| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015414258188824663, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015414258188824663, | |
| "grad_norm": 0.05415869131684303, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3675, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015414258188824663, | |
| "eval_loss": 10.369453430175781, | |
| "eval_runtime": 1.6921, | |
| "eval_samples_per_second": 80.965, | |
| "eval_steps_per_second": 80.965, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0030828516377649326, | |
| "grad_norm": 0.06159928813576698, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3608, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004624277456647399, | |
| "grad_norm": 0.05035201832652092, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3698, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004624277456647399, | |
| "eval_loss": 10.369431495666504, | |
| "eval_runtime": 1.6773, | |
| "eval_samples_per_second": 81.678, | |
| "eval_steps_per_second": 81.678, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006165703275529865, | |
| "grad_norm": 0.06343778967857361, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3694, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007707129094412331, | |
| "grad_norm": 0.04486631974577904, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3676, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009248554913294798, | |
| "grad_norm": 0.05424387380480766, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3747, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009248554913294798, | |
| "eval_loss": 10.369335174560547, | |
| "eval_runtime": 1.7112, | |
| "eval_samples_per_second": 80.062, | |
| "eval_steps_per_second": 80.062, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010789980732177264, | |
| "grad_norm": 0.0424368679523468, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3722, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01233140655105973, | |
| "grad_norm": 0.0684710443019867, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3655, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013872832369942197, | |
| "grad_norm": 0.0837874487042427, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3711, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013872832369942197, | |
| "eval_loss": 10.369171142578125, | |
| "eval_runtime": 1.7261, | |
| "eval_samples_per_second": 79.372, | |
| "eval_steps_per_second": 79.372, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015414258188824663, | |
| "grad_norm": 0.0653405711054802, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3704, | |
| "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": 523024465920.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |