Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1004d21378360b29a5dade81de51f0e4d50794821f0554f7f73c2a1f4ad9ce
+oid sha256:61a9f0d1597105b2ae2c4068c002b554e7fab84818ec9eb58143a840cbff4794
 size 267832560

run-0/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": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b83b744bd34547e593e587e47993f9deff931003bb95b350c7af99a302309e
+size 267832560

run-0/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd73d3b70d45a4e56ef2f8c4255ee4612a2e3d321b98349093187b8934e7010
+size 535727290

run-0/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add3dd6d8b9f04b2da0b21b3141bd6c35e192c09abf0ae08675ad972ac1c8384
+size 14244

run-0/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a69ebdcb9cbad7bddba9d2f7a2c470c830a7cf12d53a5b8cd958b53b2ab6cf
+size 1064

run-0/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-0/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-0/checkpoint-1070/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.49357249556059846,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1070",
+  "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,
+      "grad_norm": 4.838195323944092,
+      "learning_rate": 2.542737154981418e-05,
+      "loss": 0.5194,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.49024975299835205,
+      "eval_matthews_correlation": 0.43262718467553657,
+      "eval_runtime": 2.2476,
+      "eval_samples_per_second": 464.059,
+      "eval_steps_per_second": 29.365,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 5.74407434463501,
+      "learning_rate": 1.3921773563472922e-05,
+      "loss": 0.3182,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5491473078727722,
+      "eval_matthews_correlation": 0.49357249556059846,
+      "eval_runtime": 1.7076,
+      "eval_samples_per_second": 610.785,
+      "eval_steps_per_second": 38.65,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 86031883468536.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.693296953615544e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 9
+  }
+}

run-0/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3addc0a08604c4a6c2673cf97006fa11946224a2547ad12bbf16d166666cf45b
+size 4984

run-0/checkpoint-1605/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": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4bdaf7943b482689de3f0a447349d070a284586c5f04194b5fe1d8e80b01b0e
+size 267832560

run-0/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e007842fbddf48cd55037a20ff83918cc3f87db180cc83d12596992737cd5665
+size 535727290

run-0/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077934fbf5a5d9d1e451ef6fa416a906729b6234eb30b1dc44ec361bd9ba1274
+size 14244

run-0/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc3857d9eb77942f26f91c9977d164c41ad477679e8f359e4d4de0d4942451c
+size 1064

run-0/checkpoint-1605/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-1605/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-1605/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.5039642659976749,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1605",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1605,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.838195323944092,
+      "learning_rate": 2.542737154981418e-05,
+      "loss": 0.5194,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.49024975299835205,
+      "eval_matthews_correlation": 0.43262718467553657,
+      "eval_runtime": 2.2476,
+      "eval_samples_per_second": 464.059,
+      "eval_steps_per_second": 29.365,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 5.74407434463501,
+      "learning_rate": 1.3921773563472922e-05,
+      "loss": 0.3182,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5491473078727722,
+      "eval_matthews_correlation": 0.49357249556059846,
+      "eval_runtime": 1.7076,
+      "eval_samples_per_second": 610.785,
+      "eval_steps_per_second": 38.65,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 18.21695899963379,
+      "learning_rate": 2.416175577131664e-06,
+      "loss": 0.1905,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7505267858505249,
+      "eval_matthews_correlation": 0.5039642659976749,
+      "eval_runtime": 0.7556,
+      "eval_samples_per_second": 1380.405,
+      "eval_steps_per_second": 87.351,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 128908113493284.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.693296953615544e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 9
+  }
+}

run-0/checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3addc0a08604c4a6c2673cf97006fa11946224a2547ad12bbf16d166666cf45b
+size 4984

run-1/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": "4.38.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d46842c11f7003319cc5a53597fcf099c5f2d69350478889e45c7bfa9f5d68
+size 267832560

run-1/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6553afa883babb9bfc4d8aa0f55d2ad1f8a2ae31e9f11804d55282de8db5cf1
+size 535727290

run-1/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22d1498697868d4fd51fedc2d243dfeb0c202fd49e378d2e958096437df1b02
+size 14244

run-1/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abec49b72941ac05681ffdea503b4983b2576df3a7538bc1f229b8bd74e024dc
+size 1064

run-1/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-1/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-1/checkpoint-2138/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.15833456940979748,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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,
+      "grad_norm": 2.2052836418151855,
+      "learning_rate": 5.527461334920752e-05,
+      "loss": 0.6278,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.5090547800064087,
+      "learning_rate": 5.1842260309639244e-05,
+      "loss": 0.6192,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.86550760269165,
+      "learning_rate": 4.840990727007098e-05,
+      "loss": 0.6103,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.385833740234375,
+      "learning_rate": 4.49775542305027e-05,
+      "loss": 0.5852,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6027922034263611,
+      "eval_matthews_correlation": 0.15833456940979748,
+      "eval_runtime": 0.7524,
+      "eval_samples_per_second": 1386.172,
+      "eval_steps_per_second": 87.716,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 32633550639216.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.87069663887758e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-1/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aee351340990176090794d80423bc66843abb9d835babac4ae2c2cf2a474913
+size 4984

run-1/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": "4.38.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a9f0d1597105b2ae2c4068c002b554e7fab84818ec9eb58143a840cbff4794
+size 267832560

run-1/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b7f500638b0c8d1d418712f5fd073a635afc3ca31fd2acdedc668af0877953
+size 535727290

run-1/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f61a246d0a6581c82fe4876987da0fa2112a41aa062420f2d0b74fe07b53d3b1
+size 14244

run-1/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a06709d34c11373eed98ab1a6efdbf7e4f4ea58d126782bc9a4ccfbf9395bc3f
+size 1064

run-1/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-1/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-1/checkpoint-4276/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.35221451726824415,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.2052836418151855,
+      "learning_rate": 5.527461334920752e-05,
+      "loss": 0.6278,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.5090547800064087,
+      "learning_rate": 5.1842260309639244e-05,
+      "loss": 0.6192,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.86550760269165,
+      "learning_rate": 4.840990727007098e-05,
+      "loss": 0.6103,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.385833740234375,
+      "learning_rate": 4.49775542305027e-05,
+      "loss": 0.5852,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6027922034263611,
+      "eval_matthews_correlation": 0.15833456940979748,
+      "eval_runtime": 0.7524,
+      "eval_samples_per_second": 1386.172,
+      "eval_steps_per_second": 87.716,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 23.48023796081543,
+      "learning_rate": 4.154520119093442e-05,
+      "loss": 0.5672,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 34.38399124145508,
+      "learning_rate": 3.811284815136614e-05,
+      "loss": 0.5388,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 15.397554397583008,
+      "learning_rate": 3.468049511179787e-05,
+      "loss": 0.5675,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.596796035766602,
+      "learning_rate": 3.124814207222959e-05,
+      "loss": 0.5658,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7189152836799622,
+      "eval_matthews_correlation": 0.35221451726824415,
+      "eval_runtime": 0.816,
+      "eval_samples_per_second": 1278.13,
+      "eval_steps_per_second": 80.879,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 65223117962472.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.87069663887758e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-1/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aee351340990176090794d80423bc66843abb9d835babac4ae2c2cf2a474913
+size 4984

runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709519746.78dd22f13cdf.294.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7155ef4eed6918eece0b0100aad2d7ba1bc9ea6eac9cea18db2135bd5b09727
-size 5106
+oid sha256:1df6d7618d4451d701aa47e48ba84ce991f3dea55a7ac2a3ae57393c67b8e45d
+size 6552

runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709519889.78dd22f13cdf.294.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf73eb11ca7057d9a3688f6d5c8d1d05856b56c17a50dc07887e367083dec33
+size 7128

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3addc0a08604c4a6c2673cf97006fa11946224a2547ad12bbf16d166666cf45b
+oid sha256:0aee351340990176090794d80423bc66843abb9d835babac4ae2c2cf2a474913
 size 4984