Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b387a276a46d271831ed4c0b8b2422a9c0e1b8f922a6de345df90d62c755a87
+oid sha256:45273d24519907b1e6cd0335bd18fcf660d057efd4c7aeb8de7f6a267295f20d
 size 267832560

run-2/checkpoint-1072/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": "4.45.0",
+  "vocab_size": 30522
+}

run-2/checkpoint-1072/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad227f1306eb119920599da00edf34163320ff3692d6f3c1793ee414b65dc4e
+size 267832560

run-2/checkpoint-1072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2be42a01d96aaad8d2965f6a656b0694b0e307cdb13cdbb145cfb958ecaeb2c
+size 535727290

run-2/checkpoint-1072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788d32cbca97d67cf172a4eb83a168e17a30fdb3caeb9a634e77a6920b3fc5f4
+size 14244

run-2/checkpoint-1072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312edbf46b13d2a0bf6f639eabb29f112a26a9704991a37fe8e8100701adb177
+size 1064

run-2/checkpoint-1072/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-1072/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-1072/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": 0.42662088349566707,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1072",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1072,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.547015905380249,
+      "eval_matthews_correlation": 0.21965396568843812,
+      "eval_runtime": 0.7987,
+      "eval_samples_per_second": 1305.815,
+      "eval_steps_per_second": 82.631,
+      "step": 268
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 5.013413906097412,
+      "learning_rate": 2.4916450268020124e-06,
+      "loss": 0.5406,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5194542407989502,
+      "eval_matthews_correlation": 0.38878916468148733,
+      "eval_runtime": 0.9473,
+      "eval_samples_per_second": 1100.981,
+      "eval_steps_per_second": 69.669,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.511012613773346,
+      "eval_matthews_correlation": 0.4209176074686373,
+      "eval_runtime": 1.7589,
+      "eval_samples_per_second": 592.995,
+      "eval_steps_per_second": 37.524,
+      "step": 804
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 5.263833999633789,
+      "learning_rate": 3.1363363973731624e-07,
+      "loss": 0.4347,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5149170756340027,
+      "eval_matthews_correlation": 0.42662088349566707,
+      "eval_runtime": 0.9396,
+      "eval_samples_per_second": 1109.992,
+      "eval_steps_per_second": 70.239,
+      "step": 1072
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 190264063081320.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.669656413866708e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 15
+  }
+}

run-2/checkpoint-1072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac07b7d7c79287c619afc05fab04377c4fc350f1f525ea401e4f9d9b5b15e72c
+size 5304

run-2/checkpoint-536/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": "4.45.0",
+  "vocab_size": 30522
+}

run-2/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6403fc647d70d911040f0bb298ecfc219f288dd9c976fa2c9384fb3141f0ddd3
+size 267832560

run-2/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048245b19405ab273c9d77d0bec65b51180f2e22513335d1c252c7ee95ab5f63
+size 535727290

run-2/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f827f37a1c9c2084582a7eebf927c4456d10117d230821f32569b32524a79921
+size 14244

run-2/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994432a8a213a6e435c09adde124a3394164b04858034ac03e3134883bf2b810
+size 1064

run-2/checkpoint-536/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-536/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-536/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.38878916468148733,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-536",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.547015905380249,
+      "eval_matthews_correlation": 0.21965396568843812,
+      "eval_runtime": 0.7987,
+      "eval_samples_per_second": 1305.815,
+      "eval_steps_per_second": 82.631,
+      "step": 268
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 5.013413906097412,
+      "learning_rate": 2.4916450268020124e-06,
+      "loss": 0.5406,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5194542407989502,
+      "eval_matthews_correlation": 0.38878916468148733,
+      "eval_runtime": 0.9473,
+      "eval_samples_per_second": 1100.981,
+      "eval_steps_per_second": 69.669,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 95049498141888.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.669656413866708e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 15
+  }
+}

run-2/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac07b7d7c79287c619afc05fab04377c4fc350f1f525ea401e4f9d9b5b15e72c
+size 5304

run-2/checkpoint-804/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": "4.45.0",
+  "vocab_size": 30522
+}

run-2/checkpoint-804/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34da7d300ea68ea91fcdc491d781a80d401dc876c4c8c142752bdafc27dcae5b
+size 267832560

run-2/checkpoint-804/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73d3b7174a71c19c2d386ec5ef6f41e7e9f733f897c0858ea0a3f0cfdd5d90b
+size 535727290

run-2/checkpoint-804/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7463e99a6040d753ef8c892dfe4f8427c3c766e808be713646c249357a4acb
+size 14244

run-2/checkpoint-804/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1247b08a90228ec56f221712fef87b9f026e6b061d4b826e7b3725b9cd81b50a
+size 1064

run-2/checkpoint-804/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-804/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-804/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.4209176074686373,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-804",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 804,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.547015905380249,
+      "eval_matthews_correlation": 0.21965396568843812,
+      "eval_runtime": 0.7987,
+      "eval_samples_per_second": 1305.815,
+      "eval_steps_per_second": 82.631,
+      "step": 268
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 5.013413906097412,
+      "learning_rate": 2.4916450268020124e-06,
+      "loss": 0.5406,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5194542407989502,
+      "eval_matthews_correlation": 0.38878916468148733,
+      "eval_runtime": 0.9473,
+      "eval_samples_per_second": 1100.981,
+      "eval_steps_per_second": 69.669,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.511012613773346,
+      "eval_matthews_correlation": 0.4209176074686373,
+      "eval_runtime": 1.7589,
+      "eval_samples_per_second": 592.995,
+      "eval_steps_per_second": 37.524,
+      "step": 804
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 95049498141888.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.669656413866708e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 15
+  }
+}

run-2/checkpoint-804/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac07b7d7c79287c619afc05fab04377c4fc350f1f525ea401e4f9d9b5b15e72c
+size 5304

run-3/checkpoint-134/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": "4.45.0",
+  "vocab_size": 30522
+}

run-3/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45273d24519907b1e6cd0335bd18fcf660d057efd4c7aeb8de7f6a267295f20d
+size 267832560

run-3/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4c433450ff12580f829783b871f1588240507c540950d6bb6d8efadeeff0a3
+size 535727290

run-3/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be625c69c38ff10078cd2562b1bf7255a8c40da647e6098eb535a632cc7e525b
+size 14244

run-3/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3592427ffb6e42c819866d2793d1b0bb7d123e2c1fcb98e673f76dbdb51e2efd
+size 1064

run-3/checkpoint-134/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-134/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-134/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.3577028127616067,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-134",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 134,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5295282602310181,
+      "eval_matthews_correlation": 0.3577028127616067,
+      "eval_runtime": 0.7966,
+      "eval_samples_per_second": 1309.259,
+      "eval_steps_per_second": 82.849,
+      "step": 134
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1486502446056178e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 27
+  }
+}

run-3/checkpoint-134/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c947f4ef41847348dc05333cc6dacba9abdd7f0fda6f36ebd85c0073a00d6b56
+size 5304

runs/Sep26_13-34-33_f266a1036e13/events.out.tfevents.1727358405.f266a1036e13.258.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17fb7a4d96f5ef9547e2e9f1a5f09a4128de8e1c0be58f570476284f01d2759f
-size 6176
+oid sha256:afcf24f607abc6dd38beada55476decd96fa5d575b0d1287b6db4ece724903cc
+size 7076

runs/Sep26_13-34-33_f266a1036e13/events.out.tfevents.1727358552.f266a1036e13.258.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd47a3f042261657e3aee5a26fe28f9546e5f4634d5752ad748188659690cde9
+size 5985

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac07b7d7c79287c619afc05fab04377c4fc350f1f525ea401e4f9d9b5b15e72c
+oid sha256:c947f4ef41847348dc05333cc6dacba9abdd7f0fda6f36ebd85c0073a00d6b56
 size 5304