| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028216704288939052, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001128668171557562, | |
| "grad_norm": 46.31266784667969, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.9289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001128668171557562, | |
| "eval_loss": 11.48071575164795, | |
| "eval_runtime": 218.574, | |
| "eval_samples_per_second": 3.418, | |
| "eval_steps_per_second": 1.711, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002257336343115124, | |
| "grad_norm": 32.02701187133789, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 9.1416, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003386004514672686, | |
| "grad_norm": 22.43347930908203, | |
| "learning_rate": 0.0002, | |
| "loss": 7.6477, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004514672686230248, | |
| "grad_norm": 24.434974670410156, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 7.0388, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0056433408577878106, | |
| "grad_norm": 21.187652587890625, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 3.8237, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006772009029345372, | |
| "grad_norm": 18.851232528686523, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 2.9445, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007900677200902935, | |
| "grad_norm": 21.697521209716797, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 3.5231, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "grad_norm": 14.041197776794434, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 2.2053, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010158013544018058, | |
| "grad_norm": 15.442231178283691, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 2.3755, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011286681715575621, | |
| "grad_norm": 14.979207038879395, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 2.5331, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012415349887133182, | |
| "grad_norm": 11.316594123840332, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.2067, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013544018058690745, | |
| "grad_norm": 10.44298267364502, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.641, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014672686230248307, | |
| "grad_norm": 11.997466087341309, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 1.7946, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01580135440180587, | |
| "grad_norm": 12.115503311157227, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 2.4233, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016930022573363433, | |
| "grad_norm": 11.261882781982422, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.8223, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "grad_norm": 10.030159950256348, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 1.8842, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019187358916478554, | |
| "grad_norm": 12.912628173828125, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 2.4811, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020316027088036117, | |
| "grad_norm": 14.034784317016602, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.0478, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02144469525959368, | |
| "grad_norm": 11.340625762939453, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 1.4553, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022573363431151242, | |
| "grad_norm": 13.417366981506348, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 2.2667, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023702031602708805, | |
| "grad_norm": 10.488327026367188, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.8455, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024830699774266364, | |
| "grad_norm": 8.669241905212402, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 1.7471, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025959367945823927, | |
| "grad_norm": 8.316575050354004, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 1.4701, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02708803611738149, | |
| "grad_norm": 9.43625259399414, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.6207, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028216704288939052, | |
| "grad_norm": 8.611120223999023, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 1.642, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028216704288939052, | |
| "eval_loss": 1.9240721464157104, | |
| "eval_runtime": 220.5343, | |
| "eval_samples_per_second": 3.387, | |
| "eval_steps_per_second": 1.696, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.83447180771328e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |