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:eda6cabeba77cc43015a179bfac36fa3175635f9f551ddd302e455d07b3b7765
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e5a4925d18fcfae863de4f54e62d07a0027ae113753408e73f645998014083
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0091c17eeaef1ec3c2fb76a9933c6451c3aa8332a414073dd47fe2b336741f17
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06eb52757de476425798c5bd5f9ae9a1b26fde8a4bc6ebcefa5e84ef9c77e187
+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 +1,115 @@
+{"current_steps": 1, "total_steps": 570, "loss": 1.1068, "lr": 1.4035087719298246e-06, "epoch": 0.008724100327153763, "percentage": 0.18, "elapsed_time": "0:01:53", "remaining_time": "17:52:12"}
+{"current_steps": 2, "total_steps": 570, "loss": 1.1076, "lr": 2.8070175438596493e-06, "epoch": 0.017448200654307525, "percentage": 0.35, "elapsed_time": "0:03:32", "remaining_time": "16:44:30"}
+{"current_steps": 3, "total_steps": 570, "loss": 1.1038, "lr": 4.210526315789474e-06, "epoch": 0.026172300981461286, "percentage": 0.53, "elapsed_time": "0:05:11", "remaining_time": "16:20:54"}
+{"current_steps": 4, "total_steps": 570, "loss": 1.0592, "lr": 5.6140350877192985e-06, "epoch": 0.03489640130861505, "percentage": 0.7, "elapsed_time": "0:06:50", "remaining_time": "16:08:32"}
+{"current_steps": 5, "total_steps": 570, "loss": 0.9977, "lr": 7.017543859649123e-06, "epoch": 0.04362050163576881, "percentage": 0.88, "elapsed_time": "0:08:29", "remaining_time": "16:00:19"}
+{"current_steps": 6, "total_steps": 570, "loss": 1.0036, "lr": 8.421052631578948e-06, "epoch": 0.05234460196292257, "percentage": 1.05, "elapsed_time": "0:10:10", "remaining_time": "15:56:31"}
+{"current_steps": 7, "total_steps": 570, "loss": 0.9923, "lr": 9.824561403508772e-06, "epoch": 0.061068702290076333, "percentage": 1.23, "elapsed_time": "0:11:49", "remaining_time": "15:51:27"}
+{"current_steps": 8, "total_steps": 570, "loss": 0.9666, "lr": 1.1228070175438597e-05, "epoch": 0.0697928026172301, "percentage": 1.4, "elapsed_time": "0:13:28", "remaining_time": "15:47:11"}
+{"current_steps": 9, "total_steps": 570, "loss": 0.9552, "lr": 1.263157894736842e-05, "epoch": 0.07851690294438386, "percentage": 1.58, "elapsed_time": "0:15:08", "remaining_time": "15:43:29"}
+{"current_steps": 10, "total_steps": 570, "loss": 0.9551, "lr": 1.4035087719298246e-05, "epoch": 0.08724100327153762, "percentage": 1.75, "elapsed_time": "0:16:47", "remaining_time": "15:40:12"}
+{"current_steps": 11, "total_steps": 570, "loss": 0.9119, "lr": 1.543859649122807e-05, "epoch": 0.09596510359869138, "percentage": 1.93, "elapsed_time": "0:18:26", "remaining_time": "15:37:12"}
+{"current_steps": 12, "total_steps": 570, "loss": 0.8941, "lr": 1.6842105263157896e-05, "epoch": 0.10468920392584515, "percentage": 2.11, "elapsed_time": "0:20:06", "remaining_time": "15:35:11"}
+{"current_steps": 13, "total_steps": 570, "loss": 0.8561, "lr": 1.824561403508772e-05, "epoch": 0.1134133042529989, "percentage": 2.28, "elapsed_time": "0:21:45", "remaining_time": "15:32:31"}
+{"current_steps": 14, "total_steps": 570, "loss": 0.8535, "lr": 1.9649122807017544e-05, "epoch": 0.12213740458015267, "percentage": 2.46, "elapsed_time": "0:23:25", "remaining_time": "15:30:00"}
+{"current_steps": 15, "total_steps": 570, "loss": 0.8375, "lr": 2.105263157894737e-05, "epoch": 0.13086150490730644, "percentage": 2.63, "elapsed_time": "0:25:04", "remaining_time": "15:27:38"}
+{"current_steps": 16, "total_steps": 570, "loss": 0.8313, "lr": 2.2456140350877194e-05, "epoch": 0.1395856052344602, "percentage": 2.81, "elapsed_time": "0:26:43", "remaining_time": "15:25:20"}
+{"current_steps": 17, "total_steps": 570, "loss": 0.8135, "lr": 2.385964912280702e-05, "epoch": 0.14830970556161396, "percentage": 2.98, "elapsed_time": "0:28:23", "remaining_time": "15:23:22"}
+{"current_steps": 18, "total_steps": 570, "loss": 0.805, "lr": 2.526315789473684e-05, "epoch": 0.15703380588876772, "percentage": 3.16, "elapsed_time": "0:30:02", "remaining_time": "15:21:12"}
+{"current_steps": 19, "total_steps": 570, "loss": 0.7884, "lr": 2.6666666666666667e-05, "epoch": 0.16575790621592149, "percentage": 3.33, "elapsed_time": "0:31:41", "remaining_time": "15:19:05"}
+{"current_steps": 20, "total_steps": 570, "loss": 0.7839, "lr": 2.8070175438596492e-05, "epoch": 0.17448200654307525, "percentage": 3.51, "elapsed_time": "0:33:20", "remaining_time": "15:16:59"}
+{"current_steps": 21, "total_steps": 570, "loss": 0.7839, "lr": 2.9473684210526317e-05, "epoch": 0.183206106870229, "percentage": 3.68, "elapsed_time": "0:34:59", "remaining_time": "15:14:58"}
+{"current_steps": 22, "total_steps": 570, "loss": 0.7664, "lr": 3.087719298245614e-05, "epoch": 0.19193020719738277, "percentage": 3.86, "elapsed_time": "0:36:39", "remaining_time": "15:12:57"}
+{"current_steps": 23, "total_steps": 570, "loss": 0.764, "lr": 3.228070175438597e-05, "epoch": 0.20065430752453653, "percentage": 4.04, "elapsed_time": "0:38:18", "remaining_time": "15:10:59"}
+{"current_steps": 24, "total_steps": 570, "loss": 0.7602, "lr": 3.368421052631579e-05, "epoch": 0.2093784078516903, "percentage": 4.21, "elapsed_time": "0:39:57", "remaining_time": "15:09:14"}
+{"current_steps": 25, "total_steps": 570, "loss": 0.766, "lr": 3.508771929824562e-05, "epoch": 0.21810250817884405, "percentage": 4.39, "elapsed_time": "0:41:37", "remaining_time": "15:07:20"}
+{"current_steps": 26, "total_steps": 570, "loss": 0.7543, "lr": 3.649122807017544e-05, "epoch": 0.2268266085059978, "percentage": 4.56, "elapsed_time": "0:43:16", "remaining_time": "15:05:35"}
+{"current_steps": 27, "total_steps": 570, "loss": 0.7404, "lr": 3.789473684210526e-05, "epoch": 0.23555070883315157, "percentage": 4.74, "elapsed_time": "0:44:56", "remaining_time": "15:03:41"}
+{"current_steps": 28, "total_steps": 570, "loss": 0.7499, "lr": 3.929824561403509e-05, "epoch": 0.24427480916030533, "percentage": 4.91, "elapsed_time": "0:46:35", "remaining_time": "15:01:47"}
+{"current_steps": 29, "total_steps": 570, "loss": 0.7436, "lr": 4.070175438596492e-05, "epoch": 0.2529989094874591, "percentage": 5.09, "elapsed_time": "0:48:14", "remaining_time": "14:59:55"}
+{"current_steps": 30, "total_steps": 570, "loss": 0.7285, "lr": 4.210526315789474e-05, "epoch": 0.2617230098146129, "percentage": 5.26, "elapsed_time": "0:49:53", "remaining_time": "14:58:04"}
+{"current_steps": 31, "total_steps": 570, "loss": 0.7267, "lr": 4.350877192982457e-05, "epoch": 0.27044711014176664, "percentage": 5.44, "elapsed_time": "0:51:34", "remaining_time": "14:56:36"}
+{"current_steps": 32, "total_steps": 570, "loss": 0.7267, "lr": 4.491228070175439e-05, "epoch": 0.2791712104689204, "percentage": 5.61, "elapsed_time": "0:53:13", "remaining_time": "14:54:46"}
+{"current_steps": 33, "total_steps": 570, "loss": 0.7291, "lr": 4.6315789473684214e-05, "epoch": 0.28789531079607417, "percentage": 5.79, "elapsed_time": "0:54:52", "remaining_time": "14:52:57"}
+{"current_steps": 34, "total_steps": 570, "loss": 0.7273, "lr": 4.771929824561404e-05, "epoch": 0.2966194111232279, "percentage": 5.96, "elapsed_time": "0:56:31", "remaining_time": "14:51:08"}
+{"current_steps": 35, "total_steps": 570, "loss": 0.7278, "lr": 4.9122807017543864e-05, "epoch": 0.3053435114503817, "percentage": 6.14, "elapsed_time": "0:58:10", "remaining_time": "14:49:19"}
+{"current_steps": 36, "total_steps": 570, "loss": 0.7177, "lr": 5.052631578947368e-05, "epoch": 0.31406761177753545, "percentage": 6.32, "elapsed_time": "0:59:49", "remaining_time": "14:47:31"}
+{"current_steps": 37, "total_steps": 570, "loss": 0.7177, "lr": 5.1929824561403515e-05, "epoch": 0.3227917121046892, "percentage": 6.49, "elapsed_time": "1:01:29", "remaining_time": "14:45:51"}
+{"current_steps": 38, "total_steps": 570, "loss": 0.7072, "lr": 5.333333333333333e-05, "epoch": 0.33151581243184297, "percentage": 6.67, "elapsed_time": "1:03:08", "remaining_time": "14:44:05"}
+{"current_steps": 39, "total_steps": 570, "loss": 0.7146, "lr": 5.4736842105263165e-05, "epoch": 0.34023991275899673, "percentage": 6.84, "elapsed_time": "1:04:48", "remaining_time": "14:42:24"}
+{"current_steps": 40, "total_steps": 570, "loss": 0.7269, "lr": 5.6140350877192984e-05, "epoch": 0.3489640130861505, "percentage": 7.02, "elapsed_time": "1:06:27", "remaining_time": "14:40:38"}
+{"current_steps": 41, "total_steps": 570, "loss": 0.7166, "lr": 5.7543859649122816e-05, "epoch": 0.35768811341330425, "percentage": 7.19, "elapsed_time": "1:08:07", "remaining_time": "14:38:53"}
+{"current_steps": 42, "total_steps": 570, "loss": 0.7098, "lr": 5.8947368421052634e-05, "epoch": 0.366412213740458, "percentage": 7.37, "elapsed_time": "1:09:46", "remaining_time": "14:37:06"}
+{"current_steps": 43, "total_steps": 570, "loss": 0.7148, "lr": 6.035087719298246e-05, "epoch": 0.3751363140676118, "percentage": 7.54, "elapsed_time": "1:11:26", "remaining_time": "14:35:32"}
+{"current_steps": 44, "total_steps": 570, "loss": 0.7239, "lr": 6.175438596491228e-05, "epoch": 0.38386041439476554, "percentage": 7.72, "elapsed_time": "1:13:06", "remaining_time": "14:33:52"}
+{"current_steps": 45, "total_steps": 570, "loss": 0.7129, "lr": 6.315789473684212e-05, "epoch": 0.3925845147219193, "percentage": 7.89, "elapsed_time": "1:14:45", "remaining_time": "14:32:06"}
+{"current_steps": 46, "total_steps": 570, "loss": 0.7207, "lr": 6.456140350877194e-05, "epoch": 0.40130861504907306, "percentage": 8.07, "elapsed_time": "1:16:24", "remaining_time": "14:30:26"}
+{"current_steps": 47, "total_steps": 570, "loss": 0.7027, "lr": 6.596491228070175e-05, "epoch": 0.4100327153762268, "percentage": 8.25, "elapsed_time": "1:18:04", "remaining_time": "14:28:45"}
+{"current_steps": 48, "total_steps": 570, "loss": 0.7109, "lr": 6.736842105263159e-05, "epoch": 0.4187568157033806, "percentage": 8.42, "elapsed_time": "1:19:43", "remaining_time": "14:27:00"}
+{"current_steps": 49, "total_steps": 570, "loss": 0.7084, "lr": 6.87719298245614e-05, "epoch": 0.42748091603053434, "percentage": 8.6, "elapsed_time": "1:21:22", "remaining_time": "14:25:15"}
+{"current_steps": 50, "total_steps": 570, "loss": 0.7101, "lr": 7.017543859649124e-05, "epoch": 0.4362050163576881, "percentage": 8.77, "elapsed_time": "1:23:01", "remaining_time": "14:23:30"}
+{"current_steps": 51, "total_steps": 570, "loss": 0.7047, "lr": 7.157894736842105e-05, "epoch": 0.44492911668484186, "percentage": 8.95, "elapsed_time": "1:24:41", "remaining_time": "14:21:46"}
+{"current_steps": 52, "total_steps": 570, "loss": 0.7011, "lr": 7.298245614035087e-05, "epoch": 0.4536532170119956, "percentage": 9.12, "elapsed_time": "1:26:20", "remaining_time": "14:20:02"}
+{"current_steps": 53, "total_steps": 570, "loss": 0.6901, "lr": 7.43859649122807e-05, "epoch": 0.4623773173391494, "percentage": 9.3, "elapsed_time": "1:27:59", "remaining_time": "14:18:18"}
+{"current_steps": 54, "total_steps": 570, "loss": 0.7184, "lr": 7.578947368421052e-05, "epoch": 0.47110141766630315, "percentage": 9.47, "elapsed_time": "1:29:38", "remaining_time": "14:16:34"}
+{"current_steps": 55, "total_steps": 570, "loss": 0.7122, "lr": 7.719298245614036e-05, "epoch": 0.4798255179934569, "percentage": 9.65, "elapsed_time": "1:31:17", "remaining_time": "14:14:52"}
+{"current_steps": 56, "total_steps": 570, "loss": 0.6969, "lr": 7.859649122807017e-05, "epoch": 0.48854961832061067, "percentage": 9.82, "elapsed_time": "1:32:57", "remaining_time": "14:13:12"}
+{"current_steps": 57, "total_steps": 570, "loss": 0.7003, "lr": 8e-05, "epoch": 0.49727371864776443, "percentage": 10.0, "elapsed_time": "1:34:36", "remaining_time": "14:11:29"}
+{"current_steps": 58, "total_steps": 570, "loss": 0.7047, "lr": 7.99992499440621e-05, "epoch": 0.5059978189749182, "percentage": 10.18, "elapsed_time": "1:36:15", "remaining_time": "14:09:46"}
+{"current_steps": 59, "total_steps": 570, "loss": 0.7035, "lr": 7.999699980437755e-05, "epoch": 0.514721919302072, "percentage": 10.35, "elapsed_time": "1:37:55", "remaining_time": "14:08:03"}
+{"current_steps": 60, "total_steps": 570, "loss": 0.6799, "lr": 7.999324966533291e-05, "epoch": 0.5234460196292258, "percentage": 10.53, "elapsed_time": "1:39:34", "remaining_time": "14:06:20"}
+{"current_steps": 61, "total_steps": 570, "loss": 0.7021, "lr": 7.998799966756889e-05, "epoch": 0.5321701199563795, "percentage": 10.7, "elapsed_time": "1:41:13", "remaining_time": "14:04:37"}
+{"current_steps": 62, "total_steps": 570, "loss": 0.691, "lr": 7.998125000797506e-05, "epoch": 0.5408942202835333, "percentage": 10.88, "elapsed_time": "1:42:52", "remaining_time": "14:02:55"}
+{"current_steps": 63, "total_steps": 570, "loss": 0.6967, "lr": 7.997300093968255e-05, "epoch": 0.549618320610687, "percentage": 11.05, "elapsed_time": "1:44:32", "remaining_time": "14:01:20"}
+{"current_steps": 64, "total_steps": 570, "loss": 0.7012, "lr": 7.99632527720545e-05, "epoch": 0.5583424209378408, "percentage": 11.23, "elapsed_time": "1:46:11", "remaining_time": "13:59:37"}
+{"current_steps": 65, "total_steps": 570, "loss": 0.6892, "lr": 7.995200587067445e-05, "epoch": 0.5670665212649946, "percentage": 11.4, "elapsed_time": "1:47:51", "remaining_time": "13:57:54"}
+{"current_steps": 66, "total_steps": 570, "loss": 0.6918, "lr": 7.993926065733265e-05, "epoch": 0.5757906215921483, "percentage": 11.58, "elapsed_time": "1:49:30", "remaining_time": "13:56:12"}
+{"current_steps": 67, "total_steps": 570, "loss": 0.6896, "lr": 7.992501761001027e-05, "epoch": 0.5845147219193021, "percentage": 11.75, "elapsed_time": "1:51:09", "remaining_time": "13:54:29"}
+{"current_steps": 68, "total_steps": 570, "loss": 0.6886, "lr": 7.99092772628614e-05, "epoch": 0.5932388222464559, "percentage": 11.93, "elapsed_time": "1:52:48", "remaining_time": "13:52:49"}
+{"current_steps": 69, "total_steps": 570, "loss": 0.6961, "lr": 7.98920402061931e-05, "epoch": 0.6019629225736096, "percentage": 12.11, "elapsed_time": "1:54:27", "remaining_time": "13:51:07"}
+{"current_steps": 70, "total_steps": 570, "loss": 0.6818, "lr": 7.987330708644319e-05, "epoch": 0.6106870229007634, "percentage": 12.28, "elapsed_time": "1:56:07", "remaining_time": "13:49:25"}
+{"current_steps": 71, "total_steps": 570, "loss": 0.6842, "lr": 7.985307860615607e-05, "epoch": 0.6194111232279171, "percentage": 12.46, "elapsed_time": "1:57:46", "remaining_time": "13:47:43"}
+{"current_steps": 72, "total_steps": 570, "loss": 0.6907, "lr": 7.98313555239563e-05, "epoch": 0.6281352235550709, "percentage": 12.63, "elapsed_time": "1:59:25", "remaining_time": "13:46:01"}
+{"current_steps": 73, "total_steps": 570, "loss": 0.6726, "lr": 7.980813865452026e-05, "epoch": 0.6368593238822247, "percentage": 12.81, "elapsed_time": "2:01:04", "remaining_time": "13:44:19"}
+{"current_steps": 74, "total_steps": 570, "loss": 0.6817, "lr": 7.978342886854546e-05, "epoch": 0.6455834242093784, "percentage": 12.98, "elapsed_time": "2:02:43", "remaining_time": "13:42:37"}
+{"current_steps": 75, "total_steps": 570, "loss": 0.675, "lr": 7.975722709271799e-05, "epoch": 0.6543075245365322, "percentage": 13.16, "elapsed_time": "2:04:22", "remaining_time": "13:40:55"}
+{"current_steps": 76, "total_steps": 570, "loss": 0.6742, "lr": 7.972953430967773e-05, "epoch": 0.6630316248636859, "percentage": 13.33, "elapsed_time": "2:06:02", "remaining_time": "13:39:13"}
+{"current_steps": 77, "total_steps": 570, "loss": 0.68, "lr": 7.97003515579815e-05, "epoch": 0.6717557251908397, "percentage": 13.51, "elapsed_time": "2:07:41", "remaining_time": "13:37:31"}
+{"current_steps": 78, "total_steps": 570, "loss": 0.6799, "lr": 7.96696799320641e-05, "epoch": 0.6804798255179935, "percentage": 13.68, "elapsed_time": "2:09:20", "remaining_time": "13:35:50"}
+{"current_steps": 79, "total_steps": 570, "loss": 0.6698, "lr": 7.96375205821973e-05, "epoch": 0.6892039258451472, "percentage": 13.86, "elapsed_time": "2:10:59", "remaining_time": "13:34:08"}
+{"current_steps": 80, "total_steps": 570, "loss": 0.6832, "lr": 7.960387471444666e-05, "epoch": 0.697928026172301, "percentage": 14.04, "elapsed_time": "2:12:38", "remaining_time": "13:32:27"}
+{"current_steps": 81, "total_steps": 570, "loss": 0.6778, "lr": 7.956874359062632e-05, "epoch": 0.7066521264994547, "percentage": 14.21, "elapsed_time": "2:14:18", "remaining_time": "13:30:48"}
+{"current_steps": 82, "total_steps": 570, "loss": 0.684, "lr": 7.95321285282517e-05, "epoch": 0.7153762268266085, "percentage": 14.39, "elapsed_time": "2:15:57", "remaining_time": "13:29:06"}
+{"current_steps": 83, "total_steps": 570, "loss": 0.6811, "lr": 7.949403090049002e-05, "epoch": 0.7241003271537623, "percentage": 14.56, "elapsed_time": "2:17:36", "remaining_time": "13:27:25"}
+{"current_steps": 84, "total_steps": 570, "loss": 0.6891, "lr": 7.94544521361089e-05, "epoch": 0.732824427480916, "percentage": 14.74, "elapsed_time": "2:19:15", "remaining_time": "13:25:43"}
+{"current_steps": 85, "total_steps": 570, "loss": 0.6763, "lr": 7.941339371942269e-05, "epoch": 0.7415485278080698, "percentage": 14.91, "elapsed_time": "2:20:55", "remaining_time": "13:24:04"}
+{"current_steps": 86, "total_steps": 570, "loss": 0.6869, "lr": 7.937085719023685e-05, "epoch": 0.7502726281352236, "percentage": 15.09, "elapsed_time": "2:22:34", "remaining_time": "13:22:23"}
+{"current_steps": 87, "total_steps": 570, "loss": 0.6771, "lr": 7.932684414379021e-05, "epoch": 0.7589967284623773, "percentage": 15.26, "elapsed_time": "2:24:13", "remaining_time": "13:20:42"}
+{"current_steps": 88, "total_steps": 570, "loss": 0.6793, "lr": 7.928135623069509e-05, "epoch": 0.7677208287895311, "percentage": 15.44, "elapsed_time": "2:25:52", "remaining_time": "13:19:01"}
+{"current_steps": 89, "total_steps": 570, "loss": 0.6776, "lr": 7.923439515687546e-05, "epoch": 0.7764449291166848, "percentage": 15.61, "elapsed_time": "2:27:31", "remaining_time": "13:17:20"}
+{"current_steps": 90, "total_steps": 570, "loss": 0.6736, "lr": 7.918596268350296e-05, "epoch": 0.7851690294438386, "percentage": 15.79, "elapsed_time": "2:29:11", "remaining_time": "13:15:41"}
+{"current_steps": 91, "total_steps": 570, "loss": 0.6747, "lr": 7.913606062693077e-05, "epoch": 0.7938931297709924, "percentage": 15.96, "elapsed_time": "2:30:50", "remaining_time": "13:14:00"}
+{"current_steps": 92, "total_steps": 570, "loss": 0.6703, "lr": 7.90846908586256e-05, "epoch": 0.8026172300981461, "percentage": 16.14, "elapsed_time": "2:32:29", "remaining_time": "13:12:19"}
+{"current_steps": 93, "total_steps": 570, "loss": 0.6667, "lr": 7.903185530509743e-05, "epoch": 0.8113413304252999, "percentage": 16.32, "elapsed_time": "2:34:09", "remaining_time": "13:10:38"}
+{"current_steps": 94, "total_steps": 570, "loss": 0.6842, "lr": 7.89775559478273e-05, "epoch": 0.8200654307524536, "percentage": 16.49, "elapsed_time": "2:35:48", "remaining_time": "13:08:58"}
+{"current_steps": 95, "total_steps": 570, "loss": 0.6804, "lr": 7.892179482319297e-05, "epoch": 0.8287895310796074, "percentage": 16.67, "elapsed_time": "2:37:27", "remaining_time": "13:07:17"}
+{"current_steps": 96, "total_steps": 570, "loss": 0.6694, "lr": 7.886457402239256e-05, "epoch": 0.8375136314067612, "percentage": 16.84, "elapsed_time": "2:39:06", "remaining_time": "13:05:36"}
+{"current_steps": 97, "total_steps": 570, "loss": 0.6568, "lr": 7.880589569136616e-05, "epoch": 0.8462377317339149, "percentage": 17.02, "elapsed_time": "2:40:45", "remaining_time": "13:03:55"}
+{"current_steps": 98, "total_steps": 570, "loss": 0.6724, "lr": 7.874576203071531e-05, "epoch": 0.8549618320610687, "percentage": 17.19, "elapsed_time": "2:42:24", "remaining_time": "13:02:14"}
+{"current_steps": 99, "total_steps": 570, "loss": 0.6582, "lr": 7.868417529562043e-05, "epoch": 0.8636859323882224, "percentage": 17.37, "elapsed_time": "2:44:04", "remaining_time": "13:00:33"}
+{"current_steps": 100, "total_steps": 570, "loss": 0.6668, "lr": 7.862113779575638e-05, "epoch": 0.8724100327153762, "percentage": 17.54, "elapsed_time": "2:45:43", "remaining_time": "12:58:53"}
+{"current_steps": 101, "total_steps": 570, "loss": 0.6539, "lr": 7.85566518952057e-05, "epoch": 0.88113413304253, "percentage": 17.72, "elapsed_time": "2:47:22", "remaining_time": "12:57:12"}
+{"current_steps": 102, "total_steps": 570, "loss": 0.6647, "lr": 7.849072001237001e-05, "epoch": 0.8898582333696837, "percentage": 17.89, "elapsed_time": "2:49:01", "remaining_time": "12:55:31"}
+{"current_steps": 103, "total_steps": 570, "loss": 0.6616, "lr": 7.842334461987936e-05, "epoch": 0.8985823336968375, "percentage": 18.07, "elapsed_time": "2:50:40", "remaining_time": "12:53:51"}
+{"current_steps": 104, "total_steps": 570, "loss": 0.6609, "lr": 7.835452824449935e-05, "epoch": 0.9073064340239912, "percentage": 18.25, "elapsed_time": "2:52:19", "remaining_time": "12:52:10"}
+{"current_steps": 105, "total_steps": 570, "loss": 0.6556, "lr": 7.828427346703657e-05, "epoch": 0.916030534351145, "percentage": 18.42, "elapsed_time": "2:53:58", "remaining_time": "12:50:29"}
+{"current_steps": 106, "total_steps": 570, "loss": 0.6642, "lr": 7.821258292224166e-05, "epoch": 0.9247546346782988, "percentage": 18.6, "elapsed_time": "2:55:38", "remaining_time": "12:48:49"}
+{"current_steps": 107, "total_steps": 570, "loss": 0.6478, "lr": 7.813945929871056e-05, "epoch": 0.9334787350054525, "percentage": 18.77, "elapsed_time": "2:57:17", "remaining_time": "12:47:08"}
+{"current_steps": 108, "total_steps": 570, "loss": 0.66, "lr": 7.806490533878368e-05, "epoch": 0.9422028353326063, "percentage": 18.95, "elapsed_time": "2:58:56", "remaining_time": "12:45:27"}
+{"current_steps": 109, "total_steps": 570, "loss": 0.657, "lr": 7.798892383844303e-05, "epoch": 0.95092693565976, "percentage": 19.12, "elapsed_time": "3:00:35", "remaining_time": "12:43:47"}
+{"current_steps": 110, "total_steps": 570, "loss": 0.6548, "lr": 7.791151764720737e-05, "epoch": 0.9596510359869138, "percentage": 19.3, "elapsed_time": "3:02:15", "remaining_time": "12:42:09"}
+{"current_steps": 111, "total_steps": 570, "loss": 0.662, "lr": 7.783268966802539e-05, "epoch": 0.9683751363140676, "percentage": 19.47, "elapsed_time": "3:03:54", "remaining_time": "12:40:30"}
+{"current_steps": 112, "total_steps": 570, "loss": 0.6603, "lr": 7.775244285716679e-05, "epoch": 0.9770992366412213, "percentage": 19.65, "elapsed_time": "3:05:33", "remaining_time": "12:38:49"}
+{"current_steps": 113, "total_steps": 570, "loss": 0.6495, "lr": 7.767078022411139e-05, "epoch": 0.9858233369683751, "percentage": 19.82, "elapsed_time": "3:07:13", "remaining_time": "12:37:09"}
+{"current_steps": 114, "total_steps": 570, "loss": 0.6632, "lr": 7.758770483143634e-05, "epoch": 0.9945474372955289, "percentage": 20.0, "elapsed_time": "3:08:52", "remaining_time": "12:35:31"}
+{"current_steps": 115, "total_steps": 570, "loss": 0.6249, "lr": 7.750321979470123e-05, "epoch": 1.0076335877862594, "percentage": 20.18, "elapsed_time": "3:12:20", "remaining_time": "12:41:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27c7eeccc0a1d9ead0facd6dd9466bfb4d9868c32eaa398bbcd8bf9fce147f5
+size 7288