| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9826435246995995, | |
| "eval_steps": 3, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06408544726301736, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8393, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12817089452603472, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8182, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19225634178905207, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.806, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25634178905206945, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.7766, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3204272363150868, | |
| "grad_norm": 0.37968525290489197, | |
| "learning_rate": 0.001414213562373095, | |
| "loss": 1.8059, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.38451268357810414, | |
| "grad_norm": 2.0209860801696777, | |
| "learning_rate": 0.0011547005383792518, | |
| "loss": 1.6303, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 17.005041122436523, | |
| "learning_rate": 0.001, | |
| "loss": 2.7374, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5126835781041389, | |
| "grad_norm": 2.726215124130249, | |
| "learning_rate": 0.0007559289460184544, | |
| "loss": 2.3669, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5767690253671562, | |
| "grad_norm": 1.37969172000885, | |
| "learning_rate": 0.0006324555320336759, | |
| "loss": 1.635, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6408544726301736, | |
| "grad_norm": 0.5906515121459961, | |
| "learning_rate": 0.0005547001962252292, | |
| "loss": 1.3273, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7049399198931909, | |
| "grad_norm": 0.47537553310394287, | |
| "learning_rate": 0.0005, | |
| "loss": 1.2015, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7690253671562083, | |
| "grad_norm": 0.4244967997074127, | |
| "learning_rate": 0.0004588314677411235, | |
| "loss": 1.12, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8331108144192256, | |
| "grad_norm": 0.36951035261154175, | |
| "learning_rate": 0.00042640143271122083, | |
| "loss": 1.0757, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 0.4604327082633972, | |
| "learning_rate": 0.0004, | |
| "loss": 1.0035, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9612817089452603, | |
| "grad_norm": 0.41759026050567627, | |
| "learning_rate": 0.0003779644730092272, | |
| "loss": 0.9594, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9826435246995995, | |
| "step": 46, | |
| "total_flos": 4.671973340489974e+17, | |
| "train_loss": 1.5931461246117302, | |
| "train_runtime": 493.2732, | |
| "train_samples_per_second": 12.139, | |
| "train_steps_per_second": 0.093 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 46, | |
| "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": 4.671973340489974e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |