| { | |
| "best_metric": 1.0732088088989258, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-250", | |
| "epoch": 3.0027322404371586, | |
| "eval_steps": 50, | |
| "global_step": 274, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01092896174863388, | |
| "eval_loss": 1.390489935874939, | |
| "eval_runtime": 4.5055, | |
| "eval_samples_per_second": 136.5, | |
| "eval_steps_per_second": 4.439, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.546448087431694, | |
| "grad_norm": 0.08014677464962006, | |
| "learning_rate": 0.000212, | |
| "loss": 1.2152, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.546448087431694, | |
| "eval_loss": 1.160581111907959, | |
| "eval_runtime": 4.5553, | |
| "eval_samples_per_second": 135.008, | |
| "eval_steps_per_second": 4.391, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0956284153005464, | |
| "grad_norm": 0.07988499104976654, | |
| "learning_rate": 0.000212, | |
| "loss": 1.1693, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0956284153005464, | |
| "eval_loss": 1.1256314516067505, | |
| "eval_runtime": 4.5437, | |
| "eval_samples_per_second": 135.352, | |
| "eval_steps_per_second": 4.402, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6420765027322406, | |
| "grad_norm": 0.10925129801034927, | |
| "learning_rate": 0.000212, | |
| "loss": 1.1159, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6420765027322406, | |
| "eval_loss": 1.0956318378448486, | |
| "eval_runtime": 4.6207, | |
| "eval_samples_per_second": 133.096, | |
| "eval_steps_per_second": 4.328, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.191256830601093, | |
| "grad_norm": 0.10596978664398193, | |
| "learning_rate": 0.000212, | |
| "loss": 1.1005, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.191256830601093, | |
| "eval_loss": 1.0759819746017456, | |
| "eval_runtime": 4.6656, | |
| "eval_samples_per_second": 131.815, | |
| "eval_steps_per_second": 4.287, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.737704918032787, | |
| "grad_norm": 0.12843619287014008, | |
| "learning_rate": 0.000212, | |
| "loss": 1.0462, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.737704918032787, | |
| "eval_loss": 1.0732088088989258, | |
| "eval_runtime": 4.5325, | |
| "eval_samples_per_second": 135.688, | |
| "eval_steps_per_second": 4.413, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 274, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5797204929216512e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |