| { | |
| "best_metric": 0.14545454545454545, | |
| "best_model_checkpoint": "videomae-base-finetuned-kinetics-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": 10.89427661895752, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.9195, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 9.84024715423584, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.9823, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 15.709190368652344, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.9911, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 17.095855712890625, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 2.0181, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 10.043827056884766, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 1.9888, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 10.363592147827148, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 1.937, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 9.244985580444336, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.9099, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 6.264003753662109, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 2.0108, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 7.295020580291748, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 1.8789, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 5.525545120239258, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 1.9794, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 5.664557456970215, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 2.0856, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 6.291672706604004, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 2.0504, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 9.917661666870117, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 1.902, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 8.238541603088379, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.9035, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 11.320600509643555, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 1.951, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 8.543054580688477, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 1.9308, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 8.997832298278809, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.9112, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 7.9026713371276855, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 1.9884, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 4.980269908905029, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 2.0268, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.10909090909090909, | |
| "eval_loss": 2.038116931915283, | |
| "eval_runtime": 13.0712, | |
| "eval_samples_per_second": 4.208, | |
| "eval_steps_per_second": 2.142, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 5.153656959533691, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 1.9254, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 5.691870212554932, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 2.0473, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 3.863321304321289, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 2.0271, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 3.6589486598968506, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 1.8714, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 4.852847576141357, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 2.0027, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 3.800025463104248, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 1.9541, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 3.3564181327819824, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.9262, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 4.314349174499512, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 2.0122, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 3.4683678150177, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 2.0268, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 5.209654808044434, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 1.8604, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 7.990084171295166, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 1.9207, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 7.0981950759887695, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 1.8903, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 11.933561325073242, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 1.8676, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 9.403660774230957, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 1.9368, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 7.650759696960449, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 1.7748, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 8.465459823608398, | |
| "learning_rate": 0.0, | |
| "loss": 1.8411, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.14545454545454545, | |
| "eval_loss": 1.8625677824020386, | |
| "eval_runtime": 13.2287, | |
| "eval_samples_per_second": 4.158, | |
| "eval_steps_per_second": 2.117, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "step": 350, | |
| "total_flos": 8.710379865046057e+17, | |
| "train_loss": 1.9500097220284598, | |
| "train_runtime": 289.2328, | |
| "train_samples_per_second": 2.42, | |
| "train_steps_per_second": 1.21 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.16911764705882354, | |
| "eval_loss": 1.9171618223190308, | |
| "eval_runtime": 33.8698, | |
| "eval_samples_per_second": 4.015, | |
| "eval_steps_per_second": 2.008, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.16911764705882354, | |
| "eval_loss": 1.9171618223190308, | |
| "eval_runtime": 34.3798, | |
| "eval_samples_per_second": 3.956, | |
| "eval_steps_per_second": 1.978, | |
| "step": 350 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 350, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 8.710379865046057e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |