Training in progress, step 100

.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 sha256:18f7cb8640d4ad91cd3f2d1d25a3aac7d9d30cd094ab6e37098595ac5ebe71e7
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf658da7b4856014fb47b16eb1dd9b415c79bb631c50139a76e9a0b795bf7b94
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900e2fa01d4bc2c7d1ce38b7aa4fce9cb3f9db8ea2edb3a071c80595b1e64c89
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2147fd455cc41371c783f47dcbe75ef5b43401c086402064fdb8865233548855
+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 +1,107 @@
+{"current_steps": 1, "total_steps": 438, "loss": 0.8592, "lr": 2.2727272727272729e-07, "epoch": 0.00684931506849315, "percentage": 0.23, "elapsed_time": "0:00:32", "remaining_time": "3:55:12"}
+{"current_steps": 2, "total_steps": 438, "loss": 0.8441, "lr": 4.5454545454545457e-07, "epoch": 0.0136986301369863, "percentage": 0.46, "elapsed_time": "0:00:54", "remaining_time": "3:19:26"}
+{"current_steps": 3, "total_steps": 438, "loss": 0.8847, "lr": 6.818181818181818e-07, "epoch": 0.02054794520547945, "percentage": 0.68, "elapsed_time": "0:01:15", "remaining_time": "3:02:52"}
+{"current_steps": 4, "total_steps": 438, "loss": 0.8802, "lr": 9.090909090909091e-07, "epoch": 0.0273972602739726, "percentage": 0.91, "elapsed_time": "0:01:36", "remaining_time": "2:54:07"}
+{"current_steps": 5, "total_steps": 438, "loss": 0.9015, "lr": 1.1363636363636364e-06, "epoch": 0.03424657534246575, "percentage": 1.14, "elapsed_time": "0:01:56", "remaining_time": "2:47:50"}
+{"current_steps": 6, "total_steps": 438, "loss": 0.8771, "lr": 1.3636363636363636e-06, "epoch": 0.0410958904109589, "percentage": 1.37, "elapsed_time": "0:02:19", "remaining_time": "2:47:22"}
+{"current_steps": 7, "total_steps": 438, "loss": 0.8668, "lr": 1.590909090909091e-06, "epoch": 0.04794520547945205, "percentage": 1.6, "elapsed_time": "0:02:43", "remaining_time": "2:47:24"}
+{"current_steps": 8, "total_steps": 438, "loss": 0.8269, "lr": 1.8181818181818183e-06, "epoch": 0.0547945205479452, "percentage": 1.83, "elapsed_time": "0:03:05", "remaining_time": "2:45:58"}
+{"current_steps": 9, "total_steps": 438, "loss": 0.7879, "lr": 2.0454545454545457e-06, "epoch": 0.06164383561643835, "percentage": 2.05, "elapsed_time": "0:03:24", "remaining_time": "2:42:31"}
+{"current_steps": 10, "total_steps": 438, "loss": 0.7631, "lr": 2.2727272727272728e-06, "epoch": 0.0684931506849315, "percentage": 2.28, "elapsed_time": "0:03:42", "remaining_time": "2:38:55"}
+{"current_steps": 11, "total_steps": 438, "loss": 0.7555, "lr": 2.5e-06, "epoch": 0.07534246575342465, "percentage": 2.51, "elapsed_time": "0:04:07", "remaining_time": "2:40:08"}
+{"current_steps": 12, "total_steps": 438, "loss": 0.7413, "lr": 2.7272727272727272e-06, "epoch": 0.0821917808219178, "percentage": 2.74, "elapsed_time": "0:04:30", "remaining_time": "2:39:59"}
+{"current_steps": 13, "total_steps": 438, "loss": 0.7588, "lr": 2.954545454545455e-06, "epoch": 0.08904109589041095, "percentage": 2.97, "elapsed_time": "0:04:51", "remaining_time": "2:39:05"}
+{"current_steps": 14, "total_steps": 438, "loss": 0.7552, "lr": 3.181818181818182e-06, "epoch": 0.0958904109589041, "percentage": 3.2, "elapsed_time": "0:05:13", "remaining_time": "2:38:12"}
+{"current_steps": 15, "total_steps": 438, "loss": 0.7653, "lr": 3.409090909090909e-06, "epoch": 0.10273972602739725, "percentage": 3.42, "elapsed_time": "0:05:34", "remaining_time": "2:37:05"}
+{"current_steps": 16, "total_steps": 438, "loss": 0.7895, "lr": 3.6363636363636366e-06, "epoch": 0.1095890410958904, "percentage": 3.65, "elapsed_time": "0:05:56", "remaining_time": "2:36:44"}
+{"current_steps": 17, "total_steps": 438, "loss": 0.7636, "lr": 3.863636363636364e-06, "epoch": 0.11643835616438356, "percentage": 3.88, "elapsed_time": "0:06:17", "remaining_time": "2:35:59"}
+{"current_steps": 18, "total_steps": 438, "loss": 0.7197, "lr": 4.0909090909090915e-06, "epoch": 0.1232876712328767, "percentage": 4.11, "elapsed_time": "0:06:39", "remaining_time": "2:35:32"}
+{"current_steps": 19, "total_steps": 438, "loss": 0.6567, "lr": 4.3181818181818185e-06, "epoch": 0.13013698630136986, "percentage": 4.34, "elapsed_time": "0:07:01", "remaining_time": "2:34:58"}
+{"current_steps": 20, "total_steps": 438, "loss": 0.7121, "lr": 4.5454545454545455e-06, "epoch": 0.136986301369863, "percentage": 4.57, "elapsed_time": "0:07:23", "remaining_time": "2:34:21"}
+{"current_steps": 21, "total_steps": 438, "loss": 0.7, "lr": 4.772727272727273e-06, "epoch": 0.14383561643835616, "percentage": 4.79, "elapsed_time": "0:07:46", "remaining_time": "2:34:14"}
+{"current_steps": 22, "total_steps": 438, "loss": 0.6897, "lr": 5e-06, "epoch": 0.1506849315068493, "percentage": 5.02, "elapsed_time": "0:08:05", "remaining_time": "2:33:08"}
+{"current_steps": 23, "total_steps": 438, "loss": 0.668, "lr": 5.2272727272727274e-06, "epoch": 0.15753424657534246, "percentage": 5.25, "elapsed_time": "0:08:28", "remaining_time": "2:32:47"}
+{"current_steps": 24, "total_steps": 438, "loss": 0.6585, "lr": 5.4545454545454545e-06, "epoch": 0.1643835616438356, "percentage": 5.48, "elapsed_time": "0:08:49", "remaining_time": "2:32:10"}
+{"current_steps": 25, "total_steps": 438, "loss": 0.6639, "lr": 5.681818181818183e-06, "epoch": 0.17123287671232876, "percentage": 5.71, "elapsed_time": "0:09:08", "remaining_time": "2:31:06"}
+{"current_steps": 26, "total_steps": 438, "loss": 0.6519, "lr": 5.90909090909091e-06, "epoch": 0.1780821917808219, "percentage": 5.94, "elapsed_time": "0:09:30", "remaining_time": "2:30:47"}
+{"current_steps": 27, "total_steps": 438, "loss": 0.6133, "lr": 6.136363636363637e-06, "epoch": 0.18493150684931506, "percentage": 6.16, "elapsed_time": "0:09:54", "remaining_time": "2:30:47"}
+{"current_steps": 28, "total_steps": 438, "loss": 0.6404, "lr": 6.363636363636364e-06, "epoch": 0.1917808219178082, "percentage": 6.39, "elapsed_time": "0:10:14", "remaining_time": "2:30:05"}
+{"current_steps": 29, "total_steps": 438, "loss": 0.6385, "lr": 6.590909090909091e-06, "epoch": 0.19863013698630136, "percentage": 6.62, "elapsed_time": "0:10:34", "remaining_time": "2:29:12"}
+{"current_steps": 30, "total_steps": 438, "loss": 0.6447, "lr": 6.818181818181818e-06, "epoch": 0.2054794520547945, "percentage": 6.85, "elapsed_time": "0:10:58", "remaining_time": "2:29:12"}
+{"current_steps": 31, "total_steps": 438, "loss": 0.6244, "lr": 7.045454545454546e-06, "epoch": 0.21232876712328766, "percentage": 7.08, "elapsed_time": "0:11:19", "remaining_time": "2:28:36"}
+{"current_steps": 32, "total_steps": 438, "loss": 0.6137, "lr": 7.272727272727273e-06, "epoch": 0.2191780821917808, "percentage": 7.31, "elapsed_time": "0:11:39", "remaining_time": "2:27:57"}
+{"current_steps": 33, "total_steps": 438, "loss": 0.6211, "lr": 7.500000000000001e-06, "epoch": 0.22602739726027396, "percentage": 7.53, "elapsed_time": "0:12:00", "remaining_time": "2:27:17"}
+{"current_steps": 34, "total_steps": 438, "loss": 0.6034, "lr": 7.727272727272727e-06, "epoch": 0.2328767123287671, "percentage": 7.76, "elapsed_time": "0:12:21", "remaining_time": "2:26:46"}
+{"current_steps": 35, "total_steps": 438, "loss": 0.6151, "lr": 7.954545454545455e-06, "epoch": 0.23972602739726026, "percentage": 7.99, "elapsed_time": "0:12:44", "remaining_time": "2:26:38"}
+{"current_steps": 36, "total_steps": 438, "loss": 0.5855, "lr": 8.181818181818183e-06, "epoch": 0.2465753424657534, "percentage": 8.22, "elapsed_time": "0:13:05", "remaining_time": "2:26:13"}
+{"current_steps": 37, "total_steps": 438, "loss": 0.6001, "lr": 8.40909090909091e-06, "epoch": 0.2534246575342466, "percentage": 8.45, "elapsed_time": "0:13:27", "remaining_time": "2:25:51"}
+{"current_steps": 38, "total_steps": 438, "loss": 0.5876, "lr": 8.636363636363637e-06, "epoch": 0.2602739726027397, "percentage": 8.68, "elapsed_time": "0:13:49", "remaining_time": "2:25:33"}
+{"current_steps": 39, "total_steps": 438, "loss": 0.5883, "lr": 8.863636363636365e-06, "epoch": 0.2671232876712329, "percentage": 8.9, "elapsed_time": "0:14:08", "remaining_time": "2:24:35"}
+{"current_steps": 40, "total_steps": 438, "loss": 0.5614, "lr": 9.090909090909091e-06, "epoch": 0.273972602739726, "percentage": 9.13, "elapsed_time": "0:14:27", "remaining_time": "2:23:52"}
+{"current_steps": 41, "total_steps": 438, "loss": 0.6156, "lr": 9.318181818181819e-06, "epoch": 0.2808219178082192, "percentage": 9.36, "elapsed_time": "0:14:47", "remaining_time": "2:23:18"}
+{"current_steps": 42, "total_steps": 438, "loss": 0.586, "lr": 9.545454545454547e-06, "epoch": 0.2876712328767123, "percentage": 9.59, "elapsed_time": "0:15:08", "remaining_time": "2:22:43"}
+{"current_steps": 43, "total_steps": 438, "loss": 0.5747, "lr": 9.772727272727273e-06, "epoch": 0.2945205479452055, "percentage": 9.82, "elapsed_time": "0:15:26", "remaining_time": "2:21:49"}
+{"current_steps": 44, "total_steps": 438, "loss": 0.5419, "lr": 1e-05, "epoch": 0.3013698630136986, "percentage": 10.05, "elapsed_time": "0:15:46", "remaining_time": "2:21:14"}
+{"current_steps": 45, "total_steps": 438, "loss": 0.568, "lr": 9.999841055681184e-06, "epoch": 0.3082191780821918, "percentage": 10.27, "elapsed_time": "0:16:08", "remaining_time": "2:20:58"}
+{"current_steps": 46, "total_steps": 438, "loss": 0.5715, "lr": 9.999364232830053e-06, "epoch": 0.3150684931506849, "percentage": 10.5, "elapsed_time": "0:16:27", "remaining_time": "2:20:18"}
+{"current_steps": 47, "total_steps": 438, "loss": 0.5492, "lr": 9.99856956176192e-06, "epoch": 0.3219178082191781, "percentage": 10.73, "elapsed_time": "0:16:50", "remaining_time": "2:20:07"}
+{"current_steps": 48, "total_steps": 438, "loss": 0.5849, "lr": 9.997457093000165e-06, "epoch": 0.3287671232876712, "percentage": 10.96, "elapsed_time": "0:17:11", "remaining_time": "2:19:40"}
+{"current_steps": 49, "total_steps": 438, "loss": 0.585, "lr": 9.996026897273024e-06, "epoch": 0.3356164383561644, "percentage": 11.19, "elapsed_time": "0:17:32", "remaining_time": "2:19:11"}
+{"current_steps": 50, "total_steps": 438, "loss": 0.5813, "lr": 9.994279065509094e-06, "epoch": 0.3424657534246575, "percentage": 11.42, "elapsed_time": "0:17:54", "remaining_time": "2:19:00"}
+{"current_steps": 51, "total_steps": 438, "loss": 0.5576, "lr": 9.992213708831542e-06, "epoch": 0.3493150684931507, "percentage": 11.64, "elapsed_time": "0:18:14", "remaining_time": "2:18:23"}
+{"current_steps": 52, "total_steps": 438, "loss": 0.5776, "lr": 9.989830958551058e-06, "epoch": 0.3561643835616438, "percentage": 11.87, "elapsed_time": "0:18:34", "remaining_time": "2:17:56"}
+{"current_steps": 53, "total_steps": 438, "loss": 0.5973, "lr": 9.987130966157486e-06, "epoch": 0.363013698630137, "percentage": 12.1, "elapsed_time": "0:18:56", "remaining_time": "2:17:36"}
+{"current_steps": 54, "total_steps": 438, "loss": 0.5383, "lr": 9.984113903310206e-06, "epoch": 0.3698630136986301, "percentage": 12.33, "elapsed_time": "0:19:18", "remaining_time": "2:17:20"}
+{"current_steps": 55, "total_steps": 438, "loss": 0.5371, "lr": 9.98077996182722e-06, "epoch": 0.3767123287671233, "percentage": 12.56, "elapsed_time": "0:19:39", "remaining_time": "2:16:50"}
+{"current_steps": 56, "total_steps": 438, "loss": 0.5708, "lr": 9.977129353672951e-06, "epoch": 0.3835616438356164, "percentage": 12.79, "elapsed_time": "0:20:01", "remaining_time": "2:16:34"}
+{"current_steps": 57, "total_steps": 438, "loss": 0.5777, "lr": 9.973162310944769e-06, "epoch": 0.3904109589041096, "percentage": 13.01, "elapsed_time": "0:20:23", "remaining_time": "2:16:19"}
+{"current_steps": 58, "total_steps": 438, "loss": 0.5366, "lr": 9.968879085858234e-06, "epoch": 0.3972602739726027, "percentage": 13.24, "elapsed_time": "0:20:41", "remaining_time": "2:15:36"}
+{"current_steps": 59, "total_steps": 438, "loss": 0.5822, "lr": 9.964279950731066e-06, "epoch": 0.4041095890410959, "percentage": 13.47, "elapsed_time": "0:21:03", "remaining_time": "2:15:17"}
+{"current_steps": 60, "total_steps": 438, "loss": 0.5814, "lr": 9.959365197965824e-06, "epoch": 0.410958904109589, "percentage": 13.7, "elapsed_time": "0:21:23", "remaining_time": "2:14:47"}
+{"current_steps": 61, "total_steps": 438, "loss": 0.5594, "lr": 9.954135140031322e-06, "epoch": 0.4178082191780822, "percentage": 13.93, "elapsed_time": "0:21:44", "remaining_time": "2:14:24"}
+{"current_steps": 62, "total_steps": 438, "loss": 0.5516, "lr": 9.948590109442755e-06, "epoch": 0.4246575342465753, "percentage": 14.16, "elapsed_time": "0:22:05", "remaining_time": "2:13:58"}
+{"current_steps": 63, "total_steps": 438, "loss": 0.5335, "lr": 9.942730458740568e-06, "epoch": 0.4315068493150685, "percentage": 14.38, "elapsed_time": "0:22:24", "remaining_time": "2:13:21"}
+{"current_steps": 64, "total_steps": 438, "loss": 0.5421, "lr": 9.936556560468037e-06, "epoch": 0.4383561643835616, "percentage": 14.61, "elapsed_time": "0:22:43", "remaining_time": "2:12:48"}
+{"current_steps": 65, "total_steps": 438, "loss": 0.5375, "lr": 9.930068807147585e-06, "epoch": 0.4452054794520548, "percentage": 14.84, "elapsed_time": "0:23:03", "remaining_time": "2:12:19"}
+{"current_steps": 66, "total_steps": 438, "loss": 0.5605, "lr": 9.923267611255824e-06, "epoch": 0.4520547945205479, "percentage": 15.07, "elapsed_time": "0:23:24", "remaining_time": "2:11:57"}
+{"current_steps": 67, "total_steps": 438, "loss": 0.5229, "lr": 9.916153405197333e-06, "epoch": 0.4589041095890411, "percentage": 15.3, "elapsed_time": "0:23:41", "remaining_time": "2:11:11"}
+{"current_steps": 68, "total_steps": 438, "loss": 0.5364, "lr": 9.908726641277167e-06, "epoch": 0.4657534246575342, "percentage": 15.53, "elapsed_time": "0:24:03", "remaining_time": "2:10:56"}
+{"current_steps": 69, "total_steps": 438, "loss": 0.5351, "lr": 9.9009877916721e-06, "epoch": 0.4726027397260274, "percentage": 15.75, "elapsed_time": "0:24:23", "remaining_time": "2:10:28"}
+{"current_steps": 70, "total_steps": 438, "loss": 0.543, "lr": 9.8929373484006e-06, "epoch": 0.4794520547945205, "percentage": 15.98, "elapsed_time": "0:24:43", "remaining_time": "2:10:00"}
+{"current_steps": 71, "total_steps": 438, "loss": 0.5959, "lr": 9.884575823291561e-06, "epoch": 0.4863013698630137, "percentage": 16.21, "elapsed_time": "0:25:04", "remaining_time": "2:09:36"}
+{"current_steps": 72, "total_steps": 438, "loss": 0.569, "lr": 9.875903747951742e-06, "epoch": 0.4931506849315068, "percentage": 16.44, "elapsed_time": "0:25:26", "remaining_time": "2:09:19"}
+{"current_steps": 73, "total_steps": 438, "loss": 0.5376, "lr": 9.866921673731991e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:25:48", "remaining_time": "2:09:04"}
+{"current_steps": 74, "total_steps": 438, "loss": 0.5356, "lr": 9.857630171692175e-06, "epoch": 0.5068493150684932, "percentage": 16.89, "elapsed_time": "0:26:10", "remaining_time": "2:08:45"}
+{"current_steps": 75, "total_steps": 438, "loss": 0.5151, "lr": 9.848029832564875e-06, "epoch": 0.5136986301369864, "percentage": 17.12, "elapsed_time": "0:26:29", "remaining_time": "2:08:12"}
+{"current_steps": 76, "total_steps": 438, "loss": 0.5274, "lr": 9.83812126671784e-06, "epoch": 0.5205479452054794, "percentage": 17.35, "elapsed_time": "0:26:51", "remaining_time": "2:07:55"}
+{"current_steps": 77, "total_steps": 438, "loss": 0.5365, "lr": 9.827905104115167e-06, "epoch": 0.5273972602739726, "percentage": 17.58, "elapsed_time": "0:27:12", "remaining_time": "2:07:34"}
+{"current_steps": 78, "total_steps": 438, "loss": 0.5463, "lr": 9.81738199427726e-06, "epoch": 0.5342465753424658, "percentage": 17.81, "elapsed_time": "0:27:33", "remaining_time": "2:07:13"}
+{"current_steps": 79, "total_steps": 438, "loss": 0.5346, "lr": 9.80655260623953e-06, "epoch": 0.541095890410959, "percentage": 18.04, "elapsed_time": "0:27:51", "remaining_time": "2:06:34"}
+{"current_steps": 80, "total_steps": 438, "loss": 0.5553, "lr": 9.795417628509857e-06, "epoch": 0.547945205479452, "percentage": 18.26, "elapsed_time": "0:28:12", "remaining_time": "2:06:12"}
+{"current_steps": 81, "total_steps": 438, "loss": 0.5467, "lr": 9.783977769024821e-06, "epoch": 0.5547945205479452, "percentage": 18.49, "elapsed_time": "0:28:33", "remaining_time": "2:05:53"}
+{"current_steps": 82, "total_steps": 438, "loss": 0.5365, "lr": 9.772233755104695e-06, "epoch": 0.5616438356164384, "percentage": 18.72, "elapsed_time": "0:28:55", "remaining_time": "2:05:32"}
+{"current_steps": 83, "total_steps": 438, "loss": 0.5366, "lr": 9.76018633340719e-06, "epoch": 0.5684931506849316, "percentage": 18.95, "elapsed_time": "0:29:15", "remaining_time": "2:05:07"}
+{"current_steps": 84, "total_steps": 438, "loss": 0.5549, "lr": 9.747836269880005e-06, "epoch": 0.5753424657534246, "percentage": 19.18, "elapsed_time": "0:29:36", "remaining_time": "2:04:47"}
+{"current_steps": 85, "total_steps": 438, "loss": 0.5605, "lr": 9.73518434971211e-06, "epoch": 0.5821917808219178, "percentage": 19.41, "elapsed_time": "0:29:58", "remaining_time": "2:04:27"}
+{"current_steps": 86, "total_steps": 438, "loss": 0.5304, "lr": 9.722231377283841e-06, "epoch": 0.589041095890411, "percentage": 19.63, "elapsed_time": "0:30:15", "remaining_time": "2:03:50"}
+{"current_steps": 87, "total_steps": 438, "loss": 0.5392, "lr": 9.70897817611575e-06, "epoch": 0.5958904109589042, "percentage": 19.86, "elapsed_time": "0:30:36", "remaining_time": "2:03:28"}
+{"current_steps": 88, "total_steps": 438, "loss": 0.536, "lr": 9.695425588816248e-06, "epoch": 0.6027397260273972, "percentage": 20.09, "elapsed_time": "0:30:57", "remaining_time": "2:03:09"}
+{"current_steps": 89, "total_steps": 438, "loss": 0.531, "lr": 9.681574477028039e-06, "epoch": 0.6095890410958904, "percentage": 20.32, "elapsed_time": "0:31:15", "remaining_time": "2:02:33"}
+{"current_steps": 90, "total_steps": 438, "loss": 0.5239, "lr": 9.667425721373333e-06, "epoch": 0.6164383561643836, "percentage": 20.55, "elapsed_time": "0:31:32", "remaining_time": "2:01:58"}
+{"current_steps": 91, "total_steps": 438, "loss": 0.5462, "lr": 9.65298022139786e-06, "epoch": 0.6232876712328768, "percentage": 20.78, "elapsed_time": "0:31:55", "remaining_time": "2:01:43"}
+{"current_steps": 92, "total_steps": 438, "loss": 0.496, "lr": 9.638238895513687e-06, "epoch": 0.6301369863013698, "percentage": 21.0, "elapsed_time": "0:32:16", "remaining_time": "2:01:24"}
+{"current_steps": 93, "total_steps": 438, "loss": 0.5521, "lr": 9.623202680940811e-06, "epoch": 0.636986301369863, "percentage": 21.23, "elapsed_time": "0:32:37", "remaining_time": "2:01:03"}
+{"current_steps": 94, "total_steps": 438, "loss": 0.5576, "lr": 9.607872533647584e-06, "epoch": 0.6438356164383562, "percentage": 21.46, "elapsed_time": "0:32:58", "remaining_time": "2:00:41"}
+{"current_steps": 95, "total_steps": 438, "loss": 0.5461, "lr": 9.592249428289935e-06, "epoch": 0.6506849315068494, "percentage": 21.69, "elapsed_time": "0:33:18", "remaining_time": "2:00:17"}
+{"current_steps": 96, "total_steps": 438, "loss": 0.5065, "lr": 9.5763343581494e-06, "epoch": 0.6575342465753424, "percentage": 21.92, "elapsed_time": "0:33:41", "remaining_time": "2:00:00"}
+{"current_steps": 97, "total_steps": 438, "loss": 0.5649, "lr": 9.560128335069971e-06, "epoch": 0.6643835616438356, "percentage": 22.15, "elapsed_time": "0:34:02", "remaining_time": "1:59:39"}
+{"current_steps": 98, "total_steps": 438, "loss": 0.5235, "lr": 9.543632389393767e-06, "epoch": 0.6712328767123288, "percentage": 22.37, "elapsed_time": "0:34:23", "remaining_time": "1:59:17"}
+{"current_steps": 99, "total_steps": 438, "loss": 0.5454, "lr": 9.526847569895529e-06, "epoch": 0.678082191780822, "percentage": 22.6, "elapsed_time": "0:34:45", "remaining_time": "1:59:00"}
+{"current_steps": 100, "total_steps": 438, "loss": 0.5445, "lr": 9.50977494371594e-06, "epoch": 0.684931506849315, "percentage": 22.83, "elapsed_time": "0:35:04", "remaining_time": "1:58:34"}
+{"current_steps": 101, "total_steps": 438, "loss": 0.5241, "lr": 9.49241559629377e-06, "epoch": 0.6917808219178082, "percentage": 23.06, "elapsed_time": "0:36:12", "remaining_time": "2:00:48"}
+{"current_steps": 102, "total_steps": 438, "loss": 0.512, "lr": 9.474770631296882e-06, "epoch": 0.6986301369863014, "percentage": 23.29, "elapsed_time": "0:36:35", "remaining_time": "2:00:30"}
+{"current_steps": 103, "total_steps": 438, "loss": 0.5387, "lr": 9.456841170552054e-06, "epoch": 0.7054794520547946, "percentage": 23.52, "elapsed_time": "0:36:56", "remaining_time": "2:00:09"}
+{"current_steps": 104, "total_steps": 438, "loss": 0.5454, "lr": 9.438628353973654e-06, "epoch": 0.7123287671232876, "percentage": 23.74, "elapsed_time": "0:37:17", "remaining_time": "1:59:44"}
+{"current_steps": 105, "total_steps": 438, "loss": 0.4957, "lr": 9.420133339491171e-06, "epoch": 0.7191780821917808, "percentage": 23.97, "elapsed_time": "0:37:36", "remaining_time": "1:59:15"}
+{"current_steps": 106, "total_steps": 438, "loss": 0.5745, "lr": 9.4013573029756e-06, "epoch": 0.726027397260274, "percentage": 24.2, "elapsed_time": "0:37:55", "remaining_time": "1:58:47"}
+{"current_steps": 107, "total_steps": 438, "loss": 0.5289, "lr": 9.382301438164673e-06, "epoch": 0.7328767123287672, "percentage": 24.43, "elapsed_time": "0:38:15", "remaining_time": "1:58:21"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74819334b840dbf74549bdc40bd2ac4fa048ef1b1a22e3c08585203ee52ca43a
+size 7352