Training in progress, epoch 2

logs/events.out.tfevents.1702106674.tron63.umiacs.umd.edu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:168942ce35c30ebeab19bb9e2b616c7cedd63c15542d9646c053884ef1276277
-size 4478
+oid sha256:49faa4f6bde668c16e63a0cf623058090a4d03ff0536bedb4894cbc3264563da
+size 4958

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44c9ee2d09fd6e2029facbcb6f776c737f422ec8a21011fd3fbc202389a8ad2
+oid sha256:43ecb96ad8646e97b129cc1e9e9df206be8567022141b2cae6db8330f36de857
 size 267838720

run-2/checkpoint-480/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-2/checkpoint-480/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ecb96ad8646e97b129cc1e9e9df206be8567022141b2cae6db8330f36de857
+size 267838720

run-2/checkpoint-480/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0865674116c34e21f88503948525d5c7b9f4c90cd891b9d8017b74a9c3789371
+size 535739578

run-2/checkpoint-480/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ef4b2dfe3bc06df7d7a32d8cc58c6316531e4a9e0bd2c95f98fabbbec57a29
+size 14308

run-2/checkpoint-480/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f35494bc05ef550bcb0c5cb421ce6e02e7d431b92a18743a7b41b345a46cfd3
+size 1064

run-2/checkpoint-480/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-480/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-480/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8816270566727605,
+  "best_model_checkpoint": "distilbert-hate_speech18/run-2/checkpoint-480",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 480,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.0619191606872558e-06,
+      "loss": 0.5976,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.49282151460647583,
+      "eval_runtime": 5.4041,
+      "eval_samples_per_second": 404.876,
+      "eval_steps_per_second": 12.768,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.6245021377319335e-06,
+      "loss": 0.4571,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8816270566727605,
+      "eval_loss": 0.4616107642650604,
+      "eval_runtime": 5.4807,
+      "eval_samples_per_second": 399.222,
+      "eval_steps_per_second": 12.59,
+      "step": 480
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1920,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 328019606410944.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8436514520472223,
+    "learning_rate": 3.499336183642578e-06,
+    "num_train_epochs": 8,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 32,
+    "temperature": 11
+  }
+}

run-2/checkpoint-480/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8d646d8b778c330bf7de3115af97f26cea17442e48bdfe73257985debaa6b80
+size 4664