| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02583144979011947, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005166289958023894, | |
| "eval_loss": 10.335664749145508, | |
| "eval_runtime": 18.7204, | |
| "eval_samples_per_second": 696.565, | |
| "eval_steps_per_second": 87.071, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005166289958023894, | |
| "grad_norm": 4.865599632263184, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 165.3473, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005166289958023894, | |
| "eval_loss": 10.329593658447266, | |
| "eval_runtime": 18.6761, | |
| "eval_samples_per_second": 698.217, | |
| "eval_steps_per_second": 87.277, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010332579916047788, | |
| "grad_norm": 5.26408576965332, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 165.2227, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010332579916047788, | |
| "eval_loss": 10.322941780090332, | |
| "eval_runtime": 18.8099, | |
| "eval_samples_per_second": 693.251, | |
| "eval_steps_per_second": 86.656, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015498869874071682, | |
| "grad_norm": 5.665943145751953, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 165.1048, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015498869874071682, | |
| "eval_loss": 10.318285942077637, | |
| "eval_runtime": 18.927, | |
| "eval_samples_per_second": 688.962, | |
| "eval_steps_per_second": 86.12, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020665159832095575, | |
| "grad_norm": 5.858962059020996, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 165.0856, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020665159832095575, | |
| "eval_loss": 10.315924644470215, | |
| "eval_runtime": 18.8868, | |
| "eval_samples_per_second": 690.43, | |
| "eval_steps_per_second": 86.304, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02583144979011947, | |
| "grad_norm": 5.817805290222168, | |
| "learning_rate": 0.0, | |
| "loss": 165.0616, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02583144979011947, | |
| "eval_loss": 10.315557479858398, | |
| "eval_runtime": 18.7652, | |
| "eval_samples_per_second": 694.902, | |
| "eval_steps_per_second": 86.863, | |
| "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": 20531852083200.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |