| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.13966480446927373, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002793296089385475, |
| "eval_loss": 9.896864891052246, |
| "eval_runtime": 4.9175, |
| "eval_samples_per_second": 30.707, |
| "eval_steps_per_second": 15.455, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013966480446927373, |
| "grad_norm": 41.86698532104492, |
| "learning_rate": 5e-05, |
| "loss": 8.7545, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.027932960893854747, |
| "grad_norm": 15.126924514770508, |
| "learning_rate": 0.0001, |
| "loss": 7.191, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.027932960893854747, |
| "eval_loss": 5.595855712890625, |
| "eval_runtime": 4.8333, |
| "eval_samples_per_second": 31.241, |
| "eval_steps_per_second": 15.724, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04189944134078212, |
| "grad_norm": 4.385186672210693, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 5.0465, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.055865921787709494, |
| "grad_norm": 3.310457706451416, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 4.4644, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.055865921787709494, |
| "eval_loss": 4.217800617218018, |
| "eval_runtime": 4.9043, |
| "eval_samples_per_second": 30.789, |
| "eval_steps_per_second": 15.497, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06983240223463687, |
| "grad_norm": 3.4962682723999023, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 4.1238, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.08379888268156424, |
| "grad_norm": 3.5850486755371094, |
| "learning_rate": 5e-05, |
| "loss": 3.7438, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.08379888268156424, |
| "eval_loss": 3.5863335132598877, |
| "eval_runtime": 4.88, |
| "eval_samples_per_second": 30.942, |
| "eval_steps_per_second": 15.574, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09776536312849161, |
| "grad_norm": 3.6995723247528076, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 3.3512, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.11173184357541899, |
| "grad_norm": 3.8023898601531982, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 3.2392, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.11173184357541899, |
| "eval_loss": 3.2825071811676025, |
| "eval_runtime": 4.8262, |
| "eval_samples_per_second": 31.287, |
| "eval_steps_per_second": 15.747, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.12569832402234637, |
| "grad_norm": 4.109200477600098, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 3.2066, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.13966480446927373, |
| "grad_norm": 2.853254795074463, |
| "learning_rate": 0.0, |
| "loss": 3.1558, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.13966480446927373, |
| "eval_loss": 3.2231385707855225, |
| "eval_runtime": 4.8098, |
| "eval_samples_per_second": 31.394, |
| "eval_steps_per_second": 15.801, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1278959891251200.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
