pszemraj commited on
Commit
6ccc301
1 Parent(s): 3c7cca8

Update opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16_training_metadata.json

Browse files
opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16_training_metadata.json CHANGED
@@ -1 +1,101 @@
1
- {"output_dir": "/content/drive/MyDrive/Programming/hf-trainer/opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16", "overwrite_output_dir": true, "do_train": false, "do_eval": false, "do_predict": false, "evaluation_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 16, "per_device_eval_batch_size": 16, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 4, "eval_accumulation_steps": 2, "eval_delay": 0, "learning_rate": 1e-05, "weight_decay": 0.1, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1, "num_train_epochs": 4, "max_steps": -1, "lr_scheduler_type": "cosine", "warmup_ratio": 0.05, "warmup_steps": 0, "log_level": -1, "log_level_replica": -1, "log_on_each_node": true, "logging_dir": "/content/drive/MyDrive/Programming/hf-trainer/opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16/logs", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 5, "logging_nan_inf_filter": true, "save_strategy": "epoch", "save_steps": 500, "save_total_limit": 1, "save_on_each_node": false, "no_cuda": false, "seed": 42, "data_seed": "None", "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "amp", "bf16_full_eval": true, "fp16_full_eval": false, "tf32": "None", "local_rank": 0, "xpu_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": "[]", "dataloader_drop_last": false, "eval_steps": "None", "dataloader_num_workers": 0, "past_index": -1, "run_name": "/content/drive/MyDrive/Programming/hf-trainer/opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16", "disable_tqdm": false, "remove_unused_columns": true, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "sharded_ddp": "[]", "fsdp": "[]", "fsdp_min_num_params": 0, "deepspeed": "ds_config_zero2_bf16.json", "label_smoothing_factor": 0.0, "optim": "adamw_hf", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": "['tensorboard']", "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "dataloader_pin_memory": true, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": true, "resume_from_checkpoint": "None", "hub_model_id": "opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16", "hub_strategy": "end", "hub_token": "<HUB_TOKEN>", "hub_private_repo": false, "gradient_checkpointing": true, "include_inputs_for_metrics": false, "fp16_backend": "auto", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "_n_gpu": 1, "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "train_batch_size": 16, "eval_batch_size": 16, "configs_src": "opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16", "data_tag": "text-file-input"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir":"/content/drive/MyDrive/Programming/hf-trainer/opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16",
3
+ "overwrite_output_dir":true,
4
+ "do_train":false,
5
+ "do_eval":false,
6
+ "do_predict":false,
7
+ "evaluation_strategy":"no",
8
+ "prediction_loss_only":false,
9
+ "per_device_train_batch_size":16,
10
+ "per_device_eval_batch_size":16,
11
+ "per_gpu_train_batch_size":"None",
12
+ "per_gpu_eval_batch_size":"None",
13
+ "gradient_accumulation_steps":4,
14
+ "eval_accumulation_steps":2,
15
+ "eval_delay":0,
16
+ "learning_rate":1e-05,
17
+ "weight_decay":0.1,
18
+ "adam_beta1":0.9,
19
+ "adam_beta2":0.999,
20
+ "adam_epsilon":1e-08,
21
+ "max_grad_norm":1,
22
+ "num_train_epochs":4,
23
+ "max_steps":-1,
24
+ "lr_scheduler_type":"cosine",
25
+ "warmup_ratio":0.05,
26
+ "warmup_steps":0,
27
+ "log_level":-1,
28
+ "log_level_replica":-1,
29
+ "log_on_each_node":true,
30
+ "logging_dir":"/content/drive/MyDrive/Programming/hf-trainer/opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16/logs",
31
+ "logging_strategy":"steps",
32
+ "logging_first_step":false,
33
+ "logging_steps":5,
34
+ "logging_nan_inf_filter":true,
35
+ "save_strategy":"epoch",
36
+ "save_steps":500,
37
+ "save_total_limit":1,
38
+ "save_on_each_node":false,
39
+ "no_cuda":false,
40
+ "seed":42,
41
+ "data_seed":"None",
42
+ "bf16":true,
43
+ "fp16":false,
44
+ "fp16_opt_level":"O1",
45
+ "half_precision_backend":"amp",
46
+ "bf16_full_eval":true,
47
+ "fp16_full_eval":false,
48
+ "tf32":"None",
49
+ "local_rank":0,
50
+ "xpu_backend":"None",
51
+ "tpu_num_cores":"None",
52
+ "tpu_metrics_debug":false,
53
+ "debug":"[]",
54
+ "dataloader_drop_last":false,
55
+ "eval_steps":"None",
56
+ "dataloader_num_workers":0,
57
+ "past_index":-1,
58
+ "run_name":"/content/drive/MyDrive/Programming/hf-trainer/opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16",
59
+ "disable_tqdm":false,
60
+ "remove_unused_columns":true,
61
+ "label_names":"None",
62
+ "load_best_model_at_end":false,
63
+ "metric_for_best_model":"None",
64
+ "greater_is_better":"None",
65
+ "ignore_data_skip":false,
66
+ "sharded_ddp":"[]",
67
+ "fsdp":"[]",
68
+ "fsdp_min_num_params":0,
69
+ "deepspeed":"ds_config_zero2_bf16.json",
70
+ "label_smoothing_factor":0.0,
71
+ "optim":"adamw_hf",
72
+ "adafactor":false,
73
+ "group_by_length":false,
74
+ "length_column_name":"length",
75
+ "report_to":"['tensorboard']",
76
+ "ddp_find_unused_parameters":"None",
77
+ "ddp_bucket_cap_mb":"None",
78
+ "dataloader_pin_memory":true,
79
+ "skip_memory_metrics":true,
80
+ "use_legacy_prediction_loop":false,
81
+ "push_to_hub":true,
82
+ "resume_from_checkpoint":"None",
83
+ "hub_model_id":"opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16",
84
+ "hub_strategy":"end",
85
+ "hub_token":"<HUB_TOKEN>",
86
+ "hub_private_repo":false,
87
+ "gradient_checkpointing":true,
88
+ "include_inputs_for_metrics":false,
89
+ "fp16_backend":"auto",
90
+ "push_to_hub_model_id":"None",
91
+ "push_to_hub_organization":"None",
92
+ "push_to_hub_token":"<PUSH_TO_HUB_TOKEN>",
93
+ "_n_gpu":1,
94
+ "mp_parameters":"",
95
+ "auto_find_batch_size":false,
96
+ "full_determinism":false,
97
+ "train_batch_size":16,
98
+ "eval_batch_size":16,
99
+ "configs_src":"opt-peter-2pt7B-ps_DS-msgs_Ep-4_Bs-16",
100
+ "data_tag":"text-file-input"
101
+ }