Training in progress, epoch 3

logs/events.out.tfevents.1702107620.joseph_legion.21824.38

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7522f4611669fe71c423e37082407d90b3e9b021bd5fb7ce5697a71b6b93feb3
-size 5608
+oid sha256:a20adaefac16392b58ab12e0c1d5d403a9bc0824750b8d3000996a5eed5e18be
+size 6088

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3552011102844eda9318212536804e52ef06e1d02723424318245d0793956fce
+oid sha256:27ab657865ba7bfa1fe3ca67099a4f23225d474650fd609a5d3783bd107f8da4
 size 17550344

run-37/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-37/checkpoint-2874/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ab657865ba7bfa1fe3ca67099a4f23225d474650fd609a5d3783bd107f8da4
+size 17550344

run-37/checkpoint-2874/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694c8381b84af08d73a4005232c2c9db99499e3046e50f136f8d26f46ccffbc8
+size 35125946

run-37/checkpoint-2874/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebcc5616067f9e32baa4299ef1e41fb8d6c2f1df2c85211793d88a7acbb3ddd3
+size 14244

run-37/checkpoint-2874/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c3430ee6e1f7a622ed0a37ca750dd7552adf3a18af17d51848e4f165aa8eef
+size 1064

run-37/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-37/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-37/checkpoint-2874/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.879798903107861,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-37\\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": 5.448730733370957e-05,
+      "loss": 0.4754,
+      "step": 958
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8642595978062158,
+      "eval_loss": 0.4731012284755707,
+      "eval_runtime": 10.8286,
+      "eval_samples_per_second": 202.058,
+      "eval_steps_per_second": 1.662,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.632487155580638e-05,
+      "loss": 0.4543,
+      "step": 1916
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8756855575868373,
+      "eval_loss": 0.4699413478374481,
+      "eval_runtime": 10.91,
+      "eval_samples_per_second": 200.551,
+      "eval_steps_per_second": 1.65,
+      "step": 1916
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.816243577790319e-05,
+      "loss": 0.4439,
+      "step": 2874
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.879798903107861,
+      "eval_loss": 0.4700252115726471,
+      "eval_runtime": 10.7719,
+      "eval_samples_per_second": 203.121,
+      "eval_steps_per_second": 1.671,
+      "step": 2874
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3832,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 2936715504192.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.264974311161276e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 36
+  }
+}

run-37/checkpoint-2874/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788b716bebf70115183b79fc3fb95e168b69e55dae12f79439a8ba09ad5132ae
+size 4792