Training in progress, epoch 0

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d29d52699cbb89772524dd30c095a28a6bf5e36cf30cbcf5f95ffb92a2a974c
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac8a79f1cb898c9a0579c268a2e9be8aea2efd12de0471d02d242654303ec72
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507fa679593ce08913c770bdc5bd3f80b6f85939ba1eedadfb45dd7f9ac9497e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0252fff2a42f4681ef161edc04f222f5b70c10277a54cfee0a23ac1979a0da2f
+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 +1,88 @@
+{"current_steps": 1, "total_steps": 380, "loss": 1.0219, "lr": 2.105263157894737e-06, "epoch": 0.012997562956945572, "percentage": 0.26, "elapsed_time": "0:01:55", "remaining_time": "12:07:46"}
+{"current_steps": 2, "total_steps": 380, "loss": 1.0148, "lr": 4.210526315789474e-06, "epoch": 0.025995125913891144, "percentage": 0.53, "elapsed_time": "0:03:35", "remaining_time": "11:18:33"}
+{"current_steps": 3, "total_steps": 380, "loss": 0.9978, "lr": 6.31578947368421e-06, "epoch": 0.03899268887083672, "percentage": 0.79, "elapsed_time": "0:05:18", "remaining_time": "11:06:14"}
+{"current_steps": 4, "total_steps": 380, "loss": 0.9693, "lr": 8.421052631578948e-06, "epoch": 0.05199025182778229, "percentage": 1.05, "elapsed_time": "0:07:00", "remaining_time": "10:59:06"}
+{"current_steps": 5, "total_steps": 380, "loss": 0.932, "lr": 1.0526315789473684e-05, "epoch": 0.06498781478472786, "percentage": 1.32, "elapsed_time": "0:08:42", "remaining_time": "10:53:30"}
+{"current_steps": 6, "total_steps": 380, "loss": 0.9538, "lr": 1.263157894736842e-05, "epoch": 0.07798537774167344, "percentage": 1.58, "elapsed_time": "0:10:24", "remaining_time": "10:49:11"}
+{"current_steps": 7, "total_steps": 380, "loss": 0.9456, "lr": 1.4736842105263159e-05, "epoch": 0.09098294069861901, "percentage": 1.84, "elapsed_time": "0:12:07", "remaining_time": "10:45:39"}
+{"current_steps": 8, "total_steps": 380, "loss": 0.9347, "lr": 1.6842105263157896e-05, "epoch": 0.10398050365556458, "percentage": 2.11, "elapsed_time": "0:13:48", "remaining_time": "10:42:08"}
+{"current_steps": 9, "total_steps": 380, "loss": 0.9102, "lr": 1.894736842105263e-05, "epoch": 0.11697806661251016, "percentage": 2.37, "elapsed_time": "0:15:32", "remaining_time": "10:40:31"}
+{"current_steps": 10, "total_steps": 380, "loss": 0.8668, "lr": 2.105263157894737e-05, "epoch": 0.12997562956945571, "percentage": 2.63, "elapsed_time": "0:17:13", "remaining_time": "10:37:30"}
+{"current_steps": 11, "total_steps": 380, "loss": 0.829, "lr": 2.3157894736842107e-05, "epoch": 0.1429731925264013, "percentage": 2.89, "elapsed_time": "0:18:57", "remaining_time": "10:35:56"}
+{"current_steps": 12, "total_steps": 380, "loss": 0.8096, "lr": 2.526315789473684e-05, "epoch": 0.15597075548334688, "percentage": 3.16, "elapsed_time": "0:20:38", "remaining_time": "10:33:07"}
+{"current_steps": 13, "total_steps": 380, "loss": 0.7878, "lr": 2.7368421052631583e-05, "epoch": 0.16896831844029245, "percentage": 3.42, "elapsed_time": "0:22:20", "remaining_time": "10:30:30"}
+{"current_steps": 14, "total_steps": 380, "loss": 0.7802, "lr": 2.9473684210526317e-05, "epoch": 0.18196588139723802, "percentage": 3.68, "elapsed_time": "0:24:00", "remaining_time": "10:27:47"}
+{"current_steps": 15, "total_steps": 380, "loss": 0.7771, "lr": 3.157894736842106e-05, "epoch": 0.19496344435418358, "percentage": 3.95, "elapsed_time": "0:25:43", "remaining_time": "10:25:53"}
+{"current_steps": 16, "total_steps": 380, "loss": 0.7706, "lr": 3.368421052631579e-05, "epoch": 0.20796100731112915, "percentage": 4.21, "elapsed_time": "0:27:23", "remaining_time": "10:23:14"}
+{"current_steps": 17, "total_steps": 380, "loss": 0.7457, "lr": 3.578947368421053e-05, "epoch": 0.22095857026807472, "percentage": 4.47, "elapsed_time": "0:29:04", "remaining_time": "10:20:56"}
+{"current_steps": 18, "total_steps": 380, "loss": 0.7417, "lr": 3.789473684210526e-05, "epoch": 0.23395613322502032, "percentage": 4.74, "elapsed_time": "0:30:46", "remaining_time": "10:18:58"}
+{"current_steps": 19, "total_steps": 380, "loss": 0.7314, "lr": 4e-05, "epoch": 0.2469536961819659, "percentage": 5.0, "elapsed_time": "0:32:28", "remaining_time": "10:16:54"}
+{"current_steps": 20, "total_steps": 380, "loss": 0.7411, "lr": 4.210526315789474e-05, "epoch": 0.25995125913891143, "percentage": 5.26, "elapsed_time": "0:34:10", "remaining_time": "10:15:02"}
+{"current_steps": 21, "total_steps": 380, "loss": 0.7289, "lr": 4.421052631578948e-05, "epoch": 0.272948822095857, "percentage": 5.53, "elapsed_time": "0:35:52", "remaining_time": "10:13:14"}
+{"current_steps": 22, "total_steps": 380, "loss": 0.7153, "lr": 4.6315789473684214e-05, "epoch": 0.2859463850528026, "percentage": 5.79, "elapsed_time": "0:37:33", "remaining_time": "10:11:11"}
+{"current_steps": 23, "total_steps": 380, "loss": 0.7235, "lr": 4.842105263157895e-05, "epoch": 0.29894394800974816, "percentage": 6.05, "elapsed_time": "0:39:18", "remaining_time": "10:10:07"}
+{"current_steps": 24, "total_steps": 380, "loss": 0.7169, "lr": 5.052631578947368e-05, "epoch": 0.31194151096669376, "percentage": 6.32, "elapsed_time": "0:41:01", "remaining_time": "10:08:25"}
+{"current_steps": 25, "total_steps": 380, "loss": 0.7193, "lr": 5.263157894736843e-05, "epoch": 0.3249390739236393, "percentage": 6.58, "elapsed_time": "0:42:44", "remaining_time": "10:06:50"}
+{"current_steps": 26, "total_steps": 380, "loss": 0.6987, "lr": 5.4736842105263165e-05, "epoch": 0.3379366368805849, "percentage": 6.84, "elapsed_time": "0:44:26", "remaining_time": "10:04:58"}
+{"current_steps": 27, "total_steps": 380, "loss": 0.7044, "lr": 5.68421052631579e-05, "epoch": 0.35093419983753044, "percentage": 7.11, "elapsed_time": "0:46:09", "remaining_time": "10:03:33"}
+{"current_steps": 28, "total_steps": 380, "loss": 0.6979, "lr": 5.8947368421052634e-05, "epoch": 0.36393176279447603, "percentage": 7.37, "elapsed_time": "0:47:50", "remaining_time": "10:01:31"}
+{"current_steps": 29, "total_steps": 380, "loss": 0.6893, "lr": 6.105263157894738e-05, "epoch": 0.37692932575142163, "percentage": 7.63, "elapsed_time": "0:49:31", "remaining_time": "9:59:30"}
+{"current_steps": 30, "total_steps": 380, "loss": 0.6827, "lr": 6.315789473684212e-05, "epoch": 0.38992688870836717, "percentage": 7.89, "elapsed_time": "0:51:14", "remaining_time": "9:57:43"}
+{"current_steps": 31, "total_steps": 380, "loss": 0.6835, "lr": 6.526315789473685e-05, "epoch": 0.40292445166531277, "percentage": 8.16, "elapsed_time": "0:52:55", "remaining_time": "9:55:49"}
+{"current_steps": 32, "total_steps": 380, "loss": 0.6888, "lr": 6.736842105263159e-05, "epoch": 0.4159220146222583, "percentage": 8.42, "elapsed_time": "0:54:36", "remaining_time": "9:53:55"}
+{"current_steps": 33, "total_steps": 380, "loss": 0.6861, "lr": 6.947368421052632e-05, "epoch": 0.4289195775792039, "percentage": 8.68, "elapsed_time": "0:56:17", "remaining_time": "9:51:57"}
+{"current_steps": 34, "total_steps": 380, "loss": 0.6832, "lr": 7.157894736842105e-05, "epoch": 0.44191714053614944, "percentage": 8.95, "elapsed_time": "0:58:01", "remaining_time": "9:50:29"}
+{"current_steps": 35, "total_steps": 380, "loss": 0.6859, "lr": 7.368421052631579e-05, "epoch": 0.45491470349309504, "percentage": 9.21, "elapsed_time": "0:59:42", "remaining_time": "9:48:29"}
+{"current_steps": 36, "total_steps": 380, "loss": 0.6702, "lr": 7.578947368421052e-05, "epoch": 0.46791226645004064, "percentage": 9.47, "elapsed_time": "1:01:23", "remaining_time": "9:46:35"}
+{"current_steps": 37, "total_steps": 380, "loss": 0.671, "lr": 7.789473684210527e-05, "epoch": 0.4809098294069862, "percentage": 9.74, "elapsed_time": "1:03:03", "remaining_time": "9:44:35"}
+{"current_steps": 38, "total_steps": 380, "loss": 0.6665, "lr": 8e-05, "epoch": 0.4939073923639318, "percentage": 10.0, "elapsed_time": "1:04:44", "remaining_time": "9:42:38"}
+{"current_steps": 39, "total_steps": 380, "loss": 0.6727, "lr": 7.99983123807325e-05, "epoch": 0.5069049553208773, "percentage": 10.26, "elapsed_time": "1:06:27", "remaining_time": "9:41:08"}
+{"current_steps": 40, "total_steps": 380, "loss": 0.669, "lr": 7.999324966533291e-05, "epoch": 0.5199025182778229, "percentage": 10.53, "elapsed_time": "1:08:08", "remaining_time": "9:39:14"}
+{"current_steps": 41, "total_steps": 380, "loss": 0.661, "lr": 7.998481228099806e-05, "epoch": 0.5329000812347685, "percentage": 10.79, "elapsed_time": "1:09:52", "remaining_time": "9:37:44"}
+{"current_steps": 42, "total_steps": 380, "loss": 0.6726, "lr": 7.997300093968255e-05, "epoch": 0.545897644191714, "percentage": 11.05, "elapsed_time": "1:11:34", "remaining_time": "9:36:00"}
+{"current_steps": 43, "total_steps": 380, "loss": 0.6677, "lr": 7.995781663803876e-05, "epoch": 0.5588952071486596, "percentage": 11.32, "elapsed_time": "1:13:15", "remaining_time": "9:34:10"}
+{"current_steps": 44, "total_steps": 380, "loss": 0.668, "lr": 7.993926065733265e-05, "epoch": 0.5718927701056052, "percentage": 11.58, "elapsed_time": "1:14:57", "remaining_time": "9:32:21"}
+{"current_steps": 45, "total_steps": 380, "loss": 0.6664, "lr": 7.991733456333579e-05, "epoch": 0.5848903330625508, "percentage": 11.84, "elapsed_time": "1:16:39", "remaining_time": "9:30:42"}
+{"current_steps": 46, "total_steps": 380, "loss": 0.6491, "lr": 7.98920402061931e-05, "epoch": 0.5978878960194963, "percentage": 12.11, "elapsed_time": "1:18:21", "remaining_time": "9:28:57"}
+{"current_steps": 47, "total_steps": 380, "loss": 0.6628, "lr": 7.98633797202668e-05, "epoch": 0.6108854589764419, "percentage": 12.37, "elapsed_time": "1:20:03", "remaining_time": "9:27:15"}
+{"current_steps": 48, "total_steps": 380, "loss": 0.6542, "lr": 7.98313555239563e-05, "epoch": 0.6238830219333875, "percentage": 12.63, "elapsed_time": "1:21:45", "remaining_time": "9:25:30"}
+{"current_steps": 49, "total_steps": 380, "loss": 0.6624, "lr": 7.979597031949415e-05, "epoch": 0.6368805848903331, "percentage": 12.89, "elapsed_time": "1:23:26", "remaining_time": "9:23:41"}
+{"current_steps": 50, "total_steps": 380, "loss": 0.646, "lr": 7.975722709271799e-05, "epoch": 0.6498781478472786, "percentage": 13.16, "elapsed_time": "1:25:09", "remaining_time": "9:22:00"}
+{"current_steps": 51, "total_steps": 380, "loss": 0.648, "lr": 7.97151291128186e-05, "epoch": 0.6628757108042242, "percentage": 13.42, "elapsed_time": "1:26:50", "remaining_time": "9:20:12"}
+{"current_steps": 52, "total_steps": 380, "loss": 0.6423, "lr": 7.96696799320641e-05, "epoch": 0.6758732737611698, "percentage": 13.68, "elapsed_time": "1:28:32", "remaining_time": "9:18:28"}
+{"current_steps": 53, "total_steps": 380, "loss": 0.6414, "lr": 7.962088338550013e-05, "epoch": 0.6888708367181153, "percentage": 13.95, "elapsed_time": "1:30:13", "remaining_time": "9:16:42"}
+{"current_steps": 54, "total_steps": 380, "loss": 0.6429, "lr": 7.956874359062632e-05, "epoch": 0.7018683996750609, "percentage": 14.21, "elapsed_time": "1:31:55", "remaining_time": "9:14:58"}
+{"current_steps": 55, "total_steps": 380, "loss": 0.6321, "lr": 7.951326494704878e-05, "epoch": 0.7148659626320065, "percentage": 14.47, "elapsed_time": "1:33:38", "remaining_time": "9:13:17"}
+{"current_steps": 56, "total_steps": 380, "loss": 0.638, "lr": 7.94544521361089e-05, "epoch": 0.7278635255889521, "percentage": 14.74, "elapsed_time": "1:35:19", "remaining_time": "9:11:31"}
+{"current_steps": 57, "total_steps": 380, "loss": 0.6394, "lr": 7.939231012048833e-05, "epoch": 0.7408610885458976, "percentage": 15.0, "elapsed_time": "1:37:03", "remaining_time": "9:09:57"}
+{"current_steps": 58, "total_steps": 380, "loss": 0.6368, "lr": 7.932684414379021e-05, "epoch": 0.7538586515028433, "percentage": 15.26, "elapsed_time": "1:38:44", "remaining_time": "9:08:12"}
+{"current_steps": 59, "total_steps": 380, "loss": 0.6325, "lr": 7.925805973009672e-05, "epoch": 0.7668562144597888, "percentage": 15.53, "elapsed_time": "1:40:25", "remaining_time": "9:06:21"}
+{"current_steps": 60, "total_steps": 380, "loss": 0.6461, "lr": 7.918596268350296e-05, "epoch": 0.7798537774167343, "percentage": 15.79, "elapsed_time": "1:42:05", "remaining_time": "9:04:30"}
+{"current_steps": 61, "total_steps": 380, "loss": 0.6439, "lr": 7.911055908762718e-05, "epoch": 0.7928513403736799, "percentage": 16.05, "elapsed_time": "1:43:46", "remaining_time": "9:02:39"}
+{"current_steps": 62, "total_steps": 380, "loss": 0.6278, "lr": 7.903185530509743e-05, "epoch": 0.8058489033306255, "percentage": 16.32, "elapsed_time": "1:45:29", "remaining_time": "9:01:05"}
+{"current_steps": 63, "total_steps": 380, "loss": 0.6383, "lr": 7.894985797701472e-05, "epoch": 0.8188464662875711, "percentage": 16.58, "elapsed_time": "1:47:10", "remaining_time": "8:59:18"}
+{"current_steps": 64, "total_steps": 380, "loss": 0.6239, "lr": 7.886457402239256e-05, "epoch": 0.8318440292445166, "percentage": 16.84, "elapsed_time": "1:48:55", "remaining_time": "8:57:48"}
+{"current_steps": 65, "total_steps": 380, "loss": 0.6306, "lr": 7.877601063757323e-05, "epoch": 0.8448415922014623, "percentage": 17.11, "elapsed_time": "1:50:35", "remaining_time": "8:55:58"}
+{"current_steps": 66, "total_steps": 380, "loss": 0.6194, "lr": 7.868417529562043e-05, "epoch": 0.8578391551584078, "percentage": 17.37, "elapsed_time": "1:52:17", "remaining_time": "8:54:12"}
+{"current_steps": 67, "total_steps": 380, "loss": 0.6267, "lr": 7.858907574568882e-05, "epoch": 0.8708367181153533, "percentage": 17.63, "elapsed_time": "1:53:57", "remaining_time": "8:52:22"}
+{"current_steps": 68, "total_steps": 380, "loss": 0.622, "lr": 7.849072001237001e-05, "epoch": 0.8838342810722989, "percentage": 17.89, "elapsed_time": "1:55:38", "remaining_time": "8:50:35"}
+{"current_steps": 69, "total_steps": 380, "loss": 0.6175, "lr": 7.838911639501557e-05, "epoch": 0.8968318440292445, "percentage": 18.16, "elapsed_time": "1:57:19", "remaining_time": "8:48:47"}
+{"current_steps": 70, "total_steps": 380, "loss": 0.615, "lr": 7.828427346703657e-05, "epoch": 0.9098294069861901, "percentage": 18.42, "elapsed_time": "1:58:59", "remaining_time": "8:46:59"}
+{"current_steps": 71, "total_steps": 380, "loss": 0.6196, "lr": 7.81762000751803e-05, "epoch": 0.9228269699431356, "percentage": 18.68, "elapsed_time": "2:00:41", "remaining_time": "8:45:17"}
+{"current_steps": 72, "total_steps": 380, "loss": 0.6201, "lr": 7.806490533878368e-05, "epoch": 0.9358245329000813, "percentage": 18.95, "elapsed_time": "2:02:22", "remaining_time": "8:43:28"}
+{"current_steps": 73, "total_steps": 380, "loss": 0.6152, "lr": 7.795039864900378e-05, "epoch": 0.9488220958570268, "percentage": 19.21, "elapsed_time": "2:04:02", "remaining_time": "8:41:41"}
+{"current_steps": 74, "total_steps": 380, "loss": 0.6282, "lr": 7.783268966802539e-05, "epoch": 0.9618196588139724, "percentage": 19.47, "elapsed_time": "2:05:43", "remaining_time": "8:39:51"}
+{"current_steps": 75, "total_steps": 380, "loss": 0.6124, "lr": 7.771178832824573e-05, "epoch": 0.974817221770918, "percentage": 19.74, "elapsed_time": "2:07:23", "remaining_time": "8:38:03"}
+{"current_steps": 76, "total_steps": 380, "loss": 0.614, "lr": 7.758770483143634e-05, "epoch": 0.9878147847278635, "percentage": 20.0, "elapsed_time": "2:09:05", "remaining_time": "8:36:20"}
+{"current_steps": 77, "total_steps": 380, "loss": 0.6145, "lr": 7.74604496478822e-05, "epoch": 1.0024370430544274, "percentage": 20.26, "elapsed_time": "2:12:38", "remaining_time": "8:41:58"}
+{"current_steps": 78, "total_steps": 380, "loss": 0.5866, "lr": 7.733003351549829e-05, "epoch": 1.0154346060113728, "percentage": 20.53, "elapsed_time": "2:14:20", "remaining_time": "8:40:08"}
+{"current_steps": 79, "total_steps": 380, "loss": 0.591, "lr": 7.719646743892352e-05, "epoch": 1.0284321689683185, "percentage": 20.79, "elapsed_time": "2:16:02", "remaining_time": "8:38:18"}
+{"current_steps": 80, "total_steps": 380, "loss": 0.5936, "lr": 7.705976268859207e-05, "epoch": 1.0414297319252641, "percentage": 21.05, "elapsed_time": "2:17:44", "remaining_time": "8:36:30"}
+{"current_steps": 81, "total_steps": 380, "loss": 0.5838, "lr": 7.691993079978252e-05, "epoch": 1.0544272948822095, "percentage": 21.32, "elapsed_time": "2:19:27", "remaining_time": "8:34:49"}
+{"current_steps": 82, "total_steps": 380, "loss": 0.586, "lr": 7.677698357164431e-05, "epoch": 1.0674248578391552, "percentage": 21.58, "elapsed_time": "2:21:09", "remaining_time": "8:32:58"}
+{"current_steps": 83, "total_steps": 380, "loss": 0.6045, "lr": 7.663093306620231e-05, "epoch": 1.0804224207961006, "percentage": 21.84, "elapsed_time": "2:22:51", "remaining_time": "8:31:11"}
+{"current_steps": 84, "total_steps": 380, "loss": 0.5814, "lr": 7.648179160733883e-05, "epoch": 1.0934199837530463, "percentage": 22.11, "elapsed_time": "2:24:31", "remaining_time": "8:29:18"}
+{"current_steps": 85, "total_steps": 380, "loss": 0.5946, "lr": 7.632957177975387e-05, "epoch": 1.106417546709992, "percentage": 22.37, "elapsed_time": "2:26:13", "remaining_time": "8:27:30"}
+{"current_steps": 86, "total_steps": 380, "loss": 0.5923, "lr": 7.61742864279031e-05, "epoch": 1.1194151096669374, "percentage": 22.63, "elapsed_time": "2:27:54", "remaining_time": "8:25:37"}
+{"current_steps": 87, "total_steps": 380, "loss": 0.5803, "lr": 7.601594865491414e-05, "epoch": 1.132412672623883, "percentage": 22.89, "elapsed_time": "2:29:35", "remaining_time": "8:23:48"}
+{"current_steps": 88, "total_steps": 380, "loss": 0.5838, "lr": 7.585457182148081e-05, "epoch": 1.1454102355808287, "percentage": 23.16, "elapsed_time": "2:31:19", "remaining_time": "8:22:06"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a585bf84338e80074d3429c0236ff06299b5e6f1717f412aa97d88007a997a0a
+size 7352