| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022113544546034446, | |
| "eval_steps": 13, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008505209440782479, | |
| "grad_norm": 7.646979331970215, | |
| "learning_rate": 5e-06, | |
| "loss": 11.2339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008505209440782479, | |
| "eval_loss": 2.182969570159912, | |
| "eval_runtime": 18.1957, | |
| "eval_samples_per_second": 27.204, | |
| "eval_steps_per_second": 13.63, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017010418881564958, | |
| "grad_norm": 2.7476022243499756, | |
| "learning_rate": 1e-05, | |
| "loss": 8.1504, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0025515628322347436, | |
| "grad_norm": 4.530780792236328, | |
| "learning_rate": 1.5e-05, | |
| "loss": 9.479, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034020837763129915, | |
| "grad_norm": 4.3689985275268555, | |
| "learning_rate": 2e-05, | |
| "loss": 8.6752, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00425260472039124, | |
| "grad_norm": 4.250224590301514, | |
| "learning_rate": 2.5e-05, | |
| "loss": 8.7246, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005103125664469487, | |
| "grad_norm": 3.909888505935669, | |
| "learning_rate": 3e-05, | |
| "loss": 8.8007, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005953646608547736, | |
| "grad_norm": 4.2319536209106445, | |
| "learning_rate": 3.5e-05, | |
| "loss": 8.6001, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006804167552625983, | |
| "grad_norm": 3.7226130962371826, | |
| "learning_rate": 4e-05, | |
| "loss": 8.6729, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007654688496704231, | |
| "grad_norm": 4.978116512298584, | |
| "learning_rate": 4.5e-05, | |
| "loss": 9.7467, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00850520944078248, | |
| "grad_norm": 7.846011161804199, | |
| "learning_rate": 5e-05, | |
| "loss": 10.2529, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009355730384860728, | |
| "grad_norm": 7.632503032684326, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 10.6994, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010206251328938975, | |
| "grad_norm": 6.259686470031738, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 9.2648, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011056772273017223, | |
| "grad_norm": 4.645693302154541, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 8.8708, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011056772273017223, | |
| "eval_loss": 2.120561122894287, | |
| "eval_runtime": 18.1798, | |
| "eval_samples_per_second": 27.228, | |
| "eval_steps_per_second": 13.642, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011907293217095471, | |
| "grad_norm": 3.9054300785064697, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 7.6945, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01275781416117372, | |
| "grad_norm": 6.3420305252075195, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 8.6295, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013608335105251966, | |
| "grad_norm": 6.098008155822754, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 7.3762, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014458856049330214, | |
| "grad_norm": 6.397308826446533, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 8.6222, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015309376993408463, | |
| "grad_norm": 4.59157133102417, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 7.8273, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01615989793748671, | |
| "grad_norm": 5.998552322387695, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 9.8392, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01701041888156496, | |
| "grad_norm": 4.757502555847168, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 8.913, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017860939825643206, | |
| "grad_norm": 5.794950485229492, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 8.4942, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018711460769721456, | |
| "grad_norm": 7.268848419189453, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 9.6959, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.019561981713799702, | |
| "grad_norm": 4.623784065246582, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 7.3824, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02041250265787795, | |
| "grad_norm": 4.572867393493652, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 8.0812, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0212630236019562, | |
| "grad_norm": 6.01804780960083, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 8.0338, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022113544546034446, | |
| "grad_norm": 4.490617275238037, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 7.893, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.022113544546034446, | |
| "eval_loss": 1.961138367652893, | |
| "eval_runtime": 18.1047, | |
| "eval_samples_per_second": 27.341, | |
| "eval_steps_per_second": 13.698, | |
| "step": 26 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4316142810169344.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |