| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02658160552897395, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000531632110579479, | |
| "eval_loss": 2.794513702392578, | |
| "eval_runtime": 35.2595, | |
| "eval_samples_per_second": 22.462, | |
| "eval_steps_per_second": 11.231, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002658160552897395, | |
| "grad_norm": 2.5087876319885254, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9129, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00531632110579479, | |
| "grad_norm": 3.172278881072998, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5148, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00531632110579479, | |
| "eval_loss": 2.32590651512146, | |
| "eval_runtime": 26.5891, | |
| "eval_samples_per_second": 29.787, | |
| "eval_steps_per_second": 14.893, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007974481658692184, | |
| "grad_norm": 2.6018869876861572, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7981, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "grad_norm": 1.8246312141418457, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.145, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "eval_loss": 0.6814725399017334, | |
| "eval_runtime": 27.0108, | |
| "eval_samples_per_second": 29.322, | |
| "eval_steps_per_second": 14.661, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013290802764486975, | |
| "grad_norm": 2.5452466011047363, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6943, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01594896331738437, | |
| "grad_norm": 1.912396788597107, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3943, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01594896331738437, | |
| "eval_loss": 0.2496986836194992, | |
| "eval_runtime": 27.3235, | |
| "eval_samples_per_second": 28.986, | |
| "eval_steps_per_second": 14.493, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018607123870281767, | |
| "grad_norm": 0.5929796099662781, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1247, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02126528442317916, | |
| "grad_norm": 1.806302547454834, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1757, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02126528442317916, | |
| "eval_loss": 0.1834142655134201, | |
| "eval_runtime": 27.0169, | |
| "eval_samples_per_second": 29.315, | |
| "eval_steps_per_second": 14.657, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023923444976076555, | |
| "grad_norm": 2.3250198364257812, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2178, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02658160552897395, | |
| "grad_norm": 0.5584317445755005, | |
| "learning_rate": 0.0, | |
| "loss": 0.0977, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02658160552897395, | |
| "eval_loss": 0.17906339466571808, | |
| "eval_runtime": 26.7116, | |
| "eval_samples_per_second": 29.65, | |
| "eval_steps_per_second": 14.825, | |
| "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": 1581936279552000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |