Training in progress, step 100

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66b32dd81b3e45fb9bf813c299ac7a9262b6e7f4325167627875b8e7dfa2f87
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f8a2f5612787cd37d174f6683eb0aa635d0d558fe2181d6cfb8cd92833a6e3
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30977130cb7312664605908a8742d6c23bf5624a49c5920c7b6e92adf733b04e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1022ce6ba0fe1114f72a25d4c6bc0d36d856313bb6f23bff0166c5741a07d2e
+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 +1,102 @@
+{"current_steps": 1, "total_steps": 1524, "loss": 0.8567, "lr": 6.535947712418302e-08, "epoch": 0.001965923984272608, "percentage": 0.07, "elapsed_time": "0:01:11", "remaining_time": "1 day, 6:22:30"}
+{"current_steps": 2, "total_steps": 1524, "loss": 0.8409, "lr": 1.3071895424836603e-07, "epoch": 0.003931847968545216, "percentage": 0.13, "elapsed_time": "0:02:05", "remaining_time": "1 day, 2:31:10"}
+{"current_steps": 3, "total_steps": 1524, "loss": 0.8184, "lr": 1.9607843137254904e-07, "epoch": 0.005897771952817824, "percentage": 0.2, "elapsed_time": "0:02:59", "remaining_time": "1 day, 1:14:09"}
+{"current_steps": 4, "total_steps": 1524, "loss": 0.8196, "lr": 2.6143790849673207e-07, "epoch": 0.007863695937090432, "percentage": 0.26, "elapsed_time": "0:03:53", "remaining_time": "1 day, 0:35:58"}
+{"current_steps": 5, "total_steps": 1524, "loss": 0.8381, "lr": 3.267973856209151e-07, "epoch": 0.009829619921363041, "percentage": 0.33, "elapsed_time": "0:04:46", "remaining_time": "1 day, 0:12:19"}
+{"current_steps": 6, "total_steps": 1524, "loss": 0.849, "lr": 3.921568627450981e-07, "epoch": 0.011795543905635648, "percentage": 0.39, "elapsed_time": "0:05:40", "remaining_time": "23:56:32"}
+{"current_steps": 7, "total_steps": 1524, "loss": 0.8528, "lr": 4.5751633986928105e-07, "epoch": 0.013761467889908258, "percentage": 0.46, "elapsed_time": "0:06:34", "remaining_time": "23:44:22"}
+{"current_steps": 8, "total_steps": 1524, "loss": 0.8135, "lr": 5.228758169934641e-07, "epoch": 0.015727391874180863, "percentage": 0.52, "elapsed_time": "0:07:28", "remaining_time": "23:35:46"}
+{"current_steps": 9, "total_steps": 1524, "loss": 0.841, "lr": 5.882352941176471e-07, "epoch": 0.017693315858453473, "percentage": 0.59, "elapsed_time": "0:08:21", "remaining_time": "23:26:36"}
+{"current_steps": 10, "total_steps": 1524, "loss": 0.8116, "lr": 6.535947712418302e-07, "epoch": 0.019659239842726082, "percentage": 0.66, "elapsed_time": "0:09:14", "remaining_time": "23:18:46"}
+{"current_steps": 11, "total_steps": 1524, "loss": 0.8378, "lr": 7.189542483660131e-07, "epoch": 0.02162516382699869, "percentage": 0.72, "elapsed_time": "0:10:07", "remaining_time": "23:11:51"}
+{"current_steps": 12, "total_steps": 1524, "loss": 0.8191, "lr": 7.843137254901962e-07, "epoch": 0.023591087811271297, "percentage": 0.79, "elapsed_time": "0:11:00", "remaining_time": "23:06:22"}
+{"current_steps": 13, "total_steps": 1524, "loss": 0.8056, "lr": 8.496732026143792e-07, "epoch": 0.025557011795543906, "percentage": 0.85, "elapsed_time": "0:11:53", "remaining_time": "23:02:25"}
+{"current_steps": 14, "total_steps": 1524, "loss": 0.7871, "lr": 9.150326797385621e-07, "epoch": 0.027522935779816515, "percentage": 0.92, "elapsed_time": "0:12:46", "remaining_time": "22:58:20"}
+{"current_steps": 15, "total_steps": 1524, "loss": 0.8056, "lr": 9.80392156862745e-07, "epoch": 0.02948885976408912, "percentage": 0.98, "elapsed_time": "0:13:39", "remaining_time": "22:54:32"}
+{"current_steps": 16, "total_steps": 1524, "loss": 0.7729, "lr": 1.0457516339869283e-06, "epoch": 0.03145478374836173, "percentage": 1.05, "elapsed_time": "0:14:32", "remaining_time": "22:51:07"}
+{"current_steps": 17, "total_steps": 1524, "loss": 0.7517, "lr": 1.111111111111111e-06, "epoch": 0.033420707732634336, "percentage": 1.12, "elapsed_time": "0:15:25", "remaining_time": "22:48:05"}
+{"current_steps": 18, "total_steps": 1524, "loss": 0.764, "lr": 1.1764705882352942e-06, "epoch": 0.035386631716906945, "percentage": 1.18, "elapsed_time": "0:16:18", "remaining_time": "22:45:00"}
+{"current_steps": 19, "total_steps": 1524, "loss": 0.7601, "lr": 1.2418300653594772e-06, "epoch": 0.037352555701179554, "percentage": 1.25, "elapsed_time": "0:17:11", "remaining_time": "22:42:07"}
+{"current_steps": 20, "total_steps": 1524, "loss": 0.7611, "lr": 1.3071895424836604e-06, "epoch": 0.039318479685452164, "percentage": 1.31, "elapsed_time": "0:18:04", "remaining_time": "22:39:23"}
+{"current_steps": 21, "total_steps": 1524, "loss": 0.7507, "lr": 1.3725490196078434e-06, "epoch": 0.04128440366972477, "percentage": 1.38, "elapsed_time": "0:18:57", "remaining_time": "22:36:57"}
+{"current_steps": 22, "total_steps": 1524, "loss": 0.7888, "lr": 1.4379084967320261e-06, "epoch": 0.04325032765399738, "percentage": 1.44, "elapsed_time": "0:19:50", "remaining_time": "22:34:38"}
+{"current_steps": 23, "total_steps": 1524, "loss": 0.7509, "lr": 1.5032679738562091e-06, "epoch": 0.045216251638269984, "percentage": 1.51, "elapsed_time": "0:20:43", "remaining_time": "22:32:25"}
+{"current_steps": 24, "total_steps": 1524, "loss": 0.7112, "lr": 1.5686274509803923e-06, "epoch": 0.047182175622542594, "percentage": 1.57, "elapsed_time": "0:21:36", "remaining_time": "22:30:22"}
+{"current_steps": 25, "total_steps": 1524, "loss": 0.7437, "lr": 1.6339869281045753e-06, "epoch": 0.0491480996068152, "percentage": 1.64, "elapsed_time": "0:22:29", "remaining_time": "22:28:23"}
+{"current_steps": 26, "total_steps": 1524, "loss": 0.6998, "lr": 1.6993464052287585e-06, "epoch": 0.05111402359108781, "percentage": 1.71, "elapsed_time": "0:23:22", "remaining_time": "22:26:30"}
+{"current_steps": 27, "total_steps": 1524, "loss": 0.7304, "lr": 1.7647058823529414e-06, "epoch": 0.05307994757536042, "percentage": 1.77, "elapsed_time": "0:24:15", "remaining_time": "22:24:43"}
+{"current_steps": 28, "total_steps": 1524, "loss": 0.7093, "lr": 1.8300653594771242e-06, "epoch": 0.05504587155963303, "percentage": 1.84, "elapsed_time": "0:25:08", "remaining_time": "22:22:53"}
+{"current_steps": 29, "total_steps": 1524, "loss": 0.6828, "lr": 1.8954248366013072e-06, "epoch": 0.05701179554390563, "percentage": 1.9, "elapsed_time": "0:26:00", "remaining_time": "22:21:09"}
+{"current_steps": 30, "total_steps": 1524, "loss": 0.7195, "lr": 1.96078431372549e-06, "epoch": 0.05897771952817824, "percentage": 1.97, "elapsed_time": "0:26:54", "remaining_time": "22:19:40"}
+{"current_steps": 31, "total_steps": 1524, "loss": 0.6714, "lr": 2.0261437908496734e-06, "epoch": 0.06094364351245085, "percentage": 2.03, "elapsed_time": "0:27:47", "remaining_time": "22:18:13"}
+{"current_steps": 32, "total_steps": 1524, "loss": 0.6816, "lr": 2.0915032679738565e-06, "epoch": 0.06290956749672345, "percentage": 2.1, "elapsed_time": "0:28:40", "remaining_time": "22:17:21"}
+{"current_steps": 33, "total_steps": 1524, "loss": 0.6715, "lr": 2.1568627450980393e-06, "epoch": 0.06487549148099607, "percentage": 2.17, "elapsed_time": "0:29:34", "remaining_time": "22:15:58"}
+{"current_steps": 34, "total_steps": 1524, "loss": 0.6749, "lr": 2.222222222222222e-06, "epoch": 0.06684141546526867, "percentage": 2.23, "elapsed_time": "0:30:27", "remaining_time": "22:14:37"}
+{"current_steps": 35, "total_steps": 1524, "loss": 0.6724, "lr": 2.2875816993464053e-06, "epoch": 0.06880733944954129, "percentage": 2.3, "elapsed_time": "0:31:20", "remaining_time": "22:13:11"}
+{"current_steps": 36, "total_steps": 1524, "loss": 0.6533, "lr": 2.3529411764705885e-06, "epoch": 0.07077326343381389, "percentage": 2.36, "elapsed_time": "0:32:13", "remaining_time": "22:11:54"}
+{"current_steps": 37, "total_steps": 1524, "loss": 0.6687, "lr": 2.4183006535947716e-06, "epoch": 0.0727391874180865, "percentage": 2.43, "elapsed_time": "0:33:06", "remaining_time": "22:10:42"}
+{"current_steps": 38, "total_steps": 1524, "loss": 0.6419, "lr": 2.4836601307189544e-06, "epoch": 0.07470511140235911, "percentage": 2.49, "elapsed_time": "0:34:00", "remaining_time": "22:09:35"}
+{"current_steps": 39, "total_steps": 1524, "loss": 0.6659, "lr": 2.549019607843137e-06, "epoch": 0.07667103538663171, "percentage": 2.56, "elapsed_time": "0:34:53", "remaining_time": "22:08:50"}
+{"current_steps": 40, "total_steps": 1524, "loss": 0.6398, "lr": 2.6143790849673208e-06, "epoch": 0.07863695937090433, "percentage": 2.62, "elapsed_time": "0:35:47", "remaining_time": "22:08:00"}
+{"current_steps": 41, "total_steps": 1524, "loss": 0.6064, "lr": 2.6797385620915036e-06, "epoch": 0.08060288335517693, "percentage": 2.69, "elapsed_time": "0:36:41", "remaining_time": "22:07:14"}
+{"current_steps": 42, "total_steps": 1524, "loss": 0.648, "lr": 2.7450980392156867e-06, "epoch": 0.08256880733944955, "percentage": 2.76, "elapsed_time": "0:37:35", "remaining_time": "22:06:43"}
+{"current_steps": 43, "total_steps": 1524, "loss": 0.6018, "lr": 2.8104575163398695e-06, "epoch": 0.08453473132372215, "percentage": 2.82, "elapsed_time": "0:38:29", "remaining_time": "22:05:54"}
+{"current_steps": 44, "total_steps": 1524, "loss": 0.6285, "lr": 2.8758169934640523e-06, "epoch": 0.08650065530799476, "percentage": 2.89, "elapsed_time": "0:39:23", "remaining_time": "22:05:07"}
+{"current_steps": 45, "total_steps": 1524, "loss": 0.6006, "lr": 2.9411764705882355e-06, "epoch": 0.08846657929226737, "percentage": 2.95, "elapsed_time": "0:40:17", "remaining_time": "22:04:28"}
+{"current_steps": 46, "total_steps": 1524, "loss": 0.6071, "lr": 3.0065359477124182e-06, "epoch": 0.09043250327653997, "percentage": 3.02, "elapsed_time": "0:41:12", "remaining_time": "22:03:50"}
+{"current_steps": 47, "total_steps": 1524, "loss": 0.5908, "lr": 3.071895424836602e-06, "epoch": 0.09239842726081259, "percentage": 3.08, "elapsed_time": "0:42:06", "remaining_time": "22:03:15"}
+{"current_steps": 48, "total_steps": 1524, "loss": 0.5975, "lr": 3.1372549019607846e-06, "epoch": 0.09436435124508519, "percentage": 3.15, "elapsed_time": "0:43:00", "remaining_time": "22:02:24"}
+{"current_steps": 49, "total_steps": 1524, "loss": 0.5953, "lr": 3.2026143790849674e-06, "epoch": 0.0963302752293578, "percentage": 3.22, "elapsed_time": "0:43:54", "remaining_time": "22:01:33"}
+{"current_steps": 50, "total_steps": 1524, "loss": 0.6189, "lr": 3.2679738562091506e-06, "epoch": 0.0982961992136304, "percentage": 3.28, "elapsed_time": "0:44:48", "remaining_time": "22:00:43"}
+{"current_steps": 51, "total_steps": 1524, "loss": 0.5825, "lr": 3.3333333333333333e-06, "epoch": 0.10026212319790301, "percentage": 3.35, "elapsed_time": "0:45:41", "remaining_time": "21:59:51"}
+{"current_steps": 52, "total_steps": 1524, "loss": 0.5903, "lr": 3.398692810457517e-06, "epoch": 0.10222804718217562, "percentage": 3.41, "elapsed_time": "0:46:34", "remaining_time": "21:58:37"}
+{"current_steps": 53, "total_steps": 1524, "loss": 0.6104, "lr": 3.4640522875816997e-06, "epoch": 0.10419397116644823, "percentage": 3.48, "elapsed_time": "0:47:28", "remaining_time": "21:57:33"}
+{"current_steps": 54, "total_steps": 1524, "loss": 0.5808, "lr": 3.529411764705883e-06, "epoch": 0.10615989515072084, "percentage": 3.54, "elapsed_time": "0:48:21", "remaining_time": "21:56:20"}
+{"current_steps": 55, "total_steps": 1524, "loss": 0.5827, "lr": 3.5947712418300657e-06, "epoch": 0.10812581913499344, "percentage": 3.61, "elapsed_time": "0:49:14", "remaining_time": "21:55:10"}
+{"current_steps": 56, "total_steps": 1524, "loss": 0.5751, "lr": 3.6601307189542484e-06, "epoch": 0.11009174311926606, "percentage": 3.67, "elapsed_time": "0:50:07", "remaining_time": "21:54:00"}
+{"current_steps": 57, "total_steps": 1524, "loss": 0.5979, "lr": 3.7254901960784316e-06, "epoch": 0.11205766710353866, "percentage": 3.74, "elapsed_time": "0:51:01", "remaining_time": "21:53:19"}
+{"current_steps": 58, "total_steps": 1524, "loss": 0.5718, "lr": 3.7908496732026144e-06, "epoch": 0.11402359108781127, "percentage": 3.81, "elapsed_time": "0:51:55", "remaining_time": "21:52:38"}
+{"current_steps": 59, "total_steps": 1524, "loss": 0.5671, "lr": 3.856209150326798e-06, "epoch": 0.11598951507208388, "percentage": 3.87, "elapsed_time": "0:52:50", "remaining_time": "21:51:54"}
+{"current_steps": 60, "total_steps": 1524, "loss": 0.5621, "lr": 3.92156862745098e-06, "epoch": 0.11795543905635648, "percentage": 3.94, "elapsed_time": "0:53:43", "remaining_time": "21:51:05"}
+{"current_steps": 61, "total_steps": 1524, "loss": 0.5881, "lr": 3.986928104575164e-06, "epoch": 0.1199213630406291, "percentage": 4.0, "elapsed_time": "0:54:38", "remaining_time": "21:50:18"}
+{"current_steps": 62, "total_steps": 1524, "loss": 0.5599, "lr": 4.052287581699347e-06, "epoch": 0.1218872870249017, "percentage": 4.07, "elapsed_time": "0:55:31", "remaining_time": "21:49:10"}
+{"current_steps": 63, "total_steps": 1524, "loss": 0.5593, "lr": 4.11764705882353e-06, "epoch": 0.12385321100917432, "percentage": 4.13, "elapsed_time": "0:56:24", "remaining_time": "21:48:03"}
+{"current_steps": 64, "total_steps": 1524, "loss": 0.5632, "lr": 4.183006535947713e-06, "epoch": 0.1258191349934469, "percentage": 4.2, "elapsed_time": "0:57:17", "remaining_time": "21:46:54"}
+{"current_steps": 65, "total_steps": 1524, "loss": 0.6082, "lr": 4.2483660130718954e-06, "epoch": 0.12778505897771952, "percentage": 4.27, "elapsed_time": "0:58:10", "remaining_time": "21:45:48"}
+{"current_steps": 66, "total_steps": 1524, "loss": 0.5482, "lr": 4.313725490196079e-06, "epoch": 0.12975098296199214, "percentage": 4.33, "elapsed_time": "0:59:03", "remaining_time": "21:44:42"}
+{"current_steps": 67, "total_steps": 1524, "loss": 0.5675, "lr": 4.379084967320262e-06, "epoch": 0.13171690694626476, "percentage": 4.4, "elapsed_time": "0:59:56", "remaining_time": "21:43:36"}
+{"current_steps": 68, "total_steps": 1524, "loss": 0.5521, "lr": 4.444444444444444e-06, "epoch": 0.13368283093053734, "percentage": 4.46, "elapsed_time": "1:00:49", "remaining_time": "21:42:29"}
+{"current_steps": 69, "total_steps": 1524, "loss": 0.5765, "lr": 4.509803921568628e-06, "epoch": 0.13564875491480996, "percentage": 4.53, "elapsed_time": "1:01:42", "remaining_time": "21:41:23"}
+{"current_steps": 70, "total_steps": 1524, "loss": 0.5511, "lr": 4.5751633986928105e-06, "epoch": 0.13761467889908258, "percentage": 4.59, "elapsed_time": "1:02:35", "remaining_time": "21:40:17"}
+{"current_steps": 71, "total_steps": 1524, "loss": 0.5749, "lr": 4.640522875816994e-06, "epoch": 0.13958060288335516, "percentage": 4.66, "elapsed_time": "1:03:29", "remaining_time": "21:39:15"}
+{"current_steps": 72, "total_steps": 1524, "loss": 0.5296, "lr": 4.705882352941177e-06, "epoch": 0.14154652686762778, "percentage": 4.72, "elapsed_time": "1:04:23", "remaining_time": "21:38:27"}
+{"current_steps": 73, "total_steps": 1524, "loss": 0.6033, "lr": 4.77124183006536e-06, "epoch": 0.1435124508519004, "percentage": 4.79, "elapsed_time": "1:05:16", "remaining_time": "21:37:25"}
+{"current_steps": 74, "total_steps": 1524, "loss": 0.5632, "lr": 4.836601307189543e-06, "epoch": 0.145478374836173, "percentage": 4.86, "elapsed_time": "1:06:10", "remaining_time": "21:36:33"}
+{"current_steps": 75, "total_steps": 1524, "loss": 0.5605, "lr": 4.901960784313726e-06, "epoch": 0.1474442988204456, "percentage": 4.92, "elapsed_time": "1:07:03", "remaining_time": "21:35:30"}
+{"current_steps": 76, "total_steps": 1524, "loss": 0.5735, "lr": 4.967320261437909e-06, "epoch": 0.14941022280471822, "percentage": 4.99, "elapsed_time": "1:07:56", "remaining_time": "21:34:30"}
+{"current_steps": 77, "total_steps": 1524, "loss": 0.5742, "lr": 5.032679738562092e-06, "epoch": 0.15137614678899083, "percentage": 5.05, "elapsed_time": "1:08:49", "remaining_time": "21:33:30"}
+{"current_steps": 78, "total_steps": 1524, "loss": 0.5426, "lr": 5.098039215686274e-06, "epoch": 0.15334207077326342, "percentage": 5.12, "elapsed_time": "1:09:43", "remaining_time": "21:32:30"}
+{"current_steps": 79, "total_steps": 1524, "loss": 0.5499, "lr": 5.163398692810458e-06, "epoch": 0.15530799475753604, "percentage": 5.18, "elapsed_time": "1:10:36", "remaining_time": "21:31:30"}
+{"current_steps": 80, "total_steps": 1524, "loss": 0.547, "lr": 5.2287581699346416e-06, "epoch": 0.15727391874180865, "percentage": 5.25, "elapsed_time": "1:11:29", "remaining_time": "21:30:31"}
+{"current_steps": 81, "total_steps": 1524, "loss": 0.5517, "lr": 5.294117647058824e-06, "epoch": 0.15923984272608127, "percentage": 5.31, "elapsed_time": "1:12:22", "remaining_time": "21:29:27"}
+{"current_steps": 82, "total_steps": 1524, "loss": 0.5477, "lr": 5.359477124183007e-06, "epoch": 0.16120576671035386, "percentage": 5.38, "elapsed_time": "1:13:15", "remaining_time": "21:28:25"}
+{"current_steps": 83, "total_steps": 1524, "loss": 0.5667, "lr": 5.4248366013071894e-06, "epoch": 0.16317169069462648, "percentage": 5.45, "elapsed_time": "1:14:09", "remaining_time": "21:27:27"}
+{"current_steps": 84, "total_steps": 1524, "loss": 0.5612, "lr": 5.4901960784313735e-06, "epoch": 0.1651376146788991, "percentage": 5.51, "elapsed_time": "1:15:02", "remaining_time": "21:26:21"}
+{"current_steps": 85, "total_steps": 1524, "loss": 0.5855, "lr": 5.555555555555557e-06, "epoch": 0.16710353866317168, "percentage": 5.58, "elapsed_time": "1:15:55", "remaining_time": "21:25:15"}
+{"current_steps": 86, "total_steps": 1524, "loss": 0.5514, "lr": 5.620915032679739e-06, "epoch": 0.1690694626474443, "percentage": 5.64, "elapsed_time": "1:16:48", "remaining_time": "21:24:14"}
+{"current_steps": 87, "total_steps": 1524, "loss": 0.5377, "lr": 5.686274509803922e-06, "epoch": 0.1710353866317169, "percentage": 5.71, "elapsed_time": "1:17:41", "remaining_time": "21:23:14"}
+{"current_steps": 88, "total_steps": 1524, "loss": 0.5208, "lr": 5.7516339869281045e-06, "epoch": 0.17300131061598953, "percentage": 5.77, "elapsed_time": "1:18:34", "remaining_time": "21:22:19"}
+{"current_steps": 89, "total_steps": 1524, "loss": 0.5354, "lr": 5.816993464052289e-06, "epoch": 0.17496723460026212, "percentage": 5.84, "elapsed_time": "1:19:28", "remaining_time": "21:21:31"}
+{"current_steps": 90, "total_steps": 1524, "loss": 0.5328, "lr": 5.882352941176471e-06, "epoch": 0.17693315858453473, "percentage": 5.91, "elapsed_time": "1:20:23", "remaining_time": "21:20:48"}
+{"current_steps": 91, "total_steps": 1524, "loss": 0.5287, "lr": 5.947712418300654e-06, "epoch": 0.17889908256880735, "percentage": 5.97, "elapsed_time": "1:21:17", "remaining_time": "21:20:14"}
+{"current_steps": 92, "total_steps": 1524, "loss": 0.5582, "lr": 6.0130718954248365e-06, "epoch": 0.18086500655307994, "percentage": 6.04, "elapsed_time": "1:22:12", "remaining_time": "21:19:40"}
+{"current_steps": 93, "total_steps": 1524, "loss": 0.5666, "lr": 6.07843137254902e-06, "epoch": 0.18283093053735255, "percentage": 6.1, "elapsed_time": "1:23:06", "remaining_time": "21:18:52"}
+{"current_steps": 94, "total_steps": 1524, "loss": 0.5416, "lr": 6.143790849673204e-06, "epoch": 0.18479685452162517, "percentage": 6.17, "elapsed_time": "1:23:59", "remaining_time": "21:17:50"}
+{"current_steps": 95, "total_steps": 1524, "loss": 0.5213, "lr": 6.209150326797386e-06, "epoch": 0.18676277850589776, "percentage": 6.23, "elapsed_time": "1:24:53", "remaining_time": "21:16:49"}
+{"current_steps": 96, "total_steps": 1524, "loss": 0.5353, "lr": 6.274509803921569e-06, "epoch": 0.18872870249017037, "percentage": 6.3, "elapsed_time": "1:25:46", "remaining_time": "21:15:49"}
+{"current_steps": 97, "total_steps": 1524, "loss": 0.5232, "lr": 6.3398692810457515e-06, "epoch": 0.190694626474443, "percentage": 6.36, "elapsed_time": "1:26:39", "remaining_time": "21:14:50"}
+{"current_steps": 98, "total_steps": 1524, "loss": 0.5484, "lr": 6.405228758169935e-06, "epoch": 0.1926605504587156, "percentage": 6.43, "elapsed_time": "1:27:32", "remaining_time": "21:13:49"}
+{"current_steps": 99, "total_steps": 1524, "loss": 0.5255, "lr": 6.470588235294119e-06, "epoch": 0.1946264744429882, "percentage": 6.5, "elapsed_time": "1:28:25", "remaining_time": "21:12:49"}
+{"current_steps": 100, "total_steps": 1524, "loss": 0.5307, "lr": 6.535947712418301e-06, "epoch": 0.1965923984272608, "percentage": 6.56, "elapsed_time": "1:29:18", "remaining_time": "21:11:49"}
+{"current_steps": 101, "total_steps": 1524, "loss": 0.5319, "lr": 6.601307189542484e-06, "epoch": 0.19855832241153343, "percentage": 6.63, "elapsed_time": "1:30:56", "remaining_time": "21:21:13"}
+{"current_steps": 102, "total_steps": 1524, "loss": 0.5313, "lr": 6.666666666666667e-06, "epoch": 0.20052424639580602, "percentage": 6.69, "elapsed_time": "1:31:49", "remaining_time": "21:20:04"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf3472d8d3ebb65cc7fc552c6a4fe4ba03958a0b94ccc4e9d0a447839faa515
+size 7416