| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04106143817687215, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020530719088436073, | |
| "eval_loss": 1.3546793460845947, | |
| "eval_runtime": 87.9312, | |
| "eval_samples_per_second": 23.325, | |
| "eval_steps_per_second": 11.668, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002053071908843607, | |
| "grad_norm": 0.9955037236213684, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 1.0432, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004106143817687214, | |
| "grad_norm": 1.3997418880462646, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.4604, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006159215726530822, | |
| "grad_norm": 0.8764151334762573, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 0.3427, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008212287635374429, | |
| "grad_norm": 0.648871660232544, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.3203, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010265359544218037, | |
| "grad_norm": 0.4984304904937744, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.3191, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010265359544218037, | |
| "eval_loss": 0.31821250915527344, | |
| "eval_runtime": 86.0569, | |
| "eval_samples_per_second": 23.833, | |
| "eval_steps_per_second": 11.922, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012318431453061643, | |
| "grad_norm": 0.47477608919143677, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.315, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.014371503361905251, | |
| "grad_norm": 0.526182234287262, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3055, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.016424575270748858, | |
| "grad_norm": 0.6147613525390625, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.3017, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.018477647179592466, | |
| "grad_norm": 0.6105421781539917, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.3058, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.020530719088436074, | |
| "grad_norm": 0.5068532228469849, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.2953, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.020530719088436074, | |
| "eval_loss": 0.2939603924751282, | |
| "eval_runtime": 86.3176, | |
| "eval_samples_per_second": 23.761, | |
| "eval_steps_per_second": 11.886, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02258379099727968, | |
| "grad_norm": 0.619922399520874, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.308, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.024636862906123286, | |
| "grad_norm": 0.47642096877098083, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.2825, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.026689934814966895, | |
| "grad_norm": 0.38181358575820923, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.2863, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.028743006723810503, | |
| "grad_norm": 0.5245420336723328, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.2711, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.030796078632654107, | |
| "grad_norm": 0.40633440017700195, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.2751, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.030796078632654107, | |
| "eval_loss": 0.2869807481765747, | |
| "eval_runtime": 86.1617, | |
| "eval_samples_per_second": 23.804, | |
| "eval_steps_per_second": 11.908, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.032849150541497715, | |
| "grad_norm": 0.4666227102279663, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.2773, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03490222245034132, | |
| "grad_norm": 0.40914592146873474, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.2505, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03695529435918493, | |
| "grad_norm": 0.4898912012577057, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.2766, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03900836626802854, | |
| "grad_norm": 0.444612592458725, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.2722, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.04106143817687215, | |
| "grad_norm": 0.48914796113967896, | |
| "learning_rate": 0.0, | |
| "loss": 0.2969, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04106143817687215, | |
| "eval_loss": 0.28439101576805115, | |
| "eval_runtime": 86.2057, | |
| "eval_samples_per_second": 23.792, | |
| "eval_steps_per_second": 11.902, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.51479053795328e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |