Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ece9257eae5f80e7eefc99c741b9b50c7f0f5258508f7b5a30317f034a7ccee
+oid sha256:2fa786a4c8e38cceeda6cfea8b92771a71615edb332838c173c4826c08110269
 size 267832560

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": "4.44.0",
+  "vocab_size": 30522
+}

run-7/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fae74307ca84d68b72e0638ccfc81a28d11667bb88fe9e3f8842d8e5ef6e404
+size 267832560

run-7/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf106b1bc663646ed86d4f58a8b693d0d7e86737322b3f54829373bda74bc75c
+size 535727290

run-7/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15edfcee456ae260a4a48cfdfcb48a97944abb898b4890c7b91f27117962b47
+size 14244

run-7/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19fa7e245434973deb0cff71260d434a0c331c53a023b86b0a9c7ef1e934c8dc
+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 +1,107 @@
+{
+  "best_metric": 0.5298831429205758,
+  "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": 0.4677268475210477,
+      "grad_norm": 12.974456787109375,
+      "learning_rate": 1.1101348047567246e-05,
+      "loss": 0.5482,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 6.763242721557617,
+      "learning_rate": 9.955698094257931e-06,
+      "loss": 0.4949,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.47264614701271057,
+      "eval_matthews_correlation": 0.46472372045336796,
+      "eval_runtime": 0.7997,
+      "eval_samples_per_second": 1304.217,
+      "eval_steps_per_second": 82.53,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 21.93242835998535,
+      "learning_rate": 8.810048140948619e-06,
+      "loss": 0.3822,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 23.08902359008789,
+      "learning_rate": 7.664398187639304e-06,
+      "loss": 0.3651,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5118151903152466,
+      "eval_matthews_correlation": 0.5238946707778435,
+      "eval_runtime": 0.7256,
+      "eval_samples_per_second": 1437.525,
+      "eval_steps_per_second": 90.965,
+      "step": 2138
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 0.19134408235549927,
+      "learning_rate": 6.5187482343299915e-06,
+      "loss": 0.2818,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 25.71369743347168,
+      "learning_rate": 5.373098281020679e-06,
+      "loss": 0.2996,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.739141583442688,
+      "eval_matthews_correlation": 0.5298831429205758,
+      "eval_runtime": 0.7927,
+      "eval_samples_per_second": 1315.739,
+      "eval_steps_per_second": 83.259,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 220519927404816.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2246998000876558e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 6
+  }
+}

run-7/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
+size 5240

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": "4.44.0",
+  "vocab_size": 30522
+}

run-7/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e1be7881c0dc037fe89d34ddbea1fe54d16185c2769fad49ab5070d5786319
+size 267832560

run-7/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb75186c31d6e0810602d392cd92552ddcbb80ca73f997c3abdbaf6b41b6d29
+size 535727290

run-7/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb414303639a7a1ac43f67772ae62d7e5e9b37c292fcbbb32333b2db1174237
+size 14244

run-7/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe0b68c2a73cd50a4c99ea4fa8de2c6f9dc3d985e32e5e2f1af4d68e1b0c9e4
+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 +1,130 @@
+{
+  "best_metric": 0.5298831429205758,
+  "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": 0.4677268475210477,
+      "grad_norm": 12.974456787109375,
+      "learning_rate": 1.1101348047567246e-05,
+      "loss": 0.5482,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 6.763242721557617,
+      "learning_rate": 9.955698094257931e-06,
+      "loss": 0.4949,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.47264614701271057,
+      "eval_matthews_correlation": 0.46472372045336796,
+      "eval_runtime": 0.7997,
+      "eval_samples_per_second": 1304.217,
+      "eval_steps_per_second": 82.53,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 21.93242835998535,
+      "learning_rate": 8.810048140948619e-06,
+      "loss": 0.3822,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 23.08902359008789,
+      "learning_rate": 7.664398187639304e-06,
+      "loss": 0.3651,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5118151903152466,
+      "eval_matthews_correlation": 0.5238946707778435,
+      "eval_runtime": 0.7256,
+      "eval_samples_per_second": 1437.525,
+      "eval_steps_per_second": 90.965,
+      "step": 2138
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 0.19134408235549927,
+      "learning_rate": 6.5187482343299915e-06,
+      "loss": 0.2818,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 25.71369743347168,
+      "learning_rate": 5.373098281020679e-06,
+      "loss": 0.2996,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.739141583442688,
+      "eval_matthews_correlation": 0.5298831429205758,
+      "eval_runtime": 0.7927,
+      "eval_samples_per_second": 1315.739,
+      "eval_steps_per_second": 83.259,
+      "step": 3207
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 4.724560260772705,
+      "learning_rate": 4.227448327711365e-06,
+      "loss": 0.2348,
+      "step": 3500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 2.277522563934326,
+      "learning_rate": 3.0817983744020528e-06,
+      "loss": 0.2181,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.830931544303894,
+      "eval_matthews_correlation": 0.5138995234247261,
+      "eval_runtime": 0.7983,
+      "eval_samples_per_second": 1306.597,
+      "eval_steps_per_second": 82.68,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 258412847731296.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2246998000876558e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 6
+  }
+}

run-7/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
+size 5240

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": "4.44.0",
+  "vocab_size": 30522
+}

run-7/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa786a4c8e38cceeda6cfea8b92771a71615edb332838c173c4826c08110269
+size 267832560

run-7/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798d0e57d6fb43bf591835c33b05cdfff71a3b6bc2bf146a192486de4abbc352
+size 535727290

run-7/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc01cbfca6458cce24cd5b1c664890b3329e943240cc275ef712dc6d70dac8c3
+size 14244

run-7/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41fccacd27d473908293c79cd412b9584ac585d846176db59c76041beb5853d
+size 1064

run-7/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-7/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-7/checkpoint-5345/trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_metric": 0.5298831429205758,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-3207",
+  "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": 0.4677268475210477,
+      "grad_norm": 12.974456787109375,
+      "learning_rate": 1.1101348047567246e-05,
+      "loss": 0.5482,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 6.763242721557617,
+      "learning_rate": 9.955698094257931e-06,
+      "loss": 0.4949,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.47264614701271057,
+      "eval_matthews_correlation": 0.46472372045336796,
+      "eval_runtime": 0.7997,
+      "eval_samples_per_second": 1304.217,
+      "eval_steps_per_second": 82.53,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 21.93242835998535,
+      "learning_rate": 8.810048140948619e-06,
+      "loss": 0.3822,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 23.08902359008789,
+      "learning_rate": 7.664398187639304e-06,
+      "loss": 0.3651,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5118151903152466,
+      "eval_matthews_correlation": 0.5238946707778435,
+      "eval_runtime": 0.7256,
+      "eval_samples_per_second": 1437.525,
+      "eval_steps_per_second": 90.965,
+      "step": 2138
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 0.19134408235549927,
+      "learning_rate": 6.5187482343299915e-06,
+      "loss": 0.2818,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 25.71369743347168,
+      "learning_rate": 5.373098281020679e-06,
+      "loss": 0.2996,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.739141583442688,
+      "eval_matthews_correlation": 0.5298831429205758,
+      "eval_runtime": 0.7927,
+      "eval_samples_per_second": 1315.739,
+      "eval_steps_per_second": 83.259,
+      "step": 3207
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 4.724560260772705,
+      "learning_rate": 4.227448327711365e-06,
+      "loss": 0.2348,
+      "step": 3500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 2.277522563934326,
+      "learning_rate": 3.0817983744020528e-06,
+      "loss": 0.2181,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.830931544303894,
+      "eval_matthews_correlation": 0.5138995234247261,
+      "eval_runtime": 0.7983,
+      "eval_samples_per_second": 1306.597,
+      "eval_steps_per_second": 82.68,
+      "step": 4276
+    },
+    {
+      "epoch": 4.209541627689429,
+      "grad_norm": 0.07311611622571945,
+      "learning_rate": 1.9361484210927393e-06,
+      "loss": 0.1904,
+      "step": 4500
+    },
+    {
+      "epoch": 4.677268475210477,
+      "grad_norm": 0.10657232999801636,
+      "learning_rate": 7.904984677834261e-07,
+      "loss": 0.1807,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.9150848388671875,
+      "eval_matthews_correlation": 0.5294395294021531,
+      "eval_runtime": 0.8892,
+      "eval_samples_per_second": 1172.925,
+      "eval_steps_per_second": 74.221,
+      "step": 5345
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 296102409902808.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2246998000876558e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 6
+  }
+}

run-7/checkpoint-5345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
+size 5240

runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723864059.b5f02c58e851.301.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e79883f3175656d7cf17931867dfa4f0fcae30f462470ad878ec58cdf2995eb
-size 7924
+oid sha256:c98e325da453aca577ee44839c3e5012359cfa6bf45d3b051694888810f6e8f5
+size 9035