| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.049776007964161276, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024888003982080636, | |
| "eval_loss": 11.111771583557129, | |
| "eval_runtime": 4.0972, | |
| "eval_samples_per_second": 412.967, | |
| "eval_steps_per_second": 206.484, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024888003982080635, | |
| "grad_norm": 1.8114973306655884, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 44.4612, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004977600796416127, | |
| "grad_norm": 2.1671862602233887, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 44.3774, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007466401194624191, | |
| "grad_norm": 2.280989646911621, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 44.2183, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009955201592832254, | |
| "grad_norm": 1.8748552799224854, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 44.104, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012444001991040319, | |
| "grad_norm": 2.1447713375091553, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 44.0201, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012444001991040319, | |
| "eval_loss": 10.96944808959961, | |
| "eval_runtime": 3.6871, | |
| "eval_samples_per_second": 458.9, | |
| "eval_steps_per_second": 229.45, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014932802389248382, | |
| "grad_norm": 2.476578950881958, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 43.8501, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.017421602787456445, | |
| "grad_norm": 2.3160014152526855, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 43.7407, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.019910403185664508, | |
| "grad_norm": 2.437119722366333, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 43.6296, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.022399203583872575, | |
| "grad_norm": 2.140958309173584, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 43.5423, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.024888003982080638, | |
| "grad_norm": 2.2173733711242676, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 43.4688, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.024888003982080638, | |
| "eval_loss": 10.83658504486084, | |
| "eval_runtime": 3.7229, | |
| "eval_samples_per_second": 454.483, | |
| "eval_steps_per_second": 227.241, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0273768043802887, | |
| "grad_norm": 1.7986624240875244, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 43.3308, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.029865604778496764, | |
| "grad_norm": 2.530690908432007, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 43.2774, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03235440517670483, | |
| "grad_norm": 2.273829460144043, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 43.3605, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03484320557491289, | |
| "grad_norm": 1.8377761840820312, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 43.2228, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03733200597312095, | |
| "grad_norm": 2.013192892074585, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 43.255, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03733200597312095, | |
| "eval_loss": 10.798469543457031, | |
| "eval_runtime": 3.762, | |
| "eval_samples_per_second": 449.758, | |
| "eval_steps_per_second": 224.879, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.039820806371329016, | |
| "grad_norm": 2.0936999320983887, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 43.2306, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.042309606769537086, | |
| "grad_norm": 2.3130648136138916, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 43.1212, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.04479840716774515, | |
| "grad_norm": 2.086369752883911, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 43.2217, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04728720756595321, | |
| "grad_norm": 1.8583261966705322, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 43.2078, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.049776007964161276, | |
| "grad_norm": 2.2292990684509277, | |
| "learning_rate": 0.0, | |
| "loss": 43.2312, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.049776007964161276, | |
| "eval_loss": 10.79432487487793, | |
| "eval_runtime": 3.7905, | |
| "eval_samples_per_second": 446.374, | |
| "eval_steps_per_second": 223.187, | |
| "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": 1928960409600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |