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:c453d0e1ff3d46b8cb2f6586c847ad5dbbd6722dffe1f053934735faeac4d8f2
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb54e9a2cd0054b1d6717f025b77482f8a5f44df5445141450b952c0fe3589c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5159d159d1df427943fd576f9263c237883113a73e00f817c97552f70e8b7d9
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b842a85a276d1f50f445b05c3149b771930356c1e5789a3efd04e1c95ba8aa1b
+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 +1,108 @@
+{"current_steps": 1, "total_steps": 465, "loss": 0.991, "lr": 8.510638297872341e-07, "epoch": 0.010652463382157125, "percentage": 0.22, "elapsed_time": "0:00:21", "remaining_time": "2:48:34"}
+{"current_steps": 2, "total_steps": 465, "loss": 1.0148, "lr": 1.7021276595744682e-06, "epoch": 0.02130492676431425, "percentage": 0.43, "elapsed_time": "0:00:31", "remaining_time": "2:02:47"}
+{"current_steps": 3, "total_steps": 465, "loss": 1.0461, "lr": 2.553191489361702e-06, "epoch": 0.03195739014647137, "percentage": 0.65, "elapsed_time": "0:00:43", "remaining_time": "1:50:54"}
+{"current_steps": 4, "total_steps": 465, "loss": 0.952, "lr": 3.4042553191489363e-06, "epoch": 0.0426098535286285, "percentage": 0.86, "elapsed_time": "0:00:52", "remaining_time": "1:40:44"}
+{"current_steps": 5, "total_steps": 465, "loss": 0.9508, "lr": 4.255319148936171e-06, "epoch": 0.05326231691078562, "percentage": 1.08, "elapsed_time": "0:01:01", "remaining_time": "1:34:45"}
+{"current_steps": 6, "total_steps": 465, "loss": 0.8426, "lr": 5.106382978723404e-06, "epoch": 0.06391478029294274, "percentage": 1.29, "elapsed_time": "0:01:10", "remaining_time": "1:30:17"}
+{"current_steps": 7, "total_steps": 465, "loss": 0.837, "lr": 5.957446808510638e-06, "epoch": 0.07456724367509987, "percentage": 1.51, "elapsed_time": "0:01:19", "remaining_time": "1:26:51"}
+{"current_steps": 8, "total_steps": 465, "loss": 0.8044, "lr": 6.808510638297873e-06, "epoch": 0.085219707057257, "percentage": 1.72, "elapsed_time": "0:01:28", "remaining_time": "1:24:27"}
+{"current_steps": 9, "total_steps": 465, "loss": 0.7596, "lr": 7.659574468085107e-06, "epoch": 0.09587217043941411, "percentage": 1.94, "elapsed_time": "0:01:38", "remaining_time": "1:22:49"}
+{"current_steps": 10, "total_steps": 465, "loss": 0.7289, "lr": 8.510638297872341e-06, "epoch": 0.10652463382157124, "percentage": 2.15, "elapsed_time": "0:01:46", "remaining_time": "1:21:07"}
+{"current_steps": 11, "total_steps": 465, "loss": 0.6981, "lr": 9.361702127659576e-06, "epoch": 0.11717709720372836, "percentage": 2.37, "elapsed_time": "0:01:56", "remaining_time": "1:19:49"}
+{"current_steps": 12, "total_steps": 465, "loss": 0.7082, "lr": 1.0212765957446808e-05, "epoch": 0.1278295605858855, "percentage": 2.58, "elapsed_time": "0:02:04", "remaining_time": "1:18:35"}
+{"current_steps": 13, "total_steps": 465, "loss": 0.7113, "lr": 1.1063829787234044e-05, "epoch": 0.1384820239680426, "percentage": 2.8, "elapsed_time": "0:02:14", "remaining_time": "1:17:49"}
+{"current_steps": 14, "total_steps": 465, "loss": 0.7069, "lr": 1.1914893617021277e-05, "epoch": 0.14913448735019974, "percentage": 3.01, "elapsed_time": "0:02:23", "remaining_time": "1:16:56"}
+{"current_steps": 15, "total_steps": 465, "loss": 0.641, "lr": 1.2765957446808513e-05, "epoch": 0.15978695073235685, "percentage": 3.23, "elapsed_time": "0:02:32", "remaining_time": "1:16:09"}
+{"current_steps": 16, "total_steps": 465, "loss": 0.6473, "lr": 1.3617021276595745e-05, "epoch": 0.170439414114514, "percentage": 3.44, "elapsed_time": "0:02:41", "remaining_time": "1:15:22"}
+{"current_steps": 17, "total_steps": 465, "loss": 0.693, "lr": 1.4468085106382981e-05, "epoch": 0.1810918774966711, "percentage": 3.66, "elapsed_time": "0:02:50", "remaining_time": "1:14:43"}
+{"current_steps": 18, "total_steps": 465, "loss": 0.6576, "lr": 1.5319148936170214e-05, "epoch": 0.19174434087882822, "percentage": 3.87, "elapsed_time": "0:02:58", "remaining_time": "1:14:02"}
+{"current_steps": 19, "total_steps": 465, "loss": 0.6178, "lr": 1.6170212765957446e-05, "epoch": 0.20239680426098536, "percentage": 4.09, "elapsed_time": "0:03:07", "remaining_time": "1:13:32"}
+{"current_steps": 20, "total_steps": 465, "loss": 0.6735, "lr": 1.7021276595744682e-05, "epoch": 0.21304926764314247, "percentage": 4.3, "elapsed_time": "0:03:17", "remaining_time": "1:13:09"}
+{"current_steps": 21, "total_steps": 465, "loss": 0.6076, "lr": 1.7872340425531915e-05, "epoch": 0.2237017310252996, "percentage": 4.52, "elapsed_time": "0:03:26", "remaining_time": "1:12:39"}
+{"current_steps": 22, "total_steps": 465, "loss": 0.6772, "lr": 1.872340425531915e-05, "epoch": 0.23435419440745672, "percentage": 4.73, "elapsed_time": "0:03:35", "remaining_time": "1:12:17"}
+{"current_steps": 23, "total_steps": 465, "loss": 0.6153, "lr": 1.9574468085106384e-05, "epoch": 0.24500665778961384, "percentage": 4.95, "elapsed_time": "0:03:44", "remaining_time": "1:11:52"}
+{"current_steps": 24, "total_steps": 465, "loss": 0.5597, "lr": 2.0425531914893616e-05, "epoch": 0.255659121171771, "percentage": 5.16, "elapsed_time": "0:03:53", "remaining_time": "1:11:27"}
+{"current_steps": 25, "total_steps": 465, "loss": 0.603, "lr": 2.1276595744680852e-05, "epoch": 0.2663115845539281, "percentage": 5.38, "elapsed_time": "0:04:02", "remaining_time": "1:11:04"}
+{"current_steps": 26, "total_steps": 465, "loss": 0.6395, "lr": 2.2127659574468088e-05, "epoch": 0.2769640479360852, "percentage": 5.59, "elapsed_time": "0:04:11", "remaining_time": "1:10:41"}
+{"current_steps": 27, "total_steps": 465, "loss": 0.6158, "lr": 2.2978723404255324e-05, "epoch": 0.28761651131824234, "percentage": 5.81, "elapsed_time": "0:04:20", "remaining_time": "1:10:19"}
+{"current_steps": 28, "total_steps": 465, "loss": 0.6219, "lr": 2.3829787234042553e-05, "epoch": 0.2982689747003995, "percentage": 6.02, "elapsed_time": "0:04:28", "remaining_time": "1:09:56"}
+{"current_steps": 29, "total_steps": 465, "loss": 0.6232, "lr": 2.468085106382979e-05, "epoch": 0.30892143808255657, "percentage": 6.24, "elapsed_time": "0:04:37", "remaining_time": "1:09:35"}
+{"current_steps": 30, "total_steps": 465, "loss": 0.6181, "lr": 2.5531914893617025e-05, "epoch": 0.3195739014647137, "percentage": 6.45, "elapsed_time": "0:04:46", "remaining_time": "1:09:19"}
+{"current_steps": 31, "total_steps": 465, "loss": 0.6266, "lr": 2.6382978723404255e-05, "epoch": 0.33022636484687085, "percentage": 6.67, "elapsed_time": "0:04:55", "remaining_time": "1:09:01"}
+{"current_steps": 32, "total_steps": 465, "loss": 0.6693, "lr": 2.723404255319149e-05, "epoch": 0.340878828229028, "percentage": 6.88, "elapsed_time": "0:05:04", "remaining_time": "1:08:45"}
+{"current_steps": 33, "total_steps": 465, "loss": 0.6133, "lr": 2.8085106382978727e-05, "epoch": 0.35153129161118507, "percentage": 7.1, "elapsed_time": "0:05:13", "remaining_time": "1:08:27"}
+{"current_steps": 34, "total_steps": 465, "loss": 0.6235, "lr": 2.8936170212765963e-05, "epoch": 0.3621837549933422, "percentage": 7.31, "elapsed_time": "0:05:22", "remaining_time": "1:08:11"}
+{"current_steps": 35, "total_steps": 465, "loss": 0.5815, "lr": 2.9787234042553192e-05, "epoch": 0.37283621837549935, "percentage": 7.53, "elapsed_time": "0:05:32", "remaining_time": "1:08:01"}
+{"current_steps": 36, "total_steps": 465, "loss": 0.5851, "lr": 3.063829787234043e-05, "epoch": 0.38348868175765644, "percentage": 7.74, "elapsed_time": "0:05:41", "remaining_time": "1:07:44"}
+{"current_steps": 37, "total_steps": 465, "loss": 0.639, "lr": 3.1489361702127664e-05, "epoch": 0.3941411451398136, "percentage": 7.96, "elapsed_time": "0:05:50", "remaining_time": "1:07:28"}
+{"current_steps": 38, "total_steps": 465, "loss": 0.6266, "lr": 3.234042553191489e-05, "epoch": 0.4047936085219707, "percentage": 8.17, "elapsed_time": "0:05:58", "remaining_time": "1:07:13"}
+{"current_steps": 39, "total_steps": 465, "loss": 0.5787, "lr": 3.319148936170213e-05, "epoch": 0.41544607190412786, "percentage": 8.39, "elapsed_time": "0:06:07", "remaining_time": "1:06:58"}
+{"current_steps": 40, "total_steps": 465, "loss": 0.6132, "lr": 3.4042553191489365e-05, "epoch": 0.42609853528628494, "percentage": 8.6, "elapsed_time": "0:06:16", "remaining_time": "1:06:43"}
+{"current_steps": 41, "total_steps": 465, "loss": 0.6179, "lr": 3.48936170212766e-05, "epoch": 0.4367509986684421, "percentage": 8.82, "elapsed_time": "0:06:26", "remaining_time": "1:06:32"}
+{"current_steps": 42, "total_steps": 465, "loss": 0.5945, "lr": 3.574468085106383e-05, "epoch": 0.4474034620505992, "percentage": 9.03, "elapsed_time": "0:06:34", "remaining_time": "1:06:17"}
+{"current_steps": 43, "total_steps": 465, "loss": 0.5802, "lr": 3.6595744680851066e-05, "epoch": 0.4580559254327563, "percentage": 9.25, "elapsed_time": "0:06:43", "remaining_time": "1:06:03"}
+{"current_steps": 44, "total_steps": 465, "loss": 0.5802, "lr": 3.74468085106383e-05, "epoch": 0.46870838881491345, "percentage": 9.46, "elapsed_time": "0:06:52", "remaining_time": "1:05:50"}
+{"current_steps": 45, "total_steps": 465, "loss": 0.6652, "lr": 3.829787234042554e-05, "epoch": 0.4793608521970706, "percentage": 9.68, "elapsed_time": "0:07:01", "remaining_time": "1:05:36"}
+{"current_steps": 46, "total_steps": 465, "loss": 0.6015, "lr": 3.914893617021277e-05, "epoch": 0.49001331557922767, "percentage": 9.89, "elapsed_time": "0:07:10", "remaining_time": "1:05:22"}
+{"current_steps": 47, "total_steps": 465, "loss": 0.5485, "lr": 4e-05, "epoch": 0.5006657789613849, "percentage": 10.11, "elapsed_time": "0:07:19", "remaining_time": "1:05:08"}
+{"current_steps": 48, "total_steps": 465, "loss": 0.6397, "lr": 3.999943513438666e-05, "epoch": 0.511318242343542, "percentage": 10.32, "elapsed_time": "0:07:28", "remaining_time": "1:04:56"}
+{"current_steps": 49, "total_steps": 465, "loss": 0.5915, "lr": 3.9997740569453936e-05, "epoch": 0.521970705725699, "percentage": 10.54, "elapsed_time": "0:07:37", "remaining_time": "1:04:42"}
+{"current_steps": 50, "total_steps": 465, "loss": 0.6177, "lr": 3.999491640092199e-05, "epoch": 0.5326231691078562, "percentage": 10.75, "elapsed_time": "0:07:46", "remaining_time": "1:04:29"}
+{"current_steps": 51, "total_steps": 465, "loss": 0.6163, "lr": 3.999096278831838e-05, "epoch": 0.5432756324900133, "percentage": 10.97, "elapsed_time": "0:07:55", "remaining_time": "1:04:17"}
+{"current_steps": 52, "total_steps": 465, "loss": 0.6182, "lr": 3.998587995496908e-05, "epoch": 0.5539280958721704, "percentage": 11.18, "elapsed_time": "0:08:07", "remaining_time": "1:04:28"}
+{"current_steps": 53, "total_steps": 465, "loss": 0.6132, "lr": 3.997966818798589e-05, "epoch": 0.5645805592543276, "percentage": 11.4, "elapsed_time": "0:08:16", "remaining_time": "1:04:16"}
+{"current_steps": 54, "total_steps": 465, "loss": 0.6066, "lr": 3.9972327838250155e-05, "epoch": 0.5752330226364847, "percentage": 11.61, "elapsed_time": "0:08:25", "remaining_time": "1:04:05"}
+{"current_steps": 55, "total_steps": 465, "loss": 0.6299, "lr": 3.9963859320392984e-05, "epoch": 0.5858854860186418, "percentage": 11.83, "elapsed_time": "0:08:34", "remaining_time": "1:03:53"}
+{"current_steps": 56, "total_steps": 465, "loss": 0.6434, "lr": 3.995426311277184e-05, "epoch": 0.596537949400799, "percentage": 12.04, "elapsed_time": "0:08:43", "remaining_time": "1:03:40"}
+{"current_steps": 57, "total_steps": 465, "loss": 0.6381, "lr": 3.9943539757443494e-05, "epoch": 0.607190412782956, "percentage": 12.26, "elapsed_time": "0:08:52", "remaining_time": "1:03:30"}
+{"current_steps": 58, "total_steps": 465, "loss": 0.6073, "lr": 3.99316898601334e-05, "epoch": 0.6178428761651131, "percentage": 12.47, "elapsed_time": "0:09:01", "remaining_time": "1:03:18"}
+{"current_steps": 59, "total_steps": 465, "loss": 0.616, "lr": 3.991871409020153e-05, "epoch": 0.6284953395472703, "percentage": 12.69, "elapsed_time": "0:09:10", "remaining_time": "1:03:06"}
+{"current_steps": 60, "total_steps": 465, "loss": 0.5792, "lr": 3.9904613180604493e-05, "epoch": 0.6391478029294274, "percentage": 12.9, "elapsed_time": "0:09:19", "remaining_time": "1:02:54"}
+{"current_steps": 61, "total_steps": 465, "loss": 0.627, "lr": 3.9889387927854184e-05, "epoch": 0.6498002663115846, "percentage": 13.12, "elapsed_time": "0:09:28", "remaining_time": "1:02:45"}
+{"current_steps": 62, "total_steps": 465, "loss": 0.6034, "lr": 3.987303919197279e-05, "epoch": 0.6604527296937417, "percentage": 13.33, "elapsed_time": "0:09:38", "remaining_time": "1:02:37"}
+{"current_steps": 63, "total_steps": 465, "loss": 0.5677, "lr": 3.985556789644417e-05, "epoch": 0.6711051930758988, "percentage": 13.55, "elapsed_time": "0:09:47", "remaining_time": "1:02:27"}
+{"current_steps": 64, "total_steps": 465, "loss": 0.6235, "lr": 3.9836975028161735e-05, "epoch": 0.681757656458056, "percentage": 13.76, "elapsed_time": "0:09:56", "remaining_time": "1:02:20"}
+{"current_steps": 65, "total_steps": 465, "loss": 0.5673, "lr": 3.981726163737268e-05, "epoch": 0.6924101198402131, "percentage": 13.98, "elapsed_time": "0:10:05", "remaining_time": "1:02:07"}
+{"current_steps": 66, "total_steps": 465, "loss": 0.5882, "lr": 3.979642883761866e-05, "epoch": 0.7030625832223701, "percentage": 14.19, "elapsed_time": "0:10:14", "remaining_time": "1:01:56"}
+{"current_steps": 67, "total_steps": 465, "loss": 0.6291, "lr": 3.97744778056729e-05, "epoch": 0.7137150466045273, "percentage": 14.41, "elapsed_time": "0:10:23", "remaining_time": "1:01:44"}
+{"current_steps": 68, "total_steps": 465, "loss": 0.6076, "lr": 3.975140978147371e-05, "epoch": 0.7243675099866844, "percentage": 14.62, "elapsed_time": "0:10:32", "remaining_time": "1:01:32"}
+{"current_steps": 69, "total_steps": 465, "loss": 0.6376, "lr": 3.972722606805445e-05, "epoch": 0.7350199733688415, "percentage": 14.84, "elapsed_time": "0:10:41", "remaining_time": "1:01:21"}
+{"current_steps": 70, "total_steps": 465, "loss": 0.5903, "lr": 3.970192803146994e-05, "epoch": 0.7456724367509987, "percentage": 15.05, "elapsed_time": "0:10:50", "remaining_time": "1:01:11"}
+{"current_steps": 71, "total_steps": 465, "loss": 0.6174, "lr": 3.9675517100719275e-05, "epoch": 0.7563249001331558, "percentage": 15.27, "elapsed_time": "0:10:59", "remaining_time": "1:00:59"}
+{"current_steps": 72, "total_steps": 465, "loss": 0.568, "lr": 3.96479947676651e-05, "epoch": 0.7669773635153129, "percentage": 15.48, "elapsed_time": "0:11:08", "remaining_time": "1:00:47"}
+{"current_steps": 73, "total_steps": 465, "loss": 0.5989, "lr": 3.9619362586949385e-05, "epoch": 0.7776298268974701, "percentage": 15.7, "elapsed_time": "0:11:17", "remaining_time": "1:00:35"}
+{"current_steps": 74, "total_steps": 465, "loss": 0.6334, "lr": 3.958962217590556e-05, "epoch": 0.7882822902796272, "percentage": 15.91, "elapsed_time": "0:11:26", "remaining_time": "1:00:24"}
+{"current_steps": 75, "total_steps": 465, "loss": 0.5925, "lr": 3.955877521446717e-05, "epoch": 0.7989347536617842, "percentage": 16.13, "elapsed_time": "0:11:35", "remaining_time": "1:00:14"}
+{"current_steps": 76, "total_steps": 465, "loss": 0.6006, "lr": 3.952682344507301e-05, "epoch": 0.8095872170439414, "percentage": 16.34, "elapsed_time": "0:11:44", "remaining_time": "1:00:04"}
+{"current_steps": 77, "total_steps": 465, "loss": 0.6418, "lr": 3.949376867256863e-05, "epoch": 0.8202396804260985, "percentage": 16.56, "elapsed_time": "0:11:53", "remaining_time": "0:59:54"}
+{"current_steps": 78, "total_steps": 465, "loss": 0.5977, "lr": 3.94596127641045e-05, "epoch": 0.8308921438082557, "percentage": 16.77, "elapsed_time": "0:12:02", "remaining_time": "0:59:42"}
+{"current_steps": 79, "total_steps": 465, "loss": 0.6384, "lr": 3.942435764903042e-05, "epoch": 0.8415446071904128, "percentage": 16.99, "elapsed_time": "0:12:10", "remaining_time": "0:59:31"}
+{"current_steps": 80, "total_steps": 465, "loss": 0.6144, "lr": 3.938800531878661e-05, "epoch": 0.8521970705725699, "percentage": 17.2, "elapsed_time": "0:12:19", "remaining_time": "0:59:21"}
+{"current_steps": 81, "total_steps": 465, "loss": 0.6264, "lr": 3.935055782679121e-05, "epoch": 0.8628495339547271, "percentage": 17.42, "elapsed_time": "0:12:28", "remaining_time": "0:59:09"}
+{"current_steps": 82, "total_steps": 465, "loss": 0.5466, "lr": 3.931201728832427e-05, "epoch": 0.8735019973368842, "percentage": 17.63, "elapsed_time": "0:12:37", "remaining_time": "0:58:58"}
+{"current_steps": 83, "total_steps": 465, "loss": 0.6366, "lr": 3.927238588040827e-05, "epoch": 0.8841544607190412, "percentage": 17.85, "elapsed_time": "0:12:46", "remaining_time": "0:58:48"}
+{"current_steps": 84, "total_steps": 465, "loss": 0.6014, "lr": 3.923166584168518e-05, "epoch": 0.8948069241011984, "percentage": 18.06, "elapsed_time": "0:12:55", "remaining_time": "0:58:39"}
+{"current_steps": 85, "total_steps": 465, "loss": 0.6437, "lr": 3.9189859472289956e-05, "epoch": 0.9054593874833555, "percentage": 18.28, "elapsed_time": "0:13:05", "remaining_time": "0:58:32"}
+{"current_steps": 86, "total_steps": 465, "loss": 0.5745, "lr": 3.914696913372064e-05, "epoch": 0.9161118508655126, "percentage": 18.49, "elapsed_time": "0:13:14", "remaining_time": "0:58:21"}
+{"current_steps": 87, "total_steps": 465, "loss": 0.5937, "lr": 3.9102997248704994e-05, "epoch": 0.9267643142476698, "percentage": 18.71, "elapsed_time": "0:13:23", "remaining_time": "0:58:10"}
+{"current_steps": 88, "total_steps": 465, "loss": 0.6533, "lr": 3.9057946301063573e-05, "epoch": 0.9374167776298269, "percentage": 18.92, "elapsed_time": "0:13:32", "remaining_time": "0:57:58"}
+{"current_steps": 89, "total_steps": 465, "loss": 0.5759, "lr": 3.9011818835569516e-05, "epoch": 0.948069241011984, "percentage": 19.14, "elapsed_time": "0:13:41", "remaining_time": "0:57:48"}
+{"current_steps": 90, "total_steps": 465, "loss": 0.6224, "lr": 3.8964617457804716e-05, "epoch": 0.9587217043941412, "percentage": 19.35, "elapsed_time": "0:13:50", "remaining_time": "0:57:39"}
+{"current_steps": 91, "total_steps": 465, "loss": 0.624, "lr": 3.8916344834012695e-05, "epoch": 0.9693741677762983, "percentage": 19.57, "elapsed_time": "0:13:59", "remaining_time": "0:57:28"}
+{"current_steps": 92, "total_steps": 465, "loss": 0.5995, "lr": 3.886700369094799e-05, "epoch": 0.9800266311584553, "percentage": 19.78, "elapsed_time": "0:14:08", "remaining_time": "0:57:18"}
+{"current_steps": 93, "total_steps": 465, "loss": 0.6559, "lr": 3.881659681572209e-05, "epoch": 0.9906790945406125, "percentage": 20.0, "elapsed_time": "0:14:17", "remaining_time": "0:57:08"}
+{"current_steps": 94, "total_steps": 465, "loss": 0.6031, "lr": 3.876512705564605e-05, "epoch": 1.0013315579227697, "percentage": 20.22, "elapsed_time": "0:16:21", "remaining_time": "1:04:32"}
+{"current_steps": 95, "total_steps": 465, "loss": 0.4262, "lr": 3.871259731806964e-05, "epoch": 1.0119840213049267, "percentage": 20.43, "elapsed_time": "0:16:30", "remaining_time": "1:04:18"}
+{"current_steps": 96, "total_steps": 465, "loss": 0.4225, "lr": 3.865901057021709e-05, "epoch": 1.022636484687084, "percentage": 20.65, "elapsed_time": "0:16:39", "remaining_time": "1:04:03"}
+{"current_steps": 97, "total_steps": 465, "loss": 0.409, "lr": 3.8604369839019515e-05, "epoch": 1.033288948069241, "percentage": 20.86, "elapsed_time": "0:16:49", "remaining_time": "1:03:48"}
+{"current_steps": 98, "total_steps": 465, "loss": 0.3785, "lr": 3.854867821094394e-05, "epoch": 1.043941411451398, "percentage": 21.08, "elapsed_time": "0:16:58", "remaining_time": "1:03:32"}
+{"current_steps": 99, "total_steps": 465, "loss": 0.3891, "lr": 3.849193883181893e-05, "epoch": 1.0545938748335553, "percentage": 21.29, "elapsed_time": "0:17:06", "remaining_time": "1:03:16"}
+{"current_steps": 100, "total_steps": 465, "loss": 0.3586, "lr": 3.84341549066569e-05, "epoch": 1.0652463382157125, "percentage": 21.51, "elapsed_time": "0:17:15", "remaining_time": "1:03:01"}
+{"current_steps": 101, "total_steps": 465, "loss": 0.3643, "lr": 3.8375329699473083e-05, "epoch": 1.0758988015978694, "percentage": 21.72, "elapsed_time": "0:17:24", "remaining_time": "1:02:45"}
+{"current_steps": 102, "total_steps": 465, "loss": 0.3703, "lr": 3.8315466533101154e-05, "epoch": 1.0865512649800266, "percentage": 21.94, "elapsed_time": "0:17:33", "remaining_time": "1:02:29"}
+{"current_steps": 103, "total_steps": 465, "loss": 0.3968, "lr": 3.825456878900553e-05, "epoch": 1.0972037283621838, "percentage": 22.15, "elapsed_time": "0:17:43", "remaining_time": "1:02:17"}
+{"current_steps": 104, "total_steps": 465, "loss": 0.4043, "lr": 3.819263990709037e-05, "epoch": 1.1078561917443408, "percentage": 22.37, "elapsed_time": "0:17:52", "remaining_time": "1:02:04"}
+{"current_steps": 105, "total_steps": 465, "loss": 0.3844, "lr": 3.812968338550526e-05, "epoch": 1.118508655126498, "percentage": 22.58, "elapsed_time": "0:18:02", "remaining_time": "1:01:51"}
+{"current_steps": 106, "total_steps": 465, "loss": 0.4267, "lr": 3.806570278044762e-05, "epoch": 1.1291611185086552, "percentage": 22.8, "elapsed_time": "0:18:14", "remaining_time": "1:01:45"}
+{"current_steps": 107, "total_steps": 465, "loss": 0.387, "lr": 3.800070170596182e-05, "epoch": 1.1398135818908122, "percentage": 23.01, "elapsed_time": "0:18:23", "remaining_time": "1:01:30"}
+{"current_steps": 108, "total_steps": 465, "loss": 0.3916, "lr": 3.793468383373504e-05, "epoch": 1.1504660452729694, "percentage": 23.23, "elapsed_time": "0:18:31", "remaining_time": "1:01:15"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de3f4c42d0e0ea900115f10dfc618a6719ac0bc4e7445af4f3561259dfc520cb
+size 7352