Training in progress, step 10

Browse files

Files changed (5) hide show

adapter_config.json +8 -8
adapter_model.safetensors +2 -2
args.json +45 -17
logging.jsonl +12 -124
training_args.bin +2 -2

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/root/highspeedstorage/ft-volume/models--Qwen--Qwen2.5-72B-Instruct/snapshots/495f39366efef23836d0cfae4fbe635880d2be31",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -12,24 +12,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
   "lora_bias": false,
-  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [],
   "peft_type": "LORA",
-  "r": 512,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "k_proj",
-    "gate_proj",
     "up_proj",
     "o_proj",
-    "v_proj",
-    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "/root/highspeedstorage/ft-volume/qwen-tool-model",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
+  "lora_alpha": 64,
   "lora_bias": false,
+  "lora_dropout": 0.01,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [],
   "peft_type": "LORA",
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "k_proj",
+    "q_proj",
+    "v_proj",
     "up_proj",
+    "gate_proj",
     "o_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f5ebbfb46a1e0a9a8939bb8a9271ccc0d2f04407fb0e0124c8f8cd7dec4e46
-size 13474358304

 version https://git-lfs.github.com/spec/v1
+oid sha256:f3cd528eeee6aad4e1864698092f45999d42e5a306004cebdc7575ae9c110b07
+size 4295091864

args.json CHANGED Viewed

@@ -1,10 +1,10 @@
 {
-  "model": "/root/highspeedstorage/ft-volume/models--Qwen--Qwen2.5-72B-Instruct/snapshots/495f39366efef23836d0cfae4fbe635880d2be31",
   "model_type": "qwen2_5",
   "model_revision": null,
   "task_type": "causal_lm",
   "torch_dtype": "bfloat16",
-  "attn_impl": null,
   "num_labels": null,
   "rope_scaling": null,
   "device_map": null,
@@ -22,7 +22,7 @@
   "use_chat_template": true,
   "template_backend": "swift",
   "dataset": [
-    "new_data_new.jsonl"
   ],
   "val_dataset": [],
   "split_dataset_ratio": 0.03,
@@ -50,7 +50,7 @@
   "bnb_4bit_use_double_quant": true,
   "bnb_4bit_quant_storage": null,
   "max_new_tokens": 64,
-  "temperature": 0.0,
   "top_k": null,
   "top_p": null,
   "repetition_penalty": null,
@@ -59,7 +59,7 @@
   "stop_words": [],
   "logprobs": false,
   "top_logprobs": null,
-  "ckpt_dir": null,
   "load_dataset_config": null,
   "lora_modules": [],
   "tuner_backend": "peft",
@@ -74,7 +74,7 @@
   "custom_register_path": [],
   "ignore_args_error": false,
   "use_swift_lora": false,
-  "output_dir": "/root/dataDisk/output/v28-20250303-123303",
   "overwrite_output_dir": false,
   "do_train": false,
   "do_eval": false,
@@ -85,7 +85,7 @@
   "per_device_eval_batch_size": 1,
   "per_gpu_train_batch_size": null,
   "per_gpu_eval_batch_size": null,
-  "gradient_accumulation_steps": 8,
   "eval_accumulation_steps": null,
   "eval_delay": 0,
   "torch_empty_cache_steps": null,
@@ -104,7 +104,7 @@
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
-  "logging_dir": "/root/dataDisk/output/v28-20250303-123303/runs",
   "logging_strategy": "steps",
   "logging_first_step": true,
   "logging_steps": 1,
@@ -262,9 +262,9 @@
   ],
   "target_regex": null,
   "modules_to_save": [],
-  "lora_rank": 512,
-  "lora_alpha": 128,
-  "lora_dropout": 0.1,
   "lora_bias": "none",
   "lora_dtype": null,
   "lorap_lr_ratio": null,
@@ -332,17 +332,45 @@
   "create_checkpoint_symlink": false,
   "packing": false,
   "lazy_tokenize": false,
-  "loss_type": null,
   "optimizer": null,
   "metric": null,
   "acc_strategy": "token",
   "rank": 0,
   "global_world_size": 8,
   "local_world_size": 8,
-  "model_suffix": "Qwen2.5-72B-Instruct",
-  "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/root/highspeedstorage/ft-volume/models--Qwen--Qwen2.5-72B-Instruct/snapshots/495f39366efef23836d0cfae4fbe635880d2be31', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=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 0x7f84beb70280>, 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--Qwen2.5-72B-Instruct/snapshots/495f39366efef23836d0cfae4fbe635880d2be31",
   "hub": "<class 'swift.hub.hub.HFHub'>",
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/dataDisk/output/v28-20250303-123303', 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=8, 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/v28-20250303-123303/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/v28-20250303-123303', 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)"
 }

 {
+  "model": "/root/highspeedstorage/ft-volume/qwen-tool-model",
   "model_type": "qwen2_5",
   "model_revision": null,
   "task_type": "causal_lm",
   "torch_dtype": "bfloat16",
+  "attn_impl": "sdpa",
   "num_labels": null,
   "rope_scaling": null,
   "device_map": null,
   "use_chat_template": true,
   "template_backend": "swift",
   "dataset": [
+    "dpo_data.jsonl"
   ],
   "val_dataset": [],
   "split_dataset_ratio": 0.03,
   "bnb_4bit_use_double_quant": true,
   "bnb_4bit_quant_storage": null,
   "max_new_tokens": 64,
+  "temperature": 0.7,
   "top_k": null,
   "top_p": null,
   "repetition_penalty": null,
   "stop_words": [],
   "logprobs": false,
   "top_logprobs": null,
+  "ckpt_dir": "/root/highspeedstorage/ft-volume/qwen-tool-model",
   "load_dataset_config": null,
   "lora_modules": [],
   "tuner_backend": "peft",
   "custom_register_path": [],
   "ignore_args_error": false,
   "use_swift_lora": false,
+  "output_dir": "/root/dataDisk/output/v42-20250307-153810",
   "overwrite_output_dir": false,
   "do_train": false,
   "do_eval": false,
   "per_device_eval_batch_size": 1,
   "per_gpu_train_batch_size": null,
   "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 4,
   "eval_accumulation_steps": null,
   "eval_delay": 0,
   "torch_empty_cache_steps": null,
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
+  "logging_dir": "/root/dataDisk/output/v42-20250307-153810/runs",
   "logging_strategy": "steps",
   "logging_first_step": true,
   "logging_steps": 1,
   ],
   "target_regex": null,
   "modules_to_save": [],
+  "lora_rank": 256,
+  "lora_alpha": 64,
+  "lora_dropout": 0.01,
   "lora_bias": "none",
   "lora_dtype": null,
   "lorap_lr_ratio": null,
   "create_checkpoint_symlink": false,
   "packing": false,
   "lazy_tokenize": false,
+  "loss_type": "sigmoid",
   "optimizer": null,
   "metric": null,
   "acc_strategy": "token",
+  "reward_model": null,
+  "reward_adapters": [],
+  "reward_model_type": null,
+  "reward_model_revision": null,
+  "num_ppo_epochs": 4,
+  "whiten_rewards": false,
+  "kl_coef": 0.05,
+  "cliprange": 0.2,
+  "vf_coef": 0.1,
+  "cliprange_value": 0.2,
+  "gamma": 1.0,
+  "lam": 0.95,
+  "num_mini_batches": 1,
+  "local_rollout_forward_batch_size": 64,
+  "num_sample_generations": 10,
+  "response_length": 512,
+  "missing_eos_penalty": null,
+  "rlhf_type": "dpo",
+  "ref_model": null,
+  "ref_model_type": null,
+  "ref_model_revision": null,
+  "beta": 0.1,
+  "label_smoothing": 0,
+  "rpo_alpha": 1.0,
+  "cpo_alpha": 1.0,
+  "simpo_gamma": 1,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
   "rank": 0,
   "global_world_size": 8,
   "local_world_size": 8,
+  "model_suffix": "qwen-tool-model",
+  "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/root/highspeedstorage/ft-volume/qwen-tool-model', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=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 0x7fc81687c280>, model_arch='llama', architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.37'], tags=[])",
+  "model_dir": "/root/highspeedstorage/ft-volume/qwen-tool-model",
   "hub": "<class 'swift.hub.hub.HFHub'>",
+  "training_args": "DPOConfig(output_dir='/root/dataDisk/output/v42-20250307-153810', 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=4, 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/v42-20250307-153810/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/v42-20250307-153810', 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, model_init_kwargs=None, ref_model_init_kwargs=None, model_adapter_name=None, ref_adapter_name=None, force_use_ref_model=False, disable_dropout=True, use_num_logits_to_keep=False, dataset_num_proc=1, padding_value=None, label_pad_token_id=None, max_prompt_length=512, max_completion_length=None, max_length=22000, truncation_mode='keep_end', padding_free=False, precompute_ref_log_probs=False, precompute_ref_batch_size=None, tools=None, loss_type='sigmoid', beta=0.1, f_divergence_type=<FDivergenceType.REVERSE_KL: 'reverse_kl'>, f_alpha_divergence_coef=1.0, reference_free=False, label_smoothing=0, use_weighting=False, rpo_alpha=1.0, discopop_tau=0.05, sync_ref_model=False, ref_model_mixup_alpha=0.9, ref_model_sync_steps=64, generate_during_eval=False, is_encoder_decoder=False, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='lora', optimizer=None, galore_config=None)"
 }

logging.jsonl CHANGED Viewed

@@ -1,124 +1,12 @@
-{"loss": 1.08013344, "token_acc": 0.77033758, "grad_norm": 1.15012562, "learning_rate": 4.2e-07, "memory(GiB)": 50.2, "train_speed(iter/s)": 0.006306, "epoch": 0.00428036, "global_step/max_steps": "1/233", "percentage": "0.43%", "elapsed_time": "2m 9s", "remaining_time": "8h 22m 30s"}
-{"loss": 1.03408611, "token_acc": 0.78389394, "grad_norm": 1.04629707, "learning_rate": 8.3e-07, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.006715, "epoch": 0.00856073, "global_step/max_steps": "2/233", "percentage": "0.86%", "elapsed_time": "4m 29s", "remaining_time": "8h 38m 14s"}
-{"loss": 1.0435493, "token_acc": 0.78635015, "grad_norm": 1.14465797, "learning_rate": 1.25e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007586, "epoch": 0.01284109, "global_step/max_steps": "3/233", "percentage": "1.29%", "elapsed_time": "6m 6s", "remaining_time": "7h 48m 45s"}
-{"loss": 0.98465502, "token_acc": 0.80810558, "grad_norm": 0.92396301, "learning_rate": 1.67e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.008395, "epoch": 0.01712146, "global_step/max_steps": "4/233", "percentage": "1.72%", "elapsed_time": "7m 27s", "remaining_time": "7h 7m 18s"}
-{"loss": 0.89992946, "token_acc": 0.79354126, "grad_norm": 0.59189129, "learning_rate": 2.08e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.009436, "epoch": 0.02140182, "global_step/max_steps": "5/233", "percentage": "2.15%", "elapsed_time": "8m 21s", "remaining_time": "6h 20m 57s"}
-{"loss": 0.83590686, "token_acc": 0.81316533, "grad_norm": 0.36493647, "learning_rate": 2.5e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.010057, "epoch": 0.02568218, "global_step/max_steps": "6/233", "percentage": "2.58%", "elapsed_time": "9m 27s", "remaining_time": "5h 58m 8s"}
-{"loss": 0.74400991, "token_acc": 0.82081323, "grad_norm": 0.41631833, "learning_rate": 2.92e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.010211, "epoch": 0.02996255, "global_step/max_steps": "7/233", "percentage": "3.00%", "elapsed_time": "10m 56s", "remaining_time": "5h 53m 28s"}
-{"loss": 0.75538123, "token_acc": 0.78802524, "grad_norm": 0.25214699, "learning_rate": 3.33e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.010129, "epoch": 0.03424291, "global_step/max_steps": "8/233", "percentage": "3.43%", "elapsed_time": "12m 41s", "remaining_time": "5h 56m 48s"}
-{"loss": 0.69496286, "token_acc": 0.80500534, "grad_norm": 0.15154789, "learning_rate": 3.75e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.010166, "epoch": 0.03852327, "global_step/max_steps": "9/233", "percentage": "3.86%", "elapsed_time": "14m 16s", "remaining_time": "5h 55m 22s"}
-{"loss": 0.68788755, "token_acc": 0.81771872, "grad_norm": 0.17263316, "learning_rate": 4.17e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.009777, "epoch": 0.04280364, "global_step/max_steps": "10/233", "percentage": "4.29%", "elapsed_time": "16m 34s", "remaining_time": "6h 9m 30s"}
-{"eval_loss": 0.73368567, "eval_token_acc": 0.80271665, "eval_runtime": 242.941, "eval_samples_per_second": 1.902, "eval_steps_per_second": 0.239, "epoch": 0.04280364, "global_step/max_steps": "10/233", "percentage": "4.29%", "elapsed_time": "20m 37s", "remaining_time": "7h 39m 48s"}
-{"loss": 0.73342615, "token_acc": 0.80512214, "grad_norm": 0.16072659, "learning_rate": 4.58e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00735, "epoch": 0.047084, "global_step/max_steps": "11/233", "percentage": "4.72%", "elapsed_time": "24m 27s", "remaining_time": "8h 13m 45s"}
-{"loss": 0.67682797, "token_acc": 0.81391264, "grad_norm": 0.17208615, "learning_rate": 5e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007621, "epoch": 0.05136437, "global_step/max_steps": "12/233", "percentage": "5.15%", "elapsed_time": "25m 45s", "remaining_time": "7h 54m 31s"}
-{"loss": 0.70355046, "token_acc": 0.80930271, "grad_norm": 0.17548002, "learning_rate": 5.42e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007734, "epoch": 0.05564473, "global_step/max_steps": "13/233", "percentage": "5.58%", "elapsed_time": "27m 32s", "remaining_time": "7h 46m 1s"}
-{"loss": 0.65637207, "token_acc": 0.83605664, "grad_norm": 0.16901045, "learning_rate": 5.83e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007692, "epoch": 0.05992509, "global_step/max_steps": "14/233", "percentage": "6.01%", "elapsed_time": "29m 51s", "remaining_time": "7h 47m 1s"}
-{"loss": 0.63492227, "token_acc": 0.84747774, "grad_norm": 0.15617178, "learning_rate": 6.25e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007952, "epoch": 0.06420546, "global_step/max_steps": "15/233", "percentage": "6.44%", "elapsed_time": "30m 57s", "remaining_time": "7h 29m 56s"}
-{"loss": 0.62725329, "token_acc": 0.8294412, "grad_norm": 0.15435693, "learning_rate": 6.67e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.008083, "epoch": 0.06848582, "global_step/max_steps": "16/233", "percentage": "6.87%", "elapsed_time": "32m 30s", "remaining_time": "7h 20m 57s"}
-{"loss": 0.65263098, "token_acc": 0.84645743, "grad_norm": 0.20680472, "learning_rate": 7.08e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.008003, "epoch": 0.07276619, "global_step/max_steps": "17/233", "percentage": "7.30%", "elapsed_time": "34m 55s", "remaining_time": "7h 23m 47s"}
-{"loss": 0.58632511, "token_acc": 0.78724728, "grad_norm": 0.10024609, "learning_rate": 7.5e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.008052, "epoch": 0.07704655, "global_step/max_steps": "18/233", "percentage": "7.73%", "elapsed_time": "36m 46s", "remaining_time": "7h 19m 19s"}
-{"loss": 0.59923375, "token_acc": 0.82495438, "grad_norm": 0.09799343, "learning_rate": 7.92e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.008115, "epoch": 0.08132691, "global_step/max_steps": "19/233", "percentage": "8.15%", "elapsed_time": "38m 32s", "remaining_time": "7h 14m 7s"}
-{"loss": 0.65003109, "token_acc": 0.81783939, "grad_norm": 0.08318955, "learning_rate": 8.33e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007835, "epoch": 0.08560728, "global_step/max_steps": "20/233", "percentage": "8.58%", "elapsed_time": "42m 3s", "remaining_time": "7h 27m 59s"}
-{"eval_loss": 0.58478379, "eval_token_acc": 0.8166804, "eval_runtime": 241.7054, "eval_samples_per_second": 1.911, "eval_steps_per_second": 0.24, "epoch": 0.08560728, "global_step/max_steps": "20/233", "percentage": "8.58%", "elapsed_time": "46m 5s", "remaining_time": "8h 10m 54s"}
-{"loss": 0.62572074, "token_acc": 0.82390299, "grad_norm": 0.07679106, "learning_rate": 8.75e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.006992, "epoch": 0.08988764, "global_step/max_steps": "21/233", "percentage": "9.01%", "elapsed_time": "49m 34s", "remaining_time": "8h 20m 29s"}
-{"loss": 0.52991968, "token_acc": 0.82156822, "grad_norm": 0.09334455, "learning_rate": 9.17e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007158, "epoch": 0.094168, "global_step/max_steps": "22/233", "percentage": "9.44%", "elapsed_time": "50m 44s", "remaining_time": "8h 6m 41s"}
-{"loss": 0.59488881, "token_acc": 0.80882547, "grad_norm": 0.08410198, "learning_rate": 9.58e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00729, "epoch": 0.09844837, "global_step/max_steps": "23/233", "percentage": "9.87%", "elapsed_time": "52m 6s", "remaining_time": "7h 55m 45s"}
-{"loss": 0.60693359, "token_acc": 0.82773224, "grad_norm": 0.13357562, "learning_rate": 1e-05, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007352, "epoch": 0.10272873, "global_step/max_steps": "24/233", "percentage": "10.30%", "elapsed_time": "53m 55s", "remaining_time": "7h 49m 38s"}
-{"loss": 0.52467477, "token_acc": 0.86434676, "grad_norm": 0.07653414, "learning_rate": 9.95e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007431, "epoch": 0.1070091, "global_step/max_steps": "25/233", "percentage": "10.73%", "elapsed_time": "55m 35s", "remaining_time": "7h 42m 32s"}
-{"loss": 0.54195654, "token_acc": 0.86077069, "grad_norm": 0.13674259, "learning_rate": 9.9e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007533, "epoch": 0.11128946, "global_step/max_steps": "26/233", "percentage": "11.16%", "elapsed_time": "57m 2s", "remaining_time": "7h 34m 9s"}
-{"loss": 0.5801242, "token_acc": 0.80804077, "grad_norm": 0.08531155, "learning_rate": 9.86e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007617, "epoch": 0.11556982, "global_step/max_steps": "27/233", "percentage": "11.59%", "elapsed_time": "58m 36s", "remaining_time": "7h 27m 6s"}
-{"loss": 0.58200848, "token_acc": 0.81831659, "grad_norm": 0.0739914, "learning_rate": 9.81e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007707, "epoch": 0.11985019, "global_step/max_steps": "28/233", "percentage": "12.02%", "elapsed_time": "1h 0m 4s", "remaining_time": "7h 19m 49s"}
-{"loss": 0.56698722, "token_acc": 0.83188116, "grad_norm": 0.07506943, "learning_rate": 9.76e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007759, "epoch": 0.12413055, "global_step/max_steps": "29/233", "percentage": "12.45%", "elapsed_time": "1h 1m 49s", "remaining_time": "7h 14m 51s"}
-{"loss": 0.56398886, "token_acc": 0.84606357, "grad_norm": 0.10132041, "learning_rate": 9.71e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007885, "epoch": 0.12841091, "global_step/max_steps": "30/233", "percentage": "12.88%", "elapsed_time": "1h 2m 56s", "remaining_time": "7h 5m 51s"}
-{"eval_loss": 0.55141348, "eval_token_acc": 0.82320999, "eval_runtime": 241.6593, "eval_samples_per_second": 1.912, "eval_steps_per_second": 0.24, "epoch": 0.12841091, "global_step/max_steps": "30/233", "percentage": "12.88%", "elapsed_time": "1h 6m 57s", "remaining_time": "7h 33m 6s"}
-{"loss": 0.60077274, "token_acc": 0.82656772, "grad_norm": 0.08094721, "learning_rate": 9.67e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007367, "epoch": 0.13269128, "global_step/max_steps": "31/233", "percentage": "13.30%", "elapsed_time": "1h 9m 39s", "remaining_time": "7h 33m 54s"}
-{"loss": 0.55639946, "token_acc": 0.8264869, "grad_norm": 0.08904748, "learning_rate": 9.62e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007324, "epoch": 0.13697164, "global_step/max_steps": "32/233", "percentage": "13.73%", "elapsed_time": "1h 12m 20s", "remaining_time": "7h 34m 22s"}
-{"loss": 0.54838562, "token_acc": 0.83038135, "grad_norm": 0.08189788, "learning_rate": 9.57e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007348, "epoch": 0.14125201, "global_step/max_steps": "33/233", "percentage": "14.16%", "elapsed_time": "1h 14m 22s", "remaining_time": "7h 30m 44s"}
-{"loss": 0.5181551, "token_acc": 0.82283231, "grad_norm": 0.06707215, "learning_rate": 9.52e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007425, "epoch": 0.14553237, "global_step/max_steps": "34/233", "percentage": "14.59%", "elapsed_time": "1h 15m 50s", "remaining_time": "7h 23m 54s"}
-{"loss": 0.58804905, "token_acc": 0.83942038, "grad_norm": 0.07225088, "learning_rate": 9.47e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007494, "epoch": 0.14981273, "global_step/max_steps": "35/233", "percentage": "15.02%", "elapsed_time": "1h 17m 21s", "remaining_time": "7h 17m 39s"}
-{"loss": 0.56727856, "token_acc": 0.81316367, "grad_norm": 0.09117357, "learning_rate": 9.43e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007415, "epoch": 0.1540931, "global_step/max_steps": "36/233", "percentage": "15.45%", "elapsed_time": "1h 20m 26s", "remaining_time": "7h 20m 11s"}
-{"loss": 0.52409303, "token_acc": 0.82996109, "grad_norm": 0.07018493, "learning_rate": 9.38e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007444, "epoch": 0.15837346, "global_step/max_steps": "37/233", "percentage": "15.88%", "elapsed_time": "1h 22m 21s", "remaining_time": "7h 16m 18s"}
-{"loss": 0.52306455, "token_acc": 0.8420219, "grad_norm": 0.0978388, "learning_rate": 9.33e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007515, "epoch": 0.16265383, "global_step/max_steps": "38/233", "percentage": "16.31%", "elapsed_time": "1h 23m 47s", "remaining_time": "7h 10m 1s"}
-{"loss": 0.48335356, "token_acc": 0.85642976, "grad_norm": 0.07433824, "learning_rate": 9.28e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00759, "epoch": 0.16693419, "global_step/max_steps": "39/233", "percentage": "16.74%", "elapsed_time": "1h 25m 9s", "remaining_time": "7h 3m 36s"}
-{"loss": 0.55064964, "token_acc": 0.82078626, "grad_norm": 0.06891283, "learning_rate": 9.23e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007629, "epoch": 0.17121455, "global_step/max_steps": "40/233", "percentage": "17.17%", "elapsed_time": "1h 26m 54s", "remaining_time": "6h 59m 20s"}
-{"eval_loss": 0.53406376, "eval_token_acc": 0.82734711, "eval_runtime": 242.0038, "eval_samples_per_second": 1.909, "eval_steps_per_second": 0.24, "epoch": 0.17121455, "global_step/max_steps": "40/233", "percentage": "17.17%", "elapsed_time": "1h 30m 56s", "remaining_time": "7h 18m 48s"}
-{"loss": 0.5422141, "token_acc": 0.82994844, "grad_norm": 0.07173184, "learning_rate": 9.19e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007207, "epoch": 0.17549492, "global_step/max_steps": "41/233", "percentage": "17.60%", "elapsed_time": "1h 34m 20s", "remaining_time": "7h 21m 46s"}
-{"loss": 0.53164256, "token_acc": 0.83507031, "grad_norm": 0.06192541, "learning_rate": 9.14e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007239, "epoch": 0.17977528, "global_step/max_steps": "42/233", "percentage": "18.03%", "elapsed_time": "1h 36m 13s", "remaining_time": "7h 17m 35s"}
-{"loss": 0.52307248, "token_acc": 0.84220283, "grad_norm": 0.06557002, "learning_rate": 9.09e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007268, "epoch": 0.18405564, "global_step/max_steps": "43/233", "percentage": "18.45%", "elapsed_time": "1h 38m 7s", "remaining_time": "7h 13m 34s"}
-{"loss": 0.52469963, "token_acc": 0.84400094, "grad_norm": 0.06456995, "learning_rate": 9.04e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007251, "epoch": 0.18833601, "global_step/max_steps": "44/233", "percentage": "18.88%", "elapsed_time": "1h 40m 39s", "remaining_time": "7h 12m 23s"}
-{"loss": 0.5380199, "token_acc": 0.85072421, "grad_norm": 0.13640587, "learning_rate": 9e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00729, "epoch": 0.19261637, "global_step/max_steps": "45/233", "percentage": "19.31%", "elapsed_time": "1h 42m 24s", "remaining_time": "7h 7m 49s"}
-{"loss": 0.5200237, "token_acc": 0.83695792, "grad_norm": 0.06859917, "learning_rate": 8.95e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007334, "epoch": 0.19689674, "global_step/max_steps": "46/233", "percentage": "19.74%", "elapsed_time": "1h 44m 3s", "remaining_time": "7h 2m 59s"}
-{"loss": 0.49252573, "token_acc": 0.83674838, "grad_norm": 0.0559963, "learning_rate": 8.9e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007382, "epoch": 0.2011771, "global_step/max_steps": "47/233", "percentage": "20.17%", "elapsed_time": "1h 45m 38s", "remaining_time": "6h 58m 3s"}
-{"loss": 0.52460486, "token_acc": 0.85625432, "grad_norm": 0.08232927, "learning_rate": 8.85e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007393, "epoch": 0.20545746, "global_step/max_steps": "48/233", "percentage": "20.60%", "elapsed_time": "1h 47m 44s", "remaining_time": "6h 55m 13s"}
-{"loss": 0.50024033, "token_acc": 0.8380088, "grad_norm": 0.09158918, "learning_rate": 8.8e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007509, "epoch": 0.20973783, "global_step/max_steps": "49/233", "percentage": "21.03%", "elapsed_time": "1h 48m 16s", "remaining_time": "6h 46m 36s"}
-{"loss": 0.48477238, "token_acc": 0.86400725, "grad_norm": 0.05876737, "learning_rate": 8.76e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007562, "epoch": 0.21401819, "global_step/max_steps": "50/233", "percentage": "21.46%", "elapsed_time": "1h 49m 43s", "remaining_time": "6h 41m 35s"}
-{"eval_loss": 0.52338904, "eval_token_acc": 0.82986598, "eval_runtime": 242.0012, "eval_samples_per_second": 1.909, "eval_steps_per_second": 0.24, "epoch": 0.21401819, "global_step/max_steps": "50/233", "percentage": "21.46%", "elapsed_time": "1h 53m 45s", "remaining_time": "6h 56m 21s"}
-{"loss": 0.5260427, "token_acc": 0.83436482, "grad_norm": 0.09511821, "learning_rate": 8.71e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007293, "epoch": 0.21829856, "global_step/max_steps": "51/233", "percentage": "21.89%", "elapsed_time": "1h 56m 4s", "remaining_time": "6h 54m 11s"}
-{"loss": 0.51703411, "token_acc": 0.84615385, "grad_norm": 0.07629833, "learning_rate": 8.66e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007357, "epoch": 0.22257892, "global_step/max_steps": "52/233", "percentage": "22.32%", "elapsed_time": "1h 57m 19s", "remaining_time": "6h 48m 23s"}
-{"loss": 0.55994618, "token_acc": 0.85324845, "grad_norm": 0.08582554, "learning_rate": 8.61e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007364, "epoch": 0.22685928, "global_step/max_steps": "53/233", "percentage": "22.75%", "elapsed_time": "1h 59m 28s", "remaining_time": "6h 45m 45s"}
-{"loss": 0.51246572, "token_acc": 0.82898896, "grad_norm": 0.07559165, "learning_rate": 8.56e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007382, "epoch": 0.23113965, "global_step/max_steps": "54/233", "percentage": "23.18%", "elapsed_time": "2h 1m 26s", "remaining_time": "6h 42m 33s"}
-{"loss": 0.5547772, "token_acc": 0.83155773, "grad_norm": 0.07250986, "learning_rate": 8.52e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007392, "epoch": 0.23542001, "global_step/max_steps": "55/233", "percentage": "23.61%", "elapsed_time": "2h 3m 31s", "remaining_time": "6h 39m 46s"}
-{"loss": 0.49714839, "token_acc": 0.838548, "grad_norm": 0.09689675, "learning_rate": 8.47e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007428, "epoch": 0.23970037, "global_step/max_steps": "56/233", "percentage": "24.03%", "elapsed_time": "2h 5m 10s", "remaining_time": "6h 35m 37s"}
-{"loss": 0.51052147, "token_acc": 0.86389835, "grad_norm": 0.09153108, "learning_rate": 8.42e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007468, "epoch": 0.24398074, "global_step/max_steps": "57/233", "percentage": "24.46%", "elapsed_time": "2h 6m 44s", "remaining_time": "6h 31m 19s"}
-{"loss": 0.50234228, "token_acc": 0.82971304, "grad_norm": 0.06111566, "learning_rate": 8.37e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007492, "epoch": 0.2482611, "global_step/max_steps": "58/233", "percentage": "24.89%", "elapsed_time": "2h 8m 33s", "remaining_time": "6h 27m 53s"}
-{"loss": 0.52983558, "token_acc": 0.83344314, "grad_norm": 0.08763672, "learning_rate": 8.33e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00753, "epoch": 0.25254147, "global_step/max_steps": "59/233", "percentage": "25.32%", "elapsed_time": "2h 10m 6s", "remaining_time": "6h 23m 42s"}
-{"loss": 0.49665368, "token_acc": 0.83857223, "grad_norm": 0.07586836, "learning_rate": 8.28e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007499, "epoch": 0.25682183, "global_step/max_steps": "60/233", "percentage": "25.75%", "elapsed_time": "2h 12m 52s", "remaining_time": "6h 23m 8s"}
-{"eval_loss": 0.51617664, "eval_token_acc": 0.83148554, "eval_runtime": 241.7892, "eval_samples_per_second": 1.911, "eval_steps_per_second": 0.24, "epoch": 0.25682183, "global_step/max_steps": "60/233", "percentage": "25.75%", "elapsed_time": "2h 16m 54s", "remaining_time": "6h 34m 45s"}
-{"loss": 0.52413404, "token_acc": 0.833429, "grad_norm": 0.07934275, "learning_rate": 8.23e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007257, "epoch": 0.26110219, "global_step/max_steps": "61/233", "percentage": "26.18%", "elapsed_time": "2h 19m 37s", "remaining_time": "6h 33m 41s"}
-{"loss": 0.49663743, "token_acc": 0.83292978, "grad_norm": 0.07779735, "learning_rate": 8.18e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007296, "epoch": 0.26538256, "global_step/max_steps": "62/233", "percentage": "26.61%", "elapsed_time": "2h 21m 8s", "remaining_time": "6h 29m 17s"}
-{"loss": 0.55711979, "token_acc": 0.86215728, "grad_norm": 0.20403802, "learning_rate": 8.13e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007308, "epoch": 0.26966292, "global_step/max_steps": "63/233", "percentage": "27.04%", "elapsed_time": "2h 23m 12s", "remaining_time": "6h 26m 25s"}
-{"loss": 0.49661428, "token_acc": 0.86588141, "grad_norm": 0.0783712, "learning_rate": 8.09e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007326, "epoch": 0.27394329, "global_step/max_steps": "64/233", "percentage": "27.47%", "elapsed_time": "2h 25m 7s", "remaining_time": "6h 23m 12s"}
-{"loss": 0.47228733, "token_acc": 0.85465694, "grad_norm": 0.0606144, "learning_rate": 8.04e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007409, "epoch": 0.27822365, "global_step/max_steps": "65/233", "percentage": "27.90%", "elapsed_time": "2h 25m 44s", "remaining_time": "6h 16m 40s"}
-{"loss": 0.53328562, "token_acc": 0.81572878, "grad_norm": 0.06781668, "learning_rate": 7.99e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007434, "epoch": 0.28250401, "global_step/max_steps": "66/233", "percentage": "28.33%", "elapsed_time": "2h 27m 29s", "remaining_time": "6h 13m 12s"}
-{"loss": 0.54172069, "token_acc": 0.80318091, "grad_norm": 0.09777166, "learning_rate": 7.94e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007477, "epoch": 0.28678438, "global_step/max_steps": "67/233", "percentage": "28.76%", "elapsed_time": "2h 28m 52s", "remaining_time": "6h 8m 50s"}
-{"loss": 0.49940646, "token_acc": 0.84482073, "grad_norm": 0.14852044, "learning_rate": 7.89e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007475, "epoch": 0.29106474, "global_step/max_steps": "68/233", "percentage": "29.18%", "elapsed_time": "2h 31m 7s", "remaining_time": "6h 6m 42s"}
-{"loss": 0.51398146, "token_acc": 0.83259244, "grad_norm": 0.08095538, "learning_rate": 7.85e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007496, "epoch": 0.2953451, "global_step/max_steps": "69/233", "percentage": "29.61%", "elapsed_time": "2h 32m 56s", "remaining_time": "6h 3m 30s"}
-{"loss": 0.49674517, "token_acc": 0.83614906, "grad_norm": 0.05899839, "learning_rate": 7.8e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007512, "epoch": 0.29962547, "global_step/max_steps": "70/233", "percentage": "30.04%", "elapsed_time": "2h 34m 50s", "remaining_time": "6h 0m 32s"}
-{"eval_loss": 0.5093264, "eval_token_acc": 0.83308535, "eval_runtime": 242.137, "eval_samples_per_second": 1.908, "eval_steps_per_second": 0.24, "epoch": 0.29962547, "global_step/max_steps": "70/233", "percentage": "30.04%", "elapsed_time": "2h 38m 52s", "remaining_time": "6h 9m 56s"}
-{"loss": 0.46760559, "token_acc": 0.8389776, "grad_norm": 0.10437731, "learning_rate": 7.75e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007303, "epoch": 0.30390583, "global_step/max_steps": "71/233", "percentage": "30.47%", "elapsed_time": "2h 41m 33s", "remaining_time": "6h 8m 36s"}
-{"loss": 0.51234508, "token_acc": 0.82614632, "grad_norm": 0.09199133, "learning_rate": 7.7e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00733, "epoch": 0.3081862, "global_step/max_steps": "72/233", "percentage": "30.90%", "elapsed_time": "2h 43m 13s", "remaining_time": "6h 5m 0s"}
-{"loss": 0.47961688, "token_acc": 0.83937947, "grad_norm": 0.09719895, "learning_rate": 7.66e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007379, "epoch": 0.31246656, "global_step/max_steps": "73/233", "percentage": "31.33%", "elapsed_time": "2h 44m 24s", "remaining_time": "6h 0m 21s"}
-{"loss": 0.51225775, "token_acc": 0.82867133, "grad_norm": 0.11586607, "learning_rate": 7.61e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007382, "epoch": 0.31674692, "global_step/max_steps": "74/233", "percentage": "31.76%", "elapsed_time": "2h 46m 35s", "remaining_time": "5h 57m 57s"}
-{"loss": 0.49728289, "token_acc": 0.86580627, "grad_norm": 0.07562775, "learning_rate": 7.56e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007421, "epoch": 0.32102729, "global_step/max_steps": "75/233", "percentage": "32.19%", "elapsed_time": "2h 47m 57s", "remaining_time": "5h 53m 50s"}
-{"loss": 0.52536249, "token_acc": 0.84104859, "grad_norm": 0.08014917, "learning_rate": 7.51e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007423, "epoch": 0.32530765, "global_step/max_steps": "76/233", "percentage": "32.62%", "elapsed_time": "2h 50m 10s", "remaining_time": "5h 51m 32s"}
-{"loss": 0.53380793, "token_acc": 0.81610689, "grad_norm": 0.10109331, "learning_rate": 7.46e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00743, "epoch": 0.32958801, "global_step/max_steps": "77/233", "percentage": "33.05%", "elapsed_time": "2h 52m 14s", "remaining_time": "5h 48m 57s"}
-{"loss": 0.52443308, "token_acc": 0.81274663, "grad_norm": 0.08349298, "learning_rate": 7.42e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007422, "epoch": 0.33386838, "global_step/max_steps": "78/233", "percentage": "33.48%", "elapsed_time": "2h 54m 41s", "remaining_time": "5h 47m 8s"}
-{"loss": 0.52687961, "token_acc": 0.82810102, "grad_norm": 0.07851128, "learning_rate": 7.37e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007432, "epoch": 0.33814874, "global_step/max_steps": "79/233", "percentage": "33.91%", "elapsed_time": "2h 56m 41s", "remaining_time": "5h 44m 25s"}
-{"loss": 0.50132257, "token_acc": 0.84761292, "grad_norm": 0.07297929, "learning_rate": 7.32e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007478, "epoch": 0.34242911, "global_step/max_steps": "80/233", "percentage": "34.33%", "elapsed_time": "2h 57m 48s", "remaining_time": "5h 40m 4s"}
-{"eval_loss": 0.50374109, "eval_token_acc": 0.83457587, "eval_runtime": 241.9539, "eval_samples_per_second": 1.909, "eval_steps_per_second": 0.24, "epoch": 0.34242911, "global_step/max_steps": "80/233", "percentage": "34.33%", "elapsed_time": "3h 1m 50s", "remaining_time": "5h 47m 46s"}
-{"loss": 0.53045738, "token_acc": 0.8416672, "grad_norm": 0.06782681, "learning_rate": 7.27e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007261, "epoch": 0.34670947, "global_step/max_steps": "81/233", "percentage": "34.76%", "elapsed_time": "3h 5m 26s", "remaining_time": "5h 47m 59s"}
-{"loss": 0.48182738, "token_acc": 0.86235762, "grad_norm": 0.08035231, "learning_rate": 7.22e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007282, "epoch": 0.35098983, "global_step/max_steps": "82/233", "percentage": "35.19%", "elapsed_time": "3h 7m 11s", "remaining_time": "5h 44m 42s"}
-{"loss": 0.4680478, "token_acc": 0.83808011, "grad_norm": 0.0776862, "learning_rate": 7.18e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007333, "epoch": 0.3552702, "global_step/max_steps": "83/233", "percentage": "35.62%", "elapsed_time": "3h 8m 9s", "remaining_time": "5h 40m 3s"}
-{"loss": 0.50248015, "token_acc": 0.84487124, "grad_norm": 0.09134543, "learning_rate": 7.13e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007348, "epoch": 0.35955056, "global_step/max_steps": "84/233", "percentage": "36.05%", "elapsed_time": "3h 10m 2s", "remaining_time": "5h 37m 6s"}
-{"loss": 0.50822359, "token_acc": 0.82600143, "grad_norm": 0.13418381, "learning_rate": 7.08e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007364, "epoch": 0.36383093, "global_step/max_steps": "85/233", "percentage": "36.48%", "elapsed_time": "3h 11m 54s", "remaining_time": "5h 34m 8s"}
-{"loss": 0.48014569, "token_acc": 0.8390383, "grad_norm": 0.07202198, "learning_rate": 7.03e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007398, "epoch": 0.36811129, "global_step/max_steps": "86/233", "percentage": "36.91%", "elapsed_time": "3h 13m 16s", "remaining_time": "5h 30m 21s"}
-{"loss": 0.47805411, "token_acc": 0.84735473, "grad_norm": 0.07147595, "learning_rate": 6.99e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007409, "epoch": 0.37239165, "global_step/max_steps": "87/233", "percentage": "37.34%", "elapsed_time": "3h 15m 13s", "remaining_time": "5h 27m 37s"}
-{"loss": 0.53040433, "token_acc": 0.82925953, "grad_norm": 0.10784797, "learning_rate": 6.94e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007453, "epoch": 0.37667202, "global_step/max_steps": "88/233", "percentage": "37.77%", "elapsed_time": "3h 16m 18s", "remaining_time": "5h 23m 27s"}
-{"loss": 0.49515486, "token_acc": 0.83218153, "grad_norm": 0.06736118, "learning_rate": 6.89e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007457, "epoch": 0.38095238, "global_step/max_steps": "89/233", "percentage": "38.20%", "elapsed_time": "3h 18m 27s", "remaining_time": "5h 21m 5s"}
-{"loss": 0.47768551, "token_acc": 0.83321367, "grad_norm": 0.06201233, "learning_rate": 6.84e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007491, "epoch": 0.38523274, "global_step/max_steps": "90/233", "percentage": "38.63%", "elapsed_time": "3h 19m 45s", "remaining_time": "5h 17m 23s"}
-{"eval_loss": 0.49977466, "eval_token_acc": 0.83558711, "eval_runtime": 241.6833, "eval_samples_per_second": 1.912, "eval_steps_per_second": 0.24, "epoch": 0.38523274, "global_step/max_steps": "90/233", "percentage": "38.63%", "elapsed_time": "3h 23m 47s", "remaining_time": "5h 23m 47s"}
-{"loss": 0.48070419, "token_acc": 0.84075353, "grad_norm": 0.06807869, "learning_rate": 6.79e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007336, "epoch": 0.38951311, "global_step/max_steps": "91/233", "percentage": "39.06%", "elapsed_time": "3h 26m 16s", "remaining_time": "5h 21m 52s"}
-{"loss": 0.51375258, "token_acc": 0.83763028, "grad_norm": 0.08288609, "learning_rate": 6.75e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00732, "epoch": 0.39379347, "global_step/max_steps": "92/233", "percentage": "39.48%", "elapsed_time": "3h 28m 59s", "remaining_time": "5h 20m 18s"}
-{"loss": 0.50796258, "token_acc": 0.85515728, "grad_norm": 0.06570733, "learning_rate": 6.7e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007318, "epoch": 0.39807384, "global_step/max_steps": "93/233", "percentage": "39.91%", "elapsed_time": "3h 31m 19s", "remaining_time": "5h 18m 6s"}
-{"loss": 0.49376428, "token_acc": 0.8633339, "grad_norm": 0.06735527, "learning_rate": 6.65e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007312, "epoch": 0.4023542, "global_step/max_steps": "94/233", "percentage": "40.34%", "elapsed_time": "3h 33m 47s", "remaining_time": "5h 16m 8s"}
-{"loss": 0.48758113, "token_acc": 0.86737841, "grad_norm": 0.07038066, "learning_rate": 6.6e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007303, "epoch": 0.40663456, "global_step/max_steps": "95/233", "percentage": "40.77%", "elapsed_time": "3h 36m 20s", "remaining_time": "5h 14m 15s"}
-{"loss": 0.50346422, "token_acc": 0.84974174, "grad_norm": 0.098224, "learning_rate": 6.56e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007337, "epoch": 0.41091493, "global_step/max_steps": "96/233", "percentage": "41.20%", "elapsed_time": "3h 37m 35s", "remaining_time": "5h 10m 31s"}
-{"loss": 0.48230606, "token_acc": 0.86310905, "grad_norm": 0.0744651, "learning_rate": 6.51e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007354, "epoch": 0.41519529, "global_step/max_steps": "97/233", "percentage": "41.63%", "elapsed_time": "3h 39m 21s", "remaining_time": "5h 7m 32s"}
-{"loss": 0.53153503, "token_acc": 0.84278559, "grad_norm": 0.08317012, "learning_rate": 6.46e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007378, "epoch": 0.41947566, "global_step/max_steps": "98/233", "percentage": "42.06%", "elapsed_time": "3h 40m 54s", "remaining_time": "5h 4m 19s"}
-{"loss": 0.53740638, "token_acc": 0.84437877, "grad_norm": 0.06650413, "learning_rate": 6.41e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007355, "epoch": 0.42375602, "global_step/max_steps": "99/233", "percentage": "42.49%", "elapsed_time": "3h 43m 51s", "remaining_time": "5h 2m 59s"}
-{"loss": 0.51379466, "token_acc": 0.84055214, "grad_norm": 0.12115329, "learning_rate": 6.36e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007375, "epoch": 0.42803638, "global_step/max_steps": "100/233", "percentage": "42.92%", "elapsed_time": "3h 45m 31s", "remaining_time": "4h 59m 56s"}
-{"eval_loss": 0.49639913, "eval_token_acc": 0.83656806, "eval_runtime": 242.019, "eval_samples_per_second": 1.909, "eval_steps_per_second": 0.24, "epoch": 0.42803638, "global_step/max_steps": "100/233", "percentage": "42.92%", "elapsed_time": "3h 49m 33s", "remaining_time": "5h 5m 18s"}
-{"loss": 0.49421194, "token_acc": 0.84193455, "grad_norm": 0.08505423, "learning_rate": 6.32e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00724, "epoch": 0.43231675, "global_step/max_steps": "101/233", "percentage": "43.35%", "elapsed_time": "3h 52m 1s", "remaining_time": "5h 3m 14s"}
-{"loss": 0.45084918, "token_acc": 0.84497424, "grad_norm": 0.07715236, "learning_rate": 6.27e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007283, "epoch": 0.43659711, "global_step/max_steps": "102/233", "percentage": "43.78%", "elapsed_time": "3h 52m 56s", "remaining_time": "4h 59m 10s"}
-{"loss": 0.50429815, "token_acc": 0.85636071, "grad_norm": 0.06717362, "learning_rate": 6.22e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007306, "epoch": 0.44087747, "global_step/max_steps": "103/233", "percentage": "44.21%", "elapsed_time": "3h 54m 30s", "remaining_time": "4h 55m 58s"}
-{"loss": 0.48175743, "token_acc": 0.85780432, "grad_norm": 0.06356624, "learning_rate": 6.17e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007316, "epoch": 0.44515784, "global_step/max_steps": "104/233", "percentage": "44.64%", "elapsed_time": "3h 56m 26s", "remaining_time": "4h 53m 17s"}
-{"loss": 0.45514175, "token_acc": 0.85283688, "grad_norm": 0.07263558, "learning_rate": 6.12e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007346, "epoch": 0.4494382, "global_step/max_steps": "105/233", "percentage": "45.06%", "elapsed_time": "3h 57m 45s", "remaining_time": "4h 49m 50s"}
-{"loss": 0.46450457, "token_acc": 0.85789408, "grad_norm": 0.06798379, "learning_rate": 6.08e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007383, "epoch": 0.45371857, "global_step/max_steps": "106/233", "percentage": "45.49%", "elapsed_time": "3h 58m 48s", "remaining_time": "4h 46m 7s"}
-{"loss": 0.55218869, "token_acc": 0.83656703, "grad_norm": 0.07898691, "learning_rate": 6.03e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007392, "epoch": 0.45799893, "global_step/max_steps": "107/233", "percentage": "45.92%", "elapsed_time": "4h 0m 45s", "remaining_time": "4h 43m 30s"}
-{"loss": 0.52734697, "token_acc": 0.83814834, "grad_norm": 0.06623442, "learning_rate": 5.98e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007394, "epoch": 0.46227929, "global_step/max_steps": "108/233", "percentage": "46.35%", "elapsed_time": "4h 2m 57s", "remaining_time": "4h 41m 12s"}
-{"loss": 0.4806062, "token_acc": 0.85208591, "grad_norm": 0.12244462, "learning_rate": 5.93e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007424, "epoch": 0.46655966, "global_step/max_steps": "109/233", "percentage": "46.78%", "elapsed_time": "4h 4m 12s", "remaining_time": "4h 37m 49s"}
-{"loss": 0.45284492, "token_acc": 0.85105218, "grad_norm": 0.07013362, "learning_rate": 5.89e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007464, "epoch": 0.47084002, "global_step/max_steps": "110/233", "percentage": "47.21%", "elapsed_time": "4h 5m 8s", "remaining_time": "4h 34m 6s"}
-{"eval_loss": 0.49314782, "eval_token_acc": 0.8371698, "eval_runtime": 241.8865, "eval_samples_per_second": 1.91, "eval_steps_per_second": 0.24, "epoch": 0.47084002, "global_step/max_steps": "110/233", "percentage": "47.21%", "elapsed_time": "4h 9m 10s", "remaining_time": "4h 38m 37s"}
-{"loss": 0.48874846, "token_acc": 0.84027742, "grad_norm": 0.08379927, "learning_rate": 5.84e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007327, "epoch": 0.47512039, "global_step/max_steps": "111/233", "percentage": "47.64%", "elapsed_time": "4h 12m 1s", "remaining_time": "4h 37m 0s"}
-{"loss": 0.53626645, "token_acc": 0.85507952, "grad_norm": 0.09295525, "learning_rate": 5.79e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.007336, "epoch": 0.47940075, "global_step/max_steps": "112/233", "percentage": "48.07%", "elapsed_time": "4h 13m 59s", "remaining_time": "4h 34m 23s"}
-{"loss": 0.47284731, "token_acc": 0.85070551, "grad_norm": 0.08473851, "learning_rate": 5.74e-06, "memory(GiB)": 124.87, "train_speed(iter/s)": 0.00735, "epoch": 0.48368111, "global_step/max_steps": "113/233", "percentage": "48.50%", "elapsed_time": "4h 15m 45s", "remaining_time": "4h 31m 36s"}

+{"loss": 1.22705078, "grad_norm": 6.04194832, "learning_rate": 1.11e-06, "memory(GiB)": 60.26, "train_speed(iter/s)": 0.006333, "rewards/chosen": 0.0, "rewards/rejected": 0.0, "rewards/accuracies": 0.0, "rewards/margins": 0.0, "logps/chosen": -1016.0, "logps/rejected": -1129.0, "logits/chosen": 0.57617188, "logits/rejected": 0.63867188, "nll_loss": 0.53515625, "epoch": 0.01215805, "global_step/max_steps": "1/82", "percentage": "1.22%", "elapsed_time": "2m 25s", "remaining_time": "3h 16m 56s"}
+{"loss": 1.24609375, "grad_norm": 8.70552444, "learning_rate": 2.22e-06, "memory(GiB)": 101.54, "train_speed(iter/s)": 0.007025, "rewards/chosen": 0.0, "rewards/rejected": 0.0, "rewards/accuracies": 0.0, "rewards/margins": 0.0, "logps/chosen": -667.5, "logps/rejected": -835.0, "logits/chosen": 0.39868164, "logits/rejected": 0.57568359, "nll_loss": 0.55371094, "epoch": 0.02431611, "global_step/max_steps": "2/82", "percentage": "2.44%", "elapsed_time": "4m 32s", "remaining_time": "3h 1m 45s"}
+{"loss": 1.28076172, "grad_norm": 6.13274384, "learning_rate": 3.33e-06, "memory(GiB)": 126.46, "train_speed(iter/s)": 0.00727, "rewards/chosen": -0.08450317, "rewards/rejected": -0.0501709, "rewards/accuracies": 0.1875, "rewards/margins": -0.03442383, "logps/chosen": -875.0, "logps/rejected": -942.0, "logits/chosen": 0.46582031, "logits/rejected": 0.55126953, "nll_loss": 0.56152344, "epoch": 0.03647416, "global_step/max_steps": "3/82", "percentage": "3.66%", "elapsed_time": "6m 40s", "remaining_time": "2h 55m 50s"}
+{"loss": 1.1706543, "grad_norm": 5.45653868, "learning_rate": 4.44e-06, "memory(GiB)": 126.46, "train_speed(iter/s)": 0.006883, "rewards/chosen": -0.01716614, "rewards/rejected": -0.10641479, "rewards/accuracies": 0.34375, "rewards/margins": 0.0892334, "logps/chosen": -738.0, "logps/rejected": -911.0, "logits/chosen": 0.44433594, "logits/rejected": 0.57470703, "nll_loss": 0.48730469, "epoch": 0.04863222, "global_step/max_steps": "4/82", "percentage": "4.88%", "elapsed_time": "9m 29s", "remaining_time": "3h 4m 58s"}
+{"loss": 1.26989746, "grad_norm": 5.65177917, "learning_rate": 5.56e-06, "memory(GiB)": 126.46, "train_speed(iter/s)": 0.006898, "rewards/chosen": -0.06253052, "rewards/rejected": -0.1628418, "rewards/accuracies": 0.34375, "rewards/margins": 0.10031128, "logps/chosen": -768.0, "logps/rejected": -810.0, "logits/chosen": 0.45654297, "logits/rejected": 0.52197266, "nll_loss": 0.60253906, "epoch": 0.06079027, "global_step/max_steps": "5/82", "percentage": "6.10%", "elapsed_time": "11m 52s", "remaining_time": "3h 2m 57s"}
+{"loss": 1.07043457, "grad_norm": 5.05655146, "learning_rate": 6.67e-06, "memory(GiB)": 126.46, "train_speed(iter/s)": 0.00658, "rewards/chosen": 0.13772583, "rewards/rejected": -0.37597656, "rewards/accuracies": 0.8125, "rewards/margins": 0.51367188, "logps/chosen": -724.0, "logps/rejected": -874.0, "logits/chosen": 0.28979492, "logits/rejected": 0.55371094, "nll_loss": 0.578125, "epoch": 0.07294833, "global_step/max_steps": "6/82", "percentage": "7.32%", "elapsed_time": "14m 59s", "remaining_time": "3h 9m 57s"}
+{"loss": 0.97070312, "grad_norm": 7.46685266, "learning_rate": 7.78e-06, "memory(GiB)": 126.46, "train_speed(iter/s)": 0.006528, "rewards/chosen": 0.03759766, "rewards/rejected": -1.0, "rewards/accuracies": 0.71875, "rewards/margins": 1.0390625, "logps/chosen": -1348.0, "logps/rejected": -1514.0, "logits/chosen": 0.4609375, "logits/rejected": 0.59375, "nll_loss": 0.54541016, "epoch": 0.08510638, "global_step/max_steps": "7/82", "percentage": "8.54%", "elapsed_time": "17m 40s", "remaining_time": "3h 9m 19s"}
+{"loss": 0.94555664, "grad_norm": 4.44594049, "learning_rate": 8.89e-06, "memory(GiB)": 126.46, "train_speed(iter/s)": 0.006634, "rewards/chosen": -0.63916016, "rewards/rejected": -1.75390625, "rewards/accuracies": 0.78125, "rewards/margins": 1.11328125, "logps/chosen": -860.0, "logps/rejected": -874.0, "logits/chosen": 0.47363281, "logits/rejected": 0.53710938, "nll_loss": 0.54882812, "epoch": 0.09726444, "global_step/max_steps": "8/82", "percentage": "9.76%", "elapsed_time": "19m 53s", "remaining_time": "3h 4m 3s"}
+{"loss": 0.83972168, "grad_norm": 3.38605094, "learning_rate": 1e-05, "memory(GiB)": 126.46, "train_speed(iter/s)": 0.006754, "rewards/chosen": -0.4375, "rewards/rejected": -2.234375, "rewards/accuracies": 0.84375, "rewards/margins": 1.80078125, "logps/chosen": -915.0, "logps/rejected": -951.0, "logits/chosen": 0.49853516, "logits/rejected": 0.57324219, "nll_loss": 0.55664062, "epoch": 0.10942249, "global_step/max_steps": "9/82", "percentage": "10.98%", "elapsed_time": "22m 0s", "remaining_time": "2h 58m 30s"}
+{"loss": 0.89862061, "grad_norm": 5.00063324, "learning_rate": 9.86e-06, "memory(GiB)": 126.46, "train_speed(iter/s)": 0.006542, "rewards/chosen": -1.08129883, "rewards/rejected": -3.76953125, "rewards/accuracies": 0.875, "rewards/margins": 2.69140625, "logps/chosen": -1068.0, "logps/rejected": -1163.0, "logits/chosen": 0.52978516, "logits/rejected": 0.59179688, "nll_loss": 0.54882812, "epoch": 0.12158055, "global_step/max_steps": "10/82", "percentage": "12.20%", "elapsed_time": "25m 16s", "remaining_time": "3h 1m 59s"}
+{"eval_loss": 0.85117668, "eval_runtime": 208.2167, "eval_samples_per_second": 0.389, "eval_steps_per_second": 0.053, "eval_rewards/chosen": -1.99094462, "eval_rewards/rejected": -6.13068199, "eval_rewards/accuracies": 0.85227275, "eval_rewards/margins": 4.1420455, "eval_logps/chosen": -895.45452881, "eval_logps/rejected": -1080.36364746, "eval_logits/chosen": 0.43075284, "eval_logits/rejected": 0.59641337, "eval_nll_loss": 0.5530895, "epoch": 0.12158055, "global_step/max_steps": "10/82", "percentage": "12.20%", "elapsed_time": "28m 44s", "remaining_time": "3h 26m 58s"}
+{"loss": 0.79592896, "grad_norm": 3.04038763, "learning_rate": 9.73e-06, "memory(GiB)": 126.46, "train_speed(iter/s)": 0.005763, "rewards/chosen": -1.82421875, "rewards/rejected": -5.7109375, "rewards/accuracies": 0.90625, "rewards/margins": 3.89257812, "logps/chosen": -749.0, "logps/rejected": -896.0, "logits/chosen": 0.42138672, "logits/rejected": 0.52929688, "nll_loss": 0.546875, "epoch": 0.1337386, "global_step/max_steps": "11/82", "percentage": "13.41%", "elapsed_time": "31m 36s", "remaining_time": "3h 24m 1s"}

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df43775be3ca5ed9f493129d267bbc6c4c98ba16a1243a3f4068b7a4ddc380a
-size 8184

 version https://git-lfs.github.com/spec/v1
+oid sha256:2c0268428df93e67b6c0951edf7255cb02801b7fbf0dcb6439d2ed1a682158d2
+size 9016