Training in progress, epoch 3

logs/events.out.tfevents.1702164718.joseph_legion.21448.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c991d79449cf0aed5e6f046d991107136da6423844b53ff671cb3405bca98e4a
-size 5415
+oid sha256:616b1ec505cda12f2f2d1b79cac4f3ee7c0b6bc9ffac090ca5e4f8ba8b2e36e5
+size 5895

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1375924c6ec78b76ac6f9a073c2bfd74e06f04b5d75fdfb792396465464a0b
+oid sha256:9ddb1599a6ab2e0206486140ccab3cf5167e623156b37d45a731662958d96ff1
 size 267838720

run-4/checkpoint-720/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-4/checkpoint-720/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ddb1599a6ab2e0206486140ccab3cf5167e623156b37d45a731662958d96ff1
+size 267838720

run-4/checkpoint-720/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112ac5ba4ff4efd48a7e5790511977080bd69a44aa357cb7244e266fde4f8dd5
+size 535739578

run-4/checkpoint-720/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:966a889b4af73d37ea3fbebc384228a639190e0e9595294ffaae0e9d44b6da2f
+size 14308

run-4/checkpoint-720/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14733f7f2119e2b8a69a91db0eb81002f48e4327f08a18509e81756a27624162
+size 1064

run-4/checkpoint-720/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-720/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-720/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.8907678244972578,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-4\\checkpoint-480",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 720,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.8838345155265075e-06,
+      "loss": 0.549,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8820840950639853,
+      "eval_loss": 0.4940944314002991,
+      "eval_runtime": 8.0075,
+      "eval_samples_per_second": 273.244,
+      "eval_steps_per_second": 17.109,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.903195429605423e-06,
+      "loss": 0.4705,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8907678244972578,
+      "eval_loss": 0.4879714548587799,
+      "eval_runtime": 7.9604,
+      "eval_samples_per_second": 274.862,
+      "eval_steps_per_second": 17.21,
+      "step": 480
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.922556343684338e-06,
+      "loss": 0.4471,
+      "step": 720
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8893967093235832,
+      "eval_loss": 0.4937082529067993,
+      "eval_runtime": 8.0067,
+      "eval_samples_per_second": 273.273,
+      "eval_steps_per_second": 17.111,
+      "step": 720
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 488786947408704.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7641900951856909,
+    "learning_rate": 6.864473601447592e-06,
+    "num_train_epochs": 7,
+    "per_device_eval_batch_size": 16,
+    "per_device_train_batch_size": 32,
+    "temperature": 23
+  }
+}

run-4/checkpoint-720/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4793e25c9769afa8c89f2422861506d79331fa4f305d344623de77c38fc088
+size 4792