Training in progress, epoch 1

logs/events.out.tfevents.1702107018.tron63.umiacs.umd.edu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5bc3ac7e3b1901ba6946029c8f26d5e012f0f9fc739be8fb26e0f6d0254abdf
-size 4958
+oid sha256:e9afb4b498b25de21e684d7539db5a52e069058573554256e58fd2bf88b546b3
+size 7555

logs/events.out.tfevents.1702107272.tron63.umiacs.umd.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb35ae1528f5b4cb6679ed147317b1f2ac304b54565d024cd39ccb10315e458
+size 4479

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37590e1ea1f78955fb64813af36e1f671809a56690c2d9b0dfd77202e9ed99dd
+oid sha256:04b9e2c49d658045b0da949087385ec4d60d2e60ff3e671027859f07692c6fce
 size 267838720

run-3/checkpoint-1437/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "noHate",
+    "1": "hate",
+    "2": "idk/skip",
+    "3": "relation"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "hate": "1",
+    "idk/skip": "2",
+    "noHate": "0",
+    "relation": "3"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-1437/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb97dd3e320984859fc64122559cc72bf58bfa2440eb42263049d1204b558df
+size 267838720

run-3/checkpoint-1437/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d8cb7b83617c2c5bcb299f5a3dc3af3c8036a887e03aa336720aa1ef2de4b7
+size 535739578

run-3/checkpoint-1437/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081da486a5646510ad9a72fbfa73ab1849d65d0f898b3af15b782e4b80aa5233
+size 14308

run-3/checkpoint-1437/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d51cf50a8530c9bb0eafac269e1f70d02bebc00ea4b44a4bd50dc180a6b739
+size 1064

run-3/checkpoint-1437/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-3/checkpoint-1437/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1437/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.8893967093235832,
+  "best_model_checkpoint": "distilbert-hate_speech18/run-3/checkpoint-1437",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1437,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.574355357048456e-06,
+      "loss": 0.5031,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8825411334552102,
+      "eval_loss": 0.4724956750869751,
+      "eval_runtime": 5.381,
+      "eval_samples_per_second": 406.617,
+      "eval_steps_per_second": 12.823,
+      "step": 479
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.659484285638764e-06,
+      "loss": 0.4542,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8871115173674589,
+      "eval_loss": 0.47489938139915466,
+      "eval_runtime": 5.2987,
+      "eval_samples_per_second": 412.934,
+      "eval_steps_per_second": 13.022,
+      "step": 958
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.744613214229073e-06,
+      "loss": 0.4357,
+      "step": 1437
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8893967093235832,
+      "eval_loss": 0.4758572578430176,
+      "eval_runtime": 5.4367,
+      "eval_samples_per_second": 402.447,
+      "eval_steps_per_second": 12.691,
+      "step": 1437
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2874,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 386506048888512.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6570903092699628,
+    "learning_rate": 5.489226428458146e-06,
+    "num_train_epochs": 6,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 16,
+    "temperature": 8
+  }
+}

run-3/checkpoint-1437/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc78497c8829a0befca40322ad2f04325aca6b964299b9821a30d1f81cb24ac5
+size 4664

run-3/checkpoint-2874/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "noHate",
+    "1": "hate",
+    "2": "idk/skip",
+    "3": "relation"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "hate": "1",
+    "idk/skip": "2",
+    "noHate": "0",
+    "relation": "3"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-2874/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb1b9b23d7adc3ea854ce023a866c5b44675bfbfc339c77df99fb37fcd2a8b0
+size 267838720

run-3/checkpoint-2874/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9552dc919287d8239adf9da733280efad4215f31448fadc9f9fbfe1e71cd2f1
+size 535739578

run-3/checkpoint-2874/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9ddc3177be39e6f120b0116b9429332a5bb6582b57f1c8278f0b2e06520de2
+size 14308

run-3/checkpoint-2874/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d145b51174ddeea952f098fb3c3d2885557a657e06ff16eb2016bb051e56dc7
+size 1064

run-3/checkpoint-2874/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-3/checkpoint-2874/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-2874/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": 0.8893967093235832,
+  "best_model_checkpoint": "distilbert-hate_speech18/run-3/checkpoint-1437",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2874,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.574355357048456e-06,
+      "loss": 0.5031,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8825411334552102,
+      "eval_loss": 0.4724956750869751,
+      "eval_runtime": 5.381,
+      "eval_samples_per_second": 406.617,
+      "eval_steps_per_second": 12.823,
+      "step": 479
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.659484285638764e-06,
+      "loss": 0.4542,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8871115173674589,
+      "eval_loss": 0.47489938139915466,
+      "eval_runtime": 5.2987,
+      "eval_samples_per_second": 412.934,
+      "eval_steps_per_second": 13.022,
+      "step": 958
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.744613214229073e-06,
+      "loss": 0.4357,
+      "step": 1437
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8893967093235832,
+      "eval_loss": 0.4758572578430176,
+      "eval_runtime": 5.4367,
+      "eval_samples_per_second": 402.447,
+      "eval_steps_per_second": 12.691,
+      "step": 1437
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.829742142819382e-06,
+      "loss": 0.4259,
+      "step": 1916
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8880255941499086,
+      "eval_loss": 0.4761721193790436,
+      "eval_runtime": 5.3358,
+      "eval_samples_per_second": 410.062,
+      "eval_steps_per_second": 12.932,
+      "step": 1916
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 9.14871071409691e-07,
+      "loss": 0.4158,
+      "step": 2395
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8893967093235832,
+      "eval_loss": 0.47894012928009033,
+      "eval_runtime": 5.296,
+      "eval_samples_per_second": 413.142,
+      "eval_steps_per_second": 13.029,
+      "step": 2395
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0,
+      "loss": 0.412,
+      "step": 2874
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8889396709323584,
+      "eval_loss": 0.48173168301582336,
+      "eval_runtime": 5.4164,
+      "eval_samples_per_second": 403.962,
+      "eval_steps_per_second": 12.739,
+      "step": 2874
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2874,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 772227614421312.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6570903092699628,
+    "learning_rate": 5.489226428458146e-06,
+    "num_train_epochs": 6,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 16,
+    "temperature": 8
+  }
+}

run-3/checkpoint-2874/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc78497c8829a0befca40322ad2f04325aca6b964299b9821a30d1f81cb24ac5
+size 4664

run-4/checkpoint-479/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "noHate",
+    "1": "hate",
+    "2": "idk/skip",
+    "3": "relation"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "hate": "1",
+    "idk/skip": "2",
+    "noHate": "0",
+    "relation": "3"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-479/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b9e2c49d658045b0da949087385ec4d60d2e60ff3e671027859f07692c6fce
+size 267838720

run-4/checkpoint-479/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fcca2e8da991b4b47c1208a4368b5e1bf98c469fcadf4e3652dfee12e56f37
+size 535739578

run-4/checkpoint-479/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e9e8577f611ea3318592ab765906a60be3c91a6ea38993df88f4eab0205796
+size 14308

run-4/checkpoint-479/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c687a982436ca909893d906e308b71f1eacc72c2e40039b9a3ccba74eba93c9d
+size 1064

run-4/checkpoint-479/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-4/checkpoint-479/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-479/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.8555758683729433,
+  "best_model_checkpoint": "distilbert-hate_speech18/run-4/checkpoint-479",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 479,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.4915701906137869e-06,
+      "loss": 0.6023,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.5101819634437561,
+      "eval_runtime": 4.6457,
+      "eval_samples_per_second": 470.972,
+      "eval_steps_per_second": 29.49,
+      "step": 479
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3832,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 128356173120672.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8126810159702461,
+    "learning_rate": 1.7046516464157565e-06,
+    "num_train_epochs": 8,
+    "per_device_eval_batch_size": 16,
+    "per_device_train_batch_size": 16,
+    "temperature": 20
+  }
+}

run-4/checkpoint-479/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce024c0ae34dff8d794ffd15af1edded867961a5819af05536fcfc509621819
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc78497c8829a0befca40322ad2f04325aca6b964299b9821a30d1f81cb24ac5
+oid sha256:9ce024c0ae34dff8d794ffd15af1edded867961a5819af05536fcfc509621819
 size 4664