Training in progress, epoch 1

logs/events.out.tfevents.1702163599.joseph_legion.21448.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0128c8656499bc317eba069c2a1ec6154783952398b2b100c4c616ebef2b754b
-size 6376
+oid sha256:049d48f9a2448d76e6e4eab8e87b11e61135a6583fcc26f068e0c5e75eeacd77
+size 7210

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dee39d88848afd4379deaa42fd47474b8bc46b5d7c3525718b9fdc81407f32
+size 4935

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a9e4857a2e1222cdc4956973533edc54b2bbed4392863263fd81fa83fbb602
+oid sha256:dc92d20c7025494ee51b13306d31fc17abe12b75f30222c890b227012378e89f
 size 267838720

run-3/checkpoint-1200/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-3/checkpoint-1200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80fd190433149b7b5715aeee5f985c310066ff7de009dd96f99ca68c8f112c42
+size 267838720

run-3/checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cef666b50b10464a89b0fc143b02fe3969d4ae07cd8b99cac0fb13d80af5e2
+size 535739578

run-3/checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189fe8fafc9fd893b1200f4891d638437b4ff8fc23d11b9ad1f4330b6d696c36
+size 14308

run-3/checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc428d497cf297eacb6a3b56ebb8e75f5210d9f17fed0e039896fb61b50e624a
+size 1064

run-3/checkpoint-1200/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-1200/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-1200/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.8848263254113345,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-3\\checkpoint-960",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.741556032723218e-06,
+      "loss": 0.3969,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8606032906764168,
+      "eval_loss": 0.38725385069847107,
+      "eval_runtime": 13.634,
+      "eval_samples_per_second": 160.481,
+      "eval_steps_per_second": 5.061,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.0561670245424133e-06,
+      "loss": 0.3833,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8816270566727605,
+      "eval_loss": 0.3825770616531372,
+      "eval_runtime": 13.6065,
+      "eval_samples_per_second": 160.806,
+      "eval_steps_per_second": 5.071,
+      "step": 480
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.370778016361609e-06,
+      "loss": 0.3791,
+      "step": 720
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8834552102376599,
+      "eval_loss": 0.38152310252189636,
+      "eval_runtime": 13.6038,
+      "eval_samples_per_second": 160.837,
+      "eval_steps_per_second": 5.072,
+      "step": 720
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.853890081808044e-07,
+      "loss": 0.3767,
+      "step": 960
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8848263254113345,
+      "eval_loss": 0.37997502088546753,
+      "eval_runtime": 13.589,
+      "eval_samples_per_second": 161.012,
+      "eval_steps_per_second": 5.078,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.3753,
+      "step": 1200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8843692870201096,
+      "eval_loss": 0.37946945428848267,
+      "eval_runtime": 13.5775,
+      "eval_samples_per_second": 161.149,
+      "eval_steps_per_second": 5.082,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 814156076413344.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3534065692399305,
+    "learning_rate": 3.4269450409040222e-06,
+    "num_train_epochs": 5,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 32,
+    "temperature": 11
+  }
+}

run-3/checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a387f5bff97f17f9ccdf5718f369b40c94efa84e41a438755774bcf08a1544
+size 4792

run-4/checkpoint-240/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-240/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc92d20c7025494ee51b13306d31fc17abe12b75f30222c890b227012378e89f
+size 267838720

run-4/checkpoint-240/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026058970c328fe11c278ebe569260370feb627f592a491bdcd79e46e6b5f355
+size 535739578

run-4/checkpoint-240/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2fcff0827ca522e87f836d14f0cd5430b25ecce7f7ce5f905da8656f7dcf685
+size 14308

run-4/checkpoint-240/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf092e7fc9af76bae119c74a910bc9642d3404296bf10415fff0344cc168b0a
+size 1064

run-4/checkpoint-240/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-240/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-240/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8820840950639853,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-4\\checkpoint-240",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 240,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 163370211234720.0,
+  "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-240/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a387f5bff97f17f9ccdf5718f369b40c94efa84e41a438755774bcf08a1544
+oid sha256:df4793e25c9769afa8c89f2422861506d79331fa4f305d344623de77c38fc088
 size 4792