Training in progress, step 10

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "gate_proj",
     "down_proj",
     "k_proj",
+    "gate_proj",
+    "up_proj",
     "o_proj",
-    "up_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16cfb7ed4012e139d31d17a7e0c8887850221d9dbd03bd5ea016ac67f4a3896a
+oid sha256:2de2aa7db8b68aae38cf2762b6c25667eb59930c2585b143489a49286ed62ce7
 size 13474358304

args.json

@@ -74,7 +74,7 @@
   "custom_register_path": [],
   "ignore_args_error": false,
   "use_swift_lora": false,
-  "output_dir": "/root/dataDisk/output/v27-20250303-111010",
+  "output_dir": "/root/dataDisk/output/v28-20250303-123303",
   "overwrite_output_dir": false,
   "do_train": false,
   "do_eval": false,
@@ -89,7 +89,7 @@
   "eval_accumulation_steps": null,
   "eval_delay": 0,
   "torch_empty_cache_steps": null,
-  "learning_rate": 0.0005,
+  "learning_rate": 1e-05,
   "weight_decay": 0.01,
   "adam_beta1": 0.9,
   "adam_beta2": 0.999,
@@ -104,7 +104,7 @@
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
-  "logging_dir": "/root/dataDisk/output/v27-20250303-111010/runs",
+  "logging_dir": "/root/dataDisk/output/v28-20250303-123303/runs",
   "logging_strategy": "steps",
   "logging_first_step": true,
   "logging_steps": 1,
@@ -341,8 +341,8 @@
   "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 0x7fadf2bd4280>, 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_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/v27-20250303-111010', 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=0.0005, 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/v27-20250303-111010/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/v27-20250303-111010', 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/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)"
 }

logging.jsonl

@@ -1,37 +1,14 @@
-{"loss": 1.08013344, "token_acc": 0.77033758, "grad_norm": 1.14967191, "learning_rate": 2.083e-05, "memory(GiB)": 50.63, "train_speed(iter/s)": 0.006242, "epoch": 0.00428036, "global_step/max_steps": "1/233", "percentage": "0.43%", "elapsed_time": "2m 9s", "remaining_time": "8h 22m 26s"}
-{"loss": 1.03408611, "token_acc": 0.78389394, "grad_norm": 1.04655504, "learning_rate": 4.167e-05, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.006683, "epoch": 0.00856073, "global_step/max_steps": "2/233", "percentage": "0.86%", "elapsed_time": "4m 29s", "remaining_time": "8h 37m 51s"}
-{"loss": 0.73545182, "token_acc": 0.79800763, "grad_norm": 0.21168555, "learning_rate": 6.25e-05, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007554, "epoch": 0.01284109, "global_step/max_steps": "3/233", "percentage": "1.29%", "elapsed_time": "6m 6s", "remaining_time": "7h 48m 49s"}
-{"loss": 0.6847831, "token_acc": 0.82060266, "grad_norm": 0.18280333, "learning_rate": 8.333e-05, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.008365, "epoch": 0.01712146, "global_step/max_steps": "4/233", "percentage": "1.72%", "elapsed_time": "7m 27s", "remaining_time": "7h 7m 22s"}
-{"loss": 0.60886723, "token_acc": 0.81700248, "grad_norm": 0.10077205, "learning_rate": 0.00010417, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.009404, "epoch": 0.02140182, "global_step/max_steps": "5/233", "percentage": "2.15%", "elapsed_time": "8m 21s", "remaining_time": "6h 21m 5s"}
-{"loss": 0.60938561, "token_acc": 0.83880078, "grad_norm": 0.11720943, "learning_rate": 0.000125, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.010013, "epoch": 0.02568218, "global_step/max_steps": "6/233", "percentage": "2.58%", "elapsed_time": "9m 28s", "remaining_time": "5h 58m 45s"}
-{"loss": 0.54639411, "token_acc": 0.84131633, "grad_norm": 0.09850983, "learning_rate": 0.00014583, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.010169, "epoch": 0.02996255, "global_step/max_steps": "7/233", "percentage": "3.00%", "elapsed_time": "10m 58s", "remaining_time": "5h 54m 6s"}
-{"loss": 0.59427178, "token_acc": 0.80326218, "grad_norm": 0.1070973, "learning_rate": 0.00016667, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.010102, "epoch": 0.03424291, "global_step/max_steps": "8/233", "percentage": "3.43%", "elapsed_time": "12m 41s", "remaining_time": "5h 57m 2s"}
-{"loss": 0.55651379, "token_acc": 0.8225492, "grad_norm": 0.07836337, "learning_rate": 0.0001875, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.010143, "epoch": 0.03852327, "global_step/max_steps": "9/233", "percentage": "3.86%", "elapsed_time": "14m 17s", "remaining_time": "5h 55m 30s"}
-{"loss": 0.54214001, "token_acc": 0.83604651, "grad_norm": 0.13948776, "learning_rate": 0.00020833, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.009758, "epoch": 0.04280364, "global_step/max_steps": "10/233", "percentage": "4.29%", "elapsed_time": "16m 34s", "remaining_time": "6h 9m 37s"}
-{"eval_loss": 0.55939144, "eval_token_acc": 0.81976547, "eval_runtime": 243.6841, "eval_samples_per_second": 1.896, "eval_steps_per_second": 0.238, "epoch": 0.04280364, "global_step/max_steps": "10/233", "percentage": "4.29%", "elapsed_time": "20m 38s", "remaining_time": "7h 40m 11s"}
-{"loss": 0.61308545, "token_acc": 0.82125033, "grad_norm": 0.08491442, "learning_rate": 0.00022917, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007341, "epoch": 0.047084, "global_step/max_steps": "11/233", "percentage": "4.72%", "elapsed_time": "24m 28s", "remaining_time": "8h 13m 50s"}
-{"loss": 0.55441093, "token_acc": 0.82960534, "grad_norm": 0.10314213, "learning_rate": 0.00025, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007612, "epoch": 0.05136437, "global_step/max_steps": "12/233", "percentage": "5.15%", "elapsed_time": "25m 46s", "remaining_time": "7h 54m 34s"}
-{"loss": 0.62597644, "token_acc": 0.81842302, "grad_norm": 0.15295561, "learning_rate": 0.00027083, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007728, "epoch": 0.05564473, "global_step/max_steps": "13/233", "percentage": "5.58%", "elapsed_time": "27m 32s", "remaining_time": "7h 45m 57s"}
-{"loss": 0.59355724, "token_acc": 0.84658678, "grad_norm": 0.12701987, "learning_rate": 0.00029167, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007685, "epoch": 0.05992509, "global_step/max_steps": "14/233", "percentage": "6.01%", "elapsed_time": "29m 51s", "remaining_time": "7h 47m 3s"}
-{"loss": 0.54825062, "token_acc": 0.86142433, "grad_norm": 0.09068999, "learning_rate": 0.0003125, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007947, "epoch": 0.06420546, "global_step/max_steps": "15/233", "percentage": "6.44%", "elapsed_time": "30m 57s", "remaining_time": "7h 29m 53s"}
-{"loss": 0.57663035, "token_acc": 0.84653878, "grad_norm": 0.50620914, "learning_rate": 0.00033333, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.008079, "epoch": 0.06848582, "global_step/max_steps": "16/233", "percentage": "6.87%", "elapsed_time": "32m 30s", "remaining_time": "7h 20m 50s"}
-{"loss": 0.79894209, "token_acc": 0.82371735, "grad_norm": 1.55294037, "learning_rate": 0.00035417, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007999, "epoch": 0.07276619, "global_step/max_steps": "17/233", "percentage": "7.30%", "elapsed_time": "34m 54s", "remaining_time": "7h 23m 38s"}
-{"loss": 3.18830538, "token_acc": 0.54494557, "grad_norm": 28.07760811, "learning_rate": 0.000375, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.008048, "epoch": 0.07704655, "global_step/max_steps": "18/233", "percentage": "7.73%", "elapsed_time": "36m 46s", "remaining_time": "7h 19m 11s"}
-{"loss": 0.83831924, "token_acc": 0.77933681, "grad_norm": 1.0892489, "learning_rate": 0.00039583, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.008113, "epoch": 0.08132691, "global_step/max_steps": "19/233", "percentage": "8.15%", "elapsed_time": "38m 31s", "remaining_time": "7h 13m 55s"}
-{"loss": 2.39103127, "token_acc": 0.58057627, "grad_norm": 19.11563873, "learning_rate": 0.00041667, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007838, "epoch": 0.08560728, "global_step/max_steps": "20/233", "percentage": "8.58%", "elapsed_time": "42m 1s", "remaining_time": "7h 27m 34s"}
-{"eval_loss": 9.96582317, "eval_token_acc": 0.01661826, "eval_runtime": 242.1037, "eval_samples_per_second": 1.908, "eval_steps_per_second": 0.24, "epoch": 0.08560728, "global_step/max_steps": "20/233", "percentage": "8.58%", "elapsed_time": "46m 3s", "remaining_time": "8h 10m 33s"}
-{"loss": 10.93847656, "token_acc": 0.01688988, "grad_norm": 10.45749569, "learning_rate": 0.0004375, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007026, "epoch": 0.08988764, "global_step/max_steps": "21/233", "percentage": "9.01%", "elapsed_time": "49m 18s", "remaining_time": "8h 17m 46s"}
-{"loss": 8.95218849, "token_acc": 0.02160938, "grad_norm": 13.93012524, "learning_rate": 0.00045833, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.00719, "epoch": 0.094168, "global_step/max_steps": "22/233", "percentage": "9.44%", "elapsed_time": "50m 29s", "remaining_time": "8h 4m 16s"}
-{"loss": 12.16601658, "token_acc": 0.00779495, "grad_norm": 5.7592063, "learning_rate": 0.00047917, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007323, "epoch": 0.09844837, "global_step/max_steps": "23/233", "percentage": "9.87%", "elapsed_time": "51m 50s", "remaining_time": "7h 53m 21s"}
-{"loss": 17.70026779, "token_acc": 0.01229508, "grad_norm": 10.22618771, "learning_rate": 0.0005, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007385, "epoch": 0.10272873, "global_step/max_steps": "24/233", "percentage": "10.30%", "elapsed_time": "53m 39s", "remaining_time": "7h 47m 16s"}
-{"loss": 15.97851086, "token_acc": 0.03223443, "grad_norm": 15.5822897, "learning_rate": 0.00049761, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007465, "epoch": 0.1070091, "global_step/max_steps": "25/233", "percentage": "10.73%", "elapsed_time": "55m 18s", "remaining_time": "7h 40m 11s"}
-{"loss": 24.55121994, "token_acc": 0.0, "grad_norm": 7.36107159, "learning_rate": 0.00049522, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007578, "epoch": 0.11128946, "global_step/max_steps": "26/233", "percentage": "11.16%", "elapsed_time": "56m 40s", "remaining_time": "7h 31m 14s"}
-{"loss": 35.2902298, "token_acc": 0.02265006, "grad_norm": 5.54141712, "learning_rate": 0.00049282, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007662, "epoch": 0.11556982, "global_step/max_steps": "27/233", "percentage": "11.59%", "elapsed_time": "58m 13s", "remaining_time": "7h 24m 16s"}
-{"loss": 19.95904922, "token_acc": 0.02717839, "grad_norm": 4.47130251, "learning_rate": 0.00049043, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007751, "epoch": 0.11985019, "global_step/max_steps": "28/233", "percentage": "12.02%", "elapsed_time": "59m 42s", "remaining_time": "7h 17m 5s"}
-{"loss": 28.7828846, "token_acc": 0.0, "grad_norm": 9.8132925, "learning_rate": 0.00048804, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007803, "epoch": 0.12413055, "global_step/max_steps": "29/233", "percentage": "12.45%", "elapsed_time": "1h 1m 26s", "remaining_time": "7h 12m 12s"}
-{"loss": 16.39430046, "token_acc": 0.00518337, "grad_norm": 10.84445763, "learning_rate": 0.00048565, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007929, "epoch": 0.12841091, "global_step/max_steps": "30/233", "percentage": "12.88%", "elapsed_time": "1h 2m 33s", "remaining_time": "7h 3m 19s"}
-{"eval_loss": 15.26913452, "eval_token_acc": 0.0402941, "eval_runtime": 242.2053, "eval_samples_per_second": 1.907, "eval_steps_per_second": 0.239, "epoch": 0.12841091, "global_step/max_steps": "30/233", "percentage": "12.88%", "elapsed_time": "1h 6m 35s", "remaining_time": "7h 30m 38s"}
-{"loss": 14.93047237, "token_acc": 0.0387338, "grad_norm": 1.38892937, "learning_rate": 0.00048325, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007395, "epoch": 0.13269128, "global_step/max_steps": "31/233", "percentage": "13.30%", "elapsed_time": "1h 9m 21s", "remaining_time": "7h 31m 59s"}
-{"loss": 29.76581764, "token_acc": 0.0, "grad_norm": 4.99842024, "learning_rate": 0.00048086, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007352, "epoch": 0.13697164, "global_step/max_steps": "32/233", "percentage": "13.73%", "elapsed_time": "1h 12m 2s", "remaining_time": "7h 32m 30s"}
-{"loss": 24.07614708, "token_acc": 0.0, "grad_norm": 2.62943816, "learning_rate": 0.00047847, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007375, "epoch": 0.14125201, "global_step/max_steps": "33/233", "percentage": "14.16%", "elapsed_time": "1h 14m 4s", "remaining_time": "7h 28m 54s"}
-{"loss": 17.68056297, "token_acc": 0.03836658, "grad_norm": 2.277601, "learning_rate": 0.00047608, "memory(GiB)": 125.19, "train_speed(iter/s)": 0.007452, "epoch": 0.14553237, "global_step/max_steps": "34/233", "percentage": "14.59%", "elapsed_time": "1h 15m 32s", "remaining_time": "7h 22m 8s"}
+{"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"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f1d9d35d7a311734aa4f9d416399e918d3103037e05a94f9742f7eb4770f237
+oid sha256:2df43775be3ca5ed9f493129d267bbc6c4c98ba16a1243a3f4068b7a4ddc380a
 size 8184