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:f0b4123fe0961dd71215e02bbd5cab62e6ca006af60de97071ef86096eb5ad3e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6277599adfd6f662180bc43b3ab59c90d2828f3cece67a1c84468bff42a0f2b5
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00186ad853b3b630b63b0a56857fc26e84aaa19ae2ef6b6453776483297b39ad
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e9705559872829427a6f53c903396114a223f3957eb4bf42aaff680ebbea48
+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 +1,92 @@
+{"current_steps": 1, "total_steps": 455, "loss": 0.872, "lr": 1.7391304347826088e-06, "epoch": 0.010884353741496598, "percentage": 0.22, "elapsed_time": "0:04:31", "remaining_time": "1 day, 10:13:12"}
+{"current_steps": 2, "total_steps": 455, "loss": 0.851, "lr": 3.4782608695652175e-06, "epoch": 0.021768707482993196, "percentage": 0.44, "elapsed_time": "0:08:12", "remaining_time": "1 day, 7:00:19"}
+{"current_steps": 3, "total_steps": 455, "loss": 0.8568, "lr": 5.2173913043478265e-06, "epoch": 0.0326530612244898, "percentage": 0.66, "elapsed_time": "0:11:54", "remaining_time": "1 day, 5:54:09"}
+{"current_steps": 4, "total_steps": 455, "loss": 0.8166, "lr": 6.956521739130435e-06, "epoch": 0.04353741496598639, "percentage": 0.88, "elapsed_time": "0:15:35", "remaining_time": "1 day, 5:17:34"}
+{"current_steps": 5, "total_steps": 455, "loss": 0.7738, "lr": 8.695652173913044e-06, "epoch": 0.05442176870748299, "percentage": 1.1, "elapsed_time": "0:19:16", "remaining_time": "1 day, 4:54:39"}
+{"current_steps": 6, "total_steps": 455, "loss": 0.778, "lr": 1.0434782608695653e-05, "epoch": 0.0653061224489796, "percentage": 1.32, "elapsed_time": "0:22:57", "remaining_time": "1 day, 4:38:24"}
+{"current_steps": 7, "total_steps": 455, "loss": 0.7837, "lr": 1.2173913043478263e-05, "epoch": 0.0761904761904762, "percentage": 1.54, "elapsed_time": "0:26:38", "remaining_time": "1 day, 4:25:11"}
+{"current_steps": 8, "total_steps": 455, "loss": 0.7412, "lr": 1.391304347826087e-05, "epoch": 0.08707482993197278, "percentage": 1.76, "elapsed_time": "0:30:19", "remaining_time": "1 day, 4:14:33"}
+{"current_steps": 9, "total_steps": 455, "loss": 0.7248, "lr": 1.565217391304348e-05, "epoch": 0.09795918367346938, "percentage": 1.98, "elapsed_time": "0:34:00", "remaining_time": "1 day, 4:04:56"}
+{"current_steps": 10, "total_steps": 455, "loss": 0.7153, "lr": 1.739130434782609e-05, "epoch": 0.10884353741496598, "percentage": 2.2, "elapsed_time": "0:37:40", "remaining_time": "1 day, 3:56:46"}
+{"current_steps": 11, "total_steps": 455, "loss": 0.6763, "lr": 1.9130434782608697e-05, "epoch": 0.11972789115646258, "percentage": 2.42, "elapsed_time": "0:41:21", "remaining_time": "1 day, 3:49:37"}
+{"current_steps": 12, "total_steps": 455, "loss": 0.6582, "lr": 2.0869565217391306e-05, "epoch": 0.1306122448979592, "percentage": 2.64, "elapsed_time": "0:45:02", "remaining_time": "1 day, 3:43:03"}
+{"current_steps": 13, "total_steps": 455, "loss": 0.6376, "lr": 2.2608695652173914e-05, "epoch": 0.1414965986394558, "percentage": 2.86, "elapsed_time": "0:48:44", "remaining_time": "1 day, 3:37:02"}
+{"current_steps": 14, "total_steps": 455, "loss": 0.6266, "lr": 2.4347826086956526e-05, "epoch": 0.1523809523809524, "percentage": 3.08, "elapsed_time": "0:52:25", "remaining_time": "1 day, 3:31:17"}
+{"current_steps": 15, "total_steps": 455, "loss": 0.6091, "lr": 2.608695652173913e-05, "epoch": 0.16326530612244897, "percentage": 3.3, "elapsed_time": "0:56:06", "remaining_time": "1 day, 3:25:47"}
+{"current_steps": 16, "total_steps": 455, "loss": 0.5957, "lr": 2.782608695652174e-05, "epoch": 0.17414965986394557, "percentage": 3.52, "elapsed_time": "0:59:47", "remaining_time": "1 day, 3:20:34"}
+{"current_steps": 17, "total_steps": 455, "loss": 0.6085, "lr": 2.956521739130435e-05, "epoch": 0.18503401360544217, "percentage": 3.74, "elapsed_time": "1:03:28", "remaining_time": "1 day, 3:15:26"}
+{"current_steps": 18, "total_steps": 455, "loss": 0.6002, "lr": 3.130434782608696e-05, "epoch": 0.19591836734693877, "percentage": 3.96, "elapsed_time": "1:07:09", "remaining_time": "1 day, 3:10:30"}
+{"current_steps": 19, "total_steps": 455, "loss": 0.585, "lr": 3.304347826086957e-05, "epoch": 0.20680272108843537, "percentage": 4.18, "elapsed_time": "1:10:50", "remaining_time": "1 day, 3:05:45"}
+{"current_steps": 20, "total_steps": 455, "loss": 0.573, "lr": 3.478260869565218e-05, "epoch": 0.21768707482993196, "percentage": 4.4, "elapsed_time": "1:14:31", "remaining_time": "1 day, 3:01:03"}
+{"current_steps": 21, "total_steps": 455, "loss": 0.5681, "lr": 3.6521739130434786e-05, "epoch": 0.22857142857142856, "percentage": 4.62, "elapsed_time": "1:18:13", "remaining_time": "1 day, 2:56:30"}
+{"current_steps": 22, "total_steps": 455, "loss": 0.5756, "lr": 3.8260869565217395e-05, "epoch": 0.23945578231292516, "percentage": 4.84, "elapsed_time": "1:21:54", "remaining_time": "1 day, 2:51:59"}
+{"current_steps": 23, "total_steps": 455, "loss": 0.5697, "lr": 4e-05, "epoch": 0.2503401360544218, "percentage": 5.05, "elapsed_time": "1:25:35", "remaining_time": "1 day, 2:47:39"}
+{"current_steps": 24, "total_steps": 455, "loss": 0.5648, "lr": 4.173913043478261e-05, "epoch": 0.2612244897959184, "percentage": 5.27, "elapsed_time": "1:29:15", "remaining_time": "1 day, 2:42:58"}
+{"current_steps": 25, "total_steps": 455, "loss": 0.563, "lr": 4.347826086956522e-05, "epoch": 0.272108843537415, "percentage": 5.49, "elapsed_time": "1:32:56", "remaining_time": "1 day, 2:38:38"}
+{"current_steps": 26, "total_steps": 455, "loss": 0.5537, "lr": 4.521739130434783e-05, "epoch": 0.2829931972789116, "percentage": 5.71, "elapsed_time": "1:36:36", "remaining_time": "1 day, 2:34:09"}
+{"current_steps": 27, "total_steps": 455, "loss": 0.5454, "lr": 4.6956521739130444e-05, "epoch": 0.2938775510204082, "percentage": 5.93, "elapsed_time": "1:40:17", "remaining_time": "1 day, 2:29:41"}
+{"current_steps": 28, "total_steps": 455, "loss": 0.5565, "lr": 4.869565217391305e-05, "epoch": 0.3047619047619048, "percentage": 6.15, "elapsed_time": "1:43:57", "remaining_time": "1 day, 2:25:27"}
+{"current_steps": 29, "total_steps": 455, "loss": 0.562, "lr": 5.043478260869566e-05, "epoch": 0.31564625850340133, "percentage": 6.37, "elapsed_time": "1:47:38", "remaining_time": "1 day, 2:21:15"}
+{"current_steps": 30, "total_steps": 455, "loss": 0.5407, "lr": 5.217391304347826e-05, "epoch": 0.32653061224489793, "percentage": 6.59, "elapsed_time": "1:51:19", "remaining_time": "1 day, 2:17:00"}
+{"current_steps": 31, "total_steps": 455, "loss": 0.5428, "lr": 5.391304347826087e-05, "epoch": 0.33741496598639453, "percentage": 6.81, "elapsed_time": "1:55:00", "remaining_time": "1 day, 2:12:55"}
+{"current_steps": 32, "total_steps": 455, "loss": 0.5485, "lr": 5.565217391304348e-05, "epoch": 0.34829931972789113, "percentage": 7.03, "elapsed_time": "1:58:40", "remaining_time": "1 day, 2:08:48"}
+{"current_steps": 33, "total_steps": 455, "loss": 0.525, "lr": 5.739130434782609e-05, "epoch": 0.35918367346938773, "percentage": 7.25, "elapsed_time": "2:02:22", "remaining_time": "1 day, 2:04:50"}
+{"current_steps": 34, "total_steps": 455, "loss": 0.5426, "lr": 5.91304347826087e-05, "epoch": 0.37006802721088433, "percentage": 7.47, "elapsed_time": "2:06:03", "remaining_time": "1 day, 2:00:47"}
+{"current_steps": 35, "total_steps": 455, "loss": 0.5331, "lr": 6.086956521739131e-05, "epoch": 0.38095238095238093, "percentage": 7.69, "elapsed_time": "2:09:43", "remaining_time": "1 day, 1:56:46"}
+{"current_steps": 36, "total_steps": 455, "loss": 0.5279, "lr": 6.260869565217392e-05, "epoch": 0.39183673469387753, "percentage": 7.91, "elapsed_time": "2:13:24", "remaining_time": "1 day, 1:52:45"}
+{"current_steps": 37, "total_steps": 455, "loss": 0.527, "lr": 6.434782608695653e-05, "epoch": 0.40272108843537413, "percentage": 8.13, "elapsed_time": "2:17:06", "remaining_time": "1 day, 1:48:55"}
+{"current_steps": 38, "total_steps": 455, "loss": 0.5276, "lr": 6.608695652173914e-05, "epoch": 0.41360544217687073, "percentage": 8.35, "elapsed_time": "2:20:47", "remaining_time": "1 day, 1:44:59"}
+{"current_steps": 39, "total_steps": 455, "loss": 0.5232, "lr": 6.782608695652175e-05, "epoch": 0.42448979591836733, "percentage": 8.57, "elapsed_time": "2:24:28", "remaining_time": "1 day, 1:41:02"}
+{"current_steps": 40, "total_steps": 455, "loss": 0.529, "lr": 6.956521739130436e-05, "epoch": 0.43537414965986393, "percentage": 8.79, "elapsed_time": "2:28:09", "remaining_time": "1 day, 1:37:09"}
+{"current_steps": 41, "total_steps": 455, "loss": 0.5286, "lr": 7.130434782608696e-05, "epoch": 0.44625850340136053, "percentage": 9.01, "elapsed_time": "2:31:49", "remaining_time": "1 day, 1:33:08"}
+{"current_steps": 42, "total_steps": 455, "loss": 0.5302, "lr": 7.304347826086957e-05, "epoch": 0.45714285714285713, "percentage": 9.23, "elapsed_time": "2:35:30", "remaining_time": "1 day, 1:29:11"}
+{"current_steps": 43, "total_steps": 455, "loss": 0.5239, "lr": 7.478260869565218e-05, "epoch": 0.46802721088435373, "percentage": 9.45, "elapsed_time": "2:39:11", "remaining_time": "1 day, 1:25:18"}
+{"current_steps": 44, "total_steps": 455, "loss": 0.5279, "lr": 7.652173913043479e-05, "epoch": 0.47891156462585033, "percentage": 9.67, "elapsed_time": "2:42:52", "remaining_time": "1 day, 1:21:25"}
+{"current_steps": 45, "total_steps": 455, "loss": 0.5241, "lr": 7.82608695652174e-05, "epoch": 0.4897959183673469, "percentage": 9.89, "elapsed_time": "2:46:33", "remaining_time": "1 day, 1:17:32"}
+{"current_steps": 46, "total_steps": 455, "loss": 0.5249, "lr": 8e-05, "epoch": 0.5006802721088436, "percentage": 10.11, "elapsed_time": "2:50:13", "remaining_time": "1 day, 1:13:35"}
+{"current_steps": 47, "total_steps": 455, "loss": 0.5154, "lr": 7.999882000276476e-05, "epoch": 0.5115646258503401, "percentage": 10.33, "elapsed_time": "2:53:55", "remaining_time": "1 day, 1:09:45"}
+{"current_steps": 48, "total_steps": 455, "loss": 0.5152, "lr": 7.999528008067867e-05, "epoch": 0.5224489795918368, "percentage": 10.55, "elapsed_time": "2:57:36", "remaining_time": "1 day, 1:05:57"}
+{"current_steps": 49, "total_steps": 455, "loss": 0.5085, "lr": 7.998938044259668e-05, "epoch": 0.5333333333333333, "percentage": 10.77, "elapsed_time": "3:01:17", "remaining_time": "1 day, 1:02:05"}
+{"current_steps": 50, "total_steps": 455, "loss": 0.5121, "lr": 7.99811214365966e-05, "epoch": 0.54421768707483, "percentage": 10.99, "elapsed_time": "3:04:58", "remaining_time": "1 day, 0:58:13"}
+{"current_steps": 51, "total_steps": 455, "loss": 0.5095, "lr": 7.997050354995864e-05, "epoch": 0.5551020408163265, "percentage": 11.21, "elapsed_time": "3:08:39", "remaining_time": "1 day, 0:54:25"}
+{"current_steps": 52, "total_steps": 455, "loss": 0.5207, "lr": 7.995752740913666e-05, "epoch": 0.5659863945578232, "percentage": 11.43, "elapsed_time": "3:12:20", "remaining_time": "1 day, 0:50:37"}
+{"current_steps": 53, "total_steps": 455, "loss": 0.5321, "lr": 7.994219377972118e-05, "epoch": 0.5768707482993197, "percentage": 11.65, "elapsed_time": "3:16:00", "remaining_time": "1 day, 0:46:45"}
+{"current_steps": 54, "total_steps": 455, "loss": 0.522, "lr": 7.992450356639418e-05, "epoch": 0.5877551020408164, "percentage": 11.87, "elapsed_time": "3:19:42", "remaining_time": "1 day, 0:42:59"}
+{"current_steps": 55, "total_steps": 455, "loss": 0.5303, "lr": 7.990445781287584e-05, "epoch": 0.5986394557823129, "percentage": 12.09, "elapsed_time": "3:23:23", "remaining_time": "1 day, 0:39:09"}
+{"current_steps": 56, "total_steps": 455, "loss": 0.5228, "lr": 7.988205770186282e-05, "epoch": 0.6095238095238096, "percentage": 12.31, "elapsed_time": "3:27:04", "remaining_time": "1 day, 0:35:22"}
+{"current_steps": 57, "total_steps": 455, "loss": 0.5102, "lr": 7.985730455495858e-05, "epoch": 0.6204081632653061, "percentage": 12.53, "elapsed_time": "3:30:45", "remaining_time": "1 day, 0:31:36"}
+{"current_steps": 58, "total_steps": 455, "loss": 0.5102, "lr": 7.983019983259538e-05, "epoch": 0.6312925170068027, "percentage": 12.75, "elapsed_time": "3:34:25", "remaining_time": "1 day, 0:27:43"}
+{"current_steps": 59, "total_steps": 455, "loss": 0.5295, "lr": 7.980074513394808e-05, "epoch": 0.6421768707482993, "percentage": 12.97, "elapsed_time": "3:38:06", "remaining_time": "1 day, 0:23:58"}
+{"current_steps": 60, "total_steps": 455, "loss": 0.5171, "lr": 7.976894219683982e-05, "epoch": 0.6530612244897959, "percentage": 13.19, "elapsed_time": "3:41:47", "remaining_time": "1 day, 0:20:07"}
+{"current_steps": 61, "total_steps": 455, "loss": 0.5125, "lr": 7.97347928976395e-05, "epoch": 0.6639455782312925, "percentage": 13.41, "elapsed_time": "3:45:28", "remaining_time": "1 day, 0:16:22"}
+{"current_steps": 62, "total_steps": 455, "loss": 0.5046, "lr": 7.969829925115106e-05, "epoch": 0.6748299319727891, "percentage": 13.63, "elapsed_time": "3:49:09", "remaining_time": "1 day, 0:12:36"}
+{"current_steps": 63, "total_steps": 455, "loss": 0.5135, "lr": 7.96594634104946e-05, "epoch": 0.6857142857142857, "percentage": 13.85, "elapsed_time": "3:52:51", "remaining_time": "1 day, 0:08:53"}
+{"current_steps": 64, "total_steps": 455, "loss": 0.4996, "lr": 7.961828766697934e-05, "epoch": 0.6965986394557823, "percentage": 14.07, "elapsed_time": "3:56:32", "remaining_time": "1 day, 0:05:08"}
+{"current_steps": 65, "total_steps": 455, "loss": 0.4991, "lr": 7.957477444996846e-05, "epoch": 0.7074829931972789, "percentage": 14.29, "elapsed_time": "4:00:13", "remaining_time": "1 day, 0:01:18"}
+{"current_steps": 66, "total_steps": 455, "loss": 0.5142, "lr": 7.952892632673575e-05, "epoch": 0.7183673469387755, "percentage": 14.51, "elapsed_time": "4:03:54", "remaining_time": "23:57:34"}
+{"current_steps": 67, "total_steps": 455, "loss": 0.4975, "lr": 7.948074600231413e-05, "epoch": 0.7292517006802721, "percentage": 14.73, "elapsed_time": "4:07:35", "remaining_time": "23:53:47"}
+{"current_steps": 68, "total_steps": 455, "loss": 0.5041, "lr": 7.943023631933609e-05, "epoch": 0.7401360544217687, "percentage": 14.95, "elapsed_time": "4:11:16", "remaining_time": "23:50:01"}
+{"current_steps": 69, "total_steps": 455, "loss": 0.5027, "lr": 7.937740025786595e-05, "epoch": 0.7510204081632653, "percentage": 15.16, "elapsed_time": "4:14:57", "remaining_time": "23:46:15"}
+{"current_steps": 70, "total_steps": 455, "loss": 0.4919, "lr": 7.932224093522403e-05, "epoch": 0.7619047619047619, "percentage": 15.38, "elapsed_time": "4:18:38", "remaining_time": "23:42:32"}
+{"current_steps": 71, "total_steps": 455, "loss": 0.496, "lr": 7.926476160580272e-05, "epoch": 0.7727891156462585, "percentage": 15.6, "elapsed_time": "4:22:19", "remaining_time": "23:38:48"}
+{"current_steps": 72, "total_steps": 455, "loss": 0.4928, "lr": 7.920496566087454e-05, "epoch": 0.7836734693877551, "percentage": 15.82, "elapsed_time": "4:26:00", "remaining_time": "23:35:03"}
+{"current_steps": 73, "total_steps": 455, "loss": 0.4992, "lr": 7.914285662839197e-05, "epoch": 0.7945578231292517, "percentage": 16.04, "elapsed_time": "4:29:41", "remaining_time": "23:31:16"}
+{"current_steps": 74, "total_steps": 455, "loss": 0.4873, "lr": 7.907843817277931e-05, "epoch": 0.8054421768707483, "percentage": 16.26, "elapsed_time": "4:33:22", "remaining_time": "23:27:30"}
+{"current_steps": 75, "total_steps": 455, "loss": 0.4932, "lr": 7.901171409471658e-05, "epoch": 0.8163265306122449, "percentage": 16.48, "elapsed_time": "4:37:03", "remaining_time": "23:23:45"}
+{"current_steps": 76, "total_steps": 455, "loss": 0.4971, "lr": 7.894268833091514e-05, "epoch": 0.8272108843537415, "percentage": 16.7, "elapsed_time": "4:40:44", "remaining_time": "23:20:03"}
+{"current_steps": 77, "total_steps": 455, "loss": 0.497, "lr": 7.887136495388551e-05, "epoch": 0.8380952380952381, "percentage": 16.92, "elapsed_time": "4:44:25", "remaining_time": "23:16:18"}
+{"current_steps": 78, "total_steps": 455, "loss": 0.4911, "lr": 7.879774817169707e-05, "epoch": 0.8489795918367347, "percentage": 17.14, "elapsed_time": "4:48:06", "remaining_time": "23:12:32"}
+{"current_steps": 79, "total_steps": 455, "loss": 0.5038, "lr": 7.872184232772979e-05, "epoch": 0.8598639455782313, "percentage": 17.36, "elapsed_time": "4:51:47", "remaining_time": "23:08:48"}
+{"current_steps": 80, "total_steps": 455, "loss": 0.4996, "lr": 7.8643651900418e-05, "epoch": 0.8707482993197279, "percentage": 17.58, "elapsed_time": "4:55:29", "remaining_time": "23:05:05"}
+{"current_steps": 81, "total_steps": 455, "loss": 0.4929, "lr": 7.856318150298608e-05, "epoch": 0.8816326530612245, "percentage": 17.8, "elapsed_time": "4:59:10", "remaining_time": "23:01:21"}
+{"current_steps": 82, "total_steps": 455, "loss": 0.4806, "lr": 7.848043588317636e-05, "epoch": 0.8925170068027211, "percentage": 18.02, "elapsed_time": "5:02:51", "remaining_time": "22:57:36"}
+{"current_steps": 83, "total_steps": 455, "loss": 0.4913, "lr": 7.839541992296897e-05, "epoch": 0.9034013605442177, "percentage": 18.24, "elapsed_time": "5:06:32", "remaining_time": "22:53:52"}
+{"current_steps": 84, "total_steps": 455, "loss": 0.4874, "lr": 7.830813863829381e-05, "epoch": 0.9142857142857143, "percentage": 18.46, "elapsed_time": "5:10:12", "remaining_time": "22:50:05"}
+{"current_steps": 85, "total_steps": 455, "loss": 0.4952, "lr": 7.82185971787346e-05, "epoch": 0.9251700680272109, "percentage": 18.68, "elapsed_time": "5:13:53", "remaining_time": "22:46:22"}
+{"current_steps": 86, "total_steps": 455, "loss": 0.4925, "lr": 7.81268008272251e-05, "epoch": 0.9360544217687075, "percentage": 18.9, "elapsed_time": "5:17:34", "remaining_time": "22:42:38"}
+{"current_steps": 87, "total_steps": 455, "loss": 0.4878, "lr": 7.803275499973733e-05, "epoch": 0.9469387755102041, "percentage": 19.12, "elapsed_time": "5:21:15", "remaining_time": "22:38:54"}
+{"current_steps": 88, "total_steps": 455, "loss": 0.4907, "lr": 7.793646524496214e-05, "epoch": 0.9578231292517007, "percentage": 19.34, "elapsed_time": "5:24:56", "remaining_time": "22:35:11"}
+{"current_steps": 89, "total_steps": 455, "loss": 0.4875, "lr": 7.783793724398172e-05, "epoch": 0.9687074829931973, "percentage": 19.56, "elapsed_time": "5:28:38", "remaining_time": "22:31:28"}
+{"current_steps": 90, "total_steps": 455, "loss": 0.4929, "lr": 7.773717680993454e-05, "epoch": 0.9795918367346939, "percentage": 19.78, "elapsed_time": "5:32:19", "remaining_time": "22:27:45"}
+{"current_steps": 91, "total_steps": 455, "loss": 0.4822, "lr": 7.763418988767225e-05, "epoch": 0.9904761904761905, "percentage": 20.0, "elapsed_time": "5:36:00", "remaining_time": "22:24:03"}
+{"current_steps": 92, "total_steps": 455, "loss": 0.6339, "lr": 7.752898255340904e-05, "epoch": 1.0034013605442176, "percentage": 20.22, "elapsed_time": "5:41:26", "remaining_time": "22:27:11"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:381ccffa9f008b25d51033273151645a23e393df95703c36b60ddf94be4a044d
+size 7160