| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13186813186813187, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004395604395604396, | |
| "eval_loss": 10.36672306060791, | |
| "eval_runtime": 0.3674, | |
| "eval_samples_per_second": 261.292, | |
| "eval_steps_per_second": 130.646, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013186813186813187, | |
| "grad_norm": 0.060739461332559586, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3702, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.026373626373626374, | |
| "grad_norm": 0.0582093745470047, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3761, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.035164835164835165, | |
| "eval_loss": 10.366386413574219, | |
| "eval_runtime": 0.3663, | |
| "eval_samples_per_second": 262.078, | |
| "eval_steps_per_second": 131.039, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03956043956043956, | |
| "grad_norm": 0.054856251925230026, | |
| "learning_rate": 0.00018, | |
| "loss": 10.363, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05274725274725275, | |
| "grad_norm": 0.05579746142029762, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.3738, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06593406593406594, | |
| "grad_norm": 0.04492007568478584, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3696, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07032967032967033, | |
| "eval_loss": 10.365509986877441, | |
| "eval_runtime": 0.4005, | |
| "eval_samples_per_second": 239.726, | |
| "eval_steps_per_second": 119.863, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07912087912087912, | |
| "grad_norm": 0.061128389090299606, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3732, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09230769230769231, | |
| "grad_norm": 0.056560974568128586, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.3698, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1054945054945055, | |
| "grad_norm": 0.06187056005001068, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.3695, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1054945054945055, | |
| "eval_loss": 10.364975929260254, | |
| "eval_runtime": 0.3982, | |
| "eval_samples_per_second": 241.109, | |
| "eval_steps_per_second": 120.554, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11868131868131868, | |
| "grad_norm": 0.06369107961654663, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.3706, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13186813186813187, | |
| "grad_norm": 0.05572490394115448, | |
| "learning_rate": 0.0, | |
| "loss": 10.3707, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 784536698880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |