| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006359300476947536, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001271860095389507, | |
| "eval_loss": 0.9393907189369202, | |
| "eval_runtime": 593.7044, | |
| "eval_samples_per_second": 5.577, | |
| "eval_steps_per_second": 2.789, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006359300476947536, | |
| "grad_norm": 1.0778148174285889, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9545, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012718600953895071, | |
| "grad_norm": 1.1839332580566406, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7874, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012718600953895071, | |
| "eval_loss": 0.6840765476226807, | |
| "eval_runtime": 607.8025, | |
| "eval_samples_per_second": 5.447, | |
| "eval_steps_per_second": 2.725, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019077901430842607, | |
| "grad_norm": 0.7646489143371582, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6549, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025437201907790143, | |
| "grad_norm": 0.7357223629951477, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6392, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0025437201907790143, | |
| "eval_loss": 0.6124643087387085, | |
| "eval_runtime": 607.4172, | |
| "eval_samples_per_second": 5.451, | |
| "eval_steps_per_second": 2.726, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003179650238473768, | |
| "grad_norm": 0.6749433279037476, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6094, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0038155802861685214, | |
| "grad_norm": 0.721843957901001, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5875, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0038155802861685214, | |
| "eval_loss": 0.5959174036979675, | |
| "eval_runtime": 608.9676, | |
| "eval_samples_per_second": 5.437, | |
| "eval_steps_per_second": 2.719, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004451510333863275, | |
| "grad_norm": 0.6827080845832825, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5832, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005087440381558029, | |
| "grad_norm": 0.6650816202163696, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5706, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005087440381558029, | |
| "eval_loss": 0.5858871936798096, | |
| "eval_runtime": 607.9445, | |
| "eval_samples_per_second": 5.446, | |
| "eval_steps_per_second": 2.724, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005723370429252782, | |
| "grad_norm": 0.6271900534629822, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5911, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006359300476947536, | |
| "grad_norm": 0.6011094450950623, | |
| "learning_rate": 0.0, | |
| "loss": 0.5796, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006359300476947536, | |
| "eval_loss": 0.5840524435043335, | |
| "eval_runtime": 607.6221, | |
| "eval_samples_per_second": 5.449, | |
| "eval_steps_per_second": 2.725, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.75267079258112e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |