| { | |
| "best_metric": 1.9397222995758057, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.32323232323232326, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006464646464646465, | |
| "grad_norm": 0.14697107672691345, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1076, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006464646464646465, | |
| "eval_loss": 2.1259307861328125, | |
| "eval_runtime": 18.6955, | |
| "eval_samples_per_second": 55.789, | |
| "eval_steps_per_second": 7.007, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01292929292929293, | |
| "grad_norm": 0.20078013837337494, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1139, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019393939393939394, | |
| "grad_norm": 0.2115059792995453, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.1157, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02585858585858586, | |
| "grad_norm": 0.24832786619663239, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0639, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03232323232323232, | |
| "grad_norm": 0.19159361720085144, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0667, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03878787878787879, | |
| "grad_norm": 0.17943724989891052, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0373, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04525252525252525, | |
| "grad_norm": 0.1874370127916336, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.007, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05171717171717172, | |
| "grad_norm": 0.18170057237148285, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9832, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05818181818181818, | |
| "grad_norm": 0.22331948578357697, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9331, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06464646464646465, | |
| "grad_norm": 0.3328644037246704, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8558, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07111111111111111, | |
| "grad_norm": 0.34028002619743347, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8342, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07757575757575758, | |
| "grad_norm": 0.36402320861816406, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.7443, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08404040404040404, | |
| "grad_norm": 0.35609129071235657, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.1296, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0905050505050505, | |
| "grad_norm": 0.35171398520469666, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1048, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09696969696969697, | |
| "grad_norm": 0.27417001128196716, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.1037, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10343434343434343, | |
| "grad_norm": 0.21549075841903687, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.0583, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1098989898989899, | |
| "grad_norm": 0.1707264631986618, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.0299, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 0.1691594421863556, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0242, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12282828282828283, | |
| "grad_norm": 0.16962571442127228, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.007, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1292929292929293, | |
| "grad_norm": 0.1708366423845291, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13575757575757577, | |
| "grad_norm": 0.18287888169288635, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.9308, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14222222222222222, | |
| "grad_norm": 0.2277010977268219, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8962, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1486868686868687, | |
| "grad_norm": 0.3452220559120178, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.8403, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15515151515151515, | |
| "grad_norm": 0.4093315601348877, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.8173, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 0.5213513970375061, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.7142, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "eval_loss": 1.9495412111282349, | |
| "eval_runtime": 18.7231, | |
| "eval_samples_per_second": 55.707, | |
| "eval_steps_per_second": 6.997, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16808080808080808, | |
| "grad_norm": 0.1075863242149353, | |
| "learning_rate": 5e-05, | |
| "loss": 2.091, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17454545454545456, | |
| "grad_norm": 0.11374333500862122, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.0913, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.181010101010101, | |
| "grad_norm": 0.12921658158302307, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.0912, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1874747474747475, | |
| "grad_norm": 0.14677837491035461, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.0261, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.19393939393939394, | |
| "grad_norm": 0.15907618403434753, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.0218, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20040404040404042, | |
| "grad_norm": 0.17544959485530853, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.9967, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.20686868686868687, | |
| "grad_norm": 0.17092251777648926, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9549, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.21333333333333335, | |
| "grad_norm": 0.1808241903781891, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.9632, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2197979797979798, | |
| "grad_norm": 0.19379456341266632, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8991, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22626262626262628, | |
| "grad_norm": 0.2286708503961563, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.8443, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": 0.2920991778373718, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.8017, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2391919191919192, | |
| "grad_norm": 0.36291784048080444, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.7088, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24565656565656566, | |
| "grad_norm": 0.11166388541460037, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.045, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.25212121212121213, | |
| "grad_norm": 0.10947787016630173, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.0348, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2585858585858586, | |
| "grad_norm": 0.11435955762863159, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.0481, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26505050505050504, | |
| "grad_norm": 0.14134708046913147, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.033, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.27151515151515154, | |
| "grad_norm": 0.13096044957637787, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.9578, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.277979797979798, | |
| "grad_norm": 0.13657227158546448, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.0364, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.28444444444444444, | |
| "grad_norm": 0.14005684852600098, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9877, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 0.1538858860731125, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.9681, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2973737373737374, | |
| "grad_norm": 0.158803790807724, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.9181, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.30383838383838385, | |
| "grad_norm": 0.18612298369407654, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.8931, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3103030303030303, | |
| "grad_norm": 0.24481238424777985, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.7794, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.31676767676767675, | |
| "grad_norm": 0.32691097259521484, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7634, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": 0.468767911195755, | |
| "learning_rate": 0.0, | |
| "loss": 1.7106, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "eval_loss": 1.9397222995758057, | |
| "eval_runtime": 18.7231, | |
| "eval_samples_per_second": 55.707, | |
| "eval_steps_per_second": 6.997, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.254995537788928e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |