Training in progress, epoch 2

logs/events.out.tfevents.1702155607.tron63.umiacs.umd.edu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efe084fdd538f5a7d2d945ee703351c2bafaf98deb99231bb14a116084d20af
-size 4479
+oid sha256:baed2d0f7e58c2b715e78408eb7215d2f175bfc53f306ed6e3d25baacae194f6
+size 4959

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84c42e690cbbfbc22adad6612fbf4afc14a5c2850da1b403404abd9f15ae8eb8
+oid sha256:402e011190d9d864051dcf6e6f4bb93089d97a26f8828e9eb5f2a9ddb132cb24
 size 267838720

run-4/checkpoint-548/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-4/checkpoint-548/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402e011190d9d864051dcf6e6f4bb93089d97a26f8828e9eb5f2a9ddb132cb24
+size 267838720

run-4/checkpoint-548/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998c2dc6e61a0d1d3361fcbf8060c7fd22b932b4528d3af8eb0fab21c79ba7f0
+size 535739578

run-4/checkpoint-548/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4c1e30249fd9b6e11118ec5efc93e49514f765d8e319e939eb2de3735c5e69
+size 14308

run-4/checkpoint-548/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1318f63251686b04d0d0c094083f709aca3a002678d7a6560760a672e04bb6e
+size 1064

run-4/checkpoint-548/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-548/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-548/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.850091407678245,
+  "best_model_checkpoint": "distilbert-hate_speech18/run-4/checkpoint-274",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 548,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.15331111796953e-07,
+      "loss": 0.6946,
+      "step": 274
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.850091407678245,
+      "eval_loss": 0.5388411283493042,
+      "eval_runtime": 2.6594,
+      "eval_samples_per_second": 411.373,
+      "eval_steps_per_second": 13.161,
+      "step": 274
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.076655558984765e-07,
+      "loss": 0.5064,
+      "step": 548
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.850091407678245,
+      "eval_loss": 0.5175882577896118,
+      "eval_runtime": 2.662,
+      "eval_samples_per_second": 410.968,
+      "eval_steps_per_second": 13.148,
+      "step": 548
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 822,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 371152219305840.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7674697347517282,
+    "learning_rate": 1.2229966676954296e-06,
+    "num_train_epochs": 3,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 32,
+    "temperature": 18
+  }
+}

run-4/checkpoint-548/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f119c2c47c2ddc105a364fdbf6e72870d737cf46fe71df9314db160fb0f336d2
+size 4664