| { |
| "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 |
| } |
|
|
