| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004465780953444233, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004465780953444234, | |
| "grad_norm": 2.851041316986084, | |
| "learning_rate": 2e-05, | |
| "loss": 10.0642, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004465780953444234, | |
| "eval_loss": 2.1306488513946533, | |
| "eval_runtime": 41.7266, | |
| "eval_samples_per_second": 22.599, | |
| "eval_steps_per_second": 11.312, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008931561906888468, | |
| "grad_norm": 0.8493361473083496, | |
| "learning_rate": 4e-05, | |
| "loss": 9.0667, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00133973428603327, | |
| "grad_norm": 1.4644571542739868, | |
| "learning_rate": 6e-05, | |
| "loss": 8.6212, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00133973428603327, | |
| "eval_loss": 2.1303281784057617, | |
| "eval_runtime": 41.7184, | |
| "eval_samples_per_second": 22.604, | |
| "eval_steps_per_second": 11.314, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017863123813776935, | |
| "grad_norm": 1.7268620729446411, | |
| "learning_rate": 8e-05, | |
| "loss": 7.9747, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0022328904767221166, | |
| "grad_norm": 0.8572864532470703, | |
| "learning_rate": 0.0001, | |
| "loss": 9.5719, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00267946857206654, | |
| "grad_norm": 1.3693516254425049, | |
| "learning_rate": 0.00012, | |
| "loss": 8.7567, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00267946857206654, | |
| "eval_loss": 2.127455234527588, | |
| "eval_runtime": 41.7701, | |
| "eval_samples_per_second": 22.576, | |
| "eval_steps_per_second": 11.3, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031260466674109637, | |
| "grad_norm": 1.5636837482452393, | |
| "learning_rate": 0.00014, | |
| "loss": 9.5723, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003572624762755387, | |
| "grad_norm": 1.506066083908081, | |
| "learning_rate": 0.00016, | |
| "loss": 9.5101, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00401920285809981, | |
| "grad_norm": 1.4242777824401855, | |
| "learning_rate": 0.00018, | |
| "loss": 8.9659, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00401920285809981, | |
| "eval_loss": 2.1107497215270996, | |
| "eval_runtime": 41.7116, | |
| "eval_samples_per_second": 22.608, | |
| "eval_steps_per_second": 11.316, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004465780953444233, | |
| "grad_norm": 1.5425928831100464, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3229, | |
| "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": 1995217821499392.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |