| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004265984109209193, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.1329920546045965e-05, | |
| "eval_loss": 0.7577171921730042, | |
| "eval_runtime": 1240.3631, | |
| "eval_samples_per_second": 15.915, | |
| "eval_steps_per_second": 7.957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021329920546045967, | |
| "grad_norm": 1.315788984298706, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 2.8729, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00042659841092091935, | |
| "grad_norm": 1.1967780590057373, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.8038, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006398976163813789, | |
| "grad_norm": 1.2115387916564941, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 1.6148, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008531968218418387, | |
| "grad_norm": 0.935818076133728, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 1.3865, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "grad_norm": 1.0215239524841309, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 1.3748, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "eval_loss": 0.3277254104614258, | |
| "eval_runtime": 1241.5957, | |
| "eval_samples_per_second": 15.899, | |
| "eval_steps_per_second": 7.949, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0012797952327627579, | |
| "grad_norm": 1.1998786926269531, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 1.2868, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0014930944382232176, | |
| "grad_norm": 1.1020232439041138, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.2541, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0017063936436836774, | |
| "grad_norm": 1.032950758934021, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 1.2934, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.001919692849144137, | |
| "grad_norm": 1.2034289836883545, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 1.1281, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "grad_norm": 1.1966689825057983, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 1.2666, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "eval_loss": 0.2983585298061371, | |
| "eval_runtime": 1241.2395, | |
| "eval_samples_per_second": 15.903, | |
| "eval_steps_per_second": 7.952, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002346291260065056, | |
| "grad_norm": 1.0272051095962524, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 1.2709, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0025595904655255157, | |
| "grad_norm": 1.6282625198364258, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 1.1521, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0027728896709859757, | |
| "grad_norm": 0.982958197593689, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 1.1276, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0029861888764464353, | |
| "grad_norm": 1.0101426839828491, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 1.0648, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "grad_norm": 1.2995356321334839, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 1.1229, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "eval_loss": 0.2859799861907959, | |
| "eval_runtime": 1241.8568, | |
| "eval_samples_per_second": 15.896, | |
| "eval_steps_per_second": 7.948, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0034127872873673548, | |
| "grad_norm": 1.258757472038269, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 1.0815, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0036260864928278143, | |
| "grad_norm": 1.325924038887024, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 1.0969, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.003839385698288274, | |
| "grad_norm": 1.1691293716430664, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 1.0415, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.004052684903748734, | |
| "grad_norm": 1.2433751821517944, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 1.1115, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004265984109209193, | |
| "grad_norm": 1.129075050354004, | |
| "learning_rate": 0.0, | |
| "loss": 1.1193, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004265984109209193, | |
| "eval_loss": 0.28365498781204224, | |
| "eval_runtime": 1241.6171, | |
| "eval_samples_per_second": 15.899, | |
| "eval_steps_per_second": 7.949, | |
| "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": 7.3218937061376e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |