| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 5, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.3852219879627228, |
| "learning_rate": 0.0, |
| "loss": 1.6982421875, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.3040158450603485, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 1.77734375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.2961996793746948, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 1.7578125, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.3623664677143097, |
| "learning_rate": 1e-05, |
| "loss": 1.7568359375, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.2844073176383972, |
| "learning_rate": 9.954196488464198e-06, |
| "loss": 1.7509765625, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 1.7109375, |
| "eval_runtime": 2.0186, |
| "eval_samples_per_second": 0.991, |
| "eval_steps_per_second": 0.495, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.2740273177623749, |
| "learning_rate": 9.81771838126524e-06, |
| "loss": 1.6904296875, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.27806246280670166, |
| "learning_rate": 9.593343979095334e-06, |
| "loss": 1.720703125, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.30633893609046936, |
| "learning_rate": 9.285640897740316e-06, |
| "loss": 1.7900390625, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.2555227279663086, |
| "learning_rate": 8.900873084594164e-06, |
| "loss": 1.4390869140625, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.2538067102432251, |
| "learning_rate": 8.446873302753783e-06, |
| "loss": 1.70703125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 1.697265625, |
| "eval_runtime": 2.0251, |
| "eval_samples_per_second": 0.988, |
| "eval_steps_per_second": 0.494, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.30936306715011597, |
| "learning_rate": 7.932883678550191e-06, |
| "loss": 1.734375, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.2755681872367859, |
| "learning_rate": 7.36936755850849e-06, |
| "loss": 1.693359375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 0.24498508870601654, |
| "learning_rate": 6.767796505786435e-06, |
| "loss": 1.638671875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.30694907903671265, |
| "learning_rate": 6.140416772229785e-06, |
| "loss": 1.6572265625, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.309129536151886, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 1.6904296875, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_loss": 1.693359375, |
| "eval_runtime": 2.0251, |
| "eval_samples_per_second": 0.988, |
| "eval_steps_per_second": 0.494, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.31138136982917786, |
| "learning_rate": 4.859583227770218e-06, |
| "loss": 1.7568359375, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.25136393308639526, |
| "learning_rate": 4.232203494213567e-06, |
| "loss": 1.640625, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.30998989939689636, |
| "learning_rate": 3.630632441491512e-06, |
| "loss": 1.7490234375, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.22774231433868408, |
| "learning_rate": 3.0671163214498127e-06, |
| "loss": 1.6455078125, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.38729652762413025, |
| "learning_rate": 2.5531266972462176e-06, |
| "loss": 1.7412109375, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 1.68359375, |
| "eval_runtime": 2.0237, |
| "eval_samples_per_second": 0.988, |
| "eval_steps_per_second": 0.494, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.3755400478839874, |
| "learning_rate": 2.0991269154058387e-06, |
| "loss": 1.703125, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.3168826401233673, |
| "learning_rate": 1.7143591022596846e-06, |
| "loss": 1.7587890625, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.31902143359184265, |
| "learning_rate": 1.4066560209046673e-06, |
| "loss": 1.794921875, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.24556264281272888, |
| "learning_rate": 1.1822816187347625e-06, |
| "loss": 1.4383544921875, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5234353542327881, |
| "learning_rate": 1.0458035115358031e-06, |
| "loss": 1.5703125, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.681640625, |
| "eval_runtime": 2.0196, |
| "eval_samples_per_second": 0.99, |
| "eval_steps_per_second": 0.495, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 25, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.4638008283181875e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
