| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18930430667297682, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007572172266919072, | |
| "grad_norm": 2.4073128700256348, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0444, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007572172266919072, | |
| "eval_loss": 4.418989658355713, | |
| "eval_runtime": 3.2607, | |
| "eval_samples_per_second": 15.334, | |
| "eval_steps_per_second": 3.987, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015144344533838144, | |
| "grad_norm": 3.72934627532959, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6067, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.022716516800757217, | |
| "grad_norm": 4.2463226318359375, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.5081, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03028868906767629, | |
| "grad_norm": 3.8385074138641357, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.2803, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03786086133459536, | |
| "grad_norm": 2.1566147804260254, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.0277, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04543303360151443, | |
| "grad_norm": 2.4533753395080566, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.0663, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.053005205868433505, | |
| "grad_norm": 3.8815910816192627, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.9878, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06057737813535258, | |
| "grad_norm": 1.6462730169296265, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.9207, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06814955040227165, | |
| "grad_norm": 0.9676688313484192, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.8042, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07572172266919072, | |
| "grad_norm": 3.804490566253662, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.7335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0832938949361098, | |
| "grad_norm": 1.113680124282837, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.7169, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09086606720302887, | |
| "grad_norm": 1.01719069480896, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.4422, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09843823946994794, | |
| "grad_norm": 0.8143924474716187, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.5477, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10601041173686701, | |
| "grad_norm": 1.0786701440811157, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.6932, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11358258400378608, | |
| "grad_norm": 1.154252529144287, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.7261, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12115475627070516, | |
| "grad_norm": 1.010557770729065, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.8172, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12872692853762424, | |
| "grad_norm": 0.6834193468093872, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.7133, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1362991008045433, | |
| "grad_norm": 0.8263300657272339, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.778, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14387127307146239, | |
| "grad_norm": 0.9877240657806396, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.8338, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15144344533838144, | |
| "grad_norm": 1.397219181060791, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.8442, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15901561760530053, | |
| "grad_norm": 1.878542184829712, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.6447, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1665877898722196, | |
| "grad_norm": 2.025350332260132, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.7511, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17415996213913867, | |
| "grad_norm": 2.2214548587799072, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.6628, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.18173213440605773, | |
| "grad_norm": 2.252363681793213, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.7163, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18930430667297682, | |
| "grad_norm": 6.229862689971924, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.6675, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18930430667297682, | |
| "eval_loss": 2.6197311878204346, | |
| "eval_runtime": 3.2948, | |
| "eval_samples_per_second": 15.175, | |
| "eval_steps_per_second": 3.946, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 2.66009604784128e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |