Training in progress, step 1000

.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-Coder-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9083b698928568da851538eeb7c20a0c598ef5f73df1468b06b3e1b320d426b1
+size 4996670464

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0295acc4b1d2ad88dd58c1bb81a60ab0e240f4eb0e4b6d51fcb8bf8eda5482
+size 1178224960

model.safetensors.index.json

@@ -0,0 +1,345 @@
+{
+  "metadata": {
+    "total_size": 6174857216
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.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": "<|im_end|>",
+    "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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 16000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,102 @@
+{"current_steps": 10, "total_steps": 17884, "loss": 0.6978, "lr": 1.1179429849077698e-07, "epoch": 0.0011182867846459225, "percentage": 0.06, "elapsed_time": "0:01:27", "remaining_time": "1 day, 19:27:48"}
+{"current_steps": 20, "total_steps": 17884, "loss": 0.6923, "lr": 2.2358859698155395e-07, "epoch": 0.002236573569291845, "percentage": 0.11, "elapsed_time": "0:02:54", "remaining_time": "1 day, 19:17:28"}
+{"current_steps": 30, "total_steps": 17884, "loss": 0.6305, "lr": 3.353828954723309e-07, "epoch": 0.0033548603539377674, "percentage": 0.17, "elapsed_time": "0:04:22", "remaining_time": "1 day, 19:27:25"}
+{"current_steps": 40, "total_steps": 17884, "loss": 0.6315, "lr": 4.471771939631079e-07, "epoch": 0.00447314713858369, "percentage": 0.22, "elapsed_time": "0:05:53", "remaining_time": "1 day, 19:49:21"}
+{"current_steps": 50, "total_steps": 17884, "loss": 0.6512, "lr": 5.589714924538849e-07, "epoch": 0.005591433923229612, "percentage": 0.28, "elapsed_time": "0:07:19", "remaining_time": "1 day, 19:30:04"}
+{"current_steps": 60, "total_steps": 17884, "loss": 0.5529, "lr": 6.707657909446619e-07, "epoch": 0.006709720707875535, "percentage": 0.34, "elapsed_time": "0:08:51", "remaining_time": "1 day, 19:52:32"}
+{"current_steps": 70, "total_steps": 17884, "loss": 0.5281, "lr": 7.825600894354389e-07, "epoch": 0.007828007492521457, "percentage": 0.39, "elapsed_time": "0:10:18", "remaining_time": "1 day, 19:42:02"}
+{"current_steps": 80, "total_steps": 17884, "loss": 0.4297, "lr": 8.943543879262158e-07, "epoch": 0.00894629427716738, "percentage": 0.45, "elapsed_time": "0:11:56", "remaining_time": "1 day, 20:16:46"}
+{"current_steps": 90, "total_steps": 17884, "loss": 0.3689, "lr": 1.0061486864169928e-06, "epoch": 0.010064581061813302, "percentage": 0.5, "elapsed_time": "0:13:31", "remaining_time": "1 day, 20:33:09"}
+{"current_steps": 100, "total_steps": 17884, "loss": 0.3483, "lr": 1.1179429849077699e-06, "epoch": 0.011182867846459225, "percentage": 0.56, "elapsed_time": "0:14:53", "remaining_time": "1 day, 20:09:31"}
+{"current_steps": 110, "total_steps": 17884, "loss": 0.2577, "lr": 1.2297372833985467e-06, "epoch": 0.012301154631105147, "percentage": 0.62, "elapsed_time": "0:16:18", "remaining_time": "1 day, 19:55:47"}
+{"current_steps": 120, "total_steps": 17884, "loss": 0.2465, "lr": 1.3415315818893237e-06, "epoch": 0.01341944141575107, "percentage": 0.67, "elapsed_time": "0:17:42", "remaining_time": "1 day, 19:40:57"}
+{"current_steps": 130, "total_steps": 17884, "loss": 0.228, "lr": 1.4533258803801007e-06, "epoch": 0.014537728200396992, "percentage": 0.73, "elapsed_time": "0:19:03", "remaining_time": "1 day, 19:23:53"}
+{"current_steps": 140, "total_steps": 17884, "loss": 0.1876, "lr": 1.5651201788708778e-06, "epoch": 0.015656014985042915, "percentage": 0.78, "elapsed_time": "0:20:22", "remaining_time": "1 day, 19:03:07"}
+{"current_steps": 150, "total_steps": 17884, "loss": 0.1993, "lr": 1.6769144773616548e-06, "epoch": 0.016774301769688835, "percentage": 0.84, "elapsed_time": "0:21:49", "remaining_time": "1 day, 19:00:48"}
+{"current_steps": 160, "total_steps": 17884, "loss": 0.1842, "lr": 1.7887087758524316e-06, "epoch": 0.01789258855433476, "percentage": 0.89, "elapsed_time": "0:23:19", "remaining_time": "1 day, 19:04:21"}
+{"current_steps": 170, "total_steps": 17884, "loss": 0.1672, "lr": 1.9005030743432088e-06, "epoch": 0.01901087533898068, "percentage": 0.95, "elapsed_time": "0:24:47", "remaining_time": "1 day, 19:02:55"}
+{"current_steps": 180, "total_steps": 17884, "loss": 0.1324, "lr": 2.0122973728339857e-06, "epoch": 0.020129162123626605, "percentage": 1.01, "elapsed_time": "0:25:54", "remaining_time": "1 day, 18:29:01"}
+{"current_steps": 190, "total_steps": 17884, "loss": 0.1507, "lr": 2.1240916713247627e-06, "epoch": 0.021247448908272525, "percentage": 1.06, "elapsed_time": "0:27:15", "remaining_time": "1 day, 18:18:51"}
+{"current_steps": 200, "total_steps": 17884, "loss": 0.153, "lr": 2.2358859698155397e-06, "epoch": 0.02236573569291845, "percentage": 1.12, "elapsed_time": "0:28:48", "remaining_time": "1 day, 18:26:57"}
+{"current_steps": 210, "total_steps": 17884, "loss": 0.1351, "lr": 2.3476802683063167e-06, "epoch": 0.02348402247756437, "percentage": 1.17, "elapsed_time": "0:30:19", "remaining_time": "1 day, 18:32:14"}
+{"current_steps": 220, "total_steps": 17884, "loss": 0.128, "lr": 2.4594745667970933e-06, "epoch": 0.024602309262210294, "percentage": 1.23, "elapsed_time": "0:31:40", "remaining_time": "1 day, 18:23:30"}
+{"current_steps": 230, "total_steps": 17884, "loss": 0.1359, "lr": 2.5712688652878704e-06, "epoch": 0.025720596046856215, "percentage": 1.29, "elapsed_time": "0:33:07", "remaining_time": "1 day, 18:22:10"}
+{"current_steps": 240, "total_steps": 17884, "loss": 0.146, "lr": 2.6830631637786474e-06, "epoch": 0.02683888283150214, "percentage": 1.34, "elapsed_time": "0:34:25", "remaining_time": "1 day, 18:10:30"}
+{"current_steps": 250, "total_steps": 17884, "loss": 0.1174, "lr": 2.794857462269425e-06, "epoch": 0.02795716961614806, "percentage": 1.4, "elapsed_time": "0:35:43", "remaining_time": "1 day, 18:00:25"}
+{"current_steps": 260, "total_steps": 17884, "loss": 0.127, "lr": 2.9066517607602015e-06, "epoch": 0.029075456400793984, "percentage": 1.45, "elapsed_time": "0:37:11", "remaining_time": "1 day, 18:01:05"}
+{"current_steps": 270, "total_steps": 17884, "loss": 0.1249, "lr": 3.0184460592509785e-06, "epoch": 0.030193743185439905, "percentage": 1.51, "elapsed_time": "0:38:31", "remaining_time": "1 day, 17:53:00"}
+{"current_steps": 280, "total_steps": 17884, "loss": 0.1219, "lr": 3.1302403577417555e-06, "epoch": 0.03131202997008583, "percentage": 1.57, "elapsed_time": "0:39:55", "remaining_time": "1 day, 17:50:12"}
+{"current_steps": 290, "total_steps": 17884, "loss": 0.1238, "lr": 3.242034656232532e-06, "epoch": 0.03243031675473175, "percentage": 1.62, "elapsed_time": "0:41:23", "remaining_time": "1 day, 17:51:34"}
+{"current_steps": 300, "total_steps": 17884, "loss": 0.1195, "lr": 3.3538289547233096e-06, "epoch": 0.03354860353937767, "percentage": 1.68, "elapsed_time": "0:42:48", "remaining_time": "1 day, 17:49:13"}
+{"current_steps": 310, "total_steps": 17884, "loss": 0.1194, "lr": 3.4656232532140866e-06, "epoch": 0.0346668903240236, "percentage": 1.73, "elapsed_time": "0:44:21", "remaining_time": "1 day, 17:54:29"}
+{"current_steps": 320, "total_steps": 17884, "loss": 0.1305, "lr": 3.577417551704863e-06, "epoch": 0.03578517710866952, "percentage": 1.79, "elapsed_time": "0:45:45", "remaining_time": "1 day, 17:51:30"}
+{"current_steps": 330, "total_steps": 17884, "loss": 0.1272, "lr": 3.6892118501956402e-06, "epoch": 0.03690346389331544, "percentage": 1.85, "elapsed_time": "0:47:13", "remaining_time": "1 day, 17:51:51"}
+{"current_steps": 340, "total_steps": 17884, "loss": 0.1062, "lr": 3.8010061486864177e-06, "epoch": 0.03802175067796136, "percentage": 1.9, "elapsed_time": "0:48:42", "remaining_time": "1 day, 17:53:32"}
+{"current_steps": 350, "total_steps": 17884, "loss": 0.1079, "lr": 3.912800447177194e-06, "epoch": 0.03914003746260729, "percentage": 1.96, "elapsed_time": "0:50:17", "remaining_time": "1 day, 17:59:28"}
+{"current_steps": 360, "total_steps": 17884, "loss": 0.1023, "lr": 4.024594745667971e-06, "epoch": 0.04025832424725321, "percentage": 2.01, "elapsed_time": "0:51:35", "remaining_time": "1 day, 17:51:14"}
+{"current_steps": 370, "total_steps": 17884, "loss": 0.117, "lr": 4.136389044158749e-06, "epoch": 0.04137661103189913, "percentage": 2.07, "elapsed_time": "0:53:09", "remaining_time": "1 day, 17:56:23"}
+{"current_steps": 380, "total_steps": 17884, "loss": 0.0958, "lr": 4.248183342649525e-06, "epoch": 0.04249489781654505, "percentage": 2.12, "elapsed_time": "0:54:35", "remaining_time": "1 day, 17:55:00"}
+{"current_steps": 390, "total_steps": 17884, "loss": 0.1026, "lr": 4.359977641140302e-06, "epoch": 0.04361318460119098, "percentage": 2.18, "elapsed_time": "0:56:14", "remaining_time": "1 day, 18:02:43"}
+{"current_steps": 400, "total_steps": 17884, "loss": 0.1193, "lr": 4.4717719396310794e-06, "epoch": 0.0447314713858369, "percentage": 2.24, "elapsed_time": "0:57:46", "remaining_time": "1 day, 18:05:37"}
+{"current_steps": 410, "total_steps": 17884, "loss": 0.1145, "lr": 4.583566238121856e-06, "epoch": 0.04584975817048282, "percentage": 2.29, "elapsed_time": "0:59:13", "remaining_time": "1 day, 18:04:21"}
+{"current_steps": 420, "total_steps": 17884, "loss": 0.1065, "lr": 4.6953605366126335e-06, "epoch": 0.04696804495512874, "percentage": 2.35, "elapsed_time": "1:00:45", "remaining_time": "1 day, 18:06:15"}
+{"current_steps": 430, "total_steps": 17884, "loss": 0.0886, "lr": 4.80715483510341e-06, "epoch": 0.04808633173977467, "percentage": 2.4, "elapsed_time": "1:02:09", "remaining_time": "1 day, 18:02:44"}
+{"current_steps": 440, "total_steps": 17884, "loss": 0.0847, "lr": 4.918949133594187e-06, "epoch": 0.04920461852442059, "percentage": 2.46, "elapsed_time": "1:03:26", "remaining_time": "1 day, 17:55:11"}
+{"current_steps": 450, "total_steps": 17884, "loss": 0.106, "lr": 5.030743432084965e-06, "epoch": 0.05032290530906651, "percentage": 2.52, "elapsed_time": "1:05:11", "remaining_time": "1 day, 18:05:53"}
+{"current_steps": 460, "total_steps": 17884, "loss": 0.0869, "lr": 5.142537730575741e-06, "epoch": 0.05144119209371243, "percentage": 2.57, "elapsed_time": "1:06:33", "remaining_time": "1 day, 18:01:05"}
+{"current_steps": 470, "total_steps": 17884, "loss": 0.0954, "lr": 5.254332029066518e-06, "epoch": 0.05255947887835836, "percentage": 2.63, "elapsed_time": "1:07:57", "remaining_time": "1 day, 17:58:09"}
+{"current_steps": 480, "total_steps": 17884, "loss": 0.0969, "lr": 5.366126327557295e-06, "epoch": 0.05367776566300428, "percentage": 2.68, "elapsed_time": "1:09:34", "remaining_time": "1 day, 18:02:29"}
+{"current_steps": 490, "total_steps": 17884, "loss": 0.0988, "lr": 5.477920626048072e-06, "epoch": 0.0547960524476502, "percentage": 2.74, "elapsed_time": "1:11:07", "remaining_time": "1 day, 18:04:53"}
+{"current_steps": 500, "total_steps": 17884, "loss": 0.0867, "lr": 5.58971492453885e-06, "epoch": 0.05591433923229612, "percentage": 2.8, "elapsed_time": "1:12:17", "remaining_time": "1 day, 17:53:40"}
+{"current_steps": 510, "total_steps": 17884, "loss": 0.0948, "lr": 5.701509223029626e-06, "epoch": 0.05703262601694205, "percentage": 2.85, "elapsed_time": "1:13:44", "remaining_time": "1 day, 17:52:17"}
+{"current_steps": 520, "total_steps": 17884, "loss": 0.0949, "lr": 5.813303521520403e-06, "epoch": 0.05815091280158797, "percentage": 2.91, "elapsed_time": "1:15:06", "remaining_time": "1 day, 17:48:01"}
+{"current_steps": 530, "total_steps": 17884, "loss": 0.0862, "lr": 5.9250978200111795e-06, "epoch": 0.05926919958623389, "percentage": 2.96, "elapsed_time": "1:16:26", "remaining_time": "1 day, 17:42:42"}
+{"current_steps": 540, "total_steps": 17884, "loss": 0.0889, "lr": 6.036892118501957e-06, "epoch": 0.06038748637087981, "percentage": 3.02, "elapsed_time": "1:17:58", "remaining_time": "1 day, 17:44:14"}
+{"current_steps": 550, "total_steps": 17884, "loss": 0.095, "lr": 6.1486864169927344e-06, "epoch": 0.06150577315552574, "percentage": 3.08, "elapsed_time": "1:19:37", "remaining_time": "1 day, 17:49:14"}
+{"current_steps": 560, "total_steps": 17884, "loss": 0.0865, "lr": 6.260480715483511e-06, "epoch": 0.06262405994017166, "percentage": 3.13, "elapsed_time": "1:20:59", "remaining_time": "1 day, 17:45:33"}
+{"current_steps": 570, "total_steps": 17884, "loss": 0.094, "lr": 6.3722750139742885e-06, "epoch": 0.06374234672481759, "percentage": 3.19, "elapsed_time": "1:22:30", "remaining_time": "1 day, 17:46:22"}
+{"current_steps": 580, "total_steps": 17884, "loss": 0.0946, "lr": 6.484069312465064e-06, "epoch": 0.0648606335094635, "percentage": 3.24, "elapsed_time": "1:23:58", "remaining_time": "1 day, 17:45:33"}
+{"current_steps": 590, "total_steps": 17884, "loss": 0.0837, "lr": 6.595863610955842e-06, "epoch": 0.06597892029410943, "percentage": 3.3, "elapsed_time": "1:25:10", "remaining_time": "1 day, 17:36:34"}
+{"current_steps": 600, "total_steps": 17884, "loss": 0.088, "lr": 6.707657909446619e-06, "epoch": 0.06709720707875534, "percentage": 3.35, "elapsed_time": "1:26:27", "remaining_time": "1 day, 17:30:48"}
+{"current_steps": 610, "total_steps": 17884, "loss": 0.0882, "lr": 6.819452207937396e-06, "epoch": 0.06821549386340127, "percentage": 3.41, "elapsed_time": "1:27:57", "remaining_time": "1 day, 17:30:38"}
+{"current_steps": 620, "total_steps": 17884, "loss": 0.084, "lr": 6.931246506428173e-06, "epoch": 0.0693337806480472, "percentage": 3.47, "elapsed_time": "1:29:23", "remaining_time": "1 day, 17:29:17"}
+{"current_steps": 630, "total_steps": 17884, "loss": 0.0846, "lr": 7.043040804918951e-06, "epoch": 0.07045206743269311, "percentage": 3.52, "elapsed_time": "1:30:56", "remaining_time": "1 day, 17:30:50"}
+{"current_steps": 640, "total_steps": 17884, "loss": 0.0806, "lr": 7.154835103409726e-06, "epoch": 0.07157035421733904, "percentage": 3.58, "elapsed_time": "1:32:33", "remaining_time": "1 day, 17:33:52"}
+{"current_steps": 650, "total_steps": 17884, "loss": 0.0962, "lr": 7.266629401900504e-06, "epoch": 0.07268864100198495, "percentage": 3.63, "elapsed_time": "1:34:01", "remaining_time": "1 day, 17:32:47"}
+{"current_steps": 660, "total_steps": 17884, "loss": 0.0806, "lr": 7.3784237003912805e-06, "epoch": 0.07380692778663088, "percentage": 3.69, "elapsed_time": "1:35:25", "remaining_time": "1 day, 17:30:14"}
+{"current_steps": 670, "total_steps": 17884, "loss": 0.0762, "lr": 7.490217998882058e-06, "epoch": 0.07492521457127681, "percentage": 3.75, "elapsed_time": "1:36:46", "remaining_time": "1 day, 17:26:31"}
+{"current_steps": 680, "total_steps": 17884, "loss": 0.0929, "lr": 7.602012297372835e-06, "epoch": 0.07604350135592272, "percentage": 3.8, "elapsed_time": "1:38:30", "remaining_time": "1 day, 17:32:28"}
+{"current_steps": 690, "total_steps": 17884, "loss": 0.0962, "lr": 7.713806595863613e-06, "epoch": 0.07716178814056865, "percentage": 3.86, "elapsed_time": "1:40:04", "remaining_time": "1 day, 17:33:46"}
+{"current_steps": 700, "total_steps": 17884, "loss": 0.0883, "lr": 7.825600894354388e-06, "epoch": 0.07828007492521458, "percentage": 3.91, "elapsed_time": "1:41:59", "remaining_time": "1 day, 17:43:37"}
+{"current_steps": 710, "total_steps": 17884, "loss": 0.0825, "lr": 7.937395192845166e-06, "epoch": 0.07939836170986049, "percentage": 3.97, "elapsed_time": "1:43:23", "remaining_time": "1 day, 17:40:53"}
+{"current_steps": 720, "total_steps": 17884, "loss": 0.0892, "lr": 8.049189491335943e-06, "epoch": 0.08051664849450642, "percentage": 4.03, "elapsed_time": "1:44:57", "remaining_time": "1 day, 17:42:17"}
+{"current_steps": 730, "total_steps": 17884, "loss": 0.087, "lr": 8.16098378982672e-06, "epoch": 0.08163493527915233, "percentage": 4.08, "elapsed_time": "1:46:38", "remaining_time": "1 day, 17:45:47"}
+{"current_steps": 740, "total_steps": 17884, "loss": 0.0883, "lr": 8.272778088317498e-06, "epoch": 0.08275322206379826, "percentage": 4.14, "elapsed_time": "1:48:14", "remaining_time": "1 day, 17:47:48"}
+{"current_steps": 750, "total_steps": 17884, "loss": 0.0738, "lr": 8.384572386808274e-06, "epoch": 0.08387150884844419, "percentage": 4.19, "elapsed_time": "1:49:41", "remaining_time": "1 day, 17:46:07"}
+{"current_steps": 760, "total_steps": 17884, "loss": 0.0783, "lr": 8.49636668529905e-06, "epoch": 0.0849897956330901, "percentage": 4.25, "elapsed_time": "1:51:14", "remaining_time": "1 day, 17:46:15"}
+{"current_steps": 770, "total_steps": 17884, "loss": 0.0886, "lr": 8.608160983789827e-06, "epoch": 0.08610808241773603, "percentage": 4.31, "elapsed_time": "1:52:50", "remaining_time": "1 day, 17:48:00"}
+{"current_steps": 780, "total_steps": 17884, "loss": 0.0897, "lr": 8.719955282280604e-06, "epoch": 0.08722636920238196, "percentage": 4.36, "elapsed_time": "1:54:27", "remaining_time": "1 day, 17:49:55"}
+{"current_steps": 790, "total_steps": 17884, "loss": 0.071, "lr": 8.831749580771382e-06, "epoch": 0.08834465598702787, "percentage": 4.42, "elapsed_time": "1:56:03", "remaining_time": "1 day, 17:51:11"}
+{"current_steps": 800, "total_steps": 17884, "loss": 0.0834, "lr": 8.943543879262159e-06, "epoch": 0.0894629427716738, "percentage": 4.47, "elapsed_time": "1:57:40", "remaining_time": "1 day, 17:52:49"}
+{"current_steps": 810, "total_steps": 17884, "loss": 0.0934, "lr": 9.055338177752935e-06, "epoch": 0.09058122955631971, "percentage": 4.53, "elapsed_time": "1:59:21", "remaining_time": "1 day, 17:55:49"}
+{"current_steps": 820, "total_steps": 17884, "loss": 0.0833, "lr": 9.167132476243712e-06, "epoch": 0.09169951634096564, "percentage": 4.59, "elapsed_time": "2:00:54", "remaining_time": "1 day, 17:56:10"}
+{"current_steps": 830, "total_steps": 17884, "loss": 0.0834, "lr": 9.278926774734489e-06, "epoch": 0.09281780312561157, "percentage": 4.64, "elapsed_time": "2:02:13", "remaining_time": "1 day, 17:51:11"}
+{"current_steps": 840, "total_steps": 17884, "loss": 0.0622, "lr": 9.390721073225267e-06, "epoch": 0.09393608991025748, "percentage": 4.7, "elapsed_time": "2:03:29", "remaining_time": "1 day, 17:45:42"}
+{"current_steps": 850, "total_steps": 17884, "loss": 0.0775, "lr": 9.502515371716044e-06, "epoch": 0.09505437669490341, "percentage": 4.75, "elapsed_time": "2:04:52", "remaining_time": "1 day, 17:42:39"}
+{"current_steps": 860, "total_steps": 17884, "loss": 0.0812, "lr": 9.61430967020682e-06, "epoch": 0.09617266347954934, "percentage": 4.81, "elapsed_time": "2:06:16", "remaining_time": "1 day, 17:39:46"}
+{"current_steps": 870, "total_steps": 17884, "loss": 0.0709, "lr": 9.726103968697598e-06, "epoch": 0.09729095026419525, "percentage": 4.86, "elapsed_time": "2:07:51", "remaining_time": "1 day, 17:40:26"}
+{"current_steps": 880, "total_steps": 17884, "loss": 0.0652, "lr": 9.837898267188373e-06, "epoch": 0.09840923704884118, "percentage": 4.92, "elapsed_time": "2:09:22", "remaining_time": "1 day, 17:39:43"}
+{"current_steps": 890, "total_steps": 17884, "loss": 0.0758, "lr": 9.949692565679152e-06, "epoch": 0.09952752383348709, "percentage": 4.98, "elapsed_time": "2:10:56", "remaining_time": "1 day, 17:40:06"}
+{"current_steps": 900, "total_steps": 17884, "loss": 0.0713, "lr": 1.006148686416993e-05, "epoch": 0.10064581061813302, "percentage": 5.03, "elapsed_time": "2:12:21", "remaining_time": "1 day, 17:37:43"}
+{"current_steps": 910, "total_steps": 17884, "loss": 0.0655, "lr": 1.0173281162660705e-05, "epoch": 0.10176409740277895, "percentage": 5.09, "elapsed_time": "2:13:54", "remaining_time": "1 day, 17:37:39"}
+{"current_steps": 920, "total_steps": 17884, "loss": 0.0721, "lr": 1.0285075461151481e-05, "epoch": 0.10288238418742486, "percentage": 5.14, "elapsed_time": "2:15:21", "remaining_time": "1 day, 17:35:59"}
+{"current_steps": 930, "total_steps": 17884, "loss": 0.0602, "lr": 1.0396869759642258e-05, "epoch": 0.10400067097207079, "percentage": 5.2, "elapsed_time": "2:16:47", "remaining_time": "1 day, 17:33:35"}
+{"current_steps": 940, "total_steps": 17884, "loss": 0.0657, "lr": 1.0508664058133036e-05, "epoch": 0.10511895775671672, "percentage": 5.26, "elapsed_time": "2:18:15", "remaining_time": "1 day, 17:32:02"}
+{"current_steps": 950, "total_steps": 17884, "loss": 0.0692, "lr": 1.0620458356623813e-05, "epoch": 0.10623724454136263, "percentage": 5.31, "elapsed_time": "2:19:41", "remaining_time": "1 day, 17:29:53"}
+{"current_steps": 960, "total_steps": 17884, "loss": 0.0709, "lr": 1.073225265511459e-05, "epoch": 0.10735553132600856, "percentage": 5.37, "elapsed_time": "2:21:11", "remaining_time": "1 day, 17:29:04"}
+{"current_steps": 970, "total_steps": 17884, "loss": 0.0628, "lr": 1.0844046953605368e-05, "epoch": 0.10847381811065447, "percentage": 5.42, "elapsed_time": "2:22:39", "remaining_time": "1 day, 17:27:36"}
+{"current_steps": 980, "total_steps": 17884, "loss": 0.0729, "lr": 1.0955841252096145e-05, "epoch": 0.1095921048953004, "percentage": 5.48, "elapsed_time": "2:24:06", "remaining_time": "1 day, 17:25:50"}
+{"current_steps": 990, "total_steps": 17884, "loss": 0.089, "lr": 1.1067635550586921e-05, "epoch": 0.11071039167994633, "percentage": 5.54, "elapsed_time": "2:25:40", "remaining_time": "1 day, 17:25:50"}
+{"current_steps": 1000, "total_steps": 17884, "loss": 0.0655, "lr": 1.11794298490777e-05, "epoch": 0.11182867846459224, "percentage": 5.59, "elapsed_time": "2:27:14", "remaining_time": "1 day, 17:26:06"}
+{"current_steps": 1010, "total_steps": 17884, "loss": 0.0779, "lr": 1.1291224147568476e-05, "epoch": 0.11294696524923817, "percentage": 5.65, "elapsed_time": "2:29:31", "remaining_time": "1 day, 17:38:00"}
+{"current_steps": 1020, "total_steps": 17884, "loss": 0.0682, "lr": 1.1403018446059253e-05, "epoch": 0.1140652520338841, "percentage": 5.7, "elapsed_time": "2:31:00", "remaining_time": "1 day, 17:36:48"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47a77c854f95cb57a1ce7b7626ad697dd4c5193473d6200ef90cff35c2d29d8
+size 5752