| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.25, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.025, |
| "grad_norm": 27.5, |
| "learning_rate": 4e-05, |
| "loss": 71.893, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 11.5, |
| "learning_rate": 9e-05, |
| "loss": 62.6505, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05, |
| "eval_loss": 9.905916213989258, |
| "eval_runtime": 15.7082, |
| "eval_samples_per_second": 34.25, |
| "eval_steps_per_second": 2.292, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 9.625, |
| "learning_rate": 9.989068136093873e-05, |
| "loss": 57.5435, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 6.84375, |
| "learning_rate": 9.944739353007344e-05, |
| "loss": 53.1338, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_loss": 8.45786190032959, |
| "eval_runtime": 16.0113, |
| "eval_samples_per_second": 33.601, |
| "eval_steps_per_second": 2.248, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 4.8125, |
| "learning_rate": 9.86663298624003e-05, |
| "loss": 49.413, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 4.96875, |
| "learning_rate": 9.755282581475769e-05, |
| "loss": 46.6506, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.15, |
| "eval_loss": 7.606866836547852, |
| "eval_runtime": 16.4027, |
| "eval_samples_per_second": 32.799, |
| "eval_steps_per_second": 2.195, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.175, |
| "grad_norm": 4.875, |
| "learning_rate": 9.611448774886924e-05, |
| "loss": 44.8354, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 3.625, |
| "learning_rate": 9.43611409721806e-05, |
| "loss": 43.8419, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 7.288437843322754, |
| "eval_runtime": 16.1342, |
| "eval_samples_per_second": 33.345, |
| "eval_steps_per_second": 2.231, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.225, |
| "grad_norm": 5.0, |
| "learning_rate": 9.230476262104677e-05, |
| "loss": 43.2838, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 4.40625, |
| "learning_rate": 8.995939984474624e-05, |
| "loss": 42.7483, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.25, |
| "eval_loss": 7.132974147796631, |
| "eval_runtime": 16.0666, |
| "eval_samples_per_second": 33.486, |
| "eval_steps_per_second": 2.241, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.6791633313792e+16, |
| "train_batch_size": 15, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
