Training in progress, step 100

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48688135165ccf9ff41b0036b31ad15fd815b8a4c88be7be622c428ce3006cb0
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f1329c29f6cee4a60a570625fc60c8423a8b2f1db90edf20308a9465fc0f28
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70598421cae1b922cbf525cd3bd2e1cbc7414b9d282d1a0bb58b46ffc6ab2fdd
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11c04c9adb809922629810da1114ee3d2baaf54215224762635a6c540319556
+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 +1,107 @@
+{"current_steps": 1, "total_steps": 696, "loss": 0.7934, "lr": 1.4285714285714287e-07, "epoch": 0.00430416068866571, "percentage": 0.14, "elapsed_time": "0:00:27", "remaining_time": "5:23:13"}
+{"current_steps": 2, "total_steps": 696, "loss": 0.8156, "lr": 2.8571428571428575e-07, "epoch": 0.00860832137733142, "percentage": 0.29, "elapsed_time": "0:00:48", "remaining_time": "4:40:12"}
+{"current_steps": 3, "total_steps": 696, "loss": 0.8216, "lr": 4.285714285714286e-07, "epoch": 0.01291248206599713, "percentage": 0.43, "elapsed_time": "0:01:12", "remaining_time": "4:37:14"}
+{"current_steps": 4, "total_steps": 696, "loss": 0.8243, "lr": 5.714285714285715e-07, "epoch": 0.01721664275466284, "percentage": 0.57, "elapsed_time": "0:01:36", "remaining_time": "4:37:14"}
+{"current_steps": 5, "total_steps": 696, "loss": 0.8402, "lr": 7.142857142857143e-07, "epoch": 0.021520803443328552, "percentage": 0.72, "elapsed_time": "0:01:56", "remaining_time": "4:28:53"}
+{"current_steps": 6, "total_steps": 696, "loss": 0.7946, "lr": 8.571428571428572e-07, "epoch": 0.02582496413199426, "percentage": 0.86, "elapsed_time": "0:02:18", "remaining_time": "4:25:16"}
+{"current_steps": 7, "total_steps": 696, "loss": 0.8204, "lr": 1.0000000000000002e-06, "epoch": 0.03012912482065997, "percentage": 1.01, "elapsed_time": "0:02:40", "remaining_time": "4:22:33"}
+{"current_steps": 8, "total_steps": 696, "loss": 0.8125, "lr": 1.142857142857143e-06, "epoch": 0.03443328550932568, "percentage": 1.15, "elapsed_time": "0:03:03", "remaining_time": "4:23:36"}
+{"current_steps": 9, "total_steps": 696, "loss": 0.7809, "lr": 1.2857142857142856e-06, "epoch": 0.03873744619799139, "percentage": 1.29, "elapsed_time": "0:03:24", "remaining_time": "4:19:58"}
+{"current_steps": 10, "total_steps": 696, "loss": 0.7808, "lr": 1.4285714285714286e-06, "epoch": 0.043041606886657105, "percentage": 1.44, "elapsed_time": "0:03:46", "remaining_time": "4:18:25"}
+{"current_steps": 11, "total_steps": 696, "loss": 0.7559, "lr": 1.5714285714285714e-06, "epoch": 0.047345767575322814, "percentage": 1.58, "elapsed_time": "0:04:05", "remaining_time": "4:14:52"}
+{"current_steps": 12, "total_steps": 696, "loss": 0.734, "lr": 1.7142857142857145e-06, "epoch": 0.05164992826398852, "percentage": 1.72, "elapsed_time": "0:04:24", "remaining_time": "4:11:38"}
+{"current_steps": 13, "total_steps": 696, "loss": 0.7309, "lr": 1.8571428571428573e-06, "epoch": 0.05595408895265423, "percentage": 1.87, "elapsed_time": "0:04:47", "remaining_time": "4:11:35"}
+{"current_steps": 14, "total_steps": 696, "loss": 0.7365, "lr": 2.0000000000000003e-06, "epoch": 0.06025824964131994, "percentage": 2.01, "elapsed_time": "0:05:08", "remaining_time": "4:10:10"}
+{"current_steps": 15, "total_steps": 696, "loss": 0.7036, "lr": 2.1428571428571427e-06, "epoch": 0.06456241032998565, "percentage": 2.16, "elapsed_time": "0:05:27", "remaining_time": "4:08:03"}
+{"current_steps": 16, "total_steps": 696, "loss": 0.7078, "lr": 2.285714285714286e-06, "epoch": 0.06886657101865136, "percentage": 2.3, "elapsed_time": "0:05:50", "remaining_time": "4:08:35"}
+{"current_steps": 17, "total_steps": 696, "loss": 0.695, "lr": 2.428571428571429e-06, "epoch": 0.07317073170731707, "percentage": 2.44, "elapsed_time": "0:06:09", "remaining_time": "4:06:15"}
+{"current_steps": 18, "total_steps": 696, "loss": 0.69, "lr": 2.571428571428571e-06, "epoch": 0.07747489239598278, "percentage": 2.59, "elapsed_time": "0:06:29", "remaining_time": "4:04:31"}
+{"current_steps": 19, "total_steps": 696, "loss": 0.6966, "lr": 2.7142857142857144e-06, "epoch": 0.08177905308464849, "percentage": 2.73, "elapsed_time": "0:06:50", "remaining_time": "4:03:52"}
+{"current_steps": 20, "total_steps": 696, "loss": 0.6711, "lr": 2.8571428571428573e-06, "epoch": 0.08608321377331421, "percentage": 2.87, "elapsed_time": "0:07:13", "remaining_time": "4:04:24"}
+{"current_steps": 21, "total_steps": 696, "loss": 0.7096, "lr": 3e-06, "epoch": 0.09038737446197992, "percentage": 3.02, "elapsed_time": "0:07:35", "remaining_time": "4:04:08"}
+{"current_steps": 22, "total_steps": 696, "loss": 0.6677, "lr": 3.142857142857143e-06, "epoch": 0.09469153515064563, "percentage": 3.16, "elapsed_time": "0:07:56", "remaining_time": "4:03:08"}
+{"current_steps": 23, "total_steps": 696, "loss": 0.7003, "lr": 3.285714285714286e-06, "epoch": 0.09899569583931134, "percentage": 3.3, "elapsed_time": "0:08:16", "remaining_time": "4:02:22"}
+{"current_steps": 24, "total_steps": 696, "loss": 0.6554, "lr": 3.428571428571429e-06, "epoch": 0.10329985652797705, "percentage": 3.45, "elapsed_time": "0:08:40", "remaining_time": "4:02:46"}
+{"current_steps": 25, "total_steps": 696, "loss": 0.6168, "lr": 3.5714285714285718e-06, "epoch": 0.10760401721664276, "percentage": 3.59, "elapsed_time": "0:09:01", "remaining_time": "4:02:20"}
+{"current_steps": 26, "total_steps": 696, "loss": 0.6308, "lr": 3.7142857142857146e-06, "epoch": 0.11190817790530846, "percentage": 3.74, "elapsed_time": "0:09:22", "remaining_time": "4:01:34"}
+{"current_steps": 27, "total_steps": 696, "loss": 0.6174, "lr": 3.857142857142858e-06, "epoch": 0.11621233859397417, "percentage": 3.88, "elapsed_time": "0:09:43", "remaining_time": "4:01:06"}
+{"current_steps": 28, "total_steps": 696, "loss": 0.6314, "lr": 4.000000000000001e-06, "epoch": 0.12051649928263988, "percentage": 4.02, "elapsed_time": "0:10:04", "remaining_time": "4:00:23"}
+{"current_steps": 29, "total_steps": 696, "loss": 0.5832, "lr": 4.1428571428571435e-06, "epoch": 0.12482065997130559, "percentage": 4.17, "elapsed_time": "0:10:25", "remaining_time": "3:59:35"}
+{"current_steps": 30, "total_steps": 696, "loss": 0.6304, "lr": 4.2857142857142855e-06, "epoch": 0.1291248206599713, "percentage": 4.31, "elapsed_time": "0:10:45", "remaining_time": "3:58:41"}
+{"current_steps": 31, "total_steps": 696, "loss": 0.6215, "lr": 4.428571428571429e-06, "epoch": 0.133428981348637, "percentage": 4.45, "elapsed_time": "0:11:05", "remaining_time": "3:57:48"}
+{"current_steps": 32, "total_steps": 696, "loss": 0.5946, "lr": 4.571428571428572e-06, "epoch": 0.13773314203730272, "percentage": 4.6, "elapsed_time": "0:11:24", "remaining_time": "3:56:48"}
+{"current_steps": 33, "total_steps": 696, "loss": 0.5832, "lr": 4.714285714285715e-06, "epoch": 0.14203730272596843, "percentage": 4.74, "elapsed_time": "0:11:45", "remaining_time": "3:56:19"}
+{"current_steps": 34, "total_steps": 696, "loss": 0.5804, "lr": 4.857142857142858e-06, "epoch": 0.14634146341463414, "percentage": 4.89, "elapsed_time": "0:12:08", "remaining_time": "3:56:16"}
+{"current_steps": 35, "total_steps": 696, "loss": 0.5901, "lr": 5e-06, "epoch": 0.15064562410329985, "percentage": 5.03, "elapsed_time": "0:12:28", "remaining_time": "3:55:38"}
+{"current_steps": 36, "total_steps": 696, "loss": 0.6189, "lr": 5.142857142857142e-06, "epoch": 0.15494978479196556, "percentage": 5.17, "elapsed_time": "0:12:48", "remaining_time": "3:54:51"}
+{"current_steps": 37, "total_steps": 696, "loss": 0.5708, "lr": 5.285714285714286e-06, "epoch": 0.15925394548063126, "percentage": 5.32, "elapsed_time": "0:13:10", "remaining_time": "3:54:31"}
+{"current_steps": 38, "total_steps": 696, "loss": 0.5692, "lr": 5.428571428571429e-06, "epoch": 0.16355810616929697, "percentage": 5.46, "elapsed_time": "0:13:31", "remaining_time": "3:54:13"}
+{"current_steps": 39, "total_steps": 696, "loss": 0.5631, "lr": 5.571428571428572e-06, "epoch": 0.1678622668579627, "percentage": 5.6, "elapsed_time": "0:13:52", "remaining_time": "3:53:37"}
+{"current_steps": 40, "total_steps": 696, "loss": 0.5581, "lr": 5.7142857142857145e-06, "epoch": 0.17216642754662842, "percentage": 5.75, "elapsed_time": "0:14:12", "remaining_time": "3:52:59"}
+{"current_steps": 41, "total_steps": 696, "loss": 0.5764, "lr": 5.857142857142858e-06, "epoch": 0.17647058823529413, "percentage": 5.89, "elapsed_time": "0:14:32", "remaining_time": "3:52:17"}
+{"current_steps": 42, "total_steps": 696, "loss": 0.5248, "lr": 6e-06, "epoch": 0.18077474892395984, "percentage": 6.03, "elapsed_time": "0:14:53", "remaining_time": "3:51:48"}
+{"current_steps": 43, "total_steps": 696, "loss": 0.5609, "lr": 6.142857142857144e-06, "epoch": 0.18507890961262555, "percentage": 6.18, "elapsed_time": "0:15:13", "remaining_time": "3:51:14"}
+{"current_steps": 44, "total_steps": 696, "loss": 0.5283, "lr": 6.285714285714286e-06, "epoch": 0.18938307030129126, "percentage": 6.32, "elapsed_time": "0:15:34", "remaining_time": "3:50:42"}
+{"current_steps": 45, "total_steps": 696, "loss": 0.5505, "lr": 6.4285714285714295e-06, "epoch": 0.19368723098995697, "percentage": 6.47, "elapsed_time": "0:15:53", "remaining_time": "3:49:59"}
+{"current_steps": 46, "total_steps": 696, "loss": 0.5599, "lr": 6.571428571428572e-06, "epoch": 0.19799139167862267, "percentage": 6.61, "elapsed_time": "0:16:13", "remaining_time": "3:49:22"}
+{"current_steps": 47, "total_steps": 696, "loss": 0.5741, "lr": 6.714285714285714e-06, "epoch": 0.20229555236728838, "percentage": 6.75, "elapsed_time": "0:16:34", "remaining_time": "3:48:58"}
+{"current_steps": 48, "total_steps": 696, "loss": 0.5149, "lr": 6.857142857142858e-06, "epoch": 0.2065997130559541, "percentage": 6.9, "elapsed_time": "0:16:55", "remaining_time": "3:48:35"}
+{"current_steps": 49, "total_steps": 696, "loss": 0.5407, "lr": 7e-06, "epoch": 0.2109038737446198, "percentage": 7.04, "elapsed_time": "0:17:17", "remaining_time": "3:48:14"}
+{"current_steps": 50, "total_steps": 696, "loss": 0.5325, "lr": 7.1428571428571436e-06, "epoch": 0.2152080344332855, "percentage": 7.18, "elapsed_time": "0:17:40", "remaining_time": "3:48:22"}
+{"current_steps": 51, "total_steps": 696, "loss": 0.5325, "lr": 7.285714285714286e-06, "epoch": 0.21951219512195122, "percentage": 7.33, "elapsed_time": "0:18:01", "remaining_time": "3:47:51"}
+{"current_steps": 52, "total_steps": 696, "loss": 0.5468, "lr": 7.428571428571429e-06, "epoch": 0.22381635581061693, "percentage": 7.47, "elapsed_time": "0:18:22", "remaining_time": "3:47:39"}
+{"current_steps": 53, "total_steps": 696, "loss": 0.5144, "lr": 7.571428571428572e-06, "epoch": 0.22812051649928264, "percentage": 7.61, "elapsed_time": "0:18:43", "remaining_time": "3:47:05"}
+{"current_steps": 54, "total_steps": 696, "loss": 0.5478, "lr": 7.714285714285716e-06, "epoch": 0.23242467718794835, "percentage": 7.76, "elapsed_time": "0:19:05", "remaining_time": "3:47:02"}
+{"current_steps": 55, "total_steps": 696, "loss": 0.5162, "lr": 7.857142857142858e-06, "epoch": 0.23672883787661406, "percentage": 7.9, "elapsed_time": "0:19:26", "remaining_time": "3:46:39"}
+{"current_steps": 56, "total_steps": 696, "loss": 0.4896, "lr": 8.000000000000001e-06, "epoch": 0.24103299856527977, "percentage": 8.05, "elapsed_time": "0:19:44", "remaining_time": "3:45:39"}
+{"current_steps": 57, "total_steps": 696, "loss": 0.5184, "lr": 8.142857142857143e-06, "epoch": 0.24533715925394547, "percentage": 8.19, "elapsed_time": "0:20:06", "remaining_time": "3:45:19"}
+{"current_steps": 58, "total_steps": 696, "loss": 0.5381, "lr": 8.285714285714287e-06, "epoch": 0.24964131994261118, "percentage": 8.33, "elapsed_time": "0:20:25", "remaining_time": "3:44:43"}
+{"current_steps": 59, "total_steps": 696, "loss": 0.5344, "lr": 8.428571428571429e-06, "epoch": 0.2539454806312769, "percentage": 8.48, "elapsed_time": "0:20:49", "remaining_time": "3:44:46"}
+{"current_steps": 60, "total_steps": 696, "loss": 0.5177, "lr": 8.571428571428571e-06, "epoch": 0.2582496413199426, "percentage": 8.62, "elapsed_time": "0:21:09", "remaining_time": "3:44:14"}
+{"current_steps": 61, "total_steps": 696, "loss": 0.5148, "lr": 8.714285714285715e-06, "epoch": 0.26255380200860834, "percentage": 8.76, "elapsed_time": "0:21:30", "remaining_time": "3:43:58"}
+{"current_steps": 62, "total_steps": 696, "loss": 0.5086, "lr": 8.857142857142858e-06, "epoch": 0.266857962697274, "percentage": 8.91, "elapsed_time": "0:21:54", "remaining_time": "3:44:01"}
+{"current_steps": 63, "total_steps": 696, "loss": 0.5029, "lr": 9e-06, "epoch": 0.27116212338593976, "percentage": 9.05, "elapsed_time": "0:22:14", "remaining_time": "3:43:31"}
+{"current_steps": 64, "total_steps": 696, "loss": 0.5208, "lr": 9.142857142857144e-06, "epoch": 0.27546628407460544, "percentage": 9.2, "elapsed_time": "0:22:34", "remaining_time": "3:42:58"}
+{"current_steps": 65, "total_steps": 696, "loss": 0.5016, "lr": 9.285714285714288e-06, "epoch": 0.2797704447632712, "percentage": 9.34, "elapsed_time": "0:22:56", "remaining_time": "3:42:42"}
+{"current_steps": 66, "total_steps": 696, "loss": 0.4973, "lr": 9.42857142857143e-06, "epoch": 0.28407460545193686, "percentage": 9.48, "elapsed_time": "0:23:18", "remaining_time": "3:42:32"}
+{"current_steps": 67, "total_steps": 696, "loss": 0.5038, "lr": 9.571428571428573e-06, "epoch": 0.2883787661406026, "percentage": 9.63, "elapsed_time": "0:23:39", "remaining_time": "3:42:08"}
+{"current_steps": 68, "total_steps": 696, "loss": 0.5281, "lr": 9.714285714285715e-06, "epoch": 0.2926829268292683, "percentage": 9.77, "elapsed_time": "0:24:01", "remaining_time": "3:41:57"}
+{"current_steps": 69, "total_steps": 696, "loss": 0.5086, "lr": 9.857142857142859e-06, "epoch": 0.296987087517934, "percentage": 9.91, "elapsed_time": "0:24:22", "remaining_time": "3:41:31"}
+{"current_steps": 70, "total_steps": 696, "loss": 0.5203, "lr": 1e-05, "epoch": 0.3012912482065997, "percentage": 10.06, "elapsed_time": "0:24:43", "remaining_time": "3:41:09"}
+{"current_steps": 71, "total_steps": 696, "loss": 0.498, "lr": 9.999937036309402e-06, "epoch": 0.30559540889526543, "percentage": 10.2, "elapsed_time": "0:25:03", "remaining_time": "3:40:35"}
+{"current_steps": 72, "total_steps": 696, "loss": 0.4988, "lr": 9.999748146823376e-06, "epoch": 0.3098995695839311, "percentage": 10.34, "elapsed_time": "0:25:23", "remaining_time": "3:40:02"}
+{"current_steps": 73, "total_steps": 696, "loss": 0.4885, "lr": 9.999433336299195e-06, "epoch": 0.31420373027259685, "percentage": 10.49, "elapsed_time": "0:25:42", "remaining_time": "3:39:23"}
+{"current_steps": 74, "total_steps": 696, "loss": 0.4906, "lr": 9.99899261266551e-06, "epoch": 0.31850789096126253, "percentage": 10.63, "elapsed_time": "0:26:00", "remaining_time": "3:38:39"}
+{"current_steps": 75, "total_steps": 696, "loss": 0.5063, "lr": 9.99842598702216e-06, "epoch": 0.32281205164992827, "percentage": 10.78, "elapsed_time": "0:26:22", "remaining_time": "3:38:23"}
+{"current_steps": 76, "total_steps": 696, "loss": 0.4885, "lr": 9.997733473639876e-06, "epoch": 0.32711621233859395, "percentage": 10.92, "elapsed_time": "0:26:45", "remaining_time": "3:38:16"}
+{"current_steps": 77, "total_steps": 696, "loss": 0.4966, "lr": 9.996915089959942e-06, "epoch": 0.3314203730272597, "percentage": 11.06, "elapsed_time": "0:27:05", "remaining_time": "3:37:43"}
+{"current_steps": 78, "total_steps": 696, "loss": 0.5168, "lr": 9.995970856593739e-06, "epoch": 0.3357245337159254, "percentage": 11.21, "elapsed_time": "0:27:24", "remaining_time": "3:37:05"}
+{"current_steps": 79, "total_steps": 696, "loss": 0.4935, "lr": 9.994900797322233e-06, "epoch": 0.3400286944045911, "percentage": 11.35, "elapsed_time": "0:27:43", "remaining_time": "3:36:33"}
+{"current_steps": 80, "total_steps": 696, "loss": 0.5037, "lr": 9.993704939095376e-06, "epoch": 0.34433285509325684, "percentage": 11.49, "elapsed_time": "0:28:02", "remaining_time": "3:35:58"}
+{"current_steps": 81, "total_steps": 696, "loss": 0.4974, "lr": 9.99238331203143e-06, "epoch": 0.3486370157819225, "percentage": 11.64, "elapsed_time": "0:28:25", "remaining_time": "3:35:47"}
+{"current_steps": 82, "total_steps": 696, "loss": 0.4869, "lr": 9.9909359494162e-06, "epoch": 0.35294117647058826, "percentage": 11.78, "elapsed_time": "0:28:42", "remaining_time": "3:34:57"}
+{"current_steps": 83, "total_steps": 696, "loss": 0.4933, "lr": 9.989362887702203e-06, "epoch": 0.35724533715925394, "percentage": 11.93, "elapsed_time": "0:29:03", "remaining_time": "3:34:39"}
+{"current_steps": 84, "total_steps": 696, "loss": 0.4969, "lr": 9.987664166507749e-06, "epoch": 0.3615494978479197, "percentage": 12.07, "elapsed_time": "0:29:23", "remaining_time": "3:34:11"}
+{"current_steps": 85, "total_steps": 696, "loss": 0.5092, "lr": 9.985839828615937e-06, "epoch": 0.36585365853658536, "percentage": 12.21, "elapsed_time": "0:29:45", "remaining_time": "3:33:51"}
+{"current_steps": 86, "total_steps": 696, "loss": 0.4925, "lr": 9.983889919973586e-06, "epoch": 0.3701578192252511, "percentage": 12.36, "elapsed_time": "0:30:04", "remaining_time": "3:33:19"}
+{"current_steps": 87, "total_steps": 696, "loss": 0.4614, "lr": 9.981814489690077e-06, "epoch": 0.3744619799139168, "percentage": 12.5, "elapsed_time": "0:30:25", "remaining_time": "3:33:00"}
+{"current_steps": 88, "total_steps": 696, "loss": 0.5068, "lr": 9.979613590036108e-06, "epoch": 0.3787661406025825, "percentage": 12.64, "elapsed_time": "0:30:46", "remaining_time": "3:32:38"}
+{"current_steps": 89, "total_steps": 696, "loss": 0.5127, "lr": 9.977287276442385e-06, "epoch": 0.3830703012912482, "percentage": 12.79, "elapsed_time": "0:31:07", "remaining_time": "3:32:14"}
+{"current_steps": 90, "total_steps": 696, "loss": 0.4714, "lr": 9.974835607498224e-06, "epoch": 0.38737446197991393, "percentage": 12.93, "elapsed_time": "0:31:29", "remaining_time": "3:32:00"}
+{"current_steps": 91, "total_steps": 696, "loss": 0.5083, "lr": 9.972258644950074e-06, "epoch": 0.3916786226685796, "percentage": 13.07, "elapsed_time": "0:31:50", "remaining_time": "3:31:40"}
+{"current_steps": 92, "total_steps": 696, "loss": 0.4958, "lr": 9.969556453699966e-06, "epoch": 0.39598278335724535, "percentage": 13.22, "elapsed_time": "0:32:11", "remaining_time": "3:31:18"}
+{"current_steps": 93, "total_steps": 696, "loss": 0.4657, "lr": 9.966729101803872e-06, "epoch": 0.40028694404591103, "percentage": 13.36, "elapsed_time": "0:32:34", "remaining_time": "3:31:12"}
+{"current_steps": 94, "total_steps": 696, "loss": 0.4826, "lr": 9.963776660469996e-06, "epoch": 0.40459110473457677, "percentage": 13.51, "elapsed_time": "0:32:54", "remaining_time": "3:30:46"}
+{"current_steps": 95, "total_steps": 696, "loss": 0.4997, "lr": 9.960699204056978e-06, "epoch": 0.40889526542324245, "percentage": 13.65, "elapsed_time": "0:33:15", "remaining_time": "3:30:23"}
+{"current_steps": 96, "total_steps": 696, "loss": 0.5259, "lr": 9.957496810072027e-06, "epoch": 0.4131994261119082, "percentage": 13.79, "elapsed_time": "0:33:36", "remaining_time": "3:30:01"}
+{"current_steps": 97, "total_steps": 696, "loss": 0.5006, "lr": 9.954169559168958e-06, "epoch": 0.41750358680057387, "percentage": 13.94, "elapsed_time": "0:33:56", "remaining_time": "3:29:33"}
+{"current_steps": 98, "total_steps": 696, "loss": 0.5234, "lr": 9.95071753514617e-06, "epoch": 0.4218077474892396, "percentage": 14.08, "elapsed_time": "0:34:16", "remaining_time": "3:29:11"}
+{"current_steps": 99, "total_steps": 696, "loss": 0.4944, "lr": 9.947140824944533e-06, "epoch": 0.4261119081779053, "percentage": 14.22, "elapsed_time": "0:34:37", "remaining_time": "3:28:47"}
+{"current_steps": 100, "total_steps": 696, "loss": 0.4932, "lr": 9.943439518645193e-06, "epoch": 0.430416068866571, "percentage": 14.37, "elapsed_time": "0:34:57", "remaining_time": "3:28:22"}
+{"current_steps": 101, "total_steps": 696, "loss": 0.4882, "lr": 9.939613709467317e-06, "epoch": 0.4347202295552367, "percentage": 14.51, "elapsed_time": "0:36:04", "remaining_time": "3:32:28"}
+{"current_steps": 102, "total_steps": 696, "loss": 0.4464, "lr": 9.935663493765726e-06, "epoch": 0.43902439024390244, "percentage": 14.66, "elapsed_time": "0:36:22", "remaining_time": "3:31:48"}
+{"current_steps": 103, "total_steps": 696, "loss": 0.4761, "lr": 9.93158897102849e-06, "epoch": 0.4433285509325681, "percentage": 14.8, "elapsed_time": "0:36:41", "remaining_time": "3:31:16"}
+{"current_steps": 104, "total_steps": 696, "loss": 0.48, "lr": 9.9273902438744e-06, "epoch": 0.44763271162123386, "percentage": 14.94, "elapsed_time": "0:37:03", "remaining_time": "3:30:54"}
+{"current_steps": 105, "total_steps": 696, "loss": 0.4836, "lr": 9.923067418050399e-06, "epoch": 0.4519368723098996, "percentage": 15.09, "elapsed_time": "0:37:24", "remaining_time": "3:30:31"}
+{"current_steps": 106, "total_steps": 696, "loss": 0.4873, "lr": 9.918620602428916e-06, "epoch": 0.4562410329985653, "percentage": 15.23, "elapsed_time": "0:37:46", "remaining_time": "3:30:13"}
+{"current_steps": 107, "total_steps": 696, "loss": 0.4939, "lr": 9.91404990900512e-06, "epoch": 0.460545193687231, "percentage": 15.37, "elapsed_time": "0:38:04", "remaining_time": "3:29:38"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ef49094be9122af0fe26f184841a4979db225d7bcdf4bcde62ab016095fe87
+size 7352