| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "whisper-base-ft/checkpoint-292", | |
| "epoch": 9.0, | |
| "global_step": 2628, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.561643835616439e-07, | |
| "loss": 0.6917, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.7123287671232877e-06, | |
| "loss": 0.689, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.568493150684932e-06, | |
| "loss": 0.6774, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.4246575342465754e-06, | |
| "loss": 0.5974, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.28082191780822e-06, | |
| "loss": 0.3433, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.136986301369864e-06, | |
| "loss": 0.1137, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.993150684931507e-06, | |
| "loss": 0.0302, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.849315068493151e-06, | |
| "loss": 0.0061, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.705479452054794e-06, | |
| "loss": 0.0086, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.56164383561644e-06, | |
| "loss": 0.0025, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.417808219178083e-06, | |
| "loss": 0.0037, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0018677616026252508, | |
| "eval_runtime": 4.1932, | |
| "eval_samples_per_second": 23.848, | |
| "eval_steps_per_second": 1.669, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.969558599695586e-06, | |
| "loss": 0.0024, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.874429223744293e-06, | |
| "loss": 0.0017, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 9.779299847792999e-06, | |
| "loss": 0.001, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 9.684170471841705e-06, | |
| "loss": 0.0008, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.589041095890411e-06, | |
| "loss": 0.006, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 9.493911719939119e-06, | |
| "loss": 0.0007, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 9.398782343987825e-06, | |
| "loss": 0.0006, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.303652968036531e-06, | |
| "loss": 0.0005, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.208523592085237e-06, | |
| "loss": 0.001, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.113394216133943e-06, | |
| "loss": 0.0005, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 9.01826484018265e-06, | |
| "loss": 0.0004, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.923135464231355e-06, | |
| "loss": 0.0059, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.000401403900468722, | |
| "eval_runtime": 4.2497, | |
| "eval_samples_per_second": 23.531, | |
| "eval_steps_per_second": 1.647, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.828006088280061e-06, | |
| "loss": 0.0004, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.732876712328769e-06, | |
| "loss": 0.001, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.637747336377475e-06, | |
| "loss": 0.0004, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.542617960426181e-06, | |
| "loss": 0.0004, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.447488584474887e-06, | |
| "loss": 0.0003, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.352359208523594e-06, | |
| "loss": 0.0002, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 8.2572298325723e-06, | |
| "loss": 0.0002, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 8.162100456621006e-06, | |
| "loss": 0.0002, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 8.066971080669712e-06, | |
| "loss": 0.0007, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.971841704718418e-06, | |
| "loss": 0.0028, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 7.876712328767124e-06, | |
| "loss": 0.0091, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.78158295281583e-06, | |
| "loss": 0.0005, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00028352142544463277, | |
| "eval_runtime": 4.4612, | |
| "eval_samples_per_second": 22.416, | |
| "eval_steps_per_second": 1.569, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 7.686453576864536e-06, | |
| "loss": 0.0019, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 7.591324200913242e-06, | |
| "loss": 0.0013, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 7.496194824961948e-06, | |
| "loss": 0.0008, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 7.4010654490106545e-06, | |
| "loss": 0.0009, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 7.305936073059361e-06, | |
| "loss": 0.0002, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 7.210806697108067e-06, | |
| "loss": 0.0002, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 7.1156773211567745e-06, | |
| "loss": 0.0002, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 7.020547945205481e-06, | |
| "loss": 0.0001, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 6.925418569254187e-06, | |
| "loss": 0.0001, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 6.830289193302893e-06, | |
| "loss": 0.0007, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 6.735159817351599e-06, | |
| "loss": 0.0003, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0001292741362703964, | |
| "eval_runtime": 4.3055, | |
| "eval_samples_per_second": 23.226, | |
| "eval_steps_per_second": 1.626, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 6.640030441400305e-06, | |
| "loss": 0.0001, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 6.544901065449011e-06, | |
| "loss": 0.0005, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 6.449771689497717e-06, | |
| "loss": 0.005, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 6.354642313546424e-06, | |
| "loss": 0.0002, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 6.25951293759513e-06, | |
| "loss": 0.004, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 6.168188736681888e-06, | |
| "loss": 0.0029, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 6.073059360730594e-06, | |
| "loss": 0.0001, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 5.9779299847793e-06, | |
| "loss": 0.0001, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 5.882800608828006e-06, | |
| "loss": 0.0019, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 5.7876712328767125e-06, | |
| "loss": 0.0001, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 5.6925418569254186e-06, | |
| "loss": 0.0001, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 5.597412480974125e-06, | |
| "loss": 0.0001, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0001045739627443254, | |
| "eval_runtime": 4.1825, | |
| "eval_samples_per_second": 23.909, | |
| "eval_steps_per_second": 1.674, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 5.502283105022832e-06, | |
| "loss": 0.0001, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 5.407153729071538e-06, | |
| "loss": 0.0003, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 5.312024353120245e-06, | |
| "loss": 0.0001, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 5.216894977168951e-06, | |
| "loss": 0.0001, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 5.121765601217657e-06, | |
| "loss": 0.0002, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 5.026636225266363e-06, | |
| "loss": 0.0002, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 4.931506849315069e-06, | |
| "loss": 0.0009, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 4.836377473363775e-06, | |
| "loss": 0.0029, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 4.741248097412481e-06, | |
| "loss": 0.0001, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 4.646118721461187e-06, | |
| "loss": 0.0001, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 4.550989345509893e-06, | |
| "loss": 0.0001, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 4.4558599695586e-06, | |
| "loss": 0.0001, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 8.005261770449579e-05, | |
| "eval_runtime": 4.4258, | |
| "eval_samples_per_second": 22.595, | |
| "eval_steps_per_second": 1.582, | |
| "step": 1752 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.3607305936073065e-06, | |
| "loss": 0.0001, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 4.2656012176560126e-06, | |
| "loss": 0.0006, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 4.170471841704719e-06, | |
| "loss": 0.0004, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 4.075342465753426e-06, | |
| "loss": 0.0001, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 3.980213089802132e-06, | |
| "loss": 0.0001, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 3.885083713850838e-06, | |
| "loss": 0.0004, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 3.7899543378995435e-06, | |
| "loss": 0.0001, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 3.69482496194825e-06, | |
| "loss": 0.0001, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 3.599695585996956e-06, | |
| "loss": 0.0001, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 3.504566210045662e-06, | |
| "loss": 0.0001, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 3.4094368340943683e-06, | |
| "loss": 0.0001, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 6.137609307188541e-05, | |
| "eval_runtime": 4.0915, | |
| "eval_samples_per_second": 24.441, | |
| "eval_steps_per_second": 1.711, | |
| "step": 2044 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 3.3143074581430752e-06, | |
| "loss": 0.0001, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 3.2191780821917813e-06, | |
| "loss": 0.0001, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 3.1240487062404874e-06, | |
| "loss": 0.0001, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 3.0289193302891935e-06, | |
| "loss": 0.0002, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 2.9337899543379e-06, | |
| "loss": 0.0001, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 2.838660578386606e-06, | |
| "loss": 0.0001, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 2.7435312024353122e-06, | |
| "loss": 0.0001, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 2.6484018264840183e-06, | |
| "loss": 0.0001, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 2.553272450532725e-06, | |
| "loss": 0.0001, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 2.458143074581431e-06, | |
| "loss": 0.0001, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 2.363013698630137e-06, | |
| "loss": 0.0001, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 2.267884322678843e-06, | |
| "loss": 0.0, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 5.370378494262695e-05, | |
| "eval_runtime": 4.28, | |
| "eval_samples_per_second": 23.364, | |
| "eval_steps_per_second": 1.636, | |
| "step": 2336 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 2.1727549467275497e-06, | |
| "loss": 0.0002, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 2.0776255707762557e-06, | |
| "loss": 0.0, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 1.9824961948249623e-06, | |
| "loss": 0.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 1.8873668188736682e-06, | |
| "loss": 0.0, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 1.7922374429223747e-06, | |
| "loss": 0.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 1.6971080669710808e-06, | |
| "loss": 0.0001, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 1.601978691019787e-06, | |
| "loss": 0.0001, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 1.5068493150684932e-06, | |
| "loss": 0.0, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 1.4117199391171995e-06, | |
| "loss": 0.0001, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 1.3165905631659056e-06, | |
| "loss": 0.0001, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 1.2214611872146119e-06, | |
| "loss": 0.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 1.1263318112633182e-06, | |
| "loss": 0.0, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 4.9449205107521266e-05, | |
| "eval_runtime": 4.2858, | |
| "eval_samples_per_second": 23.333, | |
| "eval_steps_per_second": 1.633, | |
| "step": 2628 | |
| } | |
| ], | |
| "max_steps": 2920, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.41644683759616e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |