| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02126528442317916, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 1.078394889831543, | |
| "eval_runtime": 52.5101, | |
| "eval_samples_per_second": 18.854, | |
| "eval_steps_per_second": 9.427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "grad_norm": 1.10820472240448, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3677, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "grad_norm": 1.2280428409576416, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "eval_loss": 1.0476360321044922, | |
| "eval_runtime": 54.1167, | |
| "eval_samples_per_second": 18.294, | |
| "eval_steps_per_second": 9.147, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 1.6046372652053833, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.0792, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "grad_norm": 1.2883493900299072, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.6653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "eval_loss": 0.8761806488037109, | |
| "eval_runtime": 54.8267, | |
| "eval_samples_per_second": 18.057, | |
| "eval_steps_per_second": 9.028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "grad_norm": 1.3254737854003906, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.4676, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "grad_norm": 1.2836309671401978, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2089, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "eval_loss": 0.8105342388153076, | |
| "eval_runtime": 54.9224, | |
| "eval_samples_per_second": 18.025, | |
| "eval_steps_per_second": 9.013, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014885699096225412, | |
| "grad_norm": 1.3615540266036987, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.4176, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01701222753854333, | |
| "grad_norm": 1.3800708055496216, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.1392, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01701222753854333, | |
| "eval_loss": 0.788581371307373, | |
| "eval_runtime": 54.9664, | |
| "eval_samples_per_second": 18.011, | |
| "eval_steps_per_second": 9.006, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019138755980861243, | |
| "grad_norm": 1.3181637525558472, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.0037, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02126528442317916, | |
| "grad_norm": 1.3086178302764893, | |
| "learning_rate": 0.0, | |
| "loss": 3.0455, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02126528442317916, | |
| "eval_loss": 0.7847435474395752, | |
| "eval_runtime": 54.9263, | |
| "eval_samples_per_second": 18.024, | |
| "eval_steps_per_second": 9.012, | |
| "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": 4589766888652800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |