| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02040816326530612, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00040816326530612246, | |
| "eval_loss": 1.038622498512268, | |
| "eval_runtime": 100.2598, | |
| "eval_samples_per_second": 10.293, | |
| "eval_steps_per_second": 5.147, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020408163265306124, | |
| "grad_norm": 1.570367455482483, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0227, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004081632653061225, | |
| "grad_norm": 1.5186132192611694, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7081, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004081632653061225, | |
| "eval_loss": 0.9728806614875793, | |
| "eval_runtime": 100.715, | |
| "eval_samples_per_second": 10.247, | |
| "eval_steps_per_second": 5.123, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006122448979591836, | |
| "grad_norm": 1.417625069618225, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.859, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00816326530612245, | |
| "grad_norm": 2.1316819190979004, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.3143, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00816326530612245, | |
| "eval_loss": 0.8414375185966492, | |
| "eval_runtime": 100.4603, | |
| "eval_samples_per_second": 10.273, | |
| "eval_steps_per_second": 5.136, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01020408163265306, | |
| "grad_norm": 1.9280800819396973, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.1387, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012244897959183673, | |
| "grad_norm": 2.512467861175537, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2341, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012244897959183673, | |
| "eval_loss": 0.763218879699707, | |
| "eval_runtime": 100.7949, | |
| "eval_samples_per_second": 10.239, | |
| "eval_steps_per_second": 5.119, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014285714285714285, | |
| "grad_norm": 2.0444631576538086, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.1349, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0163265306122449, | |
| "grad_norm": 2.757094621658325, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.8461, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0163265306122449, | |
| "eval_loss": 0.7422359585762024, | |
| "eval_runtime": 100.6434, | |
| "eval_samples_per_second": 10.254, | |
| "eval_steps_per_second": 5.127, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018367346938775512, | |
| "grad_norm": 2.56603741645813, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8422, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 2.2543857097625732, | |
| "learning_rate": 0.0, | |
| "loss": 2.915, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "eval_loss": 0.7383472323417664, | |
| "eval_runtime": 100.892, | |
| "eval_samples_per_second": 10.229, | |
| "eval_steps_per_second": 5.114, | |
| "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": 1.74734328201216e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |