justdeen commited on
Commit
0be1155
·
verified ·
1 Parent(s): 80cb10f

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.53.0",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.53.0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9883d8c41f9004e7d9284356d90096ce6d9c30abaf25ed9240f1ba5bc004c25f
3
+ size 497774208
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c230878d67b21ad6626482bde8fe7550952c51c23b8d868ed6d28e83de7cbb
3
+ size 5841
training_metadata.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model": "/Users/ammarahk4/Downloads/Husain/Projects/iPrayer/python_training_app/models/gpt2",
3
+ "training_date": "2025-06-29T17:45:43.552674",
4
+ "dataset_size": 5,
5
+ "training_args": {
6
+ "output_dir": "/Users/ammarahk4/Downloads/Husain/Projects/iPrayer/python_training_app/models/gpt2_quran_finetuned",
7
+ "overwrite_output_dir": false,
8
+ "do_train": false,
9
+ "do_eval": false,
10
+ "do_predict": false,
11
+ "eval_strategy": "no",
12
+ "prediction_loss_only": false,
13
+ "per_device_train_batch_size": 4,
14
+ "per_device_eval_batch_size": 4,
15
+ "per_gpu_train_batch_size": null,
16
+ "per_gpu_eval_batch_size": null,
17
+ "gradient_accumulation_steps": 1,
18
+ "eval_accumulation_steps": null,
19
+ "eval_delay": 0,
20
+ "torch_empty_cache_steps": null,
21
+ "learning_rate": 5e-05,
22
+ "weight_decay": 0.01,
23
+ "adam_beta1": 0.9,
24
+ "adam_beta2": 0.999,
25
+ "adam_epsilon": 1e-08,
26
+ "max_grad_norm": 1.0,
27
+ "num_train_epochs": 3,
28
+ "max_steps": -1,
29
+ "lr_scheduler_type": "linear",
30
+ "lr_scheduler_kwargs": {},
31
+ "warmup_ratio": 0.0,
32
+ "warmup_steps": 500,
33
+ "log_level": "passive",
34
+ "log_level_replica": "warning",
35
+ "log_on_each_node": true,
36
+ "logging_dir": "/Users/ammarahk4/Downloads/Husain/Projects/iPrayer/python_training_app/logs",
37
+ "logging_strategy": "steps",
38
+ "logging_first_step": false,
39
+ "logging_steps": 100,
40
+ "logging_nan_inf_filter": true,
41
+ "save_strategy": "steps",
42
+ "save_steps": 500,
43
+ "save_total_limit": 2,
44
+ "save_safetensors": true,
45
+ "save_on_each_node": false,
46
+ "save_only_model": false,
47
+ "restore_callback_states_from_checkpoint": false,
48
+ "no_cuda": false,
49
+ "use_cpu": false,
50
+ "use_mps_device": false,
51
+ "seed": 42,
52
+ "data_seed": null,
53
+ "jit_mode_eval": false,
54
+ "use_ipex": false,
55
+ "bf16": false,
56
+ "fp16": false,
57
+ "fp16_opt_level": "O1",
58
+ "half_precision_backend": "auto",
59
+ "bf16_full_eval": false,
60
+ "fp16_full_eval": false,
61
+ "tf32": null,
62
+ "local_rank": 0,
63
+ "ddp_backend": null,
64
+ "tpu_num_cores": null,
65
+ "tpu_metrics_debug": false,
66
+ "debug": [],
67
+ "dataloader_drop_last": false,
68
+ "eval_steps": null,
69
+ "dataloader_num_workers": 0,
70
+ "dataloader_prefetch_factor": null,
71
+ "past_index": -1,
72
+ "run_name": "/Users/ammarahk4/Downloads/Husain/Projects/iPrayer/python_training_app/models/gpt2_quran_finetuned",
73
+ "disable_tqdm": false,
74
+ "remove_unused_columns": true,
75
+ "label_names": null,
76
+ "load_best_model_at_end": false,
77
+ "metric_for_best_model": null,
78
+ "greater_is_better": null,
79
+ "ignore_data_skip": false,
80
+ "fsdp": [],
81
+ "fsdp_min_num_params": 0,
82
+ "fsdp_config": {
83
+ "min_num_params": 0,
84
+ "xla": false,
85
+ "xla_fsdp_v2": false,
86
+ "xla_fsdp_grad_ckpt": false
87
+ },
88
+ "fsdp_transformer_layer_cls_to_wrap": null,
89
+ "accelerator_config": {
90
+ "split_batches": false,
91
+ "dispatch_batches": null,
92
+ "even_batches": true,
93
+ "use_seedable_sampler": true,
94
+ "non_blocking": false,
95
+ "gradient_accumulation_kwargs": null
96
+ },
97
+ "deepspeed": null,
98
+ "label_smoothing_factor": 0.0,
99
+ "optim": "adamw_torch",
100
+ "optim_args": null,
101
+ "adafactor": false,
102
+ "group_by_length": false,
103
+ "length_column_name": "length",
104
+ "report_to": [],
105
+ "ddp_find_unused_parameters": null,
106
+ "ddp_bucket_cap_mb": null,
107
+ "ddp_broadcast_buffers": null,
108
+ "dataloader_pin_memory": true,
109
+ "dataloader_persistent_workers": false,
110
+ "skip_memory_metrics": true,
111
+ "use_legacy_prediction_loop": false,
112
+ "push_to_hub": false,
113
+ "resume_from_checkpoint": null,
114
+ "hub_model_id": null,
115
+ "hub_strategy": "every_save",
116
+ "hub_token": "<HUB_TOKEN>",
117
+ "hub_private_repo": null,
118
+ "hub_always_push": false,
119
+ "hub_revision": null,
120
+ "gradient_checkpointing": false,
121
+ "gradient_checkpointing_kwargs": null,
122
+ "include_inputs_for_metrics": false,
123
+ "include_for_metrics": [],
124
+ "eval_do_concat_batches": true,
125
+ "fp16_backend": "auto",
126
+ "push_to_hub_model_id": null,
127
+ "push_to_hub_organization": null,
128
+ "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
129
+ "mp_parameters": "",
130
+ "auto_find_batch_size": false,
131
+ "full_determinism": false,
132
+ "torchdynamo": null,
133
+ "ray_scope": "last",
134
+ "ddp_timeout": 1800,
135
+ "torch_compile": false,
136
+ "torch_compile_backend": null,
137
+ "torch_compile_mode": null,
138
+ "include_tokens_per_second": false,
139
+ "include_num_input_tokens_seen": false,
140
+ "neftune_noise_alpha": null,
141
+ "optim_target_modules": null,
142
+ "batch_eval_metrics": false,
143
+ "eval_on_start": false,
144
+ "use_liger_kernel": false,
145
+ "liger_kernel_config": null,
146
+ "eval_use_gather_object": false,
147
+ "average_tokens_across_devices": false
148
+ },
149
+ "model_type": "quran_finetuned"
150
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff