| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02061218179944347, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00041224363598886944, | |
| "eval_loss": 2.2431154251098633, | |
| "eval_runtime": 80.7452, | |
| "eval_samples_per_second": 12.657, | |
| "eval_steps_per_second": 6.329, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020612181799443473, | |
| "grad_norm": 2.1363298892974854, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0041224363598886945, | |
| "grad_norm": 2.858330488204956, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7039, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0041224363598886945, | |
| "eval_loss": 1.7575262784957886, | |
| "eval_runtime": 85.318, | |
| "eval_samples_per_second": 11.979, | |
| "eval_steps_per_second": 5.989, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006183654539833041, | |
| "grad_norm": 3.944808006286621, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2071, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008244872719777389, | |
| "grad_norm": 1.3849436044692993, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.157, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008244872719777389, | |
| "eval_loss": 1.1688629388809204, | |
| "eval_runtime": 85.7517, | |
| "eval_samples_per_second": 11.918, | |
| "eval_steps_per_second": 5.959, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010306090899721735, | |
| "grad_norm": 2.004284143447876, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1034, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012367309079666083, | |
| "grad_norm": 1.3697354793548584, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0457, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012367309079666083, | |
| "eval_loss": 1.1273069381713867, | |
| "eval_runtime": 85.6446, | |
| "eval_samples_per_second": 11.933, | |
| "eval_steps_per_second": 5.967, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01442852725961043, | |
| "grad_norm": 2.059553623199463, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0748, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016489745439554778, | |
| "grad_norm": 1.5975080728530884, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9761, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016489745439554778, | |
| "eval_loss": 1.1080728769302368, | |
| "eval_runtime": 85.784, | |
| "eval_samples_per_second": 11.914, | |
| "eval_steps_per_second": 5.957, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018550963619499122, | |
| "grad_norm": 1.6504549980163574, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1147, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02061218179944347, | |
| "grad_norm": 1.9928545951843262, | |
| "learning_rate": 0.0, | |
| "loss": 0.9259, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02061218179944347, | |
| "eval_loss": 1.1036310195922852, | |
| "eval_runtime": 85.8891, | |
| "eval_samples_per_second": 11.899, | |
| "eval_steps_per_second": 5.95, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 9432777665544192.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |