| { | |
| "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": 1233.952, | |
| "eval_samples_per_second": 15.997, | |
| "eval_steps_per_second": 7.999, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021329920546045967, | |
| "grad_norm": 1.3220651149749756, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 2.8728, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00042659841092091935, | |
| "grad_norm": 1.1727917194366455, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.8062, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006398976163813789, | |
| "grad_norm": 1.2135999202728271, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 1.6181, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008531968218418387, | |
| "grad_norm": 1.0141725540161133, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 1.3658, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "grad_norm": 1.1369566917419434, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 1.3735, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "eval_loss": 0.33222588896751404, | |
| "eval_runtime": 1234.8799, | |
| "eval_samples_per_second": 15.985, | |
| "eval_steps_per_second": 7.993, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0012797952327627579, | |
| "grad_norm": 1.1296367645263672, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 1.2924, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0014930944382232176, | |
| "grad_norm": 1.1323010921478271, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.246, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0017063936436836774, | |
| "grad_norm": 0.9927407503128052, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 1.2913, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.001919692849144137, | |
| "grad_norm": 2.113898754119873, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 1.1232, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "grad_norm": 1.100758671760559, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 1.2662, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "eval_loss": 0.2988879978656769, | |
| "eval_runtime": 1235.0304, | |
| "eval_samples_per_second": 15.983, | |
| "eval_steps_per_second": 7.992, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002346291260065056, | |
| "grad_norm": 1.0766521692276, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 1.2688, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0025595904655255157, | |
| "grad_norm": 1.0353186130523682, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 1.1545, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0027728896709859757, | |
| "grad_norm": 0.9921385049819946, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 1.1265, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0029861888764464353, | |
| "grad_norm": 1.0136418342590332, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 1.0612, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "grad_norm": 1.2766144275665283, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 1.1227, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "eval_loss": 0.2857511341571808, | |
| "eval_runtime": 1235.5049, | |
| "eval_samples_per_second": 15.977, | |
| "eval_steps_per_second": 7.989, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0034127872873673548, | |
| "grad_norm": 1.2500035762786865, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 1.0789, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0036260864928278143, | |
| "grad_norm": 1.3151814937591553, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 1.0956, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.003839385698288274, | |
| "grad_norm": 1.1520051956176758, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 1.0368, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.004052684903748734, | |
| "grad_norm": 1.241952657699585, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 1.1097, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004265984109209193, | |
| "grad_norm": 1.1546802520751953, | |
| "learning_rate": 0.0, | |
| "loss": 1.1176, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004265984109209193, | |
| "eval_loss": 0.28350934386253357, | |
| "eval_runtime": 1234.2919, | |
| "eval_samples_per_second": 15.993, | |
| "eval_steps_per_second": 7.996, | |
| "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 | |
| } | |