Training in progress, epoch 0

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01acc2c089cc91d3624efd27266921d5e34680174af74a0b98f42e61c1f9975b
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c828f29d6c803c48cc5c760fb741e96a213b195bd087d8a848bee0dfb9f9a3ac
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc830850d426b4b335e3f9bd2473b0dcfd99eb70533ff2314be23c724ab03efe
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f404c290c3a6c6447e15d672708c57c894cec14a9c961ae79317007b81e1d28b
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_log.jsonl

@@ -0,0 +1,111 @@
+{"current_steps": 1, "total_steps": 333, "loss": 0.851, "lr": 1.663780588235294e-06, "epoch": 0.008983717012914094, "percentage": 0.3, "elapsed_time": "0:06:05", "remaining_time": "1 day, 9:42:39"}
+{"current_steps": 2, "total_steps": 333, "loss": 0.8589, "lr": 3.327561176470588e-06, "epoch": 0.017967434025828188, "percentage": 0.6, "elapsed_time": "0:12:14", "remaining_time": "1 day, 9:45:15"}
+{"current_steps": 3, "total_steps": 333, "loss": 0.8612, "lr": 4.991341764705883e-06, "epoch": 0.02695115103874228, "percentage": 0.9, "elapsed_time": "0:17:49", "remaining_time": "1 day, 8:41:39"}
+{"current_steps": 4, "total_steps": 333, "loss": 0.8097, "lr": 6.655122352941176e-06, "epoch": 0.035934868051656375, "percentage": 1.2, "elapsed_time": "0:23:40", "remaining_time": "1 day, 8:27:46"}
+{"current_steps": 5, "total_steps": 333, "loss": 0.7672, "lr": 8.318902941176471e-06, "epoch": 0.044918585064570464, "percentage": 1.5, "elapsed_time": "0:29:29", "remaining_time": "1 day, 8:14:19"}
+{"current_steps": 6, "total_steps": 333, "loss": 0.7561, "lr": 9.982683529411766e-06, "epoch": 0.05390230207748456, "percentage": 1.8, "elapsed_time": "0:35:13", "remaining_time": "1 day, 8:00:01"}
+{"current_steps": 7, "total_steps": 333, "loss": 0.76, "lr": 1.1646464117647058e-05, "epoch": 0.06288601909039865, "percentage": 2.1, "elapsed_time": "0:41:24", "remaining_time": "1 day, 8:08:29"}
+{"current_steps": 8, "total_steps": 333, "loss": 0.7142, "lr": 1.3310244705882352e-05, "epoch": 0.07186973610331275, "percentage": 2.4, "elapsed_time": "0:47:08", "remaining_time": "1 day, 7:55:11"}
+{"current_steps": 9, "total_steps": 333, "loss": 0.7167, "lr": 1.4974025294117648e-05, "epoch": 0.08085345311622684, "percentage": 2.7, "elapsed_time": "0:52:59", "remaining_time": "1 day, 7:47:35"}
+{"current_steps": 10, "total_steps": 333, "loss": 0.6916, "lr": 1.6637805882352943e-05, "epoch": 0.08983717012914093, "percentage": 3.0, "elapsed_time": "0:58:40", "remaining_time": "1 day, 7:35:19"}
+{"current_steps": 11, "total_steps": 333, "loss": 0.6619, "lr": 1.8301586470588235e-05, "epoch": 0.09882088714205503, "percentage": 3.3, "elapsed_time": "1:04:34", "remaining_time": "1 day, 7:30:17"}
+{"current_steps": 12, "total_steps": 333, "loss": 0.651, "lr": 1.996536705882353e-05, "epoch": 0.10780460415496912, "percentage": 3.6, "elapsed_time": "1:10:42", "remaining_time": "1 day, 7:31:16"}
+{"current_steps": 13, "total_steps": 333, "loss": 0.6292, "lr": 2.1629147647058824e-05, "epoch": 0.11678832116788321, "percentage": 3.9, "elapsed_time": "1:16:17", "remaining_time": "1 day, 7:17:57"}
+{"current_steps": 14, "total_steps": 333, "loss": 0.624, "lr": 2.3292928235294116e-05, "epoch": 0.1257720381807973, "percentage": 4.2, "elapsed_time": "1:22:00", "remaining_time": "1 day, 7:08:45"}
+{"current_steps": 15, "total_steps": 333, "loss": 0.6177, "lr": 2.4956708823529412e-05, "epoch": 0.13475575519371139, "percentage": 4.5, "elapsed_time": "1:27:51", "remaining_time": "1 day, 7:02:44"}
+{"current_steps": 16, "total_steps": 333, "loss": 0.6094, "lr": 2.6620489411764705e-05, "epoch": 0.1437394722066255, "percentage": 4.8, "elapsed_time": "1:33:45", "remaining_time": "1 day, 6:57:37"}
+{"current_steps": 17, "total_steps": 333, "loss": 0.5913, "lr": 2.828427e-05, "epoch": 0.1527231892195396, "percentage": 5.11, "elapsed_time": "1:39:39", "remaining_time": "1 day, 6:52:30"}
+{"current_steps": 18, "total_steps": 333, "loss": 0.5853, "lr": 2.9948050588235297e-05, "epoch": 0.16170690623245368, "percentage": 5.41, "elapsed_time": "1:45:23", "remaining_time": "1 day, 6:44:15"}
+{"current_steps": 19, "total_steps": 333, "loss": 0.5837, "lr": 3.161183117647059e-05, "epoch": 0.17069062324536777, "percentage": 5.71, "elapsed_time": "1:51:18", "remaining_time": "1 day, 6:39:34"}
+{"current_steps": 20, "total_steps": 333, "loss": 0.5826, "lr": 3.3275611764705885e-05, "epoch": 0.17967434025828186, "percentage": 6.01, "elapsed_time": "1:57:07", "remaining_time": "1 day, 6:33:05"}
+{"current_steps": 21, "total_steps": 333, "loss": 0.5722, "lr": 3.493939235294118e-05, "epoch": 0.18865805727119594, "percentage": 6.31, "elapsed_time": "2:03:11", "remaining_time": "1 day, 6:30:20"}
+{"current_steps": 22, "total_steps": 333, "loss": 0.5673, "lr": 3.660317294117647e-05, "epoch": 0.19764177428411006, "percentage": 6.61, "elapsed_time": "2:09:08", "remaining_time": "1 day, 6:25:30"}
+{"current_steps": 23, "total_steps": 333, "loss": 0.5588, "lr": 3.826695352941177e-05, "epoch": 0.20662549129702415, "percentage": 6.91, "elapsed_time": "2:14:39", "remaining_time": "1 day, 6:14:54"}
+{"current_steps": 24, "total_steps": 333, "loss": 0.5584, "lr": 3.993073411764706e-05, "epoch": 0.21560920830993824, "percentage": 7.21, "elapsed_time": "2:20:34", "remaining_time": "1 day, 6:09:56"}
+{"current_steps": 25, "total_steps": 333, "loss": 0.5569, "lr": 4.1594514705882355e-05, "epoch": 0.22459292532285233, "percentage": 7.51, "elapsed_time": "2:26:11", "remaining_time": "1 day, 6:01:03"}
+{"current_steps": 26, "total_steps": 333, "loss": 0.5553, "lr": 4.325829529411765e-05, "epoch": 0.23357664233576642, "percentage": 7.81, "elapsed_time": "2:31:52", "remaining_time": "1 day, 5:53:12"}
+{"current_steps": 27, "total_steps": 333, "loss": 0.554, "lr": 4.492207588235294e-05, "epoch": 0.2425603593486805, "percentage": 8.11, "elapsed_time": "2:37:20", "remaining_time": "1 day, 5:43:09"}
+{"current_steps": 28, "total_steps": 333, "loss": 0.5421, "lr": 4.658585647058823e-05, "epoch": 0.2515440763615946, "percentage": 8.41, "elapsed_time": "2:42:55", "remaining_time": "1 day, 5:34:40"}
+{"current_steps": 29, "total_steps": 333, "loss": 0.5413, "lr": 4.824963705882353e-05, "epoch": 0.2605277933745087, "percentage": 8.71, "elapsed_time": "2:48:46", "remaining_time": "1 day, 5:29:12"}
+{"current_steps": 30, "total_steps": 333, "loss": 0.5447, "lr": 4.9913417647058825e-05, "epoch": 0.26951151038742277, "percentage": 9.01, "elapsed_time": "2:54:37", "remaining_time": "1 day, 5:23:41"}
+{"current_steps": 31, "total_steps": 333, "loss": 0.5346, "lr": 5.157719823529412e-05, "epoch": 0.2784952274003369, "percentage": 9.31, "elapsed_time": "3:00:11", "remaining_time": "1 day, 5:15:27"}
+{"current_steps": 32, "total_steps": 333, "loss": 0.54, "lr": 5.324097882352941e-05, "epoch": 0.287478944413251, "percentage": 9.61, "elapsed_time": "3:05:53", "remaining_time": "1 day, 5:08:28"}
+{"current_steps": 33, "total_steps": 333, "loss": 0.5272, "lr": 5.490475941176471e-05, "epoch": 0.29646266142616506, "percentage": 9.91, "elapsed_time": "3:11:37", "remaining_time": "1 day, 5:02:03"}
+{"current_steps": 34, "total_steps": 333, "loss": 0.5269, "lr": 5.656854e-05, "epoch": 0.3054463784390792, "percentage": 10.21, "elapsed_time": "3:17:33", "remaining_time": "1 day, 4:57:20"}
+{"current_steps": 35, "total_steps": 333, "loss": 0.5254, "lr": 5.65669787647368e-05, "epoch": 0.31443009545199324, "percentage": 10.51, "elapsed_time": "3:23:21", "remaining_time": "1 day, 4:51:25"}
+{"current_steps": 36, "total_steps": 333, "loss": 0.5325, "lr": 5.6562295231301345e-05, "epoch": 0.32341381246490736, "percentage": 10.81, "elapsed_time": "3:29:12", "remaining_time": "1 day, 4:45:54"}
+{"current_steps": 37, "total_steps": 333, "loss": 0.5247, "lr": 5.655448991673705e-05, "epoch": 0.3323975294778215, "percentage": 11.11, "elapsed_time": "3:35:07", "remaining_time": "1 day, 4:40:59"}
+{"current_steps": 38, "total_steps": 333, "loss": 0.5301, "lr": 5.6543563682719456e-05, "epoch": 0.34138124649073553, "percentage": 11.41, "elapsed_time": "3:40:43", "remaining_time": "1 day, 4:33:28"}
+{"current_steps": 39, "total_steps": 333, "loss": 0.5251, "lr": 5.652951773546123e-05, "epoch": 0.35036496350364965, "percentage": 11.71, "elapsed_time": "3:46:36", "remaining_time": "1 day, 4:28:13"}
+{"current_steps": 40, "total_steps": 333, "loss": 0.529, "lr": 5.651235362557887e-05, "epoch": 0.3593486805165637, "percentage": 12.01, "elapsed_time": "3:52:21", "remaining_time": "1 day, 4:22:04"}
+{"current_steps": 41, "total_steps": 333, "loss": 0.5263, "lr": 5.649207324792161e-05, "epoch": 0.36833239752947783, "percentage": 12.31, "elapsed_time": "3:57:55", "remaining_time": "1 day, 4:14:27"}
+{"current_steps": 42, "total_steps": 333, "loss": 0.5233, "lr": 5.646867884136221e-05, "epoch": 0.3773161145423919, "percentage": 12.61, "elapsed_time": "4:03:49", "remaining_time": "1 day, 4:09:21"}
+{"current_steps": 43, "total_steps": 333, "loss": 0.5121, "lr": 5.644217298854978e-05, "epoch": 0.386299831555306, "percentage": 12.91, "elapsed_time": "4:09:21", "remaining_time": "1 day, 4:01:43"}
+{"current_steps": 44, "total_steps": 333, "loss": 0.5076, "lr": 5.641255861562469e-05, "epoch": 0.3952835485682201, "percentage": 13.21, "elapsed_time": "4:15:20", "remaining_time": "1 day, 3:57:05"}
+{"current_steps": 45, "total_steps": 333, "loss": 0.5178, "lr": 5.637983899189553e-05, "epoch": 0.4042672655811342, "percentage": 13.51, "elapsed_time": "4:21:18", "remaining_time": "1 day, 3:52:22"}
+{"current_steps": 46, "total_steps": 333, "loss": 0.5099, "lr": 5.634401772947817e-05, "epoch": 0.4132509825940483, "percentage": 13.81, "elapsed_time": "4:27:00", "remaining_time": "1 day, 3:45:53"}
+{"current_steps": 47, "total_steps": 333, "loss": 0.5125, "lr": 5.630509878289701e-05, "epoch": 0.42223469960696236, "percentage": 14.11, "elapsed_time": "4:32:52", "remaining_time": "1 day, 3:40:29"}
+{"current_steps": 48, "total_steps": 333, "loss": 0.5035, "lr": 5.626308644864844e-05, "epoch": 0.4312184166198765, "percentage": 14.41, "elapsed_time": "4:38:32", "remaining_time": "1 day, 3:33:47"}
+{"current_steps": 49, "total_steps": 333, "loss": 0.5129, "lr": 5.621798536472649e-05, "epoch": 0.4402021336327906, "percentage": 14.71, "elapsed_time": "4:44:08", "remaining_time": "1 day, 3:26:49"}
+{"current_steps": 50, "total_steps": 333, "loss": 0.4933, "lr": 5.616980051011082e-05, "epoch": 0.44918585064570465, "percentage": 15.02, "elapsed_time": "4:50:03", "remaining_time": "1 day, 3:21:42"}
+{"current_steps": 51, "total_steps": 333, "loss": 0.5114, "lr": 5.611853720421709e-05, "epoch": 0.45816956765861877, "percentage": 15.32, "elapsed_time": "4:55:51", "remaining_time": "1 day, 3:15:54"}
+{"current_steps": 52, "total_steps": 333, "loss": 0.5051, "lr": 5.606420110630966e-05, "epoch": 0.46715328467153283, "percentage": 15.62, "elapsed_time": "5:01:30", "remaining_time": "1 day, 3:09:19"}
+{"current_steps": 53, "total_steps": 333, "loss": 0.4984, "lr": 5.6006798214876905e-05, "epoch": 0.47613700168444695, "percentage": 15.92, "elapsed_time": "5:07:23", "remaining_time": "1 day, 3:03:54"}
+{"current_steps": 54, "total_steps": 333, "loss": 0.5057, "lr": 5.5946334866968935e-05, "epoch": 0.485120718697361, "percentage": 16.22, "elapsed_time": "5:12:59", "remaining_time": "1 day, 2:57:05"}
+{"current_steps": 55, "total_steps": 333, "loss": 0.5067, "lr": 5.5882817737498054e-05, "epoch": 0.4941044357102751, "percentage": 16.52, "elapsed_time": "5:18:42", "remaining_time": "1 day, 2:50:54"}
+{"current_steps": 56, "total_steps": 333, "loss": 0.5016, "lr": 5.581625383850187e-05, "epoch": 0.5030881527231892, "percentage": 16.82, "elapsed_time": "5:24:27", "remaining_time": "1 day, 2:44:54"}
+{"current_steps": 57, "total_steps": 333, "loss": 0.5105, "lr": 5.5746650518369164e-05, "epoch": 0.5120718697361033, "percentage": 17.12, "elapsed_time": "5:30:25", "remaining_time": "1 day, 2:39:58"}
+{"current_steps": 58, "total_steps": 333, "loss": 0.501, "lr": 5.5674015461028693e-05, "epoch": 0.5210555867490174, "percentage": 17.42, "elapsed_time": "5:35:58", "remaining_time": "1 day, 2:32:58"}
+{"current_steps": 59, "total_steps": 333, "loss": 0.5055, "lr": 5.559835668510092e-05, "epoch": 0.5300393037619315, "percentage": 17.72, "elapsed_time": "5:41:45", "remaining_time": "1 day, 2:27:06"}
+{"current_steps": 60, "total_steps": 333, "loss": 0.4997, "lr": 5.5519682543012745e-05, "epoch": 0.5390230207748455, "percentage": 18.02, "elapsed_time": "5:47:09", "remaining_time": "1 day, 2:19:35"}
+{"current_steps": 61, "total_steps": 333, "loss": 0.4999, "lr": 5.5438001720075464e-05, "epoch": 0.5480067377877597, "percentage": 18.32, "elapsed_time": "5:53:04", "remaining_time": "1 day, 2:14:19"}
+{"current_steps": 62, "total_steps": 333, "loss": 0.4973, "lr": 5.535332323352595e-05, "epoch": 0.5569904548006738, "percentage": 18.62, "elapsed_time": "5:58:50", "remaining_time": "1 day, 2:08:28"}
+{"current_steps": 63, "total_steps": 333, "loss": 0.5027, "lr": 5.526565643153117e-05, "epoch": 0.5659741718135879, "percentage": 18.92, "elapsed_time": "6:04:32", "remaining_time": "1 day, 2:02:18"}
+{"current_steps": 64, "total_steps": 333, "loss": 0.4927, "lr": 5.517501099215618e-05, "epoch": 0.574957888826502, "percentage": 19.22, "elapsed_time": "6:10:18", "remaining_time": "1 day, 1:56:27"}
+{"current_steps": 65, "total_steps": 333, "loss": 0.4927, "lr": 5.5081396922295734e-05, "epoch": 0.583941605839416, "percentage": 19.52, "elapsed_time": "6:15:59", "remaining_time": "1 day, 1:50:16"}
+{"current_steps": 66, "total_steps": 333, "loss": 0.4922, "lr": 5.498482455656953e-05, "epoch": 0.5929253228523301, "percentage": 19.82, "elapsed_time": "6:21:50", "remaining_time": "1 day, 1:44:44"}
+{"current_steps": 67, "total_steps": 333, "loss": 0.4911, "lr": 5.488530455618133e-05, "epoch": 0.6019090398652442, "percentage": 20.12, "elapsed_time": "6:27:24", "remaining_time": "1 day, 1:38:04"}
+{"current_steps": 68, "total_steps": 333, "loss": 0.4947, "lr": 5.4782847907741996e-05, "epoch": 0.6108927568781584, "percentage": 20.42, "elapsed_time": "6:33:25", "remaining_time": "1 day, 1:33:13"}
+{"current_steps": 69, "total_steps": 333, "loss": 0.4891, "lr": 5.4677465922056604e-05, "epoch": 0.6198764738910725, "percentage": 20.72, "elapsed_time": "6:39:09", "remaining_time": "1 day, 1:27:11"}
+{"current_steps": 70, "total_steps": 333, "loss": 0.4877, "lr": 5.456917023287581e-05, "epoch": 0.6288601909039865, "percentage": 21.02, "elapsed_time": "6:45:03", "remaining_time": "1 day, 1:21:53"}
+{"current_steps": 71, "total_steps": 333, "loss": 0.4895, "lr": 5.445797279561149e-05, "epoch": 0.6378439079169006, "percentage": 21.32, "elapsed_time": "6:50:56", "remaining_time": "1 day, 1:16:25"}
+{"current_steps": 72, "total_steps": 333, "loss": 0.4803, "lr": 5.434388588601693e-05, "epoch": 0.6468276249298147, "percentage": 21.62, "elapsed_time": "6:56:28", "remaining_time": "1 day, 1:09:43"}
+{"current_steps": 73, "total_steps": 333, "loss": 0.4914, "lr": 5.422692209883164e-05, "epoch": 0.6558113419427288, "percentage": 21.92, "elapsed_time": "7:02:11", "remaining_time": "1 day, 1:03:40"}
+{"current_steps": 74, "total_steps": 333, "loss": 0.4869, "lr": 5.4107094346390925e-05, "epoch": 0.664795058955643, "percentage": 22.22, "elapsed_time": "7:07:38", "remaining_time": "1 day, 0:56:44"}
+{"current_steps": 75, "total_steps": 333, "loss": 0.4867, "lr": 5.398441585720041e-05, "epoch": 0.673778775968557, "percentage": 22.52, "elapsed_time": "7:13:26", "remaining_time": "1 day, 0:51:01"}
+{"current_steps": 76, "total_steps": 333, "loss": 0.4991, "lr": 5.3858900174475716e-05, "epoch": 0.6827624929814711, "percentage": 22.82, "elapsed_time": "7:19:16", "remaining_time": "1 day, 0:45:26"}
+{"current_steps": 77, "total_steps": 333, "loss": 0.4867, "lr": 5.373056115464729e-05, "epoch": 0.6917462099943852, "percentage": 23.12, "elapsed_time": "7:25:01", "remaining_time": "1 day, 0:39:32"}
+{"current_steps": 78, "total_steps": 333, "loss": 0.4882, "lr": 5.359941296583069e-05, "epoch": 0.7007299270072993, "percentage": 23.42, "elapsed_time": "7:30:55", "remaining_time": "1 day, 0:34:10"}
+{"current_steps": 79, "total_steps": 333, "loss": 0.4804, "lr": 5.346547008626259e-05, "epoch": 0.7097136440202133, "percentage": 23.72, "elapsed_time": "7:36:29", "remaining_time": "1 day, 0:27:43"}
+{"current_steps": 80, "total_steps": 333, "loss": 0.4965, "lr": 5.332874730270231e-05, "epoch": 0.7186973610331274, "percentage": 24.02, "elapsed_time": "7:42:14", "remaining_time": "1 day, 0:21:49"}
+{"current_steps": 81, "total_steps": 333, "loss": 0.4863, "lr": 5.3189259708799525e-05, "epoch": 0.7276810780460415, "percentage": 24.32, "elapsed_time": "7:48:03", "remaining_time": "1 day, 0:16:11"}
+{"current_steps": 82, "total_steps": 333, "loss": 0.4709, "lr": 5.304702270342788e-05, "epoch": 0.7366647950589557, "percentage": 24.62, "elapsed_time": "7:54:02", "remaining_time": "1 day, 0:11:01"}
+{"current_steps": 83, "total_steps": 333, "loss": 0.4935, "lr": 5.290205198898512e-05, "epoch": 0.7456485120718698, "percentage": 24.92, "elapsed_time": "7:59:55", "remaining_time": "1 day, 0:05:32"}
+{"current_steps": 84, "total_steps": 333, "loss": 0.4833, "lr": 5.275436356965955e-05, "epoch": 0.7546322290847838, "percentage": 25.23, "elapsed_time": "8:05:40", "remaining_time": "23:59:40"}
+{"current_steps": 85, "total_steps": 333, "loss": 0.4831, "lr": 5.260397374966324e-05, "epoch": 0.7636159460976979, "percentage": 25.53, "elapsed_time": "8:11:34", "remaining_time": "23:54:15"}
+{"current_steps": 86, "total_steps": 333, "loss": 0.4857, "lr": 5.245089913143211e-05, "epoch": 0.772599663110612, "percentage": 25.83, "elapsed_time": "8:17:28", "remaining_time": "23:48:48"}
+{"current_steps": 87, "total_steps": 333, "loss": 0.4783, "lr": 5.229515661379311e-05, "epoch": 0.7815833801235261, "percentage": 26.13, "elapsed_time": "8:23:14", "remaining_time": "23:42:58"}
+{"current_steps": 88, "total_steps": 333, "loss": 0.4888, "lr": 5.213676339009861e-05, "epoch": 0.7905670971364402, "percentage": 26.43, "elapsed_time": "8:29:07", "remaining_time": "23:37:25"}
+{"current_steps": 89, "total_steps": 333, "loss": 0.4722, "lr": 5.197573694632837e-05, "epoch": 0.7995508141493542, "percentage": 26.73, "elapsed_time": "8:35:04", "remaining_time": "23:32:07"}
+{"current_steps": 90, "total_steps": 333, "loss": 0.4844, "lr": 5.181209505915914e-05, "epoch": 0.8085345311622684, "percentage": 27.03, "elapsed_time": "8:41:10", "remaining_time": "23:27:10"}
+{"current_steps": 91, "total_steps": 333, "loss": 0.4835, "lr": 5.164585579400215e-05, "epoch": 0.8175182481751825, "percentage": 27.33, "elapsed_time": "8:47:05", "remaining_time": "23:21:42"}
+{"current_steps": 92, "total_steps": 333, "loss": 0.4795, "lr": 5.1477037503008845e-05, "epoch": 0.8265019651880966, "percentage": 27.63, "elapsed_time": "8:52:46", "remaining_time": "23:15:37"}
+{"current_steps": 93, "total_steps": 333, "loss": 0.4752, "lr": 5.130565882304478e-05, "epoch": 0.8354856822010107, "percentage": 27.93, "elapsed_time": "8:58:27", "remaining_time": "23:09:33"}
+{"current_steps": 94, "total_steps": 333, "loss": 0.4789, "lr": 5.113173867363228e-05, "epoch": 0.8444693992139247, "percentage": 28.23, "elapsed_time": "9:04:16", "remaining_time": "23:03:50"}
+{"current_steps": 95, "total_steps": 333, "loss": 0.4805, "lr": 5.095529625486171e-05, "epoch": 0.8534531162268388, "percentage": 28.53, "elapsed_time": "9:10:02", "remaining_time": "22:58:00"}
+{"current_steps": 96, "total_steps": 333, "loss": 0.486, "lr": 5.0776351045271936e-05, "epoch": 0.862436833239753, "percentage": 28.83, "elapsed_time": "9:15:57", "remaining_time": "22:52:31"}
+{"current_steps": 97, "total_steps": 333, "loss": 0.4845, "lr": 5.0594922799699925e-05, "epoch": 0.8714205502526671, "percentage": 29.13, "elapsed_time": "9:21:53", "remaining_time": "22:47:03"}
+{"current_steps": 98, "total_steps": 333, "loss": 0.467, "lr": 5.0411031547099916e-05, "epoch": 0.8804042672655812, "percentage": 29.43, "elapsed_time": "9:28:00", "remaining_time": "22:42:03"}
+{"current_steps": 99, "total_steps": 333, "loss": 0.4808, "lr": 5.0224697588332306e-05, "epoch": 0.8893879842784952, "percentage": 29.73, "elapsed_time": "9:33:37", "remaining_time": "22:35:51"}
+{"current_steps": 100, "total_steps": 333, "loss": 0.4686, "lr": 5.003594149392247e-05, "epoch": 0.8983717012914093, "percentage": 30.03, "elapsed_time": "9:39:37", "remaining_time": "22:30:31"}
+{"current_steps": 101, "total_steps": 333, "loss": 0.481, "lr": 4.984478410178992e-05, "epoch": 0.9073554183043234, "percentage": 30.33, "elapsed_time": "9:45:24", "remaining_time": "22:24:41"}
+{"current_steps": 102, "total_steps": 333, "loss": 0.4677, "lr": 4.965124651494785e-05, "epoch": 0.9163391353172375, "percentage": 30.63, "elapsed_time": "9:51:14", "remaining_time": "22:18:59"}
+{"current_steps": 103, "total_steps": 333, "loss": 0.4802, "lr": 4.9455350099173434e-05, "epoch": 0.9253228523301515, "percentage": 30.93, "elapsed_time": "9:56:52", "remaining_time": "22:12:49"}
+{"current_steps": 104, "total_steps": 333, "loss": 0.4694, "lr": 4.925711648064916e-05, "epoch": 0.9343065693430657, "percentage": 31.23, "elapsed_time": "10:02:34", "remaining_time": "22:06:48"}
+{"current_steps": 105, "total_steps": 333, "loss": 0.4809, "lr": 4.9056567543575374e-05, "epoch": 0.9432902863559798, "percentage": 31.53, "elapsed_time": "10:08:25", "remaining_time": "22:01:10"}
+{"current_steps": 106, "total_steps": 333, "loss": 0.4677, "lr": 4.885372542775435e-05, "epoch": 0.9522740033688939, "percentage": 31.83, "elapsed_time": "10:14:20", "remaining_time": "21:55:37"}
+{"current_steps": 107, "total_steps": 333, "loss": 0.47, "lr": 4.864861252614612e-05, "epoch": 0.961257720381808, "percentage": 32.13, "elapsed_time": "10:19:52", "remaining_time": "21:49:15"}
+{"current_steps": 108, "total_steps": 333, "loss": 0.4604, "lr": 4.844125148239645e-05, "epoch": 0.970241437394722, "percentage": 32.43, "elapsed_time": "10:25:24", "remaining_time": "21:42:56"}
+{"current_steps": 109, "total_steps": 333, "loss": 0.4686, "lr": 4.823166518833697e-05, "epoch": 0.9792251544076361, "percentage": 32.73, "elapsed_time": "10:31:10", "remaining_time": "21:37:05"}
+{"current_steps": 110, "total_steps": 333, "loss": 0.4771, "lr": 4.801987678145811e-05, "epoch": 0.9882088714205502, "percentage": 33.03, "elapsed_time": "10:36:48", "remaining_time": "21:30:58"}
+{"current_steps": 111, "total_steps": 333, "loss": 0.4701, "lr": 4.7805909642354734e-05, "epoch": 0.9971925884334644, "percentage": 33.33, "elapsed_time": "10:42:35", "remaining_time": "21:25:11"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6e5a83da6c8ab2c4ba038ec240cc26f0e520d21aaee4f9b87ae040dbeedd01
+size 7224