| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02321981424148607, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007739938080495357, | |
| "eval_loss": 1.6945956945419312, | |
| "eval_runtime": 110.0753, | |
| "eval_samples_per_second": 4.951, | |
| "eval_steps_per_second": 2.48, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023219814241486067, | |
| "grad_norm": 4.82108736038208, | |
| "learning_rate": 6e-05, | |
| "loss": 6.8237, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003869969040247678, | |
| "eval_loss": 1.6913092136383057, | |
| "eval_runtime": 111.3468, | |
| "eval_samples_per_second": 4.895, | |
| "eval_steps_per_second": 2.452, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0046439628482972135, | |
| "grad_norm": 1.9441202878952026, | |
| "learning_rate": 0.00012, | |
| "loss": 6.141, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00696594427244582, | |
| "grad_norm": 1.3660614490509033, | |
| "learning_rate": 0.00018, | |
| "loss": 5.5771, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007739938080495356, | |
| "eval_loss": 1.6541721820831299, | |
| "eval_runtime": 111.3024, | |
| "eval_samples_per_second": 4.897, | |
| "eval_steps_per_second": 2.453, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009287925696594427, | |
| "grad_norm": 3.83369779586792, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 5.9687, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011609907120743035, | |
| "grad_norm": 1.0999690294265747, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.028, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011609907120743035, | |
| "eval_loss": 1.5518581867218018, | |
| "eval_runtime": 111.3292, | |
| "eval_samples_per_second": 4.895, | |
| "eval_steps_per_second": 2.452, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01393188854489164, | |
| "grad_norm": 1.7612863779067993, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.8503, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015479876160990712, | |
| "eval_loss": 1.4609495401382446, | |
| "eval_runtime": 111.3426, | |
| "eval_samples_per_second": 4.895, | |
| "eval_steps_per_second": 2.452, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016253869969040248, | |
| "grad_norm": 1.8704389333724976, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 6.6885, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018575851393188854, | |
| "grad_norm": 1.0107614994049072, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 5.4309, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01934984520123839, | |
| "eval_loss": 1.4435930252075195, | |
| "eval_runtime": 111.2717, | |
| "eval_samples_per_second": 4.898, | |
| "eval_steps_per_second": 2.453, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02089783281733746, | |
| "grad_norm": 1.209702968597412, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 5.7998, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02321981424148607, | |
| "grad_norm": 1.0272233486175537, | |
| "learning_rate": 0.0, | |
| "loss": 6.2568, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02321981424148607, | |
| "eval_loss": 1.4408866167068481, | |
| "eval_runtime": 111.248, | |
| "eval_samples_per_second": 4.899, | |
| "eval_steps_per_second": 2.454, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2987609806536704e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |