8dd207761c
Model: BAAI_Industry_Competition_tourism_dev/eatbreakfast_TouInd Source: Original Platform
63 lines
30 KiB
JSON
63 lines
30 KiB
JSON
{"loss": 0.93224913, "acc": 0.76220244, "grad_norm": 0.54498851, "learning_rate": 3.33e-06, "memory(GiB)": 19.94, "train_speed(iter/s)": 0.017019, "epoch": 0.0060652, "global_step/max_steps": "1/492", "percentage": "0.20%", "elapsed_time": "58s", "remaining_time": "7h 57m 39s"}
|
|
{"loss": 0.91722838, "acc": 0.75826671, "grad_norm": 0.46433684, "learning_rate": 3.333e-05, "memory(GiB)": 20.11, "train_speed(iter/s)": 0.017934, "epoch": 0.06065201, "global_step/max_steps": "10/492", "percentage": "2.03%", "elapsed_time": "9m 17s", "remaining_time": "7h 27m 37s"}
|
|
{"loss": 0.86249514, "acc": 0.75574059, "grad_norm": 0.41435161, "learning_rate": 4.999e-05, "memory(GiB)": 20.19, "train_speed(iter/s)": 0.018374, "epoch": 0.12130402, "global_step/max_steps": "20/492", "percentage": "4.07%", "elapsed_time": "18m 8s", "remaining_time": "7h 7m 59s"}
|
|
{"loss": 0.75827727, "acc": 0.78193603, "grad_norm": 0.34862646, "learning_rate": 4.988e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.018113, "epoch": 0.18195603, "global_step/max_steps": "30/492", "percentage": "6.10%", "elapsed_time": "27m 35s", "remaining_time": "7h 5m 0s"}
|
|
{"loss": 0.72877254, "acc": 0.79074349, "grad_norm": 0.35325161, "learning_rate": 4.966e-05, "memory(GiB)": 20.18, "train_speed(iter/s)": 0.018128, "epoch": 0.24260804, "global_step/max_steps": "40/492", "percentage": "8.13%", "elapsed_time": "36m 46s", "remaining_time": "6h 55m 29s"}
|
|
{"loss": 0.69353862, "acc": 0.80020571, "grad_norm": 0.38382262, "learning_rate": 4.934e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.018059, "epoch": 0.30326005, "global_step/max_steps": "50/492", "percentage": "10.16%", "elapsed_time": "46m 8s", "remaining_time": "6h 47m 51s"}
|
|
{"eval_loss": 0.67298102, "eval_acc": 0.78022802, "eval_runtime": 33.3888, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 0.30326005, "global_step/max_steps": "50/492", "percentage": "10.16%", "elapsed_time": "46m 41s", "remaining_time": "6h 52m 46s"}
|
|
{"loss": 0.69440799, "acc": 0.79857101, "grad_norm": 0.3445116, "learning_rate": 4.891e-05, "memory(GiB)": 20.07, "train_speed(iter/s)": 0.017825, "epoch": 0.36391205, "global_step/max_steps": "60/492", "percentage": "12.20%", "elapsed_time": "56m 5s", "remaining_time": "6h 43m 52s"}
|
|
{"loss": 0.71067386, "acc": 0.79230323, "grad_norm": 0.3882418, "learning_rate": 4.838e-05, "memory(GiB)": 20.07, "train_speed(iter/s)": 0.017889, "epoch": 0.42456406, "global_step/max_steps": "70/492", "percentage": "14.23%", "elapsed_time": "1h 5m 12s", "remaining_time": "6h 33m 7s"}
|
|
{"loss": 0.69002156, "acc": 0.7934236, "grad_norm": 0.39019343, "learning_rate": 4.774e-05, "memory(GiB)": 20.07, "train_speed(iter/s)": 0.01793, "epoch": 0.48521607, "global_step/max_steps": "80/492", "percentage": "16.26%", "elapsed_time": "1h 14m 21s", "remaining_time": "6h 22m 56s"}
|
|
{"loss": 0.6877634, "acc": 0.7960094, "grad_norm": 0.38508493, "learning_rate": 4.701e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.017919, "epoch": 0.54586808, "global_step/max_steps": "90/492", "percentage": "18.29%", "elapsed_time": "1h 23m 42s", "remaining_time": "6h 13m 52s"}
|
|
{"loss": 0.70220733, "acc": 0.79615922, "grad_norm": 0.42378929, "learning_rate": 4.618e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.017939, "epoch": 0.60652009, "global_step/max_steps": "100/492", "percentage": "20.33%", "elapsed_time": "1h 32m 54s", "remaining_time": "6h 4m 10s"}
|
|
{"eval_loss": 0.64850187, "eval_acc": 0.78825383, "eval_runtime": 33.3399, "eval_samples_per_second": 0.75, "eval_steps_per_second": 0.75, "epoch": 0.60652009, "global_step/max_steps": "100/492", "percentage": "20.33%", "elapsed_time": "1h 33m 27s", "remaining_time": "6h 6m 21s"}
|
|
{"loss": 0.70293474, "acc": 0.79093747, "grad_norm": 0.39726591, "learning_rate": 4.526e-05, "memory(GiB)": 20.22, "train_speed(iter/s)": 0.017862, "epoch": 0.6671721, "global_step/max_steps": "110/492", "percentage": "22.36%", "elapsed_time": "1h 42m 37s", "remaining_time": "5h 56m 24s"}
|
|
{"loss": 0.66394258, "acc": 0.79998345, "grad_norm": 0.39062959, "learning_rate": 4.426e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.01785, "epoch": 0.72782411, "global_step/max_steps": "120/492", "percentage": "24.39%", "elapsed_time": "1h 52m 2s", "remaining_time": "5h 47m 19s"}
|
|
{"loss": 0.67210622, "acc": 0.80572329, "grad_norm": 0.45497587, "learning_rate": 4.317e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017891, "epoch": 0.78847612, "global_step/max_steps": "130/492", "percentage": "26.42%", "elapsed_time": "2h 1m 5s", "remaining_time": "5h 37m 12s"}
|
|
{"loss": 0.68859334, "acc": 0.7952837, "grad_norm": 0.42970341, "learning_rate": 4.2e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017955, "epoch": 0.84912813, "global_step/max_steps": "140/492", "percentage": "28.46%", "elapsed_time": "2h 9m 57s", "remaining_time": "5h 26m 44s"}
|
|
{"loss": 0.68589358, "acc": 0.79690466, "grad_norm": 0.4068616, "learning_rate": 4.075e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.017997, "epoch": 0.90978014, "global_step/max_steps": "150/492", "percentage": "30.49%", "elapsed_time": "2h 18m 54s", "remaining_time": "5h 16m 42s"}
|
|
{"eval_loss": 0.63688052, "eval_acc": 0.78885389, "eval_runtime": 33.3891, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 0.90978014, "global_step/max_steps": "150/492", "percentage": "30.49%", "elapsed_time": "2h 19m 27s", "remaining_time": "5h 17m 58s"}
|
|
{"loss": 0.67849236, "acc": 0.80027781, "grad_norm": 0.41475204, "learning_rate": 3.944e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.017978, "epoch": 0.97043215, "global_step/max_steps": "160/492", "percentage": "32.52%", "elapsed_time": "2h 28m 19s", "remaining_time": "5h 7m 45s"}
|
|
{"loss": 0.64705005, "acc": 0.8089735, "grad_norm": 0.47182918, "learning_rate": 3.807e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.017992, "epoch": 1.03108415, "global_step/max_steps": "170/492", "percentage": "34.55%", "elapsed_time": "2h 37m 28s", "remaining_time": "4h 58m 15s"}
|
|
{"loss": 0.64267106, "acc": 0.81211033, "grad_norm": 0.4739745, "learning_rate": 3.663e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018023, "epoch": 1.09173616, "global_step/max_steps": "180/492", "percentage": "36.59%", "elapsed_time": "2h 46m 26s", "remaining_time": "4h 48m 30s"}
|
|
{"loss": 0.63020077, "acc": 0.81366587, "grad_norm": 0.47220412, "learning_rate": 3.515e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018044, "epoch": 1.15238817, "global_step/max_steps": "190/492", "percentage": "38.62%", "elapsed_time": "2h 55m 29s", "remaining_time": "4h 38m 56s"}
|
|
{"loss": 0.61844859, "acc": 0.81707268, "grad_norm": 0.48362505, "learning_rate": 3.363e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018021, "epoch": 1.21304018, "global_step/max_steps": "200/492", "percentage": "40.65%", "elapsed_time": "3h 4m 57s", "remaining_time": "4h 30m 3s"}
|
|
{"eval_loss": 0.6321308, "eval_acc": 0.789979, "eval_runtime": 33.3878, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 1.21304018, "global_step/max_steps": "200/492", "percentage": "40.65%", "elapsed_time": "3h 5m 31s", "remaining_time": "4h 30m 51s"}
|
|
{"loss": 0.65485716, "acc": 0.80138187, "grad_norm": 0.5110445, "learning_rate": 3.206e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.017998, "epoch": 1.27369219, "global_step/max_steps": "210/492", "percentage": "42.68%", "elapsed_time": "3h 14m 27s", "remaining_time": "4h 21m 7s"}
|
|
{"loss": 0.64407654, "acc": 0.80850792, "grad_norm": 0.53881371, "learning_rate": 3.047e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.01803, "epoch": 1.3343442, "global_step/max_steps": "220/492", "percentage": "44.72%", "elapsed_time": "3h 23m 21s", "remaining_time": "4h 11m 25s"}
|
|
{"loss": 0.62571998, "acc": 0.81196032, "grad_norm": 0.469551, "learning_rate": 2.885e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018027, "epoch": 1.39499621, "global_step/max_steps": "230/492", "percentage": "46.75%", "elapsed_time": "3h 32m 38s", "remaining_time": "4h 2m 13s"}
|
|
{"loss": 0.65291729, "acc": 0.80810652, "grad_norm": 0.59865773, "learning_rate": 2.722e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018043, "epoch": 1.45564822, "global_step/max_steps": "240/492", "percentage": "48.78%", "elapsed_time": "3h 41m 41s", "remaining_time": "3h 52m 46s"}
|
|
{"loss": 0.64576678, "acc": 0.80662775, "grad_norm": 0.58436078, "learning_rate": 2.558e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018069, "epoch": 1.51630023, "global_step/max_steps": "250/492", "percentage": "50.81%", "elapsed_time": "3h 50m 35s", "remaining_time": "3h 43m 12s"}
|
|
{"eval_loss": 0.62853843, "eval_acc": 0.79410441, "eval_runtime": 33.3745, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 1.51630023, "global_step/max_steps": "250/492", "percentage": "50.81%", "elapsed_time": "3h 51m 9s", "remaining_time": "3h 43m 45s"}
|
|
{"loss": 0.63846149, "acc": 0.81377954, "grad_norm": 0.58364713, "learning_rate": 2.393e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018041, "epoch": 1.57695224, "global_step/max_steps": "260/492", "percentage": "52.85%", "elapsed_time": "4h 0m 11s", "remaining_time": "3h 34m 19s"}
|
|
{"loss": 0.63191056, "acc": 0.81630754, "grad_norm": 0.59927553, "learning_rate": 2.229e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.01804, "epoch": 1.63760425, "global_step/max_steps": "270/492", "percentage": "54.88%", "elapsed_time": "4h 9m 26s", "remaining_time": "3h 25m 5s"}
|
|
{"loss": 0.62882524, "acc": 0.81421833, "grad_norm": 0.64250344, "learning_rate": 2.066e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018054, "epoch": 1.69825625, "global_step/max_steps": "280/492", "percentage": "56.91%", "elapsed_time": "4h 18m 28s", "remaining_time": "3h 15m 42s"}
|
|
{"loss": 0.63343344, "acc": 0.81105165, "grad_norm": 0.72810084, "learning_rate": 1.905e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018051, "epoch": 1.75890826, "global_step/max_steps": "290/492", "percentage": "58.94%", "elapsed_time": "4h 27m 44s", "remaining_time": "3h 6m 30s"}
|
|
{"loss": 0.61497531, "acc": 0.81203499, "grad_norm": 0.64226258, "learning_rate": 1.746e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018048, "epoch": 1.81956027, "global_step/max_steps": "300/492", "percentage": "60.98%", "elapsed_time": "4h 37m 2s", "remaining_time": "2h 57m 18s"}
|
|
{"eval_loss": 0.62492347, "eval_acc": 0.79162916, "eval_runtime": 33.3563, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 1.81956027, "global_step/max_steps": "300/492", "percentage": "60.98%", "elapsed_time": "4h 37m 35s", "remaining_time": "2h 57m 39s"}
|
|
{"loss": 0.62079144, "acc": 0.81845484, "grad_norm": 0.65133983, "learning_rate": 1.591e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.018002, "epoch": 1.88021228, "global_step/max_steps": "310/492", "percentage": "63.01%", "elapsed_time": "4h 46m 59s", "remaining_time": "2h 48m 29s"}
|
|
{"loss": 0.65046687, "acc": 0.80788202, "grad_norm": 0.7401945, "learning_rate": 1.44e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017998, "epoch": 1.94086429, "global_step/max_steps": "320/492", "percentage": "65.04%", "elapsed_time": "4h 56m 19s", "remaining_time": "2h 39m 16s"}
|
|
{"loss": 0.61997638, "acc": 0.82108784, "grad_norm": 0.64746267, "learning_rate": 1.293e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017998, "epoch": 2.0015163, "global_step/max_steps": "330/492", "percentage": "67.07%", "elapsed_time": "5h 5m 35s", "remaining_time": "2h 30m 0s"}
|
|
{"loss": 0.59635124, "acc": 0.82966375, "grad_norm": 0.67631805, "learning_rate": 1.152e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017997, "epoch": 2.06216831, "global_step/max_steps": "340/492", "percentage": "69.11%", "elapsed_time": "5h 14m 51s", "remaining_time": "2h 20m 45s"}
|
|
{"loss": 0.61077051, "acc": 0.81922455, "grad_norm": 0.63977343, "learning_rate": 1.016e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.018002, "epoch": 2.12282032, "global_step/max_steps": "350/492", "percentage": "71.14%", "elapsed_time": "5h 24m 1s", "remaining_time": "2h 11m 27s"}
|
|
{"eval_loss": 0.62656116, "eval_acc": 0.79065407, "eval_runtime": 33.3834, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 2.12282032, "global_step/max_steps": "350/492", "percentage": "71.14%", "elapsed_time": "5h 24m 35s", "remaining_time": "2h 11m 41s"}
|
|
{"loss": 0.58803082, "acc": 0.82154951, "grad_norm": 0.65156412, "learning_rate": 8.87e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017986, "epoch": 2.18347233, "global_step/max_steps": "360/492", "percentage": "73.17%", "elapsed_time": "5h 33m 34s", "remaining_time": "2h 2m 18s"}
|
|
{"loss": 0.59619102, "acc": 0.82550659, "grad_norm": 0.60718399, "learning_rate": 7.65e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017984, "epoch": 2.24412434, "global_step/max_steps": "370/492", "percentage": "75.20%", "elapsed_time": "5h 42m 53s", "remaining_time": "1h 53m 3s"}
|
|
{"loss": 0.60522118, "acc": 0.82611694, "grad_norm": 0.71287358, "learning_rate": 6.5e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017993, "epoch": 2.30477635, "global_step/max_steps": "380/492", "percentage": "77.24%", "elapsed_time": "5h 51m 59s", "remaining_time": "1h 43m 44s"}
|
|
{"loss": 0.59970803, "acc": 0.81816902, "grad_norm": 0.6338129, "learning_rate": 5.43e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017995, "epoch": 2.36542835, "global_step/max_steps": "390/492", "percentage": "79.27%", "elapsed_time": "6h 1m 11s", "remaining_time": "1h 34m 27s"}
|
|
{"loss": 0.60803032, "acc": 0.81789389, "grad_norm": 0.63463628, "learning_rate": 4.45e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017993, "epoch": 2.42608036, "global_step/max_steps": "400/492", "percentage": "81.30%", "elapsed_time": "6h 10m 30s", "remaining_time": "1h 25m 13s"}
|
|
{"eval_loss": 0.62541068, "eval_acc": 0.79185419, "eval_runtime": 33.3795, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 2.42608036, "global_step/max_steps": "400/492", "percentage": "81.30%", "elapsed_time": "6h 11m 4s", "remaining_time": "1h 25m 20s"}
|
|
{"loss": 0.5707685, "acc": 0.83075409, "grad_norm": 0.72052562, "learning_rate": 3.56e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017961, "epoch": 2.48673237, "global_step/max_steps": "410/492", "percentage": "83.33%", "elapsed_time": "6h 20m 27s", "remaining_time": "1h 16m 5s"}
|
|
{"loss": 0.60830874, "acc": 0.82312384, "grad_norm": 0.76082474, "learning_rate": 2.76e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017968, "epoch": 2.54738438, "global_step/max_steps": "420/492", "percentage": "85.37%", "elapsed_time": "6h 29m 34s", "remaining_time": "1h 6m 46s"}
|
|
{"loss": 0.60031681, "acc": 0.82624912, "grad_norm": 0.67250025, "learning_rate": 2.06e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017968, "epoch": 2.60803639, "global_step/max_steps": "430/492", "percentage": "87.40%", "elapsed_time": "6h 38m 50s", "remaining_time": "57m 30s"}
|
|
{"loss": 0.60740199, "acc": 0.82032661, "grad_norm": 0.7041446, "learning_rate": 1.45e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017981, "epoch": 2.6686884, "global_step/max_steps": "440/492", "percentage": "89.43%", "elapsed_time": "6h 47m 50s", "remaining_time": "48m 11s"}
|
|
{"loss": 0.59212155, "acc": 0.82620506, "grad_norm": 0.67505771, "learning_rate": 9.5e-07, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.01798, "epoch": 2.72934041, "global_step/max_steps": "450/492", "percentage": "91.46%", "elapsed_time": "6h 57m 7s", "remaining_time": "38m 55s"}
|
|
{"eval_loss": 0.62534374, "eval_acc": 0.79072907, "eval_runtime": 33.3868, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 2.72934041, "global_step/max_steps": "450/492", "percentage": "91.46%", "elapsed_time": "6h 57m 41s", "remaining_time": "38m 59s"}
|
|
{"loss": 0.60695276, "acc": 0.81830873, "grad_norm": 0.7647565, "learning_rate": 5.5e-07, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017961, "epoch": 2.78999242, "global_step/max_steps": "460/492", "percentage": "93.50%", "elapsed_time": "7h 6m 50s", "remaining_time": "29m 41s"}
|
|
{"loss": 0.59519863, "acc": 0.82221327, "grad_norm": 0.74437916, "learning_rate": 2.6e-07, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017972, "epoch": 2.85064443, "global_step/max_steps": "470/492", "percentage": "95.53%", "elapsed_time": "7h 15m 51s", "remaining_time": "20m 24s"}
|
|
{"loss": 0.61491089, "acc": 0.81781597, "grad_norm": 0.68625921, "learning_rate": 8e-08, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017987, "epoch": 2.91129644, "global_step/max_steps": "480/492", "percentage": "97.56%", "elapsed_time": "7h 24m 45s", "remaining_time": "11m 7s"}
|
|
{"loss": 0.62906442, "acc": 0.80875072, "grad_norm": 0.72898543, "learning_rate": 0.0, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.018004, "epoch": 2.97194845, "global_step/max_steps": "490/492", "percentage": "99.59%", "elapsed_time": "7h 33m 35s", "remaining_time": "1m 51s"}
|
|
{"eval_loss": 0.62484771, "eval_acc": 0.79140414, "eval_runtime": 33.3848, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 2.98407885, "global_step/max_steps": "492/492", "percentage": "100.00%", "elapsed_time": "7h 36m 0s", "remaining_time": "0s"}
|
|
{"train_runtime": 27361.9994, "train_samples_per_second": 0.289, "train_steps_per_second": 0.018, "total_flos": 2.775583207171031e+17, "train_loss": 0.6521817, "epoch": 2.98407885, "global_step/max_steps": "492/492", "percentage": "100.00%", "elapsed_time": "7h 36m 1s", "remaining_time": "0s"}
|
|
{"memory": {"cuda": "20.38GiB"}, "last_model_checkpoint": "/mnt/workspace/output/qwen2_5-7b-instruct/v19-20241204-000243/checkpoint-492", "best_model_checkpoint": "/mnt/workspace/output/qwen2_5-7b-instruct/v19-20241204-000243/checkpoint-492", "best_metric": 0.62484771, "global_step": 492, "log_history": [{"loss": 0.93224913, "acc": 0.76220244, "grad_norm": 0.5449885129928589, "learning_rate": 3.3333333333333333e-06, "memory(GiB)": 19.94, "train_speed(iter/s)": 0.017019, "epoch": 0.006065200909780136, "step": 1}, {"loss": 0.91722838, "acc": 0.75826671, "grad_norm": 0.4643368422985077, "learning_rate": 3.3333333333333335e-05, "memory(GiB)": 20.11, "train_speed(iter/s)": 0.017934, "epoch": 0.060652009097801364, "step": 10}, {"loss": 0.86249514, "acc": 0.75574059, "grad_norm": 0.41435161232948303, "learning_rate": 4.9986445803993146e-05, "memory(GiB)": 20.19, "train_speed(iter/s)": 0.018374, "epoch": 0.12130401819560273, "step": 20}, {"loss": 0.75827727, "acc": 0.78193603, "grad_norm": 0.3486264646053314, "learning_rate": 4.98781004037916e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.018113, "epoch": 0.1819560272934041, "step": 30}, {"loss": 0.72877254, "acc": 0.79074349, "grad_norm": 0.3532516062259674, "learning_rate": 4.966187940713079e-05, "memory(GiB)": 20.18, "train_speed(iter/s)": 0.018128, "epoch": 0.24260803639120546, "step": 40}, {"loss": 0.69353862, "acc": 0.80020571, "grad_norm": 0.38382261991500854, "learning_rate": 4.933872038434782e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.018059, "epoch": 0.3032600454890068, "step": 50}, {"eval_loss": 0.6729810237884521, "eval_acc": 0.7802280228022802, "eval_runtime": 33.3888, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 0.3032600454890068, "step": 50}, {"loss": 0.69440799, "acc": 0.79857101, "grad_norm": 0.34451159834861755, "learning_rate": 4.891002460691306e-05, "memory(GiB)": 20.07, "train_speed(iter/s)": 0.017825, "epoch": 0.3639120545868082, "step": 60}, {"loss": 0.71067386, "acc": 0.79230323, "grad_norm": 0.38824179768562317, "learning_rate": 4.837765097128326e-05, "memory(GiB)": 20.07, "train_speed(iter/s)": 0.017889, "epoch": 0.4245640636846095, "step": 70}, {"loss": 0.69002156, "acc": 0.7934236, "grad_norm": 0.3901934325695038, "learning_rate": 4.7743907938416074e-05, "memory(GiB)": 20.07, "train_speed(iter/s)": 0.01793, "epoch": 0.4852160727824109, "step": 80}, {"loss": 0.6877634, "acc": 0.7960094, "grad_norm": 0.38508492708206177, "learning_rate": 4.7011543523897996e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.017919, "epoch": 0.5458680818802123, "step": 90}, {"loss": 0.70220733, "acc": 0.79615922, "grad_norm": 0.42378929257392883, "learning_rate": 4.618373338209008e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.017939, "epoch": 0.6065200909780136, "step": 100}, {"eval_loss": 0.6485018730163574, "eval_acc": 0.7882538253825383, "eval_runtime": 33.3399, "eval_samples_per_second": 0.75, "eval_steps_per_second": 0.75, "epoch": 0.6065200909780136, "step": 100}, {"loss": 0.70293474, "acc": 0.79093747, "grad_norm": 0.3972659111022949, "learning_rate": 4.5264067035960434e-05, "memory(GiB)": 20.22, "train_speed(iter/s)": 0.017862, "epoch": 0.6671721000758151, "step": 110}, {"loss": 0.66394258, "acc": 0.79998345, "grad_norm": 0.3906295895576477, "learning_rate": 4.425653231231344e-05, "memory(GiB)": 20.38, "train_speed(iter/s)": 0.01785, "epoch": 0.7278241091736164, "step": 120}, {"loss": 0.67210622, "acc": 0.80572329, "grad_norm": 0.4549758732318878, "learning_rate": 4.316549804990699e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017891, "epoch": 0.7884761182714177, "step": 130}, {"loss": 0.68859334, "acc": 0.7952837, "grad_norm": 0.42970341444015503, "learning_rate": 4.1995695155438326e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017955, "epoch": 0.849128127369219, "step": 140}, {"loss": 0.68589358, "acc": 0.79690466, "grad_norm": 0.4068616032600403, "learning_rate": 4.075219608954278e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.017997, "epoch": 0.9097801364670205, "step": 150}, {"eval_loss": 0.6368805170059204, "eval_acc": 0.7888538853885388, "eval_runtime": 33.3891, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 0.9097801364670205, "step": 150}, {"loss": 0.67849236, "acc": 0.80027781, "grad_norm": 0.4147520363330841, "learning_rate": 3.944039287175774e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.017978, "epoch": 0.9704321455648218, "step": 160}, {"loss": 0.64705005, "acc": 0.8089735, "grad_norm": 0.4718291759490967, "learning_rate": 3.806597369982574e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.017992, "epoch": 1.0310841546626233, "step": 170}, {"loss": 0.64267106, "acc": 0.81211033, "grad_norm": 0.4739744961261749, "learning_rate": 3.663489828471953e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018023, "epoch": 1.0917361637604246, "step": 180}, {"loss": 0.63020077, "acc": 0.81366587, "grad_norm": 0.4722041189670563, "learning_rate": 3.515337200834034e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018044, "epoch": 1.152388172858226, "step": 190}, {"loss": 0.61844859, "acc": 0.81707268, "grad_norm": 0.48362505435943604, "learning_rate": 3.362781901594606e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018021, "epoch": 1.2130401819560273, "step": 200}, {"eval_loss": 0.6321308016777039, "eval_acc": 0.78997899789979, "eval_runtime": 33.3878, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 1.2130401819560273, "step": 200}, {"loss": 0.65485716, "acc": 0.80138187, "grad_norm": 0.5110445022583008, "learning_rate": 3.206485435998498e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.017998, "epoch": 1.2736921910538286, "step": 210}, {"loss": 0.64407654, "acc": 0.80850792, "grad_norm": 0.5388137102127075, "learning_rate": 3.0471255316124037e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.01803, "epoch": 1.3343442001516301, "step": 220}, {"loss": 0.62571998, "acc": 0.81196032, "grad_norm": 0.4695509970188141, "learning_rate": 2.8853931995850185e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018027, "epoch": 1.3949962092494315, "step": 230}, {"loss": 0.65291729, "acc": 0.80810652, "grad_norm": 0.5986577272415161, "learning_rate": 2.7219897383073373e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018043, "epoch": 1.4556482183472328, "step": 240}, {"loss": 0.64576678, "acc": 0.80662775, "grad_norm": 0.5843607783317566, "learning_rate": 2.5576236924657597e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018069, "epoch": 1.5163002274450341, "step": 250}, {"eval_loss": 0.6285384297370911, "eval_acc": 0.7941044104410441, "eval_runtime": 33.3745, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 1.5163002274450341, "step": 250}, {"loss": 0.63846149, "acc": 0.81377954, "grad_norm": 0.5836471319198608, "learning_rate": 2.3930077806740488e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018041, "epoch": 1.5769522365428355, "step": 260}, {"loss": 0.63191056, "acc": 0.81630754, "grad_norm": 0.599275529384613, "learning_rate": 2.2288558050064367e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.01804, "epoch": 1.6376042456406368, "step": 270}, {"loss": 0.62882524, "acc": 0.81421833, "grad_norm": 0.6425034403800964, "learning_rate": 2.0658795558326743e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018054, "epoch": 1.698256254738438, "step": 280}, {"loss": 0.63343344, "acc": 0.81105165, "grad_norm": 0.7281008362770081, "learning_rate": 1.904785725376162e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018051, "epoch": 1.7589082638362394, "step": 290}, {"loss": 0.61497531, "acc": 0.81203499, "grad_norm": 0.6422625780105591, "learning_rate": 1.746272843378493e-05, "memory(GiB)": 20.27, "train_speed(iter/s)": 0.018048, "epoch": 1.819560272934041, "step": 300}, {"eval_loss": 0.6249234676361084, "eval_acc": 0.7916291629162916, "eval_runtime": 33.3563, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 1.819560272934041, "step": 300}, {"loss": 0.62079144, "acc": 0.81845484, "grad_norm": 0.6513398289680481, "learning_rate": 1.591028248157884e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.018002, "epoch": 1.8802122820318423, "step": 310}, {"loss": 0.65046687, "acc": 0.80788202, "grad_norm": 0.7401944994926453, "learning_rate": 1.4397251061954847e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017998, "epoch": 1.9408642911296436, "step": 320}, {"loss": 0.61997638, "acc": 0.82108784, "grad_norm": 0.6474626660346985, "learning_rate": 1.2930194931731382e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017998, "epoch": 2.001516300227445, "step": 330}, {"loss": 0.59635124, "acc": 0.82966375, "grad_norm": 0.6763180494308472, "learning_rate": 1.1515475491196976e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017997, "epoch": 2.0621683093252465, "step": 340}, {"loss": 0.61077051, "acc": 0.81922455, "grad_norm": 0.639773428440094, "learning_rate": 1.0159227200016678e-05, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.018002, "epoch": 2.122820318423048, "step": 350}, {"eval_loss": 0.626561164855957, "eval_acc": 0.7906540654065407, "eval_runtime": 33.3834, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 2.122820318423048, "step": 350}, {"loss": 0.58803082, "acc": 0.82154951, "grad_norm": 0.6515641212463379, "learning_rate": 8.867330977190877e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017986, "epoch": 2.183472327520849, "step": 360}, {"loss": 0.59619102, "acc": 0.82550659, "grad_norm": 0.6071839928627014, "learning_rate": 7.645388700408732e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017984, "epoch": 2.2441243366186505, "step": 370}, {"loss": 0.60522118, "acc": 0.82611694, "grad_norm": 0.7128735780715942, "learning_rate": 6.498698915371359e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017993, "epoch": 2.304776345716452, "step": 380}, {"loss": 0.59970803, "acc": 0.81816902, "grad_norm": 0.6338129043579102, "learning_rate": 5.4322338604131715e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017995, "epoch": 2.365428354814253, "step": 390}, {"loss": 0.60803032, "acc": 0.81789389, "grad_norm": 0.6346362829208374, "learning_rate": 4.450617906046348e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017993, "epoch": 2.4260803639120545, "step": 400}, {"eval_loss": 0.6254106760025024, "eval_acc": 0.7918541854185418, "eval_runtime": 33.3795, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 2.4260803639120545, "step": 400}, {"loss": 0.5707685, "acc": 0.83075409, "grad_norm": 0.7205256223678589, "learning_rate": 3.5581075029183423e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017961, "epoch": 2.486732373009856, "step": 410}, {"loss": 0.60830874, "acc": 0.82312384, "grad_norm": 0.7608247399330139, "learning_rate": 2.75857272513132e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017968, "epoch": 2.547384382107657, "step": 420}, {"loss": 0.60031681, "acc": 0.82624912, "grad_norm": 0.6725002527236938, "learning_rate": 2.0554804889547586e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017968, "epoch": 2.6080363912054585, "step": 430}, {"loss": 0.60740199, "acc": 0.82032661, "grad_norm": 0.7041445970535278, "learning_rate": 1.4518795196977575e-06, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017981, "epoch": 2.6686884003032603, "step": 440}, {"loss": 0.59212155, "acc": 0.82620506, "grad_norm": 0.6750577092170715, "learning_rate": 9.503871319271551e-07, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.01798, "epoch": 2.729340409401061, "step": 450}, {"eval_loss": 0.6253437399864197, "eval_acc": 0.7907290729072908, "eval_runtime": 33.3868, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 2.729340409401061, "step": 450}, {"loss": 0.60695276, "acc": 0.81830873, "grad_norm": 0.7647565007209778, "learning_rate": 5.531778803546217e-07, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017961, "epoch": 2.789992418498863, "step": 460}, {"loss": 0.59519863, "acc": 0.82221327, "grad_norm": 0.7443791627883911, "learning_rate": 2.6197413060442266e-07, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017972, "epoch": 2.8506444275966643, "step": 470}, {"loss": 0.61491089, "acc": 0.81781597, "grad_norm": 0.6862592101097107, "learning_rate": 7.803859074854425e-08, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.017987, "epoch": 2.9112964366944656, "step": 480}, {"loss": 0.62906442, "acc": 0.80875072, "grad_norm": 0.7289854288101196, "learning_rate": 2.1688359936905547e-09, "memory(GiB)": 20.25, "train_speed(iter/s)": 0.018004, "epoch": 2.971948445792267, "step": 490}, {"eval_loss": 0.6248477101325989, "eval_acc": 0.7914041404140414, "eval_runtime": 33.3848, "eval_samples_per_second": 0.749, "eval_steps_per_second": 0.749, "epoch": 2.984078847611827, "step": 492}, {"train_runtime": 27361.9994, "train_samples_per_second": 0.289, "train_steps_per_second": 0.018, "total_flos": 2.775583207171031e+17, "train_loss": 0.6521817035064464, "epoch": 2.984078847611827, "step": 492}], "model_info": "PeftModelForCausalLM: 7637.1922M Params (21.5757M Trainable [0.2825%]), 0.0019M Buffers.", "dataset_info": {"train_dataset": "829.092115±402.392944, min=289.000000, max=2577.000000, size=2638", "val_dataset": "817.600000±402.307842, min=425.000000, max=2019.000000, size=25"}, "train_time": {"train_runtime": 27361.9994, "n_train_samples": 2638, "train_samples_per_second": 0.09641108317544952}}
|