Training in progress, epoch 5

logs/events.out.tfevents.1702162733.joseph_legion.21448.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6eb787ca2939b990ddbc668936f433ed3f2ef211c37e00601b82d94780a8b2e
-size 6374
+oid sha256:20174857f8b0f052492d48a1eadc0e65e49d362bbe83286472ca8e13ce48a33a
+size 6854

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74cd443db6be2e450d877fc017f829a6facf4a431f9066fabc859e51f852b09
+oid sha256:09761d0c7d36ded0205723a5d7cf356c266a600073cae2f79a3d06ec0961e4fa
 size 267838720

run-1/checkpoint-2395/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-1/checkpoint-2395/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09761d0c7d36ded0205723a5d7cf356c266a600073cae2f79a3d06ec0961e4fa
+size 267838720

run-1/checkpoint-2395/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bc98888bd9812b299613f8c84e524deb94eb2f4df4610f5cbe1cf708a230b6
+size 535739578

run-1/checkpoint-2395/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f67dc3384c4c3ac05b083cd11fe1e115282f847709bd7d9c29ce5ed3d24d5b5
+size 14308

run-1/checkpoint-2395/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a5db56894d8cb9a10cd6a2e1552630b675849fa1abff3c6821930d785be4c1
+size 1064

run-1/checkpoint-2395/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-1/checkpoint-2395/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-1/checkpoint-2395/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.8916819012797075,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-1\\checkpoint-958",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2395,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.1414387289205385e-06,
+      "loss": 0.2985,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8784277879341865,
+      "eval_loss": 0.29401153326034546,
+      "eval_runtime": 9.4448,
+      "eval_samples_per_second": 231.661,
+      "eval_steps_per_second": 7.306,
+      "step": 479
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.264090339074747e-06,
+      "loss": 0.2918,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8916819012797075,
+      "eval_loss": 0.29342585802078247,
+      "eval_runtime": 9.4536,
+      "eval_samples_per_second": 231.446,
+      "eval_steps_per_second": 7.299,
+      "step": 958
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.386741949228956e-06,
+      "loss": 0.2879,
+      "step": 1437
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8875685557586838,
+      "eval_loss": 0.2938942015171051,
+      "eval_runtime": 9.4764,
+      "eval_samples_per_second": 230.889,
+      "eval_steps_per_second": 7.281,
+      "step": 1437
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.509393559383165e-06,
+      "loss": 0.2853,
+      "step": 1916
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8848263254113345,
+      "eval_loss": 0.293885737657547,
+      "eval_runtime": 9.4687,
+      "eval_samples_per_second": 231.076,
+      "eval_steps_per_second": 7.287,
+      "step": 1916
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.6320451695373736e-06,
+      "loss": 0.2834,
+      "step": 2395
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8843692870201096,
+      "eval_loss": 0.2947681248188019,
+      "eval_runtime": 9.4769,
+      "eval_samples_per_second": 230.877,
+      "eval_steps_per_second": 7.281,
+      "step": 2395
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3832,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 641954735265312.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.24491283832577226,
+    "learning_rate": 7.01878711876633e-06,
+    "num_train_epochs": 8,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 16,
+    "temperature": 13
+  }
+}

run-1/checkpoint-2395/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee892723378b580d5a01e9f7cceabcc4dca2ffb2b9cb62681992da17760585a
+size 4792