| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03508771929824561, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000899685110211426, | |
| "eval_loss": 11.939785957336426, | |
| "eval_runtime": 11.7148, | |
| "eval_samples_per_second": 39.95, | |
| "eval_steps_per_second": 19.975, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00449842555105713, | |
| "grad_norm": 0.35622671246528625, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9281, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00899685110211426, | |
| "grad_norm": 0.3019970655441284, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00899685110211426, | |
| "eval_loss": 11.937747955322266, | |
| "eval_runtime": 11.3246, | |
| "eval_samples_per_second": 41.326, | |
| "eval_steps_per_second": 20.663, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01349527665317139, | |
| "grad_norm": 0.4445878863334656, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01799370220422852, | |
| "grad_norm": 0.3437993824481964, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9357, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01799370220422852, | |
| "eval_loss": 11.933320045471191, | |
| "eval_runtime": 11.3166, | |
| "eval_samples_per_second": 41.355, | |
| "eval_steps_per_second": 20.678, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02249212775528565, | |
| "grad_norm": 0.3417533338069916, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9293, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02699055330634278, | |
| "grad_norm": 0.4041164219379425, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9306, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02699055330634278, | |
| "eval_loss": 11.9298677444458, | |
| "eval_runtime": 11.3831, | |
| "eval_samples_per_second": 41.114, | |
| "eval_steps_per_second": 20.557, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03148897885739991, | |
| "grad_norm": 0.46610507369041443, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9284, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4881081434112.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |