| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1028667790893762, | |
| "eval_steps": 25, | |
| "global_step": 28, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10792580101180438, | |
| "grad_norm": 6.549549102783203, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5205, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10792580101180438, | |
| "eval_loss": 2.098513603210449, | |
| "eval_runtime": 0.6959, | |
| "eval_samples_per_second": 71.851, | |
| "eval_steps_per_second": 18.681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21585160202360876, | |
| "grad_norm": 7.940962314605713, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8349, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.32377740303541314, | |
| "grad_norm": 4.132171630859375, | |
| "learning_rate": 0.00019934379866882486, | |
| "loss": 1.2765, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.4317032040472175, | |
| "grad_norm": 3.0609889030456543, | |
| "learning_rate": 0.0001973847635683447, | |
| "loss": 0.5601, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5396290050590219, | |
| "grad_norm": 2.8161590099334717, | |
| "learning_rate": 0.00019415146184168736, | |
| "loss": 0.5591, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6475548060708263, | |
| "grad_norm": 2.2716848850250244, | |
| "learning_rate": 0.0001896910423087889, | |
| "loss": 0.2181, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7554806070826307, | |
| "grad_norm": 2.347761631011963, | |
| "learning_rate": 0.00018406854793042907, | |
| "loss": 0.2438, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.863406408094435, | |
| "grad_norm": 1.6461851596832275, | |
| "learning_rate": 0.00017736596733539909, | |
| "loss": 0.1546, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9713322091062394, | |
| "grad_norm": 0.7142131924629211, | |
| "learning_rate": 0.00016968103924167158, | |
| "loss": 0.1111, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.1062394603709949, | |
| "grad_norm": 3.211808204650879, | |
| "learning_rate": 0.00016112582720580402, | |
| "loss": 0.1508, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.2141652613827993, | |
| "grad_norm": 0.640089750289917, | |
| "learning_rate": 0.00015182508548393917, | |
| "loss": 0.0331, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.3220910623946036, | |
| "grad_norm": 0.4209713935852051, | |
| "learning_rate": 0.00014191443983382822, | |
| "loss": 0.0445, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.430016863406408, | |
| "grad_norm": 0.27695563435554504, | |
| "learning_rate": 0.00013153840978588022, | |
| "loss": 0.0137, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.5379426644182126, | |
| "grad_norm": 1.0646858215332031, | |
| "learning_rate": 0.00012084830122297907, | |
| "loss": 0.0293, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.6458684654300169, | |
| "grad_norm": 0.3604212701320648, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 0.0082, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.7537942664418211, | |
| "grad_norm": 0.37924137711524963, | |
| "learning_rate": 9.915169877702095e-05, | |
| "loss": 0.0049, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.8617200674536256, | |
| "grad_norm": 0.17383427917957306, | |
| "learning_rate": 8.846159021411984e-05, | |
| "loss": 0.0033, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.96964586846543, | |
| "grad_norm": 0.26441916823387146, | |
| "learning_rate": 7.808556016617178e-05, | |
| "loss": 0.0058, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.1045531197301854, | |
| "grad_norm": 0.3032292425632477, | |
| "learning_rate": 6.817491451606084e-05, | |
| "loss": 0.0061, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.2124789207419897, | |
| "grad_norm": 0.20044660568237305, | |
| "learning_rate": 5.887417279419599e-05, | |
| "loss": 0.0039, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.3204047217537944, | |
| "grad_norm": 0.06787917017936707, | |
| "learning_rate": 5.031896075832846e-05, | |
| "loss": 0.001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.4283305227655987, | |
| "grad_norm": 0.31433218717575073, | |
| "learning_rate": 4.2634032664600895e-05, | |
| "loss": 0.0013, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.536256323777403, | |
| "grad_norm": 0.20029595494270325, | |
| "learning_rate": 3.593145206957093e-05, | |
| "loss": 0.0042, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.6441821247892072, | |
| "grad_norm": 0.21654507517814636, | |
| "learning_rate": 3.030895769121112e-05, | |
| "loss": 0.0011, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.752107925801012, | |
| "grad_norm": 0.1746876835823059, | |
| "learning_rate": 2.584853815831268e-05, | |
| "loss": 0.0029, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.752107925801012, | |
| "eval_loss": 0.0027343386318534613, | |
| "eval_runtime": 0.6948, | |
| "eval_samples_per_second": 71.966, | |
| "eval_steps_per_second": 18.711, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.860033726812816, | |
| "grad_norm": 0.21681739389896393, | |
| "learning_rate": 2.261523643165532e-05, | |
| "loss": 0.0011, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.9679595278246205, | |
| "grad_norm": 0.049800898879766464, | |
| "learning_rate": 2.0656201331175147e-05, | |
| "loss": 0.0004, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.1028667790893762, | |
| "grad_norm": 0.1703035682439804, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0026, | |
| "step": 28 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 28, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7629254189160858e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |