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 sha256:15e6ae7a9203190229f73bf004fa1364d956d61bbee9477f9ff34701ca553e99
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8eeb5095d248700696bb8e0c39f16e5492f10d5db3824d7c89e3d48ecb160ec
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e565a252af7c3490cd812b458a25bec2645ac5f56d838e9dbfa6f3aaec203c6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d692f69a1b731bc86511b80458605e797fbae05a3119da5fd96095eedc01dd95
+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 +1,181 @@
+{"current_steps": 1, "total_steps": 895, "loss": 1.2622, "lr": 8.88888888888889e-07, "epoch": 0.005559416261292564, "percentage": 0.11, "elapsed_time": "0:01:55", "remaining_time": "1 day, 4:39:36"}
+{"current_steps": 2, "total_steps": 895, "loss": 1.2714, "lr": 1.777777777777778e-06, "epoch": 0.011118832522585128, "percentage": 0.22, "elapsed_time": "0:03:36", "remaining_time": "1 day, 2:51:46"}
+{"current_steps": 3, "total_steps": 895, "loss": 1.2541, "lr": 2.666666666666667e-06, "epoch": 0.01667824878387769, "percentage": 0.34, "elapsed_time": "0:05:18", "remaining_time": "1 day, 2:17:31"}
+{"current_steps": 4, "total_steps": 895, "loss": 1.258, "lr": 3.555555555555556e-06, "epoch": 0.022237665045170257, "percentage": 0.45, "elapsed_time": "0:07:02", "remaining_time": "1 day, 2:09:19"}
+{"current_steps": 5, "total_steps": 895, "loss": 1.2091, "lr": 4.444444444444444e-06, "epoch": 0.02779708130646282, "percentage": 0.56, "elapsed_time": "0:08:43", "remaining_time": "1 day, 1:54:31"}
+{"current_steps": 6, "total_steps": 895, "loss": 1.1656, "lr": 5.333333333333334e-06, "epoch": 0.03335649756775538, "percentage": 0.67, "elapsed_time": "0:10:27", "remaining_time": "1 day, 1:49:17"}
+{"current_steps": 7, "total_steps": 895, "loss": 1.1705, "lr": 6.222222222222223e-06, "epoch": 0.03891591382904795, "percentage": 0.78, "elapsed_time": "0:12:08", "remaining_time": "1 day, 1:39:31"}
+{"current_steps": 8, "total_steps": 895, "loss": 1.1541, "lr": 7.111111111111112e-06, "epoch": 0.04447533009034051, "percentage": 0.89, "elapsed_time": "0:13:48", "remaining_time": "1 day, 1:31:22"}
+{"current_steps": 9, "total_steps": 895, "loss": 1.1547, "lr": 8.000000000000001e-06, "epoch": 0.05003474635163308, "percentage": 1.01, "elapsed_time": "0:15:29", "remaining_time": "1 day, 1:25:22"}
+{"current_steps": 10, "total_steps": 895, "loss": 1.1347, "lr": 8.888888888888888e-06, "epoch": 0.05559416261292564, "percentage": 1.12, "elapsed_time": "0:17:10", "remaining_time": "1 day, 1:19:51"}
+{"current_steps": 11, "total_steps": 895, "loss": 1.1331, "lr": 9.777777777777779e-06, "epoch": 0.061153578874218205, "percentage": 1.23, "elapsed_time": "0:18:54", "remaining_time": "1 day, 1:19:27"}
+{"current_steps": 12, "total_steps": 895, "loss": 1.117, "lr": 1.0666666666666667e-05, "epoch": 0.06671299513551077, "percentage": 1.34, "elapsed_time": "0:20:35", "remaining_time": "1 day, 1:15:40"}
+{"current_steps": 13, "total_steps": 895, "loss": 1.0767, "lr": 1.1555555555555556e-05, "epoch": 0.07227241139680333, "percentage": 1.45, "elapsed_time": "0:22:20", "remaining_time": "1 day, 1:15:34"}
+{"current_steps": 14, "total_steps": 895, "loss": 1.0591, "lr": 1.2444444444444446e-05, "epoch": 0.0778318276580959, "percentage": 1.56, "elapsed_time": "0:24:00", "remaining_time": "1 day, 1:11:11"}
+{"current_steps": 15, "total_steps": 895, "loss": 1.0411, "lr": 1.3333333333333333e-05, "epoch": 0.08339124391938846, "percentage": 1.68, "elapsed_time": "0:25:41", "remaining_time": "1 day, 1:07:03"}
+{"current_steps": 16, "total_steps": 895, "loss": 1.0206, "lr": 1.4222222222222224e-05, "epoch": 0.08895066018068103, "percentage": 1.79, "elapsed_time": "0:27:22", "remaining_time": "1 day, 1:04:00"}
+{"current_steps": 17, "total_steps": 895, "loss": 1.0078, "lr": 1.5111111111111112e-05, "epoch": 0.0945100764419736, "percentage": 1.9, "elapsed_time": "0:29:04", "remaining_time": "1 day, 1:01:12"}
+{"current_steps": 18, "total_steps": 895, "loss": 0.9897, "lr": 1.6000000000000003e-05, "epoch": 0.10006949270326616, "percentage": 2.01, "elapsed_time": "0:30:45", "remaining_time": "1 day, 0:58:21"}
+{"current_steps": 19, "total_steps": 895, "loss": 0.9982, "lr": 1.688888888888889e-05, "epoch": 0.10562890896455872, "percentage": 2.12, "elapsed_time": "0:32:26", "remaining_time": "1 day, 0:56:04"}
+{"current_steps": 20, "total_steps": 895, "loss": 0.9708, "lr": 1.7777777777777777e-05, "epoch": 0.11118832522585129, "percentage": 2.23, "elapsed_time": "0:34:09", "remaining_time": "1 day, 0:54:40"}
+{"current_steps": 21, "total_steps": 895, "loss": 0.9798, "lr": 1.866666666666667e-05, "epoch": 0.11674774148714386, "percentage": 2.35, "elapsed_time": "0:35:51", "remaining_time": "1 day, 0:52:14"}
+{"current_steps": 22, "total_steps": 895, "loss": 0.9699, "lr": 1.9555555555555557e-05, "epoch": 0.12230715774843641, "percentage": 2.46, "elapsed_time": "0:37:32", "remaining_time": "1 day, 0:49:31"}
+{"current_steps": 23, "total_steps": 895, "loss": 0.9427, "lr": 2.0444444444444446e-05, "epoch": 0.12786657400972898, "percentage": 2.57, "elapsed_time": "0:39:12", "remaining_time": "1 day, 0:46:47"}
+{"current_steps": 24, "total_steps": 895, "loss": 0.9471, "lr": 2.1333333333333335e-05, "epoch": 0.13342599027102153, "percentage": 2.68, "elapsed_time": "0:40:54", "remaining_time": "1 day, 0:44:26"}
+{"current_steps": 25, "total_steps": 895, "loss": 0.9358, "lr": 2.2222222222222227e-05, "epoch": 0.13898540653231412, "percentage": 2.79, "elapsed_time": "0:42:35", "remaining_time": "1 day, 0:42:15"}
+{"current_steps": 26, "total_steps": 895, "loss": 0.9482, "lr": 2.3111111111111112e-05, "epoch": 0.14454482279360667, "percentage": 2.91, "elapsed_time": "0:44:16", "remaining_time": "1 day, 0:39:31"}
+{"current_steps": 27, "total_steps": 895, "loss": 0.9356, "lr": 2.4e-05, "epoch": 0.15010423905489922, "percentage": 3.02, "elapsed_time": "0:45:56", "remaining_time": "1 day, 0:37:05"}
+{"current_steps": 28, "total_steps": 895, "loss": 0.9225, "lr": 2.4888888888888893e-05, "epoch": 0.1556636553161918, "percentage": 3.13, "elapsed_time": "0:47:37", "remaining_time": "1 day, 0:34:48"}
+{"current_steps": 29, "total_steps": 895, "loss": 0.9203, "lr": 2.577777777777778e-05, "epoch": 0.16122307157748436, "percentage": 3.24, "elapsed_time": "0:49:18", "remaining_time": "1 day, 0:32:20"}
+{"current_steps": 30, "total_steps": 895, "loss": 0.927, "lr": 2.6666666666666667e-05, "epoch": 0.16678248783877692, "percentage": 3.35, "elapsed_time": "0:50:59", "remaining_time": "1 day, 0:30:18"}
+{"current_steps": 31, "total_steps": 895, "loss": 0.9089, "lr": 2.755555555555556e-05, "epoch": 0.1723419041000695, "percentage": 3.46, "elapsed_time": "0:52:41", "remaining_time": "1 day, 0:28:21"}
+{"current_steps": 32, "total_steps": 895, "loss": 0.8963, "lr": 2.8444444444444447e-05, "epoch": 0.17790132036136205, "percentage": 3.58, "elapsed_time": "0:54:24", "remaining_time": "1 day, 0:27:28"}
+{"current_steps": 33, "total_steps": 895, "loss": 0.8902, "lr": 2.9333333333333333e-05, "epoch": 0.1834607366226546, "percentage": 3.69, "elapsed_time": "0:56:05", "remaining_time": "1 day, 0:25:23"}
+{"current_steps": 34, "total_steps": 895, "loss": 0.9132, "lr": 3.0222222222222225e-05, "epoch": 0.1890201528839472, "percentage": 3.8, "elapsed_time": "0:57:47", "remaining_time": "1 day, 0:23:18"}
+{"current_steps": 35, "total_steps": 895, "loss": 0.8984, "lr": 3.111111111111112e-05, "epoch": 0.19457956914523974, "percentage": 3.91, "elapsed_time": "0:59:27", "remaining_time": "1 day, 0:21:04"}
+{"current_steps": 36, "total_steps": 895, "loss": 0.9093, "lr": 3.2000000000000005e-05, "epoch": 0.20013898540653233, "percentage": 4.02, "elapsed_time": "1:01:08", "remaining_time": "1 day, 0:19:00"}
+{"current_steps": 37, "total_steps": 895, "loss": 0.9033, "lr": 3.288888888888889e-05, "epoch": 0.20569840166782488, "percentage": 4.13, "elapsed_time": "1:02:51", "remaining_time": "1 day, 0:17:40"}
+{"current_steps": 38, "total_steps": 895, "loss": 0.9143, "lr": 3.377777777777778e-05, "epoch": 0.21125781792911744, "percentage": 4.25, "elapsed_time": "1:04:32", "remaining_time": "1 day, 0:15:45"}
+{"current_steps": 39, "total_steps": 895, "loss": 0.9062, "lr": 3.466666666666667e-05, "epoch": 0.21681723419041002, "percentage": 4.36, "elapsed_time": "1:06:16", "remaining_time": "1 day, 0:14:41"}
+{"current_steps": 40, "total_steps": 895, "loss": 0.897, "lr": 3.555555555555555e-05, "epoch": 0.22237665045170257, "percentage": 4.47, "elapsed_time": "1:07:58", "remaining_time": "1 day, 0:12:54"}
+{"current_steps": 41, "total_steps": 895, "loss": 0.8827, "lr": 3.644444444444445e-05, "epoch": 0.22793606671299513, "percentage": 4.58, "elapsed_time": "1:09:38", "remaining_time": "1 day, 0:10:41"}
+{"current_steps": 42, "total_steps": 895, "loss": 0.8888, "lr": 3.733333333333334e-05, "epoch": 0.2334954829742877, "percentage": 4.69, "elapsed_time": "1:11:20", "remaining_time": "1 day, 0:08:48"}
+{"current_steps": 43, "total_steps": 895, "loss": 0.8797, "lr": 3.8222222222222226e-05, "epoch": 0.23905489923558026, "percentage": 4.8, "elapsed_time": "1:13:01", "remaining_time": "1 day, 0:06:49"}
+{"current_steps": 44, "total_steps": 895, "loss": 0.8739, "lr": 3.9111111111111115e-05, "epoch": 0.24461431549687282, "percentage": 4.92, "elapsed_time": "1:14:43", "remaining_time": "1 day, 0:05:08"}
+{"current_steps": 45, "total_steps": 895, "loss": 0.8806, "lr": 4e-05, "epoch": 0.2501737317581654, "percentage": 5.03, "elapsed_time": "1:16:23", "remaining_time": "1 day, 0:03:04"}
+{"current_steps": 46, "total_steps": 895, "loss": 0.8763, "lr": 4.088888888888889e-05, "epoch": 0.25573314801945796, "percentage": 5.14, "elapsed_time": "1:18:06", "remaining_time": "1 day, 0:01:28"}
+{"current_steps": 47, "total_steps": 895, "loss": 0.8736, "lr": 4.177777777777778e-05, "epoch": 0.26129256428075054, "percentage": 5.25, "elapsed_time": "1:19:47", "remaining_time": "23:59:36"}
+{"current_steps": 48, "total_steps": 895, "loss": 0.8542, "lr": 4.266666666666667e-05, "epoch": 0.26685198054204307, "percentage": 5.36, "elapsed_time": "1:21:28", "remaining_time": "23:57:36"}
+{"current_steps": 49, "total_steps": 895, "loss": 0.8695, "lr": 4.355555555555556e-05, "epoch": 0.27241139680333565, "percentage": 5.47, "elapsed_time": "1:23:09", "remaining_time": "23:55:50"}
+{"current_steps": 50, "total_steps": 895, "loss": 0.8671, "lr": 4.444444444444445e-05, "epoch": 0.27797081306462823, "percentage": 5.59, "elapsed_time": "1:24:51", "remaining_time": "23:54:01"}
+{"current_steps": 51, "total_steps": 895, "loss": 0.8745, "lr": 4.5333333333333335e-05, "epoch": 0.28353022932592076, "percentage": 5.7, "elapsed_time": "1:26:34", "remaining_time": "23:52:35"}
+{"current_steps": 52, "total_steps": 895, "loss": 0.8571, "lr": 4.6222222222222224e-05, "epoch": 0.28908964558721334, "percentage": 5.81, "elapsed_time": "1:28:14", "remaining_time": "23:50:35"}
+{"current_steps": 53, "total_steps": 895, "loss": 0.8766, "lr": 4.711111111111112e-05, "epoch": 0.2946490618485059, "percentage": 5.92, "elapsed_time": "1:29:55", "remaining_time": "23:48:37"}
+{"current_steps": 54, "total_steps": 895, "loss": 0.8775, "lr": 4.8e-05, "epoch": 0.30020847810979845, "percentage": 6.03, "elapsed_time": "1:31:36", "remaining_time": "23:46:42"}
+{"current_steps": 55, "total_steps": 895, "loss": 0.8662, "lr": 4.88888888888889e-05, "epoch": 0.30576789437109103, "percentage": 6.15, "elapsed_time": "1:33:17", "remaining_time": "23:44:51"}
+{"current_steps": 56, "total_steps": 895, "loss": 0.8539, "lr": 4.9777777777777785e-05, "epoch": 0.3113273106323836, "percentage": 6.26, "elapsed_time": "1:34:58", "remaining_time": "23:43:00"}
+{"current_steps": 57, "total_steps": 895, "loss": 0.8798, "lr": 5.066666666666667e-05, "epoch": 0.31688672689367614, "percentage": 6.37, "elapsed_time": "1:36:39", "remaining_time": "23:41:03"}
+{"current_steps": 58, "total_steps": 895, "loss": 0.8634, "lr": 5.155555555555556e-05, "epoch": 0.3224461431549687, "percentage": 6.48, "elapsed_time": "1:38:20", "remaining_time": "23:39:14"}
+{"current_steps": 59, "total_steps": 895, "loss": 0.848, "lr": 5.244444444444445e-05, "epoch": 0.3280055594162613, "percentage": 6.59, "elapsed_time": "1:40:01", "remaining_time": "23:37:18"}
+{"current_steps": 60, "total_steps": 895, "loss": 0.8518, "lr": 5.333333333333333e-05, "epoch": 0.33356497567755383, "percentage": 6.7, "elapsed_time": "1:41:42", "remaining_time": "23:35:29"}
+{"current_steps": 61, "total_steps": 895, "loss": 0.874, "lr": 5.422222222222223e-05, "epoch": 0.3391243919388464, "percentage": 6.82, "elapsed_time": "1:43:23", "remaining_time": "23:33:35"}
+{"current_steps": 62, "total_steps": 895, "loss": 0.8533, "lr": 5.511111111111112e-05, "epoch": 0.344683808200139, "percentage": 6.93, "elapsed_time": "1:45:04", "remaining_time": "23:31:50"}
+{"current_steps": 63, "total_steps": 895, "loss": 0.8874, "lr": 5.6e-05, "epoch": 0.3502432244614315, "percentage": 7.04, "elapsed_time": "1:46:48", "remaining_time": "23:30:27"}
+{"current_steps": 64, "total_steps": 895, "loss": 0.872, "lr": 5.6888888888888895e-05, "epoch": 0.3558026407227241, "percentage": 7.15, "elapsed_time": "1:48:28", "remaining_time": "23:28:34"}
+{"current_steps": 65, "total_steps": 895, "loss": 0.8517, "lr": 5.777777777777778e-05, "epoch": 0.3613620569840167, "percentage": 7.26, "elapsed_time": "1:50:10", "remaining_time": "23:26:49"}
+{"current_steps": 66, "total_steps": 895, "loss": 0.8569, "lr": 5.8666666666666665e-05, "epoch": 0.3669214732453092, "percentage": 7.37, "elapsed_time": "1:51:50", "remaining_time": "23:24:52"}
+{"current_steps": 67, "total_steps": 895, "loss": 0.8616, "lr": 5.955555555555556e-05, "epoch": 0.3724808895066018, "percentage": 7.49, "elapsed_time": "1:53:32", "remaining_time": "23:23:05"}
+{"current_steps": 68, "total_steps": 895, "loss": 0.8543, "lr": 6.044444444444445e-05, "epoch": 0.3780403057678944, "percentage": 7.6, "elapsed_time": "1:55:15", "remaining_time": "23:21:41"}
+{"current_steps": 69, "total_steps": 895, "loss": 0.8446, "lr": 6.133333333333334e-05, "epoch": 0.38359972202918696, "percentage": 7.71, "elapsed_time": "1:56:56", "remaining_time": "23:19:53"}
+{"current_steps": 70, "total_steps": 895, "loss": 0.8576, "lr": 6.222222222222223e-05, "epoch": 0.3891591382904795, "percentage": 7.82, "elapsed_time": "1:58:38", "remaining_time": "23:18:18"}
+{"current_steps": 71, "total_steps": 895, "loss": 0.8563, "lr": 6.311111111111112e-05, "epoch": 0.39471855455177207, "percentage": 7.93, "elapsed_time": "2:00:19", "remaining_time": "23:16:25"}
+{"current_steps": 72, "total_steps": 895, "loss": 0.8426, "lr": 6.400000000000001e-05, "epoch": 0.40027797081306465, "percentage": 8.04, "elapsed_time": "2:02:00", "remaining_time": "23:14:33"}
+{"current_steps": 73, "total_steps": 895, "loss": 0.8531, "lr": 6.488888888888889e-05, "epoch": 0.4058373870743572, "percentage": 8.16, "elapsed_time": "2:03:41", "remaining_time": "23:12:42"}
+{"current_steps": 74, "total_steps": 895, "loss": 0.8441, "lr": 6.577777777777777e-05, "epoch": 0.41139680333564976, "percentage": 8.27, "elapsed_time": "2:05:21", "remaining_time": "23:10:51"}
+{"current_steps": 75, "total_steps": 895, "loss": 0.8496, "lr": 6.666666666666667e-05, "epoch": 0.41695621959694235, "percentage": 8.38, "elapsed_time": "2:07:04", "remaining_time": "23:09:23"}
+{"current_steps": 76, "total_steps": 895, "loss": 0.8517, "lr": 6.755555555555557e-05, "epoch": 0.4225156358582349, "percentage": 8.49, "elapsed_time": "2:08:45", "remaining_time": "23:07:30"}
+{"current_steps": 77, "total_steps": 895, "loss": 0.8621, "lr": 6.844444444444445e-05, "epoch": 0.42807505211952745, "percentage": 8.6, "elapsed_time": "2:10:26", "remaining_time": "23:05:39"}
+{"current_steps": 78, "total_steps": 895, "loss": 0.8535, "lr": 6.933333333333334e-05, "epoch": 0.43363446838082004, "percentage": 8.72, "elapsed_time": "2:12:06", "remaining_time": "23:03:41"}
+{"current_steps": 79, "total_steps": 895, "loss": 0.8534, "lr": 7.022222222222222e-05, "epoch": 0.43919388464211256, "percentage": 8.83, "elapsed_time": "2:13:47", "remaining_time": "23:02:00"}
+{"current_steps": 80, "total_steps": 895, "loss": 0.8475, "lr": 7.11111111111111e-05, "epoch": 0.44475330090340515, "percentage": 8.94, "elapsed_time": "2:15:31", "remaining_time": "23:00:35"}
+{"current_steps": 81, "total_steps": 895, "loss": 0.8557, "lr": 7.2e-05, "epoch": 0.45031271716469773, "percentage": 9.05, "elapsed_time": "2:17:12", "remaining_time": "22:58:52"}
+{"current_steps": 82, "total_steps": 895, "loss": 0.8599, "lr": 7.28888888888889e-05, "epoch": 0.45587213342599026, "percentage": 9.16, "elapsed_time": "2:18:55", "remaining_time": "22:57:20"}
+{"current_steps": 83, "total_steps": 895, "loss": 0.8585, "lr": 7.377777777777779e-05, "epoch": 0.46143154968728284, "percentage": 9.27, "elapsed_time": "2:20:36", "remaining_time": "22:55:38"}
+{"current_steps": 84, "total_steps": 895, "loss": 0.8403, "lr": 7.466666666666667e-05, "epoch": 0.4669909659485754, "percentage": 9.39, "elapsed_time": "2:22:17", "remaining_time": "22:53:51"}
+{"current_steps": 85, "total_steps": 895, "loss": 0.8301, "lr": 7.555555555555556e-05, "epoch": 0.47255038220986795, "percentage": 9.5, "elapsed_time": "2:23:58", "remaining_time": "22:52:04"}
+{"current_steps": 86, "total_steps": 895, "loss": 0.8579, "lr": 7.644444444444445e-05, "epoch": 0.47810979847116053, "percentage": 9.61, "elapsed_time": "2:25:40", "remaining_time": "22:50:23"}
+{"current_steps": 87, "total_steps": 895, "loss": 0.862, "lr": 7.733333333333333e-05, "epoch": 0.4836692147324531, "percentage": 9.72, "elapsed_time": "2:27:21", "remaining_time": "22:48:31"}
+{"current_steps": 88, "total_steps": 895, "loss": 0.8344, "lr": 7.822222222222223e-05, "epoch": 0.48922863099374564, "percentage": 9.83, "elapsed_time": "2:29:02", "remaining_time": "22:46:42"}
+{"current_steps": 89, "total_steps": 895, "loss": 0.8587, "lr": 7.911111111111112e-05, "epoch": 0.4947880472550382, "percentage": 9.94, "elapsed_time": "2:30:42", "remaining_time": "22:44:53"}
+{"current_steps": 90, "total_steps": 895, "loss": 0.868, "lr": 8e-05, "epoch": 0.5003474635163307, "percentage": 10.06, "elapsed_time": "2:32:24", "remaining_time": "22:43:09"}
+{"current_steps": 91, "total_steps": 895, "loss": 0.8533, "lr": 7.999969539471858e-05, "epoch": 0.5059068797776234, "percentage": 10.17, "elapsed_time": "2:34:05", "remaining_time": "22:41:21"}
+{"current_steps": 92, "total_steps": 895, "loss": 0.8452, "lr": 7.999878158351353e-05, "epoch": 0.5114662960389159, "percentage": 10.28, "elapsed_time": "2:35:45", "remaining_time": "22:39:30"}
+{"current_steps": 93, "total_steps": 895, "loss": 0.864, "lr": 7.999725858030245e-05, "epoch": 0.5170257123002084, "percentage": 10.39, "elapsed_time": "2:37:26", "remaining_time": "22:37:40"}
+{"current_steps": 94, "total_steps": 895, "loss": 0.8458, "lr": 7.999512640828105e-05, "epoch": 0.5225851285615011, "percentage": 10.5, "elapsed_time": "2:39:06", "remaining_time": "22:35:51"}
+{"current_steps": 95, "total_steps": 895, "loss": 0.8558, "lr": 7.999238509992291e-05, "epoch": 0.5281445448227936, "percentage": 10.61, "elapsed_time": "2:40:47", "remaining_time": "22:34:02"}
+{"current_steps": 96, "total_steps": 895, "loss": 0.8646, "lr": 7.998903469697887e-05, "epoch": 0.5337039610840861, "percentage": 10.73, "elapsed_time": "2:42:28", "remaining_time": "22:32:13"}
+{"current_steps": 97, "total_steps": 895, "loss": 0.8436, "lr": 7.998507525047644e-05, "epoch": 0.5392633773453788, "percentage": 10.84, "elapsed_time": "2:44:10", "remaining_time": "22:30:37"}
+{"current_steps": 98, "total_steps": 895, "loss": 0.8497, "lr": 7.998050682071902e-05, "epoch": 0.5448227936066713, "percentage": 10.95, "elapsed_time": "2:45:51", "remaining_time": "22:28:51"}
+{"current_steps": 99, "total_steps": 895, "loss": 0.8381, "lr": 7.997532947728505e-05, "epoch": 0.5503822098679638, "percentage": 11.06, "elapsed_time": "2:47:33", "remaining_time": "22:27:15"}
+{"current_steps": 100, "total_steps": 895, "loss": 0.8624, "lr": 7.99695432990268e-05, "epoch": 0.5559416261292565, "percentage": 11.17, "elapsed_time": "2:49:15", "remaining_time": "22:25:37"}
+{"current_steps": 101, "total_steps": 895, "loss": 0.8387, "lr": 7.99631483740693e-05, "epoch": 0.561501042390549, "percentage": 11.28, "elapsed_time": "2:50:57", "remaining_time": "22:23:55"}
+{"current_steps": 102, "total_steps": 895, "loss": 0.845, "lr": 7.995614479980896e-05, "epoch": 0.5670604586518415, "percentage": 11.4, "elapsed_time": "2:52:38", "remaining_time": "22:22:11"}
+{"current_steps": 103, "total_steps": 895, "loss": 0.8377, "lr": 7.994853268291205e-05, "epoch": 0.5726198749131342, "percentage": 11.51, "elapsed_time": "2:54:19", "remaining_time": "22:20:24"}
+{"current_steps": 104, "total_steps": 895, "loss": 0.8435, "lr": 7.994031213931312e-05, "epoch": 0.5781792911744267, "percentage": 11.62, "elapsed_time": "2:56:02", "remaining_time": "22:18:56"}
+{"current_steps": 105, "total_steps": 895, "loss": 0.8447, "lr": 7.993148329421323e-05, "epoch": 0.5837387074357192, "percentage": 11.73, "elapsed_time": "2:57:43", "remaining_time": "22:17:12"}
+{"current_steps": 106, "total_steps": 895, "loss": 0.846, "lr": 7.992204628207802e-05, "epoch": 0.5892981236970118, "percentage": 11.84, "elapsed_time": "2:59:27", "remaining_time": "22:15:48"}
+{"current_steps": 107, "total_steps": 895, "loss": 0.8304, "lr": 7.991200124663568e-05, "epoch": 0.5948575399583044, "percentage": 11.96, "elapsed_time": "3:01:08", "remaining_time": "22:14:01"}
+{"current_steps": 108, "total_steps": 895, "loss": 0.8473, "lr": 7.990134834087473e-05, "epoch": 0.6004169562195969, "percentage": 12.07, "elapsed_time": "3:02:51", "remaining_time": "22:12:28"}
+{"current_steps": 109, "total_steps": 895, "loss": 0.8383, "lr": 7.989008772704177e-05, "epoch": 0.6059763724808895, "percentage": 12.18, "elapsed_time": "3:04:32", "remaining_time": "22:10:47"}
+{"current_steps": 110, "total_steps": 895, "loss": 0.8505, "lr": 7.987821957663889e-05, "epoch": 0.6115357887421821, "percentage": 12.29, "elapsed_time": "3:06:14", "remaining_time": "22:09:07"}
+{"current_steps": 111, "total_steps": 895, "loss": 0.8327, "lr": 7.986574407042118e-05, "epoch": 0.6170952050034746, "percentage": 12.4, "elapsed_time": "3:07:56", "remaining_time": "22:07:24"}
+{"current_steps": 112, "total_steps": 895, "loss": 0.8525, "lr": 7.985266139839389e-05, "epoch": 0.6226546212647672, "percentage": 12.51, "elapsed_time": "3:09:37", "remaining_time": "22:05:43"}
+{"current_steps": 113, "total_steps": 895, "loss": 0.8385, "lr": 7.983897175980957e-05, "epoch": 0.6282140375260598, "percentage": 12.63, "elapsed_time": "3:11:21", "remaining_time": "22:04:16"}
+{"current_steps": 114, "total_steps": 895, "loss": 0.8359, "lr": 7.982467536316502e-05, "epoch": 0.6337734537873523, "percentage": 12.74, "elapsed_time": "3:13:03", "remaining_time": "22:02:37"}
+{"current_steps": 115, "total_steps": 895, "loss": 0.8497, "lr": 7.980977242619814e-05, "epoch": 0.6393328700486449, "percentage": 12.85, "elapsed_time": "3:14:46", "remaining_time": "22:01:06"}
+{"current_steps": 116, "total_steps": 895, "loss": 0.8348, "lr": 7.97942631758846e-05, "epoch": 0.6448922863099374, "percentage": 12.96, "elapsed_time": "3:16:27", "remaining_time": "21:59:22"}
+{"current_steps": 117, "total_steps": 895, "loss": 0.8291, "lr": 7.977814784843438e-05, "epoch": 0.65045170257123, "percentage": 13.07, "elapsed_time": "3:18:08", "remaining_time": "21:57:34"}
+{"current_steps": 118, "total_steps": 895, "loss": 0.837, "lr": 7.976142668928815e-05, "epoch": 0.6560111188325226, "percentage": 13.18, "elapsed_time": "3:19:49", "remaining_time": "21:55:50"}
+{"current_steps": 119, "total_steps": 895, "loss": 0.8284, "lr": 7.97440999531136e-05, "epoch": 0.6615705350938151, "percentage": 13.3, "elapsed_time": "3:21:30", "remaining_time": "21:54:04"}
+{"current_steps": 120, "total_steps": 895, "loss": 0.8498, "lr": 7.972616790380151e-05, "epoch": 0.6671299513551077, "percentage": 13.41, "elapsed_time": "3:23:12", "remaining_time": "21:52:24"}
+{"current_steps": 121, "total_steps": 895, "loss": 0.834, "lr": 7.970763081446172e-05, "epoch": 0.6726893676164003, "percentage": 13.52, "elapsed_time": "3:24:54", "remaining_time": "21:50:45"}
+{"current_steps": 122, "total_steps": 895, "loss": 0.8436, "lr": 7.968848896741896e-05, "epoch": 0.6782487838776928, "percentage": 13.63, "elapsed_time": "3:26:39", "remaining_time": "21:49:20"}
+{"current_steps": 123, "total_steps": 895, "loss": 0.8416, "lr": 7.966874265420866e-05, "epoch": 0.6838082001389854, "percentage": 13.74, "elapsed_time": "3:28:20", "remaining_time": "21:47:38"}
+{"current_steps": 124, "total_steps": 895, "loss": 0.8487, "lr": 7.964839217557237e-05, "epoch": 0.689367616400278, "percentage": 13.85, "elapsed_time": "3:30:01", "remaining_time": "21:45:54"}
+{"current_steps": 125, "total_steps": 895, "loss": 0.8309, "lr": 7.962743784145323e-05, "epoch": 0.6949270326615705, "percentage": 13.97, "elapsed_time": "3:31:42", "remaining_time": "21:44:09"}
+{"current_steps": 126, "total_steps": 895, "loss": 0.8476, "lr": 7.960587997099132e-05, "epoch": 0.700486448922863, "percentage": 14.08, "elapsed_time": "3:33:24", "remaining_time": "21:42:29"}
+{"current_steps": 127, "total_steps": 895, "loss": 0.8167, "lr": 7.958371889251868e-05, "epoch": 0.7060458651841557, "percentage": 14.19, "elapsed_time": "3:35:06", "remaining_time": "21:40:46"}
+{"current_steps": 128, "total_steps": 895, "loss": 0.8273, "lr": 7.956095494355438e-05, "epoch": 0.7116052814454482, "percentage": 14.3, "elapsed_time": "3:36:47", "remaining_time": "21:39:02"}
+{"current_steps": 129, "total_steps": 895, "loss": 0.8438, "lr": 7.95375884707994e-05, "epoch": 0.7171646977067407, "percentage": 14.41, "elapsed_time": "3:38:31", "remaining_time": "21:37:34"}
+{"current_steps": 130, "total_steps": 895, "loss": 0.8377, "lr": 7.951361983013127e-05, "epoch": 0.7227241139680334, "percentage": 14.53, "elapsed_time": "3:40:12", "remaining_time": "21:35:49"}
+{"current_steps": 131, "total_steps": 895, "loss": 0.8449, "lr": 7.948904938659872e-05, "epoch": 0.7282835302293259, "percentage": 14.64, "elapsed_time": "3:41:54", "remaining_time": "21:34:13"}
+{"current_steps": 132, "total_steps": 895, "loss": 0.8404, "lr": 7.946387751441609e-05, "epoch": 0.7338429464906184, "percentage": 14.75, "elapsed_time": "3:43:36", "remaining_time": "21:32:30"}
+{"current_steps": 133, "total_steps": 895, "loss": 0.8242, "lr": 7.943810459695764e-05, "epoch": 0.7394023627519111, "percentage": 14.86, "elapsed_time": "3:45:17", "remaining_time": "21:30:48"}
+{"current_steps": 134, "total_steps": 895, "loss": 0.8153, "lr": 7.941173102675172e-05, "epoch": 0.7449617790132036, "percentage": 14.97, "elapsed_time": "3:46:59", "remaining_time": "21:29:07"}
+{"current_steps": 135, "total_steps": 895, "loss": 0.8372, "lr": 7.938475720547477e-05, "epoch": 0.7505211952744962, "percentage": 15.08, "elapsed_time": "3:48:41", "remaining_time": "21:27:28"}
+{"current_steps": 136, "total_steps": 895, "loss": 0.8311, "lr": 7.93571835439452e-05, "epoch": 0.7560806115357888, "percentage": 15.2, "elapsed_time": "3:50:22", "remaining_time": "21:25:44"}
+{"current_steps": 137, "total_steps": 895, "loss": 0.8182, "lr": 7.932901046211715e-05, "epoch": 0.7616400277970813, "percentage": 15.31, "elapsed_time": "3:52:04", "remaining_time": "21:24:00"}
+{"current_steps": 138, "total_steps": 895, "loss": 0.8285, "lr": 7.930023838907411e-05, "epoch": 0.7671994440583739, "percentage": 15.42, "elapsed_time": "3:53:47", "remaining_time": "21:22:30"}
+{"current_steps": 139, "total_steps": 895, "loss": 0.8223, "lr": 7.927086776302235e-05, "epoch": 0.7727588603196665, "percentage": 15.53, "elapsed_time": "3:55:29", "remaining_time": "21:20:47"}
+{"current_steps": 140, "total_steps": 895, "loss": 0.821, "lr": 7.924089903128425e-05, "epoch": 0.778318276580959, "percentage": 15.64, "elapsed_time": "3:57:11", "remaining_time": "21:19:06"}
+{"current_steps": 141, "total_steps": 895, "loss": 0.8318, "lr": 7.921033265029153e-05, "epoch": 0.7838776928422516, "percentage": 15.75, "elapsed_time": "3:58:52", "remaining_time": "21:17:25"}
+{"current_steps": 142, "total_steps": 895, "loss": 0.8141, "lr": 7.917916908557822e-05, "epoch": 0.7894371091035441, "percentage": 15.87, "elapsed_time": "4:00:35", "remaining_time": "21:15:47"}
+{"current_steps": 143, "total_steps": 895, "loss": 0.8086, "lr": 7.914740881177365e-05, "epoch": 0.7949965253648367, "percentage": 15.98, "elapsed_time": "4:02:16", "remaining_time": "21:14:04"}
+{"current_steps": 144, "total_steps": 895, "loss": 0.8082, "lr": 7.911505231259516e-05, "epoch": 0.8005559416261293, "percentage": 16.09, "elapsed_time": "4:03:59", "remaining_time": "21:12:27"}
+{"current_steps": 145, "total_steps": 895, "loss": 0.8023, "lr": 7.908210008084082e-05, "epoch": 0.8061153578874218, "percentage": 16.2, "elapsed_time": "4:05:43", "remaining_time": "21:10:57"}
+{"current_steps": 146, "total_steps": 895, "loss": 0.8315, "lr": 7.904855261838179e-05, "epoch": 0.8116747741487144, "percentage": 16.31, "elapsed_time": "4:07:25", "remaining_time": "21:09:18"}
+{"current_steps": 147, "total_steps": 895, "loss": 0.8268, "lr": 7.901441043615479e-05, "epoch": 0.817234190410007, "percentage": 16.42, "elapsed_time": "4:09:09", "remaining_time": "21:07:50"}
+{"current_steps": 148, "total_steps": 895, "loss": 0.8386, "lr": 7.897967405415425e-05, "epoch": 0.8227936066712995, "percentage": 16.54, "elapsed_time": "4:10:52", "remaining_time": "21:06:13"}
+{"current_steps": 149, "total_steps": 895, "loss": 0.8325, "lr": 7.894434400142447e-05, "epoch": 0.828353022932592, "percentage": 16.65, "elapsed_time": "4:12:37", "remaining_time": "21:04:47"}
+{"current_steps": 150, "total_steps": 895, "loss": 0.8504, "lr": 7.890842081605148e-05, "epoch": 0.8339124391938847, "percentage": 16.76, "elapsed_time": "4:14:18", "remaining_time": "21:03:06"}
+{"current_steps": 151, "total_steps": 895, "loss": 0.8075, "lr": 7.887190504515485e-05, "epoch": 0.8394718554551772, "percentage": 16.87, "elapsed_time": "4:16:03", "remaining_time": "21:01:36"}
+{"current_steps": 152, "total_steps": 895, "loss": 0.8247, "lr": 7.883479724487946e-05, "epoch": 0.8450312717164697, "percentage": 16.98, "elapsed_time": "4:17:45", "remaining_time": "20:59:59"}
+{"current_steps": 153, "total_steps": 895, "loss": 0.8298, "lr": 7.879709798038685e-05, "epoch": 0.8505906879777624, "percentage": 17.09, "elapsed_time": "4:19:29", "remaining_time": "20:58:28"}
+{"current_steps": 154, "total_steps": 895, "loss": 0.8273, "lr": 7.875880782584683e-05, "epoch": 0.8561501042390549, "percentage": 17.21, "elapsed_time": "4:21:12", "remaining_time": "20:56:52"}
+{"current_steps": 155, "total_steps": 895, "loss": 0.8326, "lr": 7.871992736442852e-05, "epoch": 0.8617095205003474, "percentage": 17.32, "elapsed_time": "4:22:55", "remaining_time": "20:55:16"}
+{"current_steps": 156, "total_steps": 895, "loss": 0.8263, "lr": 7.868045718829166e-05, "epoch": 0.8672689367616401, "percentage": 17.43, "elapsed_time": "4:24:39", "remaining_time": "20:53:44"}
+{"current_steps": 157, "total_steps": 895, "loss": 0.8193, "lr": 7.864039789857743e-05, "epoch": 0.8728283530229326, "percentage": 17.54, "elapsed_time": "4:26:23", "remaining_time": "20:52:10"}
+{"current_steps": 158, "total_steps": 895, "loss": 0.8119, "lr": 7.859975010539937e-05, "epoch": 0.8783877692842251, "percentage": 17.65, "elapsed_time": "4:28:05", "remaining_time": "20:50:32"}
+{"current_steps": 159, "total_steps": 895, "loss": 0.8291, "lr": 7.855851442783414e-05, "epoch": 0.8839471855455178, "percentage": 17.77, "elapsed_time": "4:29:48", "remaining_time": "20:48:54"}
+{"current_steps": 160, "total_steps": 895, "loss": 0.8103, "lr": 7.851669149391198e-05, "epoch": 0.8895066018068103, "percentage": 17.88, "elapsed_time": "4:31:30", "remaining_time": "20:47:16"}
+{"current_steps": 161, "total_steps": 895, "loss": 0.8214, "lr": 7.847428194060722e-05, "epoch": 0.8950660180681028, "percentage": 17.99, "elapsed_time": "4:33:13", "remaining_time": "20:45:39"}
+{"current_steps": 162, "total_steps": 895, "loss": 0.8198, "lr": 7.843128641382856e-05, "epoch": 0.9006254343293955, "percentage": 18.1, "elapsed_time": "4:34:56", "remaining_time": "20:44:00"}
+{"current_steps": 163, "total_steps": 895, "loss": 0.821, "lr": 7.838770556840923e-05, "epoch": 0.906184850590688, "percentage": 18.21, "elapsed_time": "4:36:38", "remaining_time": "20:42:20"}
+{"current_steps": 164, "total_steps": 895, "loss": 0.8396, "lr": 7.834354006809699e-05, "epoch": 0.9117442668519805, "percentage": 18.32, "elapsed_time": "4:38:21", "remaining_time": "20:40:43"}
+{"current_steps": 165, "total_steps": 895, "loss": 0.8169, "lr": 7.829879058554411e-05, "epoch": 0.9173036831132731, "percentage": 18.44, "elapsed_time": "4:40:04", "remaining_time": "20:39:05"}
+{"current_steps": 166, "total_steps": 895, "loss": 0.8248, "lr": 7.8253457802297e-05, "epoch": 0.9228630993745657, "percentage": 18.55, "elapsed_time": "4:41:49", "remaining_time": "20:37:38"}
+{"current_steps": 167, "total_steps": 895, "loss": 0.8242, "lr": 7.820754240878593e-05, "epoch": 0.9284225156358582, "percentage": 18.66, "elapsed_time": "4:43:33", "remaining_time": "20:36:04"}
+{"current_steps": 168, "total_steps": 895, "loss": 0.821, "lr": 7.816104510431446e-05, "epoch": 0.9339819318971508, "percentage": 18.77, "elapsed_time": "4:45:15", "remaining_time": "20:34:25"}
+{"current_steps": 169, "total_steps": 895, "loss": 0.7994, "lr": 7.811396659704884e-05, "epoch": 0.9395413481584434, "percentage": 18.88, "elapsed_time": "4:46:59", "remaining_time": "20:32:50"}
+{"current_steps": 170, "total_steps": 895, "loss": 0.8231, "lr": 7.806630760400712e-05, "epoch": 0.9451007644197359, "percentage": 18.99, "elapsed_time": "4:48:43", "remaining_time": "20:31:20"}
+{"current_steps": 171, "total_steps": 895, "loss": 0.8138, "lr": 7.80180688510484e-05, "epoch": 0.9506601806810285, "percentage": 19.11, "elapsed_time": "4:50:26", "remaining_time": "20:29:43"}
+{"current_steps": 172, "total_steps": 895, "loss": 0.8363, "lr": 7.79692510728616e-05, "epoch": 0.9562195969423211, "percentage": 19.22, "elapsed_time": "4:52:11", "remaining_time": "20:28:14"}
+{"current_steps": 173, "total_steps": 895, "loss": 0.8124, "lr": 7.791985501295437e-05, "epoch": 0.9617790132036136, "percentage": 19.33, "elapsed_time": "4:53:54", "remaining_time": "20:26:37"}
+{"current_steps": 174, "total_steps": 895, "loss": 0.8062, "lr": 7.786988142364175e-05, "epoch": 0.9673384294649062, "percentage": 19.44, "elapsed_time": "4:55:37", "remaining_time": "20:25:00"}
+{"current_steps": 175, "total_steps": 895, "loss": 0.8202, "lr": 7.781933106603472e-05, "epoch": 0.9728978457261988, "percentage": 19.55, "elapsed_time": "4:57:21", "remaining_time": "20:23:24"}
+{"current_steps": 176, "total_steps": 895, "loss": 0.7936, "lr": 7.776820471002856e-05, "epoch": 0.9784572619874913, "percentage": 19.66, "elapsed_time": "4:59:06", "remaining_time": "20:21:56"}
+{"current_steps": 177, "total_steps": 895, "loss": 0.8091, "lr": 7.771650313429117e-05, "epoch": 0.9840166782487839, "percentage": 19.78, "elapsed_time": "5:00:50", "remaining_time": "20:20:21"}
+{"current_steps": 178, "total_steps": 895, "loss": 0.8146, "lr": 7.76642271262512e-05, "epoch": 0.9895760945100764, "percentage": 19.89, "elapsed_time": "5:02:32", "remaining_time": "20:18:41"}
+{"current_steps": 179, "total_steps": 895, "loss": 0.7959, "lr": 7.761137748208606e-05, "epoch": 0.995135510771369, "percentage": 20.0, "elapsed_time": "5:04:16", "remaining_time": "20:17:07"}
+{"current_steps": 180, "total_steps": 895, "loss": 0.8144, "lr": 7.75579550067098e-05, "epoch": 1.0006949270326615, "percentage": 20.11, "elapsed_time": "5:09:28", "remaining_time": "20:29:19"}
+{"current_steps": 181, "total_steps": 895, "loss": 0.7972, "lr": 7.750396051376082e-05, "epoch": 1.0062543432939541, "percentage": 20.22, "elapsed_time": "5:11:10", "remaining_time": "20:27:32"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994083c0d37c90028720c3ab23633773a4fe067c8195858ac54490cbf8417e23
+size 7288