Upload additional checkpoints (part 2)

ood-viclickbait2025-phobert-source-source-02-s43-20260812T062550Z-6785dbb2/trainer/checkpoint-855/trainer_state.json

@@ -0,0 +1,380 @@
+{
+  "best_global_step": 570,
+  "best_metric": 0.8502270928858682,
+  "best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-phobert-source-source-02-s43-20260812T062550Z-6785dbb2/trainer/checkpoint-570",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2638522427440633,
+      "grad_norm": 8.433926582336426,
+      "learning_rate": 2.5263157894736844e-06,
+      "loss": 2.7323,
+      "step": 25
+    },
+    {
+      "epoch": 0.5277044854881267,
+      "grad_norm": 9.85662841796875,
+      "learning_rate": 5.157894736842106e-06,
+      "loss": 2.4434,
+      "step": 50
+    },
+    {
+      "epoch": 0.7915567282321899,
+      "grad_norm": 8.7896089553833,
+      "learning_rate": 7.789473684210526e-06,
+      "loss": 2.2819,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8100890207715133,
+      "eval_loss": 0.4325940012931824,
+      "eval_macro_f1": 0.7354528505544107,
+      "eval_runtime": 0.7537,
+      "eval_samples_per_second": 447.124,
+      "eval_steps_per_second": 29.189,
+      "eval_weighted_f1": 0.7942444706695586,
+      "step": 95
+    },
+    {
+      "epoch": 1.0527704485488127,
+      "grad_norm": 10.862295150756836,
+      "learning_rate": 1.0421052631578948e-05,
+      "loss": 1.9162,
+      "step": 100
+    },
+    {
+      "epoch": 1.316622691292876,
+      "grad_norm": 27.298757553100586,
+      "learning_rate": 1.305263157894737e-05,
+      "loss": 1.6146,
+      "step": 125
+    },
+    {
+      "epoch": 1.5804749340369393,
+      "grad_norm": 18.937772750854492,
+      "learning_rate": 1.568421052631579e-05,
+      "loss": 1.4469,
+      "step": 150
+    },
+    {
+      "epoch": 1.8443271767810026,
+      "grad_norm": 20.151573181152344,
+      "learning_rate": 1.831578947368421e-05,
+      "loss": 1.4095,
+      "step": 175
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8367952522255193,
+      "eval_loss": 0.35952460765838623,
+      "eval_macro_f1": 0.8039143083840254,
+      "eval_runtime": 0.8795,
+      "eval_samples_per_second": 383.185,
+      "eval_steps_per_second": 25.015,
+      "eval_weighted_f1": 0.8375100553525083,
+      "step": 190
+    },
+    {
+      "epoch": 2.1055408970976255,
+      "grad_norm": 13.84107780456543,
+      "learning_rate": 1.9894736842105265e-05,
+      "loss": 1.255,
+      "step": 200
+    },
+    {
+      "epoch": 2.3693931398416885,
+      "grad_norm": 41.93968963623047,
+      "learning_rate": 1.9602339181286552e-05,
+      "loss": 1.0973,
+      "step": 225
+    },
+    {
+      "epoch": 2.633245382585752,
+      "grad_norm": 12.469989776611328,
+      "learning_rate": 1.930994152046784e-05,
+      "loss": 1.0442,
+      "step": 250
+    },
+    {
+      "epoch": 2.897097625329815,
+      "grad_norm": 39.338069915771484,
+      "learning_rate": 1.9017543859649123e-05,
+      "loss": 1.0669,
+      "step": 275
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8397626112759644,
+      "eval_loss": 0.38732457160949707,
+      "eval_macro_f1": 0.8102002503128911,
+      "eval_runtime": 0.8047,
+      "eval_samples_per_second": 418.764,
+      "eval_steps_per_second": 27.338,
+      "eval_weighted_f1": 0.8415407984015627,
+      "step": 285
+    },
+    {
+      "epoch": 3.158311345646438,
+      "grad_norm": 17.771846771240234,
+      "learning_rate": 1.872514619883041e-05,
+      "loss": 0.775,
+      "step": 300
+    },
+    {
+      "epoch": 3.4221635883905015,
+      "grad_norm": 20.220319747924805,
+      "learning_rate": 1.8432748538011698e-05,
+      "loss": 0.6507,
+      "step": 325
+    },
+    {
+      "epoch": 3.6860158311345645,
+      "grad_norm": 52.71541213989258,
+      "learning_rate": 1.8140350877192985e-05,
+      "loss": 0.7119,
+      "step": 350
+    },
+    {
+      "epoch": 3.949868073878628,
+      "grad_norm": 54.22813034057617,
+      "learning_rate": 1.784795321637427e-05,
+      "loss": 0.7124,
+      "step": 375
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8160237388724035,
+      "eval_loss": 0.543825626373291,
+      "eval_macro_f1": 0.792718253968254,
+      "eval_runtime": 0.7522,
+      "eval_samples_per_second": 448.0,
+      "eval_steps_per_second": 29.246,
+      "eval_weighted_f1": 0.8217985492911309,
+      "step": 380
+    },
+    {
+      "epoch": 4.211081794195251,
+      "grad_norm": 60.47969055175781,
+      "learning_rate": 1.7555555555555556e-05,
+      "loss": 0.5765,
+      "step": 400
+    },
+    {
+      "epoch": 4.474934036939314,
+      "grad_norm": 32.41143035888672,
+      "learning_rate": 1.7263157894736843e-05,
+      "loss": 0.4165,
+      "step": 425
+    },
+    {
+      "epoch": 4.738786279683377,
+      "grad_norm": 18.680706024169922,
+      "learning_rate": 1.697076023391813e-05,
+      "loss": 0.4009,
+      "step": 450
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 17.89019012451172,
+      "learning_rate": 1.6678362573099414e-05,
+      "loss": 0.4795,
+      "step": 475
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.857566765578635,
+      "eval_loss": 0.5520209670066833,
+      "eval_macro_f1": 0.8193513803269901,
+      "eval_runtime": 0.7807,
+      "eval_samples_per_second": 431.67,
+      "eval_steps_per_second": 28.18,
+      "eval_weighted_f1": 0.8541150533623574,
+      "step": 475
+    },
+    {
+      "epoch": 5.263852242744063,
+      "grad_norm": 28.204776763916016,
+      "learning_rate": 1.6385964912280702e-05,
+      "loss": 0.3411,
+      "step": 500
+    },
+    {
+      "epoch": 5.527704485488127,
+      "grad_norm": 5.027624130249023,
+      "learning_rate": 1.609356725146199e-05,
+      "loss": 0.3229,
+      "step": 525
+    },
+    {
+      "epoch": 5.79155672823219,
+      "grad_norm": 69.95579528808594,
+      "learning_rate": 1.5801169590643276e-05,
+      "loss": 0.3592,
+      "step": 550
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8783382789317508,
+      "eval_loss": 0.624035656452179,
+      "eval_macro_f1": 0.8502270928858682,
+      "eval_runtime": 0.8863,
+      "eval_samples_per_second": 380.231,
+      "eval_steps_per_second": 24.822,
+      "eval_weighted_f1": 0.8773755670808643,
+      "step": 570
+    },
+    {
+      "epoch": 6.052770448548813,
+      "grad_norm": 8.929079055786133,
+      "learning_rate": 1.5508771929824563e-05,
+      "loss": 0.1936,
+      "step": 575
+    },
+    {
+      "epoch": 6.316622691292876,
+      "grad_norm": 19.15876007080078,
+      "learning_rate": 1.5216374269005849e-05,
+      "loss": 0.4153,
+      "step": 600
+    },
+    {
+      "epoch": 6.580474934036939,
+      "grad_norm": 146.8297882080078,
+      "learning_rate": 1.4923976608187136e-05,
+      "loss": 0.3671,
+      "step": 625
+    },
+    {
+      "epoch": 6.844327176781003,
+      "grad_norm": 0.2647397816181183,
+      "learning_rate": 1.4631578947368424e-05,
+      "loss": 0.3029,
+      "step": 650
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8427299703264095,
+      "eval_loss": 0.76923668384552,
+      "eval_macro_f1": 0.817172161772082,
+      "eval_runtime": 0.8095,
+      "eval_samples_per_second": 416.329,
+      "eval_steps_per_second": 27.179,
+      "eval_weighted_f1": 0.8457725665828771,
+      "step": 665
+    },
+    {
+      "epoch": 7.105540897097625,
+      "grad_norm": 0.7920535206794739,
+      "learning_rate": 1.4339181286549707e-05,
+      "loss": 0.1472,
+      "step": 675
+    },
+    {
+      "epoch": 7.369393139841689,
+      "grad_norm": 0.19993261992931366,
+      "learning_rate": 1.4046783625730995e-05,
+      "loss": 0.0721,
+      "step": 700
+    },
+    {
+      "epoch": 7.633245382585752,
+      "grad_norm": 109.67591857910156,
+      "learning_rate": 1.3754385964912282e-05,
+      "loss": 0.2164,
+      "step": 725
+    },
+    {
+      "epoch": 7.897097625329815,
+      "grad_norm": 0.1879330724477768,
+      "learning_rate": 1.3461988304093567e-05,
+      "loss": 0.2954,
+      "step": 750
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8367952522255193,
+      "eval_loss": 0.7851014733314514,
+      "eval_macro_f1": 0.8112390903628568,
+      "eval_runtime": 0.873,
+      "eval_samples_per_second": 386.037,
+      "eval_steps_per_second": 25.201,
+      "eval_weighted_f1": 0.8402989195776585,
+      "step": 760
+    },
+    {
+      "epoch": 8.158311345646439,
+      "grad_norm": 0.8775678873062134,
+      "learning_rate": 1.3169590643274855e-05,
+      "loss": 0.1898,
+      "step": 775
+    },
+    {
+      "epoch": 8.422163588390502,
+      "grad_norm": 7.895602703094482,
+      "learning_rate": 1.2877192982456142e-05,
+      "loss": 0.1402,
+      "step": 800
+    },
+    {
+      "epoch": 8.686015831134565,
+      "grad_norm": 0.12149327993392944,
+      "learning_rate": 1.258479532163743e-05,
+      "loss": 0.1772,
+      "step": 825
+    },
+    {
+      "epoch": 8.949868073878628,
+      "grad_norm": 23.895570755004883,
+      "learning_rate": 1.2292397660818713e-05,
+      "loss": 0.2913,
+      "step": 850
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8545994065281899,
+      "eval_loss": 0.7648357152938843,
+      "eval_macro_f1": 0.816222051573125,
+      "eval_runtime": 0.8449,
+      "eval_samples_per_second": 398.858,
+      "eval_steps_per_second": 26.038,
+      "eval_weighted_f1": 0.8513597596813337,
+      "step": 855
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

ood-viclickbait2025-phobert-source-source-02-s43-20260812T062550Z-6785dbb2/trainer/checkpoint-855/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d830221c05c2eb59c0f172d3ec5c5120a44ea95e4c9a08d7a565d80f963049
+size 5624

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d023e28fc4bfcda95fe9a5ff277537730704b7d7681b975f6cdfa9c79fd6c0
+size 540023320

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-1140/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-1140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66e986ad4510f317b9e37be5a03e8cbf86747e29c45c11b0c95aa0b61efc63d
+size 540023352

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-1140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4042014e424ab7cf0c68eeec1b7194cec90e17a913dbda5fb47c85cf31975f
+size 1075440186

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-1140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf78782f84bb4d40c4d99920dd62a1661492ee57caec618a0a28f572d6c357f8
+size 14244

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-1140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9cf407c6e5ee4a4158a29995eab50c2fb6751138d29faec7c04e075a887786
+size 1064

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-1140/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-1140/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-1140/trainer_state.json

@@ -0,0 +1,490 @@
+{
+  "best_global_step": 855,
+  "best_metric": 0.834342610314497,
+  "best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855",
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 1140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2638522427440633,
+      "grad_norm": 12.084431648254395,
+      "learning_rate": 2.5263157894736844e-06,
+      "loss": 2.6631,
+      "step": 25
+    },
+    {
+      "epoch": 0.5277044854881267,
+      "grad_norm": 5.895998001098633,
+      "learning_rate": 5.157894736842106e-06,
+      "loss": 2.4047,
+      "step": 50
+    },
+    {
+      "epoch": 0.7915567282321899,
+      "grad_norm": 8.336459159851074,
+      "learning_rate": 7.789473684210526e-06,
+      "loss": 2.2559,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8130563798219584,
+      "eval_loss": 0.43394148349761963,
+      "eval_macro_f1": 0.7407217439091409,
+      "eval_runtime": 0.9507,
+      "eval_samples_per_second": 354.475,
+      "eval_steps_per_second": 23.141,
+      "eval_weighted_f1": 0.7980205285367099,
+      "step": 95
+    },
+    {
+      "epoch": 1.0527704485488127,
+      "grad_norm": 12.016444206237793,
+      "learning_rate": 1.0421052631578948e-05,
+      "loss": 1.9434,
+      "step": 100
+    },
+    {
+      "epoch": 1.316622691292876,
+      "grad_norm": 13.995548248291016,
+      "learning_rate": 1.305263157894737e-05,
+      "loss": 1.6222,
+      "step": 125
+    },
+    {
+      "epoch": 1.5804749340369393,
+      "grad_norm": 23.421491622924805,
+      "learning_rate": 1.568421052631579e-05,
+      "loss": 1.3969,
+      "step": 150
+    },
+    {
+      "epoch": 1.8443271767810026,
+      "grad_norm": 11.79333782196045,
+      "learning_rate": 1.831578947368421e-05,
+      "loss": 1.4282,
+      "step": 175
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8397626112759644,
+      "eval_loss": 0.35152772068977356,
+      "eval_macro_f1": 0.7953441295546558,
+      "eval_runtime": 0.8208,
+      "eval_samples_per_second": 410.58,
+      "eval_steps_per_second": 26.803,
+      "eval_weighted_f1": 0.8352358870241112,
+      "step": 190
+    },
+    {
+      "epoch": 2.1055408970976255,
+      "grad_norm": 15.8233642578125,
+      "learning_rate": 1.9894736842105265e-05,
+      "loss": 1.322,
+      "step": 200
+    },
+    {
+      "epoch": 2.3693931398416885,
+      "grad_norm": 24.903812408447266,
+      "learning_rate": 1.9602339181286552e-05,
+      "loss": 1.0858,
+      "step": 225
+    },
+    {
+      "epoch": 2.633245382585752,
+      "grad_norm": 9.25020980834961,
+      "learning_rate": 1.930994152046784e-05,
+      "loss": 1.0193,
+      "step": 250
+    },
+    {
+      "epoch": 2.897097625329815,
+      "grad_norm": 16.84253692626953,
+      "learning_rate": 1.9017543859649123e-05,
+      "loss": 1.0265,
+      "step": 275
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8397626112759644,
+      "eval_loss": 0.3835432827472687,
+      "eval_macro_f1": 0.8169362626750363,
+      "eval_runtime": 1.0726,
+      "eval_samples_per_second": 314.201,
+      "eval_steps_per_second": 20.512,
+      "eval_weighted_f1": 0.843982608496304,
+      "step": 285
+    },
+    {
+      "epoch": 3.158311345646438,
+      "grad_norm": 32.33864974975586,
+      "learning_rate": 1.872514619883041e-05,
+      "loss": 0.9455,
+      "step": 300
+    },
+    {
+      "epoch": 3.4221635883905015,
+      "grad_norm": 64.60922241210938,
+      "learning_rate": 1.8432748538011698e-05,
+      "loss": 0.5724,
+      "step": 325
+    },
+    {
+      "epoch": 3.6860158311345645,
+      "grad_norm": 18.83119010925293,
+      "learning_rate": 1.8140350877192985e-05,
+      "loss": 0.6516,
+      "step": 350
+    },
+    {
+      "epoch": 3.949868073878628,
+      "grad_norm": 22.454397201538086,
+      "learning_rate": 1.784795321637427e-05,
+      "loss": 0.6849,
+      "step": 375
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8635014836795252,
+      "eval_loss": 0.4114777445793152,
+      "eval_macro_f1": 0.8303344715874267,
+      "eval_runtime": 0.8097,
+      "eval_samples_per_second": 416.222,
+      "eval_steps_per_second": 27.172,
+      "eval_weighted_f1": 0.8617207045067952,
+      "step": 380
+    },
+    {
+      "epoch": 4.211081794195251,
+      "grad_norm": 71.29817962646484,
+      "learning_rate": 1.7555555555555556e-05,
+      "loss": 0.4934,
+      "step": 400
+    },
+    {
+      "epoch": 4.474934036939314,
+      "grad_norm": 90.17724609375,
+      "learning_rate": 1.7263157894736843e-05,
+      "loss": 0.5127,
+      "step": 425
+    },
+    {
+      "epoch": 4.738786279683377,
+      "grad_norm": 27.522165298461914,
+      "learning_rate": 1.697076023391813e-05,
+      "loss": 0.5211,
+      "step": 450
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.1116359233856201,
+      "learning_rate": 1.6678362573099414e-05,
+      "loss": 0.4066,
+      "step": 475
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8486646884272997,
+      "eval_loss": 0.4813137352466583,
+      "eval_macro_f1": 0.8181750859560963,
+      "eval_runtime": 0.869,
+      "eval_samples_per_second": 387.814,
+      "eval_steps_per_second": 25.317,
+      "eval_weighted_f1": 0.849327505872326,
+      "step": 475
+    },
+    {
+      "epoch": 5.263852242744063,
+      "grad_norm": 33.558204650878906,
+      "learning_rate": 1.6385964912280702e-05,
+      "loss": 0.2971,
+      "step": 500
+    },
+    {
+      "epoch": 5.527704485488127,
+      "grad_norm": 90.95702362060547,
+      "learning_rate": 1.609356725146199e-05,
+      "loss": 0.4303,
+      "step": 525
+    },
+    {
+      "epoch": 5.79155672823219,
+      "grad_norm": 11.966376304626465,
+      "learning_rate": 1.5801169590643276e-05,
+      "loss": 0.3867,
+      "step": 550
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8605341246290801,
+      "eval_loss": 0.5630809664726257,
+      "eval_macro_f1": 0.8304266366896846,
+      "eval_runtime": 1.0755,
+      "eval_samples_per_second": 313.339,
+      "eval_steps_per_second": 20.455,
+      "eval_weighted_f1": 0.8603221000661265,
+      "step": 570
+    },
+    {
+      "epoch": 6.052770448548813,
+      "grad_norm": 22.9655818939209,
+      "learning_rate": 1.5508771929824563e-05,
+      "loss": 0.2779,
+      "step": 575
+    },
+    {
+      "epoch": 6.316622691292876,
+      "grad_norm": 0.33898594975471497,
+      "learning_rate": 1.5216374269005849e-05,
+      "loss": 0.16,
+      "step": 600
+    },
+    {
+      "epoch": 6.580474934036939,
+      "grad_norm": 0.20009009540081024,
+      "learning_rate": 1.4923976608187136e-05,
+      "loss": 0.1888,
+      "step": 625
+    },
+    {
+      "epoch": 6.844327176781003,
+      "grad_norm": 121.28433227539062,
+      "learning_rate": 1.4631578947368424e-05,
+      "loss": 0.411,
+      "step": 650
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8367952522255193,
+      "eval_loss": 0.8188766241073608,
+      "eval_macro_f1": 0.8121801692253128,
+      "eval_runtime": 0.8914,
+      "eval_samples_per_second": 378.058,
+      "eval_steps_per_second": 24.68,
+      "eval_weighted_f1": 0.8406287487583384,
+      "step": 665
+    },
+    {
+      "epoch": 7.105540897097625,
+      "grad_norm": 0.18433061242103577,
+      "learning_rate": 1.4339181286549707e-05,
+      "loss": 0.2052,
+      "step": 675
+    },
+    {
+      "epoch": 7.369393139841689,
+      "grad_norm": 135.7589569091797,
+      "learning_rate": 1.4046783625730995e-05,
+      "loss": 0.0834,
+      "step": 700
+    },
+    {
+      "epoch": 7.633245382585752,
+      "grad_norm": 0.1448420137166977,
+      "learning_rate": 1.3754385964912282e-05,
+      "loss": 0.0811,
+      "step": 725
+    },
+    {
+      "epoch": 7.897097625329815,
+      "grad_norm": 225.9019775390625,
+      "learning_rate": 1.3461988304093567e-05,
+      "loss": 0.2707,
+      "step": 750
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.857566765578635,
+      "eval_loss": 0.7822797894477844,
+      "eval_macro_f1": 0.8193513803269901,
+      "eval_runtime": 0.9892,
+      "eval_samples_per_second": 340.671,
+      "eval_steps_per_second": 22.24,
+      "eval_weighted_f1": 0.8541150533623574,
+      "step": 760
+    },
+    {
+      "epoch": 8.158311345646439,
+      "grad_norm": 0.13781020045280457,
+      "learning_rate": 1.3169590643274855e-05,
+      "loss": 0.213,
+      "step": 775
+    },
+    {
+      "epoch": 8.422163588390502,
+      "grad_norm": 0.265701562166214,
+      "learning_rate": 1.2877192982456142e-05,
+      "loss": 0.1839,
+      "step": 800
+    },
+    {
+      "epoch": 8.686015831134565,
+      "grad_norm": 0.12636584043502808,
+      "learning_rate": 1.258479532163743e-05,
+      "loss": 0.0856,
+      "step": 825
+    },
+    {
+      "epoch": 8.949868073878628,
+      "grad_norm": 171.70948791503906,
+      "learning_rate": 1.2292397660818713e-05,
+      "loss": 0.2293,
+      "step": 850
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8605341246290801,
+      "eval_loss": 0.7610604763031006,
+      "eval_macro_f1": 0.834342610314497,
+      "eval_runtime": 0.8892,
+      "eval_samples_per_second": 378.986,
+      "eval_steps_per_second": 24.741,
+      "eval_weighted_f1": 0.8619023380634241,
+      "step": 855
+    },
+    {
+      "epoch": 9.21108179419525,
+      "grad_norm": 0.1209498941898346,
+      "learning_rate": 1.2e-05,
+      "loss": 0.0606,
+      "step": 875
+    },
+    {
+      "epoch": 9.474934036939313,
+      "grad_norm": 59.60261917114258,
+      "learning_rate": 1.1707602339181288e-05,
+      "loss": 0.1056,
+      "step": 900
+    },
+    {
+      "epoch": 9.738786279683378,
+      "grad_norm": 0.175954207777977,
+      "learning_rate": 1.1415204678362575e-05,
+      "loss": 0.1198,
+      "step": 925
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.10918425023555756,
+      "learning_rate": 1.112280701754386e-05,
+      "loss": 0.1225,
+      "step": 950
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8367952522255193,
+      "eval_loss": 0.9468485116958618,
+      "eval_macro_f1": 0.8121801692253128,
+      "eval_runtime": 0.9991,
+      "eval_samples_per_second": 337.289,
+      "eval_steps_per_second": 22.019,
+      "eval_weighted_f1": 0.8406287487583384,
+      "step": 950
+    },
+    {
+      "epoch": 10.263852242744063,
+      "grad_norm": 25.1407527923584,
+      "learning_rate": 1.0830409356725146e-05,
+      "loss": 0.0741,
+      "step": 975
+    },
+    {
+      "epoch": 10.527704485488126,
+      "grad_norm": 0.13354365527629852,
+      "learning_rate": 1.0538011695906433e-05,
+      "loss": 0.1074,
+      "step": 1000
+    },
+    {
+      "epoch": 10.79155672823219,
+      "grad_norm": 7.303454399108887,
+      "learning_rate": 1.024561403508772e-05,
+      "loss": 0.0404,
+      "step": 1025
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.8635014836795252,
+      "eval_loss": 0.7715884447097778,
+      "eval_macro_f1": 0.8244155491119971,
+      "eval_runtime": 0.8682,
+      "eval_samples_per_second": 388.144,
+      "eval_steps_per_second": 25.339,
+      "eval_weighted_f1": 0.8590766608982956,
+      "step": 1045
+    },
+    {
+      "epoch": 11.052770448548813,
+      "grad_norm": 0.08514150977134705,
+      "learning_rate": 9.953216374269008e-06,
+      "loss": 0.2697,
+      "step": 1050
+    },
+    {
+      "epoch": 11.316622691292876,
+      "grad_norm": 0.09421021491289139,
+      "learning_rate": 9.660818713450293e-06,
+      "loss": 0.0884,
+      "step": 1075
+    },
+    {
+      "epoch": 11.580474934036939,
+      "grad_norm": 0.08269848674535751,
+      "learning_rate": 9.36842105263158e-06,
+      "loss": 0.0568,
+      "step": 1100
+    },
+    {
+      "epoch": 11.844327176781002,
+      "grad_norm": 390.11761474609375,
+      "learning_rate": 9.076023391812866e-06,
+      "loss": 0.0723,
+      "step": 1125
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.8605341246290801,
+      "eval_loss": 0.8145036697387695,
+      "eval_macro_f1": 0.8260769306789357,
+      "eval_runtime": 0.8367,
+      "eval_samples_per_second": 402.759,
+      "eval_steps_per_second": 26.293,
+      "eval_weighted_f1": 0.8584666929920715,
+      "step": 1140
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-1140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc7bf60bbeec96829860d5e9efc984f3319b9734c1e43bd24aec91db0f74ac50
+size 5624

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dda4cc436984a18b8a1debf88de0f739ffc8e16cffff1bae530577b7962ab14
+size 540023352

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc336f7ed821b16848b31b073442ee94dcceb87cbbf292c3d86efd269db4d09
+size 1075440186

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb24b70f8001970d182424abbef544fcb5f55df1efa6e2379b170222f5865bd
+size 14244

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a4220ccc83f23280b062bddf37f306967b6d3655f302b819e7dd6d6261d0ed
+size 1064

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855/trainer_state.json

@@ -0,0 +1,380 @@
+{
+  "best_global_step": 855,
+  "best_metric": 0.834342610314497,
+  "best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2638522427440633,
+      "grad_norm": 12.084431648254395,
+      "learning_rate": 2.5263157894736844e-06,
+      "loss": 2.6631,
+      "step": 25
+    },
+    {
+      "epoch": 0.5277044854881267,
+      "grad_norm": 5.895998001098633,
+      "learning_rate": 5.157894736842106e-06,
+      "loss": 2.4047,
+      "step": 50
+    },
+    {
+      "epoch": 0.7915567282321899,
+      "grad_norm": 8.336459159851074,
+      "learning_rate": 7.789473684210526e-06,
+      "loss": 2.2559,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8130563798219584,
+      "eval_loss": 0.43394148349761963,
+      "eval_macro_f1": 0.7407217439091409,
+      "eval_runtime": 0.9507,
+      "eval_samples_per_second": 354.475,
+      "eval_steps_per_second": 23.141,
+      "eval_weighted_f1": 0.7980205285367099,
+      "step": 95
+    },
+    {
+      "epoch": 1.0527704485488127,
+      "grad_norm": 12.016444206237793,
+      "learning_rate": 1.0421052631578948e-05,
+      "loss": 1.9434,
+      "step": 100
+    },
+    {
+      "epoch": 1.316622691292876,
+      "grad_norm": 13.995548248291016,
+      "learning_rate": 1.305263157894737e-05,
+      "loss": 1.6222,
+      "step": 125
+    },
+    {
+      "epoch": 1.5804749340369393,
+      "grad_norm": 23.421491622924805,
+      "learning_rate": 1.568421052631579e-05,
+      "loss": 1.3969,
+      "step": 150
+    },
+    {
+      "epoch": 1.8443271767810026,
+      "grad_norm": 11.79333782196045,
+      "learning_rate": 1.831578947368421e-05,
+      "loss": 1.4282,
+      "step": 175
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8397626112759644,
+      "eval_loss": 0.35152772068977356,
+      "eval_macro_f1": 0.7953441295546558,
+      "eval_runtime": 0.8208,
+      "eval_samples_per_second": 410.58,
+      "eval_steps_per_second": 26.803,
+      "eval_weighted_f1": 0.8352358870241112,
+      "step": 190
+    },
+    {
+      "epoch": 2.1055408970976255,
+      "grad_norm": 15.8233642578125,
+      "learning_rate": 1.9894736842105265e-05,
+      "loss": 1.322,
+      "step": 200
+    },
+    {
+      "epoch": 2.3693931398416885,
+      "grad_norm": 24.903812408447266,
+      "learning_rate": 1.9602339181286552e-05,
+      "loss": 1.0858,
+      "step": 225
+    },
+    {
+      "epoch": 2.633245382585752,
+      "grad_norm": 9.25020980834961,
+      "learning_rate": 1.930994152046784e-05,
+      "loss": 1.0193,
+      "step": 250
+    },
+    {
+      "epoch": 2.897097625329815,
+      "grad_norm": 16.84253692626953,
+      "learning_rate": 1.9017543859649123e-05,
+      "loss": 1.0265,
+      "step": 275
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8397626112759644,
+      "eval_loss": 0.3835432827472687,
+      "eval_macro_f1": 0.8169362626750363,
+      "eval_runtime": 1.0726,
+      "eval_samples_per_second": 314.201,
+      "eval_steps_per_second": 20.512,
+      "eval_weighted_f1": 0.843982608496304,
+      "step": 285
+    },
+    {
+      "epoch": 3.158311345646438,
+      "grad_norm": 32.33864974975586,
+      "learning_rate": 1.872514619883041e-05,
+      "loss": 0.9455,
+      "step": 300
+    },
+    {
+      "epoch": 3.4221635883905015,
+      "grad_norm": 64.60922241210938,
+      "learning_rate": 1.8432748538011698e-05,
+      "loss": 0.5724,
+      "step": 325
+    },
+    {
+      "epoch": 3.6860158311345645,
+      "grad_norm": 18.83119010925293,
+      "learning_rate": 1.8140350877192985e-05,
+      "loss": 0.6516,
+      "step": 350
+    },
+    {
+      "epoch": 3.949868073878628,
+      "grad_norm": 22.454397201538086,
+      "learning_rate": 1.784795321637427e-05,
+      "loss": 0.6849,
+      "step": 375
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8635014836795252,
+      "eval_loss": 0.4114777445793152,
+      "eval_macro_f1": 0.8303344715874267,
+      "eval_runtime": 0.8097,
+      "eval_samples_per_second": 416.222,
+      "eval_steps_per_second": 27.172,
+      "eval_weighted_f1": 0.8617207045067952,
+      "step": 380
+    },
+    {
+      "epoch": 4.211081794195251,
+      "grad_norm": 71.29817962646484,
+      "learning_rate": 1.7555555555555556e-05,
+      "loss": 0.4934,
+      "step": 400
+    },
+    {
+      "epoch": 4.474934036939314,
+      "grad_norm": 90.17724609375,
+      "learning_rate": 1.7263157894736843e-05,
+      "loss": 0.5127,
+      "step": 425
+    },
+    {
+      "epoch": 4.738786279683377,
+      "grad_norm": 27.522165298461914,
+      "learning_rate": 1.697076023391813e-05,
+      "loss": 0.5211,
+      "step": 450
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.1116359233856201,
+      "learning_rate": 1.6678362573099414e-05,
+      "loss": 0.4066,
+      "step": 475
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8486646884272997,
+      "eval_loss": 0.4813137352466583,
+      "eval_macro_f1": 0.8181750859560963,
+      "eval_runtime": 0.869,
+      "eval_samples_per_second": 387.814,
+      "eval_steps_per_second": 25.317,
+      "eval_weighted_f1": 0.849327505872326,
+      "step": 475
+    },
+    {
+      "epoch": 5.263852242744063,
+      "grad_norm": 33.558204650878906,
+      "learning_rate": 1.6385964912280702e-05,
+      "loss": 0.2971,
+      "step": 500
+    },
+    {
+      "epoch": 5.527704485488127,
+      "grad_norm": 90.95702362060547,
+      "learning_rate": 1.609356725146199e-05,
+      "loss": 0.4303,
+      "step": 525
+    },
+    {
+      "epoch": 5.79155672823219,
+      "grad_norm": 11.966376304626465,
+      "learning_rate": 1.5801169590643276e-05,
+      "loss": 0.3867,
+      "step": 550
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8605341246290801,
+      "eval_loss": 0.5630809664726257,
+      "eval_macro_f1": 0.8304266366896846,
+      "eval_runtime": 1.0755,
+      "eval_samples_per_second": 313.339,
+      "eval_steps_per_second": 20.455,
+      "eval_weighted_f1": 0.8603221000661265,
+      "step": 570
+    },
+    {
+      "epoch": 6.052770448548813,
+      "grad_norm": 22.9655818939209,
+      "learning_rate": 1.5508771929824563e-05,
+      "loss": 0.2779,
+      "step": 575
+    },
+    {
+      "epoch": 6.316622691292876,
+      "grad_norm": 0.33898594975471497,
+      "learning_rate": 1.5216374269005849e-05,
+      "loss": 0.16,
+      "step": 600
+    },
+    {
+      "epoch": 6.580474934036939,
+      "grad_norm": 0.20009009540081024,
+      "learning_rate": 1.4923976608187136e-05,
+      "loss": 0.1888,
+      "step": 625
+    },
+    {
+      "epoch": 6.844327176781003,
+      "grad_norm": 121.28433227539062,
+      "learning_rate": 1.4631578947368424e-05,
+      "loss": 0.411,
+      "step": 650
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8367952522255193,
+      "eval_loss": 0.8188766241073608,
+      "eval_macro_f1": 0.8121801692253128,
+      "eval_runtime": 0.8914,
+      "eval_samples_per_second": 378.058,
+      "eval_steps_per_second": 24.68,
+      "eval_weighted_f1": 0.8406287487583384,
+      "step": 665
+    },
+    {
+      "epoch": 7.105540897097625,
+      "grad_norm": 0.18433061242103577,
+      "learning_rate": 1.4339181286549707e-05,
+      "loss": 0.2052,
+      "step": 675
+    },
+    {
+      "epoch": 7.369393139841689,
+      "grad_norm": 135.7589569091797,
+      "learning_rate": 1.4046783625730995e-05,
+      "loss": 0.0834,
+      "step": 700
+    },
+    {
+      "epoch": 7.633245382585752,
+      "grad_norm": 0.1448420137166977,
+      "learning_rate": 1.3754385964912282e-05,
+      "loss": 0.0811,
+      "step": 725
+    },
+    {
+      "epoch": 7.897097625329815,
+      "grad_norm": 225.9019775390625,
+      "learning_rate": 1.3461988304093567e-05,
+      "loss": 0.2707,
+      "step": 750
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.857566765578635,
+      "eval_loss": 0.7822797894477844,
+      "eval_macro_f1": 0.8193513803269901,
+      "eval_runtime": 0.9892,
+      "eval_samples_per_second": 340.671,
+      "eval_steps_per_second": 22.24,
+      "eval_weighted_f1": 0.8541150533623574,
+      "step": 760
+    },
+    {
+      "epoch": 8.158311345646439,
+      "grad_norm": 0.13781020045280457,
+      "learning_rate": 1.3169590643274855e-05,
+      "loss": 0.213,
+      "step": 775
+    },
+    {
+      "epoch": 8.422163588390502,
+      "grad_norm": 0.265701562166214,
+      "learning_rate": 1.2877192982456142e-05,
+      "loss": 0.1839,
+      "step": 800
+    },
+    {
+      "epoch": 8.686015831134565,
+      "grad_norm": 0.12636584043502808,
+      "learning_rate": 1.258479532163743e-05,
+      "loss": 0.0856,
+      "step": 825
+    },
+    {
+      "epoch": 8.949868073878628,
+      "grad_norm": 171.70948791503906,
+      "learning_rate": 1.2292397660818713e-05,
+      "loss": 0.2293,
+      "step": 850
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8605341246290801,
+      "eval_loss": 0.7610604763031006,
+      "eval_macro_f1": 0.834342610314497,
+      "eval_runtime": 0.8892,
+      "eval_samples_per_second": 378.986,
+      "eval_steps_per_second": 24.741,
+      "eval_weighted_f1": 0.8619023380634241,
+      "step": 855
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

ood-viclickbait2025-phobert-source-source-02-s44-20260812T072224Z-4df93cfc/trainer/checkpoint-855/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc7bf60bbeec96829860d5e9efc984f3319b9734c1e43bd24aec91db0f74ac50
+size 5624

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bccded5e5e552142038b6d6472653d0c1c9616c19aed52c306c0742c068d038f
+size 540023320

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f8440c386cb31542924933ebdf61a1243fec6d96cca004324c25b49bad6c8c
+size 540023352

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67e46797b0a398c0656fbfee54bcdbea5f503b0bec2831334eea4b948cdbd73
+size 1075440186

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197ba52938cc6ccac979f0279dee0efe939e30c23c97092ae417c779bec3a4d7
+size 14244

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549caf6eb6de25816e4a88233927e29504b6d09ff1787e023d19f5c7713892e5
+size 1064

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_global_step": 264,
+  "best_metric": 0.8360398114195914,
+  "best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 264,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2840909090909091,
+      "grad_norm": 5.692137241363525,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 2.5275,
+      "step": 25
+    },
+    {
+      "epoch": 0.5681818181818182,
+      "grad_norm": 6.832818984985352,
+      "learning_rate": 5.568181818181818e-06,
+      "loss": 2.3394,
+      "step": 50
+    },
+    {
+      "epoch": 0.8522727272727273,
+      "grad_norm": 6.720674991607666,
+      "learning_rate": 8.40909090909091e-06,
+      "loss": 2.2034,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7763578274760383,
+      "eval_loss": 0.43589943647384644,
+      "eval_macro_f1": 0.6139887244538407,
+      "eval_runtime": 1.0018,
+      "eval_samples_per_second": 312.426,
+      "eval_steps_per_second": 19.963,
+      "eval_weighted_f1": 0.7251675683951484,
+      "step": 88
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 13.874998092651367,
+      "learning_rate": 1.125e-05,
+      "loss": 1.8781,
+      "step": 100
+    },
+    {
+      "epoch": 1.4204545454545454,
+      "grad_norm": 51.494110107421875,
+      "learning_rate": 1.4090909090909092e-05,
+      "loss": 1.5951,
+      "step": 125
+    },
+    {
+      "epoch": 1.7045454545454546,
+      "grad_norm": 15.30184555053711,
+      "learning_rate": 1.6931818181818182e-05,
+      "loss": 1.5278,
+      "step": 150
+    },
+    {
+      "epoch": 1.9886363636363638,
+      "grad_norm": 18.6683406829834,
+      "learning_rate": 1.9772727272727274e-05,
+      "loss": 1.418,
+      "step": 175
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8498402555910544,
+      "eval_loss": 0.3254472613334656,
+      "eval_macro_f1": 0.8095244260872942,
+      "eval_runtime": 0.9935,
+      "eval_samples_per_second": 315.035,
+      "eval_steps_per_second": 20.13,
+      "eval_weighted_f1": 0.8484404003999515,
+      "step": 176
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 27.948440551757812,
+      "learning_rate": 1.9709595959595963e-05,
+      "loss": 1.1416,
+      "step": 200
+    },
+    {
+      "epoch": 2.5568181818181817,
+      "grad_norm": 24.933687210083008,
+      "learning_rate": 1.9393939393939395e-05,
+      "loss": 1.0575,
+      "step": 225
+    },
+    {
+      "epoch": 2.840909090909091,
+      "grad_norm": 24.883956909179688,
+      "learning_rate": 1.907828282828283e-05,
+      "loss": 1.2504,
+      "step": 250
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8722044728434505,
+      "eval_loss": 0.32443928718566895,
+      "eval_macro_f1": 0.8360398114195914,
+      "eval_runtime": 0.9809,
+      "eval_samples_per_second": 319.095,
+      "eval_steps_per_second": 20.389,
+      "eval_weighted_f1": 0.8702363280040568,
+      "step": 264
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1760,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2656c20b2b644d86216c27341a69ca9fc571a1834ab0a069bccafa771a9441
+size 5624

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-528/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-528/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743a454b06f1416afa2ca79a4baee84d7e213cef4a7786b5687c0587f0b13032
+size 540023352

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-528/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72bc1a1a3d03edb33e44408af750ae3b22a7185b1a9d0ded5520ee77a1fbf446
+size 1075440186

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-528/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94dab22b5292fcce89d73d177bcb2a2af48dc6e160cd489095b72ca7301ce32
+size 14244

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-528/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8c34572f09d7e024d2a23735795c3cc6fcdc49f5c53e79221ea846fc87d9a1
+size 1064

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-528/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-528/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-528/trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_global_step": 264,
+  "best_metric": 0.8360398114195914,
+  "best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-264",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 528,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2840909090909091,
+      "grad_norm": 5.692137241363525,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 2.5275,
+      "step": 25
+    },
+    {
+      "epoch": 0.5681818181818182,
+      "grad_norm": 6.832818984985352,
+      "learning_rate": 5.568181818181818e-06,
+      "loss": 2.3394,
+      "step": 50
+    },
+    {
+      "epoch": 0.8522727272727273,
+      "grad_norm": 6.720674991607666,
+      "learning_rate": 8.40909090909091e-06,
+      "loss": 2.2034,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7763578274760383,
+      "eval_loss": 0.43589943647384644,
+      "eval_macro_f1": 0.6139887244538407,
+      "eval_runtime": 1.0018,
+      "eval_samples_per_second": 312.426,
+      "eval_steps_per_second": 19.963,
+      "eval_weighted_f1": 0.7251675683951484,
+      "step": 88
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 13.874998092651367,
+      "learning_rate": 1.125e-05,
+      "loss": 1.8781,
+      "step": 100
+    },
+    {
+      "epoch": 1.4204545454545454,
+      "grad_norm": 51.494110107421875,
+      "learning_rate": 1.4090909090909092e-05,
+      "loss": 1.5951,
+      "step": 125
+    },
+    {
+      "epoch": 1.7045454545454546,
+      "grad_norm": 15.30184555053711,
+      "learning_rate": 1.6931818181818182e-05,
+      "loss": 1.5278,
+      "step": 150
+    },
+    {
+      "epoch": 1.9886363636363638,
+      "grad_norm": 18.6683406829834,
+      "learning_rate": 1.9772727272727274e-05,
+      "loss": 1.418,
+      "step": 175
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8498402555910544,
+      "eval_loss": 0.3254472613334656,
+      "eval_macro_f1": 0.8095244260872942,
+      "eval_runtime": 0.9935,
+      "eval_samples_per_second": 315.035,
+      "eval_steps_per_second": 20.13,
+      "eval_weighted_f1": 0.8484404003999515,
+      "step": 176
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 27.948440551757812,
+      "learning_rate": 1.9709595959595963e-05,
+      "loss": 1.1416,
+      "step": 200
+    },
+    {
+      "epoch": 2.5568181818181817,
+      "grad_norm": 24.933687210083008,
+      "learning_rate": 1.9393939393939395e-05,
+      "loss": 1.0575,
+      "step": 225
+    },
+    {
+      "epoch": 2.840909090909091,
+      "grad_norm": 24.883956909179688,
+      "learning_rate": 1.907828282828283e-05,
+      "loss": 1.2504,
+      "step": 250
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8722044728434505,
+      "eval_loss": 0.32443928718566895,
+      "eval_macro_f1": 0.8360398114195914,
+      "eval_runtime": 0.9809,
+      "eval_samples_per_second": 319.095,
+      "eval_steps_per_second": 20.389,
+      "eval_weighted_f1": 0.8702363280040568,
+      "step": 264
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 20.287246704101562,
+      "learning_rate": 1.8762626262626265e-05,
+      "loss": 0.869,
+      "step": 275
+    },
+    {
+      "epoch": 3.409090909090909,
+      "grad_norm": 35.06276321411133,
+      "learning_rate": 1.84469696969697e-05,
+      "loss": 0.6782,
+      "step": 300
+    },
+    {
+      "epoch": 3.6931818181818183,
+      "grad_norm": 37.528568267822266,
+      "learning_rate": 1.8131313131313132e-05,
+      "loss": 0.7169,
+      "step": 325
+    },
+    {
+      "epoch": 3.9772727272727275,
+      "grad_norm": 30.37287139892578,
+      "learning_rate": 1.7815656565656567e-05,
+      "loss": 0.6844,
+      "step": 350
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8562300319488818,
+      "eval_loss": 0.3836123049259186,
+      "eval_macro_f1": 0.8227699973575932,
+      "eval_runtime": 0.8614,
+      "eval_samples_per_second": 363.362,
+      "eval_steps_per_second": 23.218,
+      "eval_weighted_f1": 0.8569681209472191,
+      "step": 352
+    },
+    {
+      "epoch": 4.261363636363637,
+      "grad_norm": 4.705540657043457,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.5501,
+      "step": 375
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 130.1666259765625,
+      "learning_rate": 1.7184343434343437e-05,
+      "loss": 0.3838,
+      "step": 400
+    },
+    {
+      "epoch": 4.829545454545455,
+      "grad_norm": 58.46879959106445,
+      "learning_rate": 1.686868686868687e-05,
+      "loss": 0.5667,
+      "step": 425
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.853035143769968,
+      "eval_loss": 0.49516671895980835,
+      "eval_macro_f1": 0.8272129416282642,
+      "eval_runtime": 0.8541,
+      "eval_samples_per_second": 366.484,
+      "eval_steps_per_second": 23.418,
+      "eval_weighted_f1": 0.8568764630968331,
+      "step": 440
+    },
+    {
+      "epoch": 5.113636363636363,
+      "grad_norm": 0.9170684218406677,
+      "learning_rate": 1.6553030303030304e-05,
+      "loss": 0.3691,
+      "step": 450
+    },
+    {
+      "epoch": 5.3977272727272725,
+      "grad_norm": 0.627122163772583,
+      "learning_rate": 1.623737373737374e-05,
+      "loss": 0.2555,
+      "step": 475
+    },
+    {
+      "epoch": 5.681818181818182,
+      "grad_norm": 36.943641662597656,
+      "learning_rate": 1.5921717171717174e-05,
+      "loss": 0.445,
+      "step": 500
+    },
+    {
+      "epoch": 5.965909090909091,
+      "grad_norm": 0.2599617540836334,
+      "learning_rate": 1.5606060606060605e-05,
+      "loss": 0.2825,
+      "step": 525
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.853035143769968,
+      "eval_loss": 0.6772757172584534,
+      "eval_macro_f1": 0.8272129416282642,
+      "eval_runtime": 0.9934,
+      "eval_samples_per_second": 315.067,
+      "eval_steps_per_second": 20.132,
+      "eval_weighted_f1": 0.8568764630968331,
+      "step": 528
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1760,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

ood-viclickbait2025-phobert-source-source-03-s42-20260812T054320Z-fe163e57/trainer/checkpoint-528/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2656c20b2b644d86216c27341a69ca9fc571a1834ab0a069bccafa771a9441
+size 5624

ood-viclickbait2025-phobert-source-source-03-s43-20260812T063404Z-6785dbb2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457dcb4e1a2a284393275532490598a7a90c8ed138216b161085ce81a32dfb35
+size 540023320