Training in progress, step 10

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/root/highspeedstorage/ft-volume/phi",
+  "base_model_name_or_path": "/root/highspeedstorage/ft-volume/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -19,14 +19,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": [],
   "peft_type": "LORA",
-  "r": 512,
+  "r": 1024,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
     "down_proj",
-    "qkv_proj",
-    "o_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003767a8422f0694431cc97e9ccaacad4575c669ef64e1da6fe46adcfa2a9d53
-size 3565203280
+oid sha256:52b79c6e876fcecbc99e1b2b029aa003b86c4f8c7f739081ec7b79acecc4ab6d
+size 17179995744

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
+}

args.json

@@ -1,17 +1,17 @@
 {
-  "model": "/root/highspeedstorage/ft-volume/phi",
-  "model_type": "phi4",
+  "model": "/root/highspeedstorage/ft-volume/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd",
+  "model_type": "qwen2_5",
   "model_revision": null,
   "task_type": "causal_lm",
   "torch_dtype": "bfloat16",
-  "attn_impl": null,
+  "attn_impl": "sdpa",
   "num_labels": null,
   "rope_scaling": null,
   "device_map": null,
   "local_repo_path": null,
-  "template": "phi4",
+  "template": "qwen2_5",
   "system": "",
-  "max_length": 15000,
+  "max_length": 29000,
   "truncation_strategy": "left",
   "max_pixels": null,
   "tools_prompt": "react_en",
@@ -75,7 +75,7 @@
   "custom_register_path": [],
   "ignore_args_error": false,
   "use_swift_lora": false,
-  "output_dir": "/root/dataDisk/output/v15-20250301-174709",
+  "output_dir": "/root/dataDisk/output/v24-20250302-105846",
   "overwrite_output_dir": false,
   "do_train": false,
   "do_eval": false,
@@ -86,7 +86,7 @@
   "per_device_eval_batch_size": 1,
   "per_gpu_train_batch_size": null,
   "per_gpu_eval_batch_size": null,
-  "gradient_accumulation_steps": 1,
+  "gradient_accumulation_steps": 12,
   "eval_accumulation_steps": null,
   "eval_delay": 0,
   "torch_empty_cache_steps": null,
@@ -105,7 +105,7 @@
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
-  "logging_dir": "/root/dataDisk/output/v15-20250301-174709/runs",
+  "logging_dir": "/root/dataDisk/output/v24-20250302-105846/runs",
   "logging_strategy": "steps",
   "logging_first_step": true,
   "logging_steps": 1,
@@ -262,7 +262,7 @@
   ],
   "target_regex": null,
   "modules_to_save": [],
-  "lora_rank": 512,
+  "lora_rank": 1024,
   "lora_alpha": 128,
   "lora_dropout": 0.01,
   "lora_bias": "none",
@@ -345,10 +345,10 @@
   "rank": 0,
   "global_world_size": 8,
   "local_world_size": 8,
-  "model_suffix": "phi",
-  "model_info": "ModelInfo(model_type='phi4', model_dir='/root/highspeedstorage/ft-volume/phi', torch_dtype=torch.bfloat16, max_model_len=16384, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
-  "model_meta": "ModelMeta(model_type='phi4', model_groups=[ModelGroup(models=[Model(ms_model_id='LLM-Research/phi-4', hf_model_id='microsoft/phi-4', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='phi4', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f201dfdb760>, model_arch='phi3', architectures=['Phi3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.36'], tags=[])",
-  "model_dir": "/root/highspeedstorage/ft-volume/phi",
+  "model_suffix": "Qwen2.5-32B-Instruct",
+  "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/root/highspeedstorage/ft-volume/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding'])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x7fd935db7760>, model_arch='llama', architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=['*.zip', '*.gguf', '*.pth', '*.pt', 'consolidated*', 'onnx/*', '*.safetensors.md', '*.msgpack', '*.onnx', '*.ot', '*.h5', '*.bin', '*.safetensors'], requires=['transformers>=4.37'], tags=[])",
+  "model_dir": "/root/highspeedstorage/ft-volume/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd",
   "hub": "<class 'swift.hub.hub.HFHub'>",
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/dataDisk/output/v15-20250301-174709', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=1, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.LINEAR: 'linear'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/dataDisk/output/v15-20250301-174709/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=10, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=10, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/dataDisk/output/v15-20250301-174709', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'cpu', 'pin_memory': True}, 'offload_param': {'device': 'cpu', 'pin_memory': True}, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=True, resume_from_checkpoint=None, hub_model_id='TheAgenticAI/LLAMA-3.3-70B-Reasoning', hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=True, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': True}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='lora', optimizer=None, galore_config=None)"
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/dataDisk/output/v24-20250302-105846', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=12, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.LINEAR: 'linear'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/dataDisk/output/v24-20250302-105846/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=10, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=10, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/dataDisk/output/v24-20250302-105846', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'cpu', 'pin_memory': True}, 'offload_param': {'device': 'cpu', 'pin_memory': True}, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=True, resume_from_checkpoint=None, hub_model_id='TheAgenticAI/LLAMA-3.3-70B-Reasoning', hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=True, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': True}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='lora', optimizer=None, galore_config=None)"
 }

logging.jsonl

@@ -1,124 +1,18 @@
-{"loss": 0.93798834, "token_acc": 0.76758794, "grad_norm": 5.03938723, "learning_rate": 5e-08, "memory(GiB)": 8.05, "train_speed(iter/s)": 0.023691, "epoch": 0.00053505, "global_step/max_steps": "1/1869", "percentage": "0.05%", "elapsed_time": "12s", "remaining_time": "6h 35m 9s"}
-{"loss": 0.92002016, "token_acc": 0.70787879, "grad_norm": 6.17990303, "learning_rate": 1.1e-07, "memory(GiB)": 13.83, "train_speed(iter/s)": 0.041561, "epoch": 0.00107009, "global_step/max_steps": "2/1869", "percentage": "0.11%", "elapsed_time": "18s", "remaining_time": "4h 49m 26s"}
-{"loss": 0.93352824, "token_acc": 0.75027747, "grad_norm": 4.24871159, "learning_rate": 1.6e-07, "memory(GiB)": 13.83, "train_speed(iter/s)": 0.05581, "epoch": 0.00160514, "global_step/max_steps": "3/1869", "percentage": "0.16%", "elapsed_time": "24s", "remaining_time": "4h 11m 14s"}
-{"loss": 0.97441375, "token_acc": 0.77185501, "grad_norm": 5.50236464, "learning_rate": 2.1e-07, "memory(GiB)": 15.32, "train_speed(iter/s)": 0.067326, "epoch": 0.00214018, "global_step/max_steps": "4/1869", "percentage": "0.21%", "elapsed_time": "29s", "remaining_time": "3h 52m 17s"}
-{"loss": 0.86643094, "token_acc": 0.80839161, "grad_norm": 5.14204454, "learning_rate": 2.7e-07, "memory(GiB)": 15.32, "train_speed(iter/s)": 0.076809, "epoch": 0.00267523, "global_step/max_steps": "5/1869", "percentage": "0.27%", "elapsed_time": "35s", "remaining_time": "3h 41m 3s"}
-{"loss": 0.88649535, "token_acc": 0.78010949, "grad_norm": 5.23055983, "learning_rate": 3.2e-07, "memory(GiB)": 15.87, "train_speed(iter/s)": 0.089255, "epoch": 0.00321027, "global_step/max_steps": "6/1869", "percentage": "0.32%", "elapsed_time": "37s", "remaining_time": "3h 15m 7s"}
-{"loss": 0.92156661, "token_acc": 0.70940883, "grad_norm": 5.40514421, "learning_rate": 3.7e-07, "memory(GiB)": 16.45, "train_speed(iter/s)": 0.101701, "epoch": 0.00374532, "global_step/max_steps": "7/1869", "percentage": "0.37%", "elapsed_time": "39s", "remaining_time": "2h 54m 16s"}
-{"loss": 0.94250065, "token_acc": 0.785, "grad_norm": 5.43437529, "learning_rate": 4.3e-07, "memory(GiB)": 16.45, "train_speed(iter/s)": 0.113564, "epoch": 0.00428036, "global_step/max_steps": "8/1869", "percentage": "0.43%", "elapsed_time": "40s", "remaining_time": "2h 38m 40s"}
-{"loss": 0.94119352, "token_acc": 0.78978622, "grad_norm": 5.04455853, "learning_rate": 4.8e-07, "memory(GiB)": 16.45, "train_speed(iter/s)": 0.123471, "epoch": 0.00481541, "global_step/max_steps": "9/1869", "percentage": "0.48%", "elapsed_time": "43s", "remaining_time": "2h 29m 23s"}
-{"loss": 0.89960265, "token_acc": 0.79014599, "grad_norm": 5.64693308, "learning_rate": 5.3e-07, "memory(GiB)": 16.45, "train_speed(iter/s)": 0.134192, "epoch": 0.00535045, "global_step/max_steps": "10/1869", "percentage": "0.54%", "elapsed_time": "45s", "remaining_time": "2h 19m 25s"}
-{"eval_loss": 0.87941688, "eval_token_acc": 0.77941276, "eval_runtime": 47.0919, "eval_samples_per_second": 9.811, "eval_steps_per_second": 1.232, "epoch": 0.00535045, "global_step/max_steps": "10/1869", "percentage": "0.54%", "elapsed_time": "1m 32s", "remaining_time": "4h 45m 20s"}
-{"loss": 0.78370821, "token_acc": 0.78277115, "grad_norm": 3.82993841, "learning_rate": 5.9e-07, "memory(GiB)": 42.26, "train_speed(iter/s)": 0.07966, "epoch": 0.0058855, "global_step/max_steps": "11/1869", "percentage": "0.59%", "elapsed_time": "1m 48s", "remaining_time": "5h 5m 38s"}
-{"loss": 0.83504999, "token_acc": 0.76751592, "grad_norm": 4.17722225, "learning_rate": 6.4e-07, "memory(GiB)": 42.26, "train_speed(iter/s)": 0.083596, "epoch": 0.00642055, "global_step/max_steps": "12/1869", "percentage": "0.64%", "elapsed_time": "1m 54s", "remaining_time": "4h 54m 5s"}
-{"loss": 0.95790565, "token_acc": 0.71612903, "grad_norm": 4.68048906, "learning_rate": 7e-07, "memory(GiB)": 42.26, "train_speed(iter/s)": 0.089234, "epoch": 0.00695559, "global_step/max_steps": "13/1869", "percentage": "0.70%", "elapsed_time": "1m 56s", "remaining_time": "4h 36m 24s"}
-{"loss": 0.70565331, "token_acc": 0.84732824, "grad_norm": 3.35217595, "learning_rate": 7.5e-07, "memory(GiB)": 42.26, "train_speed(iter/s)": 0.092582, "epoch": 0.00749064, "global_step/max_steps": "14/1869", "percentage": "0.75%", "elapsed_time": "2m 1s", "remaining_time": "4h 28m 44s"}
-{"loss": 0.81927258, "token_acc": 0.78723891, "grad_norm": 4.12418127, "learning_rate": 8e-07, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.095716, "epoch": 0.00802568, "global_step/max_steps": "15/1869", "percentage": "0.80%", "elapsed_time": "2m 7s", "remaining_time": "4h 22m 1s"}
-{"loss": 0.7351442, "token_acc": 0.83187391, "grad_norm": 3.27488399, "learning_rate": 8.6e-07, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.101055, "epoch": 0.00856073, "global_step/max_steps": "16/1869", "percentage": "0.86%", "elapsed_time": "2m 8s", "remaining_time": "4h 8m 37s"}
-{"loss": 0.77999592, "token_acc": 0.77183406, "grad_norm": 13.16994381, "learning_rate": 9.1e-07, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106293, "epoch": 0.00909577, "global_step/max_steps": "17/1869", "percentage": "0.91%", "elapsed_time": "2m 10s", "remaining_time": "3h 56m 47s"}
-{"loss": 0.70006078, "token_acc": 0.85483871, "grad_norm": 3.84622741, "learning_rate": 9.6e-07, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111411, "epoch": 0.00963082, "global_step/max_steps": "18/1869", "percentage": "0.96%", "elapsed_time": "2m 12s", "remaining_time": "3h 46m 18s"}
-{"loss": 0.69562626, "token_acc": 0.83034773, "grad_norm": 2.94428468, "learning_rate": 1.02e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.116139, "epoch": 0.01016586, "global_step/max_steps": "19/1869", "percentage": "1.02%", "elapsed_time": "2m 14s", "remaining_time": "3h 37m 35s"}
-{"loss": 0.72194958, "token_acc": 0.74902975, "grad_norm": 2.36996722, "learning_rate": 1.07e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.119257, "epoch": 0.01070091, "global_step/max_steps": "20/1869", "percentage": "1.07%", "elapsed_time": "2m 18s", "remaining_time": "3h 32m 55s"}
-{"eval_loss": 0.7312116, "eval_token_acc": 0.79288082, "eval_runtime": 47.2359, "eval_samples_per_second": 9.781, "eval_steps_per_second": 1.228, "epoch": 0.01070091, "global_step/max_steps": "20/1869", "percentage": "1.07%", "elapsed_time": "3m 5s", "remaining_time": "4h 45m 42s"}
-{"loss": 0.70447195, "token_acc": 0.79690628, "grad_norm": 2.32526183, "learning_rate": 1.12e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.092843, "epoch": 0.01123596, "global_step/max_steps": "21/1869", "percentage": "1.12%", "elapsed_time": "3m 16s", "remaining_time": "4h 48m 26s"}
-{"loss": 0.75664651, "token_acc": 0.78032037, "grad_norm": 2.3690176, "learning_rate": 1.18e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.094939, "epoch": 0.011771, "global_step/max_steps": "22/1869", "percentage": "1.18%", "elapsed_time": "3m 22s", "remaining_time": "4h 42m 56s"}
-{"loss": 0.71143919, "token_acc": 0.77868852, "grad_norm": 1.86084819, "learning_rate": 1.23e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.096928, "epoch": 0.01230605, "global_step/max_steps": "23/1869", "percentage": "1.23%", "elapsed_time": "3m 27s", "remaining_time": "4h 37m 55s"}
-{"loss": 0.57238525, "token_acc": 0.89502262, "grad_norm": 1.65031064, "learning_rate": 1.28e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.100248, "epoch": 0.01284109, "global_step/max_steps": "24/1869", "percentage": "1.28%", "elapsed_time": "3m 29s", "remaining_time": "4h 28m 55s"}
-{"loss": 0.68685579, "token_acc": 0.79934211, "grad_norm": 2.21920037, "learning_rate": 1.34e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.103027, "epoch": 0.01337614, "global_step/max_steps": "25/1869", "percentage": "1.34%", "elapsed_time": "3m 33s", "remaining_time": "4h 22m 0s"}
-{"loss": 0.67744565, "token_acc": 0.79525593, "grad_norm": 1.98912394, "learning_rate": 1.39e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106434, "epoch": 0.01391118, "global_step/max_steps": "26/1869", "percentage": "1.39%", "elapsed_time": "3m 34s", "remaining_time": "4h 13m 43s"}
-{"loss": 0.60103244, "token_acc": 0.85245902, "grad_norm": 1.69945383, "learning_rate": 1.44e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.109795, "epoch": 0.01444623, "global_step/max_steps": "27/1869", "percentage": "1.44%", "elapsed_time": "3m 36s", "remaining_time": "4h 6m 2s"}
-{"loss": 0.61611456, "token_acc": 0.88035639, "grad_norm": 1.65962636, "learning_rate": 1.5e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111339, "epoch": 0.01498127, "global_step/max_steps": "28/1869", "percentage": "1.50%", "elapsed_time": "3m 41s", "remaining_time": "4h 3m 14s"}
-{"loss": 0.62859809, "token_acc": 0.80737705, "grad_norm": 1.79358125, "learning_rate": 1.55e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.114566, "epoch": 0.01551632, "global_step/max_steps": "29/1869", "percentage": "1.55%", "elapsed_time": "3m 43s", "remaining_time": "3h 56m 27s"}
-{"loss": 0.56487948, "token_acc": 0.82064298, "grad_norm": 1.58352077, "learning_rate": 1.6e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.117766, "epoch": 0.01605136, "global_step/max_steps": "30/1869", "percentage": "1.61%", "elapsed_time": "3m 45s", "remaining_time": "3h 50m 6s"}
-{"eval_loss": 0.65829676, "eval_token_acc": 0.8001531, "eval_runtime": 47.0799, "eval_samples_per_second": 9.813, "eval_steps_per_second": 1.232, "epoch": 0.01605136, "global_step/max_steps": "30/1869", "percentage": "1.61%", "elapsed_time": "4m 32s", "remaining_time": "4h 38m 12s"}
-{"loss": 0.67666018, "token_acc": 0.80539966, "grad_norm": 2.33286023, "learning_rate": 1.66e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.097787, "epoch": 0.01658641, "global_step/max_steps": "31/1869", "percentage": "1.66%", "elapsed_time": "4m 47s", "remaining_time": "4h 44m 5s"}
-{"loss": 0.63778967, "token_acc": 0.80305891, "grad_norm": 2.01571345, "learning_rate": 1.71e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.099226, "epoch": 0.01712146, "global_step/max_steps": "32/1869", "percentage": "1.71%", "elapsed_time": "4m 52s", "remaining_time": "4h 40m 18s"}
-{"loss": 0.59222853, "token_acc": 0.7991121, "grad_norm": 1.66044676, "learning_rate": 1.76e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.101818, "epoch": 0.0176565, "global_step/max_steps": "33/1869", "percentage": "1.77%", "elapsed_time": "4m 54s", "remaining_time": "4h 33m 9s"}
-{"loss": 0.69081396, "token_acc": 0.7992126, "grad_norm": 1.77187538, "learning_rate": 1.82e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.104384, "epoch": 0.01819155, "global_step/max_steps": "34/1869", "percentage": "1.82%", "elapsed_time": "4m 56s", "remaining_time": "4h 26m 26s"}
-{"loss": 0.67318571, "token_acc": 0.79340278, "grad_norm": 1.85111713, "learning_rate": 1.87e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.10676, "epoch": 0.01872659, "global_step/max_steps": "35/1869", "percentage": "1.87%", "elapsed_time": "4m 58s", "remaining_time": "4h 20m 32s"}
-{"loss": 0.67253304, "token_acc": 0.86307054, "grad_norm": 1.59842598, "learning_rate": 1.93e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.108967, "epoch": 0.01926164, "global_step/max_steps": "36/1869", "percentage": "1.93%", "elapsed_time": "5m 0s", "remaining_time": "4h 15m 18s"}
-{"loss": 0.5134393, "token_acc": 0.81165049, "grad_norm": 1.45173693, "learning_rate": 1.98e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111451, "epoch": 0.01979668, "global_step/max_steps": "37/1869", "percentage": "1.98%", "elapsed_time": "5m 2s", "remaining_time": "4h 9m 36s"}
-{"loss": 0.58593655, "token_acc": 0.89829659, "grad_norm": 1.75730073, "learning_rate": 2.03e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.113312, "epoch": 0.02033173, "global_step/max_steps": "38/1869", "percentage": "2.03%", "elapsed_time": "5m 5s", "remaining_time": "4h 5m 36s"}
-{"loss": 0.65140462, "token_acc": 0.7693041, "grad_norm": 2.10822535, "learning_rate": 2.09e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.115498, "epoch": 0.02086677, "global_step/max_steps": "39/1869", "percentage": "2.09%", "elapsed_time": "5m 8s", "remaining_time": "4h 0m 59s"}
-{"loss": 0.57421994, "token_acc": 0.75711382, "grad_norm": 1.53696847, "learning_rate": 2.14e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.117897, "epoch": 0.02140182, "global_step/max_steps": "40/1869", "percentage": "2.14%", "elapsed_time": "5m 9s", "remaining_time": "3h 56m 3s"}
-{"eval_loss": 0.6192683, "eval_token_acc": 0.80489669, "eval_runtime": 47.2084, "eval_samples_per_second": 9.786, "eval_steps_per_second": 1.229, "epoch": 0.02140182, "global_step/max_steps": "40/1869", "percentage": "2.14%", "elapsed_time": "5m 56s", "remaining_time": "4h 32m 2s"}
-{"loss": 0.55008793, "token_acc": 0.80942272, "grad_norm": 1.61669028, "learning_rate": 2.19e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.102395, "epoch": 0.02193686, "global_step/max_steps": "41/1869", "percentage": "2.19%", "elapsed_time": "6m 10s", "remaining_time": "4h 35m 36s"}
-{"loss": 0.62053865, "token_acc": 0.77777778, "grad_norm": 2.01010704, "learning_rate": 2.25e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.104464, "epoch": 0.02247191, "global_step/max_steps": "42/1869", "percentage": "2.25%", "elapsed_time": "6m 12s", "remaining_time": "4h 30m 5s"}
-{"loss": 0.55582368, "token_acc": 0.83614458, "grad_norm": 1.91279387, "learning_rate": 2.3e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106527, "epoch": 0.02300696, "global_step/max_steps": "43/1869", "percentage": "2.30%", "elapsed_time": "6m 14s", "remaining_time": "4h 24m 47s"}
-{"loss": 0.63187927, "token_acc": 0.8298109, "grad_norm": 1.11072254, "learning_rate": 2.35e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.107514, "epoch": 0.023542, "global_step/max_steps": "44/1869", "percentage": "2.35%", "elapsed_time": "6m 19s", "remaining_time": "4h 22m 30s"}
-{"loss": 0.63910359, "token_acc": 0.84244792, "grad_norm": 2.4335506, "learning_rate": 2.41e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.109528, "epoch": 0.02407705, "global_step/max_steps": "45/1869", "percentage": "2.41%", "elapsed_time": "6m 21s", "remaining_time": "4h 17m 36s"}
-{"loss": 0.60400552, "token_acc": 0.86158401, "grad_norm": 2.22681427, "learning_rate": 2.46e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111339, "epoch": 0.02461209, "global_step/max_steps": "46/1869", "percentage": "2.46%", "elapsed_time": "6m 23s", "remaining_time": "4h 13m 23s"}
-{"loss": 0.67614436, "token_acc": 0.84046693, "grad_norm": 1.86316872, "learning_rate": 2.51e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.113318, "epoch": 0.02514714, "global_step/max_steps": "47/1869", "percentage": "2.51%", "elapsed_time": "6m 25s", "remaining_time": "4h 8m 54s"}
-{"loss": 0.54839796, "token_acc": 0.79958027, "grad_norm": 1.43800616, "learning_rate": 2.57e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.115267, "epoch": 0.02568218, "global_step/max_steps": "48/1869", "percentage": "2.57%", "elapsed_time": "6m 26s", "remaining_time": "4h 4m 38s"}
-{"loss": 0.61684155, "token_acc": 0.77229299, "grad_norm": 1.36796963, "learning_rate": 2.62e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.11613, "epoch": 0.02621723, "global_step/max_steps": "49/1869", "percentage": "2.62%", "elapsed_time": "6m 32s", "remaining_time": "4h 2m 55s"}
-{"loss": 0.52599233, "token_acc": 0.89716312, "grad_norm": 1.61794019, "learning_rate": 2.67e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.118051, "epoch": 0.02675227, "global_step/max_steps": "50/1869", "percentage": "2.68%", "elapsed_time": "6m 34s", "remaining_time": "3h 58m 54s"}
-{"eval_loss": 0.59815454, "eval_token_acc": 0.80803328, "eval_runtime": 47.1012, "eval_samples_per_second": 9.809, "eval_steps_per_second": 1.231, "epoch": 0.02675227, "global_step/max_steps": "50/1869", "percentage": "2.68%", "elapsed_time": "7m 21s", "remaining_time": "4h 27m 28s"}
-{"loss": 0.51500702, "token_acc": 0.81298095, "grad_norm": 1.52756071, "learning_rate": 2.73e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.105011, "epoch": 0.02728732, "global_step/max_steps": "51/1869", "percentage": "2.73%", "elapsed_time": "7m 36s", "remaining_time": "4h 31m 0s"}
-{"loss": 0.58626986, "token_acc": 0.81697613, "grad_norm": 3.09773326, "learning_rate": 2.78e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.105844, "epoch": 0.02782236, "global_step/max_steps": "52/1869", "percentage": "2.78%", "elapsed_time": "7m 41s", "remaining_time": "4h 28m 55s"}
-{"loss": 0.63133675, "token_acc": 0.75462963, "grad_norm": 1.64922523, "learning_rate": 2.83e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.107526, "epoch": 0.02835741, "global_step/max_steps": "53/1869", "percentage": "2.84%", "elapsed_time": "7m 43s", "remaining_time": "4h 24m 37s"}
-{"loss": 0.4953768, "token_acc": 0.83932347, "grad_norm": 1.70219147, "learning_rate": 2.89e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.108906, "epoch": 0.02889246, "global_step/max_steps": "54/1869", "percentage": "2.89%", "elapsed_time": "7m 46s", "remaining_time": "4h 21m 13s"}
-{"loss": 0.482317, "token_acc": 0.88925803, "grad_norm": 1.33054411, "learning_rate": 2.94e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.110562, "epoch": 0.0294275, "global_step/max_steps": "55/1869", "percentage": "2.94%", "elapsed_time": "7m 47s", "remaining_time": "4h 17m 13s"}
-{"loss": 0.54709989, "token_acc": 0.83463035, "grad_norm": 1.64871359, "learning_rate": 2.99e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.11221, "epoch": 0.02996255, "global_step/max_steps": "56/1869", "percentage": "3.00%", "elapsed_time": "7m 49s", "remaining_time": "4h 13m 21s"}
-{"loss": 0.59203637, "token_acc": 0.80776014, "grad_norm": 1.6295495, "learning_rate": 3.05e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.113744, "epoch": 0.03049759, "global_step/max_steps": "57/1869", "percentage": "3.05%", "elapsed_time": "7m 51s", "remaining_time": "4h 9m 52s"}
-{"loss": 0.55395043, "token_acc": 0.8650519, "grad_norm": 1.50918293, "learning_rate": 3.1e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.114486, "epoch": 0.03103264, "global_step/max_steps": "58/1869", "percentage": "3.10%", "elapsed_time": "7m 57s", "remaining_time": "4h 8m 16s"}
-{"loss": 0.52487975, "token_acc": 0.79044517, "grad_norm": 1.46274054, "learning_rate": 3.16e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.116092, "epoch": 0.03156768, "global_step/max_steps": "59/1869", "percentage": "3.16%", "elapsed_time": "7m 58s", "remaining_time": "4h 4m 45s"}
-{"loss": 0.58494765, "token_acc": 0.78531073, "grad_norm": 3.75680161, "learning_rate": 3.21e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.117693, "epoch": 0.03210273, "global_step/max_steps": "60/1869", "percentage": "3.21%", "elapsed_time": "8m 0s", "remaining_time": "4h 1m 20s"}
-{"eval_loss": 0.58433348, "eval_token_acc": 0.81007931, "eval_runtime": 47.2718, "eval_samples_per_second": 9.773, "eval_steps_per_second": 1.227, "epoch": 0.03210273, "global_step/max_steps": "60/1869", "percentage": "3.21%", "elapsed_time": "8m 47s", "remaining_time": "4h 25m 5s"}
-{"loss": 0.46443856, "token_acc": 0.81141288, "grad_norm": 1.25838745, "learning_rate": 3.26e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106316, "epoch": 0.03263777, "global_step/max_steps": "61/1869", "percentage": "3.26%", "elapsed_time": "9m 4s", "remaining_time": "4h 28m 51s"}
-{"loss": 0.61769801, "token_acc": 0.85033113, "grad_norm": 1.79472578, "learning_rate": 3.32e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.107026, "epoch": 0.03317282, "global_step/max_steps": "62/1869", "percentage": "3.32%", "elapsed_time": "9m 9s", "remaining_time": "4h 27m 3s"}
-{"loss": 0.57896692, "token_acc": 0.82039574, "grad_norm": 1.62414014, "learning_rate": 3.37e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.108433, "epoch": 0.03370787, "global_step/max_steps": "63/1869", "percentage": "3.37%", "elapsed_time": "9m 11s", "remaining_time": "4h 23m 29s"}
-{"loss": 0.5766288, "token_acc": 0.84592593, "grad_norm": 1.42683816, "learning_rate": 3.42e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.10985, "epoch": 0.03424291, "global_step/max_steps": "64/1869", "percentage": "3.42%", "elapsed_time": "9m 13s", "remaining_time": "4h 19m 59s"}
-{"loss": 0.55697632, "token_acc": 0.88038278, "grad_norm": 1.73366427, "learning_rate": 3.48e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111046, "epoch": 0.03477796, "global_step/max_steps": "65/1869", "percentage": "3.48%", "elapsed_time": "9m 15s", "remaining_time": "4h 17m 6s"}
-{"loss": 0.52125347, "token_acc": 0.7486911, "grad_norm": 1.34537971, "learning_rate": 3.53e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.112359, "epoch": 0.035313, "global_step/max_steps": "66/1869", "percentage": "3.53%", "elapsed_time": "9m 17s", "remaining_time": "4h 14m 0s"}
-{"loss": 0.57437229, "token_acc": 0.73727088, "grad_norm": 1.39122069, "learning_rate": 3.58e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.113746, "epoch": 0.03584805, "global_step/max_steps": "67/1869", "percentage": "3.58%", "elapsed_time": "9m 19s", "remaining_time": "4h 10m 48s"}
-{"loss": 0.55027413, "token_acc": 0.8056338, "grad_norm": 1.32035482, "learning_rate": 3.64e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.114339, "epoch": 0.03638309, "global_step/max_steps": "68/1869", "percentage": "3.64%", "elapsed_time": "9m 25s", "remaining_time": "4h 9m 29s"}
-{"loss": 0.48549351, "token_acc": 0.81279621, "grad_norm": 1.4051944, "learning_rate": 3.69e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.115625, "epoch": 0.03691814, "global_step/max_steps": "69/1869", "percentage": "3.69%", "elapsed_time": "9m 27s", "remaining_time": "4h 6m 37s"}
-{"loss": 0.60460436, "token_acc": 0.85180055, "grad_norm": 1.62005782, "learning_rate": 3.74e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.116986, "epoch": 0.03745318, "global_step/max_steps": "70/1869", "percentage": "3.75%", "elapsed_time": "9m 28s", "remaining_time": "4h 3m 39s"}
-{"eval_loss": 0.57551694, "eval_token_acc": 0.81163705, "eval_runtime": 47.0777, "eval_samples_per_second": 9.814, "eval_steps_per_second": 1.232, "epoch": 0.03745318, "global_step/max_steps": "70/1869", "percentage": "3.75%", "elapsed_time": "10m 15s", "remaining_time": "4h 23m 49s"}
-{"loss": 0.65082449, "token_acc": 0.81581842, "grad_norm": 2.58263063, "learning_rate": 3.8e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106935, "epoch": 0.03798823, "global_step/max_steps": "71/1869", "percentage": "3.80%", "elapsed_time": "10m 34s", "remaining_time": "4h 27m 46s"}
-{"loss": 0.53372353, "token_acc": 0.79391101, "grad_norm": 3.0744555, "learning_rate": 3.85e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.10818, "epoch": 0.03852327, "global_step/max_steps": "72/1869", "percentage": "3.85%", "elapsed_time": "10m 36s", "remaining_time": "4h 24m 34s"}
-{"loss": 0.54805946, "token_acc": 0.90681972, "grad_norm": 1.42983079, "learning_rate": 3.9e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.109057, "epoch": 0.03905832, "global_step/max_steps": "73/1869", "percentage": "3.91%", "elapsed_time": "10m 39s", "remaining_time": "4h 22m 22s"}
-{"loss": 0.58714354, "token_acc": 0.81207977, "grad_norm": 1.46257544, "learning_rate": 3.96e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.109644, "epoch": 0.03959337, "global_step/max_steps": "74/1869", "percentage": "3.96%", "elapsed_time": "10m 45s", "remaining_time": "4h 20m 55s"}
-{"loss": 0.54388595, "token_acc": 0.86413043, "grad_norm": 1.51115882, "learning_rate": 4.01e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.110512, "epoch": 0.04012841, "global_step/max_steps": "75/1869", "percentage": "4.01%", "elapsed_time": "10m 49s", "remaining_time": "4h 18m 47s"}
-{"loss": 0.59524173, "token_acc": 0.81431005, "grad_norm": 1.71415317, "learning_rate": 4.06e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111063, "epoch": 0.04066346, "global_step/max_steps": "76/1869", "percentage": "4.07%", "elapsed_time": "10m 54s", "remaining_time": "4h 17m 27s"}
-{"loss": 0.52272701, "token_acc": 0.81502086, "grad_norm": 1.49193454, "learning_rate": 4.12e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.112198, "epoch": 0.0411985, "global_step/max_steps": "77/1869", "percentage": "4.12%", "elapsed_time": "10m 56s", "remaining_time": "4h 14m 44s"}
-{"loss": 0.54098392, "token_acc": 0.77158556, "grad_norm": 1.36165345, "learning_rate": 4.17e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.112744, "epoch": 0.04173355, "global_step/max_steps": "78/1869", "percentage": "4.17%", "elapsed_time": "11m 2s", "remaining_time": "4h 13m 27s"}
-{"loss": 0.47549939, "token_acc": 0.85929108, "grad_norm": 1.3266083, "learning_rate": 4.22e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.113893, "epoch": 0.04226859, "global_step/max_steps": "79/1869", "percentage": "4.23%", "elapsed_time": "11m 4s", "remaining_time": "4h 10m 47s"}
-{"loss": 0.58747751, "token_acc": 0.80721003, "grad_norm": 1.52579451, "learning_rate": 4.28e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.115065, "epoch": 0.04280364, "global_step/max_steps": "80/1869", "percentage": "4.28%", "elapsed_time": "11m 5s", "remaining_time": "4h 8m 7s"}
-{"eval_loss": 0.56743366, "eval_token_acc": 0.81274731, "eval_runtime": 47.2509, "eval_samples_per_second": 9.778, "eval_steps_per_second": 1.227, "epoch": 0.04280364, "global_step/max_steps": "80/1869", "percentage": "4.28%", "elapsed_time": "11m 52s", "remaining_time": "4h 25m 44s"}
-{"loss": 0.48316047, "token_acc": 0.81631618, "grad_norm": 1.04880619, "learning_rate": 4.33e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106718, "epoch": 0.04333868, "global_step/max_steps": "81/1869", "percentage": "4.33%", "elapsed_time": "12m 9s", "remaining_time": "4h 28m 22s"}
-{"loss": 0.62238801, "token_acc": 0.85031847, "grad_norm": 1.49701905, "learning_rate": 4.39e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.107587, "epoch": 0.04387373, "global_step/max_steps": "82/1869", "percentage": "4.39%", "elapsed_time": "12m 12s", "remaining_time": "4h 26m 6s"}
-{"loss": 0.64975607, "token_acc": 0.81523096, "grad_norm": 2.14597869, "learning_rate": 4.44e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.108118, "epoch": 0.04440877, "global_step/max_steps": "83/1869", "percentage": "4.44%", "elapsed_time": "12m 18s", "remaining_time": "4h 24m 43s"}
-{"loss": 0.68609977, "token_acc": 0.74051593, "grad_norm": 2.03061819, "learning_rate": 4.49e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.109072, "epoch": 0.04494382, "global_step/max_steps": "84/1869", "percentage": "4.49%", "elapsed_time": "12m 20s", "remaining_time": "4h 22m 18s"}
-{"loss": 0.56360674, "token_acc": 0.91630901, "grad_norm": 1.38109756, "learning_rate": 4.55e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.109579, "epoch": 0.04547887, "global_step/max_steps": "85/1869", "percentage": "4.55%", "elapsed_time": "12m 26s", "remaining_time": "4h 21m 0s"}
-{"loss": 0.62571561, "token_acc": 0.84673748, "grad_norm": 1.27034843, "learning_rate": 4.6e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.110082, "epoch": 0.04601391, "global_step/max_steps": "86/1869", "percentage": "4.60%", "elapsed_time": "12m 31s", "remaining_time": "4h 19m 45s"}
-{"loss": 0.54031986, "token_acc": 0.78795009, "grad_norm": 1.31914854, "learning_rate": 4.65e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.110572, "epoch": 0.04654896, "global_step/max_steps": "87/1869", "percentage": "4.65%", "elapsed_time": "12m 37s", "remaining_time": "4h 18m 31s"}
-{"loss": 0.65481579, "token_acc": 0.83529412, "grad_norm": 1.73724616, "learning_rate": 4.71e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111533, "epoch": 0.047084, "global_step/max_steps": "88/1869", "percentage": "4.71%", "elapsed_time": "12m 39s", "remaining_time": "4h 16m 10s"}
-{"loss": 0.51929009, "token_acc": 0.88250211, "grad_norm": 1.41756928, "learning_rate": 4.76e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.112575, "epoch": 0.04761905, "global_step/max_steps": "89/1869", "percentage": "4.76%", "elapsed_time": "12m 41s", "remaining_time": "4h 13m 41s"}
-{"loss": 0.55096114, "token_acc": 0.84288194, "grad_norm": 1.25196993, "learning_rate": 4.81e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.113037, "epoch": 0.04815409, "global_step/max_steps": "90/1869", "percentage": "4.82%", "elapsed_time": "12m 46s", "remaining_time": "4h 12m 34s"}
-{"eval_loss": 0.56129301, "eval_token_acc": 0.81405176, "eval_runtime": 47.0588, "eval_samples_per_second": 9.818, "eval_steps_per_second": 1.233, "epoch": 0.04815409, "global_step/max_steps": "90/1869", "percentage": "4.82%", "elapsed_time": "13m 33s", "remaining_time": "4h 28m 4s"}
-{"loss": 0.53046155, "token_acc": 0.81791535, "grad_norm": 1.88198757, "learning_rate": 4.87e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106037, "epoch": 0.04868914, "global_step/max_steps": "91/1869", "percentage": "4.87%", "elapsed_time": "13m 48s", "remaining_time": "4h 29m 50s"}
-{"loss": 0.56067884, "token_acc": 0.8008658, "grad_norm": 1.45423341, "learning_rate": 4.92e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.107, "epoch": 0.04922418, "global_step/max_steps": "92/1869", "percentage": "4.92%", "elapsed_time": "13m 50s", "remaining_time": "4h 27m 17s"}
-{"loss": 0.55585885, "token_acc": 0.84927798, "grad_norm": 1.86327994, "learning_rate": 4.97e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.107958, "epoch": 0.04975923, "global_step/max_steps": "93/1869", "percentage": "4.98%", "elapsed_time": "13m 51s", "remaining_time": "4h 24m 47s"}
-{"loss": 0.59563416, "token_acc": 0.81107334, "grad_norm": 1.88972461, "learning_rate": 5.03e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.108748, "epoch": 0.05029428, "global_step/max_steps": "94/1869", "percentage": "5.03%", "elapsed_time": "13m 54s", "remaining_time": "4h 22m 44s"}
-{"loss": 0.5046066, "token_acc": 0.82798834, "grad_norm": 1.68154716, "learning_rate": 5.08e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.1097, "epoch": 0.05082932, "global_step/max_steps": "95/1869", "percentage": "5.08%", "elapsed_time": "13m 56s", "remaining_time": "4h 20m 20s"}
-{"loss": 0.5304262, "token_acc": 0.7694859, "grad_norm": 1.43992364, "learning_rate": 5.13e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.110154, "epoch": 0.05136437, "global_step/max_steps": "96/1869", "percentage": "5.14%", "elapsed_time": "14m 1s", "remaining_time": "4h 19m 10s"}
-{"loss": 0.61991286, "token_acc": 0.75282309, "grad_norm": 3.14522028, "learning_rate": 5.19e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.111095, "epoch": 0.05189941, "global_step/max_steps": "97/1869", "percentage": "5.19%", "elapsed_time": "14m 3s", "remaining_time": "4h 16m 50s"}
-{"loss": 0.63002944, "token_acc": 0.85375494, "grad_norm": 1.59012771, "learning_rate": 5.24e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.112033, "epoch": 0.05243446, "global_step/max_steps": "98/1869", "percentage": "5.24%", "elapsed_time": "14m 5s", "remaining_time": "4h 14m 34s"}
-{"loss": 0.68490446, "token_acc": 0.73425197, "grad_norm": 1.70764339, "learning_rate": 5.29e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.112442, "epoch": 0.0529695, "global_step/max_steps": "99/1869", "percentage": "5.30%", "elapsed_time": "14m 10s", "remaining_time": "4h 13m 33s"}
-{"loss": 0.6501677, "token_acc": 0.8412943, "grad_norm": 1.77475035, "learning_rate": 5.35e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.11307, "epoch": 0.05350455, "global_step/max_steps": "100/1869", "percentage": "5.35%", "elapsed_time": "14m 14s", "remaining_time": "4h 12m 3s"}
-{"eval_loss": 0.55701578, "eval_token_acc": 0.81466107, "eval_runtime": 47.3417, "eval_samples_per_second": 9.759, "eval_steps_per_second": 1.225, "epoch": 0.05350455, "global_step/max_steps": "100/1869", "percentage": "5.35%", "elapsed_time": "15m 2s", "remaining_time": "4h 26m 0s"}
-{"loss": 0.57124013, "token_acc": 0.81866145, "grad_norm": 1.6674912, "learning_rate": 5.4e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.106939, "epoch": 0.05403959, "global_step/max_steps": "101/1869", "percentage": "5.40%", "elapsed_time": "15m 14s", "remaining_time": "4h 26m 56s"}
-{"loss": 0.5822041, "token_acc": 0.80506823, "grad_norm": 1.47916698, "learning_rate": 5.45e-06, "memory(GiB)": 49.79, "train_speed(iter/s)": 0.107373, "epoch": 0.05457464, "global_step/max_steps": "102/1869", "percentage": "5.46%", "elapsed_time": "15m 20s", "remaining_time": "4h 25m 45s"}
-{"loss": 0.60072786, "token_acc": 0.83898186, "grad_norm": 1.28622961, "learning_rate": 5.51e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.10782, "epoch": 0.05510968, "global_step/max_steps": "103/1869", "percentage": "5.51%", "elapsed_time": "15m 25s", "remaining_time": "4h 24m 33s"}
-{"loss": 0.53927904, "token_acc": 0.82990868, "grad_norm": 2.01003194, "learning_rate": 5.56e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.108684, "epoch": 0.05564473, "global_step/max_steps": "104/1869", "percentage": "5.56%", "elapsed_time": "15m 27s", "remaining_time": "4h 22m 18s"}
-{"loss": 0.55231047, "token_acc": 0.88588008, "grad_norm": 2.33709693, "learning_rate": 5.61e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.109544, "epoch": 0.05617978, "global_step/max_steps": "105/1869", "percentage": "5.62%", "elapsed_time": "15m 29s", "remaining_time": "4h 20m 7s"}
-{"loss": 0.52443862, "token_acc": 0.91080402, "grad_norm": 1.46956873, "learning_rate": 5.67e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.110399, "epoch": 0.05671482, "global_step/max_steps": "106/1869", "percentage": "5.67%", "elapsed_time": "15m 30s", "remaining_time": "4h 17m 58s"}
-{"loss": 0.59382796, "token_acc": 0.78, "grad_norm": 1.66870689, "learning_rate": 5.72e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.110805, "epoch": 0.05724987, "global_step/max_steps": "107/1869", "percentage": "5.72%", "elapsed_time": "15m 36s", "remaining_time": "4h 16m 55s"}
-{"loss": 0.49897149, "token_acc": 0.85014409, "grad_norm": 1.56035566, "learning_rate": 5.78e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.111209, "epoch": 0.05778491, "global_step/max_steps": "108/1869", "percentage": "5.78%", "elapsed_time": "15m 41s", "remaining_time": "4h 15m 53s"}
-{"loss": 0.5497005, "token_acc": 0.88143177, "grad_norm": 1.39917779, "learning_rate": 5.83e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.111584, "epoch": 0.05831996, "global_step/max_steps": "109/1869", "percentage": "5.83%", "elapsed_time": "15m 47s", "remaining_time": "4h 14m 56s"}
-{"loss": 0.55191898, "token_acc": 0.8778135, "grad_norm": 1.57978892, "learning_rate": 5.88e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.112422, "epoch": 0.058855, "global_step/max_steps": "110/1869", "percentage": "5.89%", "elapsed_time": "15m 48s", "remaining_time": "4h 12m 54s"}
-{"eval_loss": 0.55265617, "eval_token_acc": 0.81567564, "eval_runtime": 47.043, "eval_samples_per_second": 9.821, "eval_steps_per_second": 1.233, "epoch": 0.058855, "global_step/max_steps": "110/1869", "percentage": "5.89%", "elapsed_time": "16m 35s", "remaining_time": "4h 25m 26s"}
-{"loss": 0.51185912, "token_acc": 0.82028027, "grad_norm": 1.4405241, "learning_rate": 5.94e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.106683, "epoch": 0.05939005, "global_step/max_steps": "111/1869", "percentage": "5.94%", "elapsed_time": "16m 50s", "remaining_time": "4h 26m 51s"}
-{"loss": 0.52429932, "token_acc": 0.80310881, "grad_norm": 1.38541508, "learning_rate": 5.99e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.107074, "epoch": 0.05992509, "global_step/max_steps": "112/1869", "percentage": "5.99%", "elapsed_time": "16m 56s", "remaining_time": "4h 25m 46s"}
-{"loss": 0.52454728, "token_acc": 0.86216216, "grad_norm": 1.48425007, "learning_rate": 6.04e-06, "memory(GiB)": 50.75, "train_speed(iter/s)": 0.107862, "epoch": 0.06046014, "global_step/max_steps": "113/1869", "percentage": "6.05%", "elapsed_time": "16m 58s", "remaining_time": "4h 23m 41s"}
+{"loss": 0.86834621, "token_acc": 0.76144271, "grad_norm": 0.21878828, "learning_rate": 6.3e-07, "memory(GiB)": 59.9, "train_speed(iter/s)": 0.007309, "epoch": 0.00642055, "global_step/max_steps": "1/155", "percentage": "0.65%", "elapsed_time": "1m 54s", "remaining_time": "4h 52m 58s"}
+{"loss": 0.86366093, "token_acc": 0.78811601, "grad_norm": 0.21468824, "learning_rate": 1.25e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.008595, "epoch": 0.01284109, "global_step/max_steps": "2/155", "percentage": "1.29%", "elapsed_time": "3m 30s", "remaining_time": "4h 27m 45s"}
+{"loss": 0.90281665, "token_acc": 0.79913376, "grad_norm": 0.24619138, "learning_rate": 1.88e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.010181, "epoch": 0.01926164, "global_step/max_steps": "3/155", "percentage": "1.94%", "elapsed_time": "4m 31s", "remaining_time": "3h 49m 40s"}
+{"loss": 0.84323382, "token_acc": 0.80474518, "grad_norm": 0.1970693, "learning_rate": 2.5e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.011353, "epoch": 0.02568218, "global_step/max_steps": "4/155", "percentage": "2.58%", "elapsed_time": "5m 29s", "remaining_time": "3h 27m 24s"}
+{"loss": 0.74751514, "token_acc": 0.80169356, "grad_norm": 0.13422348, "learning_rate": 3.13e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.011604, "epoch": 0.03210273, "global_step/max_steps": "5/155", "percentage": "3.23%", "elapsed_time": "6m 48s", "remaining_time": "3h 24m 6s"}
+{"loss": 0.71631718, "token_acc": 0.79562908, "grad_norm": 0.08512163, "learning_rate": 3.75e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.011477, "epoch": 0.03852327, "global_step/max_steps": "6/155", "percentage": "3.87%", "elapsed_time": "8m 20s", "remaining_time": "3h 26m 59s"}
+{"loss": 0.71378142, "token_acc": 0.81174975, "grad_norm": 0.06945583, "learning_rate": 4.38e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.010862, "epoch": 0.04494382, "global_step/max_steps": "7/155", "percentage": "4.52%", "elapsed_time": "10m 21s", "remaining_time": "3h 39m 5s"}
+{"loss": 0.69380641, "token_acc": 0.801244, "grad_norm": 0.09017567, "learning_rate": 5e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.010689, "epoch": 0.05136437, "global_step/max_steps": "8/155", "percentage": "5.16%", "elapsed_time": "12m 5s", "remaining_time": "3h 42m 15s"}
+{"loss": 0.67643952, "token_acc": 0.81240817, "grad_norm": 0.05537791, "learning_rate": 5.63e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.010578, "epoch": 0.05778491, "global_step/max_steps": "9/155", "percentage": "5.81%", "elapsed_time": "13m 48s", "remaining_time": "3h 43m 54s"}
+{"loss": 0.64333117, "token_acc": 0.84263524, "grad_norm": 0.05175444, "learning_rate": 6.25e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.010662, "epoch": 0.06420546, "global_step/max_steps": "10/155", "percentage": "6.45%", "elapsed_time": "15m 15s", "remaining_time": "3h 41m 10s"}
+{"eval_loss": 0.64980161, "eval_token_acc": 0.80824279, "eval_runtime": 133.5121, "eval_samples_per_second": 3.46, "eval_steps_per_second": 0.434, "epoch": 0.06420546, "global_step/max_steps": "10/155", "percentage": "6.45%", "elapsed_time": "17m 28s", "remaining_time": "4h 13m 26s"}
+{"loss": 0.62835079, "token_acc": 0.81465207, "grad_norm": 0.04356396, "learning_rate": 6.88e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.008883, "epoch": 0.070626, "global_step/max_steps": "11/155", "percentage": "7.10%", "elapsed_time": "20m 15s", "remaining_time": "4h 25m 14s"}
+{"loss": 0.63268352, "token_acc": 0.79883606, "grad_norm": 0.04725697, "learning_rate": 7.5e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.008954, "epoch": 0.07704655, "global_step/max_steps": "12/155", "percentage": "7.74%", "elapsed_time": "21m 57s", "remaining_time": "4h 21m 41s"}
+{"loss": 0.64129972, "token_acc": 0.81633919, "grad_norm": 0.04313954, "learning_rate": 8.13e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.008859, "epoch": 0.08346709, "global_step/max_steps": "13/155", "percentage": "8.39%", "elapsed_time": "24m 4s", "remaining_time": "4h 23m 0s"}
+{"loss": 0.65112805, "token_acc": 0.84125643, "grad_norm": 0.03417975, "learning_rate": 8.75e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.008684, "epoch": 0.08988764, "global_step/max_steps": "14/155", "percentage": "9.03%", "elapsed_time": "26m 29s", "remaining_time": "4h 26m 47s"}
+{"loss": 0.56955582, "token_acc": 0.8122474, "grad_norm": 0.04053972, "learning_rate": 9.38e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.008979, "epoch": 0.09630819, "global_step/max_steps": "15/155", "percentage": "9.68%", "elapsed_time": "27m 27s", "remaining_time": "4h 16m 20s"}
+{"loss": 0.62472343, "token_acc": 0.81533282, "grad_norm": 0.03049115, "learning_rate": 1e-05, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.009084, "epoch": 0.10272873, "global_step/max_steps": "16/155", "percentage": "10.32%", "elapsed_time": "28m 58s", "remaining_time": "4h 11m 44s"}
+{"loss": 0.55131125, "token_acc": 0.85763717, "grad_norm": 0.03121089, "learning_rate": 9.93e-06, "memory(GiB)": 128.19, "train_speed(iter/s)": 0.009275, "epoch": 0.10914928, "global_step/max_steps": "17/155", "percentage": "10.97%", "elapsed_time": "30m 10s", "remaining_time": "4h 4m 54s"}

special_tokens_map.json

@@ -1,24 +1,31 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": 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|>"
+  ],
   "eos_token": {
     "content": "<|im_end|>",
-    "lstrip": true,
+    "lstrip": false,
     "normalized": false,
-    "rstrip": true,
+    "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|dummy_85|>",
-    "lstrip": true,
+    "content": "<|endoftext|>",
+    "lstrip": false,
     "normalized": false,
-    "rstrip": true,
+    "rstrip": false,
     "single_word": false
-  },
-  "unk_token": "<|endoftext|>"
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c612e57b2763204798271c0cdc14a373a565e6a371f1bfbd44e385a8391c9884
-size 7153083
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -1,782 +1,208 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "100256": {
-      "content": "<|dummy_0|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100257": {
+    "151643": {
       "content": "<|endoftext|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100258": {
-      "content": "<|fim_prefix|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100259": {
-      "content": "<|fim_middle|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100260": {
-      "content": "<|fim_suffix|>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100261": {
-      "content": "<|dummy_1|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100262": {
-      "content": "<|dummy_2|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100263": {
-      "content": "<|dummy_3|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100264": {
+    "151644": {
       "content": "<|im_start|>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100265": {
+    "151645": {
       "content": "<|im_end|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100266": {
-      "content": "<|im_sep|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100267": {
-      "content": "<|dummy_4|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100268": {
-      "content": "<|dummy_5|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100269": {
-      "content": "<|dummy_6|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100270": {
-      "content": "<|dummy_7|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100271": {
-      "content": "<|dummy_8|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100272": {
-      "content": "<|dummy_9|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100273": {
-      "content": "<|dummy_10|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100274": {
-      "content": "<|dummy_11|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100275": {
-      "content": "<|dummy_12|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100276": {
-      "content": "<|endofprompt|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100277": {
-      "content": "<|dummy_13|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100278": {
-      "content": "<|dummy_14|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100279": {
-      "content": "<|dummy_15|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100280": {
-      "content": "<|dummy_16|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100281": {
-      "content": "<|dummy_17|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100282": {
-      "content": "<|dummy_18|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100283": {
-      "content": "<|dummy_19|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100284": {
-      "content": "<|dummy_20|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100285": {
-      "content": "<|dummy_21|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100286": {
-      "content": "<|dummy_22|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100287": {
-      "content": "<|dummy_23|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100288": {
-      "content": "<|dummy_24|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100289": {
-      "content": "<|dummy_25|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100290": {
-      "content": "<|dummy_26|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100291": {
-      "content": "<|dummy_27|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100292": {
-      "content": "<|dummy_28|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100293": {
-      "content": "<|dummy_29|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100294": {
-      "content": "<|dummy_30|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100295": {
-      "content": "<|dummy_31|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100296": {
-      "content": "<|dummy_32|>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100297": {
-      "content": "<|dummy_33|>",
-      "lstrip": true,
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100298": {
-      "content": "<|dummy_34|>",
-      "lstrip": true,
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100299": {
-      "content": "<|dummy_35|>",
-      "lstrip": true,
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100300": {
-      "content": "<|dummy_36|>",
-      "lstrip": true,
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100301": {
-      "content": "<|dummy_37|>",
-      "lstrip": true,
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100302": {
-      "content": "<|dummy_38|>",
-      "lstrip": true,
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100303": {
-      "content": "<|dummy_39|>",
-      "lstrip": true,
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100304": {
-      "content": "<|dummy_40|>",
-      "lstrip": true,
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100305": {
-      "content": "<|dummy_41|>",
-      "lstrip": true,
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100306": {
-      "content": "<|dummy_42|>",
-      "lstrip": true,
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100307": {
-      "content": "<|dummy_43|>",
-      "lstrip": true,
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100308": {
-      "content": "<|dummy_44|>",
-      "lstrip": true,
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
-    },
-    "100309": {
-      "content": "<|dummy_45|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100310": {
-      "content": "<|dummy_46|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100311": {
-      "content": "<|dummy_47|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100312": {
-      "content": "<|dummy_48|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100313": {
-      "content": "<|dummy_49|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100314": {
-      "content": "<|dummy_50|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100315": {
-      "content": "<|dummy_51|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100316": {
-      "content": "<|dummy_52|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100317": {
-      "content": "<|dummy_53|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100318": {
-      "content": "<|dummy_54|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100319": {
-      "content": "<|dummy_55|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100320": {
-      "content": "<|dummy_56|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
+      "special": false
     },
-    "100321": {
-      "content": "<|dummy_57|>",
-      "lstrip": true,
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
-    },
-    "100322": {
-      "content": "<|dummy_58|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100323": {
-      "content": "<|dummy_59|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100324": {
-      "content": "<|dummy_60|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100325": {
-      "content": "<|dummy_61|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100326": {
-      "content": "<|dummy_62|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100327": {
-      "content": "<|dummy_63|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100328": {
-      "content": "<|dummy_64|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
+      "special": false
     },
-    "100329": {
-      "content": "<|dummy_65|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100330": {
-      "content": "<|dummy_66|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100331": {
-      "content": "<|dummy_67|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100332": {
-      "content": "<|dummy_68|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100333": {
-      "content": "<|dummy_69|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100334": {
-      "content": "<|dummy_70|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100335": {
-      "content": "<|dummy_71|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100336": {
-      "content": "<|dummy_72|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100337": {
-      "content": "<|dummy_73|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100338": {
-      "content": "<|dummy_74|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100339": {
-      "content": "<|dummy_75|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100340": {
-      "content": "<|dummy_76|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100341": {
-      "content": "<|dummy_77|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100342": {
-      "content": "<|dummy_78|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100343": {
-      "content": "<|dummy_79|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100344": {
-      "content": "<|dummy_80|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100345": {
-      "content": "<|dummy_81|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100346": {
-      "content": "<|dummy_82|>",
-      "lstrip": true,
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100347": {
-      "content": "<|dummy_83|>",
-      "lstrip": true,
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100348": {
-      "content": "<|dummy_84|>",
-      "lstrip": true,
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100349": {
-      "content": "<|dummy_85|>",
-      "lstrip": true,
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100350": {
-      "content": "<|dummy_86|>",
-      "lstrip": true,
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100351": {
-      "content": "<|dummy_87|>",
-      "lstrip": true,
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     }
   },
-  "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 16384,
-  "pad_token": "<|dummy_85|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10a4e0c73890c635511853b8bc2cf58f0a92a64a7bd3940612c7e7028ef2a5d9
+oid sha256:8d80dda3b4e9845a99ba4d534225bd14e78f4db0ec645620e766d23171b15f2a
 size 8120