| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0026217473946385265, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.2434947892770535e-05, | |
| "eval_loss": 12.45307445526123, | |
| "eval_runtime": 110.2136, | |
| "eval_samples_per_second": 72.859, | |
| "eval_steps_per_second": 36.429, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026217473946385267, | |
| "grad_norm": 0.002715166425332427, | |
| "learning_rate": 5e-05, | |
| "loss": 12.4518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005243494789277053, | |
| "grad_norm": 0.004838508553802967, | |
| "learning_rate": 0.0001, | |
| "loss": 12.4532, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005243494789277053, | |
| "eval_loss": 12.453064918518066, | |
| "eval_runtime": 110.4922, | |
| "eval_samples_per_second": 72.675, | |
| "eval_steps_per_second": 36.337, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000786524218391558, | |
| "grad_norm": 0.004974856972694397, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 12.4545, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010486989578554107, | |
| "grad_norm": 0.004730704706162214, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 12.456, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010486989578554107, | |
| "eval_loss": 12.453044891357422, | |
| "eval_runtime": 110.6233, | |
| "eval_samples_per_second": 72.589, | |
| "eval_steps_per_second": 36.294, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013108736973192633, | |
| "grad_norm": 0.005735255312174559, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 12.4515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001573048436783116, | |
| "grad_norm": 0.008840982802212238, | |
| "learning_rate": 5e-05, | |
| "loss": 12.4552, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001573048436783116, | |
| "eval_loss": 12.453033447265625, | |
| "eval_runtime": 110.6772, | |
| "eval_samples_per_second": 72.553, | |
| "eval_steps_per_second": 36.277, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0018352231762469686, | |
| "grad_norm": 0.007563808001577854, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 12.4549, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0020973979157108214, | |
| "grad_norm": 0.0029871268197894096, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 12.4555, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020973979157108214, | |
| "eval_loss": 12.453027725219727, | |
| "eval_runtime": 110.644, | |
| "eval_samples_per_second": 72.575, | |
| "eval_steps_per_second": 36.288, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002359572655174674, | |
| "grad_norm": 0.005952336825430393, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 12.4553, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0026217473946385265, | |
| "grad_norm": 0.0046081626787781715, | |
| "learning_rate": 0.0, | |
| "loss": 12.4562, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0026217473946385265, | |
| "eval_loss": 12.453025817871094, | |
| "eval_runtime": 110.6277, | |
| "eval_samples_per_second": 72.586, | |
| "eval_steps_per_second": 36.293, | |
| "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": 5421858816.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |