| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010375865736297373, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010375865736297373, | |
| "grad_norm": 1.1433764696121216, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1367, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010375865736297373, | |
| "eval_loss": 2.0775890350341797, | |
| "eval_runtime": 82.1221, | |
| "eval_samples_per_second": 49.414, | |
| "eval_steps_per_second": 24.707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020751731472594745, | |
| "grad_norm": 1.1961828470230103, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0164, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00031127597208892115, | |
| "grad_norm": 1.2340922355651855, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1282, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00031127597208892115, | |
| "eval_loss": 2.074273109436035, | |
| "eval_runtime": 81.5877, | |
| "eval_samples_per_second": 49.738, | |
| "eval_steps_per_second": 24.869, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004150346294518949, | |
| "grad_norm": 1.0359632968902588, | |
| "learning_rate": 8e-05, | |
| "loss": 1.933, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005187932868148687, | |
| "grad_norm": 1.3015316724777222, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0539, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006225519441778423, | |
| "grad_norm": 1.0627121925354004, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1394, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006225519441778423, | |
| "eval_loss": 2.040466070175171, | |
| "eval_runtime": 81.4488, | |
| "eval_samples_per_second": 49.823, | |
| "eval_steps_per_second": 24.911, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000726310601540816, | |
| "grad_norm": 1.152351975440979, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9755, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0008300692589037898, | |
| "grad_norm": 1.0372527837753296, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7394, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0009338279162667636, | |
| "grad_norm": 1.0806152820587158, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8651, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009338279162667636, | |
| "eval_loss": 1.97881281375885, | |
| "eval_runtime": 81.6516, | |
| "eval_samples_per_second": 49.699, | |
| "eval_steps_per_second": 24.849, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010375865736297373, | |
| "grad_norm": 0.955893337726593, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7457, | |
| "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": 126879383420928.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |