| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 32, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6818181818181818, |
| "grad_norm": 0.17029684782028198, |
| "learning_rate": 9.890738003669029e-05, |
| "loss": 0.5484736442565918, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5573728680610657, |
| "eval_runtime": 68.1051, |
| "eval_samples_per_second": 0.338, |
| "eval_steps_per_second": 0.338, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.2727272727272727, |
| "grad_norm": 0.13476553559303284, |
| "learning_rate": 8.715724127386972e-05, |
| "loss": 0.39622204303741454, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.9545454545454546, |
| "grad_norm": 0.10812098532915115, |
| "learning_rate": 6.545084971874738e-05, |
| "loss": 0.3172358274459839, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.5258440971374512, |
| "eval_runtime": 55.0806, |
| "eval_samples_per_second": 0.418, |
| "eval_steps_per_second": 0.418, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 0.0986139178276062, |
| "learning_rate": 3.960441545911204e-05, |
| "loss": 0.259796142578125, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.5335667729377747, |
| "eval_runtime": 55.2611, |
| "eval_samples_per_second": 0.416, |
| "eval_steps_per_second": 0.416, |
| "step": 24 |
| }, |
| { |
| "epoch": 3.1363636363636362, |
| "grad_norm": 0.10310647636651993, |
| "learning_rate": 1.6543469682057106e-05, |
| "loss": 0.22319560050964354, |
| "step": 25 |
| }, |
| { |
| "epoch": 3.8181818181818183, |
| "grad_norm": 0.09917434304952621, |
| "learning_rate": 2.4471741852423237e-06, |
| "loss": 0.2115036964416504, |
| "step": 30 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.532187819480896, |
| "eval_runtime": 57.9826, |
| "eval_samples_per_second": 0.397, |
| "eval_steps_per_second": 0.397, |
| "step": 32 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 32, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.338968069499118e+17, |
| "train_batch_size": 3, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
