| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0022423619545921705, | |
| "eval_steps": 3, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003737269924320284, | |
| "grad_norm": 1.973085880279541, | |
| "learning_rate": 2e-05, | |
| "loss": 44.5056, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003737269924320284, | |
| "eval_loss": 11.121556282043457, | |
| "eval_runtime": 4.6255, | |
| "eval_samples_per_second": 243.65, | |
| "eval_steps_per_second": 121.933, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007474539848640568, | |
| "grad_norm": 2.0783913135528564, | |
| "learning_rate": 4e-05, | |
| "loss": 44.5521, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011211809772960853, | |
| "grad_norm": 2.088665246963501, | |
| "learning_rate": 6e-05, | |
| "loss": 44.5853, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011211809772960853, | |
| "eval_loss": 11.120728492736816, | |
| "eval_runtime": 3.1954, | |
| "eval_samples_per_second": 352.69, | |
| "eval_steps_per_second": 176.502, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014949079697281135, | |
| "grad_norm": 2.0927140712738037, | |
| "learning_rate": 8e-05, | |
| "loss": 44.4291, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001868634962160142, | |
| "grad_norm": 1.9669666290283203, | |
| "learning_rate": 0.0001, | |
| "loss": 44.4457, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022423619545921705, | |
| "grad_norm": 2.133347749710083, | |
| "learning_rate": 0.00012, | |
| "loss": 44.4746, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022423619545921705, | |
| "eval_loss": 11.11185359954834, | |
| "eval_runtime": 3.2602, | |
| "eval_samples_per_second": 345.682, | |
| "eval_steps_per_second": 172.994, | |
| "step": 6 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 69924814848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |