| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07357449417535254, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002452483139178418, | |
| "eval_loss": 2.891028881072998, | |
| "eval_runtime": 3.6982, | |
| "eval_samples_per_second": 46.509, | |
| "eval_steps_per_second": 23.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007357449417535254, | |
| "grad_norm": 5.310537338256836, | |
| "learning_rate": 3e-05, | |
| "loss": 12.174, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014714898835070508, | |
| "grad_norm": 4.475032329559326, | |
| "learning_rate": 6e-05, | |
| "loss": 12.1227, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019619865113427344, | |
| "eval_loss": 2.872472047805786, | |
| "eval_runtime": 2.6196, | |
| "eval_samples_per_second": 65.658, | |
| "eval_steps_per_second": 32.829, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022072348252605765, | |
| "grad_norm": 3.777573585510254, | |
| "learning_rate": 9e-05, | |
| "loss": 12.1654, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.029429797670141016, | |
| "grad_norm": 3.815861940383911, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 12.0159, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03678724708767627, | |
| "grad_norm": 3.5043060779571533, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.5958, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03923973022685469, | |
| "eval_loss": 2.8279972076416016, | |
| "eval_runtime": 2.6373, | |
| "eval_samples_per_second": 65.218, | |
| "eval_steps_per_second": 32.609, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04414469650521153, | |
| "grad_norm": 3.8419547080993652, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.7029, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05150214592274678, | |
| "grad_norm": 3.9225502014160156, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 11.6225, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05885959534028203, | |
| "grad_norm": 3.59427547454834, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 12.0697, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05885959534028203, | |
| "eval_loss": 2.8084943294525146, | |
| "eval_runtime": 2.614, | |
| "eval_samples_per_second": 65.8, | |
| "eval_steps_per_second": 32.9, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06621704475781728, | |
| "grad_norm": 3.1728599071502686, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 11.7113, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07357449417535254, | |
| "grad_norm": 3.4855759143829346, | |
| "learning_rate": 0.0, | |
| "loss": 11.3748, | |
| "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": 175678634852352.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |