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 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5989a640d2b4bf6fe09f65540e8cecbec36fcaad93cdaf450bb3d9bfcfc586
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12f42479c3e23545c6d9d423da38100150638e2c315e9dfb88577301db7f179
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b14b0fb998740ce8ae7926fe771960f446fc1c011a56066070eb13056edecf
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3993adb714382094cecfb777227e40fb48f2667a8176daaeb3bc7eac11d5c2cc
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,106 @@
+{"current_steps": 1, "total_steps": 525, "loss": 1.5676, "lr": 1.509433962264151e-06, "epoch": 0.009523809523809525, "percentage": 0.19, "elapsed_time": "0:02:21", "remaining_time": "20:34:34"}
+{"current_steps": 2, "total_steps": 525, "loss": 1.5671, "lr": 3.018867924528302e-06, "epoch": 0.01904761904761905, "percentage": 0.38, "elapsed_time": "0:04:01", "remaining_time": "17:33:00"}
+{"current_steps": 3, "total_steps": 525, "loss": 1.5511, "lr": 4.528301886792453e-06, "epoch": 0.02857142857142857, "percentage": 0.57, "elapsed_time": "0:05:42", "remaining_time": "16:31:53"}
+{"current_steps": 4, "total_steps": 525, "loss": 1.5083, "lr": 6.037735849056604e-06, "epoch": 0.0380952380952381, "percentage": 0.76, "elapsed_time": "0:07:21", "remaining_time": "15:58:10"}
+{"current_steps": 5, "total_steps": 525, "loss": 1.4418, "lr": 7.5471698113207555e-06, "epoch": 0.047619047619047616, "percentage": 0.95, "elapsed_time": "0:09:00", "remaining_time": "15:37:12"}
+{"current_steps": 6, "total_steps": 525, "loss": 1.4431, "lr": 9.056603773584907e-06, "epoch": 0.05714285714285714, "percentage": 1.14, "elapsed_time": "0:10:40", "remaining_time": "15:23:03"}
+{"current_steps": 7, "total_steps": 525, "loss": 1.4534, "lr": 1.0566037735849058e-05, "epoch": 0.06666666666666667, "percentage": 1.33, "elapsed_time": "0:12:20", "remaining_time": "15:13:29"}
+{"current_steps": 8, "total_steps": 525, "loss": 1.4503, "lr": 1.2075471698113209e-05, "epoch": 0.0761904761904762, "percentage": 1.52, "elapsed_time": "0:14:01", "remaining_time": "15:06:38"}
+{"current_steps": 9, "total_steps": 525, "loss": 1.4895, "lr": 1.3584905660377358e-05, "epoch": 0.08571428571428572, "percentage": 1.71, "elapsed_time": "0:15:41", "remaining_time": "14:59:13"}
+{"current_steps": 10, "total_steps": 525, "loss": 1.4558, "lr": 1.5094339622641511e-05, "epoch": 0.09523809523809523, "percentage": 1.9, "elapsed_time": "0:17:20", "remaining_time": "14:53:04"}
+{"current_steps": 11, "total_steps": 525, "loss": 1.4005, "lr": 1.6603773584905664e-05, "epoch": 0.10476190476190476, "percentage": 2.1, "elapsed_time": "0:18:59", "remaining_time": "14:47:38"}
+{"current_steps": 12, "total_steps": 525, "loss": 1.353, "lr": 1.8113207547169813e-05, "epoch": 0.11428571428571428, "percentage": 2.29, "elapsed_time": "0:20:39", "remaining_time": "14:42:51"}
+{"current_steps": 13, "total_steps": 525, "loss": 1.3221, "lr": 1.9622641509433963e-05, "epoch": 0.12380952380952381, "percentage": 2.48, "elapsed_time": "0:22:18", "remaining_time": "14:38:31"}
+{"current_steps": 14, "total_steps": 525, "loss": 1.3029, "lr": 2.1132075471698115e-05, "epoch": 0.13333333333333333, "percentage": 2.67, "elapsed_time": "0:23:57", "remaining_time": "14:34:34"}
+{"current_steps": 15, "total_steps": 525, "loss": 1.304, "lr": 2.2641509433962265e-05, "epoch": 0.14285714285714285, "percentage": 2.86, "elapsed_time": "0:25:36", "remaining_time": "14:30:55"}
+{"current_steps": 16, "total_steps": 525, "loss": 1.2618, "lr": 2.4150943396226418e-05, "epoch": 0.1523809523809524, "percentage": 3.05, "elapsed_time": "0:27:17", "remaining_time": "14:28:04"}
+{"current_steps": 17, "total_steps": 525, "loss": 1.2583, "lr": 2.5660377358490567e-05, "epoch": 0.1619047619047619, "percentage": 3.24, "elapsed_time": "0:28:57", "remaining_time": "14:25:25"}
+{"current_steps": 18, "total_steps": 525, "loss": 1.2703, "lr": 2.7169811320754716e-05, "epoch": 0.17142857142857143, "percentage": 3.43, "elapsed_time": "0:30:37", "remaining_time": "14:22:23"}
+{"current_steps": 19, "total_steps": 525, "loss": 1.2392, "lr": 2.867924528301887e-05, "epoch": 0.18095238095238095, "percentage": 3.62, "elapsed_time": "0:32:17", "remaining_time": "14:19:50"}
+{"current_steps": 20, "total_steps": 525, "loss": 1.2377, "lr": 3.0188679245283022e-05, "epoch": 0.19047619047619047, "percentage": 3.81, "elapsed_time": "0:33:57", "remaining_time": "14:17:31"}
+{"current_steps": 21, "total_steps": 525, "loss": 1.2123, "lr": 3.169811320754717e-05, "epoch": 0.2, "percentage": 4.0, "elapsed_time": "0:35:38", "remaining_time": "14:15:24"}
+{"current_steps": 22, "total_steps": 525, "loss": 1.2336, "lr": 3.320754716981133e-05, "epoch": 0.20952380952380953, "percentage": 4.19, "elapsed_time": "0:37:18", "remaining_time": "14:13:01"}
+{"current_steps": 23, "total_steps": 525, "loss": 1.2172, "lr": 3.471698113207548e-05, "epoch": 0.21904761904761905, "percentage": 4.38, "elapsed_time": "0:38:57", "remaining_time": "14:10:26"}
+{"current_steps": 24, "total_steps": 525, "loss": 1.2173, "lr": 3.6226415094339626e-05, "epoch": 0.22857142857142856, "percentage": 4.57, "elapsed_time": "0:40:37", "remaining_time": "14:08:13"}
+{"current_steps": 25, "total_steps": 525, "loss": 1.201, "lr": 3.7735849056603776e-05, "epoch": 0.23809523809523808, "percentage": 4.76, "elapsed_time": "0:42:19", "remaining_time": "14:06:22"}
+{"current_steps": 26, "total_steps": 525, "loss": 1.2083, "lr": 3.9245283018867925e-05, "epoch": 0.24761904761904763, "percentage": 4.95, "elapsed_time": "0:43:59", "remaining_time": "14:04:11"}
+{"current_steps": 27, "total_steps": 525, "loss": 1.2032, "lr": 4.075471698113208e-05, "epoch": 0.2571428571428571, "percentage": 5.14, "elapsed_time": "0:45:38", "remaining_time": "14:01:48"}
+{"current_steps": 28, "total_steps": 525, "loss": 1.1896, "lr": 4.226415094339623e-05, "epoch": 0.26666666666666666, "percentage": 5.33, "elapsed_time": "0:47:18", "remaining_time": "13:59:35"}
+{"current_steps": 29, "total_steps": 525, "loss": 1.1955, "lr": 4.377358490566038e-05, "epoch": 0.2761904761904762, "percentage": 5.52, "elapsed_time": "0:48:59", "remaining_time": "13:57:48"}
+{"current_steps": 30, "total_steps": 525, "loss": 1.1714, "lr": 4.528301886792453e-05, "epoch": 0.2857142857142857, "percentage": 5.71, "elapsed_time": "0:50:38", "remaining_time": "13:55:31"}
+{"current_steps": 31, "total_steps": 525, "loss": 1.1935, "lr": 4.679245283018868e-05, "epoch": 0.29523809523809524, "percentage": 5.9, "elapsed_time": "0:52:17", "remaining_time": "13:53:19"}
+{"current_steps": 32, "total_steps": 525, "loss": 1.1823, "lr": 4.8301886792452835e-05, "epoch": 0.3047619047619048, "percentage": 6.1, "elapsed_time": "0:53:56", "remaining_time": "13:51:06"}
+{"current_steps": 33, "total_steps": 525, "loss": 1.1844, "lr": 4.9811320754716985e-05, "epoch": 0.3142857142857143, "percentage": 6.29, "elapsed_time": "0:55:36", "remaining_time": "13:48:58"}
+{"current_steps": 34, "total_steps": 525, "loss": 1.168, "lr": 5.1320754716981134e-05, "epoch": 0.3238095238095238, "percentage": 6.48, "elapsed_time": "0:57:16", "remaining_time": "13:47:06"}
+{"current_steps": 35, "total_steps": 525, "loss": 1.175, "lr": 5.283018867924528e-05, "epoch": 0.3333333333333333, "percentage": 6.67, "elapsed_time": "0:58:55", "remaining_time": "13:45:00"}
+{"current_steps": 36, "total_steps": 525, "loss": 1.1885, "lr": 5.433962264150943e-05, "epoch": 0.34285714285714286, "percentage": 6.86, "elapsed_time": "1:00:35", "remaining_time": "13:42:56"}
+{"current_steps": 37, "total_steps": 525, "loss": 1.1609, "lr": 5.584905660377359e-05, "epoch": 0.3523809523809524, "percentage": 7.05, "elapsed_time": "1:02:15", "remaining_time": "13:41:05"}
+{"current_steps": 38, "total_steps": 525, "loss": 1.1627, "lr": 5.735849056603774e-05, "epoch": 0.3619047619047619, "percentage": 7.24, "elapsed_time": "1:03:55", "remaining_time": "13:39:14"}
+{"current_steps": 39, "total_steps": 525, "loss": 1.1599, "lr": 5.886792452830189e-05, "epoch": 0.37142857142857144, "percentage": 7.43, "elapsed_time": "1:05:36", "remaining_time": "13:37:35"}
+{"current_steps": 40, "total_steps": 525, "loss": 1.1639, "lr": 6.0377358490566044e-05, "epoch": 0.38095238095238093, "percentage": 7.62, "elapsed_time": "1:07:15", "remaining_time": "13:35:34"}
+{"current_steps": 41, "total_steps": 525, "loss": 1.1672, "lr": 6.18867924528302e-05, "epoch": 0.3904761904761905, "percentage": 7.81, "elapsed_time": "1:08:55", "remaining_time": "13:33:34"}
+{"current_steps": 42, "total_steps": 525, "loss": 1.1621, "lr": 6.339622641509434e-05, "epoch": 0.4, "percentage": 8.0, "elapsed_time": "1:10:35", "remaining_time": "13:31:43"}
+{"current_steps": 43, "total_steps": 525, "loss": 1.1624, "lr": 6.49056603773585e-05, "epoch": 0.4095238095238095, "percentage": 8.19, "elapsed_time": "1:12:15", "remaining_time": "13:29:54"}
+{"current_steps": 44, "total_steps": 525, "loss": 1.1505, "lr": 6.641509433962266e-05, "epoch": 0.41904761904761906, "percentage": 8.38, "elapsed_time": "1:13:55", "remaining_time": "13:28:07"}
+{"current_steps": 45, "total_steps": 525, "loss": 1.1661, "lr": 6.79245283018868e-05, "epoch": 0.42857142857142855, "percentage": 8.57, "elapsed_time": "1:15:34", "remaining_time": "13:26:10"}
+{"current_steps": 46, "total_steps": 525, "loss": 1.1519, "lr": 6.943396226415095e-05, "epoch": 0.4380952380952381, "percentage": 8.76, "elapsed_time": "1:17:14", "remaining_time": "13:24:14"}
+{"current_steps": 47, "total_steps": 525, "loss": 1.1397, "lr": 7.09433962264151e-05, "epoch": 0.44761904761904764, "percentage": 8.95, "elapsed_time": "1:18:53", "remaining_time": "13:22:18"}
+{"current_steps": 48, "total_steps": 525, "loss": 1.1496, "lr": 7.245283018867925e-05, "epoch": 0.45714285714285713, "percentage": 9.14, "elapsed_time": "1:20:32", "remaining_time": "13:20:24"}
+{"current_steps": 49, "total_steps": 525, "loss": 1.1646, "lr": 7.396226415094341e-05, "epoch": 0.4666666666666667, "percentage": 9.33, "elapsed_time": "1:22:12", "remaining_time": "13:18:31"}
+{"current_steps": 50, "total_steps": 525, "loss": 1.1446, "lr": 7.547169811320755e-05, "epoch": 0.47619047619047616, "percentage": 9.52, "elapsed_time": "1:23:51", "remaining_time": "13:16:37"}
+{"current_steps": 51, "total_steps": 525, "loss": 1.1521, "lr": 7.698113207547171e-05, "epoch": 0.4857142857142857, "percentage": 9.71, "elapsed_time": "1:25:30", "remaining_time": "13:14:43"}
+{"current_steps": 52, "total_steps": 525, "loss": 1.1501, "lr": 7.849056603773585e-05, "epoch": 0.49523809523809526, "percentage": 9.9, "elapsed_time": "1:27:10", "remaining_time": "13:12:58"}
+{"current_steps": 53, "total_steps": 525, "loss": 1.1558, "lr": 8e-05, "epoch": 0.5047619047619047, "percentage": 10.1, "elapsed_time": "1:28:50", "remaining_time": "13:11:07"}
+{"current_steps": 54, "total_steps": 525, "loss": 1.1478, "lr": 7.99991139787449e-05, "epoch": 0.5142857142857142, "percentage": 10.29, "elapsed_time": "1:30:29", "remaining_time": "13:09:15"}
+{"current_steps": 55, "total_steps": 525, "loss": 1.1522, "lr": 7.999645595423128e-05, "epoch": 0.5238095238095238, "percentage": 10.48, "elapsed_time": "1:32:08", "remaining_time": "13:07:24"}
+{"current_steps": 56, "total_steps": 525, "loss": 1.1488, "lr": 7.999202604421244e-05, "epoch": 0.5333333333333333, "percentage": 10.67, "elapsed_time": "1:33:48", "remaining_time": "13:05:35"}
+{"current_steps": 57, "total_steps": 525, "loss": 1.135, "lr": 7.998582444493811e-05, "epoch": 0.5428571428571428, "percentage": 10.86, "elapsed_time": "1:35:27", "remaining_time": "13:03:45"}
+{"current_steps": 58, "total_steps": 525, "loss": 1.1381, "lr": 7.997785143114573e-05, "epoch": 0.5523809523809524, "percentage": 11.05, "elapsed_time": "1:37:06", "remaining_time": "13:01:55"}
+{"current_steps": 59, "total_steps": 525, "loss": 1.1488, "lr": 7.996810735604828e-05, "epoch": 0.5619047619047619, "percentage": 11.24, "elapsed_time": "1:38:46", "remaining_time": "13:00:07"}
+{"current_steps": 60, "total_steps": 525, "loss": 1.1486, "lr": 7.995659265131865e-05, "epoch": 0.5714285714285714, "percentage": 11.43, "elapsed_time": "1:40:26", "remaining_time": "12:58:27"}
+{"current_steps": 61, "total_steps": 525, "loss": 1.1463, "lr": 7.994330782707048e-05, "epoch": 0.580952380952381, "percentage": 11.62, "elapsed_time": "1:42:06", "remaining_time": "12:56:37"}
+{"current_steps": 62, "total_steps": 525, "loss": 1.1422, "lr": 7.992825347183563e-05, "epoch": 0.5904761904761905, "percentage": 11.81, "elapsed_time": "1:43:45", "remaining_time": "12:54:48"}
+{"current_steps": 63, "total_steps": 525, "loss": 1.1281, "lr": 7.991143025253801e-05, "epoch": 0.6, "percentage": 12.0, "elapsed_time": "1:45:24", "remaining_time": "12:52:59"}
+{"current_steps": 64, "total_steps": 525, "loss": 1.1509, "lr": 7.989283891446413e-05, "epoch": 0.6095238095238096, "percentage": 12.19, "elapsed_time": "1:47:03", "remaining_time": "12:51:11"}
+{"current_steps": 65, "total_steps": 525, "loss": 1.161, "lr": 7.987248028123001e-05, "epoch": 0.6190476190476191, "percentage": 12.38, "elapsed_time": "1:48:43", "remaining_time": "12:49:23"}
+{"current_steps": 66, "total_steps": 525, "loss": 1.1583, "lr": 7.985035525474475e-05, "epoch": 0.6285714285714286, "percentage": 12.57, "elapsed_time": "1:50:22", "remaining_time": "12:47:35"}
+{"current_steps": 67, "total_steps": 525, "loss": 1.1442, "lr": 7.982646481517054e-05, "epoch": 0.638095238095238, "percentage": 12.76, "elapsed_time": "1:52:01", "remaining_time": "12:45:47"}
+{"current_steps": 68, "total_steps": 525, "loss": 1.1401, "lr": 7.980081002087923e-05, "epoch": 0.6476190476190476, "percentage": 12.95, "elapsed_time": "1:53:40", "remaining_time": "12:44:00"}
+{"current_steps": 69, "total_steps": 525, "loss": 1.1488, "lr": 7.97733920084055e-05, "epoch": 0.6571428571428571, "percentage": 13.14, "elapsed_time": "1:55:20", "remaining_time": "12:42:13"}
+{"current_steps": 70, "total_steps": 525, "loss": 1.1241, "lr": 7.97442119923964e-05, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "1:56:59", "remaining_time": "12:40:26"}
+{"current_steps": 71, "total_steps": 525, "loss": 1.1383, "lr": 7.971327126555767e-05, "epoch": 0.6761904761904762, "percentage": 13.52, "elapsed_time": "1:58:39", "remaining_time": "12:38:46"}
+{"current_steps": 72, "total_steps": 525, "loss": 1.132, "lr": 7.968057119859639e-05, "epoch": 0.6857142857142857, "percentage": 13.71, "elapsed_time": "2:00:19", "remaining_time": "12:37:00"}
+{"current_steps": 73, "total_steps": 525, "loss": 1.1326, "lr": 7.96461132401603e-05, "epoch": 0.6952380952380952, "percentage": 13.9, "elapsed_time": "2:01:58", "remaining_time": "12:35:14"}
+{"current_steps": 74, "total_steps": 525, "loss": 1.131, "lr": 7.960989891677354e-05, "epoch": 0.7047619047619048, "percentage": 14.1, "elapsed_time": "2:03:37", "remaining_time": "12:33:28"}
+{"current_steps": 75, "total_steps": 525, "loss": 1.1286, "lr": 7.957192983276915e-05, "epoch": 0.7142857142857143, "percentage": 14.29, "elapsed_time": "2:05:16", "remaining_time": "12:31:41"}
+{"current_steps": 76, "total_steps": 525, "loss": 1.1334, "lr": 7.953220767021789e-05, "epoch": 0.7238095238095238, "percentage": 14.48, "elapsed_time": "2:06:56", "remaining_time": "12:29:56"}
+{"current_steps": 77, "total_steps": 525, "loss": 1.1268, "lr": 7.949073418885378e-05, "epoch": 0.7333333333333333, "percentage": 14.67, "elapsed_time": "2:08:35", "remaining_time": "12:28:11"}
+{"current_steps": 78, "total_steps": 525, "loss": 1.13, "lr": 7.944751122599613e-05, "epoch": 0.7428571428571429, "percentage": 14.86, "elapsed_time": "2:10:15", "remaining_time": "12:26:26"}
+{"current_steps": 79, "total_steps": 525, "loss": 1.1219, "lr": 7.940254069646813e-05, "epoch": 0.7523809523809524, "percentage": 15.05, "elapsed_time": "2:11:54", "remaining_time": "12:24:41"}
+{"current_steps": 80, "total_steps": 525, "loss": 1.1219, "lr": 7.935582459251202e-05, "epoch": 0.7619047619047619, "percentage": 15.24, "elapsed_time": "2:13:33", "remaining_time": "12:22:56"}
+{"current_steps": 81, "total_steps": 525, "loss": 1.1096, "lr": 7.930736498370085e-05, "epoch": 0.7714285714285715, "percentage": 15.43, "elapsed_time": "2:15:12", "remaining_time": "12:21:11"}
+{"current_steps": 82, "total_steps": 525, "loss": 1.119, "lr": 7.925716401684678e-05, "epoch": 0.780952380952381, "percentage": 15.62, "elapsed_time": "2:16:52", "remaining_time": "12:19:25"}
+{"current_steps": 83, "total_steps": 525, "loss": 1.1236, "lr": 7.920522391590604e-05, "epoch": 0.7904761904761904, "percentage": 15.81, "elapsed_time": "2:18:31", "remaining_time": "12:17:40"}
+{"current_steps": 84, "total_steps": 525, "loss": 1.1324, "lr": 7.915154698188027e-05, "epoch": 0.8, "percentage": 16.0, "elapsed_time": "2:20:10", "remaining_time": "12:15:55"}
+{"current_steps": 85, "total_steps": 525, "loss": 1.1136, "lr": 7.909613559271467e-05, "epoch": 0.8095238095238095, "percentage": 16.19, "elapsed_time": "2:21:49", "remaining_time": "12:14:11"}
+{"current_steps": 86, "total_steps": 525, "loss": 1.1226, "lr": 7.90389922031927e-05, "epoch": 0.819047619047619, "percentage": 16.38, "elapsed_time": "2:23:29", "remaining_time": "12:12:26"}
+{"current_steps": 87, "total_steps": 525, "loss": 1.1214, "lr": 7.898011934482725e-05, "epoch": 0.8285714285714286, "percentage": 16.57, "elapsed_time": "2:25:08", "remaining_time": "12:10:42"}
+{"current_steps": 88, "total_steps": 525, "loss": 1.1406, "lr": 7.89195196257485e-05, "epoch": 0.8380952380952381, "percentage": 16.76, "elapsed_time": "2:26:47", "remaining_time": "12:08:57"}
+{"current_steps": 89, "total_steps": 525, "loss": 1.1231, "lr": 7.88571957305884e-05, "epoch": 0.8476190476190476, "percentage": 16.95, "elapsed_time": "2:28:26", "remaining_time": "12:07:13"}
+{"current_steps": 90, "total_steps": 525, "loss": 1.1386, "lr": 7.879315042036176e-05, "epoch": 0.8571428571428571, "percentage": 17.14, "elapsed_time": "2:30:06", "remaining_time": "12:05:29"}
+{"current_steps": 91, "total_steps": 525, "loss": 1.1108, "lr": 7.872738653234387e-05, "epoch": 0.8666666666666667, "percentage": 17.33, "elapsed_time": "2:31:46", "remaining_time": "12:03:50"}
+{"current_steps": 92, "total_steps": 525, "loss": 1.1285, "lr": 7.865990697994488e-05, "epoch": 0.8761904761904762, "percentage": 17.52, "elapsed_time": "2:33:25", "remaining_time": "12:02:06"}
+{"current_steps": 93, "total_steps": 525, "loss": 1.1265, "lr": 7.859071475258065e-05, "epoch": 0.8857142857142857, "percentage": 17.71, "elapsed_time": "2:35:05", "remaining_time": "12:00:27"}
+{"current_steps": 94, "total_steps": 525, "loss": 1.1229, "lr": 7.85198129155404e-05, "epoch": 0.8952380952380953, "percentage": 17.9, "elapsed_time": "2:36:45", "remaining_time": "11:58:43"}
+{"current_steps": 95, "total_steps": 525, "loss": 1.1284, "lr": 7.844720460985086e-05, "epoch": 0.9047619047619048, "percentage": 18.1, "elapsed_time": "2:38:24", "remaining_time": "11:57:00"}
+{"current_steps": 96, "total_steps": 525, "loss": 1.1221, "lr": 7.837289305213715e-05, "epoch": 0.9142857142857143, "percentage": 18.29, "elapsed_time": "2:40:03", "remaining_time": "11:55:17"}
+{"current_steps": 97, "total_steps": 525, "loss": 1.122, "lr": 7.829688153448022e-05, "epoch": 0.9238095238095239, "percentage": 18.48, "elapsed_time": "2:41:43", "remaining_time": "11:53:33"}
+{"current_steps": 98, "total_steps": 525, "loss": 1.1125, "lr": 7.821917342427112e-05, "epoch": 0.9333333333333333, "percentage": 18.67, "elapsed_time": "2:43:22", "remaining_time": "11:51:50"}
+{"current_steps": 99, "total_steps": 525, "loss": 1.1098, "lr": 7.81397721640617e-05, "epoch": 0.9428571428571428, "percentage": 18.86, "elapsed_time": "2:45:02", "remaining_time": "11:50:09"}
+{"current_steps": 100, "total_steps": 525, "loss": 1.1097, "lr": 7.805868127141217e-05, "epoch": 0.9523809523809523, "percentage": 19.05, "elapsed_time": "2:46:41", "remaining_time": "11:48:26"}
+{"current_steps": 101, "total_steps": 525, "loss": 1.1146, "lr": 7.797590433873526e-05, "epoch": 0.9619047619047619, "percentage": 19.24, "elapsed_time": "2:48:20", "remaining_time": "11:46:43"}
+{"current_steps": 102, "total_steps": 525, "loss": 1.1375, "lr": 7.789144503313704e-05, "epoch": 0.9714285714285714, "percentage": 19.43, "elapsed_time": "2:50:00", "remaining_time": "11:45:01"}
+{"current_steps": 103, "total_steps": 525, "loss": 1.1191, "lr": 7.780530709625455e-05, "epoch": 0.9809523809523809, "percentage": 19.62, "elapsed_time": "2:51:39", "remaining_time": "11:43:18"}
+{"current_steps": 104, "total_steps": 525, "loss": 1.1173, "lr": 7.771749434408989e-05, "epoch": 0.9904761904761905, "percentage": 19.81, "elapsed_time": "2:53:19", "remaining_time": "11:41:36"}
+{"current_steps": 105, "total_steps": 525, "loss": 1.1137, "lr": 7.762801066684133e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "2:54:58", "remaining_time": "11:39:53"}
+{"current_steps": 106, "total_steps": 525, "loss": 1.0737, "lr": 7.753686002873087e-05, "epoch": 1.0095238095238095, "percentage": 20.19, "elapsed_time": "2:58:50", "remaining_time": "11:46:56"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e3b852f02f15f6abbccc08ab9f6192f2f38e3991be616136861fa9bfb9da66
+size 7352