| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8514851485148514, | |
| "eval_steps": 500, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": 25.20428267668325, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": 36.917025665063875, | |
| "learning_rate": 1.995184726672197e-05, | |
| "loss": 1.4728, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 8.149660114746355, | |
| "learning_rate": 1.8314696123025456e-05, | |
| "loss": 1.4332, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "eval_loss": 1.2468267679214478, | |
| "eval_runtime": 5.7996, | |
| "eval_samples_per_second": 8.966, | |
| "eval_steps_per_second": 0.345, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.188118811881188, | |
| "grad_norm": 7.683983380513048, | |
| "learning_rate": 1.4713967368259981e-05, | |
| "loss": 1.2317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5841584158415842, | |
| "grad_norm": 2.458006119450546, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9801980198019802, | |
| "grad_norm": 1.4615528467429235, | |
| "learning_rate": 5.286032631740023e-06, | |
| "loss": 1.0421, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9801980198019802, | |
| "eval_loss": 1.065010666847229, | |
| "eval_runtime": 5.6499, | |
| "eval_samples_per_second": 9.204, | |
| "eval_steps_per_second": 0.354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.376237623762376, | |
| "grad_norm": 1.251106845075615, | |
| "learning_rate": 1.6853038769745466e-06, | |
| "loss": 0.9444, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.772277227722772, | |
| "grad_norm": 0.8336224848562745, | |
| "learning_rate": 4.815273327803183e-08, | |
| "loss": 0.9193, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.8514851485148514, | |
| "eval_loss": 1.0546845197677612, | |
| "eval_runtime": 5.7189, | |
| "eval_samples_per_second": 9.093, | |
| "eval_steps_per_second": 0.35, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.8514851485148514, | |
| "step": 36, | |
| "total_flos": 120497991843840.0, | |
| "train_loss": 1.160024169418547, | |
| "train_runtime": 9224.6118, | |
| "train_samples_per_second": 4.198, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 120497991843840.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |