| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003770810158562567, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.541620317125135e-05, | |
| "eval_loss": 1.8513652086257935, | |
| "eval_runtime": 1622.5497, | |
| "eval_samples_per_second": 3.441, | |
| "eval_steps_per_second": 1.721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003770810158562567, | |
| "grad_norm": 3.8468408584594727, | |
| "learning_rate": 5e-05, | |
| "loss": 7.7614, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007541620317125134, | |
| "grad_norm": 5.220760822296143, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9834, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007541620317125134, | |
| "eval_loss": 1.3195631504058838, | |
| "eval_runtime": 1645.9689, | |
| "eval_samples_per_second": 3.393, | |
| "eval_steps_per_second": 1.696, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011312430475687702, | |
| "grad_norm": 3.5808358192443848, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.2099, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015083240634250269, | |
| "grad_norm": 4.969306945800781, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2629, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015083240634250269, | |
| "eval_loss": 0.7506620287895203, | |
| "eval_runtime": 1643.7062, | |
| "eval_samples_per_second": 3.397, | |
| "eval_steps_per_second": 1.699, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018854050792812835, | |
| "grad_norm": 3.7685539722442627, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.8307, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022624860951375404, | |
| "grad_norm": 3.4094903469085693, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6407, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022624860951375404, | |
| "eval_loss": 0.617461621761322, | |
| "eval_runtime": 1646.6956, | |
| "eval_samples_per_second": 3.391, | |
| "eval_steps_per_second": 1.696, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002639567110993797, | |
| "grad_norm": 3.3993616104125977, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4199, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0030166481268500537, | |
| "grad_norm": 2.954137086868286, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4024, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0030166481268500537, | |
| "eval_loss": 0.5890699625015259, | |
| "eval_runtime": 1646.5246, | |
| "eval_samples_per_second": 3.391, | |
| "eval_steps_per_second": 1.696, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0033937291427063106, | |
| "grad_norm": 3.225785970687866, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.182, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003770810158562567, | |
| "grad_norm": 3.351832628250122, | |
| "learning_rate": 0.0, | |
| "loss": 2.2408, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003770810158562567, | |
| "eval_loss": 0.5843084454536438, | |
| "eval_runtime": 1647.0383, | |
| "eval_samples_per_second": 3.39, | |
| "eval_steps_per_second": 1.695, | |
| "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": 2.845673344991232e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |