| { | |
| "best_metric": 0.5954957604408264, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0002807766281534725, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.12310651261389e-05, | |
| "grad_norm": 0.4133361279964447, | |
| "learning_rate": 0.0001, | |
| "loss": 0.249, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.12310651261389e-05, | |
| "eval_loss": 0.8146378397941589, | |
| "eval_runtime": 13134.3165, | |
| "eval_samples_per_second": 2.854, | |
| "eval_steps_per_second": 1.427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.24621302522778e-05, | |
| "grad_norm": 0.47328856587409973, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3426, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.36931953784167e-05, | |
| "grad_norm": 0.5796116590499878, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.3981, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.49242605045556e-05, | |
| "grad_norm": 0.6268879771232605, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.6075, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.61553256306945e-05, | |
| "grad_norm": 0.47303611040115356, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.4675, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.73863907568334e-05, | |
| "grad_norm": 0.5359629988670349, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.6045, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.86174558829723e-05, | |
| "grad_norm": 0.462693452835083, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.2506, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.98485210091112e-05, | |
| "grad_norm": 0.5416392087936401, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.5026, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001010795861352501, | |
| "grad_norm": 0.6114709973335266, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.3977, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000112310651261389, | |
| "grad_norm": 0.6693122386932373, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.6551, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001235417163875279, | |
| "grad_norm": 0.5685533285140991, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.3929, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0001347727815136668, | |
| "grad_norm": 0.6653563976287842, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.3422, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0001460038466398057, | |
| "grad_norm": 0.8029443621635437, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.6446, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0001572349117659446, | |
| "grad_norm": 0.8001309037208557, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.6897, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0001684659768920835, | |
| "grad_norm": 0.5024366974830627, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.1967, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0001796970420182224, | |
| "grad_norm": 0.6300889253616333, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.6056, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0001909281071443613, | |
| "grad_norm": 0.5821546316146851, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.3552, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0002021591722705002, | |
| "grad_norm": 0.5437122583389282, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.4312, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0002133902373966391, | |
| "grad_norm": 0.5699002742767334, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.5065, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.000224621302522778, | |
| "grad_norm": 0.7202039361000061, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.4888, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00023585236764891692, | |
| "grad_norm": 0.6731573343276978, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.7045, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0002470834327750558, | |
| "grad_norm": 0.6215887069702148, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.5809, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0002583144979011947, | |
| "grad_norm": 0.8584797978401184, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.6433, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0002695455630273336, | |
| "grad_norm": 0.7280075550079346, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.5682, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0002807766281534725, | |
| "grad_norm": 0.6702390909194946, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.6913, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0002807766281534725, | |
| "eval_loss": 0.5954957604408264, | |
| "eval_runtime": 13213.5826, | |
| "eval_samples_per_second": 2.837, | |
| "eval_steps_per_second": 1.419, | |
| "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": 3.70943641780224e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |