Training in progress, epoch 1

config.json

@@ -2,17 +2,12 @@
   "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
   "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
   "dim": 768,
   "dropout": 0.1,
-  "hidden_act": "gelu",
   "hidden_dim": 3072,
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
   "id2label": {
     "0": 0,
     "1": 1,
@@ -20,22 +15,17 @@
     "3": 3
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "0": 0,
     "1": 1,
     "2": 2,
     "3": 3
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
@@ -43,7 +33,5 @@
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.36.0.dev0",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

logs/events.out.tfevents.1702159308.joseph_legion.21448.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fcce4b04a796be6d6c2895b7a672fa80c5334e5be488a9b571d45689483ded0
-size 6216
+oid sha256:423ad46e9eba7533e72a5eaf0916c2d88353bbb8a7d3c740d2aa1392e7dd27fa
+size 7050

logs/events.out.tfevents.1702161414.joseph_legion.21448.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc9c8449a0a87b939c9c39350362f1cc2a9f001098147ae05395ab828467019
+size 4935

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07c9f34b57a3a13a342479464cb5d73b1091df4f7e03defda474e020a5de74b
-size 437964800
+oid sha256:cdf7db061b64c747840ad641e4d1dd91554db63af5589d5731f9eeef23ac906c
+size 267838720

run-0/checkpoint-240/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-0/checkpoint-240/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf7db061b64c747840ad641e4d1dd91554db63af5589d5731f9eeef23ac906c
+size 267838720

run-0/checkpoint-240/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1bf6443d168ba65c9ec352d42d0d93ba0fed23639e654b7bab7e26c00d388a
+size 535739578

run-0/checkpoint-240/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2fcff0827ca522e87f836d14f0cd5430b25ecce7f7ce5f905da8656f7dcf685
+size 14308

run-0/checkpoint-240/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54afb1f766f95429b4cbb7803c66a36dff5cfc471244fad256d6c739670b5374
+size 1064

run-0/checkpoint-240/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-0/checkpoint-240/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-0/checkpoint-240/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8555758683729433,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-0\\checkpoint-240",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 240,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.200932249944345e-06,
+      "loss": 0.3542,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.34542378783226013,
+      "eval_runtime": 27.8228,
+      "eval_samples_per_second": 78.641,
+      "eval_steps_per_second": 2.48,
+      "step": 240
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 163370211234720.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.2937223587192618,
+    "learning_rate": 1.441118699933214e-06,
+    "num_train_epochs": 6,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 32,
+    "temperature": 22
+  }
+}

run-0/checkpoint-240/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c270c372d171f05f77d295e45676e68498a717682284e18b37bf87d03001f66
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e5641ecfb96fdcb3407ab96df0305126645cc5a0272622b637913e172e8c46
+oid sha256:1c270c372d171f05f77d295e45676e68498a717682284e18b37bf87d03001f66
 size 4792