| { | |
| "best_metric": 0.9625, | |
| "best_model_checkpoint": "timesformer-base-finetuned-k400-finetuned-asl/checkpoint-90", | |
| "epoch": 3.25, | |
| "eval_steps": 500, | |
| "global_step": 360, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 2.0901, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.7266, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.4769, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 1.0936, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.783950617283951e-05, | |
| "loss": 0.824, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.8398, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.4753086419753084e-05, | |
| "loss": 0.435, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.6051, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.3325, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.9625, | |
| "eval_loss": 0.2076590359210968, | |
| "eval_runtime": 78.5536, | |
| "eval_samples_per_second": 1.018, | |
| "eval_steps_per_second": 0.127, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.3724, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.8580246913580246e-05, | |
| "loss": 0.3341, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2816, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.5493827160493834e-05, | |
| "loss": 0.393, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.1777, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.3507, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.462, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9320987654320992e-05, | |
| "loss": 0.3912, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2898, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.9375, | |
| "eval_loss": 0.1923440843820572, | |
| "eval_runtime": 76.3, | |
| "eval_samples_per_second": 1.048, | |
| "eval_steps_per_second": 0.131, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.623456790123457e-05, | |
| "loss": 0.2911, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.3739, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.1862, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.1881, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.006172839506173e-05, | |
| "loss": 0.2464, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2937, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.697530864197531e-05, | |
| "loss": 0.3399, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 0.2323, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.3358, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.95, | |
| "eval_loss": 0.11704353988170624, | |
| "eval_runtime": 78.6154, | |
| "eval_samples_per_second": 1.018, | |
| "eval_steps_per_second": 0.127, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.2584, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.0802469135802469e-05, | |
| "loss": 0.2827, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1856, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.71604938271605e-06, | |
| "loss": 0.3021, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.3106, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.2224, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.145, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.5432098765432098e-06, | |
| "loss": 0.174, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.3354, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.9625, | |
| "eval_loss": 0.1142113208770752, | |
| "eval_runtime": 76.7347, | |
| "eval_samples_per_second": 1.043, | |
| "eval_steps_per_second": 0.13, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "step": 360, | |
| "total_flos": 2.523400261997691e+18, | |
| "train_loss": 0.4772139224741194, | |
| "train_runtime": 3683.9124, | |
| "train_samples_per_second": 0.782, | |
| "train_steps_per_second": 0.098 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 360, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 2.523400261997691e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |