| { | |
| "best_metric": 1.4240585565567017, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.45146726862302483, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009029345372460496, | |
| "grad_norm": 37.726409912109375, | |
| "learning_rate": 5e-05, | |
| "loss": 7.8619, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "eval_loss": 11.497468948364258, | |
| "eval_runtime": 24.8169, | |
| "eval_samples_per_second": 30.1, | |
| "eval_steps_per_second": 3.788, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "grad_norm": 49.88737487792969, | |
| "learning_rate": 0.0001, | |
| "loss": 8.7427, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02708803611738149, | |
| "grad_norm": 33.74674987792969, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.1645, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03611738148984198, | |
| "grad_norm": 21.305233001708984, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.5492, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.045146726862302484, | |
| "grad_norm": 29.97848892211914, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.4931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05417607223476298, | |
| "grad_norm": 9.829663276672363, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.5154, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06320541760722348, | |
| "grad_norm": 8.082307815551758, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.1944, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07223476297968397, | |
| "grad_norm": 9.833307266235352, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9339, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08126410835214447, | |
| "grad_norm": 7.702181816101074, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.1949, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09029345372460497, | |
| "grad_norm": 6.005523204803467, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7961, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09932279909706546, | |
| "grad_norm": 5.7989115715026855, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.5572, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10835214446952596, | |
| "grad_norm": 5.417959213256836, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4186, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11738148984198646, | |
| "grad_norm": 5.730159282684326, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5944, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12641083521444696, | |
| "grad_norm": 7.527454853057861, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8621, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13544018058690746, | |
| "grad_norm": 5.438515663146973, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.7432, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14446952595936793, | |
| "grad_norm": 6.02592134475708, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7456, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15349887133182843, | |
| "grad_norm": 5.580264568328857, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.6698, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16252821670428894, | |
| "grad_norm": 5.626596927642822, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6433, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17155756207674944, | |
| "grad_norm": 5.15617561340332, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.446, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18058690744920994, | |
| "grad_norm": 3.988950252532959, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4819, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18961625282167044, | |
| "grad_norm": 3.58742094039917, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4135, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1986455981941309, | |
| "grad_norm": 3.880713701248169, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.4062, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2076749435665914, | |
| "grad_norm": 4.092154502868652, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.146, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21670428893905191, | |
| "grad_norm": 4.35385274887085, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3064, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22573363431151242, | |
| "grad_norm": 3.7875988483428955, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1775, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22573363431151242, | |
| "eval_loss": 1.5664660930633545, | |
| "eval_runtime": 24.7903, | |
| "eval_samples_per_second": 30.133, | |
| "eval_steps_per_second": 3.792, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23476297968397292, | |
| "grad_norm": 4.827845096588135, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6863, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24379232505643342, | |
| "grad_norm": 3.786040782928467, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4784, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2528216704288939, | |
| "grad_norm": 4.99733829498291, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.5557, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2618510158013544, | |
| "grad_norm": 3.477863073348999, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4737, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2708803611738149, | |
| "grad_norm": 3.390841245651245, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.479, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2799097065462754, | |
| "grad_norm": 3.5737245082855225, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.4372, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28893905191873587, | |
| "grad_norm": 3.6658477783203125, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3752, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2979683972911964, | |
| "grad_norm": 3.751608371734619, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3446, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.30699774266365687, | |
| "grad_norm": 4.204435348510742, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4559, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3160270880361174, | |
| "grad_norm": 3.454246997833252, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.2622, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32505643340857787, | |
| "grad_norm": 3.807039737701416, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1839, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3340857787810384, | |
| "grad_norm": 3.116135597229004, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0593, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3431151241534989, | |
| "grad_norm": 3.280864953994751, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2688, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.35214446952595935, | |
| "grad_norm": 3.6423065662384033, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5025, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3611738148984199, | |
| "grad_norm": 4.164337158203125, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.4415, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.37020316027088035, | |
| "grad_norm": 3.5268914699554443, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.5199, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3792325056433409, | |
| "grad_norm": 3.11435866355896, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.4073, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.38826185101580135, | |
| "grad_norm": 3.4523799419403076, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2832, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3972911963882618, | |
| "grad_norm": 3.1517751216888428, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.4045, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.40632054176072235, | |
| "grad_norm": 3.2089760303497314, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.3794, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4153498871331828, | |
| "grad_norm": 3.2101340293884277, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2995, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.42437923250564336, | |
| "grad_norm": 3.4631175994873047, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4122, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.43340857787810383, | |
| "grad_norm": 3.2164947986602783, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1155, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.44243792325056436, | |
| "grad_norm": 3.03357195854187, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0593, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.45146726862302483, | |
| "grad_norm": 3.364856004714966, | |
| "learning_rate": 0.0, | |
| "loss": 1.016, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.45146726862302483, | |
| "eval_loss": 1.4240585565567017, | |
| "eval_runtime": 24.8043, | |
| "eval_samples_per_second": 30.116, | |
| "eval_steps_per_second": 3.79, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |