| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0033419977720014855, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003713330857779428, | |
| "grad_norm": 0.9089969992637634, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6876, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003713330857779428, | |
| "eval_loss": 0.4146934747695923, | |
| "eval_runtime": 37.185, | |
| "eval_samples_per_second": 30.496, | |
| "eval_steps_per_second": 15.248, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007426661715558856, | |
| "grad_norm": 1.0030620098114014, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5185, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011139992573338284, | |
| "grad_norm": 1.4879279136657715, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5859, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011139992573338284, | |
| "eval_loss": 0.41284868121147156, | |
| "eval_runtime": 37.1943, | |
| "eval_samples_per_second": 30.489, | |
| "eval_steps_per_second": 15.244, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014853323431117712, | |
| "grad_norm": 0.9057229161262512, | |
| "learning_rate": 8e-05, | |
| "loss": 1.4247, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001856665428889714, | |
| "grad_norm": 0.7766861319541931, | |
| "learning_rate": 0.0001, | |
| "loss": 1.363, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022279985146676567, | |
| "grad_norm": 1.2344207763671875, | |
| "learning_rate": 0.00012, | |
| "loss": 1.5412, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022279985146676567, | |
| "eval_loss": 0.3825955390930176, | |
| "eval_runtime": 37.478, | |
| "eval_samples_per_second": 30.258, | |
| "eval_steps_per_second": 15.129, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025993316004456, | |
| "grad_norm": 1.7376594543457031, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6128, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0029706646862235424, | |
| "grad_norm": 1.4749916791915894, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1024, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033419977720014855, | |
| "grad_norm": 1.9655250310897827, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2391, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0033419977720014855, | |
| "eval_loss": 0.22511792182922363, | |
| "eval_runtime": 37.5364, | |
| "eval_samples_per_second": 30.211, | |
| "eval_steps_per_second": 15.105, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1465874317836288.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |