| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.062315002336812586, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "grad_norm": 34.01936721801758, | |
| "learning_rate": 5e-05, | |
| "loss": 51.3449, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "eval_loss": 2.1383278369903564, | |
| "eval_runtime": 3.5335, | |
| "eval_samples_per_second": 14.15, | |
| "eval_steps_per_second": 3.679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004985200186945007, | |
| "grad_norm": 34.66087341308594, | |
| "learning_rate": 0.0001, | |
| "loss": 53.1527, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00747780028041751, | |
| "grad_norm": 30.127349853515625, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 52.1352, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009970400373890013, | |
| "grad_norm": 22.915531158447266, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 49.9646, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012463000467362517, | |
| "grad_norm": 52.97492980957031, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 52.959, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01495560056083502, | |
| "grad_norm": 49.64532470703125, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 53.6426, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017448200654307525, | |
| "grad_norm": 25.895368576049805, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 52.3593, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019940800747780027, | |
| "grad_norm": 20.97550392150879, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 51.3943, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022433400841252532, | |
| "grad_norm": 14.574114799499512, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 53.4097, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024926000934725034, | |
| "grad_norm": 21.26239776611328, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 54.8947, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02741860102819754, | |
| "grad_norm": 24.055912017822266, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 54.7964, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02991120112167004, | |
| "grad_norm": 30.55950164794922, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 57.7224, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032403801215142546, | |
| "grad_norm": 26.02332878112793, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 56.8336, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03489640130861505, | |
| "grad_norm": 23.84014892578125, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 45.4639, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037389001402087556, | |
| "grad_norm": 20.399507522583008, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 45.2857, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.039881601495560054, | |
| "grad_norm": 13.766602516174316, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 45.9527, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04237420158903256, | |
| "grad_norm": 10.404088020324707, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 47.2076, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.044866801682505064, | |
| "grad_norm": 9.640239715576172, | |
| "learning_rate": 7.75e-05, | |
| "loss": 46.6353, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04735940177597757, | |
| "grad_norm": 10.350581169128418, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 47.2987, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04985200186945007, | |
| "grad_norm": 11.253185272216797, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 48.2336, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05234460196292257, | |
| "grad_norm": 11.232816696166992, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 47.7288, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05483720205639508, | |
| "grad_norm": 12.71604061126709, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 50.7921, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05732980214986758, | |
| "grad_norm": 15.633907318115234, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 50.814, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05982240224334008, | |
| "grad_norm": 22.674806594848633, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 56.9851, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "grad_norm": 44.97622299194336, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 60.9695, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "eval_loss": 1.6849799156188965, | |
| "eval_runtime": 3.5862, | |
| "eval_samples_per_second": 13.942, | |
| "eval_steps_per_second": 3.625, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7840385819816755e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |