| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0023054223533751383, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.610844706750277e-05, | |
| "eval_loss": 7.478056907653809, | |
| "eval_runtime": 646.3745, | |
| "eval_samples_per_second": 14.128, | |
| "eval_steps_per_second": 7.064, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023054223533751383, | |
| "grad_norm": 235.5802001953125, | |
| "learning_rate": 5e-05, | |
| "loss": 30.1518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00046108447067502766, | |
| "grad_norm": 107.33450317382812, | |
| "learning_rate": 0.0001, | |
| "loss": 8.7946, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00046108447067502766, | |
| "eval_loss": 0.8460701107978821, | |
| "eval_runtime": 649.6744, | |
| "eval_samples_per_second": 14.056, | |
| "eval_steps_per_second": 7.028, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006916267060125415, | |
| "grad_norm": 9.170708656311035, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8558, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009221689413500553, | |
| "grad_norm": 0.2867533564567566, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1771, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009221689413500553, | |
| "eval_loss": 0.21382905542850494, | |
| "eval_runtime": 647.7178, | |
| "eval_samples_per_second": 14.099, | |
| "eval_steps_per_second": 7.049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011527111766875691, | |
| "grad_norm": 0.2146027535200119, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0012, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001383253412025083, | |
| "grad_norm": 0.003302945988252759, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7641, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001383253412025083, | |
| "eval_loss": 0.20368286967277527, | |
| "eval_runtime": 647.9929, | |
| "eval_samples_per_second": 14.093, | |
| "eval_steps_per_second": 7.046, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016137956473625968, | |
| "grad_norm": 0.02023138664662838, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5793, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0018443378827001106, | |
| "grad_norm": 0.017362723127007484, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018443378827001106, | |
| "eval_loss": 0.13715976476669312, | |
| "eval_runtime": 643.8616, | |
| "eval_samples_per_second": 14.183, | |
| "eval_steps_per_second": 7.092, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020748801180376247, | |
| "grad_norm": 0.004537283908575773, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7151, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0023054223533751383, | |
| "grad_norm": 0.007345356047153473, | |
| "learning_rate": 0.0, | |
| "loss": 0.7912, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0023054223533751383, | |
| "eval_loss": 0.12374379485845566, | |
| "eval_runtime": 646.8445, | |
| "eval_samples_per_second": 14.118, | |
| "eval_steps_per_second": 7.059, | |
| "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": 9464427715756032.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |