Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffecd53831e2fda4561907f162811184d1b27cd72a6174a56135df37ba3efaf4
+oid sha256:f6a0cd116856436be14632b63b6b76697e6acbc599abfea55c35256599d029a8
 size 267832560

run-0/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-0/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bfe722d721c6d932e29ac5c4059409cd342d3c82356a4e4e8bb1bca2793f4e
+size 267832560

run-0/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428a21ca8d404c2e0db19307325737922835f8cf0c760a397f495ade58fec50d
+size 535727290

run-0/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bb3527a0370d64408a5726028cdcad94ec1dafbc5ed31492217202db51eab8
+size 14244

run-0/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6a0cae1b963f0dca74f60de52668cd2829353dc23d97ff569193b259ecb47d
+size 1064

run-0/checkpoint-5345/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-5345/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-5345/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": 0.45354879777314566,
+  "best_model_checkpoint": "hw-01-finetuned-cola/run-0/checkpoint-4276",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5345,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.7326435592927605e-06,
+      "loss": 0.5977,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.4506370000262214e-06,
+      "loss": 0.5335,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5340704321861267,
+      "eval_matthews_correlation": 0.36161681105121063,
+      "eval_runtime": 0.7405,
+      "eval_samples_per_second": 1408.534,
+      "eval_steps_per_second": 89.131,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.168630440759683e-06,
+      "loss": 0.4751,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.886623881493144e-06,
+      "loss": 0.4579,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5136641263961792,
+      "eval_matthews_correlation": 0.4491534084057902,
+      "eval_runtime": 0.906,
+      "eval_samples_per_second": 1151.249,
+      "eval_steps_per_second": 72.85,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.6046173222266052e-06,
+      "loss": 0.4286,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.3226107629600667e-06,
+      "loss": 0.4101,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5329485535621643,
+      "eval_matthews_correlation": 0.45115517656589194,
+      "eval_runtime": 0.7978,
+      "eval_samples_per_second": 1307.396,
+      "eval_steps_per_second": 82.731,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.0406042036935279e-06,
+      "loss": 0.3981,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 7.585976444269893e-07,
+      "loss": 0.3845,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5448588728904724,
+      "eval_matthews_correlation": 0.45354879777314566,
+      "eval_runtime": 0.7443,
+      "eval_samples_per_second": 1401.396,
+      "eval_steps_per_second": 88.679,
+      "step": 4276
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 4.765910851604504e-07,
+      "loss": 0.348,
+      "step": 4500
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 1.9458452589391174e-07,
+      "loss": 0.357,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5543220043182373,
+      "eval_matthews_correlation": 0.44836399104702945,
+      "eval_runtime": 0.7343,
+      "eval_samples_per_second": 1420.49,
+      "eval_steps_per_second": 89.887,
+      "step": 5345
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 187932947335440.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.014650118559299e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 16
+  }
+}

run-0/checkpoint-5345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7fe9927effe1f0b016401f7ae93dae94ecab2821cb36372747f5f4e611c428e
+size 4728

run-1/checkpoint-1070/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-1/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1a4c72cac799be0d6f6063588237e1c4d3274add434c35882d6a43bb7160a3
+size 267832560

run-1/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e304d77d78cd52e9a3e862c716d48a3d00f0fcef0eafe3af7fc0622d8a3e4cc8
+size 535727290

run-1/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a7e17283da60c711d8ac1014444f8bdde5a308dcec30aa54c22c235a2583be
+size 14308

run-1/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807a9d9b19995e0b101b0ac58b02e5ee810ebebdab2a549327ec061c50d76e10
+size 1064

run-1/checkpoint-1070/special_tokens_map.json

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

run-1/checkpoint-1070/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-1/checkpoint-1070/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "hw-01-finetuned-cola/run-1/checkpoint-535",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.523832453871098e-07,
+      "loss": 0.6196,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6081321835517883,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7503,
+      "eval_samples_per_second": 1390.123,
+      "eval_steps_per_second": 87.966,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 8.011724066157488e-08,
+      "loss": 0.5922,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5986050963401794,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.4026,
+      "eval_samples_per_second": 743.6,
+      "eval_steps_per_second": 47.054,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 85728657313800.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2246492501126448e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 14
+  }
+}

run-1/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f077c25ca4eb5e8ed1affa47b767b34966c6b1f391060ee6cafd893a4f18997
+size 4728

run-1/checkpoint-535/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-1/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b811699f7f9f7445d7098a2f0dbf36bf944c4d4ff11082276ef4ffe482bf314
+size 267832560

run-1/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380d688ee089e21be4f11956ac8b006dab5139b33bffc494054329d8498fb515
+size 535727290

run-1/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31cab7000d30e634d9632b79d56481dc5afe232091e77ee55a9a3e7281201738
+size 14308

run-1/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121a642ad1591965dbcab32cee044bd1b1270272f8624f41a1249ae9fbd8e0a3
+size 1064

run-1/checkpoint-535/special_tokens_map.json

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

run-1/checkpoint-535/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-1/checkpoint-535/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "hw-01-finetuned-cola/run-1/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.523832453871098e-07,
+      "loss": 0.6196,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6081321835517883,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7503,
+      "eval_samples_per_second": 1390.123,
+      "eval_steps_per_second": 87.966,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 42828365827968.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2246492501126448e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 14
+  }
+}

run-1/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f077c25ca4eb5e8ed1affa47b767b34966c6b1f391060ee6cafd893a4f18997
+size 4728

run-2/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-2/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a0cd116856436be14632b63b6b76697e6acbc599abfea55c35256599d029a8
+size 267832560

run-2/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b020b773d8504d1a099e794cef1451b32d979780cc9807f147e76bdffb3e39a
+size 535727290

run-2/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d397e91a8e27617cdc21beb7fc232f075b50df3e73f064c98f0b19870d0bd7
+size 14308

run-2/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e19d5c6d03bd526a91de8ff6f5944663c9cd62d0492f155ea7a1585bedd5b88
+size 1064

run-2/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-2/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-2/checkpoint-2138/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.4304260866765428,
+  "best_model_checkpoint": "hw-01-finetuned-cola/run-2/checkpoint-2138",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.717583231684137e-06,
+      "loss": 0.5783,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.318734463364544e-06,
+      "loss": 0.5628,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.919885695044952e-06,
+      "loss": 0.5371,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.52103692672536e-06,
+      "loss": 0.5214,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5808761715888977,
+      "eval_matthews_correlation": 0.4304260866765428,
+      "eval_runtime": 0.7545,
+      "eval_samples_per_second": 1382.293,
+      "eval_steps_per_second": 87.47,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 32649074162496.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.1164320000037285e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 26
+  }
+}

run-2/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33df9fa76c45a070b235b52e6deaa801af62492a1cc0e084d107a267b67a3f43
+size 4728

runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703297989.42b18358a534.403.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b4e8d5625fe31c52a2d5068f50c794c680ec420655cbc8dfeeaf057b1265e3c
-size 7039
+oid sha256:aaff3dbc7f8190d0ba9567f988e1a10614386e979d3d828e1c2076dcc42cdb54
+size 7885

runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703298308.42b18358a534.403.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7a04160c42b74ae81d2db5ed2682ca4c7e05e7e97c69d6bcdcad202c02f6db
+size 5626

runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703298389.42b18358a534.403.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b7a43702de137acdc162d56ae73c2fe0445c9cc2211dc4aaa88a455cb77cf2
+size 5407

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7fe9927effe1f0b016401f7ae93dae94ecab2821cb36372747f5f4e611c428e
+oid sha256:33df9fa76c45a070b235b52e6deaa801af62492a1cc0e084d107a267b67a3f43
 size 4728