Training in progress, epoch 1

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45dae420973acb85d058d64c9206453fe60e878f43282785bd67eb7ac5852581
-size 6375
+oid sha256:b241009a7e6e7a531c7458a4b574f37beff6840d26113ebd5362afd7b0890790
+size 7209

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57113a0ed5349680fd816ccb92a1af8e1ffe19d0afabdd1dc118113d02fb756d
+size 4936

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22fe9b2c3f5efbc10a51c9a823bf80d4cdd7b834bb5bfd4836d6274a693d577
+oid sha256:111357aea67148aae411fca0c342cdbcbf155b2fa8073ced2a8a93a4680c3656
 size 267838720

run-2/checkpoint-2395/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-2395/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4b8a391381861e7cadc6b78f231e0bc1d3876361993b7ae30812de6f4f697f
+size 267838720

run-2/checkpoint-2395/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a715fb28ac37a7eb9e03cbce0ec674d27a2db09b08a7776df576b482c7763b1f
+size 535739578

run-2/checkpoint-2395/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f67dc3384c4c3ac05b083cd11fe1e115282f847709bd7d9c29ce5ed3d24d5b5
+size 14308

run-2/checkpoint-2395/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f57c2ade8fc6dea5e84e1f13ed5639ac125fd0b6f5e3345b29b195df1630c6
+size 1064

run-2/checkpoint-2395/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-2395/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-2395/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.8455210237659964,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-2\\checkpoint-1437",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2395,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.8300185796553657e-06,
+      "loss": 0.1708,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8244972577696527,
+      "eval_loss": 0.17035162448883057,
+      "eval_runtime": 7.9955,
+      "eval_samples_per_second": 273.654,
+      "eval_steps_per_second": 17.135,
+      "step": 958
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.8866790531035773e-06,
+      "loss": 0.1699,
+      "step": 1437
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8455210237659964,
+      "eval_loss": 0.17017477750778198,
+      "eval_runtime": 8.0232,
+      "eval_samples_per_second": 272.708,
+      "eval_steps_per_second": 17.075,
+      "step": 1437
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.433395265517887e-07,
+      "loss": 0.1694,
+      "step": 1916
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.829981718464351,
+      "eval_loss": 0.17003203928470612,
+      "eval_runtime": 8.0266,
+      "eval_samples_per_second": 272.595,
+      "eval_steps_per_second": 17.068,
+      "step": 1916
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.1691,
+      "step": 2395
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8359232175502742,
+      "eval_loss": 0.17005686461925507,
+      "eval_runtime": 8.0706,
+      "eval_samples_per_second": 271.107,
+      "eval_steps_per_second": 16.975,
+      "step": 2395
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2395,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 641954735265312.0,
+  "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-2395/training_args.bin

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

run-3/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-3/checkpoint-240/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111357aea67148aae411fca0c342cdbcbf155b2fa8073ced2a8a93a4680c3656
+size 267838720

run-3/checkpoint-240/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ec7ff257aab499ef5cebaeeb9c1747a3acc789f0d6a64240f66c5d21d3b4ee
+size 535739578

run-3/checkpoint-240/rng_state.pth

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

run-3/checkpoint-240/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8769e4995bb3d1563b4789b74567e0c35a78d93283209009ca93c6bfb31ca46b
+size 1064

run-3/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-3/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-3/checkpoint-240/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8606032906764168,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-3\\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": 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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 163370211234720.0,
+  "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-240/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e990dcbf9bfae76dd476bdfbf6976f1f851bf842dfffef516a3bb508e91e93fa
+oid sha256:e5a387f5bff97f17f9ccdf5718f369b40c94efa84e41a438755774bcf08a1544
 size 4792