Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d8886c13e2e7cab38293cb4da8a76682411dd708712c6378a0b30e5abcb253c
+oid sha256:6b2c7864e835e5a500264357d26af36d443546e26d614c0395d14c3fdf53f436
 size 267832560

run-7/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-7/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b9f57d9925d43f0b4928601b0fafe1acc17c229f4ba3e493681af33ed70e6a
+size 267832560

run-7/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08bcf15aa537d195d23250d666b917d52b5dc5e169e2767f37ea4ced7f0cf672
+size 535727290

run-7/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5934211ece6b14eb02787d53d875e3c423d05c7db7bd2be02bb4ae0865ed93
+size 14244

run-7/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ab62452cfef71832ee38f21f126660605e9bf16fbf0368b6c6f8e0271375e97
+size 1064

run-7/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-7/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-7/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.43428613653509085,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/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": 2.883378108768492e-05,
+      "loss": 0.5687,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.5858158684415064e-05,
+      "loss": 0.4948,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4758210778236389,
+      "eval_matthews_correlation": 0.43428613653509085,
+      "eval_runtime": 0.7527,
+      "eval_samples_per_second": 1385.607,
+      "eval_steps_per_second": 87.68,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 37492413425856.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.180940349095478e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 22
+  }
+}

run-7/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc332e2dc673bba8b4fceae3f6f1ee2e0a6b02c637b78490c5d9c75d7324a98
+size 4792

run-7/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-7/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d94ae14393951299da2a577e744b0a27fad595923f6467230cff9708a1f162ba
+size 267832560

run-7/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e452e2d27ac1da8a3d0f169900b3bb15543bc54272f6c2742d453105fc61c7
+size 535727290

run-7/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae1aa2062f4b4a2ea84979ec45aa9ee3abc1d7fea86c0459d06a26e84e894f2
+size 14244

run-7/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef07c981d9401b9a759f862a4bc7e7d71b96f467d5544ef409ee7d8fc733621
+size 1064

run-7/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-7/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-7/checkpoint-2138/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.5102489493078572,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/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": 2.883378108768492e-05,
+      "loss": 0.5687,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.5858158684415064e-05,
+      "loss": 0.4948,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4758210778236389,
+      "eval_matthews_correlation": 0.43428613653509085,
+      "eval_runtime": 0.7527,
+      "eval_samples_per_second": 1385.607,
+      "eval_steps_per_second": 87.68,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.2882536281145206e-05,
+      "loss": 0.3622,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.9906913877875348e-05,
+      "loss": 0.344,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6103293895721436,
+      "eval_matthews_correlation": 0.5102489493078572,
+      "eval_runtime": 0.8162,
+      "eval_samples_per_second": 1277.866,
+      "eval_steps_per_second": 80.862,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 75192065887500.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.180940349095478e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 22
+  }
+}

run-7/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc332e2dc673bba8b4fceae3f6f1ee2e0a6b02c637b78490c5d9c75d7324a98
+size 4792

run-7/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-7/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59827278566715fd4de387540b455b30d5f33e21f633647124a286315d0c0c40
+size 267832560

run-7/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6542beefc9a703e81459b02b81a20faa810ca8ecd7e1db1cd18c99dba514472d
+size 535727290

run-7/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f71f4196abc5499cdd5866d0dca31e403587c663f11c0e7ff621e82cc1681b
+size 14244

run-7/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32749ffd3e31e5e6eb752842d12fd0d5554410bcede08ab3ee4e7d006f4ae88
+size 1064

run-7/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-7/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-7/checkpoint-3207/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": 0.5396051449500585,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/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": 2.883378108768492e-05,
+      "loss": 0.5687,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.5858158684415064e-05,
+      "loss": 0.4948,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4758210778236389,
+      "eval_matthews_correlation": 0.43428613653509085,
+      "eval_runtime": 0.7527,
+      "eval_samples_per_second": 1385.607,
+      "eval_steps_per_second": 87.68,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.2882536281145206e-05,
+      "loss": 0.3622,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.9906913877875348e-05,
+      "loss": 0.344,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6103293895721436,
+      "eval_matthews_correlation": 0.5102489493078572,
+      "eval_runtime": 0.8162,
+      "eval_samples_per_second": 1277.866,
+      "eval_steps_per_second": 80.862,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.693129147460549e-05,
+      "loss": 0.2557,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.3955669071335632e-05,
+      "loss": 0.2381,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8707840442657471,
+      "eval_matthews_correlation": 0.5396051449500585,
+      "eval_runtime": 0.7552,
+      "eval_samples_per_second": 1381.062,
+      "eval_steps_per_second": 87.392,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 112782018784632.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.180940349095478e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 22
+  }
+}

run-7/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc332e2dc673bba8b4fceae3f6f1ee2e0a6b02c637b78490c5d9c75d7324a98
+size 4792

run-7/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-7/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6c0977082d617f2b5be18e19c43c60f55162d07d454fcedc6341890a387f24
+size 267832560

run-7/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfce1ffe9f8ac112338026d792d7c75321a40348c745a0fb05c24863908faa4
+size 535727290

run-7/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a1b9c257b3496192c75586eff383f84f98d0570f20022e955efdb6b237752a7
+size 14244

run-7/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ed59be721d9293d899eab2cade8d54416dbf6bd9d90957e784f783af822614
+size 1064

run-7/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-7/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-7/checkpoint-4276/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.5396051449500585,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-3207",
+  "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": 2.883378108768492e-05,
+      "loss": 0.5687,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.5858158684415064e-05,
+      "loss": 0.4948,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4758210778236389,
+      "eval_matthews_correlation": 0.43428613653509085,
+      "eval_runtime": 0.7527,
+      "eval_samples_per_second": 1385.607,
+      "eval_steps_per_second": 87.68,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.2882536281145206e-05,
+      "loss": 0.3622,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.9906913877875348e-05,
+      "loss": 0.344,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6103293895721436,
+      "eval_matthews_correlation": 0.5102489493078572,
+      "eval_runtime": 0.8162,
+      "eval_samples_per_second": 1277.866,
+      "eval_steps_per_second": 80.862,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.693129147460549e-05,
+      "loss": 0.2557,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.3955669071335632e-05,
+      "loss": 0.2381,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8707840442657471,
+      "eval_matthews_correlation": 0.5396051449500585,
+      "eval_runtime": 0.7552,
+      "eval_samples_per_second": 1381.062,
+      "eval_steps_per_second": 87.392,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.0980046668065774e-05,
+      "loss": 0.181,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 8.004424264795918e-06,
+      "loss": 0.1475,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.1052277088165283,
+      "eval_matthews_correlation": 0.47860504193113135,
+      "eval_runtime": 0.7999,
+      "eval_samples_per_second": 1303.971,
+      "eval_steps_per_second": 82.514,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 150623970209676.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.180940349095478e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 22
+  }
+}

run-7/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc332e2dc673bba8b4fceae3f6f1ee2e0a6b02c637b78490c5d9c75d7324a98
+size 4792

run-7/checkpoint-5345/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-7/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88556b85c6caf75f542737de536297e9d70d671c9118b7a8305f703dfe5032c1
+size 267832560

run-7/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5efaf833f887f3af4f2c71fcc444fab63eb231c3030f561d4e1f11fcc958ecb
+size 535727290

run-7/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5bc162aa935c4692443ad848bf2ae6387ff39a90a1da47df276ce20a7c71043
+size 14244

run-7/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75477ce2349cfb68587b111734e4d5fccc47f8950593339b9589fa5cd26b6c84
+size 1064