Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc24a9b3b529867ce40e8ad3ada784dfb746737eae98fd2a707784a055b17ff
+oid sha256:ad205eb70a581ad8b5fb7fdef160c29c51ccc7322fb925c298680a6d45ea54c0
 size 437958648

run-2/checkpoint-108/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36df94b40c56fcddc85fdb5d52b6637cfc261a095f0785345dbf0088e1e1a03
+size 437958648

run-2/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb8c4cdb72480e1110ecabf43dc7b3337be0a67522f5a8f0351a4ecf70a9dd5
+size 876038394

run-2/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87cdd35c87e07c4aeb29b0880036742129084a96ee9fb08bd7175a05681326fe
+size 14244

run-2/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9886f252a006785337b73843fffa1abfbf23b4e444a322b78bd4ae9d7a673e13
+size 1064

run-2/checkpoint-108/special_tokens_map.json

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

run-2/checkpoint-108/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-108/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-108",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6150018572807312,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3372,
+      "eval_samples_per_second": 779.988,
+      "eval_steps_per_second": 49.357,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6089003086090088,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.4244,
+      "eval_samples_per_second": 732.255,
+      "eval_steps_per_second": 46.336,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7854323243021316e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 5
+  }
+}

run-2/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fdfb014d588afbdeccbaf5fda2c374059ca48b248507655f1c57246bc4731e1
+size 4920

run-2/checkpoint-162/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-162/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b54798c78cf39f05cf50fa788dd021b9ad7add92d0f06c58ba8627e18e74e9
+size 437958648

run-2/checkpoint-162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6f5dbccc3359308165d8c3b12ffb1342d817b88ba6fab7f876fcf24d758bd1
+size 876038394

run-2/checkpoint-162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483eee96cb3e2c0dacabf009de1e51e32d8a86a481ff239e4d0787086a07e443
+size 14244

run-2/checkpoint-162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effdba7a30169524a7267e94b80f18cac6bf5ea76fe466745108823a5678d46f
+size 1064

run-2/checkpoint-162/special_tokens_map.json

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

run-2/checkpoint-162/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-162/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-108",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 162,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6150018572807312,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3372,
+      "eval_samples_per_second": 779.988,
+      "eval_steps_per_second": 49.357,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6089003086090088,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.4244,
+      "eval_samples_per_second": 732.255,
+      "eval_steps_per_second": 46.336,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6012548208236694,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.4207,
+      "eval_samples_per_second": 734.141,
+      "eval_steps_per_second": 46.456,
+      "step": 162
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7854323243021316e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 5
+  }
+}

run-2/checkpoint-162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fdfb014d588afbdeccbaf5fda2c374059ca48b248507655f1c57246bc4731e1
+size 4920

run-2/checkpoint-216/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a241eac726a9a46dd541c1ba75a4402ec03a152257cc3b15e6009a133f4003f3
+size 437958648

run-2/checkpoint-216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4558c559411b39c5dffa7d56e254210cdf6eaa798024d42aec08da23b49f669
+size 876038394

run-2/checkpoint-216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a005c9efead36f43708fc69d803c2c0aa9d6e3af34c881adadee9ab7e8f2a5ea
+size 14244

run-2/checkpoint-216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53cdef3adfe1184711d3a09857577ba9dc6ae63d25476fc50f0f565554a9ba3
+size 1064

run-2/checkpoint-216/special_tokens_map.json

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

run-2/checkpoint-216/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-216/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-108",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6150018572807312,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3372,
+      "eval_samples_per_second": 779.988,
+      "eval_steps_per_second": 49.357,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6089003086090088,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.4244,
+      "eval_samples_per_second": 732.255,
+      "eval_steps_per_second": 46.336,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6012548208236694,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.4207,
+      "eval_samples_per_second": 734.141,
+      "eval_steps_per_second": 46.456,
+      "step": 162
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.598237156867981,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.4427,
+      "eval_samples_per_second": 722.941,
+      "eval_steps_per_second": 45.747,
+      "step": 216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7854323243021316e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 5
+  }
+}

run-2/checkpoint-216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fdfb014d588afbdeccbaf5fda2c374059ca48b248507655f1c57246bc4731e1
+size 4920

run-3/checkpoint-54/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad205eb70a581ad8b5fb7fdef160c29c51ccc7322fb925c298680a6d45ea54c0
+size 437958648

run-3/checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69c87de4a22389003fc531f17e26b0497d7341ff972eb8cf703fec968ff7f77
+size 876038394

run-3/checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190ed7e16b7dd169c6b481d5991795f911c91f8173dc280bbfdc780cdff13754
+size 14244

run-3/checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:616a72f3abb3b56a7b99fb5738365e66552337efc9458dcc66d9b099d03a2d3d
+size 1064

run-3/checkpoint-54/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-54/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-54/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.008874995467744727,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-3/checkpoint-54",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6695083975791931,
+      "eval_matthews_correlation": 0.008874995467744727,
+      "eval_runtime": 1.3066,
+      "eval_samples_per_second": 798.284,
+      "eval_steps_per_second": 50.515,
+      "step": 54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.169206507177718e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 38
+  }
+}

run-3/checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681009adf129985f1b550e6f1e9a7faeef8564fd524685bfc7430d9426ac9489
+size 4920

runs/Mar05_08-21-06_22d65867544c/events.out.tfevents.1709627420.22d65867544c.687.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ca2f06986544df95a937834ab3b673fd1628a091c7ba9454c7b997bb9e6bd1
+size 5983

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fdfb014d588afbdeccbaf5fda2c374059ca48b248507655f1c57246bc4731e1
+oid sha256:681009adf129985f1b550e6f1e9a7faeef8564fd524685bfc7430d9426ac9489
 size 4920