Upload 11 files

.gitattributes

@@ -0,0 +1,4 @@
+optimizer.pt filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/scratch/spf248/twitter_social_cohesion/models/pretrained/xlmr/5e-5_42_ddp/checkpoint-final",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt

@@ -0,0 +1,5 @@
+eval_loss = 1.310192673728707
+f1 = 0.7747240386055089
+mcc = 0.6661617678679186
+precision = 0.7747284589507807
+recall = 0.7753941965337998

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": "/scratch/mt4493/nigeria/trained_models/hate_speech/best_models/test_v25-0.1-90/results_seed-42_lr-3e-5_clean-0_epochs-10_bs-8//scratch/spf248/twitter_social_cohesion/models/pretrained/xlmr/5e-5_42_ddp/checkpoint-final/-scratch-spf248-twitter_social_cohesion-models-pretrained-xlmr-5e-5_42_ddp-checkpoint-final/fold-1/models/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": true, "early_stopping_delta": 0, "early_stopping_metric": "f1", "early_stopping_metric_minimize": false, "early_stopping_patience": 5, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 250, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 4, "learning_rate": 3e-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": "/scratch/spf248/twitter_social_cohesion/models/pretrained/xlmr/5e-5_42_ddp/checkpoint-final", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "AdamW", "output_dir": "/scratch/mt4493/nigeria/trained_models/hate_speech/best_models/test_v25-0.1-90/results_seed-42_lr-3e-5_clean-0_epochs-10_bs-8//scratch/spf248/twitter_social_cohesion/models/pretrained/xlmr/5e-5_42_ddp/checkpoint-final/-scratch-spf248-twitter_social_cohesion-models-pretrained-xlmr-5e-5_42_ddp-checkpoint-final/fold-1/models", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 46, "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": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": "runs/45537500/", "thread_count": null, "tokenizer_name": "/scratch/spf248/twitter_social_cohesion/models/pretrained/xlmr/5e-5_42_ddp/checkpoint-final", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 54, "weight_decay": 0.0, "model_class": "ClassificationModel", "labels_list": [0, 1, 2], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a4a1708706e0dc8754009d3b0ffdb01b726677e1236258ef9b0ef4f8cd8d62
+size 2224535237

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b52fdf60ef4f40ef48b311d6dba4b769a19febafc4574f962887a2f539a82a8
+size 1112257205

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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c08c80d1df11b82ada2fd707562f86a9ebd5b7de04f51ebd2b49f2cd5906d00
+size 17082925

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "/scratch/spf248/twitter_social_cohesion/models/pretrained/xlmr/5e-5_42_ddp/checkpoint-final",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": "/scratch/spf248/twitter_social_cohesion/models/pretrained/xlmr/5e-5_42_ddp/checkpoint-final/special_tokens_map.json",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}