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 sha256:944df0232afcaf4bf5bd860593db89e6728335df953390104a1f97e760cc6cae
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963a59ae34c010ae9320c0210ac90495ae4bc163763ee6c4eba39fdbacfdd7fd
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cee59d8014fb24992e2f17955026f402fcecaa165c32794b1e7548cebd9b7f
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f95203b2f2cbec7706cafb300e11cbf1b828795421ab0b60790f65df3e9173a
+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 +1,189 @@
+{"current_steps": 1, "total_steps": 945, "loss": 1.7821, "lr": 8.421052631578948e-07, "epoch": 0.005278785879247773, "percentage": 0.11, "elapsed_time": "0:03:41", "remaining_time": "2 days, 10:04:03"}
+{"current_steps": 2, "total_steps": 945, "loss": 1.7757, "lr": 1.6842105263157895e-06, "epoch": 0.010557571758495546, "percentage": 0.21, "elapsed_time": "0:06:15", "remaining_time": "2 days, 1:08:01"}
+{"current_steps": 3, "total_steps": 945, "loss": 1.7844, "lr": 2.5263157894736844e-06, "epoch": 0.01583635763774332, "percentage": 0.32, "elapsed_time": "0:08:47", "remaining_time": "1 day, 21:58:11"}
+{"current_steps": 4, "total_steps": 945, "loss": 1.7579, "lr": 3.368421052631579e-06, "epoch": 0.02111514351699109, "percentage": 0.42, "elapsed_time": "0:11:19", "remaining_time": "1 day, 20:23:25"}
+{"current_steps": 5, "total_steps": 945, "loss": 1.7134, "lr": 4.210526315789474e-06, "epoch": 0.026393929396238865, "percentage": 0.53, "elapsed_time": "0:13:49", "remaining_time": "1 day, 19:19:30"}
+{"current_steps": 6, "total_steps": 945, "loss": 1.6629, "lr": 5.052631578947369e-06, "epoch": 0.03167271527548664, "percentage": 0.63, "elapsed_time": "0:16:21", "remaining_time": "1 day, 18:41:22"}
+{"current_steps": 7, "total_steps": 945, "loss": 1.6585, "lr": 5.8947368421052634e-06, "epoch": 0.03695150115473441, "percentage": 0.74, "elapsed_time": "0:18:52", "remaining_time": "1 day, 18:10:06"}
+{"current_steps": 8, "total_steps": 945, "loss": 1.6616, "lr": 6.736842105263158e-06, "epoch": 0.04223028703398218, "percentage": 0.85, "elapsed_time": "0:21:23", "remaining_time": "1 day, 17:46:10"}
+{"current_steps": 9, "total_steps": 945, "loss": 1.6681, "lr": 7.578947368421054e-06, "epoch": 0.047509072913229956, "percentage": 0.95, "elapsed_time": "0:23:54", "remaining_time": "1 day, 17:25:59"}
+{"current_steps": 10, "total_steps": 945, "loss": 1.6635, "lr": 8.421052631578948e-06, "epoch": 0.05278785879247773, "percentage": 1.06, "elapsed_time": "0:26:25", "remaining_time": "1 day, 17:10:27"}
+{"current_steps": 11, "total_steps": 945, "loss": 1.6048, "lr": 9.263157894736842e-06, "epoch": 0.0580666446717255, "percentage": 1.16, "elapsed_time": "0:28:56", "remaining_time": "1 day, 16:57:40"}
+{"current_steps": 12, "total_steps": 945, "loss": 1.5823, "lr": 1.0105263157894738e-05, "epoch": 0.06334543055097328, "percentage": 1.27, "elapsed_time": "0:31:28", "remaining_time": "1 day, 16:47:43"}
+{"current_steps": 13, "total_steps": 945, "loss": 1.5534, "lr": 1.0947368421052633e-05, "epoch": 0.06862421643022105, "percentage": 1.38, "elapsed_time": "0:33:59", "remaining_time": "1 day, 16:37:29"}
+{"current_steps": 14, "total_steps": 945, "loss": 1.5445, "lr": 1.1789473684210527e-05, "epoch": 0.07390300230946882, "percentage": 1.48, "elapsed_time": "0:36:31", "remaining_time": "1 day, 16:28:25"}
+{"current_steps": 15, "total_steps": 945, "loss": 1.5301, "lr": 1.263157894736842e-05, "epoch": 0.0791817881887166, "percentage": 1.59, "elapsed_time": "0:39:01", "remaining_time": "1 day, 16:19:51"}
+{"current_steps": 16, "total_steps": 945, "loss": 1.5004, "lr": 1.3473684210526316e-05, "epoch": 0.08446057406796437, "percentage": 1.69, "elapsed_time": "0:41:33", "remaining_time": "1 day, 16:12:40"}
+{"current_steps": 17, "total_steps": 945, "loss": 1.4781, "lr": 1.4315789473684212e-05, "epoch": 0.08973935994721215, "percentage": 1.8, "elapsed_time": "0:44:03", "remaining_time": "1 day, 16:05:23"}
+{"current_steps": 18, "total_steps": 945, "loss": 1.4884, "lr": 1.5157894736842107e-05, "epoch": 0.09501814582645991, "percentage": 1.9, "elapsed_time": "0:46:34", "remaining_time": "1 day, 15:58:38"}
+{"current_steps": 19, "total_steps": 945, "loss": 1.463, "lr": 1.6000000000000003e-05, "epoch": 0.10029693170570769, "percentage": 2.01, "elapsed_time": "0:49:05", "remaining_time": "1 day, 15:52:22"}
+{"current_steps": 20, "total_steps": 945, "loss": 1.4694, "lr": 1.6842105263157896e-05, "epoch": 0.10557571758495546, "percentage": 2.12, "elapsed_time": "0:51:36", "remaining_time": "1 day, 15:46:35"}
+{"current_steps": 21, "total_steps": 945, "loss": 1.4472, "lr": 1.768421052631579e-05, "epoch": 0.11085450346420324, "percentage": 2.22, "elapsed_time": "0:54:06", "remaining_time": "1 day, 15:40:48"}
+{"current_steps": 22, "total_steps": 945, "loss": 1.4194, "lr": 1.8526315789473684e-05, "epoch": 0.116133289343451, "percentage": 2.33, "elapsed_time": "0:56:37", "remaining_time": "1 day, 15:35:41"}
+{"current_steps": 23, "total_steps": 945, "loss": 1.4259, "lr": 1.936842105263158e-05, "epoch": 0.12141207522269878, "percentage": 2.43, "elapsed_time": "0:59:08", "remaining_time": "1 day, 15:31:04"}
+{"current_steps": 24, "total_steps": 945, "loss": 1.4112, "lr": 2.0210526315789475e-05, "epoch": 0.12669086110194655, "percentage": 2.54, "elapsed_time": "1:01:39", "remaining_time": "1 day, 15:26:07"}
+{"current_steps": 25, "total_steps": 945, "loss": 1.4208, "lr": 2.105263157894737e-05, "epoch": 0.13196964698119432, "percentage": 2.65, "elapsed_time": "1:04:11", "remaining_time": "1 day, 15:22:27"}
+{"current_steps": 26, "total_steps": 945, "loss": 1.4158, "lr": 2.1894736842105266e-05, "epoch": 0.1372484328604421, "percentage": 2.75, "elapsed_time": "1:06:41", "remaining_time": "1 day, 15:17:30"}
+{"current_steps": 27, "total_steps": 945, "loss": 1.4037, "lr": 2.273684210526316e-05, "epoch": 0.14252721873968988, "percentage": 2.86, "elapsed_time": "1:09:12", "remaining_time": "1 day, 15:12:53"}
+{"current_steps": 28, "total_steps": 945, "loss": 1.4024, "lr": 2.3578947368421054e-05, "epoch": 0.14780600461893764, "percentage": 2.96, "elapsed_time": "1:11:43", "remaining_time": "1 day, 15:09:15"}
+{"current_steps": 29, "total_steps": 945, "loss": 1.3998, "lr": 2.442105263157895e-05, "epoch": 0.1530847904981854, "percentage": 3.07, "elapsed_time": "1:14:14", "remaining_time": "1 day, 15:05:00"}
+{"current_steps": 30, "total_steps": 945, "loss": 1.402, "lr": 2.526315789473684e-05, "epoch": 0.1583635763774332, "percentage": 3.17, "elapsed_time": "1:16:45", "remaining_time": "1 day, 15:00:54"}
+{"current_steps": 31, "total_steps": 945, "loss": 1.39, "lr": 2.610526315789474e-05, "epoch": 0.16364236225668097, "percentage": 3.28, "elapsed_time": "1:19:17", "remaining_time": "1 day, 14:57:40"}
+{"current_steps": 32, "total_steps": 945, "loss": 1.3828, "lr": 2.6947368421052632e-05, "epoch": 0.16892114813592873, "percentage": 3.39, "elapsed_time": "1:21:49", "remaining_time": "1 day, 14:54:37"}
+{"current_steps": 33, "total_steps": 945, "loss": 1.3678, "lr": 2.778947368421053e-05, "epoch": 0.1741999340151765, "percentage": 3.49, "elapsed_time": "1:24:20", "remaining_time": "1 day, 14:50:50"}
+{"current_steps": 34, "total_steps": 945, "loss": 1.3535, "lr": 2.8631578947368423e-05, "epoch": 0.1794787198944243, "percentage": 3.6, "elapsed_time": "1:26:51", "remaining_time": "1 day, 14:47:11"}
+{"current_steps": 35, "total_steps": 945, "loss": 1.3837, "lr": 2.9473684210526317e-05, "epoch": 0.18475750577367206, "percentage": 3.7, "elapsed_time": "1:29:21", "remaining_time": "1 day, 14:43:15"}
+{"current_steps": 36, "total_steps": 945, "loss": 1.3722, "lr": 3.0315789473684214e-05, "epoch": 0.19003629165291983, "percentage": 3.81, "elapsed_time": "1:31:52", "remaining_time": "1 day, 14:39:44"}
+{"current_steps": 37, "total_steps": 945, "loss": 1.3686, "lr": 3.1157894736842105e-05, "epoch": 0.1953150775321676, "percentage": 3.92, "elapsed_time": "1:34:22", "remaining_time": "1 day, 14:36:08"}
+{"current_steps": 38, "total_steps": 945, "loss": 1.3671, "lr": 3.2000000000000005e-05, "epoch": 0.20059386341141539, "percentage": 4.02, "elapsed_time": "1:36:52", "remaining_time": "1 day, 14:32:25"}
+{"current_steps": 39, "total_steps": 945, "loss": 1.3735, "lr": 3.28421052631579e-05, "epoch": 0.20587264929066315, "percentage": 4.13, "elapsed_time": "1:39:23", "remaining_time": "1 day, 14:29:00"}
+{"current_steps": 40, "total_steps": 945, "loss": 1.3674, "lr": 3.368421052631579e-05, "epoch": 0.21115143516991092, "percentage": 4.23, "elapsed_time": "1:41:54", "remaining_time": "1 day, 14:25:34"}
+{"current_steps": 41, "total_steps": 945, "loss": 1.3699, "lr": 3.452631578947369e-05, "epoch": 0.21643022104915868, "percentage": 4.34, "elapsed_time": "1:44:24", "remaining_time": "1 day, 14:22:09"}
+{"current_steps": 42, "total_steps": 945, "loss": 1.3518, "lr": 3.536842105263158e-05, "epoch": 0.22170900692840648, "percentage": 4.44, "elapsed_time": "1:46:55", "remaining_time": "1 day, 14:18:45"}
+{"current_steps": 43, "total_steps": 945, "loss": 1.3633, "lr": 3.621052631578948e-05, "epoch": 0.22698779280765424, "percentage": 4.55, "elapsed_time": "1:49:25", "remaining_time": "1 day, 14:15:25"}
+{"current_steps": 44, "total_steps": 945, "loss": 1.3497, "lr": 3.705263157894737e-05, "epoch": 0.232266578686902, "percentage": 4.66, "elapsed_time": "1:51:56", "remaining_time": "1 day, 14:12:14"}
+{"current_steps": 45, "total_steps": 945, "loss": 1.3367, "lr": 3.789473684210526e-05, "epoch": 0.23754536456614977, "percentage": 4.76, "elapsed_time": "1:54:27", "remaining_time": "1 day, 14:09:06"}
+{"current_steps": 46, "total_steps": 945, "loss": 1.3672, "lr": 3.873684210526316e-05, "epoch": 0.24282415044539757, "percentage": 4.87, "elapsed_time": "1:56:58", "remaining_time": "1 day, 14:05:57"}
+{"current_steps": 47, "total_steps": 945, "loss": 1.3534, "lr": 3.9578947368421056e-05, "epoch": 0.24810293632464533, "percentage": 4.97, "elapsed_time": "1:59:29", "remaining_time": "1 day, 14:03:02"}
+{"current_steps": 48, "total_steps": 945, "loss": 1.3559, "lr": 4.042105263157895e-05, "epoch": 0.2533817222038931, "percentage": 5.08, "elapsed_time": "2:02:00", "remaining_time": "1 day, 13:59:58"}
+{"current_steps": 49, "total_steps": 945, "loss": 1.3562, "lr": 4.126315789473685e-05, "epoch": 0.2586605080831409, "percentage": 5.19, "elapsed_time": "2:04:30", "remaining_time": "1 day, 13:56:46"}
+{"current_steps": 50, "total_steps": 945, "loss": 1.3478, "lr": 4.210526315789474e-05, "epoch": 0.26393929396238863, "percentage": 5.29, "elapsed_time": "2:07:01", "remaining_time": "1 day, 13:53:47"}
+{"current_steps": 51, "total_steps": 945, "loss": 1.3425, "lr": 4.294736842105264e-05, "epoch": 0.2692180798416364, "percentage": 5.4, "elapsed_time": "2:09:32", "remaining_time": "1 day, 13:50:51"}
+{"current_steps": 52, "total_steps": 945, "loss": 1.3484, "lr": 4.378947368421053e-05, "epoch": 0.2744968657208842, "percentage": 5.5, "elapsed_time": "2:12:03", "remaining_time": "1 day, 13:47:46"}
+{"current_steps": 53, "total_steps": 945, "loss": 1.3524, "lr": 4.463157894736842e-05, "epoch": 0.27977565160013196, "percentage": 5.61, "elapsed_time": "2:14:33", "remaining_time": "1 day, 13:44:43"}
+{"current_steps": 54, "total_steps": 945, "loss": 1.3375, "lr": 4.547368421052632e-05, "epoch": 0.28505443747937975, "percentage": 5.71, "elapsed_time": "2:17:06", "remaining_time": "1 day, 13:42:09"}
+{"current_steps": 55, "total_steps": 945, "loss": 1.3537, "lr": 4.6315789473684214e-05, "epoch": 0.2903332233586275, "percentage": 5.82, "elapsed_time": "2:19:36", "remaining_time": "1 day, 13:39:08"}
+{"current_steps": 56, "total_steps": 945, "loss": 1.3221, "lr": 4.715789473684211e-05, "epoch": 0.2956120092378753, "percentage": 5.93, "elapsed_time": "2:22:07", "remaining_time": "1 day, 13:36:08"}
+{"current_steps": 57, "total_steps": 945, "loss": 1.3551, "lr": 4.8e-05, "epoch": 0.3008907951171231, "percentage": 6.03, "elapsed_time": "2:24:37", "remaining_time": "1 day, 13:33:10"}
+{"current_steps": 58, "total_steps": 945, "loss": 1.3422, "lr": 4.88421052631579e-05, "epoch": 0.3061695809963708, "percentage": 6.14, "elapsed_time": "2:27:09", "remaining_time": "1 day, 13:30:29"}
+{"current_steps": 59, "total_steps": 945, "loss": 1.3388, "lr": 4.9684210526315796e-05, "epoch": 0.3114483668756186, "percentage": 6.24, "elapsed_time": "2:29:40", "remaining_time": "1 day, 13:27:40"}
+{"current_steps": 60, "total_steps": 945, "loss": 1.3519, "lr": 5.052631578947368e-05, "epoch": 0.3167271527548664, "percentage": 6.35, "elapsed_time": "2:32:11", "remaining_time": "1 day, 13:24:53"}
+{"current_steps": 61, "total_steps": 945, "loss": 1.3285, "lr": 5.136842105263158e-05, "epoch": 0.32200593863411414, "percentage": 6.46, "elapsed_time": "2:34:42", "remaining_time": "1 day, 13:22:05"}
+{"current_steps": 62, "total_steps": 945, "loss": 1.3285, "lr": 5.221052631578948e-05, "epoch": 0.32728472451336194, "percentage": 6.56, "elapsed_time": "2:37:13", "remaining_time": "1 day, 13:19:13"}
+{"current_steps": 63, "total_steps": 945, "loss": 1.3352, "lr": 5.305263157894737e-05, "epoch": 0.3325635103926097, "percentage": 6.67, "elapsed_time": "2:39:44", "remaining_time": "1 day, 13:16:17"}
+{"current_steps": 64, "total_steps": 945, "loss": 1.3303, "lr": 5.3894736842105265e-05, "epoch": 0.33784229627185747, "percentage": 6.77, "elapsed_time": "2:42:14", "remaining_time": "1 day, 13:13:26"}
+{"current_steps": 65, "total_steps": 945, "loss": 1.3568, "lr": 5.4736842105263165e-05, "epoch": 0.34312108215110526, "percentage": 6.88, "elapsed_time": "2:44:45", "remaining_time": "1 day, 13:10:36"}
+{"current_steps": 66, "total_steps": 945, "loss": 1.3578, "lr": 5.557894736842106e-05, "epoch": 0.348399868030353, "percentage": 6.98, "elapsed_time": "2:47:17", "remaining_time": "1 day, 13:08:00"}
+{"current_steps": 67, "total_steps": 945, "loss": 1.362, "lr": 5.642105263157895e-05, "epoch": 0.3536786539096008, "percentage": 7.09, "elapsed_time": "2:49:48", "remaining_time": "1 day, 13:05:15"}
+{"current_steps": 68, "total_steps": 945, "loss": 1.3446, "lr": 5.726315789473685e-05, "epoch": 0.3589574397888486, "percentage": 7.2, "elapsed_time": "2:52:19", "remaining_time": "1 day, 13:02:34"}
+{"current_steps": 69, "total_steps": 945, "loss": 1.3476, "lr": 5.810526315789475e-05, "epoch": 0.3642362256680963, "percentage": 7.3, "elapsed_time": "2:54:50", "remaining_time": "1 day, 12:59:47"}
+{"current_steps": 70, "total_steps": 945, "loss": 1.361, "lr": 5.8947368421052634e-05, "epoch": 0.3695150115473441, "percentage": 7.41, "elapsed_time": "2:57:21", "remaining_time": "1 day, 12:56:55"}
+{"current_steps": 71, "total_steps": 945, "loss": 1.3295, "lr": 5.978947368421053e-05, "epoch": 0.37479379742659186, "percentage": 7.51, "elapsed_time": "2:59:51", "remaining_time": "1 day, 12:54:04"}
+{"current_steps": 72, "total_steps": 945, "loss": 1.3236, "lr": 6.063157894736843e-05, "epoch": 0.38007258330583965, "percentage": 7.62, "elapsed_time": "3:02:22", "remaining_time": "1 day, 12:51:17"}
+{"current_steps": 73, "total_steps": 945, "loss": 1.3282, "lr": 6.147368421052632e-05, "epoch": 0.38535136918508744, "percentage": 7.72, "elapsed_time": "3:04:53", "remaining_time": "1 day, 12:48:34"}
+{"current_steps": 74, "total_steps": 945, "loss": 1.3124, "lr": 6.231578947368421e-05, "epoch": 0.3906301550643352, "percentage": 7.83, "elapsed_time": "3:07:26", "remaining_time": "1 day, 12:46:08"}
+{"current_steps": 75, "total_steps": 945, "loss": 1.3259, "lr": 6.315789473684212e-05, "epoch": 0.395908940943583, "percentage": 7.94, "elapsed_time": "3:09:56", "remaining_time": "1 day, 12:43:18"}
+{"current_steps": 76, "total_steps": 945, "loss": 1.3073, "lr": 6.400000000000001e-05, "epoch": 0.40118772682283077, "percentage": 8.04, "elapsed_time": "3:12:27", "remaining_time": "1 day, 12:40:37"}
+{"current_steps": 77, "total_steps": 945, "loss": 1.332, "lr": 6.484210526315789e-05, "epoch": 0.4064665127020785, "percentage": 8.15, "elapsed_time": "3:14:58", "remaining_time": "1 day, 12:37:49"}
+{"current_steps": 78, "total_steps": 945, "loss": 1.3264, "lr": 6.56842105263158e-05, "epoch": 0.4117452985813263, "percentage": 8.25, "elapsed_time": "3:17:29", "remaining_time": "1 day, 12:35:13"}
+{"current_steps": 79, "total_steps": 945, "loss": 1.3206, "lr": 6.652631578947369e-05, "epoch": 0.41702408446057404, "percentage": 8.36, "elapsed_time": "3:20:00", "remaining_time": "1 day, 12:32:32"}
+{"current_steps": 80, "total_steps": 945, "loss": 1.3233, "lr": 6.736842105263159e-05, "epoch": 0.42230287033982183, "percentage": 8.47, "elapsed_time": "3:22:31", "remaining_time": "1 day, 12:29:48"}
+{"current_steps": 81, "total_steps": 945, "loss": 1.3215, "lr": 6.821052631578948e-05, "epoch": 0.42758165621906963, "percentage": 8.57, "elapsed_time": "3:25:02", "remaining_time": "1 day, 12:27:03"}
+{"current_steps": 82, "total_steps": 945, "loss": 1.3271, "lr": 6.905263157894737e-05, "epoch": 0.43286044209831737, "percentage": 8.68, "elapsed_time": "3:27:32", "remaining_time": "1 day, 12:24:17"}
+{"current_steps": 83, "total_steps": 945, "loss": 1.3262, "lr": 6.989473684210527e-05, "epoch": 0.43813922797756516, "percentage": 8.78, "elapsed_time": "3:30:04", "remaining_time": "1 day, 12:21:43"}
+{"current_steps": 84, "total_steps": 945, "loss": 1.3339, "lr": 7.073684210526316e-05, "epoch": 0.44341801385681295, "percentage": 8.89, "elapsed_time": "3:32:34", "remaining_time": "1 day, 12:18:57"}
+{"current_steps": 85, "total_steps": 945, "loss": 1.3214, "lr": 7.157894736842105e-05, "epoch": 0.4486967997360607, "percentage": 8.99, "elapsed_time": "3:35:05", "remaining_time": "1 day, 12:16:09"}
+{"current_steps": 86, "total_steps": 945, "loss": 1.3166, "lr": 7.242105263157896e-05, "epoch": 0.4539755856153085, "percentage": 9.1, "elapsed_time": "3:37:35", "remaining_time": "1 day, 12:13:26"}
+{"current_steps": 87, "total_steps": 945, "loss": 1.3401, "lr": 7.326315789473684e-05, "epoch": 0.4592543714945563, "percentage": 9.21, "elapsed_time": "3:40:06", "remaining_time": "1 day, 12:10:42"}
+{"current_steps": 88, "total_steps": 945, "loss": 1.3378, "lr": 7.410526315789474e-05, "epoch": 0.464533157373804, "percentage": 9.31, "elapsed_time": "3:42:37", "remaining_time": "1 day, 12:08:01"}
+{"current_steps": 89, "total_steps": 945, "loss": 1.3488, "lr": 7.494736842105264e-05, "epoch": 0.4698119432530518, "percentage": 9.42, "elapsed_time": "3:45:07", "remaining_time": "1 day, 12:05:18"}
+{"current_steps": 90, "total_steps": 945, "loss": 1.3212, "lr": 7.578947368421052e-05, "epoch": 0.47509072913229955, "percentage": 9.52, "elapsed_time": "3:47:38", "remaining_time": "1 day, 12:02:32"}
+{"current_steps": 91, "total_steps": 945, "loss": 1.3339, "lr": 7.663157894736843e-05, "epoch": 0.48036951501154734, "percentage": 9.63, "elapsed_time": "3:50:08", "remaining_time": "1 day, 11:59:47"}
+{"current_steps": 92, "total_steps": 945, "loss": 1.3326, "lr": 7.747368421052633e-05, "epoch": 0.48564830089079514, "percentage": 9.74, "elapsed_time": "3:52:39", "remaining_time": "1 day, 11:57:09"}
+{"current_steps": 93, "total_steps": 945, "loss": 1.3094, "lr": 7.831578947368422e-05, "epoch": 0.4909270867700429, "percentage": 9.84, "elapsed_time": "3:55:10", "remaining_time": "1 day, 11:54:32"}
+{"current_steps": 94, "total_steps": 945, "loss": 1.3337, "lr": 7.915789473684211e-05, "epoch": 0.49620587264929067, "percentage": 9.95, "elapsed_time": "3:57:41", "remaining_time": "1 day, 11:51:51"}
+{"current_steps": 95, "total_steps": 945, "loss": 1.3209, "lr": 8e-05, "epoch": 0.5014846585285384, "percentage": 10.05, "elapsed_time": "4:00:13", "remaining_time": "1 day, 11:49:20"}
+{"current_steps": 96, "total_steps": 945, "loss": 1.3097, "lr": 7.999972679326877e-05, "epoch": 0.5067634444077862, "percentage": 10.16, "elapsed_time": "4:02:44", "remaining_time": "1 day, 11:46:44"}
+{"current_steps": 97, "total_steps": 945, "loss": 1.3255, "lr": 7.999890717680716e-05, "epoch": 0.512042230287034, "percentage": 10.26, "elapsed_time": "4:05:14", "remaining_time": "1 day, 11:43:56"}
+{"current_steps": 98, "total_steps": 945, "loss": 1.322, "lr": 7.999754116181141e-05, "epoch": 0.5173210161662818, "percentage": 10.37, "elapsed_time": "4:07:44", "remaining_time": "1 day, 11:41:14"}
+{"current_steps": 99, "total_steps": 945, "loss": 1.3241, "lr": 7.999562876694173e-05, "epoch": 0.5225998020455296, "percentage": 10.48, "elapsed_time": "4:10:14", "remaining_time": "1 day, 11:38:28"}
+{"current_steps": 100, "total_steps": 945, "loss": 1.2977, "lr": 7.999317001832211e-05, "epoch": 0.5278785879247773, "percentage": 10.58, "elapsed_time": "4:12:45", "remaining_time": "1 day, 11:35:47"}
+{"current_steps": 101, "total_steps": 945, "loss": 1.3131, "lr": 7.999016494953987e-05, "epoch": 0.5331573738040251, "percentage": 10.69, "elapsed_time": "4:15:16", "remaining_time": "1 day, 11:33:09"}
+{"current_steps": 102, "total_steps": 945, "loss": 1.3121, "lr": 7.998661360164525e-05, "epoch": 0.5384361596832729, "percentage": 10.79, "elapsed_time": "4:17:47", "remaining_time": "1 day, 11:30:38"}
+{"current_steps": 103, "total_steps": 945, "loss": 1.3249, "lr": 7.998251602315085e-05, "epoch": 0.5437149455625206, "percentage": 10.9, "elapsed_time": "4:20:19", "remaining_time": "1 day, 11:28:05"}
+{"current_steps": 104, "total_steps": 945, "loss": 1.3059, "lr": 7.997787227003101e-05, "epoch": 0.5489937314417684, "percentage": 11.01, "elapsed_time": "4:22:49", "remaining_time": "1 day, 11:25:21"}
+{"current_steps": 105, "total_steps": 945, "loss": 1.3118, "lr": 7.997268240572093e-05, "epoch": 0.5542725173210161, "percentage": 11.11, "elapsed_time": "4:25:19", "remaining_time": "1 day, 11:22:39"}
+{"current_steps": 106, "total_steps": 945, "loss": 1.3273, "lr": 7.99669465011159e-05, "epoch": 0.5595513032002639, "percentage": 11.22, "elapsed_time": "4:27:50", "remaining_time": "1 day, 11:19:59"}
+{"current_steps": 107, "total_steps": 945, "loss": 1.3228, "lr": 7.996066463457032e-05, "epoch": 0.5648300890795117, "percentage": 11.32, "elapsed_time": "4:30:21", "remaining_time": "1 day, 11:17:24"}
+{"current_steps": 108, "total_steps": 945, "loss": 1.3189, "lr": 7.99538368918966e-05, "epoch": 0.5701088749587595, "percentage": 11.43, "elapsed_time": "4:32:52", "remaining_time": "1 day, 11:14:46"}
+{"current_steps": 109, "total_steps": 945, "loss": 1.316, "lr": 7.9946463366364e-05, "epoch": 0.5753876608380073, "percentage": 11.53, "elapsed_time": "4:35:23", "remaining_time": "1 day, 11:12:07"}
+{"current_steps": 110, "total_steps": 945, "loss": 1.3488, "lr": 7.993854415869737e-05, "epoch": 0.580666446717255, "percentage": 11.64, "elapsed_time": "4:37:53", "remaining_time": "1 day, 11:09:27"}
+{"current_steps": 111, "total_steps": 945, "loss": 1.3186, "lr": 7.993007937707573e-05, "epoch": 0.5859452325965028, "percentage": 11.75, "elapsed_time": "4:40:24", "remaining_time": "1 day, 11:06:50"}
+{"current_steps": 112, "total_steps": 945, "loss": 1.3093, "lr": 7.992106913713087e-05, "epoch": 0.5912240184757506, "percentage": 11.85, "elapsed_time": "4:42:54", "remaining_time": "1 day, 11:04:09"}
+{"current_steps": 113, "total_steps": 945, "loss": 1.3087, "lr": 7.991151356194568e-05, "epoch": 0.5965028043549984, "percentage": 11.96, "elapsed_time": "4:45:25", "remaining_time": "1 day, 11:01:29"}
+{"current_steps": 114, "total_steps": 945, "loss": 1.305, "lr": 7.990141278205255e-05, "epoch": 0.6017815902342462, "percentage": 12.06, "elapsed_time": "4:47:55", "remaining_time": "1 day, 10:58:51"}
+{"current_steps": 115, "total_steps": 945, "loss": 1.3011, "lr": 7.989076693543153e-05, "epoch": 0.607060376113494, "percentage": 12.17, "elapsed_time": "4:50:26", "remaining_time": "1 day, 10:56:15"}
+{"current_steps": 116, "total_steps": 945, "loss": 1.3169, "lr": 7.987957616750845e-05, "epoch": 0.6123391619927416, "percentage": 12.28, "elapsed_time": "4:52:59", "remaining_time": "1 day, 10:53:51"}
+{"current_steps": 117, "total_steps": 945, "loss": 1.3019, "lr": 7.9867840631153e-05, "epoch": 0.6176179478719894, "percentage": 12.38, "elapsed_time": "4:55:31", "remaining_time": "1 day, 10:51:26"}
+{"current_steps": 118, "total_steps": 945, "loss": 1.3218, "lr": 7.985556048667652e-05, "epoch": 0.6228967337512372, "percentage": 12.49, "elapsed_time": "4:58:05", "remaining_time": "1 day, 10:49:07"}
+{"current_steps": 119, "total_steps": 945, "loss": 1.3122, "lr": 7.984273590182992e-05, "epoch": 0.628175519630485, "percentage": 12.59, "elapsed_time": "5:00:37", "remaining_time": "1 day, 10:46:39"}
+{"current_steps": 120, "total_steps": 945, "loss": 1.2886, "lr": 7.982936705180139e-05, "epoch": 0.6334543055097328, "percentage": 12.7, "elapsed_time": "5:03:09", "remaining_time": "1 day, 10:44:11"}
+{"current_steps": 121, "total_steps": 945, "loss": 1.3048, "lr": 7.981545411921387e-05, "epoch": 0.6387330913889805, "percentage": 12.8, "elapsed_time": "5:05:41", "remaining_time": "1 day, 10:41:41"}
+{"current_steps": 122, "total_steps": 945, "loss": 1.3203, "lr": 7.980099729412272e-05, "epoch": 0.6440118772682283, "percentage": 12.91, "elapsed_time": "5:08:16", "remaining_time": "1 day, 10:39:33"}
+{"current_steps": 123, "total_steps": 945, "loss": 1.303, "lr": 7.978599677401304e-05, "epoch": 0.6492906631474761, "percentage": 13.02, "elapsed_time": "5:10:51", "remaining_time": "1 day, 10:37:23"}
+{"current_steps": 124, "total_steps": 945, "loss": 1.3, "lr": 7.977045276379698e-05, "epoch": 0.6545694490267239, "percentage": 13.12, "elapsed_time": "5:13:24", "remaining_time": "1 day, 10:35:01"}
+{"current_steps": 125, "total_steps": 945, "loss": 1.2993, "lr": 7.975436547581096e-05, "epoch": 0.6598482349059717, "percentage": 13.23, "elapsed_time": "5:15:56", "remaining_time": "1 day, 10:32:35"}
+{"current_steps": 126, "total_steps": 945, "loss": 1.2976, "lr": 7.973773512981272e-05, "epoch": 0.6651270207852193, "percentage": 13.33, "elapsed_time": "5:18:28", "remaining_time": "1 day, 10:30:03"}
+{"current_steps": 127, "total_steps": 945, "loss": 1.3096, "lr": 7.972056195297842e-05, "epoch": 0.6704058066644671, "percentage": 13.44, "elapsed_time": "5:20:58", "remaining_time": "1 day, 10:27:24"}
+{"current_steps": 128, "total_steps": 945, "loss": 1.2976, "lr": 7.97028461798994e-05, "epoch": 0.6756845925437149, "percentage": 13.54, "elapsed_time": "5:23:29", "remaining_time": "1 day, 10:24:44"}
+{"current_steps": 129, "total_steps": 945, "loss": 1.3206, "lr": 7.968458805257913e-05, "epoch": 0.6809633784229627, "percentage": 13.65, "elapsed_time": "5:25:59", "remaining_time": "1 day, 10:22:04"}
+{"current_steps": 130, "total_steps": 945, "loss": 1.3084, "lr": 7.966578782042972e-05, "epoch": 0.6862421643022105, "percentage": 13.76, "elapsed_time": "5:28:30", "remaining_time": "1 day, 10:19:27"}
+{"current_steps": 131, "total_steps": 945, "loss": 1.3148, "lr": 7.964644574026869e-05, "epoch": 0.6915209501814583, "percentage": 13.86, "elapsed_time": "5:31:02", "remaining_time": "1 day, 10:17:00"}
+{"current_steps": 132, "total_steps": 945, "loss": 1.3209, "lr": 7.962656207631538e-05, "epoch": 0.696799736060706, "percentage": 13.97, "elapsed_time": "5:33:34", "remaining_time": "1 day, 10:14:28"}
+{"current_steps": 133, "total_steps": 945, "loss": 1.334, "lr": 7.960613710018733e-05, "epoch": 0.7020785219399538, "percentage": 14.07, "elapsed_time": "5:36:05", "remaining_time": "1 day, 10:11:56"}
+{"current_steps": 134, "total_steps": 945, "loss": 1.3034, "lr": 7.958517109089657e-05, "epoch": 0.7073573078192016, "percentage": 14.18, "elapsed_time": "5:38:38", "remaining_time": "1 day, 10:09:31"}
+{"current_steps": 135, "total_steps": 945, "loss": 1.297, "lr": 7.956366433484585e-05, "epoch": 0.7126360936984494, "percentage": 14.29, "elapsed_time": "5:41:10", "remaining_time": "1 day, 10:07:03"}
+{"current_steps": 136, "total_steps": 945, "loss": 1.3061, "lr": 7.954161712582469e-05, "epoch": 0.7179148795776972, "percentage": 14.39, "elapsed_time": "5:43:41", "remaining_time": "1 day, 10:04:27"}
+{"current_steps": 137, "total_steps": 945, "loss": 1.3038, "lr": 7.95190297650054e-05, "epoch": 0.7231936654569449, "percentage": 14.5, "elapsed_time": "5:46:12", "remaining_time": "1 day, 10:01:51"}
+{"current_steps": 138, "total_steps": 945, "loss": 1.3072, "lr": 7.949590256093892e-05, "epoch": 0.7284724513361927, "percentage": 14.6, "elapsed_time": "5:48:43", "remaining_time": "1 day, 9:59:14"}
+{"current_steps": 139, "total_steps": 945, "loss": 1.3112, "lr": 7.947223582955066e-05, "epoch": 0.7337512372154404, "percentage": 14.71, "elapsed_time": "5:51:13", "remaining_time": "1 day, 9:56:35"}
+{"current_steps": 140, "total_steps": 945, "loss": 1.2998, "lr": 7.94480298941361e-05, "epoch": 0.7390300230946882, "percentage": 14.81, "elapsed_time": "5:53:43", "remaining_time": "1 day, 9:53:56"}
+{"current_steps": 141, "total_steps": 945, "loss": 1.3106, "lr": 7.94232850853565e-05, "epoch": 0.744308808973936, "percentage": 14.92, "elapsed_time": "5:56:14", "remaining_time": "1 day, 9:51:20"}
+{"current_steps": 142, "total_steps": 945, "loss": 1.2972, "lr": 7.939800174123426e-05, "epoch": 0.7495875948531837, "percentage": 15.03, "elapsed_time": "5:58:44", "remaining_time": "1 day, 9:48:39"}
+{"current_steps": 143, "total_steps": 945, "loss": 1.3063, "lr": 7.937218020714838e-05, "epoch": 0.7548663807324315, "percentage": 15.13, "elapsed_time": "6:01:14", "remaining_time": "1 day, 9:46:01"}
+{"current_steps": 144, "total_steps": 945, "loss": 1.2949, "lr": 7.934582083582968e-05, "epoch": 0.7601451666116793, "percentage": 15.24, "elapsed_time": "6:03:45", "remaining_time": "1 day, 9:43:24"}
+{"current_steps": 145, "total_steps": 945, "loss": 1.2996, "lr": 7.931892398735608e-05, "epoch": 0.7654239524909271, "percentage": 15.34, "elapsed_time": "6:06:16", "remaining_time": "1 day, 9:40:50"}
+{"current_steps": 146, "total_steps": 945, "loss": 1.2888, "lr": 7.929149002914756e-05, "epoch": 0.7707027383701749, "percentage": 15.45, "elapsed_time": "6:08:46", "remaining_time": "1 day, 9:38:11"}
+{"current_steps": 147, "total_steps": 945, "loss": 1.3041, "lr": 7.926351933596123e-05, "epoch": 0.7759815242494227, "percentage": 15.56, "elapsed_time": "6:11:17", "remaining_time": "1 day, 9:35:35"}
+{"current_steps": 148, "total_steps": 945, "loss": 1.2864, "lr": 7.923501228988616e-05, "epoch": 0.7812603101286704, "percentage": 15.66, "elapsed_time": "6:13:47", "remaining_time": "1 day, 9:32:57"}
+{"current_steps": 149, "total_steps": 945, "loss": 1.3044, "lr": 7.920596928033819e-05, "epoch": 0.7865390960079182, "percentage": 15.77, "elapsed_time": "6:16:18", "remaining_time": "1 day, 9:30:18"}
+{"current_steps": 150, "total_steps": 945, "loss": 1.2923, "lr": 7.917639070405464e-05, "epoch": 0.791817881887166, "percentage": 15.87, "elapsed_time": "6:18:49", "remaining_time": "1 day, 9:27:46"}
+{"current_steps": 151, "total_steps": 945, "loss": 1.3, "lr": 7.91462769650888e-05, "epoch": 0.7970966677664137, "percentage": 15.98, "elapsed_time": "6:21:19", "remaining_time": "1 day, 9:25:08"}
+{"current_steps": 152, "total_steps": 945, "loss": 1.2881, "lr": 7.911562847480446e-05, "epoch": 0.8023754536456615, "percentage": 16.08, "elapsed_time": "6:23:50", "remaining_time": "1 day, 9:22:31"}
+{"current_steps": 153, "total_steps": 945, "loss": 1.2967, "lr": 7.908444565187034e-05, "epoch": 0.8076542395249092, "percentage": 16.19, "elapsed_time": "6:26:20", "remaining_time": "1 day, 9:19:54"}
+{"current_steps": 154, "total_steps": 945, "loss": 1.2922, "lr": 7.905272892225426e-05, "epoch": 0.812933025404157, "percentage": 16.3, "elapsed_time": "6:28:52", "remaining_time": "1 day, 9:17:26"}
+{"current_steps": 155, "total_steps": 945, "loss": 1.2904, "lr": 7.902047871921748e-05, "epoch": 0.8182118112834048, "percentage": 16.4, "elapsed_time": "6:31:24", "remaining_time": "1 day, 9:14:56"}
+{"current_steps": 156, "total_steps": 945, "loss": 1.2952, "lr": 7.898769548330857e-05, "epoch": 0.8234905971626526, "percentage": 16.51, "elapsed_time": "6:33:55", "remaining_time": "1 day, 9:12:20"}
+{"current_steps": 157, "total_steps": 945, "loss": 1.3084, "lr": 7.895437966235759e-05, "epoch": 0.8287693830419004, "percentage": 16.61, "elapsed_time": "6:36:25", "remaining_time": "1 day, 9:09:41"}
+{"current_steps": 158, "total_steps": 945, "loss": 1.3145, "lr": 7.892053171146988e-05, "epoch": 0.8340481689211481, "percentage": 16.72, "elapsed_time": "6:38:56", "remaining_time": "1 day, 9:07:07"}
+{"current_steps": 159, "total_steps": 945, "loss": 1.2995, "lr": 7.888615209301981e-05, "epoch": 0.8393269548003959, "percentage": 16.83, "elapsed_time": "6:41:27", "remaining_time": "1 day, 9:04:34"}
+{"current_steps": 160, "total_steps": 945, "loss": 1.2914, "lr": 7.885124127664456e-05, "epoch": 0.8446057406796437, "percentage": 16.93, "elapsed_time": "6:43:58", "remaining_time": "1 day, 9:01:59"}
+{"current_steps": 161, "total_steps": 945, "loss": 1.2995, "lr": 7.881579973923763e-05, "epoch": 0.8498845265588915, "percentage": 17.04, "elapsed_time": "6:46:29", "remaining_time": "1 day, 8:59:25"}
+{"current_steps": 162, "total_steps": 945, "loss": 1.3144, "lr": 7.877982796494235e-05, "epoch": 0.8551633124381393, "percentage": 17.14, "elapsed_time": "6:49:00", "remaining_time": "1 day, 8:56:53"}
+{"current_steps": 163, "total_steps": 945, "loss": 1.2899, "lr": 7.874332644514525e-05, "epoch": 0.860442098317387, "percentage": 17.25, "elapsed_time": "6:51:30", "remaining_time": "1 day, 8:54:16"}
+{"current_steps": 164, "total_steps": 945, "loss": 1.2922, "lr": 7.87062956784694e-05, "epoch": 0.8657208841966347, "percentage": 17.35, "elapsed_time": "6:54:01", "remaining_time": "1 day, 8:51:39"}
+{"current_steps": 165, "total_steps": 945, "loss": 1.3035, "lr": 7.86687361707675e-05, "epoch": 0.8709996700758825, "percentage": 17.46, "elapsed_time": "6:56:32", "remaining_time": "1 day, 8:49:06"}
+{"current_steps": 166, "total_steps": 945, "loss": 1.297, "lr": 7.86306484351151e-05, "epoch": 0.8762784559551303, "percentage": 17.57, "elapsed_time": "6:59:03", "remaining_time": "1 day, 8:46:33"}
+{"current_steps": 167, "total_steps": 945, "loss": 1.304, "lr": 7.859203299180347e-05, "epoch": 0.8815572418343781, "percentage": 17.67, "elapsed_time": "7:01:35", "remaining_time": "1 day, 8:44:04"}
+{"current_steps": 168, "total_steps": 945, "loss": 1.2896, "lr": 7.855289036833259e-05, "epoch": 0.8868360277136259, "percentage": 17.78, "elapsed_time": "7:04:07", "remaining_time": "1 day, 8:41:35"}
+{"current_steps": 169, "total_steps": 945, "loss": 1.296, "lr": 7.851322109940383e-05, "epoch": 0.8921148135928736, "percentage": 17.88, "elapsed_time": "7:06:40", "remaining_time": "1 day, 8:39:09"}
+{"current_steps": 170, "total_steps": 945, "loss": 1.2761, "lr": 7.847302572691277e-05, "epoch": 0.8973935994721214, "percentage": 17.99, "elapsed_time": "7:09:11", "remaining_time": "1 day, 8:36:35"}
+{"current_steps": 171, "total_steps": 945, "loss": 1.2824, "lr": 7.843230479994173e-05, "epoch": 0.9026723853513692, "percentage": 18.1, "elapsed_time": "7:11:42", "remaining_time": "1 day, 8:34:03"}
+{"current_steps": 172, "total_steps": 945, "loss": 1.2932, "lr": 7.839105887475228e-05, "epoch": 0.907951171230617, "percentage": 18.2, "elapsed_time": "7:14:14", "remaining_time": "1 day, 8:31:33"}
+{"current_steps": 173, "total_steps": 945, "loss": 1.2885, "lr": 7.834928851477764e-05, "epoch": 0.9132299571098648, "percentage": 18.31, "elapsed_time": "7:16:45", "remaining_time": "1 day, 8:29:00"}
+{"current_steps": 174, "total_steps": 945, "loss": 1.2915, "lr": 7.830699429061498e-05, "epoch": 0.9185087429891126, "percentage": 18.41, "elapsed_time": "7:19:16", "remaining_time": "1 day, 8:26:26"}
+{"current_steps": 175, "total_steps": 945, "loss": 1.302, "lr": 7.826417678001763e-05, "epoch": 0.9237875288683602, "percentage": 18.52, "elapsed_time": "7:21:49", "remaining_time": "1 day, 8:24:00"}
+{"current_steps": 176, "total_steps": 945, "loss": 1.276, "lr": 7.822083656788722e-05, "epoch": 0.929066314747608, "percentage": 18.62, "elapsed_time": "7:24:20", "remaining_time": "1 day, 8:21:29"}
+{"current_steps": 177, "total_steps": 945, "loss": 1.2962, "lr": 7.817697424626562e-05, "epoch": 0.9343451006268558, "percentage": 18.73, "elapsed_time": "7:26:54", "remaining_time": "1 day, 8:19:06"}
+{"current_steps": 178, "total_steps": 945, "loss": 1.2736, "lr": 7.813259041432689e-05, "epoch": 0.9396238865061036, "percentage": 18.84, "elapsed_time": "7:29:27", "remaining_time": "1 day, 8:16:43"}
+{"current_steps": 179, "total_steps": 945, "loss": 1.2915, "lr": 7.808768567836913e-05, "epoch": 0.9449026723853514, "percentage": 18.94, "elapsed_time": "7:31:59", "remaining_time": "1 day, 8:14:15"}
+{"current_steps": 180, "total_steps": 945, "loss": 1.2872, "lr": 7.804226065180615e-05, "epoch": 0.9501814582645991, "percentage": 19.05, "elapsed_time": "7:34:32", "remaining_time": "1 day, 8:11:47"}
+{"current_steps": 181, "total_steps": 945, "loss": 1.2963, "lr": 7.79963159551591e-05, "epoch": 0.9554602441438469, "percentage": 19.15, "elapsed_time": "7:37:05", "remaining_time": "1 day, 8:09:21"}
+{"current_steps": 182, "total_steps": 945, "loss": 1.3129, "lr": 7.794985221604798e-05, "epoch": 0.9607390300230947, "percentage": 19.26, "elapsed_time": "7:39:36", "remaining_time": "1 day, 8:06:49"}
+{"current_steps": 183, "total_steps": 945, "loss": 1.2886, "lr": 7.790287006918311e-05, "epoch": 0.9660178159023425, "percentage": 19.37, "elapsed_time": "7:42:09", "remaining_time": "1 day, 8:04:25"}
+{"current_steps": 184, "total_steps": 945, "loss": 1.3064, "lr": 7.785537015635646e-05, "epoch": 0.9712966017815903, "percentage": 19.47, "elapsed_time": "7:44:42", "remaining_time": "1 day, 8:01:57"}
+{"current_steps": 185, "total_steps": 945, "loss": 1.2782, "lr": 7.78073531264328e-05, "epoch": 0.976575387660838, "percentage": 19.58, "elapsed_time": "7:47:13", "remaining_time": "1 day, 7:59:23"}
+{"current_steps": 186, "total_steps": 945, "loss": 1.2956, "lr": 7.77588196353409e-05, "epoch": 0.9818541735400858, "percentage": 19.68, "elapsed_time": "7:49:44", "remaining_time": "1 day, 7:56:52"}
+{"current_steps": 187, "total_steps": 945, "loss": 1.2648, "lr": 7.770977034606463e-05, "epoch": 0.9871329594193335, "percentage": 19.79, "elapsed_time": "7:52:17", "remaining_time": "1 day, 7:54:24"}
+{"current_steps": 188, "total_steps": 945, "loss": 1.2968, "lr": 7.766020592863375e-05, "epoch": 0.9924117452985813, "percentage": 19.89, "elapsed_time": "7:54:48", "remaining_time": "1 day, 7:51:52"}
+{"current_steps": 189, "total_steps": 945, "loss": 1.2878, "lr": 7.76101270601149e-05, "epoch": 0.9976905311778291, "percentage": 20.0, "elapsed_time": "7:57:20", "remaining_time": "1 day, 7:49:22"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee68c29fd2c6613d5f50d059436949dff9b78cf17b060da3109cd78186b7016e
+size 7224