| { | |
| "best_metric": 1.798496961593628, | |
| "best_model_checkpoint": "autotrain-bigbird-flight/checkpoint-514", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 514, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04669260700389105, | |
| "grad_norm": 3.0252254009246826, | |
| "learning_rate": 9.724473257698543e-07, | |
| "loss": 2.2957, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0933852140077821, | |
| "grad_norm": 3.4915716648101807, | |
| "learning_rate": 1.9448946515397086e-06, | |
| "loss": 2.3137, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14007782101167315, | |
| "grad_norm": 3.5864250659942627, | |
| "learning_rate": 2.9173419773095627e-06, | |
| "loss": 2.3067, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1867704280155642, | |
| "grad_norm": 4.509471893310547, | |
| "learning_rate": 3.889789303079417e-06, | |
| "loss": 2.3144, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.23346303501945526, | |
| "grad_norm": 2.9119784832000732, | |
| "learning_rate": 4.862236628849271e-06, | |
| "loss": 2.3111, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2801556420233463, | |
| "grad_norm": 2.615067481994629, | |
| "learning_rate": 5.8346839546191254e-06, | |
| "loss": 2.3047, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.32684824902723736, | |
| "grad_norm": 3.578856945037842, | |
| "learning_rate": 6.807131280388978e-06, | |
| "loss": 2.3064, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3735408560311284, | |
| "grad_norm": 4.135900974273682, | |
| "learning_rate": 7.779578606158834e-06, | |
| "loss": 2.2958, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.42023346303501946, | |
| "grad_norm": 3.22177791595459, | |
| "learning_rate": 8.752025931928688e-06, | |
| "loss": 2.3088, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.4669260700389105, | |
| "grad_norm": 2.849999189376831, | |
| "learning_rate": 9.724473257698542e-06, | |
| "loss": 2.2959, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5136186770428015, | |
| "grad_norm": 3.1687047481536865, | |
| "learning_rate": 1.0696920583468397e-05, | |
| "loss": 2.2795, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.5603112840466926, | |
| "grad_norm": 3.0055816173553467, | |
| "learning_rate": 1.1669367909238251e-05, | |
| "loss": 2.2919, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6070038910505836, | |
| "grad_norm": 3.02952241897583, | |
| "learning_rate": 1.2641815235008103e-05, | |
| "loss": 2.2637, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6536964980544747, | |
| "grad_norm": 3.8288016319274902, | |
| "learning_rate": 1.3614262560777957e-05, | |
| "loss": 2.1604, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.7003891050583657, | |
| "grad_norm": 126.01935577392578, | |
| "learning_rate": 1.4586709886547812e-05, | |
| "loss": 2.1408, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7470817120622568, | |
| "grad_norm": 14.168249130249023, | |
| "learning_rate": 1.555915721231767e-05, | |
| "loss": 2.1199, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.7937743190661478, | |
| "grad_norm": 5.94619607925415, | |
| "learning_rate": 1.6531604538087523e-05, | |
| "loss": 2.0819, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.8404669260700389, | |
| "grad_norm": 10.58005142211914, | |
| "learning_rate": 1.7504051863857376e-05, | |
| "loss": 2.0871, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.8871595330739299, | |
| "grad_norm": 9.494062423706055, | |
| "learning_rate": 1.847649918962723e-05, | |
| "loss": 1.9864, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.933852140077821, | |
| "grad_norm": 11.363922119140625, | |
| "learning_rate": 1.9448946515397084e-05, | |
| "loss": 1.925, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.980544747081712, | |
| "grad_norm": 6.328553676605225, | |
| "learning_rate": 2.0421393841166937e-05, | |
| "loss": 1.9497, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.24708171206225682, | |
| "eval_f1_macro": 0.2015263302646054, | |
| "eval_f1_micro": 0.24708171206225682, | |
| "eval_f1_weighted": 0.20916676720406013, | |
| "eval_loss": 1.9002625942230225, | |
| "eval_precision_macro": 0.20560782159414379, | |
| "eval_precision_micro": 0.24708171206225682, | |
| "eval_precision_weighted": 0.21350682757806103, | |
| "eval_recall_macro": 0.23766745468873127, | |
| "eval_recall_micro": 0.24708171206225682, | |
| "eval_recall_weighted": 0.24708171206225682, | |
| "eval_runtime": 145.8531, | |
| "eval_samples_per_second": 3.524, | |
| "eval_steps_per_second": 0.226, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.027237354085603, | |
| "grad_norm": 25.507699966430664, | |
| "learning_rate": 2.1393841166936794e-05, | |
| "loss": 1.899, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.0739299610894941, | |
| "grad_norm": 9.898531913757324, | |
| "learning_rate": 2.2366288492706648e-05, | |
| "loss": 1.8896, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 1.1206225680933852, | |
| "grad_norm": 5.515951633453369, | |
| "learning_rate": 2.3338735818476502e-05, | |
| "loss": 1.9243, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.1673151750972763, | |
| "grad_norm": 9.817304611206055, | |
| "learning_rate": 2.4311183144246355e-05, | |
| "loss": 1.8037, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2140077821011672, | |
| "grad_norm": 8.220943450927734, | |
| "learning_rate": 2.5283630470016206e-05, | |
| "loss": 1.843, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.2607003891050583, | |
| "grad_norm": 5.196465492248535, | |
| "learning_rate": 2.625607779578606e-05, | |
| "loss": 1.7539, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.3073929961089494, | |
| "grad_norm": 8.13240909576416, | |
| "learning_rate": 2.7228525121555913e-05, | |
| "loss": 1.8114, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.3540856031128405, | |
| "grad_norm": 7.483870506286621, | |
| "learning_rate": 2.820097244732577e-05, | |
| "loss": 1.7426, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.4007782101167314, | |
| "grad_norm": 11.400574684143066, | |
| "learning_rate": 2.9173419773095624e-05, | |
| "loss": 1.8409, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.4474708171206225, | |
| "grad_norm": 15.863828659057617, | |
| "learning_rate": 3.014586709886548e-05, | |
| "loss": 1.6875, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.4941634241245136, | |
| "grad_norm": 4.706288814544678, | |
| "learning_rate": 3.111831442463534e-05, | |
| "loss": 1.8176, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.5408560311284045, | |
| "grad_norm": 10.757370948791504, | |
| "learning_rate": 3.209076175040519e-05, | |
| "loss": 1.7746, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.5875486381322959, | |
| "grad_norm": 10.204288482666016, | |
| "learning_rate": 3.3063209076175045e-05, | |
| "loss": 1.8216, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.6342412451361867, | |
| "grad_norm": 9.947104454040527, | |
| "learning_rate": 3.40356564019449e-05, | |
| "loss": 1.6656, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.6809338521400778, | |
| "grad_norm": 10.421720504760742, | |
| "learning_rate": 3.500810372771475e-05, | |
| "loss": 1.732, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.727626459143969, | |
| "grad_norm": 10.406159400939941, | |
| "learning_rate": 3.5980551053484606e-05, | |
| "loss": 1.6426, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.7743190661478598, | |
| "grad_norm": 6.852759838104248, | |
| "learning_rate": 3.695299837925446e-05, | |
| "loss": 1.9205, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.821011673151751, | |
| "grad_norm": 8.486828804016113, | |
| "learning_rate": 3.7925445705024314e-05, | |
| "loss": 1.7752, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.867704280155642, | |
| "grad_norm": 6.236423969268799, | |
| "learning_rate": 3.889789303079417e-05, | |
| "loss": 1.7871, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.914396887159533, | |
| "grad_norm": 5.621742248535156, | |
| "learning_rate": 3.987034035656402e-05, | |
| "loss": 1.8508, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.9610894941634243, | |
| "grad_norm": 11.434782981872559, | |
| "learning_rate": 4.0842787682333875e-05, | |
| "loss": 1.821, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.26653696498054474, | |
| "eval_f1_macro": 0.22749841710333368, | |
| "eval_f1_micro": 0.26653696498054474, | |
| "eval_f1_weighted": 0.23467290371308847, | |
| "eval_loss": 1.798496961593628, | |
| "eval_precision_macro": 0.2675680367049088, | |
| "eval_precision_micro": 0.26653696498054474, | |
| "eval_precision_weighted": 0.277737992326741, | |
| "eval_recall_macro": 0.2594956658786446, | |
| "eval_recall_micro": 0.26653696498054474, | |
| "eval_recall_weighted": 0.26653696498054474, | |
| "eval_runtime": 139.4857, | |
| "eval_samples_per_second": 3.685, | |
| "eval_steps_per_second": 0.237, | |
| "step": 514 | |
| } | |
| ], | |
| "logging_steps": 12, | |
| "max_steps": 6168, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 24, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "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": 272097747757056.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |