Training in progress, epoch 3

logs/events.out.tfevents.1702104062.joseph_legion.21824.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab61da92d35d043e060c52c84f8231402e517beb654bf106bee416f0b5c7e05
-size 5608
+oid sha256:1dbb62d53241cb3dd485978aba03e11f5e8ff87ecff1284c4c5350ee671670d4
+size 6442

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4da0068ab238f230c9e318b71d41851d2e04541198fd3cc7373d41e2d776b7
+oid sha256:0a2ba390c7e9d7258e30527d44a03e20d68a5a6a125566b1e7b007f9b5b42fcc
 size 17550344

run-13/checkpoint-2874/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "agvidit1/GoogleTinyBert_HateSpeech_pretrain",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "noHate",
+    "1": "hate",
+    "2": "idk/skip",
+    "3": "relation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "hate": "1",
+    "idk/skip": "2",
+    "noHate": "0",
+    "relation": "3"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-13/checkpoint-2874/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2ba390c7e9d7258e30527d44a03e20d68a5a6a125566b1e7b007f9b5b42fcc
+size 17550344

run-13/checkpoint-2874/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ddd8e297f9525f8d7e93d8df0e164275eab082d348a66f6ba99378c3fb34a19
+size 35125946

run-13/checkpoint-2874/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0694e1d6edff82757ceb4ad1817c53e15dbb229ceb168c54512c4cf2b2903eb4
+size 14244

run-13/checkpoint-2874/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fffbaffab1264fea6c4063df280dd3615762903a6911789d976b57d17d1ae7e
+size 1064

run-13/checkpoint-2874/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-13/checkpoint-2874/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-13/checkpoint-2874/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.8752285191956124,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-13\\checkpoint-2874",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2874,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.33398074154431e-05,
+      "loss": 0.4745,
+      "step": 958
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8720292504570384,
+      "eval_loss": 0.4704694151878357,
+      "eval_runtime": 10.736,
+      "eval_samples_per_second": 203.8,
+      "eval_steps_per_second": 1.677,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.166990370772155e-05,
+      "loss": 0.4517,
+      "step": 1916
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8738574040219378,
+      "eval_loss": 0.4702502191066742,
+      "eval_runtime": 10.7957,
+      "eval_samples_per_second": 202.673,
+      "eval_steps_per_second": 1.667,
+      "step": 1916
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.4398,
+      "step": 2874
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8752285191956124,
+      "eval_loss": 0.47249820828437805,
+      "eval_runtime": 10.7363,
+      "eval_samples_per_second": 203.795,
+      "eval_steps_per_second": 1.677,
+      "step": 2874
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2874,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2937053187840.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.500971112316465e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 23
+  }
+}

run-13/checkpoint-2874/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54aa3eba82c9a8d74c63e5f5f082ba4ef430b3596a3a485f7df6d807bbd87a66
+size 4792