Upload 12 files

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "HATE-SPEECH",
+    "1": "OFFENSIVE-LANGUAGE",
+    "2": "NEITHER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "HATE-SPEECH": 0,
+    "NEITHER": 2,
+    "OFFENSIVE-LANGUAGE": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509f045b26ee8087bb34349b3e373a232f4298a4465b66907b8b620a8466f5d7
+size 328495356

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ae993fd5a059d271cdc20f698b4b2b3d1cc58d6914acbb9356e86a198a10c6
+size 657053754

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2db70640e7fac4dc44868f491f52c8cc3bfe58b1626cec2e01bf9f3621e708e
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa162e1ff57101acb77a3125d873271b540af405e3cb396e60e7357b87dc14e
+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_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_metric": 0.1553138643503189,
+  "best_model_checkpoint": "speech-multiclassifier-run-2/checkpoint-6384",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9576,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15664160401002505,
+      "grad_norm": 11.20281982421875,
+      "learning_rate": 1.8955722639933167e-05,
+      "loss": 0.1599,
+      "step": 500
+    },
+    {
+      "epoch": 0.3132832080200501,
+      "grad_norm": 16.948055267333984,
+      "learning_rate": 1.7911445279866332e-05,
+      "loss": 0.2132,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4699248120300752,
+      "grad_norm": 15.359735488891602,
+      "learning_rate": 1.68671679197995e-05,
+      "loss": 0.2101,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6265664160401002,
+      "grad_norm": 0.13909225165843964,
+      "learning_rate": 1.5822890559732666e-05,
+      "loss": 0.1868,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7832080200501254,
+      "grad_norm": 1.7620573043823242,
+      "learning_rate": 1.4778613199665832e-05,
+      "loss": 0.1824,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9398496240601504,
+      "grad_norm": 2.3290231227874756,
+      "learning_rate": 1.3734335839598997e-05,
+      "loss": 0.1678,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.15620405972003937,
+      "eval_overall-accuracy": 0.9531360112755461,
+      "eval_overall-f1": 0.9531360112755461,
+      "eval_overall-precision": 0.9531360112755461,
+      "eval_overall-recall": 0.9531360112755461,
+      "eval_runtime": 5.7139,
+      "eval_samples_per_second": 496.687,
+      "eval_steps_per_second": 31.152,
+      "step": 3192
+    },
+    {
+      "epoch": 1.0964912280701755,
+      "grad_norm": 0.4430443048477173,
+      "learning_rate": 1.2690058479532166e-05,
+      "loss": 0.1655,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2531328320802004,
+      "grad_norm": 5.565830707550049,
+      "learning_rate": 1.1645781119465331e-05,
+      "loss": 0.1499,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4097744360902256,
+      "grad_norm": 0.9018378257751465,
+      "learning_rate": 1.0601503759398497e-05,
+      "loss": 0.1443,
+      "step": 4500
+    },
+    {
+      "epoch": 1.5664160401002505,
+      "grad_norm": 0.3591144382953644,
+      "learning_rate": 9.557226399331662e-06,
+      "loss": 0.1399,
+      "step": 5000
+    },
+    {
+      "epoch": 1.7230576441102756,
+      "grad_norm": 0.4499484598636627,
+      "learning_rate": 8.512949039264829e-06,
+      "loss": 0.1559,
+      "step": 5500
+    },
+    {
+      "epoch": 1.8796992481203008,
+      "grad_norm": 8.649208068847656,
+      "learning_rate": 7.468671679197995e-06,
+      "loss": 0.1522,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.1553138643503189,
+      "eval_overall-accuracy": 0.9531360112755461,
+      "eval_overall-f1": 0.9531360112755461,
+      "eval_overall-precision": 0.9531360112755461,
+      "eval_overall-recall": 0.9531360112755461,
+      "eval_runtime": 5.7234,
+      "eval_samples_per_second": 495.858,
+      "eval_steps_per_second": 31.1,
+      "step": 6384
+    },
+    {
+      "epoch": 2.036340852130326,
+      "grad_norm": 1.2995306253433228,
+      "learning_rate": 6.424394319131162e-06,
+      "loss": 0.1398,
+      "step": 6500
+    },
+    {
+      "epoch": 2.192982456140351,
+      "grad_norm": 0.18944260478019714,
+      "learning_rate": 5.380116959064328e-06,
+      "loss": 0.1164,
+      "step": 7000
+    },
+    {
+      "epoch": 2.3496240601503757,
+      "grad_norm": 4.408690929412842,
+      "learning_rate": 4.335839598997494e-06,
+      "loss": 0.1154,
+      "step": 7500
+    },
+    {
+      "epoch": 2.506265664160401,
+      "grad_norm": 0.7239732146263123,
+      "learning_rate": 3.29156223893066e-06,
+      "loss": 0.1208,
+      "step": 8000
+    },
+    {
+      "epoch": 2.662907268170426,
+      "grad_norm": 6.512196063995361,
+      "learning_rate": 2.2472848788638263e-06,
+      "loss": 0.1115,
+      "step": 8500
+    },
+    {
+      "epoch": 2.819548872180451,
+      "grad_norm": 1.97010338306427,
+      "learning_rate": 1.2030075187969925e-06,
+      "loss": 0.1169,
+      "step": 9000
+    },
+    {
+      "epoch": 2.9761904761904763,
+      "grad_norm": 1.1876590251922607,
+      "learning_rate": 1.5873015873015874e-07,
+      "loss": 0.1157,
+      "step": 9500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.16947361826896667,
+      "eval_overall-accuracy": 0.9534883720930233,
+      "eval_overall-f1": 0.9534883720930233,
+      "eval_overall-precision": 0.9534883720930233,
+      "eval_overall-recall": 0.9534883720930233,
+      "eval_runtime": 5.6944,
+      "eval_samples_per_second": 498.388,
+      "eval_steps_per_second": 31.259,
+      "step": 9576
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9576,
+  "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": 2641161396896352.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029185f2c3245c64fde08e06271c6a94b5152fe65da466f7bbb1bff6da69310b
+size 5176