| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9302325581395349, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09302325581395349, | |
| "grad_norm": 1.4063793420791626, | |
| "learning_rate": 0.0001, | |
| "loss": 3.032, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09302325581395349, | |
| "eval_loss": 3.0643718242645264, | |
| "eval_runtime": 87.6168, | |
| "eval_samples_per_second": 10.512, | |
| "eval_steps_per_second": 1.324, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "grad_norm": 1.386621117591858, | |
| "learning_rate": 0.0002, | |
| "loss": 3.0078, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.27906976744186046, | |
| "grad_norm": 1.3237416744232178, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 2.9016, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.27906976744186046, | |
| "eval_loss": 2.3843867778778076, | |
| "eval_runtime": 86.6987, | |
| "eval_samples_per_second": 10.623, | |
| "eval_steps_per_second": 1.338, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 1.200042486190796, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.3763, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 0.8425291776657104, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.9397, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5581395348837209, | |
| "grad_norm": 0.6947051882743835, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 1.702, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5581395348837209, | |
| "eval_loss": 1.5868232250213623, | |
| "eval_runtime": 85.7137, | |
| "eval_samples_per_second": 10.745, | |
| "eval_steps_per_second": 1.353, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6511627906976745, | |
| "grad_norm": 0.7523099780082703, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 1.5591, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 0.790450930595398, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.4641, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8372093023255814, | |
| "grad_norm": 0.7199322581291199, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 1.3782, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8372093023255814, | |
| "eval_loss": 1.290962815284729, | |
| "eval_runtime": 85.4665, | |
| "eval_samples_per_second": 10.776, | |
| "eval_steps_per_second": 1.357, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 0.5940478444099426, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 1.2827, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.589463780163584e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |