Training in progress, epoch 3

logs/events.out.tfevents.1702102963.joseph_legion.21824.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:932865e465e8adf61fbfb3694e2783124e794baca530e70c8117480cedad26d0
-size 5608
+oid sha256:19d432b8e0e393d772c273fbb8d0d63255ffd0ad61ef6232f47b53e5c0aa659b
+size 6088

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f52ece9aae85f20cfcd83d24dec3d38850cc508dad334758f5878d839fe7ab
+oid sha256:fd8dfff30b66896cfcc4ce80ff1376c37b0cd4f8a1a0fa11547e32941670d144
 size 17550344

run-6/checkpoint-1437/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-6/checkpoint-1437/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8dfff30b66896cfcc4ce80ff1376c37b0cd4f8a1a0fa11547e32941670d144
+size 17550344

run-6/checkpoint-1437/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39fb67ecf823dbd13ce910ab6cad24369873a6dd9015c8aced82de9001b212d3
+size 35125946

run-6/checkpoint-1437/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b23a17af1b94f916aaf107ddc076fbcdaa9539e8fb2390740ff59128a824e62
+size 14244

run-6/checkpoint-1437/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84deca64bfc93c5c0bf3081378e0c5959548a4d64556e0d9e1590b91f3019464
+size 1064

run-6/checkpoint-1437/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-6/checkpoint-1437/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-6/checkpoint-1437/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.8555758683729433,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-6\\checkpoint-479",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1437,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.436801749195149e-06,
+      "loss": 0.542,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.49427542090415955,
+      "eval_runtime": 10.8162,
+      "eval_samples_per_second": 202.29,
+      "eval_steps_per_second": 1.664,
+      "step": 479
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.624534499463433e-06,
+      "loss": 0.4855,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.4927231967449188,
+      "eval_runtime": 10.8596,
+      "eval_samples_per_second": 201.481,
+      "eval_steps_per_second": 1.658,
+      "step": 958
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.8122672497317165e-06,
+      "loss": 0.4831,
+      "step": 1437
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.49184373021125793,
+      "eval_runtime": 10.7306,
+      "eval_samples_per_second": 203.904,
+      "eval_steps_per_second": 1.677,
+      "step": 1437
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1916,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 3695808481152.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.249068998926866e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 2
+  }
+}

run-6/checkpoint-1437/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc7b733813b9e540afa8125799235bbdb9e0aa9b7d5da1840162c6d2403f7e8
+size 4792