| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0025935291447837646, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025935291447837645, | |
| "grad_norm": 5.132763385772705, | |
| "learning_rate": 2e-05, | |
| "loss": 27.91, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025935291447837645, | |
| "eval_loss": 4.831871509552002, | |
| "eval_runtime": 28.6728, | |
| "eval_samples_per_second": 56.639, | |
| "eval_steps_per_second": 28.32, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005187058289567529, | |
| "grad_norm": 4.572207450866699, | |
| "learning_rate": 4e-05, | |
| "loss": 19.1465, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007780587434351293, | |
| "grad_norm": 4.086507320404053, | |
| "learning_rate": 6e-05, | |
| "loss": 20.8536, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007780587434351293, | |
| "eval_loss": 4.829874038696289, | |
| "eval_runtime": 28.4488, | |
| "eval_samples_per_second": 57.085, | |
| "eval_steps_per_second": 28.543, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010374116579135058, | |
| "grad_norm": 3.4174814224243164, | |
| "learning_rate": 8e-05, | |
| "loss": 17.5205, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012967645723918823, | |
| "grad_norm": 3.08579158782959, | |
| "learning_rate": 0.0001, | |
| "loss": 17.1885, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015561174868702586, | |
| "grad_norm": 2.652798891067505, | |
| "learning_rate": 0.00012, | |
| "loss": 12.6005, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015561174868702586, | |
| "eval_loss": 4.7930426597595215, | |
| "eval_runtime": 28.532, | |
| "eval_samples_per_second": 56.919, | |
| "eval_steps_per_second": 28.459, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018154704013486351, | |
| "grad_norm": 4.396174907684326, | |
| "learning_rate": 0.00014, | |
| "loss": 16.8671, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0020748233158270116, | |
| "grad_norm": 5.884392261505127, | |
| "learning_rate": 0.00016, | |
| "loss": 19.9732, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002334176230305388, | |
| "grad_norm": 5.952862739562988, | |
| "learning_rate": 0.00018, | |
| "loss": 19.1747, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002334176230305388, | |
| "eval_loss": 4.522780418395996, | |
| "eval_runtime": 28.5558, | |
| "eval_samples_per_second": 56.871, | |
| "eval_steps_per_second": 28.436, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025935291447837646, | |
| "grad_norm": 5.507638931274414, | |
| "learning_rate": 0.0002, | |
| "loss": 18.321, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 328602344226816.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |