| { | |
| "best_metric": 0.6, | |
| "best_model_checkpoint": "videomae-base-finetuned-SSBD_Augm_v2/checkpoint-42", | |
| "epoch": 8.04, | |
| "global_step": 350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.1543, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.1043, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.1309, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 1.0891, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.9088060855865479, | |
| "eval_runtime": 25.1399, | |
| "eval_samples_per_second": 0.994, | |
| "eval_steps_per_second": 0.119, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.972, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 1.0649, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9936, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.0414, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.4, | |
| "eval_loss": 1.1233173608779907, | |
| "eval_runtime": 18.9992, | |
| "eval_samples_per_second": 1.316, | |
| "eval_steps_per_second": 0.158, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 1.1475, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 1.3312, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.8461, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 0.7054, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_accuracy": 0.44, | |
| "eval_loss": 1.0407100915908813, | |
| "eval_runtime": 18.9487, | |
| "eval_samples_per_second": 1.319, | |
| "eval_steps_per_second": 0.158, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 0.7719, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4189, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.369, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 1.0071, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_accuracy": 0.2, | |
| "eval_loss": 1.6253796815872192, | |
| "eval_runtime": 19.0795, | |
| "eval_samples_per_second": 1.31, | |
| "eval_steps_per_second": 0.157, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.3392, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 0.1986, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 0.4473, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.1842, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.2627, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_accuracy": 0.24, | |
| "eval_loss": 2.7734763622283936, | |
| "eval_runtime": 18.7713, | |
| "eval_samples_per_second": 1.332, | |
| "eval_steps_per_second": 0.16, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 0.1376, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 0.2114, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 0.0106, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.0226, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_accuracy": 0.12, | |
| "eval_loss": 4.147406578063965, | |
| "eval_runtime": 18.8262, | |
| "eval_samples_per_second": 1.328, | |
| "eval_steps_per_second": 0.159, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.0397, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.0067, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0386, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 0.0065, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "eval_accuracy": 0.08, | |
| "eval_loss": 4.598020553588867, | |
| "eval_runtime": 18.8972, | |
| "eval_samples_per_second": 1.323, | |
| "eval_steps_per_second": 0.159, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.0257, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 0.0028, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 0.0024, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 0.012, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "eval_accuracy": 0.08, | |
| "eval_loss": 4.68769645690918, | |
| "eval_runtime": 19.1009, | |
| "eval_samples_per_second": 1.309, | |
| "eval_steps_per_second": 0.157, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 0.0026, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 0.0, | |
| "loss": 0.0027, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_accuracy": 0.08, | |
| "eval_loss": 4.665265083312988, | |
| "eval_runtime": 19.0665, | |
| "eval_samples_per_second": 1.311, | |
| "eval_steps_per_second": 0.157, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "step": 350, | |
| "total_flos": 5.163737709298582e+18, | |
| "train_loss": 0.4886108534836343, | |
| "train_runtime": 1664.1582, | |
| "train_samples_per_second": 2.524, | |
| "train_steps_per_second": 0.21 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.9088060259819031, | |
| "eval_runtime": 19.0866, | |
| "eval_samples_per_second": 1.31, | |
| "eval_steps_per_second": 0.157, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_accuracy": 0.6190476190476191, | |
| "eval_loss": 0.9006302952766418, | |
| "eval_runtime": 8.9559, | |
| "eval_samples_per_second": 2.345, | |
| "eval_steps_per_second": 0.223, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_accuracy": 0.6190476190476191, | |
| "eval_loss": 0.9006302952766418, | |
| "eval_runtime": 3.5286, | |
| "eval_samples_per_second": 5.951, | |
| "eval_steps_per_second": 0.567, | |
| "step": 350 | |
| } | |
| ], | |
| "max_steps": 350, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 5.163737709298582e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |