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:c9211742ef2638a8ed57e216126e68d6f6ab430555ce157670307a9d027318b1
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5980625b0e88ac9690371e682be2d3ebaa7ecc1a272d1e76c50a082cce5f68
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53bf41a8b197646abb29b6c1172ac892f4499d622a9c86a7c14f10eeae1143f
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da30cc723754323cd833dc6ee7d54aac6077268ceb077ac5155c2f7c552e802c
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_log.jsonl

@@ -0,0 +1,111 @@
+{"current_steps": 1, "total_steps": 333, "loss": 0.851, "lr": 6.655117647058823e-06, "epoch": 0.008983717012914094, "percentage": 0.3, "elapsed_time": "0:06:04", "remaining_time": "1 day, 9:36:50"}
+{"current_steps": 2, "total_steps": 333, "loss": 0.8589, "lr": 1.3310235294117646e-05, "epoch": 0.017967434025828188, "percentage": 0.6, "elapsed_time": "0:12:10", "remaining_time": "1 day, 9:35:00"}
+{"current_steps": 3, "total_steps": 333, "loss": 0.8091, "lr": 1.996535294117647e-05, "epoch": 0.02695115103874228, "percentage": 0.9, "elapsed_time": "0:17:45", "remaining_time": "1 day, 8:33:27"}
+{"current_steps": 4, "total_steps": 333, "loss": 0.8296, "lr": 2.6620470588235293e-05, "epoch": 0.035934868051656375, "percentage": 1.2, "elapsed_time": "0:23:34", "remaining_time": "1 day, 8:19:13"}
+{"current_steps": 5, "total_steps": 333, "loss": 0.8406, "lr": 3.3275588235294115e-05, "epoch": 0.044918585064570464, "percentage": 1.5, "elapsed_time": "0:29:21", "remaining_time": "1 day, 8:05:52"}
+{"current_steps": 6, "total_steps": 333, "loss": 0.7848, "lr": 3.993070588235294e-05, "epoch": 0.05390230207748456, "percentage": 1.8, "elapsed_time": "0:35:04", "remaining_time": "1 day, 7:51:41"}
+{"current_steps": 7, "total_steps": 333, "loss": 0.7269, "lr": 4.658582352941176e-05, "epoch": 0.06288601909039865, "percentage": 2.1, "elapsed_time": "0:41:14", "remaining_time": "1 day, 8:00:36"}
+{"current_steps": 8, "total_steps": 333, "loss": 0.7032, "lr": 5.3240941176470586e-05, "epoch": 0.07186973610331275, "percentage": 2.4, "elapsed_time": "0:46:59", "remaining_time": "1 day, 7:48:52"}
+{"current_steps": 9, "total_steps": 333, "loss": 0.686, "lr": 5.989605882352941e-05, "epoch": 0.08085345311622684, "percentage": 2.7, "elapsed_time": "0:52:49", "remaining_time": "1 day, 7:41:48"}
+{"current_steps": 10, "total_steps": 333, "loss": 0.6731, "lr": 6.655117647058823e-05, "epoch": 0.08983717012914093, "percentage": 3.0, "elapsed_time": "0:58:30", "remaining_time": "1 day, 7:29:40"}
+{"current_steps": 11, "total_steps": 333, "loss": 0.6436, "lr": 7.320629411764706e-05, "epoch": 0.09882088714205503, "percentage": 3.3, "elapsed_time": "1:04:23", "remaining_time": "1 day, 7:24:41"}
+{"current_steps": 12, "total_steps": 333, "loss": 0.6546, "lr": 7.986141176470588e-05, "epoch": 0.10780460415496912, "percentage": 3.6, "elapsed_time": "1:10:29", "remaining_time": "1 day, 7:25:30"}
+{"current_steps": 13, "total_steps": 333, "loss": 0.6243, "lr": 8.65165294117647e-05, "epoch": 0.11678832116788321, "percentage": 3.9, "elapsed_time": "1:16:03", "remaining_time": "1 day, 7:12:18"}
+{"current_steps": 14, "total_steps": 333, "loss": 0.6431, "lr": 9.317164705882352e-05, "epoch": 0.1257720381807973, "percentage": 4.2, "elapsed_time": "1:21:46", "remaining_time": "1 day, 7:03:11"}
+{"current_steps": 15, "total_steps": 333, "loss": 0.6337, "lr": 9.982676470588235e-05, "epoch": 0.13475575519371139, "percentage": 4.5, "elapsed_time": "1:27:37", "remaining_time": "1 day, 6:57:36"}
+{"current_steps": 16, "total_steps": 333, "loss": 0.6219, "lr": 0.00010648188235294117, "epoch": 0.1437394722066255, "percentage": 4.8, "elapsed_time": "1:33:30", "remaining_time": "1 day, 6:52:39"}
+{"current_steps": 17, "total_steps": 333, "loss": 0.6009, "lr": 0.000113137, "epoch": 0.1527231892195396, "percentage": 5.11, "elapsed_time": "1:39:23", "remaining_time": "1 day, 6:47:35"}
+{"current_steps": 18, "total_steps": 333, "loss": 0.5964, "lr": 0.00011979211764705882, "epoch": 0.16170690623245368, "percentage": 5.41, "elapsed_time": "1:45:06", "remaining_time": "1 day, 6:39:24"}
+{"current_steps": 19, "total_steps": 333, "loss": 0.6148, "lr": 0.00012644723529411765, "epoch": 0.17069062324536777, "percentage": 5.71, "elapsed_time": "1:51:01", "remaining_time": "1 day, 6:34:45"}
+{"current_steps": 20, "total_steps": 333, "loss": 0.6018, "lr": 0.00013310235294117646, "epoch": 0.17967434025828186, "percentage": 6.01, "elapsed_time": "1:56:50", "remaining_time": "1 day, 6:28:35"}
+{"current_steps": 21, "total_steps": 333, "loss": 0.5954, "lr": 0.0001397574705882353, "epoch": 0.18865805727119594, "percentage": 6.31, "elapsed_time": "2:02:53", "remaining_time": "1 day, 6:25:49"}
+{"current_steps": 22, "total_steps": 333, "loss": 0.6004, "lr": 0.0001464125882352941, "epoch": 0.19764177428411006, "percentage": 6.61, "elapsed_time": "2:08:49", "remaining_time": "1 day, 6:21:03"}
+{"current_steps": 23, "total_steps": 333, "loss": 0.6111, "lr": 0.00015306770588235295, "epoch": 0.20662549129702415, "percentage": 6.91, "elapsed_time": "2:14:20", "remaining_time": "1 day, 6:10:39"}
+{"current_steps": 24, "total_steps": 333, "loss": 0.6119, "lr": 0.00015972282352941176, "epoch": 0.21560920830993824, "percentage": 7.21, "elapsed_time": "2:20:14", "remaining_time": "1 day, 6:05:37"}
+{"current_steps": 25, "total_steps": 333, "loss": 0.593, "lr": 0.0001663779411764706, "epoch": 0.22459292532285233, "percentage": 7.51, "elapsed_time": "2:25:51", "remaining_time": "1 day, 5:56:59"}
+{"current_steps": 26, "total_steps": 333, "loss": 5.673, "lr": 0.0001730330588235294, "epoch": 0.23357664233576642, "percentage": 7.81, "elapsed_time": "2:31:31", "remaining_time": "1 day, 5:49:08"}
+{"current_steps": 27, "total_steps": 333, "loss": 0.7795, "lr": 0.00017968817647058823, "epoch": 0.2425603593486805, "percentage": 8.11, "elapsed_time": "2:36:58", "remaining_time": "1 day, 5:39:08"}
+{"current_steps": 28, "total_steps": 333, "loss": 0.7672, "lr": 0.00018634329411764704, "epoch": 0.2515440763615946, "percentage": 8.41, "elapsed_time": "2:42:33", "remaining_time": "1 day, 5:30:47"}
+{"current_steps": 29, "total_steps": 333, "loss": 0.6615, "lr": 0.00019299841176470588, "epoch": 0.2605277933745087, "percentage": 8.71, "elapsed_time": "2:48:24", "remaining_time": "1 day, 5:25:21"}
+{"current_steps": 30, "total_steps": 333, "loss": 0.6385, "lr": 0.0001996535294117647, "epoch": 0.26951151038742277, "percentage": 9.01, "elapsed_time": "2:54:14", "remaining_time": "1 day, 5:19:48"}
+{"current_steps": 31, "total_steps": 333, "loss": 0.612, "lr": 0.00020630864705882353, "epoch": 0.2784952274003369, "percentage": 9.31, "elapsed_time": "2:59:48", "remaining_time": "1 day, 5:11:36"}
+{"current_steps": 32, "total_steps": 333, "loss": 0.6641, "lr": 0.00021296376470588234, "epoch": 0.287478944413251, "percentage": 9.61, "elapsed_time": "3:05:28", "remaining_time": "1 day, 5:04:33"}
+{"current_steps": 33, "total_steps": 333, "loss": 0.9157, "lr": 0.00021961888235294118, "epoch": 0.29646266142616506, "percentage": 9.91, "elapsed_time": "3:11:11", "remaining_time": "1 day, 4:58:08"}
+{"current_steps": 34, "total_steps": 333, "loss": 1.7373, "lr": 0.000226274, "epoch": 0.3054463784390792, "percentage": 10.21, "elapsed_time": "3:17:07", "remaining_time": "1 day, 4:53:29"}
+{"current_steps": 35, "total_steps": 333, "loss": 0.8771, "lr": 0.00022626775506336304, "epoch": 0.31443009545199324, "percentage": 10.51, "elapsed_time": "3:22:54", "remaining_time": "1 day, 4:47:33"}
+{"current_steps": 36, "total_steps": 333, "loss": 0.9851, "lr": 0.00022624902094286824, "epoch": 0.32341381246490736, "percentage": 10.81, "elapsed_time": "3:28:44", "remaining_time": "1 day, 4:42:04"}
+{"current_steps": 37, "total_steps": 333, "loss": 0.9069, "lr": 0.00022621779970668783, "epoch": 0.3323975294778215, "percentage": 11.11, "elapsed_time": "3:34:38", "remaining_time": "1 day, 4:37:07"}
+{"current_steps": 38, "total_steps": 333, "loss": 0.8182, "lr": 0.00022617409480152153, "epoch": 0.34138124649073553, "percentage": 11.41, "elapsed_time": "3:40:13", "remaining_time": "1 day, 4:29:39"}
+{"current_steps": 39, "total_steps": 333, "loss": 0.9486, "lr": 0.00022611791105221654, "epoch": 0.35036496350364965, "percentage": 11.71, "elapsed_time": "3:46:06", "remaining_time": "1 day, 4:24:30"}
+{"current_steps": 40, "total_steps": 333, "loss": 0.8591, "lr": 0.00022604925466123451, "epoch": 0.3593486805165637, "percentage": 12.01, "elapsed_time": "3:51:51", "remaining_time": "1 day, 4:18:19"}
+{"current_steps": 41, "total_steps": 333, "loss": 0.7781, "lr": 0.00022596813320796707, "epoch": 0.36833239752947783, "percentage": 12.31, "elapsed_time": "3:57:23", "remaining_time": "1 day, 4:10:40"}
+{"current_steps": 42, "total_steps": 333, "loss": 0.8526, "lr": 0.00022587455564789883, "epoch": 0.3773161145423919, "percentage": 12.61, "elapsed_time": "4:03:15", "remaining_time": "1 day, 4:05:28"}
+{"current_steps": 43, "total_steps": 333, "loss": 1.738, "lr": 0.00022576853231161902, "epoch": 0.386299831555306, "percentage": 12.91, "elapsed_time": "4:08:46", "remaining_time": "1 day, 3:57:50"}
+{"current_steps": 44, "total_steps": 333, "loss": 0.8999, "lr": 0.00022565007490368076, "epoch": 0.3952835485682201, "percentage": 13.21, "elapsed_time": "4:14:44", "remaining_time": "1 day, 3:53:09"}
+{"current_steps": 45, "total_steps": 333, "loss": 7.1473, "lr": 0.00022551919650130918, "epoch": 0.4042672655811342, "percentage": 13.51, "elapsed_time": "4:20:39", "remaining_time": "1 day, 3:48:15"}
+{"current_steps": 46, "total_steps": 333, "loss": 1.5197, "lr": 0.00022537591155295756, "epoch": 0.4132509825940483, "percentage": 13.81, "elapsed_time": "4:26:21", "remaining_time": "1 day, 3:41:47"}
+{"current_steps": 47, "total_steps": 333, "loss": 1.0434, "lr": 0.00022522023587671233, "epoch": 0.42223469960696236, "percentage": 14.11, "elapsed_time": "4:32:13", "remaining_time": "1 day, 3:36:28"}
+{"current_steps": 48, "total_steps": 333, "loss": 0.8122, "lr": 0.0002250521866585469, "epoch": 0.4312184166198765, "percentage": 14.41, "elapsed_time": "4:37:51", "remaining_time": "1 day, 3:29:47"}
+{"current_steps": 49, "total_steps": 333, "loss": 0.9547, "lr": 0.00022487178245042422, "epoch": 0.4402021336327906, "percentage": 14.71, "elapsed_time": "4:43:27", "remaining_time": "1 day, 3:22:51"}
+{"current_steps": 50, "total_steps": 333, "loss": 1.026, "lr": 0.0002246790431682489, "epoch": 0.44918585064570465, "percentage": 15.02, "elapsed_time": "4:49:20", "remaining_time": "1 day, 3:17:38"}
+{"current_steps": 51, "total_steps": 333, "loss": 0.8958, "lr": 0.00022447399008966853, "epoch": 0.45816956765861877, "percentage": 15.32, "elapsed_time": "4:55:07", "remaining_time": "1 day, 3:11:51"}
+{"current_steps": 52, "total_steps": 333, "loss": 0.7584, "lr": 0.0002242566458517245, "epoch": 0.46715328467153283, "percentage": 15.62, "elapsed_time": "5:00:46", "remaining_time": "1 day, 3:05:20"}
+{"current_steps": 53, "total_steps": 333, "loss": 0.7519, "lr": 0.0002240270344483534, "epoch": 0.47613700168444695, "percentage": 15.92, "elapsed_time": "5:06:37", "remaining_time": "1 day, 2:59:56"}
+{"current_steps": 54, "total_steps": 333, "loss": 0.7169, "lr": 0.00022378518122773768, "epoch": 0.485120718697361, "percentage": 16.22, "elapsed_time": "5:12:13", "remaining_time": "1 day, 2:53:08"}
+{"current_steps": 55, "total_steps": 333, "loss": 0.7069, "lr": 0.00022353111288950776, "epoch": 0.4941044357102751, "percentage": 16.52, "elapsed_time": "5:17:55", "remaining_time": "1 day, 2:46:58"}
+{"current_steps": 56, "total_steps": 333, "loss": 0.6934, "lr": 0.00022326485748179416, "epoch": 0.5030881527231892, "percentage": 16.82, "elapsed_time": "5:23:40", "remaining_time": "1 day, 2:41:02"}
+{"current_steps": 57, "total_steps": 333, "loss": 0.6997, "lr": 0.00022298644439813125, "epoch": 0.5120718697361033, "percentage": 17.12, "elapsed_time": "5:29:38", "remaining_time": "1 day, 2:36:08"}
+{"current_steps": 58, "total_steps": 333, "loss": 0.6587, "lr": 0.00022269590437421234, "epoch": 0.5210555867490174, "percentage": 17.42, "elapsed_time": "5:35:10", "remaining_time": "1 day, 2:29:10"}
+{"current_steps": 59, "total_steps": 333, "loss": 0.6444, "lr": 0.0002223932694844966, "epoch": 0.5300393037619315, "percentage": 17.72, "elapsed_time": "5:40:57", "remaining_time": "1 day, 2:23:26"}
+{"current_steps": 60, "total_steps": 333, "loss": 0.6558, "lr": 0.00022207857313866796, "epoch": 0.5390230207748455, "percentage": 18.02, "elapsed_time": "5:46:21", "remaining_time": "1 day, 2:15:55"}
+{"current_steps": 61, "total_steps": 333, "loss": 0.6647, "lr": 0.00022175185007794712, "epoch": 0.5480067377877597, "percentage": 18.32, "elapsed_time": "5:52:15", "remaining_time": "1 day, 2:10:41"}
+{"current_steps": 62, "total_steps": 333, "loss": 0.6244, "lr": 0.000221413136371256, "epoch": 0.5569904548006738, "percentage": 18.62, "elapsed_time": "5:58:01", "remaining_time": "1 day, 2:04:53"}
+{"current_steps": 63, "total_steps": 333, "loss": 0.616, "lr": 0.00022106246941123604, "epoch": 0.5659741718135879, "percentage": 18.92, "elapsed_time": "6:03:42", "remaining_time": "1 day, 1:58:43"}
+{"current_steps": 64, "total_steps": 333, "loss": 0.6097, "lr": 0.0002206998879101201, "epoch": 0.574957888826502, "percentage": 19.22, "elapsed_time": "6:09:28", "remaining_time": "1 day, 1:52:56"}
+{"current_steps": 65, "total_steps": 333, "loss": 0.6261, "lr": 0.00022032543189545893, "epoch": 0.583941605839416, "percentage": 19.52, "elapsed_time": "6:15:09", "remaining_time": "1 day, 1:46:46"}
+{"current_steps": 66, "total_steps": 333, "loss": 0.5992, "lr": 0.00021993914270570204, "epoch": 0.5929253228523301, "percentage": 19.82, "elapsed_time": "6:20:59", "remaining_time": "1 day, 1:41:16"}
+{"current_steps": 67, "total_steps": 333, "loss": 0.6003, "lr": 0.0002195410629856343, "epoch": 0.6019090398652442, "percentage": 20.12, "elapsed_time": "6:26:32", "remaining_time": "1 day, 1:34:39"}
+{"current_steps": 68, "total_steps": 333, "loss": 0.5952, "lr": 0.00021913123668166815, "epoch": 0.6108927568781584, "percentage": 20.42, "elapsed_time": "6:32:33", "remaining_time": "1 day, 1:29:48"}
+{"current_steps": 69, "total_steps": 333, "loss": 0.5844, "lr": 0.00021870970903699184, "epoch": 0.6198764738910725, "percentage": 20.72, "elapsed_time": "6:38:16", "remaining_time": "1 day, 1:23:49"}
+{"current_steps": 70, "total_steps": 333, "loss": 0.5736, "lr": 0.00021827652658657518, "epoch": 0.6288601909039865, "percentage": 21.02, "elapsed_time": "6:44:10", "remaining_time": "1 day, 1:18:33"}
+{"current_steps": 71, "total_steps": 333, "loss": 0.5677, "lr": 0.00021783173715203175, "epoch": 0.6378439079169006, "percentage": 21.32, "elapsed_time": "6:50:02", "remaining_time": "1 day, 1:13:07"}
+{"current_steps": 72, "total_steps": 333, "loss": 0.5567, "lr": 0.00021737538983634003, "epoch": 0.6468276249298147, "percentage": 21.62, "elapsed_time": "6:55:34", "remaining_time": "1 day, 1:06:27"}
+{"current_steps": 73, "total_steps": 333, "loss": 0.5652, "lr": 0.00021690753501842243, "epoch": 0.6558113419427288, "percentage": 21.92, "elapsed_time": "7:01:16", "remaining_time": "1 day, 1:00:24"}
+{"current_steps": 74, "total_steps": 333, "loss": 0.5521, "lr": 0.00021642822434758365, "epoch": 0.664795058955643, "percentage": 22.22, "elapsed_time": "7:06:43", "remaining_time": "1 day, 0:53:31"}
+{"current_steps": 75, "total_steps": 333, "loss": 0.5484, "lr": 0.0002159375107378088, "epoch": 0.673778775968557, "percentage": 22.52, "elapsed_time": "7:12:30", "remaining_time": "1 day, 0:47:48"}
+{"current_steps": 76, "total_steps": 333, "loss": 0.5629, "lr": 0.00021543544836192198, "epoch": 0.6827624929814711, "percentage": 22.82, "elapsed_time": "7:18:20", "remaining_time": "1 day, 0:42:16"}
+{"current_steps": 77, "total_steps": 333, "loss": 0.5477, "lr": 0.00021492209264560583, "epoch": 0.6917462099943852, "percentage": 23.12, "elapsed_time": "7:24:03", "remaining_time": "1 day, 0:36:21"}
+{"current_steps": 78, "total_steps": 333, "loss": 0.5486, "lr": 0.00021439750026128255, "epoch": 0.7007299270072993, "percentage": 23.42, "elapsed_time": "7:29:57", "remaining_time": "1 day, 0:31:00"}
+{"current_steps": 79, "total_steps": 333, "loss": 0.5386, "lr": 0.00021386172912185786, "epoch": 0.7097136440202133, "percentage": 23.72, "elapsed_time": "7:35:31", "remaining_time": "1 day, 0:24:35"}
+{"current_steps": 80, "total_steps": 333, "loss": 0.5526, "lr": 0.0002133148383743272, "epoch": 0.7186973610331274, "percentage": 24.02, "elapsed_time": "7:41:14", "remaining_time": "1 day, 0:18:42"}
+{"current_steps": 81, "total_steps": 333, "loss": 0.5355, "lr": 0.00021275688839324653, "epoch": 0.7276810780460415, "percentage": 24.32, "elapsed_time": "7:47:03", "remaining_time": "1 day, 0:13:05"}
+{"current_steps": 82, "total_steps": 333, "loss": 0.5214, "lr": 0.00021218794077406699, "epoch": 0.7366647950589557, "percentage": 24.62, "elapsed_time": "7:53:01", "remaining_time": "1 day, 0:07:56"}
+{"current_steps": 83, "total_steps": 333, "loss": 0.5334, "lr": 0.00021160805832633507, "epoch": 0.7456485120718698, "percentage": 24.92, "elapsed_time": "7:58:53", "remaining_time": "1 day, 0:02:27"}
+{"current_steps": 84, "total_steps": 333, "loss": 0.5246, "lr": 0.00021101730506675872, "epoch": 0.7546322290847838, "percentage": 25.23, "elapsed_time": "8:04:38", "remaining_time": "23:56:35"}
+{"current_steps": 85, "total_steps": 333, "loss": 0.5211, "lr": 0.00021041574621214016, "epoch": 0.7636159460976979, "percentage": 25.53, "elapsed_time": "8:10:31", "remaining_time": "23:51:11"}
+{"current_steps": 86, "total_steps": 333, "loss": 0.52, "lr": 0.00020980344817217607, "epoch": 0.772599663110612, "percentage": 25.83, "elapsed_time": "8:16:25", "remaining_time": "23:45:46"}
+{"current_steps": 87, "total_steps": 333, "loss": 0.5086, "lr": 0.00020918047854212644, "epoch": 0.7815833801235261, "percentage": 26.13, "elapsed_time": "8:22:10", "remaining_time": "23:39:57"}
+{"current_steps": 88, "total_steps": 333, "loss": 0.5205, "lr": 0.00020854690609535217, "epoch": 0.7905670971364402, "percentage": 26.43, "elapsed_time": "8:28:02", "remaining_time": "23:34:26"}
+{"current_steps": 89, "total_steps": 333, "loss": 0.4995, "lr": 0.0002079028007757228, "epoch": 0.7995508141493542, "percentage": 26.73, "elapsed_time": "8:33:57", "remaining_time": "23:29:04"}
+{"current_steps": 90, "total_steps": 333, "loss": 0.5108, "lr": 0.000207248233689895, "epoch": 0.8085345311622684, "percentage": 27.03, "elapsed_time": "8:40:02", "remaining_time": "23:24:07"}
+{"current_steps": 91, "total_steps": 333, "loss": 0.5105, "lr": 0.00020658327709946274, "epoch": 0.8175182481751825, "percentage": 27.33, "elapsed_time": "8:45:57", "remaining_time": "23:18:40"}
+{"current_steps": 92, "total_steps": 333, "loss": 0.5043, "lr": 0.00020590800441297976, "epoch": 0.8265019651880966, "percentage": 27.63, "elapsed_time": "8:51:36", "remaining_time": "23:12:35"}
+{"current_steps": 93, "total_steps": 333, "loss": 0.5056, "lr": 0.00020522249017785566, "epoch": 0.8354856822010107, "percentage": 27.93, "elapsed_time": "8:57:17", "remaining_time": "23:06:33"}
+{"current_steps": 94, "total_steps": 333, "loss": 0.5189, "lr": 0.00020452681007212612, "epoch": 0.8444693992139247, "percentage": 28.23, "elapsed_time": "9:03:06", "remaining_time": "23:00:52"}
+{"current_steps": 95, "total_steps": 333, "loss": 0.5167, "lr": 0.0002038210408960984, "epoch": 0.8534531162268388, "percentage": 28.53, "elapsed_time": "9:08:51", "remaining_time": "22:55:02"}
+{"current_steps": 96, "total_steps": 333, "loss": 0.5145, "lr": 0.0002031052605638728, "epoch": 0.862436833239753, "percentage": 28.83, "elapsed_time": "9:14:45", "remaining_time": "22:49:33"}
+{"current_steps": 97, "total_steps": 333, "loss": 0.5158, "lr": 0.00020237954809474134, "epoch": 0.8714205502526671, "percentage": 29.13, "elapsed_time": "9:20:39", "remaining_time": "22:44:05"}
+{"current_steps": 98, "total_steps": 333, "loss": 0.4931, "lr": 0.00020164398360446436, "epoch": 0.8804042672655812, "percentage": 29.43, "elapsed_time": "9:26:46", "remaining_time": "22:39:06"}
+{"current_steps": 99, "total_steps": 333, "loss": 0.5075, "lr": 0.00020089864829642596, "epoch": 0.8893879842784952, "percentage": 29.73, "elapsed_time": "9:32:24", "remaining_time": "22:32:57"}
+{"current_steps": 100, "total_steps": 333, "loss": 0.4907, "lr": 0.0002001436244526695, "epoch": 0.8983717012914093, "percentage": 30.03, "elapsed_time": "9:38:22", "remaining_time": "22:27:37"}
+{"current_steps": 101, "total_steps": 333, "loss": 0.5041, "lr": 0.00019937899542481408, "epoch": 0.9073554183043234, "percentage": 30.33, "elapsed_time": "9:44:08", "remaining_time": "22:21:47"}
+{"current_steps": 102, "total_steps": 333, "loss": 0.488, "lr": 0.00019860484562485276, "epoch": 0.9163391353172375, "percentage": 30.63, "elapsed_time": "9:49:57", "remaining_time": "22:16:04"}
+{"current_steps": 103, "total_steps": 333, "loss": 0.5023, "lr": 0.00019782126051583386, "epoch": 0.9253228523301515, "percentage": 30.93, "elapsed_time": "9:55:34", "remaining_time": "22:09:54"}
+{"current_steps": 104, "total_steps": 333, "loss": 0.489, "lr": 0.00019702832660242615, "epoch": 0.9343065693430657, "percentage": 31.23, "elapsed_time": "10:01:14", "remaining_time": "22:03:53"}
+{"current_steps": 105, "total_steps": 333, "loss": 0.4996, "lr": 0.0001962261314213691, "epoch": 0.9432902863559798, "percentage": 31.53, "elapsed_time": "10:07:06", "remaining_time": "21:58:16"}
+{"current_steps": 106, "total_steps": 333, "loss": 0.4856, "lr": 0.00019541476353180916, "epoch": 0.9522740033688939, "percentage": 31.83, "elapsed_time": "10:12:59", "remaining_time": "21:52:44"}
+{"current_steps": 107, "total_steps": 333, "loss": 0.4855, "lr": 0.00019459431250552317, "epoch": 0.961257720381808, "percentage": 32.13, "elapsed_time": "10:18:30", "remaining_time": "21:46:23"}
+{"current_steps": 108, "total_steps": 333, "loss": 0.4762, "lr": 0.0001937648689170301, "epoch": 0.970241437394722, "percentage": 32.43, "elapsed_time": "10:24:02", "remaining_time": "21:40:05"}
+{"current_steps": 109, "total_steps": 333, "loss": 0.4834, "lr": 0.00019292652433359177, "epoch": 0.9792251544076361, "percentage": 32.73, "elapsed_time": "10:29:47", "remaining_time": "21:34:14"}
+{"current_steps": 110, "total_steps": 333, "loss": 0.4946, "lr": 0.00019207937130510442, "epoch": 0.9882088714205502, "percentage": 33.03, "elapsed_time": "10:35:24", "remaining_time": "21:28:09"}
+{"current_steps": 111, "total_steps": 333, "loss": 0.4846, "lr": 0.0001912235033538814, "epoch": 0.9971925884334644, "percentage": 33.33, "elapsed_time": "10:41:11", "remaining_time": "21:22:22"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf0083f7f86646d0665eb933b7a75a02e45689defbb86cb977daab3d52a1023
+size 7224