Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d747f47ecdd25c1b091c915b2013ee4bdb18de77acfb25abbd5ceb5b8190e40a
+oid sha256:130dba37b199d9e6051dc08c45083f897acbfbf9abdae1dcc44ec4481dadb9db
 size 267832560

run-3/checkpoint-1340/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-3/checkpoint-1340/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d747f47ecdd25c1b091c915b2013ee4bdb18de77acfb25abbd5ceb5b8190e40a
+size 267832560

run-3/checkpoint-1340/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8db01c751efac500f08a24e16914a91dbdce92019ad52d15d91dfd5d7584ba0
+size 535727290

run-3/checkpoint-1340/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a367057fa625efca7b007ebc224a72beaeda0a326d052c2b1c59bbb2ce11a258
+size 14308

run-3/checkpoint-1340/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79985562ad393fbf89629cbfe8b1e89fb5bf880b8c8c5f3a52807441945bc97e
+size 1064

run-3/checkpoint-1340/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-1340/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-3/checkpoint-1340/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.5104242686414723,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1072",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1340,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.49783048033714294,
+      "eval_matthews_correlation": 0.4111094454070522,
+      "eval_runtime": 0.7234,
+      "eval_samples_per_second": 1441.791,
+      "eval_steps_per_second": 91.235,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 7.123299677400847e-06,
+      "loss": 0.4894,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5266438126564026,
+      "eval_matthews_correlation": 0.44722803398940786,
+      "eval_runtime": 0.7661,
+      "eval_samples_per_second": 1361.434,
+      "eval_steps_per_second": 86.15,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.4729432761669159,
+      "eval_matthews_correlation": 0.5011490576561073,
+      "eval_runtime": 0.7179,
+      "eval_samples_per_second": 1452.841,
+      "eval_steps_per_second": 91.934,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 2.8832403456146286e-06,
+      "loss": 0.3212,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5100820064544678,
+      "eval_matthews_correlation": 0.5104242686414723,
+      "eval_runtime": 0.8168,
+      "eval_samples_per_second": 1276.879,
+      "eval_steps_per_second": 80.8,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5556281208992004,
+      "eval_matthews_correlation": 0.5075813582663956,
+      "eval_runtime": 0.7329,
+      "eval_samples_per_second": 1423.103,
+      "eval_steps_per_second": 90.053,
+      "step": 1340
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 190621621567536.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1363359009187065e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 20
+  }
+}

run-3/checkpoint-1340/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79499fe7d2034d8df2f65fc54dbfcd286a83e4c8aaa162c7b786314e484018d
+size 4792

run-4/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-4/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54bf21d3622a25d34291411d31e0a2b44757e19807375937801bd937a3d071e
+size 267832560

run-4/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06074d2393665d7f539d9fe21020f1bcd453906eee3fd2382db0237650c40470
+size 535727290

run-4/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55947eba1b2608c8969193d46e23df5c532e3a1b82fe3cbc92a214c25baa39ac
+size 14308

run-4/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b51e84535fc6c64d130b186978465cefc4948fe9cdec410cb6f6e342d2eb1c7
+size 1064

run-4/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-4/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-4/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.4611631351812362,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 2.0681209971615274e-05,
+      "loss": 0.5488,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8546926176814934e-05,
+      "loss": 0.498,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48384082317352295,
+      "eval_matthews_correlation": 0.4611631351812362,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.127,
+      "eval_steps_per_second": 88.092,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 37784255663520.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.281549376641561e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 24
+  }
+}

run-4/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc878cb8d07fea1f5c4cd27f162cb2669e0bb6636b584389e9be49e2633f0a30
+size 4792

run-4/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-4/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1e587d38d1e3ccf137f4531ddf4f3640e77b7ee9377468df645e78f14179e1
+size 267832560

run-4/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e31547bc5751805fe8c8910f6ce01e42c20d9e0dd775956d13af10f921eb33
+size 535727290

run-4/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ecee28ec0d36e12d2a69d8440b854f0bb324c6899b79460571e75a4f0858ec9
+size 14308

run-4/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90cd6966c4f7460f51e655f7278e65a3ecaa622e5258fd6643d15063082fcb18
+size 1064

run-4/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-4/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-4/checkpoint-2138/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.543909089281463,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 2.0681209971615274e-05,
+      "loss": 0.5488,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8546926176814934e-05,
+      "loss": 0.498,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48384082317352295,
+      "eval_matthews_correlation": 0.4611631351812362,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.127,
+      "eval_steps_per_second": 88.092,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.6412642382014598e-05,
+      "loss": 0.3532,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.4278358587214258e-05,
+      "loss": 0.354,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5868804454803467,
+      "eval_matthews_correlation": 0.543909089281463,
+      "eval_runtime": 0.7926,
+      "eval_samples_per_second": 1315.987,
+      "eval_steps_per_second": 83.274,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 75492963513744.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.281549376641561e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 24
+  }
+}

run-4/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc878cb8d07fea1f5c4cd27f162cb2669e0bb6636b584389e9be49e2633f0a30
+size 4792

run-4/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-4/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130dba37b199d9e6051dc08c45083f897acbfbf9abdae1dcc44ec4481dadb9db
+size 267832560

run-4/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76bfd6e3894be0e9b95fe5540a116da72872f70d49ac3593612e4a1353572d9b
+size 535727290

run-4/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0454df12f7e6e534df8ddd0ed9a1da75a9f811400d613d259d1ab204e2a0b08f
+size 14308

run-4/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7344459526efeb12c798a94ef1337126880f1f0818d641953eb94d7ac13bc2c3
+size 1064

run-4/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-4/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-4/checkpoint-3207/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": 0.543909089281463,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-2138",
+  "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": 2.0681209971615274e-05,
+      "loss": 0.5488,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8546926176814934e-05,
+      "loss": 0.498,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48384082317352295,
+      "eval_matthews_correlation": 0.4611631351812362,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.127,
+      "eval_steps_per_second": 88.092,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.6412642382014598e-05,
+      "loss": 0.3532,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.4278358587214258e-05,
+      "loss": 0.354,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5868804454803467,
+      "eval_matthews_correlation": 0.543909089281463,
+      "eval_runtime": 0.7926,
+      "eval_samples_per_second": 1315.987,
+      "eval_steps_per_second": 83.274,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.214407479241392e-05,
+      "loss": 0.2699,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.0009790997613584e-05,
+      "loss": 0.2462,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7930343747138977,
+      "eval_matthews_correlation": 0.5340667882909217,
+      "eval_runtime": 0.7474,
+      "eval_samples_per_second": 1395.496,
+      "eval_steps_per_second": 88.306,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 113223145571172.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.281549376641561e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 24
+  }
+}

run-4/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc878cb8d07fea1f5c4cd27f162cb2669e0bb6636b584389e9be49e2633f0a30
+size 4792

runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298708.067bf7a71e5c.178.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c86fcfd83947acebf571dd93ee7eeb9e28a3aaece7652c2fb6d9674b4a632e8
+size 7101

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b79499fe7d2034d8df2f65fc54dbfcd286a83e4c8aaa162c7b786314e484018d
+oid sha256:dc878cb8d07fea1f5c4cd27f162cb2669e0bb6636b584389e9be49e2633f0a30
 size 4792