| { | |
| "best_metric": 9.246109962463379, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.11782032400589101, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00471281296023564, | |
| "grad_norm": 11.932207107543945, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00471281296023564, | |
| "eval_loss": 11.466318130493164, | |
| "eval_runtime": 0.2733, | |
| "eval_samples_per_second": 182.951, | |
| "eval_steps_per_second": 47.567, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00942562592047128, | |
| "grad_norm": 11.80747127532959, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8923, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014138438880706922, | |
| "grad_norm": 11.80627727508545, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.8495, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01885125184094256, | |
| "grad_norm": 10.285013198852539, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.5343, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023564064801178203, | |
| "grad_norm": 9.46924114227295, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.3134, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028276877761413844, | |
| "grad_norm": 9.285470008850098, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.1314, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.032989690721649485, | |
| "grad_norm": 9.64939022064209, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.9697, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03770250368188512, | |
| "grad_norm": 9.303040504455566, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.7524, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04241531664212077, | |
| "grad_norm": 9.011505126953125, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.5939, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.047128129602356406, | |
| "grad_norm": 8.873916625976562, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.4448, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05184094256259205, | |
| "grad_norm": 8.19795036315918, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.2765, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05655375552282769, | |
| "grad_norm": 7.416764736175537, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.0904, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.061266568483063326, | |
| "grad_norm": 6.711239337921143, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.1096, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06597938144329897, | |
| "grad_norm": 6.1158127784729, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.0172, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07069219440353461, | |
| "grad_norm": 5.647707939147949, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 9.914, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07540500736377025, | |
| "grad_norm": 5.225461483001709, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 9.8377, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0801178203240059, | |
| "grad_norm": 4.8900227546691895, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 9.7757, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08483063328424154, | |
| "grad_norm": 4.296078681945801, | |
| "learning_rate": 7.75e-05, | |
| "loss": 9.682, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08954344624447717, | |
| "grad_norm": 4.111123085021973, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 9.6565, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09425625920471281, | |
| "grad_norm": 3.808967351913452, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.5633, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09896907216494845, | |
| "grad_norm": 3.6438040733337402, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.4928, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1036818851251841, | |
| "grad_norm": 3.6163392066955566, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 9.465, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10839469808541974, | |
| "grad_norm": 3.513592481613159, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 9.3972, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11310751104565538, | |
| "grad_norm": 3.4856817722320557, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.3694, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11782032400589101, | |
| "grad_norm": 4.087053298950195, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 9.2896, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11782032400589101, | |
| "eval_loss": 9.246109962463379, | |
| "eval_runtime": 0.28, | |
| "eval_samples_per_second": 178.563, | |
| "eval_steps_per_second": 46.426, | |
| "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": 116224411828224.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |