| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09350163627863488, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018700327255726976, | |
| "eval_loss": 8.971555709838867, | |
| "eval_runtime": 1.7009, | |
| "eval_samples_per_second": 132.868, | |
| "eval_steps_per_second": 66.434, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009350163627863487, | |
| "grad_norm": 4966.99365234375, | |
| "learning_rate": 5e-05, | |
| "loss": 36.5428, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018700327255726974, | |
| "grad_norm": 5415.12353515625, | |
| "learning_rate": 0.0001, | |
| "loss": 36.8309, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018700327255726974, | |
| "eval_loss": 8.972297668457031, | |
| "eval_runtime": 1.3627, | |
| "eval_samples_per_second": 165.841, | |
| "eval_steps_per_second": 82.921, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028050490883590462, | |
| "grad_norm": 3624.78515625, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 35.9283, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03740065451145395, | |
| "grad_norm": 7291.77685546875, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 34.8422, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03740065451145395, | |
| "eval_loss": 8.811232566833496, | |
| "eval_runtime": 1.4336, | |
| "eval_samples_per_second": 157.648, | |
| "eval_steps_per_second": 78.824, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04675081813931744, | |
| "grad_norm": 6338.93017578125, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 35.2722, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.056100981767180924, | |
| "grad_norm": 6253.20263671875, | |
| "learning_rate": 5e-05, | |
| "loss": 34.6401, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.056100981767180924, | |
| "eval_loss": 8.723944664001465, | |
| "eval_runtime": 1.4416, | |
| "eval_samples_per_second": 156.771, | |
| "eval_steps_per_second": 78.386, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06545114539504442, | |
| "grad_norm": 8205.7646484375, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 34.8756, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0748013090229079, | |
| "grad_norm": 8530.24609375, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 35.5796, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0748013090229079, | |
| "eval_loss": 8.706113815307617, | |
| "eval_runtime": 1.4211, | |
| "eval_samples_per_second": 159.031, | |
| "eval_steps_per_second": 79.516, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08415147265077139, | |
| "grad_norm": 5396.7373046875, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 34.1608, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09350163627863488, | |
| "grad_norm": 49986.07421875, | |
| "learning_rate": 0.0, | |
| "loss": 37.1808, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09350163627863488, | |
| "eval_loss": 8.701628684997559, | |
| "eval_runtime": 1.4179, | |
| "eval_samples_per_second": 159.395, | |
| "eval_steps_per_second": 79.698, | |
| "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": 9495065395200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |