Initial commit

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "aubmindlab/aragpt2-large",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "initializer_range": 0.014142135623731,
+  "intermediate_size": 5120,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 5,
+      "repetition_penalty": 3.0,
+      "top_p": 0.95
+    }
+  },
+  "use_cache": true,
+  "vocab_size": 64000
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 4.1149924498684
+perplexity = tensor(61.2518)

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "best_model_dir": "outputs/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, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 8, "learning_rate": 0.0002, "local_rank": -1, "logging_steps": 50, "manual_seed": 42, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "aubmindlab/aragpt2-large", "model_type": "gpt2", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 3, "optimizer": "AdamW", "output_dir": "outputs/fine-tuned/", "overwrite_output_dir": true, "process_count": 1, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 50000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 1, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 1220, "weight_decay": 0.0, "model_class": "LanguageModelingModel", "block_size": 128, "config_name": null, "dataset_class": null, "dataset_type": "None", "discriminator_config": {}, "discriminator_loss_weight": 50.0, "generator_config": {}, "max_steps": -1, "min_frequency": 2, "mlm": false, "mlm_probability": 0.15, "sliding_window": false, "special_tokens": ["<s>", "<pad>", "</s>", "<unk>", "<mask>"], "stride": 0.8, "tie_generator_and_discriminator_embeddings": true, "tokenizer_name": "aubmindlab/aragpt2-large", "vocab_size": null, "clean_text": true, "handle_chinese_chars": true, "special_tokens_list": [], "strip_accents": true}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c62faaa142ec8547bc5ca217fdd2c512b41ce353c36e1ab36b4475af1d0cf97
+size 3204423968

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "tokenizer_file": "cache_dir/d2fe70315147c56007916ddc6d750a3e73696b65dc45754548d0f793301af019.6ce583b24c6d3225d59bf6fb3ac34ead1e0fa04af22fb464906ee74d4c25bd77", "name_or_path": "aubmindlab/aragpt2-large"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a51adc92ea5bc6c986387a1b47fc691123ffcf3107447c4c1bc2aaac641368a
+size 3247