| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007532247434328217, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.532247434328218e-05, | |
| "grad_norm": 0.07794299721717834, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3751, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.532247434328218e-05, | |
| "eval_loss": 10.367362022399902, | |
| "eval_runtime": 14.1833, | |
| "eval_samples_per_second": 394.125, | |
| "eval_steps_per_second": 197.063, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015064494868656435, | |
| "grad_norm": 0.07240435481071472, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3733, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00022596742302984652, | |
| "grad_norm": 0.08178043365478516, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3623, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00022596742302984652, | |
| "eval_loss": 10.367290496826172, | |
| "eval_runtime": 13.9963, | |
| "eval_samples_per_second": 399.392, | |
| "eval_steps_per_second": 199.696, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003012898973731287, | |
| "grad_norm": 0.07609041035175323, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3737, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00037661237171641087, | |
| "grad_norm": 0.07180183380842209, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3677, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00045193484605969304, | |
| "grad_norm": 0.0721636489033699, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3721, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00045193484605969304, | |
| "eval_loss": 10.366961479187012, | |
| "eval_runtime": 14.5198, | |
| "eval_samples_per_second": 384.992, | |
| "eval_steps_per_second": 192.496, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005272573204029753, | |
| "grad_norm": 0.0817117989063263, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3669, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006025797947462574, | |
| "grad_norm": 0.07650120556354523, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3662, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006779022690895396, | |
| "grad_norm": 0.07249870896339417, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3654, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006779022690895396, | |
| "eval_loss": 10.366414070129395, | |
| "eval_runtime": 14.3772, | |
| "eval_samples_per_second": 388.811, | |
| "eval_steps_per_second": 194.406, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007532247434328217, | |
| "grad_norm": 0.09004424512386322, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3633, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 129309081600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |