Upload 8 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-large",
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "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 sha256:2f814ce3f2ac6358cd4ef474d0960cb1b5622f83e34930bc860852a0272a1a55
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1291acad1bb6da679dfdfff82afe511b3dfac3f58da08aeb86688e6678f35b3
+size 1064

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 sha256:1c4147c7d8584d679fcabb10e7c63ac96de865feb8a5e2b6bc9308acf93cacdb
+size 17082953

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 +1,89 @@
+{
+  "best_metric": 0.2796624004840851,
+  "best_model_checkpoint": "xlm-roberta-large-all-finetuned-toxicity-classification/checkpoint-1126",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2815,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.644760213143872e-05,
+      "loss": 0.5369,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.604564905166626,
+      "eval_runtime": 12.0965,
+      "eval_samples_per_second": 41.334,
+      "eval_steps_per_second": 5.208,
+      "step": 563
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.2895204262877443e-05,
+      "loss": 0.3908,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.2796624004840851,
+      "eval_runtime": 12.1105,
+      "eval_samples_per_second": 41.287,
+      "eval_steps_per_second": 5.202,
+      "step": 1126
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 9.342806394316164e-06,
+      "loss": 0.3196,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.2894600033760071,
+      "eval_runtime": 12.1036,
+      "eval_samples_per_second": 41.31,
+      "eval_steps_per_second": 5.205,
+      "step": 1689
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 5.790408525754885e-06,
+      "loss": 0.2412,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.3928073048591614,
+      "eval_runtime": 12.0987,
+      "eval_samples_per_second": 41.327,
+      "eval_steps_per_second": 5.207,
+      "step": 2252
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 2.238010657193606e-06,
+      "loss": 0.1839,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.39615875482559204,
+      "eval_runtime": 12.0954,
+      "eval_samples_per_second": 41.338,
+      "eval_steps_per_second": 5.209,
+      "step": 2815
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2815,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2.096845567488e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:282d67ac5f653b6cd8b612f1e0ebbdfcf7e4054b868454746d2aac5447fb4f70
+size 4664