Training in progress, epoch 1

logs/events.out.tfevents.1702104257.joseph_legion.21824.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5da1e7cfb51425f2be2006bbecaa82f6ac05fdc9eb07cd43ed49f19a4ebee4
+size 5128

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2ba390c7e9d7258e30527d44a03e20d68a5a6a125566b1e7b007f9b5b42fcc
+oid sha256:89295cd3cf709a5bc68cbcf8ea0d6b3e4cf0453f5beb892723b6474e4418e045
 size 17550344

run-14/checkpoint-958/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-14/checkpoint-958/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89295cd3cf709a5bc68cbcf8ea0d6b3e4cf0453f5beb892723b6474e4418e045
+size 17550344

run-14/checkpoint-958/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752e7248d951378aa8429c0af46805d9f94b911b200d38dfc076aafb2fea2327
+size 35125946

run-14/checkpoint-958/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe97cb94e63483ace697e1d837a0c8885b1f6d4b24e5950ba36a8aa4b44d0be
+size 14308

run-14/checkpoint-958/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b3b5f349ca9958c324f2238f3b15643bd7b4a0f444225a4ef52bc23fa725bc
+size 1064

run-14/checkpoint-958/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-14/checkpoint-958/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-14/checkpoint-958/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.8569469835466179,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-14\\checkpoint-958",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 958,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5401671139683948e-05,
+      "loss": 0.4836,
+      "step": 958
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8569469835466179,
+      "eval_loss": 0.4813261330127716,
+      "eval_runtime": 10.7519,
+      "eval_samples_per_second": 203.5,
+      "eval_steps_per_second": 1.674,
+      "step": 958
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2874,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 972409723776.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.810250670952592e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 24
+  }
+}

run-14/checkpoint-958/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb41126e6bbac33a40b33ecc944fe5ff5c0ff69a37ceb7f85870931f6ae5fa1
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54aa3eba82c9a8d74c63e5f5f082ba4ef430b3596a3a485f7df6d807bbd87a66
+oid sha256:fdb41126e6bbac33a40b33ecc944fe5ff5c0ff69a37ceb7f85870931f6ae5fa1
 size 4792