| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04830917874396135, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004830917874396135, | |
| "grad_norm": 4.588574409484863, | |
| "learning_rate": 2e-05, | |
| "loss": 44.3766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004830917874396135, | |
| "eval_loss": 11.088024139404297, | |
| "eval_runtime": 1.8991, | |
| "eval_samples_per_second": 46.338, | |
| "eval_steps_per_second": 23.169, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00966183574879227, | |
| "grad_norm": 4.322054862976074, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3588, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014492753623188406, | |
| "grad_norm": 5.047557353973389, | |
| "learning_rate": 6e-05, | |
| "loss": 44.4384, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014492753623188406, | |
| "eval_loss": 11.081047058105469, | |
| "eval_runtime": 1.5273, | |
| "eval_samples_per_second": 57.619, | |
| "eval_steps_per_second": 28.81, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01932367149758454, | |
| "grad_norm": 4.04183292388916, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3261, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.024154589371980676, | |
| "grad_norm": 4.250118255615234, | |
| "learning_rate": 0.0001, | |
| "loss": 44.298, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": 3.9748477935791016, | |
| "learning_rate": 0.00012, | |
| "loss": 44.2598, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "eval_loss": 11.053829193115234, | |
| "eval_runtime": 1.5763, | |
| "eval_samples_per_second": 55.828, | |
| "eval_steps_per_second": 27.914, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.033816425120772944, | |
| "grad_norm": 4.778048992156982, | |
| "learning_rate": 0.00014, | |
| "loss": 44.2285, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03864734299516908, | |
| "grad_norm": 4.494859218597412, | |
| "learning_rate": 0.00016, | |
| "loss": 44.1229, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.043478260869565216, | |
| "grad_norm": 4.587972164154053, | |
| "learning_rate": 0.00018, | |
| "loss": 44.1111, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.043478260869565216, | |
| "eval_loss": 11.003266334533691, | |
| "eval_runtime": 1.58, | |
| "eval_samples_per_second": 55.697, | |
| "eval_steps_per_second": 27.849, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04830917874396135, | |
| "grad_norm": 4.518380641937256, | |
| "learning_rate": 0.0002, | |
| "loss": 44.0229, | |
| "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": 831982141440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |