| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013927576601671309, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00046425255338904364, | |
| "eval_loss": 2.4134891033172607, | |
| "eval_runtime": 12.1544, | |
| "eval_samples_per_second": 74.623, | |
| "eval_steps_per_second": 37.353, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001392757660167131, | |
| "grad_norm": 34.927894592285156, | |
| "learning_rate": 4e-05, | |
| "loss": 10.2426, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002321262766945218, | |
| "eval_loss": 2.4031264781951904, | |
| "eval_runtime": 11.736, | |
| "eval_samples_per_second": 77.284, | |
| "eval_steps_per_second": 38.684, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002785515320334262, | |
| "grad_norm": 37.7618293762207, | |
| "learning_rate": 8e-05, | |
| "loss": 10.4254, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004178272980501393, | |
| "grad_norm": 42.016754150390625, | |
| "learning_rate": 0.00012, | |
| "loss": 9.1572, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004642525533890436, | |
| "eval_loss": 2.306687355041504, | |
| "eval_runtime": 11.7364, | |
| "eval_samples_per_second": 77.281, | |
| "eval_steps_per_second": 38.683, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005571030640668524, | |
| "grad_norm": 35.91981887817383, | |
| "learning_rate": 0.00016, | |
| "loss": 9.3324, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006963788300835654, | |
| "grad_norm": 32.527870178222656, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0118, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006963788300835654, | |
| "eval_loss": 2.230313539505005, | |
| "eval_runtime": 11.6879, | |
| "eval_samples_per_second": 77.602, | |
| "eval_steps_per_second": 38.844, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008356545961002786, | |
| "grad_norm": 35.8166618347168, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 8.8082, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009285051067780872, | |
| "eval_loss": 2.1811230182647705, | |
| "eval_runtime": 11.73, | |
| "eval_samples_per_second": 77.323, | |
| "eval_steps_per_second": 38.704, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009749303621169917, | |
| "grad_norm": 36.95984649658203, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.5593, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011142061281337047, | |
| "grad_norm": 59.03194808959961, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 9.4143, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01160631383472609, | |
| "eval_loss": 2.1778345108032227, | |
| "eval_runtime": 11.6534, | |
| "eval_samples_per_second": 77.831, | |
| "eval_steps_per_second": 38.958, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012534818941504178, | |
| "grad_norm": 35.66450881958008, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 8.5712, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013927576601671309, | |
| "grad_norm": 46.05991744995117, | |
| "learning_rate": 0.0, | |
| "loss": 8.6996, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013927576601671309, | |
| "eval_loss": 2.1666736602783203, | |
| "eval_runtime": 11.7607, | |
| "eval_samples_per_second": 77.121, | |
| "eval_steps_per_second": 38.603, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 531009959362560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |