Upload 4 files

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38dfa0a25ed396b015a3409b4097b8188270765aaca6c11b825dd06da45ca2a
+size 504194285

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2814559b8e4d66147dcaeeff788ae8e21c76d8fd948b709e4302b96dc1457e8a
+size 3951

training_arguments.json

@@ -0,0 +1 @@
+{"lr": 0.0003, "betas": [0.9, 0.98], "weight_decay": 0.01, "eps": 1e-06, "num_warmup_steps": 2340, "num_training_steps": 23400, "overwrite_output_dir": true, "num_train_epochs": 2, "per_device_train_batch_size": 40, "per_device_eval_batch_size": 40, "do_eval": true, "do_train": true, "evaluation_strategy": "steps", "eval_steps": 500, "save_steps": 5000, "save_total_limit": 5, "logging_steps": 100, "logging_dir": "globertise-v02_rerun/logs", "gradient_accumulation_steps": 10, "eval_accumulation_steps": 10, "fp16": true, "path_to_traindata": "data/train/linebyline_transcr_v2.txt", "path_to_eval": "data/val/val.txt", "train_tokenizer": false, "outfile_tokenizer": "tokenizer_from_scratch", "start_from_checkpoint": false, "path_to_checkpoint": "globertise-v02_rerun/models/checkpoint_10000", "output_dir": "globertise-v02_rerun/models"}