| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007979253939756632, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007979253939756633, | |
| "grad_norm": 2.7286062240600586, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5192, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007979253939756633, | |
| "eval_loss": 3.5503156185150146, | |
| "eval_runtime": 16.9528, | |
| "eval_samples_per_second": 31.145, | |
| "eval_steps_per_second": 15.573, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015958507879513266, | |
| "grad_norm": 2.2886996269226074, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7697, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023937761819269898, | |
| "grad_norm": 2.2909810543060303, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4818, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023937761819269898, | |
| "eval_loss": 3.53837251663208, | |
| "eval_runtime": 16.3156, | |
| "eval_samples_per_second": 32.362, | |
| "eval_steps_per_second": 16.181, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003191701575902653, | |
| "grad_norm": 2.9981467723846436, | |
| "learning_rate": 8e-05, | |
| "loss": 4.292, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003989626969878316, | |
| "grad_norm": 2.4942939281463623, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6143, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0047875523638539795, | |
| "grad_norm": 2.9097135066986084, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4693, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0047875523638539795, | |
| "eval_loss": 3.2916226387023926, | |
| "eval_runtime": 16.3549, | |
| "eval_samples_per_second": 32.284, | |
| "eval_steps_per_second": 16.142, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005585477757829643, | |
| "grad_norm": 3.359541893005371, | |
| "learning_rate": 0.00014, | |
| "loss": 3.6185, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006383403151805306, | |
| "grad_norm": 2.894756317138672, | |
| "learning_rate": 0.00016, | |
| "loss": 3.1525, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00718132854578097, | |
| "grad_norm": 2.5824272632598877, | |
| "learning_rate": 0.00018, | |
| "loss": 2.717, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00718132854578097, | |
| "eval_loss": 2.6540489196777344, | |
| "eval_runtime": 16.3782, | |
| "eval_samples_per_second": 32.238, | |
| "eval_steps_per_second": 16.119, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "grad_norm": 3.0629162788391113, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7141, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |