| { |
| "best_metric": 27.2064, |
| "best_model_checkpoint": "/content/drive/MyDrive/Arabart/checkpoint-11229", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 11229, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1335826876836762, |
| "grad_norm": 3.386234998703003, |
| "learning_rate": 3.7102997922232118e-06, |
| "loss": 1.0678, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2671653753673524, |
| "grad_norm": 3.5773236751556396, |
| "learning_rate": 7.4205995844464235e-06, |
| "loss": 1.0284, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4007480630510286, |
| "grad_norm": 3.3108386993408203, |
| "learning_rate": 1.1130899376669635e-05, |
| "loss": 1.0298, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.5343307507347048, |
| "grad_norm": 3.4388937950134277, |
| "learning_rate": 1.4841199168892847e-05, |
| "loss": 1.0412, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.667913438418381, |
| "grad_norm": 3.6874964237213135, |
| "learning_rate": 1.855149896111606e-05, |
| "loss": 1.0445, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.8014961261020572, |
| "grad_norm": 3.868025541305542, |
| "learning_rate": 2.226179875333927e-05, |
| "loss": 1.0759, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.9350788137857333, |
| "grad_norm": 3.5139052867889404, |
| "learning_rate": 2.5972098545562486e-05, |
| "loss": 1.0966, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.939680814743042, |
| "eval_rouge1": 26.8205, |
| "eval_rouge2": 11.1497, |
| "eval_rougeL": 23.3343, |
| "eval_runtime": 806.3685, |
| "eval_samples_per_second": 5.815, |
| "eval_steps_per_second": 0.582, |
| "step": 3743 |
| }, |
| { |
| "epoch": 1.0686615014694096, |
| "grad_norm": 3.590301036834717, |
| "learning_rate": 2.9682398337785694e-05, |
| "loss": 1.0519, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.2022441891530857, |
| "grad_norm": 4.0262770652771, |
| "learning_rate": 3.33926981300089e-05, |
| "loss": 1.0335, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.3358268768367618, |
| "grad_norm": 3.4733996391296387, |
| "learning_rate": 3.710299792223212e-05, |
| "loss": 1.0759, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.4694095645204381, |
| "grad_norm": 4.025749206542969, |
| "learning_rate": 4.0813297714455326e-05, |
| "loss": 1.1336, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.6029922522041145, |
| "grad_norm": 3.807826280593872, |
| "learning_rate": 4.452359750667854e-05, |
| "loss": 1.1922, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.7365749398877905, |
| "grad_norm": 4.066860198974609, |
| "learning_rate": 4.8233897298901756e-05, |
| "loss": 1.2401, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.8701576275714666, |
| "grad_norm": 4.048403739929199, |
| "learning_rate": 4.708305499888667e-05, |
| "loss": 1.2936, |
| "step": 7000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.8382859230041504, |
| "eval_rouge1": 27.0396, |
| "eval_rouge2": 11.288, |
| "eval_rougeL": 23.5434, |
| "eval_runtime": 802.1911, |
| "eval_samples_per_second": 5.845, |
| "eval_steps_per_second": 0.585, |
| "step": 7486 |
| }, |
| { |
| "epoch": 2.003740315255143, |
| "grad_norm": 4.089428901672363, |
| "learning_rate": 3.3302164039540476e-05, |
| "loss": 1.2334, |
| "step": 7500 |
| }, |
| { |
| "epoch": 2.1373230029388193, |
| "grad_norm": 3.9481818675994873, |
| "learning_rate": 3.218897497550984e-05, |
| "loss": 1.1406, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.270905690622495, |
| "grad_norm": 4.022891521453857, |
| "learning_rate": 3.10757859114792e-05, |
| "loss": 1.193, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.4044883783061715, |
| "grad_norm": 4.349768161773682, |
| "learning_rate": 2.9962596847448572e-05, |
| "loss": 1.2447, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.5380710659898478, |
| "grad_norm": 4.266928672790527, |
| "learning_rate": 2.8849407783417938e-05, |
| "loss": 1.2706, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.6716537536735236, |
| "grad_norm": 3.9516377449035645, |
| "learning_rate": 2.77362187193873e-05, |
| "loss": 1.3529, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.8052364413572, |
| "grad_norm": 3.882983922958374, |
| "learning_rate": 2.6623029655356667e-05, |
| "loss": 1.3834, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.9388191290408763, |
| "grad_norm": 3.9039924144744873, |
| "learning_rate": 2.5509840591326034e-05, |
| "loss": 1.4255, |
| "step": 11000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.6909232139587402, |
| "eval_rouge1": 27.2064, |
| "eval_rouge2": 11.3801, |
| "eval_rougeL": 23.5876, |
| "eval_runtime": 854.0016, |
| "eval_samples_per_second": 5.491, |
| "eval_steps_per_second": 0.549, |
| "step": 11229 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 22458, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.587894865088512e+16, |
| "train_batch_size": 10, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
