| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002174054829662804, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.3481096593256084e-05, | |
| "eval_loss": 1.4841827154159546, | |
| "eval_runtime": 769.5249, | |
| "eval_samples_per_second": 12.584, | |
| "eval_steps_per_second": 6.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002174054829662804, | |
| "grad_norm": 0.3885715901851654, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4751, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004348109659325608, | |
| "grad_norm": 0.3961728513240814, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3895, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004348109659325608, | |
| "eval_loss": 1.4605967998504639, | |
| "eval_runtime": 782.2609, | |
| "eval_samples_per_second": 12.38, | |
| "eval_steps_per_second": 6.19, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006522164488988412, | |
| "grad_norm": 0.6922943592071533, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3912, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008696219318651216, | |
| "grad_norm": 0.5230913758277893, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3014, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008696219318651216, | |
| "eval_loss": 1.3218823671340942, | |
| "eval_runtime": 782.2744, | |
| "eval_samples_per_second": 12.379, | |
| "eval_steps_per_second": 6.19, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001087027414831402, | |
| "grad_norm": 0.6538348197937012, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2247, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013044328977976825, | |
| "grad_norm": 0.8174328207969666, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2074, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0013044328977976825, | |
| "eval_loss": 1.2257455587387085, | |
| "eval_runtime": 782.5361, | |
| "eval_samples_per_second": 12.375, | |
| "eval_steps_per_second": 6.188, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015218383807639629, | |
| "grad_norm": 0.7449996471405029, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2185, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0017392438637302433, | |
| "grad_norm": 0.9062265157699585, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1935, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017392438637302433, | |
| "eval_loss": 1.1781949996948242, | |
| "eval_runtime": 783.3477, | |
| "eval_samples_per_second": 12.362, | |
| "eval_steps_per_second": 6.181, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001956649346696524, | |
| "grad_norm": 0.7248935103416443, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.134, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002174054829662804, | |
| "grad_norm": 0.8981196880340576, | |
| "learning_rate": 0.0, | |
| "loss": 1.1538, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002174054829662804, | |
| "eval_loss": 1.1734018325805664, | |
| "eval_runtime": 782.847, | |
| "eval_samples_per_second": 12.37, | |
| "eval_steps_per_second": 6.185, | |
| "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": 8626612186644480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |