| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14419610670511895, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002883922134102379, | |
| "eval_loss": 2.8393139839172363, | |
| "eval_runtime": 9.8942, | |
| "eval_samples_per_second": 14.756, | |
| "eval_steps_per_second": 7.378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014419610670511895, | |
| "grad_norm": 0.9696258306503296, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7359, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02883922134102379, | |
| "grad_norm": 0.5785666108131409, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3749, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02883922134102379, | |
| "eval_loss": 2.7782912254333496, | |
| "eval_runtime": 10.0611, | |
| "eval_samples_per_second": 14.511, | |
| "eval_steps_per_second": 7.256, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.043258832011535686, | |
| "grad_norm": 1.6506845951080322, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5855, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05767844268204758, | |
| "grad_norm": 1.235003113746643, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4757, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05767844268204758, | |
| "eval_loss": 2.419625997543335, | |
| "eval_runtime": 9.963, | |
| "eval_samples_per_second": 14.654, | |
| "eval_steps_per_second": 7.327, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07209805335255948, | |
| "grad_norm": 1.0580501556396484, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4597, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08651766402307137, | |
| "grad_norm": 1.4230085611343384, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4664, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08651766402307137, | |
| "eval_loss": 2.389425277709961, | |
| "eval_runtime": 10.1849, | |
| "eval_samples_per_second": 14.335, | |
| "eval_steps_per_second": 7.167, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10093727469358327, | |
| "grad_norm": 0.7601160407066345, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4343, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11535688536409516, | |
| "grad_norm": 0.8563252687454224, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4361, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11535688536409516, | |
| "eval_loss": 2.3816773891448975, | |
| "eval_runtime": 10.3915, | |
| "eval_samples_per_second": 14.05, | |
| "eval_steps_per_second": 7.025, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12977649603460706, | |
| "grad_norm": 0.9579905867576599, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.3712, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14419610670511895, | |
| "grad_norm": 1.130354404449463, | |
| "learning_rate": 0.0, | |
| "loss": 2.1678, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14419610670511895, | |
| "eval_loss": 2.3783786296844482, | |
| "eval_runtime": 10.1247, | |
| "eval_samples_per_second": 14.42, | |
| "eval_steps_per_second": 7.21, | |
| "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": 9617734090358784.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |