| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05676979846721544, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011353959693443088, | |
| "eval_loss": 1.4296112060546875, | |
| "eval_runtime": 21.5487, | |
| "eval_samples_per_second": 17.217, | |
| "eval_steps_per_second": 8.632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005676979846721544, | |
| "grad_norm": 0.3469405174255371, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3687, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011353959693443088, | |
| "grad_norm": 0.46661630272865295, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4407, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011353959693443088, | |
| "eval_loss": 1.3932585716247559, | |
| "eval_runtime": 19.9348, | |
| "eval_samples_per_second": 18.611, | |
| "eval_steps_per_second": 9.33, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017030939540164634, | |
| "grad_norm": 0.5335865616798401, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4751, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022707919386886176, | |
| "grad_norm": 0.5056927800178528, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1882, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022707919386886176, | |
| "eval_loss": 1.2817808389663696, | |
| "eval_runtime": 19.9967, | |
| "eval_samples_per_second": 18.553, | |
| "eval_steps_per_second": 9.302, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02838489923360772, | |
| "grad_norm": 0.3559781610965729, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2401, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03406187908032927, | |
| "grad_norm": 0.4039708971977234, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2597, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03406187908032927, | |
| "eval_loss": 1.2096537351608276, | |
| "eval_runtime": 20.0923, | |
| "eval_samples_per_second": 18.465, | |
| "eval_steps_per_second": 9.257, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.039738858927050806, | |
| "grad_norm": 0.41507863998413086, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2934, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04541583877377235, | |
| "grad_norm": 0.4097580313682556, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2191, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04541583877377235, | |
| "eval_loss": 1.1771323680877686, | |
| "eval_runtime": 20.5716, | |
| "eval_samples_per_second": 18.035, | |
| "eval_steps_per_second": 9.042, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0510928186204939, | |
| "grad_norm": 0.48491784930229187, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1729, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05676979846721544, | |
| "grad_norm": 0.5116763710975647, | |
| "learning_rate": 0.0, | |
| "loss": 1.1212, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05676979846721544, | |
| "eval_loss": 1.1734027862548828, | |
| "eval_runtime": 20.2144, | |
| "eval_samples_per_second": 18.353, | |
| "eval_steps_per_second": 9.201, | |
| "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": 3993658655244288.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |