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 sha256:5a2ca06f2256f97f42266c4a26475172b00214c8b2d4a6a31c07f5fc0346b835
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4640361ca5b1401ad2aaa55a8afb9c6e9b86df0286d83ee86b20ca626a725eb
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2eaadd194fd4f1cf12e964c4fa5616c234fd617d7f86d14602cf282572a814
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f004b44d9a91a43425bb6cd068eae1a2b92e06e6f37bdbccb6ed211fc1b94c59
+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 +1,144 @@
+{"current_steps": 1, "total_steps": 715, "loss": 0.8825, "lr": 1.111111111111111e-06, "epoch": 0.006959547629404089, "percentage": 0.14, "elapsed_time": "0:01:51", "remaining_time": "22:11:25"}
+{"current_steps": 2, "total_steps": 715, "loss": 0.8704, "lr": 2.222222222222222e-06, "epoch": 0.013919095258808177, "percentage": 0.28, "elapsed_time": "0:03:31", "remaining_time": "20:55:00"}
+{"current_steps": 3, "total_steps": 715, "loss": 0.8713, "lr": 3.3333333333333333e-06, "epoch": 0.020878642888212267, "percentage": 0.42, "elapsed_time": "0:05:10", "remaining_time": "20:27:58"}
+{"current_steps": 4, "total_steps": 715, "loss": 0.8598, "lr": 4.444444444444444e-06, "epoch": 0.027838190517616355, "percentage": 0.56, "elapsed_time": "0:06:49", "remaining_time": "20:13:28"}
+{"current_steps": 5, "total_steps": 715, "loss": 0.8172, "lr": 5.555555555555557e-06, "epoch": 0.034797738147020446, "percentage": 0.7, "elapsed_time": "0:08:29", "remaining_time": "20:04:40"}
+{"current_steps": 6, "total_steps": 715, "loss": 0.7532, "lr": 6.666666666666667e-06, "epoch": 0.041757285776424534, "percentage": 0.84, "elapsed_time": "0:10:08", "remaining_time": "19:57:58"}
+{"current_steps": 7, "total_steps": 715, "loss": 0.7557, "lr": 7.77777777777778e-06, "epoch": 0.04871683340582862, "percentage": 0.98, "elapsed_time": "0:11:47", "remaining_time": "19:52:26"}
+{"current_steps": 8, "total_steps": 715, "loss": 0.7655, "lr": 8.888888888888888e-06, "epoch": 0.05567638103523271, "percentage": 1.12, "elapsed_time": "0:13:27", "remaining_time": "19:48:44"}
+{"current_steps": 9, "total_steps": 715, "loss": 0.7274, "lr": 1e-05, "epoch": 0.0626359286646368, "percentage": 1.26, "elapsed_time": "0:15:06", "remaining_time": "19:44:54"}
+{"current_steps": 10, "total_steps": 715, "loss": 0.6947, "lr": 1.1111111111111113e-05, "epoch": 0.06959547629404089, "percentage": 1.4, "elapsed_time": "0:16:45", "remaining_time": "19:41:32"}
+{"current_steps": 11, "total_steps": 715, "loss": 0.6795, "lr": 1.2222222222222224e-05, "epoch": 0.07655502392344497, "percentage": 1.54, "elapsed_time": "0:18:25", "remaining_time": "19:38:46"}
+{"current_steps": 12, "total_steps": 715, "loss": 0.6602, "lr": 1.3333333333333333e-05, "epoch": 0.08351457155284907, "percentage": 1.68, "elapsed_time": "0:20:04", "remaining_time": "19:35:47"}
+{"current_steps": 13, "total_steps": 715, "loss": 0.6394, "lr": 1.4444444444444446e-05, "epoch": 0.09047411918225315, "percentage": 1.82, "elapsed_time": "0:21:44", "remaining_time": "19:33:53"}
+{"current_steps": 14, "total_steps": 715, "loss": 0.6282, "lr": 1.555555555555556e-05, "epoch": 0.09743366681165724, "percentage": 1.96, "elapsed_time": "0:23:23", "remaining_time": "19:31:15"}
+{"current_steps": 15, "total_steps": 715, "loss": 0.6092, "lr": 1.6666666666666667e-05, "epoch": 0.10439321444106132, "percentage": 2.1, "elapsed_time": "0:25:03", "remaining_time": "19:29:05"}
+{"current_steps": 16, "total_steps": 715, "loss": 0.5894, "lr": 1.7777777777777777e-05, "epoch": 0.11135276207046542, "percentage": 2.24, "elapsed_time": "0:26:42", "remaining_time": "19:26:53"}
+{"current_steps": 17, "total_steps": 715, "loss": 0.5968, "lr": 1.888888888888889e-05, "epoch": 0.11831230969986951, "percentage": 2.38, "elapsed_time": "0:28:22", "remaining_time": "19:24:51"}
+{"current_steps": 18, "total_steps": 715, "loss": 0.576, "lr": 2e-05, "epoch": 0.1252718573292736, "percentage": 2.52, "elapsed_time": "0:30:01", "remaining_time": "19:22:36"}
+{"current_steps": 19, "total_steps": 715, "loss": 0.5698, "lr": 2.1111111111111114e-05, "epoch": 0.1322314049586777, "percentage": 2.66, "elapsed_time": "0:31:40", "remaining_time": "19:20:27"}
+{"current_steps": 20, "total_steps": 715, "loss": 0.5588, "lr": 2.2222222222222227e-05, "epoch": 0.13919095258808178, "percentage": 2.8, "elapsed_time": "0:33:20", "remaining_time": "19:18:30"}
+{"current_steps": 21, "total_steps": 715, "loss": 0.5606, "lr": 2.3333333333333336e-05, "epoch": 0.14615050021748585, "percentage": 2.94, "elapsed_time": "0:35:00", "remaining_time": "19:16:41"}
+{"current_steps": 22, "total_steps": 715, "loss": 0.5481, "lr": 2.444444444444445e-05, "epoch": 0.15311004784688995, "percentage": 3.08, "elapsed_time": "0:36:39", "remaining_time": "19:14:55"}
+{"current_steps": 23, "total_steps": 715, "loss": 0.5539, "lr": 2.5555555555555554e-05, "epoch": 0.16006959547629404, "percentage": 3.22, "elapsed_time": "0:38:19", "remaining_time": "19:12:50"}
+{"current_steps": 24, "total_steps": 715, "loss": 0.5501, "lr": 2.6666666666666667e-05, "epoch": 0.16702914310569814, "percentage": 3.36, "elapsed_time": "0:39:58", "remaining_time": "19:10:47"}
+{"current_steps": 25, "total_steps": 715, "loss": 0.5342, "lr": 2.777777777777778e-05, "epoch": 0.17398869073510223, "percentage": 3.5, "elapsed_time": "0:41:37", "remaining_time": "19:08:50"}
+{"current_steps": 26, "total_steps": 715, "loss": 0.5348, "lr": 2.888888888888889e-05, "epoch": 0.1809482383645063, "percentage": 3.64, "elapsed_time": "0:43:16", "remaining_time": "19:06:49"}
+{"current_steps": 27, "total_steps": 715, "loss": 0.5322, "lr": 3.0000000000000004e-05, "epoch": 0.1879077859939104, "percentage": 3.78, "elapsed_time": "0:44:55", "remaining_time": "19:04:51"}
+{"current_steps": 28, "total_steps": 715, "loss": 0.5213, "lr": 3.111111111111112e-05, "epoch": 0.1948673336233145, "percentage": 3.92, "elapsed_time": "0:46:34", "remaining_time": "19:02:55"}
+{"current_steps": 29, "total_steps": 715, "loss": 0.5206, "lr": 3.222222222222223e-05, "epoch": 0.20182688125271858, "percentage": 4.06, "elapsed_time": "0:48:14", "remaining_time": "19:01:02"}
+{"current_steps": 30, "total_steps": 715, "loss": 0.5322, "lr": 3.3333333333333335e-05, "epoch": 0.20878642888212265, "percentage": 4.2, "elapsed_time": "0:49:53", "remaining_time": "18:59:15"}
+{"current_steps": 31, "total_steps": 715, "loss": 0.5176, "lr": 3.444444444444445e-05, "epoch": 0.21574597651152674, "percentage": 4.34, "elapsed_time": "0:51:33", "remaining_time": "18:57:30"}
+{"current_steps": 32, "total_steps": 715, "loss": 0.5187, "lr": 3.555555555555555e-05, "epoch": 0.22270552414093084, "percentage": 4.48, "elapsed_time": "0:53:12", "remaining_time": "18:55:36"}
+{"current_steps": 33, "total_steps": 715, "loss": 0.5206, "lr": 3.6666666666666666e-05, "epoch": 0.22966507177033493, "percentage": 4.62, "elapsed_time": "0:54:51", "remaining_time": "18:53:51"}
+{"current_steps": 34, "total_steps": 715, "loss": 0.5035, "lr": 3.777777777777778e-05, "epoch": 0.23662461939973903, "percentage": 4.76, "elapsed_time": "0:56:31", "remaining_time": "18:51:59"}
+{"current_steps": 35, "total_steps": 715, "loss": 0.5072, "lr": 3.888888888888889e-05, "epoch": 0.2435841670291431, "percentage": 4.9, "elapsed_time": "0:58:10", "remaining_time": "18:50:11"}
+{"current_steps": 36, "total_steps": 715, "loss": 0.5077, "lr": 4e-05, "epoch": 0.2505437146585472, "percentage": 5.03, "elapsed_time": "0:59:49", "remaining_time": "18:48:22"}
+{"current_steps": 37, "total_steps": 715, "loss": 0.5033, "lr": 4.111111111111111e-05, "epoch": 0.2575032622879513, "percentage": 5.17, "elapsed_time": "1:01:28", "remaining_time": "18:46:31"}
+{"current_steps": 38, "total_steps": 715, "loss": 0.5, "lr": 4.222222222222223e-05, "epoch": 0.2644628099173554, "percentage": 5.31, "elapsed_time": "1:03:07", "remaining_time": "18:44:44"}
+{"current_steps": 39, "total_steps": 715, "loss": 0.4947, "lr": 4.3333333333333334e-05, "epoch": 0.2714223575467595, "percentage": 5.45, "elapsed_time": "1:04:47", "remaining_time": "18:42:58"}
+{"current_steps": 40, "total_steps": 715, "loss": 0.5042, "lr": 4.444444444444445e-05, "epoch": 0.27838190517616357, "percentage": 5.59, "elapsed_time": "1:06:26", "remaining_time": "18:41:18"}
+{"current_steps": 41, "total_steps": 715, "loss": 0.4916, "lr": 4.555555555555556e-05, "epoch": 0.28534145280556766, "percentage": 5.73, "elapsed_time": "1:08:06", "remaining_time": "18:39:32"}
+{"current_steps": 42, "total_steps": 715, "loss": 0.496, "lr": 4.666666666666667e-05, "epoch": 0.2923010004349717, "percentage": 5.87, "elapsed_time": "1:09:45", "remaining_time": "18:37:52"}
+{"current_steps": 43, "total_steps": 715, "loss": 0.4885, "lr": 4.777777777777778e-05, "epoch": 0.2992605480643758, "percentage": 6.01, "elapsed_time": "1:11:24", "remaining_time": "18:36:05"}
+{"current_steps": 44, "total_steps": 715, "loss": 0.5005, "lr": 4.88888888888889e-05, "epoch": 0.3062200956937799, "percentage": 6.15, "elapsed_time": "1:13:04", "remaining_time": "18:34:25"}
+{"current_steps": 45, "total_steps": 715, "loss": 0.4892, "lr": 5e-05, "epoch": 0.313179643323184, "percentage": 6.29, "elapsed_time": "1:14:43", "remaining_time": "18:32:39"}
+{"current_steps": 46, "total_steps": 715, "loss": 0.4997, "lr": 5.111111111111111e-05, "epoch": 0.3201391909525881, "percentage": 6.43, "elapsed_time": "1:16:23", "remaining_time": "18:30:53"}
+{"current_steps": 47, "total_steps": 715, "loss": 0.4938, "lr": 5.222222222222223e-05, "epoch": 0.3270987385819922, "percentage": 6.57, "elapsed_time": "1:18:02", "remaining_time": "18:29:09"}
+{"current_steps": 48, "total_steps": 715, "loss": 0.4968, "lr": 5.333333333333333e-05, "epoch": 0.33405828621139627, "percentage": 6.71, "elapsed_time": "1:19:41", "remaining_time": "18:27:24"}
+{"current_steps": 49, "total_steps": 715, "loss": 0.5006, "lr": 5.444444444444445e-05, "epoch": 0.34101783384080037, "percentage": 6.85, "elapsed_time": "1:21:20", "remaining_time": "18:25:38"}
+{"current_steps": 50, "total_steps": 715, "loss": 0.5007, "lr": 5.555555555555556e-05, "epoch": 0.34797738147020446, "percentage": 6.99, "elapsed_time": "1:23:00", "remaining_time": "18:24:06"}
+{"current_steps": 51, "total_steps": 715, "loss": 0.499, "lr": 5.666666666666668e-05, "epoch": 0.3549369290996085, "percentage": 7.13, "elapsed_time": "1:24:40", "remaining_time": "18:22:22"}
+{"current_steps": 52, "total_steps": 715, "loss": 0.4868, "lr": 5.777777777777778e-05, "epoch": 0.3618964767290126, "percentage": 7.27, "elapsed_time": "1:26:19", "remaining_time": "18:20:36"}
+{"current_steps": 53, "total_steps": 715, "loss": 0.4924, "lr": 5.8888888888888896e-05, "epoch": 0.3688560243584167, "percentage": 7.41, "elapsed_time": "1:27:58", "remaining_time": "18:18:56"}
