| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.29038112522686027, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014519056261343012, | |
| "eval_loss": 5.956166744232178, | |
| "eval_runtime": 10.0522, | |
| "eval_samples_per_second": 28.849, | |
| "eval_steps_per_second": 14.425, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014519056261343012, | |
| "grad_norm": 1.2935727834701538, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 5.8948, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029038112522686024, | |
| "grad_norm": 0.9941825270652771, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 5.9223, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043557168784029036, | |
| "grad_norm": 1.121877908706665, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 5.027, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05807622504537205, | |
| "grad_norm": 1.5708129405975342, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 5.5017, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "grad_norm": 1.9266424179077148, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 5.2512, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "eval_loss": 4.811445236206055, | |
| "eval_runtime": 9.4627, | |
| "eval_samples_per_second": 30.647, | |
| "eval_steps_per_second": 15.323, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08711433756805807, | |
| "grad_norm": 3.0178332328796387, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 5.0281, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10163339382940109, | |
| "grad_norm": 5.907054901123047, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.7945, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1161524500907441, | |
| "grad_norm": 4.798269748687744, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 3.874, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1306715063520871, | |
| "grad_norm": 6.5533576011657715, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 3.6984, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14519056261343014, | |
| "grad_norm": 4.253799915313721, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 3.6303, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14519056261343014, | |
| "eval_loss": 3.2204811573028564, | |
| "eval_runtime": 9.459, | |
| "eval_samples_per_second": 30.659, | |
| "eval_steps_per_second": 15.329, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15970961887477314, | |
| "grad_norm": 6.844799995422363, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 3.8731, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.17422867513611615, | |
| "grad_norm": 7.042694568634033, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 3.321, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18874773139745918, | |
| "grad_norm": 5.778402805328369, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 2.6964, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.20326678765880218, | |
| "grad_norm": 6.522513389587402, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 2.7133, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2177858439201452, | |
| "grad_norm": 8.259108543395996, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 2.9013, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2177858439201452, | |
| "eval_loss": 2.0801122188568115, | |
| "eval_runtime": 9.4829, | |
| "eval_samples_per_second": 30.582, | |
| "eval_steps_per_second": 15.291, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2323049001814882, | |
| "grad_norm": 9.756109237670898, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 3.0355, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.24682395644283123, | |
| "grad_norm": 6.9620466232299805, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 1.9431, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2613430127041742, | |
| "grad_norm": 7.356261730194092, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 1.8571, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 6.641462326049805, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 2.0129, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.29038112522686027, | |
| "grad_norm": 7.481417655944824, | |
| "learning_rate": 0.0, | |
| "loss": 2.2513, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29038112522686027, | |
| "eval_loss": 1.837255835533142, | |
| "eval_runtime": 9.5016, | |
| "eval_samples_per_second": 30.521, | |
| "eval_steps_per_second": 15.261, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.69912849629184e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |