Training in progress, epoch 4

logs/events.out.tfevents.1702166495.joseph_legion.21448.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b92d8dba638c279181c4733316a29cf8c6623e4289105d3e54bd7e7d759eba1b
-size 5895
+oid sha256:a8da96186f120aa32de4cf58eb1bb5c2281b42751c5b9e33a371006f139cce27
+size 6375

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d932e40dec103bfd9839565dd2b0f339f59611a68db34d7da3d467804656c489
+oid sha256:65a83ba49364da79a9f74c2eca8a5cb6e2ed9f5b05c2ee46a6606190acfae125
 size 267838720

run-6/checkpoint-960/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-6/checkpoint-960/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a83ba49364da79a9f74c2eca8a5cb6e2ed9f5b05c2ee46a6606190acfae125
+size 267838720

run-6/checkpoint-960/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c0788acf1298b9189b0f66d83c2e84b5e99acdcae68eafaae48add411dbdf1
+size 535739578

run-6/checkpoint-960/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7dc24ae2312cb25a58edeead64a5b9227c74d43ef8ed0a7dbb3b7b42b5e9b6c
+size 14308

run-6/checkpoint-960/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74d62d6eb04d37aba4b9efe79c65caceec174d00af697fdd54bd18c5b82a7e6
+size 1064

run-6/checkpoint-960/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-6/checkpoint-960/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-6/checkpoint-960/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.8893967093235832,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-6\\checkpoint-720",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 960,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.4189080485362326e-06,
+      "loss": 0.4732,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8706581352833638,
+      "eval_loss": 0.45438072085380554,
+      "eval_runtime": 8.0476,
+      "eval_samples_per_second": 271.882,
+      "eval_steps_per_second": 17.024,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.7876354701739137e-06,
+      "loss": 0.4459,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8857404021937842,
+      "eval_loss": 0.4488455057144165,
+      "eval_runtime": 7.9963,
+      "eval_samples_per_second": 273.628,
+      "eval_steps_per_second": 17.133,
+      "step": 480
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.1563628918115945e-06,
+      "loss": 0.4356,
+      "step": 720
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8893967093235832,
+      "eval_loss": 0.4489736258983612,
+      "eval_runtime": 8.1712,
+      "eval_samples_per_second": 267.77,
+      "eval_steps_per_second": 16.766,
+      "step": 720
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.5250903134492757e-06,
+      "loss": 0.4283,
+      "step": 960
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8889396709323584,
+      "eval_loss": 0.44683799147605896,
+      "eval_runtime": 8.1009,
+      "eval_samples_per_second": 270.094,
+      "eval_steps_per_second": 16.912,
+      "step": 960
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1920,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 651630374965248.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4787113643124785,
+    "learning_rate": 5.050180626898551e-06,
+    "num_train_epochs": 8,
+    "per_device_eval_batch_size": 16,
+    "per_device_train_batch_size": 32,
+    "temperature": 27
+  }
+}

run-6/checkpoint-960/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2caa169e337c2cdce989f2ae2edb46d990d83d311ad8d0fa7b6a8a2e8b15c867
+size 4792