Upload 9 files

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57ae2ea3e57c2244a1efaca430f6c19b3dd80610e151ffa81a26467b632ba71
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80971cd36023f00f846eee6a046dce6bf3e0ba81d997216c3160dc310da5e796
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,222 @@
+{
+  "best_metric": 0.3780292570590973,
+  "best_model_checkpoint": "/sphinx/u/culturebank/tiktok_data/controversial_data/models/combined_data_distilbert_4/checkpoint-210",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29,
+      "grad_norm": 2.306892156600952,
+      "learning_rate": 7.619047619047618e-06,
+      "loss": 0.6843,
+      "step": 10
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.6495659351348877,
+      "learning_rate": 7.238095238095238e-06,
+      "loss": 0.6717,
+      "step": 20
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.9257926940917969,
+      "learning_rate": 6.857142857142856e-06,
+      "loss": 0.6709,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6314077377319336,
+      "eval_recall": 0.5,
+      "eval_runtime": 0.1157,
+      "eval_samples_per_second": 1011.601,
+      "eval_steps_per_second": 69.169,
+      "step": 35
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 2.3859009742736816,
+      "learning_rate": 6.476190476190476e-06,
+      "loss": 0.6529,
+      "step": 40
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 2.7452704906463623,
+      "learning_rate": 6.0952380952380945e-06,
+      "loss": 0.6063,
+      "step": 50
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 2.4575912952423096,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.6315,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.417150497436523,
+      "learning_rate": 5.333333333333333e-06,
+      "loss": 0.5804,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5548444390296936,
+      "eval_recall": 0.9,
+      "eval_runtime": 0.1059,
+      "eval_samples_per_second": 1104.4,
+      "eval_steps_per_second": 75.515,
+      "step": 70
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 2.3926234245300293,
+      "learning_rate": 4.952380952380952e-06,
+      "loss": 0.5411,
+      "step": 80
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 3.461317539215088,
+      "learning_rate": 4.571428571428571e-06,
+      "loss": 0.5031,
+      "step": 90
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 4.521629333496094,
+      "learning_rate": 4.19047619047619e-06,
+      "loss": 0.5264,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.4601297676563263,
+      "eval_recall": 0.9,
+      "eval_runtime": 0.113,
+      "eval_samples_per_second": 1035.499,
+      "eval_steps_per_second": 70.803,
+      "step": 105
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 5.5885233879089355,
+      "learning_rate": 3.809523809523809e-06,
+      "loss": 0.4245,
+      "step": 110
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 4.529420852661133,
+      "learning_rate": 3.428571428571428e-06,
+      "loss": 0.4956,
+      "step": 120
+    },
+    {
+      "epoch": 3.71,
+      "grad_norm": 3.9411473274230957,
+      "learning_rate": 3.0476190476190473e-06,
+      "loss": 0.4511,
+      "step": 130
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 9.669978141784668,
+      "learning_rate": 2.6666666666666664e-06,
+      "loss": 0.4133,
+      "step": 140
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.40984398126602173,
+      "eval_recall": 0.9,
+      "eval_runtime": 0.1049,
+      "eval_samples_per_second": 1114.827,
+      "eval_steps_per_second": 76.228,
+      "step": 140
+    },
+    {
+      "epoch": 4.29,
+      "grad_norm": 4.2742390632629395,
+      "learning_rate": 2.2857142857142856e-06,
+      "loss": 0.382,
+      "step": 150
+    },
+    {
+      "epoch": 4.57,
+      "grad_norm": 3.2808213233947754,
+      "learning_rate": 1.9047619047619045e-06,
+      "loss": 0.3756,
+      "step": 160
+    },
+    {
+      "epoch": 4.86,
+      "grad_norm": 4.833192348480225,
+      "learning_rate": 1.5238095238095236e-06,
+      "loss": 0.3707,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.3795815408229828,
+      "eval_recall": 0.8,
+      "eval_runtime": 0.1097,
+      "eval_samples_per_second": 1066.759,
+      "eval_steps_per_second": 72.941,
+      "step": 175
+    },
+    {
+      "epoch": 5.14,
+      "grad_norm": 4.624128818511963,
+      "learning_rate": 1.1428571428571428e-06,
+      "loss": 0.3365,
+      "step": 180
+    },
+    {
+      "epoch": 5.43,
+      "grad_norm": 6.549154758453369,
+      "learning_rate": 7.619047619047618e-07,
+      "loss": 0.3851,
+      "step": 190
+    },
+    {
+      "epoch": 5.71,
+      "grad_norm": 2.928457021713257,
+      "learning_rate": 3.809523809523809e-07,
+      "loss": 0.32,
+      "step": 200
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 8.7202787399292,
+      "learning_rate": 0.0,
+      "loss": 0.3771,
+      "step": 210
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.3780292570590973,
+      "eval_recall": 0.9,
+      "eval_runtime": 0.1053,
+      "eval_samples_per_second": 1111.275,
+      "eval_steps_per_second": 75.985,
+      "step": 210
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 92894315659848.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbe9b38bf17a8ade4c5094d5cd61a94588699f019d674d1eefbba9934ced957
+size 5048