| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.949238578680204, | |
| "eval_steps": 500, | |
| "global_step": 490, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.20304568527918782, | |
| "grad_norm": 0.2015380859375, | |
| "learning_rate": 0.00019979453927503364, | |
| "loss": 0.7307, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.40609137055837563, | |
| "grad_norm": 0.255615234375, | |
| "learning_rate": 0.0001991790013823246, | |
| "loss": 0.7211, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6091370558375635, | |
| "grad_norm": 0.306640625, | |
| "learning_rate": 0.00019815591569910654, | |
| "loss": 0.7372, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8121827411167513, | |
| "grad_norm": 0.359130859375, | |
| "learning_rate": 0.00019672948630390294, | |
| "loss": 0.7826, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.015228426395939, | |
| "grad_norm": 0.385986328125, | |
| "learning_rate": 0.00019490557470106686, | |
| "loss": 0.8238, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.218274111675127, | |
| "grad_norm": 0.359130859375, | |
| "learning_rate": 0.0001926916757346022, | |
| "loss": 0.7958, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4213197969543148, | |
| "grad_norm": 0.34912109375, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.7704, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.6243654822335025, | |
| "grad_norm": 0.378662109375, | |
| "learning_rate": 0.00018713187041233896, | |
| "loss": 0.7576, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.8274111675126905, | |
| "grad_norm": 0.38818359375, | |
| "learning_rate": 0.00018380881048918405, | |
| "loss": 0.7895, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.030456852791878, | |
| "grad_norm": 0.3798828125, | |
| "learning_rate": 0.00018014136218679567, | |
| "loss": 0.7953, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.233502538071066, | |
| "grad_norm": 0.40869140625, | |
| "learning_rate": 0.00017614459583691346, | |
| "loss": 0.7621, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.436548223350254, | |
| "grad_norm": 0.409912109375, | |
| "learning_rate": 0.00017183493500977278, | |
| "loss": 0.7806, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.6395939086294415, | |
| "grad_norm": 0.41162109375, | |
| "learning_rate": 0.0001672300890261317, | |
| "loss": 0.7414, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.8426395939086295, | |
| "grad_norm": 0.4326171875, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.7326, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.045685279187817, | |
| "grad_norm": 0.468994140625, | |
| "learning_rate": 0.00015721166601221698, | |
| "loss": 0.7233, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.248730964467005, | |
| "grad_norm": 0.443359375, | |
| "learning_rate": 0.00015183925683105254, | |
| "loss": 0.7304, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.451776649746193, | |
| "grad_norm": 0.47705078125, | |
| "learning_rate": 0.00014625382902408356, | |
| "loss": 0.7311, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.6548223350253806, | |
| "grad_norm": 0.44287109375, | |
| "learning_rate": 0.00014047833431223938, | |
| "loss": 0.7204, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.8578680203045685, | |
| "grad_norm": 0.490478515625, | |
| "learning_rate": 0.00013453650544213076, | |
| "loss": 0.6965, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.060913705583756, | |
| "grad_norm": 0.42578125, | |
| "learning_rate": 0.00012845275866310324, | |
| "loss": 0.7102, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.2639593908629445, | |
| "grad_norm": 0.46240234375, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.7164, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.467005076142132, | |
| "grad_norm": 0.449951171875, | |
| "learning_rate": 0.00011595998950333793, | |
| "loss": 0.7068, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.67005076142132, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 0.00010960230259076818, | |
| "loss": 0.7092, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.873096446700508, | |
| "grad_norm": 0.5244140625, | |
| "learning_rate": 0.00010320515775716555, | |
| "loss": 0.6712, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.0761421319796955, | |
| "grad_norm": 0.47705078125, | |
| "learning_rate": 9.679484224283449e-05, | |
| "loss": 0.6593, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.279187817258883, | |
| "grad_norm": 0.50830078125, | |
| "learning_rate": 9.039769740923183e-05, | |
| "loss": 0.6991, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.482233502538071, | |
| "grad_norm": 0.51318359375, | |
| "learning_rate": 8.404001049666211e-05, | |
| "loss": 0.6612, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 5.685279187817259, | |
| "grad_norm": 0.50341796875, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 0.6829, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.888324873096447, | |
| "grad_norm": 0.513671875, | |
| "learning_rate": 7.154724133689677e-05, | |
| "loss": 0.6576, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 6.091370558375634, | |
| "grad_norm": 0.471435546875, | |
| "learning_rate": 6.546349455786926e-05, | |
| "loss": 0.6669, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.2944162436548226, | |
| "grad_norm": 0.55224609375, | |
| "learning_rate": 5.952166568776062e-05, | |
| "loss": 0.6569, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.49746192893401, | |
| "grad_norm": 0.5986328125, | |
| "learning_rate": 5.37461709759165e-05, | |
| "loss": 0.6517, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.700507614213198, | |
| "grad_norm": 0.5849609375, | |
| "learning_rate": 4.8160743168947496e-05, | |
| "loss": 0.6627, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.903553299492386, | |
| "grad_norm": 0.54345703125, | |
| "learning_rate": 4.278833398778306e-05, | |
| "loss": 0.6526, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.106598984771574, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 0.652, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.309644670050761, | |
| "grad_norm": 0.51611328125, | |
| "learning_rate": 3.276991097386831e-05, | |
| "loss": 0.6237, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.5126903553299496, | |
| "grad_norm": 0.5654296875, | |
| "learning_rate": 2.8165064990227252e-05, | |
| "loss": 0.6313, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 7.715736040609137, | |
| "grad_norm": 0.5810546875, | |
| "learning_rate": 2.3855404163086558e-05, | |
| "loss": 0.6452, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 7.918781725888325, | |
| "grad_norm": 0.59423828125, | |
| "learning_rate": 1.985863781320435e-05, | |
| "loss": 0.6412, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 8.121827411167512, | |
| "grad_norm": 0.55712890625, | |
| "learning_rate": 1.619118951081594e-05, | |
| "loss": 0.6532, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.3248730964467, | |
| "grad_norm": 0.60595703125, | |
| "learning_rate": 1.286812958766106e-05, | |
| "loss": 0.6271, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 8.527918781725889, | |
| "grad_norm": 0.580078125, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 0.6202, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.730964467005077, | |
| "grad_norm": 0.54833984375, | |
| "learning_rate": 7.308324265397836e-06, | |
| "loss": 0.6382, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 8.934010152284264, | |
| "grad_norm": 0.53759765625, | |
| "learning_rate": 5.094425298933136e-06, | |
| "loss": 0.6374, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 9.137055837563452, | |
| "grad_norm": 0.591796875, | |
| "learning_rate": 3.270513696097055e-06, | |
| "loss": 0.6319, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.34010152284264, | |
| "grad_norm": 0.54638671875, | |
| "learning_rate": 1.8440843008934561e-06, | |
| "loss": 0.6336, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 9.543147208121827, | |
| "grad_norm": 0.56494140625, | |
| "learning_rate": 8.209986176753948e-07, | |
| "loss": 0.6319, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 9.746192893401016, | |
| "grad_norm": 0.55029296875, | |
| "learning_rate": 2.054607249663665e-07, | |
| "loss": 0.6295, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 9.949238578680204, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 0.0, | |
| "loss": 0.6314, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 9.949238578680204, | |
| "step": 490, | |
| "total_flos": 2.391072030326784e+16, | |
| "train_loss": 0.6941771516994554, | |
| "train_runtime": 436.887, | |
| "train_samples_per_second": 4.509, | |
| "train_steps_per_second": 1.122 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 490, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2.391072030326784e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |