| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012759170653907496, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 1.6459169387817383, | |
| "eval_runtime": 13.4926, | |
| "eval_samples_per_second": 73.374, | |
| "eval_steps_per_second": 36.687, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": 26.153257369995117, | |
| "learning_rate": 3e-05, | |
| "loss": 6.5814, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "eval_loss": 1.6405055522918701, | |
| "eval_runtime": 13.5499, | |
| "eval_samples_per_second": 73.063, | |
| "eval_steps_per_second": 36.532, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": 25.290189743041992, | |
| "learning_rate": 6e-05, | |
| "loss": 6.8425, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": 20.159481048583984, | |
| "learning_rate": 9e-05, | |
| "loss": 6.7944, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "eval_loss": 1.6054966449737549, | |
| "eval_runtime": 13.6451, | |
| "eval_samples_per_second": 72.554, | |
| "eval_steps_per_second": 36.277, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005103668261562998, | |
| "grad_norm": 39.573326110839844, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 6.302, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 26.355426788330078, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.5024, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "eval_loss": 1.5709365606307983, | |
| "eval_runtime": 13.5669, | |
| "eval_samples_per_second": 72.972, | |
| "eval_steps_per_second": 36.486, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007655502392344498, | |
| "grad_norm": 27.330434799194336, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 6.3002, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "eval_loss": 1.5609004497528076, | |
| "eval_runtime": 13.5405, | |
| "eval_samples_per_second": 73.114, | |
| "eval_steps_per_second": 36.557, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008931419457735247, | |
| "grad_norm": 23.369600296020508, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 6.3961, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "grad_norm": 22.581483840942383, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 6.1837, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "eval_loss": 1.554789662361145, | |
| "eval_runtime": 13.7952, | |
| "eval_samples_per_second": 71.764, | |
| "eval_steps_per_second": 35.882, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011483253588516746, | |
| "grad_norm": 30.673725128173828, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 6.2545, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "grad_norm": 30.781036376953125, | |
| "learning_rate": 0.0, | |
| "loss": 6.1231, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "eval_loss": 1.5538281202316284, | |
| "eval_runtime": 13.5903, | |
| "eval_samples_per_second": 72.846, | |
| "eval_steps_per_second": 36.423, | |
| "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": 535435042357248.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |