Training in progress, epoch 1

logs/events.out.tfevents.1702225147.joseph_legion.22340.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db32986a5694b7c0eb0a913c4ecbfbe70b9d4c3e73ea9f5993fbfe069a00b90e
-size 7381
+oid sha256:9e6d9eea34b8a4face6c98d1efd971c43205df6b9edac0744637da562fcfd637
+size 8215

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc3a57f7c1c7001719b0694856e99fab431dc976c343fabaf694d6f1af3e8938
+size 4991

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c88bec468c836aacf9a986561af1a8688f075e1b90ee35cf45c29a2966bdab1
+oid sha256:222d24250e272dbb63e4de0855973b32ebff587ee8773176bfbdbfe3f0ffa276
 size 17549312

run-2/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-2/checkpoint-385/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a3db7bb9ddb27ae9a44173b6ddd5c337bcf0c793eaf5607e4880ca5cce4960
+size 17549312

run-2/checkpoint-385/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caeb7236761475f372530c697da1a3faa2a082560a7da34c21e377dc3d81cc16
+size 35123898

run-2/checkpoint-385/rng_state.pth

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

run-2/checkpoint-385/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965895b290c1ee573b608fe068b4d8d4e4525a1d82e0f7736fef8837ef6d0b46
+size 1064

run-2/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-2/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-2/checkpoint-385/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.3621212121212121,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-2\\checkpoint-55",
+  "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": 1.5441792724155395e-05,
+      "loss": 0.036,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3621212121212121,
+      "eval_loss": 0.035133831202983856,
+      "eval_runtime": 3.3771,
+      "eval_samples_per_second": 586.31,
+      "eval_steps_per_second": 4.738,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.286816060346283e-05,
+      "loss": 0.0354,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3621212121212121,
+      "eval_loss": 0.0350903756916523,
+      "eval_runtime": 3.3705,
+      "eval_samples_per_second": 587.442,
+      "eval_steps_per_second": 4.747,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.0294528482770263e-05,
+      "loss": 0.0353,
+      "step": 165
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3621212121212121,
+      "eval_loss": 0.03502834588289261,
+      "eval_runtime": 3.355,
+      "eval_samples_per_second": 590.167,
+      "eval_steps_per_second": 4.769,
+      "step": 165
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.720896362077698e-06,
+      "loss": 0.0353,
+      "step": 220
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3621212121212121,
+      "eval_loss": 0.035031162202358246,
+      "eval_runtime": 3.3196,
+      "eval_samples_per_second": 596.459,
+      "eval_steps_per_second": 4.82,
+      "step": 220
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.1472642413851315e-06,
+      "loss": 0.0352,
+      "step": 275
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3621212121212121,
+      "eval_loss": 0.03497819975018501,
+      "eval_runtime": 3.3426,
+      "eval_samples_per_second": 592.36,
+      "eval_steps_per_second": 4.787,
+      "step": 275
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.5736321206925658e-06,
+      "loss": 0.0352,
+      "step": 330
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3621212121212121,
+      "eval_loss": 0.03496537730097771,
+      "eval_runtime": 3.3354,
+      "eval_samples_per_second": 593.638,
+      "eval_steps_per_second": 4.797,
+      "step": 330
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0,
+      "loss": 0.0353,
+      "step": 385
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3621212121212121,
+      "eval_loss": 0.034974899142980576,
+      "eval_runtime": 3.3525,
+      "eval_samples_per_second": 590.606,
+      "eval_steps_per_second": 4.773,
+      "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": 0.04724864888100444,
+    "learning_rate": 1.801542484484796e-05,
+    "num_train_epochs": 7,
+    "temperature": 8
+  }
+}

run-2/checkpoint-385/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3665af9c3c019c7a654a9c71965a2fc9fda3a71cd4b9490a09ae818e2cde0bb0
+size 4792

run-3/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-3/checkpoint-55/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:222d24250e272dbb63e4de0855973b32ebff587ee8773176bfbdbfe3f0ffa276
+size 17549312

run-3/checkpoint-55/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a819907007e2c4441ac222d2334a3c90f263052fd4a4020ca5fda2a283dbfbc4
+size 35123898

run-3/checkpoint-55/rng_state.pth

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

run-3/checkpoint-55/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25138cc41c41d789ac4e5cb2fc066e24fbc477e6c6de5792055b9b095d7bbe40
+size 1064

run-3/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-3/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-3/checkpoint-55/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.6378787878787879,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-3\\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": 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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 385,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 847072419720.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.524441928071262,
+    "learning_rate": 1.7174458780525836e-05,
+    "num_train_epochs": 7,
+    "temperature": 11
+  }
+}

run-3/checkpoint-55/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3665af9c3c019c7a654a9c71965a2fc9fda3a71cd4b9490a09ae818e2cde0bb0
+oid sha256:beba1d8158ddcd8ff24d11a4333407e6a3952372b86d4bccb40918afb846f7c7
 size 4792