58, "elapsed_time": "0:37:28", "remaining_time": "0:06:50"}
+{"current_steps": 171, "total_steps": 201, "loss": 0.6774, "lr": 6.698729810778065e-07, "epoch": 2.5396039603960396, "percentage": 85.07, "elapsed_time": "0:37:41", "remaining_time": "0:06:36"}
+{"current_steps": 172, "total_steps": 201, "loss": 0.679, "lr": 6.269014643030214e-07, "epoch": 2.5544554455445545, "percentage": 85.57, "elapsed_time": "0:37:54", "remaining_time": "0:06:23"}
+{"current_steps": 173, "total_steps": 201, "loss": 0.6947, "lr": 5.852620357053651e-07, "epoch": 2.5693069306930694, "percentage": 86.07, "elapsed_time": "0:38:08", "remaining_time": "0:06:10"}
+{"current_steps": 174, "total_steps": 201, "loss": 0.6292, "lr": 5.449673790581611e-07, "epoch": 2.5841584158415842, "percentage": 86.57, "elapsed_time": "0:38:22", "remaining_time": "0:05:57"}
+{"current_steps": 175, "total_steps": 201, "loss": 0.6521, "lr": 5.06029768504166e-07, "epoch": 2.599009900990099, "percentage": 87.06, "elapsed_time": "0:38:32", "remaining_time": "0:05:43"}
+{"current_steps": 176, "total_steps": 201, "loss": 0.6345, "lr": 4.6846106481675035e-07, "epoch": 2.613861386138614, "percentage": 87.56, "elapsed_time": "0:38:43", "remaining_time": "0:05:30"}
+{"current_steps": 177, "total_steps": 201, "loss": 0.7187, "lr": 4.322727117869951e-07, "epoch": 2.628712871287129, "percentage": 88.06, "elapsed_time": "0:38:56", "remaining_time": "0:05:16"}
+{"current_steps": 178, "total_steps": 201, "loss": 0.6922, "lr": 3.9747573273779816e-07, "epoch": 2.6435643564356437, "percentage": 88.56, "elapsed_time": "0:39:09", "remaining_time": "0:05:03"}
+{"current_steps": 179, "total_steps": 201, "loss": 0.6394, "lr": 3.6408072716606346e-07, "epoch": 2.6584158415841586, "percentage": 89.05, "elapsed_time": "0:39:20", "remaining_time": "0:04:50"}
+{"current_steps": 180, "total_steps": 201, "loss": 0.6555, "lr": 3.320978675139919e-07, "epoch": 2.6732673267326734, "percentage": 89.55, "elapsed_time": "0:39:33", "remaining_time": "0:04:36"}
+{"current_steps": 181, "total_steps": 201, "loss": 0.6621, "lr": 3.015368960704584e-07, "epoch": 2.6881188118811883, "percentage": 90.05, "elapsed_time": "0:39:45", "remaining_time": "0:04:23"}
+{"current_steps": 182, "total_steps": 201, "loss": 0.7285, "lr": 2.724071220034158e-07, "epoch": 2.7029702970297027, "percentage": 90.55, "elapsed_time": "0:39:59", "remaining_time": "0:04:10"}
+{"current_steps": 183, "total_steps": 201, "loss": 0.6426, "lr": 2.447174185242324e-07, "epoch": 2.717821782178218, "percentage": 91.04, "elapsed_time": "0:40:11", "remaining_time": "0:03:57"}
+{"current_steps": 184, "total_steps": 201, "loss": 0.6782, "lr": 2.1847622018482283e-07, "epoch": 2.7326732673267324, "percentage": 91.54, "elapsed_time": "0:40:25", "remaining_time": "0:03:44"}
+{"current_steps": 185, "total_steps": 201, "loss": 0.6326, "lr": 1.9369152030840553e-07, "epoch": 2.7475247524752477, "percentage": 92.04, "elapsed_time": "0:40:35", "remaining_time": "0:03:30"}
+{"current_steps": 186, "total_steps": 201, "loss": 0.7419, "lr": 1.7037086855465902e-07, "epoch": 2.762376237623762, "percentage": 92.54, "elapsed_time": "0:40:53", "remaining_time": "0:03:17"}
