Training in progress, epoch 1

logs/events.out.tfevents.1702164718.joseph_legion.21448.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181b46b1ed0e5554d471a61d22ad2946b9b1cb2eb91ae814524b553753be0d73
-size 7335
+oid sha256:e3f29583bdfd7f641f7d0d7c0b3234d996714758f52c28b128dadb68db4bc245
+size 8169

logs/events.out.tfevents.1702166110.joseph_legion.21448.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3a7aa7c540c610c3e5948ce405b985a49a292ecc4ff59ed76fc8d8c4513492
+size 4936

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ffef19510eaa2ab13a368eb3704fc6c00746535a3797abf281d2b91a89b153
+oid sha256:7b75aeec602fe6c987d3578016b49368a347d57121247bb8602ea78283bbe13f
 size 267838720

run-4/checkpoint-1680/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": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 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": "4.36.0.dev0",
+  "vocab_size": 30522
+}

run-4/checkpoint-1680/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b05680cfa95e8d01175e6eb56b89859438f48d6a6d2bf80e73f924df16edee
+size 267838720

run-4/checkpoint-1680/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ba6e382f89309ee58d6b7e3e570ab649f946b00feed48d7c53f8f8a4c3c781
+size 535739578

run-4/checkpoint-1680/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866d2098bdfc2414a428bdf932175d750e857e0fef2e1afb6083551c24e6318e
+size 14308

run-4/checkpoint-1680/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0890d85e1ea8f87a4019fdd59e657d94ac6846fbbadb8a4350fb56a93e1afc
+size 1064

run-4/checkpoint-1680/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-1680/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-1680/trainer_state.json

@@ -0,0 +1,132 @@
+{
+  "best_metric": 0.8907678244972578,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-4\\checkpoint-480",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1680,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.8838345155265075e-06,
+      "loss": 0.549,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8820840950639853,
+      "eval_loss": 0.4940944314002991,
+      "eval_runtime": 8.0075,
+      "eval_samples_per_second": 273.244,
+      "eval_steps_per_second": 17.109,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.903195429605423e-06,
+      "loss": 0.4705,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8907678244972578,
+      "eval_loss": 0.4879714548587799,
+      "eval_runtime": 7.9604,
+      "eval_samples_per_second": 274.862,
+      "eval_steps_per_second": 17.21,
+      "step": 480
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.922556343684338e-06,
+      "loss": 0.4471,
+      "step": 720
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8893967093235832,
+      "eval_loss": 0.4937082529067993,
+      "eval_runtime": 8.0067,
+      "eval_samples_per_second": 273.273,
+      "eval_steps_per_second": 17.111,
+      "step": 720
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9419172577632537e-06,
+      "loss": 0.4297,
+      "step": 960
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8903107861060329,
+      "eval_loss": 0.4932664930820465,
+      "eval_runtime": 8.0508,
+      "eval_samples_per_second": 271.775,
+      "eval_steps_per_second": 17.017,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.961278171842169e-06,
+      "loss": 0.4187,
+      "step": 1200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8880255941499086,
+      "eval_loss": 0.49868300557136536,
+      "eval_runtime": 8.123,
+      "eval_samples_per_second": 269.359,
+      "eval_steps_per_second": 16.866,
+      "step": 1200
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 9.806390859210846e-07,
+      "loss": 0.4112,
+      "step": 1440
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8875685557586838,
+      "eval_loss": 0.5080177187919617,
+      "eval_runtime": 7.9906,
+      "eval_samples_per_second": 273.822,
+      "eval_steps_per_second": 17.145,
+      "step": 1440
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0,
+      "loss": 0.4066,
+      "step": 1680
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8880255941499086,
+      "eval_loss": 0.5034064650535583,
+      "eval_runtime": 8.0384,
+      "eval_samples_per_second": 272.195,
+      "eval_steps_per_second": 17.043,
+      "step": 1680
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1142849427764352.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7641900951856909,
+    "learning_rate": 6.864473601447592e-06,
+    "num_train_epochs": 7,
+    "per_device_eval_batch_size": 16,
+    "per_device_train_batch_size": 32,
+    "temperature": 23
+  }
+}

run-4/checkpoint-1680/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4793e25c9769afa8c89f2422861506d79331fa4f305d344623de77c38fc088
+size 4792

run-5/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": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 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": "4.36.0.dev0",
+  "vocab_size": 30522
+}

run-5/checkpoint-479/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b75aeec602fe6c987d3578016b49368a347d57121247bb8602ea78283bbe13f
+size 267838720

run-5/checkpoint-479/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:375e91fca354930ca21afda9fc2a3ae6aa676e586655d88a79927fc728d6daa4
+size 535739578

run-5/checkpoint-479/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46f5609acc4df73766b0f33b30656411024250c2f745a536c9e1d5d95ae5105
+size 14308

run-5/checkpoint-479/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6d4978216b88a571031c425e2f9fca37ab0b1fd2e695043be4f284a539e005
+size 1064

run-5/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-5/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-5/checkpoint-479/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8624314442413162,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-5\\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": 1.4395797527808295e-06,
+      "loss": 0.2516,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8624314442413162,
+      "eval_loss": 0.24848461151123047,
+      "eval_runtime": 9.4673,
+      "eval_samples_per_second": 231.112,
+      "eval_steps_per_second": 7.288,
+      "step": 479
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2874,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 128356173120672.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.19436109341303698,
+    "learning_rate": 1.7274957033369952e-06,
+    "num_train_epochs": 6,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 16,
+    "temperature": 12
+  }
+}

run-5/checkpoint-479/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7316aa93f572ca44c9682ad225b35745f9d355c0713119fad66ce1bad923e9c4
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df4793e25c9769afa8c89f2422861506d79331fa4f305d344623de77c38fc088
+oid sha256:7316aa93f572ca44c9682ad225b35745f9d355c0713119fad66ce1bad923e9c4
 size 4792