oyy

checkpoint-160/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEUTRAL",
+    "1": "BIT-TOXIC",
+    "2": "QUITE-TOXIC",
+    "3": "TOXIC",
+    "4": "VERY-TOXIC",
+    "5": "HIGHLY-TOXIC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "BIT-TOXIC": 1,
+    "HIGHLY-TOXIC": 5,
+    "NEUTRAL": 0,
+    "QUITE-TOXIC": 2,
+    "TOXIC": 3,
+    "VERY-TOXIC": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32001
+}

checkpoint-160/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9fbcb3c57172640144ad106b31c97d623cd07ddc95969d63c7257e6e81b7182
+size 442514440

checkpoint-160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8083959f936114a680e91bd369681538d78867febf313fea0f233696b5d8107
+size 885149946

checkpoint-160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030f797d3abd18cb53e527cf6cf1e4f89fa57bfcdd9f31cb25473191fa4c03db
+size 14244

checkpoint-160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590ffa6d84ac5f11e0c202149e9478c4654d2bbbb7a0458f8e623121da4cef9a
+size 1064

checkpoint-160/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-160/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-160/trainer_state.json

@@ -0,0 +1,261 @@
+{
+  "best_metric": 0.2997977137565613,
+  "best_model_checkpoint": "models/toxic-bert-hubert/checkpoint-150",
+  "epoch": 0.23088023088023088,
+  "eval_steps": 10,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.206,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "eval_f1": 0.7730744144170906,
+      "eval_loss": 0.6420192122459412,
+      "eval_runtime": 22.3453,
+      "eval_samples_per_second": 247.837,
+      "eval_steps_per_second": 7.787,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.5054,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "eval_f1": 0.8048163482788003,
+      "eval_loss": 0.5228331685066223,
+      "eval_runtime": 22.8204,
+      "eval_samples_per_second": 242.677,
+      "eval_steps_per_second": 7.625,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.88e-05,
+      "loss": 0.5716,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "eval_f1": 0.8136074625725318,
+      "eval_loss": 0.4328407943248749,
+      "eval_runtime": 23.1876,
+      "eval_samples_per_second": 238.834,
+      "eval_steps_per_second": 7.504,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.4257,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "eval_f1": 0.8259426500452947,
+      "eval_loss": 0.4285435080528259,
+      "eval_runtime": 23.2092,
+      "eval_samples_per_second": 238.613,
+      "eval_steps_per_second": 7.497,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8e-05,
+      "loss": 0.4937,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "eval_f1": 0.8317824244449398,
+      "eval_loss": 0.39296483993530273,
+      "eval_runtime": 23.2217,
+      "eval_samples_per_second": 238.484,
+      "eval_steps_per_second": 7.493,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.76e-05,
+      "loss": 0.4411,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "eval_f1": 0.8356587695730946,
+      "eval_loss": 0.3781413733959198,
+      "eval_runtime": 23.4641,
+      "eval_samples_per_second": 236.021,
+      "eval_steps_per_second": 7.416,
+      "step": 60
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.72e-05,
+      "loss": 0.4197,
+      "step": 70
+    },
+    {
+      "epoch": 0.1,
+      "eval_f1": 0.8497564694972085,
+      "eval_loss": 0.3615292012691498,
+      "eval_runtime": 23.1269,
+      "eval_samples_per_second": 239.462,
+      "eval_steps_per_second": 7.524,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.3702,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "eval_f1": 0.8725646676802798,
+      "eval_loss": 0.3257770836353302,
+      "eval_runtime": 22.9073,
+      "eval_samples_per_second": 241.757,
+      "eval_steps_per_second": 7.596,
+      "step": 80
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.64e-05,
+      "loss": 0.3357,
+      "step": 90
+    },
+    {
+      "epoch": 0.13,
+      "eval_f1": 0.8735307760659007,
+      "eval_loss": 0.31817400455474854,
+      "eval_runtime": 23.2006,
+      "eval_samples_per_second": 238.701,
+      "eval_steps_per_second": 7.5,
+      "step": 90
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4082,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "eval_f1": 0.8404628911456754,
+      "eval_loss": 0.35047250986099243,
+      "eval_runtime": 22.7192,
+      "eval_samples_per_second": 243.758,
+      "eval_steps_per_second": 7.659,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.5600000000000003e-05,
+      "loss": 0.4107,
+      "step": 110
+    },
+    {
+      "epoch": 0.16,
+      "eval_f1": 0.8586341129440507,
+      "eval_loss": 0.3375680148601532,
+      "eval_runtime": 23.371,
+      "eval_samples_per_second": 236.96,
+      "eval_steps_per_second": 7.445,
+      "step": 110
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.2864,
+      "step": 120
+    },
+    {
+      "epoch": 0.17,
+      "eval_f1": 0.8561894871027176,
+      "eval_loss": 0.32658323645591736,
+      "eval_runtime": 23.2113,
+      "eval_samples_per_second": 238.591,
+      "eval_steps_per_second": 7.496,
+      "step": 120
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.48e-05,
+      "loss": 0.3483,
+      "step": 130
+    },
+    {
+      "epoch": 0.19,
+      "eval_f1": 0.8645368802572093,
+      "eval_loss": 0.3245397210121155,
+      "eval_runtime": 23.0332,
+      "eval_samples_per_second": 240.436,
+      "eval_steps_per_second": 7.554,
+      "step": 130
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.317,
+      "step": 140
+    },
+    {
+      "epoch": 0.2,
+      "eval_f1": 0.8735823993344022,
+      "eval_loss": 0.32588475942611694,
+      "eval_runtime": 23.3446,
+      "eval_samples_per_second": 237.228,
+      "eval_steps_per_second": 7.454,
+      "step": 140
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.4e-05,
+      "loss": 0.3114,
+      "step": 150
+    },
+    {
+      "epoch": 0.22,
+      "eval_f1": 0.8704014314485559,
+      "eval_loss": 0.2997977137565613,
+      "eval_runtime": 22.6714,
+      "eval_samples_per_second": 244.273,
+      "eval_steps_per_second": 7.675,
+      "step": 150
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.3323,
+      "step": 160
+    },
+    {
+      "epoch": 0.23,
+      "eval_f1": 0.8661724356256255,
+      "eval_loss": 0.3152276575565338,
+      "eval_runtime": 23.046,
+      "eval_samples_per_second": 240.302,
+      "eval_steps_per_second": 7.55,
+      "step": 160
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 359241714253440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e056d88700e4c1253c7100c9c94587a6124eb1203d56f1cd161bc83611a778
+size 4728