| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021204410517387615, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008481764206955047, | |
| "grad_norm": 14.318007469177246, | |
| "learning_rate": 1e-05, | |
| "loss": 6.0266, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008481764206955047, | |
| "eval_loss": 5.938344478607178, | |
| "eval_runtime": 29.7987, | |
| "eval_samples_per_second": 33.324, | |
| "eval_steps_per_second": 4.195, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016963528413910093, | |
| "grad_norm": 12.189530372619629, | |
| "learning_rate": 2e-05, | |
| "loss": 5.9766, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002544529262086514, | |
| "grad_norm": 12.671658515930176, | |
| "learning_rate": 3e-05, | |
| "loss": 5.8605, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0033927056827820186, | |
| "grad_norm": 12.592327117919922, | |
| "learning_rate": 4e-05, | |
| "loss": 5.9025, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004240882103477523, | |
| "grad_norm": 13.333489418029785, | |
| "learning_rate": 5e-05, | |
| "loss": 5.6609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005089058524173028, | |
| "grad_norm": 13.644075393676758, | |
| "learning_rate": 6e-05, | |
| "loss": 5.3589, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005937234944868533, | |
| "grad_norm": 12.345027923583984, | |
| "learning_rate": 7e-05, | |
| "loss": 4.8207, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006785411365564037, | |
| "grad_norm": 13.133736610412598, | |
| "learning_rate": 8e-05, | |
| "loss": 4.2425, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "grad_norm": 13.290817260742188, | |
| "learning_rate": 9e-05, | |
| "loss": 3.7581, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "eval_loss": 2.8263907432556152, | |
| "eval_runtime": 28.8558, | |
| "eval_samples_per_second": 34.413, | |
| "eval_steps_per_second": 4.332, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008481764206955046, | |
| "grad_norm": 10.202874183654785, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009329940627650551, | |
| "grad_norm": 8.777361869812012, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.9677, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010178117048346057, | |
| "grad_norm": 7.6035990715026855, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.5619, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01102629346904156, | |
| "grad_norm": 9.740479469299316, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.7213, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011874469889737066, | |
| "grad_norm": 3.958515167236328, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.0046, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01272264631043257, | |
| "grad_norm": 3.2152061462402344, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.8369, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013570822731128074, | |
| "grad_norm": 9.387269973754883, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.0265, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01441899915182358, | |
| "grad_norm": 5.709386825561523, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.7527, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "grad_norm": 4.907479286193848, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.6546, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "eval_loss": 0.6198061108589172, | |
| "eval_runtime": 28.8798, | |
| "eval_samples_per_second": 34.384, | |
| "eval_steps_per_second": 4.328, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016115351993214587, | |
| "grad_norm": 9.104463577270508, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.7803, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016963528413910092, | |
| "grad_norm": 2.6081435680389404, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.5736, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017811704834605598, | |
| "grad_norm": 2.2690072059631348, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.5417, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018659881255301103, | |
| "grad_norm": 2.4608511924743652, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.5057, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.019508057675996608, | |
| "grad_norm": 3.5970542430877686, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.5794, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.020356234096692113, | |
| "grad_norm": 2.4997997283935547, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.5209, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.021204410517387615, | |
| "grad_norm": 2.0091772079467773, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5523, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2573421930086400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |