Upload 9 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 +1,29 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "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,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09391c236a21a70bd035f8ff316fa67b71333f3f50261f7213d4f5f45889d1a7
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5c54ee7c011c670893da853212409c5954873d7cf764d04d3afb04600039f7
+size 1064

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:d6f76fe13d42f80dcee0cb86a1aeb5f14f8909bb8a8782f7a4a4ad76697ef164
+size 17083021

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": 0.2546990215778351,
+  "best_model_checkpoint": "xlm-roberta-base-all-finetuned-toxicity-classification/checkpoint-2532",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 7596,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8683517640863615e-05,
+      "loss": 0.2799,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.7367035281727228e-05,
+      "loss": 0.2876,
+      "step": 1000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6050552922590838e-05,
+      "loss": 0.2671,
+      "step": 1500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.473407056345445e-05,
+      "loss": 0.2639,
+      "step": 2000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3417588204318064e-05,
+      "loss": 0.2675,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2546990215778351,
+      "eval_runtime": 35.0277,
+      "eval_samples_per_second": 128.47,
+      "eval_steps_per_second": 8.051,
+      "step": 2532
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.2101105845181676e-05,
+      "loss": 0.2072,
+      "step": 3000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.0784623486045287e-05,
+      "loss": 0.2035,
+      "step": 3500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.4681411269089e-06,
+      "loss": 0.1987,
+      "step": 4000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 8.151658767772512e-06,
+      "loss": 0.1938,
+      "step": 4500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.835176408636125e-06,
+      "loss": 0.189,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.29669827222824097,
+      "eval_runtime": 35.0287,
+      "eval_samples_per_second": 128.466,
+      "eval_steps_per_second": 8.051,
+      "step": 5064
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 5.518694049499738e-06,
+      "loss": 0.1412,
+      "step": 5500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 4.20221169036335e-06,
+      "loss": 0.1467,
+      "step": 6000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.885729331226962e-06,
+      "loss": 0.1397,
+      "step": 6500
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.5692469720905742e-06,
+      "loss": 0.1476,
+      "step": 7000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 2.527646129541864e-07,
+      "loss": 0.1383,
+      "step": 7500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.4095066785812378,
+      "eval_runtime": 35.0202,
+      "eval_samples_per_second": 128.497,
+      "eval_steps_per_second": 8.053,
+      "step": 7596
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7596,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.196799322624e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e5669b8832cbf5841d48301e9864d3640c85cceb7efe18e9227169755b90d11
+size 4664