| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016191054442420564, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.238210888484113e-05, | |
| "eval_loss": 1.5096166133880615, | |
| "eval_runtime": 1087.7586, | |
| "eval_samples_per_second": 11.954, | |
| "eval_steps_per_second": 5.977, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016191054442420561, | |
| "grad_norm": 2.1016464233398438, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3974, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00032382108884841123, | |
| "grad_norm": 1.9378647804260254, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3497, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00032382108884841123, | |
| "eval_loss": 1.039423942565918, | |
| "eval_runtime": 1092.1981, | |
| "eval_samples_per_second": 11.905, | |
| "eval_steps_per_second": 5.953, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004857316332726169, | |
| "grad_norm": 1.3999601602554321, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8078, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006476421776968225, | |
| "grad_norm": 1.3233897686004639, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6382, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006476421776968225, | |
| "eval_loss": 0.43094074726104736, | |
| "eval_runtime": 1089.4458, | |
| "eval_samples_per_second": 11.935, | |
| "eval_steps_per_second": 5.968, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008095527221210282, | |
| "grad_norm": 2.1263442039489746, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4102, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009714632665452338, | |
| "grad_norm": 1.4547182321548462, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4076, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009714632665452338, | |
| "eval_loss": 0.3389413058757782, | |
| "eval_runtime": 1089.1438, | |
| "eval_samples_per_second": 11.939, | |
| "eval_steps_per_second": 5.97, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0011333738109694394, | |
| "grad_norm": 1.7773916721343994, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3775, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001295284355393645, | |
| "grad_norm": 1.164242148399353, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4087, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001295284355393645, | |
| "eval_loss": 0.30746862292289734, | |
| "eval_runtime": 1090.1224, | |
| "eval_samples_per_second": 11.928, | |
| "eval_steps_per_second": 5.964, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0014571948998178506, | |
| "grad_norm": 1.8661969900131226, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.346, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0016191054442420564, | |
| "grad_norm": 1.8744398355484009, | |
| "learning_rate": 0.0, | |
| "loss": 0.2889, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0016191054442420564, | |
| "eval_loss": 0.3020668029785156, | |
| "eval_runtime": 1092.5142, | |
| "eval_samples_per_second": 11.902, | |
| "eval_steps_per_second": 5.951, | |
| "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": 1.2207124037763072e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |