| { | |
| "best_metric": 0.11816192560175055, | |
| "best_model_checkpoint": "videomae-base-finetuned-ssv2-finetuned-ucf101-subset\\checkpoint-433", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 433, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023094688221709007, | |
| "grad_norm": 25.757522583007812, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 5.5037, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.046189376443418015, | |
| "grad_norm": 25.24021339416504, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 5.2613, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06928406466512702, | |
| "grad_norm": 22.77121353149414, | |
| "learning_rate": 3.409090909090909e-05, | |
| "loss": 5.0758, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09237875288683603, | |
| "grad_norm": 31.911174774169922, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 5.2159, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11547344110854503, | |
| "grad_norm": 26.340246200561523, | |
| "learning_rate": 4.922879177377892e-05, | |
| "loss": 5.3368, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13856812933025403, | |
| "grad_norm": 23.175561904907227, | |
| "learning_rate": 4.7943444730077124e-05, | |
| "loss": 5.0119, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16166281755196305, | |
| "grad_norm": 27.339330673217773, | |
| "learning_rate": 4.6658097686375325e-05, | |
| "loss": 5.1378, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18475750577367206, | |
| "grad_norm": 23.49224281311035, | |
| "learning_rate": 4.537275064267352e-05, | |
| "loss": 5.3206, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20785219399538107, | |
| "grad_norm": 23.86919403076172, | |
| "learning_rate": 4.408740359897173e-05, | |
| "loss": 5.2974, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23094688221709006, | |
| "grad_norm": 17.22815704345703, | |
| "learning_rate": 4.280205655526993e-05, | |
| "loss": 5.3859, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2540415704387991, | |
| "grad_norm": 18.21339988708496, | |
| "learning_rate": 4.151670951156812e-05, | |
| "loss": 5.2278, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27713625866050806, | |
| "grad_norm": 18.38885498046875, | |
| "learning_rate": 4.0231362467866324e-05, | |
| "loss": 5.5348, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3002309468822171, | |
| "grad_norm": 17.503589630126953, | |
| "learning_rate": 3.8946015424164526e-05, | |
| "loss": 5.282, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3233256351039261, | |
| "grad_norm": 19.329565048217773, | |
| "learning_rate": 3.766066838046273e-05, | |
| "loss": 4.8012, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3464203233256351, | |
| "grad_norm": 19.029603958129883, | |
| "learning_rate": 3.637532133676093e-05, | |
| "loss": 4.6088, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3695150115473441, | |
| "grad_norm": 20.106794357299805, | |
| "learning_rate": 3.508997429305913e-05, | |
| "loss": 4.7802, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.39260969976905313, | |
| "grad_norm": 22.443622589111328, | |
| "learning_rate": 3.380462724935733e-05, | |
| "loss": 4.9326, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41570438799076215, | |
| "grad_norm": 19.69178581237793, | |
| "learning_rate": 3.251928020565553e-05, | |
| "loss": 5.1273, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4387990762124711, | |
| "grad_norm": 16.72547721862793, | |
| "learning_rate": 3.1233933161953726e-05, | |
| "loss": 4.9395, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4618937644341801, | |
| "grad_norm": 21.63971710205078, | |
| "learning_rate": 2.994858611825193e-05, | |
| "loss": 4.3805, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.48498845265588914, | |
| "grad_norm": 16.757349014282227, | |
| "learning_rate": 2.866323907455013e-05, | |
| "loss": 5.0902, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5080831408775982, | |
| "grad_norm": 16.207763671875, | |
| "learning_rate": 2.737789203084833e-05, | |
| "loss": 5.0768, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5311778290993071, | |
| "grad_norm": 21.602184295654297, | |
| "learning_rate": 2.6092544987146534e-05, | |
| "loss": 4.511, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5542725173210161, | |
| "grad_norm": 15.503689765930176, | |
| "learning_rate": 2.480719794344473e-05, | |
| "loss": 5.3379, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5773672055427251, | |
| "grad_norm": 16.484134674072266, | |
| "learning_rate": 2.3521850899742933e-05, | |
| "loss": 5.0716, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6004618937644342, | |
| "grad_norm": 28.777589797973633, | |
| "learning_rate": 2.2236503856041134e-05, | |
| "loss": 5.3695, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6235565819861432, | |
| "grad_norm": 33.19585037231445, | |
| "learning_rate": 2.095115681233933e-05, | |
| "loss": 5.2579, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6466512702078522, | |
| "grad_norm": 14.972123146057129, | |
| "learning_rate": 1.9665809768637533e-05, | |
| "loss": 4.9582, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6697459584295612, | |
| "grad_norm": 15.122587203979492, | |
| "learning_rate": 1.8380462724935734e-05, | |
| "loss": 5.4649, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6928406466512702, | |
| "grad_norm": 15.101243019104004, | |
| "learning_rate": 1.7095115681233935e-05, | |
| "loss": 5.5053, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7159353348729792, | |
| "grad_norm": 14.751006126403809, | |
| "learning_rate": 1.5809768637532136e-05, | |
| "loss": 5.2739, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7390300230946882, | |
| "grad_norm": 18.56909942626953, | |
| "learning_rate": 1.4524421593830334e-05, | |
| "loss": 5.0441, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7621247113163973, | |
| "grad_norm": 20.036487579345703, | |
| "learning_rate": 1.3239074550128535e-05, | |
| "loss": 4.6066, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7852193995381063, | |
| "grad_norm": 15.724655151367188, | |
| "learning_rate": 1.1953727506426736e-05, | |
| "loss": 4.63, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8083140877598153, | |
| "grad_norm": 27.94047737121582, | |
| "learning_rate": 1.0668380462724936e-05, | |
| "loss": 4.8191, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8314087759815243, | |
| "grad_norm": 18.26154899597168, | |
| "learning_rate": 9.383033419023137e-06, | |
| "loss": 4.3258, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8545034642032333, | |
| "grad_norm": 21.948999404907227, | |
| "learning_rate": 8.097686375321336e-06, | |
| "loss": 5.2392, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8775981524249422, | |
| "grad_norm": 18.45208740234375, | |
| "learning_rate": 6.812339331619537e-06, | |
| "loss": 5.2617, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9006928406466512, | |
| "grad_norm": 23.426355361938477, | |
| "learning_rate": 5.526992287917738e-06, | |
| "loss": 4.9801, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9237875288683602, | |
| "grad_norm": 23.681772232055664, | |
| "learning_rate": 4.241645244215939e-06, | |
| "loss": 5.2054, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9468822170900693, | |
| "grad_norm": 25.422988891601562, | |
| "learning_rate": 2.956298200514139e-06, | |
| "loss": 4.9923, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9699769053117783, | |
| "grad_norm": 25.6311092376709, | |
| "learning_rate": 1.6709511568123394e-06, | |
| "loss": 5.4941, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9930715935334873, | |
| "grad_norm": 21.09837532043457, | |
| "learning_rate": 3.8560411311053987e-07, | |
| "loss": 5.2022, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.11816192560175055, | |
| "eval_loss": 4.614536762237549, | |
| "eval_runtime": 1618.8123, | |
| "eval_samples_per_second": 0.282, | |
| "eval_steps_per_second": 0.282, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 433, | |
| "total_flos": 5.405323753225912e+17, | |
| "train_loss": 5.075382356004957, | |
| "train_runtime": 5788.9979, | |
| "train_samples_per_second": 0.075, | |
| "train_steps_per_second": 0.075 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.10382513661202186, | |
| "eval_loss": 4.723412990570068, | |
| "eval_runtime": 2027.4251, | |
| "eval_samples_per_second": 0.271, | |
| "eval_steps_per_second": 0.271, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.10382513661202186, | |
| "eval_loss": 4.723412990570068, | |
| "eval_runtime": 1903.4725, | |
| "eval_samples_per_second": 0.288, | |
| "eval_steps_per_second": 0.288, | |
| "step": 433 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 433, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "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": 5.405323753225912e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |