Upload 11 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "male",
+    "1": "female",
+    "2": "nonbinary"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "female": 1,
+    "male": 0,
+    "nonbinary": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94aef7ce77fcbd011227d64dd68932867053614d2017d8f07cd94dcc592546da
+size 427994348

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478b55f2101a0fa035b01cf6bc531f348d7251f03425d84db8247c2d1385b986
+size 1284037771

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7638de915b4501e34d811ef84cee9801d75cf5820afddc83ba40d83c19b8d6
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8707ddf85978057993ab628b93aae043abd6d40e558bdb8093f134069aa2997b
+size 1401

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 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8c1e048da64ed08d67a10ef5b727ed3d99e2bf926f7f938fdde861b9b74668
+size 17083063

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,358 @@
+{
+  "best_global_step": 7500,
+  "best_metric": 0.5938410920950099,
+  "best_model_checkpoint": "bert-finetuned-sem_eval-english/checkpoint-7500",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16286644951140064,
+      "grad_norm": 1.7576472759246826,
+      "learning_rate": 2.8374592833876224e-05,
+      "loss": 0.675,
+      "step": 500
+    },
+    {
+      "epoch": 0.16286644951140064,
+      "eval_accuracy": 0.30349433900790096,
+      "eval_f1": 0.5384447288733494,
+      "eval_loss": 0.666650652885437,
+      "eval_roc_auc": 0.5939593680164127,
+      "eval_runtime": 39.771,
+      "eval_samples_per_second": 308.692,
+      "eval_steps_per_second": 9.655,
+      "step": 500
+    },
+    {
+      "epoch": 0.3257328990228013,
+      "grad_norm": 0.9124096035957336,
+      "learning_rate": 2.6745928338762215e-05,
+      "loss": 0.6672,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3257328990228013,
+      "eval_accuracy": 0.30292416714180986,
+      "eval_f1": 0.5496491926835994,
+      "eval_loss": 0.6651883125305176,
+      "eval_roc_auc": 0.5970308146607535,
+      "eval_runtime": 39.484,
+      "eval_samples_per_second": 310.936,
+      "eval_steps_per_second": 9.725,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48859934853420195,
+      "grad_norm": 0.8060895204544067,
+      "learning_rate": 2.5117263843648207e-05,
+      "loss": 0.6629,
+      "step": 1500
+    },
+    {
+      "epoch": 0.48859934853420195,
+      "eval_accuracy": 0.28720371426244196,
+      "eval_f1": 0.5836376083979918,
+      "eval_loss": 0.6616196632385254,
+      "eval_roc_auc": 0.6027518264410479,
+      "eval_runtime": 39.4217,
+      "eval_samples_per_second": 311.427,
+      "eval_steps_per_second": 9.741,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6514657980456026,
+      "grad_norm": 0.725496232509613,
+      "learning_rate": 2.34885993485342e-05,
+      "loss": 0.6598,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6514657980456026,
+      "eval_accuracy": 0.28924004235562434,
+      "eval_f1": 0.5710412307329581,
+      "eval_loss": 0.6627053022384644,
+      "eval_roc_auc": 0.6025085911036706,
+      "eval_runtime": 39.5324,
+      "eval_samples_per_second": 310.555,
+      "eval_steps_per_second": 9.714,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8143322475570033,
+      "grad_norm": 1.2766971588134766,
+      "learning_rate": 2.1859934853420196e-05,
+      "loss": 0.6602,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8143322475570033,
+      "eval_accuracy": 0.3039016046265374,
+      "eval_f1": 0.5510751858822077,
+      "eval_loss": 0.6646136045455933,
+      "eval_roc_auc": 0.6007841702704798,
+      "eval_runtime": 39.5668,
+      "eval_samples_per_second": 310.285,
+      "eval_steps_per_second": 9.705,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9771986970684039,
+      "grad_norm": 1.1923062801361084,
+      "learning_rate": 2.023127035830619e-05,
+      "loss": 0.6591,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9771986970684039,
+      "eval_accuracy": 0.30471613586381036,
+      "eval_f1": 0.5650302501279234,
+      "eval_loss": 0.6584209203720093,
+      "eval_roc_auc": 0.604482846236001,
+      "eval_runtime": 39.6014,
+      "eval_samples_per_second": 310.014,
+      "eval_steps_per_second": 9.697,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1400651465798046,
+      "grad_norm": 0.9901787638664246,
+      "learning_rate": 1.8602605863192182e-05,
+      "loss": 0.6503,
+      "step": 3500
+    },
+    {
+      "epoch": 1.1400651465798046,
+      "eval_accuracy": 0.3002362140588092,
+      "eval_f1": 0.5821069843494511,
+      "eval_loss": 0.6575685143470764,
+      "eval_roc_auc": 0.6095021521656233,
+      "eval_runtime": 39.6519,
+      "eval_samples_per_second": 309.619,
+      "eval_steps_per_second": 9.684,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3029315960912053,
+      "grad_norm": 1.4162893295288086,
+      "learning_rate": 1.6973941368078176e-05,
+      "loss": 0.6481,
+      "step": 4000
+    },
+    {
+      "epoch": 1.3029315960912053,
+      "eval_accuracy": 0.29371996416062557,
+      "eval_f1": 0.5829980759139409,
+      "eval_loss": 0.6544238328933716,
+      "eval_roc_auc": 0.6097850034326124,
+      "eval_runtime": 39.6514,
+      "eval_samples_per_second": 309.624,
+      "eval_steps_per_second": 9.684,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4657980456026058,
+      "grad_norm": 1.1837143898010254,
+      "learning_rate": 1.534527687296417e-05,
+      "loss": 0.6407,
+      "step": 4500
+    },
+    {
+      "epoch": 1.4657980456026058,
+      "eval_accuracy": 0.30854443267899323,
+      "eval_f1": 0.5742496763900178,
+      "eval_loss": 0.6540513038635254,
+      "eval_roc_auc": 0.6128570483710014,
+      "eval_runtime": 39.6455,
+      "eval_samples_per_second": 309.669,
+      "eval_steps_per_second": 9.686,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6286644951140063,
+      "grad_norm": 1.213715672492981,
+      "learning_rate": 1.3716612377850164e-05,
+      "loss": 0.6455,
+      "step": 5000
+    },
+    {
+      "epoch": 1.6286644951140063,
+      "eval_accuracy": 0.30553066710108334,
+      "eval_f1": 0.5805761805761805,
+      "eval_loss": 0.6516779065132141,
+      "eval_roc_auc": 0.6139730041570889,
+      "eval_runtime": 39.6664,
+      "eval_samples_per_second": 309.507,
+      "eval_steps_per_second": 9.681,
+      "step": 5000
+    },
+    {
+      "epoch": 1.791530944625407,
+      "grad_norm": 1.0912699699401855,
+      "learning_rate": 1.2087947882736157e-05,
+      "loss": 0.6424,
+      "step": 5500
+    },
+    {
+      "epoch": 1.791530944625407,
+      "eval_accuracy": 0.3078928076891749,
+      "eval_f1": 0.5807968103781725,
+      "eval_loss": 0.6519107222557068,
+      "eval_roc_auc": 0.6147970899473854,
+      "eval_runtime": 39.6062,
+      "eval_samples_per_second": 309.977,
+      "eval_steps_per_second": 9.695,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9543973941368078,
+      "grad_norm": 1.0267040729522705,
+      "learning_rate": 1.045928338762215e-05,
+      "loss": 0.6421,
+      "step": 6000
+    },
+    {
+      "epoch": 1.9543973941368078,
+      "eval_accuracy": 0.3128614482365399,
+      "eval_f1": 0.5795434118281503,
+      "eval_loss": 0.6518534421920776,
+      "eval_roc_auc": 0.6160143745862132,
+      "eval_runtime": 39.5531,
+      "eval_samples_per_second": 310.393,
+      "eval_steps_per_second": 9.708,
+      "step": 6000
+    },
+    {
+      "epoch": 2.1172638436482085,
+      "grad_norm": 1.4254558086395264,
+      "learning_rate": 8.830618892508145e-06,
+      "loss": 0.6287,
+      "step": 6500
+    },
+    {
+      "epoch": 2.1172638436482085,
+      "eval_accuracy": 0.30447177649262847,
+      "eval_f1": 0.5908640680533707,
+      "eval_loss": 0.6530047059059143,
+      "eval_roc_auc": 0.616887196966502,
+      "eval_runtime": 39.557,
+      "eval_samples_per_second": 310.363,
+      "eval_steps_per_second": 9.708,
+      "step": 6500
+    },
+    {
+      "epoch": 2.2801302931596092,
+      "grad_norm": 1.6338706016540527,
+      "learning_rate": 7.2019543973941374e-06,
+      "loss": 0.6249,
+      "step": 7000
+    },
+    {
+      "epoch": 2.2801302931596092,
+      "eval_accuracy": 0.30626374521462896,
+      "eval_f1": 0.584855470828161,
+      "eval_loss": 0.6531878113746643,
+      "eval_roc_auc": 0.6162386151955095,
+      "eval_runtime": 39.5812,
+      "eval_samples_per_second": 310.172,
+      "eval_steps_per_second": 9.702,
+      "step": 7000
+    },
+    {
+      "epoch": 2.44299674267101,
+      "grad_norm": 1.2057968378067017,
+      "learning_rate": 5.57328990228013e-06,
+      "loss": 0.6236,
+      "step": 7500
+    },
+    {
+      "epoch": 2.44299674267101,
+      "eval_accuracy": 0.30039912030626376,
+      "eval_f1": 0.5938410920950099,
+      "eval_loss": 0.6521313786506653,
+      "eval_roc_auc": 0.6164883386994549,
+      "eval_runtime": 39.6768,
+      "eval_samples_per_second": 309.425,
+      "eval_steps_per_second": 9.678,
+      "step": 7500
+    },
+    {
+      "epoch": 2.6058631921824107,
+      "grad_norm": 1.49629807472229,
+      "learning_rate": 3.944625407166123e-06,
+      "loss": 0.6225,
+      "step": 8000
+    },
+    {
+      "epoch": 2.6058631921824107,
+      "eval_accuracy": 0.31041785452472104,
+      "eval_f1": 0.5854554068459078,
+      "eval_loss": 0.6527394652366638,
+      "eval_roc_auc": 0.6174151537937455,
+      "eval_runtime": 39.706,
+      "eval_samples_per_second": 309.197,
+      "eval_steps_per_second": 9.671,
+      "step": 8000
+    },
+    {
+      "epoch": 2.768729641693811,
+      "grad_norm": 1.7087451219558716,
+      "learning_rate": 2.315960912052117e-06,
+      "loss": 0.6223,
+      "step": 8500
+    },
+    {
+      "epoch": 2.768729641693811,
+      "eval_accuracy": 0.30805571393662945,
+      "eval_f1": 0.5916076167147815,
+      "eval_loss": 0.6518492102622986,
+      "eval_roc_auc": 0.6179083253618407,
+      "eval_runtime": 39.5356,
+      "eval_samples_per_second": 310.53,
+      "eval_steps_per_second": 9.713,
+      "step": 8500
+    },
+    {
+      "epoch": 2.9315960912052117,
+      "grad_norm": 1.7263160943984985,
+      "learning_rate": 6.872964169381108e-07,
+      "loss": 0.6224,
+      "step": 9000
+    },
+    {
+      "epoch": 2.9315960912052117,
+      "eval_accuracy": 0.30813716706035676,
+      "eval_f1": 0.5910419833937551,
+      "eval_loss": 0.6514719128608704,
+      "eval_roc_auc": 0.6182633220274373,
+      "eval_runtime": 39.7919,
+      "eval_samples_per_second": 308.53,
+      "eval_steps_per_second": 9.65,
+      "step": 9000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9772985975869440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a18240004a7a39dbff56fd4fd80837480ca7e0d3cc14afe4b28349989bbac53
+size 5905