Upload 11 files

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 2.8732976900107823
+perplexity = tensor(17.6953)

model_args.json

@@ -0,0 +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_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "xlm-roberta-lm/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": 500, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 42, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "xlm-roberta-base", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 8, "optimizer": "AdamW", "output_dir": "xlm-roberta-lm", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 6, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "xlm-roberta-base", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 385, "weight_decay": 0.0, "model_class": "LanguageModelingModel", "block_size": 128, "config_name": null, "dataset_class": null, "dataset_type": "simple", "discriminator_config": {}, "discriminator_loss_weight": 50.0, "generator_config": {}, "max_steps": -1, "min_frequency": 2, "mlm": true, "mlm_probability": 0.15, "sliding_window": false, "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}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:613d19001527c6a1c78c23f31ea8796710bbfd86e4249518cdcca042e84c82cc
+size 2226529989

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25236298d41f02b3c5153d4e27e85b8d7ccd32996d824a7b1915ed1eb2f035e
+size 1113250229

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16f7759e0dfdc7170ae9e6e8832cbfda2bd994e6e3f7bf734397363bf5b9968
+size 627

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4934bf849c54ab5678f7f24afbfd35253821167171777b78854ec1d15e494ce9
+size 3451

training_progress_scores.csv

@@ -0,0 +1,21 @@
+global_step,perplexity,eval_loss,train_loss
+500,tensor(25.1785),3.2259899893803383,3.6148972511291504
+802,tensor(22.6947),3.1221308005389883,3.169919490814209
+1000,tensor(22.7527),3.1246853328462856,3.259542226791382
+1500,tensor(21.0915),3.048868253159879,3.178443670272827
+1604,tensor(21.8677),3.0850108301461634,2.92553448677063
+2000,tensor(20.7868),3.0343171469311216,3.652672529220581
+2406,tensor(21.0332),3.0461017578395446,3.4821979999542236
+2500,tensor(19.8329),2.9873445879167586,2.780447244644165
+3000,tensor(20.1747),3.004430653443977,3.060286045074463
+3208,tensor(18.9665),2.9426718407602452,2.771437644958496
+3500,tensor(18.8871),2.938477090045587,3.5695018768310547
+4000,tensor(18.9398),2.941264520830183,2.701347827911377
+4010,tensor(18.8755),2.9378651843142154,2.8873403072357178
+4500,tensor(18.4492),2.9150228042211106,2.8361315727233887
+4812,tensor(18.0082),2.8908277509817437,2.683300495147705
+5000,tensor(17.9844),2.889506740356559,2.5590286254882812
+5500,tensor(17.6953),2.8732976900107823,2.92236065864563
+5614,tensor(17.8995),2.884773777492011,2.635545253753662
+6000,tensor(17.8156),2.8800762188968374,3.0371944904327393
+6416,tensor(18.1821),2.9004396787330284,2.3266353607177734