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 sha256:5c5277fb50fe56624b8cd0c3dd2a97e40fc5f3a6135d6ade055f3ed0474f4c6e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aabd6e757301822d5a0c1a233ddca092170ed6aa4982e60ba1e313b7ae2d8bb0
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d6ba329f45387e71185e2d518400aeefd7f68ea32e0b47ee25a24c5951ed82
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:203af4fbe4dca07b8848c690863d9e5b677c1be634fd8324ee6e494988af4f9c
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_log.jsonl

@@ -0,0 +1,106 @@
+{"current_steps": 1, "total_steps": 3561, "loss": 0.8115, "lr": 2.8011204481792718e-08, "epoch": 0.0008422234699606962, "percentage": 0.03, "elapsed_time": "0:00:30", "remaining_time": "1 day, 5:45:51"}
+{"current_steps": 2, "total_steps": 3561, "loss": 0.8182, "lr": 5.6022408963585437e-08, "epoch": 0.0016844469399213925, "percentage": 0.06, "elapsed_time": "0:00:52", "remaining_time": "1 day, 2:05:50"}
+{"current_steps": 3, "total_steps": 3561, "loss": 0.8416, "lr": 8.403361344537815e-08, "epoch": 0.0025266704098820887, "percentage": 0.08, "elapsed_time": "0:01:11", "remaining_time": "23:27:33"}
+{"current_steps": 4, "total_steps": 3561, "loss": 0.8424, "lr": 1.1204481792717087e-07, "epoch": 0.003368893879842785, "percentage": 0.11, "elapsed_time": "0:01:33", "remaining_time": "23:03:45"}
+{"current_steps": 5, "total_steps": 3561, "loss": 0.8598, "lr": 1.400560224089636e-07, "epoch": 0.004211117349803481, "percentage": 0.14, "elapsed_time": "0:01:57", "remaining_time": "23:13:13"}
+{"current_steps": 6, "total_steps": 3561, "loss": 0.8674, "lr": 1.680672268907563e-07, "epoch": 0.0050533408197641775, "percentage": 0.17, "elapsed_time": "0:02:18", "remaining_time": "22:51:32"}
+{"current_steps": 7, "total_steps": 3561, "loss": 0.8991, "lr": 1.9607843137254904e-07, "epoch": 0.005895564289724873, "percentage": 0.2, "elapsed_time": "0:02:41", "remaining_time": "22:43:38"}
+{"current_steps": 8, "total_steps": 3561, "loss": 0.864, "lr": 2.2408963585434175e-07, "epoch": 0.00673778775968557, "percentage": 0.22, "elapsed_time": "0:03:05", "remaining_time": "22:54:19"}
+{"current_steps": 9, "total_steps": 3561, "loss": 0.8529, "lr": 2.5210084033613445e-07, "epoch": 0.007580011229646266, "percentage": 0.25, "elapsed_time": "0:03:23", "remaining_time": "22:20:37"}
+{"current_steps": 10, "total_steps": 3561, "loss": 0.8443, "lr": 2.801120448179272e-07, "epoch": 0.008422234699606962, "percentage": 0.28, "elapsed_time": "0:03:44", "remaining_time": "22:09:22"}
+{"current_steps": 11, "total_steps": 3561, "loss": 0.8497, "lr": 3.081232492997199e-07, "epoch": 0.009264458169567658, "percentage": 0.31, "elapsed_time": "0:04:02", "remaining_time": "21:46:24"}
+{"current_steps": 12, "total_steps": 3561, "loss": 0.8511, "lr": 3.361344537815126e-07, "epoch": 0.010106681639528355, "percentage": 0.34, "elapsed_time": "0:04:26", "remaining_time": "21:53:38"}
+{"current_steps": 13, "total_steps": 3561, "loss": 0.8614, "lr": 3.641456582633054e-07, "epoch": 0.010948905109489052, "percentage": 0.37, "elapsed_time": "0:04:45", "remaining_time": "21:39:30"}
+{"current_steps": 14, "total_steps": 3561, "loss": 0.871, "lr": 3.921568627450981e-07, "epoch": 0.011791128579449747, "percentage": 0.39, "elapsed_time": "0:05:06", "remaining_time": "21:36:14"}
+{"current_steps": 15, "total_steps": 3561, "loss": 0.863, "lr": 4.201680672268908e-07, "epoch": 0.012633352049410443, "percentage": 0.42, "elapsed_time": "0:05:26", "remaining_time": "21:28:12"}
+{"current_steps": 16, "total_steps": 3561, "loss": 0.7878, "lr": 4.481792717086835e-07, "epoch": 0.01347557551937114, "percentage": 0.45, "elapsed_time": "0:05:49", "remaining_time": "21:28:54"}
+{"current_steps": 17, "total_steps": 3561, "loss": 0.867, "lr": 4.7619047619047623e-07, "epoch": 0.014317798989331837, "percentage": 0.48, "elapsed_time": "0:06:10", "remaining_time": "21:28:37"}
+{"current_steps": 18, "total_steps": 3561, "loss": 0.8244, "lr": 5.042016806722689e-07, "epoch": 0.015160022459292532, "percentage": 0.51, "elapsed_time": "0:06:33", "remaining_time": "21:30:45"}
+{"current_steps": 19, "total_steps": 3561, "loss": 0.8214, "lr": 5.322128851540616e-07, "epoch": 0.016002245929253228, "percentage": 0.53, "elapsed_time": "0:06:52", "remaining_time": "21:22:41"}
+{"current_steps": 20, "total_steps": 3561, "loss": 0.8024, "lr": 5.602240896358544e-07, "epoch": 0.016844469399213923, "percentage": 0.56, "elapsed_time": "0:07:13", "remaining_time": "21:17:50"}
+{"current_steps": 21, "total_steps": 3561, "loss": 0.8066, "lr": 5.882352941176471e-07, "epoch": 0.01768669286917462, "percentage": 0.59, "elapsed_time": "0:07:31", "remaining_time": "21:09:07"}
+{"current_steps": 22, "total_steps": 3561, "loss": 0.7916, "lr": 6.162464985994398e-07, "epoch": 0.018528916339135316, "percentage": 0.62, "elapsed_time": "0:07:48", "remaining_time": "20:56:01"}
+{"current_steps": 23, "total_steps": 3561, "loss": 0.7761, "lr": 6.442577030812325e-07, "epoch": 0.019371139809096015, "percentage": 0.65, "elapsed_time": "0:08:07", "remaining_time": "20:49:25"}
+{"current_steps": 24, "total_steps": 3561, "loss": 0.8152, "lr": 6.722689075630252e-07, "epoch": 0.02021336327905671, "percentage": 0.67, "elapsed_time": "0:08:27", "remaining_time": "20:47:04"}
+{"current_steps": 25, "total_steps": 3561, "loss": 0.7976, "lr": 7.002801120448179e-07, "epoch": 0.021055586749017405, "percentage": 0.7, "elapsed_time": "0:08:47", "remaining_time": "20:44:37"}
+{"current_steps": 26, "total_steps": 3561, "loss": 0.8081, "lr": 7.282913165266108e-07, "epoch": 0.021897810218978103, "percentage": 0.73, "elapsed_time": "0:09:08", "remaining_time": "20:42:21"}
+{"current_steps": 27, "total_steps": 3561, "loss": 0.7708, "lr": 7.563025210084034e-07, "epoch": 0.022740033688938798, "percentage": 0.76, "elapsed_time": "0:09:25", "remaining_time": "20:33:33"}
+{"current_steps": 28, "total_steps": 3561, "loss": 0.7625, "lr": 7.843137254901962e-07, "epoch": 0.023582257158899493, "percentage": 0.79, "elapsed_time": "0:09:42", "remaining_time": "20:25:39"}
+{"current_steps": 29, "total_steps": 3561, "loss": 0.7308, "lr": 8.123249299719889e-07, "epoch": 0.02442448062886019, "percentage": 0.81, "elapsed_time": "0:10:03", "remaining_time": "20:24:56"}
+{"current_steps": 30, "total_steps": 3561, "loss": 0.7876, "lr": 8.403361344537816e-07, "epoch": 0.025266704098820886, "percentage": 0.84, "elapsed_time": "0:10:24", "remaining_time": "20:24:15"}
+{"current_steps": 31, "total_steps": 3561, "loss": 0.75, "lr": 8.683473389355742e-07, "epoch": 0.026108927568781585, "percentage": 0.87, "elapsed_time": "0:10:42", "remaining_time": "20:19:51"}
+{"current_steps": 32, "total_steps": 3561, "loss": 0.7543, "lr": 8.96358543417367e-07, "epoch": 0.02695115103874228, "percentage": 0.9, "elapsed_time": "0:11:04", "remaining_time": "20:21:38"}
+{"current_steps": 33, "total_steps": 3561, "loss": 0.739, "lr": 9.243697478991598e-07, "epoch": 0.027793374508702975, "percentage": 0.93, "elapsed_time": "0:11:26", "remaining_time": "20:22:24"}
+{"current_steps": 34, "total_steps": 3561, "loss": 0.7185, "lr": 9.523809523809525e-07, "epoch": 0.028635597978663673, "percentage": 0.95, "elapsed_time": "0:11:48", "remaining_time": "20:24:20"}
+{"current_steps": 35, "total_steps": 3561, "loss": 0.7459, "lr": 9.80392156862745e-07, "epoch": 0.029477821448624368, "percentage": 0.98, "elapsed_time": "0:12:09", "remaining_time": "20:25:42"}
+{"current_steps": 36, "total_steps": 3561, "loss": 0.7009, "lr": 1.0084033613445378e-06, "epoch": 0.030320044918585063, "percentage": 1.01, "elapsed_time": "0:12:27", "remaining_time": "20:20:12"}
+{"current_steps": 37, "total_steps": 3561, "loss": 0.6827, "lr": 1.0364145658263308e-06, "epoch": 0.03116226838854576, "percentage": 1.04, "elapsed_time": "0:12:48", "remaining_time": "20:19:28"}
+{"current_steps": 38, "total_steps": 3561, "loss": 0.7261, "lr": 1.0644257703081233e-06, "epoch": 0.032004491858506456, "percentage": 1.07, "elapsed_time": "0:13:08", "remaining_time": "20:19:05"}
+{"current_steps": 39, "total_steps": 3561, "loss": 0.7263, "lr": 1.092436974789916e-06, "epoch": 0.032846715328467155, "percentage": 1.1, "elapsed_time": "0:13:30", "remaining_time": "20:19:33"}
+{"current_steps": 40, "total_steps": 3561, "loss": 0.6892, "lr": 1.1204481792717088e-06, "epoch": 0.033688938798427846, "percentage": 1.12, "elapsed_time": "0:13:48", "remaining_time": "20:14:52"}
+{"current_steps": 41, "total_steps": 3561, "loss": 0.7065, "lr": 1.1484593837535015e-06, "epoch": 0.034531162268388545, "percentage": 1.15, "elapsed_time": "0:14:05", "remaining_time": "20:09:08"}
+{"current_steps": 42, "total_steps": 3561, "loss": 0.6902, "lr": 1.1764705882352942e-06, "epoch": 0.03537338573834924, "percentage": 1.18, "elapsed_time": "0:14:25", "remaining_time": "20:09:00"}
+{"current_steps": 43, "total_steps": 3561, "loss": 0.7039, "lr": 1.204481792717087e-06, "epoch": 0.03621560920830994, "percentage": 1.21, "elapsed_time": "0:14:44", "remaining_time": "20:06:02"}
+{"current_steps": 44, "total_steps": 3561, "loss": 0.673, "lr": 1.2324929971988797e-06, "epoch": 0.03705783267827063, "percentage": 1.24, "elapsed_time": "0:15:03", "remaining_time": "20:04:05"}
+{"current_steps": 45, "total_steps": 3561, "loss": 0.6989, "lr": 1.2605042016806724e-06, "epoch": 0.03790005614823133, "percentage": 1.26, "elapsed_time": "0:15:23", "remaining_time": "20:02:28"}
+{"current_steps": 46, "total_steps": 3561, "loss": 0.6687, "lr": 1.288515406162465e-06, "epoch": 0.03874227961819203, "percentage": 1.29, "elapsed_time": "0:15:42", "remaining_time": "20:00:38"}
+{"current_steps": 47, "total_steps": 3561, "loss": 0.6974, "lr": 1.316526610644258e-06, "epoch": 0.03958450308815272, "percentage": 1.32, "elapsed_time": "0:16:04", "remaining_time": "20:01:44"}
+{"current_steps": 48, "total_steps": 3561, "loss": 0.6473, "lr": 1.3445378151260504e-06, "epoch": 0.04042672655811342, "percentage": 1.35, "elapsed_time": "0:16:24", "remaining_time": "20:00:32"}
+{"current_steps": 49, "total_steps": 3561, "loss": 0.6673, "lr": 1.3725490196078434e-06, "epoch": 0.04126895002807412, "percentage": 1.38, "elapsed_time": "0:16:43", "remaining_time": "19:58:19"}
+{"current_steps": 50, "total_steps": 3561, "loss": 0.6159, "lr": 1.4005602240896359e-06, "epoch": 0.04211117349803481, "percentage": 1.4, "elapsed_time": "0:17:03", "remaining_time": "19:58:18"}
+{"current_steps": 51, "total_steps": 3561, "loss": 0.6496, "lr": 1.4285714285714286e-06, "epoch": 0.04295339696799551, "percentage": 1.43, "elapsed_time": "0:17:24", "remaining_time": "19:57:35"}
+{"current_steps": 52, "total_steps": 3561, "loss": 0.6484, "lr": 1.4565826330532216e-06, "epoch": 0.043795620437956206, "percentage": 1.46, "elapsed_time": "0:17:44", "remaining_time": "19:57:36"}
+{"current_steps": 53, "total_steps": 3561, "loss": 0.6761, "lr": 1.484593837535014e-06, "epoch": 0.0446378439079169, "percentage": 1.49, "elapsed_time": "0:18:03", "remaining_time": "19:55:31"}
+{"current_steps": 54, "total_steps": 3561, "loss": 0.6644, "lr": 1.5126050420168068e-06, "epoch": 0.045480067377877596, "percentage": 1.52, "elapsed_time": "0:18:23", "remaining_time": "19:54:56"}
+{"current_steps": 55, "total_steps": 3561, "loss": 0.6655, "lr": 1.5406162464985996e-06, "epoch": 0.046322290847838295, "percentage": 1.54, "elapsed_time": "0:18:42", "remaining_time": "19:52:41"}
+{"current_steps": 56, "total_steps": 3561, "loss": 0.6467, "lr": 1.5686274509803923e-06, "epoch": 0.047164514317798986, "percentage": 1.57, "elapsed_time": "0:19:04", "remaining_time": "19:53:31"}
+{"current_steps": 57, "total_steps": 3561, "loss": 0.6392, "lr": 1.5966386554621848e-06, "epoch": 0.048006737787759685, "percentage": 1.6, "elapsed_time": "0:19:26", "remaining_time": "19:55:15"}
+{"current_steps": 58, "total_steps": 3561, "loss": 0.6254, "lr": 1.6246498599439778e-06, "epoch": 0.04884896125772038, "percentage": 1.63, "elapsed_time": "0:19:45", "remaining_time": "19:53:41"}
+{"current_steps": 59, "total_steps": 3561, "loss": 0.5868, "lr": 1.6526610644257705e-06, "epoch": 0.04969118472768108, "percentage": 1.66, "elapsed_time": "0:20:05", "remaining_time": "19:52:39"}
+{"current_steps": 60, "total_steps": 3561, "loss": 0.6636, "lr": 1.6806722689075632e-06, "epoch": 0.05053340819764177, "percentage": 1.68, "elapsed_time": "0:20:26", "remaining_time": "19:52:26"}
+{"current_steps": 61, "total_steps": 3561, "loss": 0.6199, "lr": 1.708683473389356e-06, "epoch": 0.05137563166760247, "percentage": 1.71, "elapsed_time": "0:20:45", "remaining_time": "19:51:29"}
+{"current_steps": 62, "total_steps": 3561, "loss": 0.6095, "lr": 1.7366946778711485e-06, "epoch": 0.05221785513756317, "percentage": 1.74, "elapsed_time": "0:21:02", "remaining_time": "19:47:14"}
+{"current_steps": 63, "total_steps": 3561, "loss": 0.6205, "lr": 1.7647058823529414e-06, "epoch": 0.05306007860752386, "percentage": 1.77, "elapsed_time": "0:21:21", "remaining_time": "19:45:26"}
+{"current_steps": 64, "total_steps": 3561, "loss": 0.5832, "lr": 1.792717086834734e-06, "epoch": 0.05390230207748456, "percentage": 1.8, "elapsed_time": "0:21:38", "remaining_time": "19:42:27"}
+{"current_steps": 65, "total_steps": 3561, "loss": 0.5914, "lr": 1.8207282913165267e-06, "epoch": 0.05474452554744526, "percentage": 1.83, "elapsed_time": "0:21:58", "remaining_time": "19:42:19"}
+{"current_steps": 66, "total_steps": 3561, "loss": 0.6166, "lr": 1.8487394957983196e-06, "epoch": 0.05558674901740595, "percentage": 1.85, "elapsed_time": "0:22:22", "remaining_time": "19:44:47"}
+{"current_steps": 67, "total_steps": 3561, "loss": 0.5915, "lr": 1.8767507002801122e-06, "epoch": 0.05642897248736665, "percentage": 1.88, "elapsed_time": "0:22:44", "remaining_time": "19:45:45"}
+{"current_steps": 68, "total_steps": 3561, "loss": 0.5782, "lr": 1.904761904761905e-06, "epoch": 0.057271195957327346, "percentage": 1.91, "elapsed_time": "0:23:01", "remaining_time": "19:42:30"}
+{"current_steps": 69, "total_steps": 3561, "loss": 0.6009, "lr": 1.932773109243698e-06, "epoch": 0.05811341942728804, "percentage": 1.94, "elapsed_time": "0:23:23", "remaining_time": "19:43:39"}
+{"current_steps": 70, "total_steps": 3561, "loss": 0.5834, "lr": 1.96078431372549e-06, "epoch": 0.058955642897248736, "percentage": 1.97, "elapsed_time": "0:23:42", "remaining_time": "19:42:36"}
+{"current_steps": 71, "total_steps": 3561, "loss": 0.6063, "lr": 1.988795518207283e-06, "epoch": 0.059797866367209435, "percentage": 1.99, "elapsed_time": "0:24:03", "remaining_time": "19:42:31"}
+{"current_steps": 72, "total_steps": 3561, "loss": 0.6041, "lr": 2.0168067226890756e-06, "epoch": 0.060640089837170126, "percentage": 2.02, "elapsed_time": "0:24:24", "remaining_time": "19:43:11"}
+{"current_steps": 73, "total_steps": 3561, "loss": 0.601, "lr": 2.0448179271708684e-06, "epoch": 0.061482313307130824, "percentage": 2.05, "elapsed_time": "0:24:48", "remaining_time": "19:45:10"}
+{"current_steps": 74, "total_steps": 3561, "loss": 0.5901, "lr": 2.0728291316526615e-06, "epoch": 0.06232453677709152, "percentage": 2.08, "elapsed_time": "0:25:09", "remaining_time": "19:45:12"}
+{"current_steps": 75, "total_steps": 3561, "loss": 0.5714, "lr": 2.100840336134454e-06, "epoch": 0.06316676024705221, "percentage": 2.11, "elapsed_time": "0:25:28", "remaining_time": "19:43:52"}
+{"current_steps": 76, "total_steps": 3561, "loss": 0.5577, "lr": 2.1288515406162466e-06, "epoch": 0.06400898371701291, "percentage": 2.13, "elapsed_time": "0:25:45", "remaining_time": "19:41:21"}
+{"current_steps": 77, "total_steps": 3561, "loss": 0.5773, "lr": 2.1568627450980393e-06, "epoch": 0.06485120718697361, "percentage": 2.16, "elapsed_time": "0:26:03", "remaining_time": "19:38:46"}
+{"current_steps": 78, "total_steps": 3561, "loss": 0.6204, "lr": 2.184873949579832e-06, "epoch": 0.06569343065693431, "percentage": 2.19, "elapsed_time": "0:26:24", "remaining_time": "19:39:02"}
+{"current_steps": 79, "total_steps": 3561, "loss": 0.5684, "lr": 2.2128851540616248e-06, "epoch": 0.06653565412689501, "percentage": 2.22, "elapsed_time": "0:26:47", "remaining_time": "19:40:44"}
+{"current_steps": 80, "total_steps": 3561, "loss": 0.5994, "lr": 2.2408963585434175e-06, "epoch": 0.06737787759685569, "percentage": 2.25, "elapsed_time": "0:27:09", "remaining_time": "19:42:04"}
+{"current_steps": 81, "total_steps": 3561, "loss": 0.5825, "lr": 2.2689075630252102e-06, "epoch": 0.06822010106681639, "percentage": 2.27, "elapsed_time": "0:27:27", "remaining_time": "19:39:54"}
+{"current_steps": 82, "total_steps": 3561, "loss": 0.5829, "lr": 2.296918767507003e-06, "epoch": 0.06906232453677709, "percentage": 2.3, "elapsed_time": "0:27:48", "remaining_time": "19:39:59"}
+{"current_steps": 83, "total_steps": 3561, "loss": 0.5526, "lr": 2.3249299719887957e-06, "epoch": 0.06990454800673779, "percentage": 2.33, "elapsed_time": "0:28:08", "remaining_time": "19:39:26"}
+{"current_steps": 84, "total_steps": 3561, "loss": 0.58, "lr": 2.3529411764705885e-06, "epoch": 0.07074677147669849, "percentage": 2.36, "elapsed_time": "0:28:26", "remaining_time": "19:37:08"}
+{"current_steps": 85, "total_steps": 3561, "loss": 0.5564, "lr": 2.380952380952381e-06, "epoch": 0.07158899494665918, "percentage": 2.39, "elapsed_time": "0:28:46", "remaining_time": "19:36:52"}
+{"current_steps": 86, "total_steps": 3561, "loss": 0.6039, "lr": 2.408963585434174e-06, "epoch": 0.07243121841661988, "percentage": 2.42, "elapsed_time": "0:29:06", "remaining_time": "19:36:18"}
+{"current_steps": 87, "total_steps": 3561, "loss": 0.577, "lr": 2.4369747899159667e-06, "epoch": 0.07327344188658057, "percentage": 2.44, "elapsed_time": "0:29:25", "remaining_time": "19:34:48"}
+{"current_steps": 88, "total_steps": 3561, "loss": 0.5984, "lr": 2.4649859943977594e-06, "epoch": 0.07411566535654127, "percentage": 2.47, "elapsed_time": "0:29:46", "remaining_time": "19:35:05"}
+{"current_steps": 89, "total_steps": 3561, "loss": 0.5857, "lr": 2.492997198879552e-06, "epoch": 0.07495788882650196, "percentage": 2.5, "elapsed_time": "0:30:07", "remaining_time": "19:35:26"}
+{"current_steps": 90, "total_steps": 3561, "loss": 0.6026, "lr": 2.521008403361345e-06, "epoch": 0.07580011229646266, "percentage": 2.53, "elapsed_time": "0:30:27", "remaining_time": "19:34:48"}
+{"current_steps": 91, "total_steps": 3561, "loss": 0.5647, "lr": 2.549019607843137e-06, "epoch": 0.07664233576642336, "percentage": 2.56, "elapsed_time": "0:30:43", "remaining_time": "19:31:31"}
+{"current_steps": 92, "total_steps": 3561, "loss": 0.5605, "lr": 2.57703081232493e-06, "epoch": 0.07748455923638406, "percentage": 2.58, "elapsed_time": "0:31:02", "remaining_time": "19:30:43"}
+{"current_steps": 93, "total_steps": 3561, "loss": 0.5663, "lr": 2.605042016806723e-06, "epoch": 0.07832678270634474, "percentage": 2.61, "elapsed_time": "0:31:22", "remaining_time": "19:30:05"}
+{"current_steps": 94, "total_steps": 3561, "loss": 0.5949, "lr": 2.633053221288516e-06, "epoch": 0.07916900617630544, "percentage": 2.64, "elapsed_time": "0:31:42", "remaining_time": "19:29:38"}
+{"current_steps": 95, "total_steps": 3561, "loss": 0.564, "lr": 2.6610644257703085e-06, "epoch": 0.08001122964626614, "percentage": 2.67, "elapsed_time": "0:32:03", "remaining_time": "19:29:54"}
+{"current_steps": 96, "total_steps": 3561, "loss": 0.557, "lr": 2.689075630252101e-06, "epoch": 0.08085345311622684, "percentage": 2.7, "elapsed_time": "0:32:25", "remaining_time": "19:30:26"}
+{"current_steps": 97, "total_steps": 3561, "loss": 0.5886, "lr": 2.7170868347338936e-06, "epoch": 0.08169567658618754, "percentage": 2.72, "elapsed_time": "0:32:40", "remaining_time": "19:26:53"}
+{"current_steps": 98, "total_steps": 3561, "loss": 0.5487, "lr": 2.7450980392156867e-06, "epoch": 0.08253790005614824, "percentage": 2.75, "elapsed_time": "0:32:59", "remaining_time": "19:25:38"}
+{"current_steps": 99, "total_steps": 3561, "loss": 0.5438, "lr": 2.7731092436974795e-06, "epoch": 0.08338012352610892, "percentage": 2.78, "elapsed_time": "0:33:17", "remaining_time": "19:24:25"}
+{"current_steps": 100, "total_steps": 3561, "loss": 0.5848, "lr": 2.8011204481792718e-06, "epoch": 0.08422234699606962, "percentage": 2.81, "elapsed_time": "0:33:36", "remaining_time": "19:22:55"}
+{"current_steps": 101, "total_steps": 3561, "loss": 0.5648, "lr": 2.8291316526610645e-06, "epoch": 0.08506457046603032, "percentage": 2.84, "elapsed_time": "0:34:43", "remaining_time": "19:49:22"}
+{"current_steps": 102, "total_steps": 3561, "loss": 0.5917, "lr": 2.8571428571428573e-06, "epoch": 0.08590679393599102, "percentage": 2.86, "elapsed_time": "0:35:03", "remaining_time": "19:48:50"}
+{"current_steps": 103, "total_steps": 3561, "loss": 0.5539, "lr": 2.88515406162465e-06, "epoch": 0.08674901740595171, "percentage": 2.89, "elapsed_time": "0:35:24", "remaining_time": "19:48:52"}
+{"current_steps": 104, "total_steps": 3561, "loss": 0.5861, "lr": 2.913165266106443e-06, "epoch": 0.08759124087591241, "percentage": 2.92, "elapsed_time": "0:35:45", "remaining_time": "19:48:45"}
+{"current_steps": 105, "total_steps": 3561, "loss": 0.5663, "lr": 2.9411764705882355e-06, "epoch": 0.08843346434587311, "percentage": 2.95, "elapsed_time": "0:36:05", "remaining_time": "19:47:58"}
+{"current_steps": 106, "total_steps": 3561, "loss": 0.5403, "lr": 2.969187675070028e-06, "epoch": 0.0892756878158338, "percentage": 2.98, "elapsed_time": "0:36:26", "remaining_time": "19:47:40"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0deb7dbbed94bf8fee369a6cd469db6e7fb6d94e0c196c1cd2eeeef856361520
+size 7352