| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01531745423910546, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006126981695642184, | |
| "grad_norm": 16.523408889770508, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 6.7324, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006126981695642184, | |
| "eval_loss": 7.338907718658447, | |
| "eval_runtime": 69.8065, | |
| "eval_samples_per_second": 19.697, | |
| "eval_steps_per_second": 9.856, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012253963391284368, | |
| "grad_norm": 18.644798278808594, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 6.6114, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018380945086926552, | |
| "grad_norm": 15.051867485046387, | |
| "learning_rate": 0.0001, | |
| "loss": 5.7936, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024507926782568737, | |
| "grad_norm": 15.758862495422363, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 5.8646, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0030634908478210923, | |
| "grad_norm": 12.907825469970703, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 4.3165, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036761890173853105, | |
| "grad_norm": 13.11896800994873, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.7056, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004288887186949529, | |
| "grad_norm": 11.859108924865723, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 3.0861, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004901585356513747, | |
| "grad_norm": 11.189018249511719, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 3.0677, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005514283526077966, | |
| "grad_norm": 8.765135765075684, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.8499, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006126981695642185, | |
| "grad_norm": 7.158143520355225, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 2.1377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006739679865206402, | |
| "grad_norm": 7.217545509338379, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.4496, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007352378034770621, | |
| "grad_norm": 7.291643142700195, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.249, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007965076204334839, | |
| "grad_norm": 8.006402015686035, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 2.7193, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008577774373899057, | |
| "grad_norm": 6.830563545227051, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 2.7104, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009190472543463276, | |
| "grad_norm": 5.633250713348389, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0096, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009803170713027495, | |
| "grad_norm": 4.747769832611084, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 1.9659, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010415868882591713, | |
| "grad_norm": 4.103663921356201, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.8876, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011028567052155932, | |
| "grad_norm": 5.507636547088623, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.6484, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01164126522172015, | |
| "grad_norm": 4.795409679412842, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.8157, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01225396339128437, | |
| "grad_norm": 4.361155033111572, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 1.8387, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012866661560848588, | |
| "grad_norm": 4.868300914764404, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2786, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013479359730412805, | |
| "grad_norm": 6.176185131072998, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 2.3026, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014092057899977023, | |
| "grad_norm": 4.714465141296387, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.1449, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014704756069541242, | |
| "grad_norm": 4.232319355010986, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.418, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01531745423910546, | |
| "grad_norm": 4.79272985458374, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 2.043, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01531745423910546, | |
| "eval_loss": 1.8542509078979492, | |
| "eval_runtime": 69.8889, | |
| "eval_samples_per_second": 19.674, | |
| "eval_steps_per_second": 9.844, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 9837753453772800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |