| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13183915622940012, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026367831245880024, | |
| "eval_loss": 9.952766418457031, | |
| "eval_runtime": 19.7234, | |
| "eval_samples_per_second": 8.112, | |
| "eval_steps_per_second": 4.056, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013183915622940013, | |
| "grad_norm": 7.932442665100098, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1812, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.026367831245880026, | |
| "grad_norm": 8.679454803466797, | |
| "learning_rate": 0.0001, | |
| "loss": 8.8656, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026367831245880026, | |
| "eval_loss": 7.980339050292969, | |
| "eval_runtime": 19.8797, | |
| "eval_samples_per_second": 8.048, | |
| "eval_steps_per_second": 4.024, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03955174686882004, | |
| "grad_norm": 11.740812301635742, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.7582, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05273566249176005, | |
| "grad_norm": 12.778048515319824, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9227, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05273566249176005, | |
| "eval_loss": 0.8312085866928101, | |
| "eval_runtime": 19.9694, | |
| "eval_samples_per_second": 8.012, | |
| "eval_steps_per_second": 4.006, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06591957811470006, | |
| "grad_norm": 3.4786934852600098, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4806, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07910349373764008, | |
| "grad_norm": 19.870271682739258, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3225, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07910349373764008, | |
| "eval_loss": 0.1717974841594696, | |
| "eval_runtime": 20.0121, | |
| "eval_samples_per_second": 7.995, | |
| "eval_steps_per_second": 3.998, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0922874093605801, | |
| "grad_norm": 4.610195636749268, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1221, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1054713249835201, | |
| "grad_norm": 8.429944038391113, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1087, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1054713249835201, | |
| "eval_loss": 0.09574756771326065, | |
| "eval_runtime": 20.1599, | |
| "eval_samples_per_second": 7.937, | |
| "eval_steps_per_second": 3.968, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11865524060646011, | |
| "grad_norm": 20.386011123657227, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13183915622940012, | |
| "grad_norm": 8.91682243347168, | |
| "learning_rate": 0.0, | |
| "loss": 0.2509, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13183915622940012, | |
| "eval_loss": 0.0755360797047615, | |
| "eval_runtime": 19.9856, | |
| "eval_samples_per_second": 8.006, | |
| "eval_steps_per_second": 4.003, | |
| "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": 1.61937503551488e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |