| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012944774356402, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.472387178201e-05, | |
| "eval_loss": 1.764864444732666, | |
| "eval_runtime": 195.6761, | |
| "eval_samples_per_second": 33.249, | |
| "eval_steps_per_second": 16.624, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006472387178201, | |
| "grad_norm": 0.4425320625305176, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4183, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012944774356402, | |
| "grad_norm": 0.7192811369895935, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4582, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019417161534603, | |
| "grad_norm": 0.7565455436706543, | |
| "learning_rate": 0.0002, | |
| "loss": 1.362, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025889548712804, | |
| "grad_norm": 0.8094374537467957, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2267, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032361935891005, | |
| "grad_norm": 1.1294043064117432, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1154, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0032361935891005, | |
| "eval_loss": 1.1239283084869385, | |
| "eval_runtime": 194.799, | |
| "eval_samples_per_second": 33.399, | |
| "eval_steps_per_second": 16.699, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0038834323069206, | |
| "grad_norm": 0.9267818927764893, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1523, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0045306710247407, | |
| "grad_norm": 1.0530893802642822, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0864, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0051779097425608, | |
| "grad_norm": 0.9379938244819641, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0639, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0058251484603809, | |
| "grad_norm": 0.6152510643005371, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9727, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006472387178201, | |
| "grad_norm": 1.0862324237823486, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1407, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006472387178201, | |
| "eval_loss": 1.0274646282196045, | |
| "eval_runtime": 194.761, | |
| "eval_samples_per_second": 33.405, | |
| "eval_steps_per_second": 16.703, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0071196258960211, | |
| "grad_norm": 0.9663441181182861, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0741, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0077668646138412, | |
| "grad_norm": 1.29120934009552, | |
| "learning_rate": 0.0002, | |
| "loss": 1.044, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0084141033316613, | |
| "grad_norm": 0.9238539338111877, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0563, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0090613420494814, | |
| "grad_norm": 1.1232694387435913, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0642, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0097085807673015, | |
| "grad_norm": 0.957047700881958, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0433, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0097085807673015, | |
| "eval_loss": 0.9908371567726135, | |
| "eval_runtime": 194.8244, | |
| "eval_samples_per_second": 33.394, | |
| "eval_steps_per_second": 16.697, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0103558194851216, | |
| "grad_norm": 0.8797596096992493, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1071, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0110030582029417, | |
| "grad_norm": 0.90439373254776, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0443, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0116502969207618, | |
| "grad_norm": 1.0083608627319336, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0347, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0122975356385819, | |
| "grad_norm": 0.8776618838310242, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9837, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.012944774356402, | |
| "grad_norm": 0.9423546195030212, | |
| "learning_rate": 0.0002, | |
| "loss": 1.048, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.012944774356402, | |
| "eval_loss": 0.9568792581558228, | |
| "eval_runtime": 195.0298, | |
| "eval_samples_per_second": 33.359, | |
| "eval_steps_per_second": 16.68, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.751024089209242e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |