Training in progress, epoch 4

logs/events.out.tfevents.1702163599.joseph_legion.21448.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb721c4c1e2312db43899bdb7b0c6aafdc89a23b4e443acfe66703432bce139f
-size 5896
+oid sha256:0128c8656499bc317eba069c2a1ec6154783952398b2b100c4c616ebef2b754b
+size 6376

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194069ad199cdfda6acff576ed4abc9e67b723781506af5dd36c04695b39416c
+oid sha256:85a9e4857a2e1222cdc4956973533edc54b2bbed4392863263fd81fa83fbb602
 size 267838720

run-3/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-3/checkpoint-960/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a9e4857a2e1222cdc4956973533edc54b2bbed4392863263fd81fa83fbb602
+size 267838720

run-3/checkpoint-960/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463dcf6c78516d41c490fc84ac01bb65aa5bc94eeb8f19d029dda6436415fdef
+size 535739578

run-3/checkpoint-960/rng_state.pth

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

run-3/checkpoint-960/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3580a83400d9ddfe6effdf1c84f5ebf585c0b625123e6119e0a408fd2fb5a1
+size 1064

run-3/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-3/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-3/checkpoint-960/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.8848263254113345,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-3\\checkpoint-960",
+  "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": 2.741556032723218e-06,
+      "loss": 0.3969,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8606032906764168,
+      "eval_loss": 0.38725385069847107,
+      "eval_runtime": 13.634,
+      "eval_samples_per_second": 160.481,
+      "eval_steps_per_second": 5.061,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.0561670245424133e-06,
+      "loss": 0.3833,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8816270566727605,
+      "eval_loss": 0.3825770616531372,
+      "eval_runtime": 13.6065,
+      "eval_samples_per_second": 160.806,
+      "eval_steps_per_second": 5.071,
+      "step": 480
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.370778016361609e-06,
+      "loss": 0.3791,
+      "step": 720
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8834552102376599,
+      "eval_loss": 0.38152310252189636,
+      "eval_runtime": 13.6038,
+      "eval_samples_per_second": 160.837,
+      "eval_steps_per_second": 5.072,
+      "step": 720
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.853890081808044e-07,
+      "loss": 0.3767,
+      "step": 960
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8848263254113345,
+      "eval_loss": 0.37997502088546753,
+      "eval_runtime": 13.589,
+      "eval_samples_per_second": 161.012,
+      "eval_steps_per_second": 5.078,
+      "step": 960
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 651630374965248.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3534065692399305,
+    "learning_rate": 3.4269450409040222e-06,
+    "num_train_epochs": 5,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 32,
+    "temperature": 11
+  }
+}

run-3/checkpoint-960/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a387f5bff97f17f9ccdf5718f369b40c94efa84e41a438755774bcf08a1544
+size 4792