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:f2f0961447e1f56e15771faac79f2abe9070bd1fef85ab848965ced9bef104ae
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044dd3d8db06fc6825296aa7c2eae7117884fa875e39786b76787de79f70b366
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170c96ca08561fdd44b9eafcb45208b796596afa0bf24d2b0c7881c600944ee4
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585cda439658a9b6504a4c249d21a87aa8b4fc7baebe708ef32451a26ec7d82d
+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 +1,136 @@
+{"current_steps": 10, "total_steps": 4023, "loss": 0.6314, "lr": 5e-06, "epoch": 0.007457121551081283, "percentage": 0.25, "elapsed_time": "0:02:16", "remaining_time": "15:14:27"}
+{"current_steps": 20, "total_steps": 4023, "loss": 0.5957, "lr": 5e-06, "epoch": 0.014914243102162566, "percentage": 0.5, "elapsed_time": "0:04:29", "remaining_time": "14:57:44"}
+{"current_steps": 30, "total_steps": 4023, "loss": 0.5858, "lr": 5e-06, "epoch": 0.02237136465324385, "percentage": 0.75, "elapsed_time": "0:06:41", "remaining_time": "14:50:55"}
+{"current_steps": 40, "total_steps": 4023, "loss": 0.6083, "lr": 5e-06, "epoch": 0.02982848620432513, "percentage": 0.99, "elapsed_time": "0:08:54", "remaining_time": "14:46:19"}
+{"current_steps": 50, "total_steps": 4023, "loss": 0.5833, "lr": 5e-06, "epoch": 0.037285607755406416, "percentage": 1.24, "elapsed_time": "0:11:06", "remaining_time": "14:42:40"}
+{"current_steps": 60, "total_steps": 4023, "loss": 0.5615, "lr": 5e-06, "epoch": 0.0447427293064877, "percentage": 1.49, "elapsed_time": "0:13:18", "remaining_time": "14:39:30"}
+{"current_steps": 70, "total_steps": 4023, "loss": 0.5599, "lr": 5e-06, "epoch": 0.05219985085756898, "percentage": 1.74, "elapsed_time": "0:15:31", "remaining_time": "14:36:26"}
+{"current_steps": 80, "total_steps": 4023, "loss": 0.5738, "lr": 5e-06, "epoch": 0.05965697240865026, "percentage": 1.99, "elapsed_time": "0:17:43", "remaining_time": "14:33:31"}
+{"current_steps": 90, "total_steps": 4023, "loss": 0.5513, "lr": 5e-06, "epoch": 0.06711409395973154, "percentage": 2.24, "elapsed_time": "0:19:55", "remaining_time": "14:30:50"}
+{"current_steps": 100, "total_steps": 4023, "loss": 0.5723, "lr": 5e-06, "epoch": 0.07457121551081283, "percentage": 2.49, "elapsed_time": "0:22:08", "remaining_time": "14:28:19"}
+{"current_steps": 110, "total_steps": 4023, "loss": 0.5666, "lr": 5e-06, "epoch": 0.08202833706189411, "percentage": 2.73, "elapsed_time": "0:24:20", "remaining_time": "14:25:56"}
+{"current_steps": 120, "total_steps": 4023, "loss": 0.5475, "lr": 5e-06, "epoch": 0.0894854586129754, "percentage": 2.98, "elapsed_time": "0:26:33", "remaining_time": "14:23:33"}
+{"current_steps": 130, "total_steps": 4023, "loss": 0.5532, "lr": 5e-06, "epoch": 0.09694258016405667, "percentage": 3.23, "elapsed_time": "0:28:45", "remaining_time": "14:21:03"}
+{"current_steps": 140, "total_steps": 4023, "loss": 0.5561, "lr": 5e-06, "epoch": 0.10439970171513796, "percentage": 3.48, "elapsed_time": "0:30:57", "remaining_time": "14:18:37"}
+{"current_steps": 150, "total_steps": 4023, "loss": 0.5542, "lr": 5e-06, "epoch": 0.11185682326621924, "percentage": 3.73, "elapsed_time": "0:33:09", "remaining_time": "14:16:12"}
+{"current_steps": 160, "total_steps": 4023, "loss": 0.55, "lr": 5e-06, "epoch": 0.11931394481730052, "percentage": 3.98, "elapsed_time": "0:35:21", "remaining_time": "14:13:47"}
+{"current_steps": 170, "total_steps": 4023, "loss": 0.5577, "lr": 5e-06, "epoch": 0.1267710663683818, "percentage": 4.23, "elapsed_time": "0:37:33", "remaining_time": "14:11:24"}
+{"current_steps": 180, "total_steps": 4023, "loss": 0.5579, "lr": 5e-06, "epoch": 0.1342281879194631, "percentage": 4.47, "elapsed_time": "0:39:46", "remaining_time": "14:09:03"}
+{"current_steps": 190, "total_steps": 4023, "loss": 0.5691, "lr": 5e-06, "epoch": 0.14168530947054436, "percentage": 4.72, "elapsed_time": "0:41:58", "remaining_time": "14:06:44"}
+{"current_steps": 200, "total_steps": 4023, "loss": 0.5441, "lr": 5e-06, "epoch": 0.14914243102162567, "percentage": 4.97, "elapsed_time": "0:44:10", "remaining_time": "14:04:24"}
+{"current_steps": 210, "total_steps": 4023, "loss": 0.5438, "lr": 5e-06, "epoch": 0.15659955257270694, "percentage": 5.22, "elapsed_time": "0:46:22", "remaining_time": "14:02:05"}
+{"current_steps": 220, "total_steps": 4023, "loss": 0.5552, "lr": 5e-06, "epoch": 0.16405667412378822, "percentage": 5.47, "elapsed_time": "0:48:34", "remaining_time": "13:59:48"}
+{"current_steps": 230, "total_steps": 4023, "loss": 0.57, "lr": 5e-06, "epoch": 0.1715137956748695, "percentage": 5.72, "elapsed_time": "0:50:47", "remaining_time": "13:57:30"}
+{"current_steps": 240, "total_steps": 4023, "loss": 0.5588, "lr": 5e-06, "epoch": 0.1789709172259508, "percentage": 5.97, "elapsed_time": "0:52:59", "remaining_time": "13:55:13"}
+{"current_steps": 250, "total_steps": 4023, "loss": 0.5435, "lr": 5e-06, "epoch": 0.18642803877703207, "percentage": 6.21, "elapsed_time": "0:55:11", "remaining_time": "13:52:58"}
+{"current_steps": 260, "total_steps": 4023, "loss": 0.5371, "lr": 5e-06, "epoch": 0.19388516032811334, "percentage": 6.46, "elapsed_time": "0:57:23", "remaining_time": "13:50:42"}
+{"current_steps": 270, "total_steps": 4023, "loss": 0.554, "lr": 5e-06, "epoch": 0.20134228187919462, "percentage": 6.71, "elapsed_time": "0:59:36", "remaining_time": "13:48:26"}
+{"current_steps": 280, "total_steps": 4023, "loss": 0.5648, "lr": 5e-06, "epoch": 0.20879940343027592, "percentage": 6.96, "elapsed_time": "1:01:48", "remaining_time": "13:46:10"}
+{"current_steps": 290, "total_steps": 4023, "loss": 0.5626, "lr": 5e-06, "epoch": 0.2162565249813572, "percentage": 7.21, "elapsed_time": "1:04:00", "remaining_time": "13:43:55"}
+{"current_steps": 300, "total_steps": 4023, "loss": 0.5495, "lr": 5e-06, "epoch": 0.22371364653243847, "percentage": 7.46, "elapsed_time": "1:06:12", "remaining_time": "13:41:39"}
+{"current_steps": 310, "total_steps": 4023, "loss": 0.5492, "lr": 5e-06, "epoch": 0.23117076808351977, "percentage": 7.71, "elapsed_time": "1:08:24", "remaining_time": "13:39:23"}
+{"current_steps": 320, "total_steps": 4023, "loss": 0.5382, "lr": 5e-06, "epoch": 0.23862788963460105, "percentage": 7.95, "elapsed_time": "1:10:36", "remaining_time": "13:37:08"}
+{"current_steps": 330, "total_steps": 4023, "loss": 0.5626, "lr": 5e-06, "epoch": 0.24608501118568232, "percentage": 8.2, "elapsed_time": "1:12:48", "remaining_time": "13:34:51"}
+{"current_steps": 340, "total_steps": 4023, "loss": 0.5537, "lr": 5e-06, "epoch": 0.2535421327367636, "percentage": 8.45, "elapsed_time": "1:15:00", "remaining_time": "13:32:36"}
+{"current_steps": 350, "total_steps": 4023, "loss": 0.5577, "lr": 5e-06, "epoch": 0.2609992542878449, "percentage": 8.7, "elapsed_time": "1:17:13", "remaining_time": "13:30:21"}
+{"current_steps": 360, "total_steps": 4023, "loss": 0.5514, "lr": 5e-06, "epoch": 0.2684563758389262, "percentage": 8.95, "elapsed_time": "1:19:25", "remaining_time": "13:28:06"}
+{"current_steps": 370, "total_steps": 4023, "loss": 0.5415, "lr": 5e-06, "epoch": 0.2759134973900075, "percentage": 9.2, "elapsed_time": "1:21:37", "remaining_time": "13:25:52"}
+{"current_steps": 380, "total_steps": 4023, "loss": 0.5641, "lr": 5e-06, "epoch": 0.2833706189410887, "percentage": 9.45, "elapsed_time": "1:23:49", "remaining_time": "13:23:39"}
+{"current_steps": 390, "total_steps": 4023, "loss": 0.5481, "lr": 5e-06, "epoch": 0.29082774049217003, "percentage": 9.69, "elapsed_time": "1:26:01", "remaining_time": "13:21:24"}
+{"current_steps": 400, "total_steps": 4023, "loss": 0.5513, "lr": 5e-06, "epoch": 0.29828486204325133, "percentage": 9.94, "elapsed_time": "1:28:14", "remaining_time": "13:19:10"}
+{"current_steps": 410, "total_steps": 4023, "loss": 0.5638, "lr": 5e-06, "epoch": 0.3057419835943326, "percentage": 10.19, "elapsed_time": "1:30:26", "remaining_time": "13:16:56"}
+{"current_steps": 420, "total_steps": 4023, "loss": 0.5492, "lr": 5e-06, "epoch": 0.3131991051454139, "percentage": 10.44, "elapsed_time": "1:32:38", "remaining_time": "13:14:43"}
+{"current_steps": 430, "total_steps": 4023, "loss": 0.5607, "lr": 5e-06, "epoch": 0.32065622669649513, "percentage": 10.69, "elapsed_time": "1:34:50", "remaining_time": "13:12:30"}
+{"current_steps": 440, "total_steps": 4023, "loss": 0.5645, "lr": 5e-06, "epoch": 0.32811334824757643, "percentage": 10.94, "elapsed_time": "1:37:02", "remaining_time": "13:10:16"}
+{"current_steps": 450, "total_steps": 4023, "loss": 0.5549, "lr": 5e-06, "epoch": 0.33557046979865773, "percentage": 11.19, "elapsed_time": "1:39:15", "remaining_time": "13:08:03"}
+{"current_steps": 460, "total_steps": 4023, "loss": 0.5548, "lr": 5e-06, "epoch": 0.343027591349739, "percentage": 11.43, "elapsed_time": "1:41:27", "remaining_time": "13:05:51"}
+{"current_steps": 470, "total_steps": 4023, "loss": 0.5583, "lr": 5e-06, "epoch": 0.3504847129008203, "percentage": 11.68, "elapsed_time": "1:43:39", "remaining_time": "13:03:38"}
+{"current_steps": 480, "total_steps": 4023, "loss": 0.545, "lr": 5e-06, "epoch": 0.3579418344519016, "percentage": 11.93, "elapsed_time": "1:45:52", "remaining_time": "13:01:26"}
+{"current_steps": 490, "total_steps": 4023, "loss": 0.5395, "lr": 5e-06, "epoch": 0.36539895600298283, "percentage": 12.18, "elapsed_time": "1:48:04", "remaining_time": "12:59:14"}
+{"current_steps": 500, "total_steps": 4023, "loss": 0.5456, "lr": 5e-06, "epoch": 0.37285607755406414, "percentage": 12.43, "elapsed_time": "1:50:16", "remaining_time": "12:57:03"}
+{"current_steps": 510, "total_steps": 4023, "loss": 0.5367, "lr": 5e-06, "epoch": 0.38031319910514544, "percentage": 12.68, "elapsed_time": "1:52:29", "remaining_time": "12:54:52"}
+{"current_steps": 520, "total_steps": 4023, "loss": 0.5716, "lr": 5e-06, "epoch": 0.3877703206562267, "percentage": 12.93, "elapsed_time": "1:54:42", "remaining_time": "12:52:40"}
+{"current_steps": 530, "total_steps": 4023, "loss": 0.5545, "lr": 5e-06, "epoch": 0.395227442207308, "percentage": 13.17, "elapsed_time": "1:56:54", "remaining_time": "12:50:29"}
+{"current_steps": 540, "total_steps": 4023, "loss": 0.5646, "lr": 5e-06, "epoch": 0.40268456375838924, "percentage": 13.42, "elapsed_time": "1:59:06", "remaining_time": "12:48:17"}
+{"current_steps": 550, "total_steps": 4023, "loss": 0.559, "lr": 5e-06, "epoch": 0.41014168530947054, "percentage": 13.67, "elapsed_time": "2:01:19", "remaining_time": "12:46:05"}
+{"current_steps": 560, "total_steps": 4023, "loss": 0.5398, "lr": 5e-06, "epoch": 0.41759880686055184, "percentage": 13.92, "elapsed_time": "2:03:31", "remaining_time": "12:43:54"}
+{"current_steps": 570, "total_steps": 4023, "loss": 0.5506, "lr": 5e-06, "epoch": 0.4250559284116331, "percentage": 14.17, "elapsed_time": "2:05:44", "remaining_time": "12:41:43"}
+{"current_steps": 580, "total_steps": 4023, "loss": 0.5624, "lr": 5e-06, "epoch": 0.4325130499627144, "percentage": 14.42, "elapsed_time": "2:07:56", "remaining_time": "12:39:31"}
+{"current_steps": 590, "total_steps": 4023, "loss": 0.5493, "lr": 5e-06, "epoch": 0.4399701715137957, "percentage": 14.67, "elapsed_time": "2:10:09", "remaining_time": "12:37:20"}
+{"current_steps": 600, "total_steps": 4023, "loss": 0.5495, "lr": 5e-06, "epoch": 0.44742729306487694, "percentage": 14.91, "elapsed_time": "2:12:21", "remaining_time": "12:35:08"}
+{"current_steps": 610, "total_steps": 4023, "loss": 0.5422, "lr": 5e-06, "epoch": 0.45488441461595824, "percentage": 15.16, "elapsed_time": "2:14:34", "remaining_time": "12:32:55"}
+{"current_steps": 620, "total_steps": 4023, "loss": 0.5575, "lr": 5e-06, "epoch": 0.46234153616703955, "percentage": 15.41, "elapsed_time": "2:16:46", "remaining_time": "12:30:43"}
+{"current_steps": 630, "total_steps": 4023, "loss": 0.552, "lr": 5e-06, "epoch": 0.4697986577181208, "percentage": 15.66, "elapsed_time": "2:18:58", "remaining_time": "12:28:30"}
+{"current_steps": 640, "total_steps": 4023, "loss": 0.5574, "lr": 5e-06, "epoch": 0.4772557792692021, "percentage": 15.91, "elapsed_time": "2:21:11", "remaining_time": "12:26:17"}
+{"current_steps": 650, "total_steps": 4023, "loss": 0.5515, "lr": 5e-06, "epoch": 0.48471290082028334, "percentage": 16.16, "elapsed_time": "2:23:23", "remaining_time": "12:24:05"}
+{"current_steps": 660, "total_steps": 4023, "loss": 0.5574, "lr": 5e-06, "epoch": 0.49217002237136465, "percentage": 16.41, "elapsed_time": "2:25:36", "remaining_time": "12:21:53"}
+{"current_steps": 670, "total_steps": 4023, "loss": 0.5585, "lr": 5e-06, "epoch": 0.49962714392244595, "percentage": 16.65, "elapsed_time": "2:27:48", "remaining_time": "12:19:41"}
+{"current_steps": 680, "total_steps": 4023, "loss": 0.556, "lr": 5e-06, "epoch": 0.5070842654735273, "percentage": 16.9, "elapsed_time": "2:30:00", "remaining_time": "12:17:28"}
+{"current_steps": 690, "total_steps": 4023, "loss": 0.5437, "lr": 5e-06, "epoch": 0.5145413870246085, "percentage": 17.15, "elapsed_time": "2:32:12", "remaining_time": "12:15:15"}
+{"current_steps": 700, "total_steps": 4023, "loss": 0.5568, "lr": 5e-06, "epoch": 0.5219985085756897, "percentage": 17.4, "elapsed_time": "2:34:25", "remaining_time": "12:13:02"}
+{"current_steps": 710, "total_steps": 4023, "loss": 0.5431, "lr": 5e-06, "epoch": 0.5294556301267711, "percentage": 17.65, "elapsed_time": "2:36:37", "remaining_time": "12:10:50"}
+{"current_steps": 720, "total_steps": 4023, "loss": 0.5552, "lr": 5e-06, "epoch": 0.5369127516778524, "percentage": 17.9, "elapsed_time": "2:38:49", "remaining_time": "12:08:37"}
+{"current_steps": 730, "total_steps": 4023, "loss": 0.554, "lr": 5e-06, "epoch": 0.5443698732289336, "percentage": 18.15, "elapsed_time": "2:41:01", "remaining_time": "12:06:24"}
+{"current_steps": 740, "total_steps": 4023, "loss": 0.5495, "lr": 5e-06, "epoch": 0.551826994780015, "percentage": 18.39, "elapsed_time": "2:43:14", "remaining_time": "12:04:12"}
+{"current_steps": 750, "total_steps": 4023, "loss": 0.5561, "lr": 5e-06, "epoch": 0.5592841163310962, "percentage": 18.64, "elapsed_time": "2:45:26", "remaining_time": "12:01:59"}
+{"current_steps": 760, "total_steps": 4023, "loss": 0.5532, "lr": 5e-06, "epoch": 0.5667412378821775, "percentage": 18.89, "elapsed_time": "2:47:38", "remaining_time": "11:59:46"}
+{"current_steps": 770, "total_steps": 4023, "loss": 0.5567, "lr": 5e-06, "epoch": 0.5741983594332588, "percentage": 19.14, "elapsed_time": "2:49:51", "remaining_time": "11:57:34"}
+{"current_steps": 780, "total_steps": 4023, "loss": 0.5411, "lr": 5e-06, "epoch": 0.5816554809843401, "percentage": 19.39, "elapsed_time": "2:52:03", "remaining_time": "11:55:21"}
+{"current_steps": 790, "total_steps": 4023, "loss": 0.5598, "lr": 5e-06, "epoch": 0.5891126025354213, "percentage": 19.64, "elapsed_time": "2:54:15", "remaining_time": "11:53:08"}
+{"current_steps": 800, "total_steps": 4023, "loss": 0.5505, "lr": 5e-06, "epoch": 0.5965697240865027, "percentage": 19.89, "elapsed_time": "2:56:27", "remaining_time": "11:50:54"}
+{"current_steps": 810, "total_steps": 4023, "loss": 0.5301, "lr": 5e-06, "epoch": 0.6040268456375839, "percentage": 20.13, "elapsed_time": "2:58:39", "remaining_time": "11:48:41"}
+{"current_steps": 820, "total_steps": 4023, "loss": 0.5616, "lr": 5e-06, "epoch": 0.6114839671886652, "percentage": 20.38, "elapsed_time": "3:00:52", "remaining_time": "11:46:28"}
+{"current_steps": 830, "total_steps": 4023, "loss": 0.5444, "lr": 5e-06, "epoch": 0.6189410887397464, "percentage": 20.63, "elapsed_time": "3:03:04", "remaining_time": "11:44:15"}
+{"current_steps": 840, "total_steps": 4023, "loss": 0.5596, "lr": 5e-06, "epoch": 0.6263982102908278, "percentage": 20.88, "elapsed_time": "3:05:16", "remaining_time": "11:42:02"}
+{"current_steps": 850, "total_steps": 4023, "loss": 0.5469, "lr": 5e-06, "epoch": 0.633855331841909, "percentage": 21.13, "elapsed_time": "3:07:28", "remaining_time": "11:39:49"}
+{"current_steps": 860, "total_steps": 4023, "loss": 0.562, "lr": 5e-06, "epoch": 0.6413124533929903, "percentage": 21.38, "elapsed_time": "3:09:40", "remaining_time": "11:37:37"}
+{"current_steps": 870, "total_steps": 4023, "loss": 0.5388, "lr": 5e-06, "epoch": 0.6487695749440716, "percentage": 21.63, "elapsed_time": "3:11:52", "remaining_time": "11:35:24"}
+{"current_steps": 880, "total_steps": 4023, "loss": 0.5406, "lr": 5e-06, "epoch": 0.6562266964951529, "percentage": 21.87, "elapsed_time": "3:14:05", "remaining_time": "11:33:11"}
+{"current_steps": 890, "total_steps": 4023, "loss": 0.5549, "lr": 5e-06, "epoch": 0.6636838180462341, "percentage": 22.12, "elapsed_time": "3:16:17", "remaining_time": "11:30:59"}
+{"current_steps": 900, "total_steps": 4023, "loss": 0.5291, "lr": 5e-06, "epoch": 0.6711409395973155, "percentage": 22.37, "elapsed_time": "3:18:29", "remaining_time": "11:28:46"}
+{"current_steps": 910, "total_steps": 4023, "loss": 0.5523, "lr": 5e-06, "epoch": 0.6785980611483967, "percentage": 22.62, "elapsed_time": "3:20:41", "remaining_time": "11:26:34"}
+{"current_steps": 920, "total_steps": 4023, "loss": 0.5448, "lr": 5e-06, "epoch": 0.686055182699478, "percentage": 22.87, "elapsed_time": "3:22:54", "remaining_time": "11:24:21"}
+{"current_steps": 930, "total_steps": 4023, "loss": 0.5415, "lr": 5e-06, "epoch": 0.6935123042505593, "percentage": 23.12, "elapsed_time": "3:25:06", "remaining_time": "11:22:08"}
+{"current_steps": 940, "total_steps": 4023, "loss": 0.5712, "lr": 5e-06, "epoch": 0.7009694258016406, "percentage": 23.37, "elapsed_time": "3:27:18", "remaining_time": "11:19:55"}
+{"current_steps": 950, "total_steps": 4023, "loss": 0.5519, "lr": 5e-06, "epoch": 0.7084265473527218, "percentage": 23.61, "elapsed_time": "3:29:30", "remaining_time": "11:17:43"}
+{"current_steps": 960, "total_steps": 4023, "loss": 0.5551, "lr": 5e-06, "epoch": 0.7158836689038032, "percentage": 23.86, "elapsed_time": "3:31:43", "remaining_time": "11:15:30"}
+{"current_steps": 970, "total_steps": 4023, "loss": 0.5561, "lr": 5e-06, "epoch": 0.7233407904548844, "percentage": 24.11, "elapsed_time": "3:33:55", "remaining_time": "11:13:17"}
+{"current_steps": 980, "total_steps": 4023, "loss": 0.553, "lr": 5e-06, "epoch": 0.7307979120059657, "percentage": 24.36, "elapsed_time": "3:36:07", "remaining_time": "11:11:04"}
+{"current_steps": 990, "total_steps": 4023, "loss": 0.5403, "lr": 5e-06, "epoch": 0.738255033557047, "percentage": 24.61, "elapsed_time": "3:38:19", "remaining_time": "11:08:52"}
+{"current_steps": 1000, "total_steps": 4023, "loss": 0.548, "lr": 5e-06, "epoch": 0.7457121551081283, "percentage": 24.86, "elapsed_time": "3:40:31", "remaining_time": "11:06:39"}
+{"current_steps": 1010, "total_steps": 4023, "loss": 0.5466, "lr": 5e-06, "epoch": 0.7531692766592095, "percentage": 25.11, "elapsed_time": "3:42:44", "remaining_time": "11:04:27"}
+{"current_steps": 1020, "total_steps": 4023, "loss": 0.5519, "lr": 5e-06, "epoch": 0.7606263982102909, "percentage": 25.35, "elapsed_time": "3:44:56", "remaining_time": "11:02:14"}
+{"current_steps": 1030, "total_steps": 4023, "loss": 0.5465, "lr": 5e-06, "epoch": 0.7680835197613721, "percentage": 25.6, "elapsed_time": "3:47:08", "remaining_time": "11:00:02"}
+{"current_steps": 1040, "total_steps": 4023, "loss": 0.5478, "lr": 5e-06, "epoch": 0.7755406413124534, "percentage": 25.85, "elapsed_time": "3:49:21", "remaining_time": "10:57:51"}
+{"current_steps": 1050, "total_steps": 4023, "loss": 0.5578, "lr": 5e-06, "epoch": 0.7829977628635347, "percentage": 26.1, "elapsed_time": "3:51:33", "remaining_time": "10:55:39"}
+{"current_steps": 1060, "total_steps": 4023, "loss": 0.5486, "lr": 5e-06, "epoch": 0.790454884414616, "percentage": 26.35, "elapsed_time": "3:53:46", "remaining_time": "10:53:27"}
+{"current_steps": 1070, "total_steps": 4023, "loss": 0.5453, "lr": 5e-06, "epoch": 0.7979120059656972, "percentage": 26.6, "elapsed_time": "3:55:58", "remaining_time": "10:51:15"}
+{"current_steps": 1080, "total_steps": 4023, "loss": 0.54, "lr": 5e-06, "epoch": 0.8053691275167785, "percentage": 26.85, "elapsed_time": "3:58:11", "remaining_time": "10:49:04"}
+{"current_steps": 1090, "total_steps": 4023, "loss": 0.5536, "lr": 5e-06, "epoch": 0.8128262490678598, "percentage": 27.09, "elapsed_time": "4:00:23", "remaining_time": "10:46:52"}
+{"current_steps": 1100, "total_steps": 4023, "loss": 0.5645, "lr": 5e-06, "epoch": 0.8202833706189411, "percentage": 27.34, "elapsed_time": "4:02:36", "remaining_time": "10:44:40"}
+{"current_steps": 1110, "total_steps": 4023, "loss": 0.5618, "lr": 5e-06, "epoch": 0.8277404921700223, "percentage": 27.59, "elapsed_time": "4:04:48", "remaining_time": "10:42:28"}
+{"current_steps": 1120, "total_steps": 4023, "loss": 0.5378, "lr": 5e-06, "epoch": 0.8351976137211037, "percentage": 27.84, "elapsed_time": "4:07:01", "remaining_time": "10:40:16"}
+{"current_steps": 1130, "total_steps": 4023, "loss": 0.552, "lr": 5e-06, "epoch": 0.8426547352721849, "percentage": 28.09, "elapsed_time": "4:09:13", "remaining_time": "10:38:04"}
+{"current_steps": 1140, "total_steps": 4023, "loss": 0.5474, "lr": 5e-06, "epoch": 0.8501118568232662, "percentage": 28.34, "elapsed_time": "4:11:26", "remaining_time": "10:35:51"}
+{"current_steps": 1150, "total_steps": 4023, "loss": 0.5568, "lr": 5e-06, "epoch": 0.8575689783743475, "percentage": 28.59, "elapsed_time": "4:13:38", "remaining_time": "10:33:39"}
+{"current_steps": 1160, "total_steps": 4023, "loss": 0.5343, "lr": 5e-06, "epoch": 0.8650260999254288, "percentage": 28.83, "elapsed_time": "4:15:50", "remaining_time": "10:31:26"}
+{"current_steps": 1170, "total_steps": 4023, "loss": 0.5428, "lr": 5e-06, "epoch": 0.87248322147651, "percentage": 29.08, "elapsed_time": "4:18:02", "remaining_time": "10:29:14"}
+{"current_steps": 1180, "total_steps": 4023, "loss": 0.5356, "lr": 5e-06, "epoch": 0.8799403430275914, "percentage": 29.33, "elapsed_time": "4:20:15", "remaining_time": "10:27:01"}
+{"current_steps": 1190, "total_steps": 4023, "loss": 0.5499, "lr": 5e-06, "epoch": 0.8873974645786726, "percentage": 29.58, "elapsed_time": "4:22:27", "remaining_time": "10:24:49"}
+{"current_steps": 1200, "total_steps": 4023, "loss": 0.5288, "lr": 5e-06, "epoch": 0.8948545861297539, "percentage": 29.83, "elapsed_time": "4:24:39", "remaining_time": "10:22:36"}
+{"current_steps": 1210, "total_steps": 4023, "loss": 0.5563, "lr": 5e-06, "epoch": 0.9023117076808352, "percentage": 30.08, "elapsed_time": "4:26:51", "remaining_time": "10:20:24"}
+{"current_steps": 1220, "total_steps": 4023, "loss": 0.5392, "lr": 5e-06, "epoch": 0.9097688292319165, "percentage": 30.33, "elapsed_time": "4:29:04", "remaining_time": "10:18:12"}
+{"current_steps": 1230, "total_steps": 4023, "loss": 0.551, "lr": 5e-06, "epoch": 0.9172259507829977, "percentage": 30.57, "elapsed_time": "4:31:16", "remaining_time": "10:15:59"}
+{"current_steps": 1240, "total_steps": 4023, "loss": 0.5603, "lr": 5e-06, "epoch": 0.9246830723340791, "percentage": 30.82, "elapsed_time": "4:33:28", "remaining_time": "10:13:47"}
+{"current_steps": 1250, "total_steps": 4023, "loss": 0.5468, "lr": 5e-06, "epoch": 0.9321401938851603, "percentage": 31.07, "elapsed_time": "4:35:41", "remaining_time": "10:11:34"}
+{"current_steps": 1260, "total_steps": 4023, "loss": 0.5609, "lr": 5e-06, "epoch": 0.9395973154362416, "percentage": 31.32, "elapsed_time": "4:37:53", "remaining_time": "10:09:21"}
+{"current_steps": 1270, "total_steps": 4023, "loss": 0.5592, "lr": 5e-06, "epoch": 0.947054436987323, "percentage": 31.57, "elapsed_time": "4:40:05", "remaining_time": "10:07:09"}
+{"current_steps": 1280, "total_steps": 4023, "loss": 0.5554, "lr": 5e-06, "epoch": 0.9545115585384042, "percentage": 31.82, "elapsed_time": "4:42:17", "remaining_time": "10:04:56"}
+{"current_steps": 1290, "total_steps": 4023, "loss": 0.5646, "lr": 5e-06, "epoch": 0.9619686800894854, "percentage": 32.07, "elapsed_time": "4:44:30", "remaining_time": "10:02:44"}
+{"current_steps": 1300, "total_steps": 4023, "loss": 0.5559, "lr": 5e-06, "epoch": 0.9694258016405667, "percentage": 32.31, "elapsed_time": "4:46:42", "remaining_time": "10:00:32"}
+{"current_steps": 1310, "total_steps": 4023, "loss": 0.5486, "lr": 5e-06, "epoch": 0.976882923191648, "percentage": 32.56, "elapsed_time": "4:48:54", "remaining_time": "9:58:20"}
+{"current_steps": 1320, "total_steps": 4023, "loss": 0.5341, "lr": 5e-06, "epoch": 0.9843400447427293, "percentage": 32.81, "elapsed_time": "4:51:07", "remaining_time": "9:56:08"}
+{"current_steps": 1330, "total_steps": 4023, "loss": 0.5446, "lr": 5e-06, "epoch": 0.9917971662938105, "percentage": 33.06, "elapsed_time": "4:53:19", "remaining_time": "9:53:55"}
+{"current_steps": 1340, "total_steps": 4023, "loss": 0.5404, "lr": 5e-06, "epoch": 0.9992542878448919, "percentage": 33.31, "elapsed_time": "4:55:31", "remaining_time": "9:51:42"}
+{"current_steps": 1341, "total_steps": 4023, "eval_loss": 0.5463822484016418, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "5:01:23", "remaining_time": "10:02:46"}
+{"current_steps": 1350, "total_steps": 4023, "loss": 0.4824, "lr": 5e-06, "epoch": 1.0067114093959733, "percentage": 33.56, "elapsed_time": "5:04:27", "remaining_time": "10:02:50"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:456cc46fa6bbfecb04e8e7b146891ff40cb037b99c53cd1c4f7bf6547dee0027
+size 7160