| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005682141030740383, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011364282061480765, | |
| "eval_loss": 4.128021717071533, | |
| "eval_runtime": 256.2346, | |
| "eval_samples_per_second": 14.459, | |
| "eval_steps_per_second": 7.232, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005682141030740383, | |
| "grad_norm": 8.950376510620117, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9502, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011364282061480766, | |
| "grad_norm": 5.7273054122924805, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8037, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011364282061480766, | |
| "eval_loss": 1.670504093170166, | |
| "eval_runtime": 258.6983, | |
| "eval_samples_per_second": 14.322, | |
| "eval_steps_per_second": 7.163, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017046423092221148, | |
| "grad_norm": 3.9927642345428467, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2672, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002272856412296153, | |
| "grad_norm": 2.623613119125366, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6607, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002272856412296153, | |
| "eval_loss": 0.4638822674751282, | |
| "eval_runtime": 258.497, | |
| "eval_samples_per_second": 14.333, | |
| "eval_steps_per_second": 7.168, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0028410705153701916, | |
| "grad_norm": 2.3146448135375977, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4691, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0034092846184442297, | |
| "grad_norm": 2.198410749435425, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3828, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0034092846184442297, | |
| "eval_loss": 0.3945086598396301, | |
| "eval_runtime": 257.4771, | |
| "eval_samples_per_second": 14.39, | |
| "eval_steps_per_second": 7.197, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003977498721518268, | |
| "grad_norm": 1.758271336555481, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4105, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004545712824592306, | |
| "grad_norm": 2.1799654960632324, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3516, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004545712824592306, | |
| "eval_loss": 0.3919433653354645, | |
| "eval_runtime": 257.8245, | |
| "eval_samples_per_second": 14.37, | |
| "eval_steps_per_second": 7.187, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005113926927666344, | |
| "grad_norm": 1.350976586341858, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3441, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005682141030740383, | |
| "grad_norm": 1.986354112625122, | |
| "learning_rate": 0.0, | |
| "loss": 0.4235, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005682141030740383, | |
| "eval_loss": 0.3892040550708771, | |
| "eval_runtime": 258.3821, | |
| "eval_samples_per_second": 14.339, | |
| "eval_steps_per_second": 7.172, | |
| "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": 9663973196562432.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |