Training in progress, epoch 4

logs/events.out.tfevents.1702108679.joseph_legion.21824.44

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee591fcb5f2658cd74b4997dc005f3856f4ad3ce053442a995ecc835a330d080
-size 6088
+oid sha256:d5580d8054020b6fbe30ff1fe550bf93e3147b801725173ed72d65331aace003
+size 6922

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7480e75e14725414e80282617fd84d2b335d4acadd5e599111bdba88535de1d5
+oid sha256:985ab7a6263cc3dc17b05cefd6cc27d05902de4d1b4a38bb6a29770c2c5a5218
 size 17550344

run-43/checkpoint-1916/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-43/checkpoint-1916/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985ab7a6263cc3dc17b05cefd6cc27d05902de4d1b4a38bb6a29770c2c5a5218
+size 17550344

run-43/checkpoint-1916/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e9114f05608ecaaab539fec1f250d281cec0935d001e17ccf7273e94733e53
+size 35125946

run-43/checkpoint-1916/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5256ead2626cb2983669f3e741261ed737d451ab8f73c512c4970fccf67d23
+size 14244

run-43/checkpoint-1916/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90fd277476cb2cf20749c507bb5f4fa2822e4a6633368b448983528dbe2cb578
+size 1064

run-43/checkpoint-1916/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-43/checkpoint-1916/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-43/checkpoint-1916/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.879798903107861,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-43\\checkpoint-1916",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1916,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.34554568566064e-05,
+      "loss": 0.483,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8596892138939671,
+      "eval_loss": 0.47507455945014954,
+      "eval_runtime": 10.9084,
+      "eval_samples_per_second": 200.58,
+      "eval_steps_per_second": 1.65,
+      "step": 479
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.56369712377376e-05,
+      "loss": 0.4592,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8779707495429616,
+      "eval_loss": 0.4689006209373474,
+      "eval_runtime": 10.9282,
+      "eval_samples_per_second": 200.215,
+      "eval_steps_per_second": 1.647,
+      "step": 958
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.78184856188688e-05,
+      "loss": 0.4483,
+      "step": 1437
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8784277879341865,
+      "eval_loss": 0.4681478440761566,
+      "eval_runtime": 10.9709,
+      "eval_samples_per_second": 199.438,
+      "eval_steps_per_second": 1.641,
+      "step": 1437
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.4428,
+      "step": 1916
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.879798903107861,
+      "eval_loss": 0.46910566091537476,
+      "eval_runtime": 10.8704,
+      "eval_samples_per_second": 201.28,
+      "eval_steps_per_second": 1.656,
+      "step": 1916
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1916,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 4969223449632.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.12739424754752e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 34
+  }
+}

run-43/checkpoint-1916/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3207499b0d64eace83ec51ecd86a3bd178d5b9cc0c7fbcee191ec716f03d9c1
+size 4792