| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1635322976287817, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003270645952575634, | |
| "eval_loss": 2.972163677215576, | |
| "eval_runtime": 12.6269, | |
| "eval_samples_per_second": 10.216, | |
| "eval_steps_per_second": 5.148, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016353229762878167, | |
| "grad_norm": 3.5115768909454346, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0694, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.032706459525756335, | |
| "grad_norm": 2.791400909423828, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6486, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.032706459525756335, | |
| "eval_loss": 2.316014528274536, | |
| "eval_runtime": 13.0805, | |
| "eval_samples_per_second": 9.862, | |
| "eval_steps_per_second": 4.969, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04905968928863451, | |
| "grad_norm": 2.6898434162139893, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.089, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06541291905151267, | |
| "grad_norm": 2.5392708778381348, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7886, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06541291905151267, | |
| "eval_loss": 1.6090553998947144, | |
| "eval_runtime": 12.7089, | |
| "eval_samples_per_second": 10.15, | |
| "eval_steps_per_second": 5.115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08176614881439084, | |
| "grad_norm": 2.6046156883239746, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6004, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09811937857726902, | |
| "grad_norm": 3.652228832244873, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4478, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09811937857726902, | |
| "eval_loss": 1.376704216003418, | |
| "eval_runtime": 12.8541, | |
| "eval_samples_per_second": 10.036, | |
| "eval_steps_per_second": 5.057, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11447260834014718, | |
| "grad_norm": 3.175065040588379, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5178, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13082583810302534, | |
| "grad_norm": 2.8207459449768066, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3346, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13082583810302534, | |
| "eval_loss": 1.3294119834899902, | |
| "eval_runtime": 13.0651, | |
| "eval_samples_per_second": 9.874, | |
| "eval_steps_per_second": 4.975, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1471790678659035, | |
| "grad_norm": 2.846841812133789, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3073, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1635322976287817, | |
| "grad_norm": 2.0426764488220215, | |
| "learning_rate": 0.0, | |
| "loss": 1.2579, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1635322976287817, | |
| "eval_loss": 1.3147763013839722, | |
| "eval_runtime": 12.9288, | |
| "eval_samples_per_second": 9.978, | |
| "eval_steps_per_second": 5.028, | |
| "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": 1.02619680866304e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |