Training in progress, epoch 1

logs/events.out.tfevents.1702162733.joseph_legion.21448.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d1549be2ae5fe95075558ccb05566666e5f693d9d4521c3467340e7f9cce02
-size 7814
+oid sha256:18e9f8e6ade4f649398e03d4f7e37f8ae3bb8ca99b75cb959559f8295b4126da
+size 8648

logs/events.out.tfevents.1702163282.joseph_legion.21448.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479d6df585ec8ce0c3cdae160eb026173beed30c8948fc165e4e6f0048d28fa8
+size 4935

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e5b3d2acce2e2e2aee3f9ff3cdc0fafecc57d301aa9827aca62ac292a9a3c90
+oid sha256:e3cdf260f427e940f7219285f637131e94c525c7ad223c4822bf2a6f5ef516b5
 size 267838720

run-1/checkpoint-3832/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-1/checkpoint-3832/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c57d1892e9c1aae1a43bb0b165969cc81a1045cc800e6320b2ab8a5feb51eb
+size 267838720

run-1/checkpoint-3832/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae38033c84e7c20c6ab3749d055266d05f954f0e270eec26118f0585a462d32
+size 535739578

run-1/checkpoint-3832/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f285adb7d89b36a0c41ebe3a1ff0286c70a3279c68e147d7a0ea7129fdf6ac4
+size 14308

run-1/checkpoint-3832/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfbcdb4bfd851d38b7d61a12b3992f25c2c7dd35c8f6e2baee45f03821bfc85
+size 1064

run-1/checkpoint-3832/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-1/checkpoint-3832/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-1/checkpoint-3832/trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.8916819012797075,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-1\\checkpoint-958",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 3832,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.1414387289205385e-06,
+      "loss": 0.2985,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8784277879341865,
+      "eval_loss": 0.29401153326034546,
+      "eval_runtime": 9.4448,
+      "eval_samples_per_second": 231.661,
+      "eval_steps_per_second": 7.306,
+      "step": 479
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.264090339074747e-06,
+      "loss": 0.2918,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8916819012797075,
+      "eval_loss": 0.29342585802078247,
+      "eval_runtime": 9.4536,
+      "eval_samples_per_second": 231.446,
+      "eval_steps_per_second": 7.299,
+      "step": 958
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.386741949228956e-06,
+      "loss": 0.2879,
+      "step": 1437
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8875685557586838,
+      "eval_loss": 0.2938942015171051,
+      "eval_runtime": 9.4764,
+      "eval_samples_per_second": 230.889,
+      "eval_steps_per_second": 7.281,
+      "step": 1437
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.509393559383165e-06,
+      "loss": 0.2853,
+      "step": 1916
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8848263254113345,
+      "eval_loss": 0.293885737657547,
+      "eval_runtime": 9.4687,
+      "eval_samples_per_second": 231.076,
+      "eval_steps_per_second": 7.287,
+      "step": 1916
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.6320451695373736e-06,
+      "loss": 0.2834,
+      "step": 2395
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8843692870201096,
+      "eval_loss": 0.2947681248188019,
+      "eval_runtime": 9.4769,
+      "eval_samples_per_second": 230.877,
+      "eval_steps_per_second": 7.281,
+      "step": 2395
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.7546967796915825e-06,
+      "loss": 0.2825,
+      "step": 2874
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8916819012797075,
+      "eval_loss": 0.2950766682624817,
+      "eval_runtime": 9.4662,
+      "eval_samples_per_second": 231.137,
+      "eval_steps_per_second": 7.289,
+      "step": 2874
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 8.773483898457912e-07,
+      "loss": 0.2816,
+      "step": 3353
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8875685557586838,
+      "eval_loss": 0.29531416296958923,
+      "eval_runtime": 9.4698,
+      "eval_samples_per_second": 231.049,
+      "eval_steps_per_second": 7.286,
+      "step": 3353
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0,
+      "loss": 0.2812,
+      "step": 3832
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.886654478976234,
+      "eval_loss": 0.2952781617641449,
+      "eval_runtime": 9.4795,
+      "eval_samples_per_second": 230.814,
+      "eval_steps_per_second": 7.279,
+      "step": 3832
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3832,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 1031238558991200.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.24491283832577226,
+    "learning_rate": 7.01878711876633e-06,
+    "num_train_epochs": 8,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 16,
+    "temperature": 13
+  }
+}

run-1/checkpoint-3832/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee892723378b580d5a01e9f7cceabcc4dca2ffb2b9cb62681992da17760585a
+size 4792

run-2/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-2/checkpoint-479/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3cdf260f427e940f7219285f637131e94c525c7ad223c4822bf2a6f5ef516b5
+size 267838720

run-2/checkpoint-479/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8bdafdf0f41fe29ff517e2aa31a06dcdbf55f89e4cb27e9b4079bc1d034c52c
+size 535739578

run-2/checkpoint-479/rng_state.pth

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

run-2/checkpoint-479/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e0a94f1b49e4dd1e6f232be2bfa2f882e7d37973bd54cc2fa40eb6e063a534
+size 1064

run-2/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-2/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-2/checkpoint-479/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.6846435100548446,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-2\\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": 3.7733581062071546e-06,
+      "loss": 0.1726,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6846435100548446,
+      "eval_loss": 0.1708744764328003,
+      "eval_runtime": 8.1063,
+      "eval_samples_per_second": 269.915,
+      "eval_steps_per_second": 16.901,
+      "step": 479
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2395,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 128356173120672.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.1262637885395267,
+    "learning_rate": 4.716697632758943e-06,
+    "num_train_epochs": 5,
+    "per_device_eval_batch_size": 16,
+    "per_device_train_batch_size": 16,
+    "temperature": 6
+  }
+}

run-2/checkpoint-479/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e990dcbf9bfae76dd476bdfbf6976f1f851bf842dfffef516a3bb508e91e93fa
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ee892723378b580d5a01e9f7cceabcc4dca2ffb2b9cb62681992da17760585a
+oid sha256:e990dcbf9bfae76dd476bdfbf6976f1f851bf842dfffef516a3bb508e91e93fa
 size 4792