| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02987551867219917, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0033195020746887966, | |
| "grad_norm": 0.1223829835653305, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3834, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033195020746887966, | |
| "eval_loss": 10.375598907470703, | |
| "eval_runtime": 2.5882, | |
| "eval_samples_per_second": 196.276, | |
| "eval_steps_per_second": 49.069, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006639004149377593, | |
| "grad_norm": 0.1390531361103058, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3776, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00995850622406639, | |
| "grad_norm": 0.12366314232349396, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3773, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00995850622406639, | |
| "eval_loss": 10.37536334991455, | |
| "eval_runtime": 2.6742, | |
| "eval_samples_per_second": 189.966, | |
| "eval_steps_per_second": 47.492, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013278008298755186, | |
| "grad_norm": 0.11774402111768723, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3769, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 0.12266664206981659, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3728, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01991701244813278, | |
| "grad_norm": 0.11839405447244644, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3754, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01991701244813278, | |
| "eval_loss": 10.374419212341309, | |
| "eval_runtime": 2.8668, | |
| "eval_samples_per_second": 177.202, | |
| "eval_steps_per_second": 44.301, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023236514522821577, | |
| "grad_norm": 0.12177033722400665, | |
| "learning_rate": 0.00014, | |
| "loss": 10.36, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026556016597510373, | |
| "grad_norm": 0.11929324269294739, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3723, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02987551867219917, | |
| "grad_norm": 0.12620662152767181, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3648, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02987551867219917, | |
| "eval_loss": 10.372748374938965, | |
| "eval_runtime": 2.6384, | |
| "eval_samples_per_second": 192.538, | |
| "eval_steps_per_second": 48.134, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2191863054336.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |