| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02191825859435468, | |
| "eval_steps": 40, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010959129297177339, | |
| "eval_loss": 2.110013484954834, | |
| "eval_runtime": 1004.5967, | |
| "eval_samples_per_second": 15.299, | |
| "eval_steps_per_second": 7.65, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0043836517188709356, | |
| "grad_norm": 14.075608253479004, | |
| "learning_rate": 1e-05, | |
| "loss": 33.3493, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0043836517188709356, | |
| "eval_loss": 2.0665688514709473, | |
| "eval_runtime": 1003.137, | |
| "eval_samples_per_second": 15.321, | |
| "eval_steps_per_second": 7.661, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008767303437741871, | |
| "grad_norm": 13.712140083312988, | |
| "learning_rate": 2e-05, | |
| "loss": 30.9777, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.008767303437741871, | |
| "eval_loss": 1.836449384689331, | |
| "eval_runtime": 1003.1953, | |
| "eval_samples_per_second": 15.32, | |
| "eval_steps_per_second": 7.661, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013150955156612807, | |
| "grad_norm": 16.177526473999023, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 28.7871, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.013150955156612807, | |
| "eval_loss": 1.7560031414031982, | |
| "eval_runtime": 1003.96, | |
| "eval_samples_per_second": 15.308, | |
| "eval_steps_per_second": 7.655, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.017534606875483742, | |
| "grad_norm": 16.116289138793945, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 28.0053, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.017534606875483742, | |
| "eval_loss": 1.7280950546264648, | |
| "eval_runtime": 1003.515, | |
| "eval_samples_per_second": 15.315, | |
| "eval_steps_per_second": 7.658, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.02191825859435468, | |
| "grad_norm": 17.095829010009766, | |
| "learning_rate": 0.0, | |
| "loss": 27.6745, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02191825859435468, | |
| "eval_loss": 1.7235428094863892, | |
| "eval_runtime": 1005.4389, | |
| "eval_samples_per_second": 15.286, | |
| "eval_steps_per_second": 7.643, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.302986508730368e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |