Upload 10 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": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e096e04349fd13845389d45f58f3e52dfb33751d36a2207e56616a2d27c7788e
+size 1112205008

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c9934e14175ef85af0a9fb051497c784afbe225ef4e815db4e066ee571907a
+size 2224529658

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0641d62f50e30322c76b890d8ffa0173bf8123009a9232fad3c8194fb80dfc5b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e19aec562275e412c44374390de345bac40442f41f6b6c61719c88a1d6efda0
+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 +1,61 @@
+{
+  "best_metric": 0.35727986693382263,
+  "best_model_checkpoint": "xlm-roberta-base-finetuned-toxicity-classification/checkpoint-1126",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1689,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.4079336885731204e-05,
+      "loss": 0.5422,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5097673535346985,
+      "eval_runtime": 4.9489,
+      "eval_samples_per_second": 101.033,
+      "eval_steps_per_second": 12.73,
+      "step": 563
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 8.158673771462404e-06,
+      "loss": 0.3396,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.35727986693382263,
+      "eval_runtime": 4.9851,
+      "eval_samples_per_second": 100.299,
+      "eval_steps_per_second": 12.638,
+      "step": 1126
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.238010657193606e-06,
+      "loss": 0.2416,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.37405291199684143,
+      "eval_runtime": 4.9729,
+      "eval_samples_per_second": 100.544,
+      "eval_steps_per_second": 12.669,
+      "step": 1689
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1689,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3551999247360000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b68e3157160aa134c1770bec385131a7e7a67e882356dccb0eed3f98b88d75
+size 4664