| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04996252810392206, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009992505620784412, | |
| "eval_loss": 11.9287691116333, | |
| "eval_runtime": 3.7887, | |
| "eval_samples_per_second": 111.383, | |
| "eval_steps_per_second": 55.691, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004996252810392206, | |
| "grad_norm": 0.013544662855565548, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9297, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009992505620784412, | |
| "grad_norm": 0.021767830476164818, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9262, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009992505620784412, | |
| "eval_loss": 11.928720474243164, | |
| "eval_runtime": 3.8391, | |
| "eval_samples_per_second": 109.921, | |
| "eval_steps_per_second": 54.96, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014988758431176618, | |
| "grad_norm": 0.019163450226187706, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9331, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019985011241568824, | |
| "grad_norm": 0.02887827344238758, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9309, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019985011241568824, | |
| "eval_loss": 11.928622245788574, | |
| "eval_runtime": 3.8279, | |
| "eval_samples_per_second": 110.244, | |
| "eval_steps_per_second": 55.122, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02498126405196103, | |
| "grad_norm": 0.013710311613976955, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.929, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029977516862353237, | |
| "grad_norm": 0.016847524791955948, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9254, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.029977516862353237, | |
| "eval_loss": 11.928537368774414, | |
| "eval_runtime": 3.8928, | |
| "eval_samples_per_second": 108.404, | |
| "eval_steps_per_second": 54.202, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03497376967274544, | |
| "grad_norm": 0.022019729018211365, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9307, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03997002248313765, | |
| "grad_norm": 0.01824772171676159, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9313, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03997002248313765, | |
| "eval_loss": 11.928504943847656, | |
| "eval_runtime": 3.868, | |
| "eval_samples_per_second": 109.1, | |
| "eval_steps_per_second": 54.55, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04496627529352985, | |
| "grad_norm": 0.021437140181660652, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9309, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04996252810392206, | |
| "grad_norm": 0.023462459444999695, | |
| "learning_rate": 0.0, | |
| "loss": 11.9284, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04996252810392206, | |
| "eval_loss": 11.928500175476074, | |
| "eval_runtime": 3.7785, | |
| "eval_samples_per_second": 111.685, | |
| "eval_steps_per_second": 55.843, | |
| "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": 5908070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |