| { | |
| "best_metric": 0.9140611886978149, | |
| "best_model_checkpoint": "ckpt/origin/pedes_environment_v2/checkpoint-91", | |
| "epoch": 4.90566037735849, | |
| "eval_steps": 7, | |
| "global_step": 130, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1312, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0024, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.998494093481022e-06, | |
| "loss": 1.1562, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.993977281025862e-06, | |
| "loss": 1.1379, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.986452283393452e-06, | |
| "loss": 1.0642, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.975923633360985e-06, | |
| "loss": 1.1291, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.962397672993552e-06, | |
| "loss": 1.0684, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.0384804010391235, | |
| "eval_runtime": 36.0334, | |
| "eval_samples_per_second": 1.915, | |
| "eval_steps_per_second": 1.915, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.945882549823906e-06, | |
| "loss": 0.9229, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.926388211944707e-06, | |
| "loss": 1.0811, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.903926402016153e-06, | |
| "loss": 0.9438, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.878510650192644e-06, | |
| "loss": 1.0043, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.850156265972722e-06, | |
| "loss": 0.9032, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.8188803289772e-06, | |
| "loss": 1.0192, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.784701678661045e-06, | |
| "loss": 1.0098, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.9786658883094788, | |
| "eval_runtime": 35.9159, | |
| "eval_samples_per_second": 1.921, | |
| "eval_steps_per_second": 1.921, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.747640902965185e-06, | |
| "loss": 0.9059, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.707720325915105e-06, | |
| "loss": 0.9866, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.664963994173695e-06, | |
| "loss": 0.9917, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.619397662556434e-06, | |
| "loss": 0.9275, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.571048778517655e-06, | |
| "loss": 0.9052, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.519946465617217e-06, | |
| "loss": 0.8874, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.466121505977577e-06, | |
| "loss": 0.978, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.9512829780578613, | |
| "eval_runtime": 35.9114, | |
| "eval_samples_per_second": 1.921, | |
| "eval_steps_per_second": 1.921, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.409606321741776e-06, | |
| "loss": 0.9062, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.350434955543557e-06, | |
| "loss": 1.0455, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.288643050001362e-06, | |
| "loss": 0.8784, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.224267826248536e-06, | |
| "loss": 0.924, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.157348061512728e-06, | |
| "loss": 0.9133, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.08792406575792e-06, | |
| "loss": 0.8332, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.016037657403225e-06, | |
| "loss": 0.9772, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.9353252649307251, | |
| "eval_runtime": 36.0706, | |
| "eval_samples_per_second": 1.913, | |
| "eval_steps_per_second": 1.913, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 8.941732138133032e-06, | |
| "loss": 0.8295, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 8.865052266813686e-06, | |
| "loss": 0.9754, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 8.786044232532423e-06, | |
| "loss": 0.9305, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 8.704755626774796e-06, | |
| "loss": 0.8728, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 8.621235414757337e-06, | |
| "loss": 0.9236, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 8.535533905932739e-06, | |
| "loss": 0.9223, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 8.447702723685335e-06, | |
| "loss": 0.9838, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.9286850690841675, | |
| "eval_runtime": 35.9219, | |
| "eval_samples_per_second": 1.921, | |
| "eval_steps_per_second": 1.921, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 8.357794774235094e-06, | |
| "loss": 0.8317, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.265864214768883e-06, | |
| "loss": 0.7946, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.171966420818227e-06, | |
| "loss": 0.9288, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.076157952903134e-06, | |
| "loss": 0.8589, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.978496522462167e-06, | |
| "loss": 0.8974, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.879040957089229e-06, | |
| "loss": 0.9479, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.777851165098012e-06, | |
| "loss": 0.8649, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.9226968288421631, | |
| "eval_runtime": 36.0309, | |
| "eval_samples_per_second": 1.915, | |
| "eval_steps_per_second": 1.915, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 7.674988099435487e-06, | |
| "loss": 0.9145, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 7.570513720966108e-06, | |
| "loss": 0.9756, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.464490961148921e-06, | |
| "loss": 0.8617, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 7.3569836841299905e-06, | |
| "loss": 0.8243, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 7.248056648273034e-06, | |
| "loss": 0.8681, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.137775467151411e-06, | |
| "loss": 0.801, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.026206570024949e-06, | |
| "loss": 0.8676, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.9197350144386292, | |
| "eval_runtime": 35.9615, | |
| "eval_samples_per_second": 1.919, | |
| "eval_steps_per_second": 1.919, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 6.913417161825449e-06, | |
| "loss": 0.8457, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.799475182674942e-06, | |
| "loss": 0.8894, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.684449266961101e-06, | |
| "loss": 0.8995, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.568408701994459e-06, | |
| "loss": 0.9544, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.451423386272312e-06, | |
| "loss": 0.8938, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.333563787374493e-06, | |
| "loss": 0.8898, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 6.21490089951632e-06, | |
| "loss": 0.8327, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 0.9180477261543274, | |
| "eval_runtime": 35.9929, | |
| "eval_samples_per_second": 1.917, | |
| "eval_steps_per_second": 1.917, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 6.095506200784349e-06, | |
| "loss": 0.8413, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5.975451610080643e-06, | |
| "loss": 0.9434, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 5.8548094438015065e-06, | |
| "loss": 0.9523, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 5.733652372276809e-06, | |
| "loss": 0.8919, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 5.612053375996082e-06, | |
| "loss": 0.85, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 5.490085701647805e-06, | |
| "loss": 0.8806, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 5.367822817998338e-06, | |
| "loss": 0.8033, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 0.9181221127510071, | |
| "eval_runtime": 36.0174, | |
| "eval_samples_per_second": 1.916, | |
| "eval_steps_per_second": 1.916, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.245338371637091e-06, | |
| "loss": 0.9186, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.122706142614562e-06, | |
| "loss": 0.8516, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8434, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.87729385738544e-06, | |
| "loss": 0.8888, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.75466162836291e-06, | |
| "loss": 0.8871, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.6321771820016635e-06, | |
| "loss": 0.8806, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 4.509914298352197e-06, | |
| "loss": 0.8538, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 0.9172544479370117, | |
| "eval_runtime": 35.8611, | |
| "eval_samples_per_second": 1.924, | |
| "eval_steps_per_second": 1.924, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 4.38794662400392e-06, | |
| "loss": 0.8353, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.266347627723192e-06, | |
| "loss": 0.8561, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.145190556198494e-06, | |
| "loss": 0.9676, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 4.02454838991936e-06, | |
| "loss": 0.8629, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.904493799215652e-06, | |
| "loss": 0.7983, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 3.7850991004836813e-06, | |
| "loss": 0.9275, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 3.6664362126255087e-06, | |
| "loss": 0.9481, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.9153242707252502, | |
| "eval_runtime": 35.946, | |
| "eval_samples_per_second": 1.92, | |
| "eval_steps_per_second": 1.92, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.5485766137276894e-06, | |
| "loss": 0.8156, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.4315912980055433e-06, | |
| "loss": 0.7228, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.3155507330389004e-06, | |
| "loss": 0.9645, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.2005248173250593e-06, | |
| "loss": 0.7754, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.0865828381745515e-06, | |
| "loss": 0.8191, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 2.9737934299750514e-06, | |
| "loss": 0.8938, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2.862224532848591e-06, | |
| "loss": 0.8995, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 0.9135288596153259, | |
| "eval_runtime": 35.9776, | |
| "eval_samples_per_second": 1.918, | |
| "eval_steps_per_second": 1.918, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 2.7519433517269665e-06, | |
| "loss": 0.8728, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 2.6430163158700116e-06, | |
| "loss": 0.9105, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 2.5355090388510806e-06, | |
| "loss": 0.7815, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 2.429486279033892e-06, | |
| "loss": 0.8562, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 2.325011900564515e-06, | |
| "loss": 0.8367, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 2.2221488349019903e-06, | |
| "loss": 0.8954, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 2.1209590429107734e-06, | |
| "loss": 0.8555, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "eval_loss": 0.9140611886978149, | |
| "eval_runtime": 35.9673, | |
| "eval_samples_per_second": 1.918, | |
| "eval_steps_per_second": 1.918, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.0215034775378336e-06, | |
| "loss": 0.8164, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.9238420470968665e-06, | |
| "loss": 0.8467, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.8280335791817733e-06, | |
| "loss": 0.8462, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.7341357852311175e-06, | |
| "loss": 0.8948, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.642205225764908e-06, | |
| "loss": 0.836, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.5522972763146653e-06, | |
| "loss": 0.8551, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.4644660940672628e-06, | |
| "loss": 0.884, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_loss": 0.9140763282775879, | |
| "eval_runtime": 35.972, | |
| "eval_samples_per_second": 1.918, | |
| "eval_steps_per_second": 1.918, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.3787645852426663e-06, | |
| "loss": 0.8857, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.2952443732252058e-06, | |
| "loss": 0.7897, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.2139557674675773e-06, | |
| "loss": 0.8527, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 1.134947733186315e-06, | |
| "loss": 0.9348, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.058267861866969e-06, | |
| "loss": 0.9066, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 9.83962342596776e-07, | |
| "loss": 0.8794, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 9.120759342420821e-07, | |
| "loss": 0.878, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "eval_loss": 0.9139989614486694, | |
| "eval_runtime": 36.0023, | |
| "eval_samples_per_second": 1.917, | |
| "eval_steps_per_second": 1.917, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.426519384872733e-07, | |
| "loss": 0.8052, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 7.757321737514645e-07, | |
| "loss": 0.8845, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 7.113569499986401e-07, | |
| "loss": 0.8134, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 6.495650444564433e-07, | |
| "loss": 0.8164, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 5.903936782582253e-07, | |
| "loss": 0.7922, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 5.338784940224239e-07, | |
| "loss": 0.7529, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 4.800535343827834e-07, | |
| "loss": 0.8288, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "eval_loss": 0.9135251641273499, | |
| "eval_runtime": 35.8899, | |
| "eval_samples_per_second": 1.923, | |
| "eval_steps_per_second": 1.923, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 4.289512214823466e-07, | |
| "loss": 0.8892, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 3.8060233744356634e-07, | |
| "loss": 0.8427, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 3.350360058263058e-07, | |
| "loss": 0.9283, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.9227967408489653e-07, | |
| "loss": 0.8674, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 2.523590970348166e-07, | |
| "loss": 0.924, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 2.152983213389559e-07, | |
| "loss": 0.8693, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 1.8111967102280082e-07, | |
| "loss": 0.8456, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "eval_loss": 0.9141875505447388, | |
| "eval_runtime": 35.8271, | |
| "eval_samples_per_second": 1.926, | |
| "eval_steps_per_second": 1.926, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 1.4984373402728014e-07, | |
| "loss": 0.8763, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 1.2148934980735772e-07, | |
| "loss": 0.8042, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 9.607359798384785e-08, | |
| "loss": 0.8456, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 7.36117880552939e-08, | |
| "loss": 0.8505, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 5.411745017609493e-08, | |
| "loss": 0.8404, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 3.7602327006450166e-08, | |
| "loss": 0.8483, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.4076366639015914e-08, | |
| "loss": 0.9049, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 0.9144126176834106, | |
| "eval_runtime": 35.948, | |
| "eval_samples_per_second": 1.919, | |
| "eval_steps_per_second": 1.919, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1.3547716606548967e-08, | |
| "loss": 0.8482, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 6.022718974137976e-09, | |
| "loss": 0.9232, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 1.5059065189787502e-09, | |
| "loss": 0.8653, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.9167, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "step": 130, | |
| "total_flos": 3.500008779892654e+17, | |
| "train_loss": 0.8952723305958968, | |
| "train_runtime": 7687.2741, | |
| "train_samples_per_second": 0.825, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 130, | |
| "num_train_epochs": 5, | |
| "save_steps": 13, | |
| "total_flos": 3.500008779892654e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |