| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18248175182481752, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036496350364963502, | |
| "eval_loss": 11.937646865844727, | |
| "eval_runtime": 0.3936, | |
| "eval_samples_per_second": 294.683, | |
| "eval_steps_per_second": 147.341, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0364963503649635, | |
| "grad_norm": 0.01586594060063362, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9381, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04744525547445255, | |
| "eval_loss": 11.937573432922363, | |
| "eval_runtime": 0.3983, | |
| "eval_samples_per_second": 291.228, | |
| "eval_steps_per_second": 145.614, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 0.02235872857272625, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 11.9375, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0948905109489051, | |
| "eval_loss": 11.937477111816406, | |
| "eval_runtime": 0.4003, | |
| "eval_samples_per_second": 289.758, | |
| "eval_steps_per_second": 144.879, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10948905109489052, | |
| "grad_norm": 0.010235522873699665, | |
| "learning_rate": 2.5e-05, | |
| "loss": 11.937, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14233576642335766, | |
| "eval_loss": 11.937421798706055, | |
| "eval_runtime": 0.395, | |
| "eval_samples_per_second": 293.694, | |
| "eval_steps_per_second": 146.847, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 0.008573858067393303, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 11.9364, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18248175182481752, | |
| "grad_norm": 0.011130424216389656, | |
| "learning_rate": 0.0, | |
| "loss": 11.9372, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5908070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |