| { | |
| "best_metric": 0.6706960797309875, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.003800294522825519, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015201178091302076, | |
| "grad_norm": 3.6593680381774902, | |
| "learning_rate": 5e-05, | |
| "loss": 10.9362, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015201178091302076, | |
| "eval_loss": 2.270036220550537, | |
| "eval_runtime": 2217.9223, | |
| "eval_samples_per_second": 19.982, | |
| "eval_steps_per_second": 2.498, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003040235618260415, | |
| "grad_norm": 4.245506763458252, | |
| "learning_rate": 0.0001, | |
| "loss": 12.8607, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00045603534273906226, | |
| "grad_norm": 4.411743640899658, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 13.5941, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000608047123652083, | |
| "grad_norm": 5.3891096115112305, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 14.3746, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007600589045651038, | |
| "grad_norm": 7.611150741577148, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 16.8511, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009120706854781245, | |
| "grad_norm": 7.441198348999023, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 16.271, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010640824663911454, | |
| "grad_norm": 8.687851905822754, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 16.6546, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001216094247304166, | |
| "grad_norm": 18.38853645324707, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 19.7066, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013681060282171868, | |
| "grad_norm": 55.841705322265625, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 27.5424, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015201178091302076, | |
| "grad_norm": 42.36283874511719, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 25.9464, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016721295900432283, | |
| "grad_norm": 37.95155715942383, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 25.4448, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001824141370956249, | |
| "grad_norm": 23.544416427612305, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 19.4115, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00197615315186927, | |
| "grad_norm": 6.003608226776123, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.717, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0021281649327822907, | |
| "grad_norm": 1.9133445024490356, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 8.8507, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0022801767136953113, | |
| "grad_norm": 1.9236044883728027, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 9.9265, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002432188494608332, | |
| "grad_norm": 2.067864179611206, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.75, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0025842002755213527, | |
| "grad_norm": 2.5621371269226074, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.0612, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0027362120564343737, | |
| "grad_norm": 4.215025901794434, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 12.8646, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0028882238373473946, | |
| "grad_norm": 5.507603168487549, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.8597, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003040235618260415, | |
| "grad_norm": 6.5292134284973145, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.8724, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003192247399173436, | |
| "grad_norm": 12.831018447875977, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.5659, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0033442591800864566, | |
| "grad_norm": 11.646411895751953, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 9.7654, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0034962709609994776, | |
| "grad_norm": 14.624390602111816, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.7632, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003648282741912498, | |
| "grad_norm": 17.542835235595703, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 12.8791, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003800294522825519, | |
| "grad_norm": 9.677604675292969, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 12.1658, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003800294522825519, | |
| "eval_loss": 0.6706960797309875, | |
| "eval_runtime": 2218.0335, | |
| "eval_samples_per_second": 19.981, | |
| "eval_steps_per_second": 2.498, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.537984561503273e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |