Upload folder using huggingface_hub

config.json

@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 29568,
   "max_position_embeddings": 32768,
-  "max_window_layers": 70,
+  "max_window_layers": 80,
   "model_type": "qwen2",
   "num_attention_heads": 64,
   "num_hidden_layers": 80,

model-00001-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad7a7ec11156a438742239b9d58e77cc4a6b6ad31fbe96e7c2cf686c1998328
+oid sha256:d189be1ade0a7bdf7f4bd86788f4846fc89b12b28ece8f42e2fc308dd46a7a66
 size 4548798728

model-00002-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:affb76f94c072141f48dbf5283ed0d71db805d934be5bb9e8e186c96be917585
+oid sha256:78b5bc3946135593a8f831e34003d7dbd375e3063f6047491c47c4ab550c27b6
 size 4964101384

model-00003-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9adc8f4ac33ff52da4e5705236af00a8d140175869e30355984872d157f9f263
+oid sha256:c7862bfe9a14ec5d156363302ef01285449cb52320041370ecb8a1c3a5129aad
 size 4781637328

model-00004-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e0c77ad152fff32e373484988bb4484416e6a54bdafaa8ff492f34d42a5499
+oid sha256:e53b60a96bd2feac4c98e2944db566ade74c4ebedf771c67c0475f81b754464a
 size 4781670320

model-00005-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a90004df778956f4f8a1bab9a123ecd567014ff68a22168647c2b66be12875b
+oid sha256:f803d2bc0fc3fb2e7143b6d6cb62baa0c0a9b41a73fcbe6db7aa00fba8f35d63
 size 4781670360

model-00006-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645983f213fed8c4b0db7eaa3fb3db7f55a7631c2da305908b243d6241a402f4
+oid sha256:9894acb53032b6e041aa0cc0f04a7ac469271ce586fc3cb668046c980b4e1c98
 size 4964101416

model-00007-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f1bd559e5d6b4b1e36e8c8d77319591f5a6b25752528da8a557ad2087150a5e
+oid sha256:26353391e8172671035fb28c0f9eeacb2640861c4810eb71e818b83d385e7661
 size 4781637360

model-00008-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cbc9a5e2c44cebd7841925db4e72a1ff6b503303ac770814ebad0a427a0f23
+oid sha256:e69ede2230a527aaf5f0682ec5fbe024225072d8872a35cde6fd1f02628a1aaa
 size 4781670360

model-00009-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b5348ac7a3786fb63406fe45af952d394ca07f47a183d609448c6fb0251a2d9
+oid sha256:2ff7dba638d6de35a8645ffc99187234da7cf0bfedbcdfb1a574282d9e3b4a5e
 size 4781670360

model-00010-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedc5b6c8c4ee2dec90b68d29bf4e97b15604ee30de0c685a4ce41946e62bdd4
+oid sha256:224ef0f6b77c28660ca872db218a01c205c4b91c21c6f4903adb240f1feaf1f8
 size 4964101416

model-00011-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f1ef26e820675b195998943571c7e3347deb33a15efee28f55ecf3b3e02f13f
+oid sha256:659a24bd9c681cd7cd8eb93cdbbffcc79dea955cd4887f37bd1799ad24e69a8c
 size 4781637360

model-00012-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a20f51d0b8b8c86f72a7811d0bc4e6c2b70a1745736f114ea03c0f47a03a47e4
+oid sha256:40484b390a629b6e841385e30f26340222aa8c0093f46d60340580565235dbd9
 size 4781670360

model-00013-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e15c10ca130da873bac8e80fd97d8fe646ea3bdca159a37126c1098a65ca21a
+oid sha256:83104b9bb184383b0bf37aab2239213001189737ea57d68811ed9964d7a6dca7
 size 4781670360

model-00014-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643eac48f2187a176ba544f950b585978a3e62571085a998200c0c36f66a78b1
+oid sha256:0ce46a4c2dc37bdf983941c0526d69d2b813d735ae0aeb876a6087229dc417e9
 size 4964101416

model-00015-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cafe18fd3bb82113e45160f99495607bc8e0a0f5fd7cc594c66654682ce16f5
+oid sha256:a4847faed6468d33dcd1788e2710fa69ccb3af19cd8596666083222dac817d24
 size 4781637360

model-00016-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ff775f9c488c9e0038f80aaf9ec7d4d0cf705bd391fd68c482349c3e9145fa
+oid sha256:c127df484608133e95f54d275190f407045546131c9592f2572b2441737e7f00
 size 4781670360

model-00017-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670f743f801a8272a19dc7adf437aab81a87a8810933f89637243b51401c3156
+oid sha256:4c45204750c9e3811f1f1ffae752f5ee6b21ac10b4a7a1e1d86b1dfb50bf7e3d
 size 4781670360

model-00018-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2e8c2835dc9e3a3c0955bafc735b4916e33b7a0be7894574799490b68af342
+oid sha256:9c62fcd870f1b623db6cb09c9e79ca81144ec6f185e0498e46aa13bc131d7d89
 size 4964101416

model-00019-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca8bab67232b46e2cf925b4cf1458e6bcf3ff89abae33d4cb92e1e2647bb03d
+oid sha256:d409e6527535f1a390bad83d35fd9854e43b362c96f422fe5c0564c3639a6be2
 size 4781637360

model-00020-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60aeedf491430e1cb551149548b9b56f8a8751e8650ca199ae20bc2644f4b77f
+oid sha256:31084d34a4ab0bfadba9c2f8291f92c8935eacbb5f300018ae7f215c69ac2d41
 size 4781670360

model-00021-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4948c297ae104ad838d98e9677528e1954b5914ecc00809bb64368d3cd875799
+oid sha256:52d14a8c3d34fd4017dec29421d18f8aae080e7e40a5584f7d426ddde143a7c3
 size 4781670360

model-00022-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebaa466ef49cbc8ec9ce4fd688dec985f6c2659e9290854a8941a3faa21ff7b
+oid sha256:d960bf183aa80d626d58d8cae7c77a6b3a790e4b5b3780631e60d9337b08a404
 size 4964101416

model-00023-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df78ced85cf522b9e0da98cc8125d5156f836c39639a25c18634e9bb289b026d
+oid sha256:18e0b8b591fbe6b65cc551f23cacdf65b704333ff06a60661cb90373812f60d9
 size 4781637360

model-00024-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9afe0fdfddf337b90c82f6bd56b25e2c193c8ba1ca2819d220d0aa1a99663824
+oid sha256:5908f63dac691fbf0bb05873263cfc42e4256f04ec6751b01052e1a7a10e9139
 size 4781670360

model-00025-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8c32191b0384dcecfeebea25e965c2cb07264bbbe1704c0dd008d153ae690fe
+oid sha256:6aa32b5839014fb96b10ddf685c0b7895ce54de4048917f1a15109a3ff497d50
 size 4781670360

model-00026-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0befd2925e999609187e3d40dcfa4b791aaa3f765abe6f3f7d5890977260bd90
+oid sha256:ca4f2b8ce19789b17e2926ed859b17007f4828f5508af163b9c70bd2c7ad6ad9
 size 4964101416

model-00027-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfc307ecb424966e66352f84bc94876c9297c459fa66737b4833b0d78832194
+oid sha256:2fe48f82357032630f6bcb1c7e191a9362f1602498709c2889f8cb3f4aaedbf3
 size 4781637360

model-00028-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aff56c24b621f027f21e0bc56ce526dfcb8c10d791b1d49a6a34229df4eab2d4
+oid sha256:b0868ceb592ef939c9703dca6b5e985abe32a797a5a2fcd08db6260cef94b835
 size 4781670360

model-00029-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b10d65c769a88b706598f2c80560b13752ca896087d31f0273ff7d8e94d1771c
+oid sha256:6bca7d7b0a094b243e47d96ff300a0e3a657df7353000e4221a899c9908f53e6
 size 4781670360

model-00030-of-00031.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a53abb9ceaae4786236beb0edceb303cf4753a56441e01d44dedd12e662ca8
+oid sha256:ade1434e683b8cc9c98732b463dca7b91a9a513a350ffad97e1e7fcb067dd5ca
 size 3208747032

sft_args.json

@@ -7,13 +7,13 @@
   "additional_trainable_parameters": [],
   "tuner_backend": "peft",
   "template_type": "qwen",
-  "output_dir": "/root/swift/esft/output/qwen2-72b-instruct/v12-20240625-155052",
+  "output_dir": "/root/swift/output/qwen2-72b-instruct/v6-20240730-130324",
   "add_output_dir_suffix": true,
   "ddp_backend": "nccl",
   "ddp_find_unused_parameters": null,
   "ddp_broadcast_buffers": null,
   "seed": 42,
-  "resume_from_checkpoint": null,
+  "resume_from_checkpoint": "/root/swift/output/qwen2-72b-instruct/v5-20240730-113708/checkpoint-700",
   "resume_only_model": false,
   "ignore_data_skip": false,
   "dtype": "bf16",
@@ -23,6 +23,8 @@
     "dataset/moni_dataset.jsonl",
     "dataset/moni_dataset.jsonl",
     "dataset/moni_dataset.jsonl",
+    "dataset/moni_dataset_en.jsonl",
+    "dataset/moni_dataset_en.jsonl",
     "dataset/covid_new.jsonl",
     "dataset/covid_new.jsonl",
     "dataset/covid_new.jsonl",
@@ -75,21 +77,18 @@
   "bnb_4bit_quant_type": "nf4",
   "bnb_4bit_use_double_quant": true,
   "bnb_4bit_quant_storage": null,
-  "lora_target_modules": [
-    "q_proj",
-    "k_proj",
-    "v_proj"
-  ],
+  "lora_target_modules": [],
+  "lora_target_regex": null,
   "lora_rank": 16,
   "lora_alpha": 32,
   "lora_dropout_p": 0.06,
   "lora_bias_trainable": "none",
   "lora_modules_to_save": [],
-  "lora_dtype": null,
+  "lora_dtype": "AUTO",
   "lora_lr_ratio": null,
   "use_rslora": false,
   "use_dora": false,
-  "init_lora_weights": true,
+  "init_lora_weights": "true",
   "rope_scaling": null,
   "boft_block_size": 4,
   "boft_block_num": 0,
@@ -117,6 +116,13 @@
   "galore_proj_type": "std",
   "galore_optim_per_parameter": false,
   "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
   "adalora_target_r": 8,
   "adalora_init_r": 12,
   "adalora_tinit": 0,
@@ -140,7 +146,7 @@
   "deepspeed": null,
   "batch_size": 2,
   "eval_batch_size": 2,
-  "num_train_epochs": 6,
+  "num_train_epochs": 8,
   "max_steps": -1,
   "optim": "adamw_torch",
   "adam_beta1": 0.9,
@@ -151,13 +157,16 @@
   "gradient_accumulation_steps": 16,
   "max_grad_norm": 0.5,
   "predict_with_generate": false,
-  "lr_scheduler_type": "linear",
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
   "warmup_ratio": 0.03,
+  "warmup_steps": 0,
   "eval_steps": 50,
   "save_steps": 50,
   "save_only_model": false,
   "save_total_limit": null,
   "logging_steps": 5,
+  "acc_steps": 1,
   "dataloader_num_workers": 1,
   "dataloader_pin_memory": true,
   "dataloader_drop_last": false,
@@ -173,7 +182,7 @@
   "use_flash_attn": true,
   "ignore_args_error": false,
   "check_model_is_latest": true,
-  "logging_dir": "/root/swift/esft/output/qwen2-72b-instruct/v12-20240625-155052/runs",
+  "logging_dir": "/root/swift/output/qwen2-72b-instruct/v6-20240730-130324/runs",
   "report_to": [
     "tensorboard"
   ],
@@ -188,6 +197,7 @@
   "custom_register_path": null,
   "custom_dataset_info": "/root/swift/dataset/ds_info.json",
   "device_map_config_path": null,
+  "device_max_memory": [],
   "max_new_tokens": 2048,
   "do_sample": true,
   "temperature": 0.3,
@@ -219,8 +229,9 @@
   "custom_train_dataset_path": [],
   "custom_val_dataset_path": [],
   "use_self_cognition": false,
+  "is_multimodal": false,
   "lora_use_embedding": false,
-  "lora_use_all": false,
+  "lora_use_all": true,
   "lora_m2s_use_embedding": false,
   "lora_m2s_use_ln": false,
   "torch_dtype": "torch.bfloat16",
@@ -230,5 +241,5 @@
   "load_in_4bit": false,
   "load_in_8bit": false,
   "train_sampler_random": true,
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/swift/esft/output/qwen2-72b-instruct/v12-20240625-155052', 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=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=6, max_steps=-1, lr_scheduler_type=<SchedulerType.LINEAR: 'linear'>, lr_scheduler_kwargs={}, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/swift/esft/output/qwen2-72b-instruct/v12-20240625-155052/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=True, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, 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='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/swift/esft/output/qwen2-72b-instruct/v12-20240625-155052', 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=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None), deepspeed=None, 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=['tensorboard'], ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=False, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"temperature\": 0.3,\n  \"top_k\": 20,\n  \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=14019)"
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/swift/output/qwen2-72b-instruct/v6-20240730-130324', 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=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=8, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/swift/output/qwen2-72b-instruct/v6-20240730-130324/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=True, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, 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='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/swift/output/qwen2-72b-instruct/v6-20240730-130324', 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=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None), deepspeed=None, 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=['tensorboard'], ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=False, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint='/root/swift/output/qwen2-72b-instruct/v5-20240730-113708/checkpoint-700', hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"temperature\": 0.3,\n  \"top_k\": 20,\n  \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=17395)"
 }