| { | |
| "best_metric": 11.086691856384277, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0016389748212493086, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.194874106246543e-05, | |
| "grad_norm": 2.0603280067443848, | |
| "learning_rate": 2e-05, | |
| "loss": 44.318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.194874106246543e-05, | |
| "eval_loss": 11.114025115966797, | |
| "eval_runtime": 39.3512, | |
| "eval_samples_per_second": 130.568, | |
| "eval_steps_per_second": 65.284, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016389748212493086, | |
| "grad_norm": 2.005817174911499, | |
| "learning_rate": 4e-05, | |
| "loss": 44.4549, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002458462231873963, | |
| "grad_norm": 1.9471571445465088, | |
| "learning_rate": 6e-05, | |
| "loss": 44.4111, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003277949642498617, | |
| "grad_norm": 1.733491063117981, | |
| "learning_rate": 8e-05, | |
| "loss": 44.5161, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00040974370531232716, | |
| "grad_norm": 2.5864765644073486, | |
| "learning_rate": 0.0001, | |
| "loss": 44.5415, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00040974370531232716, | |
| "eval_loss": 11.11214828491211, | |
| "eval_runtime": 38.9652, | |
| "eval_samples_per_second": 131.861, | |
| "eval_steps_per_second": 65.931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004916924463747926, | |
| "grad_norm": 2.0441107749938965, | |
| "learning_rate": 0.00012, | |
| "loss": 44.6115, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000573641187437258, | |
| "grad_norm": 2.113466501235962, | |
| "learning_rate": 0.00014, | |
| "loss": 44.4897, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006555899284997234, | |
| "grad_norm": 2.114064931869507, | |
| "learning_rate": 0.00016, | |
| "loss": 44.5232, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007375386695621888, | |
| "grad_norm": 2.1762325763702393, | |
| "learning_rate": 0.00018, | |
| "loss": 44.6048, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008194874106246543, | |
| "grad_norm": 1.996362328529358, | |
| "learning_rate": 0.0002, | |
| "loss": 44.4265, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008194874106246543, | |
| "eval_loss": 11.105292320251465, | |
| "eval_runtime": 38.5812, | |
| "eval_samples_per_second": 133.174, | |
| "eval_steps_per_second": 66.587, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009014361516871197, | |
| "grad_norm": 2.037875175476074, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 44.3682, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000983384892749585, | |
| "grad_norm": 1.9623230695724487, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 44.3456, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010653336338120505, | |
| "grad_norm": 2.0174567699432373, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 44.3511, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001147282374874516, | |
| "grad_norm": 2.3729968070983887, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 44.5621, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012292311159369815, | |
| "grad_norm": 2.0023834705352783, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.5584, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012292311159369815, | |
| "eval_loss": 11.094400405883789, | |
| "eval_runtime": 38.9949, | |
| "eval_samples_per_second": 131.761, | |
| "eval_steps_per_second": 65.88, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013111798569994469, | |
| "grad_norm": 2.1765761375427246, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.4832, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0013931285980619123, | |
| "grad_norm": 2.074971914291382, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 44.3978, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0014750773391243777, | |
| "grad_norm": 2.2266688346862793, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 44.4469, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001557026080186843, | |
| "grad_norm": 1.9929441213607788, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 44.3314, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0016389748212493086, | |
| "grad_norm": 1.9637781381607056, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 44.4735, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016389748212493086, | |
| "eval_loss": 11.086691856384277, | |
| "eval_runtime": 38.72, | |
| "eval_samples_per_second": 132.696, | |
| "eval_steps_per_second": 66.348, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 192896040960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |