| { | |
| "best_metric": 10.362990379333496, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1310615989515072, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002621231979030144, | |
| "grad_norm": 0.11219380050897598, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3797, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002621231979030144, | |
| "eval_loss": 10.380081176757812, | |
| "eval_runtime": 8.9566, | |
| "eval_samples_per_second": 287.051, | |
| "eval_steps_per_second": 143.581, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005242463958060288, | |
| "grad_norm": 0.11331874132156372, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3796, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007863695937090432, | |
| "grad_norm": 0.1111481636762619, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3799, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010484927916120577, | |
| "grad_norm": 0.11614502966403961, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.38, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01310615989515072, | |
| "grad_norm": 0.1130700632929802, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3795, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015727391874180863, | |
| "grad_norm": 0.12021651118993759, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3782, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01834862385321101, | |
| "grad_norm": 0.12181949615478516, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.377, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020969855832241154, | |
| "grad_norm": 0.12084761261940002, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3759, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023591087811271297, | |
| "grad_norm": 0.11672217398881912, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3755, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02621231979030144, | |
| "grad_norm": 0.12453111261129379, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3745, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028833551769331587, | |
| "grad_norm": 0.11719960719347, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3744, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03145478374836173, | |
| "grad_norm": 0.11235170811414719, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3728, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03407601572739188, | |
| "grad_norm": 0.1359206587076187, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3731, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03669724770642202, | |
| "grad_norm": 0.1403062641620636, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3723, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.039318479685452164, | |
| "grad_norm": 0.13764286041259766, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3721, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04193971166448231, | |
| "grad_norm": 0.13310225307941437, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3719, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04456094364351245, | |
| "grad_norm": 0.1395922303199768, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3721, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.047182175622542594, | |
| "grad_norm": 0.1382313072681427, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.37, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04980340760157274, | |
| "grad_norm": 0.1449769288301468, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3769, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05242463958060288, | |
| "grad_norm": 0.1445191353559494, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3723, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05504587155963303, | |
| "grad_norm": 0.17403177917003632, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3698, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.057667103538663174, | |
| "grad_norm": 0.19702069461345673, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3673, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06028833551769332, | |
| "grad_norm": 0.22738292813301086, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3661, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06290956749672345, | |
| "grad_norm": 0.2735551595687866, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3695, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0655307994757536, | |
| "grad_norm": 0.3323870301246643, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3761, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0655307994757536, | |
| "eval_loss": 10.36768913269043, | |
| "eval_runtime": 8.9056, | |
| "eval_samples_per_second": 288.693, | |
| "eval_steps_per_second": 144.403, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06815203145478375, | |
| "grad_norm": 0.15708748996257782, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3688, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07077326343381389, | |
| "grad_norm": 0.1715221405029297, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3681, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07339449541284404, | |
| "grad_norm": 0.170488640666008, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3662, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07601572739187418, | |
| "grad_norm": 0.18460598587989807, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3676, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07863695937090433, | |
| "grad_norm": 0.17913301289081573, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.367, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08125819134993446, | |
| "grad_norm": 0.17687395215034485, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3665, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08387942332896461, | |
| "grad_norm": 0.18349960446357727, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3642, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08650065530799476, | |
| "grad_norm": 0.18453364074230194, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3635, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0891218872870249, | |
| "grad_norm": 0.18889248371124268, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.364, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09174311926605505, | |
| "grad_norm": 0.17462611198425293, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3643, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09436435124508519, | |
| "grad_norm": 0.1677028387784958, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3625, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09698558322411534, | |
| "grad_norm": 0.17899693548679352, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3625, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09960681520314547, | |
| "grad_norm": 0.1832207888364792, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3628, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10222804718217562, | |
| "grad_norm": 0.19299453496932983, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3608, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10484927916120576, | |
| "grad_norm": 0.17391589283943176, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3619, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10747051114023591, | |
| "grad_norm": 0.19322608411312103, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.362, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11009174311926606, | |
| "grad_norm": 0.19793660938739777, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3619, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1127129750982962, | |
| "grad_norm": 0.1966308206319809, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3614, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11533420707732635, | |
| "grad_norm": 0.1808447688817978, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.362, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11795543905635648, | |
| "grad_norm": 0.19594459235668182, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.361, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12057667103538663, | |
| "grad_norm": 0.20733164250850677, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3615, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12319790301441677, | |
| "grad_norm": 0.22402814030647278, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3605, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1258191349934469, | |
| "grad_norm": 0.26770442724227905, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3593, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12844036697247707, | |
| "grad_norm": 0.3045000433921814, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.36, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1310615989515072, | |
| "grad_norm": 0.39083045721054077, | |
| "learning_rate": 0.0, | |
| "loss": 10.3705, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1310615989515072, | |
| "eval_loss": 10.362990379333496, | |
| "eval_runtime": 8.8685, | |
| "eval_samples_per_second": 289.903, | |
| "eval_steps_per_second": 145.008, | |
| "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": 84569751552000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |