Training in progress, epoch 2

logs/events.out.tfevents.1702224720.joseph_legion.23484.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1af3c1f64a47d6de4bdac622ccd7ad1a5ff8ee276f7b3eaf65b060e8cd639a1a
-size 4998
+oid sha256:36e1ef6cc9c0ca7e77b939437b0c3c1acd443c323b92b6e88111b8549102ca6d
+size 5478

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17ca7a363c843803f3e76638c1d11d8f7853d2f38242929059edf0481450274
+oid sha256:99e8c9193e887e869d1a1a72a1efb391b8d6a95b4dced09fe0e57250bc7ec660
 size 17549312

run-0/checkpoint-434/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "agvidit1/TinyBert-Berttoken-Toxigen-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": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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-0/checkpoint-434/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e8c9193e887e869d1a1a72a1efb391b8d6a95b4dced09fe0e57250bc7ec660
+size 17549312

run-0/checkpoint-434/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0afc125d93ad94c7deef647bcb2958e56672ff12d17fb4ccef84def37637cdb
+size 35123898

run-0/checkpoint-434/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003a76a2d66192e9cfdf018bad76e348660b27f36aec32244ff5cb22ea028892
+size 14308

run-0/checkpoint-434/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5966c5dfea937915149fa7d48680958685ce9ec3e58e69f070fe511390c3c5e1
+size 1064

run-0/checkpoint-434/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-0/checkpoint-434/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-434/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 0.3752525252525252,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-0\\checkpoint-434",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 434,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.727904240831156e-07,
+      "loss": 0.1834,
+      "step": 217
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.37424242424242427,
+      "eval_loss": 0.18295247852802277,
+      "eval_runtime": 3.4165,
+      "eval_samples_per_second": 579.533,
+      "eval_steps_per_second": 18.147,
+      "step": 217
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.863952120415578e-07,
+      "loss": 0.1833,
+      "step": 434
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3752525252525252,
+      "eval_loss": 0.18277868628501892,
+      "eval_runtime": 3.3644,
+      "eval_samples_per_second": 588.515,
+      "eval_steps_per_second": 18.428,
+      "step": 434
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 651,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1339410961920.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.2540144352572642,
+    "learning_rate": 1.4591856361246734e-06,
+    "num_train_epochs": 3,
+    "temperature": 2
+  }
+}

run-0/checkpoint-434/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:149f8fa1b61871a641264bc09cd2d38b7708e552c6ad468d5d6b5e63047463b3
+size 4792