Training in progress, epoch 1

logs/events.out.tfevents.1702161414.joseph_legion.21448.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514b6f976466662d01831486faa70ae202bf9178da56260b47e5516ea5666cf9
-size 6855
+oid sha256:c416a4baff143c91b6332e48f93dfdc45f38d0e766480c9a79571194d3637445
+size 7689

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b417f0b6a8ed1ec6079d16f51f19f52e97e16202de1769a4842434bd1880a4
+size 4934

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1ea33496df61211897277f0c5022cb8f1ebbbb5fadb41e98094749e9d9ab41
+oid sha256:01954e7709e01d7334b3e8d4b612afcd5a502cc9aea59f3411539d73b383b5e4
 size 267838720

run-0/checkpoint-1440/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-0/checkpoint-1440/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3cc554428ec0883568134c75ea2c42de876a2cf5362782c4896962c5d298e7c
+size 267838720

run-0/checkpoint-1440/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8432b9ad7b792c254b23b3ae52f2dd7ca3e7636ac227a8ba9e6f7ecb9bc594d1
+size 535739578

run-0/checkpoint-1440/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2310108ffd01794d97cde4fe338eefb02867008612d851e59280674b44ff38
+size 14308

run-0/checkpoint-1440/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13261613ddd6bed2c207117099ad012aa6189b72d161d1d054ad83d3815e7ba
+size 1064

run-0/checkpoint-1440/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-0/checkpoint-1440/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-0/checkpoint-1440/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": 0.8761425959780622,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-0\\checkpoint-1440",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1440,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.200932249944345e-06,
+      "loss": 0.3542,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.34542378783226013,
+      "eval_runtime": 27.8228,
+      "eval_samples_per_second": 78.641,
+      "eval_steps_per_second": 2.48,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.607457999554758e-07,
+      "loss": 0.3426,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8596892138939671,
+      "eval_loss": 0.34202685952186584,
+      "eval_runtime": 27.8449,
+      "eval_samples_per_second": 78.578,
+      "eval_steps_per_second": 2.478,
+      "step": 480
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.20559349966607e-07,
+      "loss": 0.3404,
+      "step": 720
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8670018281535649,
+      "eval_loss": 0.3405018150806427,
+      "eval_runtime": 27.8321,
+      "eval_samples_per_second": 78.614,
+      "eval_steps_per_second": 2.479,
+      "step": 720
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.803728999777379e-07,
+      "loss": 0.3394,
+      "step": 960
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8692870201096892,
+      "eval_loss": 0.33956673741340637,
+      "eval_runtime": 27.8533,
+      "eval_samples_per_second": 78.554,
+      "eval_steps_per_second": 2.477,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.4018644998886895e-07,
+      "loss": 0.3386,
+      "step": 1200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8752285191956124,
+      "eval_loss": 0.3389435410499573,
+      "eval_runtime": 27.8576,
+      "eval_samples_per_second": 78.542,
+      "eval_steps_per_second": 2.477,
+      "step": 1200
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0,
+      "loss": 0.3382,
+      "step": 1440
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8761425959780622,
+      "eval_loss": 0.338797390460968,
+      "eval_runtime": 27.857,
+      "eval_samples_per_second": 78.544,
+      "eval_steps_per_second": 2.477,
+      "step": 1440
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 977555265925056.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.2937223587192618,
+    "learning_rate": 1.441118699933214e-06,
+    "num_train_epochs": 6,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 32,
+    "temperature": 22
+  }
+}

run-0/checkpoint-1440/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c270c372d171f05f77d295e45676e68498a717682284e18b37bf87d03001f66
+size 4792

run-1/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-1/checkpoint-479/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01954e7709e01d7334b3e8d4b612afcd5a502cc9aea59f3411539d73b383b5e4
+size 267838720

run-1/checkpoint-479/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec537944f48e9a705e6d4e49f59a5648603fd42c3200a4181fcc94ae3980aea
+size 535739578

run-1/checkpoint-479/rng_state.pth

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

run-1/checkpoint-479/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc3684272ef6c9441d02fc785f7f07d73c758ac6992ec1fcbccbfc72e195343
+size 1064

run-1/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-1/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-1/checkpoint-479/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8784277879341865,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-1\\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": 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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3832,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 128356173120672.0,
+  "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-479/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c270c372d171f05f77d295e45676e68498a717682284e18b37bf87d03001f66
+oid sha256:5ee892723378b580d5a01e9f7cceabcc4dca2ffb2b9cb62681992da17760585a
 size 4792