Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3070b68af2b5b1af658dc1e2a6e3be8ea425f467e86eefc12039256ee87529fe
+oid sha256:74ca4ddd96bc4a4a32dd8d658aac57aca32d84a5376b2a923e3df8b458d6b88c
 size 437958648

run-4/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-4/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd85a99a8bf17e72b62f621784fc540038ad73a8cb0cdbd5105b818ccc2b13b
+size 437958648

run-4/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb3b43e431583a09fec7e22ac469ab724f716b8935e6a8a727b7eeb04545d0c
+size 876038394

run-4/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9390756cd0ccbb61d29a3cdf4de2e5bd0406795934e6b32bd1a95aa46b3b9e12
+size 14308

run-4/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bc84f5f881d930a829405cdd92258215f0571c5228e3187f4a0df3c764c94d
+size 1064

run-4/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-4/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-4/checkpoint-108/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-4/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": 0.6218078136444092,
+      "eval_matthews_correlation": 0.0437601222642778,
+      "eval_runtime": 1.3199,
+      "eval_samples_per_second": 790.222,
+      "eval_steps_per_second": 50.004,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6049550771713257,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 2.1277,
+      "eval_samples_per_second": 490.205,
+      "eval_steps_per_second": 31.02,
+      "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": 3.3551737277474504e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 26
+  }
+}

run-4/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ee2bfb29153f1a6057106ee13c97468757a2f384827dbea67c524b1adfc6bd
+size 4920

run-4/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-4/checkpoint-162/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42277ea7f8daa6eec6061f252d55179c5bd5940562845f538ea2024f6168aed5
+size 437958648

run-4/checkpoint-162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc47b985b6a203b4ac4eb78ea7b5d1bac15dcb24179d8e1b10086fe94dcb56c
+size 876038394

run-4/checkpoint-162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756bf90f9ef88927b7968a25d2b1e55769006361d21a16660508cf47499ebaf1
+size 14308

run-4/checkpoint-162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56bc3e864b551287cff8faab05f88f25e7edfeca115ee63136eb2b152bac2cb
+size 1064

run-4/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-4/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-4/checkpoint-162/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-4/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": 0.6218078136444092,
+      "eval_matthews_correlation": 0.0437601222642778,
+      "eval_runtime": 1.3199,
+      "eval_samples_per_second": 790.222,
+      "eval_steps_per_second": 50.004,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6049550771713257,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 2.1277,
+      "eval_samples_per_second": 490.205,
+      "eval_steps_per_second": 31.02,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6000790596008301,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.7923,
+      "eval_samples_per_second": 581.934,
+      "eval_steps_per_second": 36.824,
+      "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": 3.3551737277474504e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 26
+  }
+}

run-4/checkpoint-162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ee2bfb29153f1a6057106ee13c97468757a2f384827dbea67c524b1adfc6bd
+size 4920

run-4/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-4/checkpoint-216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e359c5126b04fc3f25208d1048922024e0a44a95a8d0a7f4c4924ebb24fe5ad2
+size 437958648

run-4/checkpoint-216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39458ede157809bd3caa741036a839507ede55b4127ed4fc932729d673ca6fc6
+size 876038394

run-4/checkpoint-216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59492816dfb9dd3d0774f42b3fe91114d6338b0e30e9ac611c459ec6b4679975
+size 14308

run-4/checkpoint-216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9051cc34347444b44954b2b6e32598b58cc3e800cfc1f51b877a5cdb0abbbed
+size 1064

run-4/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-4/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-4/checkpoint-216/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-4/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": 0.6218078136444092,
+      "eval_matthews_correlation": 0.0437601222642778,
+      "eval_runtime": 1.3199,
+      "eval_samples_per_second": 790.222,
+      "eval_steps_per_second": 50.004,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6049550771713257,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 2.1277,
+      "eval_samples_per_second": 490.205,
+      "eval_steps_per_second": 31.02,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6000790596008301,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.7923,
+      "eval_samples_per_second": 581.934,
+      "eval_steps_per_second": 36.824,
+      "step": 162
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5976410508155823,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.3836,
+      "eval_samples_per_second": 753.82,
+      "eval_steps_per_second": 47.701,
+      "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": 3.3551737277474504e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 26
+  }
+}

run-4/checkpoint-216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ee2bfb29153f1a6057106ee13c97468757a2f384827dbea67c524b1adfc6bd
+size 4920

runs/Mar05_08-21-06_22d65867544c/events.out.tfevents.1709627764.22d65867544c.687.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93673edc2be9f8ac5a8530b42ec45bf39a4a90734515d6667774111b8fb1da54
+size 6410