| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07054574185902139, | |
| "eval_steps": 500, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0028218296743608554, | |
| "grad_norm": 175.4037628173828, | |
| "learning_rate": 1.3261851015801355e-07, | |
| "loss": 3.1599, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.005643659348721711, | |
| "grad_norm": 24.302709579467773, | |
| "learning_rate": 2.737020316027088e-07, | |
| "loss": 1.8481, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.008465489023082567, | |
| "grad_norm": 39.38914489746094, | |
| "learning_rate": 4.147855530474041e-07, | |
| "loss": 1.2574, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.011287318697443422, | |
| "grad_norm": 28.08403205871582, | |
| "learning_rate": 5.558690744920993e-07, | |
| "loss": 1.0333, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.014109148371804279, | |
| "grad_norm": 22.54578399658203, | |
| "learning_rate": 6.969525959367947e-07, | |
| "loss": 0.9413, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.016930978046165134, | |
| "grad_norm": 17.940231323242188, | |
| "learning_rate": 8.3803611738149e-07, | |
| "loss": 0.7995, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.01975280772052599, | |
| "grad_norm": 26.575462341308594, | |
| "learning_rate": 9.79119638826185e-07, | |
| "loss": 0.7403, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.022574637394886844, | |
| "grad_norm": 51.95569610595703, | |
| "learning_rate": 1.1202031602708804e-06, | |
| "loss": 0.7774, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.0253964670692477, | |
| "grad_norm": 140.2630157470703, | |
| "learning_rate": 1.2612866817155757e-06, | |
| "loss": 0.6903, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.028218296743608557, | |
| "grad_norm": 28.976390838623047, | |
| "learning_rate": 1.402370203160271e-06, | |
| "loss": 0.6727, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03104012641796941, | |
| "grad_norm": 36.016754150390625, | |
| "learning_rate": 1.5434537246049664e-06, | |
| "loss": 0.6351, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03386195609233027, | |
| "grad_norm": 41.480491638183594, | |
| "learning_rate": 1.6845372460496615e-06, | |
| "loss": 0.6555, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.036683785766691124, | |
| "grad_norm": 24.90089225769043, | |
| "learning_rate": 1.8256207674943568e-06, | |
| "loss": 0.6714, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.03950561544105198, | |
| "grad_norm": 31.070730209350586, | |
| "learning_rate": 1.966704288939052e-06, | |
| "loss": 0.6781, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.04232744511541283, | |
| "grad_norm": 33.644046783447266, | |
| "learning_rate": 2.1077878103837474e-06, | |
| "loss": 0.6284, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04514927478977369, | |
| "grad_norm": 22.074399948120117, | |
| "learning_rate": 2.2488713318284427e-06, | |
| "loss": 0.578, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.047971104464134544, | |
| "grad_norm": 30.381807327270508, | |
| "learning_rate": 2.389954853273138e-06, | |
| "loss": 0.631, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.0507929341384954, | |
| "grad_norm": 31.510488510131836, | |
| "learning_rate": 2.531038374717833e-06, | |
| "loss": 0.61, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.05361476381285626, | |
| "grad_norm": 27.364355087280273, | |
| "learning_rate": 2.6721218961625283e-06, | |
| "loss": 0.5953, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.056436593487217114, | |
| "grad_norm": 48.54792404174805, | |
| "learning_rate": 2.8132054176072236e-06, | |
| "loss": 0.6046, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.059258423161577964, | |
| "grad_norm": 49.58477020263672, | |
| "learning_rate": 2.9542889390519193e-06, | |
| "loss": 0.5609, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.06208025283593882, | |
| "grad_norm": 26.104825973510742, | |
| "learning_rate": 3.095372460496614e-06, | |
| "loss": 0.5931, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.06490208251029968, | |
| "grad_norm": 36.350685119628906, | |
| "learning_rate": 3.2364559819413096e-06, | |
| "loss": 0.5884, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.06772391218466053, | |
| "grad_norm": 36.55471420288086, | |
| "learning_rate": 3.377539503386005e-06, | |
| "loss": 0.5957, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.07054574185902139, | |
| "grad_norm": 35.742225646972656, | |
| "learning_rate": 3.5186230248307e-06, | |
| "loss": 0.5958, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 70876, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |