Training in progress, epoch 6

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba4f1bfd87d3edd852619ea97a91a485bc5d178376418a67e305f5b19a3178d
-size 6855
+oid sha256:181b46b1ed0e5554d471a61d22ad2946b9b1cb2eb91ae814524b553753be0d73
+size 7335

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18511222f21c31a07672c594746c5130bd847a7dde976513c4e592dcaa5c55a2
+oid sha256:15ffef19510eaa2ab13a368eb3704fc6c00746535a3797abf281d2b91a89b153
 size 267838720

run-4/checkpoint-1440/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-1440/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ffef19510eaa2ab13a368eb3704fc6c00746535a3797abf281d2b91a89b153
+size 267838720

run-4/checkpoint-1440/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff236548a4e27a7b9ae3e016422f99ec4347e902397677fa487fc0abaf7e020
+size 535739578

run-4/checkpoint-1440/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2310108ffd01794d97cde4fe338eefb02867008612d851e59280674b44ff38
+size 14308

run-4/checkpoint-1440/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee535f806244273026cf3ff088dd0c20371954e5401e1b79b8e245de66cad241
+size 1064

run-4/checkpoint-1440/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-1440/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-1440/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": 0.8907678244972578,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-4\\checkpoint-480",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1440,
+  "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
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9419172577632537e-06,
+      "loss": 0.4297,
+      "step": 960
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8903107861060329,
+      "eval_loss": 0.4932664930820465,
+      "eval_runtime": 8.0508,
+      "eval_samples_per_second": 271.775,
+      "eval_steps_per_second": 17.017,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.961278171842169e-06,
+      "loss": 0.4187,
+      "step": 1200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8880255941499086,
+      "eval_loss": 0.49868300557136536,
+      "eval_runtime": 8.123,
+      "eval_samples_per_second": 269.359,
+      "eval_steps_per_second": 16.866,
+      "step": 1200
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 9.806390859210846e-07,
+      "loss": 0.4112,
+      "step": 1440
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8875685557586838,
+      "eval_loss": 0.5080177187919617,
+      "eval_runtime": 7.9906,
+      "eval_samples_per_second": 273.822,
+      "eval_steps_per_second": 17.145,
+      "step": 1440
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 977555265925056.0,
+  "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-1440/training_args.bin

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