Training in progress, epoch 0

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2dc1373b0762e4448620b59fc90b002c281e6c016750718f64d58c6c68684d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b571377ec2bd4209af616d5e642c15d78a575ca27409d5b6ddb8f44cb321019
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558f6d3ae190289391e0049487fed767fd7a1c99e4f8c6f8a1c92f7dce8e77f1
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bff831f132d3cf15de84b1b54d5c1ea43045d9acedc8aec81d5641db98971a0
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_log.jsonl

@@ -0,0 +1,111 @@
+{"current_steps": 1, "total_steps": 333, "loss": 0.851, "lr": 4.705882352941177e-06, "epoch": 0.008983717012914094, "percentage": 0.3, "elapsed_time": "0:06:04", "remaining_time": "1 day, 9:38:00"}
+{"current_steps": 2, "total_steps": 333, "loss": 0.8589, "lr": 9.411764705882354e-06, "epoch": 0.017967434025828188, "percentage": 0.6, "elapsed_time": "0:12:12", "remaining_time": "1 day, 9:41:28"}
+{"current_steps": 3, "total_steps": 333, "loss": 0.8175, "lr": 1.4117647058823532e-05, "epoch": 0.02695115103874228, "percentage": 0.9, "elapsed_time": "0:17:48", "remaining_time": "1 day, 8:39:36"}
+{"current_steps": 4, "total_steps": 333, "loss": 0.7666, "lr": 1.8823529411764708e-05, "epoch": 0.035934868051656375, "percentage": 1.2, "elapsed_time": "0:23:40", "remaining_time": "1 day, 8:27:29"}
+{"current_steps": 5, "total_steps": 333, "loss": 0.7997, "lr": 2.3529411764705884e-05, "epoch": 0.044918585064570464, "percentage": 1.5, "elapsed_time": "0:29:29", "remaining_time": "1 day, 8:14:06"}
+{"current_steps": 6, "total_steps": 333, "loss": 0.8658, "lr": 2.8235294117647063e-05, "epoch": 0.05390230207748456, "percentage": 1.8, "elapsed_time": "0:35:13", "remaining_time": "1 day, 8:00:00"}
+{"current_steps": 7, "total_steps": 333, "loss": 0.7742, "lr": 3.294117647058824e-05, "epoch": 0.06288601909039865, "percentage": 2.1, "elapsed_time": "0:41:25", "remaining_time": "1 day, 8:09:00"}
+{"current_steps": 8, "total_steps": 333, "loss": 0.7478, "lr": 3.7647058823529415e-05, "epoch": 0.07186973610331275, "percentage": 2.4, "elapsed_time": "0:47:09", "remaining_time": "1 day, 7:55:29"}
+{"current_steps": 9, "total_steps": 333, "loss": 0.7167, "lr": 4.235294117647059e-05, "epoch": 0.08085345311622684, "percentage": 2.7, "elapsed_time": "0:53:01", "remaining_time": "1 day, 7:48:40"}
+{"current_steps": 10, "total_steps": 333, "loss": 0.6839, "lr": 4.705882352941177e-05, "epoch": 0.08983717012914093, "percentage": 3.0, "elapsed_time": "0:58:43", "remaining_time": "1 day, 7:36:52"}
+{"current_steps": 11, "total_steps": 333, "loss": 0.6594, "lr": 5.176470588235295e-05, "epoch": 0.09882088714205503, "percentage": 3.3, "elapsed_time": "1:04:37", "remaining_time": "1 day, 7:31:31"}
+{"current_steps": 12, "total_steps": 333, "loss": 0.6447, "lr": 5.6470588235294126e-05, "epoch": 0.10780460415496912, "percentage": 3.6, "elapsed_time": "1:10:45", "remaining_time": "1 day, 7:32:43"}
+{"current_steps": 13, "total_steps": 333, "loss": 0.6225, "lr": 6.117647058823529e-05, "epoch": 0.11678832116788321, "percentage": 3.9, "elapsed_time": "1:16:21", "remaining_time": "1 day, 7:19:33"}
+{"current_steps": 14, "total_steps": 333, "loss": 0.6409, "lr": 6.588235294117648e-05, "epoch": 0.1257720381807973, "percentage": 4.2, "elapsed_time": "1:22:04", "remaining_time": "1 day, 7:10:13"}
+{"current_steps": 15, "total_steps": 333, "loss": 0.6265, "lr": 7.058823529411765e-05, "epoch": 0.13475575519371139, "percentage": 4.5, "elapsed_time": "1:27:56", "remaining_time": "1 day, 7:04:28"}
+{"current_steps": 16, "total_steps": 333, "loss": 0.6182, "lr": 7.529411764705883e-05, "epoch": 0.1437394722066255, "percentage": 4.8, "elapsed_time": "1:33:51", "remaining_time": "1 day, 6:59:32"}
+{"current_steps": 17, "total_steps": 333, "loss": 0.6088, "lr": 8e-05, "epoch": 0.1527231892195396, "percentage": 5.11, "elapsed_time": "1:39:44", "remaining_time": "1 day, 6:54:04"}
+{"current_steps": 18, "total_steps": 333, "loss": 0.5934, "lr": 8.470588235294118e-05, "epoch": 0.16170690623245368, "percentage": 5.41, "elapsed_time": "1:45:28", "remaining_time": "1 day, 6:45:42"}
+{"current_steps": 19, "total_steps": 333, "loss": 0.6025, "lr": 8.941176470588236e-05, "epoch": 0.17069062324536777, "percentage": 5.71, "elapsed_time": "1:51:24", "remaining_time": "1 day, 6:41:07"}
+{"current_steps": 20, "total_steps": 333, "loss": 0.5952, "lr": 9.411764705882353e-05, "epoch": 0.17967434025828186, "percentage": 6.01, "elapsed_time": "1:57:13", "remaining_time": "1 day, 6:34:33"}
+{"current_steps": 21, "total_steps": 333, "loss": 0.5812, "lr": 9.882352941176472e-05, "epoch": 0.18865805727119594, "percentage": 6.31, "elapsed_time": "2:03:18", "remaining_time": "1 day, 6:31:53"}
+{"current_steps": 22, "total_steps": 333, "loss": 0.5796, "lr": 0.0001035294117647059, "epoch": 0.19764177428411006, "percentage": 6.61, "elapsed_time": "2:09:14", "remaining_time": "1 day, 6:26:57"}
+{"current_steps": 23, "total_steps": 333, "loss": 0.5735, "lr": 0.00010823529411764708, "epoch": 0.20662549129702415, "percentage": 6.91, "elapsed_time": "2:14:46", "remaining_time": "1 day, 6:16:25"}
+{"current_steps": 24, "total_steps": 333, "loss": 0.5932, "lr": 0.00011294117647058825, "epoch": 0.21560920830993824, "percentage": 7.21, "elapsed_time": "2:20:41", "remaining_time": "1 day, 6:11:25"}
+{"current_steps": 25, "total_steps": 333, "loss": 0.5768, "lr": 0.00011764705882352943, "epoch": 0.22459292532285233, "percentage": 7.51, "elapsed_time": "2:26:18", "remaining_time": "1 day, 6:02:28"}
+{"current_steps": 26, "total_steps": 333, "loss": 0.6315, "lr": 0.00012235294117647058, "epoch": 0.23357664233576642, "percentage": 7.81, "elapsed_time": "2:32:00", "remaining_time": "1 day, 5:54:50"}
+{"current_steps": 27, "total_steps": 333, "loss": 0.6138, "lr": 0.00012705882352941178, "epoch": 0.2425603593486805, "percentage": 8.11, "elapsed_time": "2:37:29", "remaining_time": "1 day, 5:44:51"}
+{"current_steps": 28, "total_steps": 333, "loss": 0.5971, "lr": 0.00013176470588235296, "epoch": 0.2515440763615946, "percentage": 8.41, "elapsed_time": "2:43:04", "remaining_time": "1 day, 5:36:24"}
+{"current_steps": 29, "total_steps": 333, "loss": 0.6019, "lr": 0.00013647058823529413, "epoch": 0.2605277933745087, "percentage": 8.71, "elapsed_time": "2:48:55", "remaining_time": "1 day, 5:30:44"}
+{"current_steps": 30, "total_steps": 333, "loss": 0.6902, "lr": 0.0001411764705882353, "epoch": 0.26951151038742277, "percentage": 9.01, "elapsed_time": "2:54:46", "remaining_time": "1 day, 5:25:17"}
+{"current_steps": 31, "total_steps": 333, "loss": 2.1691, "lr": 0.00014588235294117648, "epoch": 0.2784952274003369, "percentage": 9.31, "elapsed_time": "3:00:21", "remaining_time": "1 day, 5:17:00"}
+{"current_steps": 32, "total_steps": 333, "loss": 2.3024, "lr": 0.00015058823529411766, "epoch": 0.287478944413251, "percentage": 9.61, "elapsed_time": "3:06:01", "remaining_time": "1 day, 5:09:51"}
+{"current_steps": 33, "total_steps": 333, "loss": 0.9312, "lr": 0.00015529411764705884, "epoch": 0.29646266142616506, "percentage": 9.91, "elapsed_time": "3:11:48", "remaining_time": "1 day, 5:03:42"}
+{"current_steps": 34, "total_steps": 333, "loss": 0.7014, "lr": 0.00016, "epoch": 0.3054463784390792, "percentage": 10.21, "elapsed_time": "3:17:44", "remaining_time": "1 day, 4:58:59"}
+{"current_steps": 35, "total_steps": 333, "loss": 0.6914, "lr": 0.0001599955841596387, "epoch": 0.31443009545199324, "percentage": 10.51, "elapsed_time": "3:23:31", "remaining_time": "1 day, 4:52:56"}
+{"current_steps": 36, "total_steps": 333, "loss": 0.716, "lr": 0.00015998233712604597, "epoch": 0.32341381246490736, "percentage": 10.81, "elapsed_time": "3:29:23", "remaining_time": "1 day, 4:47:27"}
+{"current_steps": 37, "total_steps": 333, "loss": 1.163, "lr": 0.00015996026036164143, "epoch": 0.3323975294778215, "percentage": 11.11, "elapsed_time": "3:35:19", "remaining_time": "1 day, 4:42:32"}
+{"current_steps": 38, "total_steps": 333, "loss": 0.9691, "lr": 0.00015992935630361176, "epoch": 0.34138124649073553, "percentage": 11.41, "elapsed_time": "3:40:54", "remaining_time": "1 day, 4:34:57"}
+{"current_steps": 39, "total_steps": 333, "loss": 0.8032, "lr": 0.00015988962836364164, "epoch": 0.35036496350364965, "percentage": 11.71, "elapsed_time": "3:46:48", "remaining_time": "1 day, 4:29:50"}
+{"current_steps": 40, "total_steps": 333, "loss": 0.7292, "lr": 0.00015984108092753708, "epoch": 0.3593486805165637, "percentage": 12.01, "elapsed_time": "3:52:34", "remaining_time": "1 day, 4:23:33"}
+{"current_steps": 41, "total_steps": 333, "loss": 0.681, "lr": 0.0001597837193547413, "epoch": 0.36833239752947783, "percentage": 12.31, "elapsed_time": "3:58:06", "remaining_time": "1 day, 4:15:48"}
+{"current_steps": 42, "total_steps": 333, "loss": 0.676, "lr": 0.00015971754997774298, "epoch": 0.3773161145423919, "percentage": 12.61, "elapsed_time": "4:04:01", "remaining_time": "1 day, 4:10:42"}
+{"current_steps": 43, "total_steps": 333, "loss": 0.6598, "lr": 0.0001596425801013773, "epoch": 0.386299831555306, "percentage": 12.91, "elapsed_time": "4:09:33", "remaining_time": "1 day, 4:03:02"}
+{"current_steps": 44, "total_steps": 333, "loss": 0.7401, "lr": 0.00015955881800201933, "epoch": 0.3952835485682201, "percentage": 13.21, "elapsed_time": "4:15:30", "remaining_time": "1 day, 3:58:11"}
+{"current_steps": 45, "total_steps": 333, "loss": 0.6612, "lr": 0.00015946627292667064, "epoch": 0.4042672655811342, "percentage": 13.51, "elapsed_time": "4:21:27", "remaining_time": "1 day, 3:53:19"}
+{"current_steps": 46, "total_steps": 333, "loss": 0.6393, "lr": 0.00015936495509193816, "epoch": 0.4132509825940483, "percentage": 13.81, "elapsed_time": "4:27:10", "remaining_time": "1 day, 3:46:57"}
+{"current_steps": 47, "total_steps": 333, "loss": 0.6135, "lr": 0.00015925487568290645, "epoch": 0.42223469960696236, "percentage": 14.11, "elapsed_time": "4:33:03", "remaining_time": "1 day, 3:41:37"}
+{"current_steps": 48, "total_steps": 333, "loss": 0.5968, "lr": 0.00015913604685190304, "epoch": 0.4312184166198765, "percentage": 14.41, "elapsed_time": "4:38:44", "remaining_time": "1 day, 3:34:59"}
+{"current_steps": 49, "total_steps": 333, "loss": 0.5947, "lr": 0.00015900848171715654, "epoch": 0.4402021336327906, "percentage": 14.71, "elapsed_time": "4:44:21", "remaining_time": "1 day, 3:28:04"}
+{"current_steps": 50, "total_steps": 333, "loss": 0.5986, "lr": 0.00015887219436134874, "epoch": 0.44918585064570465, "percentage": 15.02, "elapsed_time": "4:50:15", "remaining_time": "1 day, 3:22:52"}
+{"current_steps": 51, "total_steps": 333, "loss": 0.6136, "lr": 0.00015872719983005986, "epoch": 0.45816956765861877, "percentage": 15.32, "elapsed_time": "4:56:04", "remaining_time": "1 day, 3:17:05"}
+{"current_steps": 52, "total_steps": 333, "loss": 0.6008, "lr": 0.0001585735141301074, "epoch": 0.46715328467153283, "percentage": 15.62, "elapsed_time": "5:01:43", "remaining_time": "1 day, 3:10:27"}
+{"current_steps": 53, "total_steps": 333, "loss": 0.599, "lr": 0.00015841115422777935, "epoch": 0.47613700168444695, "percentage": 15.92, "elapsed_time": "5:07:36", "remaining_time": "1 day, 3:05:03"}
+{"current_steps": 54, "total_steps": 333, "loss": 0.5911, "lr": 0.0001582401380469609, "epoch": 0.485120718697361, "percentage": 16.22, "elapsed_time": "5:13:12", "remaining_time": "1 day, 2:58:16"}
+{"current_steps": 55, "total_steps": 333, "loss": 0.6018, "lr": 0.00015806048446715594, "epoch": 0.4941044357102751, "percentage": 16.52, "elapsed_time": "5:18:55", "remaining_time": "1 day, 2:52:01"}
+{"current_steps": 56, "total_steps": 333, "loss": 0.5775, "lr": 0.00015787221332140268, "epoch": 0.5030881527231892, "percentage": 16.82, "elapsed_time": "5:24:40", "remaining_time": "1 day, 2:46:01"}
+{"current_steps": 57, "total_steps": 333, "loss": 0.5764, "lr": 0.00015767534539408418, "epoch": 0.5120718697361033, "percentage": 17.12, "elapsed_time": "5:30:39", "remaining_time": "1 day, 2:41:03"}
+{"current_steps": 58, "total_steps": 333, "loss": 0.5621, "lr": 0.00015746990241863394, "epoch": 0.5210555867490174, "percentage": 17.42, "elapsed_time": "5:36:11", "remaining_time": "1 day, 2:34:00"}
+{"current_steps": 59, "total_steps": 333, "loss": 0.5626, "lr": 0.0001572559070751366, "epoch": 0.5300393037619315, "percentage": 17.72, "elapsed_time": "5:41:59", "remaining_time": "1 day, 2:28:13"}
+{"current_steps": 60, "total_steps": 333, "loss": 0.5587, "lr": 0.00015703338298782396, "epoch": 0.5390230207748455, "percentage": 18.02, "elapsed_time": "5:47:24", "remaining_time": "1 day, 2:20:40"}
+{"current_steps": 61, "total_steps": 333, "loss": 0.5524, "lr": 0.0001568023547224672, "epoch": 0.5480067377877597, "percentage": 18.32, "elapsed_time": "5:53:18", "remaining_time": "1 day, 2:15:24"}
+{"current_steps": 62, "total_steps": 333, "loss": 0.5383, "lr": 0.00015656284778366479, "epoch": 0.5569904548006738, "percentage": 18.62, "elapsed_time": "5:59:06", "remaining_time": "1 day, 2:09:38"}
+{"current_steps": 63, "total_steps": 333, "loss": 0.538, "lr": 0.00015631488861202688, "epoch": 0.5659741718135879, "percentage": 18.92, "elapsed_time": "6:04:47", "remaining_time": "1 day, 2:03:23"}
+{"current_steps": 64, "total_steps": 333, "loss": 0.531, "lr": 0.00015605850458125646, "epoch": 0.574957888826502, "percentage": 19.22, "elapsed_time": "6:10:34", "remaining_time": "1 day, 1:57:35"}
+{"current_steps": 65, "total_steps": 333, "loss": 0.5314, "lr": 0.0001557937239951273, "epoch": 0.583941605839416, "percentage": 19.52, "elapsed_time": "6:16:17", "remaining_time": "1 day, 1:51:28"}
+{"current_steps": 66, "total_steps": 333, "loss": 0.5291, "lr": 0.00015552057608435936, "epoch": 0.5929253228523301, "percentage": 19.82, "elapsed_time": "6:22:08", "remaining_time": "1 day, 1:45:56"}
+{"current_steps": 67, "total_steps": 333, "loss": 0.531, "lr": 0.00015523909100339186, "epoch": 0.6019090398652442, "percentage": 20.12, "elapsed_time": "6:27:42", "remaining_time": "1 day, 1:39:16"}
+{"current_steps": 68, "total_steps": 333, "loss": 0.5297, "lr": 0.0001549492998270544, "epoch": 0.6108927568781584, "percentage": 20.42, "elapsed_time": "6:33:43", "remaining_time": "1 day, 1:34:23"}
+{"current_steps": 69, "total_steps": 333, "loss": 0.5166, "lr": 0.00015465123454713622, "epoch": 0.6198764738910725, "percentage": 20.72, "elapsed_time": "6:39:26", "remaining_time": "1 day, 1:28:18"}
+{"current_steps": 70, "total_steps": 333, "loss": 0.5149, "lr": 0.0001543449280688547, "epoch": 0.6288601909039865, "percentage": 21.02, "elapsed_time": "6:45:21", "remaining_time": "1 day, 1:22:58"}
+{"current_steps": 71, "total_steps": 333, "loss": 0.515, "lr": 0.00015403041420722257, "epoch": 0.6378439079169006, "percentage": 21.32, "elapsed_time": "6:51:14", "remaining_time": "1 day, 1:17:30"}
+{"current_steps": 72, "total_steps": 333, "loss": 0.5026, "lr": 0.00015370772768331497, "epoch": 0.6468276249298147, "percentage": 21.62, "elapsed_time": "6:56:46", "remaining_time": "1 day, 1:10:47"}
+{"current_steps": 73, "total_steps": 333, "loss": 0.5137, "lr": 0.00015337690412043625, "epoch": 0.6558113419427288, "percentage": 21.92, "elapsed_time": "7:02:28", "remaining_time": "1 day, 1:04:43"}
+{"current_steps": 74, "total_steps": 333, "loss": 0.5059, "lr": 0.0001530379800401875, "epoch": 0.664795058955643, "percentage": 22.22, "elapsed_time": "7:07:56", "remaining_time": "1 day, 0:57:47"}
+{"current_steps": 75, "total_steps": 333, "loss": 0.5036, "lr": 0.0001526909928584345, "epoch": 0.673778775968557, "percentage": 22.52, "elapsed_time": "7:13:44", "remaining_time": "1 day, 0:52:04"}
+{"current_steps": 76, "total_steps": 333, "loss": 0.5163, "lr": 0.00015233598088117733, "epoch": 0.6827624929814711, "percentage": 22.82, "elapsed_time": "7:19:36", "remaining_time": "1 day, 0:46:32"}
+{"current_steps": 77, "total_steps": 333, "loss": 0.502, "lr": 0.00015197298330032146, "epoch": 0.6917462099943852, "percentage": 23.12, "elapsed_time": "7:25:20", "remaining_time": "1 day, 0:40:38"}
+{"current_steps": 78, "total_steps": 333, "loss": 0.5015, "lr": 0.000151602040189351, "epoch": 0.7007299270072993, "percentage": 23.42, "elapsed_time": "7:31:15", "remaining_time": "1 day, 0:35:16"}
+{"current_steps": 79, "total_steps": 333, "loss": 0.4927, "lr": 0.00015122319249890513, "epoch": 0.7097136440202133, "percentage": 23.72, "elapsed_time": "7:36:50", "remaining_time": "1 day, 0:28:48"}
+{"current_steps": 80, "total_steps": 333, "loss": 0.5102, "lr": 0.00015083648205225679, "epoch": 0.7186973610331274, "percentage": 24.02, "elapsed_time": "7:42:34", "remaining_time": "1 day, 0:22:53"}
+{"current_steps": 81, "total_steps": 333, "loss": 0.5042, "lr": 0.000150441951540696, "epoch": 0.7276810780460415, "percentage": 24.32, "elapsed_time": "7:48:23", "remaining_time": "1 day, 0:17:13"}
+{"current_steps": 82, "total_steps": 333, "loss": 0.481, "lr": 0.00015003964451881666, "epoch": 0.7366647950589557, "percentage": 24.62, "elapsed_time": "7:54:23", "remaining_time": "1 day, 0:12:06"}
+{"current_steps": 83, "total_steps": 333, "loss": 0.5007, "lr": 0.0001496296053997084, "epoch": 0.7456485120718698, "percentage": 24.92, "elapsed_time": "8:00:16", "remaining_time": "1 day, 0:06:36"}
+{"current_steps": 84, "total_steps": 333, "loss": 0.4993, "lr": 0.00014921187945005348, "epoch": 0.7546322290847838, "percentage": 25.23, "elapsed_time": "8:06:01", "remaining_time": "1 day, 0:00:43"}
+{"current_steps": 85, "total_steps": 333, "loss": 0.4903, "lr": 0.00014878651278512966, "epoch": 0.7636159460976979, "percentage": 25.53, "elapsed_time": "8:11:57", "remaining_time": "23:55:20"}
+{"current_steps": 86, "total_steps": 333, "loss": 0.4951, "lr": 0.0001483535523637191, "epoch": 0.772599663110612, "percentage": 25.83, "elapsed_time": "8:17:51", "remaining_time": "23:49:53"}
+{"current_steps": 87, "total_steps": 333, "loss": 0.4849, "lr": 0.0001479130459829244, "epoch": 0.7815833801235261, "percentage": 26.13, "elapsed_time": "8:23:37", "remaining_time": "23:44:01"}
+{"current_steps": 88, "total_steps": 333, "loss": 0.4986, "lr": 0.00014746504227289192, "epoch": 0.7905670971364402, "percentage": 26.43, "elapsed_time": "8:29:29", "remaining_time": "23:38:28"}
+{"current_steps": 89, "total_steps": 333, "loss": 0.4785, "lr": 0.00014700959069144332, "epoch": 0.7995508141493542, "percentage": 26.73, "elapsed_time": "8:35:27", "remaining_time": "23:33:11"}
+{"current_steps": 90, "total_steps": 333, "loss": 0.4907, "lr": 0.0001465467415186155, "epoch": 0.8085345311622684, "percentage": 27.03, "elapsed_time": "8:41:34", "remaining_time": "23:28:14"}
+{"current_steps": 91, "total_steps": 333, "loss": 0.4912, "lr": 0.0001460765458511099, "epoch": 0.8175182481751825, "percentage": 27.33, "elapsed_time": "8:47:29", "remaining_time": "23:22:46"}
+{"current_steps": 92, "total_steps": 333, "loss": 0.4844, "lr": 0.00014559905559665169, "epoch": 0.8265019651880966, "percentage": 27.63, "elapsed_time": "8:53:08", "remaining_time": "23:16:36"}
+{"current_steps": 93, "total_steps": 333, "loss": 0.4801, "lr": 0.00014511432346825932, "epoch": 0.8354856822010107, "percentage": 27.93, "elapsed_time": "8:58:49", "remaining_time": "23:10:32"}
+{"current_steps": 94, "total_steps": 333, "loss": 0.4793, "lr": 0.0001446224029784252, "epoch": 0.8444693992139247, "percentage": 28.23, "elapsed_time": "9:04:39", "remaining_time": "23:04:49"}
+{"current_steps": 95, "total_steps": 333, "loss": 0.4822, "lr": 0.0001441233484332082, "epoch": 0.8534531162268388, "percentage": 28.53, "elapsed_time": "9:10:27", "remaining_time": "22:59:01"}
+{"current_steps": 96, "total_steps": 333, "loss": 0.4878, "lr": 0.00014361721492623834, "epoch": 0.862436833239753, "percentage": 28.83, "elapsed_time": "9:16:21", "remaining_time": "22:53:29"}
+{"current_steps": 97, "total_steps": 333, "loss": 0.4872, "lr": 0.00014310405833263486, "epoch": 0.8714205502526671, "percentage": 29.13, "elapsed_time": "9:22:17", "remaining_time": "22:48:02"}
+{"current_steps": 98, "total_steps": 333, "loss": 0.47, "lr": 0.00014258393530283773, "epoch": 0.8804042672655812, "percentage": 29.43, "elapsed_time": "9:28:24", "remaining_time": "22:43:01"}
+{"current_steps": 99, "total_steps": 333, "loss": 0.4859, "lr": 0.0001420569032563536, "epoch": 0.8893879842784952, "percentage": 29.73, "elapsed_time": "9:34:03", "remaining_time": "22:36:52"}
+{"current_steps": 100, "total_steps": 333, "loss": 0.4747, "lr": 0.00014152302037541707, "epoch": 0.8983717012914093, "percentage": 30.03, "elapsed_time": "9:40:02", "remaining_time": "22:31:30"}
+{"current_steps": 101, "total_steps": 333, "loss": 0.487, "lr": 0.00014098234559856748, "epoch": 0.9073554183043234, "percentage": 30.33, "elapsed_time": "9:45:49", "remaining_time": "22:25:38"}
+{"current_steps": 102, "total_steps": 333, "loss": 0.4721, "lr": 0.00014043493861414235, "epoch": 0.9163391353172375, "percentage": 30.63, "elapsed_time": "9:51:39", "remaining_time": "22:19:54"}
+{"current_steps": 103, "total_steps": 333, "loss": 0.4838, "lr": 0.0001398808598536881, "epoch": 0.9253228523301515, "percentage": 30.93, "elapsed_time": "9:57:16", "remaining_time": "22:13:43"}
+{"current_steps": 104, "total_steps": 333, "loss": 0.4732, "lr": 0.00013932017048528858, "epoch": 0.9343065693430657, "percentage": 31.23, "elapsed_time": "10:02:58", "remaining_time": "22:07:42"}
+{"current_steps": 105, "total_steps": 333, "loss": 0.4829, "lr": 0.00013875293240681237, "epoch": 0.9432902863559798, "percentage": 31.53, "elapsed_time": "10:08:51", "remaining_time": "22:02:04"}
+{"current_steps": 106, "total_steps": 333, "loss": 0.4699, "lr": 0.00013817920823907946, "epoch": 0.9522740033688939, "percentage": 31.83, "elapsed_time": "10:14:45", "remaining_time": "21:56:30"}
+{"current_steps": 107, "total_steps": 333, "loss": 0.4709, "lr": 0.0001375990613189483, "epoch": 0.961257720381808, "percentage": 32.13, "elapsed_time": "10:20:16", "remaining_time": "21:50:07"}
+{"current_steps": 108, "total_steps": 333, "loss": 0.4625, "lr": 0.00013701255569232356, "epoch": 0.970241437394722, "percentage": 32.43, "elapsed_time": "10:25:49", "remaining_time": "21:43:47"}
+{"current_steps": 109, "total_steps": 333, "loss": 0.4696, "lr": 0.0001364197561070856, "epoch": 0.9792251544076361, "percentage": 32.73, "elapsed_time": "10:31:35", "remaining_time": "21:37:56"}
+{"current_steps": 110, "total_steps": 333, "loss": 0.4775, "lr": 0.00013582072800594284, "epoch": 0.9882088714205502, "percentage": 33.03, "elapsed_time": "10:37:13", "remaining_time": "21:31:49"}
+{"current_steps": 111, "total_steps": 333, "loss": 0.4707, "lr": 0.00013521553751920693, "epoch": 0.9971925884334644, "percentage": 33.33, "elapsed_time": "10:43:00", "remaining_time": "21:26:01"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50abb12f648e7f997dcdd02ed276d0b9ff66668ce9d281b10ae17873d5910da7
+size 7224