Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a15eaf3bbed538118ed24f9937adf1af772764640714e62e743bf20e0b652d9
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359127ae945db6febc2ea24506fa96ea3d8eaa50b76347038cb4a01e29ee9c98
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4fada7c8fd4356ae44cc05045a478fe601033fac69a4e3ca16add8bcfd0bb85
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3fbc941acfe8389cff2b0827d8f104b00fe794a10b97c0cab90de5a1c66df5
+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 +1,111 @@
+{"current_steps": 1, "total_steps": 333, "loss": 0.851, "lr": 3.327561176470588e-06, "epoch": 0.008983717012914094, "percentage": 0.3, "elapsed_time": "0:06:04", "remaining_time": "1 day, 9:34:20"}
+{"current_steps": 2, "total_steps": 333, "loss": 0.8589, "lr": 6.655122352941176e-06, "epoch": 0.017967434025828188, "percentage": 0.6, "elapsed_time": "0:12:10", "remaining_time": "1 day, 9:33:35"}
+{"current_steps": 3, "total_steps": 333, "loss": 0.8477, "lr": 9.982683529411766e-06, "epoch": 0.02695115103874228, "percentage": 0.9, "elapsed_time": "0:17:44", "remaining_time": "1 day, 8:30:40"}
+{"current_steps": 4, "total_steps": 333, "loss": 0.7674, "lr": 1.3310244705882352e-05, "epoch": 0.035934868051656375, "percentage": 1.2, "elapsed_time": "0:23:33", "remaining_time": "1 day, 8:17:24"}
+{"current_steps": 5, "total_steps": 333, "loss": 0.7793, "lr": 1.6637805882352943e-05, "epoch": 0.044918585064570464, "percentage": 1.5, "elapsed_time": "0:29:20", "remaining_time": "1 day, 8:04:20"}
+{"current_steps": 6, "total_steps": 333, "loss": 0.7407, "lr": 1.996536705882353e-05, "epoch": 0.05390230207748456, "percentage": 1.8, "elapsed_time": "0:35:03", "remaining_time": "1 day, 7:50:32"}
+{"current_steps": 7, "total_steps": 333, "loss": 0.7462, "lr": 2.3292928235294116e-05, "epoch": 0.06288601909039865, "percentage": 2.1, "elapsed_time": "0:41:12", "remaining_time": "1 day, 7:59:10"}
+{"current_steps": 8, "total_steps": 333, "loss": 0.6982, "lr": 2.6620489411764705e-05, "epoch": 0.07186973610331275, "percentage": 2.4, "elapsed_time": "0:46:53", "remaining_time": "1 day, 7:45:17"}
+{"current_steps": 9, "total_steps": 333, "loss": 0.6821, "lr": 2.9948050588235297e-05, "epoch": 0.08085345311622684, "percentage": 2.7, "elapsed_time": "0:52:43", "remaining_time": "1 day, 7:38:07"}
+{"current_steps": 10, "total_steps": 333, "loss": 0.6572, "lr": 3.3275611764705885e-05, "epoch": 0.08983717012914093, "percentage": 3.0, "elapsed_time": "0:58:23", "remaining_time": "1 day, 7:26:14"}
+{"current_steps": 11, "total_steps": 333, "loss": 0.6377, "lr": 3.660317294117647e-05, "epoch": 0.09882088714205503, "percentage": 3.3, "elapsed_time": "1:04:15", "remaining_time": "1 day, 7:20:57"}
+{"current_steps": 12, "total_steps": 333, "loss": 0.6226, "lr": 3.993073411764706e-05, "epoch": 0.10780460415496912, "percentage": 3.6, "elapsed_time": "1:10:20", "remaining_time": "1 day, 7:21:31"}
+{"current_steps": 13, "total_steps": 333, "loss": 0.6112, "lr": 4.325829529411765e-05, "epoch": 0.11678832116788321, "percentage": 3.9, "elapsed_time": "1:15:53", "remaining_time": "1 day, 7:08:13"}
+{"current_steps": 14, "total_steps": 333, "loss": 0.6087, "lr": 4.658585647058823e-05, "epoch": 0.1257720381807973, "percentage": 4.2, "elapsed_time": "1:21:35", "remaining_time": "1 day, 6:59:11"}
+{"current_steps": 15, "total_steps": 333, "loss": 0.6077, "lr": 4.9913417647058825e-05, "epoch": 0.13475575519371139, "percentage": 4.5, "elapsed_time": "1:27:24", "remaining_time": "1 day, 6:52:59"}
+{"current_steps": 16, "total_steps": 333, "loss": 0.5984, "lr": 5.324097882352941e-05, "epoch": 0.1437394722066255, "percentage": 4.8, "elapsed_time": "1:33:16", "remaining_time": "1 day, 6:47:57"}
+{"current_steps": 17, "total_steps": 333, "loss": 0.5822, "lr": 5.656854e-05, "epoch": 0.1527231892195396, "percentage": 5.11, "elapsed_time": "1:39:07", "remaining_time": "1 day, 6:42:38"}
+{"current_steps": 18, "total_steps": 333, "loss": 0.5763, "lr": 5.9896101176470594e-05, "epoch": 0.16170690623245368, "percentage": 5.41, "elapsed_time": "1:44:49", "remaining_time": "1 day, 6:34:28"}
+{"current_steps": 19, "total_steps": 333, "loss": 0.5756, "lr": 6.322366235294119e-05, "epoch": 0.17069062324536777, "percentage": 5.71, "elapsed_time": "1:50:43", "remaining_time": "1 day, 6:29:51"}
+{"current_steps": 20, "total_steps": 333, "loss": 0.5734, "lr": 6.655122352941177e-05, "epoch": 0.17967434025828186, "percentage": 6.01, "elapsed_time": "1:56:31", "remaining_time": "1 day, 6:23:36"}
+{"current_steps": 21, "total_steps": 333, "loss": 0.5738, "lr": 6.987878470588236e-05, "epoch": 0.18865805727119594, "percentage": 6.31, "elapsed_time": "2:02:33", "remaining_time": "1 day, 6:20:56"}
+{"current_steps": 22, "total_steps": 333, "loss": 0.5751, "lr": 7.320634588235294e-05, "epoch": 0.19764177428411006, "percentage": 6.61, "elapsed_time": "2:08:28", "remaining_time": "1 day, 6:16:09"}
+{"current_steps": 23, "total_steps": 333, "loss": 0.5699, "lr": 7.653390705882354e-05, "epoch": 0.20662549129702415, "percentage": 6.91, "elapsed_time": "2:13:57", "remaining_time": "1 day, 6:05:36"}
+{"current_steps": 24, "total_steps": 333, "loss": 0.5675, "lr": 7.986146823529412e-05, "epoch": 0.21560920830993824, "percentage": 7.21, "elapsed_time": "2:19:51", "remaining_time": "1 day, 6:00:39"}
+{"current_steps": 25, "total_steps": 333, "loss": 0.5782, "lr": 8.318902941176471e-05, "epoch": 0.22459292532285233, "percentage": 7.51, "elapsed_time": "2:25:26", "remaining_time": "1 day, 5:51:53"}
+{"current_steps": 26, "total_steps": 333, "loss": 0.5753, "lr": 8.65165905882353e-05, "epoch": 0.23357664233576642, "percentage": 7.81, "elapsed_time": "2:31:06", "remaining_time": "1 day, 5:44:16"}
+{"current_steps": 27, "total_steps": 333, "loss": 0.5693, "lr": 8.984415176470588e-05, "epoch": 0.2425603593486805, "percentage": 8.11, "elapsed_time": "2:36:33", "remaining_time": "1 day, 5:34:15"}
+{"current_steps": 28, "total_steps": 333, "loss": 0.5519, "lr": 9.317171294117647e-05, "epoch": 0.2515440763615946, "percentage": 8.41, "elapsed_time": "2:42:06", "remaining_time": "1 day, 5:25:47"}
+{"current_steps": 29, "total_steps": 333, "loss": 0.5563, "lr": 9.649927411764706e-05, "epoch": 0.2605277933745087, "percentage": 8.71, "elapsed_time": "2:47:55", "remaining_time": "1 day, 5:20:20"}
+{"current_steps": 30, "total_steps": 333, "loss": 0.5542, "lr": 9.982683529411765e-05, "epoch": 0.26951151038742277, "percentage": 9.01, "elapsed_time": "2:53:45", "remaining_time": "1 day, 5:14:55"}
+{"current_steps": 31, "total_steps": 333, "loss": 0.5533, "lr": 0.00010315439647058823, "epoch": 0.2784952274003369, "percentage": 9.31, "elapsed_time": "2:59:17", "remaining_time": "1 day, 5:06:43"}
+{"current_steps": 32, "total_steps": 333, "loss": 0.556, "lr": 0.00010648195764705882, "epoch": 0.287478944413251, "percentage": 9.61, "elapsed_time": "3:04:56", "remaining_time": "1 day, 4:59:38"}
+{"current_steps": 33, "total_steps": 333, "loss": 0.5351, "lr": 0.00010980951882352942, "epoch": 0.29646266142616506, "percentage": 9.91, "elapsed_time": "3:10:39", "remaining_time": "1 day, 4:53:16"}
+{"current_steps": 34, "total_steps": 333, "loss": 0.539, "lr": 0.00011313708, "epoch": 0.3054463784390792, "percentage": 10.21, "elapsed_time": "3:16:34", "remaining_time": "1 day, 4:48:40"}
+{"current_steps": 35, "total_steps": 333, "loss": 0.5456, "lr": 0.0001131339575294736, "epoch": 0.31443009545199324, "percentage": 10.51, "elapsed_time": "3:22:20", "remaining_time": "1 day, 4:42:44"}
+{"current_steps": 36, "total_steps": 333, "loss": 0.5434, "lr": 0.00011312459046260269, "epoch": 0.32341381246490736, "percentage": 10.81, "elapsed_time": "3:28:09", "remaining_time": "1 day, 4:37:16"}
+{"current_steps": 37, "total_steps": 333, "loss": 0.5324, "lr": 0.0001131089798334741, "epoch": 0.3323975294778215, "percentage": 11.11, "elapsed_time": "3:34:02", "remaining_time": "1 day, 4:32:20"}
+{"current_steps": 38, "total_steps": 333, "loss": 0.5411, "lr": 0.00011308712736543891, "epoch": 0.34138124649073553, "percentage": 11.41, "elapsed_time": "3:39:36", "remaining_time": "1 day, 4:24:50"}
+{"current_steps": 39, "total_steps": 333, "loss": 0.5326, "lr": 0.00011305903547092245, "epoch": 0.35036496350364965, "percentage": 11.71, "elapsed_time": "3:45:28", "remaining_time": "1 day, 4:19:40"}
+{"current_steps": 40, "total_steps": 333, "loss": 0.5349, "lr": 0.00011302470725115774, "epoch": 0.3593486805165637, "percentage": 12.01, "elapsed_time": "3:51:11", "remaining_time": "1 day, 4:13:29"}
+{"current_steps": 41, "total_steps": 333, "loss": 0.5326, "lr": 0.00011298414649584322, "epoch": 0.36833239752947783, "percentage": 12.31, "elapsed_time": "3:56:43", "remaining_time": "1 day, 4:05:54"}
+{"current_steps": 42, "total_steps": 333, "loss": 0.5323, "lr": 0.00011293735768272441, "epoch": 0.3773161145423919, "percentage": 12.61, "elapsed_time": "4:02:35", "remaining_time": "1 day, 4:00:51"}
+{"current_steps": 43, "total_steps": 333, "loss": 0.526, "lr": 0.00011288434597709956, "epoch": 0.386299831555306, "percentage": 12.91, "elapsed_time": "4:08:06", "remaining_time": "1 day, 3:53:14"}
+{"current_steps": 44, "total_steps": 333, "loss": 0.5144, "lr": 0.00011282511723124938, "epoch": 0.3952835485682201, "percentage": 13.21, "elapsed_time": "4:14:03", "remaining_time": "1 day, 3:48:40"}
+{"current_steps": 45, "total_steps": 333, "loss": 0.5354, "lr": 0.00011275967798379107, "epoch": 0.4042672655811342, "percentage": 13.51, "elapsed_time": "4:19:59", "remaining_time": "1 day, 3:43:56"}
+{"current_steps": 46, "total_steps": 333, "loss": 0.5224, "lr": 0.00011268803545895634, "epoch": 0.4132509825940483, "percentage": 13.81, "elapsed_time": "4:25:39", "remaining_time": "1 day, 3:37:27"}
+{"current_steps": 47, "total_steps": 333, "loss": 0.5212, "lr": 0.00011261019756579401, "epoch": 0.42223469960696236, "percentage": 14.11, "elapsed_time": "4:31:29", "remaining_time": "1 day, 3:32:06"}
+{"current_steps": 48, "total_steps": 333, "loss": 0.5113, "lr": 0.00011252617289729688, "epoch": 0.4312184166198765, "percentage": 14.41, "elapsed_time": "4:37:08", "remaining_time": "1 day, 3:25:30"}
+{"current_steps": 49, "total_steps": 333, "loss": 0.5164, "lr": 0.00011243597072945297, "epoch": 0.4402021336327906, "percentage": 14.71, "elapsed_time": "4:42:42", "remaining_time": "1 day, 3:18:35"}
+{"current_steps": 50, "total_steps": 333, "loss": 0.509, "lr": 0.00011233960102022164, "epoch": 0.44918585064570465, "percentage": 15.02, "elapsed_time": "4:48:35", "remaining_time": "1 day, 3:13:24"}
+{"current_steps": 51, "total_steps": 333, "loss": 0.5187, "lr": 0.00011223707440843418, "epoch": 0.45816956765861877, "percentage": 15.32, "elapsed_time": "4:54:21", "remaining_time": "1 day, 3:07:39"}
+{"current_steps": 52, "total_steps": 333, "loss": 0.5239, "lr": 0.00011212840221261932, "epoch": 0.46715328467153283, "percentage": 15.62, "elapsed_time": "4:59:59", "remaining_time": "1 day, 3:01:07"}
+{"current_steps": 53, "total_steps": 333, "loss": 0.5109, "lr": 0.00011201359642975381, "epoch": 0.47613700168444695, "percentage": 15.92, "elapsed_time": "5:05:50", "remaining_time": "1 day, 2:55:45"}
+{"current_steps": 54, "total_steps": 333, "loss": 0.5202, "lr": 0.00011189266973393787, "epoch": 0.485120718697361, "percentage": 16.22, "elapsed_time": "5:11:25", "remaining_time": "1 day, 2:48:59"}
+{"current_steps": 55, "total_steps": 333, "loss": 0.5194, "lr": 0.00011176563547499611, "epoch": 0.4941044357102751, "percentage": 16.52, "elapsed_time": "5:17:06", "remaining_time": "1 day, 2:42:48"}
+{"current_steps": 56, "total_steps": 333, "loss": 0.5084, "lr": 0.00011163250767700374, "epoch": 0.5030881527231892, "percentage": 16.82, "elapsed_time": "5:22:49", "remaining_time": "1 day, 2:36:49"}
+{"current_steps": 57, "total_steps": 333, "loss": 0.5163, "lr": 0.00011149330103673833, "epoch": 0.5120718697361033, "percentage": 17.12, "elapsed_time": "5:28:46", "remaining_time": "1 day, 2:31:55"}
+{"current_steps": 58, "total_steps": 333, "loss": 0.509, "lr": 0.00011134803092205739, "epoch": 0.5210555867490174, "percentage": 17.42, "elapsed_time": "5:34:16", "remaining_time": "1 day, 2:24:54"}
+{"current_steps": 59, "total_steps": 333, "loss": 0.5128, "lr": 0.00011119671337020184, "epoch": 0.5300393037619315, "percentage": 17.72, "elapsed_time": "5:40:01", "remaining_time": "1 day, 2:19:07"}
+{"current_steps": 60, "total_steps": 333, "loss": 0.5146, "lr": 0.00011103936508602549, "epoch": 0.5390230207748455, "percentage": 18.02, "elapsed_time": "5:45:24", "remaining_time": "1 day, 2:11:37"}
+{"current_steps": 61, "total_steps": 333, "loss": 0.5058, "lr": 0.00011087600344015093, "epoch": 0.5480067377877597, "percentage": 18.32, "elapsed_time": "5:51:16", "remaining_time": "1 day, 2:06:22"}
+{"current_steps": 62, "total_steps": 333, "loss": 0.4989, "lr": 0.0001107066464670519, "epoch": 0.5569904548006738, "percentage": 18.62, "elapsed_time": "5:57:02", "remaining_time": "1 day, 2:00:35"}
+{"current_steps": 63, "total_steps": 333, "loss": 0.5104, "lr": 0.00011053131286306234, "epoch": 0.5659741718135879, "percentage": 18.92, "elapsed_time": "6:02:41", "remaining_time": "1 day, 1:54:25"}
+{"current_steps": 64, "total_steps": 333, "loss": 0.4952, "lr": 0.00011035002198431236, "epoch": 0.574957888826502, "percentage": 19.22, "elapsed_time": "6:08:26", "remaining_time": "1 day, 1:48:36"}
+{"current_steps": 65, "total_steps": 333, "loss": 0.4991, "lr": 0.00011016279384459147, "epoch": 0.583941605839416, "percentage": 19.52, "elapsed_time": "6:14:06", "remaining_time": "1 day, 1:42:28"}
+{"current_steps": 66, "total_steps": 333, "loss": 0.4997, "lr": 0.00010996964911313906, "epoch": 0.5929253228523301, "percentage": 19.82, "elapsed_time": "6:19:55", "remaining_time": "1 day, 1:36:56"}
+{"current_steps": 67, "total_steps": 333, "loss": 0.4937, "lr": 0.00010977060911236265, "epoch": 0.6019090398652442, "percentage": 20.12, "elapsed_time": "6:25:27", "remaining_time": "1 day, 1:30:18"}
+{"current_steps": 68, "total_steps": 333, "loss": 0.5039, "lr": 0.00010956569581548399, "epoch": 0.6108927568781584, "percentage": 20.42, "elapsed_time": "6:31:26", "remaining_time": "1 day, 1:25:28"}
+{"current_steps": 69, "total_steps": 333, "loss": 0.4932, "lr": 0.00010935493184411321, "epoch": 0.6198764738910725, "percentage": 20.72, "elapsed_time": "6:37:08", "remaining_time": "1 day, 1:19:28"}
+{"current_steps": 70, "total_steps": 333, "loss": 0.4954, "lr": 0.00010913834046575162, "epoch": 0.6288601909039865, "percentage": 21.02, "elapsed_time": "6:43:00", "remaining_time": "1 day, 1:14:10"}
+{"current_steps": 71, "total_steps": 333, "loss": 0.4916, "lr": 0.00010891594559122298, "epoch": 0.6378439079169006, "percentage": 21.32, "elapsed_time": "6:48:51", "remaining_time": "1 day, 1:08:45"}
+{"current_steps": 72, "total_steps": 333, "loss": 0.4877, "lr": 0.00010868777177203387, "epoch": 0.6468276249298147, "percentage": 21.62, "elapsed_time": "6:54:22", "remaining_time": "1 day, 1:02:05"}
+{"current_steps": 73, "total_steps": 333, "loss": 0.4959, "lr": 0.00010845384419766329, "epoch": 0.6558113419427288, "percentage": 21.92, "elapsed_time": "7:00:03", "remaining_time": "1 day, 0:56:05"}
+{"current_steps": 74, "total_steps": 333, "loss": 0.4925, "lr": 0.00010821418869278185, "epoch": 0.664795058955643, "percentage": 22.22, "elapsed_time": "7:05:28", "remaining_time": "1 day, 0:49:10"}
+{"current_steps": 75, "total_steps": 333, "loss": 0.4901, "lr": 0.00010796883171440082, "epoch": 0.673778775968557, "percentage": 22.52, "elapsed_time": "7:11:15", "remaining_time": "1 day, 0:43:31"}
+{"current_steps": 76, "total_steps": 333, "loss": 0.5053, "lr": 0.00010771780034895143, "epoch": 0.6827624929814711, "percentage": 22.82, "elapsed_time": "7:17:03", "remaining_time": "1 day, 0:37:58"}
+{"current_steps": 77, "total_steps": 333, "loss": 0.4896, "lr": 0.00010746112230929458, "epoch": 0.6917462099943852, "percentage": 23.12, "elapsed_time": "7:22:46", "remaining_time": "1 day, 0:32:05"}
+{"current_steps": 78, "total_steps": 333, "loss": 0.4913, "lr": 0.00010719882593166137, "epoch": 0.7007299270072993, "percentage": 23.42, "elapsed_time": "7:28:39", "remaining_time": "1 day, 0:26:46"}
+{"current_steps": 79, "total_steps": 333, "loss": 0.4809, "lr": 0.00010693094017252518, "epoch": 0.7097136440202133, "percentage": 23.72, "elapsed_time": "7:34:11", "remaining_time": "1 day, 0:20:20"}
+{"current_steps": 80, "total_steps": 333, "loss": 0.4965, "lr": 0.00010665749460540463, "epoch": 0.7186973610331274, "percentage": 24.02, "elapsed_time": "7:39:54", "remaining_time": "1 day, 0:14:26"}
+{"current_steps": 81, "total_steps": 333, "loss": 0.4868, "lr": 0.00010637851941759905, "epoch": 0.7276810780460415, "percentage": 24.32, "elapsed_time": "7:45:41", "remaining_time": "1 day, 0:08:48"}
+{"current_steps": 82, "total_steps": 333, "loss": 0.4804, "lr": 0.00010609404540685576, "epoch": 0.7366647950589557, "percentage": 24.62, "elapsed_time": "7:51:38", "remaining_time": "1 day, 0:03:40"}
+{"current_steps": 83, "total_steps": 333, "loss": 0.4993, "lr": 0.00010580410397797024, "epoch": 0.7456485120718698, "percentage": 24.92, "elapsed_time": "7:57:28", "remaining_time": "23:58:11"}
+{"current_steps": 84, "total_steps": 333, "loss": 0.4848, "lr": 0.0001055087271393191, "epoch": 0.7546322290847838, "percentage": 25.23, "elapsed_time": "8:03:11", "remaining_time": "23:52:19"}
+{"current_steps": 85, "total_steps": 333, "loss": 0.4835, "lr": 0.00010520794749932649, "epoch": 0.7636159460976979, "percentage": 25.53, "elapsed_time": "8:09:04", "remaining_time": "23:46:57"}
+{"current_steps": 86, "total_steps": 333, "loss": 0.4858, "lr": 0.00010490179826286422, "epoch": 0.772599663110612, "percentage": 25.83, "elapsed_time": "8:14:57", "remaining_time": "23:41:32"}
+{"current_steps": 87, "total_steps": 333, "loss": 0.477, "lr": 0.00010459031322758622, "epoch": 0.7815833801235261, "percentage": 26.13, "elapsed_time": "8:20:41", "remaining_time": "23:35:44"}
+{"current_steps": 88, "total_steps": 333, "loss": 0.4857, "lr": 0.00010427352678019722, "epoch": 0.7905670971364402, "percentage": 26.43, "elapsed_time": "8:26:31", "remaining_time": "23:30:14"}
+{"current_steps": 89, "total_steps": 333, "loss": 0.4704, "lr": 0.00010395147389265675, "epoch": 0.7995508141493542, "percentage": 26.73, "elapsed_time": "8:32:27", "remaining_time": "23:24:57"}
+{"current_steps": 90, "total_steps": 333, "loss": 0.4795, "lr": 0.00010362419011831827, "epoch": 0.8085345311622684, "percentage": 27.03, "elapsed_time": "8:38:32", "remaining_time": "23:20:03"}
+{"current_steps": 91, "total_steps": 333, "loss": 0.4802, "lr": 0.0001032917115880043, "epoch": 0.8175182481751825, "percentage": 27.33, "elapsed_time": "8:44:25", "remaining_time": "23:14:37"}
+{"current_steps": 92, "total_steps": 333, "loss": 0.473, "lr": 0.00010295407500601769, "epoch": 0.8265019651880966, "percentage": 27.63, "elapsed_time": "8:50:04", "remaining_time": "23:08:33"}
+{"current_steps": 93, "total_steps": 333, "loss": 0.4711, "lr": 0.00010261131764608956, "epoch": 0.8354856822010107, "percentage": 27.93, "elapsed_time": "8:55:43", "remaining_time": "23:02:30"}
+{"current_steps": 94, "total_steps": 333, "loss": 0.471, "lr": 0.00010226347734726456, "epoch": 0.8444693992139247, "percentage": 28.23, "elapsed_time": "9:01:31", "remaining_time": "22:56:50"}
+{"current_steps": 95, "total_steps": 333, "loss": 0.4742, "lr": 0.00010191059250972342, "epoch": 0.8534531162268388, "percentage": 28.53, "elapsed_time": "9:07:16", "remaining_time": "22:51:03"}
+{"current_steps": 96, "total_steps": 333, "loss": 0.4798, "lr": 0.00010155270209054387, "epoch": 0.862436833239753, "percentage": 28.83, "elapsed_time": "9:13:09", "remaining_time": "22:45:35"}
+{"current_steps": 97, "total_steps": 333, "loss": 0.4797, "lr": 0.00010118984559939985, "epoch": 0.8714205502526671, "percentage": 29.13, "elapsed_time": "9:19:02", "remaining_time": "22:40:09"}
+{"current_steps": 98, "total_steps": 333, "loss": 0.4623, "lr": 0.00010082206309419983, "epoch": 0.8804042672655812, "percentage": 29.43, "elapsed_time": "9:25:08", "remaining_time": "22:35:11"}
+{"current_steps": 99, "total_steps": 333, "loss": 0.4752, "lr": 0.00010044939517666461, "epoch": 0.8893879842784952, "percentage": 29.73, "elapsed_time": "9:30:45", "remaining_time": "22:29:02"}
+{"current_steps": 100, "total_steps": 333, "loss": 0.461, "lr": 0.00010007188298784493, "epoch": 0.8983717012914093, "percentage": 30.03, "elapsed_time": "9:36:42", "remaining_time": "22:23:44"}
+{"current_steps": 101, "total_steps": 333, "loss": 0.4743, "lr": 9.968956820357984e-05, "epoch": 0.9073554183043234, "percentage": 30.33, "elapsed_time": "9:42:28", "remaining_time": "22:17:58"}
+{"current_steps": 102, "total_steps": 333, "loss": 0.4623, "lr": 9.93024930298957e-05, "epoch": 0.9163391353172375, "percentage": 30.63, "elapsed_time": "9:48:15", "remaining_time": "22:12:14"}
+{"current_steps": 103, "total_steps": 333, "loss": 0.4766, "lr": 9.891070019834687e-05, "epoch": 0.9253228523301515, "percentage": 30.93, "elapsed_time": "9:53:51", "remaining_time": "22:06:06"}
+{"current_steps": 104, "total_steps": 333, "loss": 0.4636, "lr": 9.851423296129832e-05, "epoch": 0.9343065693430657, "percentage": 31.23, "elapsed_time": "9:59:30", "remaining_time": "22:00:04"}
+{"current_steps": 105, "total_steps": 333, "loss": 0.4742, "lr": 9.811313508715075e-05, "epoch": 0.9432902863559798, "percentage": 31.53, "elapsed_time": "10:05:20", "remaining_time": "21:54:28"}
+{"current_steps": 106, "total_steps": 333, "loss": 0.4621, "lr": 9.77074508555087e-05, "epoch": 0.9522740033688939, "percentage": 31.83, "elapsed_time": "10:11:13", "remaining_time": "21:48:56"}
+{"current_steps": 107, "total_steps": 333, "loss": 0.4664, "lr": 9.729722505229225e-05, "epoch": 0.961257720381808, "percentage": 32.13, "elapsed_time": "10:16:43", "remaining_time": "21:42:36"}
+{"current_steps": 108, "total_steps": 333, "loss": 0.4606, "lr": 9.68825029647929e-05, "epoch": 0.970241437394722, "percentage": 32.43, "elapsed_time": "10:22:13", "remaining_time": "21:36:19"}
+{"current_steps": 109, "total_steps": 333, "loss": 0.4626, "lr": 9.646333037667394e-05, "epoch": 0.9792251544076361, "percentage": 32.73, "elapsed_time": "10:27:57", "remaining_time": "21:30:29"}
+{"current_steps": 110, "total_steps": 333, "loss": 0.4721, "lr": 9.603975356291622e-05, "epoch": 0.9882088714205502, "percentage": 33.03, "elapsed_time": "10:33:33", "remaining_time": "21:24:24"}
+{"current_steps": 111, "total_steps": 333, "loss": 0.4678, "lr": 9.561181928470947e-05, "epoch": 0.9971925884334644, "percentage": 33.33, "elapsed_time": "10:39:19", "remaining_time": "21:18:39"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01053a09d97328987fc93911df8a307ba49407dfba41830a9f6caf5f50bdca33
+size 7224