littleworth commited on
Commit
994723e
1 Parent(s): 7b8d1c2

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 0,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 0,
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": 8,
16
+ "n_inner": null,
17
+ "n_layer": 6,
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
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.39.3",
30
+ "use_cache": true,
31
+ "vocab_size": 50257
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.39.3"
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:ca6b6104ead7510c889c6eff192e4c06ca5a8a8d2dece367d9d829261e386c92
3
+ size 327657928
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
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": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1000000000000000019884624838656,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
training_hyperparameters.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "training_arguments": {
3
+ "output_dir": "./models/protgpt2-distilled-t10.0-a0.1-l6-h8-e768-p0.1.uniprot_trainset",
4
+ "overwrite_output_dir": false,
5
+ "do_train": false,
6
+ "do_eval": false,
7
+ "do_predict": false,
8
+ "evaluation_strategy": "no",
9
+ "prediction_loss_only": false,
10
+ "per_device_train_batch_size": 1,
11
+ "per_device_eval_batch_size": 8,
12
+ "per_gpu_train_batch_size": null,
13
+ "per_gpu_eval_batch_size": null,
14
+ "gradient_accumulation_steps": 32,
15
+ "eval_accumulation_steps": null,
16
+ "eval_delay": 0,
17
+ "learning_rate": 0.001,
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": 3,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "linear",
26
+ "lr_scheduler_kwargs": {},
27
+ "warmup_ratio": 0.0,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "./models/protgpt2-distilled-t10.0-a0.1-l6-h8-e768-p0.1.uniprot_trainset/runs/Apr26_01-36-39_ip-172-31-34-182",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": false,
35
+ "logging_steps": 10,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "no",
38
+ "save_steps": 500,
39
+ "save_total_limit": 1,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "no_cuda": false,
44
+ "use_cpu": false,
45
+ "use_mps_device": false,
46
+ "seed": 42,
47
+ "data_seed": null,
48
+ "jit_mode_eval": false,
49
+ "use_ipex": false,
50
+ "bf16": false,
51
+ "fp16": true,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": null,
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": [],
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": null,
64
+ "dataloader_num_workers": 0,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "./models/protgpt2-distilled-t10.0-a0.1-l6-h8-e768-p0.1.uniprot_trainset",
68
+ "disable_tqdm": false,
69
+ "remove_unused_columns": true,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": null,
73
+ "greater_is_better": null,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": {
78
+ "min_num_params": 0,
79
+ "xla": false,
80
+ "xla_fsdp_v2": false,
81
+ "xla_fsdp_grad_ckpt": false
82
+ },
83
+ "fsdp_transformer_layer_cls_to_wrap": null,
84
+ "accelerator_config": {
85
+ "split_batches": false,
86
+ "dispatch_batches": null,
87
+ "even_batches": true,
88
+ "use_seedable_sampler": true
89
+ },
90
+ "deepspeed": null,
91
+ "label_smoothing_factor": 0.0,
92
+ "optim": "adamw_torch",
93
+ "optim_args": null,
94
+ "adafactor": false,
95
+ "group_by_length": false,
96
+ "length_column_name": "length",
97
+ "report_to": [
98
+ "wandb"
99
+ ],
100
+ "ddp_find_unused_parameters": null,
101
+ "ddp_bucket_cap_mb": null,
102
+ "ddp_broadcast_buffers": null,
103
+ "dataloader_pin_memory": true,
104
+ "dataloader_persistent_workers": false,
105
+ "skip_memory_metrics": true,
106
+ "use_legacy_prediction_loop": false,
107
+ "push_to_hub": false,
108
+ "resume_from_checkpoint": null,
109
+ "hub_model_id": null,
110
+ "hub_strategy": "every_save",
111
+ "hub_token": "<HUB_TOKEN>",
112
+ "hub_private_repo": false,
113
+ "hub_always_push": false,
114
+ "gradient_checkpointing": false,
115
+ "gradient_checkpointing_kwargs": null,
116
+ "include_inputs_for_metrics": false,
117
+ "fp16_backend": "auto",
118
+ "push_to_hub_model_id": null,
119
+ "push_to_hub_organization": null,
120
+ "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
121
+ "mp_parameters": "",
122
+ "auto_find_batch_size": false,
123
+ "full_determinism": false,
124
+ "torchdynamo": null,
125
+ "ray_scope": "last",
126
+ "ddp_timeout": 1800,
127
+ "torch_compile": false,
128
+ "torch_compile_backend": null,
129
+ "torch_compile_mode": null,
130
+ "dispatch_batches": null,
131
+ "split_batches": null,
132
+ "include_tokens_per_second": false,
133
+ "include_num_input_tokens_seen": false,
134
+ "neftune_noise_alpha": null,
135
+ "optim_target_modules": null
136
+ },
137
+ "distillation_temperature": 10.0,
138
+ "distillation_alpha": 0.1,
139
+ "model_architecture": {
140
+ "n_embd": 768,
141
+ "n_layer": 6,
142
+ "n_head": 8
143
+ }
144
+ }
training_logs.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff