Training in progress, epoch 2

logs/events.out.tfevents.1702154733.tron63.umiacs.umd.edu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6777fdbda307ea029a87f184cd10c1156202779446c5eac1f0e48e11ca8f8a80
-size 4478
+oid sha256:23471f5a832432708bf67a0f8deb4625acdaf7d60f386a7169b9d2266667a5aa
+size 4958

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662767992be06ae16db39271d3a2de2fad1f80dcdc15726bdda4d1e0d491a3d9
+oid sha256:89ba3a86cd7e45116c106be7d1f4f597ce2c265c47e80b31ecc9f2671ba7b656
 size 267838720

run-1/checkpoint-1096/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": "noHate",
+    "1": "hate",
+    "2": "idk/skip",
+    "3": "relation"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "hate": "1",
+    "idk/skip": "2",
+    "noHate": "0",
+    "relation": "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": "4.35.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-1096/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ba3a86cd7e45116c106be7d1f4f597ce2c265c47e80b31ecc9f2671ba7b656
+size 267838720

run-1/checkpoint-1096/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba43be3b9d3a642c1d8420c6155d41a6a5ec9b71c747bf78f102a8e02853d20
+size 535739578

run-1/checkpoint-1096/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5edffe8b4b0456d764e6499585e8f4efb5604d8804057eefb15fb0d056520481
+size 14308

run-1/checkpoint-1096/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:351638d550b229faed817adc95bcadd309fda7c75a7b3539b09ea27a5ebe4ce1
+size 1064

run-1/checkpoint-1096/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-1096/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-1096/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8802559414990859,
+  "best_model_checkpoint": "distilbert-hate_speech18/run-1/checkpoint-1096",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1096,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.736389529369517e-06,
+      "loss": 0.1545,
+      "step": 548
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.856489945155393,
+      "eval_loss": 0.15267300605773926,
+      "eval_runtime": 2.2822,
+      "eval_samples_per_second": 479.352,
+      "eval_steps_per_second": 30.233,
+      "step": 548
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.0597624537453e-06,
+      "loss": 0.1519,
+      "step": 1096
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8802559414990859,
+      "eval_loss": 0.15240849554538727,
+      "eval_runtime": 2.2689,
+      "eval_samples_per_second": 482.166,
+      "eval_steps_per_second": 30.411,
+      "step": 1096
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4384,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 295494077833584.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.13177842170061627,
+    "learning_rate": 5.413016604993733e-06,
+    "num_train_epochs": 8,
+    "per_device_eval_batch_size": 16,
+    "per_device_train_batch_size": 16,
+    "temperature": 18
+  }
+}

run-1/checkpoint-1096/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12e12a8b5f246cc7574661b8e4cb1a18547712e46d3d677aea25c1a51a027f4
+size 4664