| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029331964508322946, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029331964508322946, | |
| "grad_norm": 1.0864355564117432, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6134, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029331964508322946, | |
| "eval_loss": 1.4803667068481445, | |
| "eval_runtime": 39.1539, | |
| "eval_samples_per_second": 36.676, | |
| "eval_steps_per_second": 18.338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005866392901664589, | |
| "grad_norm": 0.8085860013961792, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3114, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008799589352496884, | |
| "grad_norm": 0.9164823889732361, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3747, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008799589352496884, | |
| "eval_loss": 1.473850131034851, | |
| "eval_runtime": 39.1671, | |
| "eval_samples_per_second": 36.663, | |
| "eval_steps_per_second": 18.332, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011732785803329178, | |
| "grad_norm": 1.0288509130477905, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5012, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014665982254161473, | |
| "grad_norm": 0.9415997266769409, | |
| "learning_rate": 0.0001, | |
| "loss": 1.437, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017599178704993767, | |
| "grad_norm": 0.8239766955375671, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3821, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017599178704993767, | |
| "eval_loss": 1.4077444076538086, | |
| "eval_runtime": 39.063, | |
| "eval_samples_per_second": 36.761, | |
| "eval_steps_per_second": 18.381, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002053237515582606, | |
| "grad_norm": 0.8693864941596985, | |
| "learning_rate": 0.00014, | |
| "loss": 1.4923, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0023465571606658357, | |
| "grad_norm": 1.0759321451187134, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3972, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002639876805749065, | |
| "grad_norm": 0.8064371347427368, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3029, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002639876805749065, | |
| "eval_loss": 1.302195429801941, | |
| "eval_runtime": 38.9221, | |
| "eval_samples_per_second": 36.894, | |
| "eval_steps_per_second": 18.447, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0029331964508322946, | |
| "grad_norm": 0.805048942565918, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3546, | |
| "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": 500097330708480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |