| { | |
| "best_metric": 11.903162002563477, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.816901408450704, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": 0.11861895024776459, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9135, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "eval_loss": 11.917165756225586, | |
| "eval_runtime": 0.4813, | |
| "eval_samples_per_second": 249.34, | |
| "eval_steps_per_second": 31.168, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 0.13976728916168213, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9151, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 0.14872075617313385, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9133, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 0.1550625115633011, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9167, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.28169014084507044, | |
| "grad_norm": 0.13888682425022125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9111, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 0.13404583930969238, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9119, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.39436619718309857, | |
| "grad_norm": 0.13143156468868256, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9173, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": 0.14406755566596985, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9086, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5070422535211268, | |
| "grad_norm": 0.13339732587337494, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9173, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 0.12176564335823059, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9138, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6197183098591549, | |
| "grad_norm": 0.12360658496618271, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9107, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": 0.13630253076553345, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9112, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7323943661971831, | |
| "grad_norm": 0.1385597437620163, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9146, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7887323943661971, | |
| "grad_norm": 0.12031757086515427, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9134, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8450704225352113, | |
| "grad_norm": 0.13277402520179749, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9121, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9014084507042254, | |
| "grad_norm": 0.14855268597602844, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9065, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9577464788732394, | |
| "grad_norm": 0.18043559789657593, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9019, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0140845070422535, | |
| "grad_norm": 0.17862877249717712, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 14.8926, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0704225352112675, | |
| "grad_norm": 0.14035183191299438, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9116, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1267605633802817, | |
| "grad_norm": 0.16815966367721558, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9097, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1830985915492958, | |
| "grad_norm": 0.17651180922985077, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9028, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2394366197183098, | |
| "grad_norm": 0.1990969032049179, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9035, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.295774647887324, | |
| "grad_norm": 0.15273728966712952, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9049, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.352112676056338, | |
| "grad_norm": 0.16254177689552307, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9084, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "grad_norm": 0.18525931239128113, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9061, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "eval_loss": 11.907405853271484, | |
| "eval_runtime": 0.4747, | |
| "eval_samples_per_second": 252.807, | |
| "eval_steps_per_second": 31.601, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4647887323943662, | |
| "grad_norm": 0.19581171870231628, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9039, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5211267605633803, | |
| "grad_norm": 0.17904254794120789, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9073, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5774647887323945, | |
| "grad_norm": 0.17740856111049652, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9064, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6338028169014085, | |
| "grad_norm": 0.18188264966011047, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9041, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.6901408450704225, | |
| "grad_norm": 0.21682192385196686, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9039, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7464788732394365, | |
| "grad_norm": 0.20323139429092407, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9058, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8028169014084507, | |
| "grad_norm": 0.18855667114257812, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9021, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8591549295774648, | |
| "grad_norm": 0.19645343720912933, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.907, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.915492957746479, | |
| "grad_norm": 0.20963948965072632, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9042, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.971830985915493, | |
| "grad_norm": 0.22430875897407532, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 12.8947, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.028169014084507, | |
| "grad_norm": 0.23213434219360352, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 13.8829, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.084507042253521, | |
| "grad_norm": 0.2037564367055893, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.901, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.140845070422535, | |
| "grad_norm": 0.2237176150083542, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.8982, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.1971830985915495, | |
| "grad_norm": 0.22813087701797485, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.8981, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.2535211267605635, | |
| "grad_norm": 0.23737770318984985, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9021, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.3098591549295775, | |
| "grad_norm": 0.20191168785095215, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.8988, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.3661971830985915, | |
| "grad_norm": 0.2275736927986145, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9019, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.4225352112676055, | |
| "grad_norm": 0.23269234597682953, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9011, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.4788732394366195, | |
| "grad_norm": 0.27122339606285095, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.8984, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.535211267605634, | |
| "grad_norm": 0.20346561074256897, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9046, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.591549295774648, | |
| "grad_norm": 0.21024282276630402, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9059, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.647887323943662, | |
| "grad_norm": 0.24199335277080536, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.8993, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.704225352112676, | |
| "grad_norm": 0.22599415481090546, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9033, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.76056338028169, | |
| "grad_norm": 0.2118520885705948, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.904, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "grad_norm": 0.1982305496931076, | |
| "learning_rate": 0.0, | |
| "loss": 11.9034, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "eval_loss": 11.903162002563477, | |
| "eval_runtime": 0.4797, | |
| "eval_samples_per_second": 250.132, | |
| "eval_steps_per_second": 31.266, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |