| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011699669484337067, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011699669484337067, | |
| "grad_norm": 3.81866717338562, | |
| "learning_rate": 2e-05, | |
| "loss": 5.5379, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011699669484337067, | |
| "eval_loss": 5.82464075088501, | |
| "eval_runtime": 180.9737, | |
| "eval_samples_per_second": 19.887, | |
| "eval_steps_per_second": 9.946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023399338968674134, | |
| "grad_norm": 4.811659336090088, | |
| "learning_rate": 4e-05, | |
| "loss": 6.0858, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00035099008453011205, | |
| "grad_norm": 4.268662929534912, | |
| "learning_rate": 6e-05, | |
| "loss": 5.5911, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00035099008453011205, | |
| "eval_loss": 5.70864725112915, | |
| "eval_runtime": 181.188, | |
| "eval_samples_per_second": 19.863, | |
| "eval_steps_per_second": 9.934, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004679867793734827, | |
| "grad_norm": 4.1390700340271, | |
| "learning_rate": 8e-05, | |
| "loss": 5.0745, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005849834742168534, | |
| "grad_norm": 3.9610862731933594, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5696, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007019801690602241, | |
| "grad_norm": 3.7894489765167236, | |
| "learning_rate": 0.00012, | |
| "loss": 4.6503, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007019801690602241, | |
| "eval_loss": 4.3671722412109375, | |
| "eval_runtime": 181.1781, | |
| "eval_samples_per_second": 19.864, | |
| "eval_steps_per_second": 9.935, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008189768639035947, | |
| "grad_norm": 3.852618455886841, | |
| "learning_rate": 0.00014, | |
| "loss": 3.712, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009359735587469654, | |
| "grad_norm": 4.385794639587402, | |
| "learning_rate": 0.00016, | |
| "loss": 3.3531, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001052970253590336, | |
| "grad_norm": 4.388697624206543, | |
| "learning_rate": 0.00018, | |
| "loss": 3.169, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001052970253590336, | |
| "eval_loss": 2.974564790725708, | |
| "eval_runtime": 181.2761, | |
| "eval_samples_per_second": 19.854, | |
| "eval_steps_per_second": 9.93, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011699669484337067, | |
| "grad_norm": 4.671903133392334, | |
| "learning_rate": 0.0002, | |
| "loss": 2.8287, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "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": 2103703457759232.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |