| { |
| "best_metric": 0.19941402971744537, |
| "best_model_checkpoint": "/kaggle/working/trainer/checkpoint-590", |
| "epoch": 15.0, |
| "eval_steps": 500, |
| "global_step": 1770, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 4.8408871745419484e-05, |
| "loss": 2.902, |
| "step": 118 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.314755380153656, |
| "eval_runtime": 19.7216, |
| "eval_samples_per_second": 1.318, |
| "eval_steps_per_second": 0.659, |
| "step": 118 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.563645130183221e-05, |
| "loss": 0.3101, |
| "step": 236 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.8408044576644897, |
| "eval_runtime": 19.716, |
| "eval_samples_per_second": 1.319, |
| "eval_steps_per_second": 0.659, |
| "step": 236 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.2960462873674064e-05, |
| "loss": 1.0237, |
| "step": 354 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.23988741636276245, |
| "eval_runtime": 19.7335, |
| "eval_samples_per_second": 1.318, |
| "eval_steps_per_second": 0.659, |
| "step": 354 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.011571841851495e-05, |
| "loss": 0.3245, |
| "step": 472 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.20902396738529205, |
| "eval_runtime": 19.6909, |
| "eval_samples_per_second": 1.32, |
| "eval_steps_per_second": 0.66, |
| "step": 472 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 3.7270973963355835e-05, |
| "loss": 0.1679, |
| "step": 590 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.19941402971744537, |
| "eval_runtime": 19.7266, |
| "eval_samples_per_second": 1.318, |
| "eval_steps_per_second": 0.659, |
| "step": 590 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 3.442622950819672e-05, |
| "loss": 0.1973, |
| "step": 708 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.21409890055656433, |
| "eval_runtime": 19.7603, |
| "eval_samples_per_second": 1.316, |
| "eval_steps_per_second": 0.658, |
| "step": 708 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 3.158148505303761e-05, |
| "loss": 0.2323, |
| "step": 826 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.2766213119029999, |
| "eval_runtime": 19.7249, |
| "eval_samples_per_second": 1.318, |
| "eval_steps_per_second": 0.659, |
| "step": 826 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 2.87367405978785e-05, |
| "loss": 0.2064, |
| "step": 944 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.20961548388004303, |
| "eval_runtime": 19.7074, |
| "eval_samples_per_second": 1.319, |
| "eval_steps_per_second": 0.66, |
| "step": 944 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 2.589199614271938e-05, |
| "loss": 0.1943, |
| "step": 1062 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.2783980965614319, |
| "eval_runtime": 19.7328, |
| "eval_samples_per_second": 1.318, |
| "eval_steps_per_second": 0.659, |
| "step": 1062 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 2.304725168756027e-05, |
| "loss": 0.2605, |
| "step": 1180 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.28063008189201355, |
| "eval_runtime": 19.721, |
| "eval_samples_per_second": 1.318, |
| "eval_steps_per_second": 0.659, |
| "step": 1180 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 2.020250723240116e-05, |
| "loss": 0.2797, |
| "step": 1298 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.7226824164390564, |
| "eval_runtime": 19.7144, |
| "eval_samples_per_second": 1.319, |
| "eval_steps_per_second": 0.659, |
| "step": 1298 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 1.7357762777242045e-05, |
| "loss": 0.5877, |
| "step": 1416 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.3170361816883087, |
| "eval_runtime": 19.7302, |
| "eval_samples_per_second": 1.318, |
| "eval_steps_per_second": 0.659, |
| "step": 1416 |
| }, |
| { |
| "epoch": 13.0, |
| "learning_rate": 1.4513018322082934e-05, |
| "loss": 0.3059, |
| "step": 1534 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.24836881458759308, |
| "eval_runtime": 19.6883, |
| "eval_samples_per_second": 1.321, |
| "eval_steps_per_second": 0.66, |
| "step": 1534 |
| }, |
| { |
| "epoch": 14.0, |
| "learning_rate": 1.166827386692382e-05, |
| "loss": 0.1948, |
| "step": 1652 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.25250551104545593, |
| "eval_runtime": 19.7516, |
| "eval_samples_per_second": 1.316, |
| "eval_steps_per_second": 0.658, |
| "step": 1652 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 8.823529411764707e-06, |
| "loss": 0.1966, |
| "step": 1770 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.21671946346759796, |
| "eval_runtime": 19.7256, |
| "eval_samples_per_second": 1.318, |
| "eval_steps_per_second": 0.659, |
| "step": 1770 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2124, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 18, |
| "save_steps": 500, |
| "total_flos": 3.242923135598592e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
