| { | |
| "best_metric": 0.24390243902439024, | |
| "best_model_checkpoint": "google/vivit-b-16x2-kinetics400-finetuned-caer-subset\\checkpoint-350", | |
| "epoch": 1.44, | |
| "eval_steps": 500, | |
| "global_step": 350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 19.33121109008789, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.0053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 21.907333374023438, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 2.0683, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 20.9775333404541, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 2.1121, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 23.942533493041992, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 2.0314, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 19.405336380004883, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 2.0158, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 20.04143714904785, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 2.0462, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 18.069730758666992, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.9249, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 17.35310935974121, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 2.0913, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 19.297367095947266, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 2.0567, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 15.96094036102295, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 1.9516, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 14.673310279846191, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 2.2487, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 15.799952507019043, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 2.0393, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 15.999563217163086, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 2.0529, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 15.708507537841797, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.9125, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 15.592299461364746, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 2.0613, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 16.829734802246094, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 2.0227, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 14.447635650634766, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.8975, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 15.35761833190918, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 1.9479, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 13.049636840820312, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 1.8092, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.17073170731707318, | |
| "eval_loss": 1.9746465682983398, | |
| "eval_runtime": 100.3202, | |
| "eval_samples_per_second": 0.409, | |
| "eval_steps_per_second": 0.209, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 11.337438583374023, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 1.7909, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 17.9540958404541, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.5752, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 21.31819725036621, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 1.6633, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 20.168230056762695, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 1.5208, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 19.805814743041992, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 1.6649, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 15.015875816345215, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 1.6386, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 16.992019653320312, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.596, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 23.03261947631836, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 1.7409, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 15.26242446899414, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.741, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 15.778162002563477, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 1.4856, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 17.042863845825195, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 1.6621, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 13.777763366699219, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 1.6578, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 19.213926315307617, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 1.6702, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 18.964433670043945, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 1.7152, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 16.059499740600586, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 1.6965, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 19.16345977783203, | |
| "learning_rate": 0.0, | |
| "loss": 1.4353, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.24390243902439024, | |
| "eval_loss": 1.8479658365249634, | |
| "eval_runtime": 99.2431, | |
| "eval_samples_per_second": 0.413, | |
| "eval_steps_per_second": 0.212, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "step": 350, | |
| "total_flos": 1.7909488009738322e+18, | |
| "train_loss": 1.844291558946882, | |
| "train_runtime": 2641.0626, | |
| "train_samples_per_second": 0.265, | |
| "train_steps_per_second": 0.133 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.23300970873786409, | |
| "eval_loss": 1.8412702083587646, | |
| "eval_runtime": 251.1857, | |
| "eval_samples_per_second": 0.41, | |
| "eval_steps_per_second": 0.207, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.23300970873786409, | |
| "eval_loss": 1.8412706851959229, | |
| "eval_runtime": 255.9942, | |
| "eval_samples_per_second": 0.402, | |
| "eval_steps_per_second": 0.203, | |
| "step": 350 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 350, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 1.7909488009738322e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |