Training in progress, epoch 1

.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 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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_mrope": 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 sha256:309145e0748b97931f15b46d11006391840d1ee1a3511427f449adf59b871975
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a62227f97212c1e1761c2d140dcd3f0dabe7fc3416af0c3fa94d79322ab9d2
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1691d1ae87655717a25155413e75da1e799c7a855f78fa8800d056336b2d6d95
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5abd62b3dd5ad0db8d58c948c9fc8fb8f8ea9d8acc1a5d14412b1c7e00c22231
+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": "<|im_end|>",
+    "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 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 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": "<|im_end|>",
+  "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 +1,176 @@
+{"current_steps": 10, "total_steps": 5238, "loss": 0.7164, "lr": 5e-06, "epoch": 0.0057273768613974796, "percentage": 0.19, "elapsed_time": "0:02:16", "remaining_time": "19:52:13"}
+{"current_steps": 20, "total_steps": 5238, "loss": 0.6034, "lr": 5e-06, "epoch": 0.011454753722794959, "percentage": 0.38, "elapsed_time": "0:04:29", "remaining_time": "19:31:15"}
+{"current_steps": 30, "total_steps": 5238, "loss": 0.5621, "lr": 5e-06, "epoch": 0.01718213058419244, "percentage": 0.57, "elapsed_time": "0:06:41", "remaining_time": "19:22:23"}
+{"current_steps": 40, "total_steps": 5238, "loss": 0.5341, "lr": 5e-06, "epoch": 0.022909507445589918, "percentage": 0.76, "elapsed_time": "0:08:53", "remaining_time": "19:16:29"}
+{"current_steps": 50, "total_steps": 5238, "loss": 0.526, "lr": 5e-06, "epoch": 0.0286368843069874, "percentage": 0.95, "elapsed_time": "0:11:06", "remaining_time": "19:12:00"}
+{"current_steps": 60, "total_steps": 5238, "loss": 0.5078, "lr": 5e-06, "epoch": 0.03436426116838488, "percentage": 1.15, "elapsed_time": "0:13:18", "remaining_time": "19:07:59"}
+{"current_steps": 70, "total_steps": 5238, "loss": 0.5056, "lr": 5e-06, "epoch": 0.04009163802978236, "percentage": 1.34, "elapsed_time": "0:15:30", "remaining_time": "19:04:46"}
+{"current_steps": 80, "total_steps": 5238, "loss": 0.5, "lr": 5e-06, "epoch": 0.045819014891179836, "percentage": 1.53, "elapsed_time": "0:17:42", "remaining_time": "19:01:59"}
+{"current_steps": 90, "total_steps": 5238, "loss": 0.5062, "lr": 5e-06, "epoch": 0.05154639175257732, "percentage": 1.72, "elapsed_time": "0:19:55", "remaining_time": "18:59:23"}
+{"current_steps": 100, "total_steps": 5238, "loss": 0.4995, "lr": 5e-06, "epoch": 0.0572737686139748, "percentage": 1.91, "elapsed_time": "0:22:07", "remaining_time": "18:56:53"}
+{"current_steps": 110, "total_steps": 5238, "loss": 0.5018, "lr": 5e-06, "epoch": 0.06300114547537228, "percentage": 2.1, "elapsed_time": "0:24:19", "remaining_time": "18:54:08"}
+{"current_steps": 120, "total_steps": 5238, "loss": 0.4897, "lr": 5e-06, "epoch": 0.06872852233676977, "percentage": 2.29, "elapsed_time": "0:26:31", "remaining_time": "18:51:26"}
+{"current_steps": 130, "total_steps": 5238, "loss": 0.4921, "lr": 5e-06, "epoch": 0.07445589919816724, "percentage": 2.48, "elapsed_time": "0:28:44", "remaining_time": "18:49:00"}
+{"current_steps": 140, "total_steps": 5238, "loss": 0.4872, "lr": 5e-06, "epoch": 0.08018327605956473, "percentage": 2.67, "elapsed_time": "0:30:56", "remaining_time": "18:46:42"}
+{"current_steps": 150, "total_steps": 5238, "loss": 0.4771, "lr": 5e-06, "epoch": 0.0859106529209622, "percentage": 2.86, "elapsed_time": "0:33:08", "remaining_time": "18:44:24"}
+{"current_steps": 160, "total_steps": 5238, "loss": 0.4923, "lr": 5e-06, "epoch": 0.09163802978235967, "percentage": 3.05, "elapsed_time": "0:35:21", "remaining_time": "18:42:10"}
+{"current_steps": 170, "total_steps": 5238, "loss": 0.4889, "lr": 5e-06, "epoch": 0.09736540664375716, "percentage": 3.25, "elapsed_time": "0:37:34", "remaining_time": "18:39:57"}
+{"current_steps": 180, "total_steps": 5238, "loss": 0.4906, "lr": 5e-06, "epoch": 0.10309278350515463, "percentage": 3.44, "elapsed_time": "0:39:46", "remaining_time": "18:37:36"}
+{"current_steps": 190, "total_steps": 5238, "loss": 0.4792, "lr": 5e-06, "epoch": 0.10882016036655212, "percentage": 3.63, "elapsed_time": "0:41:58", "remaining_time": "18:35:10"}
+{"current_steps": 200, "total_steps": 5238, "loss": 0.4749, "lr": 5e-06, "epoch": 0.1145475372279496, "percentage": 3.82, "elapsed_time": "0:44:10", "remaining_time": "18:32:53"}
+{"current_steps": 210, "total_steps": 5238, "loss": 0.476, "lr": 5e-06, "epoch": 0.12027491408934708, "percentage": 4.01, "elapsed_time": "0:46:23", "remaining_time": "18:30:39"}
+{"current_steps": 220, "total_steps": 5238, "loss": 0.4795, "lr": 5e-06, "epoch": 0.12600229095074456, "percentage": 4.2, "elapsed_time": "0:48:35", "remaining_time": "18:28:27"}
+{"current_steps": 230, "total_steps": 5238, "loss": 0.4768, "lr": 5e-06, "epoch": 0.13172966781214204, "percentage": 4.39, "elapsed_time": "0:50:48", "remaining_time": "18:26:16"}
+{"current_steps": 240, "total_steps": 5238, "loss": 0.471, "lr": 5e-06, "epoch": 0.13745704467353953, "percentage": 4.58, "elapsed_time": "0:53:00", "remaining_time": "18:24:02"}
+{"current_steps": 250, "total_steps": 5238, "loss": 0.4713, "lr": 5e-06, "epoch": 0.143184421534937, "percentage": 4.77, "elapsed_time": "0:55:13", "remaining_time": "18:21:49"}
+{"current_steps": 260, "total_steps": 5238, "loss": 0.4696, "lr": 5e-06, "epoch": 0.14891179839633448, "percentage": 4.96, "elapsed_time": "0:57:25", "remaining_time": "18:19:34"}
+{"current_steps": 270, "total_steps": 5238, "loss": 0.4655, "lr": 5e-06, "epoch": 0.15463917525773196, "percentage": 5.15, "elapsed_time": "0:59:37", "remaining_time": "18:17:14"}
+{"current_steps": 280, "total_steps": 5238, "loss": 0.4747, "lr": 5e-06, "epoch": 0.16036655211912945, "percentage": 5.35, "elapsed_time": "1:01:49", "remaining_time": "18:14:50"}
+{"current_steps": 290, "total_steps": 5238, "loss": 0.4648, "lr": 5e-06, "epoch": 0.1660939289805269, "percentage": 5.54, "elapsed_time": "1:04:02", "remaining_time": "18:12:33"}
+{"current_steps": 300, "total_steps": 5238, "loss": 0.4659, "lr": 5e-06, "epoch": 0.1718213058419244, "percentage": 5.73, "elapsed_time": "1:06:14", "remaining_time": "18:10:18"}
+{"current_steps": 310, "total_steps": 5238, "loss": 0.4581, "lr": 5e-06, "epoch": 0.1775486827033219, "percentage": 5.92, "elapsed_time": "1:08:26", "remaining_time": "18:08:03"}
+{"current_steps": 320, "total_steps": 5238, "loss": 0.4577, "lr": 5e-06, "epoch": 0.18327605956471935, "percentage": 6.11, "elapsed_time": "1:10:39", "remaining_time": "18:05:50"}
+{"current_steps": 330, "total_steps": 5238, "loss": 0.463, "lr": 5e-06, "epoch": 0.18900343642611683, "percentage": 6.3, "elapsed_time": "1:12:51", "remaining_time": "18:03:36"}
+{"current_steps": 340, "total_steps": 5238, "loss": 0.4606, "lr": 5e-06, "epoch": 0.19473081328751432, "percentage": 6.49, "elapsed_time": "1:15:03", "remaining_time": "18:01:23"}
+{"current_steps": 350, "total_steps": 5238, "loss": 0.4722, "lr": 5e-06, "epoch": 0.2004581901489118, "percentage": 6.68, "elapsed_time": "1:17:16", "remaining_time": "17:59:09"}
+{"current_steps": 360, "total_steps": 5238, "loss": 0.461, "lr": 5e-06, "epoch": 0.20618556701030927, "percentage": 6.87, "elapsed_time": "1:19:28", "remaining_time": "17:56:51"}
+{"current_steps": 370, "total_steps": 5238, "loss": 0.4527, "lr": 5e-06, "epoch": 0.21191294387170675, "percentage": 7.06, "elapsed_time": "1:21:40", "remaining_time": "17:54:37"}
+{"current_steps": 380, "total_steps": 5238, "loss": 0.4618, "lr": 5e-06, "epoch": 0.21764032073310424, "percentage": 7.25, "elapsed_time": "1:23:52", "remaining_time": "17:52:20"}
+{"current_steps": 390, "total_steps": 5238, "loss": 0.454, "lr": 5e-06, "epoch": 0.22336769759450173, "percentage": 7.45, "elapsed_time": "1:26:05", "remaining_time": "17:50:04"}
+{"current_steps": 400, "total_steps": 5238, "loss": 0.4656, "lr": 5e-06, "epoch": 0.2290950744558992, "percentage": 7.64, "elapsed_time": "1:28:17", "remaining_time": "17:47:52"}
+{"current_steps": 410, "total_steps": 5238, "loss": 0.4594, "lr": 5e-06, "epoch": 0.23482245131729668, "percentage": 7.83, "elapsed_time": "1:30:29", "remaining_time": "17:45:39"}
+{"current_steps": 420, "total_steps": 5238, "loss": 0.4662, "lr": 5e-06, "epoch": 0.24054982817869416, "percentage": 8.02, "elapsed_time": "1:32:42", "remaining_time": "17:43:26"}
+{"current_steps": 430, "total_steps": 5238, "loss": 0.4683, "lr": 5e-06, "epoch": 0.24627720504009165, "percentage": 8.21, "elapsed_time": "1:34:54", "remaining_time": "17:41:13"}
+{"current_steps": 440, "total_steps": 5238, "loss": 0.463, "lr": 5e-06, "epoch": 0.2520045819014891, "percentage": 8.4, "elapsed_time": "1:37:06", "remaining_time": "17:38:59"}
+{"current_steps": 450, "total_steps": 5238, "loss": 0.4609, "lr": 5e-06, "epoch": 0.25773195876288657, "percentage": 8.59, "elapsed_time": "1:39:19", "remaining_time": "17:36:45"}
+{"current_steps": 460, "total_steps": 5238, "loss": 0.4457, "lr": 5e-06, "epoch": 0.2634593356242841, "percentage": 8.78, "elapsed_time": "1:41:31", "remaining_time": "17:34:34"}
+{"current_steps": 470, "total_steps": 5238, "loss": 0.4632, "lr": 5e-06, "epoch": 0.26918671248568155, "percentage": 8.97, "elapsed_time": "1:43:44", "remaining_time": "17:32:22"}
+{"current_steps": 480, "total_steps": 5238, "loss": 0.4434, "lr": 5e-06, "epoch": 0.27491408934707906, "percentage": 9.16, "elapsed_time": "1:45:56", "remaining_time": "17:30:09"}
+{"current_steps": 490, "total_steps": 5238, "loss": 0.4433, "lr": 5e-06, "epoch": 0.2806414662084765, "percentage": 9.35, "elapsed_time": "1:48:09", "remaining_time": "17:27:58"}
+{"current_steps": 500, "total_steps": 5238, "loss": 0.4562, "lr": 5e-06, "epoch": 0.286368843069874, "percentage": 9.55, "elapsed_time": "1:50:21", "remaining_time": "17:25:44"}
+{"current_steps": 510, "total_steps": 5238, "loss": 0.4654, "lr": 5e-06, "epoch": 0.2920962199312715, "percentage": 9.74, "elapsed_time": "1:52:33", "remaining_time": "17:23:28"}
+{"current_steps": 520, "total_steps": 5238, "loss": 0.4298, "lr": 5e-06, "epoch": 0.29782359679266895, "percentage": 9.93, "elapsed_time": "1:54:45", "remaining_time": "17:21:16"}
+{"current_steps": 530, "total_steps": 5238, "loss": 0.463, "lr": 5e-06, "epoch": 0.3035509736540664, "percentage": 10.12, "elapsed_time": "1:56:58", "remaining_time": "17:19:03"}
+{"current_steps": 540, "total_steps": 5238, "loss": 0.4534, "lr": 5e-06, "epoch": 0.30927835051546393, "percentage": 10.31, "elapsed_time": "1:59:10", "remaining_time": "17:16:50"}
+{"current_steps": 550, "total_steps": 5238, "loss": 0.4514, "lr": 5e-06, "epoch": 0.3150057273768614, "percentage": 10.5, "elapsed_time": "2:01:23", "remaining_time": "17:14:40"}
+{"current_steps": 560, "total_steps": 5238, "loss": 0.4606, "lr": 5e-06, "epoch": 0.3207331042382589, "percentage": 10.69, "elapsed_time": "2:03:35", "remaining_time": "17:12:26"}
+{"current_steps": 570, "total_steps": 5238, "loss": 0.4607, "lr": 5e-06, "epoch": 0.32646048109965636, "percentage": 10.88, "elapsed_time": "2:05:47", "remaining_time": "17:10:13"}
+{"current_steps": 580, "total_steps": 5238, "loss": 0.4507, "lr": 5e-06, "epoch": 0.3321878579610538, "percentage": 11.07, "elapsed_time": "2:08:00", "remaining_time": "17:08:00"}
+{"current_steps": 590, "total_steps": 5238, "loss": 0.4441, "lr": 5e-06, "epoch": 0.33791523482245134, "percentage": 11.26, "elapsed_time": "2:10:12", "remaining_time": "17:05:48"}
+{"current_steps": 600, "total_steps": 5238, "loss": 0.4518, "lr": 5e-06, "epoch": 0.3436426116838488, "percentage": 11.45, "elapsed_time": "2:12:25", "remaining_time": "17:03:36"}
+{"current_steps": 610, "total_steps": 5238, "loss": 0.4583, "lr": 5e-06, "epoch": 0.34936998854524626, "percentage": 11.65, "elapsed_time": "2:14:37", "remaining_time": "17:01:23"}
+{"current_steps": 620, "total_steps": 5238, "loss": 0.4603, "lr": 5e-06, "epoch": 0.3550973654066438, "percentage": 11.84, "elapsed_time": "2:16:49", "remaining_time": "16:59:10"}
+{"current_steps": 630, "total_steps": 5238, "loss": 0.4514, "lr": 5e-06, "epoch": 0.36082474226804123, "percentage": 12.03, "elapsed_time": "2:19:02", "remaining_time": "16:56:58"}
+{"current_steps": 640, "total_steps": 5238, "loss": 0.4537, "lr": 5e-06, "epoch": 0.3665521191294387, "percentage": 12.22, "elapsed_time": "2:21:14", "remaining_time": "16:54:45"}
+{"current_steps": 650, "total_steps": 5238, "loss": 0.4626, "lr": 5e-06, "epoch": 0.3722794959908362, "percentage": 12.41, "elapsed_time": "2:23:27", "remaining_time": "16:52:33"}
+{"current_steps": 660, "total_steps": 5238, "loss": 0.4438, "lr": 5e-06, "epoch": 0.37800687285223367, "percentage": 12.6, "elapsed_time": "2:25:39", "remaining_time": "16:50:21"}
+{"current_steps": 670, "total_steps": 5238, "loss": 0.456, "lr": 5e-06, "epoch": 0.3837342497136312, "percentage": 12.79, "elapsed_time": "2:27:52", "remaining_time": "16:48:08"}
+{"current_steps": 680, "total_steps": 5238, "loss": 0.4445, "lr": 5e-06, "epoch": 0.38946162657502864, "percentage": 12.98, "elapsed_time": "2:30:04", "remaining_time": "16:45:56"}
+{"current_steps": 690, "total_steps": 5238, "loss": 0.4439, "lr": 5e-06, "epoch": 0.3951890034364261, "percentage": 13.17, "elapsed_time": "2:32:16", "remaining_time": "16:43:43"}
+{"current_steps": 700, "total_steps": 5238, "loss": 0.4518, "lr": 5e-06, "epoch": 0.4009163802978236, "percentage": 13.36, "elapsed_time": "2:34:29", "remaining_time": "16:41:31"}
+{"current_steps": 710, "total_steps": 5238, "loss": 0.4444, "lr": 5e-06, "epoch": 0.4066437571592211, "percentage": 13.55, "elapsed_time": "2:36:41", "remaining_time": "16:39:17"}
+{"current_steps": 720, "total_steps": 5238, "loss": 0.4417, "lr": 5e-06, "epoch": 0.41237113402061853, "percentage": 13.75, "elapsed_time": "2:38:53", "remaining_time": "16:37:02"}
+{"current_steps": 730, "total_steps": 5238, "loss": 0.4531, "lr": 5e-06, "epoch": 0.41809851088201605, "percentage": 13.94, "elapsed_time": "2:41:05", "remaining_time": "16:34:47"}
+{"current_steps": 740, "total_steps": 5238, "loss": 0.4507, "lr": 5e-06, "epoch": 0.4238258877434135, "percentage": 14.13, "elapsed_time": "2:43:17", "remaining_time": "16:32:35"}
+{"current_steps": 750, "total_steps": 5238, "loss": 0.4395, "lr": 5e-06, "epoch": 0.42955326460481097, "percentage": 14.32, "elapsed_time": "2:45:30", "remaining_time": "16:30:23"}
+{"current_steps": 760, "total_steps": 5238, "loss": 0.4392, "lr": 5e-06, "epoch": 0.4352806414662085, "percentage": 14.51, "elapsed_time": "2:47:42", "remaining_time": "16:28:11"}
+{"current_steps": 770, "total_steps": 5238, "loss": 0.4571, "lr": 5e-06, "epoch": 0.44100801832760594, "percentage": 14.7, "elapsed_time": "2:49:55", "remaining_time": "16:25:59"}
+{"current_steps": 780, "total_steps": 5238, "loss": 0.4532, "lr": 5e-06, "epoch": 0.44673539518900346, "percentage": 14.89, "elapsed_time": "2:52:07", "remaining_time": "16:23:48"}
+{"current_steps": 790, "total_steps": 5238, "loss": 0.4534, "lr": 5e-06, "epoch": 0.4524627720504009, "percentage": 15.08, "elapsed_time": "2:54:20", "remaining_time": "16:21:36"}
+{"current_steps": 800, "total_steps": 5238, "loss": 0.4536, "lr": 5e-06, "epoch": 0.4581901489117984, "percentage": 15.27, "elapsed_time": "2:56:33", "remaining_time": "16:19:24"}
+{"current_steps": 810, "total_steps": 5238, "loss": 0.4469, "lr": 5e-06, "epoch": 0.4639175257731959, "percentage": 15.46, "elapsed_time": "2:58:45", "remaining_time": "16:17:13"}
+{"current_steps": 820, "total_steps": 5238, "loss": 0.4428, "lr": 5e-06, "epoch": 0.46964490263459335, "percentage": 15.65, "elapsed_time": "3:00:57", "remaining_time": "16:15:00"}
+{"current_steps": 830, "total_steps": 5238, "loss": 0.4502, "lr": 5e-06, "epoch": 0.4753722794959908, "percentage": 15.85, "elapsed_time": "3:03:09", "remaining_time": "16:12:45"}
+{"current_steps": 840, "total_steps": 5238, "loss": 0.4482, "lr": 5e-06, "epoch": 0.48109965635738833, "percentage": 16.04, "elapsed_time": "3:05:22", "remaining_time": "16:10:33"}
+{"current_steps": 850, "total_steps": 5238, "loss": 0.4446, "lr": 5e-06, "epoch": 0.4868270332187858, "percentage": 16.23, "elapsed_time": "3:07:34", "remaining_time": "16:08:22"}
+{"current_steps": 860, "total_steps": 5238, "loss": 0.4508, "lr": 5e-06, "epoch": 0.4925544100801833, "percentage": 16.42, "elapsed_time": "3:09:47", "remaining_time": "16:06:09"}
+{"current_steps": 870, "total_steps": 5238, "loss": 0.45, "lr": 5e-06, "epoch": 0.49828178694158076, "percentage": 16.61, "elapsed_time": "3:11:59", "remaining_time": "16:03:57"}
+{"current_steps": 880, "total_steps": 5238, "loss": 0.4348, "lr": 5e-06, "epoch": 0.5040091638029782, "percentage": 16.8, "elapsed_time": "3:14:12", "remaining_time": "16:01:46"}
+{"current_steps": 890, "total_steps": 5238, "loss": 0.443, "lr": 5e-06, "epoch": 0.5097365406643757, "percentage": 16.99, "elapsed_time": "3:16:25", "remaining_time": "15:59:34"}
+{"current_steps": 900, "total_steps": 5238, "loss": 0.448, "lr": 5e-06, "epoch": 0.5154639175257731, "percentage": 17.18, "elapsed_time": "3:18:37", "remaining_time": "15:57:23"}
+{"current_steps": 910, "total_steps": 5238, "loss": 0.444, "lr": 5e-06, "epoch": 0.5211912943871707, "percentage": 17.37, "elapsed_time": "3:20:50", "remaining_time": "15:55:11"}
+{"current_steps": 920, "total_steps": 5238, "loss": 0.4493, "lr": 5e-06, "epoch": 0.5269186712485682, "percentage": 17.56, "elapsed_time": "3:23:02", "remaining_time": "15:52:58"}
+{"current_steps": 930, "total_steps": 5238, "loss": 0.4541, "lr": 5e-06, "epoch": 0.5326460481099656, "percentage": 17.75, "elapsed_time": "3:25:14", "remaining_time": "15:50:44"}
+{"current_steps": 940, "total_steps": 5238, "loss": 0.4437, "lr": 5e-06, "epoch": 0.5383734249713631, "percentage": 17.95, "elapsed_time": "3:27:26", "remaining_time": "15:48:30"}
+{"current_steps": 950, "total_steps": 5238, "loss": 0.438, "lr": 5e-06, "epoch": 0.5441008018327605, "percentage": 18.14, "elapsed_time": "3:29:39", "remaining_time": "15:46:18"}
+{"current_steps": 960, "total_steps": 5238, "loss": 0.4382, "lr": 5e-06, "epoch": 0.5498281786941581, "percentage": 18.33, "elapsed_time": "3:31:51", "remaining_time": "15:44:07"}
+{"current_steps": 970, "total_steps": 5238, "loss": 0.443, "lr": 5e-06, "epoch": 0.5555555555555556, "percentage": 18.52, "elapsed_time": "3:34:04", "remaining_time": "15:41:56"}
+{"current_steps": 980, "total_steps": 5238, "loss": 0.4541, "lr": 5e-06, "epoch": 0.561282932416953, "percentage": 18.71, "elapsed_time": "3:36:17", "remaining_time": "15:39:45"}
+{"current_steps": 990, "total_steps": 5238, "loss": 0.447, "lr": 5e-06, "epoch": 0.5670103092783505, "percentage": 18.9, "elapsed_time": "3:38:29", "remaining_time": "15:37:33"}
+{"current_steps": 1000, "total_steps": 5238, "loss": 0.4371, "lr": 5e-06, "epoch": 0.572737686139748, "percentage": 19.09, "elapsed_time": "3:40:42", "remaining_time": "15:35:22"}
+{"current_steps": 1010, "total_steps": 5238, "loss": 0.4383, "lr": 5e-06, "epoch": 0.5784650630011455, "percentage": 19.28, "elapsed_time": "3:42:55", "remaining_time": "15:33:11"}
+{"current_steps": 1020, "total_steps": 5238, "loss": 0.456, "lr": 5e-06, "epoch": 0.584192439862543, "percentage": 19.47, "elapsed_time": "3:45:07", "remaining_time": "15:30:59"}
+{"current_steps": 1030, "total_steps": 5238, "loss": 0.459, "lr": 5e-06, "epoch": 0.5899198167239404, "percentage": 19.66, "elapsed_time": "3:47:20", "remaining_time": "15:28:46"}
+{"current_steps": 1040, "total_steps": 5238, "loss": 0.4379, "lr": 5e-06, "epoch": 0.5956471935853379, "percentage": 19.85, "elapsed_time": "3:49:32", "remaining_time": "15:26:33"}
+{"current_steps": 1050, "total_steps": 5238, "loss": 0.445, "lr": 5e-06, "epoch": 0.6013745704467354, "percentage": 20.05, "elapsed_time": "3:51:44", "remaining_time": "15:24:20"}
+{"current_steps": 1060, "total_steps": 5238, "loss": 0.4353, "lr": 5e-06, "epoch": 0.6071019473081328, "percentage": 20.24, "elapsed_time": "3:53:57", "remaining_time": "15:22:07"}
+{"current_steps": 1070, "total_steps": 5238, "loss": 0.4412, "lr": 5e-06, "epoch": 0.6128293241695304, "percentage": 20.43, "elapsed_time": "3:56:09", "remaining_time": "15:19:54"}
+{"current_steps": 1080, "total_steps": 5238, "loss": 0.443, "lr": 5e-06, "epoch": 0.6185567010309279, "percentage": 20.62, "elapsed_time": "3:58:21", "remaining_time": "15:17:41"}
+{"current_steps": 1090, "total_steps": 5238, "loss": 0.4435, "lr": 5e-06, "epoch": 0.6242840778923253, "percentage": 20.81, "elapsed_time": "4:00:33", "remaining_time": "15:15:27"}
+{"current_steps": 1100, "total_steps": 5238, "loss": 0.4294, "lr": 5e-06, "epoch": 0.6300114547537228, "percentage": 21.0, "elapsed_time": "4:02:45", "remaining_time": "15:13:14"}
+{"current_steps": 1110, "total_steps": 5238, "loss": 0.4443, "lr": 5e-06, "epoch": 0.6357388316151202, "percentage": 21.19, "elapsed_time": "4:04:58", "remaining_time": "15:11:02"}
+{"current_steps": 1120, "total_steps": 5238, "loss": 0.4388, "lr": 5e-06, "epoch": 0.6414662084765178, "percentage": 21.38, "elapsed_time": "4:07:10", "remaining_time": "15:08:49"}
+{"current_steps": 1130, "total_steps": 5238, "loss": 0.4278, "lr": 5e-06, "epoch": 0.6471935853379153, "percentage": 21.57, "elapsed_time": "4:09:22", "remaining_time": "15:06:36"}
+{"current_steps": 1140, "total_steps": 5238, "loss": 0.4445, "lr": 5e-06, "epoch": 0.6529209621993127, "percentage": 21.76, "elapsed_time": "4:11:35", "remaining_time": "15:04:22"}
+{"current_steps": 1150, "total_steps": 5238, "loss": 0.4443, "lr": 5e-06, "epoch": 0.6586483390607102, "percentage": 21.95, "elapsed_time": "4:13:47", "remaining_time": "15:02:10"}
+{"current_steps": 1160, "total_steps": 5238, "loss": 0.449, "lr": 5e-06, "epoch": 0.6643757159221076, "percentage": 22.15, "elapsed_time": "4:15:59", "remaining_time": "14:59:57"}
+{"current_steps": 1170, "total_steps": 5238, "loss": 0.4424, "lr": 5e-06, "epoch": 0.6701030927835051, "percentage": 22.34, "elapsed_time": "4:18:12", "remaining_time": "14:57:45"}
+{"current_steps": 1180, "total_steps": 5238, "loss": 0.4409, "lr": 5e-06, "epoch": 0.6758304696449027, "percentage": 22.53, "elapsed_time": "4:20:24", "remaining_time": "14:55:31"}
+{"current_steps": 1190, "total_steps": 5238, "loss": 0.4408, "lr": 5e-06, "epoch": 0.6815578465063001, "percentage": 22.72, "elapsed_time": "4:22:36", "remaining_time": "14:53:20"}
+{"current_steps": 1200, "total_steps": 5238, "loss": 0.4539, "lr": 5e-06, "epoch": 0.6872852233676976, "percentage": 22.91, "elapsed_time": "4:24:49", "remaining_time": "14:51:08"}
+{"current_steps": 1210, "total_steps": 5238, "loss": 0.4408, "lr": 5e-06, "epoch": 0.693012600229095, "percentage": 23.1, "elapsed_time": "4:27:02", "remaining_time": "14:48:56"}
+{"current_steps": 1220, "total_steps": 5238, "loss": 0.4318, "lr": 5e-06, "epoch": 0.6987399770904925, "percentage": 23.29, "elapsed_time": "4:29:14", "remaining_time": "14:46:42"}
+{"current_steps": 1230, "total_steps": 5238, "loss": 0.4274, "lr": 5e-06, "epoch": 0.7044673539518901, "percentage": 23.48, "elapsed_time": "4:31:26", "remaining_time": "14:44:29"}
+{"current_steps": 1240, "total_steps": 5238, "loss": 0.426, "lr": 5e-06, "epoch": 0.7101947308132875, "percentage": 23.67, "elapsed_time": "4:33:38", "remaining_time": "14:42:16"}
+{"current_steps": 1250, "total_steps": 5238, "loss": 0.4433, "lr": 5e-06, "epoch": 0.715922107674685, "percentage": 23.86, "elapsed_time": "4:35:50", "remaining_time": "14:40:03"}
+{"current_steps": 1260, "total_steps": 5238, "loss": 0.4347, "lr": 5e-06, "epoch": 0.7216494845360825, "percentage": 24.05, "elapsed_time": "4:38:03", "remaining_time": "14:37:52"}
+{"current_steps": 1270, "total_steps": 5238, "loss": 0.4404, "lr": 5e-06, "epoch": 0.7273768613974799, "percentage": 24.25, "elapsed_time": "4:40:16", "remaining_time": "14:35:40"}
+{"current_steps": 1280, "total_steps": 5238, "loss": 0.4195, "lr": 5e-06, "epoch": 0.7331042382588774, "percentage": 24.44, "elapsed_time": "4:42:28", "remaining_time": "14:33:29"}
+{"current_steps": 1290, "total_steps": 5238, "loss": 0.4399, "lr": 5e-06, "epoch": 0.738831615120275, "percentage": 24.63, "elapsed_time": "4:44:41", "remaining_time": "14:31:16"}
+{"current_steps": 1300, "total_steps": 5238, "loss": 0.4416, "lr": 5e-06, "epoch": 0.7445589919816724, "percentage": 24.82, "elapsed_time": "4:46:53", "remaining_time": "14:29:03"}
+{"current_steps": 1310, "total_steps": 5238, "loss": 0.4458, "lr": 5e-06, "epoch": 0.7502863688430699, "percentage": 25.01, "elapsed_time": "4:49:05", "remaining_time": "14:26:50"}
+{"current_steps": 1320, "total_steps": 5238, "loss": 0.4425, "lr": 5e-06, "epoch": 0.7560137457044673, "percentage": 25.2, "elapsed_time": "4:51:18", "remaining_time": "14:24:38"}
+{"current_steps": 1330, "total_steps": 5238, "loss": 0.438, "lr": 5e-06, "epoch": 0.7617411225658648, "percentage": 25.39, "elapsed_time": "4:53:30", "remaining_time": "14:22:25"}
+{"current_steps": 1340, "total_steps": 5238, "loss": 0.441, "lr": 5e-06, "epoch": 0.7674684994272624, "percentage": 25.58, "elapsed_time": "4:55:42", "remaining_time": "14:20:11"}
+{"current_steps": 1350, "total_steps": 5238, "loss": 0.4422, "lr": 5e-06, "epoch": 0.7731958762886598, "percentage": 25.77, "elapsed_time": "4:57:54", "remaining_time": "14:17:57"}
+{"current_steps": 1360, "total_steps": 5238, "loss": 0.4195, "lr": 5e-06, "epoch": 0.7789232531500573, "percentage": 25.96, "elapsed_time": "5:00:06", "remaining_time": "14:15:44"}
+{"current_steps": 1370, "total_steps": 5238, "loss": 0.4252, "lr": 5e-06, "epoch": 0.7846506300114547, "percentage": 26.16, "elapsed_time": "5:02:18", "remaining_time": "14:13:32"}
+{"current_steps": 1380, "total_steps": 5238, "loss": 0.428, "lr": 5e-06, "epoch": 0.7903780068728522, "percentage": 26.35, "elapsed_time": "5:04:31", "remaining_time": "14:11:19"}
+{"current_steps": 1390, "total_steps": 5238, "loss": 0.4321, "lr": 5e-06, "epoch": 0.7961053837342497, "percentage": 26.54, "elapsed_time": "5:06:43", "remaining_time": "14:09:07"}
+{"current_steps": 1400, "total_steps": 5238, "loss": 0.4292, "lr": 5e-06, "epoch": 0.8018327605956472, "percentage": 26.73, "elapsed_time": "5:08:56", "remaining_time": "14:06:55"}
+{"current_steps": 1410, "total_steps": 5238, "loss": 0.436, "lr": 5e-06, "epoch": 0.8075601374570447, "percentage": 26.92, "elapsed_time": "5:11:08", "remaining_time": "14:04:43"}
+{"current_steps": 1420, "total_steps": 5238, "loss": 0.4347, "lr": 5e-06, "epoch": 0.8132875143184422, "percentage": 27.11, "elapsed_time": "5:13:21", "remaining_time": "14:02:31"}
+{"current_steps": 1430, "total_steps": 5238, "loss": 0.4343, "lr": 5e-06, "epoch": 0.8190148911798396, "percentage": 27.3, "elapsed_time": "5:15:33", "remaining_time": "14:00:19"}
+{"current_steps": 1440, "total_steps": 5238, "loss": 0.4385, "lr": 5e-06, "epoch": 0.8247422680412371, "percentage": 27.49, "elapsed_time": "5:17:46", "remaining_time": "13:58:07"}
+{"current_steps": 1450, "total_steps": 5238, "loss": 0.4187, "lr": 5e-06, "epoch": 0.8304696449026346, "percentage": 27.68, "elapsed_time": "5:19:58", "remaining_time": "13:55:55"}
+{"current_steps": 1460, "total_steps": 5238, "loss": 0.4354, "lr": 5e-06, "epoch": 0.8361970217640321, "percentage": 27.87, "elapsed_time": "5:22:11", "remaining_time": "13:53:43"}
+{"current_steps": 1470, "total_steps": 5238, "loss": 0.442, "lr": 5e-06, "epoch": 0.8419243986254296, "percentage": 28.06, "elapsed_time": "5:24:24", "remaining_time": "13:51:31"}
+{"current_steps": 1480, "total_steps": 5238, "loss": 0.432, "lr": 5e-06, "epoch": 0.847651775486827, "percentage": 28.26, "elapsed_time": "5:26:36", "remaining_time": "13:49:18"}
+{"current_steps": 1490, "total_steps": 5238, "loss": 0.4349, "lr": 5e-06, "epoch": 0.8533791523482245, "percentage": 28.45, "elapsed_time": "5:28:48", "remaining_time": "13:47:06"}
+{"current_steps": 1500, "total_steps": 5238, "loss": 0.4337, "lr": 5e-06, "epoch": 0.8591065292096219, "percentage": 28.64, "elapsed_time": "5:31:01", "remaining_time": "13:44:54"}
+{"current_steps": 1510, "total_steps": 5238, "loss": 0.4304, "lr": 5e-06, "epoch": 0.8648339060710195, "percentage": 28.83, "elapsed_time": "5:33:14", "remaining_time": "13:42:42"}
+{"current_steps": 1520, "total_steps": 5238, "loss": 0.4291, "lr": 5e-06, "epoch": 0.870561282932417, "percentage": 29.02, "elapsed_time": "5:35:26", "remaining_time": "13:40:30"}
+{"current_steps": 1530, "total_steps": 5238, "loss": 0.435, "lr": 5e-06, "epoch": 0.8762886597938144, "percentage": 29.21, "elapsed_time": "5:37:39", "remaining_time": "13:38:19"}
+{"current_steps": 1540, "total_steps": 5238, "loss": 0.4455, "lr": 5e-06, "epoch": 0.8820160366552119, "percentage": 29.4, "elapsed_time": "5:39:52", "remaining_time": "13:36:07"}
+{"current_steps": 1550, "total_steps": 5238, "loss": 0.4246, "lr": 5e-06, "epoch": 0.8877434135166093, "percentage": 29.59, "elapsed_time": "5:42:04", "remaining_time": "13:33:55"}
+{"current_steps": 1560, "total_steps": 5238, "loss": 0.4459, "lr": 5e-06, "epoch": 0.8934707903780069, "percentage": 29.78, "elapsed_time": "5:44:17", "remaining_time": "13:31:43"}
+{"current_steps": 1570, "total_steps": 5238, "loss": 0.4227, "lr": 5e-06, "epoch": 0.8991981672394044, "percentage": 29.97, "elapsed_time": "5:46:29", "remaining_time": "13:29:31"}
+{"current_steps": 1580, "total_steps": 5238, "loss": 0.425, "lr": 5e-06, "epoch": 0.9049255441008018, "percentage": 30.16, "elapsed_time": "5:48:42", "remaining_time": "13:27:19"}
+{"current_steps": 1590, "total_steps": 5238, "loss": 0.4339, "lr": 5e-06, "epoch": 0.9106529209621993, "percentage": 30.36, "elapsed_time": "5:50:54", "remaining_time": "13:25:07"}
+{"current_steps": 1600, "total_steps": 5238, "loss": 0.4351, "lr": 5e-06, "epoch": 0.9163802978235968, "percentage": 30.55, "elapsed_time": "5:53:07", "remaining_time": "13:22:54"}
+{"current_steps": 1610, "total_steps": 5238, "loss": 0.4439, "lr": 5e-06, "epoch": 0.9221076746849943, "percentage": 30.74, "elapsed_time": "5:55:19", "remaining_time": "13:20:41"}
+{"current_steps": 1620, "total_steps": 5238, "loss": 0.4315, "lr": 5e-06, "epoch": 0.9278350515463918, "percentage": 30.93, "elapsed_time": "5:57:31", "remaining_time": "13:18:29"}
+{"current_steps": 1630, "total_steps": 5238, "loss": 0.4209, "lr": 5e-06, "epoch": 0.9335624284077892, "percentage": 31.12, "elapsed_time": "5:59:44", "remaining_time": "13:16:17"}
+{"current_steps": 1640, "total_steps": 5238, "loss": 0.4255, "lr": 5e-06, "epoch": 0.9392898052691867, "percentage": 31.31, "elapsed_time": "6:01:57", "remaining_time": "13:14:05"}
+{"current_steps": 1650, "total_steps": 5238, "loss": 0.4359, "lr": 5e-06, "epoch": 0.9450171821305842, "percentage": 31.5, "elapsed_time": "6:04:09", "remaining_time": "13:11:53"}
+{"current_steps": 1660, "total_steps": 5238, "loss": 0.4298, "lr": 5e-06, "epoch": 0.9507445589919816, "percentage": 31.69, "elapsed_time": "6:06:22", "remaining_time": "13:09:41"}
+{"current_steps": 1670, "total_steps": 5238, "loss": 0.4321, "lr": 5e-06, "epoch": 0.9564719358533792, "percentage": 31.88, "elapsed_time": "6:08:35", "remaining_time": "13:07:29"}
+{"current_steps": 1680, "total_steps": 5238, "loss": 0.4376, "lr": 5e-06, "epoch": 0.9621993127147767, "percentage": 32.07, "elapsed_time": "6:10:47", "remaining_time": "13:05:17"}
+{"current_steps": 1690, "total_steps": 5238, "loss": 0.4138, "lr": 5e-06, "epoch": 0.9679266895761741, "percentage": 32.26, "elapsed_time": "6:13:00", "remaining_time": "13:03:05"}
+{"current_steps": 1700, "total_steps": 5238, "loss": 0.4348, "lr": 5e-06, "epoch": 0.9736540664375716, "percentage": 32.46, "elapsed_time": "6:15:13", "remaining_time": "13:00:53"}
+{"current_steps": 1710, "total_steps": 5238, "loss": 0.4235, "lr": 5e-06, "epoch": 0.979381443298969, "percentage": 32.65, "elapsed_time": "6:17:25", "remaining_time": "12:58:41"}
+{"current_steps": 1720, "total_steps": 5238, "loss": 0.4331, "lr": 5e-06, "epoch": 0.9851088201603666, "percentage": 32.84, "elapsed_time": "6:19:38", "remaining_time": "12:56:29"}
+{"current_steps": 1730, "total_steps": 5238, "loss": 0.4324, "lr": 5e-06, "epoch": 0.9908361970217641, "percentage": 33.03, "elapsed_time": "6:21:51", "remaining_time": "12:54:17"}
+{"current_steps": 1740, "total_steps": 5238, "loss": 0.4292, "lr": 5e-06, "epoch": 0.9965635738831615, "percentage": 33.22, "elapsed_time": "6:24:03", "remaining_time": "12:52:05"}
+{"current_steps": 1746, "total_steps": 5238, "eval_loss": 0.4308567941188812, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "6:32:44", "remaining_time": "13:05:29"}
+{"current_steps": 1750, "total_steps": 5238, "loss": 0.4118, "lr": 5e-06, "epoch": 1.002290950744559, "percentage": 33.41, "elapsed_time": "6:34:41", "remaining_time": "13:06:39"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7428a618dace62c02f347959219468f4b70bbeb91cd8a96c251202d8598b0403
+size 7224