+{"current_steps": 54, "total_steps": 715, "loss": 0.4853, "lr": 6.000000000000001e-05, "epoch": 0.3758155719878208, "percentage": 7.55, "elapsed_time": "1:29:38", "remaining_time": "18:17:12"}
+{"current_steps": 55, "total_steps": 715, "loss": 0.4823, "lr": 6.111111111111111e-05, "epoch": 0.3827751196172249, "percentage": 7.69, "elapsed_time": "1:31:17", "remaining_time": "18:15:28"}
+{"current_steps": 56, "total_steps": 715, "loss": 0.4848, "lr": 6.222222222222223e-05, "epoch": 0.389734667246629, "percentage": 7.83, "elapsed_time": "1:32:56", "remaining_time": "18:13:44"}
+{"current_steps": 57, "total_steps": 715, "loss": 0.494, "lr": 6.333333333333333e-05, "epoch": 0.39669421487603307, "percentage": 7.97, "elapsed_time": "1:34:35", "remaining_time": "18:12:00"}
+{"current_steps": 58, "total_steps": 715, "loss": 0.4825, "lr": 6.444444444444446e-05, "epoch": 0.40365376250543716, "percentage": 8.11, "elapsed_time": "1:36:15", "remaining_time": "18:10:17"}
+{"current_steps": 59, "total_steps": 715, "loss": 0.4691, "lr": 6.555555555555556e-05, "epoch": 0.41061331013484126, "percentage": 8.25, "elapsed_time": "1:37:54", "remaining_time": "18:08:34"}
+{"current_steps": 60, "total_steps": 715, "loss": 0.4815, "lr": 6.666666666666667e-05, "epoch": 0.4175728577642453, "percentage": 8.39, "elapsed_time": "1:39:33", "remaining_time": "18:06:50"}
+{"current_steps": 61, "total_steps": 715, "loss": 0.4943, "lr": 6.777777777777778e-05, "epoch": 0.4245324053936494, "percentage": 8.53, "elapsed_time": "1:41:12", "remaining_time": "18:05:07"}
+{"current_steps": 62, "total_steps": 715, "loss": 0.4871, "lr": 6.88888888888889e-05, "epoch": 0.4314919530230535, "percentage": 8.67, "elapsed_time": "1:42:51", "remaining_time": "18:03:23"}
+{"current_steps": 63, "total_steps": 715, "loss": 0.4855, "lr": 7.000000000000001e-05, "epoch": 0.4384515006524576, "percentage": 8.81, "elapsed_time": "1:44:31", "remaining_time": "18:01:40"}
+{"current_steps": 64, "total_steps": 715, "loss": 0.4877, "lr": 7.11111111111111e-05, "epoch": 0.4454110482818617, "percentage": 8.95, "elapsed_time": "1:46:10", "remaining_time": "17:59:57"}
+{"current_steps": 65, "total_steps": 715, "loss": 0.4795, "lr": 7.222222222222223e-05, "epoch": 0.45237059591126577, "percentage": 9.09, "elapsed_time": "1:47:49", "remaining_time": "17:58:15"}
+{"current_steps": 66, "total_steps": 715, "loss": 0.4815, "lr": 7.333333333333333e-05, "epoch": 0.45933014354066987, "percentage": 9.23, "elapsed_time": "1:49:28", "remaining_time": "17:56:32"}
+{"current_steps": 67, "total_steps": 715, "loss": 0.4711, "lr": 7.444444444444446e-05, "epoch": 0.46628969117007396, "percentage": 9.37, "elapsed_time": "1:51:07", "remaining_time": "17:54:49"}
+{"current_steps": 68, "total_steps": 715, "loss": 0.4823, "lr": 7.555555555555556e-05, "epoch": 0.47324923879947806, "percentage": 9.51, "elapsed_time": "1:52:47", "remaining_time": "17:53:06"}
+{"current_steps": 69, "total_steps": 715, "loss": 0.4769, "lr": 7.666666666666668e-05, "epoch": 0.4802087864288821, "percentage": 9.65, "elapsed_time": "1:54:26", "remaining_time": "17:51:27"}
+{"current_steps": 70, "total_steps": 715, "loss": 0.47, "lr": 7.777777777777778e-05, "epoch": 0.4871683340582862, "percentage": 9.79, "elapsed_time": "1:56:05", "remaining_time": "17:49:45"}
+{"current_steps": 71, "total_steps": 715, "loss": 0.4748, "lr": 7.88888888888889e-05, "epoch": 0.4941278816876903, "percentage": 9.93, "elapsed_time": "1:57:45", "remaining_time": "17:48:02"}
+{"current_steps": 72, "total_steps": 715, "loss": 0.4735, "lr": 8e-05, "epoch": 0.5010874293170944, "percentage": 10.07, "elapsed_time": "1:59:24", "remaining_time": "17:46:24"}
+{"current_steps": 73, "total_steps": 715, "loss": 0.4585, "lr": 7.999952257304926e-05, "epoch": 0.5080469769464985, "percentage": 10.21, "elapsed_time": "2:01:04", "remaining_time": "17:44:43"}
+{"current_steps": 74, "total_steps": 715, "loss": 0.4817, "lr": 7.99980903035939e-05, "epoch": 0.5150065245759026, "percentage": 10.35, "elapsed_time": "2:02:43", "remaining_time": "17:43:01"}
+{"current_steps": 75, "total_steps": 715, "loss": 0.4719, "lr": 7.999570322582408e-05, "epoch": 0.5219660722053067, "percentage": 10.49, "elapsed_time": "2:04:22", "remaining_time": "17:41:18"}
+{"current_steps": 76, "total_steps": 715, "loss": 0.4744, "lr": 7.99923613967226e-05, "epoch": 0.5289256198347108, "percentage": 10.63, "elapsed_time": "2:06:01", "remaining_time": "17:39:40"}
+{"current_steps": 77, "total_steps": 715, "loss": 0.4704, "lr": 7.99880648960634e-05, "epoch": 0.5358851674641149, "percentage": 10.77, "elapsed_time": "2:07:41", "remaining_time": "17:38:02"}
+{"current_steps": 78, "total_steps": 715, "loss": 0.4654, "lr": 7.998281382640975e-05, "epoch": 0.542844715093519, "percentage": 10.91, "elapsed_time": "2:09:21", "remaining_time": "17:36:22"}
+{"current_steps": 79, "total_steps": 715, "loss": 0.475, "lr": 7.997660831311176e-05, "epoch": 0.549804262722923, "percentage": 11.05, "elapsed_time": "2:11:00", "remaining_time": "17:34:41"}
+{"current_steps": 80, "total_steps": 715, "loss": 0.4656, "lr": 7.996944850430339e-05, "epoch": 0.5567638103523271, "percentage": 11.19, "elapsed_time": "2:12:39", "remaining_time": "17:32:59"}
+{"current_steps": 81, "total_steps": 715, "loss": 0.4575, "lr": 7.996133457089894e-05, "epoch": 0.5637233579817312, "percentage": 11.33, "elapsed_time": "2:14:18", "remaining_time": "17:31:17"}
+{"current_steps": 82, "total_steps": 715, "loss": 0.4673, "lr": 7.99522667065889e-05, "epoch": 0.5706829056111353, "percentage": 11.47, "elapsed_time": "2:15:58", "remaining_time": "17:29:36"}
+{"current_steps": 83, "total_steps": 715, "loss": 0.4644, "lr": 7.994224512783544e-05, "epoch": 0.5776424532405393, "percentage": 11.61, "elapsed_time": "2:17:37", "remaining_time": "17:27:54"}
+{"current_steps": 84, "total_steps": 715, "loss": 0.4782, "lr": 7.993127007386715e-05, "epoch": 0.5846020008699434, "percentage": 11.75, "elapsed_time": "2:19:17", "remaining_time": "17:26:19"}
+{"current_steps": 85, "total_steps": 715, "loss": 0.4642, "lr": 7.991934180667333e-05, "epoch": 0.5915615484993475, "percentage": 11.89, "elapsed_time": "2:20:56", "remaining_time": "17:24:38"}
+{"current_steps": 86, "total_steps": 715, "loss": 0.4646, "lr": 7.990646061099782e-05, "epoch": 0.5985210961287516, "percentage": 12.03, "elapsed_time": "2:22:35", "remaining_time": "17:22:56"}
+{"current_steps": 87, "total_steps": 715, "loss": 0.4626, "lr": 7.989262679433211e-05, "epoch": 0.6054806437581557, "percentage": 12.17, "elapsed_time": "2:24:15", "remaining_time": "17:21:18"}
+{"current_steps": 88, "total_steps": 715, "loss": 0.4626, "lr": 7.987784068690804e-05, "epoch": 0.6124401913875598, "percentage": 12.31, "elapsed_time": "2:25:54", "remaining_time": "17:19:37"}
+{"current_steps": 89, "total_steps": 715, "loss": 0.4521, "lr": 7.986210264168991e-05, "epoch": 0.6193997390169639, "percentage": 12.45, "elapsed_time": "2:27:33", "remaining_time": "17:17:55"}
+{"current_steps": 90, "total_steps": 715, "loss": 0.4606, "lr": 7.98454130343661e-05, "epoch": 0.626359286646368, "percentage": 12.59, "elapsed_time": "2:29:13", "remaining_time": "17:16:14"}
+{"current_steps": 91, "total_steps": 715, "loss": 0.4546, "lr": 7.982777226334e-05, "epoch": 0.6333188342757721, "percentage": 12.73, "elapsed_time": "2:30:52", "remaining_time": "17:14:32"}
+{"current_steps": 92, "total_steps": 715, "loss": 0.4526, "lr": 7.980918074972059e-05, "epoch": 0.6402783819051762, "percentage": 12.87, "elapsed_time": "2:32:31", "remaining_time": "17:12:51"}
+{"current_steps": 93, "total_steps": 715, "loss": 0.4514, "lr": 7.978963893731235e-05, "epoch": 0.6472379295345803, "percentage": 13.01, "elapsed_time": "2:34:11", "remaining_time": "17:11:16"}
+{"current_steps": 94, "total_steps": 715, "loss": 0.4656, "lr": 7.976914729260468e-05, "epoch": 0.6541974771639844, "percentage": 13.15, "elapsed_time": "2:35:50", "remaining_time": "17:09:35"}
+{"current_steps": 95, "total_steps": 715, "loss": 0.4539, "lr": 7.974770630476077e-05, "epoch": 0.6611570247933884, "percentage": 13.29, "elapsed_time": "2:37:30", "remaining_time": "17:07:53"}
+{"current_steps": 96, "total_steps": 715, "loss": 0.4522, "lr": 7.972531648560587e-05, "epoch": 0.6681165724227925, "percentage": 13.43, "elapsed_time": "2:39:09", "remaining_time": "17:06:17"}
+{"current_steps": 97, "total_steps": 715, "loss": 0.4623, "lr": 7.970197836961513e-05, "epoch": 0.6750761200521966, "percentage": 13.57, "elapsed_time": "2:40:49", "remaining_time": "17:04:35"}
+{"current_steps": 98, "total_steps": 715, "loss": 0.4559, "lr": 7.967769251390083e-05, "epoch": 0.6820356676816007, "percentage": 13.71, "elapsed_time": "2:42:28", "remaining_time": "17:02:54"}
+{"current_steps": 99, "total_steps": 715, "loss": 0.4626, "lr": 7.96524594981991e-05, "epoch": 0.6889952153110048, "percentage": 13.85, "elapsed_time": "2:44:07", "remaining_time": "17:01:13"}
+{"current_steps": 100, "total_steps": 715, "loss": 0.4569, "lr": 7.9626279924856e-05, "epoch": 0.6959547629404089, "percentage": 13.99, "elapsed_time": "2:45:46", "remaining_time": "16:59:32"}
+{"current_steps": 101, "total_steps": 715, "loss": 0.4515, "lr": 7.959915441881322e-05, "epoch": 0.702914310569813, "percentage": 14.13, "elapsed_time": "2:47:25", "remaining_time": "16:57:51"}
+{"current_steps": 102, "total_steps": 715, "loss": 0.4544, "lr": 7.957108362759316e-05, "epoch": 0.709873858199217, "percentage": 14.27, "elapsed_time": "2:49:05", "remaining_time": "16:56:10"}
+{"current_steps": 103, "total_steps": 715, "loss": 0.4635, "lr": 7.954206822128343e-05, "epoch": 0.7168334058286211, "percentage": 14.41, "elapsed_time": "2:50:44", "remaining_time": "16:54:29"}
+{"current_steps": 104, "total_steps": 715, "loss": 0.465, "lr": 7.951210889252088e-05, "epoch": 0.7237929534580252, "percentage": 14.55, "elapsed_time": "2:52:23", "remaining_time": "16:52:48"}
+{"current_steps": 105, "total_steps": 715, "loss": 0.4487, "lr": 7.948120635647503e-05, "epoch": 0.7307525010874293, "percentage": 14.69, "elapsed_time": "2:54:02", "remaining_time": "16:51:07"}
+{"current_steps": 106, "total_steps": 715, "loss": 0.4523, "lr": 7.944936135083108e-05, "epoch": 0.7377120487168334, "percentage": 14.83, "elapsed_time": "2:55:41", "remaining_time": "16:49:26"}
+{"current_steps": 107, "total_steps": 715, "loss": 0.4575, "lr": 7.941657463577225e-05, "epoch": 0.7446715963462375, "percentage": 14.97, "elapsed_time": "2:57:21", "remaining_time": "16:47:46"}
+{"current_steps": 108, "total_steps": 715, "loss": 0.4498, "lr": 7.938284699396157e-05, "epoch": 0.7516311439756416, "percentage": 15.1, "elapsed_time": "2:59:00", "remaining_time": "16:46:05"}
+{"current_steps": 109, "total_steps": 715, "loss": 0.4549, "lr": 7.934817923052331e-05, "epoch": 0.7585906916050457, "percentage": 15.24, "elapsed_time": "3:00:39", "remaining_time": "16:44:24"}
+{"current_steps": 110, "total_steps": 715, "loss": 0.4504, "lr": 7.931257217302371e-05, "epoch": 0.7655502392344498, "percentage": 15.38, "elapsed_time": "3:02:19", "remaining_time": "16:42:45"}
+{"current_steps": 111, "total_steps": 715, "loss": 0.4477, "lr": 7.927602667145121e-05, "epoch": 0.7725097868638539, "percentage": 15.52, "elapsed_time": "3:03:58", "remaining_time": "16:41:04"}
+{"current_steps": 112, "total_steps": 715, "loss": 0.4484, "lr": 7.923854359819619e-05, "epoch": 0.779469334493258, "percentage": 15.66, "elapsed_time": "3:05:38", "remaining_time": "16:39:27"}
+{"current_steps": 113, "total_steps": 715, "loss": 0.447, "lr": 7.92001238480301e-05, "epoch": 0.786428882122662, "percentage": 15.8, "elapsed_time": "3:07:17", "remaining_time": "16:37:47"}
+{"current_steps": 114, "total_steps": 715, "loss": 0.4513, "lr": 7.916076833808414e-05, "epoch": 0.7933884297520661, "percentage": 15.94, "elapsed_time": "3:08:56", "remaining_time": "16:36:06"}
+{"current_steps": 115, "total_steps": 715, "loss": 0.4427, "lr": 7.91204780078274e-05, "epoch": 0.8003479773814702, "percentage": 16.08, "elapsed_time": "3:10:35", "remaining_time": "16:34:25"}
+{"current_steps": 116, "total_steps": 715, "loss": 0.4554, "lr": 7.907925381904432e-05, "epoch": 0.8073075250108743, "percentage": 16.22, "elapsed_time": "3:12:15", "remaining_time": "16:32:46"}
+{"current_steps": 117, "total_steps": 715, "loss": 0.453, "lr": 7.903709675581185e-05, "epoch": 0.8142670726402784, "percentage": 16.36, "elapsed_time": "3:13:54", "remaining_time": "16:31:05"}
+{"current_steps": 118, "total_steps": 715, "loss": 0.4541, "lr": 7.899400782447591e-05, "epoch": 0.8212266202696825, "percentage": 16.5, "elapsed_time": "3:15:33", "remaining_time": "16:29:25"}
+{"current_steps": 119, "total_steps": 715, "loss": 0.4423, "lr": 7.894998805362737e-05, "epoch": 0.8281861678990866, "percentage": 16.64, "elapsed_time": "3:17:13", "remaining_time": "16:27:44"}
+{"current_steps": 120, "total_steps": 715, "loss": 0.4519, "lr": 7.890503849407742e-05, "epoch": 0.8351457155284906, "percentage": 16.78, "elapsed_time": "3:18:52", "remaining_time": "16:26:04"}
+{"current_steps": 121, "total_steps": 715, "loss": 0.4455, "lr": 7.885916021883268e-05, "epoch": 0.8421052631578947, "percentage": 16.92, "elapsed_time": "3:20:31", "remaining_time": "16:24:25"}
+{"current_steps": 122, "total_steps": 715, "loss": 0.4407, "lr": 7.881235432306936e-05, "epoch": 0.8490648107872988, "percentage": 17.06, "elapsed_time": "3:22:12", "remaining_time": "16:22:51"}
+{"current_steps": 123, "total_steps": 715, "loss": 0.4465, "lr": 7.876462192410727e-05, "epoch": 0.8560243584167029, "percentage": 17.2, "elapsed_time": "3:23:52", "remaining_time": "16:21:14"}
+{"current_steps": 124, "total_steps": 715, "loss": 0.4497, "lr": 7.871596416138312e-05, "epoch": 0.862983906046107, "percentage": 17.34, "elapsed_time": "3:25:32", "remaining_time": "16:19:37"}
+{"current_steps": 125, "total_steps": 715, "loss": 0.4412, "lr": 7.866638219642324e-05, "epoch": 0.8699434536755111, "percentage": 17.48, "elapsed_time": "3:27:11", "remaining_time": "16:17:56"}
+{"current_steps": 126, "total_steps": 715, "loss": 0.4341, "lr": 7.861587721281598e-05, "epoch": 0.8769030013049152, "percentage": 17.62, "elapsed_time": "3:28:50", "remaining_time": "16:16:16"}
+{"current_steps": 127, "total_steps": 715, "loss": 0.4403, "lr": 7.856445041618333e-05, "epoch": 0.8838625489343193, "percentage": 17.76, "elapsed_time": "3:30:29", "remaining_time": "16:14:35"}
+{"current_steps": 128, "total_steps": 715, "loss": 0.45, "lr": 7.851210303415225e-05, "epoch": 0.8908220965637234, "percentage": 17.9, "elapsed_time": "3:32:09", "remaining_time": "16:12:54"}
+{"current_steps": 129, "total_steps": 715, "loss": 0.4371, "lr": 7.845883631632527e-05, "epoch": 0.8977816441931274, "percentage": 18.04, "elapsed_time": "3:33:48", "remaining_time": "16:11:13"}
+{"current_steps": 130, "total_steps": 715, "loss": 0.4342, "lr": 7.840465153425074e-05, "epoch": 0.9047411918225315, "percentage": 18.18, "elapsed_time": "3:35:27", "remaining_time": "16:09:34"}
+{"current_steps": 131, "total_steps": 715, "loss": 0.4393, "lr": 7.83495499813924e-05, "epoch": 0.9117007394519356, "percentage": 18.32, "elapsed_time": "3:37:06", "remaining_time": "16:07:53"}
+{"current_steps": 132, "total_steps": 715, "loss": 0.4378, "lr": 7.829353297309857e-05, "epoch": 0.9186602870813397, "percentage": 18.46, "elapsed_time": "3:38:45", "remaining_time": "16:06:12"}
+{"current_steps": 133, "total_steps": 715, "loss": 0.4419, "lr": 7.823660184657075e-05, "epoch": 0.9256198347107438, "percentage": 18.6, "elapsed_time": "3:40:25", "remaining_time": "16:04:33"}
+{"current_steps": 134, "total_steps": 715, "loss": 0.4442, "lr": 7.817875796083164e-05, "epoch": 0.9325793823401479, "percentage": 18.74, "elapsed_time": "3:42:04", "remaining_time": "16:02:52"}
+{"current_steps": 135, "total_steps": 715, "loss": 0.4448, "lr": 7.812000269669271e-05, "epoch": 0.939538929969552, "percentage": 18.88, "elapsed_time": "3:43:43", "remaining_time": "16:01:12"}
+{"current_steps": 136, "total_steps": 715, "loss": 0.4459, "lr": 7.806033745672132e-05, "epoch": 0.9464984775989561, "percentage": 19.02, "elapsed_time": "3:45:22", "remaining_time": "15:59:31"}
+{"current_steps": 137, "total_steps": 715, "loss": 0.4458, "lr": 7.799976366520714e-05, "epoch": 0.9534580252283602, "percentage": 19.16, "elapsed_time": "3:47:02", "remaining_time": "15:57:51"}
+{"current_steps": 138, "total_steps": 715, "loss": 0.4413, "lr": 7.793828276812819e-05, "epoch": 0.9604175728577642, "percentage": 19.3, "elapsed_time": "3:48:41", "remaining_time": "15:56:11"}
+{"current_steps": 139, "total_steps": 715, "loss": 0.4374, "lr": 7.787589623311635e-05, "epoch": 0.9673771204871683, "percentage": 19.44, "elapsed_time": "3:50:20", "remaining_time": "15:54:30"}
+{"current_steps": 140, "total_steps": 715, "loss": 0.4452, "lr": 7.781260554942226e-05, "epoch": 0.9743366681165724, "percentage": 19.58, "elapsed_time": "3:51:59", "remaining_time": "15:52:50"}
+{"current_steps": 141, "total_steps": 715, "loss": 0.4439, "lr": 7.774841222787983e-05, "epoch": 0.9812962157459765, "percentage": 19.72, "elapsed_time": "3:53:38", "remaining_time": "15:51:10"}
+{"current_steps": 142, "total_steps": 715, "loss": 0.4462, "lr": 7.768331780087017e-05, "epoch": 0.9882557633753806, "percentage": 19.86, "elapsed_time": "3:55:18", "remaining_time": "15:49:29"}
+{"current_steps": 143, "total_steps": 715, "loss": 0.4406, "lr": 7.761732382228494e-05, "epoch": 0.9952153110047847, "percentage": 20.0, "elapsed_time": "3:56:57", "remaining_time": "15:47:49"}
+{"current_steps": 144, "total_steps": 715, "loss": 0.4218, "lr": 7.755043186748936e-05, "epoch": 1.0060896041757286, "percentage": 20.14, "elapsed_time": "4:00:30", "remaining_time": "15:53:41"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac6ffb721c0f93d1b4d77dd2c8e7241399a717d679b284f533fff649f218e0a
+size 7352