| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007074437228518472, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4148874457036944e-05, | |
| "eval_loss": 5.3834967613220215, | |
| "eval_runtime": 1889.4258, | |
| "eval_samples_per_second": 15.75, | |
| "eval_steps_per_second": 7.875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.074437228518471e-05, | |
| "grad_norm": 26.077726364135742, | |
| "learning_rate": 5e-05, | |
| "loss": 20.0704, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00014148874457036941, | |
| "grad_norm": 26.809843063354492, | |
| "learning_rate": 0.0001, | |
| "loss": 19.5946, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00014148874457036941, | |
| "eval_loss": 3.9861538410186768, | |
| "eval_runtime": 1895.9004, | |
| "eval_samples_per_second": 15.697, | |
| "eval_steps_per_second": 7.849, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00021223311685555414, | |
| "grad_norm": 24.79098129272461, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 14.4881, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00028297748914073883, | |
| "grad_norm": 25.828630447387695, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 14.0964, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00028297748914073883, | |
| "eval_loss": 3.5989348888397217, | |
| "eval_runtime": 1891.5108, | |
| "eval_samples_per_second": 15.733, | |
| "eval_steps_per_second": 7.867, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003537218614259236, | |
| "grad_norm": 23.07585334777832, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 12.9708, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00042446623371110827, | |
| "grad_norm": 25.14630699157715, | |
| "learning_rate": 5e-05, | |
| "loss": 14.9684, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00042446623371110827, | |
| "eval_loss": 3.5218193531036377, | |
| "eval_runtime": 1883.6604, | |
| "eval_samples_per_second": 15.798, | |
| "eval_steps_per_second": 7.9, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000495210605996293, | |
| "grad_norm": 24.184917449951172, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 13.4074, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0005659549782814777, | |
| "grad_norm": 21.100221633911133, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 14.4036, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0005659549782814777, | |
| "eval_loss": 3.4930121898651123, | |
| "eval_runtime": 1886.4935, | |
| "eval_samples_per_second": 15.775, | |
| "eval_steps_per_second": 7.888, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0006366993505666624, | |
| "grad_norm": 22.75106430053711, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 13.5211, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0007074437228518472, | |
| "grad_norm": 27.424501419067383, | |
| "learning_rate": 0.0, | |
| "loss": 14.3889, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0007074437228518472, | |
| "eval_loss": 3.4873178005218506, | |
| "eval_runtime": 1885.3182, | |
| "eval_samples_per_second": 15.785, | |
| "eval_steps_per_second": 7.893, | |
| "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": 8763348929740800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |