| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04189359028068706, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008378718056137411, | |
| "eval_loss": 11.104301452636719, | |
| "eval_runtime": 57.2305, | |
| "eval_samples_per_second": 140.502, | |
| "eval_steps_per_second": 17.578, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008378718056137411, | |
| "grad_norm": 4.693471431732178, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 177.5566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008378718056137411, | |
| "eval_loss": 11.083802223205566, | |
| "eval_runtime": 56.9959, | |
| "eval_samples_per_second": 141.08, | |
| "eval_steps_per_second": 17.65, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016757436112274822, | |
| "grad_norm": 5.290127277374268, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 177.1668, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016757436112274822, | |
| "eval_loss": 11.059365272521973, | |
| "eval_runtime": 56.9535, | |
| "eval_samples_per_second": 141.185, | |
| "eval_steps_per_second": 17.664, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025136154168412233, | |
| "grad_norm": 5.889796257019043, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 176.8012, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025136154168412233, | |
| "eval_loss": 11.03995418548584, | |
| "eval_runtime": 57.0124, | |
| "eval_samples_per_second": 141.039, | |
| "eval_steps_per_second": 17.645, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.033514872224549644, | |
| "grad_norm": 6.078856945037842, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 176.5511, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.033514872224549644, | |
| "eval_loss": 11.030740737915039, | |
| "eval_runtime": 57.2146, | |
| "eval_samples_per_second": 140.541, | |
| "eval_steps_per_second": 17.583, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04189359028068706, | |
| "grad_norm": 6.04699182510376, | |
| "learning_rate": 0.0, | |
| "loss": 176.491, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04189359028068706, | |
| "eval_loss": 11.029204368591309, | |
| "eval_runtime": 57.2043, | |
| "eval_samples_per_second": 140.566, | |
| "eval_steps_per_second": 17.586, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 15431683276800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |