Training in progress, epoch 1

.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 sha256:981c4edfbb1e5911bcb0702e2c9fee936d32baa3660e57c5a73a15ae5d0b5c37
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615131db04b041f7a93b35d5d9ec0ffb4ed39837a32e0617b5ed585954701158
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5368ed6f33a9817ff13ca0ddc52007b6af9a2a7590adef462e47cc931e5a674c
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91c69c9c8e20ffcb0c076bc2cb6a2d14f269b8c011ef5c414e24abb1c310af9
+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 +1,105 @@
+{"current_steps": 1, "total_steps": 309, "loss": 1.2227, "lr": 3.2258064516129035e-07, "epoch": 0.009708737864077669, "percentage": 0.32, "elapsed_time": "0:01:01", "remaining_time": "5:13:16"}
+{"current_steps": 2, "total_steps": 309, "loss": 1.2675, "lr": 6.451612903225807e-07, "epoch": 0.019417475728155338, "percentage": 0.65, "elapsed_time": "0:01:49", "remaining_time": "4:40:06"}
+{"current_steps": 3, "total_steps": 309, "loss": 1.2517, "lr": 9.67741935483871e-07, "epoch": 0.02912621359223301, "percentage": 0.97, "elapsed_time": "0:02:43", "remaining_time": "4:37:37"}
+{"current_steps": 4, "total_steps": 309, "loss": 1.2515, "lr": 1.2903225806451614e-06, "epoch": 0.038834951456310676, "percentage": 1.29, "elapsed_time": "0:03:35", "remaining_time": "4:33:24"}
+{"current_steps": 5, "total_steps": 309, "loss": 1.2498, "lr": 1.6129032258064516e-06, "epoch": 0.04854368932038835, "percentage": 1.62, "elapsed_time": "0:04:36", "remaining_time": "4:40:21"}
+{"current_steps": 6, "total_steps": 309, "loss": 1.2283, "lr": 1.935483870967742e-06, "epoch": 0.05825242718446602, "percentage": 1.94, "elapsed_time": "0:05:29", "remaining_time": "4:37:02"}
+{"current_steps": 7, "total_steps": 309, "loss": 1.1489, "lr": 2.2580645161290324e-06, "epoch": 0.06796116504854369, "percentage": 2.27, "elapsed_time": "0:06:21", "remaining_time": "4:34:29"}
+{"current_steps": 8, "total_steps": 309, "loss": 1.1759, "lr": 2.580645161290323e-06, "epoch": 0.07766990291262135, "percentage": 2.59, "elapsed_time": "0:07:12", "remaining_time": "4:31:06"}
+{"current_steps": 9, "total_steps": 309, "loss": 1.128, "lr": 2.903225806451613e-06, "epoch": 0.08737864077669903, "percentage": 2.91, "elapsed_time": "0:07:58", "remaining_time": "4:25:38"}
+{"current_steps": 10, "total_steps": 309, "loss": 1.1088, "lr": 3.225806451612903e-06, "epoch": 0.0970873786407767, "percentage": 3.24, "elapsed_time": "0:08:53", "remaining_time": "4:25:40"}
+{"current_steps": 11, "total_steps": 309, "loss": 1.1275, "lr": 3.548387096774194e-06, "epoch": 0.10679611650485436, "percentage": 3.56, "elapsed_time": "0:09:41", "remaining_time": "4:22:20"}
+{"current_steps": 12, "total_steps": 309, "loss": 1.1287, "lr": 3.870967741935484e-06, "epoch": 0.11650485436893204, "percentage": 3.88, "elapsed_time": "0:10:37", "remaining_time": "4:23:08"}
+{"current_steps": 13, "total_steps": 309, "loss": 1.1011, "lr": 4.193548387096774e-06, "epoch": 0.1262135922330097, "percentage": 4.21, "elapsed_time": "0:11:24", "remaining_time": "4:19:35"}
+{"current_steps": 14, "total_steps": 309, "loss": 1.1392, "lr": 4.516129032258065e-06, "epoch": 0.13592233009708737, "percentage": 4.53, "elapsed_time": "0:12:16", "remaining_time": "4:18:46"}
+{"current_steps": 15, "total_steps": 309, "loss": 1.0678, "lr": 4.838709677419355e-06, "epoch": 0.14563106796116504, "percentage": 4.85, "elapsed_time": "0:13:07", "remaining_time": "4:17:13"}
+{"current_steps": 16, "total_steps": 309, "loss": 1.0683, "lr": 5.161290322580646e-06, "epoch": 0.1553398058252427, "percentage": 5.18, "elapsed_time": "0:13:52", "remaining_time": "4:14:08"}
+{"current_steps": 17, "total_steps": 309, "loss": 1.0367, "lr": 5.483870967741935e-06, "epoch": 0.1650485436893204, "percentage": 5.5, "elapsed_time": "0:14:41", "remaining_time": "4:12:25"}
+{"current_steps": 18, "total_steps": 309, "loss": 1.0401, "lr": 5.806451612903226e-06, "epoch": 0.17475728155339806, "percentage": 5.83, "elapsed_time": "0:15:29", "remaining_time": "4:10:29"}
+{"current_steps": 19, "total_steps": 309, "loss": 1.0364, "lr": 6.129032258064517e-06, "epoch": 0.18446601941747573, "percentage": 6.15, "elapsed_time": "0:16:17", "remaining_time": "4:08:34"}
+{"current_steps": 20, "total_steps": 309, "loss": 0.9807, "lr": 6.451612903225806e-06, "epoch": 0.1941747572815534, "percentage": 6.47, "elapsed_time": "0:17:05", "remaining_time": "4:07:01"}
+{"current_steps": 21, "total_steps": 309, "loss": 1.0094, "lr": 6.774193548387097e-06, "epoch": 0.20388349514563106, "percentage": 6.8, "elapsed_time": "0:17:53", "remaining_time": "4:05:17"}
+{"current_steps": 22, "total_steps": 309, "loss": 0.9756, "lr": 7.096774193548388e-06, "epoch": 0.21359223300970873, "percentage": 7.12, "elapsed_time": "0:18:33", "remaining_time": "4:02:04"}
+{"current_steps": 23, "total_steps": 309, "loss": 1.0005, "lr": 7.4193548387096784e-06, "epoch": 0.22330097087378642, "percentage": 7.44, "elapsed_time": "0:19:25", "remaining_time": "4:01:28"}
+{"current_steps": 24, "total_steps": 309, "loss": 0.9875, "lr": 7.741935483870968e-06, "epoch": 0.23300970873786409, "percentage": 7.77, "elapsed_time": "0:20:07", "remaining_time": "3:58:57"}
+{"current_steps": 25, "total_steps": 309, "loss": 0.9444, "lr": 8.064516129032258e-06, "epoch": 0.24271844660194175, "percentage": 8.09, "elapsed_time": "0:20:56", "remaining_time": "3:57:56"}
+{"current_steps": 26, "total_steps": 309, "loss": 0.9467, "lr": 8.387096774193549e-06, "epoch": 0.2524271844660194, "percentage": 8.41, "elapsed_time": "0:21:42", "remaining_time": "3:56:19"}
+{"current_steps": 27, "total_steps": 309, "loss": 0.9549, "lr": 8.70967741935484e-06, "epoch": 0.2621359223300971, "percentage": 8.74, "elapsed_time": "0:22:35", "remaining_time": "3:55:53"}
+{"current_steps": 28, "total_steps": 309, "loss": 0.9433, "lr": 9.03225806451613e-06, "epoch": 0.27184466019417475, "percentage": 9.06, "elapsed_time": "0:23:31", "remaining_time": "3:56:00"}
+{"current_steps": 29, "total_steps": 309, "loss": 0.9353, "lr": 9.35483870967742e-06, "epoch": 0.2815533980582524, "percentage": 9.39, "elapsed_time": "0:24:24", "remaining_time": "3:55:36"}
+{"current_steps": 30, "total_steps": 309, "loss": 0.9254, "lr": 9.67741935483871e-06, "epoch": 0.2912621359223301, "percentage": 9.71, "elapsed_time": "0:25:13", "remaining_time": "3:54:37"}
+{"current_steps": 31, "total_steps": 309, "loss": 0.9231, "lr": 1e-05, "epoch": 0.30097087378640774, "percentage": 10.03, "elapsed_time": "0:26:02", "remaining_time": "3:53:34"}
+{"current_steps": 32, "total_steps": 309, "loss": 0.9367, "lr": 9.999680739242022e-06, "epoch": 0.3106796116504854, "percentage": 10.36, "elapsed_time": "0:26:48", "remaining_time": "3:52:06"}
+{"current_steps": 33, "total_steps": 309, "loss": 0.9194, "lr": 9.99872299773906e-06, "epoch": 0.32038834951456313, "percentage": 10.68, "elapsed_time": "0:27:39", "remaining_time": "3:51:15"}
+{"current_steps": 34, "total_steps": 309, "loss": 0.8978, "lr": 9.997126897798826e-06, "epoch": 0.3300970873786408, "percentage": 11.0, "elapsed_time": "0:28:32", "remaining_time": "3:50:48"}
+{"current_steps": 35, "total_steps": 309, "loss": 0.9046, "lr": 9.994892643250147e-06, "epoch": 0.33980582524271846, "percentage": 11.33, "elapsed_time": "0:29:29", "remaining_time": "3:50:56"}
+{"current_steps": 36, "total_steps": 309, "loss": 0.9191, "lr": 9.99202051941695e-06, "epoch": 0.34951456310679613, "percentage": 11.65, "elapsed_time": "0:30:10", "remaining_time": "3:48:47"}
+{"current_steps": 37, "total_steps": 309, "loss": 0.8796, "lr": 9.9885108930818e-06, "epoch": 0.3592233009708738, "percentage": 11.97, "elapsed_time": "0:30:55", "remaining_time": "3:47:17"}
+{"current_steps": 38, "total_steps": 309, "loss": 0.9132, "lr": 9.984364212439089e-06, "epoch": 0.36893203883495146, "percentage": 12.3, "elapsed_time": "0:31:36", "remaining_time": "3:45:27"}
+{"current_steps": 39, "total_steps": 309, "loss": 0.8933, "lr": 9.979581007037776e-06, "epoch": 0.3786407766990291, "percentage": 12.62, "elapsed_time": "0:32:20", "remaining_time": "3:43:56"}
+{"current_steps": 40, "total_steps": 309, "loss": 0.9021, "lr": 9.974161887713775e-06, "epoch": 0.3883495145631068, "percentage": 12.94, "elapsed_time": "0:33:04", "remaining_time": "3:42:27"}
+{"current_steps": 41, "total_steps": 309, "loss": 0.9121, "lr": 9.968107546511942e-06, "epoch": 0.39805825242718446, "percentage": 13.27, "elapsed_time": "0:33:56", "remaining_time": "3:41:50"}
+{"current_steps": 42, "total_steps": 309, "loss": 0.9045, "lr": 9.961418756597703e-06, "epoch": 0.4077669902912621, "percentage": 13.59, "elapsed_time": "0:34:42", "remaining_time": "3:40:36"}
+{"current_steps": 43, "total_steps": 309, "loss": 0.9019, "lr": 9.95409637215831e-06, "epoch": 0.4174757281553398, "percentage": 13.92, "elapsed_time": "0:35:32", "remaining_time": "3:39:53"}
+{"current_steps": 44, "total_steps": 309, "loss": 0.8502, "lr": 9.94614132829377e-06, "epoch": 0.42718446601941745, "percentage": 14.24, "elapsed_time": "0:36:15", "remaining_time": "3:38:22"}
+{"current_steps": 45, "total_steps": 309, "loss": 0.9056, "lr": 9.937554640897414e-06, "epoch": 0.4368932038834951, "percentage": 14.56, "elapsed_time": "0:37:04", "remaining_time": "3:37:31"}
+{"current_steps": 46, "total_steps": 309, "loss": 0.8951, "lr": 9.928337406526172e-06, "epoch": 0.44660194174757284, "percentage": 14.89, "elapsed_time": "0:37:55", "remaining_time": "3:36:50"}
+{"current_steps": 47, "total_steps": 309, "loss": 0.919, "lr": 9.918490802260538e-06, "epoch": 0.4563106796116505, "percentage": 15.21, "elapsed_time": "0:38:41", "remaining_time": "3:35:39"}
+{"current_steps": 48, "total_steps": 309, "loss": 0.9086, "lr": 9.90801608555425e-06, "epoch": 0.46601941747572817, "percentage": 15.53, "elapsed_time": "0:39:36", "remaining_time": "3:35:20"}
+{"current_steps": 49, "total_steps": 309, "loss": 0.8707, "lr": 9.896914594073703e-06, "epoch": 0.47572815533980584, "percentage": 15.86, "elapsed_time": "0:40:20", "remaining_time": "3:34:03"}
+{"current_steps": 50, "total_steps": 309, "loss": 0.8903, "lr": 9.885187745527132e-06, "epoch": 0.4854368932038835, "percentage": 16.18, "elapsed_time": "0:41:07", "remaining_time": "3:33:01"}
+{"current_steps": 51, "total_steps": 309, "loss": 0.8803, "lr": 9.87283703748356e-06, "epoch": 0.49514563106796117, "percentage": 16.5, "elapsed_time": "0:41:54", "remaining_time": "3:31:59"}
+{"current_steps": 52, "total_steps": 309, "loss": 0.9034, "lr": 9.859864047181551e-06, "epoch": 0.5048543689320388, "percentage": 16.83, "elapsed_time": "0:42:40", "remaining_time": "3:30:54"}
+{"current_steps": 53, "total_steps": 309, "loss": 0.8962, "lr": 9.846270431327793e-06, "epoch": 0.5145631067961165, "percentage": 17.15, "elapsed_time": "0:43:30", "remaining_time": "3:30:10"}
+{"current_steps": 54, "total_steps": 309, "loss": 0.8834, "lr": 9.832057925885526e-06, "epoch": 0.5242718446601942, "percentage": 17.48, "elapsed_time": "0:44:17", "remaining_time": "3:29:09"}
+{"current_steps": 55, "total_steps": 309, "loss": 0.9023, "lr": 9.817228345852853e-06, "epoch": 0.5339805825242718, "percentage": 17.8, "elapsed_time": "0:45:07", "remaining_time": "3:28:25"}
+{"current_steps": 56, "total_steps": 309, "loss": 0.9119, "lr": 9.801783585030959e-06, "epoch": 0.5436893203883495, "percentage": 18.12, "elapsed_time": "0:46:01", "remaining_time": "3:27:56"}
+{"current_steps": 57, "total_steps": 309, "loss": 0.8605, "lr": 9.785725615782262e-06, "epoch": 0.5533980582524272, "percentage": 18.45, "elapsed_time": "0:46:39", "remaining_time": "3:26:18"}
+{"current_steps": 58, "total_steps": 309, "loss": 0.87, "lr": 9.769056488778538e-06, "epoch": 0.5631067961165048, "percentage": 18.77, "elapsed_time": "0:47:25", "remaining_time": "3:25:13"}
+{"current_steps": 59, "total_steps": 309, "loss": 0.8863, "lr": 9.751778332739033e-06, "epoch": 0.5728155339805825, "percentage": 19.09, "elapsed_time": "0:48:10", "remaining_time": "3:24:06"}
+{"current_steps": 60, "total_steps": 309, "loss": 0.8757, "lr": 9.733893354158628e-06, "epoch": 0.5825242718446602, "percentage": 19.42, "elapsed_time": "0:48:56", "remaining_time": "3:23:07"}
+{"current_steps": 61, "total_steps": 309, "loss": 0.8613, "lr": 9.715403837026046e-06, "epoch": 0.5922330097087378, "percentage": 19.74, "elapsed_time": "0:49:37", "remaining_time": "3:21:43"}
+{"current_steps": 62, "total_steps": 309, "loss": 0.8831, "lr": 9.69631214253219e-06, "epoch": 0.6019417475728155, "percentage": 20.06, "elapsed_time": "0:50:30", "remaining_time": "3:21:13"}
+{"current_steps": 63, "total_steps": 309, "loss": 0.8823, "lr": 9.676620708768608e-06, "epoch": 0.6116504854368932, "percentage": 20.39, "elapsed_time": "0:51:18", "remaining_time": "3:20:20"}
+{"current_steps": 64, "total_steps": 309, "loss": 0.8351, "lr": 9.656332050416118e-06, "epoch": 0.6213592233009708, "percentage": 20.71, "elapsed_time": "0:52:05", "remaining_time": "3:19:23"}
+{"current_steps": 65, "total_steps": 309, "loss": 0.8792, "lr": 9.635448758423703e-06, "epoch": 0.6310679611650486, "percentage": 21.04, "elapsed_time": "0:52:50", "remaining_time": "3:18:21"}
+{"current_steps": 66, "total_steps": 309, "loss": 0.912, "lr": 9.613973499677613e-06, "epoch": 0.6407766990291263, "percentage": 21.36, "elapsed_time": "0:53:43", "remaining_time": "3:17:49"}
+{"current_steps": 67, "total_steps": 309, "loss": 0.8788, "lr": 9.591909016660806e-06, "epoch": 0.6504854368932039, "percentage": 21.68, "elapsed_time": "0:54:28", "remaining_time": "3:16:45"}
+{"current_steps": 68, "total_steps": 309, "loss": 0.8965, "lr": 9.569258127102708e-06, "epoch": 0.6601941747572816, "percentage": 22.01, "elapsed_time": "0:55:18", "remaining_time": "3:16:02"}
+{"current_steps": 69, "total_steps": 309, "loss": 0.8917, "lr": 9.546023723619387e-06, "epoch": 0.6699029126213593, "percentage": 22.33, "elapsed_time": "0:56:07", "remaining_time": "3:15:14"}
+{"current_steps": 70, "total_steps": 309, "loss": 0.8872, "lr": 9.522208773344147e-06, "epoch": 0.6796116504854369, "percentage": 22.65, "elapsed_time": "0:56:51", "remaining_time": "3:14:07"}
+{"current_steps": 71, "total_steps": 309, "loss": 0.8793, "lr": 9.497816317548625e-06, "epoch": 0.6893203883495146, "percentage": 22.98, "elapsed_time": "0:57:40", "remaining_time": "3:13:21"}
+{"current_steps": 72, "total_steps": 309, "loss": 0.8539, "lr": 9.472849471254386e-06, "epoch": 0.6990291262135923, "percentage": 23.3, "elapsed_time": "0:58:28", "remaining_time": "3:12:29"}
+{"current_steps": 73, "total_steps": 309, "loss": 0.8669, "lr": 9.447311422835141e-06, "epoch": 0.7087378640776699, "percentage": 23.62, "elapsed_time": "0:59:05", "remaining_time": "3:11:03"}
+{"current_steps": 74, "total_steps": 309, "loss": 0.8991, "lr": 9.421205433609568e-06, "epoch": 0.7184466019417476, "percentage": 23.95, "elapsed_time": "0:59:55", "remaining_time": "3:10:18"}
+{"current_steps": 75, "total_steps": 309, "loss": 0.8704, "lr": 9.39453483742483e-06, "epoch": 0.7281553398058253, "percentage": 24.27, "elapsed_time": "1:00:43", "remaining_time": "3:09:26"}
+{"current_steps": 76, "total_steps": 309, "loss": 0.8866, "lr": 9.367303040230828e-06, "epoch": 0.7378640776699029, "percentage": 24.6, "elapsed_time": "1:01:29", "remaining_time": "3:08:32"}
+{"current_steps": 77, "total_steps": 309, "loss": 0.8671, "lr": 9.33951351964525e-06, "epoch": 0.7475728155339806, "percentage": 24.92, "elapsed_time": "1:02:16", "remaining_time": "3:07:38"}
+{"current_steps": 78, "total_steps": 309, "loss": 0.8435, "lr": 9.311169824509454e-06, "epoch": 0.7572815533980582, "percentage": 25.24, "elapsed_time": "1:03:05", "remaining_time": "3:06:52"}
+{"current_steps": 79, "total_steps": 309, "loss": 0.8518, "lr": 9.28227557443528e-06, "epoch": 0.7669902912621359, "percentage": 25.57, "elapsed_time": "1:03:52", "remaining_time": "3:05:59"}
+{"current_steps": 80, "total_steps": 309, "loss": 0.9034, "lr": 9.252834459342801e-06, "epoch": 0.7766990291262136, "percentage": 25.89, "elapsed_time": "1:04:39", "remaining_time": "3:05:05"}
+{"current_steps": 81, "total_steps": 309, "loss": 0.8638, "lr": 9.222850238989104e-06, "epoch": 0.7864077669902912, "percentage": 26.21, "elapsed_time": "1:05:29", "remaining_time": "3:04:20"}
+{"current_steps": 82, "total_steps": 309, "loss": 0.8658, "lr": 9.192326742488153e-06, "epoch": 0.7961165048543689, "percentage": 26.54, "elapsed_time": "1:06:16", "remaining_time": "3:03:28"}
+{"current_steps": 83, "total_steps": 309, "loss": 0.8769, "lr": 9.161267867821802e-06, "epoch": 0.8058252427184466, "percentage": 26.86, "elapsed_time": "1:07:01", "remaining_time": "3:02:31"}
+{"current_steps": 84, "total_steps": 309, "loss": 0.8677, "lr": 9.129677581342e-06, "epoch": 0.8155339805825242, "percentage": 27.18, "elapsed_time": "1:07:43", "remaining_time": "3:01:25"}
+{"current_steps": 85, "total_steps": 309, "loss": 0.8465, "lr": 9.097559917264268e-06, "epoch": 0.8252427184466019, "percentage": 27.51, "elapsed_time": "1:08:31", "remaining_time": "3:00:35"}
+{"current_steps": 86, "total_steps": 309, "loss": 0.8741, "lr": 9.064918977152517e-06, "epoch": 0.8349514563106796, "percentage": 27.83, "elapsed_time": "1:09:11", "remaining_time": "2:59:24"}
+{"current_steps": 87, "total_steps": 309, "loss": 0.8248, "lr": 9.031758929395259e-06, "epoch": 0.8446601941747572, "percentage": 28.16, "elapsed_time": "1:09:50", "remaining_time": "2:58:12"}
+{"current_steps": 88, "total_steps": 309, "loss": 0.8398, "lr": 8.998084008673284e-06, "epoch": 0.8543689320388349, "percentage": 28.48, "elapsed_time": "1:10:38", "remaining_time": "2:57:24"}
+{"current_steps": 89, "total_steps": 309, "loss": 0.8687, "lr": 8.963898515418885e-06, "epoch": 0.8640776699029126, "percentage": 28.8, "elapsed_time": "1:11:23", "remaining_time": "2:56:27"}
+{"current_steps": 90, "total_steps": 309, "loss": 0.8639, "lr": 8.929206815266653e-06, "epoch": 0.8737864077669902, "percentage": 29.13, "elapsed_time": "1:12:16", "remaining_time": "2:55:51"}
+{"current_steps": 91, "total_steps": 309, "loss": 0.8483, "lr": 8.89401333849598e-06, "epoch": 0.883495145631068, "percentage": 29.45, "elapsed_time": "1:13:00", "remaining_time": "2:54:54"}
+{"current_steps": 92, "total_steps": 309, "loss": 0.9039, "lr": 8.8583225794653e-06, "epoch": 0.8932038834951457, "percentage": 29.77, "elapsed_time": "1:13:40", "remaining_time": "2:53:47"}
+{"current_steps": 93, "total_steps": 309, "loss": 0.8814, "lr": 8.82213909603812e-06, "epoch": 0.9029126213592233, "percentage": 30.1, "elapsed_time": "1:14:29", "remaining_time": "2:53:00"}
+{"current_steps": 94, "total_steps": 309, "loss": 0.8944, "lr": 8.78546750900098e-06, "epoch": 0.912621359223301, "percentage": 30.42, "elapsed_time": "1:15:28", "remaining_time": "2:52:37"}
+{"current_steps": 95, "total_steps": 309, "loss": 0.8819, "lr": 8.748312501473351e-06, "epoch": 0.9223300970873787, "percentage": 30.74, "elapsed_time": "1:16:18", "remaining_time": "2:51:52"}
+{"current_steps": 96, "total_steps": 309, "loss": 0.8582, "lr": 8.710678818309576e-06, "epoch": 0.9320388349514563, "percentage": 31.07, "elapsed_time": "1:17:02", "remaining_time": "2:50:55"}
+{"current_steps": 97, "total_steps": 309, "loss": 0.8361, "lr": 8.672571265492944e-06, "epoch": 0.941747572815534, "percentage": 31.39, "elapsed_time": "1:17:47", "remaining_time": "2:50:01"}
+{"current_steps": 98, "total_steps": 309, "loss": 0.8679, "lr": 8.63399470952193e-06, "epoch": 0.9514563106796117, "percentage": 31.72, "elapsed_time": "1:18:32", "remaining_time": "2:49:05"}
+{"current_steps": 99, "total_steps": 309, "loss": 0.8182, "lr": 8.594954076788736e-06, "epoch": 0.9611650485436893, "percentage": 32.04, "elapsed_time": "1:19:13", "remaining_time": "2:48:02"}
+{"current_steps": 100, "total_steps": 309, "loss": 0.8622, "lr": 8.555454352950161e-06, "epoch": 0.970873786407767, "percentage": 32.36, "elapsed_time": "1:20:01", "remaining_time": "2:47:15"}
+{"current_steps": 101, "total_steps": 309, "loss": 0.845, "lr": 8.515500582290914e-06, "epoch": 0.9805825242718447, "percentage": 32.69, "elapsed_time": "1:20:42", "remaining_time": "2:46:13"}
+{"current_steps": 102, "total_steps": 309, "loss": 0.8672, "lr": 8.475097867079437e-06, "epoch": 0.9902912621359223, "percentage": 33.01, "elapsed_time": "1:21:36", "remaining_time": "2:45:37"}
+{"current_steps": 103, "total_steps": 309, "loss": 0.8989, "lr": 8.434251366916323e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:22:25", "remaining_time": "2:44:50"}
+{"current_steps": 104, "total_steps": 309, "loss": 0.8642, "lr": 8.392966298075413e-06, "epoch": 1.0097087378640777, "percentage": 33.66, "elapsed_time": "1:24:22", "remaining_time": "2:46:18"}
+{"current_steps": 105, "total_steps": 309, "loss": 0.8001, "lr": 8.351247932837655e-06, "epoch": 1.0194174757281553, "percentage": 33.98, "elapsed_time": "1:25:11", "remaining_time": "2:45:30"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5e8d835a90bedbbbb289c9b753e8a556f16c495e7319737684d39c68e39e8d
+size 7416