| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 50, |
| "global_step": 114, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13157894736842105, |
| "grad_norm": 2.8724489212036133, |
| "learning_rate": 9.999999999999999e-05, |
| "loss": 3.2117641448974608, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2631578947368421, |
| "grad_norm": 3.8114724159240723, |
| "learning_rate": 0.0001497146023568809, |
| "loss": 1.3626741409301757, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.39473684210526316, |
| "grad_norm": 2.2762057781219482, |
| "learning_rate": 0.00014797836529348678, |
| "loss": 0.37534074783325194, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.5263157894736842, |
| "grad_norm": 0.8772661089897156, |
| "learning_rate": 0.00014470106431701166, |
| "loss": 0.25732452869415284, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6578947368421053, |
| "grad_norm": 0.28068816661834717, |
| "learning_rate": 0.0001399519052838329, |
| "loss": 0.22821950912475586, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.7894736842105263, |
| "grad_norm": 0.37059611082077026, |
| "learning_rate": 0.00013383117486896816, |
| "loss": 0.21986465454101561, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.9210526315789473, |
| "grad_norm": 0.21363650262355804, |
| "learning_rate": 0.000126468122840155, |
| "loss": 0.19870233535766602, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.0526315789473684, |
| "grad_norm": 0.29518723487854004, |
| "learning_rate": 0.00011801823272632844, |
| "loss": 0.18972501754760743, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.1842105263157894, |
| "grad_norm": 0.16845785081386566, |
| "learning_rate": 0.00010865993851503467, |
| "loss": 0.18694405555725097, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.3157894736842106, |
| "grad_norm": 0.18659795820713043, |
| "learning_rate": 9.859085671137102e-05, |
| "loss": 0.18443360328674316, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.3157894736842106, |
| "eval_loss": 0.18096967041492462, |
| "eval_runtime": 0.514, |
| "eval_samples_per_second": 486.415, |
| "eval_steps_per_second": 15.565, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.4473684210526316, |
| "grad_norm": 0.09704450517892838, |
| "learning_rate": 8.802361332501978e-05, |
| "loss": 0.17949447631835938, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.5789473684210527, |
| "grad_norm": 0.149698406457901, |
| "learning_rate": 7.718135390573335e-05, |
| "loss": 0.17545132637023925, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.7105263157894737, |
| "grad_norm": 0.4086472988128662, |
| "learning_rate": 6.629303144060771e-05, |
| "loss": 0.16337993144989013, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.8421052631578947, |
| "grad_norm": 0.2512857913970947, |
| "learning_rate": 5.558857161731093e-05, |
| "loss": 0.15300323963165283, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.973684210526316, |
| "grad_norm": 0.1288457214832306, |
| "learning_rate": 4.529401754706323e-05, |
| "loss": 0.1532054901123047, |
| "step": 75 |
| }, |
| { |
| "epoch": 2.1052631578947367, |
| "grad_norm": 0.10154800862073898, |
| "learning_rate": 3.562675647490799e-05, |
| "loss": 0.1503889560699463, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.236842105263158, |
| "grad_norm": 0.010364431887865067, |
| "learning_rate": 2.6790929273509545e-05, |
| "loss": 0.15022125244140624, |
| "step": 85 |
| }, |
| { |
| "epoch": 2.3684210526315788, |
| "grad_norm": 0.0075685251504182816, |
| "learning_rate": 1.897311965692531e-05, |
| "loss": 0.15019209384918214, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.007590321823954582, |
| "learning_rate": 1.2338414144029779e-05, |
| "loss": 0.15014156103134155, |
| "step": 95 |
| }, |
| { |
| "epoch": 2.6315789473684212, |
| "grad_norm": 0.004777102265506983, |
| "learning_rate": 7.026915972251254e-06, |
| "loss": 0.15012743473052978, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.6315789473684212, |
| "eval_loss": 0.15011924505233765, |
| "eval_runtime": 0.4989, |
| "eval_samples_per_second": 501.08, |
| "eval_steps_per_second": 16.035, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.763157894736842, |
| "grad_norm": 0.004256995860487223, |
| "learning_rate": 3.150786576338332e-06, |
| "loss": 0.15010836124420165, |
| "step": 105 |
| }, |
| { |
| "epoch": 2.8947368421052633, |
| "grad_norm": 0.004810058977454901, |
| "learning_rate": 7.918771064291645e-07, |
| "loss": 0.1501091480255127, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.15010888874530792, |
| "eval_runtime": 0.4909, |
| "eval_samples_per_second": 509.265, |
| "eval_steps_per_second": 16.296, |
| "step": 114 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 114, |
| "total_flos": 3.851983523518874e+16, |
| "train_loss": 0.3688990599230716, |
| "train_runtime": 95.5617, |
| "train_samples_per_second": 149.118, |
| "train_steps_per_second": 1.193 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 114, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 3.851983523518874e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
