| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017119989728006164, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003423997945601233, | |
| "eval_loss": 2.646597146987915, | |
| "eval_runtime": 988.545, | |
| "eval_samples_per_second": 19.904, | |
| "eval_steps_per_second": 2.489, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034239979456012325, | |
| "grad_norm": 2.6664435863494873, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7919, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0034239979456012325, | |
| "eval_loss": 0.45232027769088745, | |
| "eval_runtime": 990.8876, | |
| "eval_samples_per_second": 19.857, | |
| "eval_steps_per_second": 2.483, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006847995891202465, | |
| "grad_norm": 0.8173860311508179, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1707, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006847995891202465, | |
| "eval_loss": 0.07577058672904968, | |
| "eval_runtime": 991.4538, | |
| "eval_samples_per_second": 19.846, | |
| "eval_steps_per_second": 2.481, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010271993836803698, | |
| "grad_norm": 0.6428648829460144, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0686, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010271993836803698, | |
| "eval_loss": 0.060449112206697464, | |
| "eval_runtime": 989.4637, | |
| "eval_samples_per_second": 19.886, | |
| "eval_steps_per_second": 2.486, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01369599178240493, | |
| "grad_norm": 0.21196746826171875, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0596, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01369599178240493, | |
| "eval_loss": 0.058330558240413666, | |
| "eval_runtime": 992.6916, | |
| "eval_samples_per_second": 19.821, | |
| "eval_steps_per_second": 2.478, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017119989728006164, | |
| "grad_norm": 0.10265098512172699, | |
| "learning_rate": 0.0, | |
| "loss": 0.0563, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.017119989728006164, | |
| "eval_loss": 0.057584770023822784, | |
| "eval_runtime": 991.2861, | |
| "eval_samples_per_second": 19.849, | |
| "eval_steps_per_second": 2.482, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 1.3199061616164864e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |