Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd33315e20753a48156c4b5ca9911a7e161b40165de4ae06f51de6047651f4e6
+oid sha256:abae716af60ef08df4cfda8630d61b2a17e55b01951217054670529e3ef70248
 size 267832560

run-3/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-3/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffcda789d7aa0844830063f35e81e7c4def706bd6c3f3fc49fa181223fd31a58
+size 267832560

run-3/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d74c3549dc6962ba0795fe6cccd3ced49f17d4548a54251e9d3c6384deaab72b
+size 535727290

run-3/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fa77c1dc06fee9d56a8591d2f9bbb174b3611fd68fd8c3d0d1d976b723384a
+size 14308

run-3/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d521eece26d4249b87d8ba7b54ca93f152dc895be28b5d8fc2aeb732fbc7294e
+size 1064

run-3/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-3/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-3/checkpoint-214/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.26833966259076464,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-107",
+  "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": 0.5614452362060547,
+      "eval_matthews_correlation": 0.26833966259076464,
+      "eval_runtime": 0.6971,
+      "eval_samples_per_second": 1496.255,
+      "eval_steps_per_second": 94.682,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.739422082901001,
+      "eval_matthews_correlation": 0.26077721196619447,
+      "eval_runtime": 0.7344,
+      "eval_samples_per_second": 1420.259,
+      "eval_steps_per_second": 89.873,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 428,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.455881385704775e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-3/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5f0e9113d8062cf85385591e5f5bdf6394f33b566e40e55a23d20c2257d2eb
+size 4984

run-3/checkpoint-321/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-3/checkpoint-321/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2446d4f93402c33269372886979a7c3f00226d433f7ecf5a9765e9c83038ce73
+size 267832560

run-3/checkpoint-321/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee6f05a30b78d2d1f92a41bf86cb124091f5b6803f0fbc4964b4ed6f2652223
+size 535727290

run-3/checkpoint-321/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ff0a106a99afd321cfa1a064eabef1bd222c3b9c6da18f9ad8e0da4c175c99
+size 14308

run-3/checkpoint-321/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa36b83b0637e58d40d8a5a5340a6b309d087bd689ad84541033e249bc9ebde6
+size 1064

run-3/checkpoint-321/special_tokens_map.json

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

run-3/checkpoint-321/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-3/checkpoint-321/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.30530026767951607,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-321",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 321,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5614452362060547,
+      "eval_matthews_correlation": 0.26833966259076464,
+      "eval_runtime": 0.6971,
+      "eval_samples_per_second": 1496.255,
+      "eval_steps_per_second": 94.682,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.739422082901001,
+      "eval_matthews_correlation": 0.26077721196619447,
+      "eval_runtime": 0.7344,
+      "eval_samples_per_second": 1420.259,
+      "eval_steps_per_second": 89.873,
+      "step": 214
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.1903438568115234,
+      "eval_matthews_correlation": 0.30530026767951607,
+      "eval_runtime": 0.7546,
+      "eval_samples_per_second": 1382.174,
+      "eval_steps_per_second": 87.463,
+      "step": 321
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 428,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.455881385704775e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-3/checkpoint-321/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5f0e9113d8062cf85385591e5f5bdf6394f33b566e40e55a23d20c2257d2eb
+size 4984

run-3/checkpoint-428/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-3/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ef4136638d5f8c14a505f363fb67bf0ea3bf62561d0d92e31f430f10708be9
+size 267832560

run-3/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ac164c92741cc677178ff488d9a939f4abc5031dc8b7d67eaa386d1a927303
+size 535727290

run-3/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1548230528900e2ea3ea07a36b9b092b28fe078e2b692580f55902e3f3120762
+size 14308

run-3/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05323038af5df0f0e8b32a1e67be3c17e0157e196e1f7c68bd6819d89cfb1553
+size 1064

run-3/checkpoint-428/special_tokens_map.json

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

run-3/checkpoint-428/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-3/checkpoint-428/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.30530026767951607,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-321",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5614452362060547,
+      "eval_matthews_correlation": 0.26833966259076464,
+      "eval_runtime": 0.6971,
+      "eval_samples_per_second": 1496.255,
+      "eval_steps_per_second": 94.682,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.739422082901001,
+      "eval_matthews_correlation": 0.26077721196619447,
+      "eval_runtime": 0.7344,
+      "eval_samples_per_second": 1420.259,
+      "eval_steps_per_second": 89.873,
+      "step": 214
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.1903438568115234,
+      "eval_matthews_correlation": 0.30530026767951607,
+      "eval_runtime": 0.7546,
+      "eval_samples_per_second": 1382.174,
+      "eval_steps_per_second": 87.463,
+      "step": 321
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3358757495880127,
+      "eval_matthews_correlation": 0.29220209120937635,
+      "eval_runtime": 0.7427,
+      "eval_samples_per_second": 1404.264,
+      "eval_steps_per_second": 88.86,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 428,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.455881385704775e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-3/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5f0e9113d8062cf85385591e5f5bdf6394f33b566e40e55a23d20c2257d2eb
+size 4984

run-4/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-4/checkpoint-107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abae716af60ef08df4cfda8630d61b2a17e55b01951217054670529e3ef70248
+size 267832560

run-4/checkpoint-107/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a69672aa275c3c2a0638b1e4242e2f29f576d518ec4e1c889745a484eb363a
+size 535727290

run-4/checkpoint-107/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19282da19cfd527a861f994c1aa3a26bddb7dd981c662a1369d658da95bb6a3
+size 14308

run-4/checkpoint-107/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26bda9ffb51a7b601a198f593ae23d311175eb9bcbd92524e668b304ed86e7c6
+size 1064

run-4/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-4/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-4/checkpoint-107/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.6111112833023071,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6707,
+      "eval_samples_per_second": 1555.045,
+      "eval_steps_per_second": 98.402,
+      "step": 107
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 321,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.050087494888513e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 24
+  }
+}

run-4/checkpoint-107/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59fc4da2d33b8f536673ffdc9385a7429d46124b8cb2a495dc6969510ec995d
+size 4984

runs/Feb27_13-03-25_5653ffc1374b/events.out.tfevents.1709040500.5653ffc1374b.680.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965252d4340142583639295511674a9658accc5977e9bc22dd4782201291a102
+size 5894

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5f0e9113d8062cf85385591e5f5bdf6394f33b566e40e55a23d20c2257d2eb
+oid sha256:e59fc4da2d33b8f536673ffdc9385a7429d46124b8cb2a495dc6969510ec995d
 size 4984