| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02328830926874709, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004657661853749418, | |
| "eval_loss": 4.338293552398682, | |
| "eval_runtime": 60.7879, | |
| "eval_samples_per_second": 14.888, | |
| "eval_steps_per_second": 7.452, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002328830926874709, | |
| "grad_norm": 2.6933412551879883, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9478, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004657661853749418, | |
| "grad_norm": 4.042728424072266, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0766, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004657661853749418, | |
| "eval_loss": 3.808035373687744, | |
| "eval_runtime": 61.2281, | |
| "eval_samples_per_second": 14.781, | |
| "eval_steps_per_second": 7.399, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0069864927806241265, | |
| "grad_norm": 4.20014762878418, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.6635, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009315323707498836, | |
| "grad_norm": 3.396209716796875, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.1523, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009315323707498836, | |
| "eval_loss": 2.9957079887390137, | |
| "eval_runtime": 61.223, | |
| "eval_samples_per_second": 14.782, | |
| "eval_steps_per_second": 7.399, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011644154634373545, | |
| "grad_norm": 3.6307923793792725, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.9618, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013972985561248253, | |
| "grad_norm": 4.308791637420654, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9387, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013972985561248253, | |
| "eval_loss": 2.854153871536255, | |
| "eval_runtime": 61.2445, | |
| "eval_samples_per_second": 14.777, | |
| "eval_steps_per_second": 7.397, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016301816488122962, | |
| "grad_norm": 4.229650020599365, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.5853, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018630647414997672, | |
| "grad_norm": 9.318668365478516, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.9057, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018630647414997672, | |
| "eval_loss": 2.7996816635131836, | |
| "eval_runtime": 61.2074, | |
| "eval_samples_per_second": 14.786, | |
| "eval_steps_per_second": 7.401, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02095947834187238, | |
| "grad_norm": 4.051911354064941, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.9183, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02328830926874709, | |
| "grad_norm": 3.2784907817840576, | |
| "learning_rate": 0.0, | |
| "loss": 2.5637, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02328830926874709, | |
| "eval_loss": 2.786785125732422, | |
| "eval_runtime": 61.0239, | |
| "eval_samples_per_second": 14.83, | |
| "eval_steps_per_second": 7.423, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |