| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0290627270525551, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009687575684185032, | |
| "eval_loss": 2.4858999252319336, | |
| "eval_runtime": 48.8752, | |
| "eval_samples_per_second": 8.9, | |
| "eval_steps_per_second": 4.46, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00290627270525551, | |
| "grad_norm": 19.631099700927734, | |
| "learning_rate": 6e-05, | |
| "loss": 11.0461, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00581254541051102, | |
| "grad_norm": 24.277101516723633, | |
| "learning_rate": 0.00012, | |
| "loss": 8.8259, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007750060547348026, | |
| "eval_loss": 0.7043958902359009, | |
| "eval_runtime": 49.6294, | |
| "eval_samples_per_second": 8.765, | |
| "eval_steps_per_second": 4.393, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00871881811576653, | |
| "grad_norm": 10.01905345916748, | |
| "learning_rate": 0.00018, | |
| "loss": 4.344, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01162509082102204, | |
| "grad_norm": 6.4644012451171875, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.5773, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01453136352627755, | |
| "grad_norm": 1.0154591798782349, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.2985, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015500121094696052, | |
| "eval_loss": 0.0032677568960934877, | |
| "eval_runtime": 49.715, | |
| "eval_samples_per_second": 8.75, | |
| "eval_steps_per_second": 4.385, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01743763623153306, | |
| "grad_norm": 0.02888139896094799, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0024, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020343908936788568, | |
| "grad_norm": 0.05942815542221069, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0003, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02325018164204408, | |
| "grad_norm": 0.0023815699387341738, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02325018164204408, | |
| "eval_loss": 0.004411344416439533, | |
| "eval_runtime": 49.7487, | |
| "eval_samples_per_second": 8.744, | |
| "eval_steps_per_second": 4.382, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.026156454347299588, | |
| "grad_norm": 0.001381962327286601, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0290627270525551, | |
| "grad_norm": 0.0018880991265177727, | |
| "learning_rate": 0.0, | |
| "loss": 0.2761, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9772398815477760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |