| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0093562874251497, | |
| "eval_steps": 4, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00037425149700598805, | |
| "grad_norm": 0.8269398212432861, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00037425149700598805, | |
| "eval_loss": 2.5136237144470215, | |
| "eval_runtime": 70.1082, | |
| "eval_samples_per_second": 32.093, | |
| "eval_steps_per_second": 4.022, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007485029940119761, | |
| "grad_norm": 0.9194856286048889, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5205, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001122754491017964, | |
| "grad_norm": 0.7817849516868591, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2787, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014970059880239522, | |
| "grad_norm": 0.8849879503250122, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5535, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014970059880239522, | |
| "eval_loss": 2.5120456218719482, | |
| "eval_runtime": 69.1916, | |
| "eval_samples_per_second": 32.518, | |
| "eval_steps_per_second": 4.076, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018712574850299401, | |
| "grad_norm": 0.8989524841308594, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4387, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002245508982035928, | |
| "grad_norm": 0.9557816386222839, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4527, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002619760479041916, | |
| "grad_norm": 0.9484394788742065, | |
| "learning_rate": 7e-05, | |
| "loss": 2.4293, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0029940119760479044, | |
| "grad_norm": 0.84719318151474, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4354, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0029940119760479044, | |
| "eval_loss": 2.488919258117676, | |
| "eval_runtime": 69.4486, | |
| "eval_samples_per_second": 32.398, | |
| "eval_steps_per_second": 4.061, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033682634730538923, | |
| "grad_norm": 0.8281010389328003, | |
| "learning_rate": 9e-05, | |
| "loss": 2.3667, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0037425149700598802, | |
| "grad_norm": 0.8274064064025879, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3371, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004116766467065869, | |
| "grad_norm": 1.064297080039978, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.1805, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004491017964071856, | |
| "grad_norm": 1.2108567953109741, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.4674, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004491017964071856, | |
| "eval_loss": 2.4155914783477783, | |
| "eval_runtime": 69.0774, | |
| "eval_samples_per_second": 32.572, | |
| "eval_steps_per_second": 4.082, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0048652694610778445, | |
| "grad_norm": 1.0240373611450195, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.2426, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005239520958083832, | |
| "grad_norm": 0.9014378786087036, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.5256, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00561377245508982, | |
| "grad_norm": 1.0252859592437744, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.5582, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005988023952095809, | |
| "grad_norm": 1.090508222579956, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.2826, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005988023952095809, | |
| "eval_loss": 2.4081342220306396, | |
| "eval_runtime": 69.0982, | |
| "eval_samples_per_second": 32.562, | |
| "eval_steps_per_second": 4.081, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006362275449101796, | |
| "grad_norm": 1.0605902671813965, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.5273, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006736526946107785, | |
| "grad_norm": 1.2208561897277832, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.4164, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007110778443113772, | |
| "grad_norm": 1.030013084411621, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.4282, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0074850299401197605, | |
| "grad_norm": 1.1284306049346924, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.5186, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0074850299401197605, | |
| "eval_loss": 2.401789426803589, | |
| "eval_runtime": 69.073, | |
| "eval_samples_per_second": 32.574, | |
| "eval_steps_per_second": 4.083, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007859281437125748, | |
| "grad_norm": 1.0382846593856812, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 2.32, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008233532934131737, | |
| "grad_norm": 0.9643081426620483, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.3257, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008607784431137725, | |
| "grad_norm": 1.031815528869629, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.4323, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008982035928143712, | |
| "grad_norm": 0.8642554879188538, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.1558, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008982035928143712, | |
| "eval_loss": 2.3983020782470703, | |
| "eval_runtime": 69.0603, | |
| "eval_samples_per_second": 32.58, | |
| "eval_steps_per_second": 4.083, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0093562874251497, | |
| "grad_norm": 0.9778251647949219, | |
| "learning_rate": 0.0, | |
| "loss": 2.0667, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2419306423910400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |