| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006867660188173889, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001373532037634778, | |
| "eval_loss": 1.981343388557434, | |
| "eval_runtime": 108.8442, | |
| "eval_samples_per_second": 28.169, | |
| "eval_steps_per_second": 14.084, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000686766018817389, | |
| "grad_norm": 0.7336399555206299, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7832, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001373532037634778, | |
| "grad_norm": 0.8265002965927124, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8771, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001373532037634778, | |
| "eval_loss": 1.938093662261963, | |
| "eval_runtime": 108.8765, | |
| "eval_samples_per_second": 28.16, | |
| "eval_steps_per_second": 14.08, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020602980564521666, | |
| "grad_norm": 0.7830203771591187, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.85, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002747064075269556, | |
| "grad_norm": 0.796001672744751, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8302, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002747064075269556, | |
| "eval_loss": 1.7976608276367188, | |
| "eval_runtime": 108.7834, | |
| "eval_samples_per_second": 28.184, | |
| "eval_steps_per_second": 14.092, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0034338300940869445, | |
| "grad_norm": 0.679097056388855, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6732, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004120596112904333, | |
| "grad_norm": 0.9102851152420044, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6933, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004120596112904333, | |
| "eval_loss": 1.7453827857971191, | |
| "eval_runtime": 107.8127, | |
| "eval_samples_per_second": 28.438, | |
| "eval_steps_per_second": 14.219, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004807362131721722, | |
| "grad_norm": 1.0547045469284058, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6154, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005494128150539112, | |
| "grad_norm": 0.9129773378372192, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7811, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005494128150539112, | |
| "eval_loss": 1.7244644165039062, | |
| "eval_runtime": 109.0993, | |
| "eval_samples_per_second": 28.103, | |
| "eval_steps_per_second": 14.051, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0061808941693565, | |
| "grad_norm": 0.783636748790741, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5446, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006867660188173889, | |
| "grad_norm": 0.7290799617767334, | |
| "learning_rate": 0.0, | |
| "loss": 1.6069, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006867660188173889, | |
| "eval_loss": 1.721480131149292, | |
| "eval_runtime": 108.121, | |
| "eval_samples_per_second": 28.357, | |
| "eval_steps_per_second": 14.179, | |
| "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": 2207005104144384.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |