Training in progress, epoch 1

logs/events.out.tfevents.1702225275.joseph_legion.22340.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f50dde5bd12e7833b589b92e6defa98e37231f1a97c72d6100ea493f07a42aa
-size 7382
+oid sha256:b2dfb4b74e4cb3e44303ead606000ca9a0ae493760b382af11f107b63f63df67
+size 8216

logs/events.out.tfevents.1702225402.joseph_legion.22340.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46568c5ca97bfa1d2ed599b2d71cbd91300dcf02aee3d2d108a190048b99fd2
+size 4990

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6739dc99ff0295d6306c52c7dc3c7d345ecfefd7ff7f12e6a578252df242c150
+oid sha256:372c78ddf6c4e8fa212310a8626cd53583f5cf5ac742b905d476fc931597aeea
 size 17549312

run-3/checkpoint-385/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-3/checkpoint-385/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e32664cc193bcc7eb2e5942412a76c076c343e8bfd146e3fb6eb2417e2622b
+size 17549312

run-3/checkpoint-385/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0a6dd85985cdb37923a831a1fc2bc9540f497ba45318df5416cb3cfcd9e990
+size 35123898

run-3/checkpoint-385/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de1659e53522973aa7c79c5ed754d27fcace1e246e65b9c807a28319a424b1a
+size 14308

run-3/checkpoint-385/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58fbb26fe48150260c24cf267be6bb8bf013a4dec1ef59f617712920e25fe543
+size 1064

run-3/checkpoint-385/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-3/checkpoint-385/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-3/checkpoint-385/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.7,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-3\\checkpoint-275",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 385,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.4720964669022145e-05,
+      "loss": 0.3636,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6378787878787879,
+      "eval_loss": 0.3626602292060852,
+      "eval_runtime": 3.3658,
+      "eval_samples_per_second": 588.264,
+      "eval_steps_per_second": 4.754,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2267470557518455e-05,
+      "loss": 0.3604,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6393939393939394,
+      "eval_loss": 0.35877418518066406,
+      "eval_runtime": 3.34,
+      "eval_samples_per_second": 592.817,
+      "eval_steps_per_second": 4.79,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.813976446014764e-06,
+      "loss": 0.356,
+      "step": 165
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6792929292929293,
+      "eval_loss": 0.3534165918827057,
+      "eval_runtime": 3.437,
+      "eval_samples_per_second": 576.084,
+      "eval_steps_per_second": 4.655,
+      "step": 165
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.360482334511072e-06,
+      "loss": 0.3505,
+      "step": 220
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6924242424242424,
+      "eval_loss": 0.34838515520095825,
+      "eval_runtime": 3.3922,
+      "eval_samples_per_second": 583.69,
+      "eval_steps_per_second": 4.717,
+      "step": 220
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.906988223007382e-06,
+      "loss": 0.3466,
+      "step": 275
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.34577473998069763,
+      "eval_runtime": 3.3959,
+      "eval_samples_per_second": 583.048,
+      "eval_steps_per_second": 4.712,
+      "step": 275
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.453494111503691e-06,
+      "loss": 0.3436,
+      "step": 330
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.694949494949495,
+      "eval_loss": 0.34401819109916687,
+      "eval_runtime": 3.3756,
+      "eval_samples_per_second": 586.56,
+      "eval_steps_per_second": 4.74,
+      "step": 330
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0,
+      "loss": 0.3422,
+      "step": 385
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6974747474747475,
+      "eval_loss": 0.3435021638870239,
+      "eval_runtime": 3.3725,
+      "eval_samples_per_second": 587.107,
+      "eval_steps_per_second": 4.744,
+      "step": 385
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 385,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 5884067175000.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.524441928071262,
+    "learning_rate": 1.7174458780525836e-05,
+    "num_train_epochs": 7,
+    "temperature": 11
+  }
+}

run-3/checkpoint-385/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beba1d8158ddcd8ff24d11a4333407e6a3952372b86d4bccb40918afb846f7c7
+size 4792

run-4/checkpoint-55/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-4/checkpoint-55/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372c78ddf6c4e8fa212310a8626cd53583f5cf5ac742b905d476fc931597aeea
+size 17549312

run-4/checkpoint-55/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5637f96ebfb68027ed3467cda22220645704ecbe71832b0ee4a739cc90ad3b
+size 35123898

run-4/checkpoint-55/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9684c683f536a580a60f9875e5f0c89c28c0f0b16080832ddf6bf0362cbd5e4
+size 14308

run-4/checkpoint-55/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13607e3b911d4a16935917f3c83a46bc1ac01943764f92f81cdf55d17027899
+size 1064

run-4/checkpoint-55/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-4/checkpoint-55/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-4/checkpoint-55/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.6757575757575758,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-4\\checkpoint-55",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 55,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.7562580137457846e-05,
+      "loss": 0.2619,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6757575757575758,
+      "eval_loss": 0.2587513327598572,
+      "eval_runtime": 3.3651,
+      "eval_samples_per_second": 588.396,
+      "eval_steps_per_second": 4.755,
+      "step": 55
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 165,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 847072419720.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.37297394921136384,
+    "learning_rate": 4.134387020618677e-05,
+    "num_train_epochs": 3,
+    "temperature": 9
+  }
+}

run-4/checkpoint-55/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9a11b0846e7636f5af73d31d51ba1488245981cb2986f1d864802ca6071912
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beba1d8158ddcd8ff24d11a4333407e6a3952372b86d4bccb40918afb846f7c7
+oid sha256:2e9a11b0846e7636f5af73d31d51ba1488245981cb2986f1d864802ca6071912
 size 4792