umm-maybe commited on
Commit
62f5269
1 Parent(s): fd176fd

First commit

Browse files
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.20.1",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
eval_results.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ eval_loss = 0.1959605920870567
2
+ perplexity = tensor(1.2165)
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model_args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "GPTravel/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 3000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 2, "learning_rate": 0.0001, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 510, "model_name": "gpt2-medium", "model_type": "gpt2", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 1, "optimizer": "AdamW", "output_dir": "GPTravel/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": false, "save_optimizer_and_scheduler": false, "save_steps": -1, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "gpt2-medium", "tokenizer_type": null, "train_batch_size": 2, "train_custom_parameters_only": false, "use_cached_eval_features": true, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 720, "weight_decay": 0.0, "model_class": "LanguageModelingModel", "block_size": 510, "config_name": null, "dataset_class": null, "dataset_type": "simple", "discriminator_config": {}, "discriminator_loss_weight": 50.0, "generator_config": {}, "max_steps": 12000, "min_frequency": 2, "mlm": false, "mlm_probability": 0.15, "sliding_window": true, "special_tokens": ["<s>", "<pad>", "</s>", "<unk>", "<mask>"], "stride": 0.8, "tie_generator_and_discriminator_embeddings": true, "vocab_size": null, "clean_text": true, "handle_chinese_chars": true, "special_tokens_list": [], "strip_accents": true}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdd458b5343f998df9d866c059fac834d009a01cb6e77faa0684c6c295a2ba9
3
+ size 1444566873
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c24a45ce3ef1e805929093ba283e05a0abe4cca6f0161c8dfa57589e7cc2bc
3
+ size 3375
vocab.json ADDED
The diff for this file is too large to render. See raw diff