Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf424fc0057c2849da707d8131b893925272ebb6f46803cacfcfb1e7033be0f9
+oid sha256:cd9c49b56a63c2ecb25ee0bfeff7491d3fb1a4e1c9a86b66868f943fc4964f25
 size 267832560

run-0/checkpoint-1069/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6ba27acebeb3fde8e9fb26902311097ea2fcdb4f967d1df194d7e2f58c92a7
+size 267832560

run-0/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5f6ff8a31522f54050e879180ff9db0ed51ae6b35f35caf55845fd0ac242d7
+size 535727290

run-0/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f285327d32dd43fb14664eec6244cae7a6add8f852e59aab7342e28e7621a7
+size 14308

run-0/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e9ffe5db83bffa71a00abb8db8e2f58e97b9f15b7ef00d4662ecaebc72fef9
+size 1064

run-0/checkpoint-1069/special_tokens_map.json

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

run-0/checkpoint-1069/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-0/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.34550478585347627,
+  "best_model_checkpoint": "andyWuTw/homework001-finetuned-cola/run-0/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.318541216106635e-05,
+      "loss": 0.5792,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8791157372789563e-05,
+      "loss": 0.5392,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5628832578659058,
+      "eval_matthews_correlation": 0.34550478585347627,
+      "eval_runtime": 0.735,
+      "eval_samples_per_second": 1419.139,
+      "eval_steps_per_second": 89.802,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 37815302710080.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.757966694934315e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-0/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0675c2ad8e381cf07385fa5446306204c293fb4f7110c9f599f2cd8d18ca6cf
+size 4792

run-0/checkpoint-2138/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925d626121d5a2b1f08b6a77ac50340c8482fe2bad7ba50c9b65b1656a5304f5
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ef37dcdbbba80d8398d056bf208e44a4289d9d4e838aeb1334fef49824fe87
+size 535727290

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e73da4ef20518531b14e4eb8c3dd8ef29df889fc92ad5019cc805d506dd0fca
+size 14308

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1ae6b7de384b045b8fa3ea5762f5637a8c182e19a60a4d14bf48e9bc82d8a0
+size 1064

run-0/checkpoint-2138/special_tokens_map.json

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

run-0/checkpoint-2138/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-0/checkpoint-2138/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.4357053256431942,
+  "best_model_checkpoint": "andyWuTw/homework001-finetuned-cola/run-0/checkpoint-2138",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.318541216106635e-05,
+      "loss": 0.5792,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8791157372789563e-05,
+      "loss": 0.5392,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5628832578659058,
+      "eval_matthews_correlation": 0.34550478585347627,
+      "eval_runtime": 0.735,
+      "eval_samples_per_second": 1419.139,
+      "eval_steps_per_second": 89.802,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.4396902584512767e-05,
+      "loss": 0.3888,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.000264779623597e-05,
+      "loss": 0.3726,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6155115962028503,
+      "eval_matthews_correlation": 0.4357053256431942,
+      "eval_runtime": 0.7315,
+      "eval_samples_per_second": 1425.748,
+      "eval_steps_per_second": 90.22,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 75070206229752.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.757966694934315e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0675c2ad8e381cf07385fa5446306204c293fb4f7110c9f599f2cd8d18ca6cf
+size 4792

run-0/checkpoint-3207/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb80cabb8f0c38e241ef247af5337ba377918cfda8cd324bc46b364c2153cf1e
+size 267832560

run-0/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d1c1858e6fea27e836fc3f3ae2070830905f756c1c585962d876873fd9979c
+size 535727290

run-0/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15d1ea4aaf399d17c360f87a64d3a27e38f7111b40b8b9d5b564408707362e4
+size 14308

run-0/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a3223472f9275e1a1dbd0d21675d84489d0b4a05d7c0b3d0a4e7e711cae18c
+size 1064

run-0/checkpoint-3207/special_tokens_map.json

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

run-0/checkpoint-3207/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-0/checkpoint-3207/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": 0.4517757807192715,
+  "best_model_checkpoint": "andyWuTw/homework001-finetuned-cola/run-0/checkpoint-3207",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3207,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.318541216106635e-05,
+      "loss": 0.5792,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8791157372789563e-05,
+      "loss": 0.5392,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5628832578659058,
+      "eval_matthews_correlation": 0.34550478585347627,
+      "eval_runtime": 0.735,
+      "eval_samples_per_second": 1419.139,
+      "eval_steps_per_second": 89.802,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.4396902584512767e-05,
+      "loss": 0.3888,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.000264779623597e-05,
+      "loss": 0.3726,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6155115962028503,
+      "eval_matthews_correlation": 0.4357053256431942,
+      "eval_runtime": 0.7315,
+      "eval_samples_per_second": 1425.748,
+      "eval_steps_per_second": 90.22,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.5608393007959178e-05,
+      "loss": 0.2739,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.121413821968238e-05,
+      "loss": 0.237,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8650707006454468,
+      "eval_matthews_correlation": 0.4517757807192715,
+      "eval_runtime": 0.8103,
+      "eval_samples_per_second": 1287.239,
+      "eval_steps_per_second": 81.455,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 113117844338256.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.757966694934315e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-0/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0675c2ad8e381cf07385fa5446306204c293fb4f7110c9f599f2cd8d18ca6cf
+size 4792

run-0/checkpoint-4276/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9c49b56a63c2ecb25ee0bfeff7491d3fb1a4e1c9a86b66868f943fc4964f25
+size 267832560

run-0/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3520af8882a91aea3217256f37f5996acdf16da7d312dbbe6a74563517dbd10a
+size 535727290

run-0/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2718ab4d917c18466c63396382a14604ec96d984e9c6a0761ff5602b37b975f
+size 14308

run-0/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a5701427526b94822192467dbb7c0e09a28b639440840ecbd9d497b89e7ee2
+size 1064

run-0/checkpoint-4276/special_tokens_map.json

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

run-0/checkpoint-4276/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-0/checkpoint-4276/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.4706974024636893,
+  "best_model_checkpoint": "andyWuTw/homework001-finetuned-cola/run-0/checkpoint-4276",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.318541216106635e-05,
+      "loss": 0.5792,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8791157372789563e-05,
+      "loss": 0.5392,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5628832578659058,
+      "eval_matthews_correlation": 0.34550478585347627,
+      "eval_runtime": 0.735,
+      "eval_samples_per_second": 1419.139,
+      "eval_steps_per_second": 89.802,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.4396902584512767e-05,
+      "loss": 0.3888,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.000264779623597e-05,
+      "loss": 0.3726,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6155115962028503,
+      "eval_matthews_correlation": 0.4357053256431942,
+      "eval_runtime": 0.7315,
+      "eval_samples_per_second": 1425.748,
+      "eval_steps_per_second": 90.22,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.5608393007959178e-05,
+      "loss": 0.2739,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.121413821968238e-05,
+      "loss": 0.237,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8650707006454468,
+      "eval_matthews_correlation": 0.4517757807192715,
+      "eval_runtime": 0.8103,
+      "eval_samples_per_second": 1287.239,
+      "eval_steps_per_second": 81.455,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 6.819883431405586e-06,
+      "loss": 0.1883,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 2.425628643128791e-06,
+      "loss": 0.1545,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0655596256256104,
+      "eval_matthews_correlation": 0.4706974024636893,
+      "eval_runtime": 0.7259,
+      "eval_samples_per_second": 1436.8,
+      "eval_steps_per_second": 90.919,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 150809993763648.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.757966694934315e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-0/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0675c2ad8e381cf07385fa5446306204c293fb4f7110c9f599f2cd8d18ca6cf
+size 4792

runs/Dec23_02-16-37_5c7585257882/events.out.tfevents.1703298015.5c7585257882.414.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b51b5cb058e8cd82fe1b3fc3251dcf4367c1789dec9ffef753c4fa165814400c
+size 7289

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c06298ea2251568983c8ab84194bc9649cedd81d609750f983e7a77c0d684e
+oid sha256:a0675c2ad8e381cf07385fa5446306204c293fb4f7110c9f599f2cd8d18ca6cf
 size 4792