| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00421896424427803, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.437928488556059e-05, | |
| "eval_loss": 11.131023406982422, | |
| "eval_runtime": 10.495, | |
| "eval_samples_per_second": 475.466, | |
| "eval_steps_per_second": 237.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "grad_norm": 4.046123504638672, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 44.4615, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010969307035122878, | |
| "eval_loss": 11.047707557678223, | |
| "eval_runtime": 10.0814, | |
| "eval_samples_per_second": 494.97, | |
| "eval_steps_per_second": 247.485, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "grad_norm": 3.9292571544647217, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.1562, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0021938614070245756, | |
| "eval_loss": 10.956828117370605, | |
| "eval_runtime": 10.1219, | |
| "eval_samples_per_second": 492.99, | |
| "eval_steps_per_second": 246.495, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0025313785465668178, | |
| "grad_norm": 3.7027828693389893, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 43.8833, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0032907921105368634, | |
| "eval_loss": 10.918169021606445, | |
| "eval_runtime": 10.1682, | |
| "eval_samples_per_second": 490.744, | |
| "eval_steps_per_second": 245.372, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0033751713954224237, | |
| "grad_norm": 3.8778882026672363, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 43.7333, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00421896424427803, | |
| "grad_norm": 3.8136308193206787, | |
| "learning_rate": 0.0, | |
| "loss": 43.6516, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 37355520000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |