| { | |
| "best_metric": 0.8414901387874361, | |
| "best_model_checkpoint": "videomae-base-finetuned-ElderReact-anger/checkpoint-231", | |
| "epoch": 4.189473684210526, | |
| "eval_steps": 500, | |
| "global_step": 380, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 9.803234100341797, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 0.6756, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 3.9001967906951904, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.6072, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 5.898644924163818, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.639, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 4.6400651931762695, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.6533, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 2.0733180046081543, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 0.5862, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.681271553039551, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.6974, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 3.2247824668884277, | |
| "learning_rate": 4.5321637426900585e-05, | |
| "loss": 0.6521, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_f1": 0.8396501457725948, | |
| "eval_loss": 0.5760672092437744, | |
| "eval_runtime": 1244.145, | |
| "eval_samples_per_second": 0.64, | |
| "eval_steps_per_second": 0.08, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 3.428652286529541, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.5924, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 2.4199066162109375, | |
| "learning_rate": 4.239766081871345e-05, | |
| "loss": 0.6198, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 1.6612868309020996, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.7013, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 6.7560296058654785, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.6165, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 1.1539256572723389, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.6262, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 1.500359296798706, | |
| "learning_rate": 3.654970760233918e-05, | |
| "loss": 0.6867, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 5.01125431060791, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.6146, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 6.541323661804199, | |
| "learning_rate": 3.362573099415205e-05, | |
| "loss": 0.5836, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_f1": 0.8396501457725948, | |
| "eval_loss": 0.5899893045425415, | |
| "eval_runtime": 1102.8397, | |
| "eval_samples_per_second": 0.722, | |
| "eval_steps_per_second": 0.091, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 1.118071436882019, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.7149, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 1.7673434019088745, | |
| "learning_rate": 3.0701754385964913e-05, | |
| "loss": 0.691, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 1.951958179473877, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.6627, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 3.83512806892395, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5765, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 2.5325303077697754, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.5841, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 1.832468867301941, | |
| "learning_rate": 2.485380116959064e-05, | |
| "loss": 0.5493, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 1.6643192768096924, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.4687, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 6.444340705871582, | |
| "learning_rate": 2.1929824561403507e-05, | |
| "loss": 0.6733, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_f1": 0.8414901387874361, | |
| "eval_loss": 0.5975301861763, | |
| "eval_runtime": 1053.4704, | |
| "eval_samples_per_second": 0.756, | |
| "eval_steps_per_second": 0.095, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "grad_norm": 2.2140614986419678, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.5454, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "grad_norm": 1.7166881561279297, | |
| "learning_rate": 1.9005847953216373e-05, | |
| "loss": 0.5886, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 4.783045768737793, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.6739, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "grad_norm": 1.9788509607315063, | |
| "learning_rate": 1.608187134502924e-05, | |
| "loss": 0.5494, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "grad_norm": 4.0997090339660645, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.6146, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 3.787324905395508, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 0.6205, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "grad_norm": 1.0465867519378662, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.6136, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_f1": 0.8396501457725948, | |
| "eval_loss": 0.5905158519744873, | |
| "eval_runtime": 1159.7833, | |
| "eval_samples_per_second": 0.686, | |
| "eval_steps_per_second": 0.086, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "grad_norm": 7.15081787109375, | |
| "learning_rate": 1.023391812865497e-05, | |
| "loss": 0.6304, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "grad_norm": 3.809471368789673, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.5289, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "grad_norm": 6.606677055358887, | |
| "learning_rate": 7.3099415204678366e-06, | |
| "loss": 0.4864, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "grad_norm": 3.1082494258880615, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.7082, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "grad_norm": 2.4603655338287354, | |
| "learning_rate": 4.3859649122807014e-06, | |
| "loss": 0.5509, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "grad_norm": 3.1572580337524414, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.5476, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 1.5971115827560425, | |
| "learning_rate": 1.4619883040935671e-06, | |
| "loss": 0.5939, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "grad_norm": 1.7118576765060425, | |
| "learning_rate": 0.0, | |
| "loss": 0.5394, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_f1": 0.8350515463917526, | |
| "eval_loss": 0.5992816686630249, | |
| "eval_runtime": 652.5135, | |
| "eval_samples_per_second": 1.22, | |
| "eval_steps_per_second": 0.153, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "step": 380, | |
| "total_flos": 3.783052093636215e+18, | |
| "train_loss": 0.6122152554361444, | |
| "train_runtime": 13314.3168, | |
| "train_samples_per_second": 0.228, | |
| "train_steps_per_second": 0.029 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_f1": 0.8670694864048338, | |
| "eval_loss": 0.6053914427757263, | |
| "eval_runtime": 599.5418, | |
| "eval_samples_per_second": 1.251, | |
| "eval_steps_per_second": 0.157, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_f1": 0.8670694864048338, | |
| "eval_loss": 0.6053914427757263, | |
| "eval_runtime": 599.0073, | |
| "eval_samples_per_second": 1.252, | |
| "eval_steps_per_second": 0.157, | |
| "step": 380 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 380, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 3.783052093636215e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |