| { | |
| "best_metric": 3.064283847808838, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.22753128555176336, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009101251422070534, | |
| "grad_norm": 2.209428310394287, | |
| "learning_rate": 5e-05, | |
| "loss": 4.9719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009101251422070534, | |
| "eval_loss": 4.942025184631348, | |
| "eval_runtime": 3.9301, | |
| "eval_samples_per_second": 188.545, | |
| "eval_steps_per_second": 23.664, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01820250284414107, | |
| "grad_norm": 1.7319118976593018, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9787, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.027303754266211604, | |
| "grad_norm": 1.4984430074691772, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.834, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03640500568828214, | |
| "grad_norm": 1.723325252532959, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.0757, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04550625711035267, | |
| "grad_norm": 1.8475040197372437, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.0175, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05460750853242321, | |
| "grad_norm": 1.380941390991211, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.4863, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06370875995449374, | |
| "grad_norm": 1.980647087097168, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.8039, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07281001137656427, | |
| "grad_norm": 1.38150155544281, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.8026, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08191126279863481, | |
| "grad_norm": 1.7724114656448364, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.9867, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09101251422070535, | |
| "grad_norm": 1.2675881385803223, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.3271, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10011376564277588, | |
| "grad_norm": 1.3056012392044067, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.4681, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10921501706484642, | |
| "grad_norm": 1.3030096292495728, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.0861, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11831626848691695, | |
| "grad_norm": 1.2706266641616821, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.8508, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12741751990898748, | |
| "grad_norm": 1.6742432117462158, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.7126, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13651877133105803, | |
| "grad_norm": 1.458900809288025, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.5975, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14562002275312855, | |
| "grad_norm": 1.443761944770813, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.5467, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1547212741751991, | |
| "grad_norm": 1.7539066076278687, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.653, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16382252559726962, | |
| "grad_norm": 1.558334469795227, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.4541, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17292377701934017, | |
| "grad_norm": 1.7318171262741089, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.3867, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1820250284414107, | |
| "grad_norm": 1.4786357879638672, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.5035, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19112627986348124, | |
| "grad_norm": 1.769963264465332, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.8702, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20022753128555176, | |
| "grad_norm": 1.5237165689468384, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.6431, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20932878270762229, | |
| "grad_norm": 1.3721243143081665, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.7161, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21843003412969283, | |
| "grad_norm": 1.449666142463684, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.5503, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22753128555176336, | |
| "grad_norm": 1.7347791194915771, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.1498, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22753128555176336, | |
| "eval_loss": 3.064283847808838, | |
| "eval_runtime": 3.9326, | |
| "eval_samples_per_second": 188.426, | |
| "eval_steps_per_second": 23.649, | |
| "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": 4560220952985600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |