| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014972301242701003, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014972301242701004, | |
| "grad_norm": 5.718535900115967, | |
| "learning_rate": 2e-05, | |
| "loss": 13.9691, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014972301242701004, | |
| "eval_loss": 3.1406643390655518, | |
| "eval_runtime": 95.0784, | |
| "eval_samples_per_second": 29.586, | |
| "eval_steps_per_second": 14.798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002994460248540201, | |
| "grad_norm": 3.998067855834961, | |
| "learning_rate": 4e-05, | |
| "loss": 12.1924, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004491690372810301, | |
| "grad_norm": 3.385780096054077, | |
| "learning_rate": 6e-05, | |
| "loss": 10.7001, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004491690372810301, | |
| "eval_loss": 3.1328868865966797, | |
| "eval_runtime": 94.9572, | |
| "eval_samples_per_second": 29.624, | |
| "eval_steps_per_second": 14.817, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005988920497080402, | |
| "grad_norm": 4.368773937225342, | |
| "learning_rate": 8e-05, | |
| "loss": 13.3069, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007486150621350501, | |
| "grad_norm": 4.162635803222656, | |
| "learning_rate": 0.0001, | |
| "loss": 12.3782, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008983380745620602, | |
| "grad_norm": 5.947353839874268, | |
| "learning_rate": 0.00012, | |
| "loss": 13.0741, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008983380745620602, | |
| "eval_loss": 3.0115833282470703, | |
| "eval_runtime": 95.0405, | |
| "eval_samples_per_second": 29.598, | |
| "eval_steps_per_second": 14.804, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010480610869890701, | |
| "grad_norm": 8.761029243469238, | |
| "learning_rate": 0.00014, | |
| "loss": 12.9366, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011977840994160803, | |
| "grad_norm": 9.459814071655273, | |
| "learning_rate": 0.00016, | |
| "loss": 11.1142, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013475071118430903, | |
| "grad_norm": 10.454730987548828, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8409, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013475071118430903, | |
| "eval_loss": 2.5963327884674072, | |
| "eval_runtime": 94.9898, | |
| "eval_samples_per_second": 29.614, | |
| "eval_steps_per_second": 14.812, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014972301242701003, | |
| "grad_norm": 8.69300365447998, | |
| "learning_rate": 0.0002, | |
| "loss": 9.9716, | |
| "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": 1750905435193344.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |