| { | |
| "best_metric": 0.49748743718592964, | |
| "best_model_checkpoint": "videomae-base-finetuned-ElderReact-anger-balancedf1/checkpoint-75", | |
| "epoch": 9.0625, | |
| "eval_steps": 500, | |
| "global_step": 240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 3.997068166732788, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.7186, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 3.005845785140991, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.7339, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_f1": 0.4463276836158192, | |
| "eval_loss": 0.6864726543426514, | |
| "eval_runtime": 171.9816, | |
| "eval_samples_per_second": 2.442, | |
| "eval_steps_per_second": 0.157, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 6.235264301300049, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.7253, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 3.536816358566284, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.7024, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 12.325151443481445, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.7007, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_f1": 0.047619047619047616, | |
| "eval_loss": 0.7107335925102234, | |
| "eval_runtime": 176.4951, | |
| "eval_samples_per_second": 2.38, | |
| "eval_steps_per_second": 0.153, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 2.6023736000061035, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6583, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 4.512753963470459, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.6854, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_f1": 0.49748743718592964, | |
| "eval_loss": 0.6994316577911377, | |
| "eval_runtime": 178.8944, | |
| "eval_samples_per_second": 2.348, | |
| "eval_steps_per_second": 0.151, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "grad_norm": 5.125423908233643, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.7021, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "grad_norm": 3.5603673458099365, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.6419, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "grad_norm": 21.498886108398438, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.715, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_f1": 0.13333333333333333, | |
| "eval_loss": 0.7238408923149109, | |
| "eval_runtime": 178.3055, | |
| "eval_samples_per_second": 2.356, | |
| "eval_steps_per_second": 0.151, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "grad_norm": 3.3730030059814453, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.6555, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "grad_norm": 6.0418829917907715, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.6866, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "eval_f1": 0.01951219512195122, | |
| "eval_loss": 0.7563002109527588, | |
| "eval_runtime": 176.1376, | |
| "eval_samples_per_second": 2.384, | |
| "eval_steps_per_second": 0.153, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "grad_norm": 6.097543716430664, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.7311, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "grad_norm": 2.698549509048462, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.5913, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "grad_norm": 17.406471252441406, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.6564, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "eval_f1": 0.15637860082304528, | |
| "eval_loss": 0.7628450393676758, | |
| "eval_runtime": 177.1888, | |
| "eval_samples_per_second": 2.37, | |
| "eval_steps_per_second": 0.152, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "grad_norm": 4.0975470542907715, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.598, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "grad_norm": 4.26428747177124, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.5809, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_f1": 0.38311688311688313, | |
| "eval_loss": 0.7543146014213562, | |
| "eval_runtime": 167.9465, | |
| "eval_samples_per_second": 2.501, | |
| "eval_steps_per_second": 0.161, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "grad_norm": 2.8742892742156982, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.4884, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "grad_norm": 4.310091972351074, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.5761, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "grad_norm": 3.7042274475097656, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.6035, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_f1": 0.21224489795918366, | |
| "eval_loss": 0.7982825040817261, | |
| "eval_runtime": 168.7315, | |
| "eval_samples_per_second": 2.489, | |
| "eval_steps_per_second": 0.16, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "grad_norm": 4.604009628295898, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.5098, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "grad_norm": 3.782595157623291, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.6153, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "eval_f1": 0.40634920634920635, | |
| "eval_loss": 0.7542010545730591, | |
| "eval_runtime": 176.9739, | |
| "eval_samples_per_second": 2.373, | |
| "eval_steps_per_second": 0.153, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "grad_norm": 3.7313973903656006, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.5072, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "grad_norm": 2.534163475036621, | |
| "learning_rate": 0.0, | |
| "loss": 0.5099, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "eval_f1": 0.4525993883792049, | |
| "eval_loss": 0.7408385276794434, | |
| "eval_runtime": 159.3385, | |
| "eval_samples_per_second": 2.636, | |
| "eval_steps_per_second": 0.169, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "step": 240, | |
| "total_flos": 4.616669303992812e+18, | |
| "train_loss": 0.6372330923875172, | |
| "train_runtime": 3422.175, | |
| "train_samples_per_second": 1.122, | |
| "train_steps_per_second": 0.07 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "eval_f1": 0.5797752808988764, | |
| "eval_loss": 0.7431801557540894, | |
| "eval_runtime": 150.1599, | |
| "eval_samples_per_second": 2.537, | |
| "eval_steps_per_second": 0.16, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "eval_f1": 0.5797752808988764, | |
| "eval_loss": 0.7424257397651672, | |
| "eval_runtime": 135.4113, | |
| "eval_samples_per_second": 2.814, | |
| "eval_steps_per_second": 0.177, | |
| "step": 240 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 4.616669303992812e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |