| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05235602094240838, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020942408376963353, | |
| "grad_norm": 0.34981271624565125, | |
| "learning_rate": 1e-05, | |
| "loss": 3.2781, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020942408376963353, | |
| "eval_loss": 1.7277591228485107, | |
| "eval_runtime": 53.6735, | |
| "eval_samples_per_second": 7.508, | |
| "eval_steps_per_second": 0.95, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004188481675392671, | |
| "grad_norm": 0.801185667514801, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5415, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0062827225130890054, | |
| "grad_norm": 0.3677161931991577, | |
| "learning_rate": 3e-05, | |
| "loss": 3.5543, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008376963350785341, | |
| "grad_norm": 0.448595255613327, | |
| "learning_rate": 4e-05, | |
| "loss": 3.4746, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010471204188481676, | |
| "grad_norm": 0.40933072566986084, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3815, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012565445026178011, | |
| "grad_norm": 0.4692118465900421, | |
| "learning_rate": 6e-05, | |
| "loss": 3.5705, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014659685863874346, | |
| "grad_norm": 0.5187078714370728, | |
| "learning_rate": 7e-05, | |
| "loss": 3.3902, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016753926701570682, | |
| "grad_norm": 0.4143497347831726, | |
| "learning_rate": 8e-05, | |
| "loss": 3.1211, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018848167539267015, | |
| "grad_norm": 0.4992891848087311, | |
| "learning_rate": 9e-05, | |
| "loss": 3.3897, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018848167539267015, | |
| "eval_loss": 1.690635323524475, | |
| "eval_runtime": 54.4943, | |
| "eval_samples_per_second": 7.395, | |
| "eval_steps_per_second": 0.936, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020942408376963352, | |
| "grad_norm": 0.5181413292884827, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023036649214659685, | |
| "grad_norm": 0.573737621307373, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 3.135, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025130890052356022, | |
| "grad_norm": 0.5204129219055176, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 3.2358, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.027225130890052355, | |
| "grad_norm": 0.5474736094474792, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 3.2861, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02931937172774869, | |
| "grad_norm": 0.5524812340736389, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.2345, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.031413612565445025, | |
| "grad_norm": 0.5993866324424744, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 3.025, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033507853403141365, | |
| "grad_norm": 0.5874714851379395, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.9435, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0356020942408377, | |
| "grad_norm": 0.5276877284049988, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.9228, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03769633507853403, | |
| "grad_norm": 0.5134425759315491, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 3.0417, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03769633507853403, | |
| "eval_loss": 1.5175120830535889, | |
| "eval_runtime": 54.491, | |
| "eval_samples_per_second": 7.396, | |
| "eval_steps_per_second": 0.936, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.039790575916230364, | |
| "grad_norm": 0.6345006823539734, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.0776, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.041884816753926704, | |
| "grad_norm": 0.5065171122550964, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.7851, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04397905759162304, | |
| "grad_norm": 0.6690090894699097, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.9525, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04607329842931937, | |
| "grad_norm": 0.5420049428939819, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 3.0601, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.048167539267015703, | |
| "grad_norm": 0.6415935754776001, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 2.9687, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.050261780104712044, | |
| "grad_norm": 0.4800170063972473, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.6966, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05235602094240838, | |
| "grad_norm": 0.5702900290489197, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.9085, | |
| "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": 1.63366161088512e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |