Training in progress, epoch 1

.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 sha256:568ef7ee54b270ad6308cb740e0f35c773fd8863577094be17577bb6c99957c6
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3bd1365b4779d85af0acfae8355c7f3483afed0b4c7aa2df6d37c0cf4fa944
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf1ada06884b68600bdb0b17017890ebb48cb808ed26a0c74d06f55f4c486e6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f28b82315e7a2f8425de8d131fd4d1a3b5b4940c6ab540e43d5a315543997440
+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 +1,87 @@
+{"current_steps": 1, "total_steps": 567, "loss": 0.6743, "lr": 3.5087719298245616e-07, "epoch": 0.012345679012345678, "percentage": 0.18, "elapsed_time": "0:00:47", "remaining_time": "7:27:13"}
+{"current_steps": 2, "total_steps": 567, "loss": 0.576, "lr": 7.017543859649123e-07, "epoch": 0.024691358024691357, "percentage": 0.35, "elapsed_time": "0:01:16", "remaining_time": "6:01:25"}
+{"current_steps": 3, "total_steps": 567, "loss": 0.6663, "lr": 1.0526315789473685e-06, "epoch": 0.037037037037037035, "percentage": 0.53, "elapsed_time": "0:01:46", "remaining_time": "5:32:49"}
+{"current_steps": 4, "total_steps": 567, "loss": 0.5696, "lr": 1.4035087719298246e-06, "epoch": 0.04938271604938271, "percentage": 0.71, "elapsed_time": "0:02:15", "remaining_time": "5:18:51"}
+{"current_steps": 5, "total_steps": 567, "loss": 0.5746, "lr": 1.7543859649122807e-06, "epoch": 0.06172839506172839, "percentage": 0.88, "elapsed_time": "0:02:40", "remaining_time": "5:00:29"}
+{"current_steps": 6, "total_steps": 567, "loss": 0.5319, "lr": 2.105263157894737e-06, "epoch": 0.07407407407407407, "percentage": 1.06, "elapsed_time": "0:03:08", "remaining_time": "4:53:57"}
+{"current_steps": 7, "total_steps": 567, "loss": 0.4894, "lr": 2.456140350877193e-06, "epoch": 0.08641975308641975, "percentage": 1.23, "elapsed_time": "0:03:29", "remaining_time": "4:39:25"}
+{"current_steps": 8, "total_steps": 567, "loss": 0.517, "lr": 2.8070175438596493e-06, "epoch": 0.09876543209876543, "percentage": 1.41, "elapsed_time": "0:03:56", "remaining_time": "4:35:43"}
+{"current_steps": 9, "total_steps": 567, "loss": 0.4509, "lr": 3.157894736842105e-06, "epoch": 0.1111111111111111, "percentage": 1.59, "elapsed_time": "0:04:23", "remaining_time": "4:32:47"}
+{"current_steps": 10, "total_steps": 567, "loss": 0.4467, "lr": 3.5087719298245615e-06, "epoch": 0.12345679012345678, "percentage": 1.76, "elapsed_time": "0:04:47", "remaining_time": "4:27:10"}
+{"current_steps": 11, "total_steps": 567, "loss": 0.4118, "lr": 3.859649122807018e-06, "epoch": 0.13580246913580246, "percentage": 1.94, "elapsed_time": "0:05:13", "remaining_time": "4:23:59"}
+{"current_steps": 12, "total_steps": 567, "loss": 0.3888, "lr": 4.210526315789474e-06, "epoch": 0.14814814814814814, "percentage": 2.12, "elapsed_time": "0:05:38", "remaining_time": "4:20:37"}
+{"current_steps": 13, "total_steps": 567, "loss": 0.4058, "lr": 4.56140350877193e-06, "epoch": 0.16049382716049382, "percentage": 2.29, "elapsed_time": "0:06:02", "remaining_time": "4:17:08"}
+{"current_steps": 14, "total_steps": 567, "loss": 0.3741, "lr": 4.912280701754386e-06, "epoch": 0.1728395061728395, "percentage": 2.47, "elapsed_time": "0:06:27", "remaining_time": "4:15:23"}
+{"current_steps": 15, "total_steps": 567, "loss": 0.3995, "lr": 5.263157894736842e-06, "epoch": 0.18518518518518517, "percentage": 2.65, "elapsed_time": "0:06:49", "remaining_time": "4:11:06"}
+{"current_steps": 16, "total_steps": 567, "loss": 0.385, "lr": 5.6140350877192985e-06, "epoch": 0.19753086419753085, "percentage": 2.82, "elapsed_time": "0:07:12", "remaining_time": "4:08:11"}
+{"current_steps": 17, "total_steps": 567, "loss": 0.36, "lr": 5.964912280701755e-06, "epoch": 0.20987654320987653, "percentage": 3.0, "elapsed_time": "0:07:39", "remaining_time": "4:07:37"}
+{"current_steps": 18, "total_steps": 567, "loss": 0.3499, "lr": 6.31578947368421e-06, "epoch": 0.2222222222222222, "percentage": 3.17, "elapsed_time": "0:08:04", "remaining_time": "4:06:31"}
+{"current_steps": 19, "total_steps": 567, "loss": 0.3513, "lr": 6.666666666666667e-06, "epoch": 0.2345679012345679, "percentage": 3.35, "elapsed_time": "0:08:30", "remaining_time": "4:05:35"}
+{"current_steps": 20, "total_steps": 567, "loss": 0.3412, "lr": 7.017543859649123e-06, "epoch": 0.24691358024691357, "percentage": 3.53, "elapsed_time": "0:09:00", "remaining_time": "4:06:16"}
+{"current_steps": 21, "total_steps": 567, "loss": 0.3298, "lr": 7.368421052631579e-06, "epoch": 0.25925925925925924, "percentage": 3.7, "elapsed_time": "0:09:29", "remaining_time": "4:06:37"}
+{"current_steps": 22, "total_steps": 567, "loss": 0.3365, "lr": 7.719298245614036e-06, "epoch": 0.2716049382716049, "percentage": 3.88, "elapsed_time": "0:09:53", "remaining_time": "4:05:12"}
+{"current_steps": 23, "total_steps": 567, "loss": 0.3025, "lr": 8.070175438596492e-06, "epoch": 0.2839506172839506, "percentage": 4.06, "elapsed_time": "0:10:18", "remaining_time": "4:03:54"}
+{"current_steps": 24, "total_steps": 567, "loss": 0.2703, "lr": 8.421052631578948e-06, "epoch": 0.2962962962962963, "percentage": 4.23, "elapsed_time": "0:10:48", "remaining_time": "4:04:21"}
+{"current_steps": 25, "total_steps": 567, "loss": 0.2939, "lr": 8.771929824561405e-06, "epoch": 0.30864197530864196, "percentage": 4.41, "elapsed_time": "0:11:18", "remaining_time": "4:05:00"}
+{"current_steps": 26, "total_steps": 567, "loss": 0.304, "lr": 9.12280701754386e-06, "epoch": 0.32098765432098764, "percentage": 4.59, "elapsed_time": "0:11:41", "remaining_time": "4:03:20"}
+{"current_steps": 27, "total_steps": 567, "loss": 0.3092, "lr": 9.473684210526315e-06, "epoch": 0.3333333333333333, "percentage": 4.76, "elapsed_time": "0:12:11", "remaining_time": "4:03:50"}
+{"current_steps": 28, "total_steps": 567, "loss": 0.2732, "lr": 9.824561403508772e-06, "epoch": 0.345679012345679, "percentage": 4.94, "elapsed_time": "0:12:36", "remaining_time": "4:02:48"}
+{"current_steps": 29, "total_steps": 567, "loss": 0.2745, "lr": 1.017543859649123e-05, "epoch": 0.35802469135802467, "percentage": 5.11, "elapsed_time": "0:13:04", "remaining_time": "4:02:32"}
+{"current_steps": 30, "total_steps": 567, "loss": 0.2824, "lr": 1.0526315789473684e-05, "epoch": 0.37037037037037035, "percentage": 5.29, "elapsed_time": "0:13:27", "remaining_time": "4:00:50"}
+{"current_steps": 31, "total_steps": 567, "loss": 0.2796, "lr": 1.0877192982456142e-05, "epoch": 0.38271604938271603, "percentage": 5.47, "elapsed_time": "0:13:51", "remaining_time": "3:59:41"}
+{"current_steps": 32, "total_steps": 567, "loss": 0.2413, "lr": 1.1228070175438597e-05, "epoch": 0.3950617283950617, "percentage": 5.64, "elapsed_time": "0:14:16", "remaining_time": "3:58:38"}
+{"current_steps": 33, "total_steps": 567, "loss": 0.2654, "lr": 1.1578947368421053e-05, "epoch": 0.4074074074074074, "percentage": 5.82, "elapsed_time": "0:14:45", "remaining_time": "3:58:51"}
+{"current_steps": 34, "total_steps": 567, "loss": 0.2604, "lr": 1.192982456140351e-05, "epoch": 0.41975308641975306, "percentage": 6.0, "elapsed_time": "0:15:05", "remaining_time": "3:56:29"}
+{"current_steps": 35, "total_steps": 567, "loss": 0.2374, "lr": 1.2280701754385966e-05, "epoch": 0.43209876543209874, "percentage": 6.17, "elapsed_time": "0:15:28", "remaining_time": "3:55:19"}
+{"current_steps": 36, "total_steps": 567, "loss": 0.2599, "lr": 1.263157894736842e-05, "epoch": 0.4444444444444444, "percentage": 6.35, "elapsed_time": "0:15:53", "remaining_time": "3:54:25"}
+{"current_steps": 37, "total_steps": 567, "loss": 0.2336, "lr": 1.2982456140350879e-05, "epoch": 0.4567901234567901, "percentage": 6.53, "elapsed_time": "0:16:20", "remaining_time": "3:54:05"}
+{"current_steps": 38, "total_steps": 567, "loss": 0.1984, "lr": 1.3333333333333333e-05, "epoch": 0.4691358024691358, "percentage": 6.7, "elapsed_time": "0:16:47", "remaining_time": "3:53:51"}
+{"current_steps": 39, "total_steps": 567, "loss": 0.2257, "lr": 1.3684210526315791e-05, "epoch": 0.48148148148148145, "percentage": 6.88, "elapsed_time": "0:17:10", "remaining_time": "3:52:30"}
+{"current_steps": 40, "total_steps": 567, "loss": 0.2203, "lr": 1.4035087719298246e-05, "epoch": 0.49382716049382713, "percentage": 7.05, "elapsed_time": "0:17:37", "remaining_time": "3:52:16"}
+{"current_steps": 41, "total_steps": 567, "loss": 0.2033, "lr": 1.4385964912280704e-05, "epoch": 0.5061728395061729, "percentage": 7.23, "elapsed_time": "0:18:03", "remaining_time": "3:51:42"}
+{"current_steps": 42, "total_steps": 567, "loss": 0.2035, "lr": 1.4736842105263159e-05, "epoch": 0.5185185185185185, "percentage": 7.41, "elapsed_time": "0:18:30", "remaining_time": "3:51:17"}
+{"current_steps": 43, "total_steps": 567, "loss": 0.2067, "lr": 1.5087719298245615e-05, "epoch": 0.5308641975308642, "percentage": 7.58, "elapsed_time": "0:18:58", "remaining_time": "3:51:12"}
+{"current_steps": 44, "total_steps": 567, "loss": 0.1619, "lr": 1.543859649122807e-05, "epoch": 0.5432098765432098, "percentage": 7.76, "elapsed_time": "0:19:27", "remaining_time": "3:51:15"}
+{"current_steps": 45, "total_steps": 567, "loss": 0.1763, "lr": 1.578947368421053e-05, "epoch": 0.5555555555555556, "percentage": 7.94, "elapsed_time": "0:19:54", "remaining_time": "3:50:59"}
+{"current_steps": 46, "total_steps": 567, "loss": 0.1777, "lr": 1.6140350877192984e-05, "epoch": 0.5679012345679012, "percentage": 8.11, "elapsed_time": "0:20:19", "remaining_time": "3:50:11"}
+{"current_steps": 47, "total_steps": 567, "loss": 0.1533, "lr": 1.649122807017544e-05, "epoch": 0.5802469135802469, "percentage": 8.29, "elapsed_time": "0:20:46", "remaining_time": "3:49:49"}
+{"current_steps": 48, "total_steps": 567, "loss": 0.1471, "lr": 1.6842105263157896e-05, "epoch": 0.5925925925925926, "percentage": 8.47, "elapsed_time": "0:21:11", "remaining_time": "3:49:10"}
+{"current_steps": 49, "total_steps": 567, "loss": 0.1661, "lr": 1.719298245614035e-05, "epoch": 0.6049382716049383, "percentage": 8.64, "elapsed_time": "0:21:42", "remaining_time": "3:49:33"}
+{"current_steps": 50, "total_steps": 567, "loss": 0.1544, "lr": 1.754385964912281e-05, "epoch": 0.6172839506172839, "percentage": 8.82, "elapsed_time": "0:22:08", "remaining_time": "3:48:58"}
+{"current_steps": 51, "total_steps": 567, "loss": 0.1517, "lr": 1.7894736842105264e-05, "epoch": 0.6296296296296297, "percentage": 8.99, "elapsed_time": "0:22:32", "remaining_time": "3:48:07"}
+{"current_steps": 52, "total_steps": 567, "loss": 0.1436, "lr": 1.824561403508772e-05, "epoch": 0.6419753086419753, "percentage": 9.17, "elapsed_time": "0:22:58", "remaining_time": "3:47:37"}
+{"current_steps": 53, "total_steps": 567, "loss": 0.1504, "lr": 1.8596491228070176e-05, "epoch": 0.654320987654321, "percentage": 9.35, "elapsed_time": "0:23:22", "remaining_time": "3:46:41"}
+{"current_steps": 54, "total_steps": 567, "loss": 0.1323, "lr": 1.894736842105263e-05, "epoch": 0.6666666666666666, "percentage": 9.52, "elapsed_time": "0:23:51", "remaining_time": "3:46:43"}
+{"current_steps": 55, "total_steps": 567, "loss": 0.1584, "lr": 1.929824561403509e-05, "epoch": 0.6790123456790124, "percentage": 9.7, "elapsed_time": "0:24:17", "remaining_time": "3:46:05"}
+{"current_steps": 56, "total_steps": 567, "loss": 0.1226, "lr": 1.9649122807017544e-05, "epoch": 0.691358024691358, "percentage": 9.88, "elapsed_time": "0:24:44", "remaining_time": "3:45:47"}
+{"current_steps": 57, "total_steps": 567, "loss": 0.1107, "lr": 2e-05, "epoch": 0.7037037037037037, "percentage": 10.05, "elapsed_time": "0:25:11", "remaining_time": "3:45:23"}
+{"current_steps": 58, "total_steps": 567, "loss": 0.1269, "lr": 1.999981027348727e-05, "epoch": 0.7160493827160493, "percentage": 10.23, "elapsed_time": "0:25:38", "remaining_time": "3:45:00"}
+{"current_steps": 59, "total_steps": 567, "loss": 0.1106, "lr": 1.999924110114831e-05, "epoch": 0.7283950617283951, "percentage": 10.41, "elapsed_time": "0:26:05", "remaining_time": "3:44:38"}
+{"current_steps": 60, "total_steps": 567, "loss": 0.1264, "lr": 1.9998292504580528e-05, "epoch": 0.7407407407407407, "percentage": 10.58, "elapsed_time": "0:26:34", "remaining_time": "3:44:36"}
+{"current_steps": 61, "total_steps": 567, "loss": 0.1064, "lr": 1.999696451977872e-05, "epoch": 0.7530864197530864, "percentage": 10.76, "elapsed_time": "0:27:03", "remaining_time": "3:44:30"}
+{"current_steps": 62, "total_steps": 567, "loss": 0.0924, "lr": 1.999525719713366e-05, "epoch": 0.7654320987654321, "percentage": 10.93, "elapsed_time": "0:27:31", "remaining_time": "3:44:13"}
+{"current_steps": 63, "total_steps": 567, "loss": 0.1015, "lr": 1.9993170601430233e-05, "epoch": 0.7777777777777778, "percentage": 11.11, "elapsed_time": "0:27:58", "remaining_time": "3:43:50"}
+{"current_steps": 64, "total_steps": 567, "loss": 0.0955, "lr": 1.9990704811844934e-05, "epoch": 0.7901234567901234, "percentage": 11.29, "elapsed_time": "0:28:21", "remaining_time": "3:42:49"}
+{"current_steps": 65, "total_steps": 567, "loss": 0.1045, "lr": 1.99878599219429e-05, "epoch": 0.8024691358024691, "percentage": 11.46, "elapsed_time": "0:28:51", "remaining_time": "3:42:50"}
+{"current_steps": 66, "total_steps": 567, "loss": 0.0873, "lr": 1.9984636039674342e-05, "epoch": 0.8148148148148148, "percentage": 11.64, "elapsed_time": "0:29:18", "remaining_time": "3:42:31"}
+{"current_steps": 67, "total_steps": 567, "loss": 0.1089, "lr": 1.9981033287370443e-05, "epoch": 0.8271604938271605, "percentage": 11.82, "elapsed_time": "0:29:47", "remaining_time": "3:42:17"}
+{"current_steps": 68, "total_steps": 567, "loss": 0.1364, "lr": 1.9977051801738733e-05, "epoch": 0.8395061728395061, "percentage": 11.99, "elapsed_time": "0:30:13", "remaining_time": "3:41:49"}
+{"current_steps": 69, "total_steps": 567, "loss": 0.092, "lr": 1.997269173385788e-05, "epoch": 0.8518518518518519, "percentage": 12.17, "elapsed_time": "0:30:38", "remaining_time": "3:41:06"}
+{"current_steps": 70, "total_steps": 567, "loss": 0.1083, "lr": 1.996795324917199e-05, "epoch": 0.8641975308641975, "percentage": 12.35, "elapsed_time": "0:31:02", "remaining_time": "3:40:26"}
+{"current_steps": 71, "total_steps": 567, "loss": 0.0818, "lr": 1.9962836527484296e-05, "epoch": 0.8765432098765432, "percentage": 12.52, "elapsed_time": "0:31:33", "remaining_time": "3:40:29"}
+{"current_steps": 72, "total_steps": 567, "loss": 0.0981, "lr": 1.9957341762950346e-05, "epoch": 0.8888888888888888, "percentage": 12.7, "elapsed_time": "0:32:02", "remaining_time": "3:40:20"}
+{"current_steps": 73, "total_steps": 567, "loss": 0.083, "lr": 1.9951469164070647e-05, "epoch": 0.9012345679012346, "percentage": 12.87, "elapsed_time": "0:32:26", "remaining_time": "3:39:32"}
+{"current_steps": 74, "total_steps": 567, "loss": 0.0809, "lr": 1.9945218953682736e-05, "epoch": 0.9135802469135802, "percentage": 13.05, "elapsed_time": "0:32:53", "remaining_time": "3:39:09"}
+{"current_steps": 75, "total_steps": 567, "loss": 0.0848, "lr": 1.993859136895274e-05, "epoch": 0.9259259259259259, "percentage": 13.23, "elapsed_time": "0:33:19", "remaining_time": "3:38:37"}
+{"current_steps": 76, "total_steps": 567, "loss": 0.0815, "lr": 1.9931586661366363e-05, "epoch": 0.9382716049382716, "percentage": 13.4, "elapsed_time": "0:33:46", "remaining_time": "3:38:15"}
+{"current_steps": 77, "total_steps": 567, "loss": 0.0879, "lr": 1.992420509671936e-05, "epoch": 0.9506172839506173, "percentage": 13.58, "elapsed_time": "0:34:15", "remaining_time": "3:38:00"}
+{"current_steps": 78, "total_steps": 567, "loss": 0.0805, "lr": 1.991644695510743e-05, "epoch": 0.9629629629629629, "percentage": 13.76, "elapsed_time": "0:34:45", "remaining_time": "3:37:54"}
+{"current_steps": 79, "total_steps": 567, "loss": 0.0634, "lr": 1.9908312530915603e-05, "epoch": 0.9753086419753086, "percentage": 13.93, "elapsed_time": "0:35:11", "remaining_time": "3:37:23"}
+{"current_steps": 80, "total_steps": 567, "loss": 0.074, "lr": 1.9899802132807073e-05, "epoch": 0.9876543209876543, "percentage": 14.11, "elapsed_time": "0:35:36", "remaining_time": "3:36:45"}
+{"current_steps": 81, "total_steps": 567, "loss": 0.0896, "lr": 1.9890916083711463e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:36:01", "remaining_time": "3:36:09"}
+{"current_steps": 82, "total_steps": 567, "loss": 0.0616, "lr": 1.9881654720812594e-05, "epoch": 1.0123456790123457, "percentage": 14.46, "elapsed_time": "0:38:17", "remaining_time": "3:46:28"}
+{"current_steps": 83, "total_steps": 567, "loss": 0.0546, "lr": 1.9872018395535694e-05, "epoch": 1.0246913580246915, "percentage": 14.64, "elapsed_time": "0:38:45", "remaining_time": "3:46:00"}
+{"current_steps": 84, "total_steps": 567, "loss": 0.0633, "lr": 1.9862007473534026e-05, "epoch": 1.037037037037037, "percentage": 14.81, "elapsed_time": "0:39:12", "remaining_time": "3:45:24"}
+{"current_steps": 85, "total_steps": 567, "loss": 0.0651, "lr": 1.9851622334675065e-05, "epoch": 1.0493827160493827, "percentage": 14.99, "elapsed_time": "0:39:34", "remaining_time": "3:44:24"}
+{"current_steps": 86, "total_steps": 567, "loss": 0.0378, "lr": 1.9840863373026046e-05, "epoch": 1.0617283950617284, "percentage": 15.17, "elapsed_time": "0:40:01", "remaining_time": "3:43:54"}
+{"current_steps": 87, "total_steps": 567, "loss": 0.0479, "lr": 1.982973099683902e-05, "epoch": 1.074074074074074, "percentage": 15.34, "elapsed_time": "0:40:26", "remaining_time": "3:43:10"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6a232e822330b5721fd0ca88edbc48cc3bdd3a807593c6330ec4ed559ac6c2
+size 7352