| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 59.67567567567568, |
| "eval_steps": 276, |
| "global_step": 2760, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 5.967567567567568, |
| "grad_norm": 1.919080138206482, |
| "learning_rate": 9.007246376811595e-06, |
| "loss": 1.2383, |
| "step": 276 |
| }, |
| { |
| "epoch": 5.967567567567568, |
| "eval_accuracy": 0.24171382376717865, |
| "eval_loss": 2.6388285160064697, |
| "eval_runtime": 3.7642, |
| "eval_samples_per_second": 328.62, |
| "eval_steps_per_second": 16.471, |
| "step": 276 |
| }, |
| { |
| "epoch": 11.935135135135136, |
| "grad_norm": 4.005405426025391, |
| "learning_rate": 8.007246376811595e-06, |
| "loss": 0.9769, |
| "step": 552 |
| }, |
| { |
| "epoch": 11.935135135135136, |
| "eval_accuracy": 0.22473726758286175, |
| "eval_loss": 2.817387580871582, |
| "eval_runtime": 3.6842, |
| "eval_samples_per_second": 335.761, |
| "eval_steps_per_second": 16.829, |
| "step": 552 |
| }, |
| { |
| "epoch": 17.9027027027027, |
| "grad_norm": 5.196224689483643, |
| "learning_rate": 7.007246376811595e-06, |
| "loss": 0.8157, |
| "step": 828 |
| }, |
| { |
| "epoch": 17.9027027027027, |
| "eval_accuracy": 0.21476690918889788, |
| "eval_loss": 3.148566961288452, |
| "eval_runtime": 3.7399, |
| "eval_samples_per_second": 330.758, |
| "eval_steps_per_second": 16.578, |
| "step": 828 |
| }, |
| { |
| "epoch": 23.87027027027027, |
| "grad_norm": 5.394821643829346, |
| "learning_rate": 6.007246376811595e-06, |
| "loss": 0.7322, |
| "step": 1104 |
| }, |
| { |
| "epoch": 23.87027027027027, |
| "eval_accuracy": 0.20796281325788196, |
| "eval_loss": 3.3019931316375732, |
| "eval_runtime": 3.7581, |
| "eval_samples_per_second": 329.155, |
| "eval_steps_per_second": 16.498, |
| "step": 1104 |
| }, |
| { |
| "epoch": 29.83783783783784, |
| "grad_norm": 4.061520576477051, |
| "learning_rate": 5.0072463768115946e-06, |
| "loss": 0.6777, |
| "step": 1380 |
| }, |
| { |
| "epoch": 29.83783783783784, |
| "eval_accuracy": 0.20258690379951497, |
| "eval_loss": 3.393256187438965, |
| "eval_runtime": 3.7268, |
| "eval_samples_per_second": 331.922, |
| "eval_steps_per_second": 16.636, |
| "step": 1380 |
| }, |
| { |
| "epoch": 35.8054054054054, |
| "grad_norm": 4.988523483276367, |
| "learning_rate": 4.007246376811594e-06, |
| "loss": 0.6466, |
| "step": 1656 |
| }, |
| { |
| "epoch": 35.8054054054054, |
| "eval_accuracy": 0.19967663702506064, |
| "eval_loss": 3.418116807937622, |
| "eval_runtime": 3.7118, |
| "eval_samples_per_second": 333.261, |
| "eval_steps_per_second": 16.703, |
| "step": 1656 |
| }, |
| { |
| "epoch": 41.77297297297297, |
| "grad_norm": 4.484840393066406, |
| "learning_rate": 3.0072463768115946e-06, |
| "loss": 0.6272, |
| "step": 1932 |
| }, |
| { |
| "epoch": 41.77297297297297, |
| "eval_accuracy": 0.1974823882665435, |
| "eval_loss": 3.436495304107666, |
| "eval_runtime": 3.7964, |
| "eval_samples_per_second": 325.831, |
| "eval_steps_per_second": 16.331, |
| "step": 1932 |
| }, |
| { |
| "epoch": 47.74054054054054, |
| "grad_norm": 3.4457993507385254, |
| "learning_rate": 2.0108695652173916e-06, |
| "loss": 0.6188, |
| "step": 2208 |
| }, |
| { |
| "epoch": 47.74054054054054, |
| "eval_accuracy": 0.19563459983831852, |
| "eval_loss": 3.466963529586792, |
| "eval_runtime": 3.7849, |
| "eval_samples_per_second": 326.822, |
| "eval_steps_per_second": 16.381, |
| "step": 2208 |
| }, |
| { |
| "epoch": 53.70810810810811, |
| "grad_norm": 5.685315132141113, |
| "learning_rate": 1.0108695652173914e-06, |
| "loss": 0.6052, |
| "step": 2484 |
| }, |
| { |
| "epoch": 53.70810810810811, |
| "eval_accuracy": 0.19455672325518727, |
| "eval_loss": 3.4625163078308105, |
| "eval_runtime": 3.7562, |
| "eval_samples_per_second": 329.32, |
| "eval_steps_per_second": 16.506, |
| "step": 2484 |
| }, |
| { |
| "epoch": 59.67567567567568, |
| "grad_norm": 3.5206406116485596, |
| "learning_rate": 1.0869565217391305e-08, |
| "loss": 0.6049, |
| "step": 2760 |
| }, |
| { |
| "epoch": 59.67567567567568, |
| "eval_accuracy": 0.1936944219886823, |
| "eval_loss": 3.4762697219848633, |
| "eval_runtime": 3.721, |
| "eval_samples_per_second": 332.435, |
| "eval_steps_per_second": 16.662, |
| "step": 2760 |
| }, |
| { |
| "epoch": 59.67567567567568, |
| "step": 2760, |
| "total_flos": 1.4462122119191654e+17, |
| "train_loss": 0.7543455040973166, |
| "train_runtime": 3693.2507, |
| "train_samples_per_second": 149.982, |
| "train_steps_per_second": 0.747 |
| } |
| ], |
| "logging_steps": 276, |
| "max_steps": 2760, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 60, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.4462122119191654e+17, |
| "train_batch_size": 25, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
