Prikshit7766
commited on
Commit
•
22f0621
1
Parent(s):
e975353
Upload training_args.json with huggingface_hub
Browse files- training_args.json +142 -0
training_args.json
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"output_dir": "trainer",
|
3 |
+
"overwrite_output_dir": false,
|
4 |
+
"do_train": false,
|
5 |
+
"do_eval": true,
|
6 |
+
"do_predict": false,
|
7 |
+
"eval_strategy": "epoch",
|
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": null,
|
12 |
+
"per_gpu_eval_batch_size": null,
|
13 |
+
"gradient_accumulation_steps": 2,
|
14 |
+
"eval_accumulation_steps": null,
|
15 |
+
"eval_delay": 0,
|
16 |
+
"torch_empty_cache_steps": null,
|
17 |
+
"learning_rate": 2e-05,
|
18 |
+
"weight_decay": 0.01,
|
19 |
+
"adam_beta1": 0.9,
|
20 |
+
"adam_beta2": 0.999,
|
21 |
+
"adam_epsilon": 1e-08,
|
22 |
+
"max_grad_norm": 1.0,
|
23 |
+
"num_train_epochs": 20,
|
24 |
+
"max_steps": -1,
|
25 |
+
"lr_scheduler_type": "linear",
|
26 |
+
"lr_scheduler_kwargs": {},
|
27 |
+
"warmup_ratio": 0.0,
|
28 |
+
"warmup_steps": 500,
|
29 |
+
"log_level": "passive",
|
30 |
+
"log_level_replica": "warning",
|
31 |
+
"log_on_each_node": true,
|
32 |
+
"logging_dir": "trainer\\runs\\Oct20_23-26-19_Prism",
|
33 |
+
"logging_strategy": "steps",
|
34 |
+
"logging_first_step": false,
|
35 |
+
"logging_steps": 100,
|
36 |
+
"logging_nan_inf_filter": true,
|
37 |
+
"save_strategy": "epoch",
|
38 |
+
"save_steps": 500,
|
39 |
+
"save_total_limit": 3,
|
40 |
+
"save_safetensors": true,
|
41 |
+
"save_on_each_node": false,
|
42 |
+
"save_only_model": false,
|
43 |
+
"restore_callback_states_from_checkpoint": false,
|
44 |
+
"no_cuda": false,
|
45 |
+
"use_cpu": false,
|
46 |
+
"use_mps_device": false,
|
47 |
+
"seed": 42,
|
48 |
+
"data_seed": null,
|
49 |
+
"jit_mode_eval": false,
|
50 |
+
"use_ipex": false,
|
51 |
+
"bf16": false,
|
52 |
+
"fp16": true,
|
53 |
+
"fp16_opt_level": "O1",
|
54 |
+
"half_precision_backend": "auto",
|
55 |
+
"bf16_full_eval": false,
|
56 |
+
"fp16_full_eval": false,
|
57 |
+
"tf32": null,
|
58 |
+
"local_rank": 0,
|
59 |
+
"ddp_backend": null,
|
60 |
+
"tpu_num_cores": null,
|
61 |
+
"tpu_metrics_debug": false,
|
62 |
+
"debug": [],
|
63 |
+
"dataloader_drop_last": false,
|
64 |
+
"eval_steps": null,
|
65 |
+
"dataloader_num_workers": 0,
|
66 |
+
"dataloader_prefetch_factor": null,
|
67 |
+
"past_index": -1,
|
68 |
+
"run_name": "trainer",
|
69 |
+
"disable_tqdm": false,
|
70 |
+
"remove_unused_columns": true,
|
71 |
+
"label_names": null,
|
72 |
+
"load_best_model_at_end": true,
|
73 |
+
"metric_for_best_model": "f1",
|
74 |
+
"greater_is_better": true,
|
75 |
+
"ignore_data_skip": false,
|
76 |
+
"fsdp": [],
|
77 |
+
"fsdp_min_num_params": 0,
|
78 |
+
"fsdp_config": {
|
79 |
+
"min_num_params": 0,
|
80 |
+
"xla": false,
|
81 |
+
"xla_fsdp_v2": false,
|
82 |
+
"xla_fsdp_grad_ckpt": false
|
83 |
+
},
|
84 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
85 |
+
"accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)",
|
86 |
+
"deepspeed": null,
|
87 |
+
"label_smoothing_factor": 0.0,
|
88 |
+
"optim": "adamw_torch",
|
89 |
+
"optim_args": null,
|
90 |
+
"adafactor": false,
|
91 |
+
"group_by_length": false,
|
92 |
+
"length_column_name": "length",
|
93 |
+
"report_to": [
|
94 |
+
"tensorboard"
|
95 |
+
],
|
96 |
+
"ddp_find_unused_parameters": null,
|
97 |
+
"ddp_bucket_cap_mb": null,
|
98 |
+
"ddp_broadcast_buffers": null,
|
99 |
+
"dataloader_pin_memory": true,
|
100 |
+
"dataloader_persistent_workers": false,
|
101 |
+
"skip_memory_metrics": true,
|
102 |
+
"use_legacy_prediction_loop": false,
|
103 |
+
"push_to_hub": false,
|
104 |
+
"resume_from_checkpoint": null,
|
105 |
+
"hub_model_id": null,
|
106 |
+
"hub_strategy": "every_save",
|
107 |
+
"hub_token": null,
|
108 |
+
"hub_private_repo": false,
|
109 |
+
"hub_always_push": false,
|
110 |
+
"gradient_checkpointing": false,
|
111 |
+
"gradient_checkpointing_kwargs": null,
|
112 |
+
"include_inputs_for_metrics": false,
|
113 |
+
"eval_do_concat_batches": true,
|
114 |
+
"fp16_backend": "auto",
|
115 |
+
"evaluation_strategy": "epoch",
|
116 |
+
"push_to_hub_model_id": null,
|
117 |
+
"push_to_hub_organization": null,
|
118 |
+
"push_to_hub_token": null,
|
119 |
+
"mp_parameters": "",
|
120 |
+
"auto_find_batch_size": true,
|
121 |
+
"full_determinism": false,
|
122 |
+
"torchdynamo": null,
|
123 |
+
"ray_scope": "last",
|
124 |
+
"ddp_timeout": 1800,
|
125 |
+
"torch_compile": false,
|
126 |
+
"torch_compile_backend": null,
|
127 |
+
"torch_compile_mode": null,
|
128 |
+
"dispatch_batches": null,
|
129 |
+
"split_batches": null,
|
130 |
+
"include_tokens_per_second": false,
|
131 |
+
"include_num_input_tokens_seen": false,
|
132 |
+
"neftune_noise_alpha": null,
|
133 |
+
"optim_target_modules": null,
|
134 |
+
"batch_eval_metrics": false,
|
135 |
+
"eval_on_start": false,
|
136 |
+
"use_liger_kernel": false,
|
137 |
+
"eval_use_gather_object": false,
|
138 |
+
"distributed_state": "Distributed environment: NO\nNum processes: 1\nProcess index: 0\nLocal process index: 0\nDevice: cuda\n",
|
139 |
+
"_n_gpu": 1,
|
140 |
+
"__cached__setup_devices": "cuda:0",
|
141 |
+
"deepspeed_plugin": null
|
142 |
+
}
|