| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6644518272425249, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013289036544850499, | |
| "eval_loss": 2.996713399887085, | |
| "eval_runtime": 1.7935, | |
| "eval_samples_per_second": 17.842, | |
| "eval_steps_per_second": 8.921, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0664451827242525, | |
| "grad_norm": 3.3227691650390625, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7445, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.132890365448505, | |
| "grad_norm": 2.976918935775757, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4895, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.132890365448505, | |
| "eval_loss": 2.711103916168213, | |
| "eval_runtime": 1.1402, | |
| "eval_samples_per_second": 28.066, | |
| "eval_steps_per_second": 14.033, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19933554817275748, | |
| "grad_norm": 3.3211214542388916, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4196, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 3.485300302505493, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "eval_loss": 2.3668720722198486, | |
| "eval_runtime": 1.2122, | |
| "eval_samples_per_second": 26.399, | |
| "eval_steps_per_second": 13.2, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33222591362126247, | |
| "grad_norm": 2.3391213417053223, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0734, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39867109634551495, | |
| "grad_norm": 2.566633701324463, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8426, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.39867109634551495, | |
| "eval_loss": 2.2212672233581543, | |
| "eval_runtime": 1.1523, | |
| "eval_samples_per_second": 27.77, | |
| "eval_steps_per_second": 13.885, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 3.144744634628296, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.2405, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.53156146179402, | |
| "grad_norm": 2.478245735168457, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.0135, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.53156146179402, | |
| "eval_loss": 2.1549835205078125, | |
| "eval_runtime": 1.181, | |
| "eval_samples_per_second": 27.095, | |
| "eval_steps_per_second": 13.548, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5980066445182725, | |
| "grad_norm": 2.6744627952575684, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7333, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6644518272425249, | |
| "grad_norm": 2.8500657081604004, | |
| "learning_rate": 0.0, | |
| "loss": 1.8794, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6644518272425249, | |
| "eval_loss": 2.1422481536865234, | |
| "eval_runtime": 1.1288, | |
| "eval_samples_per_second": 28.349, | |
| "eval_steps_per_second": 14.175, | |
| "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": 383619013017600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |