Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e35398ed96f06d4238aceca638c7c521a9129278a862c36bc02007641ecf2236
+oid sha256:7494b409a751d0347371ef3fc30b4add7e16c4d461399455fe430830f6c13a2f
 size 267832560

run-5/checkpoint-28/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": "4.38.1",
+  "vocab_size": 30522
+}

run-5/checkpoint-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eeb4cde5e2497aad98386dfe99bb29a66ca10b756af1cfc27933102317103ce
+size 267832560

run-5/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb58ccbd3e6b90c96f8fff876b4d82299116ae44e766876cb70094e41c104b7
+size 535727290

run-5/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43cff3408b96e3f9f74e8cd3bb2a4e72ecfee2adbbee614d3bc184f310e5be26
+size 14244

run-5/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6606795eed320b6bfb3433e964374823d5846d74f0112a8fd53bd5263e9c4214
+size 1064

run-5/checkpoint-28/special_tokens_map.json

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

run-5/checkpoint-28/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]"
+}

run-5/checkpoint-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-14",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6580806374549866,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7291,
+      "eval_samples_per_second": 1430.504,
+      "eval_steps_per_second": 90.521,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6493741273880005,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.739,
+      "eval_samples_per_second": 1411.284,
+      "eval_steps_per_second": 89.305,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 28,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.1580552287327505e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 4
+  }
+}

run-5/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f219c1169fcda35294e365c01a3032e189d9e46b6707e1f7de4a0ad24313fe55
+size 4984

run-6/checkpoint-107/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": "4.38.1",
+  "vocab_size": 30522
+}

run-6/checkpoint-107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eb13c259762b3e31e0deb3b27ab35d21ad34cf634e47f3220984f58bab2c5cf
+size 267832560

run-6/checkpoint-107/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1aac08b709fef92f99aa80f62ef1a91d71de91687ae4524514e5b346597c8bb
+size 535727290

run-6/checkpoint-107/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66755335e6748a75fdabe0d7df9f0951658c11d0b7f82a50b7a6da403db52f29
+size 14308

run-6/checkpoint-107/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36aa537a0424c890dd0b17333fc903224681d6ec7194254dfff75266472bcda6
+size 1064

run-6/checkpoint-107/special_tokens_map.json

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

run-6/checkpoint-107/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]"
+}

run-6/checkpoint-107/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.11102646115366906,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-107",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 107,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.581040620803833,
+      "eval_matthews_correlation": 0.11102646115366906,
+      "eval_runtime": 0.7481,
+      "eval_samples_per_second": 1394.158,
+      "eval_steps_per_second": 88.221,
+      "step": 107
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.085300795112664e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 37
+  }
+}

run-6/checkpoint-107/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334de261bfa845ae1e580803de4fcb92790d2a173dae14f059cd42ae15643e7e
+size 4984

run-6/checkpoint-214/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": "4.38.1",
+  "vocab_size": 30522
+}

run-6/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f5fcbf2ddc9237b5a1daab9b9b81649747a27ea8105e46aec7eec04e0e0902
+size 267832560

run-6/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85d1f66182ba1e8ab07bc071ede87c32ac7b1e866dffd0cb538319baa02cbb6
+size 535727290

run-6/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b69e67988bf8b91093712d7e30da543ca0bb7c000541dfaea05a8661f08c69fa
+size 14308

run-6/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d7a285953b0514410f2ee2ed3fa1d5018e487ee640d73ed7ed6b01db51af6b
+size 1064

run-6/checkpoint-214/special_tokens_map.json

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

run-6/checkpoint-214/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]"
+}

run-6/checkpoint-214/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.3131402496239773,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-214",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.581040620803833,
+      "eval_matthews_correlation": 0.11102646115366906,
+      "eval_runtime": 0.7481,
+      "eval_samples_per_second": 1394.158,
+      "eval_steps_per_second": 88.221,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5838358402252197,
+      "eval_matthews_correlation": 0.3131402496239773,
+      "eval_runtime": 1.3921,
+      "eval_samples_per_second": 749.221,
+      "eval_steps_per_second": 47.41,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.085300795112664e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 37
+  }
+}

run-6/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334de261bfa845ae1e580803de4fcb92790d2a173dae14f059cd42ae15643e7e
+size 4984

run-8/checkpoint-14/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": "4.38.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-14/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7494b409a751d0347371ef3fc30b4add7e16c4d461399455fe430830f6c13a2f
+size 267832560

run-8/checkpoint-14/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097c2b7ee3dffaf4a11c03c2b0cdc2d3ba090d35edf003437c5ec97ad4fa65e9
+size 535727290

run-8/checkpoint-14/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf257f671c707ccdd474b5a0ba9e754e1bb3ce68fb1afbeb3ddc1ff8c5da2f36
+size 14308

run-8/checkpoint-14/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b02e7750411dcb9604d946d192e9d673e6df4beec00553931988e3541cdb16d3
+size 1064

run-8/checkpoint-14/special_tokens_map.json

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

run-8/checkpoint-14/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]"
+}

run-8/checkpoint-14/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-14",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 14,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6572101712226868,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6768,
+      "eval_samples_per_second": 1541.101,
+      "eval_steps_per_second": 97.519,
+      "step": 14
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.4691796048354265e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 21
+  }
+}

run-8/checkpoint-14/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624a7060e032d6598d3feb122ad57670da0e70d477bd73d4690f21484ec303b6
+size 4984

runs/Feb27_12-55-59_86e2730489af/events.out.tfevents.1709040314.86e2730489af.508.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f760016ef2298967d890edbb2cc88e313e97565d993c21a79e3ef70cbacaf83
+size 5559

runs/Feb27_12-55-59_86e2730489af/events.out.tfevents.1709040387.86e2730489af.508.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f720da6315887c9e3d51c70dcab547ee815542d9b5cdc9945cf150c9e92e4b59
+size 4871

runs/Feb27_12-55-59_86e2730489af/events.out.tfevents.1709040393.86e2730489af.508.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e795fc11c8ed92c58ce2e3e9d2700725905f409c85b6e79367aca0060775e8f
+size 6536

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f219c1169fcda35294e365c01a3032e189d9e46b6707e1f7de4a0ad24313fe55
+oid sha256:624a7060e032d6598d3feb122ad57670da0e70d477bd73d4690f21484ec303b6
 size 4984