+{"current_steps": 187, "total_steps": 201, "loss": 0.6123, "lr": 1.4852136862001766e-07, "epoch": 2.7772277227722775, "percentage": 93.03, "elapsed_time": "0:41:05", "remaining_time": "0:03:04"}
+{"current_steps": 188, "total_steps": 201, "loss": 0.7775, "lr": 1.2814967607382433e-07, "epoch": 2.792079207920792, "percentage": 93.53, "elapsed_time": "0:41:22", "remaining_time": "0:02:51"}
+{"current_steps": 189, "total_steps": 201, "loss": 0.6253, "lr": 1.0926199633097156e-07, "epoch": 2.806930693069307, "percentage": 94.03, "elapsed_time": "0:41:33", "remaining_time": "0:02:38"}
+{"current_steps": 190, "total_steps": 201, "loss": 0.6817, "lr": 9.186408276168012e-08, "epoch": 2.8217821782178216, "percentage": 94.53, "elapsed_time": "0:41:44", "remaining_time": "0:02:25"}
+{"current_steps": 191, "total_steps": 201, "loss": 0.6702, "lr": 7.59612349389599e-08, "epoch": 2.8366336633663365, "percentage": 95.02, "elapsed_time": "0:41:58", "remaining_time": "0:02:11"}
+{"current_steps": 192, "total_steps": 201, "loss": 0.6687, "lr": 6.15582970243117e-08, "epoch": 2.8514851485148514, "percentage": 95.52, "elapsed_time": "0:42:11", "remaining_time": "0:01:58"}
+{"current_steps": 193, "total_steps": 201, "loss": 0.6828, "lr": 4.865965629214819e-08, "epoch": 2.866336633663366, "percentage": 96.02, "elapsed_time": "0:42:24", "remaining_time": "0:01:45"}
+{"current_steps": 194, "total_steps": 201, "loss": 0.6109, "lr": 3.726924179339009e-08, "epoch": 2.881188118811881, "percentage": 96.52, "elapsed_time": "0:42:32", "remaining_time": "0:01:32"}
+{"current_steps": 195, "total_steps": 201, "loss": 0.6467, "lr": 2.7390523158633552e-08, "epoch": 2.896039603960396, "percentage": 97.01, "elapsed_time": "0:42:43", "remaining_time": "0:01:18"}
+{"current_steps": 196, "total_steps": 201, "loss": 0.7169, "lr": 1.9026509541272276e-08, "epoch": 2.910891089108911, "percentage": 97.51, "elapsed_time": "0:42:59", "remaining_time": "0:01:05"}
+{"current_steps": 197, "total_steps": 201, "loss": 0.7351, "lr": 1.2179748700879013e-08, "epoch": 2.9257425742574257, "percentage": 98.01, "elapsed_time": "0:43:11", "remaining_time": "0:00:52"}
+{"current_steps": 198, "total_steps": 201, "loss": 0.6391, "lr": 6.852326227130835e-09, "epoch": 2.9405940594059405, "percentage": 98.51, "elapsed_time": "0:43:26", "remaining_time": "0:00:39"}
+{"current_steps": 199, "total_steps": 201, "loss": 0.6674, "lr": 3.0458649045211897e-09, "epoch": 2.9554455445544554, "percentage": 99.0, "elapsed_time": "0:43:37", "remaining_time": "0:00:26"}
+{"current_steps": 200, "total_steps": 201, "loss": 0.7427, "lr": 7.615242180436521e-10, "epoch": 2.9702970297029703, "percentage": 99.5, "elapsed_time": "0:43:51", "remaining_time": "0:00:13"}
+{"current_steps": 201, "total_steps": 201, "loss": 0.595, "lr": 0.0, "epoch": 2.985148514851485, "percentage": 100.0, "elapsed_time": "0:44:01", "remaining_time": "0:00:00"}
+{"current_steps": 201, "total_steps": 201, "epoch": 2.985148514851485, "percentage": 100.0, "elapsed_time": "0:46:04", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a6acfe6be34c24c6478b23c3554192e0eefbe9437876e43a9647e8de6f1d95
+size 7416