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 sha256:0975ae72d3cca6948b6af30f09790ad36183de41964c36d751c2ae41cbd3d529
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34f888d49ad3744734079107dd7fb9c6b3cc1af4ab6f622283462f953a502fe
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6d74946c9d6046fe9f22327b88a0221d5261f3875fba33ffbfbeb3e6bb7ee0
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9a4795e1445a51dfcefffed086f26a92099360e6871a38fc5ded7bf08dd27c
+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 +1,103 @@
+{"current_steps": 1, "total_steps": 5415, "loss": 0.8713, "lr": 1.845018450184502e-08, "epoch": 0.0005537609598523304, "percentage": 0.02, "elapsed_time": "0:00:47", "remaining_time": "2 days, 23:14:10"}
+{"current_steps": 2, "total_steps": 5415, "loss": 0.854, "lr": 3.690036900369004e-08, "epoch": 0.0011075219197046607, "percentage": 0.04, "elapsed_time": "0:01:19", "remaining_time": "2 days, 11:41:14"}
+{"current_steps": 3, "total_steps": 5415, "loss": 0.8459, "lr": 5.5350553505535055e-08, "epoch": 0.0016612828795569913, "percentage": 0.06, "elapsed_time": "0:02:01", "remaining_time": "2 days, 12:45:01"}
+{"current_steps": 4, "total_steps": 5415, "loss": 0.8932, "lr": 7.380073800738008e-08, "epoch": 0.0022150438394093214, "percentage": 0.07, "elapsed_time": "0:02:36", "remaining_time": "2 days, 10:49:50"}
+{"current_steps": 5, "total_steps": 5415, "loss": 0.843, "lr": 9.22509225092251e-08, "epoch": 0.0027688047992616522, "percentage": 0.09, "elapsed_time": "0:03:12", "remaining_time": "2 days, 9:44:52"}
+{"current_steps": 6, "total_steps": 5415, "loss": 0.8842, "lr": 1.1070110701107011e-07, "epoch": 0.0033225657591139826, "percentage": 0.11, "elapsed_time": "0:03:37", "remaining_time": "2 days, 6:28:31"}
+{"current_steps": 7, "total_steps": 5415, "loss": 0.8816, "lr": 1.2915129151291515e-07, "epoch": 0.003876326718966313, "percentage": 0.13, "elapsed_time": "0:04:09", "remaining_time": "2 days, 5:36:42"}
+{"current_steps": 8, "total_steps": 5415, "loss": 0.874, "lr": 1.4760147601476016e-07, "epoch": 0.004430087678818643, "percentage": 0.15, "elapsed_time": "0:04:50", "remaining_time": "2 days, 6:35:19"}
+{"current_steps": 9, "total_steps": 5415, "loss": 0.9232, "lr": 1.6605166051660518e-07, "epoch": 0.004983848638670974, "percentage": 0.17, "elapsed_time": "0:05:26", "remaining_time": "2 days, 6:32:18"}
+{"current_steps": 10, "total_steps": 5415, "loss": 0.8485, "lr": 1.845018450184502e-07, "epoch": 0.0055376095985233045, "percentage": 0.18, "elapsed_time": "0:06:01", "remaining_time": "2 days, 6:17:23"}
+{"current_steps": 11, "total_steps": 5415, "loss": 0.8528, "lr": 2.029520295202952e-07, "epoch": 0.006091370558375634, "percentage": 0.2, "elapsed_time": "0:06:34", "remaining_time": "2 days, 5:51:43"}
+{"current_steps": 12, "total_steps": 5415, "loss": 0.8649, "lr": 2.2140221402214022e-07, "epoch": 0.006645131518227965, "percentage": 0.22, "elapsed_time": "0:07:10", "remaining_time": "2 days, 5:48:29"}
+{"current_steps": 13, "total_steps": 5415, "loss": 0.8968, "lr": 2.3985239852398526e-07, "epoch": 0.007198892478080295, "percentage": 0.24, "elapsed_time": "0:07:48", "remaining_time": "2 days, 6:04:55"}
+{"current_steps": 14, "total_steps": 5415, "loss": 0.8543, "lr": 2.583025830258303e-07, "epoch": 0.007752653437932626, "percentage": 0.26, "elapsed_time": "0:08:26", "remaining_time": "2 days, 6:18:54"}
+{"current_steps": 15, "total_steps": 5415, "loss": 0.8819, "lr": 2.767527675276753e-07, "epoch": 0.008306414397784956, "percentage": 0.28, "elapsed_time": "0:09:06", "remaining_time": "2 days, 6:40:33"}
+{"current_steps": 16, "total_steps": 5415, "loss": 0.8706, "lr": 2.9520295202952033e-07, "epoch": 0.008860175357637286, "percentage": 0.3, "elapsed_time": "0:09:46", "remaining_time": "2 days, 6:56:54"}
+{"current_steps": 17, "total_steps": 5415, "loss": 0.8633, "lr": 3.136531365313653e-07, "epoch": 0.009413936317489617, "percentage": 0.31, "elapsed_time": "0:10:26", "remaining_time": "2 days, 7:14:06"}
+{"current_steps": 18, "total_steps": 5415, "loss": 0.8547, "lr": 3.3210332103321035e-07, "epoch": 0.009967697277341947, "percentage": 0.33, "elapsed_time": "0:11:00", "remaining_time": "2 days, 6:59:13"}
+{"current_steps": 19, "total_steps": 5415, "loss": 0.8949, "lr": 3.5055350553505534e-07, "epoch": 0.010521458237194277, "percentage": 0.35, "elapsed_time": "0:11:36", "remaining_time": "2 days, 6:58:16"}
+{"current_steps": 20, "total_steps": 5415, "loss": 0.8716, "lr": 3.690036900369004e-07, "epoch": 0.011075219197046609, "percentage": 0.37, "elapsed_time": "0:12:08", "remaining_time": "2 days, 6:37:04"}
+{"current_steps": 21, "total_steps": 5415, "loss": 0.8533, "lr": 3.874538745387454e-07, "epoch": 0.011628980156898939, "percentage": 0.39, "elapsed_time": "0:12:47", "remaining_time": "2 days, 6:45:56"}
+{"current_steps": 22, "total_steps": 5415, "loss": 0.8052, "lr": 4.059040590405904e-07, "epoch": 0.012182741116751269, "percentage": 0.41, "elapsed_time": "0:13:20", "remaining_time": "2 days, 6:32:10"}
+{"current_steps": 23, "total_steps": 5415, "loss": 0.7964, "lr": 4.2435424354243545e-07, "epoch": 0.012736502076603599, "percentage": 0.42, "elapsed_time": "0:13:56", "remaining_time": "2 days, 6:28:03"}
+{"current_steps": 24, "total_steps": 5415, "loss": 0.8123, "lr": 4.4280442804428044e-07, "epoch": 0.01329026303645593, "percentage": 0.44, "elapsed_time": "0:14:37", "remaining_time": "2 days, 6:43:47"}
+{"current_steps": 25, "total_steps": 5415, "loss": 0.8018, "lr": 4.612546125461255e-07, "epoch": 0.01384402399630826, "percentage": 0.46, "elapsed_time": "0:15:13", "remaining_time": "2 days, 6:44:03"}
+{"current_steps": 26, "total_steps": 5415, "loss": 0.7839, "lr": 4.797047970479705e-07, "epoch": 0.01439778495616059, "percentage": 0.48, "elapsed_time": "0:15:42", "remaining_time": "2 days, 6:16:40"}
+{"current_steps": 27, "total_steps": 5415, "loss": 0.8577, "lr": 4.981549815498156e-07, "epoch": 0.014951545916012922, "percentage": 0.5, "elapsed_time": "0:16:19", "remaining_time": "2 days, 6:18:49"}
+{"current_steps": 28, "total_steps": 5415, "loss": 0.7979, "lr": 5.166051660516606e-07, "epoch": 0.015505306875865252, "percentage": 0.52, "elapsed_time": "0:16:57", "remaining_time": "2 days, 6:22:22"}
+{"current_steps": 29, "total_steps": 5415, "loss": 0.8155, "lr": 5.350553505535055e-07, "epoch": 0.01605906783571758, "percentage": 0.54, "elapsed_time": "0:17:34", "remaining_time": "2 days, 6:23:18"}
+{"current_steps": 30, "total_steps": 5415, "loss": 0.8141, "lr": 5.535055350553506e-07, "epoch": 0.01661282879556991, "percentage": 0.55, "elapsed_time": "0:18:15", "remaining_time": "2 days, 6:38:50"}
+{"current_steps": 31, "total_steps": 5415, "loss": 0.7408, "lr": 5.719557195571956e-07, "epoch": 0.01716658975542224, "percentage": 0.57, "elapsed_time": "0:18:53", "remaining_time": "2 days, 6:39:49"}
+{"current_steps": 32, "total_steps": 5415, "loss": 0.7888, "lr": 5.904059040590407e-07, "epoch": 0.01772035071527457, "percentage": 0.59, "elapsed_time": "0:19:31", "remaining_time": "2 days, 6:43:10"}
+{"current_steps": 33, "total_steps": 5415, "loss": 0.7777, "lr": 6.088560885608857e-07, "epoch": 0.018274111675126905, "percentage": 0.61, "elapsed_time": "0:20:08", "remaining_time": "2 days, 6:45:54"}
+{"current_steps": 34, "total_steps": 5415, "loss": 0.7835, "lr": 6.273062730627306e-07, "epoch": 0.018827872634979235, "percentage": 0.63, "elapsed_time": "0:20:50", "remaining_time": "2 days, 6:59:21"}
+{"current_steps": 35, "total_steps": 5415, "loss": 0.7691, "lr": 6.457564575645757e-07, "epoch": 0.019381633594831565, "percentage": 0.65, "elapsed_time": "0:21:26", "remaining_time": "2 days, 6:55:26"}
+{"current_steps": 36, "total_steps": 5415, "loss": 0.7705, "lr": 6.642066420664207e-07, "epoch": 0.019935394554683895, "percentage": 0.66, "elapsed_time": "0:22:04", "remaining_time": "2 days, 6:57:45"}
+{"current_steps": 37, "total_steps": 5415, "loss": 0.716, "lr": 6.826568265682657e-07, "epoch": 0.020489155514536225, "percentage": 0.68, "elapsed_time": "0:22:42", "remaining_time": "2 days, 7:01:53"}
+{"current_steps": 38, "total_steps": 5415, "loss": 0.7769, "lr": 7.011070110701107e-07, "epoch": 0.021042916474388555, "percentage": 0.7, "elapsed_time": "0:23:22", "remaining_time": "2 days, 7:08:03"}
+{"current_steps": 39, "total_steps": 5415, "loss": 0.7486, "lr": 7.195571955719557e-07, "epoch": 0.021596677434240884, "percentage": 0.72, "elapsed_time": "0:24:02", "remaining_time": "2 days, 7:15:00"}
+{"current_steps": 40, "total_steps": 5415, "loss": 0.7325, "lr": 7.380073800738008e-07, "epoch": 0.022150438394093218, "percentage": 0.74, "elapsed_time": "0:24:39", "remaining_time": "2 days, 7:12:31"}
+{"current_steps": 41, "total_steps": 5415, "loss": 0.7488, "lr": 7.564575645756458e-07, "epoch": 0.022704199353945548, "percentage": 0.76, "elapsed_time": "0:25:09", "remaining_time": "2 days, 6:57:16"}
+{"current_steps": 42, "total_steps": 5415, "loss": 0.751, "lr": 7.749077490774908e-07, "epoch": 0.023257960313797878, "percentage": 0.78, "elapsed_time": "0:25:40", "remaining_time": "2 days, 6:45:20"}
+{"current_steps": 43, "total_steps": 5415, "loss": 0.7274, "lr": 7.933579335793358e-07, "epoch": 0.023811721273650208, "percentage": 0.79, "elapsed_time": "0:26:16", "remaining_time": "2 days, 6:42:27"}
+{"current_steps": 44, "total_steps": 5415, "loss": 0.7461, "lr": 8.118081180811808e-07, "epoch": 0.024365482233502538, "percentage": 0.81, "elapsed_time": "0:26:51", "remaining_time": "2 days, 6:39:12"}
+{"current_steps": 45, "total_steps": 5415, "loss": 0.7651, "lr": 8.302583025830259e-07, "epoch": 0.024919243193354867, "percentage": 0.83, "elapsed_time": "0:27:27", "remaining_time": "2 days, 6:37:22"}
+{"current_steps": 46, "total_steps": 5415, "loss": 0.7047, "lr": 8.487084870848709e-07, "epoch": 0.025473004153207197, "percentage": 0.85, "elapsed_time": "0:28:07", "remaining_time": "2 days, 6:42:40"}
+{"current_steps": 47, "total_steps": 5415, "loss": 0.7399, "lr": 8.671586715867159e-07, "epoch": 0.02602676511305953, "percentage": 0.87, "elapsed_time": "0:28:45", "remaining_time": "2 days, 6:45:07"}
+{"current_steps": 48, "total_steps": 5415, "loss": 0.7262, "lr": 8.856088560885609e-07, "epoch": 0.02658052607291186, "percentage": 0.89, "elapsed_time": "0:29:24", "remaining_time": "2 days, 6:47:32"}
+{"current_steps": 49, "total_steps": 5415, "loss": 0.7224, "lr": 9.040590405904059e-07, "epoch": 0.02713428703276419, "percentage": 0.9, "elapsed_time": "0:30:02", "remaining_time": "2 days, 6:49:50"}
+{"current_steps": 50, "total_steps": 5415, "loss": 0.6945, "lr": 9.22509225092251e-07, "epoch": 0.02768804799261652, "percentage": 0.92, "elapsed_time": "0:30:36", "remaining_time": "2 days, 6:43:39"}
+{"current_steps": 51, "total_steps": 5415, "loss": 0.6827, "lr": 9.40959409594096e-07, "epoch": 0.02824180895246885, "percentage": 0.94, "elapsed_time": "0:31:11", "remaining_time": "2 days, 6:40:43"}
+{"current_steps": 52, "total_steps": 5415, "loss": 0.6776, "lr": 9.59409594095941e-07, "epoch": 0.02879556991232118, "percentage": 0.96, "elapsed_time": "0:31:52", "remaining_time": "2 days, 6:46:55"}
+{"current_steps": 53, "total_steps": 5415, "loss": 0.6763, "lr": 9.77859778597786e-07, "epoch": 0.02934933087217351, "percentage": 0.98, "elapsed_time": "0:32:29", "remaining_time": "2 days, 6:47:57"}
+{"current_steps": 54, "total_steps": 5415, "loss": 0.7397, "lr": 9.963099630996311e-07, "epoch": 0.029903091832025844, "percentage": 1.0, "elapsed_time": "0:33:07", "remaining_time": "2 days, 6:48:37"}
+{"current_steps": 55, "total_steps": 5415, "loss": 0.6846, "lr": 1.0147601476014762e-06, "epoch": 0.030456852791878174, "percentage": 1.02, "elapsed_time": "0:33:43", "remaining_time": "2 days, 6:46:30"}
+{"current_steps": 56, "total_steps": 5415, "loss": 0.6997, "lr": 1.0332103321033212e-06, "epoch": 0.031010613751730504, "percentage": 1.03, "elapsed_time": "0:34:18", "remaining_time": "2 days, 6:43:35"}
+{"current_steps": 57, "total_steps": 5415, "loss": 0.675, "lr": 1.0516605166051662e-06, "epoch": 0.031564374711582834, "percentage": 1.05, "elapsed_time": "0:34:58", "remaining_time": "2 days, 6:48:10"}
+{"current_steps": 58, "total_steps": 5415, "loss": 0.6631, "lr": 1.070110701107011e-06, "epoch": 0.03211813567143516, "percentage": 1.07, "elapsed_time": "0:35:37", "remaining_time": "2 days, 6:50:41"}
+{"current_steps": 59, "total_steps": 5415, "loss": 0.7202, "lr": 1.088560885608856e-06, "epoch": 0.03267189663128749, "percentage": 1.09, "elapsed_time": "0:36:14", "remaining_time": "2 days, 6:50:29"}
+{"current_steps": 60, "total_steps": 5415, "loss": 0.6647, "lr": 1.1070110701107011e-06, "epoch": 0.03322565759113982, "percentage": 1.11, "elapsed_time": "0:36:50", "remaining_time": "2 days, 6:48:48"}
+{"current_steps": 61, "total_steps": 5415, "loss": 0.6661, "lr": 1.1254612546125462e-06, "epoch": 0.03377941855099215, "percentage": 1.13, "elapsed_time": "0:37:26", "remaining_time": "2 days, 6:46:18"}
+{"current_steps": 62, "total_steps": 5415, "loss": 0.6934, "lr": 1.1439114391143912e-06, "epoch": 0.03433317951084448, "percentage": 1.14, "elapsed_time": "0:38:00", "remaining_time": "2 days, 6:42:00"}
+{"current_steps": 63, "total_steps": 5415, "loss": 0.6344, "lr": 1.1623616236162363e-06, "epoch": 0.03488694047069681, "percentage": 1.16, "elapsed_time": "0:38:34", "remaining_time": "2 days, 6:36:38"}
+{"current_steps": 64, "total_steps": 5415, "loss": 0.6576, "lr": 1.1808118081180813e-06, "epoch": 0.03544070143054914, "percentage": 1.18, "elapsed_time": "0:39:09", "remaining_time": "2 days, 6:33:32"}
+{"current_steps": 65, "total_steps": 5415, "loss": 0.6484, "lr": 1.1992619926199263e-06, "epoch": 0.03599446239040148, "percentage": 1.2, "elapsed_time": "0:39:42", "remaining_time": "2 days, 6:28:21"}
+{"current_steps": 66, "total_steps": 5415, "loss": 0.6582, "lr": 1.2177121771217714e-06, "epoch": 0.03654822335025381, "percentage": 1.22, "elapsed_time": "0:40:20", "remaining_time": "2 days, 6:29:38"}
+{"current_steps": 67, "total_steps": 5415, "loss": 0.6424, "lr": 1.2361623616236164e-06, "epoch": 0.03710198431010614, "percentage": 1.24, "elapsed_time": "0:40:59", "remaining_time": "2 days, 6:31:20"}
+{"current_steps": 68, "total_steps": 5415, "loss": 0.635, "lr": 1.2546125461254613e-06, "epoch": 0.03765574526995847, "percentage": 1.26, "elapsed_time": "0:41:28", "remaining_time": "2 days, 6:20:53"}
+{"current_steps": 69, "total_steps": 5415, "loss": 0.6421, "lr": 1.2730627306273063e-06, "epoch": 0.0382095062298108, "percentage": 1.27, "elapsed_time": "0:42:10", "remaining_time": "2 days, 6:27:18"}
+{"current_steps": 70, "total_steps": 5415, "loss": 0.6262, "lr": 1.2915129151291513e-06, "epoch": 0.03876326718966313, "percentage": 1.29, "elapsed_time": "0:42:48", "remaining_time": "2 days, 6:29:02"}
+{"current_steps": 71, "total_steps": 5415, "loss": 0.6374, "lr": 1.3099630996309964e-06, "epoch": 0.03931702814951546, "percentage": 1.31, "elapsed_time": "0:43:26", "remaining_time": "2 days, 6:30:03"}
+{"current_steps": 72, "total_steps": 5415, "loss": 0.639, "lr": 1.3284132841328414e-06, "epoch": 0.03987078910936779, "percentage": 1.33, "elapsed_time": "0:44:06", "remaining_time": "2 days, 6:33:17"}
+{"current_steps": 73, "total_steps": 5415, "loss": 0.6392, "lr": 1.3468634686346865e-06, "epoch": 0.04042455006922012, "percentage": 1.35, "elapsed_time": "0:44:46", "remaining_time": "2 days, 6:36:28"}
+{"current_steps": 74, "total_steps": 5415, "loss": 0.6156, "lr": 1.3653136531365315e-06, "epoch": 0.04097831102907245, "percentage": 1.37, "elapsed_time": "0:45:24", "remaining_time": "2 days, 6:37:46"}
+{"current_steps": 75, "total_steps": 5415, "loss": 0.6401, "lr": 1.3837638376383765e-06, "epoch": 0.04153207198892478, "percentage": 1.39, "elapsed_time": "0:46:04", "remaining_time": "2 days, 6:40:11"}
+{"current_steps": 76, "total_steps": 5415, "loss": 0.6399, "lr": 1.4022140221402214e-06, "epoch": 0.04208583294877711, "percentage": 1.4, "elapsed_time": "0:46:43", "remaining_time": "2 days, 6:42:14"}
+{"current_steps": 77, "total_steps": 5415, "loss": 0.6116, "lr": 1.4206642066420664e-06, "epoch": 0.04263959390862944, "percentage": 1.42, "elapsed_time": "0:47:20", "remaining_time": "2 days, 6:42:31"}
+{"current_steps": 78, "total_steps": 5415, "loss": 0.6269, "lr": 1.4391143911439114e-06, "epoch": 0.04319335486848177, "percentage": 1.44, "elapsed_time": "0:48:00", "remaining_time": "2 days, 6:45:03"}
+{"current_steps": 79, "total_steps": 5415, "loss": 0.6409, "lr": 1.4575645756457565e-06, "epoch": 0.043747115828334106, "percentage": 1.46, "elapsed_time": "0:48:37", "remaining_time": "2 days, 6:44:00"}
+{"current_steps": 80, "total_steps": 5415, "loss": 0.601, "lr": 1.4760147601476015e-06, "epoch": 0.044300876788186436, "percentage": 1.48, "elapsed_time": "0:49:08", "remaining_time": "2 days, 6:37:38"}
+{"current_steps": 81, "total_steps": 5415, "loss": 0.6615, "lr": 1.4944649446494466e-06, "epoch": 0.044854637748038766, "percentage": 1.5, "elapsed_time": "0:49:48", "remaining_time": "2 days, 6:39:33"}
+{"current_steps": 82, "total_steps": 5415, "loss": 0.6234, "lr": 1.5129151291512916e-06, "epoch": 0.045408398707891096, "percentage": 1.51, "elapsed_time": "0:50:29", "remaining_time": "2 days, 6:44:02"}
+{"current_steps": 83, "total_steps": 5415, "loss": 0.5904, "lr": 1.5313653136531366e-06, "epoch": 0.045962159667743425, "percentage": 1.53, "elapsed_time": "0:51:06", "remaining_time": "2 days, 6:42:58"}
+{"current_steps": 84, "total_steps": 5415, "loss": 0.6297, "lr": 1.5498154981549817e-06, "epoch": 0.046515920627595755, "percentage": 1.55, "elapsed_time": "0:51:42", "remaining_time": "2 days, 6:41:53"}
+{"current_steps": 85, "total_steps": 5415, "loss": 0.6548, "lr": 1.5682656826568267e-06, "epoch": 0.047069681587448085, "percentage": 1.57, "elapsed_time": "0:52:19", "remaining_time": "2 days, 6:41:25"}
+{"current_steps": 86, "total_steps": 5415, "loss": 0.6145, "lr": 1.5867158671586716e-06, "epoch": 0.047623442547300415, "percentage": 1.59, "elapsed_time": "0:52:58", "remaining_time": "2 days, 6:42:52"}
+{"current_steps": 87, "total_steps": 5415, "loss": 0.5942, "lr": 1.6051660516605166e-06, "epoch": 0.048177203507152745, "percentage": 1.61, "elapsed_time": "0:53:33", "remaining_time": "2 days, 6:40:01"}
+{"current_steps": 88, "total_steps": 5415, "loss": 0.6138, "lr": 1.6236162361623616e-06, "epoch": 0.048730964467005075, "percentage": 1.63, "elapsed_time": "0:54:07", "remaining_time": "2 days, 6:36:05"}
+{"current_steps": 89, "total_steps": 5415, "loss": 0.6175, "lr": 1.6420664206642067e-06, "epoch": 0.049284725426857405, "percentage": 1.64, "elapsed_time": "0:54:39", "remaining_time": "2 days, 6:30:48"}
+{"current_steps": 90, "total_steps": 5415, "loss": 0.6114, "lr": 1.6605166051660517e-06, "epoch": 0.049838486386709735, "percentage": 1.66, "elapsed_time": "0:55:13", "remaining_time": "2 days, 6:27:40"}
+{"current_steps": 91, "total_steps": 5415, "loss": 0.6082, "lr": 1.6789667896678968e-06, "epoch": 0.050392247346562065, "percentage": 1.68, "elapsed_time": "0:55:50", "remaining_time": "2 days, 6:26:44"}
+{"current_steps": 92, "total_steps": 5415, "loss": 0.602, "lr": 1.6974169741697418e-06, "epoch": 0.050946008306414395, "percentage": 1.7, "elapsed_time": "0:56:29", "remaining_time": "2 days, 6:28:27"}
+{"current_steps": 93, "total_steps": 5415, "loss": 0.6168, "lr": 1.7158671586715868e-06, "epoch": 0.051499769266266725, "percentage": 1.72, "elapsed_time": "0:57:07", "remaining_time": "2 days, 6:28:53"}
+{"current_steps": 94, "total_steps": 5415, "loss": 0.6096, "lr": 1.7343173431734319e-06, "epoch": 0.05205353022611906, "percentage": 1.74, "elapsed_time": "0:57:41", "remaining_time": "2 days, 6:25:37"}
+{"current_steps": 95, "total_steps": 5415, "loss": 0.6246, "lr": 1.752767527675277e-06, "epoch": 0.05260729118597139, "percentage": 1.75, "elapsed_time": "0:58:19", "remaining_time": "2 days, 6:25:44"}
+{"current_steps": 96, "total_steps": 5415, "loss": 0.5873, "lr": 1.7712177121771217e-06, "epoch": 0.05316105214582372, "percentage": 1.77, "elapsed_time": "0:58:54", "remaining_time": "2 days, 6:24:16"}
+{"current_steps": 97, "total_steps": 5415, "loss": 0.599, "lr": 1.7896678966789668e-06, "epoch": 0.05371481310567605, "percentage": 1.79, "elapsed_time": "0:59:33", "remaining_time": "2 days, 6:25:13"}
+{"current_steps": 98, "total_steps": 5415, "loss": 0.5739, "lr": 1.8081180811808118e-06, "epoch": 0.05426857406552838, "percentage": 1.81, "elapsed_time": "1:00:11", "remaining_time": "2 days, 6:25:53"}
+{"current_steps": 99, "total_steps": 5415, "loss": 0.6209, "lr": 1.8265682656826569e-06, "epoch": 0.05482233502538071, "percentage": 1.83, "elapsed_time": "1:00:48", "remaining_time": "2 days, 6:24:47"}
+{"current_steps": 100, "total_steps": 5415, "loss": 0.6282, "lr": 1.845018450184502e-06, "epoch": 0.05537609598523304, "percentage": 1.85, "elapsed_time": "1:01:30", "remaining_time": "2 days, 6:29:06"}
+{"current_steps": 101, "total_steps": 5415, "loss": 0.6178, "lr": 1.863468634686347e-06, "epoch": 0.05592985694508537, "percentage": 1.87, "elapsed_time": "1:02:54", "remaining_time": "2 days, 7:09:29"}
+{"current_steps": 102, "total_steps": 5415, "loss": 0.5922, "lr": 1.881918819188192e-06, "epoch": 0.0564836179049377, "percentage": 1.88, "elapsed_time": "1:03:35", "remaining_time": "2 days, 7:12:23"}
+{"current_steps": 103, "total_steps": 5415, "loss": 0.5758, "lr": 1.900369003690037e-06, "epoch": 0.05703737886479003, "percentage": 1.9, "elapsed_time": "1:04:13", "remaining_time": "2 days, 7:12:28"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a5d983b3c07f623a935e89f0f8c62ff609ebab2b39babefe6dafee551c1ba59
+size 7352