Training in progress, epoch 4

logs/events.out.tfevents.1702107878.joseph_legion.21824.39

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b01a6f39a9e712384c18b774fed143353700f0c413c342def549e75cebfa5574
-size 6088
+oid sha256:67c6ddd0362524be14e794487aea6856f04aa97f767fc044aed7fc11f9df7b16
+size 6922

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a7f9862ff450916e427c809cdcadfb0c885a0d54fac439b3687e0dd4109c3e
+oid sha256:eb2836094bfd5e40bbb5becd1cf6826375af1318cc0d3b518f4fadbaddb7d74f
 size 17550344

run-38/checkpoint-3832/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-38/checkpoint-3832/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2836094bfd5e40bbb5becd1cf6826375af1318cc0d3b518f4fadbaddb7d74f
+size 17550344

run-38/checkpoint-3832/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2a1ff560ebf67fb755e9af210438275a55bdbbdcfd66f71d9ac814cd6ee774
+size 35125946

run-38/checkpoint-3832/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7977ff397cc77aa85ed75b632fda41f758e3c1f157fc84f632106fc9dbe9bb4
+size 14244

run-38/checkpoint-3832/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b36e88ae8e1358a0616777123ba8493d935c4c3c0af145ca3fe153f10095bd1
+size 1064

run-38/checkpoint-3832/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-38/checkpoint-3832/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-38/checkpoint-3832/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.8788848263254113,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-38\\checkpoint-3832",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 3832,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.391577145227344e-05,
+      "loss": 0.4771,
+      "step": 958
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8656307129798904,
+      "eval_loss": 0.4757784307003021,
+      "eval_runtime": 10.7985,
+      "eval_samples_per_second": 202.621,
+      "eval_steps_per_second": 1.667,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.594384763484896e-05,
+      "loss": 0.4555,
+      "step": 1916
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8747714808043876,
+      "eval_loss": 0.468022882938385,
+      "eval_runtime": 10.8634,
+      "eval_samples_per_second": 201.41,
+      "eval_steps_per_second": 1.657,
+      "step": 1916
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.797192381742448e-05,
+      "loss": 0.4439,
+      "step": 2874
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8775137111517367,
+      "eval_loss": 0.47030702233314514,
+      "eval_runtime": 10.7413,
+      "eval_samples_per_second": 203.699,
+      "eval_steps_per_second": 1.676,
+      "step": 2874
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.4368,
+      "step": 3832
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8788848263254113,
+      "eval_loss": 0.4700613021850586,
+      "eval_runtime": 10.6938,
+      "eval_samples_per_second": 204.605,
+      "eval_steps_per_second": 1.683,
+      "step": 3832
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3832,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 3932355876576.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.188769526969792e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 34
+  }
+}

run-38/checkpoint-3832/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e02b5c9ab926cbcd04f9002ad66fa2ff85c04cec23f24af0d737c74ce851f40
+size 4792